高分辨率SAR图像中车辆目标的检测
摘要
随着雷达对地观测技术的日趋发展, SAR图像数据收集能力的不断增强, SAR图像的自动目标识别技术已逐渐成为目前该领域的研究热点。其中,目标检测是SAR图像自动目标识别的基础,其结果的好坏直接影响着后续目标特征的提取,并最终影响目标识别与分类的精度。坦克、导弹发射车、装甲车等地面车辆是SAR战场监视和对地探测的重要目标,对SAR图像中车辆目标的自动检测研究具有较高的应用价值。本文对含有车辆目标的真实SAR图像进行了图像抑噪和目标检测的研究。
首先,介绍了SAR的成像原理、SAR图像的目标特点和SAR图像的统计特性,通过对含有车辆目标的真实SAR图像数据进行统计特性分析,得出几乎在整个SAR图像的灰度分布范围内,SAR图像的灰度概率分布基本上服从σ取SAR图像灰度均方差时的瑞利分布。
其次,介绍了相干斑噪声的产生机理和模型,在传统滤波方法的基础上,结合Lee算法中地物的分类思想和中值滤波,提出了一种改进的小波抑噪方法,通过对各种方法抑噪效果的评价,得出改进的小波抑噪法在抑制噪声和保持图像细节信息方面均比较优。
最后,介绍了恒虚警率检测技术和三种恒虚警率检测器,在恒虚警率(CFAR)统计检测理论的基础上,对常规双参数CFAR检测方法进行了分析,得出因SAR图像数据的统计特性与高斯分布有着明显的差异,导致实验结果中的实际虚警率与理论虚警率偏离过大。结合SAR图像的灰度概率分布服从瑞利分布的先验知识,给出了基于瑞利分布的CFAR检测方法。考虑到CFAR检测模板过大,而造成SAR图像30cm宽的外边缘不能被检测,结合数学形态学提出了一种改进的CFAR检测方法。各种检测算法对真实SAR图像的检测结果表明改进的CFAR检测算法具有相对较优的检测性能。
The daily development of the earth observation technology via radar and the constantly enhanced ability to collecting SAR images have gradually made the Automatic Target Recognition (ATR) technology for synthetic aperture radar (SAR) images a research hot in the field currently. Target detecting, the result of which directly affects the extracting of target features subsequently and will finally affect the precision of target recognizing and classifying, is the basis of the automatic target recognition for SAR images. Ground vehicle like tanks, missile launching vehicle and panzers are important targets in SAR battlefield surveillance and earh observation. It is highly practical to research the method of automatically detecting the vehicle target in SAR images. This paper focuses on researching the target detecting and speckle noise suppression on the basis of real SAR images which contain vehicle targets.
Firstly, the paper covered the SAR imaging principle, the characters of the targets in the SAR images and the the statistical features. It is concluded from the analysis on the statistical features of the real SAR image which contain vehicle targets that the gray probability distribution of SAR image is basically subject to the Rayleigh distribution (when evaluatingσof the SAR image’s mean square error) throughout the whole gray-scale distribution of the SAR image.
Secondly, the paper expatiated on the Speckle noise generating mechanism and model. On the basis of traditional filtering method and the combination of Lee algorithm and median filtering, proposed an improved wavelet method for noise suppression. The evaluation of various methods for noise suppression shows that the improved wavelet method in suppressing noise and preserving image details are more superior.
Finally, the paper described the CFAR detection techniques and three kinds of CFAR detectors and analyzed the conventional two-parameter CFAR detection method based on the constant false alarm rate (CFAR) detection theory. It is concluded that the deviation of the actual false alarm rate from the theory false alarm rate is too large due to the clear difference between statistical characteristics of SAR image and the Gaussian distribution. It provided the CFAR detecting method which is based on Rayleigh distribution according to the priori knowledge that the probability distribution of SAR images obey Rayleigh distribution.Considering that the edge of SAR image will not be detected because of the over sized CFAR decting template, we provided an improved CFAR deceting method on the combination of Morphological. The result of the test on SAR image using various detecting methods shows that CFAR detecting method is more superior on detecting performance.
