wmcnally/kapao

KAPAO is an efficient single-stage human pose estimation model that detects keypoints and poses as objects and fuses the detections to predict human poses.

47
/ 100
Emerging

This tool helps analyze human movement by identifying key body points and overall poses from images and videos. It takes in visual media (photos or video clips) and outputs annotated images or videos showing detected poses and individual keypoints like joints. Researchers, sports analysts, or security professionals interested in tracking human actions can use this to understand motion.

772 stars. No commits in the last 6 months.

Use this if you need fast and accurate identification of multiple people's poses and key body points in images or videos, even in crowded or low-resolution scenarios.

Not ideal if your primary goal is general object detection beyond human pose, or if you require very low-power, embedded real-time applications without GPU support.

human-movement-analysis video-surveillance sports-science action-recognition robotics-vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

772

Forks

104

Language

Python

License

GPL-3.0

Last pushed

Nov 02, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/wmcnally/kapao"

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