CMU-Perceptual-Computing-Lab/openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

51
/ 100
Established

This project helps you automatically detect and track human body, face, and hand movements in real-time from videos, webcams, or images. It takes visual input and outputs detailed skeletal or keypoint data (like elbow, nose, or fingertip positions) for multiple people. Researchers in human-computer interaction, sports scientists, or animators can use this to analyze or reproduce human motion.

33,855 stars. No commits in the last 6 months.

Use this if you need to precisely track full-body human motion, including subtle hand and facial expressions, from standard video sources in real-time.

Not ideal if you only need to detect simple presence or gross movement without requiring detailed skeletal information for each body part.

motion-capture human-pose-estimation animation behavior-analysis human-robot-interaction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

33,855

Forks

8,054

Language

C++

License

Last pushed

Aug 03, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/CMU-Perceptual-Computing-Lab/openpose"

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