Publication:
Local stereovision matching through the ADALINE neural network

Loading...
Thumbnail Image
Full text at PDC
Publication Date
2001-12
Advisors (or tutors)
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Elsevier Science BV
Citations
Google Scholar
Research Projects
Organizational Units
Journal Issue
Abstract
This paper presents an approach to the local stereovision matching problem using edge segments as features with four attributes. Based on these attributes we compute a matching probability between pairs of features of the stereo images. A correspondence is said to be true when this probability is maximum. The probability value is a weighted sum of the attributes. We use two combined ADALINE neural networks to compute the weight for each attribute. A comparative analysis among other recent matching methods is illustrated.
Description
Part of the work has been performed under project CICYT TAP94-0832-C02-01. The constructive recommendations provided by the reviewers are also gratefully acknowledged.
Unesco subjects
Keywords
Citation
N. Ayache. Artificial Vision for Mobile Robots: Stereo Vision and Multisensory PerceptionMIT Press, Cambridge, MA (1991). N. Ayache, B. Faverjon Efficient registration of stereo images by matching graph descriptions of edge segments Internat. J. Comput. Vision, 1 (1987), pp. 107–131 T.M. Breuel. Finding lines under bounded error Pattern Recognition, 29 (1) (1996), pp. 167–178 J.M. Cruz, G. Pajares, J. Aranda. A neural network approach to the stereovision correspondence problem by unsupervised learning. Neural Networks, 8 (5) (1995), pp. 805–813 J.M. Cruz, G. Pajares, J. Aranda, J.F.V. Vindel. Stereo matching technique based on the perceptron criterion function. Pattern Recognition Lett., 16 (1995), pp. 933–944 A.R. Dhond, J.K. Aggarwal. Structure from stereo – a review. IEEE Trans. Systems Man Cybernet., 19 (1989), pp. 1489–1510 R.O. Duda, P.E. Hart. Pattern Classification and Scene AnalysisWiley, New York (1973) P. Fua. A parallel algorithm that produces dense depth maps and preserves image features. Machine Vision Appl., 6 (1993), pp. 35–49 J.R. Hilera, V.J. Martinez. Redes Neuronales ArtificialesRA-MA, Madrid (1995) W. Hoff, N. Ahuja. Surface from stereo: integrating feature matching, disparity estimation, and contour detection. IEEE Trans. Pattern Anal. Machine Intell., 11 (1989), pp. 121–136 A. Huertas, G. Medioni. Detection of intensity changes with subpixel accuracy using Laplacian–Gaussian masks. IEEE Trans. Pattern Anal. Machine Intell., 8 (5) (1986), pp. 651–664. D.R. Hush, B. Horne. An overview of neural networks, part I: static networks. Inf. Autom., 25 (1) (1992), pp. 19–36 P. Kahn, L. Kitchen, E.M. Riseman. A fast line finder for vision-guided robot navigation. IEEE Trans. Pattern Anal. Machine Intell., 12 (11) (1990), pp. 1098–1102 Y.C. Kim, J.K. Aggarwal. Positioning three-dimensional objects using stereo images. IEEE J. Robot. Autom., 3 (4) (1987), pp. 361–373 D.H Kim, W.Y. Choi, R.H. Park. Stereo matching technique based on the theory of possibility. Pattern Recognition Lett., 13 (1992), pp. 735–744 T. Kohonen. Self-organization and Associative MemorySpringer, New York (1989) T. Kohonen. Self-organizing MapsSpringer, Berlin (1995) E.P. Krotkov. Active Computer Vision by Cooperative Focus and StereoSpringer, Berlin (1989) J.G. Leu, H.L. Yau. Detecting the dislocations in metal crystals from microscopic images. Pattern Recognition, 24 (1) (1991), pp. 41–56 M.S Lew, T.S. Huang, K. Wong. Learning and feature selection in stereo matching. IEEE Trans. Pattern Anal. Machine Intell., 16 (9) (1994), pp. 869–881 D. Maravall. Reconocimiento de Formas y Visión ArtificialRA-MA, Madrid (1993) K.V. Mardia. Statistics of Directional DataAcademic Press, London (1972) D. Marr, T. Poggio. A computational theory of human stereo vision. Proc. Roy. Soc. London Ser. B, 207 (1979), pp. 301–328 G. Medioni, R. Nevatia. Segment based stereo matching. Comput. Vision Graphics Image Process., 31 (1985), pp. 2–18 M.S. Mousavi, R.J. Schalkoff. ANN implementation of stereovision using a multi-layer feedback architecture. IEEE Trans. Systems Man Cybernet., 24 (8) (1994), pp. 1220–1238 R. Nevatia, K.R. Babu. Linear feature extraction and description. Comput. Vision Graphics Image Process., 13 (1980), pp. 257–269 T. Ozanian. Approaches for stereo matching – a review. Model. Ident. Control, 16 (2) (1995), pp. 65–94 Pajares, G., 1995. Estrategia de Solución al Problema de la Correspondencia en Vision Estereoscópica por la Jerarquı́a Metodológica y la Integración de Criterios. Ph.D. Thesis, Dpto. Informática y Automática, Facultad Ciencias, UNED, Madrid. G. Pajares, J.M. Cruz, J. Aranda. Relaxation by Hopfield network in stereo image matching. Pattern Recognition, 31 (5) (1998), pp. 561–574 G. Pajares, J.M. Cruz, J. Aranda. Stereo matching based on the self-organizing feature-mapping algorithm. Pattern Recognition Lett., 19 (1998), pp. 319–330 G. Pajares, J.M. Cruz, J.A. López-Orozco. Improving stereo vision matching through supervised learning. Pattern Anal. Appl., 1 (1998), pp. 105–120 G. Pajares, J.M. Cruz, J.A. López-Orozco. Stereo matching using Hebbian learning. IEEE Trans. Systems Man Cybernet., 29B (4) (1999), pp. 553–559 G. Pajares, J.M. Cruz, J.A. López-Orozco. Relaxation labeling in stereo image matching. Pattern Recognition, 33 (1) (2000), pp. 53–68 D.W. Patterson. Artificial Neural NetworksPrentice-Hall, Singapore (1996) S.B. Pollard, J.E.W. Mayhew, J.P. Frisby. PMF: a stereo correspondence algorithm using a disparity gradient limit Perception, 14 (1981), pp. 449–470 Y. Ruichek, J.G. Postaire. A neural matching algorithm for 3-D reconstruction from stereo pairs of linear images. Pattern Recognition Lett., 17 (1996), pp. 387–398 S. Tanaka, A.C. Kak. A rule-based approach to binocular stereopsis. R.C. Jain, A.K. Jain (Eds.), Analysis and Interpretation of Range Images, Springer, Berlin (1990) E. Trucco, A. Verri. Introductory Techniques for 3-D Computer VisionPrentice-Hall, Upper Saddle River (1998) D.M. Wuescher, K.L. Boyer. Robust contour decomposition using a constraint curvature criterion. IEEE Trans. Pattern Anal. Machine Intell., 13 (1) (1991), pp. 41–51 J.K. Wu. Neural Networks and Simulation MethodsMarcel Dekker, New York (1994)
Collections