Cross-view image matching for geo-localisation is a challenging problem due to the significant visual difference between aerial and ground-level viewpoints. The method provides localisation capabilities from geo-referenced images, eliminating the need for external devices or costly equipment. This enhances the capacity of agents to autonomously determine their position, navigate, and operate effectively in GNSS-denied environments. Current research employs a variety of techniques to reduce the domain gap such as applying polar transforms to aerial images or synthesising between perspectives. However, these approaches generally rely on having a 360° field of view, limiting real-world feasibility. We propose BEV-CV, an approach introducing two key novelties with a focus on improving the real-world viability of cross-view geo-localisation. Firstly bringing ground-level images into a semantic Birds-Eye-View before matching embeddings, allowing for direct comparison with aerial image representations. Secondly, we adapt datasets into application realistic format - limited Field-of-View images aligned to vehicle direction. BEV-CV achieves state-of-the-art recall accuracies, improving Top-1 rates of 70° crops of CVUSA and CVACT by 23% and 24% respectively. Also decreasing computational requirements by reducing floating point operations to below previous works, and decreasing embedding dimensionality by 33% - together allowing for faster localisation capabilities.

🚧 Under Construction

conda env create -f requirements.yaml

If you find BEV-CV useful for your work please cite:

@INPROCEEDINGS{bevcv,
    author={Shore, Tavis and Hadfield, Simon and Mendez, Oscar },
    booktitle={2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, 
    title={BEV-CV: Birds-Eye-View Transform for Cross-View Geo-Localisation}, 
    year={2024},
    pages={11047-11054},
}