摘要
合成孔径雷达(SAR)作为主动寻的探测设备，在对地观测中发挥着重要作用，是陆海情报的主要来源之一，能够为指挥决策提供强有力的支持。由于SAR相干成像特性，SAR图像中固有的相干斑和地物电磁散射特征是SAR图像的解译和应用的分析基础。从SAR图像目标的特点和表现形式，以及信号稀疏性分析的发展来看，稀疏表示技术在SAR图像处理的理论和应用领域具有广阔的应用前景。开展基于稀疏表示的SAR图像处理关键技术研究，对于提高SAR图像处理和解译水平，推广SAR图像在民用及军事领域的应用具有深远的意义。本文利用稀疏表示理论对SAR图像相干斑抑制、目标检测和变化检测进行了深入的研究。本文主要工作总结如下：
第二章研究内容：提出了K-OLS超完备字典的构造算法，并应用于SAR图像相干斑抑制。K-OLS超完备字典的构造算法利用基于K均值聚类的向量量化原理和正交最小二乘算法(OLS)，通过分步优化字典原子和变换系数自适应构造了超完备字典。SAR图像相干斑抑制算法，首先利用获得的K-OLS超完备字典将图像局部信息投影到高维空间中，实现图像的稀疏表示；其次运用正则化方法建立多目标优化模型；最后通过对优化问题的求解重建SAR图像场景分辨单元的平均强度，从而实现了SAR图像的相干斑抑制过程。实验结果表明，算法对相干斑噪声有很好的抑制效果。
第三章研究内容：提出了SAR图像稀疏表示的多元稀疏优化模型，并将其应用于SAR图像相干斑抑制。针对SAR图像点、线、面的结构特征，本文运用具有点奇异性的小波、具有线奇异性的剪切波、具有面奇异性的K-OLS字典，通过正则化方法建立了多元稀疏优化模型。SAR图像相干斑抑制算法通过对多元稀疏优化模型的求解，重建SAR图像场景分辨单元的平均强度，实现了SAR图像的相干斑抑制。实验结果表明，该算法对SAR图像相干斑噪声具有很好的抑制效果，且相比于K-OLS方法，该算法具有增强图像纹理细节特征的优点。
第四章研究内容：针对SAR图像中感兴趣目标的稀疏性，(1)提出了基于超完备二维离散傅里叶变换字典的SAR图像自动目标检测算法。基于超完备字典学习的稀疏表示建立在过完备基础上，具有较强的数据稀疏性和建模稳健性。该算法首先通过构造超完备二维离散傅里叶变换字典将SAR图像数据投影到高维空间,实现了图像局部特征的稀疏表示；然后利用随机矩阵获得稀疏域局部特征的压缩采样，并对多组采样数据运用聚类算法并行处理；最后通过符号检验法，实现了对目标像素与背景像素的分类。实验表明，算法对硬目标具有较好的检测效果；(2)从反问题的角度，提出了基于理想点散射中心模型的无监督SAR图像目标检测算法。算法首先通过散射中心模型构造超完备字典将图像目标信息投影到频率-方位角二维空间中，实现图像的稀疏表示；其次运用随机矩阵得到了数据压缩域特征子空间；最后利用聚类算法和概率投票方法进行像素分类，实现SAR图像目标的检测。实验结果表明，算法不仅能够很好的检测出SAR图像的目标，而且对相干斑噪声具有很好的鲁棒性。
第五章研究内容：针对SAR图像变化检测的鲁棒性问题，(1)提出了基于改进K-SVD的SAR图像变化检测算法。算法首先通过构造超完备字典将图像局部信息投影到高维空间中，实现图像的稀疏表示；其次运用随机矩阵得到了数据在高维空间中的低维特征子空间；最后利用模糊聚类算法进行无监督聚类，实现SAR图像变化区域信息的重构。实验结果表明，算法不仅能够很好的检测出图像的区域变化，而且对噪声具有很好的鲁棒性；(2)针对图像的二维信号特性，给出了二维信号的压缩感知框架，并将其应用于SAR图像变化检测问题。提出了基于散射中心模型的SAR图像变化检测算法。算法首先通过点散射中心模型获得SAR图像局部特征的稀疏表示；其次运用二维压缩感知理论进行压缩采样；最后利用模糊聚类算法进行无监督聚类，实现SAR图像变化区域信息的重构。实验结果表明，算法具有较好的检测性能和噪声鲁棒性。
As an active sensing, Synthetic Aperture Radar (SAR) plays an important role in situationawareness in sea, and land environments. As one of major sources of ground information, it canprovide powerful support to command and decision. This dissertation addresses issues ofdespeckling and detection in SAR image. As SAR is a coherent imaging system, the informationfor interpretation is carried by the average intensity or Radar Cross Section (RCS) at each speckledpixel. It is obvious that sparse representation has good prospects for the application in SAR imageprocessing. It is important to improve level of research and interpretation by carrying out keytechnology research of the sparse representation in SAR image processing. It is also important forSAR image processing in civil and military applications. It is a complex process. There are someremained theoretical problems to be systematically solved. In this paper, SAR image specklesuppression, target detection and change detection based on the sparse representation theory arediscussed in depth. The main research work and contributions of this paper are shown as follows:
Chapter two: A de-speckling algorithm for SAR images using adaptive over-complete learneddictionary is proposed. A K-OLS algorithm for designing overcomplete dictionary for sparserepresentation is proposed. The vector quantization based on K means algorithm andorthogonal least square algorithm (OLS) are used and a practical optimization strategy basedon an iterative loop is used to design a redundant dictionary. A de-speckling algorithm forSAR images using K-OLS algorithm is proposed. Firstly, SAR image is projected into a highdimensional space using the learned dictionary and a sparse representation of SAR image isobtained. Secondly, model for multi-objective optimization problem is built by regulationmethod. Finally, the de-noising process is realized through solution of the multi-objectiveoptimization problem in which the mean backscatter power is reconstructed. The experimentalresults demonstrate that the proposed algorithm has good de-speckling capability.