首先,介绍了SAR的成像原理、SAR图像的目标特点和SAR图像的统计特性,通过对含有车辆目标的真实SAR图像数据进行统计特性分析,得出几乎在整个SAR图像的灰度分布范围内,SAR图像的灰度概率分布基本上服从σ取SAR图像灰度均方差时的瑞利分布。
其次,介绍了相干斑噪声的产生机理和模型,在传统滤波方法的基础上,结合Lee算法中地物的分类思想和中值滤波,提出了一种改进的小波抑噪方法,通过对各种方法抑噪效果的评价,得出改进的小波抑噪法在抑制噪声和保持图像细节信息方面均比较优。
最后,介绍了恒虚警率检测技术和三种恒虚警率检测器,在恒虚警率(CFAR)统计检测理论的基础上,对常规双参数CFAR检测方法进行了分析,得出因SAR图像数据的统计特性与高斯分布有着明显的差异,导致实验结果中的实际虚警率与理论虚警率偏离过大。结合SAR图像的灰度概率分布服从瑞利分布的先验知识,给出了基于瑞利分布的CFAR检测方法。考虑到CFAR检测模板过大,而造成SAR图像30cm宽的外边缘不能被检测,结合数学形态学提出了一种改进的CFAR检测方法。各种检测算法对真实SAR图像的检测结果表明改进的CFAR检测算法具有相对较优的检测性能。
The daily development of the earth observation technology via radar and the constantly enhanced ability to collecting SAR images have gradually made the Automatic Target Recognition (ATR) technology for synthetic aperture radar (SAR) images a research hot in the field currently. Target detecting, the result of which directly affects the extracting of target features subsequently and will finally affect the precision of target recognizing and classifying, is the basis of the automatic target recognition for SAR images. Ground vehicle like tanks, missile launching vehicle and panzers are important targets in SAR battlefield surveillance and earh observation. It is highly practical to research the method of automatically detecting the vehicle target in SAR images. This paper focuses on researching the target detecting and speckle noise suppression on the basis of real SAR images which contain vehicle targets.
Firstly, the paper covered the SAR imaging principle, the characters of the targets in the SAR images and the the statistical features. It is concluded from the analysis on the statistical features of the real SAR image which contain vehicle targets that the gray probability distribution of SAR image is basically subject to the Rayleigh distribution (when evaluatingσof the SAR image’s mean square error) throughout the whole gray-scale distribution of the SAR image.
Secondly, the paper expatiated on the Speckle noise generating mechanism and model. On the basis of traditional filtering method and the combination of Lee algorithm and median filtering, proposed an improved wavelet method for noise suppression. The evaluation of various methods for noise suppression shows that the improved wavelet method in suppressing noise and preserving image details are more superior.
Finally, the paper described the CFAR detection techniques and three kinds of CFAR detectors and analyzed the conventional two-parameter CFAR detection method based on the constant false alarm rate (CFAR) detection theory. It is concluded that the deviation of the actual false alarm rate from the theory false alarm rate is too large due to the clear difference between statistical characteristics of SAR image and the Gaussian distribution. It provided the CFAR detecting method which is based on Rayleigh distribution according to the priori knowledge that the probability distribution of SAR images obey Rayleigh distribution.Considering that the edge of SAR image will not be detected because of the over sized CFAR decting template, we provided an improved CFAR deceting method on the combination of Morphological. The result of the test on SAR image using various detecting methods shows that CFAR detecting method is more superior on detecting performance.
引文
[1] H.C. MacDonald. Geologic Evaluation of Radar Imagery from Darien Province Panama. Modern Geology. 1969, (1): 1-63
[2]李景文合成孔径雷达动目标检测与成像.北京航空航天大学博士论文.1999.
