Vision-based GNSS-Free Localization for UAVs in the Wild

TL;DR

This paper introduces a vision-based localization method for UAVs that uses deep feature matching with satellite maps, providing GNSS-free positioning suitable for long-distance, high-altitude flights in wild environments.

Contribution

The paper presents a novel deep feature-based localization algorithm that matches UAV camera images with satellite maps, enabling GNSS-free positioning in challenging outdoor scenarios.

Findings

Achieves localization accuracy comparable to GNSS-based methods.

Effective for long-distance, high-altitude UAV flights.

Outperforms traditional Visual Odometry approaches.

Abstract

Considering the accelerated development of Unmanned Aerial Vehicles (UAVs) applications in both industrial and research scenarios, there is an increasing need for localizing these aerial systems in non-urban environments, using GNSS-Free, vision-based methods. Our paper proposes a vision-based localization algorithm that utilizes deep features to compute geographical coordinates of a UAV flying in the wild. The method is based on matching salient features of RGB photographs captured by the drone camera and sections of a pre-built map consisting of georeferenced open-source satellite images. Experimental results prove that vision-based localization has comparable accuracy with traditional GNSS-based methods, which serve as ground truth. Compared to state-of-the-art Visual Odometry (VO) approaches, our solution is designed for long-distance, high-altitude UAV flights. Code and datasets are available at https://github.com/TIERS/wildnav.