Combining support vector machines and simulated annealing for stereovision matching with fish eye lenses in forest environments

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
We present a novel strategy for computing disparity maps from omni-directional stereo images obtained with fish-eye lenses in forest environments. At a first segmentation stage, the method identifies textures of interest to be either matched or discarded. Two of them are identified by applying the powerful Support Vector Machines approach. At a second stage, a stereovision matching process is designed based on the application of four stereovision matching constraints: epipolarity, similarity, uniqueness and smoothness. The epipolarity guides the process. The similarity and uniqueness are mapped once again through the Support Vector Machines, but under a different way to the previous case; after this an initial disparity map is obtained. This map is later filtered by applying the Discrete Simulated Annealing framework where the smoothness constraint is conveniently mapped. The combination of the segmentation and stereovision matching approaches makes the main contribution. The method is compared against the usage of simple features and combined similarity matching strategies. (C) 2011 Elsevier Ltd. All rights reserved.
© 2011 Elsevier. The authors wish to acknowledge to the Council of Education of the Autonomous Community of Madrid and the Social European Fund for the research contract with the author P. Javier Herrera. Also to Drs. Fernando Montes and Isabel Canellas from the Forest Research Centre (CIFOR, INIA) for his support and the imaged material supplied.
Unesco subjects
Abraham, S., & Förstner, W. (2005). Fish-eye-stereo calibration and epipolar rectification. Photogrammetry and Remote Sensing, 59, 278–288. Barnard, S., & Fishler, M. (1982). Computational stereo. ACM Computing Surveys, 14, 553–572. Bleyer, M., & Gelautz, M. (2005b). Graph-based surface reconstruction from stereo pairs using image segmentation. In SPIE (Vol. 5665, pp. 288–299). Bleyer, M., & Gelautz, M. (2005a). A layered stereo matching algorithm using image segmentation and global visibility constraints. ISPRS Journal of Photogrammetry and Remote Sensing, 59(3), 128–150. Cherkassky, V., & Mulier, F. (1998). Learning from data: Concepts, theory and methods. New York: Wiley. Cochran, S. D., & Medioni, G. (1992). 3-D surface description from binocular stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(10), 981–994. Duda, R. O., Hart, P. E., & Stork, D. S. (2000). Pattern classification. Wiley. Felzenszwalb, P. F., & Huttenlocher, D. P. (2004). Efficient belief propagation for early vision. International Journal of Computer Vision, 70(1), 261–268. Geman, S., & Geman, G. (1984). Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6, 721–741. González, R. C., & Woods, R. E. (2007). Digital image processing. Prentice Hall. Hajek, B. (1988). Cooling schedules for optimal annealing. Mathematical Operation Research, 13, 311–329. Haykin, S. (1994). Neural networks: A comprehensive foundation. New York: Macmillan College Publishing Co.. Kirkpatrick, S. (1984). Optimization by simulated annealing: quantitative studies. Journal of Statistical Physics, 34, 975–984. Kirkpatrick, S., Gelatt, C. D., & Vecchi, M. P. (1983). Optimization by simulated annealing. Science, 220, 671–680. Klaus, A., Sormann, M., & Karner, K. (2006). Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure. In Proceedings of the18th International Conference on Pattern Recognition (ICPR’06), Washington, USA (pp. 15–18). Koffka, K. (1935). Principles of gestalt psychology. New York: Harcourt. Laarhoven, P. M. J., & Aarts, E. H. L. (1989). Simulated annealing: Theory and applications. Holland: Kluwer Academic. Lew, M. S., Huang, T. S., & Wong, K. (1994). Learning and feature selection in stereo matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16, 869–881. Lillo, A., Motta, G., & Storer, J. A. (2007). Supervised segmentation based on texture signatures extracted in the Frequency domain. In J. Martí, J. M. Benedí, A. M. Mendoça, & J. Serrat (Eds.), Pattern Recognition and Image Analysis. Lecture Notes in Computer Science (Vol. 4477, pp. 89–96). Berlin: Springer-Verlag (Part I). Liu, F., & Picard, R. W. (1996). Periodicity, directionality and randomness: Wold features for image modelling and retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(7), 722–733. Mousavi, M. S., & Schalkoff, R. J. (1994). ANN implementation of stereo vision using a multi-layer feedback architecture. IEEE Transactions on Systems, Man, and Cybernetics, 24(8), 1220–1238. Pajares, G., & Cruz, J. M. (2004). On combining support vector machines and simulated annealing in stereovision matching. IEEE Transactions on System, Man, and Cybernetics, Part B, 34(4), 1646–1657. Pajares, G., Cruz, J. M., & Aranda, J. (1998). Relaxation by Hopfield network in stereo image matching. Pattern Recognition, 31(5), 561–574. Schwalbe, E. (2005). Geometric modelling and calibration of fisheye lens camera systems. In Proceedings of the 2nd panoramic photogrammetry workshop, international archives of photogrammetry and remote sensing (Vol. 36, Part 5/W8). Tang, L., Wu, C., & Chen, Z. (2002). Image dense matching based on region growth with adaptive window. Pattern Recognition Letters, 23, 1169–1178. Tao, Y., Lam, E. C. M., & Tang, Y. Y. (2000). Extraction of fractal feature for pattern recognition. In Proceedings of the international conference on pattern recognition, IAPR, Barcelona, Spain (Vol. 2. pp. 527–530). Trias-Sanz, R., Stamon, G., & Louchet, J. (2008). Using colour, texture, and hierarchical segmentation for high-resolution remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing, 63, 156–168. Vapnik, V. N. (2000). The nature of statistical learning theory. New York: Springer-Verlag. Wan, T., Canagarajah, N., & Achim, A. (2007). Multiscale color-texture image segmentation with adaptive region merging. In Proceedings of the IEEE international conference on acoustics, speech and signal processing (ICASSP08) (Vol. 1, pp. I-1213–I-1216). Wang, D. (2005). The time dimension for scene analysis. IEEE Transactions on Neural Networks, 16(6), 1401–1426. Wang, Z., & Boesch, R. (2007). Color- and texture-based image segmentation for improved forest delineation. IEEE Transaction on Geoscience Remote Sensing, 45(10), 3055–3062.