Monocular Visual Localization for Autonomous Vehicles Based on Lightweight Landmark Map

Vehicle pose estimation is a key technology for autonomous vehicles and a prerequisite for path planning and vehicle control. Visual localization has gradually attracted extensive attention from academia and industry due to its low cost and rich semantic information. However, the incremental calculation principle of the odometry inevitably leads to the accumulation of localization error with the travel distance. To solve this problem, we propose a position correction algorithm based on lightweight landmark map, and further compensate the localization error by analyzing the error characteristics. The proposed algorithm takes the stop lines on the road as landmarks, and pairs bag-of-word vectors with the positions of the corresponding landmarks. Once landmarks in the map are encountered and successfully associated, the position of the landmarks can be exploited to effectively reduce the drift of the odometry. We also present a reliable landmark map construction method. Experiments show that with only one monocular camera and the established landmark map, the proposed algorithm can significantly reduce the cumulative error and achieve decimeter-level positioning accuracy, which meets the lane-level positioning requirements of autonomous vehicles driving long distances under fixed routes.