Real-time 3D shape recognition of high speed moving object by fixation point tracking with active camera

This paper reports a visual system that recognizes 3D shapes of high speed moving objects. In this system, an active camera fixates a point on the moving object at the center of the image and tracks it. In this tracking, other object points than the fixation point move in the image field depending on their relative depths to the fixated point. Based on this fact, we are able to reconstruct 3D object shape from the tracking images. We developed a simple algorithm to realize this reconstruction for real time processing. We utilize the relation between spatial and temporal change of image with respect to the object depths. For our purpose, it is important to obtain object shape quickly even if it will be a rough one. We constructed a system that does not need complex and difficult image processing.