Analysis of Human Walking Based on aSpaces

  • J. Gonzàlez
  • J. Varona
  • F. X. Roca
  • J. J. Villanueva
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3179)


In this paper, we address the analysis of human actions by comparing different performances of the same action, i.e. walking. To achieve this goal, we define a proper human body model which maximizes the differences between human postures and, moreover, reflects the anatomical structure of the human beings. Subsequently, a human action space, called aSpace, is built in order to represent a performance, i.e., a predefined sequence of postures, as a parametric manifold. The final human action representation is called p–action, which is based on the most characteristic human body postures found during several walking performances. These postures are found automatically by means of a predefined distance function, and they are called key-frames. By using key-frames, we synchronize any performance with respect to the action model. Furthermore, by considering an arc length parameterization, independence from the speed at which performances are played is attained. Consequently, the style of human walking can be successfully analysed by establishing differences between a male and a female walkers.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ballard, D., Brown, C.: Computer Vision. Prentice-Hall, Englewood Cliffs (1982)Google Scholar
  2. 2.
    Borotschnig, H., Paletta, L., Prantl, M., Pinz, A.: Appearance-based active object recognition. Image and Vision Computing 18, 715–727 (2000)CrossRefGoogle Scholar
  3. 3.
    Cheng, J., Moura, M.F.: Capture and represention of human walking in live video sequences. IEEE Transactions on Multimedia 1(2), 144–156 (1999)CrossRefGoogle Scholar
  4. 4.
    Davis, J., Bobick, A.F.: The representation and recognition of movement using temporal templates. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR 1997), San Juan, Puerto Rico, pp. 928–934 (1997)Google Scholar
  5. 5.
    Gonzàlez, J., Varona, J., Roca, F.X., Villanueva, J.J.: aSpaces: Action spaces for recognition and synthesis of human actions. In: Perales, F.J., Hancock, E.R. (eds.) AMDO 2002. LNCS, vol. 2492, pp. 189–200. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  6. 6.
    Gonzàlez, J., Varona, J., Roca, F.X., Villanueva, J.J.: A human action comparison framework for motion understanding. In: Artificial Intelligence Research and Developments. Frontiers in Artificial Intelligence and Applications, vol. 100, pp. 168–177. IOS Press, Amsterdam (2003)Google Scholar
  7. 7.
    Guenter, B., Parent, R.: Computing the arc length of parametric curves. IEEE Computer Graphics and Applications 10(3), 72–78 (1990)CrossRefGoogle Scholar
  8. 8.
    Murase, H., Nayar, S.K.: Visual learning and recognition of 3-D objects from appearance. International Journal of Computer Vision 14, 5–24 (1995)CrossRefGoogle Scholar
  9. 9.
    Perales, F.J., Igelmo, A., Buades, J.M., Negre, P., Bernat, G.: Human motion analysis & synthesis using computer vision and graphics techniques. Some applications. In: IX Spanish Symposium on Pattern Recognition and Image Analysis, Benicassim, Spain, May 16-18, vol. 1, pp. 271–277 (2001)Google Scholar
  10. 10.
    Press, W., Flannery, B.P., Teukolsky, S.A., Vetterling, W.T.: Numerical Recipes in C. Cambridge University Press, Cambridge (1988)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • J. Gonzàlez
    • 1
  • J. Varona
    • 2
  • F. X. Roca
    • 1
  • J. J. Villanueva
    • 1
  1. 1.Computer Vision Center & Dept. d’Informàtica, Edifici OUniversitat Autònoma de Barcelona (UAB)BellaterraSpain
  2. 2.Dept. Matemàtiques i Informàtica & Unitat de Gràfics i VisióUniversitat de les Illes Balears (UIB)Palma de MallorcaSpain

Personalised recommendations