Integration of Multiple Temporal and Spatial Scales for Robust Optic Flow Estimation in a Biologically Inspired Algorithm

  • Cornelia Beck
  • Thomas Gottbehuet
  • Heiko Neumann
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4673)


We present a biologically inspired iterative algorithm for motion estimation that combines the integration of multiple temporal and spatial scales. This work extends a previously developed algorithm that is based on mechanisms of motion processing in the human brain [1]. The temporal integration approach realizes motion detection using one reference frame and multiple past and/or future frames leading to correct motion estimates at positions that are temporarily occluded. In addition, this mechanism enables the detection of subpixel movements and therefore achieves smoother and more precise flow fields. We combine the temporal integration with a recently proposed spatial multi scale approach [2]. The combination further improves the optic flow estimates when the image contains regions of different spatial frequencies and represents a very robust and efficient algorithm for optic flow estimation, both on artificial and real-world sequences.


Motion Estimate Motion Detection Coarse Scale Temporal Integration Multiple Spatial Scale 
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.
    Bayerl, P., Neumann, H.: A fast biologically inspired algorithm for recurrent motion estimation. IEEE Transactions On PAMI 29(2), 246–260 (2007)Google Scholar
  2. 2.
    Beck, C., Bayerl, P., Neumann, H.: Optic Flow Integration at Multiple Spatial Frequencies - Neural Mechanism and Algorithm. In: Bebis, G., Boyle, R., Parvin, B., Koracin, D., Remagnino, P., Nefian, A., Meenakshisundaram, G., Pascucci, V., Zara, J., Molineros, J., Theisel, H., Malzbender, T. (eds.) ISVC 2006. LNCS, vol. 4291, pp. 741–750. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  3. 3.
    Beauchemin, S.S., Barron, J.L.: The Computation of Optical Flow. ACM Computing Surveys 27, 433–467 (1995)CrossRefGoogle Scholar
  4. 4.
    Ungerleider, L.G., Haxby, J.V.: What and where in the human brain. Current Opinion in Neurobiology 4, 157–165 (1994)CrossRefGoogle Scholar
  5. 5.
    Albright, T.D.: Direction and orientation selectivity of neurons in visual area MT of the macaque. J. Neurophys. 52, 1106–1130 (1984)Google Scholar
  6. 6.
    Bayerl, P., Neumann, H.: Disambiguating Visual Motion through Contextual Feedback Modulation. Neural Computation 16, 2041–2066 (2004)zbMATHCrossRefGoogle Scholar
  7. 7.
    Horn, B.K.P., Schunk, B.G.: Determining optical flow. Artificial Intelligence 17, 185–203 (1981)CrossRefGoogle Scholar
  8. 8.
    Weiss, Y., Fleet, D.J.: Velocity likelihoods in biological and machine vision. In: Probabilistic models of the brain: Perception and neural function, pp. 81–100. MIT Press, Cambridge, MA (2001)Google Scholar
  9. 9.
    Adelson, E., Bergen, J.: Spatiotemporal energy models for the perception of motion. Optical Society of America A 2(2), 284–299 (1985)CrossRefGoogle Scholar
  10. 10.
    Hupé, J.M., James, A.C., Girard, P., Lomber, S.G., Payne, B.R., Bullier, J.: Feedback Connections Act on the Early Part of the Responses in Monkey Visual Cortex. J. Neurophys. 85, 134–145 (2001)Google Scholar
  11. 11.
    Stein, F.: Efficient Computation of Optical Flow Using the Census Transform. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds.) Pattern Recognition. LNCS, vol. 3175, pp. 79–86. Springer, Heidelberg (2004)Google Scholar
  12. 12.
    Ogale, A.S., Fermueller, C., Aloimonos, Y.: Motion Segmentation Using Occlusions. IEEE Transactions On PAMI 27(6), 988–992 (2005)Google Scholar
  13. 13.
    Simoncelli, E.: Course-to-fine Estimation of Visual Motion. In: IEEE Eighth Workshop on Image and Multidimensional Signal Processing, Cannes France (September 1993)Google Scholar
  14. 14.
    Burt, P.J., Adelson, E.H.: The Laplacian Pyramid as a Compact Image Code. IEEE Transactions On Communications 31(4), 532–540 (1983)CrossRefGoogle Scholar
  15. 15.
    Ogale, A.S., Aloimonos, Y.: A roadmap to the integration of early visual modules. IJCV 72(1), 9–25 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Cornelia Beck
    • 1
  • Thomas Gottbehuet
    • 1
  • Heiko Neumann
    • 1
  1. 1.Inst. for Neural Information Processing, University of UlmGermany

Personalised recommendations