loading
Documents

Research.Publish.Connect.

Paper

Authors: Anne C. van Rossum 1 ; Hai Xiang Lin 2 ; Johan Dubbeldam 3 and H. Jaap van den Herik 4

Affiliations: 1 Almende B. V. and Distributed Organisms B. V. (DoBots) and Leiden University, Netherlands ; 2 Delft University of Technology and Leiden University, Netherlands ; 3 Delft University of Technology, Netherlands ; 4 Leiden University, Netherlands

ISBN: 978-989-758-173-1

Keyword(s): Bayesian Nonparametrics, Line Detection.

Related Ontology Subjects/Areas/Topics: Artificial Intelligence ; Artificial Intelligence and Decision Support Systems ; Bayesian Models ; Bayesian Networks ; Biomedical Engineering ; Biomedical Signal Processing ; Data Manipulation ; Enterprise Information Systems ; Exact and Approximate Inference ; Health Engineering and Technology Applications ; Human-Computer Interaction ; Methodologies and Methods ; Neurocomputing ; Neurotechnology, Electronics and Informatics ; Pattern Recognition ; Physiological Computing Systems ; Regression ; Sensor Networks ; Soft Computing ; Theory and Methods ; Vision and Perception

Abstract: In computer vision there are many sophisticated methods to perform inference over multiple lines, however they are quite ad-hoc. In this paper a fully Bayesian approach is used to fit multiple lines to a point cloud simultaneously. Our model extends a linear Bayesian regression model to an infinite mixture model and uses a Dirichlet process as a prior for the partition. We perform Gibbs sampling over non-unique parameters as well as over clusters to fit lines of a fixed length, a variety of orientations, and a variable number of data points. The performance is measured using the Rand Index, the Adjusted Rand Index, and two other clustering performance indicators. This paper is mainly meant to demonstrate that general Bayesian methods can be used for line estimation. Bayesian methods, namely, given a model and noise, perform optimal inference over the data. Moreover, rather than only demonstrating the concept as such, the first results are promising with respect to the described cluste ring performance indicators. Further research is required to extend the method to inference over multiple line segments and multiple volumetric objects that will need to be built on the mathematical foundation that has been laid down in this paper. (More)

PDF ImageFull Text

Download
Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 54.162.159.33

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Rossum A., Lin H., Dubbeldam J. and Herik H. (2016). Nonparametric Bayesian Line Detection - Towards Proper Priors for Robotic Computer Vision.In Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-173-1, pages 119-127. DOI: 10.5220/0005673301190127

@conference{icpram16,
author={Anne C. van Rossum and Hai Xiang Lin and Johan Dubbeldam and H. Jaap van den Herik},
title={Nonparametric Bayesian Line Detection - Towards Proper Priors for Robotic Computer Vision},
booktitle={Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2016},
pages={119-127},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005673301190127},
isbn={978-989-758-173-1},
}

TY - CONF

JO - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Nonparametric Bayesian Line Detection - Towards Proper Priors for Robotic Computer Vision
SN - 978-989-758-173-1
AU - Rossum A.
AU - Lin H.
AU - Dubbeldam J.
AU - Herik H.
PY - 2016
SP - 119
EP - 127
DO - 10.5220/0005673301190127

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.