[3]郭华东,雷达对地观测理论与应用,2000年,科学出版社
[4]张澄波.综合孔径雷达.科学出版社. 1989: 538-602 185-298
[5] D.L. Evans, T.G. Farr, et al. Radar Polarimetry: Analysis Tools and Applications. IEEE Trans. on GRS. 1988, 26(6): 774-789
[6] J.B. Boisvert, T.J. Pultz, R.J. Brown, B. Brisco. Potential of Synthetic Aperture Radar for Large-Scale Soil Moisture Monitoring: A Review. Canadian Journal of Remote Sensing. 1995, 22(1): 2-13
[7] Y. Grevier, T.J. Pultz, T. I. Lukowski. T. Toutin. Temporal Analysis of ERS-1 SAR Backscatter for Hydrology Applications. Canadian Joural of Remote Sensing. 1995,22(1): 65-76
[8] C. Dobson. Soil Moisture Measurement Using Synthetic Aperture Radar. IGARSS’81. 1981: 427-436
[9] H. Skriver, J.K. Ji, J. Dall, K. Woelders, A. Thomsen, A Multi-Temporal and Multi-Frequency Study of Polarimetric Signatures of Soil and Crops. European Conference on Synthetic Aperture Radar, Germany, 1996: 481-484
[10] M.W.J. Davidson, R. SteingieBer, W. Kuhbauch. Assessing Agricultural Land Use Early During the Growing Season Using Multi-Frequency and Multi- Polarisation SIR-C Backscatter Features. European Conference on Synthetic Aperture Radar, Germany, 1996: 473-476
[11] F.M. Seifert, H. Kietzmann, M. Zink. Monitoring Central European Forests Using SIR-C/X-SAR Data. European Conference on Synthetic Aperture Radar, Germany, 1996: 461-464
[12] F.T. Ulaby, Whitt, M.C. Dobson. Measuring the Propagation Properties of A Forest Canopy Using a Polarimetric Scatterometer. IEEE Transaction AP. 1990, 38(2): 251-258
[13] M.L. Imhoff, M. Story, C. Vermillion, et al. Forest Canopy Characterization and Vegetation Penetration Assessment with Spaceborne Radar. IEEE Trans. on GRS,1986, 24(4): 535-542
[14] Sader, A. Steven. Forest Biomass, Canopy Structure, and Species Composition Relationships with Multipolarization L-Band Synthetic Aperture Radar Data. Photogrammetric Engineering and Remote Sensing. 1987, 53(2): 193-202
[15] G.A. Efremov, V.S. Etkin, A.V. Smirnov. Radar Investigation of Sea Surface Disturbance. Proceedings of IGARSS’92, Houston, 1992: 710-712
[16] K.Tomiyasu, Tutorial Review of Synthetic Aperture Radar with Applications to Imaging of the Ocean Surface. Proceedings of IEEE. 1978, 66(5): 563-583
[17] C.Elachi. Spaceborne Imaging Radar: Geologic and Oceanographic Applications. Science. 1980, 209: 1073-1075
[18] M.L. Imhoff, M. Story, Et al. Monsoon Flood Boundary Delineation and Damage Assessment Using Spaceborne Imaging Radar and Landsat Data. Photogrammetric Engineering and Remote Sensing. 1987, 53(4): 405-413
[19]祁文杰.星载合成孔径雷达的军事应用研究.星载合成孔径雷达军事应用研究论文集. 1996: 1-6
[20] A. Freeman, D. Evans, J.J. VanZyl, SAR Applications in the 21st Century. European Conference on Synthetic Aperture Radar, Germany, 1996: 25-30
[21] R.L. Jordan. The Seasat-A Synthetic Aperture Radar System. IEEE J. of 1026-1032 and Beam Sharpening. IEEE AES. 1968, 4(6): 879-885 Oceanic Engineering. 1980,5(2): 154-164
[22] R.L. Bernstein. Seasat Special Issue I of the J. Geophys. Res. 1982, 87(C5)
[23] A.D. Kirwan, T.J. Ahrens. Seasat Special Issue II of the J. Geophys. Res. 1988, 88(C3)
[24]杨燕,一林,美国的天基雷达(SBR)计划, 2004年l2月第4期,探测与定位.
[25]孙佳,国外合成孔径雷达卫星发展趋势分析, 2007年2月第18卷第1期,装备指挥技术学院学报.
