Omnidirectional Vision and Inertial Clues for Robot Navigation

The features inherent in the visual motion field of a mobile robot indicate important clues about its navigation and environment. Combining these visual clues with additional inertial sensor information allows reliable detection of navigation direction for a mobile robot and the independent motion which may be present in the scene. The motion field, which is the 2D projection of the 3D scene variations induced by the camera-robot system, is estimated through optical flow calculations. The singular points of the global optical flow field of omnidirectional image sequences indicate the translation direction of the robot as well as the deviation from its planned path. It is also possible to detect motion patterns of near obstacles or independently moving objects of the scene. In this paper, after reviewing the image velocity measurement techniques shortly, we introduce the analysis of the intrinsic features of the omnidirectional motion fields for motion detection, giving some preliminary examples of this analysis.