面向SAR图像目标分类的关键技术研究
|
摘要
本文以发展自动和半自动的SAR图像目标分类系统为目的,围绕成像侦察情报支援作战应用,结合我国雷达成像卫星及航天器与地面应用系统建设及发展需求,以SAR图像目标解译应用为背景,在大量国内外高分辨率SAR实测数据的支持下,深入研究了SAR图像去斑技术、SAR图像分割技术、面向目标分类的SAR图像目标切片特征提取技术。论文主要研究内容包括:
第二章研究了SAR图像的相干斑抑制问题。相干斑抑制是SAR图像处理中最基础同时也是最重要的问题之一,其核心问题在于如何在充分抑制相干斑的同时保持图像的点、线、边缘等结构特征。论文首先提出了一种具有结构保持特性的MRF模型——SPMRF,并给出了模型的参数估计方法,该模型可以根据图像的局部特征自适应调整权重参数,既能描述匀质区域又能描述结构特征,为贝叶斯估计提供了准确的先验信息,从而使基于SPMRF的SAR图像贝叶斯去斑取得了较好的去斑效果;然后,借鉴自适应窗口滤波思想,提出了MRF邻域的自适应调整方法,弥补了简单MRF模型无法保持结构特征的缺陷。通过对图像局部区域匀质性的判断,自适应调整模型的邻域结构,在匀质区域使用较大邻域以充分抑制相干斑,而在含结构特征区域使用较小邻域,并筛选出与中心像素最有可能源自具有相同后向散射特性的邻域点参与计算,以保持结构特征。以此为基础的AN-MMRF去斑在充分抑制相干斑的同时较好地保持了图像结构特征;最后,在已有的基于HMT和基于HMRF模型的隐状态估计方法上,将两者结合,提出了基于HMT-HMRF模型的SAR图像小波系数隐状态估计法,该方法充分利用了小波系数尺度间和尺度内的相关性,提高了隐状态估计的准确性,为利用贝叶斯估计削弱噪声主导的小波系数并保持信号主导的小波系数奠定了基础。以此为核心的SAR图像小波去斑同样取得了较好的去斑效果。
第三章研究了SAR图像区域分割技术。为了从大幅未知的SAR场景图像有效提取目标ROI切片并分离切片中的目标区域,论文给出了三种分割算法,包括基于最大类间方差准则的SAR图像分割算法、基于分形特征组的SAR图像分割算法和基于多分辨率分析的SAR图像分割算法。首先,在现有的二维最大类间方差法分割算法的基础上,分析了叠加乘性噪声的二维直方图特点,提出新的适用于乘性噪声的直方图区域划分方法。同时,提出新的阈值选取准则。基于改进的二维直方图划分方法和新的阈值选取准则,论文提出了基于最大类间方差准则的SAR图像分割算法;其次,针对SAR图像纹理的特征,利用分形理论来计算待分割像素局部图像数据的分形维数和间隙度特征,以衡量该局部图像数据的起伏特性。论文基于这两类特征构建分形特征矢量,并结合二项式距离判决函数,实现SAR图像分割处理;最后,为了消除相干斑噪声对高分辨率SAR图像分割的影响,论文给出了基于多分辨率分析的SAR图像分割算法。该算法在对待分割图像数据进行多尺度分层处理的基础上,对多尺度数据建立MAR模型,并计算多分辨率对数似然比统计量,来实现对SAR图像的分割。
第四章研究了面向目标分类的SAR图像目标特征提取技术。立足于构建自动和半自动的SAR图像目标分类系统,深入研究了面向SAR图像目标分类的目标切片特征提取问题。首先,在广泛文献调研的基础上,综述了SAR图像目标方位角估计技术;在此基础上,提出一种主导边界与最小外接矩形联合的SAR目标方位角估计方法。该方法充分考虑了基于主导边界和最小外接矩形方法的优缺点,取长补短,大大提高了目标方位角估计的精度;然后,致力于构建半自动的SAR图像目标分类系统,研究了面向人机交互的图像目标几何特征提取与分析问题,提取了几种直观的、有效的、便于判读员理解的目标几何特征;最后,以自动目标分类系统的实时性指标为主要考虑依据,提出了一种快速的SAR目标识别方法。该方法采用基于Hebb学习规则的主分量分析(PCA)进行特征提取,使用多层感知器神经网络(MLP NN)进行目标分类。实现了自动快速的目标分类。
Aiming at developing automatic and semi-automatic systems of SAR image classification, considering imaging reconnaissance applications and the demand of building and developing radar imaging satellites, spacecraft and ground application systems, with the background of SAR image target interpretation applications and the support of abundant high-resolution SAR data, this thesis comprehensively studies the techniques of SAR image despeckling, SAR image segmentation, feature extraction from SAR chips for target classification. The research works of this thesis are as follows:
SAR image despeckling is developed in chapter 2. Despeckling is a basic and important subject of SAR image processing, which focuses on suppressing the speckle while preserving the structural features such as point, line and edge. First, a structure-preserving MRF model, the SPMRF model, is proposed and the parameter estimation method is given. This model can adaptively adjust the weights according to the local features in image. It can be used to describe both homogeneous regions and structural features. It provides accurate prior knowledge and leads to good despeckling performance. Then, based on the idea of adaptive window, a method of adaptively adjusting the MRF neighborhood is presented, which solves the problem that simple MRF model can’t preserve the structural feature. The neighborhood is adjusted via determining the homogeneity of local region. Larger neighborhood is adopted in homogeneous regions to suppress speckle. Smaller neighborhood is adopted in regions with structural features to preserve the structural feature by selecting the pixels which are most likely to have the same backscattering properties as the center pixel. In this way, the AN-MMRF despeckling method preserves the structural feature while suppressing speckle. Finally, combining the HMT-based and HMRF-based hidden state estimation methods, a HMT-HMRF-model-based method for SAR image wavelet coefficients is proposed, which utilizes the correlation within and between scales of wavelet coefficients and improves the accuracy of estimation. The corresponding wavelet despeckling method achieves good performance.
SAR image segmentation is discussed in chapter 3. In order to extract target ROI chips from large-scene SAR images and separating the target regions, three segmentation methods are studied, namely, segmentation based on maximum-between-class-variance, segmentation based on fractal features and segmentation based on multi-resolution analysis. First, based on the existing maximum-between-class-variance segmentation, 2D histogram is analyzed on image with multiplicative noise and a new method of segmenting histogram with multiplicative noise is proposed. The rule for determining threshold is also provided. Based on the improved 2D histogram segmentation and new thresholding method, SAR image segmentation based on maximum-between-class–variance is presented. Second, considering the textural feature of SAR image, fractal theory is used to compute the fractal dimension and spacing feature to measure the fluctuating properties of local data. Based on the two features and quadratic distance function, SAR image segmentation is implemented. Finally, in order to remove the influence of speckle on high-resolution SAR image segmentation, segmentation method based on multi-resolution analysis is proposed. In this method, multi-resolution processing is implemented on images, and then MAR model are built on multi-scale data. Multi-resolution log-likelihood ratio is computed to achieving SAR image segmentation.
Target feature extraction for classification is presented in chapter 4. Established in constructing an automatic and semi-automatic SAR image target classification system, the target chip extraction for SAR target classification is deeply studied. First, the techniques to estimate SAR target orientation angle are reviewed, and a method jointing dominant boundaries and minimum outer rectangles is proposed to estimate the SAR target orientation angle. The method, considering the advantages and disadvantages of that only uses dominant boundaries or outer rectangles, can significantly improve the estimation accuracy of target orientation angle. Then, established in constructing a semi-automatic SAR target classification system, the extraction of image geometric features is studied, and several intuitive and effective target geometric features are extracted. Finally, a fast SAR target recognition method is proposed. The method uses Principle Component Analysis (PCA) based on learning rules to extract target features, and Multiple Levels Perception Neural Network (MLPNN) to classify the target. The automatic and fast target classification is thus finished.
