Geo-Localization via Ground-to-Satellite Cross-View Image Retrieval

TL;DR

This paper introduces a novel cross-view geo-localization method that leverages drone-view images as a bridge to improve ground-to-satellite image retrieval accuracy, addressing large viewpoint variations and irrelevant backgrounds.

Contribution

It proposes a Peer Learning and Cross Diffusion framework utilizing drone-view data to enhance ground-to-satellite cross-view image retrieval, a novel approach in this domain.

Findings

Outperforms state-of-the-art methods on University-Earth and University-Google datasets.

Effectively handles large viewpoint changes and background clutter.

Demonstrates significant accuracy improvements in cross-view geo-localization.

Abstract

The large variation of viewpoint and irrelevant content around the target always hinder accurate image retrieval and its subsequent tasks. In this paper, we investigate an extremely challenging task: given a ground-view image of a landmark, we aim to achieve cross-view geo-localization by searching out its corresponding satellite-view images. Specifically, the challenge comes from the gap between ground-view and satellite-view, which includes not only large viewpoint changes (some parts of the landmark may be invisible from front view to top view) but also highly irrelevant background (the target landmark tend to be hidden in other surrounding buildings), making it difficult to learn a common representation or a suitable mapping. To address this issue, we take advantage of drone-view information as a bridge between ground-view and satellite-view domains. We propose a Peer Learning and Cross Diffusion (PLCD) framework. PLCD consists of three parts: 1) a peer learning across ground-view and drone-view to find visible parts to benefit ground-drone cross-view representation learning; 2) a patch-based network for satellite-drone cross-view representation learning; 3) a cross diffusion between ground-drone space and satellite-drone space. Extensive experiments conducted on the University-Earth and University-Google datasets show that our method outperforms state-of-the-arts significantly.