Moving object detection in omnidirectional vision-based mobile robot

Abstract

Detecting moving objects based on the camera attached in mobile robot is not trivial since both background and object are moving independently. For moving object detection the movement of moving object needs to be extracted by considering the background which has also changed by the ego-motion of mobile robot. Affine transformation is widely used to estimate the background transformation between images. However when using omnidirectional camera, the mixed motion of scaling, rotation and translation appears in local areas and single affine transformation is not sufficient to describe those mixed nonlinear motions. In this paper, the proposed method divides the image as grid windows and obtains each affine transform for each window. This method can obtain stable background transformation when the background has few corner features. The area of moving objects can be obtained from the background transformation-compensated frame difference using every local affine transformation for each local window. The experimental results demonstrate the proposed method is very efficient in moving object detection in mobile robot environment.