第二章研究了SAR图像的相干斑抑制问题。相干斑抑制是SAR图像处理中最基础同时也是最重要的问题之一,其核心问题在于如何在充分抑制相干斑的同时保持图像的点、线、边缘等结构特征。论文首先提出了一种具有结构保持特性的MRF模型——SPMRF,并给出了模型的参数估计方法,该模型可以根据图像的局部特征自适应调整权重参数,既能描述匀质区域又能描述结构特征,为贝叶斯估计提供了准确的先验信息,从而使基于SPMRF的SAR图像贝叶斯去斑取得了较好的去斑效果;然后,借鉴自适应窗口滤波思想,提出了MRF邻域的自适应调整方法,弥补了简单MRF模型无法保持结构特征的缺陷。通过对图像局部区域匀质性的判断,自适应调整模型的邻域结构,在匀质区域使用较大邻域以充分抑制相干斑,而在含结构特征区域使用较小邻域,并筛选出与中心像素最有可能源自具有相同后向散射特性的邻域点参与计算,以保持结构特征。以此为基础的AN-MMRF去斑在充分抑制相干斑的同时较好地保持了图像结构特征;最后,在已有的基于HMT和基于HMRF模型的隐状态估计方法上,将两者结合,提出了基于HMT-HMRF模型的SAR图像小波系数隐状态估计法,该方法充分利用了小波系数尺度间和尺度内的相关性,提高了隐状态估计的准确性,为利用贝叶斯估计削弱噪声主导的小波系数并保持信号主导的小波系数奠定了基础。以此为核心的SAR图像小波去斑同样取得了较好的去斑效果。
第三章研究了SAR图像区域分割技术。为了从大幅未知的SAR场景图像有效提取目标ROI切片并分离切片中的目标区域,论文给出了三种分割算法,包括基于最大类间方差准则的SAR图像分割算法、基于分形特征组的SAR图像分割算法和基于多分辨率分析的SAR图像分割算法。首先,在现有的二维最大类间方差法分割算法的基础上,分析了叠加乘性噪声的二维直方图特点,提出新的适用于乘性噪声的直方图区域划分方法。同时,提出新的阈值选取准则。基于改进的二维直方图划分方法和新的阈值选取准则,论文提出了基于最大类间方差准则的SAR图像分割算法;其次,针对SAR图像纹理的特征,利用分形理论来计算待分割像素局部图像数据的分形维数和间隙度特征,以衡量该局部图像数据的起伏特性。论文基于这两类特征构建分形特征矢量,并结合二项式距离判决函数,实现SAR图像分割处理;最后,为了消除相干斑噪声对高分辨率SAR图像分割的影响,论文给出了基于多分辨率分析的SAR图像分割算法。该算法在对待分割图像数据进行多尺度分层处理的基础上,对多尺度数据建立MAR模型,并计算多分辨率对数似然比统计量,来实现对SAR图像的分割。
第四章研究了面向目标分类的SAR图像目标特征提取技术。立足于构建自动和半自动的SAR图像目标分类系统,深入研究了面向SAR图像目标分类的目标切片特征提取问题。首先,在广泛文献调研的基础上,综述了SAR图像目标方位角估计技术;在此基础上,提出一种主导边界与最小外接矩形联合的SAR目标方位角估计方法。该方法充分考虑了基于主导边界和最小外接矩形方法的优缺点,取长补短,大大提高了目标方位角估计的精度;然后,致力于构建半自动的SAR图像目标分类系统,研究了面向人机交互的图像目标几何特征提取与分析问题,提取了几种直观的、有效的、便于判读员理解的目标几何特征;最后,以自动目标分类系统的实时性指标为主要考虑依据,提出了一种快速的SAR目标识别方法。该方法采用基于Hebb学习规则的主分量分析(PCA)进行特征提取,使用多层感知器神经网络(MLP NN)进行目标分类。实现了自动快速的目标分类。
Aiming at developing automatic and semi-automatic systems of SAR image classification, considering imaging reconnaissance applications and the demand of building and developing radar imaging satellites, spacecraft and ground application systems, with the background of SAR image target interpretation applications and the support of abundant high-resolution SAR data, this thesis comprehensively studies the techniques of SAR image despeckling, SAR image segmentation, feature extraction from SAR chips for target classification. The research works of this thesis are as follows:
SAR image despeckling is developed in chapter 2. Despeckling is a basic and important subject of SAR image processing, which focuses on suppressing the speckle while preserving the structural features such as point, line and edge. First, a structure-preserving MRF model, the SPMRF model, is proposed and the parameter estimation method is given. This model can adaptively adjust the weights according to the local features in image. It can be used to describe both homogeneous regions and structural features. It provides accurate prior knowledge and leads to good despeckling performance. Then, based on the idea of adaptive window, a method of adaptively adjusting the MRF neighborhood is presented, which solves the problem that simple MRF model can’t preserve the structural feature. The neighborhood is adjusted via determining the homogeneity of local region. Larger neighborhood is adopted in homogeneous regions to suppress speckle. Smaller neighborhood is adopted in regions with structural features to preserve the structural feature by selecting the pixels which are most likely to have the same backscattering properties as the center pixel. In this way, the AN-MMRF despeckling method preserves the structural feature while suppressing speckle. Finally, combining the HMT-based and HMRF-based hidden state estimation methods, a HMT-HMRF-model-based method for SAR image wavelet coefficients is proposed, which utilizes the correlation within and between scales of wavelet coefficients and improves the accuracy of estimation. The corresponding wavelet despeckling method achieves good performance.
SAR image segmentation is discussed in chapter 3. In order to extract target ROI chips from large-scene SAR images and separating the target regions, three segmentation methods are studied, namely, segmentation based on maximum-between-class-variance, segmentation based on fractal features and segmentation based on multi-resolution analysis. First, based on the existing maximum-between-class-variance segmentation, 2D histogram is analyzed on image with multiplicative noise and a new method of segmenting histogram with multiplicative noise is proposed. The rule for determining threshold is also provided. Based on the improved 2D histogram segmentation and new thresholding method, SAR image segmentation based on maximum-between-class–variance is presented. Second, considering the textural feature of SAR image, fractal theory is used to compute the fractal dimension and spacing feature to measure the fluctuating properties of local data. Based on the two features and quadratic distance function, SAR image segmentation is implemented. Finally, in order to remove the influence of speckle on high-resolution SAR image segmentation, segmentation method based on multi-resolution analysis is proposed. In this method, multi-resolution processing is implemented on images, and then MAR model are built on multi-scale data. Multi-resolution log-likelihood ratio is computed to achieving SAR image segmentation.
Target feature extraction for classification is presented in chapter 4. Established in constructing an automatic and semi-automatic SAR image target classification system, the target chip extraction for SAR target classification is deeply studied. First, the techniques to estimate SAR target orientation angle are reviewed, and a method jointing dominant boundaries and minimum outer rectangles is proposed to estimate the SAR target orientation angle. The method, considering the advantages and disadvantages of that only uses dominant boundaries or outer rectangles, can significantly improve the estimation accuracy of target orientation angle. Then, established in constructing a semi-automatic SAR target classification system, the extraction of image geometric features is studied, and several intuitive and effective target geometric features are extracted. Finally, a fast SAR target recognition method is proposed. The method uses Principle Component Analysis (PCA) based on learning rules to extract target features, and Multiple Levels Perception Neural Network (MLPNN) to classify the target. The automatic and fast target classification is thus finished.
