eddyhkchiu/DMSTrack

[ICRA2024] Official code of the paper "Probabilistic 3D Multi-Object Cooperative Tracking for Autonomous Driving via Differentiable Multi-Sensor Kalman Filter"

25
/ 100
Experimental

This project helps autonomous driving systems accurately track multiple moving objects in 3D space by combining data from several connected autonomous vehicles (CAVs). It takes raw detection data from different vehicle sensors as input and outputs highly precise 3D tracking information for all nearby objects, even with reduced communication. Operations engineers and researchers working on self-driving car perception will find this useful.

No commits in the last 6 months.

Use this if you need to improve the accuracy of 3D multi-object tracking in autonomous vehicles while significantly reducing the data exchange between connected cars.

Not ideal if your application does not involve cooperative perception between multiple vehicles or if you are not working with 3D object tracking for autonomous systems.

autonomous-driving vehicle-perception object-tracking robotics connected-vehicles
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

75

Forks

5

Language

Python

License

Last pushed

Jan 31, 2024

Commits (30d)

0

Get this data via API

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

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