Aviso: para depositar documentos, por favor, inicia sesión e identifícate con tu cuenta de correo institucional de la UCM con el botón MI CUENTA UCM. No emplees la opción AUTENTICACIÓN CON CONTRASEÑA
 

On combining support vector machines and simulated annealing in stereovision matching

dc.contributor.authorPajares Martínsanz, Gonzalo
dc.contributor.authorCruz García, Jesús Manuel de la
dc.date.accessioned2023-06-20T10:42:16Z
dc.date.available2023-06-20T10:42:16Z
dc.date.issued2004-08
dc.description© 2004 IEEE. The authors wish to acknowledge the constructive recommendations provided by the reviewers.
dc.description.abstractThis 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 strategy in which such constraints are sequentially combined. The goal is to achieve high performance in terms of correct matches by combining several strategies. The contributions of this paper are reflected in the development of a similarity measure through a support vector machines classification approach; the transformation of the smoothness, ordering and epipolar constraints into the form of an energy function, through an optimization simulated annealing approach, whose minimum value corresponds to a good matching solution and by introducing specific conditions to overcome the violation of the smoothness and ordering constraints. The performance of the proposed method is illustrated by comparative analysis against some recent global matching methods.
dc.description.departmentSección Deptal. de Arquitectura de Computadores y Automática (Físicas)
dc.description.facultyFac. de Ciencias Físicas
dc.description.refereedTRUE
dc.description.statuspub
dc.eprint.idhttps://eprints.ucm.es/id/eprint/25395
dc.identifier.doi10.1109/TSMCB.2004.827391
dc.identifier.issn1083-4419
dc.identifier.officialurlhttp://dx.doi.org/10.1109/TSMCB.2004.827391
dc.identifier.relatedurlhttp://ieeexplore.ieee.org/
dc.identifier.urihttps://hdl.handle.net/20.500.14352/51036
dc.issue.number4
dc.journal.titleIEEE Transactions on Systems Man and Cybernetics Part B-Cybernetics
dc.language.isoeng
dc.page.final1657
dc.page.initial1646
dc.publisherIEEE-Inst Electrical Electronics Engineers Inc
dc.rights.accessRightsopen access
dc.subject.cdu004
dc.subject.keywordVision
dc.subject.keywordRelaxation
dc.subject.keywordAlgorithm
dc.subject.keywordImages
dc.subject.keywordOptimization
dc.subject.keywordWindow
dc.subject.ucmInformática (Informática)
dc.subject.unesco1203.17 Informática
dc.titleOn combining support vector machines and simulated annealing in stereovision matching
dc.typejournal article
dc.volume.number34
dcterms.references[1] D. Scharstein and R. Szeliski, “A taxonomy and evaluation of densetwo-frame stereo correspondence algorithms,” Int. J. Comput. Vis., vol.47, no. 1/2/3, pp. 7–42, 2002. [2] S. Barnard and M. Fishler, “Computational stereo,” ACMComput. Surv., vol. 14, pp. 553–572, 1982. [3] D. H. Kim and R. H. Park, “Analysis of quantization error in line-based stereo matching,” Pattern Recognit., vol. 8, pp. 913–924, 1994. [4] G. Medioni and R. Nevatia, “Segment based stereo matching,” Comput. Vis., Graph., Image Process., vol. 31, pp. 2–18, 1985. [5] J. Banks and M. Bennamoun, “Reliability analysis of the rank transform for stereo matching,” IEEE Trans. Syst., Man, Cybern. B, vol. 31, pp. 870–880, Dec. 2001. [6] L. Tang, C. Wu, and Z. Chen, “Image dense matching based on region growth with adaptive window,” Pattern Recognit. Lett., vol. 23, pp. 1169–1178, 2002. [7] W. E. L. Grimson, “Computational experiments with a feature-based stereo algorithm,” IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-7, pp. 17–34, Jan. 1985. [8] D. Marr and T. Poggio, “Acomputational theory of human stereovision,” in Proc. R. Soc. Lond., vol. B207, 1979, pp. 301–328. [9] M. S. Mousavi and R. J. Schalkoff, “ANN implementation of stero vision using a multilayer feedback architecture,” IEEE Trans. Syst., Man, Cybern., vol. 24, pp. 1220–1238, Aug. 1994. [10] Y. Ruichek and J. G. Postaire, “A neural network algorithm for 3-D reconstruction from stereo pairs of linear images,” Pattern Recognit. Lett., vol. 17, pp. 387–398, 1996. [11] K. L. Boyer and A. C. Kak, “Structural stereopsis for 3-D vision,” IEEE Trans. Pattern Anal. Machine Intell., vol. 10, pp. 144–166, Mar. 1988. [12] W. Hoff and N. Ahuja, “Surface from stereo: Integrating feature matching, disparity estimation, and contour detection,” IEEE Trans. Pattern Anal. Machine Intell., vol. 11, pp. 121–136, Mar. 1989. [13] G. Pajares, J. M. Cruz, and J. Aranda, “Relaxation by Hopfield network in stereo image matching,” Pattern Recognit., vol. 31, no. 5, pp. 561–574, 1998. [14] G. Pajares, J. M. Cruz, and J. A. López- Orozco, “Relaxation labeling in stereo image matching, ”Pattern Recognit., vol. 33, pp. 53–68, 2000. [15] G. Pajares and J. M. Cruz, “The nonparametric Parzen’s window in stereo vision matching,” IEEE Trans. Syst., Man, Cybern. B, vol. 32, pp. 225–230, Aug. 2002. [16] F. Candocia and M. Adjouadi, “A similarity measure for stereo feature matching,” IEEE Trans. Image Processing, vol. 6, pp. 1460–1464, Oct. 1997. [17] J. P. P. Starink and E. Backer, “Finding point correspondences using simulated annealing,” Pattern Recognit., vol. 28, no. 2, pp. 231–240, 1995. [18] D. M.Wuescher and K. L. Boyer, “Robust contour decomposition using a constraint curvature criterion,” IEEE Trans. Pattern Anal. Machine Intell, vol. 13, pp. 41–51, Jan. 1991. [19] R. M. Haralick and L. G. Shapiro, Computer and Robot Vision Vols. I and II. Reading, MA: Addison-Wesley, 1992, 1993. [20] A. Rosenfeld, R. Hummel, and S. Zucker, “Scene labeling by relaxation operation,” IEEE Trans. Syst., Man, Cybern., vol. SMC-6, pp. 420–453, Nov./Dec. 1976. [21] N. M. Nasrabadi, “A stereo vision technique using curve-segments and relaxation matching,” IEEE Trans. Pattern Anal. Machine Intell., vol. 14, pp. 566–572, Jan. 1992. [22] K. E. Price, “Relaxation matching techniques-a comparison,” IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-7, no. 5, pp. 617–623, 1985. [23] W. J. Christmas, J. Kittler, and M.Petrou, “Structural matching in computer vision using probabilistic relaxation,” IEEE Trans. Pattern Anal. Machine Intell., vol. 17, pp. 749–764, Aug. 1995. [24] N. M. Nasrabadi and C. Y. Choo, “Hopfield network for stereovision correspondence,” IEEE Trans. Neural Networks, vol. 3, pp. 123–135, Jan. 1992. [25] S. Anily and A. Federgruen, “Simulated annealing methods,” J. Appl. Probabil., vol. 28, pp. 657–666, 1987. [26] A. Huertas and G. Medioni, “Detection of intensity changes with subpixel accuracy using Laplacian-Gaussian masks,” IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-8, pp. 651–664, May 1986. [27] J. G. Leu and H. L. Yau, “Detecting the dislocations in metal crystals from microscopic images,” Pattern Recognit., vol. 24, pp. 41–56, 1991. [28] M. S. Lew, T. S. Huang, and K. Wong, “Learning and feature selection in stereo matching,” IEEE Trans. Pattern Anal. Machine Intell., vol. 16, pp. 869–881, Sept. 1994. [29] E. P. Krotkov, Active Computer Vision by Cooperative Focus and Stereo. New York: Springer-Verlag, 1989. [30] S. Tanaka and A. C. Kak, “A rule-based approach to binocular stereopsis,” in Analysis and Interpretation of Range Images, R. C. Jain and A. K. Jain, Eds. Berlin, Germany: Springer-Verlag, 1990, pp. 33–139. [31] R. Nevatia and K. R. Babu, “Linear feature extraction and description,” Comput. Vis., Graph., Image Process., vol. 13, pp. 257–269, 1980. [32] V. N. Vapnik, The Nature of Statistical Learning Theory. New York: Springer, 2000. [33] V. Cherkassky and F. Mulier, Learning from Data: Concepts, Theory and Methods. New York: Wiley, 1998. [34] V. N. Vapnik, Statistical Learning Theory. New York: Wiley, 1998. [35] Y. S. Kim, J. J. Lee, and Y. H. Ha, “Stereo matching algorithm based on modified wavelet decomposition process,” Pattern Recognit., vol. 30, no. 6, pp. 929–952, 1997. [36] E. Kreszig, Advanced Engineering Mathematics. New York: Wiley, 1983. [37] S. Kirkpatrick, C. D. Gelatt, and M. P. Vecchi, “Optimization by simulated annealing,” Science, vol. 220, pp. 671–680, 1983. [38] S. Kirkpatrick, “Optimization by simulated annealing: Quantitative studies,” J. Stat. Phys., vol. 34, pp. 975–984, 1984. [39] R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification. New York: Wiley, 2001. [40] S. Haykin, Neural Networks: A Comprehensive Foundation. New York: Macmillan, 1994. [41] B. Hajek, “Cooling schedules for optimal annealing,” Math. Oper. Res., vol. 13, pp. 311–329, 1988. [42] P. M. J. van Laarhoven and E. H. L. Aarts, Simulated Annealing: Theory and Applications. Norwell, MA: Kluwer, 1989. [43] S. T. Barnard, “Stochastic stereo matching over scale,” Int. J, Comput. Vis., vol. 3, no. 1, pp. 17–32, 1989. [44] S. Hattori, A. Okamoto, and H. Hasegawa, “Stereo matching by simulated annealing incorporating a diffusion equation,” in Proc. ASPRS Annu. Conf., 1998, pp. 1030–1041. [45] T. Poggio, V. Torre, and C. Koch, “Computational vision and regularization theory,” Nature, vol. 317, pp. 314–319, 1985. [46] N. Yokoya, T. Shakunaga, and M. Kanbara, “Passive range sensing techniques: Depth from images,” IEICE Trans. Inform. Syst., vol. E82, no. 3, pp. 523–533, 1999. [47] A. Fusiello, U. Castellani, and V. Murino, “Relaxing symmetric multiple windows stereo using Markov random fields,” in Proc. Energy Minimization Methods Computer Vision Pattern Recognition, Berlin, Germany,2001, pp. 91–105.
dspace.entity.typePublication
relation.isAuthorOfPublication878e090e-a59f-4f17-b5a2-7746bed14484
relation.isAuthorOfPublication.latestForDiscovery878e090e-a59f-4f17-b5a2-7746bed14484

Download

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
cruzgarcia40.pdf
Size:
444.34 KB
Format:
Adobe Portable Document Format

Collections