引文
[1]张澄波.综合孔径雷达原理、系统分析与应用.北京:科学出版社,1989.
[2]刘永坦.雷达成像技术.哈尔滨:哈尔滨工业大学出版社,1999.
[3]张直中.微波成像技术.北京:科学出版社.1990.
[4]朱述龙,张占睦.遥感图像获取与分析.北京:科学出版社,2000.
[5] [美] Skolnik M. I.著,王军等译.雷达手册.北京:电子工业出版社,2003.
[6]魏钟铨等.合成孔径雷达卫星.国家863计划308主题空间信息获取与处理系统专著,北京:科学出版社,2001.
[7]舒宁.雷达遥感原理.武汉:武汉测绘科技大学出版社,2000.
[8]谢寿生,徐永进.微波遥感技术与应用.北京:电子工业出版社,1987.
[9]张直中.机载和星载合成孔径雷达导论.北京:电子工业出版社,2003.
[10] [法] Maitre H.著,孙洪译.合成孔径雷达图像处理.北京:电子工业出版社,2003.
[11]保铮等.雷达成像技术.北京:电子工业出版社,2003.
[12]第二届中国合成孔径雷达会议论文集.南京,2005.
[13] Dudgeon D E, Lacoss R T.An Overview of Automatic Target Recognition, Lincoln Laboratory Journal, 1993, 6(1):3～10.
[14] Kreithen D E, et al.Discriminating Targets from Clutter. The Lincoln Laboratory Journal, 1993, 6(1):25～51.
[15] Quoc H Pham, et al.An efficient end-to-end feature based system for SAR ATR.SPIE, Vol 3370:519～529.
[16] Alberto L, Carcloso L D.Computer Aided Recognition of Man～made Structures in Aerial Photograghs.Naval Postgraduate School.AD report.Dec.1999.
[17] Special Issue on Advances in Synthetic Aperture Radar. IEE Proceedings Radar, Sonar & Navigation, 2003, 150(3).
[18] Novak L M, et al. Performance of a High～Resolution Polarimetric SAR Automatic Target Recognition System. The Lincoln Laboratory Journal, 1993, 6(1):11～24.
[19] Novak L M, et al. Effects of Polarization and Resolution on the Performance of a SAR Automatic Target Recognition System. The Lincoln Laboratory Journal, 1995, 8(1):49～67.
[20] Timothy D R, et al . SAR ATR-so what’s the problem? -an MSTARperspective.SPIE Vol. 3721, 1999:662～672.
[21] Lee J S.Digital image enhancement and noise filtering by use of local statistics, IEEE Trans. Pattern Analysis and Machine Intelligence, 1980, 2(2):165～168.
[22] Kuan D T. Sawchuk A.A. and Strand T.C., et al, Adaptive noise smoothing filter for images with signal～dependent noise, IEEE Trans. Pattern Analysis and Machine Intelligence, 1985, 7(2):165～177.
[23] Frost V S, et al.A model for radar images and its application to adaptive digital filtering of multiplicative noise, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1982, 4(2):157～165.
[24] Lopes A, Touzi R, Nezry E.Adaptive speckle filters and scene heterogeneity, IEEE Trans.Geoscience and Remote Sensing, 1990, 28(6):992～1000.
[25] Meer P , Park R H ,Cho K.Multi～resolution adaptive image smoothing, CVGIP, 1994, 56:140～148.
[26] Ranganath S. Image filtering using multi～resolution representations, IEEE Trans. Pattern Analysis and Machine Intelligence, 1991, 13(5):426～440.
[27] Bruno Aiazzi, Luciano Alparone, Stefano Baronti . Multiresolution texture analysis of SAR images.SPIE 3497:90～98.
[28] Donoho D L, Iohnstone I M.Adapting to unknown smoothness via wavelet shrink, Journal of the American Statistical Assoc.1995, 90(432):1200～1224.
[29]刘峰.基于小波变换的图像扩散滤波方法.中国科学E辑,2006,36 (6):668～677.
[30] Sveinsson J R, Benediktsson J.A, Speckle Reduction in the Complex wavelet Domain, In:Proceedings of IGARSS 2001, CD Rom, Sydney, Australia, July 9～13, 2001.
[31] Lopes, Touzi R, Nezry E.Adaptive Speckle Filters and Scene Heterogeneity, IEEE Trans. Geoscience and Remote Sensing, 1990, 28(6):992～1000.
[32] Lopes, et al, Maximum A Posteriori Speckle Filteringand First Order Textural Models in SAR Images, Proc. IGARSS'90, 1990, 3:2409～2412.
[33] German S, German D.Stochastic Relaxation, Gibbs Distribution, and the Bayesian Restoration of Images, IEEE Trans. Pattern Analysis and Machine Intelligence, 1984, PAMI 6 (6):721～741.
[34] White R G.A Simulated Annealing Algorithm for SAR and MTI Images Cross～section Estimation, Proc.SPIE, 1994, 2316:137～145.
[35] McConnell, et al, Radar Cross～section Estimation of SAR Images, Proc. SPIE,1995, 2584:164～175.
[36] Datcu M, Seidel K, Walessa M. Spatial Information Retrieval from Remote～Sensing Images～Part II : Gibbs～Markov Random Fields, IEEE Trans. Geosci. Remote Sensing, 1998, 36(5):1431～1445.
[37] Walessa M, Datcu M. Model～Based Despeckling and Information Extraction from SAR Images, IEEE Trans. Geosci. Remote Sensing, 2000, 38(5):2258～2269.
[38] Schou J, Skriver H.Restoration of Polarimetric SAR Images Using Simulated Annealing, IEEE Trans. Geosci. Remote Sensing, 2001, 39(9):2005～2016.
[39] Bratsolis E, Sigelle M.Fast SAR Image Restoration, Segmentation, and Detection of High～Reflectance Regions, IEEE Trans. Geoscience and Remote Sensing, 2003, 41(2):2890～2899.
[40] Crouse M S, Nowak R D,Baraniuk R C.Wavelet～based signal processing using hidden markov models, IEEE Trans. Signal Processing, 1998, 46(4):886～902.
[41] Hua Xie, Pierce L E,Ulaby F T.SAR speckle reduction using wavelet denoising and Markov random field modeling, IEEE Trans.on Geosci and Remote Sensing, 2002, 40(10):2196～2212.
[42] Xin XU, Deren LI, Hong Sun.Multiscale SAR image segmentation using a double markov random field model.IEEE Proceedings.of Seventh International Symposium on Signal Processing and Its Applications, 2003, Vol.1:349～352.
[43]王爱民,沈兰荪.图像分割研究综述.测控技术,2000 (5):1～5.
[44] Cao Lanying, Zhang Kunhui, Xia Liangzheng.SAR Image segmentation by 2-D fussy entropy . IEEE Proceedings. of Geoscience and Remote Sensing Symposium, 2004, Vol.6:3798～3801.
[45]燕英,周荫清.基于分割途径的SAR单视图像斑点噪声抑制方法.北京航空航天大学学报,2003 (2):132～135.
[46] Objective evaluation of four sar image segmentation algorithms.ADA391936.
[47] Jason B G, Steven C G, Gregory J P.An objective evaluation of four SAR image segmentation algorithms.SPIE Vol. 4382:346～357.
[48] Evaluation of synthetic aperture radar image segmentation algorithms in the context of automatic target recognition.ADA421104.
[49]邓炜.SAR图像处理方法研究.西北工业大学博士论文,2000.
