tteepe/GaitGraph

Official repository for "GaitGraph: Graph Convolutional Network for Skeleton-Based Gait Recognition" (ICIP'21)

45
/ 100
Emerging

This project helps identify individuals based on how they walk, even from low-resolution or partially obscured video. It takes video footage of a person walking and processes it to extract their unique skeletal movement patterns, then outputs an identification or comparison of gait patterns. Security analysts, forensic investigators, or researchers in biometric identification would find this valuable.

109 stars. No commits in the last 6 months.

Use this if you need to identify people from video footage based purely on their walking style, especially in situations where other biometrics like facial recognition are challenging.

Not ideal if you need a plug-and-play solution for real-time security systems without significant technical setup or if you're looking to analyze subtle medical gait abnormalities.

biometric-identification video-surveillance forensic-analysis human-reidentification security-analytics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

109

Forks

27

Language

Python

License

MIT

Last pushed

Apr 19, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tteepe/GaitGraph"

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