update tracker

.gitignore

@@ -13,3 +13,5 @@ no_frame_debug.log
 
 feeder/
 .venv/
+.vscode/
+dist/

app.py

@@ -27,7 +27,7 @@ from websockets.exceptions import ConnectionClosedError
 from ultralytics import YOLO
 
 # Import shared pipeline functions
-from siwatsystem.pympta import load_pipeline_from_zip, run_pipeline
+from siwatsystem.pympta import load_pipeline_from_zip, run_pipeline, cleanup_camera_stability
 
 app = FastAPI()
 
@@ -325,6 +325,7 @@ async def detect(websocket: WebSocket):
                 "type": "imageDetection",
                 "subscriptionIdentifier": stream["subscriptionIdentifier"],
                 "timestamp": time.strftime("%Y-%m-%dT%H:%M:%S.%fZ", time.gmtime()),
+                # "timestamp": time.strftime("%Y-%m-%dT%H:%M:%S", time.gmtime()) + f".{int(time.time() * 1000) % 1000:03d}Z",
                 "data": {
                     "detection": detection_dict,
                     "modelId": stream["modelId"],
@@ -704,6 +705,7 @@ async def detect(websocket: WebSocket):
                     del camera_streams[camera_url]
             
             latest_frames.pop(subscription_id, None)
+            cleanup_camera_stability(subscription_id)
             logger.info(f"Unsubscribed from camera {subscription_id}")
 
     async def process_streams():
@@ -1018,8 +1020,9 @@ async def detect(websocket: WebSocket):
                                 else:
                                     logger.info(f"Shared stream for {camera_url} still has {shared_stream['ref_count']} references")
                             
-                            # Clean up cached frame
+                            # Clean up cached frame and stability tracking
                             latest_frames.pop(camera_id, None)
+                            cleanup_camera_stability(camera_id)
                             logger.info(f"Unsubscribed from camera {camera_id}")
                             # Note: Keep models in memory for potential reuse
                 elif msg_type == "requestState":

debug/test_camera_indices.py

@@ -0,0 +1,142 @@
+#!/usr/bin/env python3
+"""
+Test script to check available camera indices
+"""
+
+import cv2
+import logging
+import sys
+import subprocess
+
+# Configure logging
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s [%(levelname)s] %(name)s: %(message)s"
+)
+logger = logging.getLogger("camera_index_test")
+
+def test_camera_index(index):
+    """Test if a camera index is available"""
+    try:
+        cap = cv2.VideoCapture(index)
+        if cap.isOpened():
+            ret, frame = cap.read()
+            if ret and frame is not None:
+                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)
+                
+                cap.release()
+                return True, f"{width}x{height} @ {fps}fps"
+            else:
+                cap.release()
+                return False, "Can open but cannot read frames"
+        else:
+            cap.release()
+            return False, "Cannot open camera"
+    except Exception as e:
+        return False, f"Error: {str(e)}"
+
+def get_windows_cameras_ffmpeg():
+    """Get available cameras on Windows using FFmpeg"""
+    try:
+        result = subprocess.run(['ffmpeg', '-f', 'dshow', '-list_devices', 'true', '-i', 'dummy'], 
+                              capture_output=True, text=True, timeout=10, encoding='utf-8', errors='ignore')
+        output = result.stderr
+        
+        lines = output.split('\n')
+        video_devices = []
+        
+        # Parse the output - look for lines with (video) that contain device names in quotes
+        for line in lines:
+            if '[dshow @' in line and '(video)' in line and '"' in line:
+                # Extract device name between first pair of quotes
+                start = line.find('"') + 1
+                end = line.find('"', start)
+                if start > 0 and end > start:
+                    device_name = line[start:end]
+                    video_devices.append(device_name)
+        
+        logger.info(f"FFmpeg detected video devices: {video_devices}")
+        return video_devices
+    except Exception as e:
+        logger.error(f"Failed to get Windows camera names: {e}")
+        return []
+
+def main():
+    logger.info("=== Camera Index Test ===")
+    
+    # Check FFmpeg availability for Windows device detection
+    ffmpeg_available = False
+    try:
+        result = subprocess.run(['ffmpeg', '-version'], capture_output=True, text=True, timeout=5)
+        if result.returncode == 0:
+            ffmpeg_available = True
+            logger.info("FFmpeg is available")
+    except:
+        logger.info("FFmpeg not available")
+    
+    # Get Windows camera names if possible
+    if sys.platform.startswith('win') and ffmpeg_available:
+        logger.info("\n=== Windows Camera Devices (FFmpeg) ===")
+        cameras = get_windows_cameras_ffmpeg()
+        if cameras:
+            for i, camera in enumerate(cameras):
+                logger.info(f"Device {i}: {camera}")
+        else:
+            logger.info("No cameras detected via FFmpeg")
+    
+    # Test camera indices 0-9
+    logger.info("\n=== Testing Camera Indices ===")
+    available_cameras = []
+    
+    for index in range(10):
+        logger.info(f"Testing camera index {index}...")
+        is_available, info = test_camera_index(index)
+        
+        if is_available:
+            logger.info(f"✓ Camera {index}: AVAILABLE - {info}")
+            available_cameras.append(index)
+        else:
+            logger.info(f"✗ Camera {index}: NOT AVAILABLE - {info}")
+    
+    # Summary
+    logger.info("\n=== Summary ===")
+    if available_cameras:
+        logger.info(f"Available camera indices: {available_cameras}")
+        logger.info(f"Default camera index to use: {available_cameras[0]}")
+        
+        # Test the first available camera more thoroughly
+        logger.info(f"\n=== Detailed Test for Camera {available_cameras[0]} ===")
+        cap = cv2.VideoCapture(available_cameras[0])
+        if cap.isOpened():
+            # Get properties
+            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)
+            backend = cap.getBackendName()
+            
+            logger.info(f"Resolution: {width}x{height}")
+            logger.info(f"FPS: {fps}")
+            logger.info(f"Backend: {backend}")
+            
+            # Test frame capture
+            ret, frame = cap.read()
+            if ret and frame is not None:
+                logger.info(f"Frame capture: SUCCESS")
+                logger.info(f"Frame shape: {frame.shape}")
+                logger.info(f"Frame dtype: {frame.dtype}")
+            else:
+                logger.info(f"Frame capture: FAILED")
+            
+            cap.release()
+    else:
+        logger.error("No cameras available!")
+        logger.info("Possible solutions:")
+        logger.info("1. Check if camera is connected and not used by another application")
+        logger.info("2. Check camera permissions")
+        logger.info("3. Try different camera indices")
+        logger.info("4. Install camera drivers")
+
+if __name__ == "__main__":
+    main()

siwatsystem/pympta.py

@@ -17,6 +17,13 @@ from .database import DatabaseManager
 # Create a logger specifically for this module
 logger = logging.getLogger("detector_worker.pympta")
 
+# Global camera-aware stability tracking
+# Structure: {camera_id: {model_id: {"track_stability_counters": {track_id: count}, "stable_tracks": set(), "session_state": {...}}}}
+_camera_stability_tracking = {}
+
+# Timer-based cooldown configuration (for testing)
+_cooldown_duration_seconds = 30
+
 def validate_redis_config(redis_config: dict) -> bool:
     """Validate Redis configuration parameters."""
     required_fields = ["host", "port"]
@@ -78,7 +85,7 @@ def load_pipeline_node(node_config: dict, mpta_dir: str, redis_client, db_manage
     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")
+        logger.info(f"CUDA available. Moving model {node_config['modelId']} to GPU VRAM")
         model.to("cuda")
     else:
         logger.info(f"CUDA not available. Using CPU for model {node_config['modelId']}")
@@ -92,6 +99,10 @@ def load_pipeline_node(node_config: dict, mpta_dir: str, redis_client, db_manage
                                 if name in trigger_classes]
         logger.debug(f"Converted trigger classes to indices: {trigger_class_indices}")
 
