How 02-debug/ai-powered-car-parking-space-detection-using-yolov8-opencv works
This is a parking-space occupancy monitor: users mark spaces on an image, then the video program classifies each marked region as free or occupied and displays a live count. The sampled runtime uses image thresholding and pixel counts—not YOLO vehicle detection—despite the README’s broader description. The graph reflects the sampled code; the README also describes image-mode detection and YOLO capabilities whose implementation is not evident in the supplied source.
Main entry points: main.py Video Loop · 1.py Mark Spaces · CarParkPos Space Positions · faultcode.py Alternate Metrics
Components 10
Space Setup
- Mark Spaces
1.py
Video Monitoring
- Video Loop
main.py - Frame Preprocessing
main.py - Space Classification
main.py - Results Overlay
main.py - Alternate Metrics
faultcode.py
Parking Data
- Space Positions
CarParkPos - Setup Image
- Parking Video
carPark.mp4
Other components
- User
Connections 12
- User → Mark Spaces: marks spaces
- Setup Image → Mark Spaces: loads image
- Mark Spaces → Space Positions: saves coordinates
- User → Video Loop: quits playback
- Parking Video → Video Loop: supplies frames
- Space Positions → Video Loop: loads coordinates
- Video Loop → Frame Preprocessing: passes frames
- Video Loop → Space Classification: checks spaces
- Space Classification → Results Overlay: sends status
- Results Overlay → User: displays results
- Alternate Metrics → Parking Video: reads video
- Alternate Metrics → Space Positions: loads coordinates