Compare commits
2 commits
| Author | SHA1 | Date | |
|---|---|---|---|
| b22b547fdc | |||
| 9893358022 |
58 changed files with 973 additions and 16642 deletions
|
|
@ -1,11 +0,0 @@
|
|||
{
|
||||
"permissions": {
|
||||
"allow": [
|
||||
"Bash(dir:*)",
|
||||
"WebSearch",
|
||||
"Bash(mkdir:*)"
|
||||
],
|
||||
"deny": [],
|
||||
"ask": []
|
||||
}
|
||||
}
|
||||
|
|
@ -1,112 +0,0 @@
|
|||
name: Build Worker Base and Application Images
|
||||
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
- dev
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
force_base_build:
|
||||
description: 'Force base image build regardless of changes'
|
||||
required: false
|
||||
default: 'false'
|
||||
type: boolean
|
||||
|
||||
jobs:
|
||||
check-base-changes:
|
||||
runs-on: ubuntu-latest
|
||||
outputs:
|
||||
base-changed: ${{ steps.changes.outputs.base-changed }}
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v3
|
||||
with:
|
||||
fetch-depth: 2
|
||||
- name: Check for base changes
|
||||
id: changes
|
||||
run: |
|
||||
if git diff HEAD^ HEAD --name-only | grep -E "(Dockerfile\.base|requirements\.base\.txt)" > /dev/null; then
|
||||
echo "base-changed=true" >> $GITHUB_OUTPUT
|
||||
else
|
||||
echo "base-changed=false" >> $GITHUB_OUTPUT
|
||||
fi
|
||||
|
||||
build-base:
|
||||
needs: check-base-changes
|
||||
if: needs.check-base-changes.outputs.base-changed == 'true' || (github.event_name == 'workflow_dispatch' && github.event.inputs.force_base_build == 'true')
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
packages: write
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v3
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v2
|
||||
|
||||
- name: Login to GitHub Container Registry
|
||||
uses: docker/login-action@v3
|
||||
with:
|
||||
registry: git.siwatsystem.com
|
||||
username: ${{ github.actor }}
|
||||
password: ${{ secrets.RUNNER_TOKEN }}
|
||||
|
||||
- name: Build and push base Docker image
|
||||
uses: docker/build-push-action@v4
|
||||
with:
|
||||
context: .
|
||||
file: ./Dockerfile.base
|
||||
push: true
|
||||
tags: git.siwatsystem.com/adsist-cms/worker-base:latest
|
||||
|
||||
build-docker:
|
||||
needs: [check-base-changes, build-base]
|
||||
if: always() && (needs.build-base.result == 'success' || needs.build-base.result == 'skipped')
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
packages: write
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v3
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v2
|
||||
|
||||
- name: Login to GitHub Container Registry
|
||||
uses: docker/login-action@v3
|
||||
with:
|
||||
registry: git.siwatsystem.com
|
||||
username: ${{ github.actor }}
|
||||
password: ${{ secrets.RUNNER_TOKEN }}
|
||||
|
||||
- name: Build and push Docker image
|
||||
uses: docker/build-push-action@v4
|
||||
with:
|
||||
context: .
|
||||
file: ./Dockerfile
|
||||
push: true
|
||||
tags: git.siwatsystem.com/adsist-cms/worker:${{ github.ref_name == 'main' && 'latest' || 'dev' }}
|
||||
|
||||
deploy-stack:
|
||||
needs: build-docker
|
||||
runs-on: adsist
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v3
|
||||
- name: Set up SSH connection
|
||||
run: |
|
||||
mkdir -p ~/.ssh
|
||||
echo "${{ secrets.DEPLOY_KEY_CMS }}" > ~/.ssh/id_rsa
|
||||
chmod 600 ~/.ssh/id_rsa
|
||||
ssh-keyscan -H ${{ vars.DEPLOY_HOST_CMS }} >> ~/.ssh/known_hosts
|
||||
- name: Deploy stack
|
||||
run: |
|
||||
echo "Pulling and starting containers on server..."
|
||||
if [ "${{ github.ref_name }}" = "main" ]; then
|
||||
echo "Deploying production stack..."
|
||||
ssh -i ~/.ssh/id_rsa ${{ vars.DEPLOY_USER_CMS }}@${{ vars.DEPLOY_HOST_CMS }} "cd ~/cms-system-k8s && docker compose -f docker-compose.production.yml pull && docker compose -f docker-compose.production.yml up -d"
|
||||
else
|
||||
echo "Deploying staging stack..."
|
||||
ssh -i ~/.ssh/id_rsa ${{ vars.DEPLOY_USER_CMS }}@${{ vars.DEPLOY_HOST_CMS }} "cd ~/cms-system-k8s && docker compose -f docker-compose.staging.yml pull && docker compose -f docker-compose.staging.yml up -d"
|
||||
fi
|
||||
15
.gitignore
vendored
15
.gitignore
vendored
|
|
@ -1,14 +1,3 @@
|
|||
/models
|
||||
app.log
|
||||
*.pt
|
||||
|
||||
images
|
||||
|
||||
# All pycache directories
|
||||
__pycache__/
|
||||
.mptacache
|
||||
|
||||
mptas
|
||||
detector_worker.log
|
||||
.gitignore
|
||||
no_frame_debug.log
|
||||
/__pycache__
|
||||
models
|
||||
277
CLAUDE.md
277
CLAUDE.md
|
|
@ -1,277 +0,0 @@
|
|||
# Python Detector Worker - CLAUDE.md
|
||||
|
||||
## Project Overview
|
||||
This is a FastAPI-based computer vision detection worker that processes video streams from RTSP/HTTP sources and runs advanced YOLO-based machine learning pipelines for multi-class object detection and parallel classification. The system features comprehensive database integration, Redis support, and hierarchical pipeline execution designed to work within a larger CMS (Content Management System) architecture.
|
||||
|
||||
### Key Features
|
||||
- **Multi-Class Detection**: Simultaneous detection of multiple object classes (e.g., Car + Frontal)
|
||||
- **Parallel Processing**: Concurrent execution of classification branches using ThreadPoolExecutor
|
||||
- **Database Integration**: Automatic PostgreSQL schema management and record updates
|
||||
- **Redis Actions**: Image storage with region cropping and pub/sub messaging
|
||||
- **Pipeline Synchronization**: Branch coordination with `waitForBranches` functionality
|
||||
- **Dynamic Field Mapping**: Template-based field resolution for database operations
|
||||
|
||||
## Architecture & Technology Stack
|
||||
- **Framework**: FastAPI with WebSocket support
|
||||
- **ML/CV**: PyTorch, Ultralytics YOLO, OpenCV
|
||||
- **Containerization**: Docker (Python 3.13-bookworm base)
|
||||
- **Data Storage**: Redis integration for action handling + PostgreSQL for persistent storage
|
||||
- **Database**: Automatic schema management with gas_station_1 database
|
||||
- **Parallel Processing**: ThreadPoolExecutor for concurrent classification
|
||||
- **Communication**: WebSocket-based real-time protocol
|
||||
|
||||
## Core Components
|
||||
|
||||
### Main Application (`app.py`)
|
||||
- **FastAPI WebSocket server** for real-time communication
|
||||
- **Multi-camera stream management** with shared stream optimization
|
||||
- **HTTP REST endpoint** for image retrieval (`/camera/{camera_id}/image`)
|
||||
- **Threading-based frame readers** for RTSP streams and HTTP snapshots
|
||||
- **Model loading and inference** using MPTA (Machine Learning Pipeline Archive) format
|
||||
- **Session management** with display identifier mapping
|
||||
- **Resource monitoring** (CPU, memory, GPU usage via psutil)
|
||||
|
||||
### Pipeline System (`siwatsystem/pympta.py`)
|
||||
- **MPTA file handling** - ZIP archives containing model configurations
|
||||
- **Hierarchical pipeline execution** with detection → classification branching
|
||||
- **Multi-class detection** - Simultaneous detection of multiple classes (Car + Frontal)
|
||||
- **Parallel processing** - Concurrent classification branches with ThreadPoolExecutor
|
||||
- **Redis action system** - Image saving with region cropping and message publishing
|
||||
- **PostgreSQL integration** - Automatic table creation and combined updates
|
||||
- **Dynamic model loading** with GPU optimization
|
||||
- **Configurable trigger classes and confidence thresholds**
|
||||
- **Branch synchronization** - waitForBranches coordination for database updates
|
||||
|
||||
### Database System (`siwatsystem/database.py`)
|
||||
- **DatabaseManager class** for PostgreSQL operations
|
||||
- **Automatic table creation** with gas_station_1.car_frontal_info schema
|
||||
- **Combined update operations** with field mapping from branch results
|
||||
- **Session management** with UUID generation
|
||||
- **Error handling** and connection management
|
||||
|
||||
### Testing & Debugging
|
||||
- **Protocol test script** (`test_protocol.py`) for WebSocket communication validation
|
||||
- **Pipeline webcam utility** (`pipeline_webcam.py`) for local testing with visual output
|
||||
- **RTSP streaming debug tool** (`debug/rtsp_webcam.py`) using GStreamer
|
||||
|
||||
## Code Conventions & Patterns
|
||||
|
||||
### Logging
|
||||
- **Structured logging** using Python's logging module
|
||||
- **File + console output** to `detector_worker.log`
|
||||
- **Debug level separation** for detailed troubleshooting
|
||||
- **Context-aware messages** with camera IDs and model information
|
||||
|
||||
### Error Handling
|
||||
- **Graceful failure handling** with retry mechanisms (configurable max_retries)
|
||||
- **Thread-safe operations** using locks for streams and models
|
||||
- **WebSocket disconnect handling** with proper cleanup
|
||||
- **Model loading validation** with detailed error reporting
|
||||
|
||||
### Configuration
|
||||
- **JSON configuration** (`config.json`) for runtime parameters:
|
||||
- `poll_interval_ms`: Frame processing interval
|
||||
- `max_streams`: Concurrent stream limit
|
||||
- `target_fps`: Target frame rate
|
||||
- `reconnect_interval_sec`: Stream reconnection delay
|
||||
- `max_retries`: Maximum retry attempts (-1 for unlimited)
|
||||
|
||||
### Threading Model
|
||||
- **Frame reader threads** for each camera stream (RTSP/HTTP)
|
||||
- **Shared stream optimization** - multiple subscriptions can reuse the same camera stream
|
||||
- **Async WebSocket handling** with concurrent task management
|
||||
- **Thread-safe data structures** with proper locking mechanisms
|
||||
|
||||
## WebSocket Protocol
|
||||
|
||||
### Message Types
|
||||
- **subscribe**: Start camera stream with model pipeline
|
||||
- **unsubscribe**: Stop camera stream processing
|
||||
- **requestState**: Request current worker status
|
||||
- **setSessionId**: Associate display with session identifier
|
||||
- **patchSession**: Update session data
|
||||
- **stateReport**: Periodic heartbeat with system metrics
|
||||
- **imageDetection**: Detection results with timestamp and model info
|
||||
|
||||
### Subscription Format
|
||||
```json
|
||||
{
|
||||
"type": "subscribe",
|
||||
"payload": {
|
||||
"subscriptionIdentifier": "display-001;cam-001",
|
||||
"rtspUrl": "rtsp://...", // OR snapshotUrl
|
||||
"snapshotUrl": "http://...",
|
||||
"snapshotInterval": 5000,
|
||||
"modelUrl": "http://...model.mpta",
|
||||
"modelId": 101,
|
||||
"modelName": "Vehicle Detection",
|
||||
"cropX1": 100, "cropY1": 200,
|
||||
"cropX2": 300, "cropY2": 400
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Model Pipeline (MPTA) Format
|
||||
|
||||
### Enhanced Structure
|
||||
- **ZIP archive** containing models and configuration
|
||||
- **pipeline.json** - Main configuration file with Redis + PostgreSQL settings
|
||||
- **Model files** - YOLO .pt files for detection/classification
|
||||
- **Multi-model support** - Detection + multiple classification models
|
||||
|
||||
### Advanced Pipeline Flow
|
||||
1. **Multi-class detection stage** - YOLO detection of Car + Frontal simultaneously
|
||||
2. **Validation stage** - Check for expected classes (flexible matching)
|
||||
3. **Database initialization** - Create initial record with session_id
|
||||
4. **Redis actions** - Save cropped frontal images with expiration
|
||||
5. **Parallel classification** - Concurrent brand and body type classification
|
||||
6. **Branch synchronization** - Wait for all classification branches to complete
|
||||
7. **Database update** - Combined update with all classification results
|
||||
|
||||
### Enhanced Branch Configuration
|
||||
```json
|
||||
{
|
||||
"modelId": "car_frontal_detection_v1",
|
||||
"modelFile": "car_frontal_detection_v1.pt",
|
||||
"multiClass": true,
|
||||
"expectedClasses": ["Car", "Frontal"],
|
||||
"triggerClasses": ["Car", "Frontal"],
|
||||
"minConfidence": 0.8,
|
||||
"actions": [
|
||||
{
|
||||
"type": "redis_save_image",
|
||||
"region": "Frontal",
|
||||
"key": "inference:{display_id}:{timestamp}:{session_id}:{filename}",
|
||||
"expire_seconds": 600
|
||||
}
|
||||
],
|
||||
"branches": [
|
||||
{
|
||||
"modelId": "car_brand_cls_v1",
|
||||
"modelFile": "car_brand_cls_v1.pt",
|
||||
"parallel": true,
|
||||
"crop": true,
|
||||
"cropClass": "Frontal",
|
||||
"triggerClasses": ["Frontal"],
|
||||
"minConfidence": 0.85
|
||||
}
|
||||
],
|
||||
"parallelActions": [
|
||||
{
|
||||
"type": "postgresql_update_combined",
|
||||
"table": "car_frontal_info",
|
||||
"key_field": "session_id",
|
||||
"waitForBranches": ["car_brand_cls_v1", "car_bodytype_cls_v1"],
|
||||
"fields": {
|
||||
"car_brand": "{car_brand_cls_v1.brand}",
|
||||
"car_body_type": "{car_bodytype_cls_v1.body_type}"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
## Stream Management
|
||||
|
||||
### Shared Streams
|
||||
- Multiple subscriptions can share the same camera URL
|
||||
- Reference counting prevents premature stream termination
|
||||
- Automatic cleanup when last subscription ends
|
||||
|
||||
### Frame Processing
|
||||
- **Queue-based buffering** with single frame capacity (latest frame only)
|
||||
- **Configurable polling interval** based on target FPS
|
||||
- **Automatic reconnection** with exponential backoff
|
||||
|
||||
## Development & Testing
|
||||
|
||||
### Local Development
|
||||
```bash
|
||||
# Install dependencies
|
||||
pip install -r requirements.txt
|
||||
|
||||
# Run the worker
|
||||
python app.py
|
||||
|
||||
# Test protocol compliance
|
||||
python test_protocol.py
|
||||
|
||||
# Test pipeline with webcam
|
||||
python pipeline_webcam.py --mpta-file path/to/model.mpta --video 0
|
||||
```
|
||||
|
||||
### Docker Deployment
|
||||
```bash
|
||||
# Build container
|
||||
docker build -t detector-worker .
|
||||
|
||||
# Run with volume mounts for models
|
||||
docker run -p 8000:8000 -v ./models:/app/models detector-worker
|
||||
```
|
||||
|
||||
### Testing Commands
|
||||
- **Protocol testing**: `python test_protocol.py`
|
||||
- **Pipeline validation**: `python pipeline_webcam.py --mpta-file <path> --video 0`
|
||||
- **RTSP debugging**: `python debug/rtsp_webcam.py`
|
||||
|
||||
## Dependencies
|
||||
- **fastapi[standard]**: Web framework with WebSocket support
|
||||
- **uvicorn**: ASGI server
|
||||
- **torch, torchvision**: PyTorch for ML inference
|
||||
- **ultralytics**: YOLO implementation
|
||||
- **opencv-python**: Computer vision operations
|
||||
- **websockets**: WebSocket client/server
|
||||
- **redis**: Redis client for action execution
|
||||
- **psycopg2-binary**: PostgreSQL database adapter
|
||||
- **scipy**: Scientific computing for advanced algorithms
|
||||
- **filterpy**: Kalman filtering and state estimation
|
||||
|
||||
## Security Considerations
|
||||
- Model files are loaded from trusted sources only
|
||||
- Redis connections use authentication when configured
|
||||
- WebSocket connections handle disconnects gracefully
|
||||
- Resource usage is monitored to prevent DoS
|
||||
|
||||
## Database Integration
|
||||
|
||||
### Schema Management
|
||||
The system automatically creates and manages PostgreSQL tables:
|
||||
|
||||
```sql
|
||||
CREATE TABLE IF NOT EXISTS gas_station_1.car_frontal_info (
|
||||
display_id VARCHAR(255),
|
||||
captured_timestamp VARCHAR(255),
|
||||
session_id VARCHAR(255) PRIMARY KEY,
|
||||
license_character VARCHAR(255) DEFAULT NULL,
|
||||
license_type VARCHAR(255) DEFAULT 'No model available',
|
||||
car_brand VARCHAR(255) DEFAULT NULL,
|
||||
car_model VARCHAR(255) DEFAULT NULL,
|
||||
car_body_type VARCHAR(255) DEFAULT NULL,
|
||||
created_at TIMESTAMP DEFAULT NOW(),
|
||||
updated_at TIMESTAMP DEFAULT NOW()
|
||||
);
|
||||
```
|
||||
|
||||
### Workflow
|
||||
1. **Detection**: When both "Car" and "Frontal" are detected, create initial database record with UUID session_id
|
||||
2. **Redis Storage**: Save cropped frontal image to Redis with session_id in key
|
||||
3. **Parallel Processing**: Run brand and body type classification concurrently
|
||||
4. **Synchronization**: Wait for all branches to complete using `waitForBranches`
|
||||
5. **Database Update**: Update record with combined classification results using field mapping
|
||||
|
||||
### Field Mapping
|
||||
Templates like `{car_brand_cls_v1.brand}` are resolved to actual classification results:
|
||||
- `car_brand_cls_v1.brand` → "Honda"
|
||||
- `car_bodytype_cls_v1.body_type` → "Sedan"
|
||||
|
||||
## Performance Optimizations
|
||||
- GPU acceleration when CUDA is available
|
||||
- Shared camera streams reduce resource usage
|
||||
- Frame queue optimization (single latest frame)
|
||||
- Model caching across subscriptions
|
||||
- Trigger class filtering for faster inference
|
||||
- Parallel processing with ThreadPoolExecutor for classification branches
|
||||
- Multi-class detection reduces inference passes
|
||||
- Region-based cropping minimizes processing overhead
|
||||
- Database connection pooling and prepared statements
|
||||
- Redis image storage with automatic expiration
|
||||
12
Dockerfile
12
Dockerfile
|
|
@ -1,12 +0,0 @@
|
|||
# Use our pre-built base image with ML dependencies
|
||||
FROM git.siwatsystem.com/adsist-cms/worker-base:latest
|
||||
|
||||
# Copy and install application requirements (frequently changing dependencies)
|
||||
COPY requirements.txt .
|
||||
RUN pip install --no-cache-dir -r requirements.txt
|
||||
|
||||
# Copy the application code
|
||||
COPY . .
|
||||
|
||||
# Run the application
|
||||
CMD ["python3", "-m", "fastapi", "run", "--host", "0.0.0.0", "--port", "8000"]
|
||||
130
Dockerfile.base
130
Dockerfile.base
|
|
@ -1,130 +0,0 @@
|
|||
# Base image with complete ML and hardware acceleration stack
|
||||
FROM pytorch/pytorch:2.8.0-cuda12.6-cudnn9-runtime
|
||||
|
||||
# Install build dependencies and system libraries
|
||||
RUN apt-get update && apt-get install -y \
|
||||
# Build tools
|
||||
build-essential \
|
||||
cmake \
|
||||
git \
|
||||
pkg-config \
|
||||
wget \
|
||||
unzip \
|
||||
yasm \
|
||||
nasm \
|
||||
# Additional dependencies for FFmpeg/NVIDIA build
|
||||
libtool \
|
||||
libc6 \
|
||||
libc6-dev \
|
||||
libnuma1 \
|
||||
libnuma-dev \
|
||||
# Essential compilation libraries
|
||||
gcc \
|
||||
g++ \
|
||||
libc6-dev \
|
||||
linux-libc-dev \
|
||||
# System libraries
|
||||
libgl1-mesa-glx \
|
||||
libglib2.0-0 \
|
||||
libgomp1 \
|
||||
# Core media libraries (essential ones only)
|
||||
libjpeg-dev \
|
||||
libpng-dev \
|
||||
libx264-dev \
|
||||
libx265-dev \
|
||||
libvpx-dev \
|
||||
libmp3lame-dev \
|
||||
libv4l-dev \
|
||||
# TurboJPEG for fast JPEG encoding
|
||||
libturbojpeg0-dev \
|
||||
# Python development
|
||||
python3-dev \
|
||||
python3-numpy \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# Add NVIDIA CUDA repository and install minimal development tools
|
||||
RUN apt-get update && apt-get install -y wget gnupg && \
|
||||
wget -O - https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/3bf863cc.pub | apt-key add - && \
|
||||
echo "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64 /" > /etc/apt/sources.list.d/cuda.list && \
|
||||
apt-get update && \
|
||||
apt-get install -y \
|
||||
cuda-nvcc-12-6 \
|
||||
cuda-cudart-dev-12-6 \
|
||||
libnpp-dev-12-6 \
|
||||
&& apt-get remove -y wget gnupg && \
|
||||
apt-get autoremove -y && \
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# Ensure CUDA paths are available
|
||||
ENV PATH="/usr/local/cuda/bin:${PATH}"
|
||||
ENV LD_LIBRARY_PATH="/usr/local/cuda/lib64:${LD_LIBRARY_PATH}"
|
||||
|
||||
# Install NVIDIA Video Codec SDK headers (official method)
|
||||
RUN cd /tmp && \
|
||||
git clone https://git.videolan.org/git/ffmpeg/nv-codec-headers.git && \
|
||||
cd nv-codec-headers && \
|
||||
make install && \
|
||||
cd / && rm -rf /tmp/*
|
||||
|
||||
# Build FFmpeg from source with NVIDIA CUDA support
|
||||
RUN cd /tmp && \
|
||||
echo "Building FFmpeg with NVIDIA CUDA support..." && \
|
||||
# Download FFmpeg source (official method)
|
||||
git clone https://git.ffmpeg.org/ffmpeg.git ffmpeg/ && \
|
||||
cd ffmpeg && \
|
||||
# Configure with NVIDIA support (simplified to avoid configure issues)
|
||||
./configure \
|
||||
--prefix=/usr/local \
|
||||
--enable-shared \
|
||||
--disable-static \
|
||||
--enable-nonfree \
|
||||
--enable-gpl \
|
||||
--enable-cuda-nvcc \
|
||||
--enable-cuvid \
|
||||
--enable-nvdec \
|
||||
--enable-nvenc \
|
||||
--enable-libnpp \
|
||||
--extra-cflags=-I/usr/local/cuda/include \
|
||||
--extra-ldflags=-L/usr/local/cuda/lib64 \
|
||||
--enable-libx264 \
|
||||
--enable-libx265 \
|
||||
--enable-libvpx \
|
||||
--enable-libmp3lame && \
|
||||
# Build and install
|
||||
make -j$(nproc) && \
|
||||
make install && \
|
||||
ldconfig && \
|
||||
# Verify CUVID decoders are available
|
||||
echo "=== Verifying FFmpeg CUVID Support ===" && \
|
||||
(ffmpeg -hide_banner -decoders 2>/dev/null | grep cuvid || echo "No CUVID decoders found") && \
|
||||
echo "=== Verifying FFmpeg NVENC Support ===" && \
|
||||
(ffmpeg -hide_banner -encoders 2>/dev/null | grep nvenc || echo "No NVENC encoders found") && \
|
||||
cd / && rm -rf /tmp/*
|
||||
|
||||
# Set environment variables for maximum hardware acceleration
|
||||
ENV LD_LIBRARY_PATH="/usr/local/cuda/lib64:/usr/local/lib:${LD_LIBRARY_PATH}"
|
||||
ENV PKG_CONFIG_PATH="/usr/local/lib/pkgconfig:${PKG_CONFIG_PATH}"
|
||||
ENV PYTHONPATH="/usr/local/lib/python3.10/dist-packages:${PYTHONPATH}"
|
||||
|
||||
# Optimized environment variables for hardware acceleration
|
||||
ENV OPENCV_FFMPEG_CAPTURE_OPTIONS="rtsp_transport;tcp|hwaccel;cuda|hwaccel_device;0|video_codec;h264_cuvid|hwaccel_output_format;cuda"
|
||||
ENV OPENCV_FFMPEG_WRITER_OPTIONS="video_codec;h264_nvenc|preset;fast|tune;zerolatency|gpu;0"
|
||||
ENV CUDA_VISIBLE_DEVICES=0
|
||||
ENV NVIDIA_VISIBLE_DEVICES=all
|
||||
ENV NVIDIA_DRIVER_CAPABILITIES=compute,video,utility
|
||||
|
||||
# Copy and install base requirements (exclude opencv-python since we built from source)
|
||||
COPY requirements.base.txt .
|
||||
RUN grep -v opencv-python requirements.base.txt > requirements.tmp && \
|
||||
mv requirements.tmp requirements.base.txt && \
|
||||
pip install --no-cache-dir -r requirements.base.txt
|
||||
|
||||
# Set working directory
|
||||
WORKDIR /app
|
||||
|
||||
# Create images directory for bind mount
|
||||
RUN mkdir -p /app/images && \
|
||||
chmod 755 /app/images
|
||||
|
||||
# This base image will be reused for all worker builds
|
||||
CMD ["python3", "-m", "fastapi", "run", "--host", "0.0.0.0", "--port", "8000"]
|
||||
545
REFACTOR_PLAN.md
545
REFACTOR_PLAN.md
|
|
@ -1,545 +0,0 @@
|
|||
# Detector Worker Refactoring Plan
|
||||
|
||||
## Project Overview
|
||||
|
||||
Transform the current monolithic structure (~4000 lines across `app.py` and `siwatsystem/pympta.py`) into a modular, maintainable system with clear separation of concerns. The goal is to make the sophisticated computer vision pipeline easily understandable for other engineers while maintaining all existing functionality.
|
||||
|
||||
## Current System Flow Understanding
|
||||
|
||||
### Validated System Flow
|
||||
1. **WebSocket Connection** → Backend connects and sends `setSubscriptionList`
|
||||
2. **Model Management** → Download unique `.mpta` files to `models/` and extract
|
||||
3. **Tracking Phase** → Continuous tracking with `front_rear_detection_v1.pt`
|
||||
4. **Validation Phase** → Validate stable car (not just passing by)
|
||||
5. **Pipeline Execution** →
|
||||
- Detect car with `yolo11m.pt`
|
||||
- **Branch 1**: Front/rear detection → crop frontal → save to Redis + brand classification
|
||||
- **Branch 2**: Body type classification from car crop
|
||||
6. **Communication** → Send `imageDetection` → Backend generates `sessionId` → Fueling starts
|
||||
7. **Post-Fueling** → Backend clears `sessionId` → Continue tracking same car to avoid re-pipeline
|
||||
|
||||
### Core Responsibilities Identified
|
||||
1. **WebSocket Communication** - Message handling and protocol compliance
|
||||
2. **Stream Management** - RTSP/HTTP frame processing and buffering
|
||||
3. **Model Management** - MPTA download, extraction, and loading
|
||||
4. **Pipeline Configuration** - Parse `pipeline.json` and setup execution flow
|
||||
5. **Vehicle Tracking** - Continuous tracking and car identification
|
||||
6. **Validation Logic** - Stable car detection vs. passing-by cars
|
||||
7. **Detection Pipeline** - Main ML pipeline with parallel branches
|
||||
8. **Data Persistence** - Redis/PostgreSQL operations
|
||||
9. **Session Management** - Handle session IDs and lifecycle
|
||||
|
||||
## Proposed Directory Structure
|
||||
|
||||
```
|
||||
core/
|
||||
├── communication/
|
||||
│ ├── __init__.py
|
||||
│ ├── websocket.py # WebSocket message handling & protocol
|
||||
│ ├── messages.py # Message types and validation
|
||||
│ ├── models.py # Message data structures
|
||||
│ └── state.py # Worker state management
|
||||
├── streaming/
|
||||
│ ├── __init__.py
|
||||
│ ├── manager.py # Stream coordination and lifecycle
|
||||
│ ├── readers.py # RTSP/HTTP frame readers
|
||||
│ └── buffers.py # Frame buffering and caching
|
||||
├── models/
|
||||
│ ├── __init__.py
|
||||
│ ├── manager.py # MPTA download and model loading
|
||||
│ ├── pipeline.py # Pipeline.json parser and config
|
||||
│ └── inference.py # YOLO model wrapper and optimization
|
||||
├── tracking/
|
||||
│ ├── __init__.py
|
||||
│ ├── tracker.py # Vehicle tracking with front_rear_detection_v1
|
||||
│ ├── validator.py # Stable car validation logic
|
||||
│ └── integration.py # Tracking-pipeline integration
|
||||
├── detection/
|
||||
│ ├── __init__.py
|
||||
│ ├── pipeline.py # Main detection pipeline orchestration
|
||||
│ └── branches.py # Parallel branch processing (brand/bodytype)
|
||||
└── storage/
|
||||
├── __init__.py
|
||||
├── redis.py # Redis operations and image storage
|
||||
└── database.py # PostgreSQL operations (existing - will be moved)
|
||||
```
|
||||
|
||||
## Implementation Strategy (Feature-by-Feature Testing)
|
||||
|
||||
### Phase 1: Communication Layer
|
||||
- WebSocket message handling (setSubscriptionList, sessionId management)
|
||||
- HTTP API endpoints (camera image retrieval)
|
||||
- Worker state reporting
|
||||
|
||||
### Phase 2: Pipeline Configuration Reader
|
||||
- Parse `pipeline.json`
|
||||
- Model dependency resolution
|
||||
- Branch configuration setup
|
||||
|
||||
### Phase 3: Tracking System
|
||||
- Continuous vehicle tracking
|
||||
- Car identification and persistence
|
||||
|
||||
### Phase 4: Tracking Validator
|
||||
- Stable car detection logic
|
||||
- Passing-by vs. fueling car differentiation
|
||||
|
||||
### Phase 5: Model Pipeline Execution
|
||||
- Main detection pipeline
|
||||
- Parallel branch processing
|
||||
- Redis/DB integration
|
||||
|
||||
### Phase 6: Post-Session Tracking Validation
|
||||
- Same car validation after sessionId cleared
|
||||
- Prevent duplicate pipeline execution
|
||||
|
||||
## Key Preservation Requirements
|
||||
- **HTTP Endpoint**: `/camera/{camera_id}/image` must remain unchanged
|
||||
- **WebSocket Protocol**: Full compliance with `worker.md` specification
|
||||
- **MPTA Format**: Maintain compatibility with existing model archives
|
||||
- **Database Schema**: Keep existing PostgreSQL structure
|
||||
- **Redis Integration**: Preserve image storage and pub/sub functionality
|
||||
- **Configuration**: Maintain `config.json` compatibility
|
||||
- **Logging**: Preserve structured logging format
|
||||
|
||||
## Expected Benefits
|
||||
- **Maintainability**: Single responsibility modules (~200-400 lines each)
|
||||
- **Testability**: Independent testing of each component
|
||||
- **Readability**: Clear separation of concerns
|
||||
- **Scalability**: Easy to extend and modify individual components
|
||||
- **Documentation**: Self-documenting code structure
|
||||
|
||||
---
|
||||
|
||||
# Comprehensive TODO List
|
||||
|
||||
## ✅ Phase 1: Project Setup & Communication Layer - COMPLETED
|
||||
|
||||
### 1.1 Project Structure Setup
|
||||
- ✅ Create `core/` directory structure
|
||||
- ✅ Create all module directories and `__init__.py` files
|
||||
- ✅ Set up logging configuration for new modules
|
||||
- ✅ Update imports in existing files to prepare for migration
|
||||
|
||||
### 1.2 Communication Module (`core/communication/`)
|
||||
- ✅ **Create `models.py`** - Message data structures
|
||||
- ✅ Define WebSocket message models (SubscriptionList, StateReport, etc.)
|
||||
- ✅ Add validation schemas for incoming messages
|
||||
- ✅ Create response models for outgoing messages
|
||||
|
||||
- ✅ **Create `messages.py`** - Message types and validation
|
||||
- ✅ Implement message type constants
|
||||
- ✅ Add message validation functions
|
||||
- ✅ Create message builders for common responses
|
||||
|
||||
- ✅ **Create `websocket.py`** - WebSocket message handling
|
||||
- ✅ Extract WebSocket connection management from `app.py`
|
||||
- ✅ Implement message routing and dispatching
|
||||
- ✅ Add connection lifecycle management (connect, disconnect, reconnect)
|
||||
- ✅ Handle `setSubscriptionList` message processing
|
||||
- ✅ Handle `setSessionId` and `setProgressionStage` messages
|
||||
- ✅ Handle `requestState` and `patchSessionResult` messages
|
||||
|
||||
- ✅ **Create `state.py`** - Worker state management
|
||||
- ✅ Extract state reporting logic from `app.py`
|
||||
- ✅ Implement system metrics collection (CPU, memory, GPU)
|
||||
- ✅ Manage active subscriptions state
|
||||
- ✅ Handle session ID mapping and storage
|
||||
|
||||
### 1.3 HTTP API Preservation
|
||||
- ✅ **Preserve `/camera/{camera_id}/image` endpoint**
|
||||
- ✅ Extract REST API logic from `app.py`
|
||||
- ✅ Ensure frame caching mechanism works with new structure
|
||||
- ✅ Maintain exact same response format and error handling
|
||||
|
||||
### 1.4 Testing Phase 1
|
||||
- ✅ Test WebSocket connection and message handling
|
||||
- ✅ Test HTTP API endpoint functionality
|
||||
- ✅ Verify state reporting works correctly
|
||||
- ✅ Test session management functionality
|
||||
|
||||
### 1.5 Phase 1 Results
|
||||
- ✅ **Modular Architecture**: Transformed ~900 lines into 4 focused modules (~200 lines each)
|
||||
- ✅ **WebSocket Protocol**: Full compliance with worker.md specification
|
||||
- ✅ **System Metrics**: Real-time CPU, memory, GPU monitoring
|
||||
- ✅ **State Management**: Thread-safe subscription and session tracking
|
||||
- ✅ **Backward Compatibility**: All existing endpoints preserved
|
||||
- ✅ **Modern FastAPI**: Lifespan events, Pydantic v2 compatibility
|
||||
|
||||
## ✅ Phase 2: Pipeline Configuration & Model Management - COMPLETED
|
||||
|
||||
### 2.1 Models Module (`core/models/`)
|
||||
- ✅ **Create `pipeline.py`** - Pipeline.json parser
|
||||
- ✅ Extract pipeline configuration parsing from `pympta.py`
|
||||
- ✅ Implement pipeline validation
|
||||
- ✅ Add configuration schema validation
|
||||
- ✅ Handle Redis and PostgreSQL configuration parsing
|
||||
|
||||
- ✅ **Create `manager.py`** - MPTA download and model loading
|
||||
- ✅ Extract MPTA download logic from `pympta.py`
|
||||
- ✅ Implement ZIP extraction and validation
|
||||
- ✅ Add model file management and caching
|
||||
- ✅ Handle model loading with GPU optimization
|
||||
- ✅ Implement model dependency resolution
|
||||
|
||||
- ✅ **Create `inference.py`** - YOLO model wrapper
|
||||
- ✅ Create unified YOLO model interface
|
||||
- ✅ Add inference optimization and caching
|
||||
- ✅ Implement batch processing capabilities
|
||||
- ✅ Handle model switching and memory management
|
||||
|
||||
### 2.2 Testing Phase 2
|
||||
- ✅ Test MPTA file download and extraction
|
||||
- ✅ Test pipeline.json parsing and validation
|
||||
- ✅ Test model loading with different configurations
|
||||
- ✅ Verify GPU optimization works correctly
|
||||
|
||||
### 2.3 Phase 2 Results
|
||||
- ✅ **ModelManager**: Downloads, extracts, and manages MPTA files with model ID-based directory structure
|
||||
- ✅ **PipelineParser**: Parses and validates pipeline.json with full support for Redis, PostgreSQL, tracking, and branches
|
||||
- ✅ **YOLOWrapper**: Unified interface for YOLO models with caching, tracking, and classification support
|
||||
- ✅ **Model Caching**: Shared model cache across instances to optimize memory usage
|
||||
- ✅ **Dependency Resolution**: Automatically identifies and tracks all model file dependencies
|
||||
|
||||
## ✅ Phase 3: Streaming System - COMPLETED
|
||||
|
||||
### 3.1 Streaming Module (`core/streaming/`)
|
||||
- ✅ **Create `readers.py`** - RTSP/HTTP frame readers
|
||||
- ✅ Extract `frame_reader` function from `app.py`
|
||||
- ✅ Extract `snapshot_reader` function from `app.py`
|
||||
- ✅ Add connection management and retry logic
|
||||
- ✅ Implement frame rate control and optimization
|
||||
|
||||
- ✅ **Create `buffers.py`** - Frame buffering and caching
|
||||
- ✅ Extract frame buffer management from `app.py`
|
||||
- ✅ Implement efficient frame caching for REST API
|
||||
- ✅ Add buffer size management and memory optimization
|
||||
|
||||
- ✅ **Create `manager.py`** - Stream coordination
|
||||
- ✅ Extract stream lifecycle management from `app.py`
|
||||
- ✅ Implement shared stream optimization
|
||||
- ✅ Add subscription reconciliation logic
|
||||
- ✅ Handle stream sharing across multiple subscriptions
|
||||
|
||||
### 3.2 Testing Phase 3
|
||||
- ✅ Test RTSP stream reading and buffering
|
||||
- ✅ Test HTTP snapshot capture functionality
|
||||
- ✅ Test shared stream optimization
|
||||
- ✅ Verify frame caching for REST API access
|
||||
|
||||
### 3.3 Phase 3 Results
|
||||
- ✅ **RTSPReader**: OpenCV-based RTSP stream reader with automatic reconnection and frame callbacks
|
||||
- ✅ **HTTPSnapshotReader**: Periodic HTTP snapshot capture with HTTPBasicAuth and HTTPDigestAuth support
|
||||
- ✅ **FrameBuffer**: Thread-safe frame storage with automatic aging and cleanup
|
||||
- ✅ **CacheBuffer**: Enhanced frame cache with cropping support and highest quality JPEG encoding (default quality=100)
|
||||
- ✅ **StreamManager**: Complete stream lifecycle management with shared optimization and subscription reconciliation
|
||||
- ✅ **Authentication Support**: Proper handling of credentials in URLs with automatic auth type detection
|
||||
- ✅ **Real Camera Testing**: Verified with authenticated RTSP (1280x720) and HTTP snapshot (2688x1520) cameras
|
||||
- ✅ **Production Ready**: Stable concurrent streaming from multiple camera sources
|
||||
- ✅ **Dependencies**: Added opencv-python, numpy, and requests to requirements.txt
|
||||
|
||||
### 3.4 Recent Streaming Enhancements (Post-Phase 3)
|
||||
- ✅ **Format-Specific Optimization**: Tailored for 1280x720@6fps RTSP streams and 2560x1440 HTTP snapshots
|
||||
- ✅ **H.264 Error Recovery**: Enhanced error handling for corrupted frames with automatic stream recovery
|
||||
- ✅ **Frame Validation**: Implemented corruption detection using edge density analysis
|
||||
- ✅ **Buffer Size Optimization**: Adjusted buffer limits to 3MB for RTSP frames (1280x720x3 bytes)
|
||||
- ✅ **FFMPEG Integration**: Added environment variables to suppress verbose H.264 decoder errors
|
||||
- ✅ **URL Preservation**: Maintained clean RTSP URLs without parameter injection
|
||||
- ✅ **Type Detection**: Automatic stream type detection based on frame dimensions
|
||||
- ✅ **Quality Settings**: Format-specific JPEG quality (90% for RTSP, 95% for HTTP)
|
||||
|
||||
## ✅ Phase 4: Vehicle Tracking System - COMPLETED
|
||||
|
||||
### 4.1 Tracking Module (`core/tracking/`)
|
||||
- ✅ **Create `tracker.py`** - Vehicle tracking implementation (305 lines)
|
||||
- ✅ Implement continuous tracking with configurable model (front_rear_detection_v1.pt)
|
||||
- ✅ Add vehicle identification and persistence with TrackedVehicle dataclass
|
||||
- ✅ Implement tracking state management with thread-safe operations
|
||||
- ✅ Add bounding box tracking and motion analysis with position history
|
||||
- ✅ Multi-class tracking support for complex detection scenarios
|
||||
|
||||
- ✅ **Create `validator.py`** - Stable car validation (417 lines)
|
||||
- ✅ Implement stable car detection algorithm with multiple validation criteria
|
||||
- ✅ Add passing-by vs. fueling car differentiation using velocity and position analysis
|
||||
- ✅ Implement validation thresholds and timing with configurable parameters
|
||||
- ✅ Add confidence scoring for validation decisions with state history
|
||||
- ✅ Advanced motion analysis with velocity smoothing and position variance
|
||||
|
||||
- ✅ **Create `integration.py`** - Tracking-pipeline integration (547 lines)
|
||||
- ✅ Connect tracking system with main pipeline through TrackingPipelineIntegration
|
||||
- ✅ Handle tracking state transitions and session management
|
||||
- ✅ Implement post-session tracking validation with cooldown periods
|
||||
- ✅ Add same-car validation after sessionId cleared with 30-second cooldown
|
||||
- ✅ Car abandonment detection with automatic timeout monitoring
|
||||
- ✅ Mock detection system for backend communication
|
||||
- ✅ Async pipeline execution with proper error handling
|
||||
|
||||
### 4.2 Testing Phase 4
|
||||
- ✅ Test continuous vehicle tracking functionality
|
||||
- ✅ Test stable car validation logic
|
||||
- ✅ Test integration with existing pipeline
|
||||
- ✅ Verify tracking performance and accuracy
|
||||
- ✅ Test car abandonment detection with null detection messages
|
||||
- ✅ Verify session management and progression stage handling
|
||||
|
||||
### 4.3 Phase 4 Results
|
||||
- ✅ **VehicleTracker**: Complete tracking implementation with YOLO tracking integration, position history, and stability calculations
|
||||
- ✅ **StableCarValidator**: Sophisticated validation logic using velocity, position variance, and state consistency
|
||||
- ✅ **TrackingPipelineIntegration**: Full integration with pipeline system including session management and async processing
|
||||
- ✅ **StreamManager Integration**: Updated streaming manager to process tracking on every frame with proper threading
|
||||
- ✅ **Thread-Safe Operations**: All tracking operations are thread-safe with proper locking mechanisms
|
||||
- ✅ **Configurable Parameters**: All tracking parameters are configurable through pipeline.json
|
||||
- ✅ **Session Management**: Complete session lifecycle management with post-fueling validation
|
||||
- ✅ **Statistics and Monitoring**: Comprehensive statistics collection for tracking performance
|
||||
- ✅ **Car Abandonment Detection**: Automatic detection when cars leave without fueling, sends `detection: null` to backend
|
||||
- ✅ **Message Protocol**: Fixed JSON serialization to include `detection: null` for abandonment notifications
|
||||
- ✅ **Streaming Optimization**: Enhanced RTSP/HTTP readers for 1280x720@6fps RTSP and 2560x1440 HTTP snapshots
|
||||
- ✅ **Error Recovery**: Improved H.264 error handling and corrupted frame detection
|
||||
|
||||
## ✅ Phase 5: Detection Pipeline System - COMPLETED
|
||||
|
||||
### 5.1 Detection Module (`core/detection/`) ✅
|
||||
- ✅ **Create `pipeline.py`** - Main detection orchestration (574 lines)
|
||||
- ✅ Extracted main pipeline execution from `pympta.py` with full orchestration
|
||||
- ✅ Implemented detection flow coordination with async execution
|
||||
- ✅ Added pipeline state management with comprehensive statistics
|
||||
- ✅ Handled pipeline result aggregation with branch synchronization
|
||||
- ✅ Redis and database integration with error handling
|
||||
- ✅ Immediate and parallel action execution with template resolution
|
||||
|
||||
- ✅ **Create `branches.py`** - Parallel branch processing (442 lines)
|
||||
- ✅ Extracted parallel branch execution from `pympta.py`
|
||||
- ✅ Implemented ThreadPoolExecutor-based parallel processing
|
||||
- ✅ Added branch synchronization and result collection
|
||||
- ✅ Handled branch failure and retry logic with graceful degradation
|
||||
- ✅ Support for nested branches and model caching
|
||||
- ✅ Both detection and classification model support
|
||||
|
||||
### 5.2 Storage Module (`core/storage/`) ✅
|
||||
- ✅ **Create `redis.py`** - Redis operations (410 lines)
|
||||
- ✅ Extracted Redis action execution from `pympta.py`
|
||||
- ✅ Implemented async image storage with region cropping
|
||||
- ✅ Added pub/sub messaging functionality with JSON support
|
||||
- ✅ Handled Redis connection management and retry logic
|
||||
- ✅ Added statistics tracking and health monitoring
|
||||
- ✅ Support for various image formats (JPEG, PNG) with quality control
|
||||
|
||||
- ✅ **Move `database.py`** - PostgreSQL operations (339 lines)
|
||||
- ✅ Moved existing `archive/siwatsystem/database.py` to `core/storage/`
|
||||
- ✅ Updated imports and integration points
|
||||
- ✅ Ensured compatibility with new module structure
|
||||
- ✅ Added session management and statistics methods
|
||||
- ✅ Enhanced error handling and connection management
|
||||
|
||||
### 5.3 Integration Updates ✅
|
||||
- ✅ **Updated `core/tracking/integration.py`**
|
||||
- ✅ Added DetectionPipeline integration
|
||||
- ✅ Replaced placeholder `_execute_pipeline` with real implementation
|
||||
- ✅ Added detection pipeline initialization and cleanup
|
||||
- ✅ Integrated with existing tracking system flow
|
||||
- ✅ Maintained backward compatibility with test mode
|
||||
|
||||
### 5.4 Testing Phase 5 ✅
|
||||
- ✅ Verified module imports work correctly
|
||||
- ✅ All new modules follow established coding patterns
|
||||
- ✅ Integration points properly connected
|
||||
- ✅ Error handling and cleanup methods implemented
|
||||
- ✅ Statistics and monitoring capabilities added
|
||||
|
||||
### 5.5 Phase 5 Results ✅
|
||||
- ✅ **DetectionPipeline**: Complete detection orchestration with Redis/PostgreSQL integration, async execution, and comprehensive error handling
|
||||
- ✅ **BranchProcessor**: Parallel branch execution with ThreadPoolExecutor, model caching, and nested branch support
|
||||
- ✅ **RedisManager**: Async Redis operations with image storage, pub/sub messaging, and connection management
|
||||
- ✅ **DatabaseManager**: Enhanced PostgreSQL operations with session management and statistics
|
||||
- ✅ **Module Integration**: Seamless integration with existing tracking system while maintaining compatibility
|
||||
- ✅ **Error Handling**: Comprehensive error handling and graceful degradation throughout all components
|
||||
- ✅ **Performance**: Optimized parallel processing and caching for high-performance pipeline execution
|
||||
|
||||
## ✅ Additional Implemented Features (Not in Original Plan)
|
||||
|
||||
### License Plate Recognition Integration (`core/storage/license_plate.py`) ✅
|
||||
- ✅ **LicensePlateManager**: Subscribes to Redis channel `license_results` for external LPR service
|
||||
- ✅ **Multi-format Support**: Handles various message formats from LPR service
|
||||
- ✅ **Result Caching**: 5-minute TTL for license plate results
|
||||
- ✅ **WebSocket Integration**: Sends combined `imageDetection` messages with license data
|
||||
- ✅ **Asynchronous Processing**: Non-blocking Redis pub/sub listener
|
||||
|
||||
### Advanced Session State Management (`core/communication/state.py`) ✅
|
||||
- ✅ **Session ID Mapping**: Per-display session identifier tracking
|
||||
- ✅ **Progression Stage Tracking**: Workflow state per display (welcome, car_wait_staff, finished, cleared)
|
||||
- ✅ **Thread-Safe Operations**: RLock-based synchronization for concurrent access
|
||||
- ✅ **Comprehensive State Reporting**: Full system state for debugging
|
||||
|
||||
### Car Abandonment Detection (`core/tracking/integration.py`) ✅
|
||||
- ✅ **Abandonment Monitoring**: Detects cars leaving without completing fueling
|
||||
- ✅ **Timeout Configuration**: 3-second abandonment timeout
|
||||
- ✅ **Null Detection Messages**: Sends `detection: null` to backend for abandoned cars
|
||||
- ✅ **Automatic Cleanup**: Removes abandoned sessions from tracking
|
||||
|
||||
### Enhanced Message Protocol (`core/communication/models.py`) ✅
|
||||
- ✅ **PatchSessionResult**: Session data patching support
|
||||
- ✅ **SetProgressionStage**: Workflow stage management messages
|
||||
- ✅ **Null Detection Handling**: Support for abandonment notifications
|
||||
- ✅ **Complex Detection Structure**: Supports both classification and null states
|
||||
|
||||
### Comprehensive Timeout and Cooldown Systems ✅
|
||||
- ✅ **Post-Session Cooldown**: 30-second cooldown after session clearing
|
||||
- ✅ **Processing Cooldown**: 10-second cooldown for repeated processing
|
||||
- ✅ **Abandonment Timeout**: 3-second timeout for car abandonment detection
|
||||
- ✅ **Vehicle Expiration**: 2-second timeout for tracking cleanup
|
||||
- ✅ **Stream Timeouts**: 30-second connection timeout management
|
||||
|
||||
## 📋 Phase 6: Integration & Final Testing
|
||||
|
||||
### 6.1 Main Application Refactoring
|
||||
- [ ] **Refactor `app.py`**
|
||||
- [ ] Remove extracted functionality
|
||||
- [ ] Update to use new modular structure
|
||||
- [ ] Maintain FastAPI application structure
|
||||
- [ ] Update imports and dependencies
|
||||
|
||||
- [ ] **Clean up `siwatsystem/pympta.py`**
|
||||
- [ ] Remove extracted functionality
|
||||
- [ ] Keep only necessary legacy compatibility code
|
||||
- [ ] Update imports to use new modules
|
||||
|
||||
### 6.2 Post-Session Tracking Validation
|
||||
- [ ] Implement same-car validation after sessionId cleared
|
||||
- [ ] Add logic to prevent duplicate pipeline execution
|
||||
- [ ] Test tracking persistence through session lifecycle
|
||||
- [ ] Verify correct behavior during edge cases
|
||||
|
||||
### 6.3 Configuration & Documentation
|
||||
- [ ] Update configuration handling for new structure
|
||||
- [ ] Ensure `config.json` compatibility maintained
|
||||
- [ ] Update logging configuration for all modules
|
||||
- [ ] Add module-level documentation
|
||||
|
||||
### 6.4 Comprehensive Testing
|
||||
- [ ] **Integration Testing**
|
||||
- [ ] Test complete system flow end-to-end
|
||||
- [ ] Test all WebSocket message types
|
||||
- [ ] Test HTTP API endpoints
|
||||
- [ ] Test error handling and recovery
|
||||
|
||||
- [ ] **Performance Testing**
|
||||
- [ ] Verify system performance is maintained
|
||||
- [ ] Test memory usage optimization
|
||||
- [ ] Test GPU utilization efficiency
|
||||
- [ ] Benchmark against original implementation
|
||||
|
||||
- [ ] **Edge Case Testing**
|
||||
- [ ] Test connection failures and reconnection
|
||||
- [ ] Test model loading failures
|
||||
- [ ] Test stream interruption handling
|
||||
- [ ] Test concurrent subscription management
|
||||
|
||||
### 6.5 Logging Optimization & Cleanup ✅
|
||||
- ✅ **Removed Debug Frame Saving**
|
||||
- ✅ Removed hard-coded debug frame saving in `core/detection/pipeline.py`
|
||||
- ✅ Removed hard-coded debug frame saving in `core/detection/branches.py`
|
||||
- ✅ Eliminated absolute debug paths for production use
|
||||
|
||||
- ✅ **Eliminated Test/Mock Functionality**
|
||||
- ✅ Removed `save_frame_for_testing` function from `core/streaming/buffers.py`
|
||||
- ✅ Removed `save_test_frames` configuration from `StreamConfig`
|
||||
- ✅ Cleaned up test frame saving calls in stream manager
|
||||
- ✅ Updated module exports to remove test functions
|
||||
|
||||
- ✅ **Reduced Verbose Logging**
|
||||
- ✅ Commented out verbose frame storage logging (every frame)
|
||||
- ✅ Converted debug-level info logs to proper debug level
|
||||
- ✅ Reduced repetitive frame dimension logging
|
||||
- ✅ Maintained important model results and detection confidence logging
|
||||
- ✅ Kept critical pipeline execution and error messages
|
||||
|
||||
- ✅ **Production-Ready Logging**
|
||||
- ✅ Clean startup and initialization messages
|
||||
- ✅ Clear model loading and pipeline status
|
||||
- ✅ Preserved detection results with confidence scores
|
||||
- ✅ Maintained session management and tracking messages
|
||||
- ✅ Kept important error and warning messages
|
||||
|
||||
### 6.6 Final Cleanup
|
||||
- [ ] Remove any remaining duplicate code
|
||||
- [ ] Optimize imports across all modules
|
||||
- [ ] Clean up temporary files and debugging code
|
||||
- [ ] Update project documentation
|
||||
|
||||
## 📋 Post-Refactoring Tasks
|
||||
|
||||
### Documentation Updates
|
||||
- [ ] Update `CLAUDE.md` with new architecture
|
||||
- [ ] Create module-specific documentation
|
||||
- [ ] Update installation and deployment guides
|
||||
- [ ] Add troubleshooting guide for new structure
|
||||
|
||||
### Code Quality
|
||||
- [ ] Add type hints to all new modules
|
||||
- [ ] Implement proper error handling patterns
|
||||
- [ ] Add logging consistency across modules
|
||||
- [ ] Ensure proper resource cleanup
|
||||
|
||||
### Future Enhancements (Optional)
|
||||
- [ ] Add unit tests for each module
|
||||
- [ ] Implement monitoring and metrics collection
|
||||
- [ ] Add configuration validation
|
||||
- [ ] Consider adding dependency injection container
|
||||
|
||||
---
|
||||
|
||||
## Success Criteria
|
||||
|
||||
✅ **Modularity**: Each module has a single, clear responsibility
|
||||
✅ **Testability**: Each phase can be tested independently
|
||||
✅ **Maintainability**: Code is easy to understand and modify
|
||||
✅ **Compatibility**: All existing functionality preserved
|
||||
✅ **Performance**: System performance is maintained or improved
|
||||
✅ **Documentation**: Clear documentation for new architecture
|
||||
|
||||
## Risk Mitigation
|
||||
|
||||
- **Feature-by-feature testing** ensures functionality is preserved at each step
|
||||
- **Gradual migration** minimizes risk of breaking existing functionality
|
||||
- **Preserve critical interfaces** (WebSocket protocol, HTTP endpoints)
|
||||
- **Maintain backward compatibility** with existing configurations
|
||||
- **Comprehensive testing** at each phase before proceeding
|
||||
|
||||
---
|
||||
|
||||
## 🎯 Current Status Summary
|
||||
|
||||
### ✅ Completed Phases (95% Complete)
|
||||
- **Phase 1**: Communication Layer - ✅ COMPLETED
|
||||
- **Phase 2**: Pipeline Configuration & Model Management - ✅ COMPLETED
|
||||
- **Phase 3**: Streaming System - ✅ COMPLETED
|
||||
- **Phase 4**: Vehicle Tracking System - ✅ COMPLETED
|
||||
- **Phase 5**: Detection Pipeline System - ✅ COMPLETED
|
||||
- **Additional Features**: License Plate Recognition, Car Abandonment, Session Management - ✅ COMPLETED
|
||||
|
||||
### 📋 Remaining Work (5%)
|
||||
- **Phase 6**: Final Integration & Testing
|
||||
- Main application cleanup (`app.py` and `pympta.py`)
|
||||
- Comprehensive integration testing
|
||||
- Performance benchmarking
|
||||
- Documentation updates
|
||||
|
||||
### 🚀 Production Ready Features
|
||||
- ✅ **Modular Architecture**: ~4000 lines refactored into 20+ focused modules
|
||||
- ✅ **WebSocket Protocol**: Full compliance with all message types
|
||||
- ✅ **License Plate Recognition**: External LPR service integration via Redis
|
||||
- ✅ **Car Abandonment Detection**: Automatic detection and notification
|
||||
- ✅ **Session Management**: Complete lifecycle with progression stages
|
||||
- ✅ **Parallel Processing**: ThreadPoolExecutor for branch execution
|
||||
- ✅ **Redis Integration**: Pub/sub, image storage, LPR subscription
|
||||
- ✅ **PostgreSQL Integration**: Automatic schema management, combined updates
|
||||
- ✅ **Stream Optimization**: Shared streams, format-specific handling
|
||||
- ✅ **Error Recovery**: H.264 corruption detection, automatic reconnection
|
||||
- ✅ **Production Logging**: Clean, informative logging without debug clutter
|
||||
|
||||
### 📊 Metrics
|
||||
- **Modules Created**: 20+ specialized modules
|
||||
- **Lines Per Module**: ~200-500 (highly maintainable)
|
||||
- **Test Coverage**: Feature-by-feature validation completed
|
||||
- **Performance**: Maintained or improved from original implementation
|
||||
- **Backward Compatibility**: 100% preserved
|
||||
601
app.log
Normal file
601
app.log
Normal file
|
|
@ -0,0 +1,601 @@
|
|||
2025-01-09 00:43:08,967 [INFO] Will watch for changes in these directories: ['/Users/siwatsirichai/Documents/GitHub/python-detector-worker']
|
||||
2025-01-09 00:43:08,967 [INFO] Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)
|
||||
2025-01-09 00:43:08,967 [INFO] Started reloader process [36467] using WatchFiles
|
||||
2025-01-09 00:43:09,356 [INFO] 1 change detected
|
||||
2025-01-09 00:43:10,532 [INFO] Started server process [36471]
|
||||
2025-01-09 00:43:10,534 [INFO] Waiting for application startup.
|
||||
2025-01-09 00:43:10,534 [INFO] Application startup complete.
|
||||
2025-01-09 00:43:17,203 [INFO] WebSocket connection accepted
|
||||
2025-01-09 00:43:17,205 [INFO] ('127.0.0.1', 59148) - "WebSocket /" [accepted]
|
||||
2025-01-09 00:43:17,207 [INFO] connection open
|
||||
2025-01-09 00:43:17,207 [INFO] Started processing streams
|
||||
2025-01-09 00:43:23,325 [INFO] Subscribed to camera camera1 with URL rtsp://192.168.0.66:8554/common_room
|
||||
2025-01-09 00:44:48,212 [INFO] 1 change detected
|
||||
2025-01-09 00:44:48,217 [WARNING] WatchFiles detected changes in 'app.py'. Reloading...
|
||||
2025-01-09 00:44:48,227 [INFO] Shutting down
|
||||
2025-01-09 00:44:48,239 [ERROR] Error in WebSocket connection: (1012, None)
|
||||
2025-01-09 00:44:48,255 [INFO] Released camera camera1
|
||||
2025-01-09 00:44:48,255 [INFO] WebSocket connection closed
|
||||
2025-01-09 00:44:48,256 [ERROR] Exception in ASGI application
|
||||
Traceback (most recent call last):
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 243, in run_asgi
|
||||
result = await self.app(self.scope, self.asgi_receive, self.asgi_send) # type: ignore[func-returns-value]
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
|
||||
return await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/fastapi/applications.py", line 1054, in __call__
|
||||
await super().__call__(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/applications.py", line 113, in __call__
|
||||
await self.middleware_stack(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/middleware/errors.py", line 152, in __call__
|
||||
await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/middleware/exceptions.py", line 62, in __call__
|
||||
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
|
||||
raise exc
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
|
||||
await app(scope, receive, sender)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 715, in __call__
|
||||
await self.middleware_stack(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 735, in app
|
||||
await route.handle(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 362, in handle
|
||||
await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 95, in app
|
||||
await wrap_app_handling_exceptions(app, session)(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
|
||||
raise exc
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
|
||||
await app(scope, receive, sender)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 93, in app
|
||||
await func(session)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/fastapi/routing.py", line 383, in app
|
||||
await dependant.call(**solved_result.values)
|
||||
File "/Users/siwatsirichai/Documents/GitHub/python-detector-worker/app.py", line 102, in detect
|
||||
streams.clear()
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/websockets.py", line 180, in close
|
||||
await self.send({"type": "websocket.close", "code": code, "reason": reason or ""})
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/websockets.py", line 85, in send
|
||||
await self._send(message)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 39, in sender
|
||||
await send(message)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 359, in asgi_send
|
||||
raise RuntimeError(msg % message_type)
|
||||
RuntimeError: Unexpected ASGI message 'websocket.close', after sending 'websocket.close' or response already completed.
|
||||
2025-01-09 00:44:48,323 [INFO] connection closed
|
||||
2025-01-09 00:44:48,333 [INFO] Waiting for application shutdown.
|
||||
2025-01-09 00:44:48,334 [INFO] Application shutdown complete.
|
||||
2025-01-09 00:44:48,335 [INFO] Finished server process [36471]
|
||||
2025-01-09 00:44:48,728 [INFO] 1 change detected
|
||||
2025-01-09 00:44:51,790 [INFO] Started server process [36622]
|
||||
2025-01-09 00:44:51,793 [INFO] Waiting for application startup.
|
||||
2025-01-09 00:44:51,794 [INFO] Application startup complete.
|
||||
2025-01-09 00:44:52,764 [INFO] WebSocket connection accepted
|
||||
2025-01-09 00:44:52,764 [INFO] ('127.0.0.1', 59328) - "WebSocket /" [accepted]
|
||||
2025-01-09 00:44:52,765 [INFO] connection open
|
||||
2025-01-09 00:44:52,766 [INFO] Started processing streams
|
||||
2025-01-09 00:44:59,314 [INFO] Subscribed to camera camera1 with URL rtsp://192.168.0.66:8554/common_room
|
||||
2025-01-09 00:45:23,328 [ERROR] Error in WebSocket connection: (<CloseCode.ABNORMAL_CLOSURE: 1006>, '')
|
||||
2025-01-09 00:45:23,354 [INFO] Released camera camera1
|
||||
2025-01-09 00:45:23,354 [INFO] WebSocket connection closed
|
||||
2025-01-09 00:45:23,356 [ERROR] Exception in ASGI application
|
||||
Traceback (most recent call last):
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 243, in run_asgi
|
||||
result = await self.app(self.scope, self.asgi_receive, self.asgi_send) # type: ignore[func-returns-value]
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
|
||||
return await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/fastapi/applications.py", line 1054, in __call__
|
||||
await super().__call__(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/applications.py", line 113, in __call__
|
||||
await self.middleware_stack(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/middleware/errors.py", line 152, in __call__
|
||||
await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/middleware/exceptions.py", line 62, in __call__
|
||||
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
|
||||
raise exc
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
|
||||
await app(scope, receive, sender)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 715, in __call__
|
||||
await self.middleware_stack(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 735, in app
|
||||
await route.handle(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 362, in handle
|
||||
await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 95, in app
|
||||
await wrap_app_handling_exceptions(app, session)(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
|
||||
raise exc
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
|
||||
await app(scope, receive, sender)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 93, in app
|
||||
await func(session)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/fastapi/routing.py", line 383, in app
|
||||
await dependant.call(**solved_result.values)
|
||||
File "/Users/siwatsirichai/Documents/GitHub/python-detector-worker/app.py", line 104, in detect
|
||||
await websocket.close()
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/websockets.py", line 180, in close
|
||||
await self.send({"type": "websocket.close", "code": code, "reason": reason or ""})
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/websockets.py", line 85, in send
|
||||
await self._send(message)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 39, in sender
|
||||
await send(message)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 359, in asgi_send
|
||||
raise RuntimeError(msg % message_type)
|
||||
RuntimeError: Unexpected ASGI message 'websocket.close', after sending 'websocket.close' or response already completed.
|
||||
2025-01-09 00:45:23,433 [INFO] connection closed
|
||||
2025-01-09 00:45:25,088 [INFO] WebSocket connection accepted
|
||||
2025-01-09 00:45:25,088 [INFO] ('127.0.0.1', 59396) - "WebSocket /" [accepted]
|
||||
2025-01-09 00:45:25,091 [INFO] connection open
|
||||
2025-01-09 00:45:25,092 [INFO] Started processing streams
|
||||
2025-01-09 00:45:31,313 [INFO] Subscribed to camera camera1 with URL rtsp://192.168.0.66:8554/common_room
|
||||
2025-01-09 00:45:37,901 [INFO] Shutting down
|
||||
2025-01-09 00:45:37,906 [ERROR] Error in WebSocket connection: (1012, None)
|
||||
2025-01-09 00:45:37,919 [INFO] Released camera camera1
|
||||
2025-01-09 00:45:37,919 [INFO] WebSocket connection closed
|
||||
2025-01-09 00:45:37,919 [ERROR] Exception in ASGI application
|
||||
Traceback (most recent call last):
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 243, in run_asgi
|
||||
result = await self.app(self.scope, self.asgi_receive, self.asgi_send) # type: ignore[func-returns-value]
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
|
||||
return await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/fastapi/applications.py", line 1054, in __call__
|
||||
await super().__call__(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/applications.py", line 113, in __call__
|
||||
await self.middleware_stack(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/middleware/errors.py", line 152, in __call__
|
||||
await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/middleware/exceptions.py", line 62, in __call__
|
||||
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
|
||||
raise exc
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
|
||||
await app(scope, receive, sender)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 715, in __call__
|
||||
await self.middleware_stack(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 735, in app
|
||||
await route.handle(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 362, in handle
|
||||
await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 95, in app
|
||||
await wrap_app_handling_exceptions(app, session)(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
|
||||
raise exc
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
|
||||
await app(scope, receive, sender)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 93, in app
|
||||
await func(session)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/fastapi/routing.py", line 383, in app
|
||||
await dependant.call(**solved_result.values)
|
||||
File "/Users/siwatsirichai/Documents/GitHub/python-detector-worker/app.py", line 104, in detect
|
||||
await websocket.close()
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/websockets.py", line 180, in close
|
||||
await self.send({"type": "websocket.close", "code": code, "reason": reason or ""})
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/websockets.py", line 85, in send
|
||||
await self._send(message)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 39, in sender
|
||||
await send(message)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 359, in asgi_send
|
||||
raise RuntimeError(msg % message_type)
|
||||
RuntimeError: Unexpected ASGI message 'websocket.close', after sending 'websocket.close' or response already completed.
|
||||
2025-01-09 00:45:37,921 [INFO] connection closed
|
||||
2025-01-09 00:45:38,006 [INFO] Waiting for application shutdown.
|
||||
2025-01-09 00:45:38,007 [INFO] Application shutdown complete.
|
||||
2025-01-09 00:45:38,008 [INFO] Finished server process [36622]
|
||||
2025-01-09 00:45:38,031 [INFO] Stopping reloader process [36467]
|
||||
2025-01-09 00:46:40,345 [INFO] Will watch for changes in these directories: ['/Users/siwatsirichai/Documents/GitHub/python-detector-worker']
|
||||
2025-01-09 00:46:40,346 [INFO] Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)
|
||||
2025-01-09 00:46:40,347 [INFO] Started reloader process [36868] using WatchFiles
|
||||
2025-01-09 00:46:42,402 [INFO] Started server process [36902]
|
||||
2025-01-09 00:46:42,404 [INFO] Waiting for application startup.
|
||||
2025-01-09 00:46:42,405 [INFO] Application startup complete.
|
||||
2025-01-09 00:46:42,439 [INFO] WebSocket connection accepted
|
||||
2025-01-09 00:46:42,439 [INFO] ('127.0.0.1', 59523) - "WebSocket /" [accepted]
|
||||
2025-01-09 00:46:42,440 [INFO] connection open
|
||||
2025-01-09 00:46:42,440 [INFO] Started processing streams
|
||||
2025-01-09 00:46:47,311 [INFO] Subscribed to camera camera1 with URL rtsp://192.168.0.66:8554/common_room
|
||||
2025-01-09 00:46:51,990 [ERROR] Error in WebSocket connection: (<CloseCode.ABNORMAL_CLOSURE: 1006>, '')
|
||||
2025-01-09 00:46:52,001 [INFO] Released camera camera1
|
||||
2025-01-09 00:46:52,002 [INFO] WebSocket connection closed
|
||||
2025-01-09 00:46:52,002 [ERROR] Exception in ASGI application
|
||||
Traceback (most recent call last):
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 243, in run_asgi
|
||||
result = await self.app(self.scope, self.asgi_receive, self.asgi_send) # type: ignore[func-returns-value]
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
|
||||
return await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/fastapi/applications.py", line 1054, in __call__
|
||||
await super().__call__(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/applications.py", line 113, in __call__
|
||||
await self.middleware_stack(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/middleware/errors.py", line 152, in __call__
|
||||
await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/middleware/exceptions.py", line 62, in __call__
|
||||
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
|
||||
raise exc
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
|
||||
await app(scope, receive, sender)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 715, in __call__
|
||||
await self.middleware_stack(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 735, in app
|
||||
await route.handle(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 362, in handle
|
||||
await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 95, in app
|
||||
await wrap_app_handling_exceptions(app, session)(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
|
||||
raise exc
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
|
||||
await app(scope, receive, sender)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 93, in app
|
||||
await func(session)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/fastapi/routing.py", line 383, in app
|
||||
await dependant.call(**solved_result.values)
|
||||
File "/Users/siwatsirichai/Documents/GitHub/python-detector-worker/app.py", line 104, in detect
|
||||
await websocket.close()
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/websockets.py", line 180, in close
|
||||
await self.send({"type": "websocket.close", "code": code, "reason": reason or ""})
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/websockets.py", line 85, in send
|
||||
await self._send(message)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 39, in sender
|
||||
await send(message)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 359, in asgi_send
|
||||
raise RuntimeError(msg % message_type)
|
||||
RuntimeError: Unexpected ASGI message 'websocket.close', after sending 'websocket.close' or response already completed.
|
||||
2025-01-09 00:46:52,030 [INFO] connection closed
|
||||
2025-01-09 00:47:56,615 [INFO] WebSocket connection accepted
|
||||
2025-01-09 00:47:56,616 [INFO] ('127.0.0.1', 59664) - "WebSocket /" [accepted]
|
||||
2025-01-09 00:47:56,628 [INFO] connection open
|
||||
2025-01-09 00:47:56,631 [INFO] Started processing streams
|
||||
2025-01-09 00:48:03,306 [INFO] Subscribed to camera camera1 with URL rtsp://192.168.0.66:8554/common_room
|
||||
2025-01-09 00:48:06,345 [ERROR] Error in WebSocket connection: (<CloseCode.ABNORMAL_CLOSURE: 1006>, '')
|
||||
2025-01-09 00:48:06,352 [INFO] Released camera camera1
|
||||
2025-01-09 00:48:06,352 [INFO] WebSocket connection closed
|
||||
2025-01-09 00:48:06,353 [ERROR] Exception in ASGI application
|
||||
Traceback (most recent call last):
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 243, in run_asgi
|
||||
result = await self.app(self.scope, self.asgi_receive, self.asgi_send) # type: ignore[func-returns-value]
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
|
||||
return await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/fastapi/applications.py", line 1054, in __call__
|
||||
await super().__call__(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/applications.py", line 113, in __call__
|
||||
await self.middleware_stack(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/middleware/errors.py", line 152, in __call__
|
||||
await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/middleware/exceptions.py", line 62, in __call__
|
||||
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
|
||||
raise exc
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
|
||||
await app(scope, receive, sender)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 715, in __call__
|
||||
await self.middleware_stack(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 735, in app
|
||||
await route.handle(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 362, in handle
|
||||
await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 95, in app
|
||||
await wrap_app_handling_exceptions(app, session)(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
|
||||
raise exc
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
|
||||
await app(scope, receive, sender)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 93, in app
|
||||
await func(session)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/fastapi/routing.py", line 383, in app
|
||||
await dependant.call(**solved_result.values)
|
||||
File "/Users/siwatsirichai/Documents/GitHub/python-detector-worker/app.py", line 104, in detect
|
||||
await websocket.close()
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/websockets.py", line 180, in close
|
||||
await self.send({"type": "websocket.close", "code": code, "reason": reason or ""})
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/websockets.py", line 85, in send
|
||||
await self._send(message)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 39, in sender
|
||||
await send(message)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 359, in asgi_send
|
||||
raise RuntimeError(msg % message_type)
|
||||
RuntimeError: Unexpected ASGI message 'websocket.close', after sending 'websocket.close' or response already completed.
|
||||
2025-01-09 00:48:06,361 [INFO] connection closed
|
||||
2025-01-09 00:48:38,544 [INFO] WebSocket connection accepted
|
||||
2025-01-09 00:48:38,545 [INFO] ('127.0.0.1', 59735) - "WebSocket /" [accepted]
|
||||
2025-01-09 00:48:38,546 [INFO] connection open
|
||||
2025-01-09 00:48:38,550 [INFO] Started processing streams
|
||||
2025-01-09 00:48:43,303 [INFO] Subscribed to camera camera1 with URL rtsp://192.168.0.66:8554/common_room
|
||||
2025-01-09 00:49:28,103 [ERROR] Error in WebSocket connection: (<CloseCode.ABNORMAL_CLOSURE: 1006>, '')
|
||||
2025-01-09 00:49:28,115 [INFO] Released camera camera1
|
||||
2025-01-09 00:49:28,116 [INFO] WebSocket connection closed
|
||||
2025-01-09 00:49:28,116 [ERROR] Exception in ASGI application
|
||||
Traceback (most recent call last):
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 243, in run_asgi
|
||||
result = await self.app(self.scope, self.asgi_receive, self.asgi_send) # type: ignore[func-returns-value]
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
|
||||
return await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/fastapi/applications.py", line 1054, in __call__
|
||||
await super().__call__(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/applications.py", line 113, in __call__
|
||||
await self.middleware_stack(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/middleware/errors.py", line 152, in __call__
|
||||
await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/middleware/exceptions.py", line 62, in __call__
|
||||
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
|
||||
raise exc
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
|
||||
await app(scope, receive, sender)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 715, in __call__
|
||||
await self.middleware_stack(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 735, in app
|
||||
await route.handle(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 362, in handle
|
||||
await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 95, in app
|
||||
await wrap_app_handling_exceptions(app, session)(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
|
||||
raise exc
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
|
||||
await app(scope, receive, sender)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 93, in app
|
||||
await func(session)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/fastapi/routing.py", line 383, in app
|
||||
await dependant.call(**solved_result.values)
|
||||
File "/Users/siwatsirichai/Documents/GitHub/python-detector-worker/app.py", line 104, in detect
|
||||
await websocket.close()
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/websockets.py", line 180, in close
|
||||
await self.send({"type": "websocket.close", "code": code, "reason": reason or ""})
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/websockets.py", line 85, in send
|
||||
await self._send(message)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 39, in sender
|
||||
await send(message)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 359, in asgi_send
|
||||
raise RuntimeError(msg % message_type)
|
||||
RuntimeError: Unexpected ASGI message 'websocket.close', after sending 'websocket.close' or response already completed.
|
||||
2025-01-09 00:49:28,125 [INFO] connection closed
|
||||
2025-01-09 00:50:30,615 [INFO] WebSocket connection accepted
|
||||
2025-01-09 00:50:30,616 [INFO] ('127.0.0.1', 59919) - "WebSocket /" [accepted]
|
||||
2025-01-09 00:50:30,618 [INFO] connection open
|
||||
2025-01-09 00:50:30,619 [INFO] Started processing streams
|
||||
2025-01-09 00:50:35,299 [INFO] Subscribed to camera camera1 with URL rtsp://192.168.0.66:8554/common_room
|
||||
2025-01-09 00:51:20,717 [ERROR] Error in WebSocket connection: (<CloseCode.ABNORMAL_CLOSURE: 1006>, '')
|
||||
2025-01-09 00:51:20,727 [INFO] Released camera camera1
|
||||
2025-01-09 00:51:20,727 [INFO] WebSocket connection closed
|
||||
2025-01-09 00:51:20,727 [ERROR] Exception in ASGI application
|
||||
Traceback (most recent call last):
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 243, in run_asgi
|
||||
result = await self.app(self.scope, self.asgi_receive, self.asgi_send) # type: ignore[func-returns-value]
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
|
||||
return await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/fastapi/applications.py", line 1054, in __call__
|
||||
await super().__call__(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/applications.py", line 113, in __call__
|
||||
await self.middleware_stack(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/middleware/errors.py", line 152, in __call__
|
||||
await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/middleware/exceptions.py", line 62, in __call__
|
||||
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
|
||||
raise exc
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
|
||||
await app(scope, receive, sender)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 715, in __call__
|
||||
await self.middleware_stack(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 735, in app
|
||||
await route.handle(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 362, in handle
|
||||
await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 95, in app
|
||||
await wrap_app_handling_exceptions(app, session)(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
|
||||
raise exc
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
|
||||
await app(scope, receive, sender)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 93, in app
|
||||
await func(session)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/fastapi/routing.py", line 383, in app
|
||||
await dependant.call(**solved_result.values)
|
||||
File "/Users/siwatsirichai/Documents/GitHub/python-detector-worker/app.py", line 104, in detect
|
||||
await websocket.close()
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/websockets.py", line 180, in close
|
||||
await self.send({"type": "websocket.close", "code": code, "reason": reason or ""})
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/websockets.py", line 85, in send
|
||||
await self._send(message)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 39, in sender
|
||||
await send(message)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 359, in asgi_send
|
||||
raise RuntimeError(msg % message_type)
|
||||
RuntimeError: Unexpected ASGI message 'websocket.close', after sending 'websocket.close' or response already completed.
|
||||
2025-01-09 00:51:20,732 [INFO] connection closed
|
||||
2025-01-09 00:52:20,552 [INFO] 1 change detected
|
||||
2025-01-09 00:52:20,571 [WARNING] WatchFiles detected changes in 'app.py'. Reloading...
|
||||
2025-01-09 00:52:20,681 [INFO] Shutting down
|
||||
2025-01-09 00:52:20,787 [INFO] Waiting for application shutdown.
|
||||
2025-01-09 00:52:20,790 [INFO] Application shutdown complete.
|
||||
2025-01-09 00:52:20,791 [INFO] Finished server process [36902]
|
||||
2025-01-09 00:52:21,170 [INFO] 1 change detected
|
||||
2025-01-09 00:52:23,436 [INFO] Started server process [37369]
|
||||
2025-01-09 00:52:23,438 [INFO] Waiting for application startup.
|
||||
2025-01-09 00:52:23,438 [INFO] Application startup complete.
|
||||
2025-01-09 00:52:54,852 [INFO] 1 change detected
|
||||
2025-01-09 00:52:54,860 [WARNING] WatchFiles detected changes in 'app.py'. Reloading...
|
||||
2025-01-09 00:52:54,949 [INFO] Shutting down
|
||||
2025-01-09 00:52:55,052 [INFO] Waiting for application shutdown.
|
||||
2025-01-09 00:52:55,053 [INFO] Application shutdown complete.
|
||||
2025-01-09 00:52:55,053 [INFO] Finished server process [37369]
|
||||
2025-01-09 00:52:55,426 [INFO] 1 change detected
|
||||
2025-01-09 00:52:57,074 [INFO] Started server process [37436]
|
||||
2025-01-09 00:52:57,076 [INFO] Waiting for application startup.
|
||||
2025-01-09 00:52:57,078 [INFO] Application startup complete.
|
||||
2025-01-09 00:53:06,378 [INFO] 1 change detected
|
||||
2025-01-09 00:53:08,915 [INFO] Shutting down
|
||||
2025-01-09 00:53:09,018 [INFO] Waiting for application shutdown.
|
||||
2025-01-09 00:53:09,020 [INFO] Application shutdown complete.
|
||||
2025-01-09 00:53:09,021 [INFO] Finished server process [37436]
|
||||
2025-01-09 00:53:09,044 [INFO] Stopping reloader process [36868]
|
||||
2025-01-09 00:53:11,752 [INFO] Will watch for changes in these directories: ['/Users/siwatsirichai/Documents/GitHub/python-detector-worker']
|
||||
2025-01-09 00:53:11,753 [INFO] Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)
|
||||
2025-01-09 00:53:11,753 [INFO] Started reloader process [37483] using WatchFiles
|
||||
2025-01-09 00:53:13,520 [INFO] Started server process [37487]
|
||||
2025-01-09 00:53:13,522 [INFO] Waiting for application startup.
|
||||
2025-01-09 00:53:13,523 [INFO] Application startup complete.
|
||||
2025-01-09 00:53:14,050 [INFO] WebSocket connection accepted
|
||||
2025-01-09 00:53:14,050 [INFO] ('127.0.0.1', 60224) - "WebSocket /" [accepted]
|
||||
2025-01-09 00:53:14,052 [INFO] connection open
|
||||
2025-01-09 00:53:14,052 [INFO] Started processing streams
|
||||
2025-01-09 00:53:19,283 [INFO] Subscribed to camera camera1 with URL rtsp://192.168.0.66:8554/common_room
|
||||
2025-01-09 00:53:36,514 [INFO] 1 change detected
|
||||
2025-01-09 00:53:38,902 [ERROR] Error in WebSocket connection: (<CloseCode.ABNORMAL_CLOSURE: 1006>, '')
|
||||
2025-01-09 00:53:38,910 [INFO] Released camera camera1
|
||||
2025-01-09 00:53:38,911 [INFO] WebSocket connection closed
|
||||
2025-01-09 00:53:38,911 [ERROR] Exception in ASGI application
|
||||
Traceback (most recent call last):
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 243, in run_asgi
|
||||
result = await self.app(self.scope, self.asgi_receive, self.asgi_send) # type: ignore[func-returns-value]
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
|
||||
return await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/fastapi/applications.py", line 1054, in __call__
|
||||
await super().__call__(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/applications.py", line 113, in __call__
|
||||
await self.middleware_stack(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/middleware/errors.py", line 152, in __call__
|
||||
await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/middleware/exceptions.py", line 62, in __call__
|
||||
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
|
||||
raise exc
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
|
||||
await app(scope, receive, sender)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 715, in __call__
|
||||
await self.middleware_stack(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 735, in app
|
||||
await route.handle(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 362, in handle
|
||||
await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 95, in app
|
||||
await wrap_app_handling_exceptions(app, session)(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
|
||||
raise exc
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
|
||||
await app(scope, receive, sender)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 93, in app
|
||||
await func(session)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/fastapi/routing.py", line 383, in app
|
||||
await dependant.call(**solved_result.values)
|
||||
File "/Users/siwatsirichai/Documents/GitHub/python-detector-worker/app.py", line 111, in detect
|
||||
await websocket.close()
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/websockets.py", line 180, in close
|
||||
await self.send({"type": "websocket.close", "code": code, "reason": reason or ""})
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/websockets.py", line 85, in send
|
||||
await self._send(message)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 39, in sender
|
||||
await send(message)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 359, in asgi_send
|
||||
raise RuntimeError(msg % message_type)
|
||||
RuntimeError: Unexpected ASGI message 'websocket.close', after sending 'websocket.close' or response already completed.
|
||||
2025-01-09 00:53:38,944 [INFO] connection closed
|
||||
2025-01-09 00:53:40,757 [INFO] Shutting down
|
||||
2025-01-09 00:53:40,880 [INFO] Finished server process [37487]
|
||||
2025-01-09 00:53:40,980 [ERROR] Traceback (most recent call last):
|
||||
File "/Applications/Xcode.app/Contents/Developer/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/asyncio/runners.py", line 44, in run
|
||||
return loop.run_until_complete(main)
|
||||
File "uvloop/loop.pyx", line 1512, in uvloop.loop.Loop.run_until_complete
|
||||
File "uvloop/loop.pyx", line 1505, in uvloop.loop.Loop.run_until_complete
|
||||
File "uvloop/loop.pyx", line 1379, in uvloop.loop.Loop.run_forever
|
||||
File "uvloop/loop.pyx", line 557, in uvloop.loop.Loop._run
|
||||
File "uvloop/loop.pyx", line 476, in uvloop.loop.Loop._on_idle
|
||||
File "uvloop/cbhandles.pyx", line 83, in uvloop.loop.Handle._run
|
||||
File "uvloop/cbhandles.pyx", line 63, in uvloop.loop.Handle._run
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/server.py", line 70, in serve
|
||||
await self._serve(sockets)
|
||||
File "/Applications/Xcode.app/Contents/Developer/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/contextlib.py", line 124, in __exit__
|
||||
next(self.gen)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/server.py", line 330, in capture_signals
|
||||
signal.raise_signal(captured_signal)
|
||||
KeyboardInterrupt
|
||||
|
||||
During handling of the above exception, another exception occurred:
|
||||
|
||||
Traceback (most recent call last):
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 700, in lifespan
|
||||
await receive()
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/lifespan/on.py", line 137, in receive
|
||||
return await self.receive_queue.get()
|
||||
File "/Applications/Xcode.app/Contents/Developer/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/asyncio/queues.py", line 166, in get
|
||||
await getter
|
||||
asyncio.exceptions.CancelledError
|
||||
|
||||
2025-01-09 00:53:41,696 [INFO] Stopping reloader process [37483]
|
||||
2025-01-09 00:53:46,103 [INFO] Will watch for changes in these directories: ['/Users/siwatsirichai/Documents/GitHub/python-detector-worker']
|
||||
2025-01-09 00:53:46,103 [INFO] Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)
|
||||
2025-01-09 00:53:46,104 [INFO] Started reloader process [37591] using WatchFiles
|
||||
2025-01-09 00:53:47,860 [INFO] Started server process [37599]
|
||||
2025-01-09 00:53:47,862 [INFO] Waiting for application startup.
|
||||
2025-01-09 00:53:47,862 [INFO] Application startup complete.
|
||||
2025-01-09 00:54:51,976 [INFO] Shutting down
|
||||
2025-01-09 00:54:52,080 [INFO] Waiting for application shutdown.
|
||||
2025-01-09 00:54:52,083 [INFO] Application shutdown complete.