+    # Extract stability threshold from tracking config
+    tracking_config = node_config.get("tracking", {"enabled": True, "reidConfigPath": "botsort.yaml"})
+    stability_threshold = tracking_config.get("stabilityThreshold", 1)
+
     node = {
         "modelId": node_config["modelId"],
         "modelFile": node_config["modelFile"],
@@ -105,6 +116,8 @@ def load_pipeline_node(node_config: dict, mpta_dir: str, redis_client, db_manage
         "parallel": node_config.get("parallel", False),
         "actions": node_config.get("actions", []),
         "parallelActions": node_config.get("parallelActions", []),
+        "tracking": tracking_config,
+        "stabilityThreshold": stability_threshold,
         "model": model,
         "branches": [],
         "redis_client": redis_client,
@@ -514,6 +527,342 @@ def resolve_field_mapping(value_template, branch_results, action_context):
         logger.error(f"Error resolving field mapping '{value_template}': {e}")
         return None
 
+def run_detection_with_tracking(frame, node, context=None):
+    """
+    Structured function for running YOLO detection with BoT-SORT tracking.
+    
+    Args:
+        frame: Input frame/image
+        node: Pipeline node configuration with model and settings
+        context: Optional context information (camera info, session data, etc.)
+        
+    Returns:
+        tuple: (all_detections, regions_dict) where:
+            - all_detections: List of all detection objects
+            - regions_dict: Dict mapping class names to highest confidence detections
+            
+    Configuration options in node:
+        - model: YOLO model instance
+        - triggerClassIndices: List of class indices to detect (None for all classes)
+        - minConfidence: Minimum confidence threshold
+        - multiClass: Whether to enable multi-class detection mode
+        - expectedClasses: List of expected class names for multi-class validation
+        - tracking: Dict with tracking configuration
+            - enabled: Boolean to enable/disable tracking
+            - reidConfigPath: Path to ReID config file (default: "botsort.yaml")
+    """
+    try:
+        # Extract tracking configuration
+        tracking_config = node.get("tracking", {})
+        tracking_enabled = tracking_config.get("enabled", True)
+        reid_config_path = tracking_config.get("reidConfigPath", "botsort.yaml")
+        
+        # Check if we need to reset tracker after cooldown
+        camera_id = context.get("camera_id", "unknown") if context else "unknown"
+        model_id = node.get("modelId", "unknown")
+        stability_data = get_camera_stability_data(camera_id, model_id)
+        session_state = stability_data["session_state"]
+        
+        if session_state.get("reset_tracker_on_resume", False):
+            # Reset YOLO tracker to get fresh track IDs
+            if hasattr(node["model"], 'trackers') and node["model"].trackers:
+                node["model"].trackers.clear()  # Clear tracker state
+                logger.info(f"Camera {camera_id}: 🔄 Reset YOLO tracker - new cars will get fresh track IDs")
+            session_state["reset_tracker_on_resume"] = False  # Clear the flag
+        
+        # Get tracking zone from runtime context (camera-specific)
+        tracking_zone = context.get("trackingZone", []) if context else []
+        
+        # Prepare class filtering
+        trigger_class_indices = node.get("triggerClassIndices")
+        class_filter = {"classes": trigger_class_indices} if trigger_class_indices else {}
+        
+        logger.debug(f"Running detection for {node['modelId']} - tracking: {tracking_enabled}, classes: {node.get('triggerClasses', 'all')}")
+        
+        if tracking_enabled and tracking_zone:
+            # Use tracking with zone validation
+            logger.debug(f"Using tracking with ReID config: {reid_config_path}")
+            res = node["model"].track(
+                frame,
+                stream=False,
+                persist=True,
+                tracker=reid_config_path,
+                **class_filter
+            )[0]
+        elif tracking_enabled:
+            # Use tracking without zone restriction
+            logger.debug("Using tracking without zone restriction")
+            res = node["model"].track(
+                frame,
+                stream=False,
+                persist=True,
+                **class_filter
+            )[0]
+        else:
+            # Use detection only (no tracking)
+            logger.debug("Using detection only (tracking disabled)")
+            res = node["model"].predict(
+                frame,
+                stream=False,
+                **class_filter
+            )[0]
+        
+        # Process detection results
+        all_detections = []
+        regions_dict = {}
+        min_confidence = node.get("minConfidence", 0.0)
+        
+        if res.boxes is None or len(res.boxes) == 0:
+            logger.debug("No detections found")
+            return [], {}
+        
+        logger.debug(f"Processing {len(res.boxes)} raw detections")
+        
+        for i, box in enumerate(res.boxes):
+            # Extract detection data
+            conf = float(box.cpu().conf[0])
+            cls_id = int(box.cpu().cls[0])
+            class_name = node["model"].names[cls_id]
+            
+            # Apply confidence filtering
+            if conf < min_confidence:
+                logger.debug(f"Detection {i} '{class_name}' rejected: {conf:.3f} < {min_confidence}")
+                continue
+            
+            # Extract bounding box
+            xy = box.cpu().xyxy[0]
+            x1, y1, x2, y2 = map(int, xy)
+            bbox = (x1, y1, x2, y2)
+            
+            # Extract tracking ID if available
+            track_id = None
+            if hasattr(box, "id") and box.id is not None:
+                track_id = int(box.id.item())
+            
+            # Apply tracking zone validation if enabled
+            if tracking_enabled and tracking_zone:
+                bbox_center_x = (x1 + x2) // 2
+                bbox_center_y = (y1 + y2) // 2
+                
+                # Check if detection center is within tracking zone
+                if not _point_in_polygon((bbox_center_x, bbox_center_y), tracking_zone):
+                    logger.debug(f"Detection {i} '{class_name}' outside tracking zone")
+                    continue
+            
+            # Create detection object
+            detection = {
+                "class": class_name,
+                "confidence": conf,
+                "id": track_id,
+                "bbox": bbox,
+                "class_id": cls_id
+            }
+            
+            all_detections.append(detection)
+            logger.debug(f"Detection {i} accepted: {class_name} (conf={conf:.3f}, id={track_id}, bbox={bbox})")
+            
+            # Update regions_dict with highest confidence detection per class
+            if class_name not in regions_dict or conf > regions_dict[class_name]["confidence"]:
+                regions_dict[class_name] = {
+                    "bbox": bbox,
+                    "confidence": conf,
+                    "detection": detection,
+                    "track_id": track_id
+                }
+        
+        # Multi-class validation
+        if node.get("multiClass", False) and node.get("expectedClasses"):
+            expected_classes = node["expectedClasses"]
+            detected_classes = list(regions_dict.keys())
+            
+            logger.debug(f"Multi-class validation: expected={expected_classes}, detected={detected_classes}")
+            
+            # Check for required classes (flexible - at least one must match)
+            matching_classes = [cls for cls in expected_classes if cls in detected_classes]
+            if not matching_classes:
+                logger.warning(f"Multi-class validation failed: no expected classes detected")
+                return [], {}
+            
+            logger.info(f"Multi-class validation passed: {matching_classes} detected")
+        
+        logger.info(f"Detection completed: {len(all_detections)} detections, {len(regions_dict)} unique classes")
+        
+        # Update stability tracking for detections with track IDs (requires camera_id from context)
+        camera_id = context.get("camera_id", "unknown") if context else "unknown"
+        update_track_stability(node, all_detections, camera_id)
+        
+        return all_detections, regions_dict
+        
+    except Exception as e:
+        logger.error(f"Error in detection_with_tracking for {node.get('modelId', 'unknown')}: {e}")
