Daniil-Osokin/lightweight-human-pose-estimation.pytorch
Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.
This project helps computer vision practitioners and researchers analyze human movement by identifying key body points. It takes an image or video frame as input and outputs a 'skeleton' of each person, showing precise locations of ears, eyes, nose, neck, shoulders, elbows, wrists, hips, knees, and ankles. Anyone working on applications requiring real-time human pose understanding, like sports analysis, animation, or safety monitoring, would find this valuable.
2,234 stars. No commits in the last 6 months.
Use this if you need to detect human poses quickly and accurately on standard computer processors (CPUs) without specialized hardware.
Not ideal if your application requires 3D pose estimation directly from a 2D image, as this version focuses solely on 2D analysis.
Stars
2,234
Forks
493
Language
Python
License
Apache-2.0
Category
Last pushed
Apr 30, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Daniil-Osokin/lightweight-human-pose-estimation.pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
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.