A 3-D vision system incorporating solid modeler and geometric reasoning

A 3-D vision system incorporating a solid modeler and a geometric reasoning mechanism is described. A mathematical method based on the perspective geometry is employed to determine the position of predefined shapes in 3-D space from a single-view image. The solid modeler allows the precise and reliable understanding of possible objects. Furthermore, it can be used to synthesize virtual images based on the understanding result. The synthesized image from the solid modeler is effectively utilized to verify the hypothesis computed from the edge information extracted from the observed image. To lessen the inefficiency of using the mathematical geometric method in the whole understanding process, a plane recognition process is introduced at an intermediate stage