DAGM 2008: Pattern Recognition pp 355-364 | Cite as

Postprocessing of Optical Flows Via Surface Measures and Motion Inpainting

  • Claudia Kondermann
  • Daniel Kondermann
  • Christoph Garbe
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5096)

Abstract

Dense optical flow fields are required for many applications. They can be obtained by means of various global methods which employ regularization techniques for propagating estimates to regions with insufficient information. However, incorrect flow estimates are propagated as well. We, therefore, propose surface measures for the detection of locations where the full flow can be estimated reliably, that is in the absence of occlusions, intensity changes, severe noise, transparent structures, aperture problems and homogeneous regions. In this way we obtain sparse, but reliable motion fields with lower angular errors. By subsequent application of a basic motion inpainting technique to such sparsified flow fields we obtain dense fields with smaller angular errors than obtained by the original combined local global (CLG) method and the structure tensor method in all test sequences. Experiments show that this postprocessing method makes error improvements of up to 38% feasible.

Keywords

Surface Measure Homogeneous Region Invariance Function Angular Error Global Method 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Haussecker, H., Spies, H.: Motion. In: Jähne, B., Haussecker, H., Geissler, P. (eds.) Handbook of Computer Vision and Applications, ch. 13, vol. 2. Academic Press, London (1999)Google Scholar
  2. 2.
    Bruhn, A., Weickert, J.: A Confidence Measure for Variational Optic Flow Methods, pp. 283–298. Springer, Heidelberg (2006)Google Scholar
  3. 3.
    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
  4. 4.
    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
  5. 5.
    Bainbridge-Smith, R., Lane, A.: Measuring confidence in optical flow estimation. IEEE Electronics Letters 32(10), 882–884 (1996)CrossRefGoogle Scholar
  6. 6.
    Rosenberg, A., Werman, M.: Representing local motion as a probability distribution matrix applied to object tracking. In: Proceedings of the International Conference on Computer Vision and Pattern Recognition, pp. 654–659 (1997)Google Scholar
  7. 7.
    Irani, M., Anandan, P.: Robust multi-sensor image alignment. In: Proceedings of the International Conference on Computer Vision, pp. 959–966 (1998)Google Scholar
  8. 8.
    Matsushita, Y., Ofek, E., Tang, X., Shum, H.: Full-frame video stabilization. In: Proceedings of the International Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 50–57 (2005)Google Scholar
  9. 9.
    Bishop, C.: Neural Networks for Pattern Recognition. Oxford University Press, New York (1995)Google Scholar
  10. 10.
    Zetzsche, C., Barth, E.: Fundamental limits of linear filters in the visual processing of two dimensional signals. Vision Research 30(7), 1111–1117 (1990)CrossRefGoogle Scholar
  11. 11.
    Barth, E.: Bewegung als intrinsische geometrie von bildfolgen. In: Proceedings of the German Association for Pattern Recognition (DAGM) (1999)Google Scholar
  12. 12.
    Barth, E., Stuke, I., Aach, T., Mota, C.: Spatio-temporal motion estimation for transparency and occlusions. In: Proceedings of the International Conference on Image Processing (ICIP), vol. 3, pp. 69–72 (2003)Google Scholar
  13. 13.
    Krüger, N., Felsberg, M.: A continuous formulation of intrinsic dimension. In: British Machine Vision Conference (2003)Google Scholar
  14. 14.
    Horn, B., Schunck, B.: Determining optical flow. Artificial Intelligence 17, 185–204 (1981)CrossRefGoogle Scholar
  15. 15.
    McCane, B., Novins, K., Crannitch, D., Galvin, B.: On benchmarking optical flow (2001), http://of-eval.sourceforge.net/
  16. 16.
    Mota, C., Stuke, I., Barth, E.: Analytical solutions for multiple motions. In: Proceedings of the International Conference on Image Processing ICIP (2001)Google Scholar
  17. 17.
    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
  18. 18.
    Barth, E.: The minors of the structure tensor. In: Proceedings of the DAGM (2000)Google Scholar
  19. 19.
    Bruhn, A., Weickert, J., Schnörr, C.: Lucas/Kanade meets Horn/Schunck: Combining local and global optic flow methods. International Journal of Computer Vision 61(3), 211–231 (2005)CrossRefGoogle Scholar
  20. 20.
    Bigün, J., Granlund, G.H., Wiklund, J.: Multidimensional orientation estimation with applications to texture analysis and optical flow. IEEE Journal of Pattern Analysis and Machine Intelligence 13(8), 775–790 (1991)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Claudia Kondermann
    • 1
  • Daniel Kondermann
    • 1
  • Christoph Garbe
    • 1
  1. 1.HCI at Interdisciplinary Center for Scientific ComputingUniversity of HeidelbergGermany

Personalised recommendations