Reviews on planar region detection for visual navigation of mobile robot under unknown environment

Abstract

Dominant plane detection is an essential task for an autonomous navigation of mobile robots equipped with a vision system, as we assume that the robot moves on the dominant plane. In this paper, a brief review about state-of-art method for planar region detection is presented. All these methods are classified into three types, that is stereo-based, monocular-based and multi-sensor fusion based method according to the sensor they used. And the monocular-based method is further divided into three kinds, projection invariance, homography based and optical flow based method. For each kind of the method, the correspondent references and its main process are summarized. Finally, the challenges for plane detection with vision are presented in authors view. We hope that this paper can be a start point to probe deep insight in this field. © 2011 Springer-Verlag.