TOPO-EPFL/CrossLoc

[CVPR'22] CrossLoc localization: a cross-modal visual representation learning method for absolute localization

34
/ 100
Emerging

CrossLoc helps drone operators and roboticists precisely determine a drone's location using visual data, especially in environments where GPS might be unreliable or unavailable. It takes drone-captured images, both real and synthetic, and outputs highly accurate absolute localization. This tool is ideal for researchers and engineers developing autonomous aerial vehicles.

110 stars. No commits in the last 6 months.

Use this if you need to achieve highly accurate absolute localization for drones or other aerial vehicles by leveraging both real and synthetic visual data.

Not ideal if you are looking for a plug-and-play solution for general GPS-based navigation or if your primary need is not highly precise visual localization.

drone-navigation robotics-localization aerial-mapping computer-vision autonomous-vehicles
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

110

Forks

7

Language

Python

License

MIT

Last pushed

Aug 19, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/TOPO-EPFL/CrossLoc"

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