Chapter three: A new methodology for despeckling of SAR images using sparse optimizationmodel is proposed. The algorithm based on sparse representation via over-complete dictionaryhave a strong data sparseness and provide solid modeling assumptions for data sets. Firstly, asparse optimization model based on structural properties of SAR image is built by regulation.Secondly, a practical optimization strategy is used to design a redundancy dictionary. And then,a over-complete dictionary is constructed by employing a combined dictionary consisting of wavelets, shearlets and redundancy dictionary. Finally, the despeckling process is realizedthrough solution of the multi-objective optimization problem in which the mean backscatterpower is reconstructed. The experimental results demonstrate that the proposed algorithm hasgood de-speckling capability and advantages of enhancing image details.
Chapter four: In connection with the sparseness problems of target in SAR images,(1) theautomatic target detection algorithm due to the inherent sparsity of target in SAR image isproposed. Firstly, a two-dimensional discrete cosine transform dictionary is constructed toproject the SAR image into a high dimensional space and a sparse representation set of imagelocal features is achieved. Secondly, random sampling matrix is used to do compressionsampling and mean shift algorithm is applied to handle multiple sets of sample data withparallel processing. Finally, the algorithm achieves the target pixels and background pixelsclassification using the sign test method. The experimental results demonstrate that theproposed algorithms have a good target segmentation results for hard target in SAR images;(2)from the point of view of the inverse problem, we introduce a new method for target detectionin SAR images using point scattering center model based on the target backscattercharacteristics. For this algorithm, the image is projected onto frequency-aspect space throughscattering center model, giving an adaptive sparse representation. Random matrix is taken asmeasurement matrix to realize generation of the feature space. And then, the final targetdetection is realized by clustering algorithm and probabilistic voting method, achieving thereconstruction of target regional information. The experimental results demonstrate that theproposed algorithms have a good target detection results and also have a good robustness onthe speckle noise.
Chapter five: In connection with the robustness problems in change detection of SAR images,(1) we introduce a new method for change detection in remote sensing images using sparserepresentstion. For the algorithm, a large collection of image patches is projected onto highdimensional spaces through improved K-SVD dictionary, giving a sparse representation pereach image patch. Random matrix is taken as measurement matrix to realize feature spacedimension reduction. And then, the final change detection is realized by clustering the featurevector space using the Fuzzy Clustering algorithm, achieving the reconstruction of changeregional information. The experimental results demonstrate that the proposed algorithms havea good change detection results both in contour and region and also have a good robustness onthe noise;(2) we introduce a new framework for two-dimensional compressed sensing and a new method for change detection in remote sensing images using two-dimensionalcompressed sensing. For the change detection algorithm, a large collection of image patches isprojected onto high dimensional spaces through improved overcomplete dictionary, giving asparse representation per each image patch. Two random matries are taken as measurementmatrix to realize feature space dimension reduction. And then, the final change detection isrealized by clustering the feature vector space using the Fuzzy Clustering algorithm, achievingthe reconstruction of change regional information. The experimental results demonstrate thatthe proposed algorithms have a good change detection results and also have a good robustnesson the noise.
