Predicted Polar Mapping for Moving Obstacle Detection

This paper presents the predicted polar mapping that is to improve the efficiency of an unexpected moving obstacle detecting system in a single vision-based robot. The polar mapping is used to simplify the segmentation of moving objects from the background and is performed with the focus of expansion (FOE) as the center. When the movement of the robot per a step becomes a bit large, then static objects or background are detected as moving objects. Thus, the velocity of the robot becomes so slow. Therefore, to enlarge the movement of the robot and to improve this system, we propose the predicted polar mapping that predicts the polar mapped image after robot moves to be admissible. In order to verify experimentally our proposed procedure, we make several comparative tests in the corridor.