[26] Chris Oliber. Shaun Quegan. Understanding Synthetic Aperture Radar Images. Artech House.1998
[27]黄永红,毛士艺.星载合成孔径雷达多普勒参数估计.电子学报. 1994, 22(6):10-15
[28]刘纪元,李春升,周荫清.星载SAR信号处理的多普勒中心频率估计方法.北京航空航天大学学报. 1992, No. 2: 6-9
[29]李春升,李景文,周荫清.星载SAR数字成像处理及计算机仿真.宇航学报.1992, No. 4: 89-95
[30]李春升,李景文,周荫清.星载合成孔径雷达成像处理.电子学报. 1991,19(1): 20-24
[31]刘国庆,黄顺吉.星载SAR多普勒质心估计的新方法—幅度相关法.电子科学学刊. 1994, 16(1): 67-71
[32]李杰,向敬成,黄顺吉.合成孔径雷达慢运动目标成像处理的研究.电子科技大学学报. 1995, 24(2): 119-125
[33]黄永红,毛士艺,周荫清.星载SAR图象质量评估.信息获取与处理技术. 1995, No. 1: 1-9
[34]邓炜,赵荣椿.基于小波变换的SAR图像相干斑噪声消除方法研究.信号处理,第十七卷第一期2001年2月.
[35]王超,陈曦,张红.一种基于退化模型的高分辨率SAR去噪算法.遥感学报,第10卷第1期2006年1月.
[36]潘湘岳,宋建社,吴建新.基于数据融合的SAR图像斑点噪声抑制.雷达科学与技术,第6期2007年12月.
[37]石澄贤,夏德深.基于几何模型的SAR图像斑点噪声的抑制.信号处理,第21卷第5期2005年10月.
[38]万朋,王建国等.SAR图像弱反射地物边缘提取方法.信号处理.第16卷4期2000年.
[39]张名成,吴秀清,王鹏伟.一种自适应的合成孔径雷达图像目标检测方法.计算机工程与应用,2006年10月.
[40]孙慕涵,周荫清,徐华平,刘慧.结合形态学理论与Hough变换的SAR图像线目标检测方法.遥测遥控,第28卷第6期2007年11月.
[41]潘卓,高鑫,王岩飞,范俐捷.基于聚类的SAR图像快速目标检测.计算机应用研究,第8期2008年.
[42]贾承丽,赵凌君.基于遗传算法的SAR图像道路网检测方法.计算机学报.第30卷第7期2007年7月.
[43] Novak L.M., Halversen Shawn D., Owirka Gregory J., and Hiett Margarita. Effects of polarization and resolution on the performance of a SAR automatic target recognition system. The Lincoln Laboratory Journal, 1995,8(1):49-67.
[44] Blacknell D. Contextual information in SAR target detection. IEE Proceedings: Radar, Sonar and Navigation, 2001,148(1):41-47.
[45] Runkle P., Nguyen L.H., McClellan J.H., Lawrence L. Multi-aspect target detectionfor SAR imagery using hidden Markov models. IEEE Transactions on Geoscience and Remote Sensing , 2001,39( 1 ):46-55.
[46] Tan Hwee H.P., Ramanathan U. Intelligent selection of useful features for optimal feature-based classification. Proceedings of IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2000), 2000, 7: 3012–3014.
[47] A. Freeman, D. Evans, J.J. VanZyl, SAR Applications in the 21st Century. European Conference on Synthetic Aperture Radar, Germany, 1996: 25-30
[48] R.L. Jordan. The Seasat-A Synthetic Aperture Radar System. IEEE J. of 1026- 1032 and Beam Sharpening. IEEE AES. 1968, 4(6): 879-885 Oceanic Engineering. 1980,5(2): 154-164
[49] R.L. Bernstein. Seasat Special Issue I of the J. Geophys. Res. 1982, 87(C5)
[50] Valenzuela G.R.,and Laing M.B. Point-Scatterer Formulation of Terrain Clutter Statistics. Naval Research Laboratory Report7459,Washington DC,1972.
[51] Schleher D.C. Radar Detection in Log Normal Clutter. Proc.IEEE Int.Radar Conf.Radar’75,1975, 262-267.
[52] M.T.Rey, T.Drosopoulos, and D.Petrovic,”A search procedure for ships in RADARSAT imagery”, DREO Report No.1305,1996.