|
||||
2025-01-09 00:54:52,083 [INFO] Finished server process [37599]
|
||||
2025-01-09 00:54:52,102 [INFO] Stopping reloader process [37591]
|
||||
2025-01-09 00:54:54,952 [INFO] Will watch for changes in these directories: ['/Users/siwatsirichai/Documents/GitHub/python-detector-worker']
|
||||
2025-01-09 00:54:54,953 [INFO] Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)
|
||||
2025-01-09 00:54:54,953 [INFO] Started reloader process [37680] using WatchFiles
|
||||
2025-01-09 00:54:56,634 [INFO] Started server process [37693]
|
||||
2025-01-09 00:54:56,636 [INFO] Waiting for application startup.
|
||||
2025-01-09 00:54:56,636 [INFO] Application startup complete.
|
||||
2025-01-09 00:54:56,882 [INFO] WebSocket connection accepted
|
||||
2025-01-09 00:54:56,882 [INFO] ('127.0.0.1', 60381) - "WebSocket /" [accepted]
|
||||
2025-01-09 00:54:56,884 [INFO] connection open
|
||||
2025-01-09 00:54:56,885 [INFO] Started processing streams
|
||||
2025-01-09 00:55:03,279 [INFO] Subscribed to camera camera1 with URL rtsp://192.168.0.66:8554/common_room
|
||||
2025-01-09 00:55:13,896 [ERROR] Error in WebSocket connection: (<CloseCode.ABNORMAL_CLOSURE: 1006>, '')
|
||||
2025-01-09 00:55:13,907 [INFO] Released camera camera1
|
||||
2025-01-09 00:55:13,908 [INFO] WebSocket connection closed
|
||||
2025-01-09 00:55:13,908 [ERROR] Exception in ASGI application
|
||||
Traceback (most recent call last):
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 243, in run_asgi
|
||||
result = await self.app(self.scope, self.asgi_receive, self.asgi_send) # type: ignore[func-returns-value]
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
|
||||
return await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/fastapi/applications.py", line 1054, in __call__
|
||||
await super().__call__(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/applications.py", line 113, in __call__
|
||||
await self.middleware_stack(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/middleware/errors.py", line 152, in __call__
|
||||
await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/middleware/exceptions.py", line 62, in __call__
|
||||
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
|
||||
raise exc
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
|
||||
await app(scope, receive, sender)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 715, in __call__
|
||||
await self.middleware_stack(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 735, in app
|
||||
await route.handle(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 362, in handle
|
||||
await self.app(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 95, in app
|
||||
await wrap_app_handling_exceptions(app, session)(scope, receive, send)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
|
||||
raise exc
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
|
||||
await app(scope, receive, sender)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/routing.py", line 93, in app
|
||||
await func(session)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/fastapi/routing.py", line 383, in app
|
||||
await dependant.call(**solved_result.values)
|
||||
File "/Users/siwatsirichai/Documents/GitHub/python-detector-worker/app.py", line 111, in detect
|
||||
await websocket.close()
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/websockets.py", line 180, in close
|
||||
await self.send({"type": "websocket.close", "code": code, "reason": reason or ""})
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/websockets.py", line 85, in send
|
||||
await self._send(message)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/starlette/_exception_handler.py", line 39, in sender
|
||||
await send(message)
|
||||
File "/Users/siwatsirichai/Library/Python/3.9/lib/python/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 359, in asgi_send
|
||||
raise RuntimeError(msg % message_type)
|
||||
RuntimeError: Unexpected ASGI message 'websocket.close', after sending 'websocket.close' or response already completed.
|
||||
2025-01-09 00:55:13,943 [INFO] connection closed
|
||||
2025-01-09 00:55:14,603 [INFO] Shutting down
|
||||
2025-01-09 00:55:14,704 [INFO] Waiting for application shutdown.
|
||||
2025-01-09 00:55:14,705 [INFO] Application shutdown complete.
|
||||
2025-01-09 00:55:14,705 [INFO] Finished server process [37693]
|
||||
2025-01-09 00:55:14,721 [INFO] Stopping reloader process [37680]
|
||||
910
app.py
910
app.py
|
|
@ -1,576 +1,390 @@
|
|||
"""
|
||||
Detector Worker - Main FastAPI Application
|
||||
Refactored modular architecture for computer vision pipeline processing.
|
||||
"""
|
||||
from fastapi import FastAPI, WebSocket
|
||||
from fastapi.websockets import WebSocketDisconnect
|
||||
from websockets.exceptions import ConnectionClosedError
|
||||
from ultralytics import YOLO
|
||||
import torch
|
||||
import cv2
|
||||
import base64
|
||||
import numpy as np
|
||||
import json
|
||||
import logging
|
||||
import threading
|
||||
import queue
|
||||
import os
|
||||
import time
|
||||
import cv2
|
||||
from contextlib import asynccontextmanager
|
||||
from typing import Dict, Any
|
||||
from fastapi import FastAPI, WebSocket, HTTPException
|
||||
from fastapi.responses import Response
|
||||
import requests
|
||||
from urllib.parse import urlparse
|
||||
import asyncio
|
||||
import psutil
|
||||
|
||||
# Import new modular communication system
|
||||
from core.communication.websocket import websocket_endpoint
|
||||
from core.communication.state import worker_state
|
||||
app = FastAPI()
|
||||
|
||||
# Initialize the YOLO model with tracking
|
||||
model = YOLO("yolov8n.pt")
|
||||
if torch.cuda.is_available():
|
||||
model.to('cuda')
|
||||
model.track(
|
||||
persist=True,
|
||||
tracker="bytetrack.yaml" # You can choose a different tracker if desired
|
||||
)
|
||||
|
||||
# Retrieve class names from the model
|
||||
class_names = model.names
|
||||
|
||||
with open("config.json", "r") as f:
|
||||
config = json.load(f)
|
||||
|
||||
poll_interval = config.get("poll_interval_ms", 100)
|
||||
reconnect_interval = config.get("reconnect_interval_sec", 5) # New setting
|
||||
TARGET_FPS = config.get("target_fps", 10) # Add TARGET_FPS
|
||||
poll_interval = 1000 / TARGET_FPS # Adjust poll_interval based on TARGET_FPS
|
||||
logging.info(f"Poll interval: {poll_interval}ms")
|
||||
max_streams = config.get("max_streams", 5)
|
||||
max_retries = config.get("max_retries", 3)
|
||||
|
||||
# Configure logging
|
||||
logging.basicConfig(
|
||||
level=logging.DEBUG,
|
||||
format="%(asctime)s [%(levelname)s] %(name)s: %(message)s",
|
||||
level=logging.INFO,
|
||||
format="%(asctime)s [%(levelname)s] %(message)s",
|
||||
handlers=[
|
||||
logging.FileHandler("detector_worker.log"),
|
||||
logging.FileHandler("app.log"),
|
||||
logging.StreamHandler()
|
||||
]
|
||||
)
|
||||
|
||||
logger = logging.getLogger("detector_worker")
|
||||
logger.setLevel(logging.DEBUG)
|
||||
|
||||
# Frames are now stored in the shared cache buffer from core.streaming.buffers
|
||||
# latest_frames = {} # Deprecated - using shared_cache_buffer instead
|
||||
|
||||
|
||||
# Health monitoring recovery handlers
|
||||
def _handle_stream_restart_recovery(component: str, details: Dict[str, Any]) -> bool:
|
||||
"""Handle stream restart recovery at the application level."""
|
||||
try:
|
||||
from core.streaming.manager import shared_stream_manager
|
||||
|
||||
# Extract camera ID from component name (e.g., "stream_cam-001" -> "cam-001")
|
||||
if component.startswith("stream_"):
|
||||
camera_id = component[7:] # Remove "stream_" prefix
|
||||
else:
|
||||
camera_id = component
|
||||
|
||||
logger.info(f"Attempting stream restart recovery for {camera_id}")
|
||||
|
||||
# Find and restart the subscription
|
||||
subscriptions = shared_stream_manager.get_all_subscriptions()
|
||||
for sub_info in subscriptions:
|
||||
if sub_info.camera_id == camera_id:
|
||||
# Remove and re-add the subscription
|
||||
shared_stream_manager.remove_subscription(sub_info.subscription_id)
|
||||
time.sleep(1.0) # Brief delay
|
||||
|
||||
# Re-add subscription
|
||||
success = shared_stream_manager.add_subscription(
|
||||
sub_info.subscription_id,
|
||||
sub_info.stream_config,
|
||||
sub_info.crop_coords,
|
||||
sub_info.model_id,
|
||||
sub_info.model_url,
|
||||
sub_info.tracking_integration
|
||||
)
|
||||
|
||||
if success:
|
||||
logger.info(f"Stream restart recovery successful for {camera_id}")
|
||||
return True
|
||||
else:
|
||||
logger.error(f"Stream restart recovery failed for {camera_id}")
|
||||
return False
|
||||
|
||||
logger.warning(f"No subscription found for camera {camera_id} during recovery")
|
||||
return False
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in stream restart recovery for {component}: {e}")
|
||||
return False
|
||||
|
||||
|
||||
def _handle_stream_reconnect_recovery(component: str, details: Dict[str, Any]) -> bool:
|
||||
"""Handle stream reconnect recovery at the application level."""
|
||||
try:
|
||||
from core.streaming.manager import shared_stream_manager
|
||||
|
||||
# Extract camera ID from component name
|
||||
if component.startswith("stream_"):
|
||||
camera_id = component[7:]
|
||||
else:
|
||||
camera_id = component
|
||||
|
||||
logger.info(f"Attempting stream reconnect recovery for {camera_id}")
|
||||
|
||||
# For reconnect, we just need to trigger the stream's internal reconnect
|
||||
# The stream readers handle their own reconnection logic
|
||||
active_cameras = shared_stream_manager.get_active_cameras()
|
||||
|
||||
if camera_id in active_cameras:
|
||||
logger.info(f"Stream reconnect recovery triggered for {camera_id}")
|
||||
return True
|
||||
else:
|
||||
logger.warning(f"Camera {camera_id} not found in active cameras during reconnect recovery")
|
||||
return False
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in stream reconnect recovery for {component}: {e}")
|
||||
return False
|
||||
|
||||
# Lifespan event handler (modern FastAPI approach)
|
||||
@asynccontextmanager
|
||||
async def lifespan(app: FastAPI):
|
||||
"""Application lifespan management."""
|
||||
# Startup
|
||||
logger.info("Detector Worker started successfully")
|
||||
|
||||
# Initialize health monitoring system
|
||||
try:
|
||||
from core.monitoring.health import health_monitor
|
||||
from core.monitoring.stream_health import stream_health_tracker
|
||||
from core.monitoring.thread_health import thread_health_monitor
|
||||
from core.monitoring.recovery import recovery_manager
|
||||
|
||||
# Start health monitoring
|
||||
health_monitor.start()
|
||||
logger.info("Health monitoring system started")
|
||||
|
||||
# Register recovery handlers for stream management
|
||||
from core.streaming.manager import shared_stream_manager
|
||||
recovery_manager.register_recovery_handler(
|
||||
"restart_stream",
|
||||
_handle_stream_restart_recovery
|
||||
)
|
||||
recovery_manager.register_recovery_handler(
|
||||
"reconnect",
|
||||
_handle_stream_reconnect_recovery
|
||||
)
|
||||
|
||||
logger.info("Recovery handlers registered")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to initialize health monitoring: {e}")
|
||||
|
||||
logger.info("WebSocket endpoint available at: ws://0.0.0.0:8001/")
|
||||
logger.info("HTTP camera endpoint available at: http://0.0.0.0:8001/camera/{camera_id}/image")
|
||||
logger.info("Health check available at: http://0.0.0.0:8001/health")
|
||||
logger.info("Detailed health monitoring available at: http://0.0.0.0:8001/health/detailed")
|
||||
logger.info("Ready and waiting for backend WebSocket connections")
|
||||
|
||||
yield
|
||||
|
||||
# Shutdown
|
||||
logger.info("Detector Worker shutting down...")
|
||||
|
||||
# Stop health monitoring
|
||||
try:
|
||||
from core.monitoring.health import health_monitor
|
||||
health_monitor.stop()
|
||||
logger.info("Health monitoring system stopped")
|
||||
except Exception as e:
|
||||
logger.error(f"Error stopping health monitoring: {e}")
|
||||
|
||||
# Clear all state
|
||||
worker_state.set_subscriptions([])
|
||||
worker_state.session_ids.clear()
|
||||
worker_state.progression_stages.clear()
|
||||
# latest_frames.clear() # No longer needed - frames are in shared_cache_buffer
|
||||
logger.info("Detector Worker shutdown complete")
|
||||
|
||||
# Create FastAPI application with detailed WebSocket logging
|
||||
app = FastAPI(title="Detector Worker", version="2.0.0", lifespan=lifespan)
|
||||
|
||||
# Add middleware to log all requests
|
||||
@app.middleware("http")
|
||||
async def log_requests(request, call_next):
|
||||
start_time = time.time()
|
||||
response = await call_next(request)
|
||||
process_time = time.time() - start_time
|
||||
logger.debug(f"HTTP {request.method} {request.url} - {response.status_code} ({process_time:.3f}s)")
|
||||
return response
|
||||
|
||||
# Load configuration
|
||||
config_path = "config.json"
|
||||
if os.path.exists(config_path):
|
||||
with open(config_path, "r") as f:
|
||||
config = json.load(f)
|
||||
logger.info(f"Loaded configuration from {config_path}")
|
||||
else:
|
||||
# Default configuration
|
||||
config = {
|
||||
"poll_interval_ms": 100,
|
||||
"reconnect_interval_sec": 5,
|
||||
"target_fps": 10,
|
||||
"max_streams": 20,
|
||||
"max_retries": 3
|
||||
}
|
||||
logger.warning(f"Configuration file {config_path} not found, using defaults")
|
||||
|
||||
# Ensure models directory exists
|
||||
# Ensure the models directory exists
|
||||
os.makedirs("models", exist_ok=True)
|
||||
logger.info("Ensured models directory exists")
|
||||
|
||||
# Stream manager already initialized at module level with max_streams=20
|
||||
# Calling initialize_stream_manager() creates a NEW instance, breaking references
|
||||
# from core.streaming import initialize_stream_manager
|
||||
# initialize_stream_manager(max_streams=config.get('max_streams', 10))
|
||||
logger.info(f"Using stream manager with max_streams=20 (module-level initialization)")
|
||||
|
||||
# Frames are now stored in the shared cache buffer from core.streaming.buffers
|
||||
# latest_frames = {} # Deprecated - using shared_cache_buffer instead
|
||||
|
||||
logger.info("Starting detector worker application (refactored)")
|
||||
logger.info(f"Configuration: Target FPS: {config.get('target_fps', 10)}, "
|
||||
f"Max streams: {config.get('max_streams', 5)}, "
|
||||
f"Max retries: {config.get('max_retries', 3)}")
|
||||
|
||||
# Add constants for heartbeat
|
||||
HEARTBEAT_INTERVAL = 2 # seconds
|
||||
WORKER_TIMEOUT_MS = 10000
|
||||
|
||||
@app.websocket("/")
|
||||
async def websocket_handler(websocket: WebSocket):
|
||||
"""
|
||||
Main WebSocket endpoint for backend communication.
|
||||
Handles all protocol messages according to worker.md specification.
|
||||
"""
|
||||
client_info = f"{websocket.client.host}:{websocket.client.port}" if websocket.client else "unknown"
|
||||
logger.info(f"[RX ← Backend] New WebSocket connection request from {client_info}")
|
||||
async def detect(websocket: WebSocket):
|
||||
import asyncio
|
||||
import time
|
||||
|
||||
try:
|
||||
await websocket_endpoint(websocket)
|
||||
except Exception as e:
|
||||
logger.error(f"WebSocket handler error for {client_info}: {e}", exc_info=True)
|
||||
logging.info("WebSocket connection accepted")
|
||||
|
||||
streams = {}
|
||||
|
||||
@app.get("/camera/{camera_id}/image")
|
||||
async def get_camera_image(camera_id: str):
|
||||
"""
|
||||
HTTP endpoint to retrieve the latest frame from a camera as JPEG image.
|
||||
def frame_reader(camera_id, cap, buffer, stop_event):
|
||||
import time
|
||||
retries = 0
|
||||
while not stop_event.is_set():
|
||||
try:
|
||||
ret, frame = cap.read()
|
||||
if not ret:
|
||||
logging.warning(f"Connection lost for camera: {camera_id}, retry {retries+1}/{max_retries}")
|
||||
cap.release()
|
||||
time.sleep(reconnect_interval)
|
||||
retries += 1
|
||||
if retries > max_retries:
|
||||
logging.error(f"Max retries reached for camera: {camera_id}")
|
||||
break
|
||||
# Re-open the VideoCapture
|
||||
cap = cv2.VideoCapture(streams[camera_id]['rtsp_url'])
|
||||
if not cap.isOpened():
|
||||
logging.error(f"Failed to reopen RTSP stream for camera: {camera_id}")
|
||||
continue
|
||||
continue
|
||||
retries = 0 # Reset on success
|
||||
if not buffer.empty():
|
||||
try:
|
||||
buffer.get_nowait() # Discard the old frame
|
||||
except queue.Empty:
|
||||
pass
|
||||
buffer.put(frame)
|
||||
except cv2.error as e:
|
||||
logging.error(f"OpenCV error for camera {camera_id}: {e}")
|
||||
cap.release()
|
||||
time.sleep(reconnect_interval)
|
||||
retries += 1
|
||||
if retries > max_retries and max_retries != -1:
|
||||
logging.error(f"Max retries reached after OpenCV error for camera: {camera_id}")
|
||||
break
|
||||
# Re-open the VideoCapture
|
||||
cap = cv2.VideoCapture(streams[camera_id]['rtsp_url'])
|
||||
if not cap.isOpened():
|
||||
logging.error(f"Failed to reopen RTSP stream for camera {camera_id} after OpenCV error")
|
||||
continue
|
||||
except Exception as e:
|
||||
logging.error(f"Unexpected error for camera {camera_id}: {e}")
|
||||
cap.release()
|
||||
break
|
||||
|
||||
This endpoint is preserved for backward compatibility with existing systems.
|
||||
|
||||
Args:
|
||||
camera_id: The subscription identifier (e.g., "display-001;cam-001")
|
||||
|
||||
Returns:
|
||||
JPEG image as binary response
|
||||
|
||||
Raises:
|
||||
HTTPException: 404 if camera not found or no frame available
|
||||
HTTPException: 500 if encoding fails
|
||||
"""
|
||||
try:
|
||||
from urllib.parse import unquote
|
||||
|
||||
# URL decode the camera_id to handle encoded characters
|
||||
original_camera_id = camera_id
|
||||
camera_id = unquote(camera_id)
|
||||
logger.debug(f"REST API request: original='{original_camera_id}', decoded='{camera_id}'")
|
||||
|
||||
# Check if camera is in active subscriptions
|
||||
subscription = worker_state.get_subscription(camera_id)
|
||||
if not subscription:
|
||||
logger.warning(f"Camera ID '{camera_id}' not found in active subscriptions")
|
||||
available_cameras = list(worker_state.subscriptions.keys())
|
||||
logger.debug(f"Available cameras: {available_cameras}")
|
||||
raise HTTPException(
|
||||
status_code=404,
|
||||
detail=f"Camera {camera_id} not found or not active"
|
||||
)
|
||||
|
||||
# Extract actual camera_id from subscription identifier (displayId;cameraId)
|
||||
# Frames are stored using just the camera_id part
|
||||
actual_camera_id = camera_id.split(';')[-1] if ';' in camera_id else camera_id
|
||||
|
||||
# Get frame from the shared cache buffer
|
||||
from core.streaming.buffers import shared_cache_buffer
|
||||
|
||||
# Only show buffer debug info if camera not found (to reduce log spam)
|
||||
available_cameras = shared_cache_buffer.frame_buffer.get_camera_list()
|
||||
|
||||
frame = shared_cache_buffer.get_frame(actual_camera_id)
|
||||
if frame is None:
|
||||
logger.warning(f"\033[93m[API] No frame for '{actual_camera_id}' - Available: {available_cameras}\033[0m")
|
||||
raise HTTPException(
|
||||
status_code=404,
|
||||
detail=f"No frame available for camera {actual_camera_id}"
|
||||
)
|
||||
|
||||
# Successful frame retrieval - log only occasionally to avoid spam
|
||||
|
||||
# Encode frame as JPEG
|
||||
success, buffer_img = cv2.imencode('.jpg', frame, [cv2.IMWRITE_JPEG_QUALITY, 85])
|
||||
if not success:
|
||||
raise HTTPException(status_code=500, detail="Failed to encode image as JPEG")
|
||||
|
||||
# Return image as binary response
|
||||
return Response(content=buffer_img.tobytes(), media_type="image/jpeg")
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Error retrieving image for camera {camera_id}: {str(e)}", exc_info=True)
|
||||
raise HTTPException(status_code=500, detail=f"Internal server error: {str(e)}")
|
||||
|
||||
|
||||
@app.get("/session-image/{session_id}")
|
||||
async def get_session_image(session_id: int):
|
||||
"""
|
||||
HTTP endpoint to retrieve the saved session image by session ID.
|
||||
|
||||
Args:
|
||||
session_id: The session ID to retrieve the image for
|
||||
|
||||
Returns:
|
||||
JPEG image as binary response
|
||||
|
||||
Raises:
|
||||
HTTPException: 404 if no image found for the session
|
||||
HTTPException: 500 if reading image fails
|
||||
"""
|
||||
try:
|
||||
from pathlib import Path
|
||||
import glob
|
||||
|
||||
# Images directory
|
||||
images_dir = Path("images")
|
||||
|
||||
if not images_dir.exists():
|
||||
logger.warning(f"Images directory does not exist")
|
||||
raise HTTPException(
|
||||
status_code=404,
|
||||
detail=f"No images directory found"
|
||||
)
|
||||
|
||||
# Search for files matching session ID pattern: {session_id}_*
|
||||
pattern = str(images_dir / f"{session_id}_*.jpg")
|
||||
matching_files = glob.glob(pattern)
|
||||
|
||||
if not matching_files:
|
||||
logger.warning(f"No image found for session {session_id}")
|
||||
raise HTTPException(
|
||||
status_code=404,
|
||||
detail=f"No image found for session {session_id}"
|
||||
)
|
||||
|
||||
# Get the most recent file if multiple exist
|
||||
most_recent_file = max(matching_files, key=os.path.getmtime)
|
||||
logger.info(f"Found session image for session {session_id}: {most_recent_file}")
|
||||
|
||||
# Read the image file
|
||||
image_data = open(most_recent_file, 'rb').read()
|
||||
|
||||
# Return image as binary response
|
||||
return Response(content=image_data, media_type="image/jpeg")
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Error retrieving session image for session {session_id}: {str(e)}", exc_info=True)
|
||||
raise HTTPException(status_code=500, detail=f"Internal server error: {str(e)}")
|
||||
|
||||
|
||||
@app.get("/health")
|
||||
async def health_check():
|
||||
"""Health check endpoint for monitoring."""
|
||||
return {
|
||||
"status": "healthy",
|
||||
"version": "2.0.0",
|
||||
"active_subscriptions": len(worker_state.subscriptions),
|
||||
"active_sessions": len(worker_state.session_ids)
|
||||
}
|
||||
|
||||
|
||||
@app.get("/health/detailed")
|
||||
async def detailed_health_check():
|
||||
"""Comprehensive health status with detailed monitoring data."""
|
||||
try:
|
||||
from core.monitoring.health import health_monitor
|
||||
from core.monitoring.stream_health import stream_health_tracker
|
||||
from core.monitoring.thread_health import thread_health_monitor
|
||||
from core.monitoring.recovery import recovery_manager
|
||||
|
||||
# Get comprehensive health status
|
||||
overall_health = health_monitor.get_health_status()
|
||||
stream_metrics = stream_health_tracker.get_all_metrics()
|
||||
thread_info = thread_health_monitor.get_all_thread_info()
|
||||
recovery_stats = recovery_manager.get_recovery_stats()
|
||||
|
||||
return {
|
||||
"timestamp": time.time(),
|
||||
"overall_health": overall_health,
|
||||
"stream_metrics": stream_metrics,
|
||||
"thread_health": thread_info,
|
||||
"recovery_stats": recovery_stats,
|
||||
"system_info": {
|
||||
"active_subscriptions": len(worker_state.subscriptions),
|
||||
"active_sessions": len(worker_state.session_ids),
|
||||
"version": "2.0.0"
|
||||
}
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error generating detailed health report: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"Health monitoring error: {str(e)}")
|
||||
|
||||
|
||||
@app.get("/health/streams")
|
||||
async def stream_health_status():
|
||||
"""Stream-specific health monitoring."""
|
||||
try:
|
||||
from core.monitoring.stream_health import stream_health_tracker
|
||||
from core.streaming.buffers import shared_cache_buffer
|
||||
|
||||
stream_metrics = stream_health_tracker.get_all_metrics()
|
||||
buffer_stats = shared_cache_buffer.get_stats()
|
||||
|
||||
return {
|
||||
"timestamp": time.time(),
|
||||
"stream_count": len(stream_metrics),
|
||||
"stream_metrics": stream_metrics,
|
||||
"buffer_stats": buffer_stats,
|
||||
"frame_ages": {
|
||||
camera_id: {
|
||||
"age_seconds": time.time() - info["last_frame_time"] if info and info.get("last_frame_time") else None,
|
||||
"total_frames": info.get("frame_count", 0) if info else 0
|
||||
}
|
||||
for camera_id, info in stream_metrics.items()
|
||||
}
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error generating stream health report: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"Stream health error: {str(e)}")
|
||||
|
||||
|
||||
@app.get("/health/threads")
|
||||
async def thread_health_status():
|
||||
"""Thread-specific health monitoring."""
|
||||
try:
|
||||
from core.monitoring.thread_health import thread_health_monitor
|
||||
|
||||
thread_info = thread_health_monitor.get_all_thread_info()
|
||||
deadlocks = thread_health_monitor.detect_deadlocks()
|
||||
|
||||
return {
|
||||
"timestamp": time.time(),
|
||||
"thread_count": len(thread_info),
|
||||
"thread_info": thread_info,
|
||||
"potential_deadlocks": deadlocks,
|
||||
"summary": {
|
||||
"responsive_threads": sum(1 for info in thread_info.values() if info.get("is_responsive", False)),
|
||||
"unresponsive_threads": sum(1 for info in thread_info.values() if not info.get("is_responsive", True)),
|
||||
"deadlock_count": len(deadlocks)
|
||||
}
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error generating thread health report: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"Thread health error: {str(e)}")
|
||||
|
||||
|
||||
@app.get("/health/recovery")
|
||||
async def recovery_status():
|
||||
"""Recovery system status and history."""
|
||||
try:
|
||||
from core.monitoring.recovery import recovery_manager
|
||||
|
||||
recovery_stats = recovery_manager.get_recovery_stats()
|
||||
|
||||
return {
|
||||
"timestamp": time.time(),
|
||||
"recovery_stats": recovery_stats,
|
||||
"summary": {
|
||||
"total_recoveries_last_hour": recovery_stats.get("total_recoveries_last_hour", 0),
|
||||
"components_with_recovery_state": len(recovery_stats.get("recovery_states", {})),
|
||||
"total_recovery_failures": sum(
|
||||
state.get("failure_count", 0)
|
||||
for state in recovery_stats.get("recovery_states", {}).values()
|
||||
),
|
||||
"total_recovery_successes": sum(
|
||||
state.get("success_count", 0)
|
||||
for state in recovery_stats.get("recovery_states", {}).values()
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error generating recovery status report: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"Recovery status error: {str(e)}")
|
||||
|
||||
|
||||
@app.post("/health/recovery/force/{component}")
|
||||
async def force_recovery(component: str, action: str = "restart_stream"):
|
||||
"""Force recovery action for a specific component."""
|
||||
try:
|
||||
from core.monitoring.recovery import recovery_manager, RecoveryAction
|
||||
|
||||
# Validate action
|
||||
async def process_streams():
|
||||
global model, class_names # Added line
|
||||
logging.info("Started processing streams")
|
||||
try:
|
||||
recovery_action = RecoveryAction(action)
|
||||
except ValueError:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"Invalid recovery action: {action}. Valid actions: {[a.value for a in RecoveryAction]}"
|
||||
)
|
||||
while True:
|
||||
start_time = time.time()
|
||||
# Round-robin processing
|
||||
for camera_id, stream in list(streams.items()):
|
||||
buffer = stream['buffer']
|
||||
if not buffer.empty():
|
||||
frame = buffer.get()
|
||||
results = model.track(frame, stream=False) # Updated for tracking
|
||||
boxes = []
|
||||
for r in results:
|
||||
for track in r.tracks:
|
||||
if not track.is_confirmed():
|
||||
continue
|
||||
track_id = track.track_id
|
||||
cls = int(track.cls)
|
||||
boxes.append({
|
||||
"class": class_names[cls],
|
||||
"confidence": float(track.conf),
|
||||
"track_id": track_id # Added track ID
|
||||
})
|
||||
# Broadcast to all subscribers of this URL
|
||||
detection_data = {
|
||||
"type": "imageDetection",
|
||||
"cameraIdentifier": camera_id,
|
||||
"timestamp": time.time(),
|
||||
"data": {
|
||||
"detections": boxes,
|
||||
"modelId": stream['modelId'],
|
||||
"modelName": stream['modelName']
|
||||
}
|
||||
}
|
||||
logging.debug(f"Sending detection data for camera {camera_id}: {detection_data}")
|
||||
await websocket.send_json(detection_data)
|
||||
elapsed_time = (time.time() - start_time) * 1000 # in ms
|
||||
sleep_time = max(poll_interval - elapsed_time, 0)
|
||||
logging.debug(f"Elapsed time: {elapsed_time}ms, sleeping for: {sleep_time}ms")
|
||||
await asyncio.sleep(sleep_time / 1000.0)
|
||||
except asyncio.CancelledError:
|
||||
logging.info("Stream processing task cancelled")
|
||||
except Exception as e:
|
||||
logging.error(f"Error in process_streams: {e}")
|
||||
|
||||
# Force recovery
|
||||
success = recovery_manager.force_recovery(component, recovery_action, "manual_api_request")
|
||||
async def send_heartbeat():
|
||||
while True:
|
||||
try:
|
||||
cpu_usage = psutil.cpu_percent()
|
||||
memory_usage = psutil.virtual_memory().percent
|
||||
if torch.cuda.is_available():
|
||||
gpu_usage = torch.cuda.memory_allocated() / (1024 ** 2) # Convert to MB
|
||||
gpu_memory_usage = torch.cuda.memory_reserved() / (1024 ** 2) # Convert to MB
|
||||
else:
|
||||
gpu_usage = None
|
||||
gpu_memory_usage = None
|
||||
|
||||
camera_connections = [
|
||||
{
|
||||
"cameraIdentifier": camera_id,
|
||||
"modelId": stream['modelId'],
|
||||
"modelName": stream['modelName'],
|
||||
"online": True
|
||||
}
|
||||
for camera_id, stream in streams.items()
|
||||
]
|
||||
|
||||
state_report = {
|
||||
"type": "stateReport",
|
||||
"cpuUsage": cpu_usage,
|
||||
"memoryUsage": memory_usage,
|
||||
"gpuUsage": gpu_usage,
|
||||
"gpuMemoryUsage": gpu_memory_usage,
|
||||
"cameraConnections": camera_connections
|
||||
}
|
||||
await websocket.send_text(json.dumps(state_report))
|
||||
logging.debug("Sent stateReport as heartbeat")
|
||||
await asyncio.sleep(HEARTBEAT_INTERVAL)
|
||||
except Exception as e:
|
||||
logging.error(f"Error sending stateReport heartbeat: {e}")
|
||||
break
|
||||
|
||||
return {
|
||||
"timestamp": time.time(),
|
||||
"component": component,
|
||||
"action": action,
|
||||
"success": success,
|
||||
"message": f"Recovery {'successful' if success else 'failed'} for component {component}"
|
||||
}
|
||||
async def on_message():
|
||||
global model, class_names # Changed from nonlocal to global
|
||||
while True:
|
||||
msg = await websocket.receive_text()
|
||||
logging.debug(f"Received message: {msg}")
|
||||
data = json.loads(msg)
|
||||
msg_type = data.get("type")
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Error forcing recovery for {component}: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"Recovery error: {str(e)}")
|
||||
if msg_type == "subscribe":
|
||||
payload = data.get("payload", {})
|
||||
camera_id = payload.get("cameraIdentifier")
|
||||
rtsp_url = payload.get("rtspUrl")
|
||||
model_url = payload.get("modelUrl")
|
||||
modelId = payload.get("modelId")
|
||||
modelName = payload.get("modelName")
|
||||
|
||||
if model_url:
|
||||
print(f"Downloading model from {model_url}")
|
||||
parsed_url = urlparse(model_url)
|
||||
filename = os.path.basename(parsed_url.path)
|
||||
model_filename = os.path.join("models", filename)
|
||||
# Download the model
|
||||
response = requests.get(model_url, stream=True)
|
||||
if response.status_code == 200:
|
||||
with open(model_filename, 'wb') as f:
|
||||
for chunk in response.iter_content(chunk_size=8192):
|
||||
f.write(chunk)
|
||||
logging.info(f"Downloaded model from {model_url} to {model_filename}")
|
||||
model = YOLO(model_filename)
|
||||
if torch.cuda.is_available():
|
||||
model.to('cuda')
|
||||
class_names = model.names
|
||||
else:
|
||||
logging.error(f"Failed to download model from {model_url}")
|
||||
continue
|
||||
if camera_id and rtsp_url:
|
||||
if camera_id not in streams and len(streams) < max_streams:
|
||||
cap = cv2.VideoCapture(rtsp_url)
|
||||
if not cap.isOpened():
|
||||
logging.error(f"Failed to open RTSP stream for camera {camera_id}")
|
||||
continue
|
||||
buffer = queue.Queue(maxsize=1)
|
||||
stop_event = threading.Event()
|
||||
thread = threading.Thread(target=frame_reader, args=(camera_id, cap, buffer, stop_event))
|
||||
thread.daemon = True
|
||||
thread.start()
|
||||
streams[camera_id] = {
|
||||
'cap': cap,
|
||||
'buffer': buffer,
|
||||
'thread': thread,
|
||||
'rtsp_url': rtsp_url,
|
||||
'stop_event': stop_event,
|
||||
'modelId': modelId,
|
||||
'modelName': modelName
|
||||
}
|
||||
logging.info(f"Subscribed to camera {camera_id} with modelId {modelId}, modelName {modelName} and URL {rtsp_url}")
|
||||
elif camera_id and camera_id in streams:
|
||||
stream = streams.pop(camera_id)
|
||||
stream['cap'].release()
|
||||
logging.info(f"Unsubscribed from camera {camera_id}")
|
||||
elif msg_type == "unsubscribe":
|
||||
payload = data.get("payload", {})
|
||||
camera_id = payload.get("cameraIdentifier")
|
||||
if camera_id and camera_id in streams:
|
||||
stream = streams.pop(camera_id)
|
||||
stream['cap'].release()
|
||||
logging.info(f"Unsubscribed from camera {camera_id}")
|
||||
elif msg_type == "requestState":
|
||||
# Handle state request
|
||||
cpu_usage = psutil.cpu_percent()
|
||||
memory_usage = psutil.virtual_memory().percent
|
||||
if torch.cuda.is_available():
|
||||
gpu_usage = torch.cuda.memory_allocated() / (1024 ** 2) # Convert to MB
|
||||
gpu_memory_usage = torch.cuda.memory_reserved() / (1024 ** 2) # Convert to MB
|
||||
else:
|
||||
gpu_usage = None
|
||||
gpu_memory_usage = None
|
||||
|
||||
camera_connections = [
|
||||
{
|
||||
"cameraIdentifier": camera_id,
|
||||
"modelId": stream['modelId'],
|
||||
"modelName": stream['modelName'],
|
||||
"online": True
|
||||
}
|
||||
for camera_id, stream in streams.items()
|
||||
]
|
||||
|
||||
state_report = {
|
||||
"type": "stateReport",
|
||||
"cpuUsage": cpu_usage,
|
||||
"memoryUsage": memory_usage,
|
||||
"gpuUsage": gpu_usage,
|
||||
"gpuMemoryUsage": gpu_memory_usage,
|
||||
"cameraConnections": camera_connections
|
||||
}
|
||||
await websocket.send_text(json.dumps(state_report))
|
||||
else:
|
||||
logging.error(f"Unknown message type: {msg_type}")
|
||||
|
||||
await websocket.accept()
|
||||
task = asyncio.create_task(process_streams())
|
||||
heartbeat_task = asyncio.create_task(send_heartbeat())
|
||||
message_task = asyncio.create_task(on_message())
|
||||
|
||||
await asyncio.gather(heartbeat_task, message_task)
|
||||
|
||||
model = None
|
||||
model_path = None
|
||||
|
||||
@app.get("/health/metrics")
|
||||
async def health_metrics():
|
||||
"""Performance and health metrics in a format suitable for monitoring systems."""
|
||||
try:
|
||||
from core.monitoring.health import health_monitor
|
||||
from core.monitoring.stream_health import stream_health_tracker
|
||||
from core.streaming.buffers import shared_cache_buffer
|
||||
|
||||
# Get basic metrics
|
||||
overall_health = health_monitor.get_health_status()
|
||||
stream_metrics = stream_health_tracker.get_all_metrics()
|
||||
buffer_stats = shared_cache_buffer.get_stats()
|
||||
|
||||
# Format for monitoring systems (Prometheus-style)
|
||||
metrics = {
|
||||
"detector_worker_up": 1,
|
||||
"detector_worker_streams_total": len(stream_metrics),
|
||||
"detector_worker_subscriptions_total": len(worker_state.subscriptions),
|
||||
"detector_worker_sessions_total": len(worker_state.session_ids),
|
||||
"detector_worker_memory_mb": buffer_stats.get("total_memory_mb", 0),
|
||||
"detector_worker_health_status": {
|
||||
"healthy": 1,
|
||||
"warning": 2,
|
||||
"critical": 3,
|
||||
"unknown": 4
|
||||
}.get(overall_health.get("overall_status", "unknown"), 4)
|
||||
}
|
||||
|
||||
# Add per-stream metrics
|
||||
for camera_id, stream_info in stream_metrics.items():
|
||||
safe_camera_id = camera_id.replace("-", "_").replace(".", "_")
|
||||
metrics.update({
|
||||
f"detector_worker_stream_frames_total{{camera=\"{safe_camera_id}\"}}": stream_info.get("frame_count", 0),
|
||||
f"detector_worker_stream_errors_total{{camera=\"{safe_camera_id}\"}}": stream_info.get("error_count", 0),
|
||||
f"detector_worker_stream_fps{{camera=\"{safe_camera_id}\"}}": stream_info.get("frames_per_second", 0),
|
||||
f"detector_worker_stream_frame_age_seconds{{camera=\"{safe_camera_id}\"}}": stream_info.get("last_frame_age_seconds") or 0
|
||||
})
|
||||
|
||||
return {
|
||||
"timestamp": time.time(),
|
||||
"metrics": metrics
|
||||
}
|
||||
|
||||
while True:
|
||||
try:
|
||||
msg = await websocket.receive_text()
|
||||
logging.debug(f"Received message: {msg}")
|
||||
data = json.loads(msg)
|
||||
camera_id = data.get("cameraIdentifier")
|
||||
rtsp_url = data.get("rtspUrl")
|
||||
model_url = data.get("modelUrl")
|
||||
modelId = data.get("modelId")
|
||||
modelName = data.get("modelName")
|
||||
|
||||
if model_url:
|
||||
print(f"Downloading model from {model_url}")
|
||||
parsed_url = urlparse(model_url)
|
||||
filename = os.path.basename(parsed_url.path)
|
||||
model_filename = os.path.join("models", filename)
|
||||
# Download the model
|
||||
response = requests.get(model_url, stream=True)
|
||||
if response.status_code == 200:
|
||||
with open(model_filename, 'wb') as f:
|
||||
for chunk in response.iter_content(chunk_size=8192):
|
||||
f.write(chunk)
|
||||
logging.info(f"Downloaded model from {model_url} to {model_filename}")
|
||||
model = YOLO(model_filename)
|
||||
if torch.cuda.is_available():
|
||||
model.to('cuda')
|
||||
class_names = model.names
|
||||
else:
|
||||
logging.error(f"Failed to download model from {model_url}")
|
||||
continue
|
||||
if camera_id and rtsp_url:
|
||||
if camera_id not in streams and len(streams) < max_streams:
|
||||
cap = cv2.VideoCapture(rtsp_url)
|
||||
if not cap.isOpened():
|
||||
logging.error(f"Failed to open RTSP stream for camera {camera_id}")
|
||||
continue
|
||||
buffer = queue.Queue(maxsize=1)
|
||||
stop_event = threading.Event()
|
||||
thread = threading.Thread(target=frame_reader, args=(camera_id, cap, buffer, stop_event))
|
||||
thread.daemon = True
|
||||
thread.start()
|
||||
streams[camera_id] = {
|
||||
'cap': cap,
|
||||
'buffer': buffer,
|
||||
'thread': thread,
|
||||
'rtsp_url': rtsp_url,
|
||||
'stop_event': stop_event,
|
||||
'modelId': modelId,
|
||||
'modelName': modelName
|
||||
}
|
||||
logging.info(f"Subscribed to camera {camera_id} with modelId {modelId}, modelName {modelName} and URL {rtsp_url}")
|
||||
elif camera_id and camera_id in streams:
|
||||
stream = streams.pop(camera_id)
|
||||
stream['cap'].release()
|
||||
logging.info(f"Unsubscribed from camera {camera_id}")
|
||||
elif data.get("command") == "stop":
|
||||
logging.info("Received stop command")
|
||||
break
|
||||
except json.JSONDecodeError:
|
||||
logging.error("Received invalid JSON message")
|
||||
except (WebSocketDisconnect, ConnectionClosedError) as e:
|
||||
logging.warning(f"WebSocket disconnected: {e}")
|
||||
break
|
||||
except Exception as e:
|
||||
logging.error(f"Error handling message: {e}")
|
||||
break
|
||||
except Exception as e:
|
||||
logger.error(f"Error generating health metrics: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"Metrics error: {str(e)}")
|
||||
|
||||
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import uvicorn
|
||||
uvicorn.run(app, host="0.0.0.0", port=8001)
|
||||
logging.error(f"Unexpected error in WebSocket connection: {e}")
|
||||
finally:
|
||||
task.cancel()
|
||||
await task
|
||||
for camera_id, stream in streams.items():
|
||||
stream['stop_event'].set()
|
||||
stream['thread'].join()
|
||||
stream['cap'].release()
|
||||
stream['buffer'].queue.clear()
|
||||
logging.info(f"Released camera {camera_id} and cleaned up resources")
|
||||
streams.clear()
|
||||
if model_path and os.path.exists(model_path):
|
||||
os.remove(model_path)
|
||||
logging.info(f"Deleted model file {model_path}")
|
||||
logging.info("WebSocket connection closed")
|
||||
|
|
|
|||
903
archive/app.py
903
archive/app.py
|
|
@ -1,903 +0,0 @@
|
|||
from typing import Any, Dict
|
||||
import os
|
||||
import json
|
||||
import time
|
||||
import queue
|
||||
import torch
|
||||
import cv2
|
||||
import numpy as np
|
||||
import base64
|
||||
import logging
|
||||
import threading
|
||||
import requests
|
||||
import asyncio
|
||||
import psutil
|
||||
import zipfile
|
||||
from urllib.parse import urlparse
|
||||
from fastapi import FastAPI, WebSocket, HTTPException
|
||||
from fastapi.websockets import WebSocketDisconnect
|
||||
from fastapi.responses import Response
|
||||
from websockets.exceptions import ConnectionClosedError
|
||||
from ultralytics import YOLO
|
||||
|
||||
# Import shared pipeline functions
|
||||
from siwatsystem.pympta import load_pipeline_from_zip, run_pipeline
|
||||
|
||||
app = FastAPI()
|
||||
|
||||
# Global dictionaries to keep track of models and streams
|
||||
# "models" now holds a nested dict: { camera_id: { modelId: model_tree } }
|
||||
models: Dict[str, Dict[str, Any]] = {}
|
||||
streams: Dict[str, Dict[str, Any]] = {}
|
||||
# Store session IDs per display
|
||||
session_ids: Dict[str, int] = {}
|
||||
# Track shared camera streams by camera URL
|
||||
camera_streams: Dict[str, Dict[str, Any]] = {}
|
||||
# Map subscriptions to their camera URL
|
||||
subscription_to_camera: Dict[str, str] = {}
|
||||
# Store latest frames for REST API access (separate from processing buffer)
|
||||
latest_frames: Dict[str, Any] = {}
|
||||
|
||||
with open("config.json", "r") as f:
|
||||
config = json.load(f)
|
||||
|
||||
poll_interval = config.get("poll_interval_ms", 100)
|
||||
reconnect_interval = config.get("reconnect_interval_sec", 5)
|
||||
TARGET_FPS = config.get("target_fps", 10)
|
||||
poll_interval = 1000 / TARGET_FPS
|
||||
logging.info(f"Poll interval: {poll_interval}ms")
|
||||
max_streams = config.get("max_streams", 5)
|
||||
max_retries = config.get("max_retries", 3)
|
||||
|
||||
# Configure logging
|
||||
logging.basicConfig(
|
||||
level=logging.INFO, # Set to INFO level for less verbose output
|
||||
format="%(asctime)s [%(levelname)s] %(name)s: %(message)s",
|
||||
handlers=[
|
||||
logging.FileHandler("detector_worker.log"), # Write logs to a file
|
||||
logging.StreamHandler() # Also output to console
|
||||
]
|
||||
)
|
||||
|
||||
# Create a logger specifically for this application
|
||||
logger = logging.getLogger("detector_worker")
|
||||
logger.setLevel(logging.DEBUG) # Set app-specific logger to DEBUG level
|
||||
|
||||
# Ensure all other libraries (including root) use at least INFO level
|
||||
logging.getLogger().setLevel(logging.INFO)
|
||||
|
||||
logger.info("Starting detector worker application")
|
||||
logger.info(f"Configuration: Target FPS: {TARGET_FPS}, Max streams: {max_streams}, Max retries: {max_retries}")
|
||||
|
||||
# Ensure the models directory exists
|
||||
os.makedirs("models", exist_ok=True)
|
||||
logger.info("Ensured models directory exists")
|
||||
|
||||
# Constants for heartbeat and timeouts
|
||||
HEARTBEAT_INTERVAL = 2 # seconds
|
||||
WORKER_TIMEOUT_MS = 10000
|
||||
logger.debug(f"Heartbeat interval set to {HEARTBEAT_INTERVAL} seconds")
|
||||
|
||||
# Locks for thread-safe operations
|
||||
streams_lock = threading.Lock()
|
||||
models_lock = threading.Lock()
|
||||
logger.debug("Initialized thread locks")
|
||||
|
||||
# Add helper to download mpta ZIP file from a remote URL
|
||||
def download_mpta(url: str, dest_path: str) -> str:
|
||||
try:
|
||||
logger.info(f"Starting download of model from {url} to {dest_path}")
|
||||
os.makedirs(os.path.dirname(dest_path), exist_ok=True)
|
||||
response = requests.get(url, stream=True)
|
||||
if response.status_code == 200:
|
||||
file_size = int(response.headers.get('content-length', 0))
|
||||
logger.info(f"Model file size: {file_size/1024/1024:.2f} MB")
|
||||
downloaded = 0
|
||||
with open(dest_path, "wb") as f:
|
||||
for chunk in response.iter_content(chunk_size=8192):
|
||||
f.write(chunk)
|
||||
downloaded += len(chunk)
|
||||
if file_size > 0 and downloaded % (file_size // 10) < 8192: # Log approximately every 10%
|
||||
logger.debug(f"Download progress: {downloaded/file_size*100:.1f}%")
|
||||
logger.info(f"Successfully downloaded mpta file from {url} to {dest_path}")
|
||||
return dest_path
|
||||
else:
|
||||
logger.error(f"Failed to download mpta file (status code {response.status_code}): {response.text}")
|
||||
return None
|
||||
except Exception as e:
|
||||
logger.error(f"Exception downloading mpta file from {url}: {str(e)}", exc_info=True)
|
||||
return None
|
||||
|
||||
# Add helper to fetch snapshot image from HTTP/HTTPS URL
|
||||
def fetch_snapshot(url: str):
|
||||
try:
|
||||
from requests.auth import HTTPBasicAuth, HTTPDigestAuth
|
||||
|
||||
# Parse URL to extract credentials
|
||||
parsed = urlparse(url)
|
||||
|
||||
# Prepare headers - some cameras require User-Agent
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (compatible; DetectorWorker/1.0)'
|
||||
}
|
||||
|
||||
# Reconstruct URL without credentials
|
||||
clean_url = f"{parsed.scheme}://{parsed.hostname}"
|
||||
if parsed.port:
|
||||
clean_url += f":{parsed.port}"
|
||||
clean_url += parsed.path
|
||||
if parsed.query:
|
||||
clean_url += f"?{parsed.query}"
|
||||
|
||||
auth = None
|
||||
if parsed.username and parsed.password:
|
||||
# Try HTTP Digest authentication first (common for IP cameras)
|
||||
try:
|
||||
auth = HTTPDigestAuth(parsed.username, parsed.password)
|
||||
response = requests.get(clean_url, auth=auth, headers=headers, timeout=10)
|
||||
if response.status_code == 200:
|
||||
logger.debug(f"Successfully authenticated using HTTP Digest for {clean_url}")
|
||||
elif response.status_code == 401:
|
||||
# If Digest fails, try Basic auth
|
||||
logger.debug(f"HTTP Digest failed, trying Basic auth for {clean_url}")
|
||||
auth = HTTPBasicAuth(parsed.username, parsed.password)
|
||||
response = requests.get(clean_url, auth=auth, headers=headers, timeout=10)
|
||||
if response.status_code == 200:
|
||||
logger.debug(f"Successfully authenticated using HTTP Basic for {clean_url}")
|
||||
except Exception as auth_error:
|
||||
logger.debug(f"Authentication setup error: {auth_error}")
|
||||
# Fallback to original URL with embedded credentials
|
||||
response = requests.get(url, headers=headers, timeout=10)
|
||||
else:
|
||||
# No credentials in URL, make request as-is
|
||||
response = requests.get(url, headers=headers, timeout=10)
|
||||
|
||||
if response.status_code == 200:
|
||||
# Convert response content to numpy array
|
||||
nparr = np.frombuffer(response.content, np.uint8)
|
||||
# Decode image
|
||||
frame = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
|
||||
if frame is not None:
|
||||
logger.debug(f"Successfully fetched snapshot from {clean_url}, shape: {frame.shape}")
|
||||
return frame
|
||||
else:
|
||||
logger.error(f"Failed to decode image from snapshot URL: {clean_url}")
|
||||
return None
|
||||
else:
|
||||
logger.error(f"Failed to fetch snapshot (status code {response.status_code}): {clean_url}")
|
||||
return None
|
||||
except Exception as e:
|
||||
logger.error(f"Exception fetching snapshot from {url}: {str(e)}")
|
||||
return None
|
||||
|
||||
# Helper to get crop coordinates from stream
|
||||
def get_crop_coords(stream):
|
||||
return {
|
||||
"cropX1": stream.get("cropX1"),
|
||||
"cropY1": stream.get("cropY1"),
|
||||
"cropX2": stream.get("cropX2"),
|
||||
"cropY2": stream.get("cropY2")
|
||||
}
|
||||
|
||||
####################################################
|
||||
# REST API endpoint for image retrieval
|
||||
####################################################
|
||||
@app.get("/camera/{camera_id}/image")
|
||||
async def get_camera_image(camera_id: str):
|
||||
"""
|
||||
Get the current frame from a camera as JPEG image
|
||||
"""
|
||||
try:
|
||||
# URL decode the camera_id to handle encoded characters like %3B for semicolon
|
||||
from urllib.parse import unquote
|
||||
original_camera_id = camera_id
|
||||
camera_id = unquote(camera_id)
|
||||
logger.debug(f"REST API request: original='{original_camera_id}', decoded='{camera_id}'")
|
||||
|
||||
with streams_lock:
|
||||
if camera_id not in streams:
|
||||
logger.warning(f"Camera ID '{camera_id}' not found in streams. Current streams: {list(streams.keys())}")
|
||||
raise HTTPException(status_code=404, detail=f"Camera {camera_id} not found or not active")
|
||||
|
||||
# Check if we have a cached frame for this camera
|
||||
if camera_id not in latest_frames:
|
||||
logger.warning(f"No cached frame available for camera '{camera_id}'.")
|
||||
raise HTTPException(status_code=404, detail=f"No frame available for camera {camera_id}")
|
||||
|
||||
frame = latest_frames[camera_id]
|
||||
logger.debug(f"Retrieved cached frame for camera '{camera_id}', frame shape: {frame.shape}")
|
||||
# Encode frame as JPEG
|
||||
success, buffer_img = cv2.imencode('.jpg', frame, [cv2.IMWRITE_JPEG_QUALITY, 85])
|
||||
if not success:
|
||||
raise HTTPException(status_code=500, detail="Failed to encode image as JPEG")
|
||||
|
||||
# Return image as binary response
|
||||
return Response(content=buffer_img.tobytes(), media_type="image/jpeg")
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Error retrieving image for camera {camera_id}: {str(e)}", exc_info=True)
|
||||
raise HTTPException(status_code=500, detail=f"Internal server error: {str(e)}")
|
||||
|
||||
####################################################
|
||||
# Detection and frame processing functions
|
||||
####################################################
|
||||
@app.websocket("/")
|
||||
async def detect(websocket: WebSocket):
|
||||
logger.info("WebSocket connection accepted")
|
||||
persistent_data_dict = {}
|
||||
|
||||
async def handle_detection(camera_id, stream, frame, websocket, model_tree, persistent_data):
|
||||
try:
|
||||
# Apply crop if specified
|
||||
cropped_frame = frame
|
||||
if all(coord is not None for coord in [stream.get("cropX1"), stream.get("cropY1"), stream.get("cropX2"), stream.get("cropY2")]):
|
||||
cropX1, cropY1, cropX2, cropY2 = stream["cropX1"], stream["cropY1"], stream["cropX2"], stream["cropY2"]
|
||||
cropped_frame = frame[cropY1:cropY2, cropX1:cropX2]
|
||||
logger.debug(f"Applied crop coordinates ({cropX1}, {cropY1}, {cropX2}, {cropY2}) to frame for camera {camera_id}")
|
||||
|
||||
logger.debug(f"Processing frame for camera {camera_id} with model {stream['modelId']}")
|
||||
start_time = time.time()
|
||||
|
||||
# Extract display identifier for session ID lookup
|
||||
subscription_parts = stream["subscriptionIdentifier"].split(';')
|
||||
display_identifier = subscription_parts[0] if subscription_parts else None
|
||||
session_id = session_ids.get(display_identifier) if display_identifier else None
|
||||
|
||||
# Create context for pipeline execution
|
||||
pipeline_context = {
|
||||
"camera_id": camera_id,
|
||||
"display_id": display_identifier,
|
||||
"session_id": session_id
|
||||
}
|
||||
|
||||
detection_result = run_pipeline(cropped_frame, model_tree, context=pipeline_context)
|
||||
process_time = (time.time() - start_time) * 1000
|
||||
logger.debug(f"Detection for camera {camera_id} completed in {process_time:.2f}ms")
|
||||
|
||||
# Log the raw detection result for debugging
|
||||
logger.debug(f"Raw detection result for camera {camera_id}:\n{json.dumps(detection_result, indent=2, default=str)}")
|
||||
|
||||
# Direct class result (no detections/classifications structure)
|
||||
if detection_result and isinstance(detection_result, dict) and "class" in detection_result and "confidence" in detection_result:
|
||||
highest_confidence_detection = {
|
||||
"class": detection_result.get("class", "none"),
|
||||
"confidence": detection_result.get("confidence", 1.0),
|
||||
"box": [0, 0, 0, 0] # Empty bounding box for classifications
|
||||
}
|
||||
# Handle case when no detections found or result is empty
|
||||
elif not detection_result or not detection_result.get("detections"):
|
||||
# Check if we have classification results
|
||||
if detection_result and detection_result.get("classifications"):
|
||||
# Get the highest confidence classification
|
||||
classifications = detection_result.get("classifications", [])
|
||||
highest_confidence_class = max(classifications, key=lambda x: x.get("confidence", 0)) if classifications else None
|
||||
|
||||
if highest_confidence_class:
|
||||
highest_confidence_detection = {
|
||||
"class": highest_confidence_class.get("class", "none"),
|
||||
"confidence": highest_confidence_class.get("confidence", 1.0),
|
||||
"box": [0, 0, 0, 0] # Empty bounding box for classifications
|
||||
}
|
||||
else:
|
||||
highest_confidence_detection = {
|
||||
"class": "none",
|
||||
"confidence": 1.0,
|
||||
"box": [0, 0, 0, 0]
|
||||
}
|
||||
else:
|
||||
highest_confidence_detection = {
|
||||
"class": "none",
|
||||
"confidence": 1.0,
|
||||
"box": [0, 0, 0, 0]
|
||||
}
|
||||
else:
|
||||
# Find detection with highest confidence
|
||||
detections = detection_result.get("detections", [])
|
||||
highest_confidence_detection = max(detections, key=lambda x: x.get("confidence", 0)) if detections else {
|
||||
"class": "none",
|
||||
"confidence": 1.0,
|
||||
"box": [0, 0, 0, 0]
|
||||
}
|
||||
|
||||
# Convert detection format to match protocol - flatten detection attributes
|
||||
detection_dict = {}
|
||||
|
||||
# Handle different detection result formats
|
||||
if isinstance(highest_confidence_detection, dict):
|
||||
# Copy all fields from the detection result
|
||||
for key, value in highest_confidence_detection.items():
|
||||
if key not in ["box", "id"]: # Skip internal fields
|
||||
detection_dict[key] = value
|
||||
|
||||
detection_data = {
|
||||
"type": "imageDetection",
|
||||
"subscriptionIdentifier": stream["subscriptionIdentifier"],
|
||||
"timestamp": time.strftime("%Y-%m-%dT%H:%M:%S.%fZ", time.gmtime()),
|
||||
"data": {
|
||||
"detection": detection_dict,
|
||||
"modelId": stream["modelId"],
|
||||
"modelName": stream["modelName"]
|
||||
}
|
||||
}
|
||||
|
||||
# Add session ID if available
|
||||
if session_id is not None:
|
||||
detection_data["sessionId"] = session_id
|
||||
|
||||
if highest_confidence_detection["class"] != "none":
|
||||
logger.info(f"Camera {camera_id}: Detected {highest_confidence_detection['class']} with confidence {highest_confidence_detection['confidence']:.2f} using model {stream['modelName']}")
|
||||
|
||||
# Log session ID if available
|
||||
if session_id:
|
||||
logger.debug(f"Detection associated with session ID: {session_id}")
|
||||
|
||||
await websocket.send_json(detection_data)
|
||||
logger.debug(f"Sent detection data to client for camera {camera_id}")
|
||||
return persistent_data
|
||||
except Exception as e:
|
||||
logger.error(f"Error in handle_detection for camera {camera_id}: {str(e)}", exc_info=True)
|
||||
return persistent_data
|
||||
|
||||
def frame_reader(camera_id, cap, buffer, stop_event):
|
||||
retries = 0
|
||||
logger.info(f"Starting frame reader thread for camera {camera_id}")
|
||||
frame_count = 0
|
||||
last_log_time = time.time()
|
||||
|
||||
try:
|
||||
# Log initial camera status and properties
|
||||
if cap.isOpened():
|
||||
width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
|
||||
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
|
||||
fps = cap.get(cv2.CAP_PROP_FPS)
|
||||
logger.info(f"Camera {camera_id} opened successfully with resolution {width}x{height}, FPS: {fps}")
|
||||
else:
|
||||
logger.error(f"Camera {camera_id} failed to open initially")
|
||||
|
||||
while not stop_event.is_set():
|
||||
try:
|
||||
if not cap.isOpened():
|
||||
logger.error(f"Camera {camera_id} is not open before trying to read")
|
||||
# Attempt to reopen
|
||||
cap = cv2.VideoCapture(streams[camera_id]["rtsp_url"])
|
||||
time.sleep(reconnect_interval)
|
||||
continue
|
||||
|
||||
logger.debug(f"Attempting to read frame from camera {camera_id}")
|
||||
ret, frame = cap.read()
|
||||
|
||||
if not ret:
|
||||
logger.warning(f"Connection lost for camera: {camera_id}, retry {retries+1}/{max_retries}")
|
||||
cap.release()
|
||||
time.sleep(reconnect_interval)
|
||||
retries += 1
|
||||
if retries > max_retries and max_retries != -1:
|
||||
logger.error(f"Max retries reached for camera: {camera_id}, stopping frame reader")
|
||||
break
|
||||
# Re-open
|
||||
logger.info(f"Attempting to reopen RTSP stream for camera: {camera_id}")
|
||||
cap = cv2.VideoCapture(streams[camera_id]["rtsp_url"])
|
||||
if not cap.isOpened():
|
||||
logger.error(f"Failed to reopen RTSP stream for camera: {camera_id}")
|
||||
continue
|
||||
logger.info(f"Successfully reopened RTSP stream for camera: {camera_id}")
|
||||
continue
|
||||
|
||||
# Successfully read a frame
|
||||
frame_count += 1
|
||||
current_time = time.time()
|
||||
# Log frame stats every 5 seconds
|
||||
if current_time - last_log_time > 5:
|
||||
logger.info(f"Camera {camera_id}: Read {frame_count} frames in the last {current_time - last_log_time:.1f} seconds")
|
||||
frame_count = 0
|
||||
last_log_time = current_time
|
||||
|
||||
logger.debug(f"Successfully read frame from camera {camera_id}, shape: {frame.shape}")
|
||||
retries = 0
|
||||
|
||||
# Overwrite old frame if buffer is full
|
||||
if not buffer.empty():
|
||||
try:
|
||||
buffer.get_nowait()
|
||||
logger.debug(f"[frame_reader] Removed old frame from buffer for camera {camera_id}")
|
||||
except queue.Empty:
|
||||
pass
|
||||
buffer.put(frame)
|
||||
logger.debug(f"[frame_reader] Added new frame to buffer for camera {camera_id}. Buffer size: {buffer.qsize()}")
|
||||
|
||||
# Short sleep to avoid CPU overuse
|
||||
time.sleep(0.01)
|
||||
|
||||
except cv2.error as e:
|
||||
logger.error(f"OpenCV error for camera {camera_id}: {e}", exc_info=True)
|
||||
cap.release()
|
||||
time.sleep(reconnect_interval)
|
||||
retries += 1
|
||||
if retries > max_retries and max_retries != -1:
|
||||
logger.error(f"Max retries reached after OpenCV error for camera {camera_id}")
|
||||
break
|
||||
logger.info(f"Attempting to reopen RTSP stream after OpenCV error for camera: {camera_id}")
|
||||
cap = cv2.VideoCapture(streams[camera_id]["rtsp_url"])
|
||||
if not cap.isOpened():
|
||||
logger.error(f"Failed to reopen RTSP stream for camera {camera_id} after OpenCV error")
|
||||
continue
|
||||
logger.info(f"Successfully reopened RTSP stream after OpenCV error for camera: {camera_id}")
|
||||
except Exception as e:
|
||||
logger.error(f"Unexpected error for camera {camera_id}: {str(e)}", exc_info=True)
|
||||
cap.release()
|
||||
break
|
||||
except Exception as e:
|
||||
logger.error(f"Error in frame_reader thread for camera {camera_id}: {str(e)}", exc_info=True)
|
||||
finally:
|
||||
logger.info(f"Frame reader thread for camera {camera_id} is exiting")
|
||||
if cap and cap.isOpened():
|
||||
cap.release()
|
||||
|
||||
def snapshot_reader(camera_id, snapshot_url, snapshot_interval, buffer, stop_event):
|
||||
"""Frame reader that fetches snapshots from HTTP/HTTPS URL at specified intervals"""
|
||||
retries = 0
|
||||
logger.info(f"Starting snapshot reader thread for camera {camera_id} from {snapshot_url}")
|
||||
frame_count = 0
|
||||
last_log_time = time.time()
|
||||
|
||||
try:
|
||||
interval_seconds = snapshot_interval / 1000.0 # Convert milliseconds to seconds
|
||||
logger.info(f"Snapshot interval for camera {camera_id}: {interval_seconds}s")
|
||||
|
||||
while not stop_event.is_set():
|
||||
try:
|
||||
start_time = time.time()
|
||||
frame = fetch_snapshot(snapshot_url)
|
||||
|
||||
if frame is None:
|
||||
logger.warning(f"Failed to fetch snapshot for camera: {camera_id}, retry {retries+1}/{max_retries}")
|
||||
retries += 1
|
||||
if retries > max_retries and max_retries != -1:
|
||||
logger.error(f"Max retries reached for snapshot camera: {camera_id}, stopping reader")
|
||||
break
|
||||
time.sleep(min(interval_seconds, reconnect_interval))
|
||||
continue
|
||||
|
||||
# Successfully fetched a frame
|
||||
frame_count += 1
|
||||
current_time = time.time()
|
||||
# Log frame stats every 5 seconds
|
||||
if current_time - last_log_time > 5:
|
||||
logger.info(f"Camera {camera_id}: Fetched {frame_count} snapshots in the last {current_time - last_log_time:.1f} seconds")
|
||||
frame_count = 0
|
||||
last_log_time = current_time
|
||||
|
||||
logger.debug(f"Successfully fetched snapshot from camera {camera_id}, shape: {frame.shape}")
|
||||
retries = 0
|
||||
|
||||
# Overwrite old frame if buffer is full
|
||||
if not buffer.empty():
|
||||
try:
|
||||
buffer.get_nowait()
|
||||
logger.debug(f"[snapshot_reader] Removed old snapshot from buffer for camera {camera_id}")
|
||||
except queue.Empty:
|
||||
pass
|
||||
buffer.put(frame)
|
||||
logger.debug(f"[snapshot_reader] Added new snapshot to buffer for camera {camera_id}. Buffer size: {buffer.qsize()}")
|
||||
|
||||
# Wait for the specified interval
|
||||
elapsed = time.time() - start_time
|
||||
sleep_time = max(interval_seconds - elapsed, 0)
|
||||
if sleep_time > 0:
|
||||
time.sleep(sleep_time)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Unexpected error fetching snapshot for camera {camera_id}: {str(e)}", exc_info=True)
|
||||
retries += 1
|
||||
if retries > max_retries and max_retries != -1:
|
||||
logger.error(f"Max retries reached after error for snapshot camera {camera_id}")
|
||||
break
|
||||
time.sleep(min(interval_seconds, reconnect_interval))
|
||||
except Exception as e:
|
||||
logger.error(f"Error in snapshot_reader thread for camera {camera_id}: {str(e)}", exc_info=True)
|
||||
finally:
|
||||
logger.info(f"Snapshot reader thread for camera {camera_id} is exiting")
|
||||
|
||||
async def process_streams():
|
||||
logger.info("Started processing streams")
|
||||
try:
|
||||
while True:
|
||||
start_time = time.time()
|
||||
with streams_lock:
|
||||
current_streams = list(streams.items())
|
||||
if current_streams:
|
||||
logger.debug(f"Processing {len(current_streams)} active streams")
|
||||
else:
|
||||
logger.debug("No active streams to process")
|
||||
|
||||
for camera_id, stream in current_streams:
|
||||
buffer = stream["buffer"]
|
||||
if buffer.empty():
|
||||
logger.debug(f"Frame buffer is empty for camera {camera_id}")
|
||||
continue
|
||||
|
||||
logger.debug(f"Got frame from buffer for camera {camera_id}")
|
||||
frame = buffer.get()
|
||||
|
||||
# Cache the frame for REST API access
|
||||
latest_frames[camera_id] = frame.copy()
|
||||
logger.debug(f"Cached frame for REST API access for camera {camera_id}")
|
||||
|
||||
with models_lock:
|
||||
model_tree = models.get(camera_id, {}).get(stream["modelId"])
|
||||
if not model_tree:
|
||||
logger.warning(f"Model not found for camera {camera_id}, modelId {stream['modelId']}")
|
||||
continue
|
||||
logger.debug(f"Found model tree for camera {camera_id}, modelId {stream['modelId']}")
|
||||
|
||||
key = (camera_id, stream["modelId"])
|
||||
persistent_data = persistent_data_dict.get(key, {})
|
||||
logger.debug(f"Starting detection for camera {camera_id} with modelId {stream['modelId']}")
|
||||
updated_persistent_data = await handle_detection(
|
||||
camera_id, stream, frame, websocket, model_tree, persistent_data
|
||||
)
|
||||
persistent_data_dict[key] = updated_persistent_data
|
||||
|
||||
elapsed_time = (time.time() - start_time) * 1000 # ms
|
||||
sleep_time = max(poll_interval - elapsed_time, 0)
|
||||
logger.debug(f"Frame processing cycle: {elapsed_time:.2f}ms, sleeping for: {sleep_time:.2f}ms")
|
||||
await asyncio.sleep(sleep_time / 1000.0)
|
||||
except asyncio.CancelledError:
|
||||
logger.info("Stream processing task cancelled")
|
||||
except Exception as e:
|
||||
logger.error(f"Error in process_streams: {str(e)}", exc_info=True)
|
||||
|
||||
async def send_heartbeat():
|
||||
while True:
|
||||
try:
|
||||
cpu_usage = psutil.cpu_percent()
|
||||
memory_usage = psutil.virtual_memory().percent
|
||||
if torch.cuda.is_available():
|
||||
gpu_usage = torch.cuda.utilization() if hasattr(torch.cuda, 'utilization') else None
|
||||
gpu_memory_usage = torch.cuda.memory_reserved() / (1024 ** 2)
|
||||
else:
|
||||
gpu_usage = None
|
||||
gpu_memory_usage = None
|
||||
|
||||
camera_connections = [
|
||||
{
|
||||
"subscriptionIdentifier": stream["subscriptionIdentifier"],
|
||||
"modelId": stream["modelId"],
|
||||
"modelName": stream["modelName"],
|
||||
"online": True,
|
||||
**{k: v for k, v in get_crop_coords(stream).items() if v is not None}
|
||||
}
|
||||
for camera_id, stream in streams.items()
|
||||
]
|
||||
|
||||
state_report = {
|
||||
"type": "stateReport",
|
||||
"cpuUsage": cpu_usage,
|
||||
"memoryUsage": memory_usage,
|
||||
"gpuUsage": gpu_usage,
|
||||
"gpuMemoryUsage": gpu_memory_usage,
|
||||
"cameraConnections": camera_connections
|
||||
}
|
||||
await websocket.send_text(json.dumps(state_report))
|
||||
logger.debug(f"Sent stateReport as heartbeat: CPU {cpu_usage:.1f}%, Memory {memory_usage:.1f}%, {len(camera_connections)} active cameras")
|
||||
await asyncio.sleep(HEARTBEAT_INTERVAL)
|
||||
except Exception as e:
|
||||
logger.error(f"Error sending stateReport heartbeat: {e}")
|
||||
break
|
||||
|
||||
async def on_message():
|
||||
while True:
|
||||
try:
|
||||
msg = await websocket.receive_text()
|
||||
logger.debug(f"Received message: {msg}")
|
||||
data = json.loads(msg)
|
||||
msg_type = data.get("type")
|
||||
|
||||
if msg_type == "subscribe":
|
||||
payload = data.get("payload", {})
|
||||
subscriptionIdentifier = payload.get("subscriptionIdentifier")
|
||||
rtsp_url = payload.get("rtspUrl")
|
||||
snapshot_url = payload.get("snapshotUrl")
|
||||
snapshot_interval = payload.get("snapshotInterval")
|
||||
model_url = payload.get("modelUrl")
|
||||
modelId = payload.get("modelId")
|
||||
modelName = payload.get("modelName")
|
||||
cropX1 = payload.get("cropX1")
|
||||
cropY1 = payload.get("cropY1")
|
||||
cropX2 = payload.get("cropX2")
|
||||
cropY2 = payload.get("cropY2")
|
||||
|
||||
# Extract camera_id from subscriptionIdentifier (format: displayIdentifier;cameraIdentifier)
|
||||
parts = subscriptionIdentifier.split(';')
|
||||
if len(parts) != 2:
|
||||
logger.error(f"Invalid subscriptionIdentifier format: {subscriptionIdentifier}")
|
||||
continue
|
||||
|
||||
display_identifier, camera_identifier = parts
|
||||
camera_id = subscriptionIdentifier # Use full subscriptionIdentifier as camera_id for mapping
|
||||
|
||||
if model_url:
|
||||
with models_lock:
|
||||
if (camera_id not in models) or (modelId not in models[camera_id]):
|
||||
logger.info(f"Loading model from {model_url} for camera {camera_id}, modelId {modelId}")
|
||||
extraction_dir = os.path.join("models", camera_identifier, str(modelId))
|
||||
os.makedirs(extraction_dir, exist_ok=True)
|
||||
# If model_url is remote, download it first.
|
||||
parsed = urlparse(model_url)
|
||||
if parsed.scheme in ("http", "https"):
|
||||
logger.info(f"Downloading remote .mpta file from {model_url}")
|
||||
filename = os.path.basename(parsed.path) or f"model_{modelId}.mpta"
|
||||
local_mpta = os.path.join(extraction_dir, filename)
|
||||
logger.debug(f"Download destination: {local_mpta}")
|
||||
local_path = download_mpta(model_url, local_mpta)
|
||||
if not local_path:
|
||||
logger.error(f"Failed to download the remote .mpta file from {model_url}")
|
||||
error_response = {
|
||||
"type": "error",
|
||||
"subscriptionIdentifier": subscriptionIdentifier,
|
||||
"error": f"Failed to download model from {model_url}"
|
||||
}
|
||||
await websocket.send_json(error_response)
|
||||
continue
|
||||
model_tree = load_pipeline_from_zip(local_path, extraction_dir)
|
||||
else:
|
||||
logger.info(f"Loading local .mpta file from {model_url}")
|
||||
# Check if file exists before attempting to load
|
||||
if not os.path.exists(model_url):
|
||||
logger.error(f"Local .mpta file not found: {model_url}")
|
||||
logger.debug(f"Current working directory: {os.getcwd()}")
|
||||
error_response = {
|
||||
"type": "error",
|
||||
"subscriptionIdentifier": subscriptionIdentifier,
|
||||
"error": f"Model file not found: {model_url}"
|
||||
}
|
||||
await websocket.send_json(error_response)
|
||||
continue
|
||||
model_tree = load_pipeline_from_zip(model_url, extraction_dir)
|
||||
if model_tree is None:
|
||||
logger.error(f"Failed to load model {modelId} from .mpta file for camera {camera_id}")
|
||||
error_response = {
|
||||
"type": "error",
|
||||
"subscriptionIdentifier": subscriptionIdentifier,
|
||||
"error": f"Failed to load model {modelId}"
|
||||
}
|
||||
await websocket.send_json(error_response)
|
||||
continue
|
||||
if camera_id not in models:
|
||||
models[camera_id] = {}
|
||||
models[camera_id][modelId] = model_tree
|
||||
logger.info(f"Successfully loaded model {modelId} for camera {camera_id}")
|
||||
logger.debug(f"Model extraction directory: {extraction_dir}")
|
||||
if camera_id and (rtsp_url or snapshot_url):
|
||||
with streams_lock:
|
||||
# Determine camera URL for shared stream management
|
||||
camera_url = snapshot_url if snapshot_url else rtsp_url
|
||||
|
||||
if camera_id not in streams and len(streams) < max_streams:
|
||||
# Check if we already have a stream for this camera URL
|
||||
shared_stream = camera_streams.get(camera_url)
|
||||
|
||||
if shared_stream:
|
||||
# Reuse existing stream
|
||||
logger.info(f"Reusing existing stream for camera URL: {camera_url}")
|
||||
buffer = shared_stream["buffer"]
|
||||
stop_event = shared_stream["stop_event"]
|
||||
thread = shared_stream["thread"]
|
||||
mode = shared_stream["mode"]
|
||||
|
||||
# Increment reference count
|
||||
shared_stream["ref_count"] = shared_stream.get("ref_count", 0) + 1
|
||||
else:
|
||||
# Create new stream
|
||||
buffer = queue.Queue(maxsize=1)
|
||||
stop_event = threading.Event()
|
||||
|
||||
if snapshot_url and snapshot_interval:
|
||||
logger.info(f"Creating new snapshot stream for camera {camera_id}: {snapshot_url}")
|
||||
thread = threading.Thread(target=snapshot_reader, args=(camera_id, snapshot_url, snapshot_interval, buffer, stop_event))
|
||||
thread.daemon = True
|
||||
thread.start()
|
||||
mode = "snapshot"
|
||||
|
||||
# Store shared stream info
|
||||
shared_stream = {
|
||||
"buffer": buffer,
|
||||
"thread": thread,
|
||||
"stop_event": stop_event,
|
||||
"mode": mode,
|
||||
"url": snapshot_url,
|
||||
"snapshot_interval": snapshot_interval,
|
||||
"ref_count": 1
|
||||
}
|
||||
camera_streams[camera_url] = shared_stream
|
||||
|
||||
elif rtsp_url:
|
||||
logger.info(f"Creating new RTSP stream for camera {camera_id}: {rtsp_url}")
|
||||
cap = cv2.VideoCapture(rtsp_url)
|
||||
if not cap.isOpened():
|
||||
logger.error(f"Failed to open RTSP stream for camera {camera_id}")
|
||||
continue
|
||||
thread = threading.Thread(target=frame_reader, args=(camera_id, cap, buffer, stop_event))
|
||||
thread.daemon = True
|
||||
thread.start()
|
||||
mode = "rtsp"
|
||||
|
||||
# Store shared stream info
|
||||
shared_stream = {
|
||||
"buffer": buffer,
|
||||
"thread": thread,
|
||||
"stop_event": stop_event,
|
||||
"mode": mode,
|
||||
"url": rtsp_url,
|
||||
"cap": cap,
|
||||
"ref_count": 1
|
||||
}
|
||||
camera_streams[camera_url] = shared_stream
|
||||
else:
|
||||
logger.error(f"No valid URL provided for camera {camera_id}")
|
||||
continue
|
||||
|
||||
# Create stream info for this subscription
|
||||
stream_info = {
|
||||
"buffer": buffer,
|
||||
"thread": thread,
|
||||
"stop_event": stop_event,
|
||||
"modelId": modelId,
|
||||
"modelName": modelName,
|
||||
"subscriptionIdentifier": subscriptionIdentifier,
|
||||
"cropX1": cropX1,
|
||||
"cropY1": cropY1,
|
||||
"cropX2": cropX2,
|
||||
"cropY2": cropY2,
|
||||
"mode": mode,
|
||||
"camera_url": camera_url
|
||||
}
|
||||
|
||||
if mode == "snapshot":
|
||||
stream_info["snapshot_url"] = snapshot_url
|
||||
stream_info["snapshot_interval"] = snapshot_interval
|
||||
elif mode == "rtsp":
|
||||
stream_info["rtsp_url"] = rtsp_url
|
||||
stream_info["cap"] = shared_stream["cap"]
|
||||
|
||||
streams[camera_id] = stream_info
|
||||
subscription_to_camera[camera_id] = camera_url
|
||||
|
||||
elif camera_id and camera_id in streams:
|
||||
# If already subscribed, unsubscribe first
|
||||
logger.info(f"Resubscribing to camera {camera_id}")
|
||||
# Note: Keep models in memory for reuse across subscriptions
|
||||
elif msg_type == "unsubscribe":
|
||||
payload = data.get("payload", {})
|
||||
subscriptionIdentifier = payload.get("subscriptionIdentifier")
|
||||
camera_id = subscriptionIdentifier
|
||||
with streams_lock:
|
||||
if camera_id and camera_id in streams:
|
||||
stream = streams.pop(camera_id)
|
||||
camera_url = subscription_to_camera.pop(camera_id, None)
|
||||
|
||||
if camera_url and camera_url in camera_streams:
|
||||
shared_stream = camera_streams[camera_url]
|
||||
shared_stream["ref_count"] -= 1
|
||||
|
||||
# If no more references, stop the shared stream
|
||||
if shared_stream["ref_count"] <= 0:
|
||||
logger.info(f"Stopping shared stream for camera URL: {camera_url}")
|
||||
shared_stream["stop_event"].set()
|
||||
shared_stream["thread"].join()
|
||||
if "cap" in shared_stream:
|
||||
shared_stream["cap"].release()
|
||||
del camera_streams[camera_url]
|
||||
else:
|
||||
logger.info(f"Shared stream for {camera_url} still has {shared_stream['ref_count']} references")
|
||||
|
||||
# Clean up cached frame
|
||||
latest_frames.pop(camera_id, None)
|
||||
logger.info(f"Unsubscribed from camera {camera_id}")
|
||||
# Note: Keep models in memory for potential reuse
|
||||
elif msg_type == "requestState":
|
||||
cpu_usage = psutil.cpu_percent()
|
||||
memory_usage = psutil.virtual_memory().percent
|
||||
if torch.cuda.is_available():
|
||||
gpu_usage = torch.cuda.utilization() if hasattr(torch.cuda, 'utilization') else None
|
||||
gpu_memory_usage = torch.cuda.memory_reserved() / (1024 ** 2)
|
||||
else:
|
||||
gpu_usage = None
|
||||
gpu_memory_usage = None
|
||||
|
||||
camera_connections = [
|
||||
{
|
||||
"subscriptionIdentifier": stream["subscriptionIdentifier"],
|
||||
"modelId": stream["modelId"],
|
||||
"modelName": stream["modelName"],
|
||||
"online": True,
|
||||
**{k: v for k, v in get_crop_coords(stream).items() if v is not None}
|
||||
}
|
||||
for camera_id, stream in streams.items()
|
||||
]
|
||||
|
||||
state_report = {
|
||||
"type": "stateReport",
|
||||
"cpuUsage": cpu_usage,
|
||||
"memoryUsage": memory_usage,
|
||||
"gpuUsage": gpu_usage,
|
||||
"gpuMemoryUsage": gpu_memory_usage,
|
||||
"cameraConnections": camera_connections
|
||||
}
|
||||
await websocket.send_text(json.dumps(state_report))
|
||||
|
||||
elif msg_type == "setSessionId":
|
||||
payload = data.get("payload", {})
|
||||
display_identifier = payload.get("displayIdentifier")
|
||||
session_id = payload.get("sessionId")
|
||||
|
||||
if display_identifier:
|
||||
# Store session ID for this display
|
||||
if session_id is None:
|
||||
session_ids.pop(display_identifier, None)
|
||||
logger.info(f"Cleared session ID for display {display_identifier}")
|
||||
else:
|
||||
session_ids[display_identifier] = session_id
|
||||
logger.info(f"Set session ID {session_id} for display {display_identifier}")
|
||||
|
||||
elif msg_type == "patchSession":
|
||||
session_id = data.get("sessionId")
|
||||
patch_data = data.get("data", {})
|
||||
|
||||
# For now, just acknowledge the patch - actual implementation depends on backend requirements
|
||||
response = {
|
||||
"type": "patchSessionResult",
|
||||
"payload": {
|
||||
"sessionId": session_id,
|
||||
"success": True,
|
||||
"message": "Session patch acknowledged"
|
||||
}
|
||||
}
|
||||
await websocket.send_json(response)
|
||||
logger.info(f"Acknowledged patch for session {session_id}")
|
||||
|
||||
else:
|
||||
logger.error(f"Unknown message type: {msg_type}")
|
||||
except json.JSONDecodeError:
|
||||
logger.error("Received invalid JSON message")
|
||||
except (WebSocketDisconnect, ConnectionClosedError) as e:
|
||||
logger.warning(f"WebSocket disconnected: {e}")
|
||||
break
|
||||
except Exception as e:
|
||||
logger.error(f"Error handling message: {e}")
|
||||
break
|
||||
try:
|
||||
await websocket.accept()
|
||||
stream_task = asyncio.create_task(process_streams())
|
||||
heartbeat_task = asyncio.create_task(send_heartbeat())
|
||||
message_task = asyncio.create_task(on_message())
|
||||
await asyncio.gather(heartbeat_task, message_task)
|
||||
except Exception as e:
|
||||
logger.error(f"Error in detect websocket: {e}")
|
||||
finally:
|
||||
stream_task.cancel()
|
||||
await stream_task
|
||||
with streams_lock:
|
||||
# Clean up shared camera streams
|
||||
for camera_url, shared_stream in camera_streams.items():
|
||||
shared_stream["stop_event"].set()
|
||||
shared_stream["thread"].join()
|
||||
if "cap" in shared_stream:
|
||||
shared_stream["cap"].release()
|
||||
while not shared_stream["buffer"].empty():
|
||||
try:
|
||||
shared_stream["buffer"].get_nowait()
|
||||
except queue.Empty:
|
||||
pass
|
||||
logger.info(f"Released shared camera stream for {camera_url}")
|
||||
|
||||
streams.clear()
|
||||
camera_streams.clear()
|
||||
subscription_to_camera.clear()
|
||||
with models_lock:
|
||||
models.clear()
|
||||
latest_frames.clear()
|
||||
session_ids.clear()
|
||||
logger.info("WebSocket connection closed")
|
||||
|
|
@ -1,211 +0,0 @@
|
|||
import psycopg2
|
||||
import psycopg2.extras
|
||||
from typing import Optional, Dict, Any
|
||||
import logging
|
||||
import uuid
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
class DatabaseManager:
|
||||
def __init__(self, config: Dict[str, Any]):
|
||||
self.config = config
|
||||
self.connection: Optional[psycopg2.extensions.connection] = None
|
||||
|
||||
def connect(self) -> bool:
|
||||
try:
|
||||
self.connection = psycopg2.connect(
|
||||
host=self.config['host'],
|
||||
port=self.config['port'],
|
||||
database=self.config['database'],
|
||||
user=self.config['username'],
|
||||
password=self.config['password']
|
||||
)
|
||||
logger.info("PostgreSQL connection established successfully")
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to connect to PostgreSQL: {e}")
|
||||
return False
|
||||
|
||||
def disconnect(self):
|
||||
if self.connection:
|
||||
self.connection.close()
|
||||
self.connection = None
|
||||
logger.info("PostgreSQL connection closed")
|
||||
|
||||
def is_connected(self) -> bool:
|
||||
try:
|
||||
if self.connection and not self.connection.closed:
|
||||
cur = self.connection.cursor()
|
||||
cur.execute("SELECT 1")
|
||||
cur.fetchone()
|
||||
cur.close()
|
||||
return True
|
||||
except:
|
||||
pass
|
||||
return False
|
||||
|
||||
def update_car_info(self, session_id: str, brand: str, model: str, body_type: str) -> bool:
|
||||
if not self.is_connected():
|
||||
if not self.connect():
|
||||
return False
|
||||
|
||||
try:
|
||||
cur = self.connection.cursor()
|
||||
query = """
|
||||
INSERT INTO car_frontal_info (session_id, car_brand, car_model, car_body_type, updated_at)
|
||||
VALUES (%s, %s, %s, %s, NOW())
|
||||
ON CONFLICT (session_id)
|
||||
DO UPDATE SET
|
||||
car_brand = EXCLUDED.car_brand,
|
||||
car_model = EXCLUDED.car_model,
|
||||
car_body_type = EXCLUDED.car_body_type,
|
||||
updated_at = NOW()
|
||||
"""
|
||||
cur.execute(query, (session_id, brand, model, body_type))
|
||||
self.connection.commit()
|
||||
cur.close()
|
||||
logger.info(f"Updated car info for session {session_id}: {brand} {model} ({body_type})")
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to update car info: {e}")
|
||||
if self.connection:
|
||||
self.connection.rollback()
|
||||
return False
|
||||
|
||||
def execute_update(self, table: str, key_field: str, key_value: str, fields: Dict[str, str]) -> bool:
|
||||
if not self.is_connected():
|
||||
if not self.connect():
|
||||
return False
|
||||
|
||||
try:
|
||||
cur = self.connection.cursor()
|
||||
|
||||
# Build the UPDATE query dynamically
|
||||
set_clauses = []
|
||||
values = []
|
||||
|
||||
for field, value in fields.items():
|
||||
if value == "NOW()":
|
||||
set_clauses.append(f"{field} = NOW()")
|
||||
else:
|
||||
set_clauses.append(f"{field} = %s")
|
||||
values.append(value)
|
||||
|
||||
# Add schema prefix if table doesn't already have it
|
||||
full_table_name = table if '.' in table else f"gas_station_1.{table}"
|
||||
|
||||
query = f"""
|
||||
INSERT INTO {full_table_name} ({key_field}, {', '.join(fields.keys())})
|
||||
VALUES (%s, {', '.join(['%s'] * len(fields))})
|
||||
ON CONFLICT ({key_field})
|
||||
DO UPDATE SET {', '.join(set_clauses)}
|
||||
"""
|
||||
|
||||
# Add key_value to the beginning of values list
|
||||
all_values = [key_value] + list(fields.values()) + values
|
||||
|
||||
cur.execute(query, all_values)
|
||||
self.connection.commit()
|
||||
cur.close()
|
||||
logger.info(f"Updated {table} for {key_field}={key_value}")
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to execute update on {table}: {e}")
|
||||
if self.connection:
|
||||
self.connection.rollback()
|
||||
return False
|
||||
|
||||
def create_car_frontal_info_table(self) -> bool:
|
||||
"""Create the car_frontal_info table in gas_station_1 schema if it doesn't exist."""