[50]刘振华.SAR图像处理及融合研究.北京航空航天大学博士论文,2003.
[51]薛景浩,章毓晋,林行刚.SAR图像基于Rayleigh分布假设的最小误差阈值化分割.电子科学学刊,1999 (2):219～225.
[52] Fjortoft R, et al . An optimal multiedge detector for SAR image segmentation.IEEE Transactions on Geoscience and Remote Sensing, 1998: 793～802.
[53] Cook R, McConnell I, Oliver C J.MUM(Merge Using Moments) segmentation for SAR images.SPIE, 2316, 1994:92～103.
[54] Stewart D, et al . Optimal approach to SAR image segmentation and classification.IEE Proceedings of Radar, Sonar and Navigation, 2000, Vol 147 (3):134～142.
[55] Robert A, et al.MRF based algorithms for segmentation of SAR images. ICIP Chicago 1998,3:770～774.
[56]高贵,计科峰,匡纲要,李德仁.基于各向异性热扩散方程的SAR图像分割方法.信号处理,2006,22 (1):105～109.
[57]何勇.分形方法在SAR图像区域分割中的应用.武汉大学硕士论文,2004.
[58] William Irving,Gil Ettinger. Classification of Targets in Synthetic Aperture Radar Imagery Via Quantized Grayscale Matching.Proc.SPIE,1999,3721:320～331.
[59] Bahnu B, et al.Recognition of articulated objects in SAR images. In Proceedings of the ARPA Image Understanding Workshop , February,1996:1237～1250.
[60] By-Her Wang . An Automatic Target Recognition System For SAR Imagery.Doctor’s dissertation, Stanford University, Nov. 1997.
[61] Ettinger G J, et al.A probabilistic optimization approach to SAR feature matching.Algorithms for Synthetic Aperture Radar III, Proc. SPIE, April 1996, 2757:318～329.
[62] Robert M. Haralick, et al.The Topographic Primal Sketch.The International Journal of Robotics Research, Spring 1983,2 (1):50~72.
[63] Ryan T W, et al . SAR target indexing with hierarchical distance transforms.Algorithms for Synthetic Aperture Radar Imagery III, Proc SPIE, April 1996,2757:243～252.
[64] Pei-Chun Chiang, Thomas O. Binford.Generic, Model-Based Edge Estimation in the Image Surface.1-10.
[65] Touzi R, Lopes A, Bousquet P.A statistical and geometrical edge detector forSAR images.IEEE Trans. Geosci. Remote Sensing, Nov. 1988,26:764～773.
[66] Ward K D.Compound Representation of High Resolution Sea Clutter.Electron,Lett, 1981, 7:561～565.
[67] Besag J, et al.On the statistical analysis of dirty pictures, 1986, 48(3):259–302.
[68] Park J M, Song W J, Pearlman W A. Speckle filtering of SAR images based on adaptive windowing, IEE～proc.Vis.Image Signal Process, 1999, 146 (4):191～197.
[69] Rohling H.Radar CFAR thresholding in clutter and multiple target situations, IEEE Transactions on Aerospace and Electronic Systems, 1983, 19(4):608～621.
[70]蔡红苹,基于小波变换的去噪方法研究,国防科技大学研究生院学位论文, 2003.
[71] Arsenault H H,et al.Properties of Speckle Integrated with a Finite Aperture and Logarithmically Transformed, J.Opt.Soc Am, 1976, 11(22):1160～1168.
[72] Oliver C, Quegan S.Understanding Synthetic Aperture Radar Images, Artech House:Boston, 1998.
[73] Achim A, Bezerianos A, and Tsakalides P.Novel Bayesian multiscale method for speckle removal in medical ultrasound images, IEEE Trans. Med Imag, 2001, 20(8):772～783.
[74]陈建祥,贾承丽,匡纲要,改进的基于结构检测的SAR图像去斑算法,计算机仿真, 2005, 22(9):25～28.
[75] Frery A C, Lucca E V D.SAR segmentation algorithms:a quantitative assessment.IEEE Proceedings of Geoscience and Remote Sensing Symposium, 1999, Vol.2:1265～1267.
[76] Chumsamrong W, Thitimajshima P, Rangsanseri Y.Synthetic aperture radar (sar) image segmentation using a new modified fuzzy c-means algorithm.IEEE Trans. Geoscience and Remote Sensing Symposium, 2000, 2:624～626.
[77]盛国芳.SAR图像去噪与分割算法的研究.西安电子科技大学硕士论文,2003.
[78]李禹.SAR图像机动目标检测与鉴别技术研究,国防科学技术大学博士论文,2007.
[79]郦苏丹.SAR图像特征提取与目标识别方法研究.国防科学技术大学博士论文,2001.
[80] Otsu N. A Threshold Selection Method from Gray～Level Histogram [J]. IEEE Trans. Systems, Man, and Cybernetics, 1979,9 (1):62～66.
[81] Liu Jianzhuang, Li Wenqing, Tian Yupeng. Automatic Thresholding of Gray～Level Pictures Using Two～Dimensional Otsu Method [A].Proc.IEEE ISCAS '91 [C].1991:325～327.
[82]刘建庄,栗文清.灰度图像的二维Otsu自动阈值分割法[J].自动化学报, 1993, 19 (1):101～105.
[83]芦蓉,沈毅.一种改进的二维直方图的图像阈值分割方法[J].系统工程与电子技术, 2004, 26 (10):1487～1490.
[84]郝颖明,朱枫.二维Otsu自适应阈值的快速算法[J].中国图象图形学报, 2005, 10 (4):484～488.
[85]梁光明,刘东华,李波,唐朝京.二维Otsu自适应阈值分割算法的改进[J].自动化技术与应用, 2002, 21 (5):43～47.
[86]朱峻,王世晞,计科峰,粟毅,一种适用于SAR图像的二维Otsu改进算法,中国图形图象学报,已录用.
[87] Pentlan A.Fractal～based description of nature scences.IEEE Trans.On Pattern Analyses and Machine Intelligence, 1984, Vol 10:661～674.
[88] Mandelbrot B B.The fractal geometry of nature.New York:Freeman and Co. 1983.
[89]杜干,张守宏.高阶分形特征在雷达信号检测中的应用.电子学报,2000,28 (3):90～92.
[90] Dong P . Test of a new lacunarity estimation method for image texture analysis.International Journal of Remote Sensing, 2000, Vol 21(17):3369～3373.
[91] Soe Win Myint, Nina Lam.A study of lacunarity～based texture analysis approaches to improve urban image classification.Computers, Environment and Urban Systems, 2005, Vol 29:501～523.
[92]赵巨波,万建伟,王永杰.基于分形理论的目标检测.电子学报,2005,33(12):2524～2526.
[93]安国成,刘振华,于文震,基于分形特征的高分辨率SAR图像分类,现代雷达,2006,28(6):26～29.
[94]薛笑荣,张艳宁,赵荣椿.基于分形理论的SAR图像分割.计算机工程与应用,2003:27～29.
[95] Gan Du, Tat Soon Yeo. A novel lacunarity estimation method applied to SAR image segmentation.IEEE Transactions on Geoscience and Remote Sensing,2002:2687～2691.
[96]李厚强,刘政凯,林峰.基于分形理论的航空图像分类方法.遥感学报,2001,5(5):353～358.
[97] Novak L M, et al.Effects of Polarization and Resolution on SAR ATR.IEEE Trans. On Aerospace and Electronic Systems, 1997, 33(1):102～116.
[98] Nikola S S, et al.Multiresolution detection of coherent radar targets.IEEE Trans. On Image Processing, 1997, 6 (1):21～35.
