Summary: A Model for Dynamic Shape and Its Applications
Che-Bin Liu and Narendra Ahuja
Beckman Institute
University of Illinois at Urbana-Champaign
Urbana, IL 61801, USA
cbliu, ahuja @vision.ai.uiuc.edu
Abstract
Variation in object shape is an important visual cue for de-
formable object recognition and classification. In this pa-
per, we present an approach to model gradual changes in
the ¾-D shape of an object. We represent ¾-D region shape
in terms of the spatial frequency content of the region con-
tour using Fourier coefficients. The temporal changes in
these coefficients are used as the temporal signatures of the
shape changes. Specifically, we use autoregressive model
of the coefficient series. We demonstrate the efficacy of the
model on several applications. First, we use the model pa-
rameters as discriminating features for object recognition
and classification. Second, we show the use of the model for
synthesis of dynamic shape using the model learned from a

Source: Ahuja, Narendra - Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign

Collections: Computer Technologies and Information Sciences; Engineering