VlSomers/keypoint_promptable_reidentification

[ECCV24] Keypoint Promptable Re-Identification: SOTA ReID method robust to occlusions and multi-person ambiguity

44
/ 100
Emerging

This project helps security analysts and surveillance system operators accurately identify and track individuals across different camera views, especially in crowded or obstructed scenes. It takes video frames or image crops of people, optionally with specific body part 'keypoint' hints, and outputs unique identity matches. This is invaluable for pinpointing specific individuals even when they are partially hidden or among many other people.

200 stars. No commits in the last 6 months.

Use this if you need to reliably identify or re-identify individuals in surveillance footage, particularly when faces are obscured or multiple people are close together.

Not ideal if your primary need is general object detection or tracking non-human subjects, as this tool is specifically designed for human re-identification.

surveillance security person-tracking forensics video-analytics
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

200

Forks

24

Language

Python

License

Last pushed

Jun 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/VlSomers/keypoint_promptable_reidentification"

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