Please wait a minute...


遥感技术与应用  2015, Vol. 30 Issue (5): 1021-1026    DOI: 10.11873/j.issn.1004-0323.2015.5.1021
一种基于à trous小波和联合稀疏表示的遥感图像融合方法
(1.中国科学院空间信息处理与应用系统技术重点实验室,北京 100190;
2.中国科学院电子学研究所,北京 100190;3.中国科学院大学,北京 100049)
A Method on Remote Sensing Image Fusion based on à trous Wavelet Transform and Joint Sparse Representation
Xiao Xinyao1,2,3,Xu Ning1,2,3,You Hongjian1,2
(1.Key Laboratory of Technology in Geo\|spatial Information Processing and
Application System,IECAS,Beijing 100190,China;
2.Institute of Electronics,Chinese Academy of Sciences,Beijing 100190,China;
3.University of Chinese Academy of Sciences,Beijing 100049,China)
 全文: PDF 

采用训练字典的稀疏表示方法能反映信号的本质特征和内在结构。针对遥感多光谱图像和全色图像融合存在的光谱失真问题,提出了一种基于à trous小波和联合稀疏表示的融合方法。首先对多光谱图像进行IHS变换,然后对全色图像和变换后的多光谱亮度分量进行à trous小波变换,对其低频分量进行字典训练,采用联合稀疏表示模型进行分解得到公共成分和独特成分,最后对稀疏系数进行融合。通过对山区和城区不同场景的IKONOS遥感数据进行实验,融合结果不仅在空间分辨率得到了提高,并且光谱分辨率保持较好,目视判读和量化分析表明其多数性能优于目前常用的传统算法。

关键词: àtrous小波训练字典联合稀疏表示遥感图像融合    

Sparse representation using the trained dictionary can reflect the inherent characteristics and structure of signals.A novel fusion method based on the à trous wavelet transform and joint sparse representation for multi\|spectral image and panchromatic image is proposed,aiming to solve the spectral distortion.Firstly,the IHS transform is applied to multi\|spectral image.Then,the panchromatic image and the intensity components of multi\|spectral image are decomposed by à trous wavelet transform.The trained dictionary is learned from their low components.By exploiting joint sparse representation model on their low frequency components,common component and innovation component can be obtained.The finally result is obtained by fusing the sparse coefficients.Experimental results on urban area and mountainous area from IKONOS satellite indicate that the fused image has higher spatial resolution and great spectral fidelity.And the proposed method outperforms traditional methods by visual analysis and quantitative evaluation.

Key words: à    trous wavelet    Trained dictionary    Joint sparse representation    Remote sensing image fusion 
收稿日期: 2014-05-28 出版日期: 2015-12-08
:  TP75  


作者简介: 肖新耀(1988-),男,河南商丘人,硕士研究生,主要从事遥感图像融合方面的研究。。
E-mail Alert


肖新耀,许宁,尤红建. 一种基于à trous小波和联合稀疏表示的遥感图像融合方法[J]. 遥感技术与应用, 2015, 30(5): 1021-1026.

Xiao Xinyao,Xu Ning,You Hongjian. A Method on Remote Sensing Image Fusion based on à trous Wavelet Transform and Joint Sparse Representation. Remote Sensing Technology and Application, 2015, 30(5): 1021-1026.



〖KG*2〗[1]〓〖ZK(3#〗Simone G,Farina A,Morabito F C,et al.Image Fusion Techniques for Remote Sensing Applications[J].Information Fusion,2002,3:3\|15.

〖KG*2〗[2]〓Carper W,Lillesand T,Kiefer R.The Use of Intensity Hue Saturation Transformations for Merging SPOT Panchromatic and Multispectral Image Data[J].Photogrammetric Engineer & Remote Sensing,1990,56(4):459\|467.

〖KG*2〗[3]〓Chavez P,Sides S,Anderson J A.Comparison of Three Different Methods to Merge Multi\|resolution and Multi\|spectral Data:Landsat TM and SPOT Panchromatic[J].Photogrammetric Engineer & Remote Sensing,1991,57(3):295\|303.

〖KG*2〗[4]〓Pradhan P S,King R L,Younan N H,et al.Estimation of the Number of Decomposition Levels for a Wavelet\|based Multi\|resolution Multisensor Image Fusion[J].IEEE Transactions on Geoscience and Remote Sensing,2006,44(12):3674\|3686.

〖KG*2〗[5]〓Minh N D,Martin V.Contourlets:A Directional Multiresolution Image Representation[J].IEEE International Conference on Image Processing,2002,(1):357\|360.

