Visual SLAM using Multiple RGB-D Cameras
Shaowu Yang Xiaodong Yi Zhiyuan Wang Yanzhen Wang Xuejun Yang
HPCL | School of Computer, National University of Defense Technology
In this paper, we present a solution to visual simultaneous localization and mapping (SLAM) using multiple RGB-D cameras. In the SLAM system, we integrate visual and depth measurements from those RGB-D cameras to achieve more robust pose tracking and more detailed environmental mapping in unknown environments. We present the mathematical analysis of the iterative optimizations for pose tracking and map refinement of a RGB-D SLAM system in multi-camera cases. The resulted SLAM system allows configurations of multiple RGB-D cameras with non-overlapping fields of view (FOVs). Furthermore, we provide a SLAM-based semi-automatic method for extrinsic calibration among such cameras. Finally, the experiments in complex indoor scenarios demonstrate the efficiency of the proposed visual SLAM algorithm.
The authors would like to thank Prof. Andreas Zell and Sebastian A. Scherer, from the Department of Computer Science, University of Tuebingen, form helpful discussions and providing us the source code related to the work in .
This work is supported by Research on Foundations of Major Applications, Research Programs of NUDT, Project ZDYYJCYJ20140601, and NSFC Project 61303185, 61403409.