WeaponSynopsis analyzes video footage to identify weapons (firearms, knives, etc.) and creates a shortened video containing only the relevant segments where detections occur. This is useful for security review, forensic analysis, and efficient surveillance monitoring.
- Real-time Weapon Detection - Identifies firearms, knives, and other weapons using deep learning
- Video Synopsis Generation - Outputs a condensed video with only detection events
- Multiple Input Sources - Supports video files, RTSP streams, and webcams
- Python
- YOLOv5
- PyTorch
This project is intended for legitimate security and research purposes only. Users are responsible for ensuring compliance with local laws and regulations.
MIT License
Contributions welcome! Please open an issue or submit a pull request.