A Robust and Accurate Simultaneous Localization and Mapping System for RGB-D Cameras

Abstract

This paper presents a feature-based simultaneous localization and mapping (SLAM) system for RGB-D cameras that operates in real time, in indoor environments. The system is composed of three central components: tracking, mapping and loop closing which are based on ORB-SLAM2 [1]. The tracking part estimates the pose of a frame via optimizing both the reprojection error and inverse depth error of matching feature points, rather than just optimizing the reprojection error like ORB-SLAM2 [1]. The mapping part optimizes the pose of all keyframes and the position of all map points by using bundle adjustment, and an occupancy grid map of the surrounding environment is constructed based on the octree-based mapping framework OctoMap [2] for high-level tasks, and the map is more useful then the sparse points representation in ORB-SLAM2 [1]. The loop closing of ORB-SLAM2 [1] just uses color appearance information, but our system uses both the color appearance information and depth consistency to deal with inaccurate data association. The experiment results in the TUM RGB-D dataset [3] shows that our system achieves better localization accuracy and robustness than ORB-SLAM2 [1].