exitudio/GaitMixer

Official repository for "GaitMixer: Skeleton-based Gait Representation Learning via Wide-spectrum Multi-axial Mixer" (ICASSP 2023)

25
/ 100
Experimental

This project helps security professionals or biometric researchers improve how they identify individuals by analyzing their walking patterns. It takes in skeletal motion data (like key points on a person's body as they walk) and learns to represent these movements in a way that allows for highly accurate person identification, even from different angles or under varying conditions. The output is a robust gait signature that can be used for recognition.

No commits in the last 6 months.

Use this if you need to identify individuals with high accuracy based solely on their unique walking style from skeletal data.

Not ideal if you are working with raw video footage and don't have skeletal pose estimation as a preprocessing step.

biometric-identification gait-analysis person-recognition security-systems surveillance
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

26

Forks

3

Language

Python

License

Last pushed

Dec 12, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/exitudio/GaitMixer"

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