WHU-USI3DV/PatchAugNet

PatchAugNet: Patch feature augmentation-based heterogeneous point cloud place recognition in large-scale street scenes

24
/ 100
Experimental

This project helps self-driving cars, robots, or drones understand their exact location in complex street environments, even when the scenery changes (like day vs. night or seasons). It takes raw 3D point cloud data from laser scanners and outputs a precise localization or 'place recognition' for the vehicle. Robotics engineers, autonomous vehicle developers, or mapping specialists would find this useful for robust navigation.

No commits in the last 6 months.

Use this if you need to reliably determine a robot's location in large, diverse urban settings using 3D point cloud data, especially when dealing with changes in environment over time.

Not ideal if you are working with 2D image data for localization or if your primary need is object detection rather than place recognition.

autonomous-navigation robotics 3d-mapping localization place-recognition
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

49

Forks

Language

Python

License

Apache-2.0

Last pushed

Apr 01, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/WHU-USI3DV/PatchAugNet"

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