[53] Qingshan Jiang, Shengrui Wang, Djemel Ziou, and Ali EI Zaart,”Automatic detection for ship targets in RADARSAT SAR images from coastal regions”,Vision Interface’99,May 1999,Trois-Tivieres,Canada,pp.131-137.
[54] Lee J S,Digital image enhancement and noise filtering by use of local statistics [J].IEEE Transaction Pattern Analysis and Machine Intelligence,1980,2(2):165—168.
[55] Kuan D.T., Sawchuk A.A., Strand T.C., and Chavel P. Adaptive Restoration of Images with Speckle. IEEE Trans. on Acoustics, Speech and Signal Processing, 1987,35(3): 373-383.
[56] Lopes A., Touzi R., Nezry E. Adaptive Speckle Filters and Scene Heterogeneity. IEEE Trans. on Geoscience and Remote Sensing,1990, 28(6): 992-1000.
[57] Lee J.S. Refined Filtering of Image Noise Using Local Statistics. Computer Graphic and Image Processing,1981,15:380-389.
[58]边肇棋等,模式识别,清华大学出版社,2000.
[59]何友、关键、彭应宁、陆大著,雷达自动检测与恒虚警处理,清华大学出版社,1999年5月.
[60] Oliver Chris and Quegan Shaun. Understanding Synthetic Aperture Radar Images. Boston : Artech House, 1998.
[61] Rafael C. Gonzalez and Richard E. Woods著,阮秋琦阮宇智等译,数字图像处理(第二版),电子工业出版社,2008年11月。
[62] Wang Lin-Cheng,Der S.Z., Nasrabadi N.M. Automatic target recognition using a feature-decomposition and data-decomposition modular neural network. IEEE Transactions on Image Processing, 1998, 7 (8): 1113-1121.
[63]沈庭芝方子文编著.数字图像处理及模式识别.北京:北京理工大学出版社,1998.
[64] H.Rohling,”Radar CFAR thresholding in clutter and multiple target situations”, IEEE Transactions on Aerospace and Electronic Systems,1983,Vol.19,No.4,pp.608- 621.
[65] Chitroub S, Houacine A, Sansal B. Statistical Characterization and Modelling of SAR Images. Signal Processing,2002,82:69-92.
[2]李景文合成孔径雷达动目标检测与成像.北京航空航天大学博士论文.1999.
[3]郭华东,雷达对地观测理论与应用,2000年,科学出版社
[4]张澄波.综合孔径雷达.科学出版社. 1989: 538-602 185-298
[5] D.L. Evans, T.G. Farr, et al. Radar Polarimetry: Analysis Tools and Applications. IEEE Trans. on GRS. 1988, 26(6): 774-789
[6] J.B. Boisvert, T.J. Pultz, R.J. Brown, B. Brisco. Potential of Synthetic Aperture Radar for Large-Scale Soil Moisture Monitoring: A Review. Canadian Journal of Remote Sensing. 1995, 22(1): 2-13
[7] Y. Grevier, T.J. Pultz, T. I. Lukowski. T. Toutin. Temporal Analysis of ERS-1 SAR Backscatter for Hydrology Applications. Canadian Joural of Remote Sensing. 1995,22(1): 65-76
[8] C. Dobson. Soil Moisture Measurement Using Synthetic Aperture Radar. IGARSS’81. 1981: 427-436
[9] H. Skriver, J.K. Ji, J. Dall, K. Woelders, A. Thomsen, A Multi-Temporal and Multi-Frequency Study of Polarimetric Signatures of Soil and Crops. European Conference on Synthetic Aperture Radar, Germany, 1996: 481-484
[10] M.W.J. Davidson, R. SteingieBer, W. Kuhbauch. Assessing Agricultural Land Use Early During the Growing Season Using Multi-Frequency and Multi- Polarisation SIR-C Backscatter Features. European Conference on Synthetic Aperture Radar, Germany, 1996: 473-476