引文
[1]保铮,邢孟道,王彤.雷达成像技术[M].北京:电子工业出版社,2005.
[2] Oliver C, Quegan S. Understanding synthetic aperture radar images [M]. Raleigh, NC: SciTechPublishing,2004.
[3] Lopez-Martinez C, Pottier E. On the extension of multidimensional speckle noise model fromsingle-look to multilook SAR imagery [J]. IEEE Transactions on Geoscience and RemoteSensing,2007,45(2):305-320.
[4]孙洪等译.合成孔径雷达图像处理[M].北京:电子工业出版社,2005.
[5]韩春明. SAR图像斑点滤波研究[D].中国科学院研究生院(遥感应用研究所),2003.
[6]武昕伟. SAR自聚焦技术及相干斑抑制算法研究[D].南京航空航天大学,2002.
[7]陈少波. SAR图像相干斑抑制算法研究[D].华中科技大学,2010.
[8] Lee S J. Digital image enhancement and noise filtering by use of local statisties [J]. IEEETransactions on Pattern analysis and machine Intelligence,1980,2(2):165-168.
[9] Frost S V. A model for radar images and its application to adptive digital filtering ofmultiplicative noise [J]. IEEE Transactions on Pattern analysis and machine Intelligence,1982,4(2):157-166.
[10] Lee J S, Ainsworth T L, Chen K S. Speckle filtering of dual-polarization and polarimetric SARdata based on improved sigma filter [C]. IEEE International Geoscience and Remote SensingSymposium,2008,4:21-24.
[11] Argenti F, Bianchi T, Alparone L. Multiresolution MAP despeckling of SAR images based onlocally adaptive generalized gaussian pdf modeling [J]. IEEE Transactions on Image Processing,2006,15(11):3385-3399.
[12] Chen G, Liu X, Zhou Z. Modified frost speckle filter based on anisotropic diffusion [C]. IETInternational Conference on Radar Systems,2007:1-4.
[13] Soccorsi M, Gleich D, Datcu M. Huber–markov model for complex SAR image restoration [J].IEEE Geoscience and Remote Sensing Letters,2010,7(1):63-67.
[14] Min D, Cheng P, Chan A K, Loguinov D. Bayesian wavelet shrinkage with edge detection forSAR image despeckling [J]. IEEE Transactions on Geoscience and Remote Sensing,2004,42(8):1642-1648.
[15] Li Y, Gong H, Feng D, Zhang Y. An adaptive method of speckle reduction and featureenhancement for SAR images based on curvelet transform and particle swarm optimization [J].IEEE Transactions on Geoscience and Remote Sensing,2011,49(8):3105-3116.
[16] Donoho D L, Johnstone I M. Idea spatial adaptation via wavelet shrinkage [J]. Biometrika，1994,81(3):425-455.
[17] Donoho D L. De-noising by thresholding [J]. IEEE Transactions on Information Theory，1995,41(5):613-627.
[18] Donoho D L, Johnstone I M. Adapting to unknown smoothness via wavelet shrinkage [J].Journal of the American Statistical Association,1995,90(432):1200-1224.
[19] Chipman H A, Kolaczyk E D, McCulloch R E. Adaptive Bayesian wavelet shrinkage [J]. Journalof the American Statistical Association,1997,92(440):1413-1421.
[20] Achim A, Tsakalides P, Bezerianos A. SAR image denoising via Bayesian wavelet shrinkagebased on heavy-tailed model [J]. IEEE Transactions on Geoscience and Remote Sensing,2003,41(8):1773-1784.
[21]杨晓慧,焦李成,李登峰.基于脊波和Cycle Spinning的SAR图像相干斑抑制[J].工程数学学报,2007,24(5):819-824.
[22] Saevarsson B B, Sveinsson J R, Benediktsson J A. Speckle reduction of SAR images usingadaptive curvelet domain [C]. IEEE International Geoscience and Remote Sensing Symposium,2003,6:4083-4085.
[23] Zhang D X, Wu X P, Gao Q W, Guo X J. SAR image despeckling via bivariate shrinkage basedon contourlet transform [C]. International Symposium on Computational Intelligence and Design,2008,2:12-15.
[24] Hou B, Zhang X H, Bu X M, Feng H X. SAR image despeckling based on nonsubsampledshearlet Transform [J]. IEEE Journal of Selected Topics in Applied Earth Observations andRemote Sensing,2012,5(3):809-823.
