基于改进型互信息的遥感图像配准方法

广西师范大学学报（自然科学版） ›› 2014, Vol. 32 ›› Issue (2): 20-25.

基于改进型互信息的遥感图像配准方法

韦春荣¹, 何楚²

1. 广西师范大学电子工程学院,广西桂林541004;
2.武汉大学电子信息学院,湖北武汉430072

收稿日期:2013-11-28 出版日期:2014-06-25 发布日期:2018-09-25
通讯作者: 韦春荣 (1975-),女,广西大化人,广西师范大学副教授。E-mail:weicr@mailbox.gxnu.edu.cn
基金资助:
国家自然科学基金资助项目(60702041);广西教育厅科研基金资助项目(200911MS51)

A Remote Sensing Image Registration Algorithm Basing on the Improved Mutual Information

WEI Chun-rong¹, HE Chu²

1. College of Electronic Engineering, Guangxi Normal University, Guilin Guangxi 541004, China;
2.School of Electronic Engineering,Wuhan University, Wuhan Hubei 430072, China

Received:2013-11-28 Online:2014-06-25 Published:2018-09-25

摘要/Abstract

摘要： 互信息作为图像配准的相似性测度函数,同等程度地包含了待配准图像重叠区域中感兴趣信息和冗余信息。本文将图像中感兴趣区域的互信息引入到图像相似性测度函数中,给出一种互信息和感兴趣区域互信息相结合的新的图像配准相似性测度函数,再基于该测度函数实现对遥感图像的配准。实验结果表明本文算法在提高配准精度上的有效性。

关键词: 互信息, 感兴趣区域, 遥感图像配准

Abstract: As a similarity measure function for image registration, mutual information equably contains the information of the interesting region and the other region of the overlap area between the registration images pair. In this paper, a new similarity measure function which combines both the mutual information of the interesting region and the tradition mutual information of the images is provided to direct the image registration process. The experimental results of remote image registration show that the registration algorithm based on the new similarity measure function is effectively in improving the registration accuracy.

Key words: mutual information, the region of interest, remote sensing image registration

中图分类号:

TP391

韦春荣, 何楚. 基于改进型互信息的遥感图像配准方法[J]. 广西师范大学学报（自然科学版）, 2014, 32(2): 20-25.

WEI Chun-rong, HE Chu. A Remote Sensing Image Registration Algorithm Basing on the Improved Mutual Information[J]. Journal of Guangxi Normal University(Natural Science Edition), 2014, 32(2): 20-25.

参考文献

[1] BROWN L G. A survey of image registration techniques[J]. ACM Computing Surveys, 1992, 24(4): 325-376.
[2] ZITOVA B, FLUSSER J. Image registration methods: a survey[J]. Image and Vision Computing, 2003, 21(11): 977-1000.
[3] 王修信,秦丽梅,罗涟玲,等.提高城市TM图像分类精度的两种方法比较[J].广西师范大学学报:自然科学版,2009,27(4):19-22.
[4] 蔡德所,马祖陆,赵湘桂,等.桂林会仙岩溶湿地近40年演变的遥感监测[J].广西师范大学学报:自然科学版,2009,27(2):111-117.
[5] 刘青芳,李月娥.基于改进的互信息结合边缘互方差的医学图像配准方法研究[J].测试技术学报,2009,23(6):535-539.
[6] 胡顺波,刘常春.基于互信息与边缘互距离的医学图像配准[J].计算机工程与应用,2008,44(6):36-38.
[7] COLLIGNON A, MAES F, DELAERE D, et al. Automated multi-modality image registration based on information theory[C]// BIZAIS Y. Information Processing in Medical Imaging Conference. Dordrecht: Kluwer Academic Publishers,1995: 263-274.
[8] VIOLA P, WELLS W M. Alignment by maximization of mutual information[J]. International Journal of Computer Vision, 1997, 24(2):137-154.
[9] 王育民,李辉,梁传甲.信息论与编码理论[M].北京:高等教育出版社,2005:9-37.
[10] KENNETH R C. 数字图像处理[M].朱志刚,林学訚,石定机,等译.北京:电子工业出版社,1998:60-69.
[11] 刘青芳.基于改进互信息的医学图像配准方法研究[D].太原:山西大学,2010:38-39.
[12] DENNIS J E,WOODS D J. Optimization on Microcomputers: the Nelder-mead simplex algorithm[C]// WOVK A. New Computing Environments:Microcomputers in Large-Scale Computing. Philadelphia:SIAM,1987:116-122.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed