A production-ready computer vision system for real-time object detection and multi-object tracking, built with YOLOv8 and Streamlit. This project demonstrates clean architecture, comprehensive testing, and modern ML engineering practices.
Key Features#
- Real-time Object Detection - YOLOv8-powered detection with adjustable confidence thresholds
- Multi-Object Tracking - Persistent object tracking across frames with unique IDs
- Multiple Input Sources - Support for webcam streams, video files, and static images
- Interactive Web UI - Clean Streamlit interface with real-time parameter adjustment
- Performance Optimization - Frame skipping, model caching, and IOU threshold tuning
- Comprehensive Testing - 71 tests with 94% code coverage
- Production-Ready - Type hints, error handling, logging, and configuration management
Technologies#
- Python 3.10+ - Modern Python with full type hint support
- YOLOv8 (Ultralytics) - State-of-the-art object detection
- OpenCV - Computer vision and video processing
- Streamlit - Interactive web interface
- pytest - Comprehensive testing framework (94% coverage)
Project Status#
Active development - Last updated October 2025