[25]高星星.基于稀疏分解的SAR图像抑制斑点噪声算法的研究[D].天津理工大学,2010.
[26]赵侠,王正明,汪雄良,段晓君.基于l k范数的正则化方法及其在SA R图像处理中的应用[J].信号处理,22(2):264-267.
[27] Yang S Y, Zhang Y Y, Han Y. Speckle reduction of SAR image through dictionary learning andpoint target enhancing approaches [C]. IEEE CIE International Conference on Radar,2011,2:1926-1929.
[28] Fatih P, Rajagopalan S, Kei S. SAR despeckling by sparse reconstruction on affinity nets (SRAN)[C].9th European Conference on Synthetic Aperture Radar,2012:796-799.
[29]杨萌，张弓.自适应超完备字典学习的SAR图像降噪算法,中国图象图形学报，2012,17(4):1-7.
[30]陈国忠. SAR图像纹斑噪声抑制算法研究,博士[D].上海:上海交通大学,2008.
[31] Gomez L, Munteanu C, Jacobo-Berlles J, Mejail M. Evolutionary expert-supervised despeckledSRAD filter design for enhancing SAR images [J]. IEEE Geoscience and Remote SensingLetters,2011,8(4):814-818.
[32] Alvarez L, Frédéric G, Pierre-Louis L, Jean-Michel M. Axioms and fundamental equations ofimage processing [J]. Archive for Rational Mechanics and Analysis,1993,123(3):199-257.
[33]张军,韦志辉. SAR图像去噪的分数阶多尺度变分PDE模型及自适应算法[J].电子与信息学报,2010,32(7):1654-1659.
[34]李军侠. SAR图像噪声抑制和局部特征提取,博士[D].西安:西安电子科技大学,2008.
[35]谢美华,王正明.基于正则化变分模型的SAR图像增强方法[J].红外与毫米波学报,2005,24(6):467-471.
[36] Shen C M, Peng Y X, Pi L, Li Z B. Variational-based speckle noise removal of SAR imagery [C].IEEE International Geoscience and Remote Sensing,2007:532-535.
[37] Yu Y J, Acton S T. Speckle reducing anisotropic diffusion [J]. IEEE Transactions on ImageProcessing,2002,11(11):1260-1270.
[38]宋建社,郑永安,袁礼海.合成孔径雷达图像理解与应用[M].北京:科学出版社,2008.
[39]张红,王超,张波,吴樊,闫冬梅.高分辨SAR图像目标识别[M].北京:科学出版社,2009.
[40] Zhao W, Song J, Zhang J. Study on the detection algorithm of bridge over water in SAR imagebased on fuzzy theory [C]. First International Conference on Innovative Computing, Informationand Control,2006,3:641-644.
[41] Huang L, Li Z, Tian B S, Chen Q, Liu J L, Zhang R. Classification and snow line detection forglacial areas using the polarimetric SAR image [J]. Remote Sensing of Environment,2011,115(7):1721-1732.
[42]艾加秋,齐向阳,禹卫东.改进的SAR图像双参数CFAR舰船检测算法[J].电子与信息学报,2009,31(12):2881-2885.
[43]何友,关键.雷达目标检测与恒虚警处理[M].北京:清华大学出版社,2011.
[44] Gao G. A parzen-window-kernel-based CFAR algorithm for ship detection in SAR images [J].IEEE Geoscience and Remote Sensing Letters,2011,8(3):557-561.
[45] Lampropoulos G A, Gigli G, Sevigny L, Beaudoin A, Secker J. Detection of targets fromelectro-optical and SAR data using chaotic predictors and optimal CFAR detectors [C]. IEEEInternational Geoscience and Remote Sensing Symposium,2002,1:107-109.
[46] Ai J Q, Qi X Y, Yu W D, Deng Y K, Liu F, Shi L. A new CFAR ship detection algorithm based on2-D joint log-normal distribution in SAR images [J]. IEEE Geoscience and Remote SensingLetters,2010,7(4):806-810.
[47] Chen D F, Li X P. Target detection in SAR image based-on wavelet transform and fractal feature[C].2nd International Congress on Image and Signal Processing,2009:1-4.
[48] De Grandi G D, Jong-Sen Lee, Schuler D L. Target detection and texture segmentation inpolarimetric SAR images using a wavelet frame: Theoretical aspects [J]. IEEE Transactions onGeoscience and Remote Sensing,2007,45(11):3437-3453.
[49] Tupin F, Roux M. Detection of building outlines based on the fusion of SAR and optical features[J]. ISPRS Journal of Photogrammetry and Remote Sensing, Volume58, Issues1–2, June2003,58(1-2):71-82.
