From 428f7a96717134c60249ebf91add394e8aa340b8 Mon Sep 17 00:00:00 2001 From: pixchy-commits <6341430@schoolptk.ac.th> Date: Mon, 14 Jul 2025 23:40:19 +0700 Subject: [PATCH 1/4] feat: enhance session management in worker communication protocol; implement session ID handling and crop frame processing --- app.py | 291 ++++++++++++++++++++++++++++++++++------------- test_protocol.py | 125 ++++++++++++++++++++ 2 files changed, 334 insertions(+), 82 deletions(-) create mode 100644 test_protocol.py diff --git a/app.py b/app.py index 4e9be15..60beb27 100644 --- a/app.py +++ b/app.py @@ -29,6 +29,12 @@ app = FastAPI() # "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] = {} with open("config.json", "r") as f: config = json.load(f) @@ -184,9 +190,16 @@ async def detect(websocket: WebSocket): 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() - detection_result = run_pipeline(frame, model_tree) + detection_result = run_pipeline(cropped_frame, model_tree) process_time = (time.time() - start_time) * 1000 logger.debug(f"Detection for camera {camera_id} completed in {process_time:.2f}ms") @@ -235,22 +248,48 @@ async def detect(websocket: WebSocket): "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 + + # 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 + detection_data = { "type": "imageDetection", "subscriptionIdentifier": stream["subscriptionIdentifier"], "timestamp": time.strftime("%Y-%m-%dT%H:%M:%S.%fZ", time.gmtime()), "data": { - "detection": highest_confidence_detection, # Send only the highest confidence detection + "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 + 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 + 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}:\n{json.dumps(detection_data, indent=2)}") + 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) @@ -521,50 +560,58 @@ async def detect(websocket: WebSocket): cropX2 = payload.get("cropX2") cropY2 = payload.get("cropY2") - camera_id = subscriptionIdentifier # Use subscriptionIdentifier as camera_id for mapping + # 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_id, str(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 model from {model_url}") - local_mpta = os.path.join(extraction_dir, os.path.basename(parsed.path)) + 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}") + logger.error(f"Failed to download the remote .mpta file from {model_url}") error_response = { "type": "error", - "cameraIdentifier": camera_id, + "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 model from {model_url}") + 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 model file not found: {model_url}") + logger.error(f"Local .mpta file not found: {model_url}") logger.debug(f"Current working directory: {os.getcwd()}") error_response = { "type": "error", - "cameraIdentifier": camera_id, + "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}") + logger.error(f"Failed to load model {modelId} from .mpta file for camera {camera_id}") error_response = { "type": "error", - "cameraIdentifier": camera_id, + "subscriptionIdentifier": subscriptionIdentifier, "error": f"Failed to load model {modelId}" } await websocket.send_json(error_response) @@ -573,20 +620,80 @@ async def detect(websocket: WebSocket): models[camera_id] = {} models[camera_id][modelId] = model_tree logger.info(f"Successfully loaded model {modelId} for camera {camera_id}") - success_response = { - "type": "modelLoaded", - "cameraIdentifier": camera_id, - "modelId": modelId - } - await websocket.send_json(success_response) + 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: - buffer = queue.Queue(maxsize=1) - stop_event = threading.Event() + # 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_identifier, 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_identifier, 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": None, + "thread": thread, "stop_event": stop_event, "modelId": modelId, "modelName": modelName, @@ -594,52 +701,25 @@ async def detect(websocket: WebSocket): "cropX1": cropX1, "cropY1": cropY1, "cropX2": cropX2, - "cropY2": cropY2 + "cropY2": cropY2, + "mode": mode, + "camera_url": camera_url } - if snapshot_url and snapshot_interval: - logger.info(f"Using snapshot mode 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() - stream_info.update({ - "snapshot_url": snapshot_url, - "snapshot_interval": snapshot_interval, - "mode": "snapshot" - }) - stream_info["thread"] = thread - streams[camera_id] = stream_info - elif rtsp_url: - logger.info(f"Using RTSP mode 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() - stream_info.update({ - "cap": cap, - "rtsp_url": rtsp_url, - "mode": "rtsp" - }) - stream_info["thread"] = thread - streams[camera_id] = stream_info - else: - logger.error(f"No valid URL provided for camera {camera_id}") - continue + + 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 - stream = streams.pop(camera_id) - stream["stop_event"].set() - stream["thread"].join() - if "cap" in stream: - stream["cap"].release() - logger.info(f"Unsubscribed from camera {camera_id} for resubscription") - with models_lock: - if camera_id in models and modelId in models[camera_id]: - del models[camera_id][modelId] - if not models[camera_id]: - del models[camera_id] + 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") @@ -647,13 +727,25 @@ async def detect(websocket: WebSocket): with streams_lock: if camera_id and camera_id in streams: stream = streams.pop(camera_id) - stream["stop_event"].set() - stream["thread"].join() - if "cap" in stream: - stream["cap"].release() - with models_lock: - if camera_id in models: - del models[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") + + 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 @@ -684,6 +776,37 @@ async def detect(websocket: WebSocket): "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: @@ -706,19 +829,23 @@ async def detect(websocket: WebSocket): stream_task.cancel() await stream_task with streams_lock: - for camera_id, stream in streams.items(): - stream["stop_event"].set() - stream["thread"].join() - # Only release cap if it exists (RTSP mode) - if "cap" in stream: - stream["cap"].release() - while not stream["buffer"].empty(): + # 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: - stream["buffer"].get_nowait() + shared_stream["buffer"].get_nowait() except queue.Empty: pass - logger.info(f"Released camera {camera_id} and cleaned up resources") + logger.info(f"Released shared camera stream for {camera_url}") + streams.clear() + camera_streams.clear() + subscription_to_camera.clear() with models_lock: models.clear() + session_ids.clear() logger.info("WebSocket connection closed") diff --git a/test_protocol.py b/test_protocol.py new file mode 100644 index 0000000..74af7d8 --- /dev/null +++ b/test_protocol.py @@ -0,0 +1,125 @@ +#!/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:8000" + + 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:8000") + +if __name__ == "__main__": + asyncio.run(test_protocol()) \ No newline at end of file From a1f797f564eb2eb60c659052544589622cf09aea Mon Sep 17 00:00:00 2001 From: Siwat Sirichai Date: Tue, 15 Jul 2025 00:18:28 +0700 Subject: [PATCH 2/4] feat: add HTTP API for image retrieval from camera; implement endpoint for accessing latest image frames --- worker.md | 42 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) diff --git a/worker.md b/worker.md index 00a13cf..c50bae5 100644 --- a/worker.md +++ b/worker.md @@ -439,3 +439,45 @@ This section shows a typical sequence of messages between the backend and the wo "cameraConnections": [] } ``` +## 7. 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. From 769371a1a34584c1a1708d4b8abf03f8179aa3d5 Mon Sep 17 00:00:00 2001 From: Siwat Sirichai Date: Tue, 15 Jul 2025 00:30:09 +0700 Subject: [PATCH 3/4] feat: integrate Redis support in pipeline execution; add actions for saving images and publishing messages --- pympta.md | 200 ++++++++++++++++++++++++++++++++++++++++++ requirements.txt | 3 +- siwatsystem/pympta.py | 52 ++++++++++- 3 files changed, 250 insertions(+), 5 deletions(-) create mode 100644 pympta.md diff --git a/pympta.md b/pympta.md new file mode 100644 index 0000000..2136480 --- /dev/null +++ b/pympta.md @@ -0,0 +1,200 @@ +# 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 and an optional `redis` key for Redis configuration. + +### 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. | + +### 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`. | + +### 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 | 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`. | +| `branches` | Array | No | A list of child node objects that can be triggered by this node's detections. | +| `actions` | Array | No | A list of actions to execute upon a successful detection in this node. | + +### Action Object Structure + +Actions allow the pipeline to interact with Redis. + +#### `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 placeholders like `{class}` or `{id}` to be formatted with detection results. | + +#### `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 placeholders like `{class}` or `{id}` to be formatted with detection results. | + +### Example `pipeline.json` with Redis + +```json +{ + "redis": { + "host": "localhost", + "port": 