Advertisement

Spatiotemporally adaptive estimation and segmentation of OF-fields

  • H. -H. Nagel
  • A. Gehrke
Conference paper
First Online:
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1407)

Abstract

A grayvalue structure tensor provides knowledge about a local grayvalue variation. This knowledge can be used to devise a spatiotemporally adaptive optic flow estimation process. Such an adaptive estimation lowers the level at which the resulting optic flow (OF) field is disturbed by noise and estimation artefacts. This in turn substantially simplifies the analysis of remaining — often subtle — effects which easily jeopardize a ‘naive’ segmentation approach. Appropriate treatment of such effects eventually results in a basically simple, but nevertheless surprisingly robust segmentation approach. Various stages of this approach are illustrated by examples for the extraction of moving vehicle images from a digitized road intersection video-sequence.

Keywords

Optic Flow Finite Impulse Response Small Eigenvalue Adaptive Estimation Edge Segment 
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.
Download to read the full conference paper text

References

  1. 1.
    J.L. Barron, D.J. Fleet, and S.S. Beauchemin: Performance of Optical Flow Techniques. International Journal of Computer Vision 12 (1994) 43–77CrossRefGoogle Scholar
  2. 2.
    H. Hau\ecker and B. JÄhne: A Tensor Approach for Precise Computation of Dense Displacement Vector Fields. E. Paulus and F.M. Wahl (Hrsg.), Mustererkennung 1997, 19. DAGM-Symposium, Braunschweig/Germany, 15.–17. September 1997; Informatik aktuell, Springer-Verlag Berlin Heidelberg 1997, pp. 199–208Google Scholar
  3. 3.
    R.M. Haralick and L.G. Shapiro: Computer and Robot Vision. Addison-Wesley Publishing Company, Reading/MA 1992 (Vol. I)Google Scholar
  4. 4.
    B.K.P. Horn: Robot Vision. The MIT Press, Cambridge/MA and London/UK 1986Google Scholar
  5. 5.
    B. JÄhne: Spatio-Temporal Image Processing, Theory and Scientific Applications. Lecture Notes in Computer Science, Vol. 751, Springer-Verlag Berlin Heidelberg 1993.Google Scholar
  6. 6.
    H. Knutsson: Filtering and Reconstruction in Image Processing. Ph.D. Thesis, Department of Electrical Engineering; In: Linköping Studies in Science and Technology, Dissertations No. 88, Linköping University, S-581 83, Linköping, Sweden, 1982.Google Scholar
  7. 7.
    T. Lindeberg, J. Gårding: Shape-Adapted Smoothing in Estimation of 3-D Depth Cues from Affine Distortions of Local 2-D Brightness Structure. Proc. 3rd European Conference on Computer Vision ECCV '94, 2–6 May 1994, Stockholm/S; J.-O. Eklundh (Ed.), Lecture Notes in Computer Science LNCS 800, Springer-Verlag Berlin Heidelberg New York/NY 1994, pp. 389–400.Google Scholar
  8. 8.
    H. Liu, T.-H. Hong, M. Herman, and R. Chellappa: A General Motion Model and Spatio-Temporal Filters for Computing Optical Flow. International Journal of Computer Vision 22:2 (1997) 141–172.CrossRefGoogle Scholar
  9. 9.
    H.-H. Nagel, A. Gehrke, M. Haag, and M. Otte: Space-and Time-Variant Estimation Approaches and the Segmentation of the Resulting Optical Flow Field. Proc. Second Asian Conference on Computer Vision, 5–8 December 1995, Singapore, Vol. II, pp. 296–300.Google Scholar
  10. 10.
    V. S. Nalwa, T. O. Binford: On Detecting Edges. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-8 (1986) 699–714.CrossRefGoogle Scholar
  11. 11.
    J. Weber and J. Malik: Robust Computation of Optical Flow in a Multi-Scale Differential Framework. Proc. Fourth International Conference on Computer Vision ICCV '93, 11–14 May 1993, Berlin/Germany, pp. 12–20; see, too, Int. Journal of Computer Vision 14:1 (1995) 67–81.Google Scholar
  12. 12.
    C.-F. Westin: A Tensor Framework for Multidimensional Signal Processing. Ph.D. Thesis, Department of Electrical Engineering; In: Linköping Studies in Science and Technology, Dissertations No. 348, (ISBN 91-7871-421-4) Linköping University, S-581 83, Linköping, Sweden, 1994.Google Scholar
  13. 13.
    Y. Xiong and S.A. Shafer: Moment and Hypergeometric Filters for High Precision Computation of Focus, Stereo and Optical Flow. International Journal of Computer Vision 22:1 (1997) 25–59.zbMATHCrossRefGoogle Scholar
  14. 14.
    Y. Xiong and S.A. Shafer: Hypergeometric Filters for Optical Flow and Affine Matching. International Journal of Computer Vision 24:2 (1997) 163–177.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • H. -H. Nagel
    • 1
    • 2
  • A. Gehrke
    • 1
  1. 1.Institut für Algorithmen und Kognitive SystemeFakultät für Informatik der Universität Karlsruhe (TH)KarlsruheGermany
  2. 2.Fraunhofer-Institut für Informations- und Datenverarbeitung (IITB)KarlsruheGermany

Personalised recommendations

Cite paper