[99] Fosgate C H, et al. Multiscale segmentation and anomaly enhancement of SAR imagery.IEEE Trans. On Image Processing, 1997, 6 (1):7～20.
[100] Irving W W, Novak L M, Willsky A S.A multiresolution approach to discrimination in SAR imagery.IEEE Trans. On Aerospace and Electronic Systems, 1997, 33 (4):1157～1169.
[101] David Howard, Jim Schroeder.Multiscale models for target detection and background discrimination in synthetic aperture radar imagery.Digital Signal Processing, 1999, 9:149～161.
[102] Li Yu, Ji Kefeng, Su Yi.Quantitative analysis of statistical models for typical terrains in SAR data. Proceedings of 2006 CIE International Conference on Radar, Vol 1:696～699,(EI:073310760134).
[103] Ronald Caves, Shaun Quegan, Richard White.Quantitative comparison of the performance of SAR segmentation algorithms.IEEE Transactions on Image Processing, 1998,Vol.7:1534～1546.
[104] Delves L M, et al . Comparing the perfoemance of SAR segmentation algorithms.International Journal of Remote Sensing, Vol. 13, 1992:2122～2149.
[105] Gregory J. Power.Multimetric inter～algorithmic evaluation of SAR image segmentation algorithms.Proceedings of SPIE, Vol. 4382, Algorithms for Synthetic Aperture Radar Imagery VIII, April 2001:330～337.
[106] Leslie M. Novak, Gregory J. Owirak, William W.Irving, Performance of 10～and 20～target MSE classifiers, IEEE Transactions on Aerospace and Electronic Systems VOL.36, No.4, Oct.2000:1279～1289
[107] Eric R. Keydel, MSTAR Extended Operating Conditions:A Tutorial, SPIE Vol 2757, 1996:228～242
[108] Eric R. Keydel, Signature Prediction for Model～Based Automatic TargetRecognition, SPIE Vol.2757, 1996:306～317.
[109] Joseph Diemunsch, John Wissinger, Moving and Stationary Target Acquisition and Recognition(MSTAR) Model～Based Automatic Target Recognition:Search Technology for a Robust ATR, SPIE, Vol.3370, 1998, p481～492.
[110] William Irving, Gil Ettinger, Classification of Target in Synthetic Aperture Radar Imagery via Quantized Grayscale Matching, SPIE Vol.3721, 1999:320～331.
[111] Liviu I.Voicu, Ron Patton, Harley R. Myler, Multi～criterion vehicle pose estimation for SAR ATR, SPIE Vol.3721, 1999:497～506.
[112] Walessa M. Bayesian information extraction from SAR images, Ph.D.thesis, Univ. Siegen, Siegen, Germany, 2001.
[113] Principe J, Zhao Q,Xu D.A novel ATR classifier exploiting pose information.In Proceedings of Image Understanding Workshop, Monterey, CA ,1998:833～836.
[114] Munchurl Kim, Focus of Attention Based on Gamma Kernels for Automatic Target Recognition, doctor’s dissertation, University of FLORIDA, 1996
[115]计科峰,匡纲要,郁文贤,基于线性回归的SAR目标方位角估计方法,现代雷达,Vol. 25(2),2003,15～18.
[116] Thomas O B, et al.Context and Quasi～invariant in ATR with SAR Imagery, http://robotics.stanford.edu/groups/reality/binford.html
[117] By～Her Wang,“An Automatic Target Recognition System For SAR Imagery”, Doctor’s dissertation, Stanford University, Nov.1997.
[118]计科峰,匡纲要,粟毅,郁文贤,SAR图像目标峰值特征提取与方位角估计方法研究,宇航学报,2004,25(1):102～108。
[119]高贵,高分辨率SAR图像目标特征提取研究,国防科技大学硕士学位论文,2003。
[120]计科峰,高分辨率SAR图像特征提取与分类方法研究,国防科技大学博士学位论文,2003。
[121] Paul Runkle,et al.Multi～Aspect Target Detection for SAR Imagery Using Hidden Markov Models.IEEE Trans On GRS.39(1), 2001:46～54.
[122]张翠,郦苏丹,王正志,SAR图像目标分割与方位角估计,国防科技大学学报,2001,23(5):74～78.
[123]黄培康.雷达目标特征信号.北京:宇航出版社.1987年8月.
[124] w.mbvlab.wpafb.af.mil/public/MBVDATA
[125] Liviu I V, et al.Multi～criterion vehicle pose estimation for SAR～ATR,Proc.SPIE, 3721:497～506.
[126]种劲松,朱敏慧,合成孔径雷达图像舰船目标检测与分析,现代雷达,第25卷,第8期,2003年8月.
[127]邹焕新,SAR图像舰船目标与航迹检测方法研究,国防科技大学博士学位论文,2003.
[128] Bahnu B, et al. Recognition of articulated objects in SAR images. In Proceedings of the ARPA Image Understanding Workshop,February,1996:1237～1250.
[129] Reuven Meth.Target Characterization And Matching In Synthetic Aperture Radar Imagery, Doctor’s dissertation, The University of Maryland, college Park, 1998.
[130] Meth R, Chellappa R, Kuttikkad S.Target aspect estimation from single and multi～pass SAR images, IEEE, 1998:2745～2748.
[131] Meth R.Target/shadow segmentation and aspect estimation in Sythetic Aperture Radar Imagery, SPIE ,1998,Vol.3370:188～196.
[132] Xu D X,et al.Pose estimation in SAR using an information theoretic criterion, Proc.of SPIE, 1998:218～229
[133] Yanting Dong, Lawrence Carin, Rate～Distortion analysis of pose estimation via multi～aspect scattering data,2001.
[134] Shawn D H . Calculating the orientation of a rectangular target in SAR imagery.IEEE, 1992.
[135] John A Richards.Target model generation from multiple synthetic aperture radar images.Doctor’s Thesis, 2001, MIT.
[136] Robert A W, et al.Markov random field segmentation methods for SAR target chips, SPIE, 1999,Vol.3721:463～473.
[137] Runkle P R, et al . Hidden markov model for multi-aspect target classification.IEEE Trans on Signal Processing, 1999, 47 (7):2035～2040.
[138] Jinfei Wang, Philip J H.Use of the hough transform in automatic lineament detection, IEEE Trans.on Geosc.Remote Sensing,1990, 28(7):561～566.
[139]吴翊,李永乐,胡庆军,应用数理统计,研究生教材,长沙,国防科技大学出版社,1995
[140]郦苏丹,李光侠,张翠,王正志,一种SAR图像中目标姿态估计的综合方法,信号处理,Vol.19,No.5,2003
[141] Sandirasegaram N M.Automatic Target Recognintion in SAR Imagery using aMLP Neural Network.Defence R&D Canada～Ottawa, Ottawa.2002, 11.
[142] Zhao Q, Xu D and Principe J C.Pose Estimation For Sar Automatic Target Recognition. Proceedings of the DARPA Image Understanding Workshop (IUW'98), 827～831.Monterey, California.1998.
[143] Anil K J, et al. Statistical pattern recognition:a review. IEEE Transactions on Pattern Analysis and Machine Intelligence, January 2000,22(1):4～37.
[144]孙即祥等著.现代模式识别.长沙:国防科技大学出版社.2002, 1.
[145] Simon Haykin著,叶世伟,史忠植译.神经网络原理.北京:机械工业出版社.2004, 5.
[146] DeVore M D, O’Sullivan J A.Perfromance Complexity Study of Several Approaches to ATR from SAR Images. IEEE Transactions on Aerospace and Electronic Systems, April 2002,38(2):632～648.
