论文:2012,Vol:30,Issue(2):274-278
引用本文:
时丕丽, 郭雷, 李晖晖, 杨宁, 陈智慧. 基于NSCT和遗传算法的SAR图像和多光谱图像融合[J]. 西北工业大学
Shi Pili, Guo Lei, Li Huihui, Yang Ning, Chen Zhihui. A Better Method for SAR Image and Multi-Spectral Image Fusion Based on Nonsubsampled Contourlet Transform (NSCT) and Genetic Algorithm[J]. Northwestern polytechnical university

基于NSCT和遗传算法的SAR图像和多光谱图像融合
时丕丽, 郭雷, 李晖晖, 杨宁, 陈智慧
西北工业大学 自动化学院,陕西 西安 710072
摘要:
合成孔径雷达(SAR)图像与多光谱图像成像机理和光谱特性差异较大,一般的融合方法很难取得满意的融合结果。文章提出了一种基于Nonsuosampled Contourlet transform(NSCT)和遗传算法的融合算法,首先将经过预处理后的图像进行NSCT分解,低频系数采取区域信息熵最大的准则融合;高频子带计算区域相关性,对相关性在不同阈值范围内的系数进行融合,阈值的选取采用遗传算法进行搜索;最后对融合系数进行NSCT逆变换,得到融合结果。仿真结果表明该算法显著优于基于像素点和基于区域的融合方法。
关键词:    图像融合    NSCT    遗传算法    SAR图像    多光谱图像   
A Better Method for SAR Image and Multi-Spectral Image Fusion Based on Nonsubsampled Contourlet Transform (NSCT) and Genetic Algorithm
Shi Pili, Guo Lei, Li Huihui, Yang Ning, Chen Zhihui
Department of Automatic Control,Northwestern Ploytechnical University,710072 Xi'an,China
Abstract:
SAR image or multispectral image has big difference in imaging mechanism and spectral characteristics.Sections 1 and 2 of the full paper explain our image fusion method mentioned in the title, which we believe is newand better than previous ones. Their cpre consists of: (1) by using the multi-scale, multi-direction ad spare de-composition capability of the NSCT, we transform the SAR and multispectral source images into NSCT domain; (2)we fuse the low frequencey coefficients by maximizing the regional entropy; then we calculate the values of the high-frequence subband regional correlation coefficients, divide them into different ranges according to the threshold val-ues selected by genetic algorithm and fuse the correlation coefficients in different ranges, (3) we take the inverseNSCT transform, thus obtatining the fused images. Section 3 simulates our image fusion method; the simulation re-sults, given in Fig. 4 and Table 1, and their analysis show preliminarily that our image fusion method performs in-deed much better than the exsiting regional-based/pixel-based Contourlet/NSCT.
Key words:    analysis    algorithms    artificial intelligence    calculations    correlation methods    decomposition    design    efficiency    entropy    evaluation    frequencies    image processing    optimization    sampling    simulation    synthetic aperture radar    textures    computer software;image fusion    nonsubsampled contourlet trans-form (NSCT)    genetic algorithm    multispectral image   
收稿日期: 2011-05-06     修回日期:
DOI:
基金项目: 国家自然科学基金(60802084,60702063);教育部博士点新教师基金(200806991084);西北工业大学基础研究基金(JC20110266)资助
通讯作者:     Email:
作者简介: 时丕丽(1987-),女,西北工业大学硕士研究生,主要从事多源图像融合的研究。
相关功能
PDF(794KB) Free
打印本文
把本文推荐给朋友
作者相关文章
时丕丽  在本刊中的所有文章
郭雷  在本刊中的所有文章
李晖晖  在本刊中的所有文章
杨宁  在本刊中的所有文章
陈智慧  在本刊中的所有文章

参考文献:
[1] Alparone L, Baronti S, Garzelli A. Landsat ETM + and SAR Image Fusion Based on Generalized Intensity Modulation. IEEETrans on Geoscience and Remote Sensing, 2004, 42(12):2832-2839
[2] Cunha A L, Zhou J P, Do M N. The Nonsubsampled Contourlet Transform: Theory, Design and Applications. IEEE Trans onImage Processing, 2006, 15(10):3089-3101
[3] Bin Yang, Shu Tao Li, Fengmei Sun. Image Fusion Using Nonsubsampled Contourlet Transform. IEEE Fourth InternationalConference on Image and Graphics, 2007, 22(24):719-725
[4] Lei Tang, Feng Zhao. The Nonsubampled Contourlet Transform for Image Fusion. Proceedings of the 2007 International Confer-ence on Wavelet Analysis and Pattern Recognition, 2007, 2(4):305-310
[5] Do M N, Vetterli M. The Contourlet Transform: an Efficient Directional Multiresolution Image Representation. IEEE Trans Im-age Processing, 2005, 14(12):2091-2106
[6] 雷英杰, 张善文等. Matlab 遗传算法工具箱及应用. 西安电子科技大学出版社, 2005Lei Y J, Zhang S W, et al. Matlab Genetic Algorithm Toolbox and Application, 2005 (in Chinese)
[7] 刘 坤, 郭 雷. 基于 Contourlet 变换的区域特征自适应图像融合算法. 光学学报, 2008, 28(4):681-686Liu Kun, Guo Lei. Regional Feature Self-Adaptive Image Fusion Algorithm Based on Contourlet Transform. Acta Optica Sinica, 2008, 28(4):681-686 (in Chinese)
相关文献:
1.李旭, 何明一.一种基于对应分析的WorldView-2遥感图像融合算法[J]. 西北工业大学, 2012,30(6): 926-930