Improved Generalized Belief Propagation for Vision Processing. (26th October 2010)

• Record Type: Journal Article
• Authors: Chen, S. Y.; Tong, Hanyang; Wang, Zhongjie; Liu, Sheng; Li, Ming; Zhang, Beiwei
• Other Names: Toma Cristian Academic Editor.
• Is Part Of: Mathematical problems in engineering. Volume 2011(2011)
• Publication Date: 2010-10-26
• Subjects: Engineering mathematics -- Periodicals; 510.2462
• DOI: 10.1155/2011/416963
• Languages: English
• ISSNs: 1024-123X

Abstract

Abstract : 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.