[147] Qun Zhao, Jose C P . Support Vector Machines for SAR Automatic Recognition.IEEE Transactions on Aerospace and Electronic Systems, April 2001,37(2):643～654.
[2]刘永坦.雷达成像技术.哈尔滨:哈尔滨工业大学出版社,1999.
[3]张直中.微波成像技术.北京:科学出版社.1990.
[4]朱述龙,张占睦.遥感图像获取与分析.北京:科学出版社,2000.
[5] [美] Skolnik M. I.著,王军等译.雷达手册.北京:电子工业出版社,2003.
[6]魏钟铨等.合成孔径雷达卫星.国家863计划308主题空间信息获取与处理系统专著,北京:科学出版社,2001.
[7]舒宁.雷达遥感原理.武汉:武汉测绘科技大学出版社,2000.
[8]谢寿生,徐永进.微波遥感技术与应用.北京:电子工业出版社,1987.
[9]张直中.机载和星载合成孔径雷达导论.北京:电子工业出版社,2003.
[10] [法] Maitre H.著,孙洪译.合成孔径雷达图像处理.北京:电子工业出版社,2003.
[11]保铮等.雷达成像技术.北京:电子工业出版社,2003.
[12]第二届中国合成孔径雷达会议论文集.南京,2005.
[13] Dudgeon D E, Lacoss R T.An Overview of Automatic Target Recognition, Lincoln Laboratory Journal, 1993, 6(1):3～10.
[14] Kreithen D E, et al.Discriminating Targets from Clutter. The Lincoln Laboratory Journal, 1993, 6(1):25～51.
[15] Quoc H Pham, et al.An efficient end-to-end feature based system for SAR ATR.SPIE, Vol 3370:519～529.
[16] Alberto L, Carcloso L D.Computer Aided Recognition of Man～made Structures in Aerial Photograghs.Naval Postgraduate School.AD report.Dec.1999.
[17] Special Issue on Advances in Synthetic Aperture Radar. IEE Proceedings Radar, Sonar & Navigation, 2003, 150(3).
[18] Novak L M, et al. Performance of a High～Resolution Polarimetric SAR Automatic Target Recognition System. The Lincoln Laboratory Journal, 1993, 6(1):11～24.
[19] Novak L M, et al. Effects of Polarization and Resolution on the Performance of a SAR Automatic Target Recognition System. The Lincoln Laboratory Journal, 1995, 8(1):49～67.
[20] Timothy D R, et al . SAR ATR-so what’s the problem? -an MSTARperspective.SPIE Vol. 3721, 1999:662～672.
[21] Lee J S.Digital image enhancement and noise filtering by use of local statistics, IEEE Trans. Pattern Analysis and Machine Intelligence, 1980, 2(2):165～168.
[22] Kuan D T. Sawchuk A.A. and Strand T.C., et al, Adaptive noise smoothing filter for images with signal～dependent noise, IEEE Trans. Pattern Analysis and Machine Intelligence, 1985, 7(2):165～177.
[23] Frost V S, et al.A model for radar images and its application to adaptive digital filtering of multiplicative noise, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1982, 4(2):157～165.
[24] Lopes A, Touzi R, Nezry E.Adaptive speckle filters and scene heterogeneity, IEEE Trans.Geoscience and Remote Sensing, 1990, 28(6):992～1000.
[25] Meer P , Park R H ,Cho K.Multi～resolution adaptive image smoothing, CVGIP, 1994, 56:140～148.
[26] Ranganath S. Image filtering using multi～resolution representations, IEEE Trans. Pattern Analysis and Machine Intelligence, 1991, 13(5):426～440.
[27] Bruno Aiazzi, Luciano Alparone, Stefano Baronti . Multiresolution texture analysis of SAR images.SPIE 3497:90～98.
[28] Donoho D L, Iohnstone I M.Adapting to unknown smoothness via wavelet shrink, Journal of the American Statistical Assoc.1995, 90(432):1200～1224.
[29]刘峰.基于小波变换的图像扩散滤波方法.中国科学E辑,2006,36 (6):668～677.
[30] Sveinsson J R, Benediktsson J.A, Speckle Reduction in the Complex wavelet Domain, In:Proceedings of IGARSS 2001, CD Rom, Sydney, Australia, July 9～13, 2001.
[31] Lopes, Touzi R, Nezry E.Adaptive Speckle Filters and Scene Heterogeneity, IEEE Trans. Geoscience and Remote Sensing, 1990, 28(6):992～1000.
[32] Lopes, et al, Maximum A Posteriori Speckle Filteringand First Order Textural Models in SAR Images, Proc. IGARSS'90, 1990, 3:2409～2412.
[33] German S, German D.Stochastic Relaxation, Gibbs Distribution, and the Bayesian Restoration of Images, IEEE Trans. Pattern Analysis and Machine Intelligence, 1984, PAMI 6 (6):721～741.
[34] White R G.A Simulated Annealing Algorithm for SAR and MTI Images Cross～section Estimation, Proc.SPIE, 1994, 2316:137～145.
[35] McConnell, et al, Radar Cross～section Estimation of SAR Images, Proc. SPIE,1995, 2584:164～175.
[36] Datcu M, Seidel K, Walessa M. Spatial Information Retrieval from Remote～Sensing Images～Part II : Gibbs～Markov Random Fields, IEEE Trans. Geosci. Remote Sensing, 1998, 36(5):1431～1445.
[37] Walessa M, Datcu M. Model～Based Despeckling and Information Extraction from SAR Images, IEEE Trans. Geosci. Remote Sensing, 2000, 38(5):2258～2269.
[38] Schou J, Skriver H.Restoration of Polarimetric SAR Images Using Simulated Annealing, IEEE Trans. Geosci. Remote Sensing, 2001, 39(9):2005～2016.
[39] Bratsolis E, Sigelle M.Fast SAR Image Restoration, Segmentation, and Detection of High～Reflectance Regions, IEEE Trans. Geoscience and Remote Sensing, 2003, 41(2):2890～2899.
[40] Crouse M S, Nowak R D,Baraniuk R C.Wavelet～based signal processing using hidden markov models, IEEE Trans. Signal Processing, 1998, 46(4):886～902.
[41] Hua Xie, Pierce L E,Ulaby F T.SAR speckle reduction using wavelet denoising and Markov random field modeling, IEEE Trans.on Geosci and Remote Sensing, 2002, 40(10):2196～2212.
[42] Xin XU, Deren LI, Hong Sun.Multiscale SAR image segmentation using a double markov random field model.IEEE Proceedings.of Seventh International Symposium on Signal Processing and Its Applications, 2003, Vol.1:349～352.
[43]王爱民,沈兰荪.图像分割研究综述.测控技术,2000 (5):1～5.
[44] Cao Lanying, Zhang Kunhui, Xia Liangzheng.SAR Image segmentation by 2-D fussy entropy . IEEE Proceedings. of Geoscience and Remote Sensing Symposium, 2004, Vol.6:3798～3801.
[45]燕英,周荫清.基于分割途径的SAR单视图像斑点噪声抑制方法.北京航空航天大学学报,2003 (2):132～135.
[46] Objective evaluation of four sar image segmentation algorithms.ADA391936.
[47] Jason B G, Steven C G, Gregory J P.An objective evaluation of four SAR image segmentation algorithms.SPIE Vol. 4382:346～357.
[48] Evaluation of synthetic aperture radar image segmentation algorithms in the context of automatic target recognition.ADA421104.
[49]邓炜.SAR图像处理方法研究.西北工业大学博士论文,2000.
[50]刘振华.SAR图像处理及融合研究.北京航空航天大学博士论文,2003.