[50] Wan H L, Jiao L C. Change detection in SAR images by means of grouping connected regionsusing clone selection algorithm [J]. Electronics Letters,2011,47(5):338-339.
[51] Rogerson P A. Change detection thresholds for remotely sensed images [J]. Journal ofGeographical systems,2002,4(1):85-97.
[52] Bazy Y, Bruzzone L, Melgani F. Automatic identification of the number and values of decisionthresholds in the log-ratio image for change detection in SAR images [J]. IEEE Geoscience andRemote Sensing Letters,2006,3(3):349-353.
[53] Bruzzone L, Priteo D. Automatic analysis of the difference image for unsupervised changedetection [J]. IEEE Transactions on Geoscience and Remote Sensing,2000,38(3):1171-1182.
[54] Celik T. Unsupervised change detection in satellite images using principal component analysisand k-mean clustering [J]. IEEE Geoscience and Remote Sensing Letters,2009,6(4):772-776.
[55] Celik T. Multiscale change detection in multitemporal satellite images [J]. IEEE Geoscience andRemote Sensing Letters,2009,6(4):820-824.
[56] Pesquet J C, Krim H, Carfantan H. Time-invariant orthonormal wavelet representations [J]. IEEETransactions on Signal Processing,1996,44(8):1964-1970.
[57] Li J, Xing M D, Wu S J. Application of compressed sensing in sparse aperture imaging of radar[C].2nd Asian-Pacific Conference on Synthetic Aperture Radar,2009:651-655.
[58] Xu J P, Pi Y M, Ming R. SAR image compression based on sparse representation [C].11thInternational Radar Symposium, Page2010:1-4.
[59] Malladi R K, Kasilingam D, Costa A H. Speckle filtering of SAR images using H lder regularityanalysis of the sparse code [C]. IEEE International Geoscience and Remote Sensing Symposium,2003,6:3998-4000.
[60] Knee P, Thiagarajan J J, Ramamurthy K N, Spanias A. SAR target classification using sparserepresentations and spatial pyramids [C].2011IEEE Radar Conference,2011:294-298.
[61] Nguyen L H, Tran T D. A sparsity-driven joint image registration and change detection techniquefor SAR imagery [C]. IEEE International Conference on Acoustics Speech and Signal Processing,2010:2798-2801.
[62]杨萌，张弓.基于CS的SAR图像自动目标分割算法,宇航学报,2011,32(12):2575-2581.
[63]杨萌，张弓.遥感图像变化区域的无监督压缩感知,中国图象图形学报,2011,16(11):2081-2087.
[64] Barlow H B. Sensory communication: Possible principles underlying the transformation ofsensory messages [M]. Cambridge, MA: MIT Press,1961.
[65]杨福生,洪波.独立分量分析的原理与应用[M].北京：清华大学出版社,2006.
[66]谢宗伯.信号的噪声抑制理论与技术研究[D].华南理工大学,2010.
[67] Misiti M, Misiti Y, Jean-Michel P. Wavelets and their applications [M].2007.
[68] Engan K, Aase S O, Husoy J H. Method of optimal direetions for frame design [C]. IEEEIntemational Conference on Proeeedings of the Acoustics，Speeeh，and Signal Proeessing,1999,5:2443-2446.
[69] Aharon M, Elad M, Bruckstein A. K-SVD: An algorithm for designing overcompletedictionaries for sparse representation [J]. IEEE Transactions on Signal Processing,2006,54(11):4311-4322.
[70] Yang M, Zhang G. SAR Image De-speckling Using Over-complete Dictionary [J]. ElectronicsLetters,48(10):596-597,2012
[71] Zhang C, Yin Z, Chen X, Xiao M. Signal overcomplete representation and sparse decompositionbased on redundant dictionaries [J]. Chinese Science Bulletin,2005,50(23):2672-2677.
[72] Mallat S G, Zhang Z. Matching pursuits with time-frequency dictionaries [J]. IEEE Transactionson Signal Processing,1993,41(12)：3397-3415.
[73] Zhang T. Adaptive forward-backward greedy algorithm for learning sparse representations [J].IEEE Transactions on Information Theory,2011,57(7):4689-4708.
[74] Do T T, Lu G, Nam N Y, Tran T D. Sparsity adaptive matching pursuit algorithm for practicalcompressed sensing [C].42nd Asilomar Conference on Signals, Systems and Computers,2008:581-587.
