3D object modeling using a binocular vision system

Abstract

A man-machine interaction based stereo vision system is developed for modeling an unknown environment. The data points needed for modeling an objects are obtained through the intersection of lines, or calculation from equations of curve, derived via fitting from human guided edge detection. The modeling accuracy is ensured by using image feature extraction. A multi-viewpoint modeling approach has been developed in order to deal with occlusion problems. The virtual environment can be rendered based on the modeling data of real scenes with known model of mobile robot. The system implementation and some 3D measurements on real scene have been performed, with some results given.