Optic Flow Scale Space

  • Oliver Demetz
  • Joachim Weickert
  • Andrés Bruhn
  • Henning Zimmer
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6667)


While image scale spaces are well understood, it is undeniable that the regularisation parameter in variational optic flow methods serves a similar role as the scale parameter in scale space evolutions. However, no thorough analysis of this optic flow scale-space exists to date. Our paper closes this gap by interpreting variational optic flow methods as Whittaker-Tikhonov regularisations of the normal flow, evaluated in a constraint-specific norm. The transition from this regularisation framework to an optic flow evolution creates novel vector-valued scale-spaces that are not in divergence form and act in a highly anisotropic way. From a practical viewpoint, the deep structure in optic flow scale space allows the automatic selection of the most accurate scale by means of an optimal prediction principle. Moreover, we show that our general class of optic flow scale-spaces incorporates novel methods that outperform classical variational approaches.


Optic Flow Scale Space Scale Selection Smoothness Term Mathematical Image 
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.
    Abhau, J., Belhachmi, Z., Scherzer, O.: On a decomposition model for optical flow. In: Cremers, D., Boykov, Y., Blake, A., Schmidt, F.R. (eds.) EMMCVPR 2009. LNCS, vol. 5681, pp. 126–139. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  2. 2.
    Alvarez, L., Guichard, F., Lions, P.-L., Morel, J.-M.: Axioms and fundamental equations in image processing. Archive for Rational Mechanics and Analysis 123, 199–257 (1993)CrossRefzbMATHMathSciNetGoogle Scholar
  3. 3.
    Baker, S., Scharstein, D., Lewis, J.P., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. Technical Report MSR-TR-2009-179, Microsoft Research, Redmond, WA (December 2009)Google Scholar
  4. 4.
    Barron, J.L., Fleet, D.J., Beauchemin, S.S.: Performance of optical flow techniques. International Journal of Computer Vision 12(1), 43–77 (1994)CrossRefGoogle Scholar
  5. 5.
    Ben-Ari, R., Sochen, N.: A geometric framework and a new criterion in optical flow modeling. Journal of Mathematical Imaging and Vision 33, 178–194 (2009)CrossRefMathSciNetGoogle Scholar
  6. 6.
    Bertero, M., Poggio, T.A., Torre, V.: Ill-posed problems in early vision. Proceedings of the IEEE 76(8), 869–889 (1988)CrossRefGoogle Scholar
  7. 7.
    Fagerström, D.: Spatio-temporal scale-spaces. In: Sgallari, F., Murli, A., Paragios, N. (eds.) SSVM 2007. LNCS, vol. 4485, pp. 326–337. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  8. 8.
    Florack, L.: Image Structure. Computational Imaging and Vision, vol. 10. Kluwer, Dordrecht (1997)Google Scholar
  9. 9.
    Grewenig, S., Weickert, J., Bruhn, A.: From box filtering to fast explicit diffusion. In: Goesele, M., Roth, S., Kuijper, A., Schiele, B., Schindler, K. (eds.) DAGM 2010. LNCS, vol. 6376, pp. 533–542. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  10. 10.
    Guichard, F.: A morphological, affine, and Galilean invariant scale-space for movies. IEEE Transactions on Image Processing 7(3), 444–456 (1998)CrossRefGoogle Scholar
  11. 11.
    Horn, B., Schunck, B.: Determining optical flow. Artificial Intelligence 17, 185–203 (1981)CrossRefGoogle Scholar
  12. 12.
    Iijima, T.: Theory of pattern recognition. In: Electronics and Communications in Japan, pp. 123–134 (November 1963) (in English)Google Scholar
  13. 13.
    Iijima, T., Genchi, H., Mori, K.: A theory of character recognition by pattern matching method. In: Proc. First International Joint Conference on Pattern Recognition, Washington, DC, pp. 50–56 (October 1973) (in English)Google Scholar
  14. 14.
    Krajsek, K., Mester, R.: A maximum likelihood estimator for choosing the regularization parameters in global optical flow methods. In: Proc. 2006 IEEE International Conference on Image Processing, Atlanta, GA, pp. 1081–1084 (2006)Google Scholar
  15. 15.
    Lindeberg, T.: Scale-Space Theory in Computer Vision. Kluwer, Boston (1994)CrossRefzbMATHGoogle Scholar
  16. 16.
    Mrázek, P., Navara, M.: Selection of optimal stopping time for nonlinear diffusion filtering. International Journal of Computer Vision 52(2-3), 189–203 (2003)CrossRefGoogle Scholar
  17. 17.
    Nagel, H.-H., Enkelmann, W.: An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE Transactions on Pattern Analysis and Machine Intelligence 8, 565–593 (1986)CrossRefGoogle Scholar
  18. 18.
    Scherzer, O., Weickert, J.: Relations between regularization and diffusion filtering. Journal of Mathematical Imaging and Vision 12(1), 43–63 (2000)CrossRefzbMATHMathSciNetGoogle Scholar
  19. 19.
    Schnörr, C.: On functionals with greyvalue-controlled smoothness terms for determining optical flow. IEEE Transactions on Pattern Analysis and Machine Intelligence 15(10), 1074–1079 (1993)CrossRefGoogle Scholar
  20. 20.
    Sochen, N., Kimmel, R., Bruckstein, F.: Diffusions and confusions in signal and image processing. Journal of Mathematical Imaging and Vision 14(3), 195–210 (2001)CrossRefzbMATHMathSciNetGoogle Scholar
  21. 21.
    Sporring, J., Nielsen, M., Florack, L., Johansen, P. (eds.): Gaussian Scale-Space Theory. Computational Imaging and Vision, vol. 8. Kluwer, Dordrecht (1997)zbMATHGoogle Scholar
  22. 22.
    Tikhonov, A.N.: Solution of incorrectly formulated problems and the regularization method. Soviet Mathematics Doklady 4, 1035–1038 (1963)zbMATHGoogle Scholar
  23. 23.
    Weickert, J.: Anisotropic Diffusion in Image Processing. Teubner, Stuttgart (1998)zbMATHGoogle Scholar
  24. 24.
    Whittaker, E.T.: A new method of graduation. Proceedings of the Edinburgh Mathematical Society 41, 65–75 (1923)Google Scholar
  25. 25.
    Zimmer, H., Bruhn, A., Weickert, J.: Optic flow in harmony. International Journal of Computer Vision 93(3), 368–388 (2011)CrossRefzbMATHMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Oliver Demetz
    • 1
  • Joachim Weickert
    • 1
  • Andrés Bruhn
    • 2
  • Henning Zimmer
    • 1
  1. 1.Mathematical Image Analysis Group, Faculty of Mathematics and Computer ScienceSaarland UniversitySaarbrückenGermany
  2. 2.Vision and Image Processing Group, Cluster of Excellence Multimodal Computing and InteractionSaarland UniversitySaarbrückenGermany

Personalised recommendations