michalfaber/keras_Realtime_Multi-Person_Pose_Estimation

Keras version of Realtime Multi-Person Pose Estimation project

51
/ 100
Established

This project helps you identify and track human poses in images and videos. It takes an image or video as input and outputs the location of key body points (like joints) for multiple people in real-time. This is ideal for researchers and developers working on computer vision applications that require understanding human movement.

782 stars. No commits in the last 6 months.

Use this if you are a developer or researcher who needs to implement real-time multi-person pose estimation using Keras and want to reproduce the results from the 2017 CVPR paper.

Not ideal if you are looking for a pre-built application or a solution compatible with the latest TensorFlow 2.0, as this project is deprecated in favor of a newer TensorFlow-based repository.

computer-vision human-pose-estimation real-time-tracking motion-analysis deep-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

782

Forks

369

Language

Jupyter Notebook

License

Last pushed

Dec 10, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/michalfaber/keras_Realtime_Multi-Person_Pose_Estimation"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.