Tightly-Coupled, Speed-aided Monocular Visual-Inertial Localization in Topological Map

TL;DR

This paper introduces a speed-aided monocular visual-inertial localization method using a topological map, achieving accurate vehicle positioning without relying on expensive sensors like GPS or LiDAR.

Contribution

The paper presents a novel algorithm that combines vehicle speed, monocular camera data, and a topological map for improved localization accuracy.

Findings

Outperforms existing methods in challenging scenarios like tunnels

Effective use of topological maps for real-time localization

Enhanced accuracy with the Iterated Error State Kalman Filter

Abstract

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.