BEVRender: Vision-based Cross-view Vehicle Registration in Off-road GNSS-denied Environment

TL;DR

BEVRender is a new vision-based method that generates bird's-eye-view images for accurate vehicle localization in off-road, GNSS-denied environments, overcoming limitations of existing systems.

Contribution

It introduces a novel approach that creates high-quality BEV images and aligns them with geo-referenced maps for improved localization accuracy in challenging terrains.

Findings

Significantly improves localization accuracy.

Enhances update frequency over existing methods.

Overcomes drift and scalability issues.

Abstract

We introduce BEVRender, a novel learning based approach for the localization of ground vehicles in Global Navigation Satellite System(GNSS)-denied off-road scenarios. These environments are typically challenging for conventional vision-based state estimation due to the lack of distinct visual landmarks and the instability of vehicle poses. To address this, BEVRender generates high-quality local bird's-eye-view(BEV) images of the local terrain. Subsequently, these images are aligned with a geo referenced aerial map through template matching to achieve accurate cross-view registration. Our approach overcomes the inherent limitations of visual inertial odometry systems and the substantial storage requirements of image-retrieval localization strategies, which are susceptible to drift and scalability issues, respectively. Extensive experimentation validates BEVRender's advancement over existing GNSS-denied visual localization methods, demonstrating notable enhancements in both localization accuracy and update frequency.