sydsim/personlab-tf
implementation of PersonLab(https://arxiv.org/abs/1803.08225) using TF-slim
This tool helps you analyze images to automatically detect and identify individual people, along with their key body parts. You provide images containing people, and it outputs detailed information about each person's location and pose within those images. This is useful for researchers and engineers working with computer vision applications that require understanding human presence and movement.
103 stars. No commits in the last 6 months.
Use this if you need to precisely locate people and their body joints in images for tasks like human-computer interaction, surveillance, or sports analysis.
Not ideal if you require real-time processing on a CPU-only setup, as it currently has known performance issues in that environment.
Stars
103
Forks
19
Language
Jupyter Notebook
License
—
Category
Last pushed
Dec 29, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sydsim/personlab-tf"
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)