Advertisement

An Effective Stereo Matching Algorithm with Optimal Path Cost Aggregation

  • Mikhail Mozerov
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4174)

Abstract

This paper presents a stereo matching algorithm for obtaining dense disparity maps. Our main contribution is to introduce a new cost aggregation technique of a 3D disparity-space image data, referred to as the Optimal Path Cost Aggregation. The approach is based on the dynamic programming principle, which exactly solves one dimensional optimization problem. Furthermore, the 2D extension of the proposed technique proves an excellent approximation to the global 2D optimization problem. The effectiveness of our approach is demonstrated with several widely used synthetic and real image pairs, including ones with ground-truth value.

Keywords

Machine Intelligence Stereo Image Stereo Match Cost Aggregation Minimal Projection 
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.
    Bhatand, D.N., Nayar, S.K.: Ordinal measures for image correspondence. IEEE Trans. Pattern Analysis and Machine Intelligence 20, 415–423 (1998)CrossRefGoogle Scholar
  2. 2.
    Brown, M.Z., Burschka, D., Hager, G.D.: Advances in computational stereo. IEEE Trans. Pattern Analysis and Machine Intelligence 25, 993–1008 (2003)CrossRefGoogle Scholar
  3. 3.
    Gong, M., Yang, Y.-H.: Fast unambiguous stereo matching using reliability-based dynamic programming. IEEE Trans. Pattern Analysis and Machine Intelligence 27, 998–1003 (2005)CrossRefGoogle Scholar
  4. 4.
    Hirschmuller, H.: Accurate and efficient stereo processing by semi-global matching and mutual information. In: Proc. Computer Vision and Pattern Recognition (CVPR 2005), vol. 2, pp. 807–814 (2005)Google Scholar
  5. 5.
    Kim, J., Kolmogorov, V., Zabih, R.: Visual correspondence using energy minimization and mutual information. In: Proc. International Conference on Computer Vision, pp. 1033–1040 (2003)Google Scholar
  6. 6.
    Lin, M.H., Tomasi, C.: Surfaces with occlusions from layered stereo. IEEE Trans. Pattern Analysis and Machine Intelligence 26, 1073–1078 (2004)CrossRefGoogle Scholar
  7. 7.
    Ohta, Y., Kanade, T.: Stereo by intra – and intra-scanline search using dynamic programming. IEEE Trans. Pattern Analysis and Machine Intelligence 7, 139–154 (1985)CrossRefGoogle Scholar
  8. 8.
    Roy, S., Cox, I.J.: A maximum-flow formulation of the N-camera stereo correspondence problem. In: Proc. Int’l. Conf. Computer Vision, pp. 492–499 (1998)Google Scholar
  9. 9.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision 47, 7–42 (2002)MATHCrossRefGoogle Scholar
  10. 10.
    Sun, J., Shum, H.Y., Zheng, N.N.: Stereo matching using belief propagation. IEEE Trans. Pattern Analysis and Machine Intelligence 25, 787–800 (2003)CrossRefGoogle Scholar
  11. 11.
    Tomasi, C., Manduchi, R.: Stereo matching as a nearest-neighbor problem. IEEE Trans. Pattern Analysis and Machine Intelligence 20, 333–340 (1998)CrossRefGoogle Scholar
  12. 12.
    Zhao, H.: Global optimal surface from stereo. In: Proc. Int’l. Conf. Pattern Recognition, vol. 1, pp. 101–104 (2000)Google Scholar
  13. 13.
    Zitnik, C.L., Kanade, T.: A cooperative algorithm for stereo matching and occlusion detection. IEEE Trans. Pattern Analysis and Machine Intelligence 22, 675–684 (2000)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Mikhail Mozerov
    • 1
  1. 1.Computer Vision Center and Departament d’Informática Universitat Autònoma de Barcelona (UAB)CerdanyolaSpain

Personalised recommendations