+        logger.debug(f"Detection error traceback: {traceback.format_exc()}")
+        return [], {}
+
+def _point_in_polygon(point, polygon):
+    """Check if a point is inside a polygon using ray casting algorithm."""
+    if not polygon or len(polygon) < 3:
+        return True  # No zone restriction if invalid polygon
+    
+    x, y = point
+    n = len(polygon)
+    inside = False
+    
+    p1x, p1y = polygon[0]
+    for i in range(1, n + 1):
+        p2x, p2y = polygon[i % n]
+        if y > min(p1y, p2y):
+            if y <= max(p1y, p2y):
+                if x <= max(p1x, p2x):
+                    if p1y != p2y:
+                        xinters = (y - p1y) * (p2x - p1x) / (p2y - p1y) + p1x
+                    if p1x == p2x or x <= xinters:
+                        inside = not inside
+        p1x, p1y = p2x, p2y
+    
+    return inside
+
+def get_camera_stability_data(camera_id, model_id):
+    """Get or create stability tracking data for a specific camera and model."""
+    global _camera_stability_tracking
+    
+    if camera_id not in _camera_stability_tracking:
+        _camera_stability_tracking[camera_id] = {}
+    
+    if model_id not in _camera_stability_tracking[camera_id]:
+        logger.warning(f"🔄 Camera {camera_id}: Creating NEW stability data for {model_id} - this will reset any cooldown!")
+        _camera_stability_tracking[camera_id][model_id] = {
+            "track_stability_counters": {},
+            "stable_tracks": set(),
+            "session_state": {
+                "active": True,
+                "cooldown_until": 0.0,
+                "reset_tracker_on_resume": False
+            }
+        }
+    
+    return _camera_stability_tracking[camera_id][model_id]
+
+def update_track_stability(node, detections, camera_id):
+    """Update stability counters for tracked objects per camera."""
+    stability_threshold = node.get("stabilityThreshold", 1)
+    model_id = node.get("modelId", "unknown")
+    
+    # Get camera-specific stability data
+    stability_data = get_camera_stability_data(camera_id, model_id)
+    track_counters = stability_data["track_stability_counters"]
+    stable_tracks = stability_data["stable_tracks"]
+    
+    # Get current track IDs from detections
+    current_track_ids = set()
+    for detection in detections:
+        track_id = detection.get("id")
+        if track_id is not None:
+            current_track_ids.add(track_id)
+            
+            # Increment counter for this track
+            track_counters[track_id] = track_counters.get(track_id, 0) + 1
+            
+            # Check if track becomes stable
+            if track_counters[track_id] >= stability_threshold and track_id not in stable_tracks:
+                stable_tracks.add(track_id)
+                logger.info(f"Camera {camera_id}: Track ID {track_id} became stable after {track_counters[track_id]} detections (threshold: {stability_threshold})")
+    
+    # Clean up counters for tracks that disappeared
+    disappeared_tracks = set(track_counters.keys()) - current_track_ids
+    for track_id in disappeared_tracks:
+        logger.debug(f"Camera {camera_id}: Track ID {track_id} disappeared, removing from counters")
+        track_counters.pop(track_id, None)
+        stable_tracks.discard(track_id)
+    
+    logger.debug(f"Camera {camera_id}: Track stability: active={list(current_track_ids)}, stable={list(stable_tracks)}, counters={track_counters}")
+
+def check_stable_tracks(camera_id, model_id, regions_dict):
+    """Check if any stable tracks match the detected classes for a specific camera."""
+    # Get camera-specific stability data
+    stability_data = get_camera_stability_data(camera_id, model_id)
+    stable_tracks = stability_data["stable_tracks"]
+    
+    if not stable_tracks:
+        return False, []
+    
+    # Check if any detection in regions_dict has a stable track ID
+    stable_detections = []
+    for class_name, region_data in regions_dict.items():
+        detection = region_data.get("detection", {})
+        track_id = detection.get("id")
+        
+        if track_id is not None and track_id in stable_tracks:
+            stable_detections.append((class_name, track_id))
+            logger.debug(f"Camera {camera_id}: Found stable detection: {class_name} with stable track ID {track_id}")
+    
+    has_stable_tracks = len(stable_detections) > 0
+    return has_stable_tracks, stable_detections
+
+def start_cooldown_timer(camera_id, model_id):
+    """Start 30-second cooldown timer after successful pipeline completion."""
+    stability_data = get_camera_stability_data(camera_id, model_id)
+    session_state = stability_data["session_state"]
+    
+    # Start timer-based cooldown
+    cooldown_until = time.time() + _cooldown_duration_seconds
+    session_state["cooldown_until"] = cooldown_until
+    session_state["active"] = False
+    session_state["reset_tracker_on_resume"] = True  # Flag to reset YOLO tracker
+    
+    logger.info(f"Camera {camera_id}: 🛑 Starting {_cooldown_duration_seconds}s cooldown timer (until: {cooldown_until:.2f})")
+    
+    # DO NOT clear tracking state here - preserve it during cooldown
+    # Tracking state will be cleared when cooldown expires and new session starts
+
+def is_camera_active(camera_id, model_id):
+    """Check if camera should be processing detections (timer-based cooldown)."""
+    stability_data = get_camera_stability_data(camera_id, model_id)
+    session_state = stability_data["session_state"]
+    
+    # Check if cooldown timer has expired
+    if not session_state["active"]:
+        current_time = time.time()
+        cooldown_until = session_state["cooldown_until"]
+        remaining_time = cooldown_until - current_time
+        
+        if current_time >= cooldown_until:
+            session_state["active"] = True
+            session_state["reset_tracker_on_resume"] = True  # Ensure tracker reset flag is set
+            
+            # Clear tracking state NOW - before new detection session starts
+            stability_data["track_stability_counters"].clear()
+            stability_data["stable_tracks"].clear()
+            
+            logger.info(f"Camera {camera_id}: 📢 Cooldown timer ended, resuming detection with fresh track IDs")
+            logger.info(f"Camera {camera_id}: 🧹 Cleared stability counters and stable tracks for fresh session")
+        else:
+            logger.debug(f"Camera {camera_id}: Still in cooldown - {remaining_time:.1f}s remaining")
+    
+    return session_state["active"]
+
+def cleanup_camera_stability(camera_id):
+    """Clean up stability tracking data when a camera is disconnected, preserving cooldown timers."""
+    global _camera_stability_tracking
+    if camera_id in _camera_stability_tracking:
+        # Check if any models are still in cooldown before cleanup
+        models_in_cooldown = []
+        for model_id, model_data in _camera_stability_tracking[camera_id].items():
+            session_state = model_data.get("session_state", {})
+            if not session_state.get("active", True) and time.time() < session_state.get("cooldown_until", 0):
+                cooldown_remaining = session_state["cooldown_until"] - time.time()
+                models_in_cooldown.append((model_id, cooldown_remaining))
+                logger.warning(f"⚠️ Camera {camera_id}: Model {model_id} is in cooldown ({cooldown_remaining:.1f}s remaining) - preserving timer!")
+        
+        if models_in_cooldown:
+            # DO NOT clear any tracking data during cooldown - preserve everything
+            logger.warning(f"⚠️ Camera {camera_id}: PRESERVING ALL data during cooldown - no cleanup performed!")
+            logger.warning(f"   - Track IDs will reset only AFTER cooldown expires")
+            logger.warning(f"   - Stability counters preserved until cooldown ends")
+        else:
+            # Safe to delete everything - no active cooldowns
+            del _camera_stability_tracking[camera_id]
+            logger.info(f"Cleaned up stability tracking data for camera {camera_id} (no active cooldowns)")
+
 def validate_pipeline_execution(node, regions_dict):
     """
     Pre-validate that all required branches will execute successfully before 
@@ -618,92 +967,42 @@ def run_pipeline(frame, node: dict, return_bbox: bool=False, context=None):
             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)}")
+        # ─── Session management check ───────────────────────────────────────
+        camera_id = context.get("camera_id", "unknown") if context else "unknown"
+        model_id = node.get("modelId", "unknown")
         
