SLAM systems can retrieve their metric scales and depth information using RGB-D cameras. However, limited by the sensing range and objects structure, RGB-D cameras can not always work well, resulting in failures sometimes. In this work, we present initialization and localization methods based on maximum-a-posteriori estimation. Our system endows monocular keypoints with valid depth values and introduce them into bundle adjustment. Depth bias coefficient and scale factor are also optimized in the local window, obtaining robustness in large scale environments and long-running operations. The experimental results indicate that our system provides the best robustness compared with other excellent methods in the literature, being able to process the most challenging sequences in the TUM RGB-D dataset.

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.