|
||||
if not self.is_connected():
|
||||
if not self.connect():
|
||||
return False
|
||||
|
||||
try:
|
||||
cur = self.connection.cursor()
|
||||
|
||||
# Create schema if it doesn't exist
|
||||
cur.execute("CREATE SCHEMA IF NOT EXISTS gas_station_1")
|
||||
|
||||
# Create table if it doesn't exist
|
||||
create_table_query = """
|
||||
CREATE TABLE IF NOT EXISTS gas_station_1.car_frontal_info (
|
||||
display_id VARCHAR(255),
|
||||
captured_timestamp VARCHAR(255),
|
||||
session_id VARCHAR(255) PRIMARY KEY,
|
||||
license_character VARCHAR(255) DEFAULT NULL,
|
||||
license_type VARCHAR(255) DEFAULT 'No model available',
|
||||
car_brand VARCHAR(255) DEFAULT NULL,
|
||||
car_model VARCHAR(255) DEFAULT NULL,
|
||||
car_body_type VARCHAR(255) DEFAULT NULL,
|
||||
updated_at TIMESTAMP DEFAULT NOW()
|
||||
)
|
||||
"""
|
||||
|
||||
cur.execute(create_table_query)
|
||||
|
||||
# Add columns if they don't exist (for existing tables)
|
||||
alter_queries = [
|
||||
"ALTER TABLE gas_station_1.car_frontal_info ADD COLUMN IF NOT EXISTS car_brand VARCHAR(255) DEFAULT NULL",
|
||||
"ALTER TABLE gas_station_1.car_frontal_info ADD COLUMN IF NOT EXISTS car_model VARCHAR(255) DEFAULT NULL",
|
||||
"ALTER TABLE gas_station_1.car_frontal_info ADD COLUMN IF NOT EXISTS car_body_type VARCHAR(255) DEFAULT NULL",
|
||||
"ALTER TABLE gas_station_1.car_frontal_info ADD COLUMN IF NOT EXISTS updated_at TIMESTAMP DEFAULT NOW()"
|
||||
]
|
||||
|
||||
for alter_query in alter_queries:
|
||||
try:
|
||||
cur.execute(alter_query)
|
||||
logger.debug(f"Executed: {alter_query}")
|
||||
except Exception as e:
|
||||
# Ignore errors if column already exists (for older PostgreSQL versions)
|
||||
if "already exists" in str(e).lower():
|
||||
logger.debug(f"Column already exists, skipping: {alter_query}")
|
||||
else:
|
||||
logger.warning(f"Error in ALTER TABLE: {e}")
|
||||
|
||||
self.connection.commit()
|
||||
cur.close()
|
||||
logger.info("Successfully created/verified car_frontal_info table with all required columns")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to create car_frontal_info table: {e}")
|
||||
if self.connection:
|
||||
self.connection.rollback()
|
||||
return False
|
||||
|
||||
def insert_initial_detection(self, display_id: str, captured_timestamp: str, session_id: str = None) -> str:
|
||||
"""Insert initial detection record and return the session_id."""
|
||||
if not self.is_connected():
|
||||
if not self.connect():
|
||||
return None
|
||||
|
||||
# Generate session_id if not provided
|
||||
if not session_id:
|
||||
session_id = str(uuid.uuid4())
|
||||
|
||||
try:
|
||||
# Ensure table exists
|
||||
if not self.create_car_frontal_info_table():
|
||||
logger.error("Failed to create/verify table before insertion")
|
||||
return None
|
||||
|
||||
cur = self.connection.cursor()
|
||||
insert_query = """
|
||||
INSERT INTO gas_station_1.car_frontal_info
|
||||
(display_id, captured_timestamp, session_id, license_character, license_type, car_brand, car_model, car_body_type)
|
||||
VALUES (%s, %s, %s, NULL, 'No model available', NULL, NULL, NULL)
|
||||
ON CONFLICT (session_id) DO NOTHING
|
||||
"""
|
||||
|
||||
cur.execute(insert_query, (display_id, captured_timestamp, session_id))
|
||||
self.connection.commit()
|
||||
cur.close()
|
||||
logger.info(f"Inserted initial detection record with session_id: {session_id}")
|
||||
return session_id
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to insert initial detection record: {e}")
|
||||
if self.connection:
|
||||
self.connection.rollback()
|
||||
return None
|
||||
|
|
@ -1,798 +0,0 @@
|
|||
import os
|
||||
import json
|
||||
import logging
|
||||
import torch
|
||||
import cv2
|
||||
import zipfile
|
||||
import shutil
|
||||
import traceback
|
||||
import redis
|
||||
import time
|
||||
import uuid
|
||||
import concurrent.futures
|
||||
from ultralytics import YOLO
|
||||
from urllib.parse import urlparse
|
||||
from .database import DatabaseManager
|
||||
|
||||
# Create a logger specifically for this module
|
||||
logger = logging.getLogger("detector_worker.pympta")
|
||||
|
||||
def validate_redis_config(redis_config: dict) -> bool:
|
||||
"""Validate Redis configuration parameters."""
|
||||
required_fields = ["host", "port"]
|
||||
for field in required_fields:
|
||||
if field not in redis_config:
|
||||
logger.error(f"Missing required Redis config field: {field}")
|
||||
return False
|
||||
|
||||
if not isinstance(redis_config["port"], int) or redis_config["port"] <= 0:
|
||||
logger.error(f"Invalid Redis port: {redis_config['port']}")
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
def validate_postgresql_config(pg_config: dict) -> bool:
|
||||
"""Validate PostgreSQL configuration parameters."""
|
||||
required_fields = ["host", "port", "database", "username", "password"]
|
||||
for field in required_fields:
|
||||
if field not in pg_config:
|
||||
logger.error(f"Missing required PostgreSQL config field: {field}")
|
||||
return False
|
||||
|
||||
if not isinstance(pg_config["port"], int) or pg_config["port"] <= 0:
|
||||
logger.error(f"Invalid PostgreSQL port: {pg_config['port']}")
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
def crop_region_by_class(frame, regions_dict, class_name):
|
||||
"""Crop a specific region from frame based on detected class."""
|
||||
if class_name not in regions_dict:
|
||||
logger.warning(f"Class '{class_name}' not found in detected regions")
|
||||
return None
|
||||
|
||||
bbox = regions_dict[class_name]['bbox']
|
||||
x1, y1, x2, y2 = bbox
|
||||
cropped = frame[y1:y2, x1:x2]
|
||||
|
||||
if cropped.size == 0:
|
||||
logger.warning(f"Empty crop for class '{class_name}' with bbox {bbox}")
|
||||
return None
|
||||
|
||||
return cropped
|
||||
|
||||
def format_action_context(base_context, additional_context=None):
|
||||
"""Format action context with dynamic values."""
|
||||
context = {**base_context}
|
||||
if additional_context:
|
||||
context.update(additional_context)
|
||||
return context
|
||||
|
||||
def load_pipeline_node(node_config: dict, mpta_dir: str, redis_client, db_manager=None) -> dict:
|
||||
# Recursively load a model node from configuration.
|
||||
model_path = os.path.join(mpta_dir, node_config["modelFile"])
|
||||
if not os.path.exists(model_path):
|
||||
logger.error(f"Model file {model_path} not found. Current directory: {os.getcwd()}")
|
||||
logger.error(f"Directory content: {os.listdir(os.path.dirname(model_path))}")
|
||||
raise FileNotFoundError(f"Model file {model_path} not found.")
|
||||
logger.info(f"Loading model for node {node_config['modelId']} from {model_path}")
|
||||
model = YOLO(model_path)
|
||||
if torch.cuda.is_available():
|
||||
logger.info(f"CUDA available. Moving model {node_config['modelId']} to GPU")
|
||||
model.to("cuda")
|
||||
else:
|
||||
logger.info(f"CUDA not available. Using CPU for model {node_config['modelId']}")
|
||||
|
||||
# Prepare trigger class indices for optimization
|
||||
trigger_classes = node_config.get("triggerClasses", [])
|
||||
trigger_class_indices = None
|
||||
if trigger_classes and hasattr(model, "names"):
|
||||
# Convert class names to indices for the model
|
||||
trigger_class_indices = [i for i, name in model.names.items()
|
||||
if name in trigger_classes]
|
||||
logger.debug(f"Converted trigger classes to indices: {trigger_class_indices}")
|
||||
|
||||
node = {
|
||||
"modelId": node_config["modelId"],
|
||||
"modelFile": node_config["modelFile"],
|
||||
"triggerClasses": trigger_classes,
|
||||
"triggerClassIndices": trigger_class_indices,
|
||||
"crop": node_config.get("crop", False),
|
||||
"cropClass": node_config.get("cropClass"),
|
||||
"minConfidence": node_config.get("minConfidence", None),
|
||||
"multiClass": node_config.get("multiClass", False),
|
||||
"expectedClasses": node_config.get("expectedClasses", []),
|
||||
"parallel": node_config.get("parallel", False),
|
||||
"actions": node_config.get("actions", []),
|
||||
"parallelActions": node_config.get("parallelActions", []),
|
||||
"model": model,
|
||||
"branches": [],
|
||||
"redis_client": redis_client,
|
||||
"db_manager": db_manager
|
||||
}
|
||||
logger.debug(f"Configured node {node_config['modelId']} with trigger classes: {node['triggerClasses']}")
|
||||
for child in node_config.get("branches", []):
|
||||
logger.debug(f"Loading branch for parent node {node_config['modelId']}")
|
||||
node["branches"].append(load_pipeline_node(child, mpta_dir, redis_client, db_manager))
|
||||
return node
|
||||
|
||||
def load_pipeline_from_zip(zip_source: str, target_dir: str) -> dict:
|
||||
logger.info(f"Attempting to load pipeline from {zip_source} to {target_dir}")
|
||||
os.makedirs(target_dir, exist_ok=True)
|
||||
zip_path = os.path.join(target_dir, "pipeline.mpta")
|
||||
|
||||
# Parse the source; only local files are supported here.
|
||||
parsed = urlparse(zip_source)
|
||||
if parsed.scheme in ("", "file"):
|
||||
local_path = parsed.path if parsed.scheme == "file" else zip_source
|
||||
logger.debug(f"Checking if local file exists: {local_path}")
|
||||
if os.path.exists(local_path):
|
||||
try:
|
||||
shutil.copy(local_path, zip_path)
|
||||
logger.info(f"Copied local .mpta file from {local_path} to {zip_path}")
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to copy local .mpta file from {local_path}: {str(e)}", exc_info=True)
|
||||
return None
|
||||
else:
|
||||
logger.error(f"Local file {local_path} does not exist. Current directory: {os.getcwd()}")
|
||||
# List all subdirectories of models directory to help debugging
|
||||
if os.path.exists("models"):
|
||||
logger.error(f"Content of models directory: {os.listdir('models')}")
|
||||
for root, dirs, files in os.walk("models"):
|
||||
logger.error(f"Directory {root} contains subdirs: {dirs} and files: {files}")
|
||||
else:
|
||||
logger.error("The models directory doesn't exist")
|
||||
return None
|
||||
else:
|
||||
logger.error(f"HTTP download functionality has been moved. Use a local file path here. Received: {zip_source}")
|
||||
return None
|
||||
|
||||
try:
|
||||
if not os.path.exists(zip_path):
|
||||
logger.error(f"Zip file not found at expected location: {zip_path}")
|
||||
return None
|
||||
|
||||
logger.debug(f"Extracting .mpta file from {zip_path} to {target_dir}")
|
||||
# Extract contents and track the directories created
|
||||
extracted_dirs = []
|
||||
with zipfile.ZipFile(zip_path, "r") as zip_ref:
|
||||
file_list = zip_ref.namelist()
|
||||
logger.debug(f"Files in .mpta archive: {file_list}")
|
||||
|
||||
# Extract and track the top-level directories
|
||||
for file_path in file_list:
|
||||
parts = file_path.split('/')
|
||||
if len(parts) > 1:
|
||||
top_dir = parts[0]
|
||||
if top_dir and top_dir not in extracted_dirs:
|
||||
extracted_dirs.append(top_dir)
|
||||
|
||||
# Now extract the files
|
||||
zip_ref.extractall(target_dir)
|
||||
|
||||
logger.info(f"Successfully extracted .mpta file to {target_dir}")
|
||||
logger.debug(f"Extracted directories: {extracted_dirs}")
|
||||
|
||||
# Check what was actually created after extraction
|
||||
actual_dirs = [d for d in os.listdir(target_dir) if os.path.isdir(os.path.join(target_dir, d))]
|
||||
logger.debug(f"Actual directories created: {actual_dirs}")
|
||||
except zipfile.BadZipFile as e:
|
||||
logger.error(f"Bad zip file {zip_path}: {str(e)}", exc_info=True)
|
||||
return None
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to extract .mpta file {zip_path}: {str(e)}", exc_info=True)
|
||||
return None
|
||||
finally:
|
||||
if os.path.exists(zip_path):
|
||||
os.remove(zip_path)
|
||||
logger.debug(f"Removed temporary zip file: {zip_path}")
|
||||
|
||||
# Use the first extracted directory if it exists, otherwise use the expected name
|
||||
pipeline_name = os.path.basename(zip_source)
|
||||
pipeline_name = os.path.splitext(pipeline_name)[0]
|
||||
|
||||
# Find the directory with pipeline.json
|
||||
mpta_dir = None
|
||||
# First try the expected directory name
|
||||
expected_dir = os.path.join(target_dir, pipeline_name)
|
||||
if os.path.exists(expected_dir) and os.path.exists(os.path.join(expected_dir, "pipeline.json")):
|
||||
mpta_dir = expected_dir
|
||||
logger.debug(f"Found pipeline.json in the expected directory: {mpta_dir}")
|
||||
else:
|
||||
# Look through all subdirectories for pipeline.json
|
||||
for subdir in actual_dirs:
|
||||
potential_dir = os.path.join(target_dir, subdir)
|
||||
if os.path.exists(os.path.join(potential_dir, "pipeline.json")):
|
||||
mpta_dir = potential_dir
|
||||
logger.info(f"Found pipeline.json in directory: {mpta_dir} (different from expected: {expected_dir})")
|
||||
break
|
||||
|
||||
if not mpta_dir:
|
||||
logger.error(f"Could not find pipeline.json in any extracted directory. Directory content: {os.listdir(target_dir)}")
|
||||
return None
|
||||
|
||||
pipeline_json_path = os.path.join(mpta_dir, "pipeline.json")
|
||||
if not os.path.exists(pipeline_json_path):
|
||||
logger.error(f"pipeline.json not found in the .mpta file. Files in directory: {os.listdir(mpta_dir)}")
|
||||
return None
|
||||
|
||||
try:
|
||||
with open(pipeline_json_path, "r") as f:
|
||||
pipeline_config = json.load(f)
|
||||
logger.info(f"Successfully loaded pipeline configuration from {pipeline_json_path}")
|
||||
logger.debug(f"Pipeline config: {json.dumps(pipeline_config, indent=2)}")
|
||||
|
||||
# Establish Redis connection if configured
|
||||
redis_client = None
|
||||
if "redis" in pipeline_config:
|
||||
redis_config = pipeline_config["redis"]
|
||||
if not validate_redis_config(redis_config):
|
||||
logger.error("Invalid Redis configuration, skipping Redis connection")
|
||||
else:
|
||||
try:
|
||||
redis_client = redis.Redis(
|
||||
host=redis_config["host"],
|
||||
port=redis_config["port"],
|
||||
password=redis_config.get("password"),
|
||||
db=redis_config.get("db", 0),
|
||||
decode_responses=True
|
||||
)
|
||||
redis_client.ping()
|
||||
logger.info(f"Successfully connected to Redis at {redis_config['host']}:{redis_config['port']}")
|
||||
except redis.exceptions.ConnectionError as e:
|
||||
logger.error(f"Failed to connect to Redis: {e}")
|
||||
redis_client = None
|
||||
|
||||
# Establish PostgreSQL connection if configured
|
||||
db_manager = None
|
||||
if "postgresql" in pipeline_config:
|
||||
pg_config = pipeline_config["postgresql"]
|
||||
if not validate_postgresql_config(pg_config):
|
||||
logger.error("Invalid PostgreSQL configuration, skipping database connection")
|
||||
else:
|
||||
try:
|
||||
db_manager = DatabaseManager(pg_config)
|
||||
if db_manager.connect():
|
||||
logger.info(f"Successfully connected to PostgreSQL at {pg_config['host']}:{pg_config['port']}")
|
||||
else:
|
||||
logger.error("Failed to connect to PostgreSQL")
|
||||
db_manager = None
|
||||
except Exception as e:
|
||||
logger.error(f"Error initializing PostgreSQL connection: {e}")
|
||||
db_manager = None
|
||||
|
||||
return load_pipeline_node(pipeline_config["pipeline"], mpta_dir, redis_client, db_manager)
|
||||
except json.JSONDecodeError as e:
|
||||
logger.error(f"Error parsing pipeline.json: {str(e)}", exc_info=True)
|
||||
return None
|
||||
except KeyError as e:
|
||||
logger.error(f"Missing key in pipeline.json: {str(e)}", exc_info=True)
|
||||
return None
|
||||
except Exception as e:
|
||||
logger.error(f"Error loading pipeline.json: {str(e)}", exc_info=True)
|
||||
return None
|
||||
|
||||
def execute_actions(node, frame, detection_result, regions_dict=None):
|
||||
if not node["redis_client"] or not node["actions"]:
|
||||
return
|
||||
|
||||
# Create a dynamic context for this detection event
|
||||
from datetime import datetime
|
||||
action_context = {
|
||||
**detection_result,
|
||||
"timestamp_ms": int(time.time() * 1000),
|
||||
"uuid": str(uuid.uuid4()),
|
||||
"timestamp": datetime.now().strftime("%Y-%m-%dT%H-%M-%S"),
|
||||
"filename": f"{uuid.uuid4()}.jpg"
|
||||
}
|
||||
|
||||
for action in node["actions"]:
|
||||
try:
|
||||
if action["type"] == "redis_save_image":
|
||||
key = action["key"].format(**action_context)
|
||||
|
||||
# Check if we need to crop a specific region
|
||||
region_name = action.get("region")
|
||||
image_to_save = frame
|
||||
|
||||
if region_name and regions_dict:
|
||||
cropped_image = crop_region_by_class(frame, regions_dict, region_name)
|
||||
if cropped_image is not None:
|
||||
image_to_save = cropped_image
|
||||
logger.debug(f"Cropped region '{region_name}' for redis_save_image")
|
||||
else:
|
||||
logger.warning(f"Could not crop region '{region_name}', saving full frame instead")
|
||||
|
||||
# Encode image with specified format and quality (default to JPEG)
|
||||
img_format = action.get("format", "jpeg").lower()
|
||||
quality = action.get("quality", 90)
|
||||
|
||||
if img_format == "jpeg":
|
||||
encode_params = [cv2.IMWRITE_JPEG_QUALITY, quality]
|
||||
success, buffer = cv2.imencode('.jpg', image_to_save, encode_params)
|
||||
elif img_format == "png":
|
||||
success, buffer = cv2.imencode('.png', image_to_save)
|
||||
else:
|
||||
success, buffer = cv2.imencode('.jpg', image_to_save, [cv2.IMWRITE_JPEG_QUALITY, quality])
|
||||
|
||||
if not success:
|
||||
logger.error(f"Failed to encode image for redis_save_image")
|
||||
continue
|
||||
|
||||
expire_seconds = action.get("expire_seconds")
|
||||
if expire_seconds:
|
||||
node["redis_client"].setex(key, expire_seconds, buffer.tobytes())
|
||||
logger.info(f"Saved image to Redis with key: {key} (expires in {expire_seconds}s)")
|
||||
else:
|
||||
node["redis_client"].set(key, buffer.tobytes())
|
||||
logger.info(f"Saved image to Redis with key: {key}")
|
||||
action_context["image_key"] = key
|
||||
elif action["type"] == "redis_publish":
|
||||
channel = action["channel"]
|
||||
try:
|
||||
# Handle JSON message format by creating it programmatically
|
||||
message_template = action["message"]
|
||||
|
||||
# Check if the message is JSON-like (starts and ends with braces)
|
||||
if message_template.strip().startswith('{') and message_template.strip().endswith('}'):
|
||||
# Create JSON data programmatically to avoid formatting issues
|
||||
json_data = {}
|
||||
|
||||
# Add common fields
|
||||
json_data["event"] = "frontal_detected"
|
||||
json_data["display_id"] = action_context.get("display_id", "unknown")
|
||||
json_data["session_id"] = action_context.get("session_id")
|
||||
json_data["timestamp"] = action_context.get("timestamp", "")
|
||||
json_data["image_key"] = action_context.get("image_key", "")
|
||||
|
||||
# Convert to JSON string
|
||||
message = json.dumps(json_data)
|
||||
else:
|
||||
# Use regular string formatting for non-JSON messages
|
||||
message = message_template.format(**action_context)
|
||||
|
||||
# Publish to Redis
|
||||
if not node["redis_client"]:
|
||||
logger.error("Redis client is None, cannot publish message")
|
||||
continue
|
||||
|
||||
# Test Redis connection
|
||||
try:
|
||||
node["redis_client"].ping()
|
||||
logger.debug("Redis connection is active")
|
||||
except Exception as ping_error:
|
||||
logger.error(f"Redis connection test failed: {ping_error}")
|
||||
continue
|
||||
|
||||
result = node["redis_client"].publish(channel, message)
|
||||
logger.info(f"Published message to Redis channel '{channel}': {message}")
|
||||
logger.info(f"Redis publish result (subscribers count): {result}")
|
||||
|
||||
# Additional debug info
|
||||
if result == 0:
|
||||
logger.warning(f"No subscribers listening to channel '{channel}'")
|
||||
else:
|
||||
logger.info(f"Message delivered to {result} subscriber(s)")
|
||||
|
||||
except KeyError as e:
|
||||
logger.error(f"Missing key in redis_publish message template: {e}")
|
||||
logger.debug(f"Available context keys: {list(action_context.keys())}")
|
||||
except Exception as e:
|
||||
logger.error(f"Error in redis_publish action: {e}")
|
||||
logger.debug(f"Message template: {action['message']}")
|
||||
logger.debug(f"Available context keys: {list(action_context.keys())}")
|
||||
import traceback
|
||||
logger.debug(f"Full traceback: {traceback.format_exc()}")
|
||||
except Exception as e:
|
||||
logger.error(f"Error executing action {action['type']}: {e}")
|
||||
|
||||
def execute_parallel_actions(node, frame, detection_result, regions_dict):
|
||||
"""Execute parallel actions after all required branches have completed."""
|
||||
if not node.get("parallelActions"):
|
||||
return
|
||||
|
||||
logger.debug("Executing parallel actions...")
|
||||
branch_results = detection_result.get("branch_results", {})
|
||||
|
||||
for action in node["parallelActions"]:
|
||||
try:
|
||||
action_type = action.get("type")
|
||||
logger.debug(f"Processing parallel action: {action_type}")
|
||||
|
||||
if action_type == "postgresql_update_combined":
|
||||
# Check if all required branches have completed
|
||||
wait_for_branches = action.get("waitForBranches", [])
|
||||
missing_branches = [branch for branch in wait_for_branches if branch not in branch_results]
|
||||
|
||||
if missing_branches:
|
||||
logger.warning(f"Cannot execute postgresql_update_combined: missing branch results for {missing_branches}")
|
||||
continue
|
||||
|
||||
logger.info(f"All required branches completed: {wait_for_branches}")
|
||||
|
||||
# Execute the database update
|
||||
execute_postgresql_update_combined(node, action, detection_result, branch_results)
|
||||
else:
|
||||
logger.warning(f"Unknown parallel action type: {action_type}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error executing parallel action {action.get('type', 'unknown')}: {e}")
|
||||
import traceback
|
||||
logger.debug(f"Full traceback: {traceback.format_exc()}")
|
||||
|
||||
def execute_postgresql_update_combined(node, action, detection_result, branch_results):
|
||||
"""Execute a PostgreSQL update with combined branch results."""
|
||||
if not node.get("db_manager"):
|
||||
logger.error("No database manager available for postgresql_update_combined action")
|
||||
return
|
||||
|
||||
try:
|
||||
table = action["table"]
|
||||
key_field = action["key_field"]
|
||||
key_value_template = action["key_value"]
|
||||
fields = action["fields"]
|
||||
|
||||
# Create context for key value formatting
|
||||
action_context = {**detection_result}
|
||||
key_value = key_value_template.format(**action_context)
|
||||
|
||||
logger.info(f"Executing database update: table={table}, {key_field}={key_value}")
|
||||
|
||||
# Process field mappings
|
||||
mapped_fields = {}
|
||||
for db_field, value_template in fields.items():
|
||||
try:
|
||||
mapped_value = resolve_field_mapping(value_template, branch_results, action_context)
|
||||
if mapped_value is not None:
|
||||
mapped_fields[db_field] = mapped_value
|
||||
logger.debug(f"Mapped field: {db_field} = {mapped_value}")
|
||||
else:
|
||||
logger.warning(f"Could not resolve field mapping for {db_field}: {value_template}")
|
||||
except Exception as e:
|
||||
logger.error(f"Error mapping field {db_field} with template '{value_template}': {e}")
|
||||
|
||||
if not mapped_fields:
|
||||
logger.warning("No fields mapped successfully, skipping database update")
|
||||
return
|
||||
|
||||
# Execute the database update
|
||||
success = node["db_manager"].execute_update(table, key_field, key_value, mapped_fields)
|
||||
|
||||
if success:
|
||||
logger.info(f"Successfully updated database: {table} with {len(mapped_fields)} fields")
|
||||
else:
|
||||
logger.error(f"Failed to update database: {table}")
|
||||
|
||||
except KeyError as e:
|
||||
logger.error(f"Missing required field in postgresql_update_combined action: {e}")
|
||||
except Exception as e:
|
||||
logger.error(f"Error in postgresql_update_combined action: {e}")
|
||||
import traceback
|
||||
logger.debug(f"Full traceback: {traceback.format_exc()}")
|
||||
|
||||
def resolve_field_mapping(value_template, branch_results, action_context):
|
||||
"""Resolve field mapping templates like {car_brand_cls_v1.brand}."""
|
||||
try:
|
||||
# Handle simple context variables first (non-branch references)
|
||||
if not '.' in value_template:
|
||||
return value_template.format(**action_context)
|
||||
|
||||
# Handle branch result references like {model_id.field}
|
||||
import re
|
||||
branch_refs = re.findall(r'\{([^}]+\.[^}]+)\}', value_template)
|
||||
|
||||
resolved_template = value_template
|
||||
for ref in branch_refs:
|
||||
try:
|
||||
model_id, field_name = ref.split('.', 1)
|
||||
|
||||
if model_id in branch_results:
|
||||
branch_data = branch_results[model_id]
|
||||
if field_name in branch_data:
|
||||
field_value = branch_data[field_name]
|
||||
resolved_template = resolved_template.replace(f'{{{ref}}}', str(field_value))
|
||||
logger.debug(f"Resolved {ref} to {field_value}")
|
||||
else:
|
||||
logger.warning(f"Field '{field_name}' not found in branch '{model_id}' results. Available fields: {list(branch_data.keys())}")
|
||||
return None
|
||||
else:
|
||||
logger.warning(f"Branch '{model_id}' not found in results. Available branches: {list(branch_results.keys())}")
|
||||
return None
|
||||
except ValueError as e:
|
||||
logger.error(f"Invalid branch reference format: {ref}")
|
||||
return None
|
||||
|
||||
# Format any remaining simple variables
|
||||
try:
|
||||
final_value = resolved_template.format(**action_context)
|
||||
return final_value
|
||||
except KeyError as e:
|
||||
logger.warning(f"Could not resolve context variable in template: {e}")
|
||||
return resolved_template
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error resolving field mapping '{value_template}': {e}")
|
||||
return None
|
||||
|
||||
def run_pipeline(frame, node: dict, return_bbox: bool=False, context=None):
|
||||
"""
|
||||
Enhanced pipeline that supports:
|
||||
- Multi-class detection (detecting multiple classes simultaneously)
|
||||
- Parallel branch processing
|
||||
- Region-based actions and cropping
|
||||
- Context passing for session/camera information
|
||||
"""
|
||||
try:
|
||||
task = getattr(node["model"], "task", None)
|
||||
|
||||
# ─── Classification stage ───────────────────────────────────
|
||||
if task == "classify":
|
||||
results = node["model"].predict(frame, stream=False)
|
||||
if not results:
|
||||
return (None, None) if return_bbox else None
|
||||
|
||||
r = results[0]
|
||||
probs = r.probs
|
||||
if probs is None:
|
||||
return (None, None) if return_bbox else None
|
||||
|
||||
top1_idx = int(probs.top1)
|
||||
top1_conf = float(probs.top1conf)
|
||||
class_name = node["model"].names[top1_idx]
|
||||
|
||||
det = {
|
||||
"class": class_name,
|
||||
"confidence": top1_conf,
|
||||
"id": None,
|
||||
class_name: class_name # Add class name as key for backward compatibility
|
||||
}
|
||||
|
||||
# Add specific field mappings for database operations based on model type
|
||||
model_id = node.get("modelId", "").lower()
|
||||
if "brand" in model_id or "brand_cls" in model_id:
|
||||
det["brand"] = class_name
|
||||
elif "bodytype" in model_id or "body" in model_id:
|
||||
det["body_type"] = class_name
|
||||
elif "color" in model_id:
|
||||
det["color"] = class_name
|
||||
|
||||
execute_actions(node, frame, det)
|
||||
return (det, None) if return_bbox else det
|
||||
|
||||
# ─── Detection stage - Multi-class support ──────────────────
|
||||
tk = node["triggerClassIndices"]
|
||||
logger.debug(f"Running detection for node {node['modelId']} with trigger classes: {node.get('triggerClasses', [])} (indices: {tk})")
|
||||
logger.debug(f"Node configuration: minConfidence={node['minConfidence']}, multiClass={node.get('multiClass', False)}")
|
||||
|
||||
res = node["model"].track(
|
||||
frame,
|
||||
stream=False,
|
||||
persist=True,
|
||||
**({"classes": tk} if tk else {})
|
||||
)[0]
|
||||
|
||||
# Collect all detections above confidence threshold
|
||||
all_detections = []
|
||||
all_boxes = []
|
||||
regions_dict = {}
|
||||
|
||||
logger.debug(f"Raw detection results from model: {len(res.boxes) if res.boxes is not None else 0} detections")
|
||||
|
||||
for i, box in enumerate(res.boxes):
|
||||
conf = float(box.cpu().conf[0])
|
||||
cid = int(box.cpu().cls[0])
|
||||
name = node["model"].names[cid]
|
||||
|
||||
logger.debug(f"Detection {i}: class='{name}' (id={cid}), confidence={conf:.3f}, threshold={node['minConfidence']}")
|
||||
|
||||
if conf < node["minConfidence"]:
|
||||
logger.debug(f" -> REJECTED: confidence {conf:.3f} < threshold {node['minConfidence']}")
|
||||
continue
|
||||
|
||||
xy = box.cpu().xyxy[0]
|
||||
x1, y1, x2, y2 = map(int, xy)
|
||||
bbox = (x1, y1, x2, y2)
|
||||
|
||||
detection = {
|
||||
"class": name,
|
||||
"confidence": conf,
|
||||
"id": box.id.item() if hasattr(box, "id") else None,
|
||||
"bbox": bbox
|
||||
}
|
||||
|
||||
all_detections.append(detection)
|
||||
all_boxes.append(bbox)
|
||||
|
||||
logger.debug(f" -> ACCEPTED: {name} with confidence {conf:.3f}, bbox={bbox}")
|
||||
|
||||
# Store highest confidence detection for each class
|
||||
if name not in regions_dict or conf > regions_dict[name]["confidence"]:
|
||||
regions_dict[name] = {
|
||||
"bbox": bbox,
|
||||
"confidence": conf,
|
||||
"detection": detection
|
||||
}
|
||||
logger.debug(f" -> Updated regions_dict['{name}'] with confidence {conf:.3f}")
|
||||
|
||||
logger.info(f"Detection summary: {len(all_detections)} accepted detections from {len(res.boxes) if res.boxes is not None else 0} total")
|
||||
logger.info(f"Detected classes: {list(regions_dict.keys())}")
|
||||
|
||||
if not all_detections:
|
||||
logger.warning("No detections above confidence threshold - returning null")
|
||||
return (None, None) if return_bbox else None
|
||||
|
||||
# ─── Multi-class validation ─────────────────────────────────
|
||||
if node.get("multiClass", False) and node.get("expectedClasses"):
|
||||
expected_classes = node["expectedClasses"]
|
||||
detected_classes = list(regions_dict.keys())
|
||||
|
||||
logger.info(f"Multi-class validation: expected={expected_classes}, detected={detected_classes}")
|
||||
|
||||
# Check if at least one expected class is detected (flexible mode)
|
||||
matching_classes = [cls for cls in expected_classes if cls in detected_classes]
|
||||
missing_classes = [cls for cls in expected_classes if cls not in detected_classes]
|
||||
|
||||
logger.debug(f"Matching classes: {matching_classes}, Missing classes: {missing_classes}")
|
||||
|
||||
if not matching_classes:
|
||||
# No expected classes found at all
|
||||
logger.warning(f"PIPELINE REJECTED: No expected classes detected. Expected: {expected_classes}, Detected: {detected_classes}")
|
||||
return (None, None) if return_bbox else None
|
||||
|
||||
if missing_classes:
|
||||
logger.info(f"Partial multi-class detection: {matching_classes} found, {missing_classes} missing")
|
||||
else:
|
||||
logger.info(f"Complete multi-class detection success: {detected_classes}")
|
||||
else:
|
||||
logger.debug("No multi-class validation - proceeding with all detections")
|
||||
|
||||
# ─── Execute actions with region information ────────────────
|
||||
detection_result = {
|
||||
"detections": all_detections,
|
||||
"regions": regions_dict,
|
||||
**(context or {})
|
||||
}
|
||||
|
||||
# ─── Create initial database record when Car+Frontal detected ────
|
||||
if node.get("db_manager") and node.get("multiClass", False):
|
||||
# Only create database record if we have both Car and Frontal
|
||||
has_car = "Car" in regions_dict
|
||||
has_frontal = "Frontal" in regions_dict
|
||||
|
||||
if has_car and has_frontal:
|
||||
# Generate UUID session_id since client session is None for now
|
||||
import uuid as uuid_lib
|
||||
from datetime import datetime
|
||||
generated_session_id = str(uuid_lib.uuid4())
|
||||
|
||||
# Insert initial detection record
|
||||
display_id = detection_result.get("display_id", "unknown")
|
||||
timestamp = datetime.now().strftime("%Y-%m-%dT%H-%M-%S")
|
||||
|
||||
inserted_session_id = node["db_manager"].insert_initial_detection(
|
||||
display_id=display_id,
|
||||
captured_timestamp=timestamp,
|
||||
session_id=generated_session_id
|
||||
)
|
||||
|
||||
if inserted_session_id:
|
||||
# Update detection_result with the generated session_id for actions and branches
|
||||
detection_result["session_id"] = inserted_session_id
|
||||
detection_result["timestamp"] = timestamp # Update with proper timestamp
|
||||
logger.info(f"Created initial database record with session_id: {inserted_session_id}")
|
||||
else:
|
||||
logger.debug(f"Database record not created - missing required classes. Has Car: {has_car}, Has Frontal: {has_frontal}")
|
||||
|
||||
execute_actions(node, frame, detection_result, regions_dict)
|
||||
|
||||
# ─── Parallel branch processing ─────────────────────────────
|
||||
if node["branches"]:
|
||||
branch_results = {}
|
||||
|
||||
# Filter branches that should be triggered
|
||||
active_branches = []
|
||||
for br in node["branches"]:
|
||||
trigger_classes = br.get("triggerClasses", [])
|
||||
min_conf = br.get("minConfidence", 0)
|
||||
|
||||
logger.debug(f"Evaluating branch {br['modelId']}: trigger_classes={trigger_classes}, min_conf={min_conf}")
|
||||
|
||||
# Check if any detected class matches branch trigger
|
||||
branch_triggered = False
|
||||
for det_class in regions_dict:
|
||||
det_confidence = regions_dict[det_class]["confidence"]
|
||||
logger.debug(f" Checking detected class '{det_class}' (confidence={det_confidence:.3f}) against triggers {trigger_classes}")
|
||||
|
||||
if (det_class in trigger_classes and det_confidence >= min_conf):
|
||||
active_branches.append(br)
|
||||
branch_triggered = True
|
||||
logger.info(f"Branch {br['modelId']} activated by class '{det_class}' (conf={det_confidence:.3f} >= {min_conf})")
|
||||
break
|
||||
|
||||
if not branch_triggered:
|
||||
logger.debug(f"Branch {br['modelId']} not triggered - no matching classes or insufficient confidence")
|
||||
|
||||
if active_branches:
|
||||
if node.get("parallel", False) or any(br.get("parallel", False) for br in active_branches):
|
||||
# Run branches in parallel
|
||||
with concurrent.futures.ThreadPoolExecutor(max_workers=len(active_branches)) as executor:
|
||||
futures = {}
|
||||
|
||||
for br in active_branches:
|
||||
crop_class = br.get("cropClass", br.get("triggerClasses", [])[0] if br.get("triggerClasses") else None)
|
||||
sub_frame = frame
|
||||
|
||||
logger.info(f"Starting parallel branch: {br['modelId']}, crop_class: {crop_class}")
|
||||
|
||||
if br.get("crop", False) and crop_class:
|
||||
cropped = crop_region_by_class(frame, regions_dict, crop_class)
|
||||
if cropped is not None:
|
||||
sub_frame = cv2.resize(cropped, (224, 224))
|
||||
logger.debug(f"Successfully cropped {crop_class} region for {br['modelId']}")
|
||||
else:
|
||||
logger.warning(f"Failed to crop {crop_class} region for {br['modelId']}, skipping branch")
|
||||
continue
|
||||
|
||||
future = executor.submit(run_pipeline, sub_frame, br, True, context)
|
||||
futures[future] = br
|
||||
|
||||
# Collect results
|
||||
for future in concurrent.futures.as_completed(futures):
|
||||
br = futures[future]
|
||||
try:
|
||||
result, _ = future.result()
|
||||
if result:
|
||||
branch_results[br["modelId"]] = result
|
||||
logger.info(f"Branch {br['modelId']} completed: {result}")
|
||||
except Exception as e:
|
||||
logger.error(f"Branch {br['modelId']} failed: {e}")
|
||||
else:
|
||||
# Run branches sequentially
|
||||
for br in active_branches:
|
||||
crop_class = br.get("cropClass", br.get("triggerClasses", [])[0] if br.get("triggerClasses") else None)
|
||||
sub_frame = frame
|
||||
|
||||
logger.info(f"Starting sequential branch: {br['modelId']}, crop_class: {crop_class}")
|
||||
|
||||
if br.get("crop", False) and crop_class:
|
||||
cropped = crop_region_by_class(frame, regions_dict, crop_class)
|
||||
if cropped is not None:
|
||||
sub_frame = cv2.resize(cropped, (224, 224))
|
||||
logger.debug(f"Successfully cropped {crop_class} region for {br['modelId']}")
|
||||
else:
|
||||
logger.warning(f"Failed to crop {crop_class} region for {br['modelId']}, skipping branch")
|
||||
continue
|
||||
|
||||
try:
|
||||
result, _ = run_pipeline(sub_frame, br, True, context)
|
||||
if result:
|
||||
branch_results[br["modelId"]] = result
|
||||
logger.info(f"Branch {br['modelId']} completed: {result}")
|
||||
else:
|
||||
logger.warning(f"Branch {br['modelId']} returned no result")
|
||||
except Exception as e:
|
||||
logger.error(f"Error in sequential branch {br['modelId']}: {e}")
|
||||
import traceback
|
||||
logger.debug(f"Branch error traceback: {traceback.format_exc()}")
|
||||
|
||||
# Store branch results in detection_result for parallel actions
|
||||
detection_result["branch_results"] = branch_results
|
||||
|
||||
# ─── Execute Parallel Actions ───────────────────────────────
|
||||
if node.get("parallelActions") and "branch_results" in detection_result:
|
||||
execute_parallel_actions(node, frame, detection_result, regions_dict)
|
||||
|
||||
# ─── Return detection result ────────────────────────────────
|
||||
primary_detection = max(all_detections, key=lambda x: x["confidence"])
|
||||
primary_bbox = primary_detection["bbox"]
|
||||
|
||||
# Add branch results to primary detection for compatibility
|
||||
if "branch_results" in detection_result:
|
||||
primary_detection["branch_results"] = detection_result["branch_results"]
|
||||
|
||||
return (primary_detection, primary_bbox) if return_bbox else primary_detection
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in node {node.get('modelId')}: {e}")
|
||||
traceback.print_exc()
|
||||
return (None, None) if return_bbox else None
|
||||
|
|
@ -1,9 +1,7 @@
|
|||
{
|
||||
"poll_interval_ms": 100,
|
||||
"max_streams": 20,
|
||||
"max_streams": 5,
|
||||
"target_fps": 2,
|
||||
"reconnect_interval_sec": 10,
|
||||
"max_retries": -1,
|
||||
"rtsp_buffer_size": 3,
|
||||
"rtsp_tcp_transport": true
|
||||
"reconnect_interval_sec": 5,
|
||||
"max_retries": -1
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1 +0,0 @@
|
|||
# Core package for detector worker
|
||||
|
|
@ -1 +0,0 @@
|
|||
# Communication module for WebSocket and HTTP handling
|
||||
|
|
@ -1,212 +0,0 @@
|
|||
"""
|
||||
Message types, constants, and validation functions for WebSocket communication.
|
||||
"""
|
||||
import json
|
||||
import logging
|
||||
from typing import Dict, Any, Optional, Union
|
||||
from .models import (
|
||||
IncomingMessage, OutgoingMessage,
|
||||
SetSubscriptionListMessage, SetSessionIdMessage, SetProgressionStageMessage,
|
||||
RequestStateMessage, PatchSessionResultMessage,
|
||||
StateReportMessage, ImageDetectionMessage, PatchSessionMessage
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Message type constants
|
||||
class MessageTypes:
|
||||
"""WebSocket message type constants."""
|
||||
|
||||
# Incoming from backend
|
||||
SET_SUBSCRIPTION_LIST = "setSubscriptionList"
|
||||
SET_SESSION_ID = "setSessionId"
|
||||
SET_PROGRESSION_STAGE = "setProgressionStage"
|
||||
REQUEST_STATE = "requestState"
|
||||
PATCH_SESSION_RESULT = "patchSessionResult"
|
||||
|
||||
# Outgoing to backend
|
||||
STATE_REPORT = "stateReport"
|
||||
IMAGE_DETECTION = "imageDetection"
|
||||
PATCH_SESSION = "patchSession"
|
||||
|
||||
|
||||
def parse_incoming_message(raw_message: str) -> Optional[IncomingMessage]:
|
||||
"""
|
||||
Parse incoming WebSocket message and validate against known types.
|
||||
|
||||
Args:
|
||||
raw_message: Raw JSON string from WebSocket
|
||||
|
||||
Returns:
|
||||
Parsed message object or None if invalid
|
||||
"""
|
||||
try:
|
||||
data = json.loads(raw_message)
|
||||
message_type = data.get("type")
|
||||
|
||||
if not message_type:
|
||||
logger.error("Message missing 'type' field")
|
||||
return None
|
||||
|
||||
# Route to appropriate message class
|
||||
if message_type == MessageTypes.SET_SUBSCRIPTION_LIST:
|
||||
return SetSubscriptionListMessage(**data)
|
||||
elif message_type == MessageTypes.SET_SESSION_ID:
|
||||
return SetSessionIdMessage(**data)
|
||||
elif message_type == MessageTypes.SET_PROGRESSION_STAGE:
|
||||
return SetProgressionStageMessage(**data)
|
||||
elif message_type == MessageTypes.REQUEST_STATE:
|
||||
return RequestStateMessage(**data)
|
||||
elif message_type == MessageTypes.PATCH_SESSION_RESULT:
|
||||
return PatchSessionResultMessage(**data)
|
||||
else:
|
||||
logger.warning(f"Unknown message type: {message_type}")
|
||||
return None
|
||||
|
||||
except json.JSONDecodeError as e:
|
||||
logger.error(f"Failed to decode JSON message: {e}")
|
||||
return None
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to parse incoming message: {e}")
|
||||
return None
|
||||
|
||||
|
||||
def serialize_outgoing_message(message: OutgoingMessage) -> str:
|
||||
"""
|
||||
Serialize outgoing message to JSON string.
|
||||
|
||||
Args:
|
||||
message: Message object to serialize
|
||||
|
||||
Returns:
|
||||
JSON string representation
|
||||
"""
|
||||
try:
|
||||
# For ImageDetectionMessage, we need to include None values for abandonment detection
|
||||
from .models import ImageDetectionMessage
|
||||
if isinstance(message, ImageDetectionMessage):
|
||||
return message.model_dump_json(exclude_none=False)
|
||||
else:
|
||||
return message.model_dump_json(exclude_none=True)
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to serialize outgoing message: {e}")
|
||||
raise
|
||||
|
||||
|
||||
def validate_subscription_identifier(identifier: str) -> bool:
|
||||
"""
|
||||
Validate subscription identifier format (displayId;cameraId).
|
||||
|
||||
Args:
|
||||
identifier: Subscription identifier to validate
|
||||
|
||||
Returns:
|
||||
True if valid format, False otherwise
|
||||
"""
|
||||
if not identifier or not isinstance(identifier, str):
|
||||
return False
|
||||
|
||||
parts = identifier.split(';')
|
||||
if len(parts) != 2:
|
||||
logger.error(f"Invalid subscription identifier format: {identifier}")
|
||||
return False
|
||||
|
||||
display_id, camera_id = parts
|
||||
if not display_id or not camera_id:
|
||||
logger.error(f"Empty display or camera ID in identifier: {identifier}")
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
|
||||
def extract_display_identifier(subscription_identifier: str) -> Optional[str]:
|
||||
"""
|
||||
Extract display identifier from subscription identifier.
|
||||
|
||||
Args:
|
||||
subscription_identifier: Full subscription identifier (displayId;cameraId)
|
||||
|
||||
Returns:
|
||||
Display identifier or None if invalid format
|
||||
"""
|
||||
if not validate_subscription_identifier(subscription_identifier):
|
||||
return None
|
||||
|
||||
return subscription_identifier.split(';')[0]
|
||||
|
||||
|
||||
def create_state_report(cpu_usage: float, memory_usage: float,
|
||||
gpu_usage: Optional[float] = None,
|
||||
gpu_memory_usage: Optional[float] = None,
|
||||
camera_connections: Optional[list] = None) -> StateReportMessage:
|
||||
"""
|
||||
Create a state report message with system metrics.
|
||||
|
||||
Args:
|
||||
cpu_usage: CPU usage percentage
|
||||
memory_usage: Memory usage percentage
|
||||
gpu_usage: GPU usage percentage (optional)
|
||||
gpu_memory_usage: GPU memory usage in MB (optional)
|
||||
camera_connections: List of active camera connections
|
||||
|
||||
Returns:
|
||||
StateReportMessage object
|
||||
"""
|
||||
return StateReportMessage(
|
||||
cpuUsage=cpu_usage,
|
||||
memoryUsage=memory_usage,
|
||||
gpuUsage=gpu_usage,
|
||||
gpuMemoryUsage=gpu_memory_usage,
|
||||
cameraConnections=camera_connections or []
|
||||
)
|
||||
|
||||
|
||||
def create_image_detection(subscription_identifier: str, detection_data: Union[Dict[str, Any], None],
|
||||
model_id: int, model_name: str) -> ImageDetectionMessage:
|
||||
"""
|
||||
Create an image detection message.
|
||||
|
||||
Args:
|
||||
subscription_identifier: Camera subscription identifier
|
||||
detection_data: Detection results - Dict for data, {} for empty, None for abandonment
|
||||
model_id: Model identifier
|
||||
model_name: Model name
|
||||
|
||||
Returns:
|
||||
ImageDetectionMessage object
|
||||
"""
|
||||
from .models import DetectionData
|
||||
from typing import Union
|
||||
|
||||
# Handle three cases:
|
||||
# 1. None = car abandonment (detection: null)
|
||||
# 2. {} = empty detection (triggers session creation)
|
||||
# 3. {...} = full detection data (updates session)
|
||||
|
||||
data = DetectionData(
|
||||
detection=detection_data,
|
||||
modelId=model_id,
|
||||
modelName=model_name
|
||||
)
|
||||
|
||||
return ImageDetectionMessage(
|
||||
subscriptionIdentifier=subscription_identifier,
|
||||
data=data
|
||||
)
|
||||
|
||||
|
||||
def create_patch_session(session_id: int, patch_data: Dict[str, Any]) -> PatchSessionMessage:
|
||||
"""
|
||||
Create a patch session message.
|
||||
|
||||
Args:
|
||||
session_id: Session ID to patch
|
||||
patch_data: Partial session data to update
|
||||
|
||||
Returns:
|
||||
PatchSessionMessage object
|
||||
"""
|
||||
return PatchSessionMessage(
|
||||
sessionId=session_id,
|
||||
data=patch_data
|
||||
)
|
||||
|
|
@ -1,150 +0,0 @@
|
|||
"""
|
||||
Message data structures for WebSocket communication.
|
||||
Based on worker.md protocol specification.
|
||||
"""
|
||||
from typing import Dict, Any, List, Optional, Union, Literal
|
||||
from pydantic import BaseModel, Field
|
||||
from datetime import datetime
|
||||
|
||||
|
||||
class SubscriptionObject(BaseModel):
|
||||
"""Individual camera subscription configuration."""
|
||||
subscriptionIdentifier: str = Field(..., description="Format: displayId;cameraId")
|
||||
rtspUrl: Optional[str] = Field(None, description="RTSP stream URL")
|
||||
snapshotUrl: Optional[str] = Field(None, description="HTTP snapshot URL")
|
||||
snapshotInterval: Optional[int] = Field(None, description="Snapshot interval in milliseconds")
|
||||
modelUrl: str = Field(..., description="Pre-signed URL to .mpta file")
|
||||
modelId: int = Field(..., description="Unique model identifier")
|
||||
modelName: str = Field(..., description="Human-readable model name")
|
||||
cropX1: Optional[int] = Field(None, description="Crop region X1 coordinate")
|
||||
cropY1: Optional[int] = Field(None, description="Crop region Y1 coordinate")
|
||||
cropX2: Optional[int] = Field(None, description="Crop region X2 coordinate")
|
||||
cropY2: Optional[int] = Field(None, description="Crop region Y2 coordinate")
|
||||
|
||||
|
||||
class CameraConnection(BaseModel):
|
||||
"""Camera connection status for state reporting."""
|
||||
subscriptionIdentifier: str
|
||||
modelId: int
|
||||
modelName: str
|
||||
online: bool
|
||||
cropX1: Optional[int] = None
|
||||
cropY1: Optional[int] = None
|
||||
cropX2: Optional[int] = None
|
||||
cropY2: Optional[int] = None
|
||||
|
||||
|
||||
class DetectionData(BaseModel):
|
||||
"""
|
||||
Detection result data structure.
|
||||
|
||||
Supports three cases:
|
||||
1. Empty detection: detection = {} (triggers session creation)
|
||||
2. Full detection: detection = {"carBrand": "Honda", ...} (updates session)
|
||||
3. Null detection: detection = None (car abandonment)
|
||||
"""
|
||||
model_config = {
|
||||
"json_encoders": {type(None): lambda v: None},
|
||||
"arbitrary_types_allowed": True
|
||||
}
|
||||
|
||||
detection: Union[Dict[str, Any], None] = Field(
|
||||
default_factory=dict,
|
||||
description="Detection results: {} for empty, {...} for data, None/null for abandonment"
|
||||
)
|
||||
modelId: int
|
||||
modelName: str
|
||||
|
||||
|
||||
# Incoming Messages from Backend to Worker
|
||||
|
||||
class SetSubscriptionListMessage(BaseModel):
|
||||
"""Complete subscription list for declarative state management."""
|
||||
type: Literal["setSubscriptionList"] = "setSubscriptionList"
|
||||
subscriptions: List[SubscriptionObject]
|
||||
|
||||
|
||||
class SetSessionIdPayload(BaseModel):
|
||||
"""Session ID association payload."""
|
||||
displayIdentifier: str
|
||||
sessionId: Optional[int] = None
|
||||
|
||||
|
||||
class SetSessionIdMessage(BaseModel):
|
||||
"""Associate session ID with display."""
|
||||
type: Literal["setSessionId"] = "setSessionId"
|
||||
payload: SetSessionIdPayload
|
||||
|
||||
|
||||
class SetProgressionStagePayload(BaseModel):
|
||||
"""Progression stage payload."""
|
||||
displayIdentifier: str
|
||||
progressionStage: Optional[str] = None
|
||||
|
||||
|
||||
class SetProgressionStageMessage(BaseModel):
|
||||
"""Set progression stage for display."""
|
||||
type: Literal["setProgressionStage"] = "setProgressionStage"
|
||||
payload: SetProgressionStagePayload
|
||||
|
||||
|
||||
class RequestStateMessage(BaseModel):
|
||||
"""Request current worker state."""
|
||||
type: Literal["requestState"] = "requestState"
|
||||
|
||||
|
||||
class PatchSessionResultPayload(BaseModel):
|
||||
"""Patch session result payload."""
|
||||
sessionId: int
|
||||
success: bool
|
||||
message: str
|
||||
|
||||
|
||||
class PatchSessionResultMessage(BaseModel):
|
||||
"""Response to patch session request."""
|
||||
type: Literal["patchSessionResult"] = "patchSessionResult"
|
||||
payload: PatchSessionResultPayload
|
||||
|
||||
|
||||
# Outgoing Messages from Worker to Backend
|
||||
|
||||
class StateReportMessage(BaseModel):
|
||||
"""Periodic heartbeat with system metrics."""
|
||||
type: Literal["stateReport"] = "stateReport"
|
||||
cpuUsage: float
|
||||
memoryUsage: float
|
||||
gpuUsage: Optional[float] = None
|
||||
gpuMemoryUsage: Optional[float] = None
|
||||
cameraConnections: List[CameraConnection]
|
||||
|
||||
|
||||
class ImageDetectionMessage(BaseModel):
|
||||
"""Detection event message."""
|
||||
type: Literal["imageDetection"] = "imageDetection"
|
||||
subscriptionIdentifier: str
|
||||
timestamp: str = Field(default_factory=lambda: datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%S.%fZ"))
|
||||
data: DetectionData
|
||||
|
||||
|
||||
class PatchSessionMessage(BaseModel):
|
||||
"""Request to modify session data."""
|
||||
type: Literal["patchSession"] = "patchSession"
|
||||
sessionId: int
|
||||
data: Dict[str, Any] = Field(..., description="Partial DisplayPersistentData structure")
|
||||
|
||||
|
||||
# Union type for all incoming messages
|
||||
IncomingMessage = Union[
|
||||
SetSubscriptionListMessage,
|
||||
SetSessionIdMessage,
|
||||
SetProgressionStageMessage,
|
||||
RequestStateMessage,
|
||||
PatchSessionResultMessage
|
||||
]
|
||||
|
||||
# Union type for all outgoing messages
|
||||
OutgoingMessage = Union[
|
||||
StateReportMessage,
|
||||
ImageDetectionMessage,
|
||||
PatchSessionMessage
|
||||
]
|
||||
|
|
@ -1,234 +0,0 @@
|
|||
"""
|
||||
Worker state management for system metrics and subscription tracking.
|
||||
"""
|
||||
import logging
|
||||
import psutil
|
||||
import threading
|
||||
from typing import Dict, Set, Optional, List
|
||||
from dataclasses import dataclass, field
|
||||
from .models import CameraConnection, SubscriptionObject
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Try to import torch and pynvml for GPU monitoring
|
||||
try:
|
||||
import torch
|
||||
TORCH_AVAILABLE = True
|
||||
except ImportError:
|
||||
TORCH_AVAILABLE = False
|
||||
logger.warning("PyTorch not available, GPU metrics will not be collected")
|
||||
|
||||
try:
|
||||
import pynvml
|
||||
PYNVML_AVAILABLE = True
|
||||
pynvml.nvmlInit()
|
||||
logger.info("NVIDIA ML Python (pynvml) initialized successfully")
|
||||
except ImportError:
|
||||
PYNVML_AVAILABLE = False
|
||||
logger.debug("pynvml not available, falling back to PyTorch GPU monitoring")
|
||||
except Exception as e:
|
||||
PYNVML_AVAILABLE = False
|
||||
logger.warning(f"Failed to initialize pynvml: {e}")
|
||||
|
||||
|
||||
@dataclass
|
||||
class WorkerState:
|
||||
"""Central state management for the detector worker."""
|
||||
|
||||
# Active subscriptions indexed by subscription identifier
|
||||
subscriptions: Dict[str, SubscriptionObject] = field(default_factory=dict)
|
||||
|
||||
# Session ID mapping: display_identifier -> session_id
|
||||
session_ids: Dict[str, int] = field(default_factory=dict)
|
||||
|
||||
# Progression stage mapping: display_identifier -> stage
|
||||
progression_stages: Dict[str, str] = field(default_factory=dict)
|
||||
|
||||
# Active camera connections for state reporting
|
||||
camera_connections: List[CameraConnection] = field(default_factory=list)
|
||||
|
||||
# Thread lock for state synchronization
|
||||
_lock: threading.RLock = field(default_factory=threading.RLock)
|
||||
|
||||
def set_subscriptions(self, new_subscriptions: List[SubscriptionObject]) -> None:
|
||||
"""
|
||||
Update active subscriptions with declarative list from backend.
|
||||
|
||||
Args:
|
||||
new_subscriptions: Complete list of desired subscriptions
|
||||
"""
|
||||
with self._lock:
|
||||
# Convert to dict for easy lookup
|
||||
new_sub_dict = {sub.subscriptionIdentifier: sub for sub in new_subscriptions}
|
||||
|
||||
# Log changes for debugging
|
||||
current_ids = set(self.subscriptions.keys())
|
||||
new_ids = set(new_sub_dict.keys())
|
||||
|
||||
added = new_ids - current_ids
|
||||
removed = current_ids - new_ids
|
||||
updated = current_ids & new_ids
|
||||
|
||||
if added:
|
||||
logger.info(f"[State Update] Adding subscriptions: {added}")
|
||||
if removed:
|
||||
logger.info(f"[State Update] Removing subscriptions: {removed}")
|
||||
if updated:
|
||||
logger.info(f"[State Update] Updating subscriptions: {updated}")
|
||||
|
||||
# Replace entire subscription dict
|
||||
self.subscriptions = new_sub_dict
|
||||
|
||||
# Update camera connections for state reporting
|
||||
self._update_camera_connections()
|
||||
|
||||
def get_subscription(self, subscription_identifier: str) -> Optional[SubscriptionObject]:
|
||||
"""Get subscription by identifier."""
|
||||
with self._lock:
|
||||
return self.subscriptions.get(subscription_identifier)
|
||||
|
||||
def get_all_subscriptions(self) -> List[SubscriptionObject]:
|
||||
"""Get all active subscriptions."""
|
||||
with self._lock:
|
||||
return list(self.subscriptions.values())
|
||||
|
||||
def set_session_id(self, display_identifier: str, session_id: Optional[int]) -> None:
|
||||
"""
|
||||
Set or clear session ID for a display.
|
||||
|
||||
Args:
|
||||
display_identifier: Display identifier
|
||||
session_id: Session ID to set, or None to clear
|
||||
"""
|
||||
with self._lock:
|
||||
if session_id is None:
|
||||
self.session_ids.pop(display_identifier, None)
|
||||
logger.info(f"[State Update] Cleared session ID for display {display_identifier}")
|
||||
else:
|
||||
self.session_ids[display_identifier] = session_id
|
||||
logger.info(f"[State Update] Set session ID {session_id} for display {display_identifier}")
|
||||
|
||||
def get_session_id(self, display_identifier: str) -> Optional[int]:
|
||||
"""Get session ID for display identifier."""
|
||||
with self._lock:
|
||||
return self.session_ids.get(display_identifier)
|
||||
|
||||
def get_session_id_for_subscription(self, subscription_identifier: str) -> Optional[int]:
|
||||
"""Get session ID for subscription by extracting display identifier."""
|
||||
from .messages import extract_display_identifier
|
||||
|
||||
display_id = extract_display_identifier(subscription_identifier)
|
||||
if display_id:
|
||||
return self.get_session_id(display_id)
|
||||
return None
|
||||
|
||||
def set_progression_stage(self, display_identifier: str, stage: Optional[str]) -> None:
|
||||
"""
|
||||
Set or clear progression stage for a display.
|
||||
|
||||
Args:
|
||||
display_identifier: Display identifier
|
||||
stage: Progression stage to set, or None to clear
|
||||
"""
|
||||
with self._lock:
|
||||
if stage is None:
|
||||
self.progression_stages.pop(display_identifier, None)
|
||||
logger.info(f"[State Update] Cleared progression stage for display {display_identifier}")
|
||||
else:
|
||||
self.progression_stages[display_identifier] = stage
|
||||
logger.info(f"[State Update] Set progression stage '{stage}' for display {display_identifier}")
|
||||
|
||||
def get_progression_stage(self, display_identifier: str) -> Optional[str]:
|
||||
"""Get progression stage for display identifier."""
|
||||
with self._lock:
|
||||
return self.progression_stages.get(display_identifier)
|
||||
|
||||
def _update_camera_connections(self) -> None:
|
||||
"""Update camera connections list for state reporting."""
|
||||
connections = []
|
||||
|
||||
for sub in self.subscriptions.values():
|
||||
connection = CameraConnection(
|
||||
subscriptionIdentifier=sub.subscriptionIdentifier,
|
||||
modelId=sub.modelId,
|
||||
modelName=sub.modelName,
|
||||
online=True, # TODO: Add actual online status tracking
|
||||
cropX1=sub.cropX1,
|
||||
cropY1=sub.cropY1,
|
||||
cropX2=sub.cropX2,
|
||||
cropY2=sub.cropY2
|
||||
)
|
||||
connections.append(connection)
|
||||
|
||||
self.camera_connections = connections
|
||||
|
||||
def get_camera_connections(self) -> List[CameraConnection]:
|
||||
"""Get current camera connections for state reporting."""
|
||||
with self._lock:
|
||||
return self.camera_connections.copy()
|
||||
|
||||
|
||||
class SystemMetrics:
|
||||
"""System metrics collection for state reporting."""
|
||||
|
||||
@staticmethod
|
||||
def get_cpu_usage() -> float:
|
||||
"""Get current CPU usage percentage."""
|
||||
try:
|
||||
return psutil.cpu_percent(interval=0.1)
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to get CPU usage: {e}")
|
||||
return 0.0
|
||||
|
||||
@staticmethod
|
||||
def get_memory_usage() -> float:
|
||||
"""Get current memory usage percentage."""
|
||||
try:
|
||||
return psutil.virtual_memory().percent
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to get memory usage: {e}")
|
||||
return 0.0
|
||||
|
||||
@staticmethod
|
||||
def get_gpu_usage() -> Optional[float]:
|
||||
"""Get current GPU usage percentage."""
|
||||
try:
|
||||
# Prefer pynvml for accurate GPU utilization
|
||||
if PYNVML_AVAILABLE:
|
||||
handle = pynvml.nvmlDeviceGetHandleByIndex(0) # First GPU
|
||||
utilization = pynvml.nvmlDeviceGetUtilizationRates(handle)
|
||||
return float(utilization.gpu)
|
||||
|
||||
# Fallback to PyTorch memory-based estimation
|
||||
elif TORCH_AVAILABLE and torch.cuda.is_available():
|
||||
if hasattr(torch.cuda, 'utilization'):
|
||||
return torch.cuda.utilization()
|
||||
else:
|
||||
# Estimate based on memory usage
|
||||
allocated = torch.cuda.memory_allocated()
|
||||
reserved = torch.cuda.memory_reserved()
|
||||
if reserved > 0:
|
||||
return (allocated / reserved) * 100
|
||||
|
||||
return None
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to get GPU usage: {e}")
|
||||
return None
|
||||
|
||||
@staticmethod
|
||||
def get_gpu_memory_usage() -> Optional[float]:
|
||||
"""Get current GPU memory usage in MB."""
|
||||
if not TORCH_AVAILABLE:
|
||||
return None
|
||||
|
||||
try:
|
||||
if torch.cuda.is_available():
|
||||
return torch.cuda.memory_reserved() / (1024 ** 2) # Convert to MB
|
||||
return None
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to get GPU memory usage: {e}")
|
||||
return None
|
||||
|
||||
|
||||
# Global worker state instance
|
||||
worker_state = WorkerState()
|
||||
|
|
@ -1,677 +0,0 @@
|
|||
"""
|
||||
WebSocket message handling and protocol implementation.
|
||||
"""
|
||||
import asyncio
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import cv2
|
||||
from datetime import datetime, timezone, timedelta
|
||||
from pathlib import Path
|
||||
from typing import Optional
|
||||
from fastapi import WebSocket, WebSocketDisconnect
|
||||
from websockets.exceptions import ConnectionClosedError
|
||||
|
||||
from .messages import (
|
||||
parse_incoming_message, serialize_outgoing_message,
|
||||
MessageTypes, create_state_report
|
||||
)
|
||||
from .models import (
|
||||
SetSubscriptionListMessage, SetSessionIdMessage, SetProgressionStageMessage,
|
||||
RequestStateMessage, PatchSessionResultMessage
|
||||
)
|
||||
from .state import worker_state, SystemMetrics
|
||||
from ..models import ModelManager
|
||||
from ..streaming.manager import shared_stream_manager
|
||||
from ..tracking.integration import TrackingPipelineIntegration
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Constants
|
||||
HEARTBEAT_INTERVAL = 2.0 # seconds
|
||||
WORKER_TIMEOUT_MS = 10000
|
||||
|
||||
# Global model manager instance
|
||||
model_manager = ModelManager()
|
||||
|
||||
|
||||
class WebSocketHandler:
|
||||
"""
|
||||
Handles WebSocket connection lifecycle and message processing.
|
||||
"""
|
||||
|
||||
def __init__(self, websocket: WebSocket):
|
||||
self.websocket = websocket
|
||||
self.connected = False
|
||||
self._heartbeat_task: Optional[asyncio.Task] = None
|
||||
self._message_task: Optional[asyncio.Task] = None
|
||||
self._heartbeat_count = 0
|
||||
self._last_processed_models: set = set() # Cache of last processed model IDs
|
||||
|
||||
async def handle_connection(self) -> None:
|
||||
"""
|
||||
Main connection handler that manages the WebSocket lifecycle.
|
||||
Based on the original architecture from archive/app.py
|
||||
"""
|
||||
client_info = f"{self.websocket.client.host}:{self.websocket.client.port}" if self.websocket.client else "unknown"
|
||||
logger.info(f"Starting WebSocket handler for {client_info}")
|
||||
|
||||
stream_task = None
|
||||
try:
|
||||
logger.info(f"Accepting WebSocket connection from {client_info}")
|
||||
await self.websocket.accept()
|
||||
self.connected = True
|
||||
logger.info(f"WebSocket connection accepted and established for {client_info}")
|
||||
|
||||
# Send immediate heartbeat to show connection is alive
|
||||
await self._send_immediate_heartbeat()
|
||||
|
||||
# Start background tasks (matching original architecture)
|
||||
stream_task = asyncio.create_task(self._process_streams())
|
||||
heartbeat_task = asyncio.create_task(self._send_heartbeat())
|
||||
message_task = asyncio.create_task(self._handle_messages())
|
||||
|
||||
logger.info(f"WebSocket background tasks started for {client_info} (stream + heartbeat + message handler)")
|
||||
|
||||
# Wait for heartbeat and message tasks (stream runs independently)
|
||||
await asyncio.gather(heartbeat_task, message_task)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in WebSocket connection for {client_info}: {e}", exc_info=True)
|
||||
finally:
|
||||
logger.info(f"Cleaning up connection for {client_info}")
|
||||
# Cancel stream task
|
||||
if stream_task and not stream_task.done():
|
||||
stream_task.cancel()
|
||||
try:
|
||||
await stream_task
|
||||
except asyncio.CancelledError:
|
||||
logger.debug(f"Stream task cancelled for {client_info}")
|
||||
await self._cleanup()
|
||||
|
||||
async def _send_immediate_heartbeat(self) -> None:
|
||||
"""Send immediate heartbeat on connection to show we're alive."""
|
||||
try:
|
||||
cpu_usage = SystemMetrics.get_cpu_usage()
|
||||
memory_usage = SystemMetrics.get_memory_usage()
|
||||
gpu_usage = SystemMetrics.get_gpu_usage()
|
||||
gpu_memory_usage = SystemMetrics.get_gpu_memory_usage()
|
||||
camera_connections = worker_state.get_camera_connections()
|
||||
|
||||
state_report = create_state_report(
|
||||
cpu_usage=cpu_usage,
|
||||
memory_usage=memory_usage,
|
||||
gpu_usage=gpu_usage,
|
||||
gpu_memory_usage=gpu_memory_usage,
|
||||
camera_connections=camera_connections
|
||||
)
|
||||
|
||||
await self._send_message(state_report)
|
||||
logger.info(f"[TX → Backend] Initial stateReport: CPU {cpu_usage:.1f}%, Memory {memory_usage:.1f}%, "
|
||||
f"GPU {gpu_usage or 'N/A'}, {len(camera_connections)} cameras")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error sending immediate heartbeat: {e}")
|
||||
|
||||
async def _send_heartbeat(self) -> None:
|
||||
"""Send periodic state reports as heartbeat."""
|
||||
while self.connected:
|
||||
try:
|
||||
# Collect system metrics
|
||||
cpu_usage = SystemMetrics.get_cpu_usage()
|
||||
memory_usage = SystemMetrics.get_memory_usage()
|
||||
gpu_usage = SystemMetrics.get_gpu_usage()
|
||||
gpu_memory_usage = SystemMetrics.get_gpu_memory_usage()
|
||||
camera_connections = worker_state.get_camera_connections()
|
||||
|
||||
# Create and send state report
|
||||
state_report = create_state_report(
|
||||
cpu_usage=cpu_usage,
|
||||
memory_usage=memory_usage,
|
||||
gpu_usage=gpu_usage,
|
||||
gpu_memory_usage=gpu_memory_usage,
|
||||
camera_connections=camera_connections
|
||||
)
|
||||
|
||||
await self._send_message(state_report)
|
||||
|
||||
# Only log full details every 10th heartbeat, otherwise just show a dot
|
||||
self._heartbeat_count += 1
|
||||
if self._heartbeat_count % 10 == 0:
|
||||
logger.info(f"[TX → Backend] Heartbeat #{self._heartbeat_count}: CPU {cpu_usage:.1f}%, Memory {memory_usage:.1f}%, "
|
||||
f"GPU {gpu_usage or 'N/A'}, {len(camera_connections)} cameras")
|
||||
else:
|
||||
print(".", end="", flush=True) # Just show a dot to indicate heartbeat activity
|
||||
|
||||
await asyncio.sleep(HEARTBEAT_INTERVAL)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error sending heartbeat: {e}")
|
||||
break
|
||||
|
||||
async def _handle_messages(self) -> None:
|
||||
"""Handle incoming WebSocket messages."""
|
||||
while self.connected:
|
||||
try:
|
||||
raw_message = await self.websocket.receive_text()
|
||||
logger.info(f"[RX ← Backend] {raw_message}")
|
||||
|
||||
# Parse incoming message
|
||||
message = parse_incoming_message(raw_message)
|
||||
if not message:
|
||||
logger.warning("Failed to parse incoming message")
|
||||
continue
|
||||
|
||||
# Route message to appropriate handler
|
||||
await self._route_message(message)
|
||||
|
||||
except (WebSocketDisconnect, ConnectionClosedError) as e:
|
||||
logger.warning(f"WebSocket disconnected: {e}")
|
||||
break
|
||||
except json.JSONDecodeError:
|
||||
logger.error("Received invalid JSON message")
|
||||
except Exception as e:
|
||||
logger.error(f"Error handling message: {e}")
|
||||
break
|
||||
|
||||
async def _route_message(self, message) -> None:
|
||||
"""Route parsed message to appropriate handler."""
|
||||
message_type = message.type
|
||||
|
||||
try:
|
||||
if message_type == MessageTypes.SET_SUBSCRIPTION_LIST:
|
||||
await self._handle_set_subscription_list(message)
|
||||
elif message_type == MessageTypes.SET_SESSION_ID:
|
||||
await self._handle_set_session_id(message)
|
||||
elif message_type == MessageTypes.SET_PROGRESSION_STAGE:
|
||||
await self._handle_set_progression_stage(message)
|
||||
elif message_type == MessageTypes.REQUEST_STATE:
|
||||
await self._handle_request_state(message)
|
||||
elif message_type == MessageTypes.PATCH_SESSION_RESULT:
|
||||
await self._handle_patch_session_result(message)
|
||||
else:
|
||||
logger.warning(f"Unknown message type: {message_type}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error handling {message_type} message: {e}")
|
||||
|
||||
async def _handle_set_subscription_list(self, message: SetSubscriptionListMessage) -> None:
|
||||
"""Handle setSubscriptionList message for declarative subscription management."""
|
||||
logger.info(f"[RX Processing] setSubscriptionList with {len(message.subscriptions)} subscriptions")
|
||||
|
||||
# Update worker state with new subscriptions
|
||||
worker_state.set_subscriptions(message.subscriptions)
|
||||
|
||||
# Phase 2: Download and manage models
|
||||
await self._ensure_models(message.subscriptions)
|
||||
|
||||
# Phase 3 & 4: Integrate with streaming management and tracking
|
||||
await self._update_stream_subscriptions(message.subscriptions)
|
||||
|
||||
logger.info("Subscription list updated successfully")
|
||||
|
||||
async def _ensure_models(self, subscriptions) -> None:
|
||||
"""Ensure all required models are downloaded and available."""
|
||||
# Extract unique model requirements
|
||||
unique_models = {}
|
||||
for subscription in subscriptions:
|
||||
model_id = subscription.modelId
|
||||
if model_id not in unique_models:
|
||||
unique_models[model_id] = {
|
||||
'model_url': subscription.modelUrl,
|
||||
'model_name': subscription.modelName
|
||||
}
|
||||
|
||||
# Check if model set has changed to avoid redundant processing
|
||||
current_model_ids = set(unique_models.keys())
|
||||
if current_model_ids == self._last_processed_models:
|
||||
logger.debug(f"[Model Management] Model set unchanged {list(current_model_ids)}, skipping checks")
|
||||
return
|
||||
|
||||
logger.info(f"[Model Management] Processing {len(unique_models)} unique models: {list(unique_models.keys())}")
|
||||
self._last_processed_models = current_model_ids
|
||||
|
||||
# Check and download models concurrently
|
||||
download_tasks = []
|
||||
for model_id, model_info in unique_models.items():
|
||||
task = asyncio.create_task(
|
||||
self._ensure_single_model(model_id, model_info['model_url'], model_info['model_name'])
|
||||
)
|
||||
download_tasks.append(task)
|
||||
|
||||
# Wait for all downloads to complete
|
||||
if download_tasks:
|
||||
results = await asyncio.gather(*download_tasks, return_exceptions=True)
|
||||
|
||||
# Log results
|
||||
success_count = 0
|
||||
for i, result in enumerate(results):
|
||||
model_id = list(unique_models.keys())[i]
|
||||
if isinstance(result, Exception):
|
||||
logger.error(f"[Model Management] Failed to ensure model {model_id}: {result}")
|
||||
elif result:
|
||||
success_count += 1
|
||||
logger.info(f"[Model Management] Model {model_id} ready for use")
|
||||
else:
|
||||
logger.error(f"[Model Management] Failed to ensure model {model_id}")
|
||||
|
||||
logger.info(f"[Model Management] Successfully ensured {success_count}/{len(unique_models)} models")
|
||||
|
||||
async def _update_stream_subscriptions(self, subscriptions) -> None:
|
||||
"""Update streaming subscriptions with tracking integration."""
|
||||
try:
|
||||
# Convert subscriptions to the format expected by StreamManager
|
||||
subscription_payloads = []
|
||||
for subscription in subscriptions:
|
||||
payload = {
|
||||
'subscriptionIdentifier': subscription.subscriptionIdentifier,
|
||||
'rtspUrl': subscription.rtspUrl,
|
||||
'snapshotUrl': subscription.snapshotUrl,
|
||||
'snapshotInterval': subscription.snapshotInterval,
|
||||
'modelId': subscription.modelId,
|
||||
'modelUrl': subscription.modelUrl,
|
||||
'modelName': subscription.modelName
|
||||
}
|
||||
# Add crop coordinates if present
|
||||
if hasattr(subscription, 'cropX1'):
|
||||
payload.update({
|
||||
'cropX1': subscription.cropX1,
|
||||
'cropY1': subscription.cropY1,
|
||||
'cropX2': subscription.cropX2,
|
||||
'cropY2': subscription.cropY2
|
||||
})
|
||||
subscription_payloads.append(payload)
|
||||
|
||||
# Reconcile subscriptions with StreamManager
|
||||
logger.info("[Streaming] Reconciling stream subscriptions with tracking")
|
||||
reconcile_result = await self._reconcile_subscriptions_with_tracking(subscription_payloads)
|
||||
|
||||
logger.info(f"[Streaming] Subscription reconciliation complete: "
|
||||
f"added={reconcile_result.get('added', 0)}, "
|
||||
f"removed={reconcile_result.get('removed', 0)}, "
|
||||
f"failed={reconcile_result.get('failed', 0)}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error updating stream subscriptions: {e}", exc_info=True)
|
||||
|
||||
async def _reconcile_subscriptions_with_tracking(self, target_subscriptions) -> dict:
|
||||
"""Reconcile subscriptions with tracking integration."""
|
||||
try:
|
||||
# Create separate tracking integrations for each subscription (camera isolation)
|
||||
tracking_integrations = {}
|
||||
|
||||
for subscription_payload in target_subscriptions:
|
||||
subscription_id = subscription_payload['subscriptionIdentifier']
|
||||
model_id = subscription_payload['modelId']
|
||||
|
||||
# Create separate tracking integration per subscription for camera isolation
|
||||
# Get pipeline configuration for this model
|
||||
pipeline_parser = model_manager.get_pipeline_config(model_id)
|
||||
if pipeline_parser:
|
||||
# Create tracking integration with message sender (separate instance per camera)
|
||||
tracking_integration = TrackingPipelineIntegration(
|
||||
pipeline_parser, model_manager, model_id, self._send_message
|
||||
)
|
||||
|
||||
# Initialize tracking model
|
||||
success = await tracking_integration.initialize_tracking_model()
|
||||
if success:
|
||||
tracking_integrations[subscription_id] = tracking_integration
|
||||
logger.info(f"[Tracking] Created isolated tracking integration for subscription {subscription_id} (model {model_id})")
|
||||
else:
|
||||
logger.warning(f"[Tracking] Failed to initialize tracking for subscription {subscription_id} (model {model_id})")
|
||||
else:
|
||||
logger.warning(f"[Tracking] No pipeline config found for model {model_id} in subscription {subscription_id}")
|
||||
|
||||
# Now reconcile with StreamManager, adding tracking integrations
|
||||
current_subscription_ids = set()
|
||||
for subscription_info in shared_stream_manager.get_all_subscriptions():
|
||||
current_subscription_ids.add(subscription_info.subscription_id)
|
||||
|
||||
target_subscription_ids = {sub['subscriptionIdentifier'] for sub in target_subscriptions}
|
||||
|
||||
# Find subscriptions to remove and add
|
||||
to_remove = current_subscription_ids - target_subscription_ids
|
||||
to_add = target_subscription_ids - current_subscription_ids
|
||||
|
||||
# Remove old subscriptions
|
||||
removed_count = 0
|
||||
for subscription_id in to_remove:
|
||||
if shared_stream_manager.remove_subscription(subscription_id):
|
||||
removed_count += 1
|
||||
logger.info(f"[Streaming] Removed subscription {subscription_id}")
|
||||
|
||||
# Add new subscriptions with tracking
|
||||
added_count = 0
|
||||
failed_count = 0
|
||||
for subscription_payload in target_subscriptions:
|
||||
subscription_id = subscription_payload['subscriptionIdentifier']
|
||||
if subscription_id in to_add:
|
||||
success = await self._add_subscription_with_tracking(
|
||||
subscription_payload, tracking_integrations
|
||||
)
|
||||
if success:
|
||||
added_count += 1
|
||||
logger.info(f"[Streaming] Added subscription {subscription_id} with tracking")
|
||||
else:
|
||||
failed_count += 1
|
||||
logger.error(f"[Streaming] Failed to add subscription {subscription_id}")
|
||||
|
||||
return {
|
||||
'removed': removed_count,
|
||||
'added': added_count,
|
||||
'failed': failed_count,
|
||||
'total_active': len(shared_stream_manager.get_all_subscriptions())
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in subscription reconciliation with tracking: {e}", exc_info=True)
|
||||
return {'removed': 0, 'added': 0, 'failed': 0, 'total_active': 0}
|
||||
|
||||
async def _add_subscription_with_tracking(self, payload, tracking_integrations) -> bool:
|
||||
"""Add a subscription with tracking integration."""
|
||||
try:
|
||||
from ..streaming.manager import StreamConfig
|
||||
|
||||
subscription_id = payload['subscriptionIdentifier']
|
||||
camera_id = subscription_id.split(';')[-1]
|
||||
model_id = payload['modelId']
|
||||
|
||||
logger.info(f"[SUBSCRIPTION_MAPPING] subscription_id='{subscription_id}' → camera_id='{camera_id}'")
|
||||
|
||||
# Get tracking integration for this subscription (camera-isolated)
|
||||
tracking_integration = tracking_integrations.get(subscription_id)
|
||||
|
||||
# Extract crop coordinates if present
|
||||
crop_coords = None
|
||||
if all(key in payload for key in ['cropX1', 'cropY1', 'cropX2', 'cropY2']):
|
||||
crop_coords = (
|
||||
payload['cropX1'],
|
||||
payload['cropY1'],
|
||||
payload['cropX2'],
|
||||
payload['cropY2']
|
||||
)
|
||||
|
||||
# Create stream configuration
|
||||
stream_config = StreamConfig(
|
||||
camera_id=camera_id,
|
||||
rtsp_url=payload.get('rtspUrl'),
|
||||
snapshot_url=payload.get('snapshotUrl'),
|
||||
snapshot_interval=payload.get('snapshotInterval', 5000),
|
||||
max_retries=3,
|
||||
)
|
||||
|
||||
# Add subscription to StreamManager with tracking
|
||||
success = shared_stream_manager.add_subscription(
|
||||
subscription_id=subscription_id,
|
||||
stream_config=stream_config,
|
||||
crop_coords=crop_coords,
|
||||
model_id=model_id,
|
||||
model_url=payload.get('modelUrl'),
|
||||
tracking_integration=tracking_integration
|
||||
)
|
||||
|
||||
if success and tracking_integration:
|
||||
logger.info(f"[Tracking] Subscription {subscription_id} configured with isolated tracking for model {model_id}")
|
||||
|
||||
return success
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error adding subscription with tracking: {e}", exc_info=True)
|
||||
return False
|
||||
|
||||
async def _ensure_single_model(self, model_id: int, model_url: str, model_name: str) -> bool:
|
||||
"""Ensure a single model is downloaded and available."""