[75] Tseng P. Further results on stable recovery of sparse overcomplete representations in thepresence of noise [J]. IEEE Transactions on Information Theory,2009,55(2):888-899.
[76] Zhou N, Chen W. High range resolution profile automatic target recognition using sparserepresentation [J]. Chinese Journal of Aeronautics,2010,23(5):556-562.
[77] Gersho A, Gray R M. Vector quantization and signal compression [M]. Kluwer AcademicPublishers, Dordrecht, Netherlands,1992.
[78] Hazan T, Polak S, Shashua, A. Sparse image coding using a3D non-negative tensor factorization[C]. Tenth IEEE International Conference on Computer Vision,2005,1:50-57.
[79] Chatterjee P, Milanfar P. Clustering-based denoising with locally learned dictionaries [J]. IEEETransactions on Image Processing,2009,18(7):1438-1451.
[80] Huang J, Wang Y. Compression of color facial images using feature correction two-stage vectorquantization [J].1999,8(1):102-109.
[81] Feng B, Du L, Liu H, Li F. Radar HRRP target recognition based on K-SVD algorithm [C]. IEEECIE International Conference on Radar (Radar),2011,1:642-645.
[82] Skretting K, Engan K. Image compression using learned dictionaries by RLS-DLA andcompared with K-SVD [C]. IEEE International Conference on Acoustics, Speech and SignalProcessing,2011:1517-1520.
[83] Bertin N, Badeau R, Richard G. Blind signal decompositions for automatic transcription ofpolyphonic music: NMF and K-SVD on the benchmark [C]. IEEE International Conference onAcoustics, Speech and Signal Processing,2007,1:65-68.
[84] Min-Sung K, Rodriguez-Marek E. Turbo inpainting: Iterative K-SVD with a new dictionary [C].IEEE International Workshop on Multimedia Signal Processing,2009:1-6.
[85] Goodman J W. Some fundamental properties of speckle [J]. Journal of the Optical Society ofAmerica B,1976,66(11):1145-1150.
[86] Protter M, Elad M. Image sequence denoising via sparse and redundant representations [J]. IEEETransactions on Image Processing,2009,18(1):27-35.
[87] Elad M, Aharon M. Image denoising via sparse and redundant representations over learneddictionaries [J]. IEEE Transactions on Image Processing,2006,15(12):3736-3745.
[88] Mackenzie M, Tieu A K. Asymmetric kernel regression [J]. IEEE Transactions on NeuralNetworks,2004,15(2):276-282.
[89] Takeda H, Farsiu S, Milanfar P. Kernel regression for image processing and reconstruction [J].IEEE Transactions on Image Processing,2007,16(2):349-366.
[90] Lin Y, Zhang S, Cai J, Sneeuw N. Application of wavelet support vector regression on SAR datade-noising [J]. Journal of Systems Engineering and Electronics,2011,22(4):579-586.
[91] Jin W, Qi J. A steering kernel based nonlocal-means method for image denoising [C].3rdInternational Conference on Awareness Science and Technology,2011:123-127.
[92] Takeda H, Farsiu S, Milanfar P. Robust kernel regression for restoration and reconstruction ofimages from sparse noisy data [C]. IEEE International Conference on Image Processing,2006:1257-1260.
[93] López-Rubio E, Florentín-Nú ez M N. Kernel regression based feature extraction for3D MRimage denoising [J]. Medical Image Analysis,2011,15(4):498-513.
[94] Chen S, Wang X X, Harris C J. NARX-based nonlinear system identification using orthogonalleast squares basis hunting [J]. IEEE Transactions on Control Systems Technology,2008,16(1):78-84.
[95] Lee J. Refined filtering of image noise using local statistics [J]. Computer Graphics and ImageProcessing,1981,15(4):380–389.
[96] Rui B, Cristina M, Pedro S, Adérito A. Improved adaptive complex diffusion despeckling filter[J]. Optics Express,2010,18(23):24048-24059.
[97] Srivastava R, Gupta J R P, Parthasarthy H. Comparison of PDE based and other techniques forspeckle reduction from digitally reconstructed holographic images [J]. Optics and Lasers inEngineering,2010,48(5):626-635.
[98] Foucher S. SAR image filtering via learned dictionaries and sparse representations [C]. IEEEInternational Geosciences and Remote Sensing Symposium, Boston, MA, Jul.7-11,2008,229-232.
[99] Hebar M, Gleich D, Cucej Z. Autobinomial model for SAR image despeckling and informationextraction [J]. IEEE Transactions on Geoscience and Remote Sensing,2009,47(8):2818-2835.