-        res = node["model"].track(
-            frame,
-            stream=False,
-            persist=True,
-            **({"classes": tk} if tk else {})
-        )[0]
+        if not is_camera_active(camera_id, model_id):
+            logger.info(f"⏰ Camera {camera_id}: Tracker stopped - in cooldown period, skipping all detection")
+            return (None, None) if return_bbox else None
 
-        # 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())}")
+        # ─── Detection stage - Using structured detection function ──────────────────
+        all_detections, regions_dict = run_detection_with_tracking(frame, node, context)
         
         if not all_detections:
-            logger.warning("No detections above confidence threshold - returning null")
+            logger.warning("No detections from structured detection function - 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())
+        # Extract bounding boxes for compatibility
+        all_boxes = [det["bbox"] for det in all_detections]
 
-            logger.info(f"Multi-class validation: expected={expected_classes}, detected={detected_classes}")
+        # ─── Stability validation (only for root pipeline node) ────────────────────────
+        stability_threshold = node.get("stabilityThreshold", 1)
+        if stability_threshold > 1:
+            # Extract camera_id for stability check
+            camera_id = context.get("camera_id", "unknown") if context else "unknown"
+            model_id = node.get("modelId", "unknown")
             
-            # 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]
+            # Check if we have stable tracks for this specific camera
+            has_stable_tracks, stable_detections = check_stable_tracks(camera_id, model_id, regions_dict)
             
-            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")
+            if not has_stable_tracks:
+                logger.info(f"Camera {camera_id}: Track not stable yet (threshold: {stability_threshold}) - validation only, skipping branches")
+                # Return early with just the detection result, no branch processing
+                primary_detection = max(all_detections, key=lambda x: x["confidence"]) if all_detections else {"class": "none", "confidence": 0.0, "bbox": [0, 0, 0, 0]}
+                primary_bbox = primary_detection.get("bbox", [0, 0, 0, 0])
+                return (primary_detection, primary_bbox) if return_bbox else primary_detection
             else:
-                logger.info(f"Complete multi-class detection success: {detected_classes}")
-        else:
-            logger.debug("No multi-class validation - proceeding with all detections")
+                logger.info(f"Camera {camera_id}: Stable tracks {[det[1] for det in stable_detections]} detected - proceeding with full pipeline")
 
         # ─── Pre-validate pipeline execution ────────────────────────
         pipeline_valid, missing_branches = validate_pipeline_execution(node, regions_dict)
@@ -752,10 +1051,14 @@ def run_pipeline(frame, node: dict, return_bbox: bool=False, context=None):
         
         execute_actions(node, frame, detection_result, regions_dict)
 
-        # ─── Parallel branch processing ─────────────────────────────
+        # ─── Branch processing (no stability check here) ─────────────────────────────
         if node["branches"]:
             branch_results = {}
             
+            # Extract camera_id for logging
+            camera_id = detection_result.get("camera_id", context.get("camera_id", "unknown") if context else "unknown")
+            
+            
             # Filter branches that should be triggered
             active_branches = []
             for br in node["branches"]:
@@ -849,6 +1152,10 @@ def run_pipeline(frame, node: dict, return_bbox: bool=False, context=None):
         if node.get("parallelActions") and "branch_results" in detection_result:
             execute_parallel_actions(node, frame, detection_result, regions_dict)
             
+            # ─── Start 30s cooldown timer after successful pipeline completion ─────────────────
+            start_cooldown_timer(camera_id, model_id)
+            logger.info(f"Camera {camera_id}: Pipeline completed successfully, starting 30s cooldown")
+
         # ─── Return detection result ────────────────────────────────
         primary_detection = max(all_detections, key=lambda x: x["confidence"])
         primary_bbox = primary_detection["bbox"]

