3D environment measurement using binocular stereo and motion stereo by mobile robot with omnidirectional stereo camera

Abstract

Map information is important for path planning and selflocalization when mobile robots accomplish autonomous tasks. In unknown environments, they should generate environment maps by themselves. An omnidirectional camera is effective for environment measurement, because it has a wide field of view. There are binocular stereo and motion stereo in traditional methods for measurement by omnidirectional camera. However, each method has advantages and disadvantages. In this paper, we aim to improve measurement accuracy by integrating binocular stereo and motion stereo using two omnidirectional cameras installed on a mobile robot. In addition, stereo matching accuracy is improved by considering omnidirectional image distortion. Experimental results show the effectiveness of our proposed method.