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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jin, Lihong, Dong, Wei, Wang, Wenshan, Kaess, Michael
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910736757817344
author Jin, Lihong
Dong, Wei
Wang, Wenshan
Kaess, Michael
author_facet Jin, Lihong
Dong, Wei
Wang, Wenshan
Kaess, Michael
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_09001
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BEVRender: Vision-based Cross-view Vehicle Registration in Off-road GNSS-denied Environment
Jin, Lihong
Dong, Wei
Wang, Wenshan
Kaess, Michael
Robotics
I.2.9
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.
title BEVRender: Vision-based Cross-view Vehicle Registration in Off-road GNSS-denied Environment
topic Robotics
I.2.9
url https://arxiv.org/abs/2405.09001