Increasing SLAM Pose Accuracy by Ground-to-Satellite Image Registration

Vision-based localization for autonomous driving has been of great interest among researchers. When a pre-built 3D map is not available, the techniques of visual simultaneous localization and mapping (SLAM) are typically adopted. Due to error accumulation, visual SLAM (vSLAM) usually suffers from lo...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Zhang, Yanhao, Shi, Yujiao, Wang, Shan, Vora, Ankit, Perincherry, Akhil, Chen, Yongbo, Li, Hongdong
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 14.04.2024
Subjects
Image registration
Odometers
Satellite imagery
Simultaneous localization and mapping
Online AccessGet full text

Cover

More Information
Summary:Vision-based localization for autonomous driving has been of great interest among researchers. When a pre-built 3D map is not available, the techniques of visual simultaneous localization and mapping (SLAM) are typically adopted. Due to error accumulation, visual SLAM (vSLAM) usually suffers from long-term drift. This paper proposes a framework to increase the localization accuracy by fusing the vSLAM with a deep-learning-based ground-to-satellite (G2S) image registration method. In this framework, a coarse (spatial correlation bound check) to fine (visual odometry consistency check) method is designed to select the valid G2S prediction. The selected prediction is then fused with the SLAM measurement by solving a scaled pose graph problem. To further increase the localization accuracy, we provide an iterative trajectory fusion pipeline. The proposed framework is evaluated on two well-known autonomous driving datasets, and the results demonstrate the accuracy and robustness in terms of vehicle localization.
ISSN:2331-8422