A fuzzy model in trinocular vision matching

The importance of 3D data acquisition is widely recognized in the robotics field. One approach is to measure the distance on the basis of triangulation principle from the disparity of two images. This stereo method has, however, a difficult problem that is to find correspondence of features between two images. This correspondence problem can be solved geometrically by adding one more camera (trinocular vision). This paper presents the application of the fuzzy logic for segmentation and correspondence of features, for static and dynamic 3D structures in an industrial environment.