RGB-D mapping for indoor environment

Abstract

RGB-D sensors provide RGB images along with pre-pixel depth information, the richness of their data and recent development of low-cost sensors have made them more popular in mobile robotics research. In this paper, we introduce a framework for real-time mapping in indoor environment by using a RGB-D sensor and present RGB-D mapping, a 3D mapping system that utilizes 3D point clouds available for RGB-D cameras combining local position of the robot computed by a visual odometry. Thereinto, SURF features have been extracted and matched to estimate the poses of robot combining with a nonlinear least-squares solver. A sliding window Sparse Bundle Adjustment (SBA) has been used to refine both the robot poses and landmarks, then 3D point clouds were projected into global map with a 3D pose of the robot. At last, Experimental results have validated the feasibility and effectiveness of this system.