BMVC 2004, Kingston, 7th-9th Sept, 2004
Articulated Shape Mixtures for Object Recognition
A. Al-Shaher and E.R. Hancock (University of York)
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.
(pdf article)