Abstract
This paper describes a probabilistic 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 pose recognition.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cootes, T., Taylor, C.: Combining point distribution models with shape models based on finite element analysis. IVC 13(5), 403–409 (1995)
Duta, N., Jain, A., Dubuisson, P.: Learning 2d shape models. In: International Conference on Computer Vision and pattern Recognition, vol. 2, pp. 8–14 (1999)
Isard, M., Blake, A.: Contour tracking by stochastic propagation of conditional density. In: Proc. ECCV, pp. 343–356 (1996)
Gonzales, J., Varona, J., Roca, F.X., Villanueva, J.: aspace:Action space for recognition and synthesis of human actions. In: 2 IWAMDO, Spain, pp. 189–200 (2002)
Rehg, J.M., Kanade, T.: Visual tracking of high dof articulated structures: an application to human hand tracking. In: 3 ECCV, Sweden, pp. 35–46 (1994)
Heap, T., Hogg, D.: Extending the point distribution model using polar coordinates. Image and Vision Computing 14, 589–599 (1996)
Cootes, T., Taylor, C.: A mixture models for representing shape variation. Image and Vision Computing 17, 403–409 (1999)
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)
Jordan, M., Jacobs, R.: Hierarchical mixtures of experts and the em algorithm. Neural Computation 6, 181–214 (1994)
Hancock, E.R., Kittler, J.: Edge-labelling using dictionary-based relaxation. IEEE Transaction on PAMI 12(2), 165–181 (1990)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Al-Shaher, A.A., Hancock, E.R. (2004). A Probabilistic Framework for Articulated Shape Recognition. In: Perales, F.J., Draper, B.A. (eds) Articulated Motion and Deformable Objects. AMDO 2004. Lecture Notes in Computer Science, vol 3179. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30074-8_8
Download citation
DOI: https://doi.org/10.1007/978-3-540-30074-8_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22958-2
Online ISBN: 978-3-540-30074-8
eBook Packages: Springer Book Archive