A Third Eye for Performance Evaluation in Stereo Sequence Analysis

  • Sandino Morales
  • Reinhard Klette
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5702)


Prediction errors are commonly used when analyzing the performance of a multi-camera stereo system using at least three cameras. This paper discusses this methodology for performance evaluation for the first time on long stereo sequences (in the context of vision-based driver assistance systems). Three cameras are calibrated in an ego-vehicle, and prediction error analysis is performed on recorded stereo sequences. They are evaluated using various common stereo matching algorithms, such as belief propagation, dynamic programming, semi-global matching, or graph cut. Performance is evaluated on both synthetic and real data.


Root Mean Square Dynamic Programming Algorithm Virtual Image Virtual View Normalize Cross Correlation 
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.
    Baker, S., Scharstein, S., Lewis, J.P., Roth, S., Black, M.J., Szelisky, R.: A database and evaluation methodology for optical flow. In: Proc. IEEE Int. Conf. Computer Vision, CD (2007)Google Scholar
  2. 2.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Analysis Machine Intelligence 23, 1222–1239 (2001)CrossRefGoogle Scholar
  3. 3.
    .enpeda.. image sequence analysis test site (EISATS),
  4. 4.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient belief propagation for early vision. Int. J. Computer Vision 70, 261–268 (2006)CrossRefGoogle Scholar
  5. 5.
    Guan, S., Klette, R., Woo, Y.W.: Belief propagation for stereo analysis of night-vision sequences. In: Wada, T., Huang, F., Lin, S. (eds.) PSIVT 2009. LNCS, vol. 5414, pp. 932–943. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  6. 6.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2004)zbMATHGoogle Scholar
  7. 7.
    Hirschmüller, H.: Accurate and efficient stereo processing by semi-global matching and mutual information. In: Proc. Computer Vision Pattern Recognition, vol. 2, pp. 807–814 (2005)Google Scholar
  8. 8.
    Klette, R., Zamperoni, P.: Handbook of Image Processing Operators. Wiley, Chichester (1996)Google Scholar
  9. 9.
    Klette, R., Schlüns, K., Koschan, A.: Computer Vision. Three-Dimensional Data from Images. Springer, Singapore (1998)zbMATHGoogle Scholar
  10. 10.
    Kolmogorov, V., Zabih, R.: What energy functions can be minimized via graph cuts? IEEE Trans. Pattern Analysis Machine Intelligence 26, 65–81 (2004)Google Scholar
  11. 11.
    Liu, Z., Klette, R.: Dynamic programming stereo on real-world sequences. In: Proc. ICONIP. LNCS. Springer, Heidelberg (to appear, 2009)Google Scholar
  12. 12.
    Morales, S., Vaudrey, T., Klette, R.: An in depth robustness evaluation of stereo algorithms on long stereo sequences. In: Proc. Intelligent Vehicles (to appear, 2009)Google Scholar
  13. 13.
    Ohta, Y., Kanade, T.: Stereo by two-level dynamic programming. In: Proc. IJCAI, pp. 1120–1126 (1985)Google Scholar
  14. 14.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Computer Vision 47, 7–42 (2002)zbMATHCrossRefGoogle Scholar
  15. 15.
    Szeliski, R.: Prediction error as a quality metric for motion and stereo. In: Proc. Int. Conf. Computer Vision, vol. 2, pp. 781–788 (1999)Google Scholar
  16. 16.
    Vaudrey, T., Rabe, C., Klette, R., Milburn, J.: Differences between stereo and motion behavior on synthetic and real-world stereo sequences. In: Proc. Image Vision Computing New Zealand. IEEE, Los Alamitos (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Sandino Morales
    • 1
  • Reinhard Klette
    • 1
  1. 1.The .enpeda.. ProjectThe University of AucklandAucklandNew Zealand

Personalised recommendations