6379, + "password": "your-password" + }, + "pipeline": { + "modelId": "vehicle-detector", + "modelFile": "vehicle_model.pt", + "minConfidence": 0.5, + "triggerClasses": ["car", "truck"], + "actions": [ + { + "type": "redis_save_image", + "key": "detection:image:{id}" + }, + { + "type": "redis_publish", + "channel": "detections", + "message": "Detected a {class} with ID {id}" + } + ], + "branches": [ + { + "modelId": "lpr-us", + "modelFile": "lpr_model.pt", + "minConfidence": 0.7, + "triggerClasses": ["car"], + "crop": true, + "branches": [] + } + ] + } +} +``` + +## 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 a Redis connection 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)` + +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`. +- **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`). + +## Usage Example + +This snippet, inspired by `pipeline_webcam.py`, shows how to use `pympta` to load a pipeline and process an image from a webcam. + +```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 + # The function will handle the entire logic tree (e.g., find a car, then find its license plate). + detection_result, bounding_box = run_pipeline(frame, model_tree, return_bbox=True) + + # 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() +``` \ No newline at end of file diff --git a/requirements.txt b/requirements.txt index 84f45cc..49ca601 100644 --- a/requirements.txt +++ b/requirements.txt @@ -5,4 +5,5 @@ torchvision ultralytics opencv-python websockets -fastapi[standard] \ No newline at end of file +fastapi[standard] +redis \ No newline at end of file diff --git a/siwatsystem/pympta.py b/siwatsystem/pympta.py index 5e32596..4514182 100644 --- a/siwatsystem/pympta.py +++ b/siwatsystem/pympta.py @@ -7,13 +7,14 @@ import requests import zipfile import shutil import traceback +import redis from ultralytics import YOLO from urllib.parse import urlparse # Create a logger specifically for this module logger = logging.getLogger("detector_worker.pympta") -def load_pipeline_node(node_config: dict, mpta_dir: str) -> dict: +def load_pipeline_node(node_config: dict, mpta_dir: str, redis_client) -> 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): @@ -44,13 +45,15 @@ def load_pipeline_node(node_config: dict, mpta_dir: str) -> dict: "triggerClassIndices": trigger_class_indices, "crop": node_config.get("crop", False), "minConfidence": node_config.get("minConfidence", None), + "actions": node_config.get("actions", []), "model": model, - "branches": [] + "branches": [], + "redis_client": redis_client } 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)) + node["branches"].append(load_pipeline_node(child, mpta_dir, redis_client)) return node def load_pipeline_from_zip(zip_source: str, target_dir: str) -> dict: @@ -158,7 +161,26 @@ def load_pipeline_from_zip(zip_source: str, target_dir: str) -> dict: 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)}") - return load_pipeline_node(pipeline_config["pipeline"], mpta_dir) + + # Establish Redis connection if configured + redis_client = None + if "redis" in pipeline_config: + redis_config = pipeline_config["redis"] + 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 + + return load_pipeline_node(pipeline_config["pipeline"], mpta_dir, redis_client) except json.JSONDecodeError as e: logger.error(f"Error parsing pipeline.json: {str(e)}", exc_info=True) return None @@ -169,6 +191,25 @@ def load_pipeline_from_zip(zip_source: str, target_dir: str) -> dict: logger.error(f"Error loading pipeline.json: {str(e)}", exc_info=True) return None +def execute_actions(node, frame, detection_result): + if not node["redis_client"] or not node["actions"]: + return + + for action in node["actions"]: + try: + if action["type"] == "redis_save_image": + key = action["key"].format(**detection_result) + _, buffer = cv2.imencode('.jpg', frame) + node["redis_client"].set(key, buffer.tobytes()) + logger.info(f"Saved image to Redis with key: {key}") + elif action["type"] == "redis_publish": + channel = action["channel"] + message = action["message"].format(**detection_result) + node["redis_client"].publish(channel, message) + logger.info(f"Published message to Redis channel '{channel}': {message}") + except Exception as e: + logger.error(f"Error executing action {action['type']}: {e}") + def run_pipeline(frame, node: dict, return_bbox: bool=False): """ - For detection nodes (task != 'classify'): @@ -206,6 +247,7 @@ def run_pipeline(frame, node: dict, return_bbox: bool=False): "confidence": top1_conf, "id": None } + execute_actions(node, frame, det) return (det, None) if return_bbox else det @@ -254,9 +296,11 @@ def run_pipeline(frame, node: