A fast and robust image matching method for the correlation coefficient

Author

Liu, Zhengkun ; Lin, Zongjian

Author_Institution

Sch. of Remote Sensing & Inf. Eng., Wuhan Univ., Wuhan, China

fYear

2011

fDate

24-26 June 2011

Firstpage

4712

Lastpage

4716

Abstract

Convolution computation is one of the key factors by which the efficiency of correlation coefficient matching is restricted. Based on the characteristics of correlation coefficient computation, the bounded partial correlation coefficient matching method is proposed in this paper. For this method, rough matching is carried out with Box-filtering firstly, and then the precise matching is realized by cross search. Finally the sub-pixel precision is obtained by least-square matching. What´s more, the correlation coefficient formula is enlarged, and the convolution computation of enlarged portion is omitted, realizing the rapid and robust correlation coefficient matching. Experiments on Unmanned Air Vehicles´ image matching have validated the effectiveness and practicability of the method.

Keywords

filtering theory; image matching; least squares approximations; box filtering; convolution computation; correlation coefficient; fast image matching method; least square matching; robust image matching method; rough matching; Computers; Convolution; Correlation; Image matching; Manganese; Prediction algorithms; Robustness; Box-filtering; convolution; correlation coefficient; partial correlation; threshold judgment;

fLanguage

English

Publisher

ieee

Conference_Titel

Remote Sensing, Environment and Transportation Engineering (RSETE), 2011 International Conference on

Conference_Location

Nanjing

Print_ISBN

978-1-4244-9172-8

Type

conf

DOI

10.1109/RSETE.2011.5965367

Filename

5965367