|
||||
try:
|
||||
# Check if model is already available
|
||||
if model_manager.is_model_downloaded(model_id):
|
||||
logger.info(f"[Model Management] Model {model_id} ({model_name}) already available")
|
||||
return True
|
||||
|
||||
# Download and extract model in a thread pool to avoid blocking the event loop
|
||||
logger.info(f"[Model Management] Downloading model {model_id} ({model_name}) from {model_url}")
|
||||
|
||||
# Use asyncio.to_thread for CPU-bound operations (Python 3.9+)
|
||||
# For compatibility, we'll use run_in_executor
|
||||
loop = asyncio.get_event_loop()
|
||||
model_path = await loop.run_in_executor(
|
||||
None,
|
||||
model_manager.ensure_model,
|
||||
model_id,
|
||||
model_url,
|
||||
model_name
|
||||
)
|
||||
|
||||
if model_path:
|
||||
logger.info(f"[Model Management] Successfully prepared model {model_id} at {model_path}")
|
||||
return True
|
||||
else:
|
||||
logger.error(f"[Model Management] Failed to prepare model {model_id}")
|
||||
return False
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[Model Management] Exception ensuring model {model_id}: {str(e)}", exc_info=True)
|
||||
return False
|
||||
|
||||
async def _save_snapshot(self, display_identifier: str, session_id: int) -> None:
|
||||
"""
|
||||
Save snapshot image to images folder after receiving sessionId.
|
||||
|
||||
Args:
|
||||
display_identifier: Display identifier to match with subscriptionIdentifier
|
||||
session_id: Session ID to include in filename
|
||||
"""
|
||||
try:
|
||||
# Find subscription that matches the displayIdentifier
|
||||
matching_subscription = None
|
||||
for subscription in worker_state.get_all_subscriptions():
|
||||
# Extract display ID from subscriptionIdentifier (format: displayId;cameraId)
|
||||
from .messages import extract_display_identifier
|
||||
sub_display_id = extract_display_identifier(subscription.subscriptionIdentifier)
|
||||
if sub_display_id == display_identifier:
|
||||
matching_subscription = subscription
|
||||
break
|
||||
|
||||
if not matching_subscription:
|
||||
logger.error(f"[Snapshot Save] No subscription found for display {display_identifier}")
|
||||
return
|
||||
|
||||
if not matching_subscription.snapshotUrl:
|
||||
logger.error(f"[Snapshot Save] No snapshotUrl found for display {display_identifier}")
|
||||
return
|
||||
|
||||
# Ensure images directory exists (relative path for Docker bind mount)
|
||||
images_dir = Path("images")
|
||||
images_dir.mkdir(exist_ok=True)
|
||||
|
||||
# Generate filename with timestamp and session ID
|
||||
timestamp = datetime.now(tz=timezone(timedelta(hours=7))).strftime("%Y%m%d_%H%M%S")
|
||||
filename = f"{session_id}_{display_identifier}_{timestamp}.jpg"
|
||||
filepath = images_dir / filename
|
||||
|
||||
# Use existing HTTPSnapshotReader to fetch snapshot
|
||||
logger.info(f"[Snapshot Save] Fetching snapshot from {matching_subscription.snapshotUrl}")
|
||||
|
||||
# Run snapshot fetch in thread pool to avoid blocking async loop
|
||||
loop = asyncio.get_event_loop()
|
||||
frame = await loop.run_in_executor(None, self._fetch_snapshot_sync, matching_subscription.snapshotUrl)
|
||||
|
||||
if frame is not None:
|
||||
# Save the image using OpenCV
|
||||
success = cv2.imwrite(str(filepath), frame)
|
||||
if success:
|
||||
logger.info(f"[Snapshot Save] Successfully saved snapshot to {filepath}")
|
||||
else:
|
||||
logger.error(f"[Snapshot Save] Failed to save image file {filepath}")
|
||||
else:
|
||||
logger.error(f"[Snapshot Save] Failed to fetch snapshot from {matching_subscription.snapshotUrl}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[Snapshot Save] Error saving snapshot for display {display_identifier}: {e}", exc_info=True)
|
||||
|
||||
def _fetch_snapshot_sync(self, snapshot_url: str):
|
||||
"""
|
||||
Synchronous snapshot fetching using existing HTTPSnapshotReader infrastructure.
|
||||
|
||||
Args:
|
||||
snapshot_url: URL to fetch snapshot from
|
||||
|
||||
Returns:
|
||||
np.ndarray or None: Fetched frame or None on error
|
||||
"""
|
||||
try:
|
||||
from ..streaming.readers import HTTPSnapshotReader
|
||||
|
||||
# Create temporary snapshot reader for single fetch
|
||||
snapshot_reader = HTTPSnapshotReader(
|
||||
camera_id="temp_snapshot",
|
||||
snapshot_url=snapshot_url,
|
||||
interval_ms=5000 # Not used for single fetch
|
||||
)
|
||||
|
||||
# Use existing fetch_single_snapshot method
|
||||
return snapshot_reader.fetch_single_snapshot()
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in sync snapshot fetch: {e}")
|
||||
return None
|
||||
|
||||
async def _handle_set_session_id(self, message: SetSessionIdMessage) -> None:
|
||||
"""Handle setSessionId message."""
|
||||
display_identifier = message.payload.displayIdentifier
|
||||
session_id = str(message.payload.sessionId) if message.payload.sessionId is not None else None
|
||||
|
||||
logger.info(f"[RX Processing] setSessionId for display {display_identifier}: {session_id}")
|
||||
|
||||
# Update worker state
|
||||
worker_state.set_session_id(display_identifier, session_id)
|
||||
|
||||
# Update tracking integrations with session ID
|
||||
shared_stream_manager.set_session_id(display_identifier, session_id)
|
||||
|
||||
async def _handle_set_progression_stage(self, message: SetProgressionStageMessage) -> None:
|
||||
"""Handle setProgressionStage message."""
|
||||
display_identifier = message.payload.displayIdentifier
|
||||
stage = message.payload.progressionStage
|
||||
|
||||
logger.info(f"[RX Processing] setProgressionStage for display {display_identifier}: {stage}")
|
||||
|
||||
# Update worker state
|
||||
worker_state.set_progression_stage(display_identifier, stage)
|
||||
|
||||
# Update tracking integration for car abandonment detection
|
||||
session_id = worker_state.get_session_id(display_identifier)
|
||||
if session_id:
|
||||
shared_stream_manager.set_progression_stage(session_id, stage)
|
||||
|
||||
# Save snapshot image when progression stage is car_fueling
|
||||
if stage == 'car_fueling' and session_id:
|
||||
await self._save_snapshot(display_identifier, session_id)
|
||||
|
||||
# If stage indicates session is cleared/finished, clear from tracking
|
||||
if stage in ['finished', 'cleared', 'idle']:
|
||||
# Get session ID for this display and clear it
|
||||
if session_id:
|
||||
shared_stream_manager.clear_session_id(session_id)
|
||||
logger.info(f"[Tracking] Cleared session {session_id} due to progression stage: {stage}")
|
||||
|
||||
async def _handle_request_state(self, message: RequestStateMessage) -> None:
|
||||
"""Handle requestState message by sending immediate state report."""
|
||||
logger.debug("[RX Processing] requestState - sending immediate state report")
|
||||
|
||||
# Collect metrics and send state report
|
||||
cpu_usage = SystemMetrics.get_cpu_usage()
|
||||
memory_usage = SystemMetrics.get_memory_usage()
|
||||
gpu_usage = SystemMetrics.get_gpu_usage()
|
||||
gpu_memory_usage = SystemMetrics.get_gpu_memory_usage()
|
||||
camera_connections = worker_state.get_camera_connections()
|
||||
|
||||
state_report = create_state_report(
|
||||
cpu_usage=cpu_usage,
|
||||
memory_usage=memory_usage,
|
||||
gpu_usage=gpu_usage,
|
||||
gpu_memory_usage=gpu_memory_usage,
|
||||
camera_connections=camera_connections
|
||||
)
|
||||
|
||||
await self._send_message(state_report)
|
||||
|
||||
async def _handle_patch_session_result(self, message: PatchSessionResultMessage) -> None:
|
||||
"""Handle patchSessionResult message."""
|
||||
payload = message.payload
|
||||
logger.info(f"[RX Processing] patchSessionResult for session {payload.sessionId}: "
|
||||
f"success={payload.success}, message='{payload.message}'")
|
||||
|
||||
# TODO: Handle patch session result if needed
|
||||
# For now, just log the response
|
||||
|
||||
async def _send_message(self, message) -> None:
|
||||
"""Send message to backend via WebSocket."""
|
||||
if not self.connected:
|
||||
logger.warning("Cannot send message: WebSocket not connected")
|
||||
return
|
||||
|
||||
try:
|
||||
json_message = serialize_outgoing_message(message)
|
||||
await self.websocket.send_text(json_message)
|
||||
# Log non-heartbeat messages only (heartbeats are logged in their respective functions)
|
||||
if not (hasattr(message, 'type') and message.type == 'stateReport'):
|
||||
logger.info(f"[TX → Backend] {json_message}")
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to send WebSocket message: {e}")
|
||||
raise
|
||||
|
||||
async def _process_streams(self) -> None:
|
||||
"""
|
||||
Stream processing task that handles frame processing and detection.
|
||||
This is a placeholder for Phase 2 - currently just logs that it's running.
|
||||
"""
|
||||
logger.info("Stream processing task started")
|
||||
try:
|
||||
while self.connected:
|
||||
# Get current subscriptions
|
||||
subscriptions = worker_state.get_all_subscriptions()
|
||||
|
||||
# TODO: Phase 2 - Add actual frame processing logic here
|
||||
# This will include:
|
||||
# - Frame reading from RTSP/HTTP streams
|
||||
# - Model inference using loaded pipelines
|
||||
# - Detection result sending via WebSocket
|
||||
|
||||
# Sleep to prevent excessive CPU usage (similar to old poll_interval)
|
||||
await asyncio.sleep(0.1) # 100ms polling interval
|
||||
|
||||
except asyncio.CancelledError:
|
||||
logger.info("Stream processing task cancelled")
|
||||
except Exception as e:
|
||||
logger.error(f"Error in stream processing: {e}", exc_info=True)
|
||||
|
||||
async def _cleanup(self) -> None:
|
||||
"""Clean up resources when connection closes."""
|
||||
logger.info("Cleaning up WebSocket connection")
|
||||
self.connected = False
|
||||
|
||||
# Cancel background tasks
|
||||
if self._heartbeat_task and not self._heartbeat_task.done():
|
||||
self._heartbeat_task.cancel()
|
||||
if self._message_task and not self._message_task.done():
|
||||
self._message_task.cancel()
|
||||
|
||||
# Clear worker state
|
||||
worker_state.set_subscriptions([])
|
||||
worker_state.session_ids.clear()
|
||||
worker_state.progression_stages.clear()
|
||||
|
||||
logger.info("WebSocket connection cleanup completed")
|
||||
|
||||
|
||||
# Factory function for FastAPI integration
|
||||
async def websocket_endpoint(websocket: WebSocket) -> None:
|
||||
"""
|
||||
FastAPI WebSocket endpoint handler.
|
||||
|
||||
Args:
|
||||
websocket: FastAPI WebSocket connection
|
||||
"""
|
||||
handler = WebSocketHandler(websocket)
|
||||
await handler.handle_connection()
|
||||
|
|
@ -1,10 +0,0 @@
|
|||
"""
|
||||
Detection module for the Python Detector Worker.
|
||||
|
||||
This module provides the main detection pipeline orchestration and parallel branch processing
|
||||
for advanced computer vision detection systems.
|
||||
"""
|
||||
from .pipeline import DetectionPipeline
|
||||
from .branches import BranchProcessor
|
||||
|
||||
__all__ = ['DetectionPipeline', 'BranchProcessor']
|
||||
|
|
@ -1,791 +0,0 @@
|
|||
"""
|
||||
Parallel Branch Processing Module.
|
||||
Handles concurrent execution of classification branches and result synchronization.
|
||||
"""
|
||||
import logging
|
||||
import asyncio
|
||||
import time
|
||||
from typing import Dict, List, Optional, Any, Tuple
|
||||
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||||
import numpy as np
|
||||
import cv2
|
||||
|
||||
from ..models.inference import YOLOWrapper
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class BranchProcessor:
|
||||
"""
|
||||
Handles parallel processing of classification branches.
|
||||
Manages branch synchronization and result collection.
|
||||
"""
|
||||
|
||||
def __init__(self, model_manager: Any, model_id: int):
|
||||
"""
|
||||
Initialize branch processor.
|
||||
|
||||
Args:
|
||||
model_manager: Model manager for loading models
|
||||
model_id: The model ID to use for loading models
|
||||
"""
|
||||
self.model_manager = model_manager
|
||||
self.model_id = model_id
|
||||
|
||||
# Branch models cache
|
||||
self.branch_models: Dict[str, YOLOWrapper] = {}
|
||||
|
||||
# Thread pool for parallel execution
|
||||
self.executor = ThreadPoolExecutor(max_workers=4)
|
||||
|
||||
# Storage managers (set during initialization)
|
||||
self.redis_manager = None
|
||||
self.db_manager = None
|
||||
|
||||
# Statistics
|
||||
self.stats = {
|
||||
'branches_processed': 0,
|
||||
'parallel_executions': 0,
|
||||
'total_processing_time': 0.0,
|
||||
'models_loaded': 0
|
||||
}
|
||||
|
||||
logger.info("BranchProcessor initialized")
|
||||
|
||||
async def initialize(self, pipeline_config: Any, redis_manager: Any, db_manager: Any) -> bool:
|
||||
"""
|
||||
Initialize branch processor with pipeline configuration.
|
||||
|
||||
Args:
|
||||
pipeline_config: Pipeline configuration object
|
||||
redis_manager: Redis manager instance
|
||||
db_manager: Database manager instance
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
try:
|
||||
self.redis_manager = redis_manager
|
||||
self.db_manager = db_manager
|
||||
|
||||
# Pre-load branch models if they exist
|
||||
branches = getattr(pipeline_config, 'branches', [])
|
||||
if branches:
|
||||
await self._preload_branch_models(branches)
|
||||
|
||||
logger.info(f"BranchProcessor initialized with {len(self.branch_models)} models")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error initializing branch processor: {e}", exc_info=True)
|
||||
return False
|
||||
|
||||
async def _preload_branch_models(self, branches: List[Any]) -> None:
|
||||
"""
|
||||
Pre-load all branch models for faster execution.
|
||||
|
||||
Args:
|
||||
branches: List of branch configurations
|
||||
"""
|
||||
for branch in branches:
|
||||
try:
|
||||
await self._load_branch_model(branch)
|
||||
|
||||
# Recursively load nested branches
|
||||
nested_branches = getattr(branch, 'branches', [])
|
||||
if nested_branches:
|
||||
await self._preload_branch_models(nested_branches)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error preloading branch model {getattr(branch, 'model_id', 'unknown')}: {e}")
|
||||
|
||||
async def _load_branch_model(self, branch_config: Any) -> Optional[YOLOWrapper]:
|
||||
"""
|
||||
Load a branch model if not already loaded.
|
||||
|
||||
Args:
|
||||
branch_config: Branch configuration object
|
||||
|
||||
Returns:
|
||||
Loaded YOLO model wrapper or None
|
||||
"""
|
||||
try:
|
||||
model_id = getattr(branch_config, 'model_id', None)
|
||||
model_file = getattr(branch_config, 'model_file', None)
|
||||
|
||||
if not model_id or not model_file:
|
||||
logger.warning(f"Invalid branch config: model_id={model_id}, model_file={model_file}")
|
||||
return None
|
||||
|
||||
# Check if model is already loaded
|
||||
if model_id in self.branch_models:
|
||||
logger.debug(f"Branch model {model_id} already loaded")
|
||||
return self.branch_models[model_id]
|
||||
|
||||
# Load model
|
||||
logger.info(f"Loading branch model: {model_id} ({model_file})")
|
||||
|
||||
# Load model using the proper model ID
|
||||
model = self.model_manager.get_yolo_model(self.model_id, model_file)
|
||||
|
||||
if model:
|
||||
self.branch_models[model_id] = model
|
||||
self.stats['models_loaded'] += 1
|
||||
logger.info(f"Branch model {model_id} loaded successfully")
|
||||
return model
|
||||
else:
|
||||
logger.error(f"Failed to load branch model {model_id}")
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error loading branch model {getattr(branch_config, 'model_id', 'unknown')}: {e}")
|
||||
return None
|
||||
|
||||
async def execute_branches(self,
|
||||
frame: np.ndarray,
|
||||
branches: List[Any],
|
||||
detected_regions: Dict[str, Any],
|
||||
detection_context: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""
|
||||
Execute all branches in parallel and collect results.
|
||||
|
||||
Args:
|
||||
frame: Input frame
|
||||
branches: List of branch configurations
|
||||
detected_regions: Dictionary of detected regions from main detection
|
||||
detection_context: Detection context data
|
||||
|
||||
Returns:
|
||||
Dictionary with branch execution results
|
||||
"""
|
||||
start_time = time.time()
|
||||
branch_results = {}
|
||||
|
||||
try:
|
||||
# Separate parallel and sequential branches
|
||||
parallel_branches = []
|
||||
sequential_branches = []
|
||||
|
||||
for branch in branches:
|
||||
if getattr(branch, 'parallel', False):
|
||||
parallel_branches.append(branch)
|
||||
else:
|
||||
sequential_branches.append(branch)
|
||||
|
||||
# Execute parallel branches concurrently
|
||||
if parallel_branches:
|
||||
logger.info(f"Executing {len(parallel_branches)} branches in parallel")
|
||||
parallel_results = await self._execute_parallel_branches(
|
||||
frame, parallel_branches, detected_regions, detection_context
|
||||
)
|
||||
branch_results.update(parallel_results)
|
||||
self.stats['parallel_executions'] += 1
|
||||
|
||||
# Execute sequential branches one by one
|
||||
if sequential_branches:
|
||||
logger.info(f"Executing {len(sequential_branches)} branches sequentially")
|
||||
sequential_results = await self._execute_sequential_branches(
|
||||
frame, sequential_branches, detected_regions, detection_context
|
||||
)
|
||||
branch_results.update(sequential_results)
|
||||
|
||||
# Update statistics
|
||||
self.stats['branches_processed'] += len(branches)
|
||||
processing_time = time.time() - start_time
|
||||
self.stats['total_processing_time'] += processing_time
|
||||
|
||||
logger.info(f"Branch execution completed in {processing_time:.3f}s with {len(branch_results)} results")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in branch execution: {e}", exc_info=True)
|
||||
|
||||
return branch_results
|
||||
|
||||
async def _execute_parallel_branches(self,
|
||||
frame: np.ndarray,
|
||||
branches: List[Any],
|
||||
detected_regions: Dict[str, Any],
|
||||
detection_context: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""
|
||||
Execute branches in parallel using ThreadPoolExecutor.
|
||||
|
||||
Args:
|
||||
frame: Input frame
|
||||
branches: List of parallel branch configurations
|
||||
detected_regions: Dictionary of detected regions
|
||||
detection_context: Detection context data
|
||||
|
||||
Returns:
|
||||
Dictionary with parallel branch results
|
||||
"""
|
||||
results = {}
|
||||
|
||||
# Submit all branches for parallel execution
|
||||
future_to_branch = {}
|
||||
|
||||
for branch in branches:
|
||||
branch_id = getattr(branch, 'model_id', 'unknown')
|
||||
logger.info(f"[PARALLEL SUBMIT] {branch_id}: Submitting branch to thread pool")
|
||||
|
||||
future = self.executor.submit(
|
||||
self._execute_single_branch_sync,
|
||||
frame, branch, detected_regions, detection_context
|
||||
)
|
||||
future_to_branch[future] = branch
|
||||
|
||||
# Collect results as they complete
|
||||
for future in as_completed(future_to_branch):
|
||||
branch = future_to_branch[future]
|
||||
branch_id = getattr(branch, 'model_id', 'unknown')
|
||||
|
||||
try:
|
||||
result = future.result()
|
||||
results[branch_id] = result
|
||||
logger.info(f"[PARALLEL COMPLETE] {branch_id}: Branch completed successfully")
|
||||
except Exception as e:
|
||||
logger.error(f"Error in parallel branch {branch_id}: {e}")
|
||||
results[branch_id] = {
|
||||
'status': 'error',
|
||||
'message': str(e),
|
||||
'processing_time': 0.0
|
||||
}
|
||||
|
||||
# Flatten nested branch results to top level for database access
|
||||
flattened_results = {}
|
||||
for branch_id, branch_result in results.items():
|
||||
# Add the branch result itself
|
||||
flattened_results[branch_id] = branch_result
|
||||
|
||||
# If this branch has nested branches, add them to the top level too
|
||||
if isinstance(branch_result, dict) and 'nested_branches' in branch_result:
|
||||
nested_branches = branch_result['nested_branches']
|
||||
for nested_branch_id, nested_result in nested_branches.items():
|
||||
flattened_results[nested_branch_id] = nested_result
|
||||
logger.info(f"[FLATTEN] Added nested branch {nested_branch_id} to top-level results")
|
||||
|
||||
return flattened_results
|
||||
|
||||
async def _execute_sequential_branches(self,
|
||||
frame: np.ndarray,
|
||||
branches: List[Any],
|
||||
detected_regions: Dict[str, Any],
|
||||
detection_context: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""
|
||||
Execute branches sequentially.
|
||||
|
||||
Args:
|
||||
frame: Input frame
|
||||
branches: List of sequential branch configurations
|
||||
detected_regions: Dictionary of detected regions
|
||||
detection_context: Detection context data
|
||||
|
||||
Returns:
|
||||
Dictionary with sequential branch results
|
||||
"""
|
||||
results = {}
|
||||
|
||||
for branch in branches:
|
||||
branch_id = getattr(branch, 'model_id', 'unknown')
|
||||
|
||||
try:
|
||||
result = await asyncio.get_event_loop().run_in_executor(
|
||||
self.executor,
|
||||
self._execute_single_branch_sync,
|
||||
frame, branch, detected_regions, detection_context
|
||||
)
|
||||
results[branch_id] = result
|
||||
logger.debug(f"Sequential branch {branch_id} completed successfully")
|
||||
except Exception as e:
|
||||
logger.error(f"Error in sequential branch {branch_id}: {e}")
|
||||
results[branch_id] = {
|
||||
'status': 'error',
|
||||
'message': str(e),
|
||||
'processing_time': 0.0
|
||||
}
|
||||
|
||||
# Flatten nested branch results to top level for database access
|
||||
flattened_results = {}
|
||||
for branch_id, branch_result in results.items():
|
||||
# Add the branch result itself
|
||||
flattened_results[branch_id] = branch_result
|
||||
|
||||
# If this branch has nested branches, add them to the top level too
|
||||
if isinstance(branch_result, dict) and 'nested_branches' in branch_result:
|
||||
nested_branches = branch_result['nested_branches']
|
||||
for nested_branch_id, nested_result in nested_branches.items():
|
||||
flattened_results[nested_branch_id] = nested_result
|
||||
logger.info(f"[FLATTEN] Added nested branch {nested_branch_id} to top-level results")
|
||||
|
||||
return flattened_results
|
||||
|
||||
def _execute_single_branch_sync(self,
|
||||
frame: np.ndarray,
|
||||
branch_config: Any,
|
||||
detected_regions: Dict[str, Any],
|
||||
detection_context: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""
|
||||
Synchronous execution of a single branch (for ThreadPoolExecutor).
|
||||
|
||||
Args:
|
||||
frame: Input frame
|
||||
branch_config: Branch configuration object
|
||||
detected_regions: Dictionary of detected regions
|
||||
detection_context: Detection context data
|
||||
|
||||
Returns:
|
||||
Dictionary with branch execution result
|
||||
"""
|
||||
start_time = time.time()
|
||||
branch_id = getattr(branch_config, 'model_id', 'unknown')
|
||||
|
||||
logger.info(f"[BRANCH START] {branch_id}: Starting branch execution")
|
||||
logger.debug(f"[BRANCH CONFIG] {branch_id}: crop={getattr(branch_config, 'crop', False)}, "
|
||||
f"trigger_classes={getattr(branch_config, 'trigger_classes', [])}, "
|
||||
f"min_confidence={getattr(branch_config, 'min_confidence', 0.6)}")
|
||||
|
||||
# Check if branch should execute based on triggerClasses (execution conditions)
|
||||
trigger_classes = getattr(branch_config, 'trigger_classes', [])
|
||||
logger.info(f"[DETECTED REGIONS] {branch_id}: Available parent detections: {list(detected_regions.keys())}")
|
||||
for region_name, region_data in detected_regions.items():
|
||||
logger.debug(f"[REGION DATA] {branch_id}: '{region_name}' -> bbox={region_data.get('bbox')}, conf={region_data.get('confidence')}")
|
||||
|
||||
if trigger_classes:
|
||||
# Check if any parent detection matches our trigger classes
|
||||
should_execute = False
|
||||
for trigger_class in trigger_classes:
|
||||
if trigger_class in detected_regions:
|
||||
should_execute = True
|
||||
logger.info(f"[TRIGGER CHECK] {branch_id}: Found '{trigger_class}' in parent detections - branch will execute")
|
||||
break
|
||||
|
||||
if not should_execute:
|
||||
logger.warning(f"[TRIGGER CHECK] {branch_id}: None of trigger classes {trigger_classes} found in parent detections {list(detected_regions.keys())} - skipping branch")
|
||||
return {
|
||||
'status': 'skipped',
|
||||
'branch_id': branch_id,
|
||||
'message': f'No trigger classes {trigger_classes} found in parent detections',
|
||||
'processing_time': time.time() - start_time
|
||||
}
|
||||
|
||||
result = {
|
||||
'status': 'success',
|
||||
'branch_id': branch_id,
|
||||
'result': {},
|
||||
'processing_time': 0.0,
|
||||
'timestamp': time.time()
|
||||
}
|
||||
|
||||
try:
|
||||
# Get or load branch model
|
||||
if branch_id not in self.branch_models:
|
||||
logger.warning(f"Branch model {branch_id} not preloaded, loading now...")
|
||||
# This should be rare since models are preloaded
|
||||
return {
|
||||
'status': 'error',
|
||||
'message': f'Branch model {branch_id} not available',
|
||||
'processing_time': time.time() - start_time
|
||||
}
|
||||
|
||||
model = self.branch_models[branch_id]
|
||||
|
||||
# Get configuration values first
|
||||
min_confidence = getattr(branch_config, 'min_confidence', 0.6)
|
||||
|
||||
# Prepare input frame for this branch
|
||||
input_frame = frame
|
||||
|
||||
# Handle cropping if required - use biggest bbox that passes min_confidence
|
||||
if getattr(branch_config, 'crop', False):
|
||||
crop_classes = getattr(branch_config, 'crop_class', [])
|
||||
if isinstance(crop_classes, str):
|
||||
crop_classes = [crop_classes]
|
||||
|
||||
# Find the biggest bbox that passes min_confidence threshold
|
||||
best_region = None
|
||||
best_class = None
|
||||
best_area = 0.0
|
||||
|
||||
for crop_class in crop_classes:
|
||||
if crop_class in detected_regions:
|
||||
region = detected_regions[crop_class]
|
||||
confidence = region.get('confidence', 0.0)
|
||||
|
||||
# Only use detections above min_confidence
|
||||
if confidence >= min_confidence:
|
||||
bbox = region['bbox']
|
||||
area = (bbox[2] - bbox[0]) * (bbox[3] - bbox[1]) # width * height
|
||||
|
||||
# Choose biggest bbox among valid detections
|
||||
if area > best_area:
|
||||
best_region = region
|
||||
best_class = crop_class
|
||||
best_area = area
|
||||
|
||||
if best_region:
|
||||
bbox = best_region['bbox']
|
||||
x1, y1, x2, y2 = [int(coord) for coord in bbox]
|
||||
cropped = frame[y1:y2, x1:x2]
|
||||
if cropped.size > 0:
|
||||
input_frame = cropped
|
||||
confidence = best_region.get('confidence', 0.0)
|
||||
logger.info(f"[CROP SUCCESS] {branch_id}: cropped '{best_class}' region (conf={confidence:.3f}, area={int(best_area)}) -> shape={cropped.shape}")
|
||||
else:
|
||||
logger.warning(f"Branch {branch_id}: empty crop, using full frame")
|
||||
else:
|
||||
logger.warning(f"Branch {branch_id}: no valid crop regions found (min_conf={min_confidence})")
|
||||
|
||||
logger.info(f"[INFERENCE START] {branch_id}: Running inference on {'cropped' if input_frame is not frame else 'full'} frame "
|
||||
f"({input_frame.shape[1]}x{input_frame.shape[0]}) with confidence={min_confidence}")
|
||||
|
||||
|
||||
# Use .predict() method for both detection and classification models
|
||||
inference_start = time.time()
|
||||
detection_results = model.model.predict(input_frame, conf=min_confidence, verbose=False)
|
||||
inference_time = time.time() - inference_start
|
||||
logger.info(f"[INFERENCE DONE] {branch_id}: Predict completed in {inference_time:.3f}s using .predict() method")
|
||||
|
||||
# Initialize branch_detections outside the conditional
|
||||
branch_detections = []
|
||||
|
||||
# Process results using clean, unified logic
|
||||
if detection_results and len(detection_results) > 0:
|
||||
result_obj = detection_results[0]
|
||||
|
||||
# Handle detection models (have .boxes attribute)
|
||||
if hasattr(result_obj, 'boxes') and result_obj.boxes is not None:
|
||||
logger.info(f"[RAW DETECTIONS] {branch_id}: Found {len(result_obj.boxes)} raw detections")
|
||||
|
||||
for i, box in enumerate(result_obj.boxes):
|
||||
class_id = int(box.cls[0])
|
||||
confidence = float(box.conf[0])
|
||||
bbox = box.xyxy[0].cpu().numpy().tolist() # [x1, y1, x2, y2]
|
||||
class_name = model.model.names[class_id]
|
||||
|
||||
logger.debug(f"[RAW DETECTION {i+1}] {branch_id}: '{class_name}', conf={confidence:.3f}")
|
||||
|
||||
# All detections are included - no filtering by trigger_classes here
|
||||
branch_detections.append({
|
||||
'class_name': class_name,
|
||||
'confidence': confidence,
|
||||
'bbox': bbox
|
||||
})
|
||||
|
||||
# Handle classification models (have .probs attribute)
|
||||
elif hasattr(result_obj, 'probs') and result_obj.probs is not None:
|
||||
logger.info(f"[RAW CLASSIFICATION] {branch_id}: Processing classification results")
|
||||
|
||||
probs = result_obj.probs
|
||||
top_indices = probs.top5 # Get top 5 predictions
|
||||
top_conf = probs.top5conf.cpu().numpy()
|
||||
|
||||
for idx, conf in zip(top_indices, top_conf):
|
||||
if conf >= min_confidence:
|
||||
class_name = model.model.names[int(idx)]
|
||||
logger.debug(f"[CLASSIFICATION RESULT {len(branch_detections)+1}] {branch_id}: '{class_name}', conf={conf:.3f}")
|
||||
|
||||
# For classification, use full input frame dimensions as bbox
|
||||
branch_detections.append({
|
||||
'class_name': class_name,
|
||||
'confidence': float(conf),
|
||||
'bbox': [0, 0, input_frame.shape[1], input_frame.shape[0]]
|
||||
})
|
||||
else:
|
||||
logger.warning(f"[UNKNOWN MODEL] {branch_id}: Model results have no .boxes or .probs")
|
||||
|
||||
result['result'] = {
|
||||
'detections': branch_detections,
|
||||
'detection_count': len(branch_detections)
|
||||
}
|
||||
|
||||
logger.info(f"[FINAL RESULTS] {branch_id}: {len(branch_detections)} detections processed")
|
||||
|
||||
# Extract best result for classification models
|
||||
if branch_detections:
|
||||
best_detection = max(branch_detections, key=lambda x: x['confidence'])
|
||||
logger.info(f"[BEST DETECTION] {branch_id}: '{best_detection['class_name']}' with confidence {best_detection['confidence']:.3f}")
|
||||
|
||||
# Add classification-style results for database operations
|
||||
if 'brand' in branch_id.lower():
|
||||
result['result']['brand'] = best_detection['class_name']
|
||||
elif 'body' in branch_id.lower() or 'bodytype' in branch_id.lower():
|
||||
result['result']['body_type'] = best_detection['class_name']
|
||||
elif 'front_rear' in branch_id.lower():
|
||||
result['result']['front_rear'] = best_detection['confidence']
|
||||
|
||||
logger.info(f"[CLASSIFICATION RESULT] {branch_id}: Extracted classification fields")
|
||||
else:
|
||||
logger.warning(f"[NO RESULTS] {branch_id}: No detections found")
|
||||
|
||||
# Execute branch actions if this branch found valid detections
|
||||
actions_executed = []
|
||||
branch_actions = getattr(branch_config, 'actions', [])
|
||||
if branch_actions and branch_detections:
|
||||
logger.info(f"[BRANCH ACTIONS] {branch_id}: Executing {len(branch_actions)} actions")
|
||||
|
||||
# Create detected_regions from THIS branch's detections for actions
|
||||
branch_detected_regions = {}
|
||||
for detection in branch_detections:
|
||||
branch_detected_regions[detection['class_name']] = {
|
||||
'bbox': detection['bbox'],
|
||||
'confidence': detection['confidence']
|
||||
}
|
||||
|
||||
for action in branch_actions:
|
||||
try:
|
||||
action_type = action.type.value # Access the enum value
|
||||
logger.info(f"[ACTION EXECUTE] {branch_id}: Executing action '{action_type}'")
|
||||
|
||||
if action_type == 'redis_save_image':
|
||||
action_result = self._execute_redis_save_image_sync(
|
||||
action, input_frame, branch_detected_regions, detection_context
|
||||
)
|
||||
elif action_type == 'redis_publish':
|
||||
action_result = self._execute_redis_publish_sync(
|
||||
action, detection_context
|
||||
)
|
||||
else:
|
||||
logger.warning(f"[ACTION UNKNOWN] {branch_id}: Unknown action type '{action_type}'")
|
||||
action_result = {'status': 'error', 'message': f'Unknown action type: {action_type}'}
|
||||
|
||||
actions_executed.append({
|
||||
'action_type': action_type,
|
||||
'result': action_result
|
||||
})
|
||||
|
||||
logger.info(f"[ACTION COMPLETE] {branch_id}: Action '{action_type}' result: {action_result.get('status')}")
|
||||
|
||||
except Exception as e:
|
||||
action_type = getattr(action, 'type', None)
|
||||
if action_type:
|
||||
action_type = action_type.value if hasattr(action_type, 'value') else str(action_type)
|
||||
logger.error(f"[ACTION ERROR] {branch_id}: Error executing action '{action_type}': {e}", exc_info=True)
|
||||
actions_executed.append({
|
||||
'action_type': action_type,
|
||||
'result': {'status': 'error', 'message': str(e)}
|
||||
})
|
||||
|
||||
# Add actions executed to result
|
||||
if actions_executed:
|
||||
result['actions_executed'] = actions_executed
|
||||
|
||||
# Handle nested branches ONLY if parent found valid detections
|
||||
nested_branches = getattr(branch_config, 'branches', [])
|
||||
if nested_branches:
|
||||
# Check if parent branch found any valid detections
|
||||
if not branch_detections:
|
||||
logger.warning(f"[BRANCH SKIP] {branch_id}: Skipping {len(nested_branches)} nested branches - parent found no valid detections")
|
||||
else:
|
||||
logger.debug(f"Branch {branch_id}: executing {len(nested_branches)} nested branches")
|
||||
|
||||
# Create detected_regions from THIS branch's detections for nested branches
|
||||
# Nested branches should see their immediate parent's detections, not the root pipeline
|
||||
nested_detected_regions = {}
|
||||
for detection in branch_detections:
|
||||
nested_detected_regions[detection['class_name']] = {
|
||||
'bbox': detection['bbox'],
|
||||
'confidence': detection['confidence']
|
||||
}
|
||||
|
||||
logger.info(f"[NESTED REGIONS] {branch_id}: Passing {list(nested_detected_regions.keys())} to nested branches")
|
||||
|
||||
# Note: For simplicity, nested branches are executed sequentially in this sync method
|
||||
# In a full async implementation, these could also be parallelized
|
||||
nested_results = {}
|
||||
for nested_branch in nested_branches:
|
||||
nested_result = self._execute_single_branch_sync(
|
||||
input_frame, nested_branch, nested_detected_regions, detection_context
|
||||
)
|
||||
nested_branch_id = getattr(nested_branch, 'model_id', 'unknown')
|
||||
nested_results[nested_branch_id] = nested_result
|
||||
|
||||
result['nested_branches'] = nested_results
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[BRANCH ERROR] {branch_id}: Error in execution: {e}", exc_info=True)
|
||||
result['status'] = 'error'
|
||||
result['message'] = str(e)
|
||||
|
||||
result['processing_time'] = time.time() - start_time
|
||||
|
||||
# Summary log
|
||||
logger.info(f"[BRANCH COMPLETE] {branch_id}: status={result['status']}, "
|
||||
f"processing_time={result['processing_time']:.3f}s, "
|
||||
f"result_keys={list(result['result'].keys()) if result['result'] else 'none'}")
|
||||
|
||||
return result
|
||||
|
||||
def _execute_redis_save_image_sync(self,
|
||||
action: Dict,
|
||||
frame: np.ndarray,
|
||||
detected_regions: Dict[str, Any],
|
||||
context: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Execute redis_save_image action synchronously."""
|
||||
if not self.redis_manager:
|
||||
return {'status': 'error', 'message': 'Redis not available'}
|
||||
|
||||
try:
|
||||
# Get image to save (cropped or full frame)
|
||||
image_to_save = frame
|
||||
region_name = action.params.get('region')
|
||||
|
||||
bbox = None
|
||||
if region_name and region_name in detected_regions:
|
||||
# Crop the specified region
|
||||
bbox = detected_regions[region_name]['bbox']
|
||||
elif region_name and region_name.lower() == 'frontal' and 'front_rear' in detected_regions:
|
||||
# Special case: "frontal" region maps to "front_rear" detection
|
||||
bbox = detected_regions['front_rear']['bbox']
|
||||
|
||||
if bbox is not None:
|
||||
x1, y1, x2, y2 = [int(coord) for coord in bbox]
|
||||
cropped = frame[y1:y2, x1:x2]
|
||||
if cropped.size > 0:
|
||||
image_to_save = cropped
|
||||
logger.debug(f"Cropped region '{region_name}' for redis_save_image")
|
||||
else:
|
||||
logger.warning(f"Empty crop for region '{region_name}', using full frame")
|
||||
|
||||
# Format key with context
|
||||
key = action.params['key'].format(**context)
|
||||
|
||||
# Convert image to bytes
|
||||
import cv2
|
||||
image_format = action.params.get('format', 'jpeg')
|
||||
quality = action.params.get('quality', 90)
|
||||
|
||||
if image_format.lower() == 'jpeg':
|
||||
encode_param = [cv2.IMWRITE_JPEG_QUALITY, quality]
|
||||
_, image_bytes = cv2.imencode('.jpg', image_to_save, encode_param)
|
||||
else:
|
||||
_, image_bytes = cv2.imencode('.png', image_to_save)
|
||||
|
||||
# Save to Redis synchronously using a sync Redis client
|
||||
try:
|
||||
import redis
|
||||
import cv2
|
||||
|
||||
# Create a synchronous Redis client with same connection details
|
||||
sync_redis = redis.Redis(
|
||||
host=self.redis_manager.host,
|
||||
port=self.redis_manager.port,
|
||||
password=self.redis_manager.password,
|
||||
db=self.redis_manager.db,
|
||||
decode_responses=False, # We're storing binary data
|
||||
socket_timeout=self.redis_manager.socket_timeout,
|
||||
socket_connect_timeout=self.redis_manager.socket_connect_timeout
|
||||
)
|
||||
|
||||
# Encode the image
|
||||
if image_format.lower() == 'jpeg':
|
||||
encode_param = [cv2.IMWRITE_JPEG_QUALITY, quality]
|
||||
success, encoded_image = cv2.imencode('.jpg', image_to_save, encode_param)
|
||||
else:
|
||||
success, encoded_image = cv2.imencode('.png', image_to_save)
|
||||
|
||||
if not success:
|
||||
return {'status': 'error', 'message': 'Failed to encode image'}
|
||||
|
||||
# Save to Redis with expiration
|
||||
expire_seconds = action.params.get('expire_seconds', 600)
|
||||
result = sync_redis.setex(key, expire_seconds, encoded_image.tobytes())
|
||||
|
||||
sync_redis.close() # Clean up connection
|
||||
|
||||
if result:
|
||||
# Add image_key to context for subsequent actions
|
||||
context['image_key'] = key
|
||||
return {'status': 'success', 'key': key}
|
||||
else:
|
||||
return {'status': 'error', 'message': 'Failed to save image to Redis'}
|
||||
|
||||
except Exception as redis_error:
|
||||
logger.error(f"Error calling Redis from sync context: {redis_error}")
|
||||
return {'status': 'error', 'message': f'Redis operation failed: {redis_error}'}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in redis_save_image action: {e}", exc_info=True)
|
||||
return {'status': 'error', 'message': str(e)}
|
||||
|
||||
def _execute_redis_publish_sync(self, action: Dict, context: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Execute redis_publish action synchronously."""
|
||||
if not self.redis_manager:
|
||||
return {'status': 'error', 'message': 'Redis not available'}
|
||||
|
||||
try:
|
||||
channel = action.params['channel']
|
||||
message_template = action.params['message']
|
||||
|
||||
# Debug the message template
|
||||
logger.debug(f"Message template: {repr(message_template)}")
|
||||
logger.debug(f"Context keys: {list(context.keys())}")
|
||||
|
||||
# Format message with context - handle JSON string formatting carefully
|
||||
# The message template contains JSON which causes issues with .format()
|
||||
# Use string replacement instead of format to avoid JSON brace conflicts
|
||||
try:
|
||||
# Ensure image_key is available for message formatting
|
||||
if 'image_key' not in context:
|
||||
context['image_key'] = '' # Default empty value if redis_save_image failed
|
||||
|
||||
# Use string replacement to avoid JSON formatting issues
|
||||
message = message_template
|
||||
for key, value in context.items():
|
||||
placeholder = '{' + key + '}'
|
||||
message = message.replace(placeholder, str(value))
|
||||
|
||||
logger.debug(f"Formatted message using replacement: {message}")
|
||||
except Exception as e:
|
||||
logger.error(f"Message formatting failed: {e}")
|
||||
logger.error(f"Template: {repr(message_template)}")
|
||||
logger.error(f"Context: {context}")
|
||||
return {'status': 'error', 'message': f'Message formatting failed: {e}'}
|
||||
|
||||
# Publish message synchronously using a sync Redis client
|
||||
try:
|
||||
import redis
|
||||
|
||||
# Create a synchronous Redis client with same connection details
|
||||
sync_redis = redis.Redis(
|
||||
host=self.redis_manager.host,
|
||||
port=self.redis_manager.port,
|
||||
password=self.redis_manager.password,
|
||||
db=self.redis_manager.db,
|
||||
decode_responses=True, # For publishing text messages
|
||||
socket_timeout=self.redis_manager.socket_timeout,
|
||||
socket_connect_timeout=self.redis_manager.socket_connect_timeout
|
||||
)
|
||||
|
||||
# Publish message
|
||||
result = sync_redis.publish(channel, message)
|
||||
sync_redis.close() # Clean up connection
|
||||
|
||||
if result >= 0: # Redis publish returns number of subscribers
|
||||
return {'status': 'success', 'subscribers': result, 'channel': channel}
|
||||
else:
|
||||
return {'status': 'error', 'message': 'Failed to publish message to Redis'}
|
||||
|
||||
except Exception as redis_error:
|
||||
logger.error(f"Error calling Redis from sync context: {redis_error}")
|
||||
return {'status': 'error', 'message': f'Redis operation failed: {redis_error}'}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in redis_publish action: {e}", exc_info=True)
|
||||
return {'status': 'error', 'message': str(e)}
|
||||
|
||||
def get_statistics(self) -> Dict[str, Any]:
|
||||
"""Get branch processor statistics."""
|
||||
return {
|
||||
**self.stats,
|
||||
'loaded_models': list(self.branch_models.keys()),
|
||||
'model_count': len(self.branch_models)
|
||||
}
|
||||
|
||||
def cleanup(self):
|
||||
"""Cleanup resources."""
|
||||
if self.executor:
|
||||
self.executor.shutdown(wait=False)
|
||||
|
||||
# Clear model cache
|
||||
self.branch_models.clear()
|
||||
|
||||
logger.info("BranchProcessor cleaned up")
|
||||
File diff suppressed because it is too large
Load diff
|
|
@ -1,42 +0,0 @@
|
|||
"""
|
||||
Models Module - MPTA management, pipeline configuration, and YOLO inference
|
||||
"""
|
||||
|
||||
from .manager import ModelManager
|
||||
from .pipeline import (
|
||||
PipelineParser,
|
||||
PipelineConfig,
|
||||
TrackingConfig,
|
||||
ModelBranch,
|
||||
Action,
|
||||
ActionType,
|
||||
RedisConfig,
|
||||
PostgreSQLConfig
|
||||
)
|
||||
from .inference import (
|
||||
YOLOWrapper,
|
||||
ModelInferenceManager,
|
||||
Detection,
|
||||
InferenceResult
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
# Manager
|
||||
'ModelManager',
|
||||
|
||||
# Pipeline
|
||||
'PipelineParser',
|
||||
'PipelineConfig',
|
||||
'TrackingConfig',
|
||||
'ModelBranch',
|
||||
'Action',
|
||||
'ActionType',
|
||||
'RedisConfig',
|
||||
'PostgreSQLConfig',
|
||||
|
||||
# Inference
|
||||
'YOLOWrapper',
|
||||
'ModelInferenceManager',
|
||||
'Detection',
|
||||
'InferenceResult',
|
||||
]
|
||||
|
|
@ -1,447 +0,0 @@
|
|||
"""
|
||||
YOLO Model Inference Wrapper - Handles model loading and inference optimization
|
||||
"""
|
||||
|
||||
import logging
|
||||
import torch
|
||||
import numpy as np
|
||||
from pathlib import Path
|
||||
from typing import Dict, List, Optional, Any, Tuple, Union
|
||||
from threading import Lock
|
||||
from dataclasses import dataclass
|
||||
import cv2
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@dataclass
|
||||
class Detection:
|
||||
"""Represents a single detection result"""
|
||||
bbox: List[float] # [x1, y1, x2, y2]
|
||||
confidence: float
|
||||
class_id: int
|
||||
class_name: str
|
||||
track_id: Optional[int] = None
|
||||
|
||||
|
||||
@dataclass
|
||||
class InferenceResult:
|
||||
"""Result from model inference"""
|
||||
detections: List[Detection]
|
||||
image_shape: Tuple[int, int] # (height, width)
|
||||
inference_time: float
|
||||
model_id: str
|
||||
|
||||
|
||||
class YOLOWrapper:
|
||||
"""Wrapper for YOLO models with caching and optimization"""
|
||||
|
||||
# Class-level model cache shared across all instances
|
||||
_model_cache: Dict[str, Any] = {}
|
||||
_cache_lock = Lock()
|
||||
|
||||
def __init__(self, model_path: Path, model_id: str, device: Optional[str] = None):
|
||||
"""
|
||||
Initialize YOLO wrapper
|
||||
|
||||
Args:
|
||||
model_path: Path to the .pt model file
|
||||
model_id: Unique identifier for the model
|
||||
device: Device to run inference on ('cuda', 'cpu', or None for auto)
|
||||
"""
|
||||
self.model_path = model_path
|
||||
self.model_id = model_id
|
||||
|
||||
# Auto-detect device if not specified
|
||||
if device is None:
|
||||
self.device = 'cuda' if torch.cuda.is_available() else 'cpu'
|
||||
else:
|
||||
self.device = device
|
||||
|
||||
self.model = None
|
||||
self._class_names = []
|
||||
|
||||
|
||||
self._load_model()
|
||||
|
||||
logger.info(f"Initialized YOLO wrapper for {model_id} on {self.device}")
|
||||
|
||||
def _load_model(self) -> None:
|
||||
"""Load the YOLO model with caching"""
|
||||
cache_key = str(self.model_path)
|
||||
|
||||
with self._cache_lock:
|
||||
# Check if model is already cached
|
||||
if cache_key in self._model_cache:
|
||||
logger.info(f"Loading model {self.model_id} from cache")
|
||||
self.model = self._model_cache[cache_key]
|
||||
self._extract_class_names()
|
||||
return
|
||||
|
||||
# Load model
|
||||
try:
|
||||
from ultralytics import YOLO
|
||||
|
||||
logger.info(f"Loading YOLO model from {self.model_path}")
|
||||
self.model = YOLO(str(self.model_path))
|
||||
|
||||
# Move model to device
|
||||
if self.device == 'cuda' and torch.cuda.is_available():
|
||||
self.model.to('cuda')
|
||||
logger.info(f"Model {self.model_id} moved to GPU")
|
||||
|
||||
# Cache the model
|
||||
self._model_cache[cache_key] = self.model
|
||||
self._extract_class_names()
|
||||
|
||||
logger.info(f"Successfully loaded model {self.model_id}")
|
||||
|
||||
except ImportError:
|
||||
logger.error("Ultralytics YOLO not installed. Install with: pip install ultralytics")
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to load YOLO model {self.model_id}: {str(e)}", exc_info=True)
|
||||
raise
|
||||
|
||||
def _extract_class_names(self) -> None:
|
||||
"""Extract class names from the model"""
|
||||
try:
|
||||
if hasattr(self.model, 'names'):
|
||||
self._class_names = self.model.names
|
||||
elif hasattr(self.model, 'model') and hasattr(self.model.model, 'names'):
|
||||
self._class_names = self.model.model.names
|
||||
else:
|
||||
logger.warning(f"Could not extract class names from model {self.model_id}")
|
||||
self._class_names = {}
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to extract class names: {str(e)}")
|
||||
self._class_names = {}
|
||||
|
||||
|
||||
def infer(
|
||||
self,
|
||||
image: np.ndarray,
|
||||
confidence_threshold: float = 0.5,
|
||||
trigger_classes: Optional[List[str]] = None,
|
||||
iou_threshold: float = 0.45
|
||||
) -> InferenceResult:
|
||||
"""
|
||||
Run inference on an image
|
||||
|
||||
Args:
|
||||
image: Input image as numpy array (BGR format)
|
||||
confidence_threshold: Minimum confidence for detections
|
||||
trigger_classes: List of class names to filter (None = all classes)
|
||||
iou_threshold: IoU threshold for NMS
|
||||
|
||||
Returns:
|
||||
InferenceResult containing detections
|
||||
"""
|
||||
if self.model is None:
|
||||
raise RuntimeError(f"Model {self.model_id} not loaded")
|
||||
|
||||
try:
|
||||
import time
|
||||
start_time = time.time()
|
||||
|
||||
# Run inference
|
||||
results = self.model(
|
||||
image,
|
||||
conf=confidence_threshold,
|
||||
iou=iou_threshold,
|
||||
verbose=False
|
||||
)
|
||||
|
||||
inference_time = time.time() - start_time
|
||||
|
||||
# Parse results
|
||||
detections = self._parse_results(results[0], trigger_classes)
|
||||
|
||||
return InferenceResult(
|
||||
detections=detections,
|
||||
image_shape=(image.shape[0], image.shape[1]),
|
||||
inference_time=inference_time,
|
||||
model_id=self.model_id
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Inference failed for model {self.model_id}: {str(e)}", exc_info=True)
|
||||
raise
|
||||
|
||||
def _parse_results(
|
||||
self,
|
||||
result: Any,
|
||||
trigger_classes: Optional[List[str]] = None
|
||||
) -> List[Detection]:
|
||||
"""
|
||||
Parse YOLO results into Detection objects
|
||||
|
||||
Args:
|
||||
result: YOLO result object
|
||||
trigger_classes: Optional list of class names to filter
|
||||
|
||||
Returns:
|
||||
List of Detection objects
|
||||
"""
|
||||
detections = []
|
||||
|
||||
try:
|
||||
if result.boxes is None:
|
||||
return detections
|
||||
|
||||
boxes = result.boxes
|
||||
for i in range(len(boxes)):
|
||||
# Get box coordinates
|
||||
box = boxes.xyxy[i].cpu().numpy()
|
||||
x1, y1, x2, y2 = box
|
||||
|
||||
# Get confidence and class
|
||||
conf = float(boxes.conf[i])
|
||||
cls_id = int(boxes.cls[i])
|
||||
|
||||
# Get class name
|
||||
class_name = self._class_names.get(cls_id, f"class_{cls_id}")
|
||||
|
||||
# Filter by trigger classes if specified
|
||||
if trigger_classes and class_name not in trigger_classes:
|
||||
continue
|
||||
|
||||
# Get track ID if available
|
||||
track_id = None
|
||||
if hasattr(boxes, 'id') and boxes.id is not None:
|
||||
track_id = int(boxes.id[i])
|
||||
|
||||
detection = Detection(
|
||||
bbox=[float(x1), float(y1), float(x2), float(y2)],
|
||||
confidence=conf,
|
||||
class_id=cls_id,
|
||||
class_name=class_name,
|
||||
track_id=track_id
|
||||
)
|
||||
detections.append(detection)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to parse results: {str(e)}", exc_info=True)
|
||||
|
||||
return detections
|
||||
|
||||
|
||||
def track(
|
||||
self,
|
||||
image: np.ndarray,
|
||||
confidence_threshold: float = 0.5,
|
||||
trigger_classes: Optional[List[str]] = None,
|
||||
persist: bool = True,
|
||||
camera_id: Optional[str] = None
|
||||
) -> InferenceResult:
|
||||
"""
|
||||
Run detection (tracking will be handled by external tracker)
|
||||
|
||||
Args:
|
||||
image: Input image as numpy array (BGR format)
|
||||
confidence_threshold: Minimum confidence for detections
|
||||
trigger_classes: List of class names to filter
|
||||
persist: Ignored - tracking handled externally
|
||||
camera_id: Ignored - tracking handled externally
|
||||
|
||||
Returns:
|
||||
InferenceResult containing detections (no track IDs from YOLO)
|
||||
"""
|
||||
# Just do detection - no YOLO tracking
|
||||
return self.infer(image, confidence_threshold, trigger_classes)
|
||||
|
||||
def predict_classification(
|
||||
self,
|
||||
image: np.ndarray,
|
||||
top_k: int = 1
|
||||
) -> Dict[str, float]:
|
||||
"""
|
||||
Run classification on an image
|
||||
|
||||
Args:
|
||||
image: Input image as numpy array (BGR format)
|
||||
top_k: Number of top predictions to return
|
||||
|
||||
Returns:
|
||||
Dictionary of class_name -> confidence scores
|
||||
"""
|
||||
if self.model is None:
|
||||
raise RuntimeError(f"Model {self.model_id} not loaded")
|
||||
|
||||
try:
|
||||
# Run inference
|
||||
results = self.model(image, verbose=False)
|
||||
|
||||
# For classification models, extract probabilities
|
||||
if hasattr(results[0], 'probs'):
|
||||
probs = results[0].probs
|
||||
top_indices = probs.top5[:top_k]
|
||||
top_conf = probs.top5conf[:top_k].cpu().numpy()
|
||||
|
||||
predictions = {}
|
||||
for idx, conf in zip(top_indices, top_conf):
|
||||
class_name = self._class_names.get(int(idx), f"class_{idx}")
|
||||
predictions[class_name] = float(conf)
|
||||
|
||||
return predictions
|
||||
else:
|
||||
logger.warning(f"Model {self.model_id} does not support classification")
|
||||
return {}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Classification failed for model {self.model_id}: {str(e)}", exc_info=True)
|
||||
raise
|
||||
|
||||
def crop_detection(
|
||||
self,
|
||||
image: np.ndarray,
|
||||
detection: Detection,
|
||||
padding: int = 0
|
||||
) -> np.ndarray:
|
||||
"""
|
||||
Crop image to detection bounding box
|
||||
|
||||
Args:
|
||||
image: Original image
|
||||
detection: Detection to crop
|
||||
padding: Additional padding around the box
|
||||
|
||||
Returns:
|
||||
Cropped image region
|
||||
"""
|
||||
h, w = image.shape[:2]
|
||||
x1, y1, x2, y2 = detection.bbox
|
||||
|
||||
# Add padding and clip to image boundaries
|
||||
x1 = max(0, int(x1) - padding)
|
||||
y1 = max(0, int(y1) - padding)
|
||||
x2 = min(w, int(x2) + padding)
|
||||
y2 = min(h, int(y2) + padding)
|
||||
|
||||
return image[y1:y2, x1:x2]
|
||||
|
||||
def get_class_names(self) -> Dict[int, str]:
|
||||
"""Get the class names dictionary"""
|
||||
return self._class_names.copy()
|
||||
|
||||
def get_num_classes(self) -> int:
|
||||
"""Get the number of classes the model can detect"""
|
||||
return len(self._class_names)
|
||||
|
||||
|
||||
def clear_cache(self) -> None:
|
||||
"""Clear the model cache"""
|
||||
with self._cache_lock:
|
||||
cache_key = str(self.model_path)
|
||||
if cache_key in self._model_cache:
|
||||
del self._model_cache[cache_key]
|
||||
logger.info(f"Cleared cache for model {self.model_id}")
|
||||
|
||||
@classmethod
|
||||
def clear_all_cache(cls) -> None:
|
||||
"""Clear all cached models"""
|
||||
with cls._cache_lock:
|
||||
cls._model_cache.clear()
|
||||
logger.info("Cleared all model cache")
|
||||
|
||||
def warmup(self, image_size: Tuple[int, int] = (640, 640)) -> None:
|
||||
"""
|
||||
Warmup the model with a dummy inference
|
||||
|
||||
Args:
|
||||
image_size: Size of dummy image (height, width)
|
||||
"""
|
||||
try:
|
||||
dummy_image = np.zeros((image_size[0], image_size[1], 3), dtype=np.uint8)
|
||||
self.infer(dummy_image, confidence_threshold=0.5)
|
||||
logger.info(f"Model {self.model_id} warmed up")
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to warmup model {self.model_id}: {str(e)}")
|
||||
|
||||
|
||||
class ModelInferenceManager:
|
||||
"""Manages multiple YOLO models for a pipeline"""
|
||||
|
||||
def __init__(self, model_dir: Path):
|
||||
"""
|
||||
Initialize the inference manager
|
||||
|
||||
Args:
|
||||
model_dir: Directory containing model files
|
||||
"""
|
||||
self.model_dir = model_dir
|
||||
self.models: Dict[str, YOLOWrapper] = {}
|
||||
self._lock = Lock()
|
||||
|
||||
logger.info(f"Initialized ModelInferenceManager with model directory: {model_dir}")
|
||||
|
||||
def load_model(
|
||||
self,
|
||||
model_id: str,
|
||||
model_file: str,
|
||||
device: Optional[str] = None
|
||||
) -> YOLOWrapper:
|
||||
"""
|
||||
Load a model for inference
|
||||
|
||||
Args:
|
||||
model_id: Unique identifier for the model
|
||||
model_file: Filename of the model
|
||||
device: Device to run on
|
||||
|
||||
Returns:
|
||||
YOLOWrapper instance
|
||||
"""
|
||||
with self._lock:
|
||||
# Check if already loaded
|
||||
if model_id in self.models:
|
||||
logger.debug(f"Model {model_id} already loaded")
|
||||
return self.models[model_id]
|
||||
|
||||
# Load the model
|
||||
model_path = self.model_dir / model_file
|
||||
if not model_path.exists():
|
||||
raise FileNotFoundError(f"Model file not found: {model_path}")
|
||||
|
||||
wrapper = YOLOWrapper(model_path, model_id, device)
|
||||
self.models[model_id] = wrapper
|
||||
|
||||
return wrapper
|
||||
|
||||
def get_model(self, model_id: str) -> Optional[YOLOWrapper]:
|
||||
"""
|
||||
Get a loaded model
|
||||
|
||||
Args:
|
||||
model_id: Model identifier
|
||||
|
||||
Returns:
|
||||
YOLOWrapper instance or None if not loaded
|
||||
"""
|
||||
return self.models.get(model_id)
|
||||
|
||||
def unload_model(self, model_id: str) -> bool:
|
||||
"""
|
||||
Unload a model to free memory
|
||||
|
||||
Args:
|
||||
model_id: Model identifier
|
||||
|
||||
Returns:
|
||||
True if unloaded, False if not found
|
||||
"""
|
||||
with self._lock:
|
||||
if model_id in self.models:
|
||||
self.models[model_id].clear_cache()
|
||||
del self.models[model_id]
|
||||
logger.info(f"Unloaded model {model_id}")
|
||||
return True
|
||||
return False
|
||||
|
||||
def unload_all(self) -> None:
|
||||
"""Unload all models"""
|
||||
with self._lock:
|
||||
for model_id in list(self.models.keys()):
|
||||
self.models[model_id].clear_cache()
|
||||
self.models.clear()
|
||||
logger.info("Unloaded all models")
|
||||
|
|
@ -1,439 +0,0 @@
|
|||
"""
|
||||
Model Manager Module - Handles MPTA download, extraction, and model loading
|
||||
"""
|
||||
|
||||
import os
|
||||
import logging
|
||||
import zipfile
|
||||
import json
|
||||
import hashlib
|
||||
import requests
|
||||
from pathlib import Path
|
||||
from typing import Dict, Optional, Any, Set
|
||||
from threading import Lock
|
||||
from urllib.parse import urlparse, parse_qs
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class ModelManager:
|
||||
"""Manages MPTA model downloads, extraction, and caching"""
|
||||
|
||||
def __init__(self, models_dir: str = "models"):
|
||||
"""
|
||||
Initialize the Model Manager
|
||||
|
||||
Args:
|
||||
models_dir: Base directory for storing models
|
||||
"""
|
||||
self.models_dir = Path(models_dir)
|
||||
self.models_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# Track downloaded models to avoid duplicates
|
||||
self._downloaded_models: Set[int] = set()
|
||||
self._model_paths: Dict[int, Path] = {}
|
||||
self._download_lock = Lock()
|
||||
|
||||
# Scan existing models
|
||||
self._scan_existing_models()
|
||||
|
||||
logger.info(f"ModelManager initialized with models directory: {self.models_dir}")
|
||||
logger.info(f"Found existing models: {list(self._downloaded_models)}")
|
||||
|
||||
def _scan_existing_models(self) -> None:
|
||||
"""Scan the models directory for existing downloaded models"""
|
||||
if not self.models_dir.exists():
|
||||
return
|
||||
|
||||
for model_dir in self.models_dir.iterdir():
|
||||
if model_dir.is_dir() and model_dir.name.isdigit():
|
||||
model_id = int(model_dir.name)
|
||||
# Check if extraction was successful by looking for pipeline.json
|
||||
extracted_dirs = list(model_dir.glob("*/pipeline.json"))
|
||||
if extracted_dirs:
|
||||
self._downloaded_models.add(model_id)
|
||||
# Store path to the extracted model directory
|
||||
self._model_paths[model_id] = extracted_dirs[0].parent
|
||||
logger.debug(f"Found existing model {model_id} at {extracted_dirs[0].parent}")
|
||||
|
||||
def get_model_path(self, model_id: int) -> Optional[Path]:
|
||||
"""
|
||||
Get the path to an extracted model directory
|
||||
|
||||
Args:
|
||||
model_id: The model ID
|
||||
|
||||
Returns:
|
||||
Path to the extracted model directory or None if not found
|
||||
"""
|
||||
return self._model_paths.get(model_id)
|
||||
|
||||
def is_model_downloaded(self, model_id: int) -> bool:
|
||||
"""
|
||||
Check if a model has already been downloaded and extracted
|
||||
|
||||
Args:
|
||||
model_id: The model ID to check
|
||||
|
||||
Returns:
|
||||
True if the model is already available
|
||||
"""
|
||||
return model_id in self._downloaded_models
|
||||
|
||||
def ensure_model(self, model_id: int, model_url: str, model_name: str = None) -> Optional[Path]:
|
||||
"""
|
||||
Ensure a model is downloaded and extracted, downloading if necessary
|
||||
|
||||
Args:
|
||||
model_id: The model ID
|
||||
model_url: URL to download the MPTA file from
|
||||
model_name: Optional model name for logging
|
||||
|
||||
Returns:
|
||||
Path to the extracted model directory or None if failed
|
||||
"""
|
||||
# Check if already downloaded
|
||||
if self.is_model_downloaded(model_id):
|
||||
logger.info(f"Model {model_id} already available at {self._model_paths[model_id]}")
|
||||
return self._model_paths[model_id]
|
||||
|
||||
# Download and extract with lock to prevent concurrent downloads of same model
|
||||
with self._download_lock:
|
||||
# Double-check after acquiring lock
|
||||
if self.is_model_downloaded(model_id):
|
||||
return self._model_paths[model_id]
|
||||
|
||||
logger.info(f"Model {model_id} not found locally, downloading from {model_url}")
|
||||
|
||||
# Create model directory
|
||||
model_dir = self.models_dir / str(model_id)
|
||||
model_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# Extract filename from URL
|
||||
mpta_filename = self._extract_filename_from_url(model_url, model_name, model_id)
|
||||
mpta_path = model_dir / mpta_filename
|
||||
|
||||
# Download MPTA file
|
||||
if not self._download_mpta(model_url, mpta_path):
|
||||
logger.error(f"Failed to download model {model_id}")
|
||||
return None
|
||||
|
||||
# Extract MPTA file
|
||||
extracted_path = self._extract_mpta(mpta_path, model_dir)
|
||||
if not extracted_path:
|
||||
logger.error(f"Failed to extract model {model_id}")
|
||||
return None
|
||||
|
||||
# Mark as downloaded and store path
|
||||
self._downloaded_models.add(model_id)
|
||||
self._model_paths[model_id] = extracted_path
|
||||
|
||||
logger.info(f"Successfully prepared model {model_id} at {extracted_path}")
|
||||
return extracted_path
|
||||
|
||||
def _extract_filename_from_url(self, url: str, model_name: str = None, model_id: int = None) -> str:
|
||||
"""
|
||||
Extract a suitable filename from the URL
|
||||
|
||||
Args:
|
||||
url: The URL to extract filename from
|
||||
model_name: Optional model name
|
||||
model_id: Optional model ID
|
||||
|
||||
Returns:
|
||||
A suitable filename for the MPTA file
|
||||
"""
|
||||
parsed = urlparse(url)
|
||||
path = parsed.path
|
||||
|
||||
# Try to get filename from path
|
||||
if path:
|
||||
filename = os.path.basename(path)
|
||||
if filename and filename.endswith('.mpta'):
|
||||
return filename
|
||||
|
||||
# Fallback to constructed name
|
||||
if model_name:
|
||||
return f"{model_name}-{model_id}.mpta"
|
||||
else:
|
||||
return f"model-{model_id}.mpta"
|
||||
|
||||
def _download_mpta(self, url: str, dest_path: Path) -> bool:
|
||||
"""
|
||||
Download an MPTA file from a URL
|
||||
|
||||
Args:
|
||||
url: URL to download from
|
||||
dest_path: Destination path for the file
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
try:
|
||||
logger.info(f"Starting download of model from {url}")
|
||||
logger.debug(f"Download destination: {dest_path}")
|
||||
|
||||
response = requests.get(url, stream=True, timeout=300)
|
||||
if response.status_code != 200:
|
||||
logger.error(f"Failed to download MPTA file (status {response.status_code})")
|
||||
return False
|
||||
|
||||
file_size = int(response.headers.get('content-length', 0))
|
||||
logger.info(f"Model file size: {file_size/1024/1024:.2f} MB")
|
||||
|
||||
downloaded = 0
|
||||
last_log_percent = 0
|
||||
|
||||
with open(dest_path, 'wb') as f:
|
||||
for chunk in response.iter_content(chunk_size=8192):
|
||||
if chunk:
|
||||
f.write(chunk)
|
||||
downloaded += len(chunk)
|
||||
|
||||
# Log progress every 10%
|
||||
if file_size > 0:
|
||||
percent = int(downloaded * 100 / file_size)
|
||||
if percent >= last_log_percent + 10:
|
||||
logger.debug(f"Download progress: {percent}%")
|
||||
last_log_percent = percent
|
||||
|
||||
logger.info(f"Successfully downloaded MPTA file to {dest_path}")
|
||||
return True
|
||||
|
||||
except requests.RequestException as e:
|
||||
logger.error(f"Network error downloading MPTA: {str(e)}", exc_info=True)
|
||||
# Clean up partial download
|
||||
if dest_path.exists():
|
||||
dest_path.unlink()
|
||||
return False
|
||||
except Exception as e:
|
||||
logger.error(f"Unexpected error downloading MPTA: {str(e)}", exc_info=True)
|
||||
# Clean up partial download
|
||||
if dest_path.exists():
|
||||
dest_path.unlink()
|
||||
return False
|
||||
|
||||
def _extract_mpta(self, mpta_path: Path, target_dir: Path) -> Optional[Path]:
|
||||
"""
|
||||
Extract an MPTA (ZIP) file to the target directory
|
||||
|
||||
Args:
|
||||
mpta_path: Path to the MPTA file
|
||||
target_dir: Directory to extract to
|
||||
|
||||
Returns:
|
||||
Path to the extracted model directory containing pipeline.json, or None if failed
|
||||
"""
|
||||
try:
|
||||
if not mpta_path.exists():
|
||||
logger.error(f"MPTA file not found: {mpta_path}")
|
||||
return None
|
||||
|
||||
logger.info(f"Extracting MPTA file from {mpta_path} to {target_dir}")
|
||||
|
||||
with zipfile.ZipFile(mpta_path, 'r') as zip_ref:
|
||||
# Get list of files
|
||||
file_list = zip_ref.namelist()
|
||||
logger.debug(f"Files in MPTA archive: {len(file_list)} files")
|
||||
|
||||
# Extract all files
|
||||
zip_ref.extractall(target_dir)
|
||||
|
||||
logger.info(f"Successfully extracted MPTA file to {target_dir}")
|
||||
|
||||
# Find the directory containing pipeline.json
|
||||
pipeline_files = list(target_dir.glob("*/pipeline.json"))
|
||||
if not pipeline_files:
|
||||
# Check if pipeline.json is in root
|
||||
if (target_dir / "pipeline.json").exists():
|
||||
logger.info(f"Found pipeline.json in root of {target_dir}")
|
||||
return target_dir
|
||||
logger.error(f"No pipeline.json found after extraction in {target_dir}")
|
||||
return None
|
||||
|
||||
# Return the directory containing pipeline.json
|
||||
extracted_dir = pipeline_files[0].parent
|
||||
logger.info(f"Extracted model to {extracted_dir}")
|
||||
|
||||
# Keep the MPTA file for reference but could delete if space is a concern
|
||||
# mpta_path.unlink()
|
||||
# logger.debug(f"Removed MPTA file after extraction: {mpta_path}")
|
||||
|
||||
return extracted_dir
|
||||
|
||||
except zipfile.BadZipFile as e:
|
||||
logger.error(f"Invalid ZIP/MPTA file {mpta_path}: {str(e)}", exc_info=True)
|
||||
return None
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to extract MPTA file {mpta_path}: {str(e)}", exc_info=True)
|
||||
return None
|
||||
|
||||
def load_pipeline_config(self, model_id: int) -> Optional[Dict[str, Any]]:
|
||||
"""
|
||||
Load the pipeline.json configuration for a model
|
||||
|
||||
Args:
|
||||
model_id: The model ID
|
||||
|
||||
Returns:
|
||||
The pipeline configuration dictionary or None if not found
|
||||
"""
|
||||
model_path = self.get_model_path(model_id)
|
||||
if not model_path:
|
||||
logger.error(f"Model {model_id} not found")
|
||||
return None
|
||||
|
||||
pipeline_path = model_path / "pipeline.json"
|
||||
if not pipeline_path.exists():
|
||||
logger.error(f"pipeline.json not found for model {model_id}")
|
||||
return None
|
||||
|
||||
try:
|
||||
with open(pipeline_path, 'r') as f:
|
||||
config = json.load(f)
|
||||
logger.debug(f"Loaded pipeline config for model {model_id}")
|
||||
return config
|
||||
except json.JSONDecodeError as e:
|
||||
logger.error(f"Invalid JSON in pipeline.json for model {model_id}: {str(e)}")
|
||||
return None
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to load pipeline.json for model {model_id}: {str(e)}")
|
||||
return None
|
||||
|
||||
def get_model_file_path(self, model_id: int, filename: str) -> Optional[Path]:
|
||||
"""
|
||||
Get the full path to a model file (e.g., .pt file)
|
||||
|
||||
Args:
|
||||
model_id: The model ID
|
||||
filename: The filename within the model directory
|
||||
|
||||
Returns:
|
||||
Full path to the model file or None if not found
|
||||
"""
|
||||
model_path = self.get_model_path(model_id)
|
||||
if not model_path:
|
||||
return None
|
||||
|
||||
file_path = model_path / filename
|
||||
if not file_path.exists():
|
||||
logger.error(f"Model file {filename} not found in model {model_id}")
|
||||
return None
|
||||
|
||||
return file_path
|
||||
|
||||
def cleanup_model(self, model_id: int) -> bool:
|
||||
"""
|
||||
Remove a downloaded model to free up space
|
||||
|
||||
Args:
|
||||
model_id: The model ID to remove
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
if model_id not in self._downloaded_models:
|
||||
logger.warning(f"Model {model_id} not in downloaded models")
|
||||
return False
|
||||
|
||||
try:
|
||||
model_dir = self.models_dir / str(model_id)
|
||||
if model_dir.exists():
|
||||
import shutil
|
||||
shutil.rmtree(model_dir)
|
||||
logger.info(f"Removed model directory: {model_dir}")
|
||||
|
||||
self._downloaded_models.discard(model_id)
|
||||
self._model_paths.pop(model_id, None)
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to cleanup model {model_id}: {str(e)}")
|
||||
return False
|
||||
|
||||
def get_all_downloaded_models(self) -> Set[int]:
|
||||
"""
|
||||
Get a set of all downloaded model IDs
|
||||
|
||||
Returns:
|
||||
Set of model IDs that are currently downloaded
|
||||
"""
|
||||
return self._downloaded_models.copy()
|
||||
|
||||
def get_pipeline_config(self, model_id: int) -> Optional[Any]:
|
||||
"""
|
||||
Get the pipeline configuration for a model.
|
||||
|
||||
Args:
|
||||
model_id: The model ID
|
||||
|
||||
Returns:
|
||||
PipelineConfig object if found, None otherwise
|
||||
"""
|
||||
try:
|
||||
if model_id not in self._downloaded_models:
|
||||
logger.warning(f"Model {model_id} not downloaded")
|
||||
return None
|
||||
|
||||
model_path = self._model_paths.get(model_id)
|
||||
if not model_path:
|
||||
logger.warning(f"Model path not found for model {model_id}")
|
||||
return None
|
||||
|
||||
# Import here to avoid circular imports
|
||||
from .pipeline import PipelineParser
|
||||
|
||||
# Load pipeline.json
|
||||
pipeline_file = model_path / "pipeline.json"
|
||||
if not pipeline_file.exists():
|
||||
logger.warning(f"No pipeline.json found for model {model_id}")
|
||||
return None
|
||||
|
||||
# Create PipelineParser object and parse the configuration
|
||||
pipeline_parser = PipelineParser()
|
||||
success = pipeline_parser.parse(pipeline_file)
|
||||
|
||||
if success:
|
||||
return pipeline_parser
|
||||
else:
|
||||
logger.error(f"Failed to parse pipeline.json for model {model_id}")
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error getting pipeline config for model {model_id}: {e}", exc_info=True)
|
||||
return None
|
||||
|
||||
def get_yolo_model(self, model_id: int, model_filename: str) -> Optional[Any]:
|
||||
"""
|
||||
Create a YOLOWrapper instance for a specific model file.
|
||||
|
||||
Args:
|
||||
model_id: The model ID
|
||||
model_filename: The .pt model filename
|
||||
|
||||
Returns:
|
||||
YOLOWrapper instance if successful, None otherwise
|
||||
"""
|
||||
try:
|
||||
# Get the model file path
|
||||
model_file_path = self.get_model_file_path(model_id, model_filename)
|
||||
if not model_file_path or not model_file_path.exists():
|
||||
logger.error(f"Model file {model_filename} not found for model {model_id}")
|
||||
return None
|
||||
|
||||
# Import here to avoid circular imports
|
||||
from .inference import YOLOWrapper
|
||||
|
||||
# Create YOLOWrapper instance
|
||||
yolo_model = YOLOWrapper(
|
||||
model_path=model_file_path,
|
||||
model_id=f"{model_id}_{model_filename}",
|
||||
device=None # Auto-detect device
|
||||
)
|
||||
|
||||
logger.info(f"Created YOLOWrapper for model {model_id}: {model_filename}")
|
||||
return yolo_model
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error creating YOLO model for {model_id}:{model_filename}: {e}", exc_info=True)
|
||||
return None
|
||||
|
|
@ -1,357 +0,0 @@
|
|||
"""
|
||||
Pipeline Configuration Parser - Handles pipeline.json parsing and validation
|
||||
"""
|
||||
|
||||
import json
|
||||
import logging
|
||||
from pathlib import Path
|
||||
from typing import Dict, List, Any, Optional, Set
|
||||
from dataclasses import dataclass, field
|
||||
from enum import Enum
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class ActionType(Enum):
|
||||
"""Supported action types in pipeline"""
|
||||
REDIS_SAVE_IMAGE = "redis_save_image"
|
||||
REDIS_PUBLISH = "redis_publish"
|
||||
POSTGRESQL_UPDATE = "postgresql_update"
|
||||
POSTGRESQL_UPDATE_COMBINED = "postgresql_update_combined"
|
||||
POSTGRESQL_INSERT = "postgresql_insert"
|
||||
|
||||
|
||||
@dataclass
|
||||
class RedisConfig:
|
||||
"""Redis connection configuration"""
|
||||
host: str
|
||||
port: int = 6379
|
||||
password: Optional[str] = None
|
||||
db: int = 0
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, data: Dict[str, Any]) -> 'RedisConfig':
|
||||
return cls(
|
||||
host=data['host'],
|
||||
port=data.get('port', 6379),
|
||||
password=data.get('password'),
|
||||
db=data.get('db', 0)
|
||||
)
|
||||
|
||||
|
||||
@dataclass
|
||||
class PostgreSQLConfig:
|
||||
"""PostgreSQL connection configuration"""
|
||||
host: str
|
||||
port: int
|
||||
database: str
|
||||
username: str
|
||||
password: str
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, data: Dict[str, Any]) -> 'PostgreSQLConfig':
|
||||
return cls(
|
||||
host=data['host'],
|
||||
port=data.get('port', 5432),
|
||||
database=data['database'],
|
||||
username=data['username'],
|
||||
password=data['password']
|
||||
)
|
||||
|
||||
|
||||
@dataclass
|
||||
class Action:
|
||||
"""Represents an action in the pipeline"""
|
||||
type: ActionType
|
||||
params: Dict[str, Any] = field(default_factory=dict)
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, data: Dict[str, Any]) -> 'Action':
|
||||
action_type = ActionType(data['type'])
|
||||
params = {k: v for k, v in data.items() if k != 'type'}
|
||||
return cls(type=action_type, params=params)
|
||||
|
||||
|
||||
@dataclass
|
||||
class ModelBranch:
|
||||
"""Represents a branch in the pipeline with its own model"""
|
||||
model_id: str
|
||||
model_file: str
|
||||
trigger_classes: List[str]
|
||||
min_confidence: float = 0.5
|
||||
crop: bool = False
|
||||
crop_class: Optional[Any] = None # Can be string or list
|
||||
parallel: bool = False
|
||||
actions: List[Action] = field(default_factory=list)
|
||||
branches: List['ModelBranch'] = field(default_factory=list)
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, data: Dict[str, Any]) -> 'ModelBranch':
|
||||
actions = [Action.from_dict(a) for a in data.get('actions', [])]
|
||||
branches = [cls.from_dict(b) for b in data.get('branches', [])]
|
||||
|
||||
return cls(
|
||||
model_id=data['modelId'],
|
||||
model_file=data['modelFile'],
|
||||
trigger_classes=data.get('triggerClasses', []),
|
||||
min_confidence=data.get('minConfidence', 0.5),
|
||||
crop=data.get('crop', False),
|
||||
crop_class=data.get('cropClass'),
|
||||
parallel=data.get('parallel', False),
|
||||
actions=actions,
|
||||
branches=branches
|
||||
)
|
||||
|
||||
|
||||
@dataclass
|
||||
class TrackingConfig:
|
||||
"""Configuration for the tracking phase"""
|
||||
model_id: str
|
||||
model_file: str
|
||||
trigger_classes: List[str]
|
||||
min_confidence: float = 0.6
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, data: Dict[str, Any]) -> 'TrackingConfig':
|
||||
return cls(
|
||||
model_id=data['modelId'],
|
||||
model_file=data['modelFile'],
|
||||
trigger_classes=data.get('triggerClasses', []),
|
||||
min_confidence=data.get('minConfidence', 0.6)
|
||||
)
|
||||
|
||||
|
||||
@dataclass
|
||||
class PipelineConfig:
|
||||
"""Main pipeline configuration"""
|
||||
model_id: str
|
||||
model_file: str
|
||||
trigger_classes: List[str]
|
||||
min_confidence: float = 0.5
|
||||
crop: bool = False
|
||||
branches: List[ModelBranch] = field(default_factory=list)
|
||||
parallel_actions: List[Action] = field(default_factory=list)
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, data: Dict[str, Any]) -> 'PipelineConfig':
|
||||
branches = [ModelBranch.from_dict(b) for b in data.get('branches', [])]
|
||||
parallel_actions = [Action.from_dict(a) for a in data.get('parallelActions', [])]
|
||||
|
||||
return cls(
|
||||
model_id=data['modelId'],
|
||||
model_file=data['modelFile'],
|
||||
trigger_classes=data.get('triggerClasses', []),
|
||||
min_confidence=data.get('minConfidence', 0.5),
|
||||
crop=data.get('crop', False),
|
||||
branches=branches,
|
||||
parallel_actions=parallel_actions
|
||||
)
|
||||
|
||||
|
||||
class PipelineParser:
|
||||
"""Parser for pipeline.json configuration files"""
|
||||
|
||||
def __init__(self):
|
||||
self.redis_config: Optional[RedisConfig] = None
|
||||
self.postgresql_config: Optional[PostgreSQLConfig] = None
|
||||
self.tracking_config: Optional[TrackingConfig] = None
|
||||
self.pipeline_config: Optional[PipelineConfig] = None
|
||||
self._model_dependencies: Set[str] = set()
|
||||
|
||||
def parse(self, config_path: Path) -> bool:
|
||||
"""
|
||||
Parse a pipeline.json configuration file
|
||||
|
||||
Args:
|
||||
config_path: Path to the pipeline.json file
|
||||
|
||||
Returns:
|
||||
True if parsing was successful, False otherwise
|
||||
"""
|
||||
try:
|
||||
if not config_path.exists():
|
||||
logger.error(f"Pipeline config not found: {config_path}")
|
||||
return False
|
||||
|
||||
with open(config_path, 'r') as f:
|
||||
data = json.load(f)
|
||||
|
||||
return self.parse_dict(data)
|
||||
|
||||
except json.JSONDecodeError as e:
|
||||
logger.error(f"Invalid JSON in pipeline config: {str(e)}")
|
||||
return False
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to parse pipeline config: {str(e)}", exc_info=True)
|
||||
return False
|
||||
|
||||
def parse_dict(self, data: Dict[str, Any]) -> bool:
|
||||
"""
|
||||
Parse a pipeline configuration from a dictionary
|
||||
|
||||
Args:
|
||||
data: The configuration dictionary
|
||||
|
||||
Returns:
|
||||
True if parsing was successful, False otherwise
|
||||
"""
|
||||
try:
|
||||
# Parse Redis configuration
|
||||
if 'redis' in data:
|
||||
self.redis_config = RedisConfig.from_dict(data['redis'])
|
||||
logger.debug(f"Parsed Redis config: {self.redis_config.host}:{self.redis_config.port}")
|
||||
|
||||
# Parse PostgreSQL configuration
|
||||
if 'postgresql' in data:
|
||||
self.postgresql_config = PostgreSQLConfig.from_dict(data['postgresql'])
|
||||
logger.debug(f"Parsed PostgreSQL config: {self.postgresql_config.host}:{self.postgresql_config.port}/{self.postgresql_config.database}")
|
||||
|
||||
# Parse tracking configuration
|
||||
if 'tracking' in data:
|
||||
self.tracking_config = TrackingConfig.from_dict(data['tracking'])
|
||||
self._model_dependencies.add(self.tracking_config.model_file)
|
||||
logger.debug(f"Parsed tracking config: {self.tracking_config.model_id}")
|
||||
|
||||
# Parse main pipeline configuration
|
||||
if 'pipeline' in data:
|
||||
self.pipeline_config = PipelineConfig.from_dict(data['pipeline'])
|
||||
self._collect_model_dependencies(self.pipeline_config)
|
||||
logger.debug(f"Parsed pipeline config: {self.pipeline_config.model_id}")
|
||||
|
||||
logger.info(f"Successfully parsed pipeline configuration")
|
||||
logger.debug(f"Model dependencies: {self._model_dependencies}")
|
||||
return True
|
||||
|
||||
except KeyError as e:
|
||||
logger.error(f"Missing required field in pipeline config: {str(e)}")
|
||||
return False
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to parse pipeline config: {str(e)}", exc_info=True)
|
||||
return False
|
||||
|
||||
def _collect_model_dependencies(self, config: Any) -> None:
|
||||
"""
|
||||
Recursively collect all model file dependencies
|
||||
|
||||
Args:
|
||||
config: Pipeline or branch configuration
|
||||
"""
|
||||
if hasattr(config, 'model_file'):
|
||||
self._model_dependencies.add(config.model_file)
|
||||
|
||||
if hasattr(config, 'branches'):
|
||||
for branch in config.branches:
|
||||
self._collect_model_dependencies(branch)
|
||||
|
||||
def get_model_dependencies(self) -> Set[str]:
|
||||
"""
|
||||
Get all model file dependencies from the pipeline
|
||||
|
||||
Returns:
|
||||
Set of model filenames required by the pipeline
|
||||
"""
|
||||
return self._model_dependencies.copy()
|
||||
|
||||
def validate(self) -> bool:
|
||||
"""
|
||||
Validate the parsed configuration
|
||||
|
||||
Returns:
|
||||
True if configuration is valid, False otherwise
|
||||
"""
|
||||
if not self.pipeline_config:
|
||||
logger.error("No pipeline configuration found")
|
||||
return False
|
||||
|
||||
# Check that all required model files are specified
|
||||
if not self.pipeline_config.model_file:
|
||||
logger.error("Main pipeline model file not specified")
|
||||
return False
|
||||
|
||||
# Validate action configurations
|
||||
if not self._validate_actions(self.pipeline_config):
|
||||
return False
|
||||
|
||||
# Validate parallel actions
|
||||
for action in self.pipeline_config.parallel_actions:
|
||||
if action.type == ActionType.POSTGRESQL_UPDATE_COMBINED:
|
||||
wait_for = action.params.get('waitForBranches', [])
|
||||
if wait_for:
|
||||
# Check that referenced branches exist
|
||||
branch_ids = self._get_all_branch_ids(self.pipeline_config)
|
||||
for branch_id in wait_for:
|
||||
if branch_id not in branch_ids:
|
||||
logger.error(f"Referenced branch '{branch_id}' in waitForBranches not found")
|
||||
return False
|
||||
|
||||
logger.info("Pipeline configuration validated successfully")
|
||||
return True
|
||||
|
||||
def _validate_actions(self, config: Any) -> bool:
|
||||
"""
|
||||
Validate actions in a pipeline or branch configuration
|
||||
|
||||
Args:
|
||||
config: Pipeline or branch configuration
|
||||
|
||||
Returns:
|
||||
True if valid, False otherwise
|
||||
"""
|
||||
if hasattr(config, 'actions'):
|
||||
for action in config.actions:
|
||||
# Validate Redis actions need Redis config
|
||||
if action.type in [ActionType.REDIS_SAVE_IMAGE, ActionType.REDIS_PUBLISH]:
|
||||
if not self.redis_config:
|
||||
logger.error(f"Action {action.type} requires Redis configuration")
|
||||
return False
|
||||
|
||||
# Validate PostgreSQL actions need PostgreSQL config
|
||||
if action.type in [ActionType.POSTGRESQL_UPDATE, ActionType.POSTGRESQL_UPDATE_COMBINED, ActionType.POSTGRESQL_INSERT]:
|
||||
if not self.postgresql_config:
|
||||
logger.error(f"Action {action.type} requires PostgreSQL configuration")
|
||||
return False
|
||||
|
||||
# Recursively validate branches
|
||||
if hasattr(config, 'branches'):
|
||||
for branch in config.branches:
|
||||
if not self._validate_actions(branch):
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
def _get_all_branch_ids(self, config: Any, branch_ids: Set[str] = None) -> Set[str]:
|
||||
"""
|
||||
Recursively collect all branch model IDs
|
||||
|
||||
Args:
|
||||
config: Pipeline or branch configuration
|
||||
branch_ids: Set to collect IDs into
|
||||
|
||||
Returns:
|
||||
Set of all branch model IDs
|
||||
"""
|
||||
if branch_ids is None:
|
||||
branch_ids = set()
|
||||
|
||||
if hasattr(config, 'branches'):
|
||||
for branch in config.branches:
|
||||
branch_ids.add(branch.model_id)
|
||||
self._get_all_branch_ids(branch, branch_ids)
|
||||
|
||||
return branch_ids
|
||||
|
||||
def get_redis_config(self) -> Optional[RedisConfig]:
|
||||
"""Get the Redis configuration"""
|
||||
return self.redis_config
|
||||
|
||||
def get_postgresql_config(self) -> Optional[PostgreSQLConfig]:
|
||||
"""Get the PostgreSQL configuration"""
|
||||
return self.postgresql_config
|
||||
|
||||
def get_tracking_config(self) -> Optional[TrackingConfig]:
|
||||
"""Get the tracking configuration"""
|
||||
return self.tracking_config
|
||||
|
||||
def get_pipeline_config(self) -> Optional[PipelineConfig]:
|
||||
"""Get the main pipeline configuration"""
|
||||
return self.pipeline_config
|
||||
|
|
@ -1,18 +0,0 @@
|
|||
"""
|
||||
Comprehensive health monitoring system for detector worker.
