A Statistical Confidence Measure for Optical Flows

  • Claudia Kondermann
  • Rudolf Mester
  • Christoph Garbe
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5304)


Confidence measures are crucial to the interpretation of any optical flow measurement. Even though numerous methods for estimating optical flow have been proposed over the last three decades, a sound, universal, and statistically motivated confidence measure for optical flow measurements is still missing. We aim at filling this gap with this contribution, where such a confidence measure is derived, using statistical test theory and measurable statistics of flow fields from the regarded domain. The new confidence measure is computed from merely the results of the optical flow estimator and hence can be applied to any optical flow estimation method, covering the range from local parametric to global variational approaches. Experimental results using state-of-the-art optical flow estimators and various test sequences demonstrate the superiority of the proposed technique compared to existing ’confidence’ measures.


Optical Flow Confidence Measure Endpoint Error Intrinsic Dimensionality Optical Flow Estimator 
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.


  1. 1.
    Barron, J.L., Fleet, D.J., Beauchemin, S.: Performance of optical flow techniques. International Journal of Computer Vision 12(1), 43–77 (1994)CrossRefGoogle Scholar
  2. 2.
    Bainbridge-Smith, A., Lane, R.: Measuring confidence in optical flow estimation. IEEE Electronics Letters 32, 882–884 (1996)CrossRefGoogle Scholar
  3. 3.
    Bishop, C.: In: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)Google Scholar
  4. 4.
    Zetzsche, C., Barth, E.: Fundamental limits of linear filters in the visual processing of two dimensional signals. Vision Research 30, 1111–1117 (1990)CrossRefGoogle Scholar
  5. 5.
    Felsberg, M., Kalkan, S., Krüger, N.: Continuous dimensionality characterization of image structures. Journal of Image and Vision Computing (2008)Google Scholar
  6. 6.
    Haussecker, H., Spies, H.: Motion. In: Jähne, B., Haussecker, H., Geißler, P. (eds.) Handbook of Computer Vision and Applications, vol. 2, pp. 336–338. Academic Press, London (1999)Google Scholar
  7. 7.
    Bigün, J., Granlund, G., Wiklund, J.: Multidimensional orientation estimation with applications to texture analysis and optical flow. IEEE Journal of Pattern Analysis and Machine Intelligence 13, 775–790 (1991)CrossRefGoogle Scholar
  8. 8.
    Bruhn, A., Weickert, J.: A confidence measure for variational optic flow methods. In: Geometric Properties for Incomplete data, pp. 283–298. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  9. 9.
    Kondermann, C., Kondermann, D., Jähne, B., Garbe, C.: An adaptive confidence measure for optical flows based on linear subspace projections. In: Hamprecht, F.A., Schnörr, C., Jähne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 132–141. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  10. 10.
    Singh, A.: An estimation-theoretic framework for image-flow computation. In: Proceedings of IEEE ICCV, pp. 168–177 (1990)Google Scholar
  11. 11.
    Waxman, A., Wu, J., Bergholm, F.: Convected activation profiles and receptive fields for real time measurement of short range visual motion. In: Proceedings of IEEE CVPR, pp. 717–723 (1988)Google Scholar
  12. 12.
    Anandan, P.: A computational framework and an algorithm for the measurement of visual motion. International Journal of Computer Vision 2, 283–319 (1989)CrossRefGoogle Scholar
  13. 13.
    Uras, S., Girosi, F., Verri, A., Torre, V.: A computational approach to motion perception. Journal of Biological Cybernetics 60, 79–97 (1988)CrossRefGoogle Scholar
  14. 14.
    Mester, R., Hötter, M.: Robust displacement vector estimation including a statistical error analysis. In: Proc. 5th International Conference on Image Processing and its Applications, Edinburgh, UK, pp. 168–172. Institution of Electrical Engineers (IEE), London (1995)CrossRefGoogle Scholar
  15. 15.
    Simoncelli, E.P., Adelson, E.H., Heeger, D.J.: Probability distributions of optical flow. In: Proc Conf on Computer Vision and Pattern Recognition, pp. 310–315. IEEE Computer Society, Los Alamitos (1991)Google Scholar
  16. 16.
    Fermüller, C., Shulman, D., Aloimonos, Y.: The statistics of optical flow. Journal of Computer Vision and Image Understanding 82, 1–32 (2001)CrossRefzbMATHGoogle Scholar
  17. 17.
    Fleet, D.J., Black, M.J., Yacoob, Y., Jepson, A.D.: Design and use of linear models for image motion analysis. International Journal of Computer Vision 36, 171–193 (2000)CrossRefGoogle Scholar
  18. 18.
    Fisher, R.: Statistical Methods for Research Workers. Oliver and Boyd (1925)Google Scholar
  19. 19.
    Baker, S., Roth, S., Scharstein, D., Black, M., Lewis, J., Szeliski, R.: A database and evaluation methodology for optical flow. In: Proceedings of the International Conference on Computer Vision, pp. 1–8 (2007)Google Scholar
  20. 20.
    Bruhn, A., Weickert, J., Schnörr, C.: Lucas/Kanade meets Horn/Schunck: Combining local and global optic flow methods. International Journal of Computer Vision 61, 211–231 (2005)CrossRefGoogle Scholar
  21. 21.
    Nir, T., Bruckstein, A.M., Kimmel, R.: Over-parameterized variational optical flow. International Journal of Computer Vision 76, 205–216 (2008)CrossRefGoogle Scholar
  22. 22.
    Farnebäck, G.: Very high accuracy velocity estimation using orientation tensors, parametric motion, and simultaneous segmentation of the motion field. In: International Conference on Computer Vision, Proceedings, Vancouver, Canada, vol. I, pp. 171–177 (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Claudia Kondermann
    • 1
  • Rudolf Mester
    • 2
  • Christoph Garbe
    • 1
  1. 1.Interdisciplinary Center for Scientific ComputingUniversity of HeidelbergGermany
  2. 2.Visual Sensorics and Information Processing LabUniversity of FrankfurtGermany

Personalised recommendations