Computing Optic Flow by Scale-Space Integration of Normal Flow

  • Kim S. Pedersen
  • Mads Nielsen
Conference paper
Part of the Lecture Notes in Computer Science 2106 book series (LNCS, volume 2106)


In this paper we will present a least committed multi-scale method for computation of optic flow fields. We extract optic flow fields from normal flow, by fitting the normal components of a local polynomial model of the optic flow to the normal flow. This fitting is based on an analytically solvable optimization problem, in which an integration scale-space over the normal flow field regularizes the solution. An automatic local scale selection mechanism is used in order to adapt to the local structure of the flow field. The performance profile of the method is compared with that of existing optic flow techniques and we show that the proposed method performs at least as well as the leading algorithms on the benchmark image sequences proposed by Barron et al. [3]. We also do a performance comparison on a synthetic fire particle sequence and apply our method to a real sequence of smoke circulation in a pigsty. Both consist of highly complex non-rigid motion.


Optic Flow Polynomial Model Integration Scale Angular Error Stereo Match 
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.
    L. Alvarez, J. Weickert, and J. Sanchez. Reliable estimation of dense optical flow fields with large displacements. IJCV, 39(1):41–56, 2000.zbMATHCrossRefGoogle Scholar
  2. 2.
    J. Arnspang. Optic acceleration. In Proc. of 2nd ICCV, pages 364–373, 1988.Google Scholar
  3. 3.
    J.L. Barron, D.J. Fleet, and S.S. Beauchemin. Performance of optical flow techniques. IJCV, 12(1):43–77, 1994.CrossRefGoogle Scholar
  4. 4.
    L. Florack, W. Niessen, and M. Nielsen. The intrinsic structure of optic flow incorporating measurement duality. IJCV, 27(3):263–286, 1998.CrossRefGoogle Scholar
  5. 5.
    L. Florack, B. ter Haar Romeny, J. Koenderink, and M. Viergever. Linear scalespace. JMIV, 4(4):325–351, 1994.MathSciNetCrossRefGoogle Scholar
  6. 6.
    J. Gårding and T. Lindeberg. Direct computation of shape cues using scale-adapted spatial derivative operators. IJCV, 17(2):163–191, 1996.CrossRefGoogle Scholar
  7. 7.
    G.H. Granlund and H. Knutsson. Signal Processing for Computer Vision. Kluwer, Dordrecht, 1995.CrossRefGoogle Scholar
  8. 8.
    B.K.P. Horn and B.G. Schunck. Determining optical flow. Artificial Intelligence, 17:185–203, 1981.CrossRefGoogle Scholar
  9. 9.
    T. Kanade and M. Okutomi. A stereo matching algorithm with an adaptive window: Theory and experiment. IEEE Trans. PAMI, 16(9):920–932, 1994.CrossRefGoogle Scholar
  10. 10.
    J. Koenderink. The structure of images. Biol. Cyber., 50:363–370, 1984.MathSciNetzbMATHCrossRefGoogle Scholar
  11. 11.
    J. Koenderink. Scale-time. Biol. Cyber., 58:159–162, 1988.MathSciNetzbMATHCrossRefGoogle Scholar
  12. 12.
    T. Lindeberg. Direct estimation of affine image deformations using visual front-end operations with automatic scale selection. In Proc. of ICCV’95. Springer, 1995.Google Scholar
  13. 13.
    T. Lindeberg. Linear spatio-temporal scale-space. In Proc. of Scale-Space’97, LNCS. Springer, 1997.Google Scholar
  14. 14.
    T. Lindeberg. Edge detection and ridge detection with automatic scale selection. IJCV, 30(2):117–154, 1998.CrossRefGoogle Scholar
  15. 15.
    D. Marr. Vision. W. H. Freeman & Co., San Francisco, 1982.Google Scholar
  16. 16.
    M. Nielsen, R. Maas, W. Niessen, L. Florack, and B. ter Haar Romeny. Binocular stereo from grey-scale images. JMIV, 10(2):103–122, 1999.MathSciNetzbMATHCrossRefGoogle Scholar
  17. 17.
    M. Nielsen and O.F. Olsen. The structure of the optic flow field. In Proc. of ECCV’98, LNCS. Springer, 1998.Google Scholar
  18. 18.
    W. Niessen and R. Maas. Optic flow and stereo. In J. Sporring et al., editor, Gaussian Scale-Space Theory, pages 31–42. Kluwer, 1997.Google Scholar
  19. 19.
    M. Otte and H.-H. Nagel. Optical flow estimation: Advances and comparisons. In Proc. of ECCV’94, LNCS. Springer, 1994.Google Scholar
  20. 20.
    K.S. Pedersen. Turbulence in optical flow fields. Technical Report DIKU-00-3, DIKU, 2000.Google Scholar
  21. 21.
    K.S. Pedersen and M. Nielsen. The hausdorff dimension and scale-space normalisation of natural images. JVCIR, 11(2):266–277, 2000.Google Scholar
  22. 22.
    J. Weber and J. Malik. Robust computation of optical flow in a multi-scale differential framework. IJCV, 14:67–81, 1995.CrossRefGoogle Scholar
  23. 23.
    J. Weickert. Anisotropic Difusion in Image Processing. Teubner, 1998.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Kim S. Pedersen
    • 1
  • Mads Nielsen
    • 2
  1. 1.DIKUUniversity of CopenhagenCopenhagenDenmark
  2. 2.IT University of CopenhagenCopenhagenDenmark

Personalised recommendations