How redah13/yolov8-object-detection works
LiveDetekt combines a PyQt desktop client for biometric-gated object detection with a Flask authentication backend backed by SQL Server. The user flow starts at the welcome screen, proceeds through facial registration or login, then opens a dashboard for webcam, image, or video analysis; YOLO results feed visual overlays and analytics. The graph covers the principal UI, inference, and authentication layers. Some mode-switching and deployment details are documented but not fully sampled, so those links are identified as documented or left unverified.
Main entry points: detect_window.py Detection dashboard · services.py Face registration and verification · main.py App navigation · auth_window.py Auth window
Components 14
Desktop client
- App navigation
main.py - Welcome screen
gui/welcome_window.py - Auth window
gui/auth_window.py
Detection and analytics
- Detection dashboard
gui/detect_window.py - Image/video analysis
gui/image_video_window.py - Dashboard widgets
gui/widgets.py - YOLO inference
backend/detection/predict.py - Model weights
yolo_models/best.pt
Biometric authentication
- Flask auth API
backend/app.py - Face registration and verification
backend/services.py
Authentication storage
- SQL connection config
backend/config.py - SQL Server users
Other components
- User
- Face recognition library
Connections 15
- User → Welcome screen: starts at
README.md - Welcome screen → App navigation: signals start
main.py - App navigation → Auth window: opens auth
main.py - Auth window → Flask auth API: sends auth requests
gui/auth_window.py - Flask auth API → Face registration and verification: routes register/login
backend/app.py - Face registration and verification → SQL connection config: uses connection settings
backend/services.py - Face registration and verification → SQL Server users: reads/writes users
backend/services.py - Face registration and verification → Face recognition library: encodes and compares faces
backend/services.py - Auth window → App navigation: signals success
main.py - App navigation → Detection dashboard: opens dashboard
main.py - Detection dashboard → YOLO inference: detects frames
gui/detect_window.py - Image/video analysis → YOLO inference: detects file frames
gui/image_video_window.py - YOLO inference → Model weights: loads model
backend/detection/predict.py - Detection dashboard → Dashboard widgets: renders analytics
gui/detect_window.py - Detection dashboard → Image/video analysis: opens file modes
README.md