test_botsort_zone_track.py

@@ -0,0 +1,352 @@
+import cv2
+import torch
+import numpy as np
+import time
+from collections import defaultdict
+from ultralytics import YOLO
+
+def point_in_polygon(point, polygon):
+    """Check if a point is inside a polygon using ray casting algorithm"""
+    x, y = point
+    n = len(polygon)
+    inside = False
+    
+    p1x, p1y = polygon[0]
+    for i in range(1, n + 1):
+        p2x, p2y = polygon[i % n]
+        if y > min(p1y, p2y):
+            if y <= max(p1y, p2y):
+                if x <= max(p1x, p2x):
+                    if p1y != p2y:
+                        xinters = (y - p1y) * (p2x - p1x) / (p2y - p1y) + p1x
+                    if p1x == p2x or x <= xinters:
+                        inside = not inside
+        p1x, p1y = p2x, p2y
+    
+    return inside
+
+def draw_zone(frame, zone_polygon, color=(255, 0, 0), thickness=3):
+    """Draw tracking zone on frame"""
+    pts = np.array(zone_polygon, np.int32)
+    pts = pts.reshape((-1, 1, 2))
+    cv2.polylines(frame, [pts], True, color, thickness)
+    
+    # Add semi-transparent fill
+    overlay = frame.copy()
+    cv2.fillPoly(overlay, [pts], color)
+    cv2.addWeighted(overlay, 0.2, frame, 0.8, 0, frame)
+
+def setup_video_writer(output_path, fps, width, height):
+    """Setup video writer for output"""
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    return cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+def write_frame_to_video(video_writer, frame, repeat_count):
+    """Write frame to video with specified repeat count"""
+    for _ in range(repeat_count):
+        video_writer.write(frame)
+
+def finalize_video(video_writer):
+    """Release video writer"""
+    video_writer.release()
+
+def main():
+    video_path = "sample2.mp4"
+    yolo_model = "bangchakv2/yolov8n.pt"
+    
+    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+    print(f"Using device: {device}")
+    
+    print("Loading YOLO model...")
+    model = YOLO(yolo_model)
+    
+    print("Opening video...")
+    cap = cv2.VideoCapture(video_path)
+    fps = int(cap.get(cv2.CAP_PROP_FPS))
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+    
+    print(f"Video info: {width}x{height}, {fps} FPS, {total_frames} frames")
+    
+    # Define tracking zone - Gas station floor area (trapezoidal shape)
+    # Based on the perspective of the gas station floor from your image
+    # width 2560, height 1440
+    
+    tracking_zone = [
+        (423, 974),   # Point 1
+        (1540, 1407), # Point 2
+        (1976, 806),  # Point 3
+        (1364, 749)   # Point 4
+    ]
+    
+    print(f"🎯 Tracking zone defined: {tracking_zone}")
+    
+    # CONTINUOUS TRACKING: Process every 118 frames (~2.0s intervals)
+    frame_skip = 118
+    
+    print(f"🎯 CONTINUOUS MODE: Processing every {frame_skip} frames ({frame_skip/fps:.2f}s intervals)")
+    print(f"🎬 Output video will have same duration as input (each processed frame shown for 2 seconds)")
+    print("🔥 ZONE-FIRST TRACKING: Only cars entering the zone will be tracked!")
+    print("Requires 5 consecutive detections IN ZONE for verification")
+    print("🕐 24/7 MODE: Memory reset every hour to prevent overflow")
+    print("Press 'q' to quit")
+    
+    # Setup video writer for output (same fps as input for normal playback speed)
+    output_path = "tracking_output_botsort_zone_track.mp4"
+    output_fps = fps  # Use same fps as input video
+    out = setup_video_writer(output_path, output_fps, width, height)
+    
+    # Track car IDs and their consecutive detections
+    car_id_counts = defaultdict(int)
+    successful_cars = set()
+    last_positions = {}
+    processed_count = 0
+    
+    # ID remapping for clean sequential zone IDs
+    tracker_to_zone_id = {}  # Maps tracker IDs to clean zone IDs
+    next_zone_id = 1  # Next clean zone ID to assign
+    
+    # Store previous frame detections to filter tracking inputs
+    previous_zone_cars = set()
+    
+    # 24/7 operation: Reset every hour (1800 snapshots at 2-sec intervals = 1 hour)
+    RESET_INTERVAL = 1800  # Reset every 1800 processed frames (1 hour)
+    
+    frame_idx = 0
+    
+    while True:
+        # Skip frames to maintain interval
+        for _ in range(frame_skip):
+            ret, frame = cap.read()
+            if not ret:
+                print("\nNo more frames to read")
+                cap.release()
+                cv2.destroyAllWindows()
+                return
+            frame_idx += 1
+        
+        processed_count += 1
+        current_time = frame_idx / fps
+        
+        print(f"\n🎬 Frame {frame_idx} at {current_time:.2f}s (processed #{processed_count})")
+        
+        # 24/7 Memory Management: Reset every hour
+        if processed_count % RESET_INTERVAL == 0:
+            print(f"🕐 HOURLY RESET: Clearing all tracking data (processed {processed_count} frames)")
+            print(f"   📊 Before reset: {len(tracker_to_zone_id)} tracked cars, next Zone ID was {next_zone_id}")
+            
+            # Clear all tracking data
+            tracker_to_zone_id.clear()
+            car_id_counts.clear()
+            successful_cars.clear()
+            last_positions.clear()
+            next_zone_id = 1  # Reset to 1
+            
+            # Reset BoT-SORT tracker state
+            try:
+                model.reset()
+                print(f"   ✅ BoT-SORT tracker reset successfully")
+            except:
+                print(f"   ⚠️ BoT-SORT reset not available (continuing without reset)")
+            
+            print(f"   🆕 Zone IDs will start from 1 again")
+        
+        # Draw tracking zone on frame
+        draw_zone(frame, tracking_zone, color=(0, 255, 255), thickness=3)  # Yellow zone
+        
+        # First run YOLO detection (without tracking) to find cars in zone
+        detection_results = model(frame, verbose=False, conf=0.7, classes=[2])
+        
+        # Find cars currently in the tracking zone
+        current_zone_cars = []
+        total_detections = 0
+        
+        if detection_results[0].boxes is not None:
+            boxes = detection_results[0].boxes.xyxy.cpu()
+            scores = detection_results[0].boxes.conf.cpu()
+            
+            total_detections = len(boxes)
+            print(f"  🔍 Total car detections: {total_detections}")
+            
+            for i in range(len(boxes)):
+                x1, y1, x2, y2 = boxes[i]
+                conf = float(scores[i])
+                
+                # Check if detection is in zone (using bottom center)
+                box_bottom = ((x1 + x2) / 2, y2)
+                if point_in_polygon(box_bottom, tracking_zone):
+                    current_zone_cars.append({
+                        'bbox': [float(x1), float(y1), float(x2), float(y2)],
+                        'conf': conf,
+                        'center': ((x1 + x2) / 2, (y1 + y2) / 2),
+                        'bottom': box_bottom
+                    })
+        
+        print(f"  🎯 Cars in zone: {len(current_zone_cars)}")
+        
+        # Only run tracking if there are cars in the zone
+        detected_car_ids = set()
+        
+        if current_zone_cars:
+            # Run tracking on the full frame (let tracker handle associations)
+            # But we'll filter results to only zone cars afterward
+            results = model.track(
+                frame, 
+                persist=True,
+                verbose=False,
+                conf=0.7,
+                classes=[2],
+                tracker="botsort_reid.yaml"
+            )
+            
+            if results[0].boxes is not None and results[0].boxes.id is not None:
+                boxes = results[0].boxes.xyxy.cpu()
+                scores = results[0].boxes.conf.cpu()
+                track_ids = results[0].boxes.id.cpu().int()
+                
