How sivaprakash2k3/container-door-detection works
This is a single-script video application that tracks container detections and classifies each tracked crop as Open or Closed. The main workflow reads video frames, runs YOLO tracking, preprocesses each crop, combines two intensity-based decisions using a per-object reference image, and overlays results for display. The graph reflects the inspected script and README; input and model paths are hard-coded, and no separate persistence or service layer is shown.
Main entry points: door_state_detection.py Container Crop
Components 11
Video Detection Runtime
- Video Input
door_state_detection.py - YOLO Tracking
door_state_detection.py - Container Crop
door_state_detection.py - Per-ID Reference
door_state_detection.py
Image Analysis
- Contour Preprocessing
door_state_detection.py - Side Intensity
door_state_detection.py - Reference Difference
door_state_detection.py - State Decision
door_state_detection.py
Result Display
- Overlay Rendering
door_state_detection.py - Video Display
door_state_detection.py
Other components
- Operator
Connections 13
- Operator → Video Input: provides footage
README.md - Video Input → YOLO Tracking: reads frames
door_state_detection.py - YOLO Tracking → Container Crop: yields boxes
door_state_detection.py - Container Crop → Contour Preprocessing: extracts contours
door_state_detection.py - Container Crop → Side Intensity: analyzes gray crop
door_state_detection.py - Container Crop → Per-ID Reference: initializes per ID
door_state_detection.py - Per-ID Reference → Reference Difference: supplies baseline
door_state_detection.py - Container Crop → Reference Difference: compares frame
door_state_detection.py - Side Intensity → State Decision: supplies state
door_state_detection.py - Reference Difference → State Decision: supplies state
door_state_detection.py - State Decision → Overlay Rendering: sets label
door_state_detection.py - Contour Preprocessing → Overlay Rendering: supplies contours
door_state_detection.py - Overlay Rendering → Video Display: draws results
door_state_detection.py