qubvel/rt-pose

Real-time pose estimation pipeline with 🤗 Transformers

38
/ 100
Emerging

This tool helps you automatically identify and track human body positions in videos or images. You input a video file or image, and it outputs the locations of people and 17 key points on their bodies (like elbows, knees, and nose) for each person detected. It's designed for anyone working with video analysis who needs to understand human movement, such as in sports analysis, ergonomic studies, or security monitoring.

No commits in the last 6 months.

Use this if you need to precisely locate and track human body joints in real-time video streams or still images.

Not ideal if you're analyzing static objects, require highly specialized pose estimation for non-human subjects, or don't have access to a GPU.

motion-capture sports-analytics human-computer-interaction video-surveillance gait-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

67

Forks

9

Language

Python

License

Apache-2.0

Last pushed

Feb 07, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/qubvel/rt-pose"

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