+                print(f"  📊 Total tracked objects: {len(track_ids)}")
+                
+                # Filter tracked objects to only those in zone
+                zone_tracks = []
+                for i, track_id in enumerate(track_ids):
+                    x1, y1, x2, y2 = boxes[i]
+                    conf = float(scores[i])
+                    
+                    # Check if this tracked object is in our zone
+                    box_bottom = ((x1 + x2) / 2, y2)
+                    if point_in_polygon(box_bottom, tracking_zone):
+                        zone_tracks.append({
+                            'id': int(track_id),
+                            'bbox': [int(x1), int(y1), int(x2), int(y2)],
+                            'conf': conf,
+                            'center': ((x1 + x2) / 2, (y1 + y2) / 2),
+                            'bottom': box_bottom
+                        })
+                
+                print(f"  ✅ Zone tracks: {len(zone_tracks)}")
+                
+                # Process each zone track
+                for track in zone_tracks:
+                    tracker_id = track['id']  # Original tracker ID
+                    x1, y1, x2, y2 = track['bbox']
+                    conf = track['conf']
+                    box_center = track['center']
+                    
+                    # Map tracker ID to clean zone ID
+                    if tracker_id not in tracker_to_zone_id:
+                        tracker_to_zone_id[tracker_id] = next_zone_id
+                        print(f"  🆕 New car: Tracker ID {tracker_id} → Zone ID {next_zone_id}")
+                        next_zone_id += 1
+                    
+                    zone_id = tracker_to_zone_id[tracker_id]  # Clean sequential ID
+                    
+                    # Validate track continuity (use tracker_id for internal logic)
+                    is_valid = True
+                    
+                    # Check for suspicious jumps
+                    if tracker_id in last_positions:
+                        last_center = last_positions[tracker_id]
+                        distance = np.sqrt((box_center[0] - last_center[0])**2 + 
+                                         (box_center[1] - last_center[1])**2)
+                        
+                        if distance > 400:  # pixels in ~2.0s
+                            is_valid = False
+                            print(f"  ⚠️ Zone ID {zone_id} (Tracker {tracker_id}): suspicious jump {distance:.0f}px")
+                    
+                    # Skip already successful cars (use zone_id for user logic)
+                    if zone_id in successful_cars:
+                        is_valid = False
+                        print(f"  ✅ Zone ID {zone_id}: already successful, skipping")
+                    
+                    # Only process valid, high-confidence zone tracks
+                    if is_valid and conf > 0.7:
+                        detected_car_ids.add(zone_id)  # Use zone_id for display
+                        car_id_counts[zone_id] += 1
+                        last_positions[tracker_id] = box_center  # Track by tracker_id internally
+                        
+                        # Draw tracking results with clean zone ID
+                        zone_color = (0, 255, 0)  # Green for zone cars
+                        cv2.rectangle(frame, (x1, y1), (x2, y2), zone_color, 2)
+                        cv2.putText(frame, f'ZONE ID:{zone_id}', 
+                                  (x1, y1-30), cv2.FONT_HERSHEY_SIMPLEX, 0.6, zone_color, 2)
+                        cv2.putText(frame, f'#{car_id_counts[zone_id]} {conf:.2f}', 
+                                  (x1, y1-10), cv2.FONT_HERSHEY_SIMPLEX, 0.6, zone_color, 2)
+                        
+                        # Draw center point
+                        cv2.circle(frame, (int(track['bottom'][0]), int(track['bottom'][1])), 5, zone_color, -1)
+                        
+                        print(f"  ✅ Zone ID {zone_id} (Tracker {tracker_id}): ZONE detection #{car_id_counts[zone_id]} (conf: {conf:.2f})")
+                        
+                        # Check for success (5 consecutive detections IN ZONE)
+                        if car_id_counts[zone_id] == 5:
+                            print(f"🏆 SUCCESS: Zone ID {zone_id} achieved 5 continuous ZONE detections - TRIGGER NEXT MODEL!")
+                            successful_cars.add(zone_id)
+                            
+                            # Add success indicator to frame
+                            cv2.putText(frame, f"SUCCESS: Zone Car {zone_id}!", 
+                                      (50, height-50), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0, 255, 0), 3)
+        else:
+            print("  📋 No cars in zone - no tracking performed")
+            
+            # Draw any cars outside the zone in red (for reference)
+            if detection_results[0].boxes is not None:
+                boxes = detection_results[0].boxes.xyxy.cpu()
+                scores = detection_results[0].boxes.conf.cpu()
+                
+                for i in range(len(boxes)):
+                    x1, y1, x2, y2 = boxes[i]
+                    conf = float(scores[i])
+                    
+                    box_bottom = ((x1 + x2) / 2, y2)
+                    if not point_in_polygon(box_bottom, tracking_zone):
+                        # Draw cars outside zone in red (not tracked)
+                        x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2)
+                        cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 0, 255), 1)
+                        cv2.putText(frame, f'OUT {conf:.2f}', 
+                                  (x1, y1-10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 1)
+        
+        # Display results
+        if detected_car_ids:
+            print(f"  📋 Active Zone IDs: {sorted(detected_car_ids)} (Clean sequential IDs)")
+        
+        # Show ID mapping for debugging
+        if tracker_to_zone_id:
+            mapping_str = ", ".join([f"Tracker{k}→Zone{v}" for k, v in tracker_to_zone_id.items()])
+            print(f"  🔄 ID Mapping: {mapping_str}")
+        
+        # Add annotations to frame
+        cv2.putText(frame, f"BoT-SORT Zone-First Tracking | Frame: {frame_idx} | {current_time:.2f}s", 
+                   (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (255, 255, 255), 2)
+        cv2.putText(frame, f"Zone Cars: {len(current_zone_cars)} | Active Tracks: {len(detected_car_ids)}", 
+                   (10, 65), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (255, 255, 255), 2)
+        cv2.putText(frame, f"Successful Cars: {len(successful_cars)}", 
+                   (10, 100), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2)
+        cv2.putText(frame, "TRACKING ZONE", 
+                   (tracking_zone[0][0], tracking_zone[0][1]-10), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 255), 2)
+        
+        # Write annotated frame to output video (repeat for 2 seconds duration)
+        write_frame_to_video(out, frame, frame_skip)
+        
+        # Show video with zone tracking info
+        display_frame = cv2.resize(frame, (960, 540))
+        cv2.imshow('BoT-SORT Zone-First Tracking', display_frame)
+        
+        # Quick check for quit
+        key = cv2.waitKey(1) & 0xFF
+        if key == ord('q'):
+            break
+        
+        # Small delay to see results
+        time.sleep(0.1)
+    
+    cap.release()
+    finalize_video(out)
+    cv2.destroyAllWindows()
+    print(f"\n🎯 BoT-SORT zone-first tracking completed!")
+    print(f"📊 Processed {processed_count} frames with {frame_skip/fps:.2f}s intervals")
+    print(f"🏆 Successfully tracked {len(successful_cars)} unique cars IN ZONE")
+    print(f"💾 Annotated video saved to: {output_path}")
+
+if __name__ == "__main__":
+    main()

