Advertisement

Motion boundary detection in image sequences by local stochastic tests

  • H. -H. Nagel
  • G. Socher
  • H. Kollnig
  • M. Otte
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 801)

Abstract

While estimating both components of optical flow based on the postulated validity of the Optical Flow Constraint Equation (OFCE), it has been tacitly assumed so far that the partial derivatives of the gray value distribution — which are required for this approach at the pixel positions involved — are independent from each other. [Nagel 94] has shown in a theoretical investigation how dropping this assumption affects the estimation procedure. The advantage of such a more rigorous approach consists in the possibility to replace heuristic tests for the local detection of discontinuities in optical flow fields by well known stochastic tests. First results from various experiments with this new approach are presented and discussed.

Keywords

Optical Flow Image Area Pixel Position Contour Segment Optical Flow Field 
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.

References

  1. [Bairon et al. 92]
    Barron, J.L., Fleet, D.J., Beauchemin, S.S., and Burkitt, T.A.: Performance of Optical Flow Techniques. In Proc. IEEE Conference on Computer Vision and Pattern Recognition CVPR '92, 15–18 June 1992, Champaign, IL, pp. 236–242. See, too, Int. Journal of Computer Vision 12:1 (1994) 43–77.Google Scholar
  2. [Bouthemy & Santillana Rivero 87]
    Bouthemy, P., and Santillana Rivero, J.: A Hierarchical Likelihood Approach for Region Segmentation According to Motion-Based Criteria. In Proc. First Intern. Conference on Computer Vision ICCV '87, London, UK, 8–11 June 1987, pp. 463–467.Google Scholar
  3. [Bouthemy & Francois 93]
    Bouthemy, P., and Francois, E.: Motion Segmentation and Qualitative Scene Analysis from an Image Sequence. Int. Journal of Computer Vision 10:2 (1993) 157–182Google Scholar
  4. [Burt et al. 91]
    Burt, P. J., Hingorani, R., and Kolczynski, R.: Mechanisms for Isolation Component Patterns in the Sequential Analysis of Multiple Motion. In Proc. IEEE Workshop on Visual Motion, Princeton, NJ, 7–9 October 1991, pp. 187–193.Google Scholar
  5. [Campani & Verri 92]
    Campani, M., and Verri, A.: Motion Analysis from First Order Properties of Optical Flow. CVGIP: Image Understanding 56:1 (1992) 90–107.Google Scholar
  6. [Chou & Chen 93]
    Chou, W.-S., and Chen, Y.-C.: Estimation of the Velocity Field of Two-Dimensional Deformable Motion. Pattern Recognition 26:2 (1993) 351–364.Google Scholar
  7. [De Micheli et al. 93]
    De Micheli, E., Torre, V., and Uras, S.: The Accuracy of the Computation of Optical Flow and of the Recovery of Motion Parameters. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-15:5 (1993) 434–447.Google Scholar
  8. [Etoh & Shirai 93]
    Etoh, M., and Shirai, Y.: Segmentation and 2D Motion Estimation by Region Fragments. In Proc. Fourth Intern. Conference on Computer Vision ICCV '93, 11–14 May 1993, Berlin, Germany, pp. 192–199.Google Scholar
  9. [Fleet 92]
    Fleet, D.J.: Measurement of Image Velocity. Kluwer Academic Publishers: Boston, MA; London, UK; Dordrecht, NL, 1992Google Scholar
  10. [Gu et al. 93]
    H. Gu, M. Asada, and Y. Shirai: The Optimal Partition of Moving Edge Segments. In Proc. IEEE Conference on Computer Vision and Pattern Recognition CVPR '93, 15–17 June 1993, New York City, NY, pp. 367–372.Google Scholar
  11. [Horn 86]
    Horn, B.K.P.: Robot Vision. The MIT Press: Cambridge, MA, 1986Google Scholar
  12. [Irani et al. 92]
    Irani, M., Rousso, B., and Peleg, S.: Detecting and Tracking Multiple Moving Objects Using Temporal Integration. In Proc. Second European Conference on Computer Vision ECCV '92, Santa Margherita Ligure, Italy, 18–23 May 1992, Lecture Notes in Computer Science 588, G. Sandini (ed.), Springer-Verlag: Berlin Heidelberg New York and others, pp. 282–287.Google Scholar
