Object-Level Cross-View Geolocalization With Location Enhancement and Multihead Cross Attention

Cross-view geolocalization determines the location of a query image, captured by a drone or ground-based camera, by matching it to a georeferenced satellite image. While traditional approaches focus on image-level localization, many applications, such as search-and-rescue, infrastructure inspection, and precision delivery, demand object-level accuracy. This enables users to prompt a specific object with a single click on a drone image to retrieve precise geotagged information of the object. However, variations in viewpoints, timing, and imaging conditions pose significant challenges, especially when identifying visually similar objects in extensive satellite imagery. To address these challenges, we propose an object-level cross-view geolocalization network (OCGNet). It integrates user-specified click locations using Gaussian kernel transfer to preserve location information throughout the network. This cue is dually embedded into the feature encoder and feature matching blocks, ensuring robust object-specific localization. In addition, OCGNet incorporates a location enhancement module and a multihead cross attention module to adaptively emphasize object-specific features or expand focus to relevant contextual regions when necessary. OCGNet achieves state-of-the-art performance on a public dataset, CVOGL. It also demonstrates few-shot learning capabilities, effectively generalizing from limited examples, making it suitable for diverse applications.