test_detection_tracking.py

@@ -0,0 +1,190 @@
+#!/usr/bin/env python3
+"""
+Test script for the refactored detection and tracking functionality.
+"""
+import os
+import sys
+import cv2
+import numpy as np
+import logging
+from pathlib import Path
+
+# Add the project root to Python path
+sys.path.insert(0, str(Path(__file__).parent))
+
+from siwatsystem.pympta import run_detection_with_tracking, load_pipeline_from_zip
+
+# Set up logging
+logging.basicConfig(
+    level=logging.DEBUG,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+)
+logger = logging.getLogger(__name__)
+
+def create_test_frame():
+    """Create a simple test frame for detection testing."""
+    frame = np.zeros((480, 640, 3), dtype=np.uint8)
+    # Add some simple shapes to simulate objects
+    cv2.rectangle(frame, (50, 50), (200, 150), (255, 0, 0), -1)  # Blue rectangle
+    cv2.rectangle(frame, (300, 200), (450, 350), (0, 255, 0), -1)  # Green rectangle
+    cv2.putText(frame, "Test Frame", (250, 400), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2)
+    return frame
+
+def test_detection_function():
+    """Test the structured detection function with mock data."""
+    logger.info("Testing run_detection_with_tracking function...")
+    
+    # Create test frame
+    test_frame = create_test_frame()
+    
+    # Mock node configuration (simulating what would come from an MPTA file)
+    mock_node = {
+        "modelId": "test_detection_v1",
+        "triggerClasses": ["car", "person"],
+        "triggerClassIndices": [0, 1],
+        "minConfidence": 0.5,
+        "multiClass": False,
+        "expectedClasses": [],
+        "tracking": {
+            "enabled": True,
+            "reidConfigPath": "botsort.yaml"
+        }
+    }
+    
+    # Mock context
+    test_context = {
+        "display_id": "test-display-001",
+        "camera_id": "test-cam-001"
+    }
+    
+    logger.info("Mock node configuration:")
+    for key, value in mock_node.items():
+        logger.info(f"  {key}: {value}")
+    
+    # Note: This test will fail without a real YOLO model, but demonstrates the structure
+    try:
+        detections, regions = run_detection_with_tracking(test_frame, mock_node, test_context)
+        logger.info(f"Function executed successfully!")
+        logger.info(f"Returned detections: {len(detections)}")
+        logger.info(f"Returned regions: {list(regions.keys())}")
+        return True
+    except Exception as e:
+        logger.error(f"Function failed (expected without real model): {e}")
+        return False
+
+def test_mpta_loading():
+    """Test loading an MPTA file with tracking configuration."""
+    logger.info("Testing MPTA loading with tracking configuration...")
+    
+    # Check if models directory exists
+    models_dir = Path("models")
+    if not models_dir.exists():
+        logger.warning("No models directory found - skipping MPTA test")
+        return False
+    
+    # Look for any .mpta files
+    mpta_files = list(models_dir.glob("**/*.mpta"))
+    if not mpta_files:
+        logger.warning("No .mpta files found in models directory - skipping MPTA test")
+        return False
+    
+    mpta_file = mpta_files[0]
+    logger.info(f"Testing with MPTA file: {mpta_file}")
+    
+    try:
+        # Attempt to load pipeline
+        target_dir = f"temp_test_{os.getpid()}"
+        pipeline = load_pipeline_from_zip(str(mpta_file), target_dir)
+        
+        if pipeline:
+            logger.info("MPTA loaded successfully!")
+            logger.info(f"Pipeline model ID: {pipeline.get('modelId')}")
+            logger.info(f"Tracking config: {pipeline.get('tracking')}")
+            
+            # Clean up
+            import shutil
+            if os.path.exists(target_dir):
+                shutil.rmtree(target_dir)
+            
+            return True
+        else:
+            logger.error("Failed to load MPTA pipeline")
+            return False
+            
+    except Exception as e:
+        logger.error(f"MPTA loading failed: {e}")
+        return False
+
+def print_usage_example():
+    """Print example usage of the new structured functions."""
+    logger.info("\n" + "="*60)
+    logger.info("USAGE EXAMPLE - Structured Detection & Tracking")
+    logger.info("="*60)
+    
+    example_config = '''
+    Example pipeline.json configuration:
+    
+    {
+      "pipeline": {
+        "modelId": "car_frontal_detection_v1",
+        "modelFile": "yolo11n.pt",
+        "triggerClasses": ["Car", "Frontal"],
+        "minConfidence": 0.7,
+        "multiClass": true,
+        "expectedClasses": ["Car", "Frontal"],
+        "tracking": {
+          "enabled": true,
+          "reidConfigPath": "botsort_reid.yaml"
+        },
+        "actions": [...],
+        "branches": [...]
+      }
+    }
+    '''
+    
+    logger.info(example_config)
+    
+    code_example = '''
+    Usage in code:
+    
+    # Load pipeline from MPTA file
+    pipeline = load_pipeline_from_zip("model.mpta", "temp_dir")
+    
+    # Run detection with tracking
+    detections, regions = run_detection_with_tracking(frame, pipeline, context)
+    
+    # Process results
+    for detection in detections:
+        class_name = detection["class"]
+        confidence = detection["confidence"]
+        track_id = detection["id"]  # Available when tracking enabled
+        bbox = detection["bbox"]
+        print(f"Detected: {class_name} (ID: {track_id}, conf: {confidence:.2f})")
+    '''
+    
+    logger.info(code_example)
+
+def main():
+    """Main test function."""
+    logger.info("Starting detection & tracking refactoring tests...")
+    
+    # Test 1: Function structure
+    test1_passed = test_detection_function()
+    
+    # Test 2: MPTA loading
+    test2_passed = test_mpta_loading()
+    
+    # Print usage examples
+    print_usage_example()
+    
+    # Summary
+    logger.info("\n" + "="*60)
+    logger.info("TEST SUMMARY")
+    logger.info("="*60)
+    logger.info(f"Function structure test: {'PASS' if test1_passed else 'EXPECTED FAIL (no model)'}")
+    logger.info(f"MPTA loading test: {'PASS' if test2_passed else 'SKIP (no files)'}")
+    logger.info("\nRefactoring completed successfully!")
+    logger.info("The detection and tracking code is now structured and easy to configure.")
+
+if __name__ == "__main__":
+    main()

