Stereo Matching Using Iterated Graph Cuts and Mean Shift Filtering

  • Ju Yong Chang
  • Kyoung Mu Lee
  • Sang Uk Lee
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3851)


In this paper, we propose a new stereo matching algorithm using an iterated graph cuts and mean shift filtering technique. Our algorithm consists of following two steps. In the first step, given an estimated sparse RDM (Reliable Disparity Map), we obtain an updated dense disparity map through a new constrained energy minimization framework that can cope with occlusion. The graph cuts technique is employed for the solution of the proposed stereo model. In the second step, we re-estimate the RDM from the disparity map obtained in the first step. In order to obtain accurate reliable disparities, the crosschecking technique followed by the mean shift filtering in the color-disparity space is introduced. The proposed algorithm expands the RDM repeatedly through the above two steps until it converges. Experimental results on the standard data set demonstrate that the proposed algorithm achieves comparable performance to the state-of-the-arts, and gives good results especially in the areas such as the disparity discontinuous boundaries and occluded regions, where the conventional methods usually suffer.


Stereo Match Shift Vector Color Segmentation Shift Algorithm Occlude Region 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. IJCV 47, 7–42 (2002)zbMATHCrossRefGoogle Scholar
  2. 2.
    Birchfield, S., Tomasi, C.: A pixel dissimilarity measure that is insensitive to image sampling. PAMI 20, 401–406 (1998)Google Scholar
  3. 3.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. PAMI 23, 1222–1239 (2001)Google Scholar
  4. 4.
    Kolmogorov, V., Zabih, R.: Computing visual correspondence with occlusions using graph cuts. In: ICCV 2001, pp. 508–515 (2001)Google Scholar
  5. 5.
    Sun, J., Zheng, N.N., Shum, H.Y.: Stereo matching using belief propagation. PAMI 25, 787–800 (2003)Google Scholar
  6. 6.
    Tao, H., Sawhney, H.: A global matching framework for stereo computation. In: ICCV 2001, vol. I, pp. 532–539 (2001)Google Scholar
  7. 7.
    Ernst, F., Wilinski, P., Overveld, K.V.: Dense structure-from-motion: An approach based on segment matching. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2351, pp. 217–231. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  8. 8.
    Hong, L., Chen, G.: Segment-based stereo matching using graph cuts. In: CVPR 2004, vol. I, pp. 74–81 (2004)Google Scholar
  9. 9.
    Wei, Y., Quan, L.: Region-based progressive stereo matching. In: CVPR 2004, vol. I, pp. 106–113 (2004)Google Scholar
  10. 10.
    Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. PAMI 24, 1–18 (2002)Google Scholar
  11. 11.
    Kolmogorov, V., Zabih, R.: What energy functions can be minimized via graph cuts. PAMI 26, 147–159 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Ju Yong Chang
    • 1
  • Kyoung Mu Lee
    • 1
  • Sang Uk Lee
    • 1
  1. 1.School of Electrical Eng., ASRISeoul National UniversitySeoulKorea

Personalised recommendations