[51]薛景浩,章毓晋,林行刚.SAR图像基于Rayleigh分布假设的最小误差阈值化分割.电子科学学刊,1999 (2):219～225.
[52] Fjortoft R, et al . An optimal multiedge detector for SAR image segmentation.IEEE Transactions on Geoscience and Remote Sensing, 1998: 793～802.
[53] Cook R, McConnell I, Oliver C J.MUM(Merge Using Moments) segmentation for SAR images.SPIE, 2316, 1994:92～103.
[54] Stewart D, et al . Optimal approach to SAR image segmentation and classification.IEE Proceedings of Radar, Sonar and Navigation, 2000, Vol 147 (3):134～142.
[55] Robert A, et al.MRF based algorithms for segmentation of SAR images. ICIP Chicago 1998,3:770～774.
[56]高贵,计科峰,匡纲要,李德仁.基于各向异性热扩散方程的SAR图像分割方法.信号处理,2006,22 (1):105～109.
[57]何勇.分形方法在SAR图像区域分割中的应用.武汉大学硕士论文,2004.
[58] William Irving,Gil Ettinger. Classification of Targets in Synthetic Aperture Radar Imagery Via Quantized Grayscale Matching.Proc.SPIE,1999,3721:320～331.
[59] Bahnu B, et al.Recognition of articulated objects in SAR images. In Proceedings of the ARPA Image Understanding Workshop , February,1996:1237～1250.
[60] By-Her Wang . An Automatic Target Recognition System For SAR Imagery.Doctor’s dissertation, Stanford University, Nov. 1997.
[61] Ettinger G J, et al.A probabilistic optimization approach to SAR feature matching.Algorithms for Synthetic Aperture Radar III, Proc. SPIE, April 1996, 2757:318～329.
[62] Robert M. Haralick, et al.The Topographic Primal Sketch.The International Journal of Robotics Research, Spring 1983,2 (1):50~72.
[63] Ryan T W, et al . SAR target indexing with hierarchical distance transforms.Algorithms for Synthetic Aperture Radar Imagery III, Proc SPIE, April 1996,2757:243～252.
[64] Pei-Chun Chiang, Thomas O. Binford.Generic, Model-Based Edge Estimation in the Image Surface.1-10.
[65] Touzi R, Lopes A, Bousquet P.A statistical and geometrical edge detector forSAR images.IEEE Trans. Geosci. Remote Sensing, Nov. 1988,26:764～773.
[66] Ward K D.Compound Representation of High Resolution Sea Clutter.Electron,Lett, 1981, 7:561～565.
[67] Besag J, et al.On the statistical analysis of dirty pictures, 1986, 48(3):259–302.
[68] Park J M, Song W J, Pearlman W A. Speckle filtering of SAR images based on adaptive windowing, IEE～proc.Vis.Image Signal Process, 1999, 146 (4):191～197.
[69] Rohling H.Radar CFAR thresholding in clutter and multiple target situations, IEEE Transactions on Aerospace and Electronic Systems, 1983, 19(4):608～621.
[70]蔡红苹,基于小波变换的去噪方法研究,国防科技大学研究生院学位论文, 2003.
[71] Arsenault H H,et al.Properties of Speckle Integrated with a Finite Aperture and Logarithmically Transformed, J.Opt.Soc Am, 1976, 11(22):1160～1168.
[72] Oliver C, Quegan S.Understanding Synthetic Aperture Radar Images, Artech House:Boston, 1998.
[73] Achim A, Bezerianos A, and Tsakalides P.Novel Bayesian multiscale method for speckle removal in medical ultrasound images, IEEE Trans. Med Imag, 2001, 20(8):772～783.
[74]陈建祥,贾承丽,匡纲要,改进的基于结构检测的SAR图像去斑算法,计算机仿真, 2005, 22(9):25～28.
[75] Frery A C, Lucca E V D.SAR segmentation algorithms:a quantitative assessment.IEEE Proceedings of Geoscience and Remote Sensing Symposium, 1999, Vol.2:1265～1267.
[76] Chumsamrong W, Thitimajshima P, Rangsanseri Y.Synthetic aperture radar (sar) image segmentation using a new modified fuzzy c-means algorithm.IEEE Trans. Geoscience and Remote Sensing Symposium, 2000, 2:624～626.
[77]盛国芳.SAR图像去噪与分割算法的研究.西安电子科技大学硕士论文,2003.
[78]李禹.SAR图像机动目标检测与鉴别技术研究,国防科学技术大学博士论文,2007.
[79]郦苏丹.SAR图像特征提取与目标识别方法研究.国防科学技术大学博士论文,2001.
[80] Otsu N. A Threshold Selection Method from Gray～Level Histogram [J]. IEEE Trans. Systems, Man, and Cybernetics, 1979,9 (1):62～66.
[81] Liu Jianzhuang, Li Wenqing, Tian Yupeng. Automatic Thresholding of Gray～Level Pictures Using Two～Dimensional Otsu Method [A].Proc.IEEE ISCAS '91 [C].1991:325～327.
[82]刘建庄,栗文清.灰度图像的二维Otsu自动阈值分割法[J].自动化学报, 1993, 19 (1):101～105.
[83]芦蓉,沈毅.一种改进的二维直方图的图像阈值分割方法[J].系统工程与电子技术, 2004, 26 (10):1487～1490.
[84]郝颖明,朱枫.二维Otsu自适应阈值的快速算法[J].中国图象图形学报, 2005, 10 (4):484～488.
[85]梁光明,刘东华,李波,唐朝京.二维Otsu自适应阈值分割算法的改进[J].自动化技术与应用, 2002, 21 (5):43～47.
[86]朱峻,王世晞,计科峰,粟毅,一种适用于SAR图像的二维Otsu改进算法,中国图形图象学报,已录用.
[87] Pentlan A.Fractal～based description of nature scences.IEEE Trans.On Pattern Analyses and Machine Intelligence, 1984, Vol 10:661～674.
[88] Mandelbrot B B.The fractal geometry of nature.New York:Freeman and Co. 1983.
[89]杜干,张守宏.高阶分形特征在雷达信号检测中的应用.电子学报,2000,28 (3):90～92.
[90] Dong P . Test of a new lacunarity estimation method for image texture analysis.International Journal of Remote Sensing, 2000, Vol 21(17):3369～3373.
[91] Soe Win Myint, Nina Lam.A study of lacunarity～based texture analysis approaches to improve urban image classification.Computers, Environment and Urban Systems, 2005, Vol 29:501～523.
[92]赵巨波,万建伟,王永杰.基于分形理论的目标检测.电子学报,2005,33(12):2524～2526.
[93]安国成,刘振华,于文震,基于分形特征的高分辨率SAR图像分类,现代雷达,2006,28(6):26～29.
[94]薛笑荣,张艳宁,赵荣椿.基于分形理论的SAR图像分割.计算机工程与应用,2003:27～29.
[95] Gan Du, Tat Soon Yeo. A novel lacunarity estimation method applied to SAR image segmentation.IEEE Transactions on Geoscience and Remote Sensing,2002:2687～2691.
[96]李厚强,刘政凯,林峰.基于分形理论的航空图像分类方法.遥感学报,2001,5(5):353～358.
[97] Novak L M, et al.Effects of Polarization and Resolution on SAR ATR.IEEE Trans. On Aerospace and Electronic Systems, 1997, 33(1):102～116.
[98] Nikola S S, et al.Multiresolution detection of coherent radar targets.IEEE Trans. On Image Processing, 1997, 6 (1):21～35.
[99] Fosgate C H, et al. Multiscale segmentation and anomaly enhancement of SAR imagery.IEEE Trans. On Image Processing, 1997, 6 (1):7～20.
