dyneth02/MoveNet-Multipose-Detection-OpenCV

A real-time multi-person human pose estimation system using TensorFlow MoveNet Multipose (Lightning). Built with OpenCV for video and webcam inference, it detects and visualizes keypoints and skeletal connections with confidence-based filtering, optimized for speed and multi-person scenarios.

23
/ 100
Experimental

This tool helps you analyze human movement in real-time from video files or a live camera feed. It takes your video or webcam stream and identifies up to six people, showing their body keypoints and skeletal connections. Fitness instructors, sports coaches, and surveillance operators could use this to track movement.

Use this if you need to automatically detect and visualize the poses of multiple people simultaneously for applications like fitness analysis or security monitoring.

Not ideal if you only need to detect single-person poses or require extremely high precision for medical-grade motion capture.

fitness-monitoring sports-performance-analysis security-surveillance human-activity-recognition gesture-control
No Package No Dependents
Maintenance 6 / 25
Adoption 4 / 25
Maturity 13 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 02, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/dyneth02/MoveNet-Multipose-Detection-OpenCV"

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