Xharlie/BtcDet

Behind the Curtain: Learning Occluded Shapes for 3D Object Detection

47
/ 100
Emerging

This project helps improve the accuracy of 3D object detection systems, especially when objects are partially hidden or occluded. It takes raw 3D point cloud data and optionally accompanying image data, processing it to generate more complete object shapes, which then leads to better identification of objects like cars. Autonomous vehicle engineers, robotics researchers, and anyone developing perception systems for real-world environments would use this.

201 stars. No commits in the last 6 months.

Use this if you need to reliably detect 3D objects from LiDAR or similar point cloud data, particularly when those objects might be partially obscured from view.

Not ideal if you are working solely with 2D image data for object detection or if your application does not involve occluded objects in 3D environments.

autonomous-driving robotics-perception 3d-scene-understanding lidar-data-processing object-detection
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

201

Forks

41

Language

Python

License

Apache-2.0

Last pushed

Dec 20, 2021

Commits (30d)

0

Get this data via API

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

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