engares/MoViNets-for-Violence-Detection-in-Live-Video-Streaming

Violence recognition in streaming video using Transfer Learning and MoViNets. The project leverages state-of-the-art deep learning techniques to create an efficient and accurate violence detection system.

23
/ 100
Experimental

This project helps security and operations teams automatically detect violence in live video streams. It takes a raw video feed as input and outputs real-time alerts or classifications when violent acts are identified. This is designed for security personnel, system integrators, or facility managers who need to monitor surveillance feeds efficiently, especially in environments with limited computing resources.

No commits in the last 6 months.

Use this if you need an efficient, real-time solution for flagging violent incidents in video surveillance using devices like a Raspberry Pi.

Not ideal if you require a solution for detecting non-violent anomalies or specific actions beyond general violence.

video-surveillance security-monitoring real-time-alerting edge-AI facility-management
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

16

Forks

2

Language

Jupyter Notebook

License

Last pushed

Jul 15, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/engares/MoViNets-for-Violence-Detection-in-Live-Video-Streaming"

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