Cross-view Image Geo-Localization using Multi-Scale Generalized Pooling with Attention Mechanism
Duc Viet Bui, Masao Kubo, Hiroshi Sato · Proceedings of International Conference on Artificial Life and Robotics · 2022
Cross-view image matching for geo-localization is the task of finding images containing the same geographic target across different platforms.This task has drawn significant attention due to its vast applications in UAV's selflocalization and navigation.Given a query image from UAV-view, a matching model can find the same georeferenced satellite image from the database, which can be used later to precisely locate the UAV's current position.Many studies have achieved high accuracy on existing datasets, but they can be further improved by combining different feature processing methods.Inspired by previous studies, in this paper, we proposed a new strategy by using a channel-based attention mechanism with a generalized mean pooling method to enhance the feature extracting process, which improved accuracy.