lmy98129/UMPD

Official Code of ACM MM'24 Paper "Unsupervised Multi-view Pedestrian Detection"

28
/ 100
Experimental

This project helps surveillance system operators or security analysts automatically detect and track pedestrians in complex environments using multiple camera feeds. It takes raw video frames from several cameras and outputs precise 3D locations of people, even without needing extensive manual labeling for training. It's designed for professionals managing large-scale surveillance or monitoring systems.

No commits in the last 6 months.

Use this if you need to reliably identify and locate pedestrians across multiple camera views without the time and expense of manually labeling vast amounts of training data.

Not ideal if you are working with single-camera systems or require real-time detection on resource-constrained devices without dedicated GPUs.

multi-camera surveillance pedestrian detection security monitoring crowd analytics 3D tracking
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

Python

License

MIT

Last pushed

Nov 05, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/lmy98129/UMPD"

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