ZheC/Realtime_Multi-Person_Pose_Estimation

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

51
/ 100
Established

This project helps you automatically detect and track the body posture (pose) of multiple people in real-time from videos or images. You provide a video stream or image, and it outputs the precise location of key body points for each person. This is ideal for researchers or developers working on applications that require understanding human movement, such as in sports analysis, animation, or interactive systems.

5,125 stars. No commits in the last 6 months.

Use this if you need to identify and track individual body keypoints (like elbows, knees, head) for multiple people simultaneously in live video feeds or pre-recorded media.

Not ideal if you only need to detect the presence of people without detailed pose information, or if you require 3D pose estimation.

human-pose-estimation motion-capture video-analysis computer-vision sports-science
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

5,125

Forks

1,362

Language

Jupyter Notebook

License

Last pushed

Mar 21, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ZheC/Realtime_Multi-Person_Pose_Estimation"

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