Learning Cross-Scale Visual Representations for Real-Time Image Geo-Localization

TL;DR

This paper presents a novel framework for real-time image geo-localization that learns cross-scale visual representations without supervision, improving accuracy and efficiency in GPS-denied environments across underwater and aerial domains.

Contribution

The study introduces a new cross-scale dataset, a data augmentation methodology, and a supervised-free learning framework for cross-scale visual representations in geo-localization.

Findings

Better performance on smaller-scale multi-modal maps

More computationally efficient for real-time applications

Can be integrated with state estimation pipelines

Abstract

Robot localization remains a challenging task in GPS denied environments. State estimation approaches based on local sensors, e.g. cameras or IMUs, are drifting-prone for long-range missions as error accumulates. In this study, we aim to address this problem by localizing image observations in a 2D multi-modal geospatial map. We introduce the cross-scale dataset and a methodology to produce additional data from cross-modality sources. We propose a framework that learns cross-scale visual representations without supervision. Experiments are conducted on data from two different domains, underwater and aerial. In contrast to existing studies in cross-view image geo-localization, our approach a) performs better on smaller-scale multi-modal maps; b) is more computationally efficient for real-time applications; c) can serve directly in concert with state estimation pipelines.