A Robust Stereo Visual–Inertial–GNSS Localization System for Dynamic Environments via Light-Enhanced Semantic–Geometric Perception

Visual-Inertial Odometry (VIO) is critical for autonomous vehicle localization but remains vulnerable to pose estimation drift caused by dynamic objects and severe illumination variations in real-world scenarios. To address these coupled challenges, a robust stereo VIO-GNSS localization system tailo...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Pengyu Wang, Wenjun Mo, Qiyao Chen, Jiaqi Li, Yongxin Yu, Wentao Fang, Yanhui Lu
Formato:	Artigo
Idioma:	Inglês
Publicado em:	IEEE 2026-01-01
coleção:	IEEE Access
Assuntos:	Visual inertial odometry dynamic environment semantic segmentation GNSS fusion graph optimization
Acesso em linha:	https://ieeexplore.ieee.org/document/11553239/
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!