robertklee/COCO-Human-Pose
Train a stacked hourglass deep neural network for human pose estimation on the COCO 2017 dataset.
This tool helps analyze human movement by identifying key body points in images. You provide an image of a person, and it outputs the same image with a skeletal overlay marking 17 joints like elbows, knees, and wrists. It's designed for professionals in fields such as sports science, animation, or security who need to track single-person poses.
No commits in the last 6 months.
Use this if you need to precisely locate and track individual body joints on a single, centrally-positioned person within an image.
Not ideal if your images contain multiple people, as it will only process the person closest to the center, or if subjects are heavily obscured.
Stars
49
Forks
13
Language
Python
License
MIT
Category
Last pushed
May 10, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/robertklee/COCO-Human-Pose"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
talmolab/sleap
A deep learning framework for multi-animal pose tracking.
kennymckormick/pyskl
A toolbox for skeleton-based action recognition.
open-mmlab/mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
jgraving/DeepPoseKit
a toolkit for pose estimation using deep learning
DenisTome/Lifting-from-the-Deep-release
Implementation of "Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image"