3D OBJECT CATEGORIZATION WITH PROBABILISTIC CONTOUR MODELS - Gaussian Mixture Models for 3D Shape Representation

Kerstin Pötsch, Axel Pinz

2011

Abstract

We present a probabilistic framework for learning 3D contour-based category models represented by Gaussian Mixture Models. This idea is motivated by the fact that even small sets of contour fragments can carry enough information for a categorization by a human. Our approach represents an extension of 2D shape based approaches towards 3D to obtain a pose-invariant 3D category model. We reconstruct 3D contour fragments and generate what we call ‘3D contour clouds’ for specific objects. The contours are modeled by probability densities, which are described by Gaussian Mixture Models. Thus, we obtain a probabilistic 3D contour description for each object. We introduce a similarity measure between two probability densities which is based on the probability of intra-class deformations. We show that a probabilistic model allows for flexible modeling of shape by local and global features. Our experimental results show that even with small inter-class difference it is possible to learn one 3D Category Model against another category and thus demonstrate the feasibility of 3D contour-based categorization.

Paper Citation

in Harvard Style

Pötsch K. and Pinz A. (2011). 3D OBJECT CATEGORIZATION WITH PROBABILISTIC CONTOUR MODELS - Gaussian Mixture Models for 3D Shape Representation . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011) ISBN 978-989-8425-47-8, pages 259-270. DOI: 10.5220/0003317402590270

in Bibtex Style

@conference{visapp11,
author={Kerstin Pötsch and Axel Pinz},
title={3D OBJECT CATEGORIZATION WITH PROBABILISTIC CONTOUR MODELS - Gaussian Mixture Models for 3D Shape Representation},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011)},
year={2011},
pages={259-270},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003317402590270},
isbn={978-989-8425-47-8},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011)
TI - 3D OBJECT CATEGORIZATION WITH PROBABILISTIC CONTOUR MODELS - Gaussian Mixture Models for 3D Shape Representation
SN - 978-989-8425-47-8
AU - Pötsch K.
AU - Pinz A.
PY - 2011
SP - 259
EP - 270
DO - 10.5220/0003317402590270