|
||||
Tracks stream health, thread responsiveness, and system performance.
|
||||
"""
|
||||
|
||||
from .health import HealthMonitor, HealthStatus, HealthCheck
|
||||
from .stream_health import StreamHealthTracker
|
||||
from .thread_health import ThreadHealthMonitor
|
||||
from .recovery import RecoveryManager
|
||||
|
||||
__all__ = [
|
||||
'HealthMonitor',
|
||||
'HealthStatus',
|
||||
'HealthCheck',
|
||||
'StreamHealthTracker',
|
||||
'ThreadHealthMonitor',
|
||||
'RecoveryManager'
|
||||
]
|
||||
|
|
@ -1,456 +0,0 @@
|
|||
"""
|
||||
Core health monitoring system for comprehensive stream and system health tracking.
|
||||
Provides centralized health status, alerting, and recovery coordination.
|
||||
"""
|
||||
import time
|
||||
import threading
|
||||
import logging
|
||||
import psutil
|
||||
from typing import Dict, List, Optional, Any, Callable
|
||||
from dataclasses import dataclass, field
|
||||
from enum import Enum
|
||||
from collections import defaultdict, deque
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class HealthStatus(Enum):
|
||||
"""Health status levels."""
|
||||
HEALTHY = "healthy"
|
||||
WARNING = "warning"
|
||||
CRITICAL = "critical"
|
||||
UNKNOWN = "unknown"
|
||||
|
||||
|
||||
@dataclass
|
||||
class HealthCheck:
|
||||
"""Individual health check result."""
|
||||
name: str
|
||||
status: HealthStatus
|
||||
message: str
|
||||
timestamp: float = field(default_factory=time.time)
|
||||
details: Dict[str, Any] = field(default_factory=dict)
|
||||
recovery_action: Optional[str] = None
|
||||
|
||||
|
||||
@dataclass
|
||||
class HealthMetrics:
|
||||
"""Health metrics for a component."""
|
||||
component_id: str
|
||||
last_update: float
|
||||
frame_count: int = 0
|
||||
error_count: int = 0
|
||||
warning_count: int = 0
|
||||
restart_count: int = 0
|
||||
avg_frame_interval: float = 0.0
|
||||
last_frame_time: Optional[float] = None
|
||||
thread_alive: bool = True
|
||||
connection_healthy: bool = True
|
||||
memory_usage_mb: float = 0.0
|
||||
cpu_usage_percent: float = 0.0
|
||||
|
||||
|
||||
class HealthMonitor:
|
||||
"""Comprehensive health monitoring system."""
|
||||
|
||||
def __init__(self, check_interval: float = 30.0):
|
||||
"""
|
||||
Initialize health monitor.
|
||||
|
||||
Args:
|
||||
check_interval: Interval between health checks in seconds
|
||||
"""
|
||||
self.check_interval = check_interval
|
||||
self.running = False
|
||||
self.monitor_thread = None
|
||||
self._lock = threading.RLock()
|
||||
|
||||
# Health data storage
|
||||
self.health_checks: Dict[str, HealthCheck] = {}
|
||||
self.metrics: Dict[str, HealthMetrics] = {}
|
||||
self.alert_history: deque = deque(maxlen=1000)
|
||||
self.recovery_actions: deque = deque(maxlen=500)
|
||||
|
||||
# Thresholds (configurable)
|
||||
self.thresholds = {
|
||||
'frame_stale_warning_seconds': 120, # 2 minutes
|
||||
'frame_stale_critical_seconds': 300, # 5 minutes
|
||||
'thread_unresponsive_seconds': 60, # 1 minute
|
||||
'memory_warning_mb': 500, # 500MB per stream
|
||||
'memory_critical_mb': 1000, # 1GB per stream
|
||||
'cpu_warning_percent': 80, # 80% CPU
|
||||
'cpu_critical_percent': 95, # 95% CPU
|
||||
'error_rate_warning': 0.1, # 10% error rate
|
||||
'error_rate_critical': 0.3, # 30% error rate
|
||||
'restart_threshold': 3 # Max restarts per hour
|
||||
}
|
||||
|
||||
# Health check functions
|
||||
self.health_checkers: List[Callable[[], List[HealthCheck]]] = []
|
||||
self.recovery_callbacks: Dict[str, Callable[[str, HealthCheck], bool]] = {}
|
||||
|
||||
# System monitoring
|
||||
self.process = psutil.Process()
|
||||
self.system_start_time = time.time()
|
||||
|
||||
def start(self):
|
||||
"""Start health monitoring."""
|
||||
if self.running:
|
||||
logger.warning("Health monitor already running")
|
||||
return
|
||||
|
||||
self.running = True
|
||||
self.monitor_thread = threading.Thread(target=self._monitor_loop, daemon=True)
|
||||
self.monitor_thread.start()
|
||||
logger.info(f"Health monitor started (check interval: {self.check_interval}s)")
|
||||
|
||||
def stop(self):
|
||||
"""Stop health monitoring."""
|
||||
self.running = False
|
||||
if self.monitor_thread:
|
||||
self.monitor_thread.join(timeout=5.0)
|
||||
logger.info("Health monitor stopped")
|
||||
|
||||
def register_health_checker(self, checker: Callable[[], List[HealthCheck]]):
|
||||
"""Register a health check function."""
|
||||
self.health_checkers.append(checker)
|
||||
logger.debug(f"Registered health checker: {checker.__name__}")
|
||||
|
||||
def register_recovery_callback(self, component: str, callback: Callable[[str, HealthCheck], bool]):
|
||||
"""Register a recovery callback for a component."""
|
||||
self.recovery_callbacks[component] = callback
|
||||
logger.debug(f"Registered recovery callback for {component}")
|
||||
|
||||
def update_metrics(self, component_id: str, **kwargs):
|
||||
"""Update metrics for a component."""
|
||||
with self._lock:
|
||||
if component_id not in self.metrics:
|
||||
self.metrics[component_id] = HealthMetrics(
|
||||
component_id=component_id,
|
||||
last_update=time.time()
|
||||
)
|
||||
|
||||
metrics = self.metrics[component_id]
|
||||
metrics.last_update = time.time()
|
||||
|
||||
# Update provided metrics
|
||||
for key, value in kwargs.items():
|
||||
if hasattr(metrics, key):
|
||||
setattr(metrics, key, value)
|
||||
|
||||
def report_frame_received(self, component_id: str):
|
||||
"""Report that a frame was received for a component."""
|
||||
current_time = time.time()
|
||||
with self._lock:
|
||||
if component_id not in self.metrics:
|
||||
self.metrics[component_id] = HealthMetrics(
|
||||
component_id=component_id,
|
||||
last_update=current_time
|
||||
)
|
||||
|
||||
metrics = self.metrics[component_id]
|
||||
|
||||
# Update frame metrics
|
||||
if metrics.last_frame_time:
|
||||
interval = current_time - metrics.last_frame_time
|
||||
# Moving average of frame intervals
|
||||
if metrics.avg_frame_interval == 0:
|
||||
metrics.avg_frame_interval = interval
|
||||
else:
|
||||
metrics.avg_frame_interval = (metrics.avg_frame_interval * 0.9) + (interval * 0.1)
|
||||
|
||||
metrics.last_frame_time = current_time
|
||||
metrics.frame_count += 1
|
||||
metrics.last_update = current_time
|
||||
|
||||
def report_error(self, component_id: str, error_type: str = "general"):
|
||||
"""Report an error for a component."""
|
||||
with self._lock:
|
||||
if component_id not in self.metrics:
|
||||
self.metrics[component_id] = HealthMetrics(
|
||||
component_id=component_id,
|
||||
last_update=time.time()
|
||||
)
|
||||
|
||||
self.metrics[component_id].error_count += 1
|
||||
self.metrics[component_id].last_update = time.time()
|
||||
|
||||
logger.debug(f"Error reported for {component_id}: {error_type}")
|
||||
|
||||
def report_warning(self, component_id: str, warning_type: str = "general"):
|
||||
"""Report a warning for a component."""
|
||||
with self._lock:
|
||||
if component_id not in self.metrics:
|
||||
self.metrics[component_id] = HealthMetrics(
|
||||
component_id=component_id,
|
||||
last_update=time.time()
|
||||
)
|
||||
|
||||
self.metrics[component_id].warning_count += 1
|
||||
self.metrics[component_id].last_update = time.time()
|
||||
|
||||
logger.debug(f"Warning reported for {component_id}: {warning_type}")
|
||||
|
||||
def report_restart(self, component_id: str):
|
||||
"""Report that a component was restarted."""
|
||||
with self._lock:
|
||||
if component_id not in self.metrics:
|
||||
self.metrics[component_id] = HealthMetrics(
|
||||
component_id=component_id,
|
||||
last_update=time.time()
|
||||
)
|
||||
|
||||
self.metrics[component_id].restart_count += 1
|
||||
self.metrics[component_id].last_update = time.time()
|
||||
|
||||
# Log recovery action
|
||||
recovery_action = {
|
||||
'timestamp': time.time(),
|
||||
'component': component_id,
|
||||
'action': 'restart',
|
||||
'reason': 'manual_restart'
|
||||
}
|
||||
|
||||
with self._lock:
|
||||
self.recovery_actions.append(recovery_action)
|
||||
|
||||
logger.info(f"Restart reported for {component_id}")
|
||||
|
||||
def get_health_status(self, component_id: Optional[str] = None) -> Dict[str, Any]:
|
||||
"""Get comprehensive health status."""
|
||||
with self._lock:
|
||||
if component_id:
|
||||
# Get health for specific component
|
||||
return self._get_component_health(component_id)
|
||||
else:
|
||||
# Get overall health status
|
||||
return self._get_overall_health()
|
||||
|
||||
def _get_component_health(self, component_id: str) -> Dict[str, Any]:
|
||||
"""Get health status for a specific component."""
|
||||
if component_id not in self.metrics:
|
||||
return {
|
||||
'component_id': component_id,
|
||||
'status': HealthStatus.UNKNOWN.value,
|
||||
'message': 'No metrics available',
|
||||
'metrics': {}
|
||||
}
|
||||
|
||||
metrics = self.metrics[component_id]
|
||||
current_time = time.time()
|
||||
|
||||
# Determine health status
|
||||
status = HealthStatus.HEALTHY
|
||||
issues = []
|
||||
|
||||
# Check frame freshness
|
||||
if metrics.last_frame_time:
|
||||
frame_age = current_time - metrics.last_frame_time
|
||||
if frame_age > self.thresholds['frame_stale_critical_seconds']:
|
||||
status = HealthStatus.CRITICAL
|
||||
issues.append(f"Frames stale for {frame_age:.1f}s")
|
||||
elif frame_age > self.thresholds['frame_stale_warning_seconds']:
|
||||
if status == HealthStatus.HEALTHY:
|
||||
status = HealthStatus.WARNING
|
||||
issues.append(f"Frames aging ({frame_age:.1f}s)")
|
||||
|
||||
# Check error rates
|
||||
if metrics.frame_count > 0:
|
||||
error_rate = metrics.error_count / metrics.frame_count
|
||||
if error_rate > self.thresholds['error_rate_critical']:
|
||||
status = HealthStatus.CRITICAL
|
||||
issues.append(f"High error rate ({error_rate:.1%})")
|
||||
elif error_rate > self.thresholds['error_rate_warning']:
|
||||
if status == HealthStatus.HEALTHY:
|
||||
status = HealthStatus.WARNING
|
||||
issues.append(f"Elevated error rate ({error_rate:.1%})")
|
||||
|
||||
# Check restart frequency
|
||||
restart_rate = metrics.restart_count / max(1, (current_time - self.system_start_time) / 3600)
|
||||
if restart_rate > self.thresholds['restart_threshold']:
|
||||
status = HealthStatus.CRITICAL
|
||||
issues.append(f"Frequent restarts ({restart_rate:.1f}/hour)")
|
||||
|
||||
# Check thread health
|
||||
if not metrics.thread_alive:
|
||||
status = HealthStatus.CRITICAL
|
||||
issues.append("Thread not alive")
|
||||
|
||||
# Check connection health
|
||||
if not metrics.connection_healthy:
|
||||
if status == HealthStatus.HEALTHY:
|
||||
status = HealthStatus.WARNING
|
||||
issues.append("Connection unhealthy")
|
||||
|
||||
return {
|
||||
'component_id': component_id,
|
||||
'status': status.value,
|
||||
'message': '; '.join(issues) if issues else 'All checks passing',
|
||||
'metrics': {
|
||||
'frame_count': metrics.frame_count,
|
||||
'error_count': metrics.error_count,
|
||||
'warning_count': metrics.warning_count,
|
||||
'restart_count': metrics.restart_count,
|
||||
'avg_frame_interval': metrics.avg_frame_interval,
|
||||
'last_frame_age': current_time - metrics.last_frame_time if metrics.last_frame_time else None,
|
||||
'thread_alive': metrics.thread_alive,
|
||||
'connection_healthy': metrics.connection_healthy,
|
||||
'memory_usage_mb': metrics.memory_usage_mb,
|
||||
'cpu_usage_percent': metrics.cpu_usage_percent,
|
||||
'uptime_seconds': current_time - self.system_start_time
|
||||
},
|
||||
'last_update': metrics.last_update
|
||||
}
|
||||
|
||||
def _get_overall_health(self) -> Dict[str, Any]:
|
||||
"""Get overall system health status."""
|
||||
current_time = time.time()
|
||||
components = {}
|
||||
overall_status = HealthStatus.HEALTHY
|
||||
|
||||
# Get health for all components
|
||||
for component_id in self.metrics.keys():
|
||||
component_health = self._get_component_health(component_id)
|
||||
components[component_id] = component_health
|
||||
|
||||
# Determine overall status
|
||||
component_status = HealthStatus(component_health['status'])
|
||||
if component_status == HealthStatus.CRITICAL:
|
||||
overall_status = HealthStatus.CRITICAL
|
||||
elif component_status == HealthStatus.WARNING and overall_status == HealthStatus.HEALTHY:
|
||||
overall_status = HealthStatus.WARNING
|
||||
|
||||
# System metrics
|
||||
try:
|
||||
system_memory = self.process.memory_info()
|
||||
system_cpu = self.process.cpu_percent()
|
||||
except Exception:
|
||||
system_memory = None
|
||||
system_cpu = 0.0
|
||||
|
||||
return {
|
||||
'overall_status': overall_status.value,
|
||||
'timestamp': current_time,
|
||||
'uptime_seconds': current_time - self.system_start_time,
|
||||
'total_components': len(self.metrics),
|
||||
'components': components,
|
||||
'system_metrics': {
|
||||
'memory_mb': system_memory.rss / (1024 * 1024) if system_memory else 0,
|
||||
'cpu_percent': system_cpu,
|
||||
'process_id': self.process.pid
|
||||
},
|
||||
'recent_alerts': list(self.alert_history)[-10:], # Last 10 alerts
|
||||
'recent_recoveries': list(self.recovery_actions)[-10:] # Last 10 recovery actions
|
||||
}
|
||||
|
||||
def _monitor_loop(self):
|
||||
"""Main health monitoring loop."""
|
||||
logger.info("Health monitor loop started")
|
||||
|
||||
while self.running:
|
||||
try:
|
||||
start_time = time.time()
|
||||
|
||||
# Run all registered health checks
|
||||
all_checks = []
|
||||
for checker in self.health_checkers:
|
||||
try:
|
||||
checks = checker()
|
||||
all_checks.extend(checks)
|
||||
except Exception as e:
|
||||
logger.error(f"Error in health checker {checker.__name__}: {e}")
|
||||
|
||||
# Process health checks and trigger recovery if needed
|
||||
for check in all_checks:
|
||||
self._process_health_check(check)
|
||||
|
||||
# Update system metrics
|
||||
self._update_system_metrics()
|
||||
|
||||
# Sleep until next check
|
||||
elapsed = time.time() - start_time
|
||||
sleep_time = max(0, self.check_interval - elapsed)
|
||||
if sleep_time > 0:
|
||||
time.sleep(sleep_time)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in health monitor loop: {e}")
|
||||
time.sleep(5.0) # Fallback sleep
|
||||
|
||||
logger.info("Health monitor loop ended")
|
||||
|
||||
def _process_health_check(self, check: HealthCheck):
|
||||
"""Process a health check result and trigger recovery if needed."""
|
||||
with self._lock:
|
||||
# Store health check
|
||||
self.health_checks[check.name] = check
|
||||
|
||||
# Log alerts for non-healthy status
|
||||
if check.status != HealthStatus.HEALTHY:
|
||||
alert = {
|
||||
'timestamp': check.timestamp,
|
||||
'component': check.name,
|
||||
'status': check.status.value,
|
||||
'message': check.message,
|
||||
'details': check.details
|
||||
}
|
||||
self.alert_history.append(alert)
|
||||
|
||||
logger.warning(f"Health alert [{check.status.value.upper()}] {check.name}: {check.message}")
|
||||
|
||||
# Trigger recovery if critical and recovery action available
|
||||
if check.status == HealthStatus.CRITICAL and check.recovery_action:
|
||||
self._trigger_recovery(check.name, check)
|
||||
|
||||
def _trigger_recovery(self, component: str, check: HealthCheck):
|
||||
"""Trigger recovery action for a component."""
|
||||
if component in self.recovery_callbacks:
|
||||
try:
|
||||
logger.info(f"Triggering recovery for {component}: {check.recovery_action}")
|
||||
|
||||
success = self.recovery_callbacks[component](component, check)
|
||||
|
||||
recovery_action = {
|
||||
'timestamp': time.time(),
|
||||
'component': component,
|
||||
'action': check.recovery_action,
|
||||
'reason': check.message,
|
||||
'success': success
|
||||
}
|
||||
|
||||
with self._lock:
|
||||
self.recovery_actions.append(recovery_action)
|
||||
|
||||
if success:
|
||||
logger.info(f"Recovery successful for {component}")
|
||||
else:
|
||||
logger.error(f"Recovery failed for {component}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in recovery callback for {component}: {e}")
|
||||
|
||||
def _update_system_metrics(self):
|
||||
"""Update system-level metrics."""
|
||||
try:
|
||||
# Update process metrics for all components
|
||||
current_time = time.time()
|
||||
|
||||
with self._lock:
|
||||
for component_id, metrics in self.metrics.items():
|
||||
# Update CPU and memory if available
|
||||
try:
|
||||
# This is a simplified approach - in practice you'd want
|
||||
# per-thread or per-component resource tracking
|
||||
metrics.cpu_usage_percent = self.process.cpu_percent() / len(self.metrics)
|
||||
memory_info = self.process.memory_info()
|
||||
metrics.memory_usage_mb = memory_info.rss / (1024 * 1024) / len(self.metrics)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error updating system metrics: {e}")
|
||||
|
||||
|
||||
# Global health monitor instance
|
||||
health_monitor = HealthMonitor()
|
||||
|
|
@ -1,385 +0,0 @@
|
|||
"""
|
||||
Recovery manager for automatic handling of health issues.
|
||||
Provides circuit breaker patterns, automatic restarts, and graceful degradation.
|
||||
"""
|
||||
import time
|
||||
import logging
|
||||
import threading
|
||||
from typing import Dict, List, Optional, Any, Callable
|
||||
from dataclasses import dataclass
|
||||
from enum import Enum
|
||||
from collections import defaultdict, deque
|
||||
|
||||
from .health import HealthCheck, HealthStatus, health_monitor
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class RecoveryAction(Enum):
|
||||
"""Types of recovery actions."""
|
||||
RESTART_STREAM = "restart_stream"
|
||||
RESTART_THREAD = "restart_thread"
|
||||
CLEAR_BUFFER = "clear_buffer"
|
||||
RECONNECT = "reconnect"
|
||||
THROTTLE = "throttle"
|
||||
DISABLE = "disable"
|
||||
|
||||
|
||||
@dataclass
|
||||
class RecoveryAttempt:
|
||||
"""Record of a recovery attempt."""
|
||||
timestamp: float
|
||||
component: str
|
||||
action: RecoveryAction
|
||||
reason: str
|
||||
success: bool
|
||||
details: Dict[str, Any] = None
|
||||
|
||||
|
||||
@dataclass
|
||||
class RecoveryState:
|
||||
"""Recovery state for a component - simplified without circuit breaker."""
|
||||
failure_count: int = 0
|
||||
success_count: int = 0
|
||||
last_failure_time: Optional[float] = None
|
||||
last_success_time: Optional[float] = None
|
||||
|
||||
|
||||
class RecoveryManager:
|
||||
"""Manages automatic recovery actions for health issues."""
|
||||
|
||||
def __init__(self):
|
||||
self.recovery_handlers: Dict[str, Callable[[str, HealthCheck], bool]] = {}
|
||||
self.recovery_states: Dict[str, RecoveryState] = {}
|
||||
self.recovery_history: deque = deque(maxlen=1000)
|
||||
self._lock = threading.RLock()
|
||||
|
||||
# Configuration - simplified without circuit breaker
|
||||
self.recovery_cooldown = 30 # 30 seconds between recovery attempts
|
||||
self.max_attempts_per_hour = 20 # Still limit to prevent spam, but much higher
|
||||
|
||||
# Track recovery attempts per component
|
||||
self.recovery_attempts: Dict[str, deque] = defaultdict(lambda: deque(maxlen=50))
|
||||
|
||||
# Register with health monitor
|
||||
health_monitor.register_recovery_callback("stream", self._handle_stream_recovery)
|
||||
health_monitor.register_recovery_callback("thread", self._handle_thread_recovery)
|
||||
health_monitor.register_recovery_callback("buffer", self._handle_buffer_recovery)
|
||||
|
||||
def register_recovery_handler(self, action: RecoveryAction, handler: Callable[[str, Dict[str, Any]], bool]):
|
||||
"""
|
||||
Register a recovery handler for a specific action.
|
||||
|
||||
Args:
|
||||
action: Type of recovery action
|
||||
handler: Function that performs the recovery
|
||||
"""
|
||||
self.recovery_handlers[action.value] = handler
|
||||
logger.info(f"Registered recovery handler for {action.value}")
|
||||
|
||||
def can_attempt_recovery(self, component: str) -> bool:
|
||||
"""
|
||||
Check if recovery can be attempted for a component.
|
||||
|
||||
Args:
|
||||
component: Component identifier
|
||||
|
||||
Returns:
|
||||
True if recovery can be attempted (always allow with minimal throttling)
|
||||
"""
|
||||
with self._lock:
|
||||
current_time = time.time()
|
||||
|
||||
# Check recovery attempt rate limiting (much more permissive)
|
||||
recent_attempts = [
|
||||
attempt for attempt in self.recovery_attempts[component]
|
||||
if current_time - attempt <= 3600 # Last hour
|
||||
]
|
||||
|
||||
# Only block if truly excessive attempts
|
||||
if len(recent_attempts) >= self.max_attempts_per_hour:
|
||||
logger.warning(f"Recovery rate limit exceeded for {component} "
|
||||
f"({len(recent_attempts)} attempts in last hour)")
|
||||
return False
|
||||
|
||||
# Check cooldown period (shorter cooldown)
|
||||
if recent_attempts:
|
||||
last_attempt = max(recent_attempts)
|
||||
if current_time - last_attempt < self.recovery_cooldown:
|
||||
logger.debug(f"Recovery cooldown active for {component} "
|
||||
f"(last attempt {current_time - last_attempt:.1f}s ago)")
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
def attempt_recovery(self, component: str, action: RecoveryAction, reason: str,
|
||||
details: Optional[Dict[str, Any]] = None) -> bool:
|
||||
"""
|
||||
Attempt recovery for a component.
|
||||
|
||||
Args:
|
||||
component: Component identifier
|
||||
action: Recovery action to perform
|
||||
reason: Reason for recovery
|
||||
details: Additional details
|
||||
|
||||
Returns:
|
||||
True if recovery was successful
|
||||
"""
|
||||
if not self.can_attempt_recovery(component):
|
||||
return False
|
||||
|
||||
current_time = time.time()
|
||||
|
||||
logger.info(f"Attempting recovery for {component}: {action.value} ({reason})")
|
||||
|
||||
try:
|
||||
# Record recovery attempt
|
||||
with self._lock:
|
||||
self.recovery_attempts[component].append(current_time)
|
||||
|
||||
# Perform recovery action
|
||||
success = self._execute_recovery_action(component, action, details or {})
|
||||
|
||||
# Record recovery result
|
||||
attempt = RecoveryAttempt(
|
||||
timestamp=current_time,
|
||||
component=component,
|
||||
action=action,
|
||||
reason=reason,
|
||||
success=success,
|
||||
details=details
|
||||
)
|
||||
|
||||
with self._lock:
|
||||
self.recovery_history.append(attempt)
|
||||
|
||||
# Update recovery state
|
||||
self._update_recovery_state(component, success)
|
||||
|
||||
if success:
|
||||
logger.info(f"Recovery successful for {component}: {action.value}")
|
||||
else:
|
||||
logger.error(f"Recovery failed for {component}: {action.value}")
|
||||
|
||||
return success
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error during recovery for {component}: {e}")
|
||||
self._update_recovery_state(component, False)
|
||||
return False
|
||||
|
||||
def _execute_recovery_action(self, component: str, action: RecoveryAction,
|
||||
details: Dict[str, Any]) -> bool:
|
||||
"""Execute a specific recovery action."""
|
||||
handler_key = action.value
|
||||
|
||||
if handler_key not in self.recovery_handlers:
|
||||
logger.error(f"No recovery handler registered for action: {handler_key}")
|
||||
return False
|
||||
|
||||
try:
|
||||
handler = self.recovery_handlers[handler_key]
|
||||
return handler(component, details)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error executing recovery action {handler_key} for {component}: {e}")
|
||||
return False
|
||||
|
||||
def _update_recovery_state(self, component: str, success: bool):
|
||||
"""Update recovery state based on recovery result."""
|
||||
current_time = time.time()
|
||||
|
||||
with self._lock:
|
||||
if component not in self.recovery_states:
|
||||
self.recovery_states[component] = RecoveryState()
|
||||
|
||||
state = self.recovery_states[component]
|
||||
|
||||
if success:
|
||||
state.success_count += 1
|
||||
state.last_success_time = current_time
|
||||
# Reset failure count on success
|
||||
state.failure_count = max(0, state.failure_count - 1)
|
||||
logger.debug(f"Recovery success for {component} (total successes: {state.success_count})")
|
||||
else:
|
||||
state.failure_count += 1
|
||||
state.last_failure_time = current_time
|
||||
logger.debug(f"Recovery failure for {component} (total failures: {state.failure_count})")
|
||||
|
||||
def _handle_stream_recovery(self, component: str, health_check: HealthCheck) -> bool:
|
||||
"""Handle recovery for stream-related issues."""
|
||||
if "frames" in health_check.name:
|
||||
# Frame-related issue - restart stream
|
||||
return self.attempt_recovery(
|
||||
component,
|
||||
RecoveryAction.RESTART_STREAM,
|
||||
health_check.message,
|
||||
health_check.details
|
||||
)
|
||||
elif "connection" in health_check.name:
|
||||
# Connection issue - reconnect
|
||||
return self.attempt_recovery(
|
||||
component,
|
||||
RecoveryAction.RECONNECT,
|
||||
health_check.message,
|
||||
health_check.details
|
||||
)
|
||||
elif "errors" in health_check.name:
|
||||
# High error rate - throttle or restart
|
||||
return self.attempt_recovery(
|
||||
component,
|
||||
RecoveryAction.THROTTLE,
|
||||
health_check.message,
|
||||
health_check.details
|
||||
)
|
||||
else:
|
||||
# Generic stream issue - restart
|
||||
return self.attempt_recovery(
|
||||
component,
|
||||
RecoveryAction.RESTART_STREAM,
|
||||
health_check.message,
|
||||
health_check.details
|
||||
)
|
||||
|
||||
def _handle_thread_recovery(self, component: str, health_check: HealthCheck) -> bool:
|
||||
"""Handle recovery for thread-related issues."""
|
||||
if "deadlock" in health_check.name:
|
||||
# Deadlock detected - restart thread
|
||||
return self.attempt_recovery(
|
||||
component,
|
||||
RecoveryAction.RESTART_THREAD,
|
||||
health_check.message,
|
||||
health_check.details
|
||||
)
|
||||
elif "responsive" in health_check.name:
|
||||
# Thread unresponsive - restart
|
||||
return self.attempt_recovery(
|
||||
component,
|
||||
RecoveryAction.RESTART_THREAD,
|
||||
health_check.message,
|
||||
health_check.details
|
||||
)
|
||||
else:
|
||||
# Generic thread issue - restart
|
||||
return self.attempt_recovery(
|
||||
component,
|
||||
RecoveryAction.RESTART_THREAD,
|
||||
health_check.message,
|
||||
health_check.details
|
||||
)
|
||||
|
||||
def _handle_buffer_recovery(self, component: str, health_check: HealthCheck) -> bool:
|
||||
"""Handle recovery for buffer-related issues."""
|
||||
# Buffer issues - clear buffer
|
||||
return self.attempt_recovery(
|
||||
component,
|
||||
RecoveryAction.CLEAR_BUFFER,
|
||||
health_check.message,
|
||||
health_check.details
|
||||
)
|
||||
|
||||
def get_recovery_stats(self) -> Dict[str, Any]:
|
||||
"""Get recovery statistics."""
|
||||
current_time = time.time()
|
||||
|
||||
with self._lock:
|
||||
# Calculate stats from history
|
||||
recent_recoveries = [
|
||||
attempt for attempt in self.recovery_history
|
||||
if current_time - attempt.timestamp <= 3600 # Last hour
|
||||
]
|
||||
|
||||
stats_by_component = defaultdict(lambda: {
|
||||
'attempts': 0,
|
||||
'successes': 0,
|
||||
'failures': 0,
|
||||
'last_attempt': None,
|
||||
'last_success': None
|
||||
})
|
||||
|
||||
for attempt in recent_recoveries:
|
||||
stats = stats_by_component[attempt.component]
|
||||
stats['attempts'] += 1
|
||||
|
||||
if attempt.success:
|
||||
stats['successes'] += 1
|
||||
if not stats['last_success'] or attempt.timestamp > stats['last_success']:
|
||||
stats['last_success'] = attempt.timestamp
|
||||
else:
|
||||
stats['failures'] += 1
|
||||
|
||||
if not stats['last_attempt'] or attempt.timestamp > stats['last_attempt']:
|
||||
stats['last_attempt'] = attempt.timestamp
|
||||
|
||||
return {
|
||||
'total_recoveries_last_hour': len(recent_recoveries),
|
||||
'recovery_by_component': dict(stats_by_component),
|
||||
'recovery_states': {
|
||||
component: {
|
||||
'failure_count': state.failure_count,
|
||||
'success_count': state.success_count,
|
||||
'last_failure_time': state.last_failure_time,
|
||||
'last_success_time': state.last_success_time
|
||||
}
|
||||
for component, state in self.recovery_states.items()
|
||||
},
|
||||
'recent_history': [
|
||||
{
|
||||
'timestamp': attempt.timestamp,
|
||||
'component': attempt.component,
|
||||
'action': attempt.action.value,
|
||||
'reason': attempt.reason,
|
||||
'success': attempt.success
|
||||
}
|
||||
for attempt in list(self.recovery_history)[-10:] # Last 10 attempts
|
||||
]
|
||||
}
|
||||
|
||||
def force_recovery(self, component: str, action: RecoveryAction, reason: str = "manual") -> bool:
|
||||
"""
|
||||
Force recovery for a component, bypassing rate limiting.
|
||||
|
||||
Args:
|
||||
component: Component identifier
|
||||
action: Recovery action to perform
|
||||
reason: Reason for forced recovery
|
||||
|
||||
Returns:
|
||||
True if recovery was successful
|
||||
"""
|
||||
logger.info(f"Forcing recovery for {component}: {action.value} ({reason})")
|
||||
|
||||
current_time = time.time()
|
||||
|
||||
try:
|
||||
# Execute recovery action directly
|
||||
success = self._execute_recovery_action(component, action, {})
|
||||
|
||||
# Record forced recovery
|
||||
attempt = RecoveryAttempt(
|
||||
timestamp=current_time,
|
||||
component=component,
|
||||
action=action,
|
||||
reason=f"forced: {reason}",
|
||||
success=success,
|
||||
details={'forced': True}
|
||||
)
|
||||
|
||||
with self._lock:
|
||||
self.recovery_history.append(attempt)
|
||||
self.recovery_attempts[component].append(current_time)
|
||||
|
||||
# Update recovery state
|
||||
self._update_recovery_state(component, success)
|
||||
|
||||
return success
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error during forced recovery for {component}: {e}")
|
||||
return False
|
||||
|
||||
|
||||
# Global recovery manager instance
|
||||
recovery_manager = RecoveryManager()
|
||||
|
|
@ -1,351 +0,0 @@
|
|||
"""
|
||||
Stream-specific health monitoring for video streams.
|
||||
Tracks frame production, connection health, and stream-specific metrics.
|
||||
"""
|
||||
import time
|
||||
import logging
|
||||
import threading
|
||||
import requests
|
||||
from typing import Dict, Optional, List, Any
|
||||
from collections import deque
|
||||
from dataclasses import dataclass
|
||||
|
||||
from .health import HealthCheck, HealthStatus, health_monitor
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@dataclass
|
||||
class StreamMetrics:
|
||||
"""Metrics for an individual stream."""
|
||||
camera_id: str
|
||||
stream_type: str # 'rtsp', 'http_snapshot'
|
||||
start_time: float
|
||||
last_frame_time: Optional[float] = None
|
||||
frame_count: int = 0
|
||||
error_count: int = 0
|
||||
reconnect_count: int = 0
|
||||
bytes_received: int = 0
|
||||
frames_per_second: float = 0.0
|
||||
connection_attempts: int = 0
|
||||
last_connection_test: Optional[float] = None
|
||||
connection_healthy: bool = True
|
||||
last_error: Optional[str] = None
|
||||
last_error_time: Optional[float] = None
|
||||
|
||||
|
||||
class StreamHealthTracker:
|
||||
"""Tracks health for individual video streams."""
|
||||
|
||||
def __init__(self):
|
||||
self.streams: Dict[str, StreamMetrics] = {}
|
||||
self._lock = threading.RLock()
|
||||
|
||||
# Configuration
|
||||
self.connection_test_interval = 300 # Test connection every 5 minutes
|
||||
self.frame_timeout_warning = 120 # Warn if no frames for 2 minutes
|
||||
self.frame_timeout_critical = 300 # Critical if no frames for 5 minutes
|
||||
self.error_rate_threshold = 0.1 # 10% error rate threshold
|
||||
|
||||
# Register with health monitor
|
||||
health_monitor.register_health_checker(self._perform_health_checks)
|
||||
|
||||
def register_stream(self, camera_id: str, stream_type: str, source_url: Optional[str] = None):
|
||||
"""Register a new stream for monitoring."""
|
||||
with self._lock:
|
||||
if camera_id not in self.streams:
|
||||
self.streams[camera_id] = StreamMetrics(
|
||||
camera_id=camera_id,
|
||||
stream_type=stream_type,
|
||||
start_time=time.time()
|
||||
)
|
||||
logger.info(f"Registered stream for monitoring: {camera_id} ({stream_type})")
|
||||
|
||||
# Update health monitor metrics
|
||||
health_monitor.update_metrics(
|
||||
camera_id,
|
||||
thread_alive=True,
|
||||
connection_healthy=True
|
||||
)
|
||||
|
||||
def unregister_stream(self, camera_id: str):
|
||||
"""Unregister a stream from monitoring."""
|
||||
with self._lock:
|
||||
if camera_id in self.streams:
|
||||
del self.streams[camera_id]
|
||||
logger.info(f"Unregistered stream from monitoring: {camera_id}")
|
||||
|
||||
def report_frame_received(self, camera_id: str, frame_size_bytes: int = 0):
|
||||
"""Report that a frame was received."""
|
||||
current_time = time.time()
|
||||
|
||||
with self._lock:
|
||||
if camera_id not in self.streams:
|
||||
logger.warning(f"Frame received for unregistered stream: {camera_id}")
|
||||
return
|
||||
|
||||
stream = self.streams[camera_id]
|
||||
|
||||
# Update frame metrics
|
||||
if stream.last_frame_time:
|
||||
interval = current_time - stream.last_frame_time
|
||||
# Calculate FPS as moving average
|
||||
if stream.frames_per_second == 0:
|
||||
stream.frames_per_second = 1.0 / interval if interval > 0 else 0
|
||||
else:
|
||||
new_fps = 1.0 / interval if interval > 0 else 0
|
||||
stream.frames_per_second = (stream.frames_per_second * 0.9) + (new_fps * 0.1)
|
||||
|
||||
stream.last_frame_time = current_time
|
||||
stream.frame_count += 1
|
||||
stream.bytes_received += frame_size_bytes
|
||||
|
||||
# Report to health monitor
|
||||
health_monitor.report_frame_received(camera_id)
|
||||
health_monitor.update_metrics(
|
||||
camera_id,
|
||||
frame_count=stream.frame_count,
|
||||
avg_frame_interval=1.0 / stream.frames_per_second if stream.frames_per_second > 0 else 0,
|
||||
last_frame_time=current_time
|
||||
)
|
||||
|
||||
def report_error(self, camera_id: str, error_message: str):
|
||||
"""Report an error for a stream."""
|
||||
current_time = time.time()
|
||||
|
||||
with self._lock:
|
||||
if camera_id not in self.streams:
|
||||
logger.warning(f"Error reported for unregistered stream: {camera_id}")
|
||||
return
|
||||
|
||||
stream = self.streams[camera_id]
|
||||
stream.error_count += 1
|
||||
stream.last_error = error_message
|
||||
stream.last_error_time = current_time
|
||||
|
||||
# Report to health monitor
|
||||
health_monitor.report_error(camera_id, "stream_error")
|
||||
health_monitor.update_metrics(
|
||||
camera_id,
|
||||
error_count=stream.error_count
|
||||
)
|
||||
|
||||
logger.debug(f"Error reported for stream {camera_id}: {error_message}")
|
||||
|
||||
def report_reconnect(self, camera_id: str, reason: str = "unknown"):
|
||||
"""Report that a stream reconnected."""
|
||||
current_time = time.time()
|
||||
|
||||
with self._lock:
|
||||
if camera_id not in self.streams:
|
||||
logger.warning(f"Reconnect reported for unregistered stream: {camera_id}")
|
||||
return
|
||||
|
||||
stream = self.streams[camera_id]
|
||||
stream.reconnect_count += 1
|
||||
|
||||
# Report to health monitor
|
||||
health_monitor.report_restart(camera_id)
|
||||
health_monitor.update_metrics(
|
||||
camera_id,
|
||||
restart_count=stream.reconnect_count
|
||||
)
|
||||
|
||||
logger.info(f"Reconnect reported for stream {camera_id}: {reason}")
|
||||
|
||||
def report_connection_attempt(self, camera_id: str, success: bool):
|
||||
"""Report a connection attempt."""
|
||||
with self._lock:
|
||||
if camera_id not in self.streams:
|
||||
return
|
||||
|
||||
stream = self.streams[camera_id]
|
||||
stream.connection_attempts += 1
|
||||
stream.connection_healthy = success
|
||||
|
||||
# Report to health monitor
|
||||
health_monitor.update_metrics(
|
||||
camera_id,
|
||||
connection_healthy=success
|
||||
)
|
||||
|
||||
def test_http_connection(self, camera_id: str, url: str) -> bool:
|
||||
"""Test HTTP connection health for snapshot streams."""
|
||||
try:
|
||||
# Quick HEAD request to test connectivity
|
||||
response = requests.head(url, timeout=5, verify=False)
|
||||
success = response.status_code in [200, 404] # 404 might be normal for some cameras
|
||||
|
||||
self.report_connection_attempt(camera_id, success)
|
||||
|
||||
if success:
|
||||
logger.debug(f"Connection test passed for {camera_id}")
|
||||
else:
|
||||
logger.warning(f"Connection test failed for {camera_id}: HTTP {response.status_code}")
|
||||
|
||||
return success
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"Connection test failed for {camera_id}: {e}")
|
||||
self.report_connection_attempt(camera_id, False)
|
||||
return False
|
||||
|
||||
def get_stream_metrics(self, camera_id: str) -> Optional[Dict[str, Any]]:
|
||||
"""Get metrics for a specific stream."""
|
||||
with self._lock:
|
||||
if camera_id not in self.streams:
|
||||
return None
|
||||
|
||||
stream = self.streams[camera_id]
|
||||
current_time = time.time()
|
||||
|
||||
# Calculate derived metrics
|
||||
uptime = current_time - stream.start_time
|
||||
frame_age = current_time - stream.last_frame_time if stream.last_frame_time else None
|
||||
error_rate = stream.error_count / max(1, stream.frame_count)
|
||||
|
||||
return {
|
||||
'camera_id': camera_id,
|
||||
'stream_type': stream.stream_type,
|
||||
'uptime_seconds': uptime,
|
||||
'frame_count': stream.frame_count,
|
||||
'frames_per_second': stream.frames_per_second,
|
||||
'bytes_received': stream.bytes_received,
|
||||
'error_count': stream.error_count,
|
||||
'error_rate': error_rate,
|
||||
'reconnect_count': stream.reconnect_count,
|
||||
'connection_attempts': stream.connection_attempts,
|
||||
'connection_healthy': stream.connection_healthy,
|
||||
'last_frame_age_seconds': frame_age,
|
||||
'last_error': stream.last_error,
|
||||
'last_error_time': stream.last_error_time
|
||||
}
|
||||
|
||||
def get_all_metrics(self) -> Dict[str, Dict[str, Any]]:
|
||||
"""Get metrics for all streams."""
|
||||
with self._lock:
|
||||
return {
|
||||
camera_id: self.get_stream_metrics(camera_id)
|
||||
for camera_id in self.streams.keys()
|
||||
}
|
||||
|
||||
def _perform_health_checks(self) -> List[HealthCheck]:
|
||||
"""Perform health checks for all streams."""
|
||||
checks = []
|
||||
current_time = time.time()
|
||||
|
||||
with self._lock:
|
||||
for camera_id, stream in self.streams.items():
|
||||
checks.extend(self._check_stream_health(camera_id, stream, current_time))
|
||||
|
||||
return checks
|
||||
|
||||
def _check_stream_health(self, camera_id: str, stream: StreamMetrics, current_time: float) -> List[HealthCheck]:
|
||||
"""Perform health checks for a single stream."""
|
||||
checks = []
|
||||
|
||||
# Check frame freshness
|
||||
if stream.last_frame_time:
|
||||
frame_age = current_time - stream.last_frame_time
|
||||
|
||||
if frame_age > self.frame_timeout_critical:
|
||||
checks.append(HealthCheck(
|
||||
name=f"stream_{camera_id}_frames",
|
||||
status=HealthStatus.CRITICAL,
|
||||
message=f"No frames for {frame_age:.1f}s (critical threshold: {self.frame_timeout_critical}s)",
|
||||
details={
|
||||
'frame_age': frame_age,
|
||||
'threshold': self.frame_timeout_critical,
|
||||
'last_frame_time': stream.last_frame_time
|
||||
},
|
||||
recovery_action="restart_stream"
|
||||
))
|
||||
elif frame_age > self.frame_timeout_warning:
|
||||
checks.append(HealthCheck(
|
||||
name=f"stream_{camera_id}_frames",
|
||||
status=HealthStatus.WARNING,
|
||||
message=f"Frames aging: {frame_age:.1f}s (warning threshold: {self.frame_timeout_warning}s)",
|
||||
details={
|
||||
'frame_age': frame_age,
|
||||
'threshold': self.frame_timeout_warning,
|
||||
'last_frame_time': stream.last_frame_time
|
||||
}
|
||||
))
|
||||
else:
|
||||
# No frames received yet
|
||||
startup_time = current_time - stream.start_time
|
||||
if startup_time > 60: # Allow 1 minute for initial connection
|
||||
checks.append(HealthCheck(
|
||||
name=f"stream_{camera_id}_startup",
|
||||
status=HealthStatus.CRITICAL,
|
||||
message=f"No frames received since startup {startup_time:.1f}s ago",
|
||||
details={
|
||||
'startup_time': startup_time,
|
||||
'start_time': stream.start_time
|
||||
},
|
||||
recovery_action="restart_stream"
|
||||
))
|
||||
|
||||
# Check error rate
|
||||
if stream.frame_count > 10: # Need sufficient samples
|
||||
error_rate = stream.error_count / stream.frame_count
|
||||
if error_rate > self.error_rate_threshold:
|
||||
checks.append(HealthCheck(
|
||||
name=f"stream_{camera_id}_errors",
|
||||
status=HealthStatus.WARNING,
|
||||
message=f"High error rate: {error_rate:.1%} ({stream.error_count}/{stream.frame_count})",
|
||||
details={
|
||||
'error_rate': error_rate,
|
||||
'error_count': stream.error_count,
|
||||
'frame_count': stream.frame_count,
|
||||
'last_error': stream.last_error
|
||||
}
|
||||
))
|
||||
|
||||
# Check connection health
|
||||
if not stream.connection_healthy:
|
||||
checks.append(HealthCheck(
|
||||
name=f"stream_{camera_id}_connection",
|
||||
status=HealthStatus.WARNING,
|
||||
message="Connection unhealthy (last test failed)",
|
||||
details={
|
||||
'connection_attempts': stream.connection_attempts,
|
||||
'last_connection_test': stream.last_connection_test
|
||||
}
|
||||
))
|
||||
|
||||
# Check excessive reconnects
|
||||
uptime_hours = (current_time - stream.start_time) / 3600
|
||||
if uptime_hours > 1 and stream.reconnect_count > 5: # More than 5 reconnects per hour
|
||||
reconnect_rate = stream.reconnect_count / uptime_hours
|
||||
checks.append(HealthCheck(
|
||||
name=f"stream_{camera_id}_stability",
|
||||
status=HealthStatus.WARNING,
|
||||
message=f"Frequent reconnects: {reconnect_rate:.1f}/hour ({stream.reconnect_count} total)",
|
||||
details={
|
||||
'reconnect_rate': reconnect_rate,
|
||||
'reconnect_count': stream.reconnect_count,
|
||||
'uptime_hours': uptime_hours
|
||||
}
|
||||
))
|
||||
|
||||
# Check frame rate health
|
||||
if stream.last_frame_time and stream.frames_per_second > 0:
|
||||
expected_fps = 6.0 # Expected FPS for streams
|
||||
if stream.frames_per_second < expected_fps * 0.5: # Less than 50% of expected
|
||||
checks.append(HealthCheck(
|
||||
name=f"stream_{camera_id}_framerate",
|
||||
status=HealthStatus.WARNING,
|
||||
message=f"Low frame rate: {stream.frames_per_second:.1f} fps (expected: ~{expected_fps} fps)",
|
||||
details={
|
||||
'current_fps': stream.frames_per_second,
|
||||
'expected_fps': expected_fps
|
||||
}
|
||||
))
|
||||
|
||||
return checks
|
||||
|
||||
|
||||
# Global stream health tracker instance
|
||||
stream_health_tracker = StreamHealthTracker()
|
||||
|
|
@ -1,381 +0,0 @@
|
|||
"""
|
||||
Thread health monitoring for detecting unresponsive and deadlocked threads.
|
||||
Provides thread liveness detection and responsiveness testing.
|
||||
"""
|
||||
import time
|
||||
import threading
|
||||
import logging
|
||||
import signal
|
||||
import traceback
|
||||
from typing import Dict, List, Optional, Any, Callable
|
||||
from dataclasses import dataclass
|
||||
from collections import defaultdict
|
||||
|
||||
from .health import HealthCheck, HealthStatus, health_monitor
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@dataclass
|
||||
class ThreadInfo:
|
||||
"""Information about a monitored thread."""
|
||||
thread_id: int
|
||||
thread_name: str
|
||||
start_time: float
|
||||
last_heartbeat: float
|
||||
heartbeat_count: int = 0
|
||||
is_responsive: bool = True
|
||||
last_activity: Optional[str] = None
|
||||
stack_traces: List[str] = None
|
||||
|
||||
|
||||
class ThreadHealthMonitor:
|
||||
"""Monitors thread health and responsiveness."""
|
||||
|
||||
def __init__(self):
|
||||
self.monitored_threads: Dict[int, ThreadInfo] = {}
|
||||
self.heartbeat_callbacks: Dict[int, Callable[[], bool]] = {}
|
||||
self._lock = threading.RLock()
|
||||
|
||||
# Configuration
|
||||
self.heartbeat_timeout = 60.0 # 1 minute without heartbeat = unresponsive
|
||||
self.responsiveness_test_interval = 30.0 # Test responsiveness every 30 seconds
|
||||
self.stack_trace_count = 5 # Keep last 5 stack traces for analysis
|
||||
|
||||
# Register with health monitor
|
||||
health_monitor.register_health_checker(self._perform_health_checks)
|
||||
|
||||
# Enable periodic responsiveness testing
|
||||
self.test_thread = threading.Thread(target=self._responsiveness_test_loop, daemon=True)
|
||||
self.test_thread.start()
|
||||
|
||||
def register_thread(self, thread: threading.Thread, heartbeat_callback: Optional[Callable[[], bool]] = None):
|
||||
"""
|
||||
Register a thread for monitoring.
|
||||
|
||||
Args:
|
||||
thread: Thread to monitor
|
||||
heartbeat_callback: Optional callback to test thread responsiveness
|
||||
"""
|
||||
with self._lock:
|
||||
thread_info = ThreadInfo(
|
||||
thread_id=thread.ident,
|
||||
thread_name=thread.name,
|
||||
start_time=time.time(),
|
||||
last_heartbeat=time.time()
|
||||
)
|
||||
|
||||
self.monitored_threads[thread.ident] = thread_info
|
||||
|
||||
if heartbeat_callback:
|
||||
self.heartbeat_callbacks[thread.ident] = heartbeat_callback
|
||||
|
||||
logger.info(f"Registered thread for monitoring: {thread.name} (ID: {thread.ident})")
|
||||
|
||||
def unregister_thread(self, thread_id: int):
|
||||
"""Unregister a thread from monitoring."""
|
||||
with self._lock:
|
||||
if thread_id in self.monitored_threads:
|
||||
thread_name = self.monitored_threads[thread_id].thread_name
|
||||
del self.monitored_threads[thread_id]
|
||||
|
||||
if thread_id in self.heartbeat_callbacks:
|
||||
del self.heartbeat_callbacks[thread_id]
|
||||
|
||||
logger.info(f"Unregistered thread from monitoring: {thread_name} (ID: {thread_id})")
|
||||
|
||||
def heartbeat(self, thread_id: Optional[int] = None, activity: Optional[str] = None):
|
||||
"""
|
||||
Report thread heartbeat.
|
||||
|
||||
Args:
|
||||
thread_id: Thread ID (uses current thread if None)
|
||||
activity: Description of current activity
|
||||
"""
|
||||
if thread_id is None:
|
||||
thread_id = threading.current_thread().ident
|
||||
|
||||
current_time = time.time()
|
||||
|
||||
with self._lock:
|
||||
if thread_id in self.monitored_threads:
|
||||
thread_info = self.monitored_threads[thread_id]
|
||||
thread_info.last_heartbeat = current_time
|
||||
thread_info.heartbeat_count += 1
|
||||
thread_info.is_responsive = True
|
||||
|
||||
if activity:
|
||||
thread_info.last_activity = activity
|
||||
|
||||
# Report to health monitor
|
||||
health_monitor.update_metrics(
|
||||
f"thread_{thread_info.thread_name}",
|
||||
thread_alive=True,
|
||||
last_frame_time=current_time
|
||||
)
|
||||
|
||||
def get_thread_info(self, thread_id: int) -> Optional[Dict[str, Any]]:
|
||||
"""Get information about a monitored thread."""
|
||||
with self._lock:
|
||||
if thread_id not in self.monitored_threads:
|
||||
return None
|
||||
|
||||
thread_info = self.monitored_threads[thread_id]
|
||||
current_time = time.time()
|
||||
|
||||
return {
|
||||
'thread_id': thread_id,
|
||||
'thread_name': thread_info.thread_name,
|
||||
'uptime_seconds': current_time - thread_info.start_time,
|
||||
'last_heartbeat_age': current_time - thread_info.last_heartbeat,
|
||||
'heartbeat_count': thread_info.heartbeat_count,
|
||||
'is_responsive': thread_info.is_responsive,
|
||||
'last_activity': thread_info.last_activity,
|
||||
'stack_traces': thread_info.stack_traces or []
|
||||
}
|
||||
|
||||
def get_all_thread_info(self) -> Dict[int, Dict[str, Any]]:
|
||||
"""Get information about all monitored threads."""
|
||||
with self._lock:
|
||||
return {
|
||||
thread_id: self.get_thread_info(thread_id)
|
||||
for thread_id in self.monitored_threads.keys()
|
||||
}
|
||||
|
||||
def test_thread_responsiveness(self, thread_id: int) -> bool:
|
||||
"""
|
||||
Test if a thread is responsive by calling its heartbeat callback.
|
||||
|
||||
Args:
|
||||
thread_id: ID of thread to test
|
||||
|
||||
Returns:
|
||||
True if thread responds within timeout
|
||||
"""
|
||||
if thread_id not in self.heartbeat_callbacks:
|
||||
return True # Can't test if no callback provided
|
||||
|
||||
try:
|
||||
# Call the heartbeat callback with a timeout
|
||||
callback = self.heartbeat_callbacks[thread_id]
|
||||
|
||||
# This is a simple approach - in practice you might want to use
|
||||
# threading.Timer or asyncio for more sophisticated timeout handling
|
||||
start_time = time.time()
|
||||
result = callback()
|
||||
response_time = time.time() - start_time
|
||||
|
||||
with self._lock:
|
||||
if thread_id in self.monitored_threads:
|
||||
self.monitored_threads[thread_id].is_responsive = result
|
||||
|
||||
if response_time > 5.0: # Slow response
|
||||
logger.warning(f"Thread {thread_id} slow response: {response_time:.1f}s")
|
||||
|
||||
return result
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error testing thread {thread_id} responsiveness: {e}")
|
||||
with self._lock:
|
||||
if thread_id in self.monitored_threads:
|
||||
self.monitored_threads[thread_id].is_responsive = False
|
||||
return False
|
||||
|
||||
def capture_stack_trace(self, thread_id: int) -> Optional[str]:
|
||||
"""
|
||||
Capture stack trace for a thread.
|
||||
|
||||
Args:
|
||||
thread_id: ID of thread to capture
|
||||
|
||||
Returns:
|
||||
Stack trace string or None if not available
|
||||
"""
|
||||
try:
|
||||
# Get all frames for all threads
|
||||
frames = dict(threading._current_frames())
|
||||
|
||||
if thread_id not in frames:
|
||||
return None
|
||||
|
||||
# Format stack trace
|
||||
frame = frames[thread_id]
|
||||
stack_trace = ''.join(traceback.format_stack(frame))
|
||||
|
||||
# Store in thread info
|
||||
with self._lock:
|
||||
if thread_id in self.monitored_threads:
|
||||
thread_info = self.monitored_threads[thread_id]
|
||||
if thread_info.stack_traces is None:
|
||||
thread_info.stack_traces = []
|
||||
|
||||
thread_info.stack_traces.append(f"{time.time()}: {stack_trace}")
|
||||
|
||||
# Keep only last N stack traces
|
||||
if len(thread_info.stack_traces) > self.stack_trace_count:
|
||||
thread_info.stack_traces = thread_info.stack_traces[-self.stack_trace_count:]
|
||||
|
||||
return stack_trace
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error capturing stack trace for thread {thread_id}: {e}")
|
||||
return None
|
||||
|
||||
def detect_deadlocks(self) -> List[Dict[str, Any]]:
|
||||
"""
|
||||
Attempt to detect potential deadlocks by analyzing thread states.
|
||||
|
||||
Returns:
|
||||
List of potential deadlock scenarios
|
||||
"""
|
||||
deadlocks = []
|
||||
current_time = time.time()
|
||||
|
||||
with self._lock:
|
||||
# Look for threads that haven't had heartbeats for a long time
|
||||
# and are supposedly alive
|
||||
for thread_id, thread_info in self.monitored_threads.items():
|
||||
heartbeat_age = current_time - thread_info.last_heartbeat
|
||||
|
||||
if heartbeat_age > self.heartbeat_timeout * 2: # Double the timeout
|
||||
# Check if thread still exists
|
||||
thread_exists = any(
|
||||
t.ident == thread_id and t.is_alive()
|
||||
for t in threading.enumerate()
|
||||
)
|
||||
|
||||
if thread_exists:
|
||||
# Thread exists but not responding - potential deadlock
|
||||
stack_trace = self.capture_stack_trace(thread_id)
|
||||
|
||||
deadlock_info = {
|
||||
'thread_id': thread_id,
|
||||
'thread_name': thread_info.thread_name,
|
||||
'heartbeat_age': heartbeat_age,
|
||||
'last_activity': thread_info.last_activity,
|
||||
'stack_trace': stack_trace,
|
||||
'detection_time': current_time
|
||||
}
|
||||
|
||||
deadlocks.append(deadlock_info)
|
||||
logger.warning(f"Potential deadlock detected in thread {thread_info.thread_name}")
|
||||
|
||||
return deadlocks
|
||||
|
||||
def _responsiveness_test_loop(self):
|
||||
"""Background loop to test thread responsiveness."""
|
||||
logger.info("Thread responsiveness testing started")
|
||||
|
||||
while True:
|
||||
try:
|
||||
time.sleep(self.responsiveness_test_interval)
|
||||
|
||||
with self._lock:
|
||||
thread_ids = list(self.monitored_threads.keys())
|
||||
|
||||
for thread_id in thread_ids:
|
||||
try:
|
||||
self.test_thread_responsiveness(thread_id)
|
||||
except Exception as e:
|
||||
logger.error(f"Error testing thread {thread_id}: {e}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in responsiveness test loop: {e}")
|
||||
time.sleep(10.0) # Fallback sleep
|
||||
|
||||
def _perform_health_checks(self) -> List[HealthCheck]:
|
||||
"""Perform health checks for all monitored threads."""
|
||||
checks = []
|
||||
current_time = time.time()
|
||||
|
||||
with self._lock:
|
||||
for thread_id, thread_info in self.monitored_threads.items():
|
||||
checks.extend(self._check_thread_health(thread_id, thread_info, current_time))
|
||||
|
||||
# Check for deadlocks
|
||||
deadlocks = self.detect_deadlocks()
|
||||
for deadlock in deadlocks:
|
||||
checks.append(HealthCheck(
|
||||
name=f"deadlock_detection_{deadlock['thread_id']}",
|
||||
status=HealthStatus.CRITICAL,
|
||||
message=f"Potential deadlock in thread {deadlock['thread_name']} "
|
||||
f"(unresponsive for {deadlock['heartbeat_age']:.1f}s)",
|
||||
details=deadlock,
|
||||
recovery_action="restart_thread"
|
||||
))
|
||||
|
||||
return checks
|
||||
|
||||
def _check_thread_health(self, thread_id: int, thread_info: ThreadInfo, current_time: float) -> List[HealthCheck]:
|
||||
"""Perform health checks for a single thread."""
|
||||
checks = []
|
||||
|
||||
# Check if thread still exists
|
||||
thread_exists = any(
|
||||
t.ident == thread_id and t.is_alive()
|
||||
for t in threading.enumerate()
|
||||
)
|
||||
|
||||
if not thread_exists:
|
||||
checks.append(HealthCheck(
|
||||
name=f"thread_{thread_info.thread_name}_alive",
|
||||
status=HealthStatus.CRITICAL,
|
||||
message=f"Thread {thread_info.thread_name} is no longer alive",
|
||||
details={
|
||||
'thread_id': thread_id,
|
||||
'uptime': current_time - thread_info.start_time,
|
||||
'last_heartbeat': thread_info.last_heartbeat
|
||||
},
|
||||
recovery_action="restart_thread"
|
||||
))
|
||||
return checks
|
||||
|
||||
# Check heartbeat freshness
|
||||
heartbeat_age = current_time - thread_info.last_heartbeat
|
||||
|
||||
if heartbeat_age > self.heartbeat_timeout:
|
||||
checks.append(HealthCheck(
|
||||
name=f"thread_{thread_info.thread_name}_responsive",
|
||||
status=HealthStatus.CRITICAL,
|
||||
message=f"Thread {thread_info.thread_name} unresponsive for {heartbeat_age:.1f}s",
|
||||
details={
|
||||
'thread_id': thread_id,
|
||||
'heartbeat_age': heartbeat_age,
|
||||
'heartbeat_count': thread_info.heartbeat_count,
|
||||
'last_activity': thread_info.last_activity,
|
||||
'is_responsive': thread_info.is_responsive
|
||||
},
|
||||
recovery_action="restart_thread"
|
||||
))
|
||||
elif heartbeat_age > self.heartbeat_timeout * 0.5: # Warning at 50% of timeout
|
||||
checks.append(HealthCheck(
|
||||
name=f"thread_{thread_info.thread_name}_responsive",
|
||||
status=HealthStatus.WARNING,
|
||||
message=f"Thread {thread_info.thread_name} slow heartbeat: {heartbeat_age:.1f}s",
|
||||
details={
|
||||
'thread_id': thread_id,
|
||||
'heartbeat_age': heartbeat_age,
|
||||
'heartbeat_count': thread_info.heartbeat_count,
|
||||
'last_activity': thread_info.last_activity,
|
||||
'is_responsive': thread_info.is_responsive
|
||||
}
|
||||
))
|
||||
|
||||
# Check responsiveness test results
|
||||
if not thread_info.is_responsive:
|
||||
checks.append(HealthCheck(
|
||||
name=f"thread_{thread_info.thread_name}_callback",
|
||||
status=HealthStatus.WARNING,
|
||||
message=f"Thread {thread_info.thread_name} failed responsiveness test",
|
||||
details={
|
||||
'thread_id': thread_id,
|
||||
'last_activity': thread_info.last_activity
|
||||
}
|
||||
))
|
||||
|
||||
return checks
|
||||
|
||||
|
||||
# Global thread health monitor instance
|
||||
thread_health_monitor = ThreadHealthMonitor()
|
||||
|
|
@ -1,10 +0,0 @@
|
|||
"""
|
||||
Storage module for the Python Detector Worker.
|
||||
|
||||
This module provides Redis and PostgreSQL operations for data persistence
|
||||
and caching in the detection pipeline.
|
||||
"""
|
||||
from .redis import RedisManager
|
||||
from .database import DatabaseManager
|
||||
|
||||
__all__ = ['RedisManager', 'DatabaseManager']
|
||||
|
|
@ -1,357 +0,0 @@
|
|||
"""
|
||||
Database Operations Module.
|
||||
Handles PostgreSQL operations for the detection pipeline.
|
||||
"""
|
||||
import psycopg2
|
||||
import psycopg2.extras
|
||||
from typing import Optional, Dict, Any
|
||||
import logging
|
||||
import uuid
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class DatabaseManager:
|
||||
"""
|
||||
Manages PostgreSQL connections and operations for the detection pipeline.
|
||||
Handles database operations and schema management.
|
||||
"""
|
||||
|
||||
def __init__(self, config: Dict[str, Any]):
|
||||
"""
|
||||
Initialize database manager with configuration.
|
||||
|
||||
Args:
|
||||
config: Database configuration dictionary
|
||||
"""
|
||||
self.config = config
|
||||
self.connection: Optional[psycopg2.extensions.connection] = None
|
||||
|
||||
def connect(self) -> bool:
|
||||
"""
|
||||
Connect to PostgreSQL database.
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
try:
|
||||
self.connection = psycopg2.connect(
|
||||
host=self.config['host'],
|
||||
port=self.config['port'],
|
||||
database=self.config['database'],
|
||||
user=self.config['username'],
|
||||
password=self.config['password']
|
||||
)
|
||||
logger.info("PostgreSQL connection established successfully")
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to connect to PostgreSQL: {e}")
|
||||
return False
|
||||
|
||||
def disconnect(self):
|
||||
"""Disconnect from PostgreSQL database."""
|
||||
if self.connection:
|
||||
self.connection.close()
|
||||
self.connection = None
|
||||
logger.info("PostgreSQL connection closed")
|
||||
|
||||
def is_connected(self) -> bool:
|
||||
"""
|
||||
Check if database connection is active.
|
||||
|
||||
Returns:
|
||||
True if connected, False otherwise
|
||||
"""
|
||||
try:
|
||||
if self.connection and not self.connection.closed:
|
||||
cur = self.connection.cursor()
|
||||
cur.execute("SELECT 1")
|
||||
cur.fetchone()
|
||||
cur.close()
|
||||
return True
|
||||
except:
|
||||
pass
|
||||
return False
|
||||
|
||||
def update_car_info(self, session_id: str, brand: str, model: str, body_type: str) -> bool:
|
||||
"""
|
||||
Update car information in the database.
|
||||
|
||||
Args:
|
||||
session_id: Session identifier
|
||||
brand: Car brand
|
||||
model: Car model
|
||||
body_type: Car body type
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
if not self.is_connected():
|
||||
if not self.connect():
|
||||
return False
|
||||
|
||||
try:
|
||||
cur = self.connection.cursor()
|
||||
query = """
|
||||
INSERT INTO car_frontal_info (session_id, car_brand, car_model, car_body_type, updated_at)
|
||||
VALUES (%s, %s, %s, %s, NOW())
|
||||
ON CONFLICT (session_id)
|
||||
DO UPDATE SET
|
||||
car_brand = EXCLUDED.car_brand,
|
||||
car_model = EXCLUDED.car_model,
|
||||
car_body_type = EXCLUDED.car_body_type,
|
||||
updated_at = NOW()
|
||||
"""
|
||||
cur.execute(query, (session_id, brand, model, body_type))
|
||||
self.connection.commit()
|
||||
cur.close()
|
||||
logger.info(f"Updated car info for session {session_id}: {brand} {model} ({body_type})")
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to update car info: {e}")
|
||||
if self.connection:
|
||||
self.connection.rollback()
|
||||
return False
|
||||
|
||||
def execute_update(self, table: str, key_field: str, key_value: str, fields: Dict[str, str]) -> bool:
|
||||
"""
|
||||
Execute a dynamic update query on the database.
|
||||
|
||||
Args:
|
||||
table: Table name
|
||||
key_field: Primary key field name
|
||||
key_value: Primary key value
|
||||
fields: Dictionary of fields to update
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
if not self.is_connected():
|
||||
if not self.connect():
|
||||
return False
|
||||
|
||||
try:
|
||||
cur = self.connection.cursor()
|
||||
|
||||
# Build the UPDATE query dynamically
|
||||
set_clauses = []
|
||||
values = []
|
||||
|
||||
for field, value in fields.items():
|
||||
if value == "NOW()":
|
||||
set_clauses.append(f"{field} = NOW()")
|
||||
else:
|
||||
set_clauses.append(f"{field} = %s")
|
||||
values.append(value)
|
||||
|
||||
# Add schema prefix if table doesn't already have it
|
||||
full_table_name = table if '.' in table else f"gas_station_1.{table}"
|
||||
|
||||
query = f"""
|
||||
INSERT INTO {full_table_name} ({key_field}, {', '.join(fields.keys())})
|
||||
VALUES (%s, {', '.join(['%s'] * len(fields))})
|
||||
ON CONFLICT ({key_field})
|
||||
DO UPDATE SET {', '.join(set_clauses)}
|
||||
"""
|
||||
|
||||
# Add key_value to the beginning of values list
|
||||
all_values = [key_value] + list(fields.values()) + values
|
||||
|
||||
cur.execute(query, all_values)
|
||||
self.connection.commit()
|
||||
cur.close()
|
||||
logger.info(f"Updated {table} for {key_field}={key_value}")
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to execute update on {table}: {e}")
|
||||
if self.connection:
|
||||
self.connection.rollback()
|
||||
return False
|
||||
|
||||
def create_car_frontal_info_table(self) -> bool:
|
||||
"""
|
||||
Create the car_frontal_info table in gas_station_1 schema if it doesn't exist.
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
if not self.is_connected():
|
||||
if not self.connect():
|
||||
return False
|
||||
|
||||
try:
|
||||
# Since the database already exists, just verify connection
|
||||
cur = self.connection.cursor()
|
||||
|
||||
# Simple verification that the table exists
|
||||
cur.execute("""
|
||||
SELECT EXISTS (
|
||||
SELECT FROM information_schema.tables
|
||||
WHERE table_schema = 'gas_station_1'
|
||||
AND table_name = 'car_frontal_info'
|
||||
)
|
||||
""")
|
||||
|
||||
table_exists = cur.fetchone()[0]
|
||||
cur.close()
|
||||
|
||||
if table_exists:
|
||||
logger.info("Verified car_frontal_info table exists")
|
||||
return True
|
||||
else:
|
||||
logger.error("car_frontal_info table does not exist in the database")
|
||||
return False
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to create car_frontal_info table: {e}")
|
||||
if self.connection:
|
||||
self.connection.rollback()
|
||||
return False
|
||||
|
||||
def insert_initial_detection(self, display_id: str, captured_timestamp: str, session_id: str = None) -> str:
|
||||
"""
|
||||
Insert initial detection record and return the session_id.
|
||||
|
||||
Args:
|
||||
display_id: Display identifier
|
||||
captured_timestamp: Timestamp of the detection
|
||||
session_id: Optional session ID, generates one if not provided
|
||||
|
||||
Returns:
|
||||
Session ID string or None on error
|
||||
"""
|
||||
if not self.is_connected():
|
||||
if not self.connect():
|
||||
return None
|
||||
|
||||
# Generate session_id if not provided
|
||||
if not session_id:
|
||||
session_id = str(uuid.uuid4())
|
||||
|
||||
try:
|
||||
# Ensure table exists
|
||||
if not self.create_car_frontal_info_table():
|
||||
logger.error("Failed to create/verify table before insertion")
|
||||
return None
|
||||
|
||||
cur = self.connection.cursor()
|
||||
insert_query = """
|
||||
INSERT INTO gas_station_1.car_frontal_info
|
||||
(display_id, captured_timestamp, session_id, license_character, license_type, car_brand, car_model, car_body_type)
|
||||
VALUES (%s, %s, %s, NULL, 'No model available', NULL, NULL, NULL)
|
||||
ON CONFLICT (session_id) DO NOTHING
|
||||
"""
|
||||
|
||||
cur.execute(insert_query, (display_id, captured_timestamp, session_id))
|
||||
self.connection.commit()
|
||||
cur.close()
|
||||
logger.info(f"Inserted initial detection record with session_id: {session_id}")
|
||||
return session_id
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to insert initial detection record: {e}")
|
||||
if self.connection:
|
||||
self.connection.rollback()
|
||||
return None
|
||||
|
||||
def get_session_info(self, session_id: str) -> Optional[Dict[str, Any]]:
|
||||
"""
|
||||
Get session information from the database.
|
||||
|
||||
Args:
|
||||
session_id: Session identifier
|
||||
|
||||
Returns:
|
||||
Dictionary with session data or None if not found
|
||||
"""
|
||||
if not self.is_connected():
|
||||
if not self.connect():
|
||||
return None
|
||||
|
||||
try:
|
||||
cur = self.connection.cursor(cursor_factory=psycopg2.extras.RealDictCursor)
|
||||
query = "SELECT * FROM gas_station_1.car_frontal_info WHERE session_id = %s"
|
||||
cur.execute(query, (session_id,))
|
||||
result = cur.fetchone()
|
||||
cur.close()
|
||||
|
||||
if result:
|
||||
return dict(result)
|
||||
else:
|
||||
logger.debug(f"No session info found for session_id: {session_id}")
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to get session info: {e}")
|
||||
return None
|
||||
|
||||
def delete_session(self, session_id: str) -> bool:
|
||||
"""
|
||||
Delete session record from the database.
|
||||
|
||||
Args:
|
||||
session_id: Session identifier
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
if not self.is_connected():
|
||||
if not self.connect():
|
||||
return False
|
||||
|
||||
try:
|
||||
cur = self.connection.cursor()
|
||||
query = "DELETE FROM gas_station_1.car_frontal_info WHERE session_id = %s"
|
||||
cur.execute(query, (session_id,))
|
||||
rows_affected = cur.rowcount
|
||||
self.connection.commit()
|
||||
cur.close()
|
||||
|
||||
if rows_affected > 0:
|
||||
logger.info(f"Deleted session record: {session_id}")
|
||||
return True
|
||||
else:
|
||||
logger.warning(f"No session record found to delete: {session_id}")
|
||||
return False
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to delete session: {e}")
|
||||
if self.connection:
|
||||
self.connection.rollback()
|
||||
return False
|
||||
|
||||
def get_statistics(self) -> Dict[str, Any]:
|
||||
"""
|
||||
Get database statistics.
|
||||
|
||||
Returns:
|
||||
Dictionary with database statistics
|
||||
"""
|
||||
stats = {
|
||||
'connected': self.is_connected(),
|
||||
'host': self.config.get('host', 'unknown'),
|
||||
'port': self.config.get('port', 'unknown'),
|
||||
'database': self.config.get('database', 'unknown')
|
||||
}
|
||||
|
||||
if self.is_connected():
|
||||
try:
|
||||
cur = self.connection.cursor()
|
||||
|
||||
# Get table record count
|
||||
cur.execute("SELECT COUNT(*) FROM gas_station_1.car_frontal_info")
|
||||
stats['total_records'] = cur.fetchone()[0]
|
||||
|
||||
# Get recent records count (last hour)
|
||||
cur.execute("""
|
||||
SELECT COUNT(*) FROM gas_station_1.car_frontal_info
|
||||
WHERE created_at > NOW() - INTERVAL '1 hour'
|
||||
""")
|
||||
stats['recent_records'] = cur.fetchone()[0]
|
||||
|
||||
cur.close()
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to get database statistics: {e}")
|
||||
stats['error'] = str(e)
|
||||
|
||||
return stats
|
||||
|
|
@ -1,300 +0,0 @@
|
|||
"""
|
||||
License Plate Manager Module.
|
||||
Handles Redis subscription to license plate results from LPR service.
|
||||
"""
|
||||
import logging
|
||||
import json
|
||||
import asyncio
|
||||
from typing import Dict, Optional, Any, Callable
|
||||
import redis.asyncio as redis
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class LicensePlateManager:
|
||||
"""
|
||||
Manages license plate result subscription from Redis channel.
|
||||
Subscribes to 'license_results' channel for license plate data from LPR service.
|
||||
"""
|
||||
|
||||
def __init__(self, redis_config: Dict[str, Any]):
|
||||
"""
|
||||
Initialize license plate manager with Redis configuration.
|
||||
|
||||
Args:
|
||||
redis_config: Redis configuration dictionary
|
||||
"""
|
||||
self.config = redis_config
|
||||
self.redis_client: Optional[redis.Redis] = None
|
||||
self.pubsub = None
|
||||
self.subscription_task = None
|
||||
self.callback = None
|
||||
|
||||
# Connection parameters
|
||||
self.host = redis_config.get('host', 'localhost')
|
||||
self.port = redis_config.get('port', 6379)
|
||||
self.password = redis_config.get('password')
|
||||
self.db = redis_config.get('db', 0)
|
||||
|
||||
# License plate data cache - store recent results by session_id
|
||||
self.license_plate_cache: Dict[str, Dict[str, Any]] = {}
|
||||
self.cache_ttl = 300 # 5 minutes TTL for cached results
|
||||
|
||||
logger.info(f"LicensePlateManager initialized for {self.host}:{self.port}")
|
||||
|
||||
async def initialize(self, callback: Optional[Callable] = None) -> bool:
|
||||
"""
|
||||
Initialize Redis connection and start subscription to license_results channel.
|
||||
|
||||
Args:
|
||||
callback: Optional callback function for processing license plate results
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
try:
|
||||
# Create Redis connection
|
||||
self.redis_client = redis.Redis(
|
||||
host=self.host,
|
||||
port=self.port,
|
||||
password=self.password,
|
||||
db=self.db,
|
||||
decode_responses=True
|
||||
)
|
||||
|
||||
# Test connection
|
||||
await self.redis_client.ping()
|
||||
logger.info(f"Connected to Redis for license plate subscription")
|
||||
|
||||
# Set callback
|
||||
self.callback = callback
|
||||
|
||||
# Start subscription
|
||||
await self._start_subscription()
|
||||
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to initialize license plate manager: {e}", exc_info=True)
|
||||
return False
|
||||
|
||||
async def _start_subscription(self):
|
||||
"""Start Redis subscription to license_results channel."""
|
||||
try:
|
||||
if not self.redis_client:
|
||||
logger.error("Redis client not initialized")
|
||||
return
|
||||
|
||||
# Create pubsub and subscribe
|
||||
self.pubsub = self.redis_client.pubsub()
|
||||
await self.pubsub.subscribe('license_results')
|
||||
|
||||
logger.info("Subscribed to Redis channel: license_results")
|
||||
|
||||
# Start listening task
|
||||
self.subscription_task = asyncio.create_task(self._listen_for_messages())
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error starting license plate subscription: {e}", exc_info=True)
|
||||
|
||||
async def _listen_for_messages(self):
|
||||
"""Listen for messages on the license_results channel."""
|
||||
listen_generator = None
|
||||
try:
|
||||
if not self.pubsub:
|
||||
return
|
||||
|
||||
listen_generator = self.pubsub.listen()
|
||||
async for message in listen_generator:
|
||||
if message['type'] == 'message':
|
||||
try:
|
||||
# Log the raw message from Redis channel
|
||||
logger.info(f"[LICENSE PLATE RAW] Received from 'license_results' channel: {message['data']}")
|
||||
|
||||
# Parse the license plate result message
|
||||
data = json.loads(message['data'])
|
||||
logger.info(f"[LICENSE PLATE PARSED] Parsed JSON data: {data}")
|
||||
await self._process_license_plate_result(data)
|
||||
except json.JSONDecodeError as e:
|
||||
logger.error(f"[LICENSE PLATE ERROR] Invalid JSON in license plate message: {e}")
|
||||
logger.error(f"[LICENSE PLATE ERROR] Raw message was: {message['data']}")
|
||||
except Exception as e:
|
||||
logger.error(f"Error processing license plate message: {e}", exc_info=True)
|
||||
|
||||
except asyncio.CancelledError:
|
||||
logger.info("License plate subscription task cancelled")
|
||||
# Don't try to close generator here - let it be handled by the context
|
||||
# The async generator will be properly closed by the cancellation mechanism
|
||||
raise # Re-raise to maintain proper cancellation semantics
|
||||
except Exception as e:
|
||||
logger.error(f"Error in license plate message listener: {e}", exc_info=True)
|
||||
# Only attempt cleanup if it's not a cancellation
|
||||
finally:
|
||||
# Safe cleanup of async generator
|
||||
if listen_generator is not None:
|
||||
try:
|
||||
# Check if we can safely close without conflicting with ongoing operations
|
||||
if hasattr(listen_generator, 'aclose') and not asyncio.current_task().cancelled():
|
||||
await listen_generator.aclose()
|
||||
except (RuntimeError, AttributeError) as e:
|
||||
# Generator is already closing or in invalid state - safe to ignore
|
||||
logger.debug(f"Generator cleanup skipped (safe): {e}")
|
||||
except Exception as e:
|
||||
logger.debug(f"Generator cleanup error (non-critical): {e}")
|
||||
|
||||
async def _process_license_plate_result(self, data: Dict[str, Any]):
|
||||
"""
|
||||
Process incoming license plate result from LPR service.
|
||||
|
||||
Expected message format (from actual LPR service):
|
||||
{
|
||||
"session_id": "511",
|
||||
"license_character": "ข3184"
|
||||
}
|
||||
or
|
||||
{
|
||||
"session_id": "508",
|
||||
"display_id": "test3",
|
||||
"license_plate_text": "ABC-123",
|
||||
"confidence": 0.95,
|
||||
"timestamp": "2025-09-24T21:10:00Z"
|
||||
}
|
||||
|
||||
Args:
|
||||
data: License plate result data
|
||||
"""
|
||||
try:
|
||||
session_id = data.get('session_id')
|
||||
if not session_id:
|
||||
logger.warning("License plate result missing session_id")
|
||||
return
|
||||
|
||||
# Handle different message formats
|
||||
# Format 1: {"session_id": "511", "license_character": "ข3184"}
|
||||
# Format 2: {"session_id": "508", "license_plate_text": "ABC-123", "confidence": 0.95, ...}
|
||||
license_plate_text = data.get('license_plate_text') or data.get('license_character')
|
||||
confidence = data.get('confidence', 1.0) # Default confidence for LPR service results
|
||||
display_id = data.get('display_id', '')
|
||||
timestamp = data.get('timestamp', '')
|
||||
|
||||
logger.info(f"[LICENSE PLATE] Received result for session {session_id}: "
|
||||
f"text='{license_plate_text}', confidence={confidence:.3f}")
|
||||
|
||||
# Store in cache
|
||||
self.license_plate_cache[session_id] = {
|
||||
'license_plate_text': license_plate_text,
|
||||
'confidence': confidence,
|
||||
'display_id': display_id,
|
||||
'timestamp': timestamp,
|
||||
'received_at': asyncio.get_event_loop().time()
|
||||
}
|
||||
|
||||
# Call callback if provided
|
||||
if self.callback:
|
||||
await self.callback(session_id, {
|
||||
'license_plate_text': license_plate_text,
|
||||
'confidence': confidence,
|
||||
'display_id': display_id,
|
||||
'timestamp': timestamp
|
||||
})
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error processing license plate result: {e}", exc_info=True)
|
||||
|
||||
def get_license_plate_result(self, session_id: str) -> Optional[Dict[str, Any]]:
|
||||
"""
|
||||
Get cached license plate result for a session.
|
||||
|
||||
Args:
|
||||
session_id: Session identifier
|
||||
|
||||
Returns:
|
||||
License plate result dictionary or None if not found
|
||||
"""
|
||||
if session_id not in self.license_plate_cache:
|
||||
return None
|
||||
|
||||
result = self.license_plate_cache[session_id]
|
||||
|
||||
# Check TTL
|
||||
current_time = asyncio.get_event_loop().time()
|
||||
if current_time - result.get('received_at', 0) > self.cache_ttl:
|
||||
# Expired, remove from cache
|
||||
del self.license_plate_cache[session_id]
|
||||
return None
|
||||
|
||||
return {
|
||||
'license_plate_text': result.get('license_plate_text'),
|
||||
'confidence': result.get('confidence'),
|
||||
'display_id': result.get('display_id'),
|
||||
'timestamp': result.get('timestamp')
|
||||
}
|
||||
|
||||
def cleanup_expired_results(self):
|
||||
"""Remove expired license plate results from cache."""
|
||||
try:
|
||||
current_time = asyncio.get_event_loop().time()
|
||||
expired_sessions = []
|
||||
|
||||
for session_id, result in self.license_plate_cache.items():
|
||||
if current_time - result.get('received_at', 0) > self.cache_ttl:
|
||||
expired_sessions.append(session_id)
|
||||
|
||||
for session_id in expired_sessions:
|
||||
del self.license_plate_cache[session_id]
|
||||
logger.debug(f"Removed expired license plate result for session {session_id}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error cleaning up expired license plate results: {e}", exc_info=True)
|
||||
|
||||
async def close(self):
|
||||
"""Close Redis connection and cleanup resources."""
|
||||
try:
|
||||
# Cancel subscription task first
|
||||
if self.subscription_task and not self.subscription_task.done():
|
||||
self.subscription_task.cancel()
|
||||
try:
|
||||
await self.subscription_task
|
||||
except asyncio.CancelledError:
|
||||
logger.debug("License plate subscription task cancelled successfully")
|
||||
except Exception as e:
|
||||
logger.warning(f"Error waiting for subscription task cancellation: {e}")
|
||||
|
||||
# Close pubsub connection properly
|
||||
if self.pubsub:
|
||||
try:
|
||||
# First unsubscribe from channels
|
||||
await self.pubsub.unsubscribe('license_results')
|
||||
# Then close the pubsub connection
|
||||
await self.pubsub.aclose()
|
||||
except Exception as e:
|
||||
logger.warning(f"Error closing pubsub connection: {e}")
|
||||
finally:
|
||||
self.pubsub = None
|
||||
|
||||
# Close Redis connection
|
||||
if self.redis_client:
|
||||
try:
|
||||
await self.redis_client.aclose()
|
||||
except Exception as e:
|
||||
logger.warning(f"Error closing Redis connection: {e}")
|
||||
finally:
|
||||
self.redis_client = None
|
||||
|
||||
# Clear cache
|
||||
self.license_plate_cache.clear()
|
||||
|
||||
logger.info("License plate manager closed successfully")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error closing license plate manager: {e}", exc_info=True)
|
||||
|
||||
def get_statistics(self) -> Dict[str, Any]:
|
||||
"""Get license plate manager statistics."""
|
||||
return {
|
||||
'cached_results': len(self.license_plate_cache),
|
||||
'connected': self.redis_client is not None,
|
||||
'subscribed': self.pubsub is not None,
|
||||
'host': self.host,
|
||||
'port': self.port
|
||||
}
|
||||
|
|
@ -1,478 +0,0 @@
|
|||
"""
|
||||
Redis Operations Module.
|
||||
Handles Redis connections, image storage, and pub/sub messaging.
|
||||
"""
|
||||
import logging
|
||||
import json
|
||||
import time
|
||||
from typing import Optional, Dict, Any, Union
|
||||
import asyncio
|
||||
import cv2
|
||||
import numpy as np
|
||||
import redis.asyncio as redis
|
||||
from redis.exceptions import ConnectionError, TimeoutError
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class RedisManager:
|
||||
"""
|
||||
Manages Redis connections and operations for the detection pipeline.
|
||||
Handles image storage with region cropping and pub/sub messaging.
|
||||
"""
|
||||
|
||||
def __init__(self, redis_config: Dict[str, Any]):
|
||||
"""
|
||||
Initialize Redis manager with configuration.
|
||||
|
||||
Args:
|
||||
redis_config: Redis configuration dictionary
|
||||
"""
|
||||
self.config = redis_config
|
||||
self.redis_client: Optional[redis.Redis] = None
|
||||
|
||||
# Connection parameters
|
||||
self.host = redis_config.get('host', 'localhost')
|
||||
self.port = redis_config.get('port', 6379)
|
||||
self.password = redis_config.get('password')
|
||||
self.db = redis_config.get('db', 0)
|
||||
self.decode_responses = redis_config.get('decode_responses', True)
|
||||
|
||||
# Connection pool settings
|
||||
self.max_connections = redis_config.get('max_connections', 10)
|
||||
self.socket_timeout = redis_config.get('socket_timeout', 5)
|
||||
self.socket_connect_timeout = redis_config.get('socket_connect_timeout', 5)
|
||||
self.health_check_interval = redis_config.get('health_check_interval', 30)
|
||||
|
||||
# Statistics
|
||||
self.stats = {
|
||||
'images_stored': 0,
|
||||
'messages_published': 0,
|
||||
'connection_errors': 0,
|
||||
'operations_successful': 0,
|
||||
'operations_failed': 0
|
||||
}
|
||||
|
||||
logger.info(f"RedisManager initialized for {self.host}:{self.port}")
|
||||
|
||||
async def initialize(self) -> bool:
|
||||
"""
|
||||
Initialize Redis connection and test connectivity.
