chandran-jr/Violence-Alert-System

🎦A violence detector using MobileNetV2 pretrained model and image enhancement algorithms and face detection algorithms implemented using Python, including an alert system built using telegram for alerting concerned authorities, and all data stored neatly in cloud firestore🎦

45
/ 100
Emerging

The system implements a multi-stage detection pipeline combining Faster RCNN for human localization, MobileNetV2 for violence classification, and MTCNN for facial recognition, with image enhancement via PIL sharpness/color adjustment. Real-time alerts are dispatched through a Telegram bot upon violence detection, transmitting enhanced frames with extracted facial data and metadata (location, timestamp, camera ID). All evidence—original frames, face detection outputs, and incident metadata—is persisted to Google Cloud Firestore with access controls for authorized personnel.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

82

Forks

28

Language

Jupyter Notebook

License

MIT

Last pushed

Jul 04, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/chandran-jr/Violence-Alert-System"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.