dict, return_bbox: bool=False): det2, _ = run_pipeline(sub, br, return_bbox=True) if det2: # return classification result + original bbox + execute_actions(br, sub, det2) return (det2, best_box) if return_bbox else det2 # ─── No branch matched → return this detection ───────────── + execute_actions(node, frame, best_det) return (best_det, best_box) if return_bbox else best_det except Exception as e: From f50585f26d11bdb25e0e72f1bc002ae6366c604e Mon Sep 17 00:00:00 2001 From: Siwat Sirichai Date: Tue, 15 Jul 2025 00:35:22 +0700 Subject: [PATCH 4/4] feat: enhance Redis action handling; add dynamic context for actions and support for expiration time --- pympta.md | 48 +++++++++++++++++++++++-------------------- siwatsystem/pympta.py | 24 ++++++++++++++++++---- 2 files changed, 46 insertions(+), 26 deletions(-) diff --git a/pympta.md b/pympta.md index 2136480..ac61f4a 100644 --- a/pympta.md +++ b/pympta.md @@ -64,16 +64,26 @@ This file defines the entire pipeline logic. The root object contains a `pipelin ### Action Object Structure -Actions allow the pipeline to interact with Redis. +Actions allow the pipeline to interact with Redis. 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. +- `{uuid}`: A unique identifier (UUID4) for the detection event. +- `{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 placeholders like `{class}` or `{id}` to be formatted with detection results. | +| 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. | +| `expire_seconds` | Number | No | If provided, sets an expiration time (in seconds) for the Redis key. | #### `redis_publish` @@ -83,43 +93,37 @@ Publishes a message to a Redis channel. | --------- | ------ | -------- | ------------------------------------------------------------------------------------------------------- | | `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 placeholders like `{class}` or `{id}` to be formatted with detection results. | +| `message` | String | Yes | The message to publish. Can contain any of the dynamic placeholders, including `{image_key}`. | ### Example `pipeline.json` with Redis +This example demonstrates a pipeline that detects vehicles, saves a uniquely named image of each detection that expires in one hour, and then publishes a notification with the image key. + ```json { "redis": { - "host": "localhost", + "host": "redis.local", "port": 6379, - "password": "your-password" + "password": "your-super-secret-password" }, "pipeline": { "modelId": "vehicle-detector", "modelFile": "vehicle_model.pt", - "minConfidence": 0.5, + "minConfidence": 0.6, "triggerClasses": ["car", "truck"], "actions": [ { "type": "redis_save_image", - "key": "detection:image:{id}" + "key": "detections:{class}:{timestamp_ms}:{uuid}", + "expire_seconds": 3600 }, { "type": "redis_publish", - "channel": "detections", - "message": "Detected a {class} with ID {id}" + "channel": "vehicle_events", + "message": "{\"event\":\"new_detection\",\"class\":\"{class}\",\"confidence\":{confidence},\"image_key\":\"{image_key}\"}" } ], - "branches": [ - { - "modelId": "lpr-us", - "modelFile": "lpr_model.pt", - "minConfidence": 0.7, - "triggerClasses": ["car"], - "crop": true, - "branches": [] - } - ] + "branches": [] } } ``` diff --git a/siwatsystem/pympta.py b/siwatsystem/pympta.py index 4514182..f151b55 100644 --- a/siwatsystem/pympta.py +++ b/siwatsystem/pympta.py @@ -8,6 +8,8 @@ import zipfile import shutil import traceback import redis +import time +import uuid from ultralytics import YOLO from urllib.parse import urlparse @@ -195,16 +197,30 @@ def execute_actions(node, frame, detection_result): if not node["redis_client"] or not node["actions"]: return + # Create a dynamic context for this detection event + action_context = { + **detection_result, + "timestamp_ms": int(time.time() * 1000), + "uuid": str(uuid.uuid4()), + } + for action in node["actions"]: try: if action["type"] == "redis_save_image": - key = action["key"].format(**detection_result) + key = action["key"].format(**action_context) _, buffer = cv2.imencode('.jpg', frame) - node["redis_client"].set(key, buffer.tobytes()) - logger.info(f"Saved image to Redis with key: {key}") + 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}") + # Add the generated key to the context for subsequent actions + action_context["image_key"] = key elif action["type"] == "redis_publish": channel = action["channel"] - message = action["message"].format(**detection_result) + message = action["message"].format(**action_context) node["redis_client"].publish(channel, message) logger.info(f"Published message to Redis channel '{channel}': {message}") except Exception as e: