Advertisement

Learning Image Structures for Optimizing Disparity Estimation

  • M. V. Rohith
  • Chandra Kambhamettu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6494)

Abstract

We present a method for optimizing the stereo matching process when it is applied to a series of images with similar depth structures. We observe that there are similar regions with homogeneous colors in many images and propose to use image characteristics to recognize them. We use patterns in the data dependent triangulations of images to learn characteristics of the scene. As our learning method is based on triangulations rather than segments, the method can be used for diverse types of scenes. A hypotheses of interpolation is generated for each type of structure and tested against the ground truth to retain only those which are valid. The information learned is used in finding the solution to the Markov random field associated with a new scene. We modify the graph cuts algorithm to include steps which impose learned disparity patterns on current scene. We show that our method reduces errors in the disparities and also decreases the number of pixels which have to be subjected to a complete cycle of graph cuts. We train and evaluate our algorithm on the Middlebury stereo dataset and quantitatively show that it produces better disparity than unmodified graph cuts.

Keywords

IEEE Computer Society Gaussian Mixture Model Markov Random Field Stereo Pair Disparity Estimation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision 47, 7–42 (2002)CrossRefzbMATHGoogle Scholar
  2. 2.
    Kostková, J., Čech, J., Šára, R.: Dense stereomatching algorithm performance for view prediction and structure reconstruction. In: Bigun, J., Gustavsson, T. (eds.) SCIA 2003. LNCS, vol. 2749, pp. 101–107. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  3. 3.
    Felzenszwalb, P., Huttenlocher, D.: Efficient belief propagation for early vision. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2004, vol. 1, pp. I–261–I–268 (2004)Google Scholar
  4. 4.
    Leung, C., Appleton, B., Sun, C.: Iterated dynamic programming and quadtree subregioning for fast stereo matching. Image Vision Comput. 26, 1371–1383 (2008)CrossRefGoogle Scholar
  5. 5.
    Trinh, H.: Efficient stereo algorithm using multiscale belief propagation on segmented images (2008)Google Scholar
  6. 6.
    Tingting Jiang, F.J., Schmid, C.: Learning shape prior models for object matching. In: Proc. Computer Vision and Pattern Recognition Conf. (2009)Google Scholar
  7. 7.
    Besbes, A., Nikos Komodakis, G.L., Paragios, N.: Shape priors and discrete mrfs for knowledge-based segmentation. In: Proc. Computer Vision and Pattern Recognition Conf. (2009)Google Scholar
  8. 8.
    Zhang, L., Seitz, S.M.: Parameter estimation for mrf stereo. In: CVPR 2005: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), Washington, DC, USA, pp. 288–295. IEEE Computer Society, Los Alamitos (2005)Google Scholar
  9. 9.
    Li, Y., Huttenlocher, D.P.: Learning for stereo vision using the structured support vector machine. In: CVPR. IEEE Computer Society, Los Alamitos (2008)Google Scholar
  10. 10.
    Kong, D., Tao, H.: A method for learning matching errors for stereo computation (2004)Google Scholar
  11. 11.
    Labatut, P., Pons, J.P., Keriven, R.: Efficient multi-view reconstruction of large-scale scenes using interest points, delaunay triangulation and graph cuts. In: IEEE International Conference on Computer Vision, pp. 1–8 (2007)Google Scholar
  12. 12.
    Wey, P., Fischer, B., Bay, H., Buhmann, J.M.: Dense stereo by triangular meshing and cross validation. In: Franke, K., Müller, K.-R., Nickolay, B., Schäfer, R. (eds.) DAGM 2006. LNCS, vol. 4174, pp. 708–717. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  13. 13.
    Strecha, C., Fransens, R., Gool, L.V.: Wide-baseline stereo from multiple views: A probabilistic account. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 552–559 (2004)Google Scholar
  14. 14.
    Rohith, M., Somanath, G., Kambhamettu, C., Geiger, C.: Towards estimation of dense disparities from stereo images containing large textureless regions. In: 19th International Conference on Pattern Recognition, ICPR 2008, pp. 1–5 (2008)Google Scholar
  15. 15.
    Woodford, O.J., Torr, P.H.S., Reid, I.D., Fitzgibbon, A.W.: Global stereo reconstruction under second order smoothness priors. In: CVPR. IEEE Computer Society, Los Alamitos (2008)Google Scholar
  16. 16.
    Komodakis, N., Paragios, N.: Beyond pairwise energies: Efficient optimization for higher-order mrfs. In: Proc. Computer Vision and Pattern Recognition Conf. (2009)Google Scholar
  17. 17.
    Lempitsky, V.S., Roth, S., Rother, C.: Fusionflow: Discrete-continuous optimization for optical flow estimation. In: CVPR. IEEE Computer Society, Los Alamitos (2008)Google Scholar
  18. 18.
    Kolmogorov, V., Zabih, R.: Computing visual correspondence with occlusions using graph cuts. In: Proceedings of Eighth IEEE International Conference on Computer Vision, ICCV 2001, vol. 2, pp. 508–515 (2001)Google Scholar
  19. 19.
    Baker, S., Sim, T., Kanade, T.: A characterization of inherent stereo ambiguities. In: Proceedings of the 8th International Conference on Computer Vision, pp. 428–435. IEEE Computer Society Press, Los Alamitos (2001)Google Scholar
  20. 20.
    Kolmogorov, V., Zabih, R.: Multi-camera scene reconstruction via graph cuts. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 82–96. Springer, Heidelberg (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • M. V. Rohith
    • 1
  • Chandra Kambhamettu
    • 1
  1. 1.Video/Image Modeling and Synthesis (VIMS) Lab, Department of Computer and Information SciencesUniversity of DelawareNewarkUSA

Personalised recommendations