# Image-Based Geo-Localization Using Satellite Imagery

## TL;DR

This paper advances image-based geo-localization by extending the CVM-Net for ground-to-aerial matching and introducing a Markov localization framework that leverages temporal consistency to improve vehicle localization accuracy.

## Contribution

It extends the CVM-Net architecture for better ground-to-aerial image matching and proposes a Markov localization framework that enhances localization in video streams.

## Key findings

- CVM-Net performs well on ground-to-aerial matching tasks.
- Markov localization improves vehicle localization accuracy.
- The approach achieves small error localization on Singapore dataset.

## Abstract

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.