PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Extending Pictorial Structures for Object Recognition
M. Pawan Kumar, Philip Torr and Andrew Zisserman
In: BMVC 2004, Kingston, UK(2004).

There is a more recent version of this eprint available. Click here to view it.

Abstract

The goal of this paper is to recognize various deformable objects from images. To this end we extend the class of generative probabilistic models known as pictorial structures. This class of models is particularly suited to represent articulated structures, and has previously been used by Felzenszwalb and Huttenlocher for pose estimation of humans. We extend pictorial structures in three ways: (i) likelihoods are included for both the boundary and the enclosed texture of the animal; (ii) a complete graph is modelled (rather than a tree structure); (iii) it is demonstrated that the model can be fitted in polynomial time using belief propagation. We show examples for two types of quadrupeds, cows and horses. We achieve excellent recognition performance for cows with an equal error rate of 3% for 500 positive and 5000 negative images.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
ID Code:252
Deposited By:Andrew Zisserman
Deposited On:23 November 2004

Available Versions of this Item