Modelling Human Shape with Articulated Shape Mixtures

  • Abdullah A. Al-Shaher
  • Edwin R. Hancock
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3138)


This paper describes a statistical framework for recognising 2D shapes with articulated components. The shapes are represented using both geometrical and a symbolic primitives, that are encapsulated in a two layer hierarchical architecture. Each primitive is modelled so as to allow a degree of articulated freedom using a polar point distribution model that captures how the primitive movement varies over a training set. Each segment is assigned a symbolic label to distinguish its identity, and the overall shape is represented by a configuration of labels. We demonstrate how both the point-distribution model and the symbolic labels can be combined to perform recognition using a probabilistic hierarchical algorithm. This involves recovering the parameters of the point distribution model that minimise an alignment error, and recovering symbol configurations that minimise a structural error. We apply the recognition method to human moving skeleton.


Recognition Rate Modelling Human Training Pattern Posteriori Probability Alignment Error 
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.


  1. 1.
    Cootes, T., Taylor, C.: Combining point distribution models with shape models based on finite element analysis. IVC 13(5), 403–409 (1995)Google Scholar
  2. 2.
    Duta, N., Jain, A., Dubuisson, P.: Learning 2d shape models. International Conference on Computer Vision and pattern Recognition 2, 8–14 (1999)Google Scholar
  3. 3.
    Isard, M., Blake, A.: Contour tracking by stochastic propagation of conditional density. In: Buxton, B.F., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1064, pp. 343–356. Springer, Heidelberg (1996)CrossRefGoogle Scholar
  4. 4.
    Gonzales, J., Varona, J., Roca, F., Villanueva, J.: aspace: Action space for recognition and synthesis of human actions. In: 2nd IWAMDO, Spain, pp. 189–200 (2002)Google Scholar
  5. 5.
    Rehg, J., Kanade, T.: Visual tracking of high dof articulated structures: an application to human hand tracking. In: Eklundh, J.-O. (ed.) ECCV 1994. LNCS, vol. 800, pp. 35–46. Springer, Heidelberg (1994)CrossRefGoogle Scholar
  6. 6.
    Heap, T., Hogg, D.: Extending the point distribution model using polar coordinates. Image and Vision Computing 14, 589–599 (1996)CrossRefGoogle Scholar
  7. 7.
    Cootes, T., Taylor, C.: A mixture models for representing shape variation. Image and Vision Computing 17, 403–409 (1999)CrossRefGoogle Scholar
  8. 8.
    Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data via the em algorithm. Journal of Royal Statistical Soc. Ser. 39, 1–38 (1977)zbMATHMathSciNetGoogle Scholar
  9. 9.
    Jordan, M., Jacobs, R.: Hierarchical mixtures of experts and the em algorithm. Neural Computation 6, 181–214 (1994)CrossRefGoogle Scholar
  10. 10.
    Hancock, E.R., Kittler, J.: Edge-labelling using dictionary-based relaxation. IEEE Transaction on PAMI 12(2), 165–181 (1990)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Abdullah A. Al-Shaher
    • 1
  • Edwin R. Hancock
    • 1
  1. 1.University of YorkYorkUK

Personalised recommendations