smaranjitghose/MoveNet
Fastest Pose Estimation on any device
This tool helps you quickly identify and track 17 key points on a human body, like elbows, knees, and nose, and draw lines connecting them to visualize posture. It takes a live camera feed or a video file as input and outputs a video stream with the detected poses overlaid. This is useful for anyone needing to observe and analyze human movement or body positioning.
No commits in the last 6 months.
Use this if you need a fast way to prototype or demonstrate basic human pose detection from video.
Not ideal if you require highly precise, production-ready pose tracking, as this version is for prototyping and a 'Thunder Version' is recommended for better results.
Stars
10
Forks
6
Language
Python
License
MIT
Category
Last pushed
Jul 11, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/smaranjitghose/MoveNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DeepLabCut/DeepLabCut
Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with...
openpifpaf/openpifpaf
Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and...
lambdaloop/anipose
🐜🐀🐒🚶 A toolkit for robust markerless 3D pose estimation
DIYer22/bpycv
Computer vision utils for Blender (generate instance annoatation, depth and 6D pose by one line code)
NeLy-EPFL/DeepFly3D
Motion capture (markerless 3D pose estimation) pipeline and helper GUI for tethered Drosophila.