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
try:
|
||||
# Validate configuration
|
||||
if not self._validate_config():
|
||||
return False
|
||||
|
||||
# Create Redis connection
|
||||
self.redis_client = redis.Redis(
|
||||
host=self.host,
|
||||
port=self.port,
|
||||
password=self.password,
|
||||
db=self.db,
|
||||
decode_responses=self.decode_responses,
|
||||
max_connections=self.max_connections,
|
||||
socket_timeout=self.socket_timeout,
|
||||
socket_connect_timeout=self.socket_connect_timeout,
|
||||
health_check_interval=self.health_check_interval
|
||||
)
|
||||
|
||||
# Test connection
|
||||
await self.redis_client.ping()
|
||||
logger.info(f"Successfully connected to Redis at {self.host}:{self.port}")
|
||||
return True
|
||||
|
||||
except ConnectionError as e:
|
||||
logger.error(f"Failed to connect to Redis: {e}")
|
||||
self.stats['connection_errors'] += 1
|
||||
return False
|
||||
except Exception as e:
|
||||
logger.error(f"Error initializing Redis connection: {e}", exc_info=True)
|
||||
self.stats['connection_errors'] += 1
|
||||
return False
|
||||
|
||||
def _validate_config(self) -> bool:
|
||||
"""
|
||||
Validate Redis configuration parameters.
|
||||
|
||||
Returns:
|
||||
True if valid, False otherwise
|
||||
"""
|
||||
required_fields = ['host', 'port']
|
||||
for field in required_fields:
|
||||
if field not in self.config:
|
||||
logger.error(f"Missing required Redis config field: {field}")
|
||||
return False
|
||||
|
||||
if not isinstance(self.port, int) or self.port <= 0:
|
||||
logger.error(f"Invalid Redis port: {self.port}")
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
async def is_connected(self) -> bool:
|
||||
"""
|
||||
Check if Redis connection is active.
|
||||
|
||||
Returns:
|
||||
True if connected, False otherwise
|
||||
"""
|
||||
try:
|
||||
if self.redis_client:
|
||||
await self.redis_client.ping()
|
||||
return True
|
||||
except Exception:
|
||||
pass
|
||||
return False
|
||||
|
||||
async def save_image(self,
|
||||
key: str,
|
||||
image: np.ndarray,
|
||||
expire_seconds: Optional[int] = None,
|
||||
image_format: str = 'jpeg',
|
||||
quality: int = 90) -> bool:
|
||||
"""
|
||||
Save image to Redis with optional expiration.
|
||||
|
||||
Args:
|
||||
key: Redis key for the image
|
||||
image: Image array to save
|
||||
expire_seconds: Optional expiration time in seconds
|
||||
image_format: Image format ('jpeg' or 'png')
|
||||
quality: JPEG quality (1-100)
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
try:
|
||||
if not self.redis_client:
|
||||
logger.error("Redis client not initialized")
|
||||
self.stats['operations_failed'] += 1
|
||||
return False
|
||||
|
||||
# Encode image
|
||||
encoded_image = self._encode_image(image, image_format, quality)
|
||||
if encoded_image is None:
|
||||
logger.error("Failed to encode image")
|
||||
self.stats['operations_failed'] += 1
|
||||
return False
|
||||
|
||||
# Save to Redis
|
||||
if expire_seconds:
|
||||
await self.redis_client.setex(key, expire_seconds, encoded_image)
|
||||
logger.debug(f"Saved image to Redis with key: {key} (expires in {expire_seconds}s)")
|
||||
else:
|
||||
await self.redis_client.set(key, encoded_image)
|
||||
logger.debug(f"Saved image to Redis with key: {key}")
|
||||
|
||||
self.stats['images_stored'] += 1
|
||||
self.stats['operations_successful'] += 1
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error saving image to Redis: {e}", exc_info=True)
|
||||
self.stats['operations_failed'] += 1
|
||||
return False
|
||||
|
||||
async def get_image(self, key: str) -> Optional[np.ndarray]:
|
||||
"""
|
||||
Retrieve image from Redis.
|
||||
|
||||
Args:
|
||||
key: Redis key for the image
|
||||
|
||||
Returns:
|
||||
Image array or None if not found
|
||||
"""
|
||||
try:
|
||||
if not self.redis_client:
|
||||
logger.error("Redis client not initialized")
|
||||
self.stats['operations_failed'] += 1
|
||||
return None
|
||||
|
||||
# Get image data from Redis
|
||||
image_data = await self.redis_client.get(key)
|
||||
if image_data is None:
|
||||
logger.debug(f"Image not found for key: {key}")
|
||||
return None
|
||||
|
||||
# Decode image
|
||||
image_array = np.frombuffer(image_data, np.uint8)
|
||||
image = cv2.imdecode(image_array, cv2.IMREAD_COLOR)
|
||||
|
||||
if image is not None:
|
||||
logger.debug(f"Retrieved image from Redis with key: {key}")
|
||||
self.stats['operations_successful'] += 1
|
||||
return image
|
||||
else:
|
||||
logger.error(f"Failed to decode image for key: {key}")
|
||||
self.stats['operations_failed'] += 1
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error retrieving image from Redis: {e}", exc_info=True)
|
||||
self.stats['operations_failed'] += 1
|
||||
return None
|
||||
|
||||
async def delete_image(self, key: str) -> bool:
|
||||
"""
|
||||
Delete image from Redis.
|
||||
|
||||
Args:
|
||||
key: Redis key for the image
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
try:
|
||||
if not self.redis_client:
|
||||
logger.error("Redis client not initialized")
|
||||
self.stats['operations_failed'] += 1
|
||||
return False
|
||||
|
||||
result = await self.redis_client.delete(key)
|
||||
if result > 0:
|
||||
logger.debug(f"Deleted image from Redis with key: {key}")
|
||||
self.stats['operations_successful'] += 1
|
||||
return True
|
||||
else:
|
||||
logger.debug(f"Image not found for deletion: {key}")
|
||||
return False
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error deleting image from Redis: {e}", exc_info=True)
|
||||
self.stats['operations_failed'] += 1
|
||||
return False
|
||||
|
||||
async def publish_message(self, channel: str, message: Union[str, Dict]) -> int:
|
||||
"""
|
||||
Publish message to Redis channel.
|
||||
|
||||
Args:
|
||||
channel: Redis channel name
|
||||
message: Message to publish (string or dict)
|
||||
|
||||
Returns:
|
||||
Number of subscribers that received the message, -1 on error
|
||||
"""
|
||||
try:
|
||||
if not self.redis_client:
|
||||
logger.error("Redis client not initialized")
|
||||
self.stats['operations_failed'] += 1
|
||||
return -1
|
||||
|
||||
# Convert dict to JSON string if needed
|
||||
if isinstance(message, dict):
|
||||
message_str = json.dumps(message)
|
||||
else:
|
||||
message_str = str(message)
|
||||
|
||||
# Test connection before publishing
|
||||
await self.redis_client.ping()
|
||||
|
||||
# Publish message
|
||||
result = await self.redis_client.publish(channel, message_str)
|
||||
|
||||
logger.info(f"Published message to Redis channel '{channel}': {message_str}")
|
||||
logger.info(f"Redis publish result (subscribers count): {result}")
|
||||
|
||||
if result == 0:
|
||||
logger.warning(f"No subscribers listening to channel '{channel}'")
|
||||
else:
|
||||
logger.info(f"Message delivered to {result} subscriber(s)")
|
||||
|
||||
self.stats['messages_published'] += 1
|
||||
self.stats['operations_successful'] += 1
|
||||
return result
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error publishing message to Redis: {e}", exc_info=True)
|
||||
self.stats['operations_failed'] += 1
|
||||
return -1
|
||||
|
||||
async def subscribe_to_channel(self, channel: str, callback=None):
|
||||
"""
|
||||
Subscribe to Redis channel (for future use).
|
||||
|
||||
Args:
|
||||
channel: Redis channel name
|
||||
callback: Optional callback function for messages
|
||||
"""
|
||||
try:
|
||||
if not self.redis_client:
|
||||
logger.error("Redis client not initialized")
|
||||
return
|
||||
|
||||
pubsub = self.redis_client.pubsub()
|
||||
await pubsub.subscribe(channel)
|
||||
|
||||
logger.info(f"Subscribed to Redis channel: {channel}")
|
||||
|
||||
if callback:
|
||||
async for message in pubsub.listen():
|
||||
if message['type'] == 'message':
|
||||
try:
|
||||
await callback(message['data'])
|
||||
except Exception as e:
|
||||
logger.error(f"Error in message callback: {e}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error subscribing to Redis channel: {e}", exc_info=True)
|
||||
|
||||
async def set_key(self, key: str, value: Union[str, bytes], expire_seconds: Optional[int] = None) -> bool:
|
||||
"""
|
||||
Set a key-value pair in Redis.
|
||||
|
||||
Args:
|
||||
key: Redis key
|
||||
value: Value to store
|
||||
expire_seconds: Optional expiration time in seconds
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
try:
|
||||
if not self.redis_client:
|
||||
logger.error("Redis client not initialized")
|
||||
self.stats['operations_failed'] += 1
|
||||
return False
|
||||
|
||||
if expire_seconds:
|
||||
await self.redis_client.setex(key, expire_seconds, value)
|
||||
else:
|
||||
await self.redis_client.set(key, value)
|
||||
|
||||
logger.debug(f"Set Redis key: {key}")
|
||||
self.stats['operations_successful'] += 1
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error setting Redis key: {e}", exc_info=True)
|
||||
self.stats['operations_failed'] += 1
|
||||
return False
|
||||
|
||||
async def get_key(self, key: str) -> Optional[Union[str, bytes]]:
|
||||
"""
|
||||
Get value for a Redis key.
|
||||
|
||||
Args:
|
||||
key: Redis key
|
||||
|
||||
Returns:
|
||||
Value or None if not found
|
||||
"""
|
||||
try:
|
||||
if not self.redis_client:
|
||||
logger.error("Redis client not initialized")
|
||||
self.stats['operations_failed'] += 1
|
||||
return None
|
||||
|
||||
value = await self.redis_client.get(key)
|
||||
if value is not None:
|
||||
logger.debug(f"Retrieved Redis key: {key}")
|
||||
self.stats['operations_successful'] += 1
|
||||
|
||||
return value
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error getting Redis key: {e}", exc_info=True)
|
||||
self.stats['operations_failed'] += 1
|
||||
return None
|
||||
|
||||
async def delete_key(self, key: str) -> bool:
|
||||
"""
|
||||
Delete a Redis key.
|
||||
|
||||
Args:
|
||||
key: Redis key
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
try:
|
||||
if not self.redis_client:
|
||||
logger.error("Redis client not initialized")
|
||||
self.stats['operations_failed'] += 1
|
||||
return False
|
||||
|
||||
result = await self.redis_client.delete(key)
|
||||
if result > 0:
|
||||
logger.debug(f"Deleted Redis key: {key}")
|
||||
self.stats['operations_successful'] += 1
|
||||
return True
|
||||
else:
|
||||
logger.debug(f"Redis key not found: {key}")
|
||||
return False
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error deleting Redis key: {e}", exc_info=True)
|
||||
self.stats['operations_failed'] += 1
|
||||
return False
|
||||
|
||||
def _encode_image(self, image: np.ndarray, image_format: str, quality: int) -> Optional[bytes]:
|
||||
"""
|
||||
Encode image to bytes for Redis storage.
|
||||
|
||||
Args:
|
||||
image: Image array
|
||||
image_format: Image format ('jpeg' or 'png')
|
||||
quality: JPEG quality (1-100)
|
||||
|
||||
Returns:
|
||||
Encoded image bytes or None on error
|
||||
"""
|
||||
try:
|
||||
format_lower = image_format.lower()
|
||||
|
||||
if format_lower == 'jpeg' or format_lower == 'jpg':
|
||||
encode_params = [cv2.IMWRITE_JPEG_QUALITY, quality]
|
||||
success, buffer = cv2.imencode('.jpg', image, encode_params)
|
||||
elif format_lower == 'png':
|
||||
success, buffer = cv2.imencode('.png', image)
|
||||
else:
|
||||
logger.warning(f"Unknown image format '{image_format}', using JPEG")
|
||||
encode_params = [cv2.IMWRITE_JPEG_QUALITY, quality]
|
||||
success, buffer = cv2.imencode('.jpg', image, encode_params)
|
||||
|
||||
if success:
|
||||
return buffer.tobytes()
|
||||
else:
|
||||
logger.error(f"Failed to encode image as {image_format}")
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error encoding image: {e}", exc_info=True)
|
||||
return None
|
||||
|
||||
def get_statistics(self) -> Dict[str, Any]:
|
||||
"""
|
||||
Get Redis manager statistics.
|
||||
|
||||
Returns:
|
||||
Dictionary with statistics
|
||||
"""
|
||||
return {
|
||||
**self.stats,
|
||||
'connected': self.redis_client is not None,
|
||||
'host': self.host,
|
||||
'port': self.port,
|
||||
'db': self.db
|
||||
}
|
||||
|
||||
def cleanup(self):
|
||||
"""Cleanup Redis connection."""
|
||||
if self.redis_client:
|
||||
# Note: redis.asyncio doesn't have a synchronous close method
|
||||
# The connection will be closed when the event loop shuts down
|
||||
self.redis_client = None
|
||||
logger.info("Redis connection cleaned up")
|
||||
|
||||
async def aclose(self):
|
||||
"""Async cleanup for Redis connection."""
|
||||
if self.redis_client:
|
||||
await self.redis_client.aclose()
|
||||
self.redis_client = None
|
||||
logger.info("Redis connection closed")
|
||||
|
|
@ -1,26 +0,0 @@
|
|||
"""
|
||||
Streaming system for RTSP and HTTP camera feeds.
|
||||
Provides modular frame readers, buffers, and stream management.
|
||||
"""
|
||||
from .readers import HTTPSnapshotReader, FFmpegRTSPReader
|
||||
from .buffers import FrameBuffer, CacheBuffer, shared_frame_buffer, shared_cache_buffer
|
||||
from .manager import StreamManager, StreamConfig, SubscriptionInfo, shared_stream_manager, initialize_stream_manager
|
||||
|
||||
__all__ = [
|
||||
# Readers
|
||||
'HTTPSnapshotReader',
|
||||
'FFmpegRTSPReader',
|
||||
|
||||
# Buffers
|
||||
'FrameBuffer',
|
||||
'CacheBuffer',
|
||||
'shared_frame_buffer',
|
||||
'shared_cache_buffer',
|
||||
|
||||
# Manager
|
||||
'StreamManager',
|
||||
'StreamConfig',
|
||||
'SubscriptionInfo',
|
||||
'shared_stream_manager',
|
||||
'initialize_stream_manager'
|
||||
]
|
||||
|
|
@ -1,295 +0,0 @@
|
|||
"""
|
||||
Frame buffering and caching system optimized for different stream formats.
|
||||
Supports 1280x720 RTSP streams and 2560x1440 HTTP snapshots.
|
||||
"""
|
||||
import threading
|
||||
import time
|
||||
import cv2
|
||||
import logging
|
||||
import numpy as np
|
||||
from typing import Optional, Dict, Any, Tuple
|
||||
from collections import defaultdict
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class FrameBuffer:
|
||||
"""Thread-safe frame buffer for all camera streams."""
|
||||
|
||||
def __init__(self, max_age_seconds: int = 5):
|
||||
self.max_age_seconds = max_age_seconds
|
||||
self._frames: Dict[str, Dict[str, Any]] = {}
|
||||
self._lock = threading.RLock()
|
||||
|
||||
def put_frame(self, camera_id: str, frame: np.ndarray):
|
||||
"""Store a frame for the given camera ID."""
|
||||
with self._lock:
|
||||
# Validate frame
|
||||
if not self._validate_frame(frame):
|
||||
logger.warning(f"Frame validation failed for camera {camera_id}")
|
||||
return
|
||||
|
||||
self._frames[camera_id] = {
|
||||
'frame': frame.copy(),
|
||||
'timestamp': time.time(),
|
||||
'shape': frame.shape,
|
||||
'dtype': str(frame.dtype),
|
||||
'size_mb': frame.nbytes / (1024 * 1024)
|
||||
}
|
||||
|
||||
def get_frame(self, camera_id: str) -> Optional[np.ndarray]:
|
||||
"""Get the latest frame for the given camera ID."""
|
||||
with self._lock:
|
||||
if camera_id not in self._frames:
|
||||
return None
|
||||
|
||||
frame_data = self._frames[camera_id]
|
||||
|
||||
# Return frame regardless of age - frames persist until replaced
|
||||
return frame_data['frame'].copy()
|
||||
|
||||
def get_frame_info(self, camera_id: str) -> Optional[Dict[str, Any]]:
|
||||
"""Get frame metadata without copying the frame data."""
|
||||
with self._lock:
|
||||
if camera_id not in self._frames:
|
||||
return None
|
||||
|
||||
frame_data = self._frames[camera_id]
|
||||
age = time.time() - frame_data['timestamp']
|
||||
|
||||
# Return frame info regardless of age - frames persist until replaced
|
||||
return {
|
||||
'timestamp': frame_data['timestamp'],
|
||||
'age': age,
|
||||
'shape': frame_data['shape'],
|
||||
'dtype': frame_data['dtype'],
|
||||
'size_mb': frame_data.get('size_mb', 0)
|
||||
}
|
||||
|
||||
def has_frame(self, camera_id: str) -> bool:
|
||||
"""Check if a valid frame exists for the camera."""
|
||||
return self.get_frame_info(camera_id) is not None
|
||||
|
||||
def clear_camera(self, camera_id: str):
|
||||
"""Remove all frames for a specific camera."""
|
||||
with self._lock:
|
||||
if camera_id in self._frames:
|
||||
del self._frames[camera_id]
|
||||
logger.debug(f"Cleared frames for camera {camera_id}")
|
||||
|
||||
def clear_all(self):
|
||||
"""Clear all stored frames."""
|
||||
with self._lock:
|
||||
count = len(self._frames)
|
||||
self._frames.clear()
|
||||
logger.debug(f"Cleared all frames ({count} cameras)")
|
||||
|
||||
def get_camera_list(self) -> list:
|
||||
"""Get list of cameras with frames - all frames persist until replaced."""
|
||||
with self._lock:
|
||||
# Return all cameras that have frames - no age-based filtering
|
||||
return list(self._frames.keys())
|
||||
|
||||
def get_stats(self) -> Dict[str, Any]:
|
||||
"""Get buffer statistics."""
|
||||
with self._lock:
|
||||
current_time = time.time()
|
||||
stats = {
|
||||
'total_cameras': len(self._frames),
|
||||
'recent_cameras': 0,
|
||||
'stale_cameras': 0,
|
||||
'total_memory_mb': 0,
|
||||
'cameras': {}
|
||||
}
|
||||
|
||||
for camera_id, frame_data in self._frames.items():
|
||||
age = current_time - frame_data['timestamp']
|
||||
size_mb = frame_data.get('size_mb', 0)
|
||||
|
||||
# All frames are valid/available, but categorize by freshness for monitoring
|
||||
if age <= self.max_age_seconds:
|
||||
stats['recent_cameras'] += 1
|
||||
else:
|
||||
stats['stale_cameras'] += 1
|
||||
|
||||
stats['total_memory_mb'] += size_mb
|
||||
|
||||
stats['cameras'][camera_id] = {
|
||||
'age': age,
|
||||
'recent': age <= self.max_age_seconds, # Recent but all frames available
|
||||
'shape': frame_data['shape'],
|
||||
'dtype': frame_data['dtype'],
|
||||
'size_mb': size_mb
|
||||
}
|
||||
|
||||
return stats
|
||||
|
||||
def _validate_frame(self, frame: np.ndarray) -> bool:
|
||||
"""Validate frame - basic validation for any stream type."""
|
||||
if frame is None or frame.size == 0:
|
||||
return False
|
||||
|
||||
h, w = frame.shape[:2]
|
||||
size_mb = frame.nbytes / (1024 * 1024)
|
||||
|
||||
# Basic size validation - reject extremely large frames regardless of type
|
||||
max_size_mb = 50 # Generous limit for any frame type
|
||||
if size_mb > max_size_mb:
|
||||
logger.warning(f"Frame too large: {size_mb:.2f}MB (max {max_size_mb}MB) for {w}x{h}")
|
||||
return False
|
||||
|
||||
# Basic dimension validation
|
||||
if w < 100 or h < 100:
|
||||
logger.warning(f"Frame too small: {w}x{h}")
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
|
||||
class CacheBuffer:
|
||||
"""Enhanced frame cache with support for cropping."""
|
||||
|
||||
def __init__(self, max_age_seconds: int = 10):
|
||||
self.frame_buffer = FrameBuffer(max_age_seconds)
|
||||
self._crop_cache: Dict[str, Dict[str, Any]] = {}
|
||||
self._cache_lock = threading.RLock()
|
||||
self.jpeg_quality = 95 # High quality for all frames
|
||||
|
||||
def put_frame(self, camera_id: str, frame: np.ndarray):
|
||||
"""Store a frame and clear any associated crop cache."""
|
||||
self.frame_buffer.put_frame(camera_id, frame)
|
||||
|
||||
# Clear crop cache for this camera since we have a new frame
|
||||
with self._cache_lock:
|
||||
keys_to_remove = [key for key in self._crop_cache.keys() if key.startswith(f"{camera_id}_")]
|
||||
for key in keys_to_remove:
|
||||
del self._crop_cache[key]
|
||||
|
||||
def get_frame(self, camera_id: str, crop_coords: Optional[Tuple[int, int, int, int]] = None) -> Optional[np.ndarray]:
|
||||
"""Get frame with optional cropping."""
|
||||
if crop_coords is None:
|
||||
return self.frame_buffer.get_frame(camera_id)
|
||||
|
||||
# Check crop cache first
|
||||
crop_key = f"{camera_id}_{crop_coords}"
|
||||
with self._cache_lock:
|
||||
if crop_key in self._crop_cache:
|
||||
cache_entry = self._crop_cache[crop_key]
|
||||
age = time.time() - cache_entry['timestamp']
|
||||
if age <= self.frame_buffer.max_age_seconds:
|
||||
return cache_entry['cropped_frame'].copy()
|
||||
else:
|
||||
del self._crop_cache[crop_key]
|
||||
|
||||
# Get original frame and crop it
|
||||
original_frame = self.frame_buffer.get_frame(camera_id)
|
||||
if original_frame is None:
|
||||
return None
|
||||
|
||||
try:
|
||||
x1, y1, x2, y2 = crop_coords
|
||||
|
||||
# Ensure coordinates are within frame bounds
|
||||
h, w = original_frame.shape[:2]
|
||||
x1 = max(0, min(x1, w))
|
||||
y1 = max(0, min(y1, h))
|
||||
x2 = max(x1, min(x2, w))
|
||||
y2 = max(y1, min(y2, h))
|
||||
|
||||
cropped_frame = original_frame[y1:y2, x1:x2]
|
||||
|
||||
# Cache the cropped frame
|
||||
with self._cache_lock:
|
||||
# Limit cache size to prevent memory issues
|
||||
if len(self._crop_cache) > 100:
|
||||
# Remove oldest entries
|
||||
oldest_keys = sorted(self._crop_cache.keys(),
|
||||
key=lambda k: self._crop_cache[k]['timestamp'])[:50]
|
||||
for key in oldest_keys:
|
||||
del self._crop_cache[key]
|
||||
|
||||
self._crop_cache[crop_key] = {
|
||||
'cropped_frame': cropped_frame.copy(),
|
||||
'timestamp': time.time(),
|
||||
'crop_coords': (x1, y1, x2, y2)
|
||||
}
|
||||
|
||||
return cropped_frame
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error cropping frame for camera {camera_id}: {e}")
|
||||
return original_frame
|
||||
|
||||
def get_frame_as_jpeg(self, camera_id: str, crop_coords: Optional[Tuple[int, int, int, int]] = None,
|
||||
quality: Optional[int] = None) -> Optional[bytes]:
|
||||
"""Get frame as JPEG bytes."""
|
||||
frame = self.get_frame(camera_id, crop_coords)
|
||||
if frame is None:
|
||||
return None
|
||||
|
||||
try:
|
||||
# Use specified quality or default
|
||||
if quality is None:
|
||||
quality = self.jpeg_quality
|
||||
|
||||
# Encode as JPEG with specified quality
|
||||
encode_params = [cv2.IMWRITE_JPEG_QUALITY, quality]
|
||||
success, encoded_img = cv2.imencode('.jpg', frame, encode_params)
|
||||
|
||||
if success:
|
||||
jpeg_bytes = encoded_img.tobytes()
|
||||
logger.debug(f"Encoded JPEG for camera {camera_id}: quality={quality}, size={len(jpeg_bytes)} bytes")
|
||||
return jpeg_bytes
|
||||
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error encoding frame as JPEG for camera {camera_id}: {e}")
|
||||
return None
|
||||
|
||||
def has_frame(self, camera_id: str) -> bool:
|
||||
"""Check if a valid frame exists for the camera."""
|
||||
return self.frame_buffer.has_frame(camera_id)
|
||||
|
||||
def clear_camera(self, camera_id: str):
|
||||
"""Remove all frames and cache for a specific camera."""
|
||||
self.frame_buffer.clear_camera(camera_id)
|
||||
with self._cache_lock:
|
||||
# Clear crop cache entries for this camera
|
||||
keys_to_remove = [key for key in self._crop_cache.keys() if key.startswith(f"{camera_id}_")]
|
||||
for key in keys_to_remove:
|
||||
del self._crop_cache[key]
|
||||
|
||||
def clear_all(self):
|
||||
"""Clear all stored frames and cache."""
|
||||
self.frame_buffer.clear_all()
|
||||
with self._cache_lock:
|
||||
self._crop_cache.clear()
|
||||
|
||||
def get_stats(self) -> Dict[str, Any]:
|
||||
"""Get comprehensive buffer and cache statistics."""
|
||||
buffer_stats = self.frame_buffer.get_stats()
|
||||
|
||||
with self._cache_lock:
|
||||
cache_stats = {
|
||||
'crop_cache_entries': len(self._crop_cache),
|
||||
'crop_cache_cameras': len(set(key.split('_')[0] for key in self._crop_cache.keys() if '_' in key)),
|
||||
'crop_cache_memory_mb': sum(
|
||||
entry['cropped_frame'].nbytes / (1024 * 1024)
|
||||
for entry in self._crop_cache.values()
|
||||
)
|
||||
}
|
||||
|
||||
return {
|
||||
'buffer': buffer_stats,
|
||||
'cache': cache_stats,
|
||||
'total_memory_mb': buffer_stats.get('total_memory_mb', 0) + cache_stats.get('crop_cache_memory_mb', 0)
|
||||
}
|
||||
|
||||
|
||||
# Global shared instances for application use
|
||||
shared_frame_buffer = FrameBuffer(max_age_seconds=5)
|
||||
shared_cache_buffer = CacheBuffer(max_age_seconds=10)
|
||||
|
||||
|
||||
|
|
@ -1,722 +0,0 @@
|
|||
"""
|
||||
Stream coordination and lifecycle management.
|
||||
Optimized for 1280x720@6fps RTSP and 2560x1440 HTTP snapshots.
|
||||
"""
|
||||
import logging
|
||||
import threading
|
||||
import time
|
||||
import queue
|
||||
import asyncio
|
||||
from typing import Dict, Set, Optional, List, Any
|
||||
from dataclasses import dataclass
|
||||
from collections import defaultdict
|
||||
|
||||
from .readers import HTTPSnapshotReader, FFmpegRTSPReader
|
||||
from .buffers import shared_cache_buffer
|
||||
from ..tracking.integration import TrackingPipelineIntegration
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@dataclass
|
||||
class StreamConfig:
|
||||
"""Configuration for a stream."""
|
||||
camera_id: str
|
||||
rtsp_url: Optional[str] = None
|
||||
snapshot_url: Optional[str] = None
|
||||
snapshot_interval: int = 5000 # milliseconds
|
||||
max_retries: int = 3
|
||||
|
||||
|
||||
@dataclass
|
||||
class SubscriptionInfo:
|
||||
"""Information about a subscription."""
|
||||
subscription_id: str
|
||||
camera_id: str
|
||||
stream_config: StreamConfig
|
||||
created_at: float
|
||||
crop_coords: Optional[tuple] = None
|
||||
model_id: Optional[str] = None
|
||||
model_url: Optional[str] = None
|
||||
tracking_integration: Optional[TrackingPipelineIntegration] = None
|
||||
|
||||
|
||||
class StreamManager:
|
||||
"""Manages multiple camera streams with shared optimization."""
|
||||
|
||||
def __init__(self, max_streams: int = 10):
|
||||
self.max_streams = max_streams
|
||||
self._streams: Dict[str, Any] = {} # camera_id -> reader instance
|
||||
self._subscriptions: Dict[str, SubscriptionInfo] = {} # subscription_id -> info
|
||||
self._camera_subscribers: Dict[str, Set[str]] = defaultdict(set) # camera_id -> set of subscription_ids
|
||||
self._lock = threading.RLock()
|
||||
|
||||
# Fair tracking queue system - per camera queues
|
||||
self._tracking_queues: Dict[str, queue.Queue] = {} # camera_id -> queue
|
||||
self._tracking_workers = []
|
||||
self._stop_workers = threading.Event()
|
||||
self._dropped_frame_counts: Dict[str, int] = {} # per-camera drop counts
|
||||
|
||||
# Round-robin scheduling state
|
||||
self._camera_list = [] # Ordered list of active cameras
|
||||
self._camera_round_robin_index = 0
|
||||
self._round_robin_lock = threading.Lock()
|
||||
|
||||
# Start worker threads for tracking processing
|
||||
num_workers = min(4, max_streams // 2 + 1) # Scale with streams
|
||||
for i in range(num_workers):
|
||||
worker = threading.Thread(
|
||||
target=self._tracking_worker_loop,
|
||||
name=f"TrackingWorker-{i}",
|
||||
daemon=True
|
||||
)
|
||||
worker.start()
|
||||
self._tracking_workers.append(worker)
|
||||
|
||||
logger.info(f"Started {num_workers} tracking worker threads")
|
||||
|
||||
def _ensure_camera_queue(self, camera_id: str):
|
||||
"""Ensure a tracking queue exists for the camera."""
|
||||
if camera_id not in self._tracking_queues:
|
||||
self._tracking_queues[camera_id] = queue.Queue(maxsize=10) # 10 frames per camera
|
||||
self._dropped_frame_counts[camera_id] = 0
|
||||
|
||||
with self._round_robin_lock:
|
||||
if camera_id not in self._camera_list:
|
||||
self._camera_list.append(camera_id)
|
||||
logger.info(f"Created tracking queue for camera {camera_id}")
|
||||
else:
|
||||
logger.debug(f"Camera {camera_id} already has tracking queue")
|
||||
|
||||
def _remove_camera_queue(self, camera_id: str):
|
||||
"""Remove tracking queue for a camera that's no longer active."""
|
||||
if camera_id in self._tracking_queues:
|
||||
# Clear any remaining items
|
||||
while not self._tracking_queues[camera_id].empty():
|
||||
try:
|
||||
self._tracking_queues[camera_id].get_nowait()
|
||||
except queue.Empty:
|
||||
break
|
||||
|
||||
del self._tracking_queues[camera_id]
|
||||
del self._dropped_frame_counts[camera_id]
|
||||
|
||||
with self._round_robin_lock:
|
||||
if camera_id in self._camera_list:
|
||||
self._camera_list.remove(camera_id)
|
||||
# Reset index if needed
|
||||
if self._camera_round_robin_index >= len(self._camera_list):
|
||||
self._camera_round_robin_index = 0
|
||||
|
||||
logger.info(f"Removed tracking queue for camera {camera_id}")
|
||||
|
||||
def add_subscription(self, subscription_id: str, stream_config: StreamConfig,
|
||||
crop_coords: Optional[tuple] = None,
|
||||
model_id: Optional[str] = None,
|
||||
model_url: Optional[str] = None,
|
||||
tracking_integration: Optional[TrackingPipelineIntegration] = None) -> bool:
|
||||
"""Add a new subscription. Returns True if successful."""
|
||||
with self._lock:
|
||||
if subscription_id in self._subscriptions:
|
||||
logger.warning(f"Subscription {subscription_id} already exists")
|
||||
return False
|
||||
|
||||
camera_id = stream_config.camera_id
|
||||
|
||||
# Create subscription info
|
||||
subscription_info = SubscriptionInfo(
|
||||
subscription_id=subscription_id,
|
||||
camera_id=camera_id,
|
||||
stream_config=stream_config,
|
||||
created_at=time.time(),
|
||||
crop_coords=crop_coords,
|
||||
model_id=model_id,
|
||||
model_url=model_url,
|
||||
tracking_integration=tracking_integration
|
||||
)
|
||||
|
||||
# Pass subscription info to tracking integration for snapshot access
|
||||
if tracking_integration:
|
||||
tracking_integration.set_subscription_info(subscription_info)
|
||||
|
||||
self._subscriptions[subscription_id] = subscription_info
|
||||
self._camera_subscribers[camera_id].add(subscription_id)
|
||||
|
||||
# Start stream if not already running
|
||||
if camera_id not in self._streams:
|
||||
if len(self._streams) >= self.max_streams:
|
||||
logger.error(f"Maximum streams ({self.max_streams}) reached, cannot add {camera_id}")
|
||||
self._remove_subscription_internal(subscription_id)
|
||||
return False
|
||||
|
||||
success = self._start_stream(camera_id, stream_config)
|
||||
if not success:
|
||||
self._remove_subscription_internal(subscription_id)
|
||||
return False
|
||||
else:
|
||||
# Stream already exists, but ensure queue exists too
|
||||
logger.info(f"Stream already exists for {camera_id}, ensuring queue exists")
|
||||
self._ensure_camera_queue(camera_id)
|
||||
|
||||
logger.info(f"Added subscription {subscription_id} for camera {camera_id} "
|
||||
f"({len(self._camera_subscribers[camera_id])} total subscribers)")
|
||||
return True
|
||||
|
||||
def remove_subscription(self, subscription_id: str) -> bool:
|
||||
"""Remove a subscription. Returns True if found and removed."""
|
||||
with self._lock:
|
||||
return self._remove_subscription_internal(subscription_id)
|
||||
|
||||
def _remove_subscription_internal(self, subscription_id: str) -> bool:
|
||||
"""Internal method to remove subscription (assumes lock is held)."""
|
||||
if subscription_id not in self._subscriptions:
|
||||
logger.warning(f"Subscription {subscription_id} not found")
|
||||
return False
|
||||
|
||||
subscription_info = self._subscriptions[subscription_id]
|
||||
camera_id = subscription_info.camera_id
|
||||
|
||||
# Remove from tracking
|
||||
del self._subscriptions[subscription_id]
|
||||
self._camera_subscribers[camera_id].discard(subscription_id)
|
||||
|
||||
# Stop stream if no more subscribers
|
||||
if not self._camera_subscribers[camera_id]:
|
||||
self._stop_stream(camera_id)
|
||||
del self._camera_subscribers[camera_id]
|
||||
|
||||
logger.info(f"Removed subscription {subscription_id} for camera {camera_id} "
|
||||
f"({len(self._camera_subscribers[camera_id])} remaining subscribers)")
|
||||
return True
|
||||
|
||||
def _start_stream(self, camera_id: str, stream_config: StreamConfig) -> bool:
|
||||
"""Start a stream for the given camera."""
|
||||
try:
|
||||
if stream_config.rtsp_url:
|
||||
# RTSP stream using FFmpeg subprocess with CUDA acceleration
|
||||
logger.info(f"\033[94m[RTSP] Starting {camera_id}\033[0m")
|
||||
reader = FFmpegRTSPReader(
|
||||
camera_id=camera_id,
|
||||
rtsp_url=stream_config.rtsp_url,
|
||||
max_retries=stream_config.max_retries
|
||||
)
|
||||
reader.set_frame_callback(self._frame_callback)
|
||||
reader.start()
|
||||
self._streams[camera_id] = reader
|
||||
self._ensure_camera_queue(camera_id) # Create tracking queue
|
||||
logger.info(f"\033[92m[RTSP] {camera_id} connected\033[0m")
|
||||
|
||||
elif stream_config.snapshot_url:
|
||||
# HTTP snapshot stream
|
||||
logger.info(f"\033[95m[HTTP] Starting {camera_id}\033[0m")
|
||||
reader = HTTPSnapshotReader(
|
||||
camera_id=camera_id,
|
||||
snapshot_url=stream_config.snapshot_url,
|
||||
interval_ms=stream_config.snapshot_interval,
|
||||
max_retries=stream_config.max_retries
|
||||
)
|
||||
reader.set_frame_callback(self._frame_callback)
|
||||
reader.start()
|
||||
self._streams[camera_id] = reader
|
||||
self._ensure_camera_queue(camera_id) # Create tracking queue
|
||||
logger.info(f"\033[92m[HTTP] {camera_id} connected\033[0m")
|
||||
|
||||
else:
|
||||
logger.error(f"No valid URL provided for camera {camera_id}")
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error starting stream for camera {camera_id}: {e}")
|
||||
return False
|
||||
|
||||
def _stop_stream(self, camera_id: str):
|
||||
"""Stop a stream for the given camera."""
|
||||
if camera_id in self._streams:
|
||||
try:
|
||||
self._streams[camera_id].stop()
|
||||
del self._streams[camera_id]
|
||||
self._remove_camera_queue(camera_id) # Remove tracking queue
|
||||
# DON'T clear frames - they should persist until replaced
|
||||
# shared_cache_buffer.clear_camera(camera_id) # REMOVED - frames should persist
|
||||
logger.info(f"Stopped stream for camera {camera_id} (frames preserved in buffer)")
|
||||
except Exception as e:
|
||||
logger.error(f"Error stopping stream for camera {camera_id}: {e}")
|
||||
|
||||
def _frame_callback(self, camera_id: str, frame):
|
||||
"""Callback for when a new frame is available."""
|
||||
try:
|
||||
# Store frame in shared buffer
|
||||
shared_cache_buffer.put_frame(camera_id, frame)
|
||||
# Quieter frame callback logging - only log occasionally
|
||||
if hasattr(self, '_frame_log_count'):
|
||||
self._frame_log_count += 1
|
||||
else:
|
||||
self._frame_log_count = 1
|
||||
|
||||
# Log every 100 frames to avoid spam
|
||||
if self._frame_log_count % 100 == 0:
|
||||
available_cameras = shared_cache_buffer.frame_buffer.get_camera_list()
|
||||
logger.info(f"\033[96m[BUFFER] {len(available_cameras)} active cameras: {', '.join(available_cameras)}\033[0m")
|
||||
|
||||
# Queue for tracking processing (non-blocking) - route to camera-specific queue
|
||||
if camera_id in self._tracking_queues:
|
||||
try:
|
||||
self._tracking_queues[camera_id].put_nowait({
|
||||
'frame': frame,
|
||||
'timestamp': time.time()
|
||||
})
|
||||
except queue.Full:
|
||||
# Drop frame if camera queue is full (maintain real-time)
|
||||
self._dropped_frame_counts[camera_id] += 1
|
||||
|
||||
if self._dropped_frame_counts[camera_id] % 50 == 0:
|
||||
logger.warning(f"Dropped {self._dropped_frame_counts[camera_id]} frames for camera {camera_id} due to full queue")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in frame callback for camera {camera_id}: {e}")
|
||||
|
||||
def _process_tracking_for_camera(self, camera_id: str, frame):
|
||||
"""Process tracking for all subscriptions of a camera."""
|
||||
try:
|
||||
with self._lock:
|
||||
for subscription_id in self._camera_subscribers[camera_id]:
|
||||
subscription_info = self._subscriptions[subscription_id]
|
||||
|
||||
# Skip if no tracking integration
|
||||
if not subscription_info.tracking_integration:
|
||||
continue
|
||||
|
||||
# Extract display_id from subscription_id
|
||||
display_id = subscription_id.split(';')[0] if ';' in subscription_id else subscription_id
|
||||
|
||||
# Process frame through tracking asynchronously
|
||||
# Note: This is synchronous for now, can be made async in future
|
||||
try:
|
||||
# Create a simple asyncio event loop for this frame
|
||||
import asyncio
|
||||
loop = asyncio.new_event_loop()
|
||||
asyncio.set_event_loop(loop)
|
||||
try:
|
||||
result = loop.run_until_complete(
|
||||
subscription_info.tracking_integration.process_frame(
|
||||
frame, display_id, subscription_id
|
||||
)
|
||||
)
|
||||
# Log tracking results
|
||||
if result:
|
||||
tracked_count = len(result.get('tracked_vehicles', []))
|
||||
validated_vehicle = result.get('validated_vehicle')
|
||||
pipeline_result = result.get('pipeline_result')
|
||||
|
||||
if tracked_count > 0:
|
||||
logger.info(f"[Tracking] {camera_id}: {tracked_count} vehicles tracked")
|
||||
|
||||
if validated_vehicle:
|
||||
logger.info(f"[Tracking] {camera_id}: Vehicle {validated_vehicle['track_id']} "
|
||||
f"validated as {validated_vehicle['state']} "
|
||||
f"(confidence: {validated_vehicle['confidence']:.2f})")
|
||||
|
||||
if pipeline_result:
|
||||
logger.info(f"[Pipeline] {camera_id}: {pipeline_result.get('status', 'unknown')} - "
|
||||
f"{pipeline_result.get('message', 'no message')}")
|
||||
finally:
|
||||
loop.close()
|
||||
except Exception as track_e:
|
||||
logger.error(f"Error in tracking for {subscription_id}: {track_e}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error processing tracking for camera {camera_id}: {e}")
|
||||
|
||||
def _tracking_worker_loop(self):
|
||||
"""Worker thread loop for round-robin processing of camera queues."""
|
||||
logger.info(f"Tracking worker {threading.current_thread().name} started")
|
||||
|
||||
consecutive_empty = 0
|
||||
max_consecutive_empty = 10 # Sleep if all cameras empty this many times
|
||||
|
||||
while not self._stop_workers.is_set():
|
||||
try:
|
||||
# Get next camera in round-robin fashion
|
||||
camera_id, item = self._get_next_camera_item()
|
||||
|
||||
if camera_id is None:
|
||||
# No cameras have items, sleep briefly
|
||||
consecutive_empty += 1
|
||||
if consecutive_empty >= max_consecutive_empty:
|
||||
time.sleep(0.1) # Sleep 100ms if nothing to process
|
||||
consecutive_empty = 0
|
||||
continue
|
||||
|
||||
consecutive_empty = 0 # Reset counter when we find work
|
||||
|
||||
frame = item['frame']
|
||||
timestamp = item['timestamp']
|
||||
|
||||
# Check if frame is too old (drop if > 1 second old)
|
||||
age = time.time() - timestamp
|
||||
if age > 1.0:
|
||||
logger.debug(f"Dropping old frame for {camera_id} (age: {age:.2f}s)")
|
||||
continue
|
||||
|
||||
# Process tracking for this camera's frame
|
||||
self._process_tracking_for_camera_sync(camera_id, frame)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in tracking worker: {e}", exc_info=True)
|
||||
|
||||
logger.info(f"Tracking worker {threading.current_thread().name} stopped")
|
||||
|
||||
def _get_next_camera_item(self):
|
||||
"""Get next item from camera queues using round-robin scheduling."""
|
||||
with self._round_robin_lock:
|
||||
# Get current list of cameras from actual tracking queues (central state)
|
||||
camera_list = list(self._tracking_queues.keys())
|
||||
|
||||
if not camera_list:
|
||||
return None, None
|
||||
|
||||
attempts = 0
|
||||
max_attempts = len(camera_list)
|
||||
|
||||
while attempts < max_attempts:
|
||||
# Get current camera using round-robin index
|
||||
if self._camera_round_robin_index >= len(camera_list):
|
||||
self._camera_round_robin_index = 0
|
||||
|
||||
camera_id = camera_list[self._camera_round_robin_index]
|
||||
|
||||
# Move to next camera for next call
|
||||
self._camera_round_robin_index = (self._camera_round_robin_index + 1) % len(camera_list)
|
||||
|
||||
# Try to get item from this camera's queue
|
||||
try:
|
||||
item = self._tracking_queues[camera_id].get_nowait()
|
||||
return camera_id, item
|
||||
except queue.Empty:
|
||||
pass # Try next camera
|
||||
|
||||
attempts += 1
|
||||
|
||||
return None, None # All cameras empty
|
||||
|
||||
def _process_tracking_for_camera_sync(self, camera_id: str, frame):
|
||||
"""Synchronous version of tracking processing for worker threads."""
|
||||
try:
|
||||
with self._lock:
|
||||
subscription_ids = list(self._camera_subscribers.get(camera_id, []))
|
||||
|
||||
for subscription_id in subscription_ids:
|
||||
subscription_info = self._subscriptions.get(subscription_id)
|
||||
|
||||
if not subscription_info:
|
||||
logger.warning(f"No subscription info found for {subscription_id}")
|
||||
continue
|
||||
|
||||
if not subscription_info.tracking_integration:
|
||||
logger.debug(f"No tracking integration for {subscription_id} (camera {camera_id}), skipping inference")
|
||||
continue
|
||||
|
||||
display_id = subscription_id.split(';')[0] if ';' in subscription_id else subscription_id
|
||||
|
||||
try:
|
||||
# Run async tracking in thread's event loop
|
||||
loop = asyncio.new_event_loop()
|
||||
asyncio.set_event_loop(loop)
|
||||
try:
|
||||
result = loop.run_until_complete(
|
||||
subscription_info.tracking_integration.process_frame(
|
||||
frame, display_id, subscription_id
|
||||
)
|
||||
)
|
||||
|
||||
# Log tracking results
|
||||
if result:
|
||||
tracked_count = len(result.get('tracked_vehicles', []))
|
||||
validated_vehicle = result.get('validated_vehicle')
|
||||
pipeline_result = result.get('pipeline_result')
|
||||
|
||||
if tracked_count > 0:
|
||||
logger.info(f"[Tracking] {camera_id}: {tracked_count} vehicles tracked")
|
||||
|
||||
if validated_vehicle:
|
||||
logger.info(f"[Tracking] {camera_id}: Vehicle {validated_vehicle['track_id']} "
|
||||
f"validated as {validated_vehicle['state']} "
|
||||
f"(confidence: {validated_vehicle['confidence']:.2f})")
|
||||
|
||||
if pipeline_result:
|
||||
logger.info(f"[Pipeline] {camera_id}: {pipeline_result.get('status', 'unknown')} - "
|
||||
f"{pipeline_result.get('message', 'no message')}")
|
||||
finally:
|
||||
loop.close()
|
||||
|
||||
except Exception as track_e:
|
||||
logger.error(f"Error in tracking for {subscription_id}: {track_e}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error processing tracking for camera {camera_id}: {e}")
|
||||
|
||||
def get_frame(self, camera_id: str, crop_coords: Optional[tuple] = None):
|
||||
"""Get the latest frame for a camera with optional cropping."""
|
||||
return shared_cache_buffer.get_frame(camera_id, crop_coords)
|
||||
|
||||
def get_frame_as_jpeg(self, camera_id: str, crop_coords: Optional[tuple] = None,
|
||||
quality: int = 100) -> Optional[bytes]:
|
||||
"""Get frame as JPEG bytes for HTTP responses with highest quality by default."""
|
||||
return shared_cache_buffer.get_frame_as_jpeg(camera_id, crop_coords, quality)
|
||||
|
||||
def has_frame(self, camera_id: str) -> bool:
|
||||
"""Check if a frame is available for the camera."""
|
||||
return shared_cache_buffer.has_frame(camera_id)
|
||||
|
||||
def get_subscription_info(self, subscription_id: str) -> Optional[SubscriptionInfo]:
|
||||
"""Get information about a subscription."""
|
||||
with self._lock:
|
||||
return self._subscriptions.get(subscription_id)
|
||||
|
||||
def get_camera_subscribers(self, camera_id: str) -> Set[str]:
|
||||
"""Get all subscription IDs for a camera."""
|
||||
with self._lock:
|
||||
return self._camera_subscribers[camera_id].copy()
|
||||
|
||||
def get_active_cameras(self) -> List[str]:
|
||||
"""Get list of cameras with active streams."""
|
||||
with self._lock:
|
||||
return list(self._streams.keys())
|
||||
|
||||
def get_all_subscriptions(self) -> List[SubscriptionInfo]:
|
||||
"""Get all active subscriptions."""
|
||||
with self._lock:
|
||||
return list(self._subscriptions.values())
|
||||
|
||||
def reconcile_subscriptions(self, target_subscriptions: List[Dict[str, Any]]) -> Dict[str, Any]:
|
||||
"""
|
||||
Reconcile current subscriptions with target list.
|
||||
Returns summary of changes made.
|
||||
"""
|
||||
with self._lock:
|
||||
current_subscription_ids = set(self._subscriptions.keys())
|
||||
target_subscription_ids = {sub['subscriptionIdentifier'] for sub in target_subscriptions}
|
||||
|
||||
# Find subscriptions to remove and add
|
||||
to_remove = current_subscription_ids - target_subscription_ids
|
||||
to_add = target_subscription_ids - current_subscription_ids
|
||||
|
||||
# Remove old subscriptions
|
||||
removed_count = 0
|
||||
for subscription_id in to_remove:
|
||||
if self._remove_subscription_internal(subscription_id):
|
||||
removed_count += 1
|
||||
|
||||
# Add new subscriptions
|
||||
added_count = 0
|
||||
failed_count = 0
|
||||
for target_sub in target_subscriptions:
|
||||
subscription_id = target_sub['subscriptionIdentifier']
|
||||
if subscription_id in to_add:
|
||||
success = self._add_subscription_from_payload(subscription_id, target_sub)
|
||||
if success:
|
||||
added_count += 1
|
||||
else:
|
||||
failed_count += 1
|
||||
|
||||
result = {
|
||||
'removed': removed_count,
|
||||
'added': added_count,
|
||||
'failed': failed_count,
|
||||
'total_active': len(self._subscriptions),
|
||||
'active_streams': len(self._streams)
|
||||
}
|
||||
|
||||
logger.info(f"Subscription reconciliation: {result}")
|
||||
return result
|
||||
|
||||
def _add_subscription_from_payload(self, subscription_id: str, payload: Dict[str, Any]) -> bool:
|
||||
"""Add subscription from WebSocket payload format."""
|
||||
try:
|
||||
# Extract camera ID from subscription identifier
|
||||
# Format: "display-001;cam-001" -> camera_id = "cam-001"
|
||||
camera_id = subscription_id.split(';')[-1]
|
||||
|
||||
# Extract crop coordinates if present
|
||||
crop_coords = None
|
||||
if all(key in payload for key in ['cropX1', 'cropY1', 'cropX2', 'cropY2']):
|
||||
crop_coords = (
|
||||
payload['cropX1'],
|
||||
payload['cropY1'],
|
||||
payload['cropX2'],
|
||||
payload['cropY2']
|
||||
)
|
||||
|
||||
# Create stream configuration
|
||||
stream_config = StreamConfig(
|
||||
camera_id=camera_id,
|
||||
rtsp_url=payload.get('rtspUrl'),
|
||||
snapshot_url=payload.get('snapshotUrl'),
|
||||
snapshot_interval=payload.get('snapshotInterval', 5000),
|
||||
max_retries=3,
|
||||
)
|
||||
|
||||
return self.add_subscription(
|
||||
subscription_id,
|
||||
stream_config,
|
||||
crop_coords,
|
||||
model_id=payload.get('modelId'),
|
||||
model_url=payload.get('modelUrl')
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error adding subscription from payload {subscription_id}: {e}")
|
||||
return False
|
||||
|
||||
def stop_all(self):
|
||||
"""Stop all streams and clear all subscriptions."""
|
||||
# Signal workers to stop
|
||||
self._stop_workers.set()
|
||||
|
||||
# Clear all camera queues
|
||||
for camera_id, camera_queue in list(self._tracking_queues.items()):
|
||||
while not camera_queue.empty():
|
||||
try:
|
||||
camera_queue.get_nowait()
|
||||
except queue.Empty:
|
||||
break
|
||||
|
||||
# Wait for workers to finish
|
||||
for worker in self._tracking_workers:
|
||||
worker.join(timeout=2.0)
|
||||
|
||||
# Clear queue management structures
|
||||
self._tracking_queues.clear()
|
||||
self._dropped_frame_counts.clear()
|
||||
with self._round_robin_lock:
|
||||
self._camera_list.clear()
|
||||
self._camera_round_robin_index = 0
|
||||
|
||||
logger.info("Stopped all tracking worker threads")
|
||||
|
||||
with self._lock:
|
||||
# Stop all streams
|
||||
for camera_id in list(self._streams.keys()):
|
||||
self._stop_stream(camera_id)
|
||||
|
||||
# Clear all tracking
|
||||
self._subscriptions.clear()
|
||||
self._camera_subscribers.clear()
|
||||
shared_cache_buffer.clear_all()
|
||||
|
||||
logger.info("Stopped all streams and cleared all subscriptions")
|
||||
|
||||
def set_session_id(self, display_id: str, session_id: str):
|
||||
"""Set session ID for tracking integration."""
|
||||
# Ensure session_id is always a string for consistent type handling
|
||||
session_id = str(session_id) if session_id is not None else None
|
||||
with self._lock:
|
||||
for subscription_info in self._subscriptions.values():
|
||||
# Check if this subscription matches the display_id
|
||||
subscription_display_id = subscription_info.subscription_id.split(';')[0]
|
||||
if subscription_display_id == display_id and subscription_info.tracking_integration:
|
||||
# Pass the full subscription_id (displayId;cameraId) to the tracking integration
|
||||
subscription_info.tracking_integration.set_session_id(
|
||||
display_id,
|
||||
session_id,
|
||||
subscription_id=subscription_info.subscription_id
|
||||
)
|
||||
logger.debug(f"Set session {session_id} for display {display_id} with subscription {subscription_info.subscription_id}")
|
||||
|
||||
def clear_session_id(self, session_id: str):
|
||||
"""Clear session ID from the specific tracking integration handling this session."""
|
||||
with self._lock:
|
||||
# Find the subscription that's handling this session
|
||||
session_subscription = None
|
||||
for subscription_info in self._subscriptions.values():
|
||||
if subscription_info.tracking_integration:
|
||||
# Check if this integration is handling the given session_id
|
||||
integration = subscription_info.tracking_integration
|
||||
if session_id in integration.session_vehicles:
|
||||
session_subscription = subscription_info
|
||||
break
|
||||
|
||||
if session_subscription and session_subscription.tracking_integration:
|
||||
session_subscription.tracking_integration.clear_session_id(session_id)
|
||||
logger.debug(f"Cleared session {session_id} from subscription {session_subscription.subscription_id}")
|
||||
else:
|
||||
logger.warning(f"No tracking integration found for session {session_id}, broadcasting to all subscriptions")
|
||||
# Fallback: broadcast to all (original behavior)
|
||||
for subscription_info in self._subscriptions.values():
|
||||
if subscription_info.tracking_integration:
|
||||
subscription_info.tracking_integration.clear_session_id(session_id)
|
||||
|
||||
def set_progression_stage(self, session_id: str, stage: str):
|
||||
"""Set progression stage for the specific tracking integration handling this session."""
|
||||
with self._lock:
|
||||
# Find the subscription that's handling this session
|
||||
session_subscription = None
|
||||
for subscription_info in self._subscriptions.values():
|
||||
if subscription_info.tracking_integration:
|
||||
# Check if this integration is handling the given session_id
|
||||
# We need to check the integration's active sessions
|
||||
integration = subscription_info.tracking_integration
|
||||
if session_id in integration.session_vehicles:
|
||||
session_subscription = subscription_info
|
||||
break
|
||||
|
||||
if session_subscription and session_subscription.tracking_integration:
|
||||
session_subscription.tracking_integration.set_progression_stage(session_id, stage)
|
||||
logger.debug(f"Set progression stage for session {session_id}: {stage} on subscription {session_subscription.subscription_id}")
|
||||
else:
|
||||
logger.warning(f"No tracking integration found for session {session_id}, broadcasting to all subscriptions")
|
||||
# Fallback: broadcast to all (original behavior)
|
||||
for subscription_info in self._subscriptions.values():
|
||||
if subscription_info.tracking_integration:
|
||||
subscription_info.tracking_integration.set_progression_stage(session_id, stage)
|
||||
|
||||
def get_tracking_stats(self) -> Dict[str, Any]:
|
||||
"""Get tracking statistics from all subscriptions."""
|
||||
stats = {}
|
||||
with self._lock:
|
||||
for subscription_id, subscription_info in self._subscriptions.items():
|
||||
if subscription_info.tracking_integration:
|
||||
stats[subscription_id] = subscription_info.tracking_integration.get_statistics()
|
||||
return stats
|
||||
|
||||
|
||||
def get_stats(self) -> Dict[str, Any]:
|
||||
"""Get comprehensive streaming statistics."""
|
||||
with self._lock:
|
||||
buffer_stats = shared_cache_buffer.get_stats()
|
||||
tracking_stats = self.get_tracking_stats()
|
||||
|
||||
return {
|
||||
'active_subscriptions': len(self._subscriptions),
|
||||
'active_streams': len(self._streams),
|
||||
'cameras_with_subscribers': len(self._camera_subscribers),
|
||||
'max_streams': self.max_streams,
|
||||
'subscriptions_by_camera': {
|
||||
camera_id: len(subscribers)
|
||||
for camera_id, subscribers in self._camera_subscribers.items()
|
||||
},
|
||||
'buffer_stats': buffer_stats,
|
||||
'tracking_stats': tracking_stats,
|
||||
'memory_usage_mb': buffer_stats.get('total_memory_mb', 0)
|
||||
}
|
||||
|
||||
|
||||
# Global shared instance for application use
|
||||
# Default initialization, will be updated with config value in app.py
|
||||
shared_stream_manager = StreamManager(max_streams=20)
|
||||
|
||||
def initialize_stream_manager(max_streams: int = 10):
|
||||
"""Re-initialize the global stream manager with config value."""
|
||||
global shared_stream_manager
|
||||
# Release old manager if exists
|
||||
if shared_stream_manager:
|
||||
try:
|
||||
# Stop all existing streams gracefully
|
||||
shared_stream_manager.stop_all()
|
||||
except Exception as e:
|
||||
logger.warning(f"Error stopping previous stream manager: {e}")
|
||||
shared_stream_manager = StreamManager(max_streams=max_streams)
|
||||
return shared_stream_manager
|
||||
|
|
@ -1,18 +0,0 @@
|
|||
"""
|
||||
Stream readers for RTSP and HTTP camera feeds.
|
||||
"""
|
||||
from .base import VideoReader
|
||||
from .ffmpeg_rtsp import FFmpegRTSPReader
|
||||
from .http_snapshot import HTTPSnapshotReader
|
||||
from .utils import log_success, log_warning, log_error, log_info, Colors
|
||||
|
||||
__all__ = [
|
||||
'VideoReader',
|
||||
'FFmpegRTSPReader',
|
||||
'HTTPSnapshotReader',
|
||||
'log_success',
|
||||
'log_warning',
|
||||
'log_error',
|
||||
'log_info',
|
||||
'Colors'
|
||||
]
|
||||
|
|
@ -1,65 +0,0 @@
|
|||
"""
|
||||
Abstract base class for video stream readers.
|
||||
"""
|
||||
from abc import ABC, abstractmethod
|
||||
from typing import Optional, Callable
|
||||
import numpy as np
|
||||
|
||||
|
||||
class VideoReader(ABC):
|
||||
"""Abstract base class for video stream readers."""
|
||||
|
||||
def __init__(self, camera_id: str, source_url: str, max_retries: int = 3):
|
||||
"""
|
||||
Initialize the video reader.
|
||||
|
||||
Args:
|
||||
camera_id: Unique identifier for the camera
|
||||
source_url: URL or path to the video source
|
||||
max_retries: Maximum number of retry attempts
|
||||
"""
|
||||
self.camera_id = camera_id
|
||||
self.source_url = source_url
|
||||
self.max_retries = max_retries
|
||||
self.frame_callback: Optional[Callable[[str, np.ndarray], None]] = None
|
||||
|
||||
@abstractmethod
|
||||
def start(self) -> None:
|
||||
"""Start the video reader."""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def stop(self) -> None:
|
||||
"""Stop the video reader."""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def set_frame_callback(self, callback: Callable[[str, np.ndarray], None]) -> None:
|
||||
"""
|
||||
Set callback function to handle captured frames.
|
||||
|
||||
Args:
|
||||
callback: Function that takes (camera_id, frame) as arguments
|
||||
"""
|
||||
pass
|
||||
|
||||
@property
|
||||
@abstractmethod
|
||||
def is_running(self) -> bool:
|
||||
"""Check if the reader is currently running."""
|
||||
pass
|
||||
|
||||
@property
|
||||
@abstractmethod
|
||||
def reader_type(self) -> str:
|
||||
"""Get the type of reader (e.g., 'rtsp', 'http_snapshot')."""
|
||||
pass
|
||||
|
||||
def __enter__(self):
|
||||
"""Context manager entry."""
|
||||
self.start()
|
||||
return self
|
||||
|
||||
def __exit__(self, exc_type, exc_val, exc_tb):
|
||||
"""Context manager exit."""
|
||||
self.stop()
|
||||
|
|
@ -1,436 +0,0 @@
|
|||
"""
|
||||
FFmpeg RTSP stream reader using subprocess piping frames directly to buffer.
|
||||
Enhanced with comprehensive health monitoring and automatic recovery.
|
||||
"""
|
||||
import cv2
|
||||
import time
|
||||
import threading
|
||||
import numpy as np
|
||||
import subprocess
|
||||
import struct
|
||||
from typing import Optional, Callable, Dict, Any
|
||||
|
||||
from .base import VideoReader
|
||||
from .utils import log_success, log_warning, log_error, log_info
|
||||
from ...monitoring.stream_health import stream_health_tracker
|
||||
from ...monitoring.thread_health import thread_health_monitor
|
||||
from ...monitoring.recovery import recovery_manager, RecoveryAction
|
||||
|
||||
|
||||
class FFmpegRTSPReader(VideoReader):
|
||||
"""RTSP stream reader using subprocess FFmpeg piping frames directly to buffer."""
|
||||
|
||||
def __init__(self, camera_id: str, rtsp_url: str, max_retries: int = 3):
|
||||
super().__init__(camera_id, rtsp_url, max_retries)
|
||||
self.rtsp_url = rtsp_url
|
||||
self.process = None
|
||||
self.stop_event = threading.Event()
|
||||
self.thread = None
|
||||
self.stderr_thread = None
|
||||
|
||||
# Expected stream specs (for reference, actual dimensions read from PPM header)
|
||||
self.width = 1280
|
||||
self.height = 720
|
||||
|
||||
# Watchdog timers for stream reliability
|
||||
self.process_start_time = None
|
||||
self.last_frame_time = None
|
||||
self.is_restart = False # Track if this is a restart (shorter timeout)
|
||||
self.first_start_timeout = 30.0 # 30s timeout on first start
|
||||
self.restart_timeout = 15.0 # 15s timeout after restart
|
||||
|
||||
# Health monitoring setup
|
||||
self.last_heartbeat = time.time()
|
||||
self.consecutive_errors = 0
|
||||
self.ffmpeg_restart_count = 0
|
||||
|
||||
# Register recovery handlers
|
||||
recovery_manager.register_recovery_handler(
|
||||
RecoveryAction.RESTART_STREAM,
|
||||
self._handle_restart_recovery
|
||||
)
|
||||
recovery_manager.register_recovery_handler(
|
||||
RecoveryAction.RECONNECT,
|
||||
self._handle_reconnect_recovery
|
||||
)
|
||||
|
||||
@property
|
||||
def is_running(self) -> bool:
|
||||
"""Check if the reader is currently running."""
|
||||
return self.thread is not None and self.thread.is_alive()
|
||||
|
||||
@property
|
||||
def reader_type(self) -> str:
|
||||
"""Get the type of reader."""
|
||||
return "rtsp_ffmpeg"
|
||||
|
||||
def set_frame_callback(self, callback: Callable[[str, np.ndarray], None]):
|
||||
"""Set callback function to handle captured frames."""
|
||||
self.frame_callback = callback
|
||||
|
||||
def start(self):
|
||||
"""Start the FFmpeg subprocess reader."""
|
||||
if self.thread and self.thread.is_alive():
|
||||
log_warning(self.camera_id, "FFmpeg reader already running")
|
||||
return
|
||||
|
||||
self.stop_event.clear()
|
||||
self.thread = threading.Thread(target=self._read_frames, daemon=True)
|
||||
self.thread.start()
|
||||
|
||||
# Register with health monitoring
|
||||
stream_health_tracker.register_stream(self.camera_id, "rtsp_ffmpeg", self.rtsp_url)
|
||||
thread_health_monitor.register_thread(self.thread, self._heartbeat_callback)
|
||||
|
||||
log_success(self.camera_id, "Stream started with health monitoring")
|
||||
|
||||
def stop(self):
|
||||
"""Stop the FFmpeg subprocess reader."""
|
||||
self.stop_event.set()
|
||||
|
||||
# Unregister from health monitoring
|
||||
if self.thread:
|
||||
thread_health_monitor.unregister_thread(self.thread.ident)
|
||||
|
||||
if self.process:
|
||||
self.process.terminate()
|
||||
try:
|
||||
self.process.wait(timeout=5)
|
||||
except subprocess.TimeoutExpired:
|
||||
self.process.kill()
|
||||
|
||||
if self.thread:
|
||||
self.thread.join(timeout=5.0)
|
||||
if self.stderr_thread:
|
||||
self.stderr_thread.join(timeout=2.0)
|
||||
|
||||
stream_health_tracker.unregister_stream(self.camera_id)
|
||||
|
||||
log_info(self.camera_id, "Stream stopped")
|
||||
|
||||
def _start_ffmpeg_process(self):
|
||||
"""Start FFmpeg subprocess outputting BMP frames to stdout pipe."""
|
||||
cmd = [
|
||||
'ffmpeg',
|
||||
# DO NOT REMOVE
|
||||
'-hwaccel', 'cuda',
|
||||
'-hwaccel_device', '0',
|
||||
# Real-time input flags
|
||||
'-fflags', 'nobuffer+genpts',
|
||||
'-flags', 'low_delay',
|
||||
'-max_delay', '0', # No reordering delay
|
||||
# RTSP configuration
|
||||
'-rtsp_transport', 'tcp',
|
||||
'-i', self.rtsp_url,
|
||||
# Output configuration (keeping BMP)
|
||||
'-f', 'image2pipe', # Output images to pipe
|
||||
'-vcodec', 'bmp', # BMP format with header containing dimensions
|
||||
'-vsync', 'passthrough', # Pass frames as-is
|
||||
# Use native stream resolution and framerate
|
||||
'-an', # No audio
|
||||
'-' # Output to stdout
|
||||
]
|
||||
|
||||
try:
|
||||
# Start FFmpeg with stdout pipe to read frames directly
|
||||
self.process = subprocess.Popen(
|
||||
cmd,
|
||||
stdout=subprocess.PIPE, # Capture stdout for frame data
|
||||
stderr=subprocess.PIPE, # Capture stderr for error logging
|
||||
bufsize=0 # Unbuffered for real-time processing
|
||||
)
|
||||
|
||||
# Start stderr reading thread
|
||||
if self.stderr_thread and self.stderr_thread.is_alive():
|
||||
# Stop previous stderr thread
|
||||
try:
|
||||
self.stderr_thread.join(timeout=1.0)
|
||||
except:
|
||||
pass
|
||||
|
||||
self.stderr_thread = threading.Thread(target=self._read_stderr, daemon=True)
|
||||
self.stderr_thread.start()
|
||||
|
||||
# Set process start time for watchdog
|
||||
self.process_start_time = time.time()
|
||||
self.last_frame_time = None # Reset frame time
|
||||
|
||||
# After successful restart, next timeout will be back to 30s
|
||||
if self.is_restart:
|
||||
log_info(self.camera_id, f"FFmpeg restarted successfully, next timeout: {self.first_start_timeout}s")
|
||||
self.is_restart = False
|
||||
|
||||
return True
|
||||
except Exception as e:
|
||||
log_error(self.camera_id, f"FFmpeg startup failed: {e}")
|
||||
return False
|
||||
|
||||
def _read_bmp_frame(self, pipe):
|
||||
"""Read BMP frame from pipe - BMP header contains dimensions."""
|
||||
try:
|
||||
# Read BMP header (14 bytes file header + 40 bytes info header = 54 bytes minimum)
|
||||
header_data = b''
|
||||
bytes_to_read = 54
|
||||
|
||||
while len(header_data) < bytes_to_read:
|
||||
chunk = pipe.read(bytes_to_read - len(header_data))
|
||||
if not chunk:
|
||||
return None # Silent end of stream
|
||||
header_data += chunk
|
||||
|
||||
# Parse BMP header
|
||||
if header_data[:2] != b'BM':
|
||||
return None # Invalid format, skip frame silently
|
||||
|
||||
# Extract file size from header (bytes 2-5)
|
||||
file_size = struct.unpack('<L', header_data[2:6])[0]
|
||||
|
||||
# Extract width and height from info header (bytes 18-21 and 22-25)
|
||||
width = struct.unpack('<L', header_data[18:22])[0]
|
||||
height = struct.unpack('<L', header_data[22:26])[0]
|
||||
|
||||
# Read remaining file data
|
||||
remaining_size = file_size - 54
|
||||
remaining_data = b''
|
||||
|
||||
while len(remaining_data) < remaining_size:
|
||||
chunk = pipe.read(remaining_size - len(remaining_data))
|
||||
if not chunk:
|
||||
return None # Stream ended silently
|
||||
remaining_data += chunk
|
||||
|
||||
# Complete BMP data
|
||||
bmp_data = header_data + remaining_data
|
||||
|
||||
# Use OpenCV to decode BMP directly from memory
|
||||
frame_array = np.frombuffer(bmp_data, dtype=np.uint8)
|
||||
frame = cv2.imdecode(frame_array, cv2.IMREAD_COLOR)
|
||||
|
||||
if frame is None:
|
||||
return None # Decode failed silently
|
||||
|
||||
return frame
|
||||
|
||||
except Exception:
|
||||
return None # Error reading frame silently
|
||||
|
||||
def _read_stderr(self):
|
||||
"""Read and log FFmpeg stderr output in background thread."""
|
||||
if not self.process or not self.process.stderr:
|
||||
return
|
||||
|
||||
try:
|
||||
while self.process and self.process.poll() is None:
|
||||
try:
|
||||
line = self.process.stderr.readline()
|
||||
if line:
|
||||
error_msg = line.decode('utf-8', errors='ignore').strip()
|
||||
if error_msg and not self.stop_event.is_set():
|
||||
# Filter out common noise but log actual errors
|
||||
if any(keyword in error_msg.lower() for keyword in ['error', 'failed', 'cannot', 'invalid']):
|
||||
log_error(self.camera_id, f"FFmpeg: {error_msg}")
|
||||
elif 'warning' in error_msg.lower():
|
||||
log_warning(self.camera_id, f"FFmpeg: {error_msg}")
|
||||
except Exception:
|
||||
break
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _check_watchdog_timeout(self) -> bool:
|
||||
"""Check if watchdog timeout has been exceeded."""
|
||||
if not self.process_start_time:
|
||||
return False
|
||||
|
||||
current_time = time.time()
|
||||
time_since_start = current_time - self.process_start_time
|
||||
|
||||
# Determine timeout based on whether this is a restart
|
||||
timeout = self.restart_timeout if self.is_restart else self.first_start_timeout
|
||||
|
||||
# If no frames received yet, check against process start time
|
||||
if not self.last_frame_time:
|
||||
if time_since_start > timeout:
|
||||
log_warning(self.camera_id, f"Watchdog timeout: No frames for {time_since_start:.1f}s (limit: {timeout}s)")
|
||||
return True
|
||||
else:
|
||||
# Check time since last frame
|
||||
time_since_frame = current_time - self.last_frame_time
|
||||
if time_since_frame > timeout:
|
||||
log_warning(self.camera_id, f"Watchdog timeout: No frames for {time_since_frame:.1f}s (limit: {timeout}s)")
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
def _restart_ffmpeg_process(self):
|
||||
"""Restart FFmpeg process due to watchdog timeout."""
|
||||
log_warning(self.camera_id, "Watchdog triggered FFmpeg restart")
|
||||
|
||||
# Terminate current process
|
||||
if self.process:
|
||||
try:
|
||||
self.process.terminate()
|
||||
self.process.wait(timeout=3)
|
||||
except subprocess.TimeoutExpired:
|
||||
self.process.kill()
|
||||
except Exception:
|
||||
pass
|
||||
self.process = None
|
||||
|
||||
# Mark as restart for shorter timeout
|
||||
self.is_restart = True
|
||||
|
||||
# Small delay before restart
|
||||
time.sleep(1.0)
|
||||
|
||||
def _read_frames(self):
|
||||
"""Read frames directly from FFmpeg stdout pipe."""
|
||||
frame_count = 0
|
||||
last_log_time = time.time()
|
||||
|
||||
while not self.stop_event.is_set():
|
||||
try:
|
||||
# Send heartbeat for thread health monitoring
|
||||
self._send_heartbeat("reading_frames")
|
||||
|
||||
# Check watchdog timeout if process is running
|
||||
if self.process and self.process.poll() is None:
|
||||
if self._check_watchdog_timeout():
|
||||
self._restart_ffmpeg_process()
|
||||
continue
|
||||
|
||||
# Start FFmpeg if not running
|
||||
if not self.process or self.process.poll() is not None:
|
||||
if self.process and self.process.poll() is not None:
|
||||
log_warning(self.camera_id, "Stream disconnected, reconnecting...")
|
||||
stream_health_tracker.report_error(
|
||||
self.camera_id,
|
||||
"FFmpeg process disconnected"
|
||||
)
|
||||
|
||||
if not self._start_ffmpeg_process():
|
||||
self.consecutive_errors += 1
|
||||
stream_health_tracker.report_error(
|
||||
self.camera_id,
|
||||
"Failed to start FFmpeg process"
|
||||
)
|
||||
time.sleep(5.0)
|
||||
continue
|
||||
|
||||
# Read frames directly from FFmpeg stdout
|
||||
try:
|
||||
if self.process and self.process.stdout:
|
||||
# Read BMP frame data
|
||||
frame = self._read_bmp_frame(self.process.stdout)
|
||||
if frame is None:
|
||||
continue
|
||||
|
||||
# Update watchdog - we got a frame
|
||||
self.last_frame_time = time.time()
|
||||
|
||||
# Reset error counter on successful frame
|
||||
self.consecutive_errors = 0
|
||||
|
||||
# Report successful frame to health monitoring
|
||||
frame_size = frame.nbytes
|
||||
stream_health_tracker.report_frame_received(self.camera_id, frame_size)
|
||||
|
||||
# Call frame callback
|
||||
if self.frame_callback:
|
||||
try:
|
||||
self.frame_callback(self.camera_id, frame)
|
||||
except Exception as e:
|
||||
stream_health_tracker.report_error(
|
||||
self.camera_id,
|
||||
f"Frame callback error: {e}"
|
||||
)
|
||||
|
||||
frame_count += 1
|
||||
|
||||
# Log progress every 60 seconds (quieter)
|
||||
current_time = time.time()
|
||||
if current_time - last_log_time >= 60:
|
||||
log_success(self.camera_id, f"{frame_count} frames captured ({frame.shape[1]}x{frame.shape[0]})")
|
||||
last_log_time = current_time
|
||||
|
||||
except Exception as e:
|
||||
# Process might have died, let it restart on next iteration
|
||||
stream_health_tracker.report_error(
|
||||
self.camera_id,
|
||||
f"Frame reading error: {e}"
|
||||
)
|
||||
if self.process:
|
||||
self.process.terminate()
|
||||
self.process = None
|
||||
time.sleep(1.0)
|
||||
|
||||
except Exception as e:
|
||||
stream_health_tracker.report_error(
|
||||
self.camera_id,
|
||||
f"Main loop error: {e}"
|
||||
)
|
||||
time.sleep(1.0)
|
||||
|
||||
# Cleanup
|
||||
if self.process:
|
||||
self.process.terminate()
|
||||
|
||||
# Health monitoring methods
|
||||
def _send_heartbeat(self, activity: str = "running"):
|
||||
"""Send heartbeat to thread health monitor."""
|
||||
self.last_heartbeat = time.time()
|
||||
thread_health_monitor.heartbeat(activity=activity)
|
||||
|
||||
def _heartbeat_callback(self) -> bool:
|
||||
"""Heartbeat callback for thread responsiveness testing."""
|
||||
try:
|
||||
# Check if thread is responsive by checking recent heartbeat
|
||||
current_time = time.time()
|
||||
age = current_time - self.last_heartbeat
|
||||
|
||||
# Thread is responsive if heartbeat is recent
|
||||
return age < 30.0 # 30 second responsiveness threshold
|
||||
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
def _handle_restart_recovery(self, component: str, details: Dict[str, Any]) -> bool:
|
||||
"""Handle restart recovery action."""
|
||||
try:
|
||||
log_info(self.camera_id, "Restarting FFmpeg RTSP reader for health recovery")
|
||||
|
||||
# Stop current instance
|
||||
self.stop()
|
||||
|
||||
# Small delay
|
||||
time.sleep(2.0)
|
||||
|
||||
# Restart
|
||||
self.start()
|
||||
|
||||
# Report successful restart
|
||||
stream_health_tracker.report_reconnect(self.camera_id, "health_recovery_restart")
|
||||
self.ffmpeg_restart_count += 1
|
||||
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
log_error(self.camera_id, f"Failed to restart FFmpeg RTSP reader: {e}")
|
||||
return False
|
||||
|
||||
def _handle_reconnect_recovery(self, component: str, details: Dict[str, Any]) -> bool:
|
||||
"""Handle reconnect recovery action."""
|
||||
try:
|
||||
log_info(self.camera_id, "Reconnecting FFmpeg RTSP reader for health recovery")
|
||||
|
||||
# Force restart FFmpeg process
|
||||
self._restart_ffmpeg_process()
|
||||
|
||||
# Reset error counters
|
||||
self.consecutive_errors = 0
|
||||
stream_health_tracker.report_reconnect(self.camera_id, "health_recovery_reconnect")
|
||||
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
log_error(self.camera_id, f"Failed to reconnect FFmpeg RTSP reader: {e}")
|
||||
return False
|
||||
|
|
@ -1,378 +0,0 @@
|
|||
"""
|
||||
HTTP snapshot reader optimized for 2560x1440 (2K) high quality images.
|
||||
Enhanced with comprehensive health monitoring and automatic recovery.
|
||||
"""
|
||||
import cv2
|
||||
import logging
|
||||
import time
|
||||
import threading
|
||||
import requests
|
||||
import numpy as np
|
||||
from typing import Optional, Callable, Dict, Any
|
||||
|
||||
from .base import VideoReader
|
||||
from .utils import log_success, log_warning, log_error, log_info
|
||||
from ...monitoring.stream_health import stream_health_tracker
|
||||
from ...monitoring.thread_health import thread_health_monitor
|
||||
from ...monitoring.recovery import recovery_manager, RecoveryAction
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class HTTPSnapshotReader(VideoReader):
|
||||
"""HTTP snapshot reader optimized for 2560x1440 (2K) high quality images."""
|
||||
|
||||
def __init__(self, camera_id: str, snapshot_url: str, interval_ms: int = 5000, max_retries: int = 3):
|
||||
super().__init__(camera_id, snapshot_url, max_retries)
|
||||
self.snapshot_url = snapshot_url
|
||||
self.interval_ms = interval_ms
|
||||
self.stop_event = threading.Event()
|
||||
self.thread = None
|
||||
|
||||
# Expected snapshot specifications
|
||||
self.expected_width = 2560
|
||||
self.expected_height = 1440
|
||||
self.max_file_size = 10 * 1024 * 1024 # 10MB max for 2K image
|
||||
|
||||
# Health monitoring setup
|
||||
self.last_heartbeat = time.time()
|
||||
self.consecutive_errors = 0
|
||||
self.connection_test_interval = 300 # Test connection every 5 minutes
|
||||
self.last_connection_test = None
|
||||
|
||||
# Register recovery handlers
|
||||
recovery_manager.register_recovery_handler(
|
||||
RecoveryAction.RESTART_STREAM,
|
||||
self._handle_restart_recovery
|
||||
)
|
||||
recovery_manager.register_recovery_handler(
|
||||
RecoveryAction.RECONNECT,
|
||||
self._handle_reconnect_recovery
|
||||
)
|
||||
|
||||
@property
|
||||
def is_running(self) -> bool:
|
||||
"""Check if the reader is currently running."""
|
||||
return self.thread is not None and self.thread.is_alive()
|
||||
|
||||
@property
|
||||
def reader_type(self) -> str:
|
||||
"""Get the type of reader."""
|
||||
return "http_snapshot"
|
||||
|
||||
def set_frame_callback(self, callback: Callable[[str, np.ndarray], None]):
|
||||
"""Set callback function to handle captured frames."""
|
||||
self.frame_callback = callback
|
||||
|
||||
def start(self):
|
||||
"""Start the snapshot reader thread."""
|
||||
if self.thread and self.thread.is_alive():
|
||||
logger.warning(f"Snapshot reader for {self.camera_id} already running")
|
||||
return
|
||||
|
||||
self.stop_event.clear()
|
||||
self.thread = threading.Thread(target=self._read_snapshots, daemon=True)
|
||||
self.thread.start()
|
||||
|
||||
# Register with health monitoring
|
||||
stream_health_tracker.register_stream(self.camera_id, "http_snapshot", self.snapshot_url)
|
||||
thread_health_monitor.register_thread(self.thread, self._heartbeat_callback)
|
||||
|
||||
logger.info(f"Started snapshot reader for camera {self.camera_id} with health monitoring")
|
||||
|
||||
def stop(self):
|
||||
"""Stop the snapshot reader thread."""
|
||||
self.stop_event.set()
|
||||
|
||||
# Unregister from health monitoring
|
||||
if self.thread:
|
||||
thread_health_monitor.unregister_thread(self.thread.ident)
|
||||
self.thread.join(timeout=5.0)
|
||||
|
||||
stream_health_tracker.unregister_stream(self.camera_id)
|
||||
|
||||
logger.info(f"Stopped snapshot reader for camera {self.camera_id}")
|
||||
|
||||
def _read_snapshots(self):
|
||||
"""Main snapshot reading loop for high quality 2K images."""