[100] Irving W W, Novak L M, Willsky A S.A multiresolution approach to discrimination in SAR imagery.IEEE Trans. On Aerospace and Electronic Systems, 1997, 33 (4):1157～1169.
[101] David Howard, Jim Schroeder.Multiscale models for target detection and background discrimination in synthetic aperture radar imagery.Digital Signal Processing, 1999, 9:149～161.
[102] Li Yu, Ji Kefeng, Su Yi.Quantitative analysis of statistical models for typical terrains in SAR data. Proceedings of 2006 CIE International Conference on Radar, Vol 1:696～699,(EI:073310760134).
[103] Ronald Caves, Shaun Quegan, Richard White.Quantitative comparison of the performance of SAR segmentation algorithms.IEEE Transactions on Image Processing, 1998,Vol.7:1534～1546.
[104] Delves L M, et al . Comparing the perfoemance of SAR segmentation algorithms.International Journal of Remote Sensing, Vol. 13, 1992:2122～2149.
[105] Gregory J. Power.Multimetric inter～algorithmic evaluation of SAR image segmentation algorithms.Proceedings of SPIE, Vol. 4382, Algorithms for Synthetic Aperture Radar Imagery VIII, April 2001:330～337.
[106] Leslie M. Novak, Gregory J. Owirak, William W.Irving, Performance of 10～and 20～target MSE classifiers, IEEE Transactions on Aerospace and Electronic Systems VOL.36, No.4, Oct.2000:1279～1289
[107] Eric R. Keydel, MSTAR Extended Operating Conditions:A Tutorial, SPIE Vol 2757, 1996:228～242
[108] Eric R. Keydel, Signature Prediction for Model～Based Automatic TargetRecognition, SPIE Vol.2757, 1996:306～317.
[109] Joseph Diemunsch, John Wissinger, Moving and Stationary Target Acquisition and Recognition(MSTAR) Model～Based Automatic Target Recognition:Search Technology for a Robust ATR, SPIE, Vol.3370, 1998, p481～492.
[110] William Irving, Gil Ettinger, Classification of Target in Synthetic Aperture Radar Imagery via Quantized Grayscale Matching, SPIE Vol.3721, 1999:320～331.
[111] Liviu I.Voicu, Ron Patton, Harley R. Myler, Multi～criterion vehicle pose estimation for SAR ATR, SPIE Vol.3721, 1999:497～506.
[112] Walessa M. Bayesian information extraction from SAR images, Ph.D.thesis, Univ. Siegen, Siegen, Germany, 2001.
[113] Principe J, Zhao Q,Xu D.A novel ATR classifier exploiting pose information.In Proceedings of Image Understanding Workshop, Monterey, CA ,1998:833～836.
[114] Munchurl Kim, Focus of Attention Based on Gamma Kernels for Automatic Target Recognition, doctor’s dissertation, University of FLORIDA, 1996
[115]计科峰,匡纲要,郁文贤,基于线性回归的SAR目标方位角估计方法,现代雷达,Vol. 25(2),2003,15～18.
[116] Thomas O B, et al.Context and Quasi～invariant in ATR with SAR Imagery, http://robotics.stanford.edu/groups/reality/binford.html
[117] By～Her Wang,“An Automatic Target Recognition System For SAR Imagery”, Doctor’s dissertation, Stanford University, Nov.1997.
[118]计科峰,匡纲要,粟毅,郁文贤,SAR图像目标峰值特征提取与方位角估计方法研究,宇航学报,2004,25(1):102～108。
[119]高贵,高分辨率SAR图像目标特征提取研究,国防科技大学硕士学位论文,2003。
[120]计科峰,高分辨率SAR图像特征提取与分类方法研究,国防科技大学博士学位论文,2003。
[121] Paul Runkle,et al.Multi～Aspect Target Detection for SAR Imagery Using Hidden Markov Models.IEEE Trans On GRS.39(1), 2001:46～54.
[122]张翠,郦苏丹,王正志,SAR图像目标分割与方位角估计,国防科技大学学报,2001,23(5):74～78.
[123]黄培康.雷达目标特征信号.北京:宇航出版社.1987年8月.
[124] w.mbvlab.wpafb.af.mil/public/MBVDATA
[125] Liviu I V, et al.Multi～criterion vehicle pose estimation for SAR～ATR,Proc.SPIE, 3721:497～506.
[126]种劲松,朱敏慧,合成孔径雷达图像舰船目标检测与分析,现代雷达,第25卷,第8期,2003年8月.
[127]邹焕新,SAR图像舰船目标与航迹检测方法研究,国防科技大学博士学位论文,2003.
[128] Bahnu B, et al. Recognition of articulated objects in SAR images. In Proceedings of the ARPA Image Understanding Workshop,February,1996:1237～1250.
[129] Reuven Meth.Target Characterization And Matching In Synthetic Aperture Radar Imagery, Doctor’s dissertation, The University of Maryland, college Park, 1998.
[130] Meth R, Chellappa R, Kuttikkad S.Target aspect estimation from single and multi～pass SAR images, IEEE, 1998:2745～2748.
[131] Meth R.Target/shadow segmentation and aspect estimation in Sythetic Aperture Radar Imagery, SPIE ,1998,Vol.3370:188～196.
[132] Xu D X,et al.Pose estimation in SAR using an information theoretic criterion, Proc.of SPIE, 1998:218～229
[133] Yanting Dong, Lawrence Carin, Rate～Distortion analysis of pose estimation via multi～aspect scattering data,2001.
[134] Shawn D H . Calculating the orientation of a rectangular target in SAR imagery.IEEE, 1992.
[135] John A Richards.Target model generation from multiple synthetic aperture radar images.Doctor’s Thesis, 2001, MIT.
[136] Robert A W, et al.Markov random field segmentation methods for SAR target chips, SPIE, 1999,Vol.3721:463～473.
[137] Runkle P R, et al . Hidden markov model for multi-aspect target classification.IEEE Trans on Signal Processing, 1999, 47 (7):2035～2040.
[138] Jinfei Wang, Philip J H.Use of the hough transform in automatic lineament detection, IEEE Trans.on Geosc.Remote Sensing,1990, 28(7):561～566.
[139]吴翊,李永乐,胡庆军,应用数理统计,研究生教材,长沙,国防科技大学出版社,1995
[140]郦苏丹,李光侠,张翠,王正志,一种SAR图像中目标姿态估计的综合方法,信号处理,Vol.19,No.5,2003
[141] Sandirasegaram N M.Automatic Target Recognintion in SAR Imagery using aMLP Neural Network.Defence R&D Canada～Ottawa, Ottawa.2002, 11.
[142] Zhao Q, Xu D and Principe J C.Pose Estimation For Sar Automatic Target Recognition. Proceedings of the DARPA Image Understanding Workshop (IUW'98), 827～831.Monterey, California.1998.
[143] Anil K J, et al. Statistical pattern recognition:a review. IEEE Transactions on Pattern Analysis and Machine Intelligence, January 2000,22(1):4～37.
[144]孙即祥等著.现代模式识别.长沙:国防科技大学出版社.2002, 1.
[145] Simon Haykin著,叶世伟,史忠植译.神经网络原理.北京:机械工业出版社.2004, 5.
[146] DeVore M D, O’Sullivan J A.Perfromance Complexity Study of Several Approaches to ATR from SAR Images. IEEE Transactions on Aerospace and Electronic Systems, April 2002,38(2):632～648.
[147] Qun Zhao, Jose C P . Support Vector Machines for SAR Automatic Recognition.IEEE Transactions on Aerospace and Electronic Systems, April 2001,37(2):643～654.