The article introduces the HDA-LVIO system, a novel LiDAR-Visual-Inertial odometry method for enhancing localization accuracy in urban settings. The system is divided into two subsystems: LiDAR-Inertial and Visual-Inertial. It employs hybrid data association to improve accuracy by extracting planes, projecting centroids onto images, tracking feature points, and utilizing epipolar geometric constraints. Extensive experiments validate the algorithm's superior performance compared to existing methods.
To Another Language
from source content
arxiv.org
Key Insights Distilled From
by Jian Shi,Wei... at arxiv.org 03-12-2024
https://arxiv.org/pdf/2403.06590.pdfDeeper Inquiries