CV-ZMH/human-action-recognition

Multi Person Skeleton Based Action Recognition and Tracking

46
/ 100
Emerging

This project helps security and surveillance professionals automatically identify and track human actions in real-time video feeds. It takes live video or recorded footage as input and outputs a labeled stream indicating actions like 'walk,' 'run,' 'jump,' or 'fight' for multiple people simultaneously. Law enforcement, retail security, or event organizers could use this to monitor behavior.

165 stars. No commits in the last 6 months.

Use this if you need to automatically detect and classify common human actions within video, especially in scenarios with multiple people.

Not ideal if you require recognition of highly specialized or nuanced actions, or if your primary goal is facial recognition.

video-surveillance security-monitoring behavior-analysis real-time-analytics public-safety
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

165

Forks

32

Language

Python

License

MIT

Last pushed

Jan 26, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/CV-ZMH/human-action-recognition"

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