用拓扑地图和速度信息提升单目视觉惯性定位精度
Tightly-Coupled, Speed-aided Monocular Visual-Inertial Localization in Topological Map
- 基于拓扑地图匹配与速度辅助，优化单目视觉惯性定位
- 在隧道等挑战场景下定位误差显著低于传统方法
- 适合低成本车载系统，尤其依赖摄像头的自动驾驶
本文提出一种新型算法，利用拓扑地图实现车辆速度辅助的单目视觉惯性定位。该系统旨在克服依赖昂贵传感器（如GPS、LiDAR）的现有方法局限，转而采用成本较低的摄像头进行位姿估计。拓扑地图通过离线处理LiDAR点云生成，包含深度图、强度图及对应相机位姿。实时定位时，通过当前相机图像与存储的拓扑图像进行对应匹配。系统采用迭代误差状态卡尔曼滤波器（IESKF）优化位姿估计，融合图像间对应关系与车辆速度测量数据以提升精度。在公开数据集及自采的复杂场景（如隧道）数据上实验表明，该算法在拓扑地图构建与定位任务中均表现优异。
原文摘要 · Abstract (English)
This paper proposes a novel algorithm for vehicle speed-aided monocular visual-inertial localization using a topological map. The proposed system aims to address the limitations of existing methods that rely heavily on expensive sensors like GPS and LiDAR by leveraging relatively inexpensive camera-based pose estimation. The topological map is generated offline from LiDAR point clouds and includes depth images, intensity images, and corresponding camera poses. This map is then used for real-time localization through correspondence matching between current camera images and the stored topological images. The system employs an Iterated Error State Kalman Filter (IESKF) for optimized pose estimation, incorporating correspondence among images and vehicle speed measurements to enhance accuracy. Experimental results using both open dataset and our collected data in challenging scenario, such as tunnel, demonstrate the proposed algorithm's superior performance in topological map generation and localization tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。