ACTIVE VISUAL SENSING OF THE 3-D POSE OF A FLEXIBLE OBJECT

This paper presents an active visual method for determining the 3-D po se of a flexible object with a hand-eye system. Some simple and effect ive on-line algorithms to overcome various exceptional situations in c haincoding or determine the object pose more precisely are developed. The pose of a flexible object can be easily changed because of the fle xible nature and the prediction of the pose is almost impossible. A ne w sensing pose is computed by using the image coordinates of the point s on the border line of an image window and the current pose of a hand -eye system for the cases that the flexible object is extended outside the window. In a case of exceptional overlapping, a new sensing pose is computed by using the image coordinates of four extreme image point s and the current pose of the hand-eye system. Through a chaincoding p rocess on the skeletonized images, the stereo matching problem of two images is transformed into the matching of the curvature representatio ns of the two skeletonized images. The 3-D pose of a flexible object i s computed by using the results of this matching and the camera and ha nd-eye parameters calibrated beforehand. The initial sensing results a re used in computing a new sensing pose to determine the object more p recisely.