[100]Yong B, Mercer B. Interferometric SAR phase filtering in the wavelet domain usingsimultaneous detection and estimation [J]. IEEE Transactions on Geoscience and RemoteSensing,2011,49(4):1396-1416.
[101]Portilla J, Strela V, Wainwright M, Simoncelli E P. Image denoising using scale mixtures ofgaussians in the wavelet domain [J]. IEEE Transactions on Image Processing,2003,12(11):1338-1351.
[102]Tian J, Chen L, Ma L. A wavelet-domain non-parametric statistical approach for imagedenoising [J]. IEICE Electronics Express,2010,7(18):1409-1415.
[103]Gao X, Lu W, Tao D, Li X. Image quality assessment based on multiscale geometric analysis [J].IEEE Transactions on Image Processing,2009,18(7):1409-1423.
[104]Ramesh K, Das B. Multiscale geometric analysis based image quality assessment [C].3rdInternational Conference on Electronics Computer Technology,2011,4:57-60.
[105]Kong W, Lei Y, Ni X. Fusion technique for grey-scale visible light and infrared images based onnon-subsampled contourlet transform and intensity-hue-saturation transform [J]. IET SignalProcessing,2011,5(1):75-80.
[106]Guo Q, Yu S, Chen X, Liu C, Wei W. Shearlet-based image denoising using bivariate shrinkagewith intra-band and opposite orientation dependencies [C]. International Joint Conference onComputational Sciences and Optimization,2009,1:863-866.
[107]Gomathi R, Kumar A V A. An efficient GEM model for image inpainting using a new directionalsparse representation: Discrete shearlet transform [C]. IEEE International Conference onComputational Intelligence and Computing Research,2010:1-4.
[108]焦李成,侯彪,王爽,刘芳.图像多尺度几何分析理论与应用—后小波分析理论与应用[M].西安电子科技大学出版社,2008.
[109]Guo K, Labate D. Optimally sparse multidimensional representation using shearlets [J]. SIAMJournal on Mathematical Analysis,2008,39(1):298-318.
[110]Patel V M, Easley G R, Healy D M. Shearlet-based deconvolution [J]. IEEE Transactions onImage Processing,2009,18(2):2673-2685.
[111]Yang J, Peng Y, Xu W. Qionghai Dai. Ways to sparse representation: A comparative study [J].Tsinghua Science&Technology,2009,14(4):434-443.
[112]Needell D, Tropp J A. Cosamp: Iterative signal recovery from in-complete and inaccuratesamples [J]. Applied and Computational Harmonic Analysis,2009,26(3):301-321.
[113]Varshney K R, etin M, Fisher J W, et al. Sparse representation in structured dictionaries withapplication to synthetic aperture radar [J]. IEEE Transactions on Signal Processing,2008,56(8):3548-3561.
[114]Jung C H, Song W Y, Rho S H, Jung K, Park J T, Kwag Y K. Double-step fast CFAR schemefor multiple target detection in high resolution SAR images [C]. IEEE Radar Conference,2010:1172-1175.
[115]Jung C H, Kwag Y K, Song W Y. CFAR detection algorithm for ground target in heterogeneousclutter using high resolution SAR image [C].3rd International Asia-Pacific Conference onSynthetic Aperture Radar,2011:1-4.
[116]Cui Y, Yang J, Zhang X. New CFAR target detector for SAR images based on kernel densityestimation and mean square error distance [J]. Journal of Systems Engineering and Electronics,2012,23(1):40-46.
[117]Jung Chul H, Yang, Hee J, Song Woo Y, Kwag Young K. Multi-target detection using2-Ddistributed cell-averaging CFAR in high resolution SAR images [C].8th European Conferenceon Synthetic Aperture Radar,2010:1-4.
[118]Candès E, Braun N, Wakin M. Sparse signal and image recovery from compressive sensing [C].4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro,2007:976-979.
[119]Candès E, Romberg J, Tao T. Robust uncertainty principles: Exact signal reconstruction fromhighly incomplete frequency information [J]. IEEE Transactions on Information Theory,2006,52(2):489–509.
[120]Donoho D. Compressed sensing [J]. IEEE Transactions on Information Theory,2006,52(4):1289-1306.
[121]Comaniciu D, Meer P. Mean shift: a robust approach toward feature space analysis [J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.
[122]Cheng Y. Mean shift, mode seeking, and clustering [J]. IEEE Transactions on Pattern Analysisand Machine Intelligence,1995,17(8):790-799.
[123]Laptev I. Improving object detection with boosted histograms [J]. Image and Vision Computing,2009,27(5):535-544.
