A new stereomatching algorithm based on linear features and the fuzzy integral

This paper presents a new algorithm to the local stereomatching problem using the fuzzy integral and primarily aimed at static scene (industrial image) analysis. Our purpose is to build the planar surfaces of 3D polyhedric objects using a stereoscopic vision system with a good accuracy. Only linear features and their geometric attributes are considered in a method using a direct matching of image features (and using the fuzzy integral-like aggregation operator). The experimental results show that the proposed method is effective and suitable for matching line segments and is compared with some other methods. (C) 2001 Elsevier Science B.V. All rights reserved.