Dense Stereomatching Algorithm Performance for View Prediction and Structure Reconstruction

  • Jana Kostková
  • Jan Čech
  • Radim Šára
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)


The knowledge of stereo matching algorithm properties and behaviour under varying conditions is crucial for the selection of a proper method for the desired application. In this paper we study the behaviour of four representative matching algorithms under varying signal-to-noise ratio in six types of error statistics. The errors are focused on basic matching failure mechanisms and their definition observes the principles of independence, symmetry and completeness. A ground truth experiment shows that the best choice for view prediction is the Graph Cuts algorithm and for structure reconstruction it is the Confidently Stable Matching.


  1. 1.
    R. C. Bolles, H. H. Baker, and M. J. Hannah. The JISCT stereo evaluation. In Proc. DARPA Image Understanding Workshop, pages 263–274, 1993.Google Scholar
  2. 2.
    I. J. Cox, S. L. Higorani, S. B. Rao, and B. M. Maggs. A maximum likelihood stereo algorithm. Computer Vision and Image Understanding, 63(3):542–567, 1996.CrossRefGoogle Scholar
  3. 3.
    T. Day and J.-P. Muller. Digital elevation model production by stereo-matching spot imagepairs: a comparison of algorithms. Image and Vision Computing, 7(2):95–101, 1989.CrossRefGoogle Scholar
  4. 4.
    G. Gimel’farb. Pros and cons of using ground control points to validate stereo and multiview terrain reconstruction. Evaluation and Validation of Computer Vision Algorithms, 1998.Google Scholar
  5. 5.
    G. Gimel’farb and H. Li. Probabilistic regularisation in symmetric dynamic programming stereo. In Proc. Image and Vision Computing New Zealand 2000, pages 144–149, 2000.Google Scholar
  6. 6.
    V. Kolmogorov and R. Zabih. Computing visual correspondence with occlusions using graph cuts. In Proc. International Conf. on Computer Vision, 2001.Google Scholar
  7. 7.
    J. Kostková, J. Čech, and R. Šára. The CMP evaluation of stereo algorithms. Tech. Report CTU-CMP-2003-01, Center for Machine Perception, Czech Technical University, 2003.Google Scholar
  8. 8.
    Y. G. Leclerc, Q.-T. Luong, and P. Fua. Measuring the self-consistency of stereo algorithms. In Proc. European Conf. on Computer Vision, volume 2, pages 282–298, 2000.Google Scholar
  9. 9.
    J. Mulligan, V. Isler, and K. Daniilidis. Performance evaluation of stereo for tele-presence. In Proc. of International Conf. on Computer Vision, 2001.Google Scholar
  10. 10.
    R. Šára. Finding the largest unambiguous component of stereo matching. In Proc. European Conf. on Computer Vision, volume 3, pages 900–914, 2002.Google Scholar
  11. 11.
    D. Scharstein, R. Szeliski, and R. Zabih. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. IJCV, 47(1):7–42, 2002. url: Scholar
  12. 12.
    R. Szeliski. Prediction error as a quality metric for motion and stereo. In Proc. International Conf. on Computer Vision, volume 2, pages 781–788, 1999. 107CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Jana Kostková
    • 1
  • Jan Čech
    • 1
  • Radim Šára
    • 1
  1. 1.Center for Machine PerceptionCzech Technical UniversityPragueCzech Republic

Personalised recommendations