sanchit2843/Videoclassification

Crime detection in cctv footage using deep learning

37
/ 100
Emerging

This project helps security personnel and surveillance teams automatically identify criminal activities in CCTV footage. It takes video clips from surveillance cameras as input and outputs classifications like 'abuse', 'arrest', 'arson', 'assault', 'burglary', 'explosion', and 'fighting', alongside 'normal' activity. This tool is ideal for security managers, law enforcement, or anyone responsible for monitoring large volumes of video surveillance.

No commits in the last 6 months.

Use this if you need an automated system to flag specific criminal behaviors in your security camera feeds, reducing the need for constant manual monitoring.

Not ideal if you need to detect nuanced or less overt criminal activities beyond the eight predefined categories, or if your video quality is consistently very low.

video-surveillance crime-detection security-monitoring public-safety loss-prevention
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 20 / 25

How are scores calculated?

Stars

99

Forks

23

Language

Jupyter Notebook

License

Category

home-security-ai

Last pushed

Apr 17, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sanchit2843/Videoclassification"

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