|
||||
retries = 0
|
||||
frame_count = 0
|
||||
last_log_time = time.time()
|
||||
last_connection_test = time.time()
|
||||
interval_seconds = self.interval_ms / 1000.0
|
||||
|
||||
logger.info(f"Snapshot interval for camera {self.camera_id}: {interval_seconds}s")
|
||||
|
||||
while not self.stop_event.is_set():
|
||||
try:
|
||||
# Send heartbeat for thread health monitoring
|
||||
self._send_heartbeat("fetching_snapshot")
|
||||
|
||||
start_time = time.time()
|
||||
frame = self._fetch_snapshot()
|
||||
|
||||
if frame is None:
|
||||
retries += 1
|
||||
self.consecutive_errors += 1
|
||||
|
||||
# Report error to health monitoring
|
||||
stream_health_tracker.report_error(
|
||||
self.camera_id,
|
||||
f"Failed to fetch snapshot (retry {retries}/{self.max_retries})"
|
||||
)
|
||||
|
||||
logger.warning(f"Failed to fetch snapshot for camera {self.camera_id}, retry {retries}/{self.max_retries}")
|
||||
|
||||
if self.max_retries != -1 and retries > self.max_retries:
|
||||
logger.error(f"Max retries reached for snapshot camera {self.camera_id}")
|
||||
break
|
||||
|
||||
time.sleep(min(2.0, interval_seconds))
|
||||
continue
|
||||
|
||||
# Accept any valid image dimensions - don't force specific resolution
|
||||
if frame.shape[1] <= 0 or frame.shape[0] <= 0:
|
||||
logger.warning(f"Camera {self.camera_id}: Invalid frame dimensions {frame.shape[1]}x{frame.shape[0]}")
|
||||
stream_health_tracker.report_error(
|
||||
self.camera_id,
|
||||
f"Invalid frame dimensions: {frame.shape[1]}x{frame.shape[0]}"
|
||||
)
|
||||
continue
|
||||
|
||||
# Reset retry counter on successful fetch
|
||||
retries = 0
|
||||
self.consecutive_errors = 0
|
||||
frame_count += 1
|
||||
|
||||
# Report successful frame to health monitoring
|
||||
frame_size = frame.nbytes
|
||||
stream_health_tracker.report_frame_received(self.camera_id, frame_size)
|
||||
|
||||
# Call frame callback
|
||||
if self.frame_callback:
|
||||
try:
|
||||
self.frame_callback(self.camera_id, frame)
|
||||
except Exception as e:
|
||||
logger.error(f"Camera {self.camera_id}: Frame callback error: {e}")
|
||||
stream_health_tracker.report_error(self.camera_id, f"Frame callback error: {e}")
|
||||
|
||||
# Periodic connection health test
|
||||
current_time = time.time()
|
||||
if current_time - last_connection_test >= self.connection_test_interval:
|
||||
self._test_connection_health()
|
||||
last_connection_test = current_time
|
||||
|
||||
# Log progress every 30 seconds
|
||||
if current_time - last_log_time >= 30:
|
||||
logger.info(f"Camera {self.camera_id}: {frame_count} snapshots processed")
|
||||
last_log_time = current_time
|
||||
|
||||
# Wait for next interval
|
||||
elapsed = time.time() - start_time
|
||||
sleep_time = max(0, interval_seconds - elapsed)
|
||||
if sleep_time > 0:
|
||||
self.stop_event.wait(sleep_time)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in snapshot loop for camera {self.camera_id}: {e}")
|
||||
stream_health_tracker.report_error(self.camera_id, f"Snapshot loop error: {e}")
|
||||
retries += 1
|
||||
if self.max_retries != -1 and retries > self.max_retries:
|
||||
break
|
||||
time.sleep(min(2.0, interval_seconds))
|
||||
|
||||
logger.info(f"Snapshot reader thread ended for camera {self.camera_id}")
|
||||
|
||||
def _fetch_snapshot(self) -> Optional[np.ndarray]:
|
||||
"""Fetch a single high quality snapshot from HTTP URL."""
|
||||
try:
|
||||
# Parse URL for authentication
|
||||
from urllib.parse import urlparse
|
||||
parsed_url = urlparse(self.snapshot_url)
|
||||
|
||||
headers = {
|
||||
'User-Agent': 'Python-Detector-Worker/1.0',
|
||||
'Accept': 'image/jpeg, image/png, image/*'
|
||||
}
|
||||
auth = None
|
||||
|
||||
if parsed_url.username and parsed_url.password:
|
||||
from requests.auth import HTTPBasicAuth, HTTPDigestAuth
|
||||
auth = HTTPBasicAuth(parsed_url.username, parsed_url.password)
|
||||
|
||||
# Reconstruct URL without credentials
|
||||
clean_url = f"{parsed_url.scheme}://{parsed_url.hostname}"
|
||||
if parsed_url.port:
|
||||
clean_url += f":{parsed_url.port}"
|
||||
clean_url += parsed_url.path
|
||||
if parsed_url.query:
|
||||
clean_url += f"?{parsed_url.query}"
|
||||
|
||||
# Try Basic Auth first
|
||||
response = requests.get(clean_url, auth=auth, timeout=15, headers=headers,
|
||||
stream=True, verify=False)
|
||||
|
||||
# If Basic Auth fails, try Digest Auth
|
||||
if response.status_code == 401:
|
||||
auth = HTTPDigestAuth(parsed_url.username, parsed_url.password)
|
||||
response = requests.get(clean_url, auth=auth, timeout=15, headers=headers,
|
||||
stream=True, verify=False)
|
||||
else:
|
||||
response = requests.get(self.snapshot_url, timeout=15, headers=headers,
|
||||
stream=True, verify=False)
|
||||
|
||||
if response.status_code == 200:
|
||||
# Check content size
|
||||
content_length = int(response.headers.get('content-length', 0))
|
||||
if content_length > self.max_file_size:
|
||||
logger.warning(f"Snapshot too large for camera {self.camera_id}: {content_length} bytes")
|
||||
return None
|
||||
|
||||
# Read content
|
||||
content = response.content
|
||||
|
||||
# Convert to numpy array
|
||||
image_array = np.frombuffer(content, np.uint8)
|
||||
|
||||
# Decode as high quality image
|
||||
frame = cv2.imdecode(image_array, cv2.IMREAD_COLOR)
|
||||
|
||||
if frame is None:
|
||||
logger.error(f"Failed to decode snapshot for camera {self.camera_id}")
|
||||
return None
|
||||
|
||||
logger.debug(f"Fetched snapshot for camera {self.camera_id}: {frame.shape[1]}x{frame.shape[0]}")
|
||||
return frame
|
||||
else:
|
||||
logger.warning(f"HTTP {response.status_code} from {self.camera_id}")
|
||||
return None
|
||||
|
||||
except requests.RequestException as e:
|
||||
logger.error(f"Request error fetching snapshot for {self.camera_id}: {e}")
|
||||
return None
|
||||
except Exception as e:
|
||||
logger.error(f"Error decoding snapshot for {self.camera_id}: {e}")
|
||||
return None
|
||||
|
||||
def fetch_single_snapshot(self) -> Optional[np.ndarray]:
|
||||
"""
|
||||
Fetch a single high-quality snapshot on demand for pipeline processing.
|
||||
This method is for one-time fetch from HTTP URL, not continuous streaming.
|
||||
|
||||
Returns:
|
||||
High quality 2K snapshot frame or None if failed
|
||||
"""
|
||||
logger.info(f"[SNAPSHOT] Fetching snapshot for {self.camera_id} from {self.snapshot_url}")
|
||||
|
||||
# Try to fetch snapshot with retries
|
||||
for attempt in range(self.max_retries):
|
||||
frame = self._fetch_snapshot()
|
||||
|
||||
if frame is not None:
|
||||
logger.info(f"[SNAPSHOT] Successfully fetched {frame.shape[1]}x{frame.shape[0]} snapshot for {self.camera_id}")
|
||||
return frame
|
||||
|
||||
if attempt < self.max_retries - 1:
|
||||
logger.warning(f"[SNAPSHOT] Attempt {attempt + 1}/{self.max_retries} failed for {self.camera_id}, retrying...")
|
||||
time.sleep(0.5)
|
||||
|
||||
logger.error(f"[SNAPSHOT] Failed to fetch snapshot for {self.camera_id} after {self.max_retries} attempts")
|
||||
return None
|
||||
|
||||
def _resize_maintain_aspect(self, frame: np.ndarray, target_width: int, target_height: int) -> np.ndarray:
|
||||
"""Resize image while maintaining aspect ratio for high quality."""
|
||||
h, w = frame.shape[:2]
|
||||
aspect = w / h
|
||||
target_aspect = target_width / target_height
|
||||
|
||||
if aspect > target_aspect:
|
||||
# Image is wider
|
||||
new_width = target_width
|
||||
new_height = int(target_width / aspect)
|
||||
else:
|
||||
# Image is taller
|
||||
new_height = target_height
|
||||
new_width = int(target_height * aspect)
|
||||
|
||||
# Use INTER_LANCZOS4 for high quality downsampling
|
||||
resized = cv2.resize(frame, (new_width, new_height), interpolation=cv2.INTER_LANCZOS4)
|
||||
|
||||
# Pad to target size if needed
|
||||
if new_width < target_width or new_height < target_height:
|
||||
top = (target_height - new_height) // 2
|
||||
bottom = target_height - new_height - top
|
||||
left = (target_width - new_width) // 2
|
||||
right = target_width - new_width - left
|
||||
resized = cv2.copyMakeBorder(resized, top, bottom, left, right, cv2.BORDER_CONSTANT, value=[0, 0, 0])
|
||||
|
||||
return resized
|
||||
|
||||
# Health monitoring methods
|
||||
def _send_heartbeat(self, activity: str = "running"):
|
||||
"""Send heartbeat to thread health monitor."""
|
||||
self.last_heartbeat = time.time()
|
||||
thread_health_monitor.heartbeat(activity=activity)
|
||||
|
||||
def _heartbeat_callback(self) -> bool:
|
||||
"""Heartbeat callback for thread responsiveness testing."""
|
||||
try:
|
||||
# Check if thread is responsive by checking recent heartbeat
|
||||
current_time = time.time()
|
||||
age = current_time - self.last_heartbeat
|
||||
|
||||
# Thread is responsive if heartbeat is recent
|
||||
return age < 30.0 # 30 second responsiveness threshold
|
||||
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
def _test_connection_health(self):
|
||||
"""Test HTTP connection health."""
|
||||
try:
|
||||
stream_health_tracker.test_http_connection(self.camera_id, self.snapshot_url)
|
||||
except Exception as e:
|
||||
logger.error(f"Error testing connection health for {self.camera_id}: {e}")
|
||||
|
||||
def _handle_restart_recovery(self, component: str, details: Dict[str, Any]) -> bool:
|
||||
"""Handle restart recovery action."""
|
||||
try:
|
||||
logger.info(f"Restarting HTTP snapshot reader for {self.camera_id}")
|
||||
|
||||
# Stop current instance
|
||||
self.stop()
|
||||
|
||||
# Small delay
|
||||
time.sleep(2.0)
|
||||
|
||||
# Restart
|
||||
self.start()
|
||||
|
||||
# Report successful restart
|
||||
stream_health_tracker.report_reconnect(self.camera_id, "health_recovery_restart")
|
||||
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to restart HTTP snapshot reader for {self.camera_id}: {e}")
|
||||
return False
|
||||
|
||||
def _handle_reconnect_recovery(self, component: str, details: Dict[str, Any]) -> bool:
|
||||
"""Handle reconnect recovery action."""
|
||||
try:
|
||||
logger.info(f"Reconnecting HTTP snapshot reader for {self.camera_id}")
|
||||
|
||||
# Test connection first
|
||||
success = stream_health_tracker.test_http_connection(self.camera_id, self.snapshot_url)
|
||||
|
||||
if success:
|
||||
# Reset error counters
|
||||
self.consecutive_errors = 0
|
||||
stream_health_tracker.report_reconnect(self.camera_id, "health_recovery_reconnect")
|
||||
return True
|
||||
else:
|
||||
logger.warning(f"Connection test failed during recovery for {self.camera_id}")
|
||||
return False
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to reconnect HTTP snapshot reader for {self.camera_id}: {e}")
|
||||
return False
|
||||
|
|
@ -1,38 +0,0 @@
|
|||
"""
|
||||
Utility functions for stream readers.
|
||||
"""
|
||||
import logging
|
||||
import os
|
||||
|
||||
# Keep OpenCV errors visible but allow FFmpeg stderr logging
|
||||
os.environ["OPENCV_LOG_LEVEL"] = "ERROR"
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Color codes for pretty logging
|
||||
class Colors:
|
||||
GREEN = '\033[92m'
|
||||
YELLOW = '\033[93m'
|
||||
RED = '\033[91m'
|
||||
BLUE = '\033[94m'
|
||||
PURPLE = '\033[95m'
|
||||
CYAN = '\033[96m'
|
||||
WHITE = '\033[97m'
|
||||
BOLD = '\033[1m'
|
||||
END = '\033[0m'
|
||||
|
||||
def log_success(camera_id: str, message: str):
|
||||
"""Log success messages in green"""
|
||||
logger.info(f"{Colors.GREEN}[{camera_id}] {message}{Colors.END}")
|
||||
|
||||
def log_warning(camera_id: str, message: str):
|
||||
"""Log warnings in yellow"""
|
||||
logger.warning(f"{Colors.YELLOW}[{camera_id}] {message}{Colors.END}")
|
||||
|
||||
def log_error(camera_id: str, message: str):
|
||||
"""Log errors in red"""
|
||||
logger.error(f"{Colors.RED}[{camera_id}] {message}{Colors.END}")
|
||||
|
||||
def log_info(camera_id: str, message: str):
|
||||
"""Log info in cyan"""
|
||||
logger.info(f"{Colors.CYAN}[{camera_id}] {message}{Colors.END}")
|
||||
|
|
@ -1,14 +0,0 @@
|
|||
# Tracking module for vehicle tracking and validation
|
||||
|
||||
from .tracker import VehicleTracker, TrackedVehicle
|
||||
from .validator import StableCarValidator, ValidationResult, VehicleState
|
||||
from .integration import TrackingPipelineIntegration
|
||||
|
||||
__all__ = [
|
||||
'VehicleTracker',
|
||||
'TrackedVehicle',
|
||||
'StableCarValidator',
|
||||
'ValidationResult',
|
||||
'VehicleState',
|
||||
'TrackingPipelineIntegration'
|
||||
]
|
||||
|
|
@ -1,408 +0,0 @@
|
|||
"""
|
||||
BoT-SORT Multi-Object Tracker with Camera Isolation
|
||||
Based on BoT-SORT: Robust Associations Multi-Pedestrian Tracking
|
||||
"""
|
||||
|
||||
import logging
|
||||
import time
|
||||
import numpy as np
|
||||
from typing import Dict, List, Optional, Tuple, Any
|
||||
from dataclasses import dataclass
|
||||
from scipy.optimize import linear_sum_assignment
|
||||
from filterpy.kalman import KalmanFilter
|
||||
import cv2
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@dataclass
|
||||
class TrackState:
|
||||
"""Track state enumeration"""
|
||||
TENTATIVE = "tentative" # New track, not confirmed yet
|
||||
CONFIRMED = "confirmed" # Confirmed track
|
||||
DELETED = "deleted" # Track to be deleted
|
||||
|
||||
|
||||
class Track:
|
||||
"""
|
||||
Individual track representation with Kalman filter for motion prediction
|
||||
"""
|
||||
|
||||
def __init__(self, detection, track_id: int, camera_id: str):
|
||||
"""
|
||||
Initialize a new track
|
||||
|
||||
Args:
|
||||
detection: Initial detection (bbox, confidence, class)
|
||||
track_id: Unique track identifier within camera
|
||||
camera_id: Camera identifier
|
||||
"""
|
||||
self.track_id = track_id
|
||||
self.camera_id = camera_id
|
||||
self.state = TrackState.TENTATIVE
|
||||
|
||||
# Time tracking
|
||||
self.start_time = time.time()
|
||||
self.last_update_time = time.time()
|
||||
|
||||
# Appearance and motion
|
||||
self.bbox = detection.bbox # [x1, y1, x2, y2]
|
||||
self.confidence = detection.confidence
|
||||
self.class_name = detection.class_name
|
||||
|
||||
# Track management
|
||||
self.hit_streak = 1
|
||||
self.time_since_update = 0
|
||||
self.age = 1
|
||||
|
||||
# Kalman filter for motion prediction
|
||||
self.kf = self._create_kalman_filter()
|
||||
self._update_kalman_filter(detection.bbox)
|
||||
|
||||
# Track history
|
||||
self.history = [detection.bbox]
|
||||
self.max_history = 10
|
||||
|
||||
def _create_kalman_filter(self) -> KalmanFilter:
|
||||
"""Create Kalman filter for bbox tracking (x, y, w, h, vx, vy, vw, vh)"""
|
||||
kf = KalmanFilter(dim_x=8, dim_z=4)
|
||||
|
||||
# State transition matrix (constant velocity model)
|
||||
kf.F = np.array([
|
||||
[1, 0, 0, 0, 1, 0, 0, 0],
|
||||
[0, 1, 0, 0, 0, 1, 0, 0],
|
||||
[0, 0, 1, 0, 0, 0, 1, 0],
|
||||
[0, 0, 0, 1, 0, 0, 0, 1],
|
||||
[0, 0, 0, 0, 1, 0, 0, 0],
|
||||
[0, 0, 0, 0, 0, 1, 0, 0],
|
||||
[0, 0, 0, 0, 0, 0, 1, 0],
|
||||
[0, 0, 0, 0, 0, 0, 0, 1]
|
||||
])
|
||||
|
||||
# Measurement matrix (observe x, y, w, h)
|
||||
kf.H = np.array([
|
||||
[1, 0, 0, 0, 0, 0, 0, 0],
|
||||
[0, 1, 0, 0, 0, 0, 0, 0],
|
||||
[0, 0, 1, 0, 0, 0, 0, 0],
|
||||
[0, 0, 0, 1, 0, 0, 0, 0]
|
||||
])
|
||||
|
||||
# Process noise
|
||||
kf.Q *= 0.01
|
||||
|
||||
# Measurement noise
|
||||
kf.R *= 10
|
||||
|
||||
# Initial covariance
|
||||
kf.P *= 100
|
||||
|
||||
return kf
|
||||
|
||||
def _update_kalman_filter(self, bbox: List[float]):
|
||||
"""Update Kalman filter with new bbox"""
|
||||
# Convert [x1, y1, x2, y2] to [cx, cy, w, h]
|
||||
x1, y1, x2, y2 = bbox
|
||||
cx = (x1 + x2) / 2
|
||||
cy = (y1 + y2) / 2
|
||||
w = x2 - x1
|
||||
h = y2 - y1
|
||||
|
||||
# Properly assign to column vector
|
||||
self.kf.x[:4, 0] = [cx, cy, w, h]
|
||||
|
||||
def predict(self) -> np.ndarray:
|
||||
"""Predict next position using Kalman filter"""
|
||||
self.kf.predict()
|
||||
|
||||
# Convert back to [x1, y1, x2, y2] format
|
||||
cx, cy, w, h = self.kf.x[:4, 0] # Extract from column vector
|
||||
x1 = cx - w/2
|
||||
y1 = cy - h/2
|
||||
x2 = cx + w/2
|
||||
y2 = cy + h/2
|
||||
|
||||
return np.array([x1, y1, x2, y2])
|
||||
|
||||
def update(self, detection):
|
||||
"""Update track with new detection"""
|
||||
self.last_update_time = time.time()
|
||||
self.time_since_update = 0
|
||||
self.hit_streak += 1
|
||||
self.age += 1
|
||||
|
||||
# Update track properties
|
||||
self.bbox = detection.bbox
|
||||
self.confidence = detection.confidence
|
||||
|
||||
# Update Kalman filter
|
||||
x1, y1, x2, y2 = detection.bbox
|
||||
cx = (x1 + x2) / 2
|
||||
cy = (y1 + y2) / 2
|
||||
w = x2 - x1
|
||||
h = y2 - y1
|
||||
|
||||
self.kf.update([cx, cy, w, h])
|
||||
|
||||
# Update history
|
||||
self.history.append(detection.bbox)
|
||||
if len(self.history) > self.max_history:
|
||||
self.history.pop(0)
|
||||
|
||||
# Update state
|
||||
if self.state == TrackState.TENTATIVE and self.hit_streak >= 3:
|
||||
self.state = TrackState.CONFIRMED
|
||||
|
||||
def mark_missed(self):
|
||||
"""Mark track as missed in this frame"""
|
||||
self.time_since_update += 1
|
||||
self.age += 1
|
||||
|
||||
if self.time_since_update > 5: # Delete after 5 missed frames
|
||||
self.state = TrackState.DELETED
|
||||
|
||||
def is_confirmed(self) -> bool:
|
||||
"""Check if track is confirmed"""
|
||||
return self.state == TrackState.CONFIRMED
|
||||
|
||||
def is_deleted(self) -> bool:
|
||||
"""Check if track should be deleted"""
|
||||
return self.state == TrackState.DELETED
|
||||
|
||||
|
||||
class CameraTracker:
|
||||
"""
|
||||
BoT-SORT tracker for a single camera
|
||||
"""
|
||||
|
||||
def __init__(self, camera_id: str, max_disappeared: int = 10):
|
||||
"""
|
||||
Initialize camera tracker
|
||||
|
||||
Args:
|
||||
camera_id: Unique camera identifier
|
||||
max_disappeared: Maximum frames a track can be missed before deletion
|
||||
"""
|
||||
self.camera_id = camera_id
|
||||
self.max_disappeared = max_disappeared
|
||||
|
||||
# Track management
|
||||
self.tracks: Dict[int, Track] = {}
|
||||
self.next_id = 1
|
||||
self.frame_count = 0
|
||||
|
||||
logger.info(f"Initialized BoT-SORT tracker for camera {camera_id}")
|
||||
|
||||
def update(self, detections: List) -> List[Track]:
|
||||
"""
|
||||
Update tracker with new detections
|
||||
|
||||
Args:
|
||||
detections: List of Detection objects
|
||||
|
||||
Returns:
|
||||
List of active confirmed tracks
|
||||
"""
|
||||
self.frame_count += 1
|
||||
|
||||
# Predict all existing tracks
|
||||
for track in self.tracks.values():
|
||||
track.predict()
|
||||
|
||||
# Associate detections to tracks
|
||||
matched_tracks, unmatched_detections, unmatched_tracks = self._associate(detections)
|
||||
|
||||
# Update matched tracks
|
||||
for track_id, detection in matched_tracks:
|
||||
self.tracks[track_id].update(detection)
|
||||
|
||||
# Mark unmatched tracks as missed
|
||||
for track_id in unmatched_tracks:
|
||||
self.tracks[track_id].mark_missed()
|
||||
|
||||
# Create new tracks for unmatched detections
|
||||
for detection in unmatched_detections:
|
||||
track = Track(detection, self.next_id, self.camera_id)
|
||||
self.tracks[self.next_id] = track
|
||||
self.next_id += 1
|
||||
|
||||
# Remove deleted tracks
|
||||
tracks_to_remove = [tid for tid, track in self.tracks.items() if track.is_deleted()]
|
||||
for tid in tracks_to_remove:
|
||||
del self.tracks[tid]
|
||||
|
||||
# Return confirmed tracks
|
||||
confirmed_tracks = [track for track in self.tracks.values() if track.is_confirmed()]
|
||||
|
||||
return confirmed_tracks
|
||||
|
||||
def _associate(self, detections: List) -> Tuple[List[Tuple[int, Any]], List[Any], List[int]]:
|
||||
"""
|
||||
Associate detections to existing tracks using IoU distance
|
||||
|
||||
Returns:
|
||||
(matched_tracks, unmatched_detections, unmatched_tracks)
|
||||
"""
|
||||
if not detections or not self.tracks:
|
||||
return [], detections, list(self.tracks.keys())
|
||||
|
||||
# Calculate IoU distance matrix
|
||||
track_ids = list(self.tracks.keys())
|
||||
cost_matrix = np.zeros((len(track_ids), len(detections)))
|
||||
|
||||
for i, track_id in enumerate(track_ids):
|
||||
track = self.tracks[track_id]
|
||||
predicted_bbox = track.predict()
|
||||
|
||||
for j, detection in enumerate(detections):
|
||||
iou = self._calculate_iou(predicted_bbox, detection.bbox)
|
||||
cost_matrix[i, j] = 1 - iou # Convert IoU to distance
|
||||
|
||||
# Solve assignment problem
|
||||
row_indices, col_indices = linear_sum_assignment(cost_matrix)
|
||||
|
||||
# Filter matches by IoU threshold
|
||||
iou_threshold = 0.3
|
||||
matched_tracks = []
|
||||
matched_detection_indices = set()
|
||||
matched_track_indices = set()
|
||||
|
||||
for row, col in zip(row_indices, col_indices):
|
||||
if cost_matrix[row, col] <= (1 - iou_threshold):
|
||||
track_id = track_ids[row]
|
||||
detection = detections[col]
|
||||
matched_tracks.append((track_id, detection))
|
||||
matched_detection_indices.add(col)
|
||||
matched_track_indices.add(row)
|
||||
|
||||
# Find unmatched detections and tracks
|
||||
unmatched_detections = [detections[i] for i in range(len(detections))
|
||||
if i not in matched_detection_indices]
|
||||
unmatched_tracks = [track_ids[i] for i in range(len(track_ids))
|
||||
if i not in matched_track_indices]
|
||||
|
||||
return matched_tracks, unmatched_detections, unmatched_tracks
|
||||
|
||||
def _calculate_iou(self, bbox1: np.ndarray, bbox2: List[float]) -> float:
|
||||
"""Calculate IoU between two bounding boxes"""
|
||||
x1_1, y1_1, x2_1, y2_1 = bbox1
|
||||
x1_2, y1_2, x2_2, y2_2 = bbox2
|
||||
|
||||
# Calculate intersection area
|
||||
x1_i = max(x1_1, x1_2)
|
||||
y1_i = max(y1_1, y1_2)
|
||||
x2_i = min(x2_1, x2_2)
|
||||
y2_i = min(y2_1, y2_2)
|
||||
|
||||
if x2_i <= x1_i or y2_i <= y1_i:
|
||||
return 0.0
|
||||
|
||||
intersection = (x2_i - x1_i) * (y2_i - y1_i)
|
||||
|
||||
# Calculate union area
|
||||
area1 = (x2_1 - x1_1) * (y2_1 - y1_1)
|
||||
area2 = (x2_2 - x1_2) * (y2_2 - y1_2)
|
||||
union = area1 + area2 - intersection
|
||||
|
||||
return intersection / union if union > 0 else 0.0
|
||||
|
||||
|
||||
class MultiCameraBoTSORT:
|
||||
"""
|
||||
Multi-camera BoT-SORT tracker with complete camera isolation
|
||||
"""
|
||||
|
||||
def __init__(self, trigger_classes: List[str], min_confidence: float = 0.6):
|
||||
"""
|
||||
Initialize multi-camera tracker
|
||||
|
||||
Args:
|
||||
trigger_classes: List of class names to track
|
||||
min_confidence: Minimum detection confidence threshold
|
||||
"""
|
||||
self.trigger_classes = trigger_classes
|
||||
self.min_confidence = min_confidence
|
||||
|
||||
# Camera-specific trackers
|
||||
self.camera_trackers: Dict[str, CameraTracker] = {}
|
||||
|
||||
logger.info(f"Initialized MultiCameraBoTSORT with classes={trigger_classes}, "
|
||||
f"min_confidence={min_confidence}")
|
||||
|
||||
def get_or_create_tracker(self, camera_id: str) -> CameraTracker:
|
||||
"""Get or create tracker for specific camera"""
|
||||
if camera_id not in self.camera_trackers:
|
||||
self.camera_trackers[camera_id] = CameraTracker(camera_id)
|
||||
logger.info(f"Created new tracker for camera {camera_id}")
|
||||
|
||||
return self.camera_trackers[camera_id]
|
||||
|
||||
def update(self, camera_id: str, inference_result) -> List[Dict]:
|
||||
"""
|
||||
Update tracker for specific camera with detections
|
||||
|
||||
Args:
|
||||
camera_id: Camera identifier
|
||||
inference_result: InferenceResult with detections
|
||||
|
||||
Returns:
|
||||
List of track information dictionaries
|
||||
"""
|
||||
# Filter detections by confidence and trigger classes
|
||||
filtered_detections = []
|
||||
|
||||
if hasattr(inference_result, 'detections') and inference_result.detections:
|
||||
for detection in inference_result.detections:
|
||||
if (detection.confidence >= self.min_confidence and
|
||||
detection.class_name in self.trigger_classes):
|
||||
filtered_detections.append(detection)
|
||||
|
||||
# Get camera tracker and update
|
||||
tracker = self.get_or_create_tracker(camera_id)
|
||||
confirmed_tracks = tracker.update(filtered_detections)
|
||||
|
||||
# Convert tracks to output format
|
||||
track_results = []
|
||||
for track in confirmed_tracks:
|
||||
track_results.append({
|
||||
'track_id': track.track_id,
|
||||
'camera_id': track.camera_id,
|
||||
'bbox': track.bbox,
|
||||
'confidence': track.confidence,
|
||||
'class_name': track.class_name,
|
||||
'hit_streak': track.hit_streak,
|
||||
'age': track.age
|
||||
})
|
||||
|
||||
return track_results
|
||||
|
||||
def get_statistics(self) -> Dict[str, Any]:
|
||||
"""Get tracking statistics across all cameras"""
|
||||
stats = {}
|
||||
total_tracks = 0
|
||||
|
||||
for camera_id, tracker in self.camera_trackers.items():
|
||||
camera_stats = {
|
||||
'active_tracks': len([t for t in tracker.tracks.values() if t.is_confirmed()]),
|
||||
'total_tracks': len(tracker.tracks),
|
||||
'frame_count': tracker.frame_count
|
||||
}
|
||||
stats[camera_id] = camera_stats
|
||||
total_tracks += camera_stats['active_tracks']
|
||||
|
||||
stats['summary'] = {
|
||||
'total_cameras': len(self.camera_trackers),
|
||||
'total_active_tracks': total_tracks
|
||||
}
|
||||
|
||||
return stats
|
||||
|
||||
def reset_camera(self, camera_id: str):
|
||||
"""Reset tracking for specific camera"""
|
||||
if camera_id in self.camera_trackers:
|
||||
del self.camera_trackers[camera_id]
|
||||
logger.info(f"Reset tracking for camera {camera_id}")
|
||||
|
||||
def reset_all(self):
|
||||
"""Reset all camera trackers"""
|
||||
self.camera_trackers.clear()
|
||||
logger.info("Reset all camera trackers")
|
||||
|
|
@ -1,858 +0,0 @@
|
|||
"""
|
||||
Tracking-Pipeline Integration Module.
|
||||
Connects the tracking system with the main detection pipeline and manages the flow.
|
||||
"""
|
||||
import logging
|
||||
import time
|
||||
import uuid
|
||||
from typing import Dict, Optional, Any, List, Tuple
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
import asyncio
|
||||
import numpy as np
|
||||
|
||||
from .tracker import VehicleTracker, TrackedVehicle
|
||||
from .validator import StableCarValidator
|
||||
from ..models.inference import YOLOWrapper
|
||||
from ..models.pipeline import PipelineParser
|
||||
from ..detection.pipeline import DetectionPipeline
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class TrackingPipelineIntegration:
|
||||
"""
|
||||
Integrates vehicle tracking with the detection pipeline.
|
||||
Manages tracking state transitions and pipeline execution triggers.
|
||||
"""
|
||||
|
||||
def __init__(self, pipeline_parser: PipelineParser, model_manager: Any, model_id: int, message_sender=None):
|
||||
"""
|
||||
Initialize tracking-pipeline integration.
|
||||
|
||||
Args:
|
||||
pipeline_parser: Pipeline parser with loaded configuration
|
||||
model_manager: Model manager for loading models
|
||||
model_id: The model ID to use for loading models
|
||||
message_sender: Optional callback function for sending WebSocket messages
|
||||
"""
|
||||
self.pipeline_parser = pipeline_parser
|
||||
self.model_manager = model_manager
|
||||
self.model_id = model_id
|
||||
self.message_sender = message_sender
|
||||
|
||||
# Store subscription info for snapshot access
|
||||
self.subscription_info = None
|
||||
|
||||
# Initialize tracking components
|
||||
tracking_config = pipeline_parser.tracking_config.__dict__ if pipeline_parser.tracking_config else {}
|
||||
self.tracker = VehicleTracker(tracking_config)
|
||||
self.validator = StableCarValidator()
|
||||
|
||||
# Tracking model
|
||||
self.tracking_model: Optional[YOLOWrapper] = None
|
||||
self.tracking_model_id = None
|
||||
|
||||
# Detection pipeline (Phase 5)
|
||||
self.detection_pipeline: Optional[DetectionPipeline] = None
|
||||
|
||||
# Session management
|
||||
self.active_sessions: Dict[str, str] = {} # display_id -> session_id
|
||||
self.session_vehicles: Dict[str, int] = {} # session_id -> track_id
|
||||
self.cleared_sessions: Dict[str, float] = {} # session_id -> clear_time
|
||||
self.pending_vehicles: Dict[str, int] = {} # display_id -> track_id (waiting for session ID)
|
||||
self.pending_processing_data: Dict[str, Dict] = {} # display_id -> processing data (waiting for session ID)
|
||||
self.display_to_subscription: Dict[str, str] = {} # display_id -> subscription_id (for fallback)
|
||||
|
||||
# Additional validators for enhanced flow control
|
||||
self.permanently_processed: Dict[str, float] = {} # "camera_id:track_id" -> process_time (never process again)
|
||||
self.progression_stages: Dict[str, str] = {} # session_id -> current_stage
|
||||
self.last_detection_time: Dict[str, float] = {} # display_id -> last_detection_timestamp
|
||||
self.abandonment_timeout = 3.0 # seconds to wait before declaring car abandoned
|
||||
|
||||
# Thread pool for pipeline execution
|
||||
self.executor = ThreadPoolExecutor(max_workers=2)
|
||||
|
||||
# Min bbox filtering configuration
|
||||
# TODO: Make this configurable via pipeline.json in the future
|
||||
self.min_bbox_area_percentage = 3.5 # 3.5% of frame area minimum
|
||||
|
||||
# Statistics
|
||||
self.stats = {
|
||||
'frames_processed': 0,
|
||||
'vehicles_detected': 0,
|
||||
'vehicles_validated': 0,
|
||||
'pipelines_executed': 0,
|
||||
'frontals_filtered_small': 0 # Track filtered detections
|
||||
}
|
||||
|
||||
|
||||
logger.info("TrackingPipelineIntegration initialized")
|
||||
|
||||
async def initialize_tracking_model(self) -> bool:
|
||||
"""
|
||||
Load and initialize the tracking model.
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
try:
|
||||
if not self.pipeline_parser.tracking_config:
|
||||
logger.warning("No tracking configuration found in pipeline")
|
||||
return False
|
||||
|
||||
model_file = self.pipeline_parser.tracking_config.model_file
|
||||
model_id = self.pipeline_parser.tracking_config.model_id
|
||||
|
||||
if not model_file:
|
||||
logger.warning("No tracking model file specified")
|
||||
return False
|
||||
|
||||
# Load tracking model
|
||||
logger.info(f"Loading tracking model: {model_id} ({model_file})")
|
||||
self.tracking_model = self.model_manager.get_yolo_model(self.model_id, model_file)
|
||||
if not self.tracking_model:
|
||||
logger.error(f"Failed to load tracking model {model_file} from model {self.model_id}")
|
||||
return False
|
||||
self.tracking_model_id = model_id
|
||||
|
||||
if self.tracking_model:
|
||||
logger.info(f"Tracking model {model_id} loaded successfully")
|
||||
|
||||
# Initialize detection pipeline (Phase 5)
|
||||
await self._initialize_detection_pipeline()
|
||||
|
||||
return True
|
||||
else:
|
||||
logger.error(f"Failed to load tracking model {model_id}")
|
||||
return False
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error initializing tracking model: {e}", exc_info=True)
|
||||
return False
|
||||
|
||||
async def _initialize_detection_pipeline(self) -> bool:
|
||||
"""
|
||||
Initialize the detection pipeline for main detection processing.
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
try:
|
||||
if not self.pipeline_parser:
|
||||
logger.warning("No pipeline parser available for detection pipeline")
|
||||
return False
|
||||
|
||||
# Create detection pipeline with message sender capability
|
||||
self.detection_pipeline = DetectionPipeline(self.pipeline_parser, self.model_manager, self.model_id, self.message_sender)
|
||||
|
||||
# Initialize detection pipeline
|
||||
if await self.detection_pipeline.initialize():
|
||||
logger.info("Detection pipeline initialized successfully")
|
||||
return True
|
||||
else:
|
||||
logger.error("Failed to initialize detection pipeline")
|
||||
return False
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error initializing detection pipeline: {e}", exc_info=True)
|
||||
return False
|
||||
|
||||
async def process_frame(self,
|
||||
frame: np.ndarray,
|
||||
display_id: str,
|
||||
subscription_id: str,
|
||||
session_id: Optional[str] = None) -> Dict[str, Any]:
|
||||
"""
|
||||
Process a frame through tracking and potentially the detection pipeline.
|
||||
|
||||
Args:
|
||||
frame: Input frame to process
|
||||
display_id: Display identifier
|
||||
subscription_id: Full subscription identifier
|
||||
session_id: Optional session ID from backend
|
||||
|
||||
Returns:
|
||||
Dictionary with processing results
|
||||
"""
|
||||
start_time = time.time()
|
||||
result = {
|
||||
'tracked_vehicles': [],
|
||||
'validated_vehicle': None,
|
||||
'pipeline_result': None,
|
||||
'session_id': session_id,
|
||||
'processing_time': 0.0
|
||||
}
|
||||
|
||||
try:
|
||||
# Update stats
|
||||
self.stats['frames_processed'] += 1
|
||||
|
||||
# Run tracking model
|
||||
if self.tracking_model:
|
||||
# Run detection-only (tracking handled by our own tracker)
|
||||
tracking_results = self.tracking_model.track(
|
||||
frame,
|
||||
confidence_threshold=self.tracker.min_confidence,
|
||||
trigger_classes=self.tracker.trigger_classes,
|
||||
persist=True
|
||||
)
|
||||
|
||||
# Debug: Log raw detection results
|
||||
if tracking_results and hasattr(tracking_results, 'detections'):
|
||||
raw_detections = len(tracking_results.detections)
|
||||
if raw_detections > 0:
|
||||
class_names = [detection.class_name for detection in tracking_results.detections]
|
||||
logger.debug(f"Raw detections: {raw_detections}, classes: {class_names}")
|
||||
else:
|
||||
logger.debug(f"No raw detections found")
|
||||
else:
|
||||
logger.debug(f"No tracking results or detections attribute")
|
||||
|
||||
# Filter out small frontal detections (neighboring pumps/distant cars)
|
||||
if tracking_results and hasattr(tracking_results, 'detections'):
|
||||
tracking_results = self._filter_small_frontals(tracking_results, frame)
|
||||
|
||||
# Process tracking results
|
||||
tracked_vehicles = self.tracker.process_detections(
|
||||
tracking_results,
|
||||
display_id,
|
||||
frame
|
||||
)
|
||||
|
||||
# Update last detection time for abandonment detection
|
||||
# Update when vehicles ARE detected, so when they leave, timestamp ages
|
||||
if tracked_vehicles:
|
||||
self.last_detection_time[display_id] = time.time()
|
||||
logger.debug(f"Updated last_detection_time for {display_id}: {len(tracked_vehicles)} vehicles")
|
||||
|
||||
# Check for car abandonment (vehicle left after getting car_wait_staff stage)
|
||||
await self._check_car_abandonment(display_id, subscription_id)
|
||||
|
||||
result['tracked_vehicles'] = [
|
||||
{
|
||||
'track_id': v.track_id,
|
||||
'bbox': v.bbox,
|
||||
'confidence': v.confidence,
|
||||
'is_stable': v.is_stable,
|
||||
'session_id': v.session_id
|
||||
}
|
||||
for v in tracked_vehicles
|
||||
]
|
||||
|
||||
# Log tracking info periodically
|
||||
if self.stats['frames_processed'] % 30 == 0: # Every 30 frames
|
||||
logger.debug(f"Tracking: {len(tracked_vehicles)} vehicles, "
|
||||
f"display={display_id}")
|
||||
|
||||
# Get stable vehicles for validation
|
||||
stable_vehicles = self.tracker.get_stable_vehicles(display_id)
|
||||
|
||||
# Validate and potentially process stable vehicles
|
||||
for vehicle in stable_vehicles:
|
||||
# Check if vehicle is already processed or has session
|
||||
if vehicle.processed_pipeline:
|
||||
continue
|
||||
|
||||
# Check for session cleared (post-fueling)
|
||||
if session_id and vehicle.session_id == session_id:
|
||||
# Same vehicle with same session, skip
|
||||
continue
|
||||
|
||||
# Check if this was a recently cleared session
|
||||
session_cleared = False
|
||||
if vehicle.session_id in self.cleared_sessions:
|
||||
clear_time = self.cleared_sessions[vehicle.session_id]
|
||||
if (time.time() - clear_time) < 30: # 30 second cooldown
|
||||
session_cleared = True
|
||||
|
||||
# Skip same car after session clear or if permanently processed
|
||||
if self.validator.should_skip_same_car(vehicle, session_cleared, self.permanently_processed):
|
||||
continue
|
||||
|
||||
# Validate vehicle
|
||||
validation_result = self.validator.validate_vehicle(vehicle, frame.shape)
|
||||
|
||||
if validation_result.is_valid and validation_result.should_process:
|
||||
logger.info(f"Vehicle {vehicle.track_id} validated for processing: "
|
||||
f"{validation_result.reason}")
|
||||
|
||||
result['validated_vehicle'] = {
|
||||
'track_id': vehicle.track_id,
|
||||
'state': validation_result.state.value,
|
||||
'confidence': validation_result.confidence
|
||||
}
|
||||
|
||||
# Execute detection pipeline - this will send real imageDetection when detection is found
|
||||
|
||||
# Mark vehicle as pending session ID assignment
|
||||
self.pending_vehicles[display_id] = vehicle.track_id
|
||||
logger.info(f"Vehicle {vehicle.track_id} waiting for session ID from backend")
|
||||
|
||||
# Execute detection pipeline (placeholder for Phase 5)
|
||||
pipeline_result = await self._execute_pipeline(
|
||||
frame,
|
||||
vehicle,
|
||||
display_id,
|
||||
None, # No session ID yet
|
||||
subscription_id
|
||||
)
|
||||
|
||||
result['pipeline_result'] = pipeline_result
|
||||
# No session_id in result yet - backend will provide it
|
||||
self.stats['pipelines_executed'] += 1
|
||||
|
||||
# Only process one vehicle per frame
|
||||
break
|
||||
|
||||
self.stats['vehicles_detected'] = len(tracked_vehicles)
|
||||
self.stats['vehicles_validated'] = len(stable_vehicles)
|
||||
|
||||
else:
|
||||
logger.warning("No tracking model available")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in tracking pipeline: {e}", exc_info=True)
|
||||
|
||||
|
||||
result['processing_time'] = time.time() - start_time
|
||||
return result
|
||||
|
||||
async def _execute_pipeline(self,
|
||||
frame: np.ndarray,
|
||||
vehicle: TrackedVehicle,
|
||||
display_id: str,
|
||||
session_id: str,
|
||||
subscription_id: str) -> Dict[str, Any]:
|
||||
"""
|
||||
Execute the main detection pipeline for a validated vehicle.
|
||||
|
||||
Args:
|
||||
frame: Input frame
|
||||
vehicle: Validated tracked vehicle
|
||||
display_id: Display identifier
|
||||
session_id: Session identifier
|
||||
subscription_id: Full subscription identifier
|
||||
|
||||
Returns:
|
||||
Pipeline execution results
|
||||
"""
|
||||
logger.info(f"Executing detection pipeline for vehicle {vehicle.track_id}, "
|
||||
f"session={session_id}, display={display_id}")
|
||||
|
||||
try:
|
||||
# Check if detection pipeline is available
|
||||
if not self.detection_pipeline:
|
||||
logger.warning("Detection pipeline not initialized, using fallback")
|
||||
return {
|
||||
'status': 'error',
|
||||
'message': 'Detection pipeline not available',
|
||||
'vehicle_id': vehicle.track_id,
|
||||
'session_id': session_id
|
||||
}
|
||||
|
||||
# Execute only the detection phase (first phase)
|
||||
# This will run detection and send imageDetection message to backend
|
||||
detection_result = await self.detection_pipeline.execute_detection_phase(
|
||||
frame=frame,
|
||||
display_id=display_id,
|
||||
subscription_id=subscription_id
|
||||
)
|
||||
|
||||
# Add vehicle information to result
|
||||
detection_result['vehicle_id'] = vehicle.track_id
|
||||
detection_result['vehicle_bbox'] = vehicle.bbox
|
||||
detection_result['vehicle_confidence'] = vehicle.confidence
|
||||
detection_result['phase'] = 'detection'
|
||||
|
||||
logger.info(f"Detection phase executed for vehicle {vehicle.track_id}: "
|
||||
f"status={detection_result.get('status', 'unknown')}, "
|
||||
f"message_sent={detection_result.get('message_sent', False)}, "
|
||||
f"processing_time={detection_result.get('processing_time', 0):.3f}s")
|
||||
|
||||
# Store frame and detection results for processing phase
|
||||
if detection_result['message_sent']:
|
||||
# Store for later processing when sessionId is received
|
||||
self.pending_processing_data[display_id] = {
|
||||
'frame': frame.copy(), # Store copy of frame for processing phase
|
||||
'vehicle': vehicle,
|
||||
'subscription_id': subscription_id,
|
||||
'detection_result': detection_result,
|
||||
'timestamp': time.time()
|
||||
}
|
||||
logger.info(f"Stored processing data for {display_id}, waiting for sessionId from backend")
|
||||
|
||||
return detection_result
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error executing detection pipeline: {e}", exc_info=True)
|
||||
return {
|
||||
'status': 'error',
|
||||
'message': str(e),
|
||||
'vehicle_id': vehicle.track_id,
|
||||
'session_id': session_id,
|
||||
'processing_time': 0.0
|
||||
}
|
||||
|
||||
async def _execute_processing_phase(self,
|
||||
processing_data: Dict[str, Any],
|
||||
session_id: str,
|
||||
display_id: str) -> None:
|
||||
"""
|
||||
Execute the processing phase after receiving sessionId from backend.
|
||||
This includes branch processing and database operations.
|
||||
|
||||
Args:
|
||||
processing_data: Stored processing data from detection phase
|
||||
session_id: Session ID from backend
|
||||
display_id: Display identifier
|
||||
"""
|
||||
try:
|
||||
vehicle = processing_data['vehicle']
|
||||
subscription_id = processing_data['subscription_id']
|
||||
detection_result = processing_data['detection_result']
|
||||
|
||||
logger.info(f"Executing processing phase for session {session_id}, vehicle {vehicle.track_id}")
|
||||
|
||||
# Capture high-quality snapshot for pipeline processing
|
||||
logger.info(f"[PROCESSING PHASE] Fetching 2K snapshot for session {session_id}")
|
||||
frame = self._fetch_snapshot()
|
||||
|
||||
if frame is None:
|
||||
logger.warning(f"[PROCESSING PHASE] Failed to capture snapshot, falling back to RTSP frame")
|
||||
# Fall back to RTSP frame if snapshot fails
|
||||
frame = processing_data['frame']
|
||||
|
||||
# Extract detected regions from detection phase result if available
|
||||
detected_regions = detection_result.get('detected_regions', {})
|
||||
logger.info(f"[INTEGRATION] Passing detected_regions to processing phase: {list(detected_regions.keys())}")
|
||||
|
||||
# Execute processing phase with detection pipeline
|
||||
if self.detection_pipeline:
|
||||
processing_result = await self.detection_pipeline.execute_processing_phase(
|
||||
frame=frame,
|
||||
display_id=display_id,
|
||||
session_id=session_id,
|
||||
subscription_id=subscription_id,
|
||||
detected_regions=detected_regions
|
||||
)
|
||||
|
||||
logger.info(f"Processing phase completed for session {session_id}: "
|
||||
f"status={processing_result.get('status', 'unknown')}, "
|
||||
f"branches={len(processing_result.get('branch_results', {}))}, "
|
||||
f"actions={len(processing_result.get('actions_executed', []))}, "
|
||||
f"processing_time={processing_result.get('processing_time', 0):.3f}s")
|
||||
|
||||
# Update stats
|
||||
self.stats['pipelines_executed'] += 1
|
||||
|
||||
else:
|
||||
logger.error("Detection pipeline not available for processing phase")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in processing phase for session {session_id}: {e}", exc_info=True)
|
||||
|
||||
|
||||
def set_subscription_info(self, subscription_info):
|
||||
"""
|
||||
Set subscription info to access snapshot URL and other stream details.
|
||||
|
||||
Args:
|
||||
subscription_info: SubscriptionInfo object containing stream config
|
||||
"""
|
||||
self.subscription_info = subscription_info
|
||||
logger.debug(f"Set subscription info with snapshot_url: {subscription_info.stream_config.snapshot_url if subscription_info else None}")
|
||||
|
||||
def set_session_id(self, display_id: str, session_id: str, subscription_id: str = None):
|
||||
"""
|
||||
Set session ID for a display (from backend).
|
||||
This is called when backend sends setSessionId after receiving imageDetection.
|
||||
|
||||
Args:
|
||||
display_id: Display identifier
|
||||
session_id: Session identifier
|
||||
subscription_id: Subscription identifier (displayId;cameraId) - needed for fallback
|
||||
"""
|
||||
# Ensure session_id is always a string for consistent type handling
|
||||
session_id = str(session_id) if session_id is not None else None
|
||||
self.active_sessions[display_id] = session_id
|
||||
|
||||
# Store subscription_id for fallback usage
|
||||
if subscription_id:
|
||||
self.display_to_subscription[display_id] = subscription_id
|
||||
logger.info(f"Set session {session_id} for display {display_id} with subscription {subscription_id}")
|
||||
else:
|
||||
logger.info(f"Set session {session_id} for display {display_id}")
|
||||
|
||||
# Check if we have a pending vehicle for this display
|
||||
if display_id in self.pending_vehicles:
|
||||
track_id = self.pending_vehicles[display_id]
|
||||
|
||||
# Mark vehicle as processed with the session ID
|
||||
self.tracker.mark_processed(track_id, session_id)
|
||||
self.session_vehicles[session_id] = track_id
|
||||
|
||||
# Mark vehicle as permanently processed (won't process again even after session clear)
|
||||
# Use composite key to distinguish same track IDs across different cameras
|
||||
camera_id = display_id # Using display_id as camera_id for isolation
|
||||
permanent_key = f"{camera_id}:{track_id}"
|
||||
self.permanently_processed[permanent_key] = time.time()
|
||||
|
||||
# Remove from pending
|
||||
del self.pending_vehicles[display_id]
|
||||
|
||||
logger.info(f"Assigned session {session_id} to vehicle {track_id}, marked as permanently processed")
|
||||
else:
|
||||
logger.warning(f"No pending vehicle found for display {display_id} when setting session {session_id}")
|
||||
|
||||
# Check if we have pending processing data for this display
|
||||
if display_id in self.pending_processing_data:
|
||||
processing_data = self.pending_processing_data[display_id]
|
||||
|
||||
# Trigger the processing phase asynchronously
|
||||
asyncio.create_task(self._execute_processing_phase(
|
||||
processing_data=processing_data,
|
||||
session_id=session_id,
|
||||
display_id=display_id
|
||||
))
|
||||
|
||||
# Remove from pending processing
|
||||
del self.pending_processing_data[display_id]
|
||||
|
||||
logger.info(f"Triggered processing phase for session {session_id} on display {display_id}")
|
||||
else:
|
||||
logger.warning(f"No pending processing data found for display {display_id} when setting session {session_id}")
|
||||
|
||||
# FALLBACK: Execute pipeline for POS-initiated sessions
|
||||
# Skip if session_id is None (no car present or car has left)
|
||||
if session_id is not None:
|
||||
# Use stored subscription_id instead of creating fake one
|
||||
stored_subscription_id = self.display_to_subscription.get(display_id)
|
||||
if stored_subscription_id:
|
||||
logger.info(f"[FALLBACK] Triggering fallback pipeline for session {session_id} on display {display_id} with subscription {stored_subscription_id}")
|
||||
|
||||
# Trigger the fallback pipeline asynchronously with real subscription_id
|
||||
asyncio.create_task(self._execute_fallback_pipeline(
|
||||
display_id=display_id,
|
||||
session_id=session_id,
|
||||
subscription_id=stored_subscription_id
|
||||
))
|
||||
else:
|
||||
logger.error(f"[FALLBACK] No subscription_id stored for display {display_id}, cannot execute fallback pipeline")
|
||||
else:
|
||||
logger.debug(f"[FALLBACK] Skipping pipeline execution for session_id=None on display {display_id}")
|
||||
|
||||
def clear_session_id(self, session_id: str):
|
||||
"""
|
||||
Clear session ID (post-fueling).
|
||||
|
||||
Args:
|
||||
session_id: Session identifier to clear
|
||||
"""
|
||||
# Mark session as cleared
|
||||
self.cleared_sessions[session_id] = time.time()
|
||||
|
||||
# Clear from tracker
|
||||
self.tracker.clear_session(session_id)
|
||||
|
||||
# Remove from active sessions
|
||||
display_to_remove = None
|
||||
for display_id, sess_id in self.active_sessions.items():
|
||||
if sess_id == session_id:
|
||||
display_to_remove = display_id
|
||||
break
|
||||
|
||||
if display_to_remove:
|
||||
del self.active_sessions[display_to_remove]
|
||||
|
||||
if session_id in self.session_vehicles:
|
||||
del self.session_vehicles[session_id]
|
||||
|
||||
logger.info(f"Cleared session {session_id}")
|
||||
|
||||
# Clean old cleared sessions (older than 5 minutes)
|
||||
current_time = time.time()
|
||||
old_sessions = [
|
||||
sid for sid, clear_time in self.cleared_sessions.items()
|
||||
if (current_time - clear_time) > 300
|
||||
]
|
||||
for sid in old_sessions:
|
||||
del self.cleared_sessions[sid]
|
||||
|
||||
def get_session_for_display(self, display_id: str) -> Optional[str]:
|
||||
"""Get active session for a display."""
|
||||
return self.active_sessions.get(display_id)
|
||||
|
||||
def reset_tracking(self):
|
||||
"""Reset all tracking state."""
|
||||
self.tracker.reset_tracking()
|
||||
self.active_sessions.clear()
|
||||
self.session_vehicles.clear()
|
||||
self.cleared_sessions.clear()
|
||||
self.pending_vehicles.clear()
|
||||
self.pending_processing_data.clear()
|
||||
self.display_to_subscription.clear()
|
||||
self.permanently_processed.clear()
|
||||
self.progression_stages.clear()
|
||||
self.last_detection_time.clear()
|
||||
logger.info("Tracking pipeline integration reset")
|
||||
|
||||
def get_statistics(self) -> Dict[str, Any]:
|
||||
"""Get comprehensive statistics."""
|
||||
tracker_stats = self.tracker.get_statistics()
|
||||
validator_stats = self.validator.get_statistics()
|
||||
|
||||
return {
|
||||
'integration': self.stats,
|
||||
'tracker': tracker_stats,
|
||||
'validator': validator_stats,
|
||||
'active_sessions': len(self.active_sessions),
|
||||
'cleared_sessions': len(self.cleared_sessions)
|
||||
}
|
||||
|
||||
async def _check_car_abandonment(self, display_id: str, subscription_id: str):
|
||||
"""
|
||||
Check if a car has abandoned the fueling process (left after getting car_wait_staff stage).
|
||||
|
||||
Args:
|
||||
display_id: Display identifier
|
||||
subscription_id: Subscription identifier
|
||||
"""
|
||||
current_time = time.time()
|
||||
|
||||
# Check all sessions in car_wait_staff stage
|
||||
abandoned_sessions = []
|
||||
for session_id, stage in self.progression_stages.items():
|
||||
if stage == "car_wait_staff":
|
||||
# Check if we have recent detections for this session's display
|
||||
session_display = None
|
||||
for disp_id, sess_id in self.active_sessions.items():
|
||||
if sess_id == session_id:
|
||||
session_display = disp_id
|
||||
break
|
||||
|
||||
if session_display:
|
||||
last_detection = self.last_detection_time.get(session_display, 0)
|
||||
time_since_detection = current_time - last_detection
|
||||
|
||||
logger.info(f"[ABANDON CHECK] Session {session_id} (display: {session_display}): "
|
||||
f"time_since_detection={time_since_detection:.1f}s, "
|
||||
f"timeout={self.abandonment_timeout}s")
|
||||
|
||||
if time_since_detection > self.abandonment_timeout:
|
||||
logger.warning(f"🚨 Car abandonment detected: session {session_id}, "
|
||||
f"no detection for {time_since_detection:.1f}s")
|
||||
abandoned_sessions.append(session_id)
|
||||
else:
|
||||
logger.debug(f"[ABANDON CHECK] Session {session_id} has no associated display")
|
||||
|
||||
# Send abandonment detection for each abandoned session
|
||||
for session_id in abandoned_sessions:
|
||||
await self._send_abandonment_detection(subscription_id, session_id)
|
||||
# Remove from progression stages to avoid repeated detection
|
||||
if session_id in self.progression_stages:
|
||||
del self.progression_stages[session_id]
|
||||
logger.info(f"[ABANDON] Removed session {session_id} from progression_stages after notification")
|
||||
|
||||
async def _send_abandonment_detection(self, subscription_id: str, session_id: str):
|
||||
"""
|
||||
Send imageDetection with null detection to indicate car abandonment.
|
||||
|
||||
Args:
|
||||
subscription_id: Subscription identifier
|
||||
session_id: Session ID of the abandoned car
|
||||
"""
|
||||
try:
|
||||
# Import here to avoid circular imports
|
||||
from ..communication.messages import create_image_detection
|
||||
|
||||
# Create abandonment detection message with null detection
|
||||
detection_message = create_image_detection(
|
||||
subscription_identifier=subscription_id,
|
||||
detection_data=None, # Null detection indicates abandonment
|
||||
model_id=self.model_id,
|
||||
model_name=self.pipeline_parser.tracking_config.model_id if self.pipeline_parser.tracking_config else "tracking_model"
|
||||
)
|
||||
|
||||
# Send to backend via WebSocket if sender is available
|
||||
if self.message_sender:
|
||||
await self.message_sender(detection_message)
|
||||
logger.info(f"[CAR ABANDONMENT] Sent null detection for session {session_id}")
|
||||
else:
|
||||
logger.info(f"[CAR ABANDONMENT] No message sender available, would send: {detection_message}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error sending abandonment detection: {e}", exc_info=True)
|
||||
|
||||
def set_progression_stage(self, session_id: str, stage: str):
|
||||
"""
|
||||
Set progression stage for a session (from backend setProgessionStage message).
|
||||
|
||||
Args:
|
||||
session_id: Session identifier
|
||||
stage: Progression stage (e.g., "car_wait_staff")
|
||||
"""
|
||||
self.progression_stages[session_id] = stage
|
||||
logger.info(f"Set progression stage for session {session_id}: {stage}")
|
||||
|
||||
# If car reaches car_wait_staff, start monitoring for abandonment
|
||||
if stage == "car_wait_staff":
|
||||
logger.info(f"Started monitoring session {session_id} for car abandonment")
|
||||
|
||||
def _fetch_snapshot(self) -> Optional[np.ndarray]:
|
||||
"""
|
||||
Fetch high-quality snapshot from camera's snapshot URL.
|
||||
Reusable method for both processing phase and fallback pipeline.
|
||||
|
||||
Returns:
|
||||
Snapshot frame or None if unavailable
|
||||
"""
|
||||
if not (self.subscription_info and self.subscription_info.stream_config.snapshot_url):
|
||||
logger.warning("[SNAPSHOT] No subscription info or snapshot URL available")
|
||||
return None
|
||||
|
||||
try:
|
||||
from ..streaming.readers import HTTPSnapshotReader
|
||||
|
||||
logger.info(f"[SNAPSHOT] Fetching snapshot for {self.subscription_info.camera_id}")
|
||||
snapshot_reader = HTTPSnapshotReader(
|
||||
camera_id=self.subscription_info.camera_id,
|
||||
snapshot_url=self.subscription_info.stream_config.snapshot_url,
|
||||
max_retries=3
|
||||
)
|
||||
|
||||
frame = snapshot_reader.fetch_single_snapshot()
|
||||
|
||||
if frame is not None:
|
||||
logger.info(f"[SNAPSHOT] Successfully fetched {frame.shape[1]}x{frame.shape[0]} snapshot")
|
||||
return frame
|
||||
else:
|
||||
logger.warning("[SNAPSHOT] Failed to fetch snapshot")
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[SNAPSHOT] Error fetching snapshot: {e}", exc_info=True)
|
||||
return None
|
||||
|
||||
async def _execute_fallback_pipeline(self, display_id: str, session_id: str, subscription_id: str):
|
||||
"""
|
||||
Execute fallback pipeline when sessionId is received without prior detection.
|
||||
This handles POS-initiated sessions where backend starts transaction before car detection.
|
||||
|
||||
Args:
|
||||
display_id: Display identifier
|
||||
session_id: Session ID from backend
|
||||
subscription_id: Subscription identifier for pipeline execution
|
||||
"""
|
||||
try:
|
||||
logger.info(f"[FALLBACK PIPELINE] Executing for session {session_id}, display {display_id}")
|
||||
|
||||
# Fetch fresh snapshot from camera
|
||||
frame = self._fetch_snapshot()
|
||||
|
||||
if frame is None:
|
||||
logger.error(f"[FALLBACK] Failed to fetch snapshot for session {session_id}, cannot execute pipeline")
|
||||
return
|
||||
|
||||
logger.info(f"[FALLBACK] Using snapshot frame {frame.shape[1]}x{frame.shape[0]} for session {session_id}")
|
||||
|
||||
# Check if detection pipeline is available
|
||||
if not self.detection_pipeline:
|
||||
logger.error(f"[FALLBACK] Detection pipeline not available for session {session_id}")
|
||||
return
|
||||
|
||||
# Execute detection phase to get detected regions
|
||||
detection_result = await self.detection_pipeline.execute_detection_phase(
|
||||
frame=frame,
|
||||
display_id=display_id,
|
||||
subscription_id=subscription_id
|
||||
)
|
||||
|
||||
logger.info(f"[FALLBACK] Detection phase completed for session {session_id}: "
|
||||
f"status={detection_result.get('status', 'unknown')}, "
|
||||
f"regions={list(detection_result.get('detected_regions', {}).keys())}")
|
||||
|
||||
# If detection found regions, execute processing phase
|
||||
detected_regions = detection_result.get('detected_regions', {})
|
||||
if detected_regions:
|
||||
processing_result = await self.detection_pipeline.execute_processing_phase(
|
||||
frame=frame,
|
||||
display_id=display_id,
|
||||
session_id=session_id,
|
||||
subscription_id=subscription_id,
|
||||
detected_regions=detected_regions
|
||||
)
|
||||
|
||||
logger.info(f"[FALLBACK] Processing phase completed for session {session_id}: "
|
||||
f"status={processing_result.get('status', 'unknown')}, "
|
||||
f"branches={len(processing_result.get('branch_results', {}))}, "
|
||||
f"actions={len(processing_result.get('actions_executed', []))}")
|
||||
|
||||
# Update statistics
|
||||
self.stats['pipelines_executed'] += 1
|
||||
|
||||
else:
|
||||
logger.warning(f"[FALLBACK] No detections found in snapshot for session {session_id}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[FALLBACK] Error executing fallback pipeline for session {session_id}: {e}", exc_info=True)
|
||||
|
||||
def _filter_small_frontals(self, tracking_results, frame):
|
||||
"""
|
||||
Filter out frontal detections that are smaller than minimum bbox area percentage.
|
||||
This prevents processing of cars from neighboring pumps that appear in camera view.
|
||||
|
||||
Args:
|
||||
tracking_results: YOLO tracking results with detections
|
||||
frame: Input frame for calculating frame area
|
||||
|
||||
Returns:
|
||||
Modified tracking_results with small frontals removed
|
||||
"""
|
||||
if not hasattr(tracking_results, 'detections') or not tracking_results.detections:
|
||||
return tracking_results
|
||||
|
||||
# Calculate frame area and minimum bbox area threshold
|
||||
frame_area = frame.shape[0] * frame.shape[1] # height * width
|
||||
min_bbox_area = frame_area * (self.min_bbox_area_percentage / 100.0)
|
||||
|
||||
# Filter detections
|
||||
filtered_detections = []
|
||||
filtered_count = 0
|
||||
|
||||
for detection in tracking_results.detections:
|
||||
# Calculate detection bbox area
|
||||
bbox = detection.bbox # Assuming bbox is [x1, y1, x2, y2]
|
||||
bbox_area = (bbox[2] - bbox[0]) * (bbox[3] - bbox[1])
|
||||
|
||||
if bbox_area >= min_bbox_area:
|
||||
# Keep detection - bbox is large enough
|
||||
filtered_detections.append(detection)
|
||||
else:
|
||||
# Filter out small detection
|
||||
filtered_count += 1
|
||||
area_percentage = (bbox_area / frame_area) * 100
|
||||
logger.debug(f"Filtered small frontal: area={bbox_area:.0f}px² ({area_percentage:.1f}% of frame, "
|
||||
f"min required: {self.min_bbox_area_percentage}%)")
|
||||
|
||||
# Update tracking results with filtered detections
|
||||
tracking_results.detections = filtered_detections
|
||||
|
||||
# Update statistics
|
||||
if filtered_count > 0:
|
||||
self.stats['frontals_filtered_small'] += filtered_count
|
||||
logger.info(f"Filtered {filtered_count} small frontal detections, "
|
||||
f"{len(filtered_detections)} remaining (total filtered: {self.stats['frontals_filtered_small']})")
|
||||
|
||||
return tracking_results
|
||||
|
||||
def cleanup(self):
|
||||
"""Cleanup resources."""
|
||||
self.executor.shutdown(wait=False)
|
||||
self.reset_tracking()
|
||||
|
||||
|
||||
# Cleanup detection pipeline
|
||||
if self.detection_pipeline:
|
||||
self.detection_pipeline.cleanup()
|
||||
|
||||
logger.info("Tracking pipeline integration cleaned up")
|
||||
|
|
@ -1,293 +0,0 @@
|
|||
"""
|
||||
Vehicle Tracking Module - BoT-SORT based tracking with camera isolation
|
||||
Implements vehicle identification, persistence, and motion analysis using external tracker.
|
||||
"""
|
||||
import logging
|
||||
import time
|
||||
import uuid
|
||||
from typing import Dict, List, Optional, Tuple, Any
|
||||
from dataclasses import dataclass, field
|
||||
import numpy as np
|
||||
from threading import Lock
|
||||
|
||||
from .bot_sort_tracker import MultiCameraBoTSORT
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@dataclass
|
||||
class TrackedVehicle:
|
||||
"""Represents a tracked vehicle with all its state information."""
|
||||
track_id: int
|
||||
camera_id: str
|
||||
first_seen: float
|
||||
last_seen: float
|
||||
session_id: Optional[str] = None
|
||||
display_id: Optional[str] = None
|
||||
confidence: float = 0.0
|
||||
bbox: Tuple[int, int, int, int] = (0, 0, 0, 0) # x1, y1, x2, y2
|
||||
center: Tuple[float, float] = (0.0, 0.0)
|
||||
stable_frames: int = 0
|
||||
total_frames: int = 0
|
||||
is_stable: bool = False
|
||||
processed_pipeline: bool = False
|
||||
last_position_history: List[Tuple[float, float]] = field(default_factory=list)
|
||||
avg_confidence: float = 0.0
|
||||
hit_streak: int = 0
|
||||
age: int = 0
|
||||
|
||||
def update_position(self, bbox: Tuple[int, int, int, int], confidence: float):
|
||||
"""Update vehicle position and confidence."""
|
||||
self.bbox = bbox
|
||||
self.center = ((bbox[0] + bbox[2]) / 2, (bbox[1] + bbox[3]) / 2)
|
||||
self.last_seen = time.time()
|
||||
self.confidence = confidence
|
||||
self.total_frames += 1
|
||||
|
||||
# Update confidence average
|
||||
self.avg_confidence = ((self.avg_confidence * (self.total_frames - 1)) + confidence) / self.total_frames
|
||||
|
||||
# Maintain position history (last 10 positions)
|
||||
self.last_position_history.append(self.center)
|
||||
if len(self.last_position_history) > 10:
|
||||
self.last_position_history.pop(0)
|
||||
|
||||
def calculate_stability(self) -> float:
|
||||
"""Calculate stability score based on position history."""
|
||||
if len(self.last_position_history) < 2:
|
||||
return 0.0
|
||||
|
||||
# Calculate movement variance
|
||||
positions = np.array(self.last_position_history)
|
||||
if len(positions) < 2:
|
||||
return 0.0
|
||||
|
||||
# Calculate standard deviation of positions
|
||||
std_x = np.std(positions[:, 0])
|
||||
std_y = np.std(positions[:, 1])
|
||||
|
||||
# Lower variance means more stable (inverse relationship)
|
||||
# Normalize to 0-1 range (assuming max reasonable std is 50 pixels)
|
||||
stability = max(0, 1 - (std_x + std_y) / 100)
|
||||
return stability
|
||||
|
||||
def is_expired(self, timeout_seconds: float = 2.0) -> bool:
|
||||
"""Check if vehicle tracking has expired."""
|
||||
return (time.time() - self.last_seen) > timeout_seconds
|
||||
|
||||
|
||||
class VehicleTracker:
|
||||
"""
|
||||
Main vehicle tracking implementation using BoT-SORT with camera isolation.
|
||||
Manages continuous tracking, vehicle identification, and state persistence.
|
||||
"""
|
||||
|
||||
def __init__(self, tracking_config: Optional[Dict] = None):
|
||||
"""
|
||||
Initialize the vehicle tracker.
|
||||
|
||||
Args:
|
||||
tracking_config: Configuration from pipeline.json tracking section
|
||||
"""
|
||||
self.config = tracking_config or {}
|
||||
self.trigger_classes = self.config.get('trigger_classes', self.config.get('triggerClasses', ['frontal']))
|
||||
self.min_confidence = self.config.get('minConfidence', 0.6)
|
||||
|
||||
# BoT-SORT multi-camera tracker
|
||||
self.bot_sort = MultiCameraBoTSORT(self.trigger_classes, self.min_confidence)
|
||||
|
||||
# Tracking state - maintain compatibility with existing code
|
||||
self.tracked_vehicles: Dict[str, Dict[int, TrackedVehicle]] = {} # camera_id -> {track_id: vehicle}
|
||||
self.lock = Lock()
|
||||
|
||||
# Tracking parameters
|
||||
self.stability_threshold = 0.7
|
||||
self.min_stable_frames = 5
|
||||
self.timeout_seconds = 2.0
|
||||
|
||||
logger.info(f"VehicleTracker initialized with BoT-SORT: trigger_classes={self.trigger_classes}, "
|
||||
f"min_confidence={self.min_confidence}")
|
||||
|
||||
def process_detections(self,
|
||||
results: Any,
|
||||
display_id: str,
|
||||
frame: np.ndarray) -> List[TrackedVehicle]:
|
||||
"""
|
||||
Process detection results using BoT-SORT tracking.
|
||||
|
||||
Args:
|
||||
results: Detection results (InferenceResult)
|
||||
display_id: Display identifier for this stream
|
||||
frame: Current frame being processed
|
||||
|
||||
Returns:
|
||||
List of currently tracked vehicles
|
||||
"""
|
||||
current_time = time.time()
|
||||
|
||||
# Extract camera_id from display_id for tracking isolation
|
||||
camera_id = display_id # Using display_id as camera_id for isolation
|
||||
|
||||
with self.lock:
|
||||
# Update BoT-SORT tracker
|
||||
track_results = self.bot_sort.update(camera_id, results)
|
||||
|
||||
# Ensure camera tracking dict exists
|
||||
if camera_id not in self.tracked_vehicles:
|
||||
self.tracked_vehicles[camera_id] = {}
|
||||
|
||||
# Update tracked vehicles based on BoT-SORT results
|
||||
current_tracks = {}
|
||||
active_tracks = []
|
||||
|
||||
for track_result in track_results:
|
||||
track_id = track_result['track_id']
|
||||
|
||||
# Create or update TrackedVehicle
|
||||
if track_id in self.tracked_vehicles[camera_id]:
|
||||
# Update existing vehicle
|
||||
vehicle = self.tracked_vehicles[camera_id][track_id]
|
||||
vehicle.update_position(track_result['bbox'], track_result['confidence'])
|
||||
vehicle.hit_streak = track_result['hit_streak']
|
||||
vehicle.age = track_result['age']
|
||||
|
||||
# Update stability based on hit_streak
|
||||
if vehicle.hit_streak >= self.min_stable_frames:
|
||||
vehicle.is_stable = True
|
||||
vehicle.stable_frames = vehicle.hit_streak
|
||||
|
||||
logger.debug(f"Updated track {track_id}: conf={vehicle.confidence:.2f}, "
|
||||
f"stable={vehicle.is_stable}, hit_streak={vehicle.hit_streak}")
|
||||
else:
|
||||
# Create new vehicle
|
||||
x1, y1, x2, y2 = track_result['bbox']
|
||||
vehicle = TrackedVehicle(
|
||||
track_id=track_id,
|
||||
camera_id=camera_id,
|
||||
first_seen=current_time,
|
||||
last_seen=current_time,
|
||||
display_id=display_id,
|
||||
confidence=track_result['confidence'],
|
||||
bbox=tuple(track_result['bbox']),
|
||||
center=((x1 + x2) / 2, (y1 + y2) / 2),
|
||||
total_frames=1,
|
||||
hit_streak=track_result['hit_streak'],
|
||||
age=track_result['age']
|
||||
)
|
||||
vehicle.last_position_history.append(vehicle.center)
|
||||
logger.info(f"New vehicle tracked: ID={track_id}, camera={camera_id}, display={display_id}")
|
||||
|
||||
current_tracks[track_id] = vehicle
|
||||
active_tracks.append(vehicle)
|
||||
|
||||
# Update the camera's tracked vehicles
|
||||
self.tracked_vehicles[camera_id] = current_tracks
|
||||
|
||||
return active_tracks
|
||||
|
||||
def get_stable_vehicles(self, display_id: Optional[str] = None) -> List[TrackedVehicle]:
|
||||
"""
|
||||
Get all stable vehicles, optionally filtered by display.
|
||||
|
||||
Args:
|
||||
display_id: Optional display ID to filter by
|
||||
|
||||
Returns:
|
||||
List of stable tracked vehicles
|
||||
"""
|
||||
with self.lock:
|
||||
stable = []
|
||||
camera_id = display_id # Using display_id as camera_id
|
||||
|
||||
if camera_id in self.tracked_vehicles:
|
||||
for vehicle in self.tracked_vehicles[camera_id].values():
|
||||
if (vehicle.is_stable and not vehicle.is_expired(self.timeout_seconds) and
|
||||
(display_id is None or vehicle.display_id == display_id)):
|
||||
stable.append(vehicle)
|
||||
|
||||
return stable
|
||||
|
||||
def get_vehicle_by_session(self, session_id: str) -> Optional[TrackedVehicle]:
|
||||
"""
|
||||
Get a tracked vehicle by its session ID.
|
||||
|
||||
Args:
|
||||
session_id: Session ID to look up
|
||||
|
||||
Returns:
|
||||
Tracked vehicle if found, None otherwise
|
||||
"""
|
||||
with self.lock:
|
||||
# Search across all cameras
|
||||
for camera_vehicles in self.tracked_vehicles.values():
|
||||
for vehicle in camera_vehicles.values():
|
||||
if vehicle.session_id == session_id:
|
||||
return vehicle
|
||||
return None
|
||||
|
||||
def mark_processed(self, track_id: int, session_id: str):
|
||||
"""
|
||||
Mark a vehicle as processed through the pipeline.
|
||||
|
||||
Args:
|
||||
track_id: Track ID of the vehicle
|
||||
session_id: Session ID assigned to this vehicle
|
||||
"""
|
||||
with self.lock:
|
||||
# Search across all cameras for the track_id
|
||||
for camera_vehicles in self.tracked_vehicles.values():
|
||||
if track_id in camera_vehicles:
|
||||
vehicle = camera_vehicles[track_id]
|
||||
vehicle.processed_pipeline = True
|
||||
vehicle.session_id = session_id
|
||||
logger.info(f"Marked vehicle {track_id} as processed with session {session_id}")
|
||||
return
|
||||
|
||||
def clear_session(self, session_id: str):
|
||||
"""
|
||||
Clear session ID from a tracked vehicle (post-fueling).
|
||||
|
||||
Args:
|
||||
session_id: Session ID to clear
|
||||
"""
|
||||
with self.lock:
|
||||
# Search across all cameras
|
||||
for camera_vehicles in self.tracked_vehicles.values():
|
||||
for vehicle in camera_vehicles.values():
|
||||
if vehicle.session_id == session_id:
|
||||
logger.info(f"Clearing session {session_id} from vehicle {vehicle.track_id}")
|
||||
vehicle.session_id = None
|
||||
# Keep processed_pipeline=True to prevent re-processing
|
||||
|
||||
def reset_tracking(self):
|
||||
"""Reset all tracking state."""
|
||||
with self.lock:
|
||||
self.tracked_vehicles.clear()
|
||||
self.bot_sort.reset_all()
|
||||
logger.info("Vehicle tracking state reset")
|
||||
|
||||
def get_statistics(self) -> Dict:
|
||||
"""Get tracking statistics."""
|
||||
with self.lock:
|
||||
total = 0
|
||||
stable = 0
|
||||
processed = 0
|
||||
all_confidences = []
|
||||
|
||||
# Aggregate stats across all cameras
|
||||
for camera_vehicles in self.tracked_vehicles.values():
|
||||
total += len(camera_vehicles)
|
||||
for vehicle in camera_vehicles.values():
|
||||
if vehicle.is_stable:
|
||||
stable += 1
|
||||
if vehicle.processed_pipeline:
|
||||
processed += 1
|
||||
all_confidences.append(vehicle.avg_confidence)
|
||||
|
||||
return {
|
||||
'total_tracked': total,
|
||||
'stable_vehicles': stable,
|
||||
'processed_vehicles': processed,
|
||||
'avg_confidence': np.mean(all_confidences) if all_confidences else 0.0,
|
||||
'bot_sort_stats': self.bot_sort.get_statistics()
|
||||
}
|
||||
|
|
@ -1,402 +0,0 @@
|
|||
"""
|
||||
Vehicle Validation Module - Stable car detection and validation logic.
|
||||
Differentiates between stable (fueling) cars and passing-by vehicles.
|
||||
"""
|
||||
import logging
|
||||
import time
|
||||
import numpy as np
|
||||
from typing import List, Optional, Tuple, Dict, Any
|
||||
from dataclasses import dataclass
|
||||
from enum import Enum
|
||||
|
||||
from .tracker import TrackedVehicle
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class VehicleState(Enum):
|
||||
"""Vehicle state classification."""
|
||||
UNKNOWN = "unknown"
|
||||
ENTERING = "entering"
|
||||
STABLE = "stable"
|
||||
LEAVING = "leaving"
|
||||
PASSING_BY = "passing_by"
|
||||
|
||||
|
||||
@dataclass
|
||||
class ValidationResult:
|
||||
"""Result of vehicle validation."""
|
||||
is_valid: bool
|
||||
state: VehicleState
|
||||
confidence: float
|
||||
reason: str
|
||||
should_process: bool = False
|
||||
track_id: Optional[int] = None
|
||||
|
||||
|
||||
class StableCarValidator:
|
||||
"""
|
||||
Validates whether a tracked vehicle should be processed through the pipeline.
|
||||
|
||||
Updated for BoT-SORT integration: Trusts the sophisticated BoT-SORT tracking algorithm
|
||||
for stability determination and focuses on business logic validation:
|
||||
- Duration requirements for processing
|
||||
- Confidence thresholds
|
||||
- Session management and cooldowns
|
||||
- Camera isolation with composite keys
|
||||
"""
|
||||
|
||||
def __init__(self, config: Optional[Dict] = None):
|
||||
"""
|
||||
Initialize the validator with configuration.
|
||||
|
||||
Args:
|
||||
config: Optional configuration dictionary
|
||||
"""
|
||||
self.config = config or {}
|
||||
|
||||
# Validation thresholds
|
||||
self.min_stable_duration = self.config.get('min_stable_duration', 3.0) # seconds
|
||||
self.min_stable_frames = self.config.get('min_stable_frames', 10)
|
||||
self.position_variance_threshold = self.config.get('position_variance_threshold', 25.0) # pixels
|
||||
self.min_confidence = self.config.get('min_confidence', 0.7)
|
||||
self.velocity_threshold = self.config.get('velocity_threshold', 5.0) # pixels/frame
|
||||
self.entering_zone_ratio = self.config.get('entering_zone_ratio', 0.3) # 30% of frame
|
||||
self.leaving_zone_ratio = self.config.get('leaving_zone_ratio', 0.3)
|
||||
|
||||
# Frame dimensions (will be updated on first frame)
|
||||
self.frame_width = 1920
|
||||
self.frame_height = 1080
|
||||
|
||||
# History for validation
|
||||
self.validation_history: Dict[int, List[VehicleState]] = {}
|
||||
self.last_processed_vehicles: Dict[int, float] = {} # track_id -> last_process_time
|
||||
|
||||
logger.info(f"StableCarValidator initialized with min_duration={self.min_stable_duration}s, "
|
||||
f"min_frames={self.min_stable_frames}, position_variance={self.position_variance_threshold}")
|
||||
|
||||
def update_frame_dimensions(self, width: int, height: int):
|
||||
"""Update frame dimensions for zone calculations."""
|
||||
self.frame_width = width
|
||||
self.frame_height = height
|
||||
# Commented out verbose frame dimension logging
|
||||
# logger.debug(f"Updated frame dimensions: {width}x{height}")
|
||||
|
||||
def validate_vehicle(self, vehicle: TrackedVehicle, frame_shape: Optional[Tuple] = None) -> ValidationResult:
|
||||
"""
|
||||
Validate whether a tracked vehicle is stable and should be processed.
|
||||
|
||||
Args:
|
||||
vehicle: The tracked vehicle to validate
|
||||
frame_shape: Optional frame shape (height, width, channels)
|
||||
|
||||
Returns:
|
||||
ValidationResult with validation status and reasoning
|
||||
"""
|
||||
# Update frame dimensions if provided
|
||||
if frame_shape:
|
||||
self.update_frame_dimensions(frame_shape[1], frame_shape[0])
|
||||
|
||||
# Initialize validation history for new vehicles
|
||||
if vehicle.track_id not in self.validation_history:
|
||||
self.validation_history[vehicle.track_id] = []
|
||||
|
||||
# Check if already processed
|
||||
if vehicle.processed_pipeline:
|
||||
return ValidationResult(
|
||||
is_valid=False,
|
||||
state=VehicleState.STABLE,
|
||||
confidence=1.0,
|
||||
reason="Already processed through pipeline",
|
||||
should_process=False,
|
||||
track_id=vehicle.track_id
|
||||
)
|
||||
|
||||
# Check if recently processed (cooldown period)
|
||||
if vehicle.track_id in self.last_processed_vehicles:
|
||||
time_since_process = time.time() - self.last_processed_vehicles[vehicle.track_id]
|
||||
if time_since_process < 10.0: # 10 second cooldown
|
||||
return ValidationResult(
|
||||
is_valid=False,
|
||||
state=VehicleState.STABLE,
|
||||
confidence=1.0,
|
||||
reason=f"Recently processed ({time_since_process:.1f}s ago)",
|
||||
should_process=False,
|
||||
track_id=vehicle.track_id
|
||||
)
|
||||
|
||||
# Determine vehicle state
|
||||
state = self._determine_vehicle_state(vehicle)
|
||||
|
||||
# Update history
|
||||
self.validation_history[vehicle.track_id].append(state)
|
||||
if len(self.validation_history[vehicle.track_id]) > 20:
|
||||
self.validation_history[vehicle.track_id].pop(0)
|
||||
|
||||
# Validate based on state
|
||||
if state == VehicleState.STABLE:
|
||||
return self._validate_stable_vehicle(vehicle)
|
||||
elif state == VehicleState.PASSING_BY:
|
||||
return ValidationResult(
|
||||
is_valid=False,
|
||||
state=state,
|
||||
confidence=0.8,
|
||||
reason="Vehicle is passing by",
|
||||
should_process=False,
|
||||
track_id=vehicle.track_id
|
||||
)
|
||||
elif state == VehicleState.ENTERING:
|
||||
return ValidationResult(
|
||||
is_valid=False,
|
||||
state=state,
|
||||
confidence=0.5,
|
||||
reason="Vehicle is entering, waiting for stability",
|
||||
should_process=False,
|
||||
track_id=vehicle.track_id
|
||||
)
|
||||
elif state == VehicleState.LEAVING:
|
||||
return ValidationResult(
|
||||
is_valid=False,
|
||||
state=state,
|
||||
confidence=0.5,
|
||||
reason="Vehicle is leaving",
|
||||
should_process=False,
|
||||
track_id=vehicle.track_id
|
||||
)
|
||||
else:
|
||||
return ValidationResult(
|
||||
is_valid=False,
|
||||
state=state,
|
||||
confidence=0.0,
|
||||
reason="Unknown vehicle state",
|
||||
should_process=False,
|
||||
track_id=vehicle.track_id
|
||||
)
|
||||
|
||||
def _determine_vehicle_state(self, vehicle: TrackedVehicle) -> VehicleState:
|
||||
"""
|
||||
Determine the current state of the vehicle based on BoT-SORT tracking results.
|
||||
|
||||
BoT-SORT provides sophisticated tracking, so we trust its stability determination
|
||||
and focus on business logic validation.
|
||||
|
||||
Args:
|
||||
vehicle: The tracked vehicle
|
||||
|
||||
Returns:
|
||||
Current vehicle state
|
||||
"""
|
||||
# Trust BoT-SORT's stability determination
|
||||
if vehicle.is_stable:
|
||||
# Check if it's been stable long enough for processing
|
||||
duration = time.time() - vehicle.first_seen
|
||||
if duration >= self.min_stable_duration:
|
||||
return VehicleState.STABLE
|
||||
else:
|
||||
return VehicleState.ENTERING
|
||||
|
||||
# For non-stable vehicles, use simplified state determination
|
||||
if len(vehicle.last_position_history) < 2:
|
||||
return VehicleState.UNKNOWN
|
||||
|
||||
# Calculate velocity for movement classification
|
||||
velocity = self._calculate_velocity(vehicle)
|
||||
|
||||
# Basic movement classification
|
||||
if velocity > self.velocity_threshold:
|
||||
# Vehicle is moving - classify as passing by or entering/leaving
|
||||
x_position = vehicle.center[0] / self.frame_width
|
||||
|
||||
# Simple heuristic: vehicles near edges are entering/leaving, center vehicles are passing
|
||||
if x_position < 0.2 or x_position > 0.8:
|
||||
return VehicleState.ENTERING
|
||||
else:
|
||||
return VehicleState.PASSING_BY
|
||||
|
||||
# Low velocity but not marked stable by tracker - likely entering
|
||||
return VehicleState.ENTERING
|
||||
|
||||
def _validate_stable_vehicle(self, vehicle: TrackedVehicle) -> ValidationResult:
|
||||
"""
|
||||
Perform business logic validation of a stable vehicle.
|
||||
|
||||
Since BoT-SORT already determined the vehicle is stable, we focus on:
|
||||
- Duration requirements for processing
|
||||
- Confidence thresholds
|
||||
- Business logic constraints
|
||||
|
||||
Args:
|
||||
vehicle: The stable vehicle to validate
|
||||
|
||||
Returns:
|
||||
Detailed validation result
|
||||
"""
|
||||
# Check duration (business requirement)
|
||||
duration = time.time() - vehicle.first_seen
|
||||
if duration < self.min_stable_duration:
|
||||
return ValidationResult(
|
||||
is_valid=False,
|
||||
state=VehicleState.STABLE,
|
||||
confidence=0.6,
|
||||
reason=f"Not stable long enough ({duration:.1f}s < {self.min_stable_duration}s)",
|
||||
should_process=False,
|
||||
track_id=vehicle.track_id
|
||||
)
|
||||
|
||||
# Check confidence (business requirement)
|
||||
if vehicle.avg_confidence < self.min_confidence:
|
||||
return ValidationResult(
|
||||
is_valid=False,
|
||||
state=VehicleState.STABLE,
|
||||
confidence=vehicle.avg_confidence,
|
||||
reason=f"Confidence too low ({vehicle.avg_confidence:.2f} < {self.min_confidence})",
|
||||
should_process=False,
|
||||
track_id=vehicle.track_id
|
||||
)
|
||||
|
||||
# Trust BoT-SORT's stability determination - skip position variance check
|
||||
# BoT-SORT's sophisticated tracking already ensures consistent positioning
|
||||
|
||||
# Simplified state history check - just ensure recent stability
|
||||
if vehicle.track_id in self.validation_history:
|
||||
history = self.validation_history[vehicle.track_id][-3:] # Last 3 states
|
||||
stable_count = sum(1 for s in history if s == VehicleState.STABLE)
|
||||
if len(history) >= 2 and stable_count == 0: # Only fail if clear instability
|
||||
return ValidationResult(
|
||||
is_valid=False,
|
||||
state=VehicleState.STABLE,
|
||||
confidence=0.7,
|
||||
reason="Recent state history shows instability",
|
||||
should_process=False,
|
||||
track_id=vehicle.track_id
|
||||
)
|
||||
|
||||
# All checks passed - vehicle is valid for processing
|
||||
self.last_processed_vehicles[vehicle.track_id] = time.time()
|
||||
|
||||
return ValidationResult(
|
||||
is_valid=True,
|
||||
state=VehicleState.STABLE,
|
||||
confidence=vehicle.avg_confidence,
|
||||
reason="Vehicle is stable and ready for processing (BoT-SORT validated)",
|
||||
should_process=True,
|
||||
track_id=vehicle.track_id
|
||||
)
|
||||
|
||||
def _calculate_velocity(self, vehicle: TrackedVehicle) -> float:
|
||||
"""
|
||||
Calculate the velocity of the vehicle based on position history.
|
||||
|
||||
Args:
|
||||
vehicle: The tracked vehicle
|
||||
|
||||
Returns:
|
||||
Velocity in pixels per frame
|
||||
"""
|
||||
if len(vehicle.last_position_history) < 2:
|
||||
return 0.0
|
||||
|
||||
positions = np.array(vehicle.last_position_history)
|
||||
if len(positions) < 2:
|
||||
return 0.0
|
||||
|
||||
# Calculate velocity over last 3 frames
|
||||
recent_positions = positions[-min(3, len(positions)):]
|
||||
velocities = []
|
||||
|
||||
for i in range(1, len(recent_positions)):
|
||||
dx = recent_positions[i][0] - recent_positions[i-1][0]
|
||||
dy = recent_positions[i][1] - recent_positions[i-1][1]
|
||||
velocity = np.sqrt(dx**2 + dy**2)
|
||||
velocities.append(velocity)
|
||||
|
||||
return np.mean(velocities) if velocities else 0.0
|
||||
|
||||
def _calculate_position_variance(self, vehicle: TrackedVehicle) -> float:
|
||||
"""
|
||||
Calculate the position variance of the vehicle.
|
||||
|
||||
Args:
|
||||
vehicle: The tracked vehicle
|
||||
|
||||
Returns:
|
||||
Position variance in pixels
|
||||
"""
|
||||
if len(vehicle.last_position_history) < 2:
|
||||
return 0.0
|
||||
|
||||
positions = np.array(vehicle.last_position_history)
|
||||
variance_x = np.var(positions[:, 0])
|
||||
variance_y = np.var(positions[:, 1])
|
||||
|
||||
return np.sqrt(variance_x + variance_y)
|
||||
|
||||
def should_skip_same_car(self,
|
||||
vehicle: TrackedVehicle,
|
||||
session_cleared: bool = False,
|
||||
permanently_processed: Dict[str, float] = None) -> bool:
|
||||
"""
|
||||
Determine if we should skip processing for the same car after session clear.
|
||||
|
||||
Args:
|
||||
vehicle: The tracked vehicle
|
||||
session_cleared: Whether the session was recently cleared
|
||||
permanently_processed: Dict of permanently processed vehicles (camera_id:track_id -> time)
|
||||
|
||||
Returns:
|
||||
True if we should skip this vehicle
|
||||
"""
|
||||
# Check if this vehicle was permanently processed (never process again)
|
||||
if permanently_processed:
|
||||
# Create composite key using camera_id and track_id
|
||||
permanent_key = f"{vehicle.camera_id}:{vehicle.track_id}"
|
||||
if permanent_key in permanently_processed:
|
||||
process_time = permanently_processed[permanent_key]
|
||||
time_since = time.time() - process_time
|
||||
logger.debug(f"Skipping permanently processed vehicle {vehicle.track_id} on camera {vehicle.camera_id} "
|
||||
f"(processed {time_since:.1f}s ago)")
|
||||
return True
|
||||
|
||||
# If vehicle has a session_id but it was cleared, skip for a period
|
||||
if vehicle.session_id is None and vehicle.processed_pipeline and session_cleared:
|
||||
# Check if enough time has passed since processing
|
||||
if vehicle.track_id in self.last_processed_vehicles:
|
||||
time_since = time.time() - self.last_processed_vehicles[vehicle.track_id]
|
||||
if time_since < 30.0: # 30 second cooldown after session clear
|
||||
logger.debug(f"Skipping same car {vehicle.track_id} after session clear "
|
||||
f"({time_since:.1f}s since processing)")
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
def reset_vehicle(self, track_id: int):
|
||||
"""
|
||||
Reset validation state for a specific vehicle.
|
||||
|
||||
Args:
|
||||
track_id: Track ID of the vehicle to reset
|
||||
"""
|
||||
if track_id in self.validation_history:
|
||||
del self.validation_history[track_id]
|
||||
if track_id in self.last_processed_vehicles:
|
||||
del self.last_processed_vehicles[track_id]
|
||||
logger.debug(f"Reset validation state for vehicle {track_id}")
|
||||
|
||||
def get_statistics(self) -> Dict:
|
||||
"""Get validation statistics."""
|
||||
return {
|
||||
'vehicles_in_history': len(self.validation_history),
|
||||
'recently_processed': len(self.last_processed_vehicles),
|
||||
'state_distribution': self._get_state_distribution()
|
||||
}
|
||||
|
||||
def _get_state_distribution(self) -> Dict[str, int]:
|
||||
"""Get distribution of current vehicle states."""
|
||||
distribution = {state.value: 0 for state in VehicleState}
|
||||
|
||||
for history in self.validation_history.values():
|
||||
if history:
|
||||
current_state = history[-1]
|
||||
distribution[current_state.value] += 1
|
||||
|
||||
return distribution
|
||||
|
|
@ -1,214 +0,0 @@
|
|||
"""
|
||||
FFmpeg hardware acceleration detection and configuration
|
||||
"""
|
||||
|
||||
import subprocess
|
||||
import logging
|
||||
import re
|
||||
from typing import Dict, List, Optional
|
||||
|
||||
logger = logging.getLogger("detector_worker")
|
||||
|
||||
|
||||
class FFmpegCapabilities:
|
||||
"""Detect and configure FFmpeg hardware acceleration capabilities."""
