yuntaeJ/SCIT-MCMT-Tracking

[CVPRW 2023] "Leveraging Future Trajectory Prediction for Multi-Camera People Tracking"

36
/ 100
Emerging

This project helps security personnel or crowd managers accurately track individual people across multiple surveillance cameras. It takes video feeds from several cameras as input and outputs continuous, distinct trajectories for each person, even when they move between camera views. This is ideal for anyone needing to monitor the movement of individuals in a large area, like a shopping mall, airport, or public event.

No commits in the last 6 months.

Use this if you need to reliably follow specific individuals through an area covered by an array of security cameras.

Not ideal if you only need to count people or detect their presence within a single camera's view, or if you don't require their future movement to be predicted.

surveillance crowd-monitoring security-management person-tracking video-analytics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

54

Forks

6

Language

Python

License

MIT

Last pushed

Nov 17, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/yuntaeJ/SCIT-MCMT-Tracking"

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