octiapp/KerasPersonLab
Keras-tensorflow implementation of PersonLab (https://arxiv.org/abs/1803.08225)
This project helps computer vision engineers and researchers accurately identify and outline multiple people in images. It takes raw image files and COCO person keypoint annotations as input, and outputs precise locations of body joints and distinct outlines for each individual. This is useful for tasks requiring detailed human analysis in visual data.
161 stars. No commits in the last 6 months.
Use this if you need a pre-built, trainable Keras model for advanced multi-person pose estimation and instance segmentation.
Not ideal if you are looking for a ready-to-use application and don't have experience with deep learning model training and configuration.
Stars
161
Forks
24
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Apr 15, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/octiapp/KerasPersonLab"
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
kenshohara/3D-ResNets-PyTorch
3D ResNets for Action Recognition (CVPR 2018)