Spatio-temporal Composite-Features for Motion Analysis and Segmentation

  • Raquel Dosil
  • Xosé M. Pardo
  • Xosé R. Fdez-Vidal
  • Antón García
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4179)


Motion estimation by means of spatio-temporal energy filters –velocity tuned filters– is known to be robust to noise and aliasing and to allow an easy treatment of the aperture problem. In this paper we propose a motion representation based on the composition of spatio-temporal energy features, i.e., responses of a set of filters in phase quadrature tuned to different scales and orientations. Complex motion patterns are identified by unsupervised cluster analysis of energy features. The integration criterion reflects the degree of alignment of maxima of the features’s amplitude, which is related to phase congruence. The composite-feature representation has been applied to motion segmentation with a geodesic active model both for initialization and image potential definition. We will show that the resulting method is able to handle typical problems, such as partial and total occlusions, large inter-frame displacements, moving background and noise.


Motion Pattern Active Model Image Potential Previous Frame Integration Criterion 
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.
    Sato, K., Aggarwal, J.: Temporal spatio-temporal transform and its application to tracking and interaction. Comput. Vis. Image Underst. 96, 100–128 (2000)CrossRefGoogle Scholar
  2. 2.
    Boykov, Y., Huttenlocher, D.: Adaptive bayesian recognition in tracking rigid objects. In: IEEE CVPR, vol. 2, pp. 697–704 (2000)Google Scholar
  3. 3.
    Nguyen, H., Smeulders, A.: Fast occluded object tracking by a robust appearance filter. IEEE Trans. Pattern Anal. Mach. Intell. 26, 1099–1104 (2004)CrossRefGoogle Scholar
  4. 4.
    Montoliu, R., Pla, F.: An iterative region-growing algorithm for motion segmentation and estimation. Int. J. Intell. Syst. 20, 577–590 (2005)zbMATHCrossRefGoogle Scholar
  5. 5.
    Paragios, N., Deriche, R.: Geodesic active contours and level sets for the detection and tracking of moving objects. IEEE Trans. Pattern Anal. Mach. Intell. 22, 266–279 (2000)CrossRefGoogle Scholar
  6. 6.
    Barron, J., Fleet, D., Beauchemin, S.: Performance of optical flow techniques. Int. J. Comput. Vis. 12, 43–77 (1994)CrossRefGoogle Scholar
  7. 7.
    Heeger, D.: Model for the extraction of image flow. J. Opt. Soc. Am. A 4, 1471–1555 (1987)CrossRefGoogle Scholar
  8. 8.
    Simoncelli, E., Adelson, E.: Computing optical flow distributions using spatio-temporal filters. Technical Report 165, MIT Media Lab. Vision and Modeling, Massachusetts (1991)Google Scholar
  9. 9.
    Watson, A., Ahumada, A.: Model for human visual-motion sensing. J. Opt. Soc. Am. A 2, 322–342 (1985)CrossRefGoogle Scholar
  10. 10.
    Adelson, E., Bergen, J.: Spatiotemporal energy models for the perception of motion. J. Opt. Soc. Am. A 2, 284–299 (1985)CrossRefGoogle Scholar
  11. 11.
    Fleet, D.: Measurement of Image Velocity. Kluwer Academic Publishers, Massachusetts (1992)zbMATHGoogle Scholar
  12. 12.
    Chamorro-Martínez, J., Fdez-Valdivia, J., García, J., Martínez-Baena, J.: A frequency domain approach for the extraction of motion patterns. In: IEEE Int. Conf. on Acoustics, Speech and Signal Processing, vol. 3, pp. 165–168 (2003)Google Scholar
  13. 13.
    Morrone, M., Owens, R.: Feature detection from local energy. Pattern Recognit. Lett. 6, 303–313 (1987)CrossRefGoogle Scholar
  14. 14.
    Venkatesh, S., Owens, R.: On the classification of image features. Pattern Recognit. Lett. 11, 339–349 (1990)zbMATHCrossRefGoogle Scholar
  15. 15.
    Weickert, J., Kühne, G.: Fast methods for implicit active contour models. In: Osher, S., Paragios, N. (eds.) Geometric Level Set Methods in Imaging, Vision and Graphics, pp. 43–58. Springer, New York (2003)CrossRefGoogle Scholar
  16. 16.
    Tsechpenakis, G., Rapantzikos, K., Tsapatsoulis, N., Kollias, S.: A snake model for object tracking in natural sequences. Signal Process. Image Commun. 19, 219–238 (2004)CrossRefGoogle Scholar
  17. 17.
    Dosil, R., Pardo, X., Fdez-Vidal, X.: Data driven detection of composite feature detectors for 3D image analysis. Image Vis. Comput. 32, 225–238 (2006)CrossRefGoogle Scholar
  18. 18.
    Field, D.: What is the goal of sensory coding. Neural Comput. 6, 559–601 (1994)CrossRefGoogle Scholar
  19. 19.
    Faas, F., van Vliet, L.: 3D-orientation space; filters and sampling. In: Bigun, J., Gustavsson, T. (eds.) SCIA 2003. LNCS, vol. 2749, pp. 36–42. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  20. 20.
    Kovesi, P.: Invariant Measures of Image Features from Phase Information. PhD thesis, The University or Western Australia (1996)Google Scholar
  21. 21.
    Jain, A., Dubes, R.: Algorithms for Clustering Data. Prentice-Hall, Englewood Cliffs (1988)zbMATHGoogle Scholar
  22. 22.
    Pal, N., Biswas, J.: Cluster validation using graph theoretic concepts. Pattern Recognit. 30, 847–857 (1996)CrossRefGoogle Scholar
  23. 23.
    Dosil, R., Pardo, X.: Generalized ellipsoids and anisotropic filtering for segmentation improvement in 3D medical imaging. Image Vis. Comput. 21, 325–343 (2003)CrossRefGoogle Scholar
  24. 24.

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Raquel Dosil
    • 1
  • Xosé M. Pardo
    • 1
  • Xosé R. Fdez-Vidal
    • 2
  • Antón García
    • 1
  1. 1.Dept. Electrónica e ComputaciónUniversidade de Santiago de CompostelaSantiago de Compostela, A CorunaSpain
  2. 2.Escola Politécnica SuperiorUniv. de Santiago de CompostelaLugoSpain

Personalised recommendations