Search Results for author:
Found 3 papers, 3 papers with code
PEnG: Pose-Enhanced Geo-Localisation
To solve this limitation, we propose combining cross-view geo-localisation and relative pose estimation to increase precision to a level practical for real-world application.
SpaGBOL: Spatial-Graph-Based Orientated Localisation
SpaGBOL achieves state-of-the-art accuracies on the unseen test graph - with relative Top-1 retrieval improvements on previous techniques of 11%, and 50% when filtering with Bearing Vector Matching on the SpaGBOL dataset.
Ranked #1 on
Cross-View Geo-Localisation
on VIGOR-Graph
BEV-CV: Birds-Eye-View Transform for Cross-View Geo-Localisation
Cross-view image matching for geo-localisation is a challenging problem due to the significant visual difference between aerial and ground-level viewpoints.
Ranked #1 on
Cross-View Geo-Localisation
on CVUSA 90
(R@5 metric)