  13. [Kollnig et al. 94]
    H. Kollnig, H.-H. Nagel, and M. Otte: Association of Motion Verbs with Vehicle Movements Extracted from Dense Optical Flow Fields. Proc. ECCV '94, Stockholm / Sweden, 2–6 May 1994.Google Scholar
  14. [Letang et al. 93]
    Letang, J.M., Rebuffel, V., and Bouthemy, P.: Motion Detection Robust to Perturbations: a Statistical Regularization and Temporal Integration Framework. In Proc. Fourth Intern. Conference on Computer Vision ICCV '93, 11–14 May 1993, Berlin, Germany, pp. 21–30.Google Scholar
  15. [Nagel 92]
    Nagel, H.-H.: Direct Estimation of Optical Flow and of Its Derivatives. In Artificial and Biological Vision Systems, G. Orban and H.-H. Nagel (eds.). Springer-Verlag: Berlin Heidelberg New York and others, 1992, pp. 193–224.Google Scholar
  16. [Nagel 94]
    Nagel, H.-H.: Optical Flow Estimation and the Interaction Between Measurement Errors at Adjacent Pixel Positions. Int. Journal of Computer Vision, to appear 1994.Google Scholar
  17. [Negahdaripour & Lee 92]
    Negahdaripour, S., and Lee, S.: Motion Recovery from Image Sequences Using Only First Order Optical Flow Information. Int. Journal of Computer Vision 9:3 (1992) 163–184.Google Scholar
  18. [Negahdaripour & Yu 93]
    Negahdaripour, S., and Yu, C.-H.: A Generalized Brightness Change Model for Computing Optical Flow. In Proc. Fourth Intern. Conference on Computer Vision ICCV '93, 11–14 May 1993, Berlin, Germany, pp. 2–11.Google Scholar
  19. [Otte & Nagel 94]
    M. Otte and H.-H. Nagel: Optical Flow Estimation: Advances and Comparisons. Proc. ECCV '94, Stockholm / Sweden, 2–6 May 1994.Google Scholar
  20. [Simoncelli et al. 91]
    Simoncelli, E.P., Adelson, E.H., and Heeger, D.J.: Probability Distributions of Optical Flow. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, Lahaina, Maui, Hawaii, 3–6 June 1991, pp. 310–315.Google Scholar
  21. [Spoerri & Ullman 87]
    Spoerri, A., and Ullman, S.: The Early Detection of Motion Boundaries. In Proc. First Intern. Conference on Computer Vision ICCV '87, London, UK, 8–11 June 1987, pp. 209–218.Google Scholar
  22. [Szeliski 89]
    Szeliski, R.: Bayesian Modeling of Uncertainty in Low-level Vision. Kluwer Academic Publishers: Boston, MA; Dordrecht, NL; London, UK, 1989Google Scholar
  23. [Szeliski 90]
    Szeliski, R.: Bayesian Modeling of Uncertainty in Low-Level Vision. Int. Journal of Computer Vision 5:3 (1990) 271–301.Google Scholar
  24. [Thompson & Pong 90]
    Thompson, W.B., and Pong, T.-C.: Detecting Moving Objects. Intern. Journal of Computer Vision 4:1 (1990) 39–57.Google Scholar
  25. [Torr & Murray 92]
    Torr, P.H.S., and Murray, D.W.: Statistical Detection of Independent Movement from a Moving Camera. In Proc. British Machine Vision Conference, Leeds, UK, 22–24 Sept. 1992, D. Hogg and R. Boyle (eds.), Springer-Verlag: London Berlin Heidelberg and others, pp. 79–88. See, too, Image and Vision Computing 11:4 (1993) 180–187.Google Scholar
  26. [Wang & Adelson 93]
    Wang, J.Y.A., and Adelson, E.H.: Layered Representation for Motion Analysis. In Proc. IEEE Conference on Computer Vision and Pattern Recognition CVPR '93, 15–17 June 1993, New York City, NY, pp. 361–366.Google Scholar
  27. [Weber & Malik 93]
    Weber, J., and Malik, J.: Robust Computation of Optical Flow in a Multiscale Differential Framework. In Proc. Fourth Intern. Conference on Computer Vision ICCV '93, 11–14 May 1993, Berlin, Germany, pp. 12–20.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • H. -H. Nagel
    • 1
    • 2
  • G. Socher
    • 2
  • H. Kollnig
    • 2
  • M. Otte
    • 2
  1. 1.Fraunhofer-Institut für Informations- und Datenverarbeitung IITBKarlsruhe
  2. 2.Institut für Algorithmen und Kognitive SystemeFakultät für Informatik der Universität KarlsruheDeutschland

Personalised recommendations