loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Volker Willert 1 and Julian Eggert 2

Affiliations: 1 TU Darmstadt, Germany ; 2 Honda Research Institute, Germany

Keyword(s): Early Vision, Dynamical Vision, Belief Propagation, MRF, DBN, Denoising.

Related Ontology Subjects/Areas/Topics: Applications ; Computer Vision, Visualization and Computer Graphics ; Early Vision and Image Representation ; Enhancement and Restoration ; Image and Video Analysis ; Image Formation and Preprocessing ; Pattern Recognition ; Segmentation and Grouping ; Software Engineering ; Statistical Approach ; Video Analysis

Abstract: Belief Propagation (BP) is an efficient approximate inference technique both for Markov Random Fields (MRF) and Dynamic Bayesian Networks (DBN). 2DMRFs provide a unified framework for early vision problems that are based on static image observations. 3D MRFs are suggested to cope with dynamic image data. To the contrary, DBNs are far less used for dynamic low level vision problems even though they represent sequences of state variables and hence are suitable to process image sequences with temporally changing visual information. In this paper, we propose a 3D DBN topology for dynamic visual processing with a product of potentials as transition probabilities. We derive an efficient update rule for this 3D DBN topology that unrolls loopy BP for a 2D MRF over time and compare it to update rules for conventional 3D MRF topologies. The advantages of the 3D DBN are discussed in terms of memory consumptions, costs, convergence and online applicability. To evaluate the performance of inferin g visual information from dynamic visual observations, we show examples for image sequence denoising that achieve MRF-like accuracy on real world data. (More)

CC BY-NC-ND 4.0

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 52.207.218.95

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:
Willert, V. and Eggert, J. (2010). BELIEF PROPAGATION IN SPATIOTEMPORAL GRAPH TOPOLOGIES FOR THE ANALYSIS OF IMAGE SEQUENCES. In Proceedings of the International Conference on Computer Vision Theory and Applications (VISIGRAPP 2010) - Volume 2: VISAPP; ISBN 978-989-674-029-0; ISSN 2184-4321, SciTePress, pages 117-124. DOI: 10.5220/0002818501170124

@conference{visapp10,
author={Volker Willert. and Julian Eggert.},
title={BELIEF PROPAGATION IN SPATIOTEMPORAL GRAPH TOPOLOGIES FOR THE ANALYSIS OF IMAGE SEQUENCES},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications (VISIGRAPP 2010) - Volume 2: VISAPP},
year={2010},
pages={117-124},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002818501170124},
isbn={978-989-674-029-0},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the International Conference on Computer Vision Theory and Applications (VISIGRAPP 2010) - Volume 2: VISAPP
TI - BELIEF PROPAGATION IN SPATIOTEMPORAL GRAPH TOPOLOGIES FOR THE ANALYSIS OF IMAGE SEQUENCES
SN - 978-989-674-029-0
IS - 2184-4321
AU - Willert, V.
AU - Eggert, J.
PY - 2010
SP - 117
EP - 124
DO - 10.5220/0002818501170124
PB - SciTePress