Image-Based Geo-Localization Using Satellite Imagery
This work addresses geo-localization for applications like autonomous vehicles, but it is incremental as it builds on prior methods.
The paper tackles the problem of geo-localizing a ground-view image on a satellite map by extending a previous cross-view matching network and proposing a Markov localization framework for video streams, achieving continuous localization with small error on a Singapore dataset.
The problem of localization on a geo-referenced satellite map given a query ground view image is useful yet remains challenging due to the drastic change in viewpoint. To this end, in this paper we work on the extension of our earlier work on the Cross-View Matching Network (CVM-Net) for the ground-to-aerial image matching task since the traditional image descriptors fail due to the drastic viewpoint change. In particular, we show more extensive experimental results and analyses of the network architecture on our CVM-Net. Furthermore, we propose a Markov localization framework that enforces the temporal consistency between image frames to enhance the geo-localization results in the case where a video stream of ground view images is available. Experimental results show that our proposed Markov localization framework can continuously localize the vehicle within a small error on our Singapore dataset.