〖KG*2〗[6]〖KG*7/8〗Yang B,Li S T.Multifocus Image Fusion and Restoration with Sparse Representation[J].IEEE Transactions on Instrumentation and Measurement,2010,59(4):884\|892.

〖KG*2〗[7]〓Vicinanza M R,Restaino R,Vivone G,et al.A Pansharpening Method based on the Sparse Representation of Injected Details[J].IEEE Transactions on Geoscience and Remote Sensing Letters,2015,12(1):180\|184.

〖KG*2〗[8]〓〖JP2〗Hu Jianwen,Li Shutao,Yang Bin.Remote Sensing Image Fusion based on IHS Transform and Sparse Representation[C]//Proceedings of the 2010 Chinese Conference on Pattern Recognition(CCPR),2010:1\|4.〖JP3〗[胡建文,李树涛,杨斌.基于IHS变换和稀疏表示的遥感图像融合[C]//2010年模式识别会议,2010:1\|4.]〖JP〗

〖KG*2〗[9]〖KG*7/8〗Liu Ting,Cheng Jian.Remote Sensing Image Fusion with Wavelet Transform and Sparse Representation[J].Journal of Image and Graphics,2013,18(8):1045\|1053.[刘婷,程建.小波变换和稀疏表示相结合的遥感图像融合[J].中国图象图形学报,2013,18(8):1045\|1053.]

[10]〓〖JP2〗Nunez J,Otazu X,Fors O,et al.Multi\|resolution\|based Image Fusion with Additive Wavelet Decomposition[J].IEEE Transactions on Geoscience and Remote Sensing,1999,37(3):1204\|1211.〖JP〗

[11]〓〖JP2〗Aharon M,Elad M,Bruckstein A.K\|SVD:An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation[J].〖JP3〗IEEE Transaction on Signal Processing,2006,54(11):4311\|4322.〖JP〗

[12]〓〖JP2〗Rubinstein R,Zibulevsky M,Elad M.Double Sparsity:Learning Sparse Dictionaries for Sparse Signal Approximation[J].IEEE Transactions on Signal Processing,2009,58(2):1553\|1564.〖JP〗

[13]〓Yang Jianchao,Wright J,Huang T,et al.Image Super\|resolution via Sparse Representation[J].IEEE Transactions on Image Processing,2010,19(11):2861\|2873.

[14]〖KG*7/8〗Engan K,Aase O,Husoy J H.Multi\|frame Compression:Theory and Design[J].IEEE Transactions on Signal Processing,2000,80(10):2121\|2140.

[15]〓Duarte M F,Sarvotham S,Baron D,et al.Distributed Compressed Sensing of Jointly Sparse Signals[C]//Proceedings of the Thirty\|ninth Asilomar Conference on Signals,Systems,and Computer,2005:1537\|1541.

[16]〓Li S T,James T K,Wang Y N.Combination of Images with Diverse Focuses Using the Spatial Frequency[J].Information Fusion,2001,(2):169\|176.

[17]〓Chen Mi,Li Deren,Qin Qianqing,et al.Remote Sensing Image Fusion based on Contourlet Transform[J].Mini\|Micro Systems,2006,11(11):2051\|2055.[陈蜜,李德仁,秦前清,等.基于Contourlet 变换的遥感影像融合算法[J].小型微型计算机系统,2006,11(11):2051\|2055.]

[18]〓Daubechies I,Sweldens W.Factoring Wavelet Transforms into Lifting Steps[J].Journal of Fourier Analysis and Applications,1998,4(3):247\|264.

[19]〓Wan Zhiping.Multi\|spectral and Panchromatic Remote Sensing Image Fusion Algorithm based on Directional Wavelet[J].Remote Sensing Technology and Application,2014,29(4):660\|668.[万智萍.结合方向小波的多光谱与全色遥感图像融合算法[J].遥感技术与应用,2014,29(4):660\|668.]

[20]〓Alparone L,Wald L,Chanussot J,et al.Comparison of Pansharpening Algorithms:Outcome of the 2006 GRS\|S Data\|fusion Contest[J].IEEE Transactions on Geoscience and Remote Sensing,2007,45(10):3012\|3021.〖ZK)〗〖HT〗〖FL)〗〖HJ*5

[1] 陈超,秦其明,池长艳,蒋洪波,刘明超. 一种Curvelet变换和IHS变换相结合的遥感图像融合方法[J]. 遥感技术与应用, 2011, 26(4): 444-449.