webcam_rtsp_server.py

@@ -0,0 +1,325 @@
+#!/usr/bin/env python3
+"""
+Enhanced webcam server that provides both RTSP streaming and HTTP snapshot endpoints
+Compatible with CMS UI requirements for camera configuration
+"""
+
+import cv2
+import threading
+import time
+import logging
+import socket
+from http.server import BaseHTTPRequestHandler, HTTPServer
+import subprocess
+import sys
+import os
+
+# Configure logging
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s [%(levelname)s] %(name)s: %(message)s"
+)
+logger = logging.getLogger("webcam_rtsp_server")
+
+# Global webcam capture object
+webcam_cap = None
+rtsp_process = None
+
+class WebcamHTTPHandler(BaseHTTPRequestHandler):
+    """HTTP handler for snapshot requests"""
+    
+    def do_GET(self):
+        if self.path == '/snapshot' or self.path == '/snapshot.jpg':
+            try:
+                # Capture fresh frame from webcam for each request
+                ret, frame = webcam_cap.read()
+                if ret and frame is not None:
+                    # Encode as JPEG
+                    success, buffer = cv2.imencode('.jpg', frame, [cv2.IMWRITE_JPEG_QUALITY, 85])
+                    if success:
+                        self.send_response(200)
+                        self.send_header('Content-Type', 'image/jpeg')
+                        self.send_header('Content-Length', str(len(buffer)))
+                        self.send_header('Cache-Control', 'no-cache, no-store, must-revalidate')
+                        self.send_header('Pragma', 'no-cache')
+                        self.send_header('Expires', '0')
+                        self.end_headers()
+                        self.wfile.write(buffer.tobytes())
+                        logger.debug(f"Served webcam snapshot, size: {len(buffer)} bytes")
+                        return
+                    else:
+                        logger.error("Failed to encode frame as JPEG")
+                else:
+                    logger.error("Failed to capture frame from webcam")
+                
+                # Send error response
+                self.send_response(500)
+                self.send_header('Content-Type', 'text/plain')
+                self.end_headers()
+                self.wfile.write(b'Failed to capture webcam frame')
+                
+            except Exception as e:
+                logger.error(f"Error serving snapshot: {e}")
+                self.send_response(500)
+                self.send_header('Content-Type', 'text/plain')
+                self.end_headers()
+                self.wfile.write(f'Error: {str(e)}'.encode())
+        
+        elif self.path == '/status':
+            # Status endpoint for health checking
+            self.send_response(200)
+            self.send_header('Content-Type', 'application/json')
+            self.end_headers()
+            
+            width = int(webcam_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+            height = int(webcam_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+            fps = webcam_cap.get(cv2.CAP_PROP_FPS)
+            
+            status = f'{{"status": "online", "width": {width}, "height": {height}, "fps": {fps}}}'
+            self.wfile.write(status.encode())
+        
+        else:
+            # 404 for other paths
+            self.send_response(404)
+            self.send_header('Content-Type', 'text/plain')
+            self.end_headers()
+            self.wfile.write(b'Not Found - Available endpoints: /snapshot, /snapshot.jpg, /status')
+    
+    def log_message(self, format, *args):
+        # Suppress default HTTP server logging to avoid spam
+        pass
+
+def check_ffmpeg():
+    """Check if FFmpeg is available for RTSP streaming"""
+    try:
+        result = subprocess.run(['ffmpeg', '-version'], 
+                              capture_output=True, text=True, timeout=5)
+        if result.returncode == 0:
+            logger.info("FFmpeg found and working")
+            return True
+    except (subprocess.TimeoutExpired, FileNotFoundError, subprocess.SubprocessError):
+        pass
+    
+    logger.warning("FFmpeg not found. RTSP streaming will not be available.")
+    logger.info("To enable RTSP streaming, install FFmpeg:")
+    logger.info("  Windows: Download from https://ffmpeg.org/download.html")
+    logger.info("  Linux: sudo apt install ffmpeg")
+    logger.info("  macOS: brew install ffmpeg")
+    return False
+
+def get_windows_camera_name():
+    """Get the actual camera device name on Windows"""
+    try:
+        # List video devices using FFmpeg with proper encoding handling
+        result = subprocess.run(['ffmpeg', '-f', 'dshow', '-list_devices', 'true', '-i', 'dummy'], 
+                              capture_output=True, text=True, timeout=10, encoding='utf-8', errors='ignore')
+        output = result.stderr  # FFmpeg outputs device list to stderr
+        
+        # Look for video devices in the output
+        lines = output.split('\n')
+        video_devices = []
+        
+        # Parse the output - look for lines with (video) that contain device names in quotes
+        for line in lines:
+            if '[dshow @' in line and '(video)' in line and '"' in line:
+                # Extract device name between first pair of quotes
+                start = line.find('"') + 1
+                end = line.find('"', start)
+                if start > 0 and end > start:
+                    device_name = line[start:end]
+                    video_devices.append(device_name)
+        
+        logger.info(f"Found Windows video devices: {video_devices}")
+        if video_devices:
+            # Force use the first device (index 0) which is the Logitech HD webcam
+            return video_devices[0]  # This will be "罗技高清网络摄像机 C930c"
+        else:
+            logger.info("No devices found via FFmpeg detection, using fallback")
+            # Fall through to fallback names
+        
+    except Exception as e:
+        logger.debug(f"Failed to get Windows camera name: {e}")
+    
+    # Try common camera device names as fallback
+    # Prioritize Integrated Camera since that's what's working now
+    common_names = [
+        "Integrated Camera",  # This is working for the current setup
+        "USB Video Device",  # Common name for USB cameras
+        "USB2.0 Camera",
+        "C930c",  # Direct model name
+        "HD Pro Webcam C930c",  # Full Logitech name
+        "Logitech",  # Brand name
+        "USB Camera",
+        "Webcam"
+    ]
+    logger.info(f"Using fallback camera names: {common_names}")
+    return common_names[0]  # Return "Integrated Camera" first
+
+def start_rtsp_stream(webcam_index=0, rtsp_port=8554):
+    """Start RTSP streaming using FFmpeg"""
+    global rtsp_process
+    
+    if not check_ffmpeg():
+        return None
+    
+    try:
+        # Get the actual camera device name for Windows
+        if sys.platform.startswith('win'):
+            camera_name = get_windows_camera_name()
+            logger.info(f"Using Windows camera device: {camera_name}")
+        
+        # FFmpeg command to stream webcam via RTSP
+        if sys.platform.startswith('win'):
+            cmd = [
+                'ffmpeg',
+                '-f', 'dshow',
+                '-i', f'video={camera_name}',  # Use detected camera name
+                '-c:v', 'libx264',
+                '-preset', 'veryfast',
+                '-tune', 'zerolatency',
+                '-r', '30',
+                '-s', '1280x720',
+                '-f', 'rtsp',
+                f'rtsp://localhost:{rtsp_port}/stream'
+            ]
+        elif sys.platform.startswith('linux'):
+            cmd = [
+                'ffmpeg',
+                '-f', 'v4l2',
+                '-i', f'/dev/video{webcam_index}',
+                '-c:v', 'libx264',
+                '-preset', 'veryfast',
+                '-tune', 'zerolatency',
+                '-r', '30',
+                '-s', '1280x720',
+                '-f', 'rtsp',
+                f'rtsp://localhost:{rtsp_port}/stream'
+            ]
+        else:  # macOS
+            cmd = [
+                'ffmpeg',
+                '-f', 'avfoundation',
+                '-i', f'{webcam_index}:',
+                '-c:v', 'libx264',
+                '-preset', 'veryfast',
+                '-tune', 'zerolatency',
+                '-r', '30',
+                '-s', '1280x720',
+                '-f', 'rtsp',
+                f'rtsp://localhost:{rtsp_port}/stream'
+            ]
+        
+        logger.info(f"Starting RTSP stream on rtsp://localhost:{rtsp_port}/stream")
+        logger.info(f"FFmpeg command: {' '.join(cmd)}")
+        
+        rtsp_process = subprocess.Popen(
+            cmd,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            text=True
+        )
+        
+        # Give FFmpeg a moment to start
+        time.sleep(2)
+        
+        # Check if process is still running
+        if rtsp_process.poll() is None:
+            logger.info("RTSP streaming started successfully")
+            return rtsp_process
+        else:
+            # Get error output if process failed
+            stdout, stderr = rtsp_process.communicate(timeout=2)
+            logger.error("RTSP streaming failed to start")
+            logger.error(f"FFmpeg stdout: {stdout}")
+            logger.error(f"FFmpeg stderr: {stderr}")
+            return None
+            
+    except Exception as e:
+        logger.error(f"Failed to start RTSP stream: {e}")
+        return None
+
+def get_local_ip():
+    """Get the Wireguard IP address for external access"""
+    # Use Wireguard IP for external access
+    return "10.101.1.4"
+
+def main():
+    global webcam_cap, rtsp_process
+    
+    # Configuration - Force use index 0 for Logitech HD webcam
+    webcam_index = 0  # Logitech HD webcam C930c (1920x1080@30fps)
+    http_port = 8080
+    rtsp_port = 8554
+    
+    logger.info("=== Webcam RTSP & HTTP Server ===")
+    
+    # Initialize webcam
+    logger.info("Initializing webcam...")
+    webcam_cap = cv2.VideoCapture(webcam_index)
+    
+    if not webcam_cap.isOpened():
+        logger.error(f"Failed to open webcam at index {webcam_index}")
+        logger.info("Try different webcam indices (0, 1, 2, etc.)")
+        return
+    
+    # Set webcam properties - Use high resolution for Logitech HD webcam
+    webcam_cap.set(cv2.CAP_PROP_FRAME_WIDTH, 1920)
+    webcam_cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 1080)
+    webcam_cap.set(cv2.CAP_PROP_FPS, 30)
+    
+    width = int(webcam_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(webcam_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    fps = webcam_cap.get(cv2.CAP_PROP_FPS)
+    
+    logger.info(f"Webcam initialized: {width}x{height} @ {fps}fps")
+    
+    # Get local IP for CMS configuration
+    local_ip = get_local_ip()
+    
+    # Start RTSP streaming (optional, requires FFmpeg)
+    rtsp_process = start_rtsp_stream(webcam_index, rtsp_port)
+    
+    # Start HTTP server for snapshots
+    server_address = ('0.0.0.0', http_port)  # Bind to all interfaces
+    http_server = HTTPServer(server_address, WebcamHTTPHandler)
+    
+    logger.info("\n=== Server URLs for CMS Configuration ===")
+    logger.info(f"HTTP Snapshot URL: http://{local_ip}:{http_port}/snapshot")
+    
+    if rtsp_process:
+        logger.info(f"RTSP Stream URL: rtsp://{local_ip}:{rtsp_port}/stream")
+    else:
+        logger.info("RTSP Stream: Not available (FFmpeg not found)")
+        logger.info("HTTP-only mode: Use Snapshot URL for camera input")
+    
+    logger.info(f"Status URL: http://{local_ip}:{http_port}/status")
+    logger.info("\n=== CMS Configuration Suggestions ===")
+    logger.info(f"Camera Identifier: webcam-local-01")
+    logger.info(f"RTSP Stream URL: rtsp://{local_ip}:{rtsp_port}/stream")
+    logger.info(f"Snapshot URL: http://{local_ip}:{http_port}/snapshot")
+    logger.info(f"Snapshot Interval: 2000 (ms)")
+    logger.info("\nPress Ctrl+C to stop all servers")
+    
+    try:
+        # Start HTTP server
+        http_server.serve_forever()
+    except KeyboardInterrupt:
+        logger.info("Shutting down servers...")
+    finally:
+        # Clean up
+        if webcam_cap:
+            webcam_cap.release()
+        
+        if rtsp_process:
+            logger.info("Stopping RTSP stream...")
+            rtsp_process.terminate()
+            try:
+                rtsp_process.wait(timeout=5)
+            except subprocess.TimeoutExpired:
+                rtsp_process.kill()
+        
+        http_server.server_close()
+        logger.info("All servers stopped")
+
+if __name__ == "__main__":
+    main()