GAMa: Cross-view Video Geo-localization
This work addresses geo-localization for video analysis, but it is incremental as it extends existing image-based methods to videos with new data and techniques.
The authors tackled cross-view geo-localization using ground videos instead of images, proposing the GAMa dataset and a novel hierarchical method, achieving a Top-1 recall rate of 19.4% and 45.1% at 1.0 mile.
The existing work in cross-view geo-localization is based on images where a ground panorama is matched to an aerial image. In this work, we focus on ground videos instead of images which provides additional contextual cues which are important for this task. There are no existing datasets for this problem, therefore we propose GAMa dataset, a large-scale dataset with ground videos and corresponding aerial images. We also propose a novel approach to solve this problem. At clip-level, a short video clip is matched with corresponding aerial image and is later used to get video-level geo-localization of a long video. Moreover, we propose a hierarchical approach to further improve the clip-level geolocalization. It is a challenging dataset, unaligned and limited field of view, and our proposed method achieves a Top-1 recall rate of 19.4% and 45.1% @1.0mile. Code and dataset are available at following link: https://github.com/svyas23/GAMa.