felixchenfy/Realtime-Action-Recognition

Apply ML to the skeletons from OpenPose; 9 actions; multiple people. (WARNING: I'm sorry that this is only good for course demo, not for real world applications !!! Those ary very difficult !!!)

51
/ 100
Established

This project identifies nine different human actions—like walking, running, or waving—in real-time video or webcam feeds, even with multiple people present. It takes live video as input, analyzes people's movements using skeletal tracking, and labels each person with the action they are performing. This could be useful for researchers studying human behavior or movement patterns.

940 stars. No commits in the last 6 months.

Use this if you need to automatically detect basic human actions from video footage for a course demonstration or a preliminary study.

Not ideal if you require robust, production-ready action recognition for real-world applications with high accuracy demands, as this project is noted to be best for demonstration purposes.

human-behavior-analysis video-analytics movement-recognition activity-detection computer-vision-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

940

Forks

259

Language

Python

License

MIT

Last pushed

Jul 03, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/felixchenfy/Realtime-Action-Recognition"

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