Geolocalization of Unmanned Aerial Vehicle Images and Mapping onto Satellite Images Utilizing 3D Gaussian Splatting

TL;DR

This paper introduces a new method for geolocalizing UAV images in GPS-denied areas by aligning them with satellite images using 3D Gaussian Splatting.

Contribution

The novel approach uses 3DGS to render images from satellite-like viewpoints and directly match them with satellite images for improved geolocalization.

Findings

The proposed method achieves higher geolocalization accuracy compared to existing image retrieval techniques.

The method enables geographically consistent integration of independently captured 3DGS models.

Pixel-level matching between 3DGS-rendered and satellite images improves alignment accuracy.

Abstract

Geolocalization of images captured by unmanned aerial vehicles (UAVs) remains a significant challenge in Global Navigation Satellite System-denied environments. Although geolocalization is typically achieved by matching UAV images with satellite images, the viewpoint discrepancy between oblique UAV and nadir satellite images complicates this task. In this study, we employ 3D Gaussian Splatting (3DGS) to generate images from viewpoints close to the satellite viewpoint based on multiview UAV images. Assuming that the approximate flight area of the UAV is known, we propose a geolocalization method that directly establishes correspondences between 3DGS-rendered and satellite images using pixel-level image matching. These satellite images, which we refer to as wide-area satellite images, cover a larger area than the UAV observation range. Experimental results demonstrate that the proposed method achieves higher geolocalization accuracy than existing approaches that divide wide-area satellite images and perform image retrieval. Moreover, we demonstrate the potential for geographically consistent integration of independently captured and trained 3DGS models by leveraging the correspondences between 3DGS-rendered and wide-area satellite images.

Figures