rwightman/posenet-python

A Python port of Google TensorFlow.js PoseNet (Real-time Human Pose Estimation)

51
/ 100
Established

This tool helps you automatically detect and track human poses in images or live video feeds. You input images or a webcam stream, and it outputs the same images or video with human skeletal keypoints and outlines overlaid. This is useful for anyone working with human movement analysis, such as animators, sports trainers, or researchers studying human behavior.

505 stars. No commits in the last 6 months.

Use this if you need to identify and visualize human body keypoints and skeletons in pre-recorded images or real-time webcam footage using a Python environment.

Not ideal if you require extremely high performance for complex multi-person scenes in a production environment, as further optimization beyond this Python implementation might be needed.

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

How are scores calculated?

Stars

505

Forks

183

Language

Python

License

Apache-2.0

Last pushed

Sep 02, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rwightman/posenet-python"

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