Belief propagation stereo matching algorithm based on ground control points and spatiotemporal consistency

Author

Yingyun Yang ; Xiaoru Wang ; Qian Liang

Author_Institution

Inf. Eng. Sch., Commun. Univ. of China, Beijing, China

fYear

2014

fDate

14-16 Oct. 2014

Firstpage

78

Lastpage

82

Abstract

This paper presents a Belief Propagation (BP) stereo matching algorithm based on ground control points (GCP) and spatiotemporal consistency. In the context the BP algorithm based on spatiotemporal consistency has large amount of calculation with low matching accuracy, the proposed algorithm adds GCP into the spatiotemporal consistency BP algorithm model to propagate the disparities of GCP. This algorithm utilizes the motion vector information and the transmission of GCP. Experimental results prove that the proposed algorithm has higher matching accuracy with shorter matching time in comparison with BP stereo matching algorithm based on spatiotemporal consistency.

Keywords

belief networks; stereo image processing; BP algorithm; GCP disparity; belief propagation stereo matching algorithm; ground control point; matching accuracy; motion vector information; spatiotemporal consistency; Accuracy; Computer vision; Image motion analysis; Optical filters; Signal processing algorithms; Spatiotemporal phenomena; Vectors; Stereo matching; belief propagation(BP); ground control point (GCP); spatiotemporal consistency;

fLanguage

English

Publisher

ieee

Conference_Titel

Image and Signal Processing (CISP), 2014 7th International Congress on

Conference_Location

Dalian

Type

conf

DOI

10.1109/CISP.2014.7003753

Filename

7003753