Fuzzy cognitive maps for stereovision matching

Thumbnail Image
Full text at PDC
Publication Date
Advisors (or tutors)
Journal Title
Journal ISSN
Volume Title
Pergamon-Elsevier Science LTD
Google Scholar
Research Projects
Organizational Units
Journal Issue
This paper outlines a method for solving the stereovision matching problem using edge segments as the primitives. In stereovision matching the following constraints are commonly used: epipolar, similarity, smoothness, ordering and uniqueness. We propose a new matching strategy under a fuzzy context in which such constraints are mapped. The fuzzy context integrates both Fuzzy Clustering and Fuzzy Cognitive Maps. With such purpose a network of concepts (nodes) is designed, each concept represents a pair of primitives to be matched. Each concept has associated a fuzzy value which determines the degree of the correspondence. The goal is to achieve high performance in terms of correct matches. The main findings of this paper are reflected in the use of the fuzzy context that allows building the network of concepts where the matching constraints are mapped. Initially, each concept value is loaded via the Fuzzy Clustering and then updated by the Fuzzy Cognitive Maps framework. This updating is achieved through the influence of the remainder neighboring concepts until a good global matching solution is achieved. Under this fuzzy approach we gain quantitative and qualitative matching correspondences. This method works as a relaxation matching approach and its performance is illustrated by comparative analysis against some existing global matching methods. (c) 2006 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.
© 2006 Pattern Recognition Society. Part of the work has been performed under Projects CICYT DPI2002-02924 and CICYT TAP94-0832-C02-01. The authors wish to acknowledge the constructive recommendations provided by the reviewers.
Unesco subjects
[1] D. Scharstein, R. Szeliski, A taxonomy and evaluation of dense twoframe stereo correspondence algorithms, Int. J. Comput. Vision 47 (1/2/3) (2002) 7–42. [2] L. Tang, C. Wu, Z. Chen, Image dense matching based on region growth with adaptive window, Pattern Recognition Lett. 23 (2002) 1169–1178. [3] W.E.L. Grimson, Computational experiments with a feature-based stereo algorithm, IEEE Trans. Pattern Anal. Mach. Intell. 7 (1985) 17–34. [4] Y. Ruichek, J.G. Postaire, A neural network algorithm for 3-D reconstruction from stereo pairs of linear images, Pattern Recognition Lett. 17 (1996) 387–398. [5] G. Medioni, R. Nevatia, Segment based stereo matching, Comput. Vision Graphics Image Process. 31 (1985) 2–18. [6] G. Pajares, J.M. Cruz, J. Aranda, Relaxation by Hopfield network in stereo image matching, Pattern Recognition 31 (5) (1998) 561–574. [7] G. Pajares, J.M. Cruz, On combining support vector machines and simulated annealing in stereovision matching, IEEE Trans. Syst. Man Cybern. Part B 34 (4) (2004) 1646–1657. [8] G. Pajares, J.M. Cruz, J.A. López-Orozco, Relaxation labeling in stereo image matching, Pattern Recognition 33 (2000) 53–68. [9] J.P. Starink, E. Backer, Finding point correspondences using simulated annealing, Pattern Recognition 28 (2) (1995) 231–240. [10] J.M.M. Montiel, D. Orth, Indoor robot motion based on monocular images, Robotica 19 (2001) 331–342. [11] A. Luo, W. Tao, H. Burkhardt, A new multilevel line-based stereo vision algorithm based on fuzzy techniques, in: Proceedings of the 13th International Conference on Pattern Recognition, vol. 1 (25–29), 1996, pp. 383–387. [12] G. Pajares, J.M. Cruz, A new learning strategy for stereo matching derived from a fuzzy clustering method, Fuzzy Sets Syst. 110 (3) (2000) 413–427. [13] G. Pajares, J.M. Cruz, Stereovision matching through support vector machines, Pattern Recognition Lett. 24 (15) (2003) 2575–2583.