[124]Chen S, Hong S, Harris C J. An orthogonal forward regression technique for sparse kerneldensity estimation [J]. Neurocomputing,2008,71(46):931–943.
[125]Derrac J, García S, Herrera F. IFS-CoCo: Instance and feature selection based on cooperativecoevolution with nearest neighbor rule [J]. Pattern Recognition,2010,43(6):2082-2105.
[126]Mayer A, Greenspan H. An adaptive mean-shift framework for MRI brain segmentation [J].IEEE Transactions on Medical Image,2009,28(8):1238-1250.
[127]Comaniciu D, Meer P. Mean shift analysis and application [C]. Seventh IEEE InternationalConference on Computer Vision,1999:12-15.
[128]Engan K, Skretting K, Herredsvela J, et al. Frame texture classification method (FTCM) appliedon mammograms for detection of abnormalities [J]. International Journal of Signal Processing,2008,4(2):122-132.
[129]Marques R, Medeiros F, Ushizima D. Target detection in SAR images based on a level setapproach [J]. IEEE Transactions on Systems, Man and Cybernetics,2009,39(2):214-222.
[130]Mairal J, Elad M, Sapiro G. Sparse representation for color image restoration [J]. IEEETransactions on Image Processing,2008,17(1):53-69.
[131]Dainty J. Laser speckle and related phenomena [M]. Bering: Spring-Verlag,1984.
[132]Lee J S. Digital image smoothing and the sigma filter [J]. Computer Vision, Graphics and ImageProcessing,1983,24(2):255-269.
[133]Conover W J. Practical nonparametric statistics [M]. New York: John Wiley&Sons,1999.
[134]Tu M W, Gupta I J. Application of maximum likelihood estimation to radar imaging [J]. IEEETransactions on Antennas and Propagation,1997,45(1):20-27.
[135]Cetin M, Karl W C. Feature-enhanced synthetic aperture radar image formation based onnonquadratic regularization [J]. IEEE Transactions on Image Processing,2001,10(4):623-631.
[136]Ming-Wang Tu, Gupta I J. Application of maximum likelihood estimation to Radar imaging [J].IEEE Transactions on Antennas and Propagation,1997,45(1):20-27.
[137]Zheng-ming Wang, Wei-wei Wang. Fast and adaptive method for SAR superresolution imagingbased on point scattering model and optimal basis selection [J]. IEEE Transactions on ImageProcessing,2009,18(7):1477-1486.
[138]Gao G, Liu L, Zhao L, Shi G, Kuang G. An adaptive and fast CFAR algorithm based onautomatic censoring for target detection in high-resolution SAR images [J]. IEEE Transactionson Geoscience and Remote Sensing,2009,47(6):1685-1697
[139]Bazi Y, Bruzzone L, Melgani F. An unsupervised approach based on the generalized Gaussianmodel to automatic change detection in multitemporal SAR images [J]. IEEE Transactions onGeoscience and Remote Sensing,2005,43(4):874-887.
[140]Gamba P, Dell'Acqua F, Lisini G. Change detection of multitemporal SAR data in urban areascombining feature-based and pixel-based techniques [J]. IEEE Transactions on Geoscience andRemote Sensing,2006,10(1):2820-2827.
[141]He M, He X F. Urban change detection using coherence and intensity characteristics ofmulti-temporal SAR imagery [C].2nd Asian-Pacific Conference on Synthetic Aperture Radar,2009:840-843.
[142]Su J, Wang R, Du K. A change detection method for man-made objects in SAR images based oncurvelet and level set [C]. Sixth International Conference on Image and Graphics,2011:543–547.
[143]Inglada J, Mercier G A. new statistical similarity measure for change detection in multitemporalSAR images and its extension to multiscale change analysis [J]. IEEE Transactions onGeoscience and Remote Sensing,2007,45(5):1432-1445.
[144]Pantze A, Fransson J E S, Santoro M. Forest change detection from L-band satellite SAR imagesusing iterative histogram matching and thresholding together with data fusion [C]. IEEEInternational Geoscience and Remote Sensing Symposium,2010:1226-1229.
[145]Zheng Z, Xu W, Niu K, He Z, Tian B. A novel Bayesian compressed sensing algorithm usingsparse tree representation [C].4th IEEE International Conference on Broadband Network andMultimedia Technology,2011:178-182.
[146]Eftekhari A, Babaie-Zadeh M, Moghaddam H A. Two-dimensional random projection [J]. SignalProcessing,2011,91:1589–1603.