Visual-IMU State Estimation with GPS and OpenStreetMap for Vehicles on a Smartphone

In this paper, we propose an approach for ego-motion estimation and vehicle localization using low-cost portable sensors. It combines Visual Inertial Odometry with GPS and street map information obtained from OpenStreetMap. For conventional vehicle driving scenarios, we present a lightweight and targeted multi-sensor fusion method based on graph optimization, and implement the entire system on a smartphone. Extensive experiments on the benchmark dataset and real-world data show that the system could achieve robust, accurate and real-time tracking and localization in complex and dynamic scenarios.