Hashing for Image Geolocalization of Street Views

We develop a deep cross-view hashing method for street-view image geolocalization by referencing remote sensing images with location information. We commence by exploiting attention-weighted image feature extractor models to construct feature descriptors for both a street-view image (as a query) and a set of remote sensing images (as a database) with universal transverse mercator (UTM) information. The cross-view similarity between street view and remote sensing feature descriptors for a common location is effectively maintained by the Vision Transformer (ViT) backbone in the models. We then design hash encoders to convert the feature descriptors into hash codes. By retrieving remote sensing images in terms of small Hamming distance values between the cross-view hash codes, we achieve preliminary geolocalization of the query street-view image. This hashing technique enables fast localization with economical computational costs. We further refine the preliminary geolocalization results by applying a geographically clustered averaging method to the locations of the retrieved remote sensing images, resulting in exact geolocalization of the query street-view image. The experimental results show that our method achieves fast geolocation of street-view images on the cross-view ACT (CVACT) dataset. In scenes with a smaller field of view (FoV), its accuracy is not only on par with the existing state-of-the-art methods, but also demonstrates significant efficiency advantages.