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize FFmpeg capabilities detector."""
|
||||
self.hwaccels = []
|
||||
self.codecs = {}
|
||||
self.nvidia_support = False
|
||||
self.vaapi_support = False
|
||||
self.qsv_support = False
|
||||
|
||||
self._detect_capabilities()
|
||||
|
||||
def _detect_capabilities(self):
|
||||
"""Detect available hardware acceleration methods."""
|
||||
try:
|
||||
# Get hardware accelerators
|
||||
result = subprocess.run(
|
||||
['ffmpeg', '-hide_banner', '-hwaccels'],
|
||||
capture_output=True, text=True, timeout=10
|
||||
)
|
||||
if result.returncode == 0:
|
||||
self.hwaccels = [line.strip() for line in result.stdout.strip().split('\n')[1:] if line.strip()]
|
||||
logger.info(f"Available FFmpeg hardware accelerators: {', '.join(self.hwaccels)}")
|
||||
|
||||
# Check for NVIDIA support
|
||||
self.nvidia_support = any(hw in self.hwaccels for hw in ['cuda', 'cuvid', 'nvdec'])
|
||||
self.vaapi_support = 'vaapi' in self.hwaccels
|
||||
self.qsv_support = 'qsv' in self.hwaccels
|
||||
|
||||
# Get decoder information
|
||||
self._detect_decoders()
|
||||
|
||||
# Log capabilities
|
||||
if self.nvidia_support:
|
||||
logger.info("NVIDIA hardware acceleration available (CUDA/CUVID/NVDEC)")
|
||||
logger.info(f"Detected hardware codecs: {self.codecs}")
|
||||
if self.vaapi_support:
|
||||
logger.info("VAAPI hardware acceleration available")
|
||||
if self.qsv_support:
|
||||
logger.info("Intel QuickSync hardware acceleration available")
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to detect FFmpeg capabilities: {e}")
|
||||
|
||||
def _detect_decoders(self):
|
||||
"""Detect available hardware decoders."""
|
||||
try:
|
||||
result = subprocess.run(
|
||||
['ffmpeg', '-hide_banner', '-decoders'],
|
||||
capture_output=True, text=True, timeout=10
|
||||
)
|
||||
if result.returncode == 0:
|
||||
# Parse decoder output to find hardware decoders
|
||||
for line in result.stdout.split('\n'):
|
||||
if 'cuvid' in line or 'nvdec' in line:
|
||||
match = re.search(r'(\w+)\s+.*?(\w+(?:_cuvid|_nvdec))', line)
|
||||
if match:
|
||||
codec_type, decoder = match.groups()
|
||||
if 'h264' in decoder:
|
||||
self.codecs['h264_hw'] = decoder
|
||||
elif 'hevc' in decoder or 'h265' in decoder:
|
||||
self.codecs['h265_hw'] = decoder
|
||||
elif 'vaapi' in line:
|
||||
match = re.search(r'(\w+)\s+.*?(\w+_vaapi)', line)
|
||||
if match:
|
||||
codec_type, decoder = match.groups()
|
||||
if 'h264' in decoder:
|
||||
self.codecs['h264_vaapi'] = decoder
|
||||
|
||||
except Exception as e:
|
||||
logger.debug(f"Failed to detect decoders: {e}")
|
||||
|
||||
def get_optimal_capture_options(self, codec: str = 'h264') -> Dict[str, str]:
|
||||
"""
|
||||
Get optimal FFmpeg capture options for the given codec.
|
||||
|
||||
Args:
|
||||
codec: Video codec (h264, h265, etc.)
|
||||
|
||||
Returns:
|
||||
Dictionary of FFmpeg options
|
||||
"""
|
||||
options = {
|
||||
'rtsp_transport': 'tcp',
|
||||
'buffer_size': '1024k',
|
||||
'max_delay': '500000', # 500ms
|
||||
'fflags': '+genpts',
|
||||
'flags': '+low_delay',
|
||||
'probesize': '32',
|
||||
'analyzeduration': '0'
|
||||
}
|
||||
|
||||
# Add hardware acceleration if available
|
||||
if self.nvidia_support:
|
||||
# Force enable CUDA hardware acceleration for H.264 if CUDA is available
|
||||
if codec == 'h264':
|
||||
options.update({
|
||||
'hwaccel': 'cuda',
|
||||
'hwaccel_device': '0'
|
||||
})
|
||||
logger.info("Using NVIDIA NVDEC hardware acceleration for H.264")
|
||||
elif codec == 'h265':
|
||||
options.update({
|
||||
'hwaccel': 'cuda',
|
||||
'hwaccel_device': '0',
|
||||
'video_codec': 'hevc_cuvid',
|
||||
'hwaccel_output_format': 'cuda'
|
||||
})
|
||||
logger.info("Using NVIDIA CUVID hardware acceleration for H.265")
|
||||
|
||||
elif self.vaapi_support:
|
||||
if codec == 'h264':
|
||||
options.update({
|
||||
'hwaccel': 'vaapi',
|
||||
'hwaccel_device': '/dev/dri/renderD128',
|
||||
'video_codec': 'h264_vaapi'
|
||||
})
|
||||
logger.debug("Using VAAPI hardware acceleration")
|
||||
|
||||
return options
|
||||
|
||||
def format_opencv_options(self, options: Dict[str, str]) -> str:
|
||||
"""
|
||||
Format options for OpenCV FFmpeg backend.
|
||||
|
||||
Args:
|
||||
options: Dictionary of FFmpeg options
|
||||
|
||||
Returns:
|
||||
Formatted options string for OpenCV
|
||||
"""
|
||||
return '|'.join(f"{key};{value}" for key, value in options.items())
|
||||
|
||||
def get_hardware_encoder_options(self, codec: str = 'h264', quality: str = 'fast') -> Dict[str, str]:
|
||||
"""
|
||||
Get optimal hardware encoding options.
|
||||
|
||||
Args:
|
||||
codec: Video codec for encoding
|
||||
quality: Quality preset (fast, medium, slow)
|
||||
|
||||
Returns:
|
||||
Dictionary of encoding options
|
||||
"""
|
||||
options = {}
|
||||
|
||||
if self.nvidia_support:
|
||||
if codec == 'h264':
|
||||
options.update({
|
||||
'video_codec': 'h264_nvenc',
|
||||
'preset': quality,
|
||||
'tune': 'zerolatency',
|
||||
'gpu': '0',
|
||||
'rc': 'cbr_hq',
|
||||
'surfaces': '64'
|
||||
})
|
||||
elif codec == 'h265':
|
||||
options.update({
|
||||
'video_codec': 'hevc_nvenc',
|
||||
'preset': quality,
|
||||
'tune': 'zerolatency',
|
||||
'gpu': '0'
|
||||
})
|
||||
|
||||
elif self.vaapi_support:
|
||||
if codec == 'h264':
|
||||
options.update({
|
||||
'video_codec': 'h264_vaapi',
|
||||
'vaapi_device': '/dev/dri/renderD128'
|
||||
})
|
||||
|
||||
return options
|
||||
|
||||
|
||||
# Global instance
|
||||
_ffmpeg_caps = None
|
||||
|
||||
def get_ffmpeg_capabilities() -> FFmpegCapabilities:
|
||||
"""Get or create the global FFmpeg capabilities instance."""
|
||||
global _ffmpeg_caps
|
||||
if _ffmpeg_caps is None:
|
||||
_ffmpeg_caps = FFmpegCapabilities()
|
||||
return _ffmpeg_caps
|
||||
|
||||
def get_optimal_rtsp_options(rtsp_url: str) -> str:
|
||||
"""
|
||||
Get optimal OpenCV FFmpeg options for RTSP streaming.
|
||||
|
||||
Args:
|
||||
rtsp_url: RTSP stream URL
|
||||
|
||||
Returns:
|
||||
Formatted options string for cv2.VideoCapture
|
||||
"""
|
||||
caps = get_ffmpeg_capabilities()
|
||||
|
||||
# Detect codec from URL or assume H.264
|
||||
codec = 'h265' if any(x in rtsp_url.lower() for x in ['h265', 'hevc']) else 'h264'
|
||||
|
||||
options = caps.get_optimal_capture_options(codec)
|
||||
return caps.format_opencv_options(options)
|
||||
|
|
@ -1,173 +0,0 @@
|
|||
"""
|
||||
Hardware-accelerated image encoding using NVIDIA NVENC or Intel QuickSync
|
||||
"""
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
import logging
|
||||
from typing import Optional, Tuple
|
||||
import os
|
||||
|
||||
logger = logging.getLogger("detector_worker")
|
||||
|
||||
|
||||
class HardwareEncoder:
|
||||
"""Hardware-accelerated JPEG encoder using GPU."""
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize hardware encoder."""
|
||||
self.nvenc_available = False
|
||||
self.vaapi_available = False
|
||||
self.turbojpeg_available = False
|
||||
|
||||
# Check for TurboJPEG (fastest CPU-based option)
|
||||
try:
|
||||
from turbojpeg import TurboJPEG
|
||||
self.turbojpeg = TurboJPEG()
|
||||
self.turbojpeg_available = True
|
||||
logger.info("TurboJPEG accelerated encoding available")
|
||||
except ImportError:
|
||||
logger.debug("TurboJPEG not available")
|
||||
|
||||
# Check for NVIDIA NVENC support
|
||||
try:
|
||||
# Test if we can create an NVENC encoder
|
||||
test_frame = np.zeros((720, 1280, 3), dtype=np.uint8)
|
||||
fourcc = cv2.VideoWriter_fourcc(*'H264')
|
||||
test_writer = cv2.VideoWriter(
|
||||
"test.mp4",
|
||||
fourcc,
|
||||
30,
|
||||
(1280, 720),
|
||||
[cv2.CAP_PROP_HW_ACCELERATION, cv2.VIDEO_ACCELERATION_ANY]
|
||||
)
|
||||
if test_writer.isOpened():
|
||||
self.nvenc_available = True
|
||||
logger.info("NVENC hardware encoding available")
|
||||
test_writer.release()
|
||||
if os.path.exists("test.mp4"):
|
||||
os.remove("test.mp4")
|
||||
except Exception as e:
|
||||
logger.debug(f"NVENC not available: {e}")
|
||||
|
||||
def encode_jpeg(self, frame: np.ndarray, quality: int = 85) -> Optional[bytes]:
|
||||
"""
|
||||
Encode frame to JPEG using the fastest available method.
|
||||
|
||||
Args:
|
||||
frame: BGR image frame
|
||||
quality: JPEG quality (1-100)
|
||||
|
||||
Returns:
|
||||
Encoded JPEG bytes or None on failure
|
||||
"""
|
||||
try:
|
||||
# Method 1: TurboJPEG (3-5x faster than cv2.imencode)
|
||||
if self.turbojpeg_available:
|
||||
# Convert BGR to RGB for TurboJPEG
|
||||
rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
|
||||
encoded = self.turbojpeg.encode(rgb_frame, quality=quality)
|
||||
return encoded
|
||||
|
||||
# Method 2: Hardware-accelerated encoding via GStreamer (if available)
|
||||
if self.nvenc_available:
|
||||
return self._encode_with_nvenc(frame, quality)
|
||||
|
||||
# Fallback: Standard OpenCV encoding
|
||||
encode_params = [cv2.IMWRITE_JPEG_QUALITY, quality]
|
||||
success, encoded = cv2.imencode('.jpg', frame, encode_params)
|
||||
if success:
|
||||
return encoded.tobytes()
|
||||
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to encode frame: {e}")
|
||||
return None
|
||||
|
||||
def _encode_with_nvenc(self, frame: np.ndarray, quality: int) -> Optional[bytes]:
|
||||
"""
|
||||
Encode using NVIDIA NVENC hardware encoder.
|
||||
|
||||
This is complex to implement directly, so we'll use a GStreamer pipeline
|
||||
if available.
|
||||
"""
|
||||
try:
|
||||
# Create a GStreamer pipeline for hardware encoding
|
||||
height, width = frame.shape[:2]
|
||||
gst_pipeline = (
|
||||
f"appsrc ! "
|
||||
f"video/x-raw,format=BGR,width={width},height={height},framerate=30/1 ! "
|
||||
f"videoconvert ! "
|
||||
f"nvvideoconvert ! " # GPU color conversion
|
||||
f"nvjpegenc quality={quality} ! " # Hardware JPEG encoder
|
||||
f"appsink"
|
||||
)
|
||||
|
||||
# This would require GStreamer Python bindings
|
||||
# For now, fall back to TurboJPEG or standard encoding
|
||||
logger.debug("NVENC JPEG encoding not fully implemented, using fallback")
|
||||
encode_params = [cv2.IMWRITE_JPEG_QUALITY, quality]
|
||||
success, encoded = cv2.imencode('.jpg', frame, encode_params)
|
||||
if success:
|
||||
return encoded.tobytes()
|
||||
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"NVENC encoding failed: {e}")
|
||||
return None
|
||||
|
||||
def encode_batch(self, frames: list, quality: int = 85) -> list:
|
||||
"""
|
||||
Batch encode multiple frames for better GPU utilization.
|
||||
|
||||
Args:
|
||||
frames: List of BGR frames
|
||||
quality: JPEG quality
|
||||
|
||||
Returns:
|
||||
List of encoded JPEG bytes
|
||||
"""
|
||||
encoded_frames = []
|
||||
|
||||
if self.turbojpeg_available:
|
||||
# TurboJPEG can handle batch encoding efficiently
|
||||
for frame in frames:
|
||||
rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
|
||||
encoded = self.turbojpeg.encode(rgb_frame, quality=quality)
|
||||
encoded_frames.append(encoded)
|
||||
else:
|
||||
# Fallback to sequential encoding
|
||||
for frame in frames:
|
||||
encoded = self.encode_jpeg(frame, quality)
|
||||
encoded_frames.append(encoded)
|
||||
|
||||
return encoded_frames
|
||||
|
||||
|
||||
# Global encoder instance
|
||||
_hardware_encoder = None
|
||||
|
||||
|
||||
def get_hardware_encoder() -> HardwareEncoder:
|
||||
"""Get or create the global hardware encoder instance."""
|
||||
global _hardware_encoder
|
||||
if _hardware_encoder is None:
|
||||
_hardware_encoder = HardwareEncoder()
|
||||
return _hardware_encoder
|
||||
|
||||
|
||||
def encode_frame_hardware(frame: np.ndarray, quality: int = 85) -> Optional[bytes]:
|
||||
"""
|
||||
Convenience function to encode a frame using hardware acceleration.
|
||||
|
||||
Args:
|
||||
frame: BGR image frame
|
||||
quality: JPEG quality (1-100)
|
||||
|
||||
Returns:
|
||||
Encoded JPEG bytes or None on failure
|
||||
"""
|
||||
encoder = get_hardware_encoder()
|
||||
return encoder.encode_jpeg(frame, quality)
|
||||
|
|
@ -1,51 +0,0 @@
|
|||
import cv2
|
||||
import gi
|
||||
import time
|
||||
|
||||
gi.require_version('Gst', '1.0')
|
||||
from gi.repository import Gst
|
||||
|
||||
# Initialize GStreamer
|
||||
Gst.init(None)
|
||||
|
||||
# Open the default webcam
|
||||
cap = cv2.VideoCapture(0)
|
||||
|
||||
# Define the RTSP pipeline using GStreamer
|
||||
rtsp_pipeline = (
|
||||
"appsrc ! videoconvert ! video/x-raw,format=I420 ! x264enc tune=zerolatency bitrate=2048 speed-preset=ultrafast "
|
||||
"! rtph264pay config-interval=1 pt=96 ! udpsink host=127.0.0.1 port=8554"
|
||||
)
|
||||
|
||||
# Create GStreamer pipeline
|
||||
pipeline = Gst.parse_launch(rtsp_pipeline)
|
||||
appsrc = pipeline.get_by_name("appsrc")
|
||||
|
||||
# Start streaming
|
||||
pipeline.set_state(Gst.State.PLAYING)
|
||||
time.sleep(1)
|
||||
|
||||
while cap.isOpened():
|
||||
ret, frame = cap.read()
|
||||
if not ret:
|
||||
break
|
||||
|
||||
# Convert frame to I420 format (YUV420)
|
||||
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2YUV_I420)
|
||||
data = frame.tobytes()
|
||||
|
||||
# Push frame to GStreamer pipeline
|
||||
buf = Gst.Buffer.new_allocate(None, len(data), None)
|
||||
buf.fill(0, data)
|
||||
appsrc.emit("push-buffer", buf)
|
||||
|
||||
# Display frame locally (optional)
|
||||
cv2.imshow("RTSP Streaming", frame)
|
||||
|
||||
if cv2.waitKey(1) & 0xFF == ord('q'):
|
||||
break
|
||||
|
||||
# Cleanup
|
||||
cap.release()
|
||||
cv2.destroyAllWindows()
|
||||
pipeline.set_state(Gst.State.NULL)
|
||||
|
|
@ -1,137 +0,0 @@
|
|||
import argparse
|
||||
import os
|
||||
import cv2
|
||||
import time
|
||||
import logging
|
||||
import shutil
|
||||
import threading # added threading
|
||||
import yaml # for silencing YOLO
|
||||
|
||||
from siwatsystem.pympta import load_pipeline_from_zip, run_pipeline
|
||||
|
||||
# Configure logging
|
||||
logging.basicConfig(level=logging.INFO, format="%(asctime)s [%(levelname)s] %(message)s")
|
||||
|
||||
# Silence YOLO logging
|
||||
os.environ["YOLO_VERBOSE"] = "False"
|
||||
for logger_name in ["ultralytics", "ultralytics.hub", "ultralytics.yolo.utils"]:
|
||||
logging.getLogger(logger_name).setLevel(logging.WARNING)
|
||||
|
||||
# Global variables for frame sharing
|
||||
global_frame = None
|
||||
global_ret = False
|
||||
capture_running = False
|
||||
|
||||
def video_capture_loop(cap):
|
||||
global global_frame, global_ret, capture_running
|
||||
while capture_running:
|
||||
global_ret, global_frame = cap.read()
|
||||
time.sleep(0.01) # slight delay to reduce CPU usage
|
||||
|
||||
def clear_cache(cache_dir: str):
|
||||
if os.path.exists(cache_dir):
|
||||
shutil.rmtree(cache_dir)
|
||||
|
||||
def log_pipeline_flow(frame, model_tree, level=0):
|
||||
"""
|
||||
Wrapper around run_pipeline that logs the model flow and detection results.
|
||||
Returns the same output as the original run_pipeline function.
|
||||
"""
|
||||
indent = " " * level
|
||||
model_id = model_tree.get("modelId", "unknown")
|
||||
logging.info(f"{indent}→ Running model: {model_id}")
|
||||
|
||||
detection, bbox = run_pipeline(frame, model_tree, return_bbox=True)
|
||||
|
||||
if detection:
|
||||
confidence = detection.get("confidence", 0) * 100
|
||||
class_name = detection.get("class", "unknown")
|
||||
object_id = detection.get("id", "N/A")
|
||||
|
||||
logging.info(f"{indent}✓ Detected: {class_name} (ID: {object_id}, confidence: {confidence:.1f}%)")
|
||||
|
||||
# Check if any branches were triggered
|
||||
triggered = False
|
||||
for branch in model_tree.get("branches", []):
|
||||
trigger_classes = branch.get("triggerClasses", [])
|
||||
min_conf = branch.get("minConfidence", 0)
|
||||
|
||||
if class_name in trigger_classes and detection.get("confidence", 0) >= min_conf:
|
||||
triggered = True
|
||||
if branch.get("crop", False) and bbox:
|
||||
x1, y1, x2, y2 = bbox
|
||||
cropped_frame = frame[y1:y2, x1:x2]
|
||||
logging.info(f"{indent} ⌊ Triggering branch with cropped region {x1},{y1} to {x2},{y2}")
|
||||
branch_result = log_pipeline_flow(cropped_frame, branch, level + 1)
|
||||
else:
|
||||
logging.info(f"{indent} ⌊ Triggering branch with full frame")
|
||||
branch_result = log_pipeline_flow(frame, branch, level + 1)
|
||||
|
||||
if branch_result[0]: # If branch detection successful, return it
|
||||
return branch_result
|
||||
|
||||
if not triggered and model_tree.get("branches"):
|
||||
logging.info(f"{indent} ⌊ No branches triggered")
|
||||
else:
|
||||
logging.info(f"{indent}✗ No detection for {model_id}")
|
||||
|
||||
return detection, bbox
|
||||
|
||||
def main(mpta_file: str, video_source: str):
|
||||
global capture_running
|
||||
CACHE_DIR = os.path.join(".", ".mptacache")
|
||||
clear_cache(CACHE_DIR)
|
||||
logging.info(f"Loading pipeline from local file: {mpta_file}")
|
||||
model_tree = load_pipeline_from_zip(mpta_file, CACHE_DIR)
|
||||
if model_tree is None:
|
||||
logging.error("Failed to load pipeline.")
|
||||
return
|
||||
|
||||
cap = cv2.VideoCapture(video_source)
|
||||
if not cap.isOpened():
|
||||
logging.error(f"Cannot open video source {video_source}")
|
||||
return
|
||||
|
||||
# Start video capture in a separate thread
|
||||
capture_running = True
|
||||
capture_thread = threading.Thread(target=video_capture_loop, args=(cap,))
|
||||
capture_thread.start()
|
||||
|
||||
logging.info("Press 'q' to exit.")
|
||||
try:
|
||||
while True:
|
||||
# Use the global frame and ret updated by the thread
|
||||
if not global_ret or global_frame is None:
|
||||
continue # wait until a frame is available
|
||||
|
||||
frame = global_frame.copy() # local copy to work with
|
||||
|
||||
# Replace run_pipeline with our logging version
|
||||
detection, bbox = log_pipeline_flow(frame, model_tree)
|
||||
|
||||
if bbox:
|
||||
x1, y1, x2, y2 = bbox
|
||||
cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
|
||||
label = detection["class"] if detection else "Detection"
|
||||
cv2.putText(frame, label, (x1, y1 - 10),
|
||||
cv2.FONT_HERSHEY_SIMPLEX, 0.9, (36, 255, 12), 2)
|
||||
|
||||
cv2.imshow("Pipeline Webcam", frame)
|
||||
if cv2.waitKey(1) & 0xFF == ord('q'):
|
||||
break
|
||||
finally:
|
||||
# Stop capture thread and cleanup
|
||||
capture_running = False
|
||||
capture_thread.join()
|
||||
cap.release()
|
||||
cv2.destroyAllWindows()
|
||||
clear_cache(CACHE_DIR)
|
||||
logging.info("Cleaned up .mptacache directory on shutdown.")
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser(description="Run pipeline webcam utility.")
|
||||
parser.add_argument("--mpta-file", type=str, required=True, help="Path to the local pipeline mpta (ZIP) file.")
|
||||
parser.add_argument("--video", type=str, default="0", help="Video source (default webcam index 0).")
|
||||
args = parser.parse_args()
|
||||
video_source = int(args.video) if args.video.isdigit() else args.video
|
||||
main(args.mpta_file, video_source)
|
||||
327
pympta.md
327
pympta.md
|
|
@ -1,327 +0,0 @@
|
|||
# pympta: Modular Pipeline Task Executor
|
||||
|
||||
`pympta` is a Python module designed to load and execute modular, multi-stage AI pipelines defined in a special package format (`.mpta`). It is primarily used within the detector worker to run complex computer vision tasks where the output of one model can trigger a subsequent model on a specific region of interest.
|
||||
|
||||
## Core Concepts
|
||||
|
||||
### 1. MPTA Package (`.mpta`)
|
||||
|
||||
An `.mpta` file is a standard `.zip` archive with a different extension. It bundles all the necessary components for a pipeline to run.
|
||||
|
||||
A typical `.mpta` file has the following structure:
|
||||
|
||||
```
|
||||
my_pipeline.mpta/
|
||||
├── pipeline.json
|
||||
├── model1.pt
|
||||
├── model2.pt
|
||||
└── ...
|
||||
```
|
||||
|
||||
- **`pipeline.json`**: (Required) The manifest file that defines the structure of the pipeline, the models to use, and the logic connecting them.
|
||||
- **Model Files (`.pt`, etc.)**: The actual pre-trained model files (e.g., PyTorch, ONNX). The pipeline currently uses `ultralytics.YOLO` models.
|
||||
|
||||
### 2. Pipeline Structure
|
||||
|
||||
A pipeline is a tree-like structure of "nodes," defined in `pipeline.json`.
|
||||
|
||||
- **Root Node**: The entry point of the pipeline. It processes the initial, full-frame image.
|
||||
- **Branch Nodes**: Child nodes that are triggered by specific detection results from their parent. For example, a root node might detect a "vehicle," which then triggers a branch node to detect a "license plate" within the vehicle's bounding box.
|
||||
|
||||
This modular structure allows for creating complex and efficient inference logic, avoiding the need to run every model on every frame.
|
||||
|
||||
## `pipeline.json` Specification
|
||||
|
||||
This file defines the entire pipeline logic. The root object contains a `pipeline` key for the pipeline definition, optional `redis` key for Redis configuration, and optional `postgresql` key for database integration.
|
||||
|
||||
### Top-Level Object Structure
|
||||
|
||||
| Key | Type | Required | Description |
|
||||
| ------------ | ------ | -------- | ------------------------------------------------------- |
|
||||
| `pipeline` | Object | Yes | The root node object of the pipeline. |
|
||||
| `redis` | Object | No | Configuration for connecting to a Redis server. |
|
||||
| `postgresql` | Object | No | Configuration for connecting to a PostgreSQL database. |
|
||||
|
||||
### Redis Configuration (`redis`)
|
||||
|
||||
| Key | Type | Required | Description |
|
||||
| ---------- | ------ | -------- | ------------------------------------------------------- |
|
||||
| `host` | String | Yes | The hostname or IP address of the Redis server. |
|
||||
| `port` | Number | Yes | The port number of the Redis server. |
|
||||
| `password` | String | No | The password for Redis authentication. |
|
||||
| `db` | Number | No | The Redis database number to use. Defaults to `0`. |
|
||||
|
||||
### PostgreSQL Configuration (`postgresql`)
|
||||
|
||||
| Key | Type | Required | Description |
|
||||
| ---------- | ------ | -------- | ------------------------------------------------------- |
|
||||
| `host` | String | Yes | The hostname or IP address of the PostgreSQL server. |
|
||||
| `port` | Number | Yes | The port number of the PostgreSQL server. |
|
||||
| `database` | String | Yes | The database name to connect to. |
|
||||
| `username` | String | Yes | The username for database authentication. |
|
||||
| `password` | String | Yes | The password for database authentication. |
|
||||
|
||||
### Node Object Structure
|
||||
|
||||
| Key | Type | Required | Description |
|
||||
| ------------------- | ------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `modelId` | String | Yes | A unique identifier for this model node (e.g., "vehicle-detector"). |
|
||||
| `modelFile` | String | Yes | The path to the model file within the `.mpta` archive (e.g., "yolov8n.pt"). |
|
||||
| `minConfidence` | Float | Yes | The minimum confidence score (0.0 to 1.0) required for a detection to be considered valid and potentially trigger a branch. |
|
||||
| `triggerClasses` | Array<String> | Yes | A list of class names that, when detected by the parent, can trigger this node. For the root node, this lists all classes of interest. |
|
||||
| `crop` | Boolean | No | If `true`, the image is cropped to the parent's detection bounding box before being passed to this node's model. Defaults to `false`. |
|
||||
| `cropClass` | String | No | The specific class to use for cropping (e.g., "Frontal" for frontal view cropping). |
|
||||
| `multiClass` | Boolean | No | If `true`, enables multi-class detection mode where multiple classes can be detected simultaneously. |
|
||||
| `expectedClasses` | Array<String> | No | When `multiClass` is true, defines which classes are expected. At least one must be detected for processing to continue. |
|
||||
| `parallel` | Boolean | No | If `true`, this branch will be processed in parallel with other parallel branches. |
|
||||
| `branches` | Array<Node> | No | A list of child node objects that can be triggered by this node's detections. |
|
||||
| `actions` | Array<Action> | No | A list of actions to execute upon a successful detection in this node. |
|
||||
| `parallelActions` | Array<Action> | No | A list of actions to execute after all specified branches have completed. |
|
||||
|
||||
### Action Object Structure
|
||||
|
||||
Actions allow the pipeline to interact with Redis and PostgreSQL databases. They are executed sequentially for a given detection.
|
||||
|
||||
#### Action Context & Dynamic Keys
|
||||
|
||||
All actions have access to a dynamic context for formatting keys and messages. The context is created for each detection event and includes:
|
||||
|
||||
- All key-value pairs from the detection result (e.g., `class`, `confidence`, `id`).
|
||||
- `{timestamp_ms}`: The current Unix timestamp in milliseconds.
|
||||
- `{timestamp}`: Formatted timestamp string (YYYY-MM-DDTHH-MM-SS).
|
||||
- `{uuid}`: A unique identifier (UUID4) for the detection event.
|
||||
- `{filename}`: Generated filename with UUID.
|
||||
- `{camera_id}`: Full camera subscription identifier.
|
||||
- `{display_id}`: Display identifier extracted from subscription.
|
||||
- `{session_id}`: Session ID for database operations.
|
||||
- `{image_key}`: If a `redis_save_image` action has already been executed for this event, this placeholder will be replaced with the key where the image was stored.
|
||||
|
||||
#### `redis_save_image`
|
||||
|
||||
Saves the current image frame (or cropped sub-image) to a Redis key.
|
||||
|
||||
| Key | Type | Required | Description |
|
||||
| ---------------- | ------ | -------- | ------------------------------------------------------------------------------------------------------- |
|
||||
| `type` | String | Yes | Must be `"redis_save_image"`. |
|
||||
| `key` | String | Yes | The Redis key to save the image to. Can contain any of the dynamic placeholders. |
|
||||
| `region` | String | No | Specific detected region to crop and save (e.g., "Frontal"). |
|
||||
| `format` | String | No | Image format: "jpeg" or "png". Defaults to "jpeg". |
|
||||
| `quality` | Number | No | JPEG quality (1-100). Defaults to 90. |
|
||||
| `expire_seconds` | Number | No | If provided, sets an expiration time (in seconds) for the Redis key. |
|
||||
|
||||
#### `redis_publish`
|
||||
|
||||
Publishes a message to a Redis channel.
|
||||
|
||||
| Key | Type | Required | Description |
|
||||
| --------- | ------ | -------- | ------------------------------------------------------------------------------------------------------- |
|
||||
| `type` | String | Yes | Must be `"redis_publish"`. |
|
||||
| `channel` | String | Yes | The Redis channel to publish the message to. |
|
||||
| `message` | String | Yes | The message to publish. Can contain any of the dynamic placeholders, including `{image_key}`. |
|
||||
|
||||
#### `postgresql_update_combined`
|
||||
|
||||
Updates PostgreSQL database with results from multiple branches after they complete.
|
||||
|
||||
| Key | Type | Required | Description |
|
||||
| ------------------ | ------------- | -------- | ------------------------------------------------------------------------------------------------------- |
|
||||
| `type` | String | Yes | Must be `"postgresql_update_combined"`. |
|
||||
| `table` | String | Yes | The database table name (will be prefixed with `gas_station_1.` schema). |
|
||||
| `key_field` | String | Yes | The field to use as the update key (typically "session_id"). |
|
||||
| `key_value` | String | Yes | Template for the key value (e.g., "{session_id}"). |
|
||||
| `waitForBranches` | Array<String> | Yes | List of branch model IDs to wait for completion before executing update. |
|
||||
| `fields` | Object | Yes | Field mapping object where keys are database columns and values are templates (e.g., "{branch.field}").|
|
||||
|
||||
### Complete Example `pipeline.json`
|
||||
|
||||
This example demonstrates a comprehensive pipeline for vehicle detection with parallel classification and database integration:
|
||||
|
||||
```json
|
||||
{
|
||||
"redis": {
|
||||
"host": "10.100.1.3",
|
||||
"port": 6379,
|
||||
"password": "your-redis-password",
|
||||
"db": 0
|
||||
},
|
||||
"postgresql": {
|
||||
"host": "10.100.1.3",
|
||||
"port": 5432,
|
||||
"database": "inference",
|
||||
"username": "root",
|
||||
"password": "your-db-password"
|
||||
},
|
||||
"pipeline": {
|
||||
"modelId": "car_frontal_detection_v1",
|
||||
"modelFile": "car_frontal_detection_v1.pt",
|
||||
"crop": false,
|
||||
"triggerClasses": ["Car", "Frontal"],
|
||||
"minConfidence": 0.8,
|
||||
"multiClass": true,
|
||||
"expectedClasses": ["Car", "Frontal"],
|
||||
"actions": [
|
||||
{
|
||||
"type": "redis_save_image",
|
||||
"region": "Frontal",
|
||||
"key": "inference:{display_id}:{timestamp}:{session_id}:{filename}",
|
||||
"expire_seconds": 600,
|
||||
"format": "jpeg",
|
||||
"quality": 90
|
||||
},
|
||||
{
|
||||
"type": "redis_publish",
|
||||
"channel": "car_detections",
|
||||
"message": "{\"event\":\"frontal_detected\"}"
|
||||
}
|
||||
],
|
||||
"branches": [
|
||||
{
|
||||
"modelId": "car_brand_cls_v1",
|
||||
"modelFile": "car_brand_cls_v1.pt",
|
||||
"crop": true,
|
||||
"cropClass": "Frontal",
|
||||
"resizeTarget": [224, 224],
|
||||
"triggerClasses": ["Frontal"],
|
||||
"minConfidence": 0.85,
|
||||
"parallel": true,
|
||||
"branches": []
|
||||
},
|
||||
{
|
||||
"modelId": "car_bodytype_cls_v1",
|
||||
"modelFile": "car_bodytype_cls_v1.pt",
|
||||
"crop": true,
|
||||
"cropClass": "Car",
|
||||
"resizeTarget": [224, 224],
|
||||
"triggerClasses": ["Car"],
|
||||
"minConfidence": 0.85,
|
||||
"parallel": true,
|
||||
"branches": []
|
||||
}
|
||||
],
|
||||
"parallelActions": [
|
||||
{
|
||||
"type": "postgresql_update_combined",
|
||||
"table": "car_frontal_info",
|
||||
"key_field": "session_id",
|
||||
"key_value": "{session_id}",
|
||||
"waitForBranches": ["car_brand_cls_v1", "car_bodytype_cls_v1"],
|
||||
"fields": {
|
||||
"car_brand": "{car_brand_cls_v1.brand}",
|
||||
"car_body_type": "{car_bodytype_cls_v1.body_type}"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## API Reference
|
||||
|
||||
The `pympta` module exposes two main functions.
|
||||
|
||||
### `load_pipeline_from_zip(zip_source: str, target_dir: str) -> dict`
|
||||
|
||||
Loads, extracts, and parses an `.mpta` file to build a pipeline tree in memory. It also establishes Redis and PostgreSQL connections if configured in `pipeline.json`.
|
||||
|
||||
- **Parameters:**
|
||||
- `zip_source` (str): The file path to the local `.mpta` zip archive.
|
||||
- `target_dir` (str): A directory path where the archive's contents will be extracted.
|
||||
- **Returns:**
|
||||
- A dictionary representing the root node of the pipeline, ready to be used with `run_pipeline`. Returns `None` if loading fails.
|
||||
|
||||
### `run_pipeline(frame, node: dict, return_bbox: bool = False, context: dict = None)`
|
||||
|
||||
Executes the inference pipeline on a single image frame.
|
||||
|
||||
- **Parameters:**
|
||||
- `frame`: The input image frame (e.g., a NumPy array from OpenCV).
|
||||
- `node` (dict): The pipeline node to execute (typically the root node returned by `load_pipeline_from_zip`).
|
||||
- `return_bbox` (bool): If `True`, the function returns a tuple `(detection, bounding_box)`. Otherwise, it returns only the `detection`.
|
||||
- `context` (dict): Optional context dictionary containing camera_id, display_id, session_id for action formatting.
|
||||
- **Returns:**
|
||||
- The final detection result from the last executed node in the chain. A detection is a dictionary like `{'class': 'car', 'confidence': 0.95, 'id': 1}`. If no detection meets the criteria, it returns `None` (or `(None, None)` if `return_bbox` is `True`).
|
||||
|
||||
## Database Integration
|
||||
|
||||
The pipeline system includes automatic PostgreSQL database management:
|
||||
|
||||
### Table Schema (`gas_station_1.car_frontal_info`)
|
||||
|
||||
The system automatically creates and manages the following table structure:
|
||||
|
||||
```sql
|
||||
CREATE TABLE IF NOT EXISTS gas_station_1.car_frontal_info (
|
||||
display_id VARCHAR(255),
|
||||
captured_timestamp VARCHAR(255),
|
||||
session_id VARCHAR(255) PRIMARY KEY,
|
||||
license_character VARCHAR(255) DEFAULT NULL,
|
||||
license_type VARCHAR(255) DEFAULT 'No model available',
|
||||
car_brand VARCHAR(255) DEFAULT NULL,
|
||||
car_model VARCHAR(255) DEFAULT NULL,
|
||||
car_body_type VARCHAR(255) DEFAULT NULL,
|
||||
created_at TIMESTAMP DEFAULT NOW(),
|
||||
updated_at TIMESTAMP DEFAULT NOW()
|
||||
);
|
||||
```
|
||||
|
||||
### Workflow
|
||||
|
||||
1. **Initial Record Creation**: When both "Car" and "Frontal" are detected, an initial database record is created with a UUID session_id.
|
||||
2. **Redis Storage**: Vehicle images are stored in Redis with keys containing the session_id.
|
||||
3. **Parallel Classification**: Brand and body type classification run concurrently.
|
||||
4. **Database Update**: After all branches complete, the database record is updated with classification results.
|
||||
|
||||
## Usage Example
|
||||
|
||||
This snippet shows how to use `pympta` with the enhanced features:
|
||||
|
||||
```python
|
||||
import cv2
|
||||
from siwatsystem.pympta import load_pipeline_from_zip, run_pipeline
|
||||
|
||||
# 1. Define paths
|
||||
MPTA_FILE = "path/to/your/pipeline.mpta"
|
||||
CACHE_DIR = ".mptacache"
|
||||
|
||||
# 2. Load the pipeline from the .mpta file
|
||||
# This reads pipeline.json and loads the YOLO models into memory.
|
||||
model_tree = load_pipeline_from_zip(MPTA_FILE, CACHE_DIR)
|
||||
|
||||
if not model_tree:
|
||||
print("Failed to load pipeline.")
|
||||
exit()
|
||||
|
||||
# 3. Open a video source
|
||||
cap = cv2.VideoCapture(0)
|
||||
|
||||
while True:
|
||||
ret, frame = cap.read()
|
||||
if not ret:
|
||||
break
|
||||
|
||||
# 4. Run the pipeline on the current frame with context
|
||||
context = {
|
||||
"camera_id": "display-001;cam-001",
|
||||
"display_id": "display-001",
|
||||
"session_id": None # Will be generated automatically
|
||||
}
|
||||
|
||||
detection_result, bounding_box = run_pipeline(frame, model_tree, return_bbox=True, context=context)
|
||||
|
||||
# 5. Display the results
|
||||
if detection_result:
|
||||
print(f"Detected: {detection_result['class']} with confidence {detection_result['confidence']:.2f}")
|
||||
if bounding_box:
|
||||
x1, y1, x2, y2 = bounding_box
|
||||
cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
|
||||
cv2.putText(frame, detection_result['class'], (x1, y1 - 10),
|
||||
cv2.FONT_HERSHEY_SIMPLEX, 0.9, (36, 255, 12), 2)
|
||||
|
||||
cv2.imshow("Pipeline Output", frame)
|
||||
|
||||
if cv2.waitKey(1) & 0xFF == ord('q'):
|
||||
break
|
||||
|
||||
cap.release()
|
||||
cv2.destroyAllWindows()
|
||||
```
|
||||
|
|
@ -1,12 +0,0 @@
|
|||
torch
|
||||
torchvision
|
||||
ultralytics
|
||||
opencv-python
|
||||
scipy
|
||||
filterpy
|
||||
psycopg2-binary
|
||||
lap>=0.5.12
|
||||
pynvml
|
||||
PyTurboJPEG
|
||||
PyNvVideoCodec
|
||||
cupy-cuda12x
|
||||
|
|
@ -1,9 +1,7 @@
|
|||
fastapi
|
||||
uvicorn
|
||||
websockets
|
||||
fastapi[standard]
|
||||
redis
|
||||
urllib3<2.0.0
|
||||
numpy
|
||||
requests
|
||||
watchdog
|
||||
torch
|
||||
torchvision
|
||||
ultralytics
|
||||
opencv-python
|
||||
lapx
|
||||
125
test_protocol.py
125
test_protocol.py
|
|
@ -1,125 +0,0 @@
|
|||
#!/usr/bin/env python3
|
||||
"""
|
||||
Test script to verify the worker implementation follows the protocol
|
||||
"""
|
||||
import json
|
||||
import asyncio
|
||||
import websockets
|
||||
import time
|
||||
|
||||
async def test_protocol():
|
||||
"""Test the worker protocol implementation"""
|
||||
uri = "ws://localhost:8001"
|
||||
|
||||
try:
|
||||
async with websockets.connect(uri) as websocket:
|
||||
print("✓ Connected to worker")
|
||||
|
||||
# Test 1: Check if we receive heartbeat (stateReport)
|
||||
print("\n1. Testing heartbeat...")
|
||||
try:
|
||||
message = await asyncio.wait_for(websocket.recv(), timeout=5)
|
||||
data = json.loads(message)
|
||||
if data.get("type") == "stateReport":
|
||||
print("✓ Received stateReport heartbeat")
|
||||
print(f" - CPU Usage: {data.get('cpuUsage', 'N/A')}%")
|
||||
print(f" - Memory Usage: {data.get('memoryUsage', 'N/A')}%")
|
||||
print(f" - Camera Connections: {len(data.get('cameraConnections', []))}")
|
||||
else:
|
||||
print(f"✗ Expected stateReport, got {data.get('type')}")
|
||||
except asyncio.TimeoutError:
|
||||
print("✗ No heartbeat received within 5 seconds")
|
||||
|
||||
# Test 2: Request state
|
||||
print("\n2. Testing requestState...")
|
||||
await websocket.send(json.dumps({"type": "requestState"}))
|
||||
try:
|
||||
message = await asyncio.wait_for(websocket.recv(), timeout=5)
|
||||
data = json.loads(message)
|
||||
if data.get("type") == "stateReport":
|
||||
print("✓ Received stateReport response")
|
||||
else:
|
||||
print(f"✗ Expected stateReport, got {data.get('type')}")
|
||||
except asyncio.TimeoutError:
|
||||
print("✗ No response to requestState within 5 seconds")
|
||||
|
||||
# Test 3: Set session ID
|
||||
print("\n3. Testing setSessionId...")
|
||||
session_message = {
|
||||
"type": "setSessionId",
|
||||
"payload": {
|
||||
"displayIdentifier": "display-001",
|
||||
"sessionId": 12345
|
||||
}
|
||||
}
|
||||
await websocket.send(json.dumps(session_message))
|
||||
print("✓ Sent setSessionId message")
|
||||
|
||||
# Test 4: Test patchSession
|
||||
print("\n4. Testing patchSession...")
|
||||
patch_message = {
|
||||
"type": "patchSession",
|
||||
"sessionId": 12345,
|
||||
"data": {
|
||||
"currentCar": {
|
||||
"carModel": "Civic",
|
||||
"carBrand": "Honda"
|
||||
}
|
||||
}
|
||||
}
|
||||
await websocket.send(json.dumps(patch_message))
|
||||
|
||||
# Wait for patchSessionResult
|
||||
try:
|
||||
message = await asyncio.wait_for(websocket.recv(), timeout=5)
|
||||
data = json.loads(message)
|
||||
if data.get("type") == "patchSessionResult":
|
||||
print("✓ Received patchSessionResult")
|
||||
print(f" - Success: {data.get('payload', {}).get('success')}")
|
||||
print(f" - Message: {data.get('payload', {}).get('message')}")
|
||||
else:
|
||||
print(f"✗ Expected patchSessionResult, got {data.get('type')}")
|
||||
except asyncio.TimeoutError:
|
||||
print("✗ No patchSessionResult received within 5 seconds")
|
||||
|
||||
# Test 5: Test subscribe message format (without actual camera)
|
||||
print("\n5. Testing subscribe message format...")
|
||||
subscribe_message = {
|
||||
"type": "subscribe",
|
||||
"payload": {
|
||||
"subscriptionIdentifier": "display-001;cam-001",
|
||||
"snapshotUrl": "http://example.com/snapshot.jpg",
|
||||
"snapshotInterval": 5000,
|
||||
"modelUrl": "http://example.com/model.mpta",
|
||||
"modelName": "Test Model",
|
||||
"modelId": 101,
|
||||
"cropX1": 100,
|
||||
"cropY1": 200,
|
||||
"cropX2": 300,
|
||||
"cropY2": 400
|
||||
}
|
||||
}
|
||||
await websocket.send(json.dumps(subscribe_message))
|
||||
print("✓ Sent subscribe message (will fail without actual camera/model)")
|
||||
|
||||
# Listen for a few more messages to catch any errors
|
||||
print("\n6. Listening for additional messages...")
|
||||
for i in range(3):
|
||||
try:
|
||||
message = await asyncio.wait_for(websocket.recv(), timeout=2)
|
||||
data = json.loads(message)
|
||||
msg_type = data.get("type")
|
||||
print(f" - Received {msg_type}")
|
||||
if msg_type == "error":
|
||||
print(f" Error: {data.get('error')}")
|
||||
except asyncio.TimeoutError:
|
||||
break
|
||||
|
||||
print("\n✓ Protocol test completed successfully!")
|
||||
|
||||
except Exception as e:
|
||||
print(f"✗ Connection failed: {e}")
|
||||
print("Make sure the worker is running on localhost:8001")
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(test_protocol())
|
||||
812
worker.md
812
worker.md
|
|
@ -1,812 +0,0 @@
|
|||
# Worker Communication Protocol
|
||||
|
||||
This document outlines the WebSocket-based communication protocol between the CMS backend and a detector worker. As a worker developer, your primary responsibility is to implement a WebSocket server that adheres to this protocol.
|
||||
|
||||
## 1. Connection
|
||||
|
||||
The worker must run a WebSocket server, preferably on port `8000`. The backend system, which is managed by a container orchestration service, will automatically discover and establish a WebSocket connection to your worker.
|
||||
|
||||
Upon a successful connection from the backend, you should begin sending `stateReport` messages as heartbeats.
|
||||
|
||||
## 2. Communication Overview
|
||||
|
||||
Communication is bidirectional and asynchronous. All messages are JSON objects with a `type` field that indicates the message's purpose, and an optional `payload` field containing the data.
|
||||
|
||||
- **Worker -> Backend:** You will send messages to the backend to report status, forward detection events, or request changes to session data.
|
||||
- **Backend -> Worker:** The backend will send commands to you to manage camera subscriptions.
|
||||
|
||||
### 2.1. Multi-Process Cluster Architecture
|
||||
|
||||
The backend uses a sophisticated multi-process cluster architecture with Redis-based coordination to manage worker connections at scale:
|
||||
|
||||
**Redis Communication Channels:**
|
||||
|
||||
- `worker:commands` - Commands sent TO workers (subscribe, unsubscribe, setSessionId, setProgressionStage)
|
||||
- `worker:responses` - Detection responses and state reports FROM workers
|
||||
- `worker:events` - Worker lifecycle events (connection, disconnection, health status)
|
||||
|
||||
**Distributed State Management:**
|
||||
|
||||
- `worker:states` - Redis hash map storing real-time worker performance metrics and connection status
|
||||
- `worker:assignments` - Redis hash map tracking camera-to-worker assignments across the cluster
|
||||
- `worker:owners` - Redis key-based worker ownership leases with 30-second TTL for automatic failover
|
||||
|
||||
**Load Balancing & Failover:**
|
||||
|
||||
- **Assignment Algorithm**: Workers are assigned based on subscription count and CPU usage
|
||||
- **Distributed Locking**: Assignment operations use Redis locks to prevent race conditions
|
||||
- **Automatic Failover**: Orphaned workers are detected via lease expiration and automatically reclaimed
|
||||
- **Horizontal Scaling**: New backend processes automatically join the cluster and participate in load balancing
|
||||
|
||||
**Inter-Process Coordination:**
|
||||
|
||||
- Each backend process maintains local WebSocket connections with workers
|
||||
- Commands are routed via Redis pub/sub to the process that owns the target worker connection
|
||||
- Master election ensures coordinated cluster management and prevents split-brain scenarios
|
||||
- Process identification uses UUIDs for clean process tracking and ownership management
|
||||
|
||||
## 3. Message Types and Command Structure
|
||||
|
||||
All worker communication follows a standardized message structure with the following command types:
|
||||
|
||||
**Commands from Backend to Worker:**
|
||||
|
||||
- `setSubscriptionList` - Set complete list of camera subscriptions for declarative state management
|
||||
- `setSessionId` - Associate a session ID with a display for detection linking
|
||||
- `setProgressionStage` - Update the progression stage for context-aware processing
|
||||
- `requestState` - Request immediate state report from worker
|
||||
- `patchSessionResult` - Response to worker's patch session request
|
||||
|
||||
**Messages from Worker to Backend:**
|
||||
|
||||
- `stateReport` - Periodic heartbeat with performance metrics and subscription status
|
||||
- `imageDetection` - Real-time detection results with timestamp and data
|
||||
- `patchSession` - Request to modify display persistent session data
|
||||
|
||||
**Command Structure:**
|
||||
|
||||
```typescript
|
||||
interface WorkerCommand {
|
||||
type: string;
|
||||
subscriptions?: SubscriptionObject[]; // For setSubscriptionList
|
||||
payload?: {
|
||||
displayIdentifier?: string;
|
||||
sessionId?: number | null;
|
||||
progressionStage?: string | null;
|
||||
// Additional payload fields based on command type
|
||||
};
|
||||
}
|
||||
|
||||
interface SubscriptionObject {
|
||||
subscriptionIdentifier: string; // Format: "displayId;cameraId"
|
||||
rtspUrl: string;
|
||||
snapshotUrl?: string;
|
||||
snapshotInterval?: number; // milliseconds
|
||||
modelUrl: string; // Fresh pre-signed URL (1-hour TTL)
|
||||
modelId: number;
|
||||
modelName: string;
|
||||
cropX1?: number;
|
||||
cropY1?: number;
|
||||
cropX2?: number;
|
||||
cropY2?: number;
|
||||
}
|
||||
```
|
||||
|
||||
## 4. Dynamic Configuration via MPTA File
|
||||
|
||||
To enable modularity and dynamic configuration, the backend will send you a URL to a `.mpta` file in each subscription within the `setSubscriptionList` command. This file is a renamed `.zip` archive that contains everything your worker needs to perform its task.
|
||||
|
||||
**Your worker is responsible for:**
|
||||
|
||||
1. Fetching this file from the provided URL.
|
||||
2. Extracting its contents.
|
||||
3. Interpreting the contents to configure its internal pipeline.
|
||||
|
||||
**The contents of the `.mpta` file are entirely up to the user who configures the model in the CMS.** This allows for maximum flexibility. For example, the archive could contain:
|
||||
|
||||
- AI/ML Models: Pre-trained models for libraries like TensorFlow, PyTorch, or ONNX.
|
||||
- Configuration Files: A `config.json` or `pipeline.yaml` that defines a sequence of operations, specifies model paths, or sets detection thresholds.
|
||||
- Scripts: Custom Python scripts for pre-processing or post-processing.
|
||||
- API Integration Details: A JSON file with endpoint information and credentials for interacting with third-party detection services.
|
||||
|
||||
Essentially, the `.mpta` file is a self-contained package that tells your worker _how_ to process the video stream for a given subscription.
|
||||
|
||||
## 5. Worker State Recovery and Reconnection
|
||||
|
||||
The system provides comprehensive state recovery mechanisms to ensure seamless operation across worker disconnections and backend restarts.
|
||||
|
||||
### 5.1. Automatic Resubscription
|
||||
|
||||
**Connection Recovery Flow:**
|
||||
|
||||
1. **Connection Detection**: Backend detects worker reconnection via WebSocket events
|
||||
2. **State Restoration**: All subscription states are restored from backend memory and Redis
|
||||
3. **Fresh Model URLs**: New model URLs are generated to handle S3 URL expiration
|
||||
4. **Session Recovery**: Session IDs and progression stages are automatically restored
|
||||
5. **Heartbeat Resumption**: Worker immediately begins sending state reports
|
||||
|
||||
### 5.2. State Persistence Architecture
|
||||
|
||||
**Backend State Storage:**
|
||||
|
||||
- **Local State**: Each backend process maintains `DetectorWorkerState` with active subscriptions
|
||||
- **Redis Coordination**: Assignment mappings stored in `worker:assignments` Redis hash
|
||||
- **Session Tracking**: Display session IDs tracked in display persistent data
|
||||
- **Progression Stages**: Current stages maintained in display controllers
|
||||
|
||||
**Recovery Guarantees:**
|
||||
|
||||
- **Zero Configuration Loss**: All subscription parameters are preserved across disconnections
|
||||
- **Session Continuity**: Active sessions remain linked after worker reconnection
|
||||
- **Stage Synchronization**: Progression stages are immediately synchronized on reconnection
|
||||
- **Model Availability**: Fresh model URLs ensure continuous access to detection models
|
||||
|
||||
### 5.3. Heartbeat and Health Monitoring
|
||||
|
||||
**Health Check Protocol:**
|
||||
|
||||
- **Heartbeat Interval**: Workers send `stateReport` every 2 seconds
|
||||
- **Timeout Detection**: Backend marks workers offline after 10-second timeout
|
||||
- **Automatic Recovery**: Offline workers are automatically rescheduled when they reconnect
|
||||
- **Performance Tracking**: CPU, memory, and GPU usage monitored for load balancing
|
||||
|
||||
**Failure Scenarios:**
|
||||
|
||||
- **Worker Crash**: Subscriptions are reassigned to other available workers
|
||||
- **Network Interruption**: Automatic reconnection with full state restoration
|
||||
- **Backend Restart**: Worker assignments are restored from Redis state
|
||||
- **Redis Failure**: Local state provides temporary operation until Redis recovers
|
||||
|
||||
### 5.4. Multi-Process Coordination
|
||||
|
||||
**Ownership and Leasing:**
|
||||
|
||||
- **Worker Ownership**: Each worker is owned by a single backend process via Redis lease
|
||||
- **Lease Renewal**: 30-second TTL leases automatically renewed by owning process
|
||||
- **Orphan Detection**: Expired leases allow worker reassignment to active processes
|
||||
- **Graceful Handover**: Clean ownership transfer during process shutdown
|
||||
|
||||
## 6. Messages from Worker to Backend
|
||||
|
||||
These are the messages your worker is expected to send to the backend.
|
||||
|
||||
### 6.1. State Report (Heartbeat)
|
||||
|
||||
This message is crucial for the backend to monitor your worker's health and status, including GPU usage.
|
||||
|
||||
- **Type:** `stateReport`
|
||||
- **When to Send:** Periodically (e.g., every 2 seconds) after a connection is established.
|
||||
|
||||
**Payload:**
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "stateReport",
|
||||
"cpuUsage": 75.5,
|
||||
"memoryUsage": 40.2,
|
||||
"gpuUsage": 60.0,
|
||||
"gpuMemoryUsage": 25.1,
|
||||
"cameraConnections": [
|
||||
{
|
||||
"subscriptionIdentifier": "display-001;cam-001",
|
||||
"modelId": 101,
|
||||
"modelName": "General Object Detection",
|
||||
"online": true,
|
||||
"cropX1": 100,
|
||||
"cropY1": 200,
|
||||
"cropX2": 300,
|
||||
"cropY2": 400
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
> **Note:**
|
||||
>
|
||||
> - `cropX1`, `cropY1`, `cropX2`, `cropY2` (optional, integer) should be included in each camera connection to indicate the crop coordinates for that subscription.
|
||||
|
||||
### 6.2. Image Detection
|
||||
|
||||
Sent when the worker detects a relevant object. The `detection` object should be flat and contain key-value pairs corresponding to the detected attributes.
|
||||
|
||||
- **Type:** `imageDetection`
|
||||
|
||||
**Payload Example:**
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "imageDetection",
|
||||
"subscriptionIdentifier": "display-001;cam-001",
|
||||
"timestamp": "2025-07-14T12:34:56.789Z",
|
||||
"data": {
|
||||
"detection": {
|
||||
"carModel": "Civic",
|
||||
"carBrand": "Honda",
|
||||
"carYear": 2023,
|
||||
"bodyType": "Sedan",
|
||||
"licensePlateText": "ABCD1234",
|
||||
"licensePlateConfidence": 0.95
|
||||
},
|
||||
"modelId": 101,
|
||||
"modelName": "US-LPR-and-Vehicle-ID"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### 6.3. Patch Session
|
||||
|
||||
> **Note:** Patch messages are only used when the worker can't keep up and needs to retroactively send detections. Normally, detections should be sent in real-time using `imageDetection` messages. Use `patchSession` only to update session data after the fact.
|
||||
|
||||
Allows the worker to request a modification to an active session's data. The `data` payload must be a partial object of the `DisplayPersistentData` structure.
|
||||
|
||||
- **Type:** `patchSession`
|
||||
|
||||
**Payload Example:**
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "patchSession",
|
||||
"sessionId": 12345,
|
||||
"data": {
|
||||
"currentCar": {
|
||||
"carModel": "Civic",
|
||||
"carBrand": "Honda",
|
||||
"licensePlateText": "ABCD1234"
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
The backend will respond with a `patchSessionResult` command.
|
||||
|
||||
#### `DisplayPersistentData` Structure
|
||||
|
||||
The `data` object in the `patchSession` message is merged with the existing `DisplayPersistentData` on the backend. Here is its structure:
|
||||
|
||||
```typescript
|
||||
interface DisplayPersistentData {
|
||||
progressionStage:
|
||||
| 'welcome'
|
||||
| 'car_fueling'
|
||||
| 'car_waitpayment'
|
||||
| 'car_postpayment'
|
||||
| null;
|
||||
qrCode: string | null;
|
||||
adsPlayback: {
|
||||
playlistSlotOrder: number; // The 'order' of the current slot
|
||||
adsId: number | null;
|
||||
adsUrl: string | null;
|
||||
} | null;
|
||||
currentCar: {
|
||||
carModel?: string;
|
||||
carBrand?: string;
|
||||
carYear?: number;
|
||||
bodyType?: string;
|
||||
licensePlateText?: string;
|
||||
licensePlateType?: string;
|
||||
} | null;
|
||||
fuelPump: {
|
||||
/* FuelPumpData structure */
|
||||
} | null;
|
||||
weatherData: {
|
||||
/* WeatherResponse structure */
|
||||
} | null;
|
||||
sessionId: number | null;
|
||||
}
|
||||
```
|
||||
|
||||
#### Patching Behavior
|
||||
|
||||
- The patch is a **deep merge**.
|
||||
- **`undefined`** values are ignored.
|
||||
- **`null`** values will set the corresponding field to `null`.
|
||||
- Nested objects are merged recursively.
|
||||
|
||||
## 7. Commands from Backend to Worker
|
||||
|
||||
These are the commands your worker will receive from the backend. The subscription system uses a **fully declarative approach** with `setSubscriptionList` - the backend sends the complete desired subscription list, and workers handle reconciliation internally.
|
||||
|
||||
### 7.1. Set Subscription List (Declarative Subscriptions)
|
||||
|
||||
**The primary subscription command that replaces individual subscribe/unsubscribe operations.**
|
||||
|
||||
Instructs the worker to process the complete list of camera streams. The worker must reconcile this list with its current subscriptions, adding new ones, removing obsolete ones, and updating existing ones as needed.
|
||||
|
||||
- **Type:** `setSubscriptionList`
|
||||
|
||||
**Payload:**
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "setSubscriptionList",
|
||||
"subscriptions": [
|
||||
{
|
||||
"subscriptionIdentifier": "display-001;cam-001",
|
||||
"rtspUrl": "rtsp://user:pass@host:port/stream1",
|
||||
"snapshotUrl": "http://go2rtc/snapshot/1",
|
||||
"snapshotInterval": 5000,
|
||||
"modelUrl": "http://storage/models/us-lpr.mpta?token=fresh-token",
|
||||
"modelName": "US-LPR-and-Vehicle-ID",
|
||||
"modelId": 102,
|
||||
"cropX1": 100,
|
||||
"cropY1": 200,
|
||||
"cropX2": 300,
|
||||
"cropY2": 400
|
||||
},
|
||||
{
|
||||
"subscriptionIdentifier": "display-002;cam-001",
|
||||
"rtspUrl": "rtsp://user:pass@host:port/stream1",
|
||||
"snapshotUrl": "http://go2rtc/snapshot/1",
|
||||
"snapshotInterval": 5000,
|
||||
"modelUrl": "http://storage/models/vehicle-detect.mpta?token=fresh-token",
|
||||
"modelName": "Vehicle Detection",
|
||||
"modelId": 201,
|
||||
"cropX1": 0,
|
||||
"cropY1": 0,
|
||||
"cropX2": 1920,
|
||||
"cropY2": 1080
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
**Declarative Subscription Behavior:**
|
||||
|
||||
- **Complete State Definition**: The backend sends the complete desired subscription list for this worker
|
||||
- **Worker-Side Reconciliation**: Workers compare the new list with current subscriptions and handle differences
|
||||
- **Fresh Model URLs**: Each command includes fresh pre-signed S3 URLs (1-hour TTL) for ML models
|
||||
- **Load Balancing**: The backend intelligently distributes subscriptions across available workers
|
||||
- **State Recovery**: Complete subscription list is sent on worker reconnection
|
||||
|
||||
**Worker Reconciliation Responsibility:**
|
||||
|
||||
When receiving a `setSubscriptionList` command, your worker must:
|
||||
|
||||
1. **Compare with Current State**: Identify new subscriptions, removed subscriptions, and updated subscriptions
|
||||
2. **Add New Subscriptions**: Start processing new camera streams with the provided configuration
|
||||
3. **Remove Obsolete Subscriptions**: Stop processing camera streams not in the new list
|
||||
4. **Update Existing Subscriptions**: Handle configuration changes (model updates, crop coordinates, etc.)
|
||||
5. **Maintain Single Streams**: Ensure only one RTSP stream per camera, even with multiple display bindings
|
||||
6. **Report Final State**: Send updated `stateReport` confirming the actual subscription state
|
||||
|
||||
> **Note:**
|
||||
>
|
||||
> - `cropX1`, `cropY1`, `cropX2`, `cropY2` (optional, integer) specify the crop coordinates for the camera stream
|
||||
> - `snapshotUrl` and `snapshotInterval` (optional) enable periodic snapshot capture
|
||||
> - Multiple subscriptions may share the same `rtspUrl` but have different `subscriptionIdentifier` values
|
||||
>
|
||||
> **Camera Stream Optimization:**
|
||||
> When multiple subscriptions share the same camera (same `rtspUrl`), your worker must:
|
||||
>
|
||||
> - Open the RTSP stream **once** for that camera
|
||||
> - Capture each frame/snapshot **once** per cycle
|
||||
> - Process the shared stream for each subscription's requirements (crop coordinates, model)
|
||||
> - Route detection results separately for each `subscriptionIdentifier`
|
||||
> - Apply display-specific crop coordinates during processing
|
||||
>
|
||||
> This optimization reduces bandwidth usage and ensures consistent detection timing across displays.
|
||||
|
||||
### 7.2. Request State
|
||||
|
||||
Direct request for the worker's current state. Respond with a `stateReport` message.
|
||||
|
||||
- **Type:** `requestState`
|
||||
|
||||
**Payload:**
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "requestState"
|
||||
}
|
||||
```
|
||||
|
||||
### 7.3. Patch Session Result
|
||||
|
||||
Backend's response to a `patchSession` message.
|
||||
|
||||
- **Type:** `patchSessionResult`
|
||||
|
||||
**Payload:**
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "patchSessionResult",
|
||||
"payload": {
|
||||
"sessionId": 12345,
|
||||
"success": true,
|
||||
"message": "Session updated successfully."
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### 7.4. Set Session ID
|
||||
|
||||
**Real-time session association for linking detection events to user sessions.**
|
||||
|
||||
Allows the backend to instruct the worker to associate a session ID with a display. This enables linking detection events to specific user sessions. The system automatically propagates session changes across all worker processes via Redis pub/sub.
|
||||
|
||||
- **Type:** `setSessionId`
|
||||
|
||||
**Payload:**
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "setSessionId",
|
||||
"payload": {
|
||||
"displayIdentifier": "display-001",
|
||||
"sessionId": 12345
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Or to clear the session:
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "setSessionId",
|
||||
"payload": {
|
||||
"displayIdentifier": "display-001",
|
||||
"sessionId": null
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Session Management Flow:**
|
||||
|
||||
1. **Session Creation**: When a new session is created (user interaction), the backend immediately sends `setSessionId` to all relevant workers
|
||||
2. **Cross-Process Distribution**: The command is distributed across multiple backend processes via Redis `worker:commands` channel
|
||||
3. **Worker State Synchronization**: Workers maintain session IDs for each display and apply them to all matching subscriptions
|
||||
4. **Automatic Recovery**: Session IDs are restored when workers reconnect, ensuring no session context is lost
|
||||
5. **Multi-Subscription Support**: A single session ID applies to all camera subscriptions for the given display
|
||||
|
||||
**Worker Responsibility:**
|
||||
|
||||
- Store the session ID for the given `displayIdentifier`
|
||||
- Apply the session ID to **all active subscriptions** that start with `displayIdentifier;` (e.g., `display-001;cam-001`, `display-001;cam-002`)
|
||||
- Include the session ID in subsequent `imageDetection` and `patchSession` messages
|
||||
- Handle session clearing when `sessionId` is `null`
|
||||
- Restore session IDs from backend state after reconnection
|
||||
|
||||
**Multi-Process Coordination:**
|
||||
|
||||
The session ID command uses the distributed worker communication system:
|
||||
|
||||
- Commands are routed via Redis pub/sub to the process managing the target worker
|
||||
- Automatic failover ensures session updates reach workers even during process changes
|
||||
- Lease-based worker ownership prevents duplicate session notifications
|
||||
|
||||
### 7.5. Set Progression Stage
|
||||
|
||||
**Real-time progression stage synchronization for dynamic content adaptation.**
|
||||
|
||||
Notifies workers about the current progression stage of a display, enabling context-aware content selection and detection behavior. The system automatically tracks stage changes and avoids redundant updates.
|
||||
|
||||
- **Type:** `setProgressionStage`
|
||||
|
||||
**Payload:**
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "setProgressionStage",
|
||||
"payload": {
|
||||
"displayIdentifier": "display-001",
|
||||
"progressionStage": "car_fueling"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Or to clear the progression stage:
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "setProgressionStage",
|
||||
"payload": {
|
||||
"displayIdentifier": "display-001",
|
||||
"progressionStage": null
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Available Progression Stages:**
|
||||
|
||||
- `"welcome"` - Initial state, awaiting user interaction
|
||||
- `"car_fueling"` - Vehicle is actively fueling
|
||||
- `"car_waitpayment"` - Fueling complete, awaiting payment
|
||||
- `"car_postpayment"` - Payment completed, transaction finishing
|
||||
- `null` - No active progression stage
|
||||
|
||||
**Progression Stage Flow:**
|
||||
|
||||
1. **Automatic Detection**: Display controllers automatically detect progression stage changes based on display persistent data
|
||||
2. **Change Filtering**: The system compares current stage with last sent stage to avoid redundant updates
|
||||
3. **Instant Propagation**: Stage changes are immediately sent to all workers associated with the display
|
||||
4. **Cross-Process Distribution**: Commands are distributed via Redis `worker:commands` channel to all backend processes
|
||||
5. **State Recovery**: Progression stages are restored when workers reconnect
|
||||
|
||||
**Worker Responsibility:**
|
||||
|
||||
- Store the progression stage for the given `displayIdentifier`
|
||||
- Apply the stage to **all active subscriptions** for that display
|
||||
- Use progression stage for context-aware detection and content adaptation
|
||||
- Handle stage clearing when `progressionStage` is `null`
|
||||
- Restore progression stages from backend state after reconnection
|
||||
|
||||
**Use Cases:**
|
||||
|
||||
- **Fuel Station Displays**: Adapt content based on fueling progress (welcome ads vs. payment prompts)
|
||||
- **Dynamic Detection**: Adjust detection sensitivity based on interaction stage
|
||||
- **Content Personalization**: Select appropriate advertisements for current user journey stage
|
||||
- **Analytics**: Track user progression through interaction stages
|
||||
|
||||
## 8. Subscription Identifier Format
|
||||
|
||||
The `subscriptionIdentifier` used in all messages is constructed as:
|
||||
|
||||
```
|
||||
displayIdentifier;cameraIdentifier
|
||||
```
|
||||
|
||||
This uniquely identifies a camera subscription for a specific display.
|
||||
|
||||
### Session ID Association
|
||||
|
||||
When the backend sends a `setSessionId` command, it will only provide the `displayIdentifier` (not the full `subscriptionIdentifier`).
|
||||
|
||||
**Worker Responsibility:**
|
||||
|
||||
- The worker must match the `displayIdentifier` to all active subscriptions for that display (i.e., all `subscriptionIdentifier` values that start with `displayIdentifier;`).
|
||||
- The worker should set or clear the session ID for all matching subscriptions.
|
||||
|
||||
## 9. Example Communication Log
|
||||
|
||||
This section shows a typical sequence of messages between the backend and the worker, including the new declarative subscription model, session ID management, and progression stage synchronization.
|
||||
|
||||
> **Note:** Unsubscribe is triggered during load rebalancing or when displays/cameras are removed from the system. The system automatically handles worker reconnection with full state recovery.
|
||||
|
||||
1. **Connection Established** & **Heartbeat**
|
||||
- **Worker -> Backend**
|
||||
```json
|
||||
{
|
||||
"type": "stateReport",
|
||||
"cpuUsage": 70.2,
|
||||
"memoryUsage": 38.1,
|
||||
"gpuUsage": 55.0,
|
||||
"gpuMemoryUsage": 20.0,
|
||||
"cameraConnections": []
|
||||
}
|
||||
```
|
||||
2. **Backend Sets Subscription List**
|
||||
- **Backend -> Worker**
|
||||
```json
|
||||
{
|
||||
"type": "setSubscriptionList",
|
||||
"subscriptions": [
|
||||
{
|
||||
"subscriptionIdentifier": "display-001;entry-cam-01",
|
||||
"rtspUrl": "rtsp://192.168.1.100/stream1",
|
||||
"modelUrl": "http://storage/models/vehicle-id.mpta?token=fresh-token",
|
||||
"modelName": "Vehicle Identification",
|
||||
"modelId": 201,
|
||||
"snapshotInterval": 5000
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
3. **Worker Acknowledges with Reconciled State**
|
||||
- **Worker -> Backend**
|
||||
```json
|
||||
{
|
||||
"type": "stateReport",
|
||||
"cpuUsage": 72.5,
|
||||
"memoryUsage": 39.0,
|
||||
"gpuUsage": 57.0,
|
||||
"gpuMemoryUsage": 21.0,
|
||||
"cameraConnections": [
|
||||
{
|
||||
"subscriptionIdentifier": "display-001;entry-cam-01",
|
||||
"modelId": 201,
|
||||
"modelName": "Vehicle Identification",
|
||||
"online": true
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
4. **Backend Sets Session ID**
|
||||
|
||||
- **Backend -> Worker**
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "setSessionId",
|
||||
"payload": {
|
||||
"displayIdentifier": "display-001",
|
||||
"sessionId": 12345
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
5. **Backend Sets Progression Stage**
|
||||
|
||||
- **Backend -> Worker**
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "setProgressionStage",
|
||||
"payload": {
|
||||
"displayIdentifier": "display-001",
|
||||
"progressionStage": "welcome"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
6. **Worker Detects a Car with Session Context**
|
||||
|
||||
- **Worker -> Backend**
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "imageDetection",
|
||||
"subscriptionIdentifier": "display-001;entry-cam-01",
|
||||
"timestamp": "2025-07-15T10:00:00.000Z",
|
||||
"sessionId": 12345,
|
||||
"data": {
|
||||
"detection": {
|
||||
"carBrand": "Honda",
|
||||
"carModel": "CR-V",
|
||||
"bodyType": "SUV",
|
||||
"licensePlateText": "GEMINI-AI",
|
||||
"licensePlateConfidence": 0.98
|
||||
},
|
||||
"modelId": 201,
|
||||
"modelName": "Vehicle Identification"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
7. **Progression Stage Change**
|
||||
|
||||
- **Backend -> Worker**
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "setProgressionStage",
|
||||
"payload": {
|
||||
"displayIdentifier": "display-001",
|
||||
"progressionStage": "car_fueling"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
8. **Worker Reconnection with State Recovery**
|
||||
|
||||
- **Worker Disconnects and Reconnects**
|
||||
- **Worker -> Backend** (Immediate heartbeat after reconnection)
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "stateReport",
|
||||
"cpuUsage": 70.0,
|
||||
"memoryUsage": 38.0,
|
||||
"gpuUsage": 55.0,
|
||||
"gpuMemoryUsage": 20.0,
|
||||
"cameraConnections": []
|
||||
}
|
||||
```
|
||||
|
||||
- **Backend -> Worker** (Automatic subscription list restoration with fresh model URLs)
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "setSubscriptionList",
|
||||
"subscriptions": [
|
||||
{
|
||||
"subscriptionIdentifier": "display-001;entry-cam-01",
|
||||
"rtspUrl": "rtsp://192.168.1.100/stream1",
|
||||
"modelUrl": "http://storage/models/vehicle-id.mpta?token=fresh-reconnect-token",
|
||||
"modelName": "Vehicle Identification",
|
||||
"modelId": 201,
|
||||
"snapshotInterval": 5000
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
- **Backend -> Worker** (Session ID recovery)
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "setSessionId",
|
||||
"payload": {
|
||||
"displayIdentifier": "display-001",
|
||||
"sessionId": 12345
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
- **Backend -> Worker** (Progression stage recovery)
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "setProgressionStage",
|
||||
"payload": {
|
||||
"displayIdentifier": "display-001",
|
||||
"progressionStage": "car_fueling"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
9. **Backend Updates Subscription List** (Load balancing or system cleanup)
|
||||
- **Backend -> Worker** (Empty list removes all subscriptions)
|
||||
```json
|
||||
{
|
||||
"type": "setSubscriptionList",
|
||||
"subscriptions": []
|
||||
}
|
||||
```
|
||||
10. **Worker Acknowledges Subscription Removal**
|
||||
- **Worker -> Backend** (Updated heartbeat showing no active connections after reconciliation)
|
||||
```json
|
||||
{
|
||||
"type": "stateReport",
|
||||
"cpuUsage": 68.0,
|
||||
"memoryUsage": 37.0,
|
||||
"gpuUsage": 50.0,
|
||||
"gpuMemoryUsage": 18.0,
|
||||
"cameraConnections": []
|
||||
}
|
||||
```
|
||||
|
||||
**Key Improvements in Communication Flow:**
|
||||
|
||||
1. **Fully Declarative Subscriptions**: Complete subscription list sent in single command, worker handles reconciliation
|
||||
2. **Worker-Side Reconciliation**: Workers compare desired vs. current state and make necessary changes internally
|
||||
3. **Session Context**: All detection events include session IDs for proper user linking
|
||||
4. **Progression Stages**: Real-time stage updates enable context-aware content selection
|
||||
5. **State Recovery**: Complete automatic recovery of subscription lists, session IDs, and progression stages
|
||||
6. **Fresh Model URLs**: S3 URL expiration is handled transparently with 1-hour TTL tokens
|
||||
7. **Load Balancing**: Backend intelligently distributes complete subscription lists across available workers
|
||||
|
||||
## 10. HTTP API: Image Retrieval
|
||||
|
||||
In addition to the WebSocket protocol, the worker exposes an HTTP endpoint for retrieving the latest image frame from a camera.
|
||||
|
||||
### Endpoint
|
||||
|
||||
```
|
||||
GET /camera/{camera_id}/image
|
||||
```
|
||||
|
||||
- **`camera_id`**: The full `subscriptionIdentifier` (e.g., `display-001;cam-001`).
|
||||
|
||||
### Response
|
||||
|
||||
- **Success (200):** Returns the latest JPEG image from the camera stream.
|
||||
|
||||
- `Content-Type: image/jpeg`
|
||||
- Binary JPEG data.
|
||||
|
||||
- **Error (404):** If the camera is not found or no frame is available.
|
||||
|
||||
- JSON error response.
|
||||
|
||||
- **Error (500):** Internal server error.
|
||||
|
||||
### Example Request
|
||||
|
||||
```
|
||||
GET /camera/display-001;cam-001/image
|
||||
```
|
||||
|
||||
### Example Response
|
||||
|
||||
- **Headers:**
|
||||
```
|
||||
Content-Type: image/jpeg
|
||||
```
|
||||
- **Body:** Binary JPEG image.
|
||||
|
||||
### Notes
|
||||
|
||||
- The endpoint returns the most recent frame available for the specified camera subscription.
|
||||
- If multiple displays share the same camera, each subscription has its own buffer; the endpoint uses the buffer for the given `camera_id`.
|
||||
- This API is useful for debugging, monitoring, or integrating with external systems that require direct image access.
|
||||
BIN
yolov8n.pt
Normal file
BIN
yolov8n.pt
Normal file
Binary file not shown.
Loading…
Add table
Add a link
Reference in a new issue