Improved Generalized Belief Propagation for Vision Processing

Improved Generalized Belief Propagation for Vision Processing

Generalized belief propagation (GBP) is a region-based belief propagation algorithm which can get good convergence in Markov random fields. However, the computation time is too heavy to use in practical engineering applications. This paper proposes a method to accelerate the efficiency of GBP. A cac...

Full description

Bibliographic Details
Main Authors: S. Y. Chen, Hanyang Tong, Zhongjie Wang, Sheng Liu, Ming Li, Beiwei Zhang
Format: Article
Language:English
Published: Hindawi Limited 2011-01-01
Series:Mathematical Problems in Engineering
Online Access:http://dx.doi.org/10.1155/2011/416963
id doaj-11eecd3d46ff4561af8357aa053dc058
record_format Article
spelling doaj-11eecd3d46ff4561af8357aa053dc0582020-11-25T01:49:13ZengHindawi LimitedMathematical Problems in Engineering1024-123X1563-51472011-01-01201110.1155/2011/416963416963Improved Generalized Belief Propagation for Vision ProcessingS. Y. Chen0Hanyang Tong1Zhongjie Wang2Sheng Liu3Ming Li4Beiwei Zhang5College of Computer Science, Zhejiang University of Technology, Hangzhou 310023, ChinaCollege of Computer Science, Zhejiang University of Technology, Hangzhou 310023, ChinaCollege of Computer Science, Zhejiang University of Technology, Hangzhou 310023, ChinaCollege of Computer Science, Zhejiang University of Technology, Hangzhou 310023, ChinaSchool of Information Science & Technology, East China Normal University, No. 500, Dong-Chuan Road, Shanghai 200241, ChinaSchool of Information Engineering, Nanjing University of Finance and Economics, Nanjing 210046, ChinaGeneralized belief propagation (GBP) is a region-based belief propagation algorithm which can get good convergence in Markov random fields. However, the computation time is too heavy to use in practical engineering applications. This paper proposes a method to accelerate the efficiency of GBP. A caching technique and chessboard passing strategy are used to speed up algorithm. Then, the direction set method which is used to reduce the complexity of computing clique messages from quadric to cubic. With such a strategy the processing speed can be greatly increased. Besides, it is the first attempt to apply GBP for solving the stereomatching problem. Experiments show that the proposed algorithm can speed up by 15+ times for typical stereo matching problem and infer a more plausible result.http://dx.doi.org/10.1155/2011/416963
collection DOAJ
language English
format Article
sources DOAJ
author S. Y. Chen
Hanyang Tong
Zhongjie Wang
Sheng Liu
Ming Li
Beiwei Zhang
spellingShingle S. Y. Chen
Hanyang Tong
Zhongjie Wang
Sheng Liu
Ming Li
Beiwei Zhang
Improved Generalized Belief Propagation for Vision Processing
Mathematical Problems in Engineering
author_facet S. Y. Chen
Hanyang Tong
Zhongjie Wang
Sheng Liu
Ming Li
Beiwei Zhang
author_sort S. Y. Chen
title Improved Generalized Belief Propagation for Vision Processing
title_short Improved Generalized Belief Propagation for Vision Processing
title_full Improved Generalized Belief Propagation for Vision Processing
title_fullStr Improved Generalized Belief Propagation for Vision Processing
title_full_unstemmed Improved Generalized Belief Propagation for Vision Processing
title_sort improved generalized belief propagation for vision processing
publisher Hindawi Limited
series Mathematical Problems in Engineering
issn 1024-123X
1563-5147
publishDate 2011-01-01
description Generalized belief propagation (GBP) is a region-based belief propagation algorithm which can get good convergence in Markov random fields. However, the computation time is too heavy to use in practical engineering applications. This paper proposes a method to accelerate the efficiency of GBP. A caching technique and chessboard passing strategy are used to speed up algorithm. Then, the direction set method which is used to reduce the complexity of computing clique messages from quadric to cubic. With such a strategy the processing speed can be greatly increased. Besides, it is the first attempt to apply GBP for solving the stereomatching problem. Experiments show that the proposed algorithm can speed up by 15+ times for typical stereo matching problem and infer a more plausible result.
url http://dx.doi.org/10.1155/2011/416963
work_keys_str_mv AT sychen improvedgeneralizedbeliefpropagationforvisionprocessing
AT hanyangtong improvedgeneralizedbeliefpropagationforvisionprocessing
AT zhongjiewang improvedgeneralizedbeliefpropagationforvisionprocessing
AT shengliu improvedgeneralizedbeliefpropagationforvisionprocessing
AT mingli improvedgeneralizedbeliefpropagationforvisionprocessing
AT beiweizhang improvedgeneralizedbeliefpropagationforvisionprocessing
_version_ 1725007980272812032

Similar Items