Multi sensory system for the recovery of 3D structure; industrial applications

Abstract

The importance of 3D data acquisition is widely recognized in 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 a difficult problem of finding the 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 this method. The two industrial examples presented here need a good precision in 3D representation, so epipolar constraints and camera calibration are studied in details.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>