[11] F.M. Seifert, H. Kietzmann, M. Zink. Monitoring Central European Forests Using SIR-C/X-SAR Data. European Conference on Synthetic Aperture Radar, Germany, 1996: 461-464
[12] F.T. Ulaby, Whitt, M.C. Dobson. Measuring the Propagation Properties of A Forest Canopy Using a Polarimetric Scatterometer. IEEE Transaction AP. 1990, 38(2): 251-258
[13] M.L. Imhoff, M. Story, C. Vermillion, et al. Forest Canopy Characterization and Vegetation Penetration Assessment with Spaceborne Radar. IEEE Trans. on GRS,1986, 24(4): 535-542
[14] Sader, A. Steven. Forest Biomass, Canopy Structure, and Species Composition Relationships with Multipolarization L-Band Synthetic Aperture Radar Data. Photogrammetric Engineering and Remote Sensing. 1987, 53(2): 193-202
[15] G.A. Efremov, V.S. Etkin, A.V. Smirnov. Radar Investigation of Sea Surface Disturbance. Proceedings of IGARSS’92, Houston, 1992: 710-712
[16] K.Tomiyasu, Tutorial Review of Synthetic Aperture Radar with Applications to Imaging of the Ocean Surface. Proceedings of IEEE. 1978, 66(5): 563-583
[17] C.Elachi. Spaceborne Imaging Radar: Geologic and Oceanographic Applications. Science. 1980, 209: 1073-1075
[18] M.L. Imhoff, M. Story, Et al. Monsoon Flood Boundary Delineation and Damage Assessment Using Spaceborne Imaging Radar and Landsat Data. Photogrammetric Engineering and Remote Sensing. 1987, 53(4): 405-413
[19]祁文杰.星载合成孔径雷达的军事应用研究.星载合成孔径雷达军事应用研究论文集. 1996: 1-6
[20] A. Freeman, D. Evans, J.J. VanZyl, SAR Applications in the 21st Century. European Conference on Synthetic Aperture Radar, Germany, 1996: 25-30
[21] R.L. Jordan. The Seasat-A Synthetic Aperture Radar System. IEEE J. of 1026-1032 and Beam Sharpening. IEEE AES. 1968, 4(6): 879-885 Oceanic Engineering. 1980,5(2): 154-164
[22] R.L. Bernstein. Seasat Special Issue I of the J. Geophys. Res. 1982, 87(C5)
[23] A.D. Kirwan, T.J. Ahrens. Seasat Special Issue II of the J. Geophys. Res. 1988, 88(C3)
[24]杨燕,一林,美国的天基雷达(SBR)计划, 2004年l2月第4期,探测与定位.
[25]孙佳,国外合成孔径雷达卫星发展趋势分析, 2007年2月第18卷第1期,装备指挥技术学院学报.
[26] Chris Oliber. Shaun Quegan. Understanding Synthetic Aperture Radar Images. Artech House.1998
[27]黄永红,毛士艺.星载合成孔径雷达多普勒参数估计.电子学报. 1994, 22(6):10-15
[28]刘纪元,李春升,周荫清.星载SAR信号处理的多普勒中心频率估计方法.北京航空航天大学学报. 1992, No. 2: 6-9
[29]李春升,李景文,周荫清.星载SAR数字成像处理及计算机仿真.宇航学报.1992, No. 4: 89-95
[30]李春升,李景文,周荫清.星载合成孔径雷达成像处理.电子学报. 1991,19(1): 20-24
[31]刘国庆,黄顺吉.星载SAR多普勒质心估计的新方法—幅度相关法.电子科学学刊. 1994, 16(1): 67-71
[32]李杰,向敬成,黄顺吉.合成孔径雷达慢运动目标成像处理的研究.电子科技大学学报. 1995, 24(2): 119-125
[33]黄永红,毛士艺,周荫清.星载SAR图象质量评估.信息获取与处理技术. 1995, No. 1: 1-9
[34]邓炜,赵荣椿.基于小波变换的SAR图像相干斑噪声消除方法研究.信号处理,第十七卷第一期2001年2月.
[35]王超,陈曦,张红.一种基于退化模型的高分辨率SAR去噪算法.遥感学报,第10卷第1期2006年1月.
[36]潘湘岳,宋建社,吴建新.基于数据融合的SAR图像斑点噪声抑制.雷达科学与技术,第6期2007年12月.
[37]石澄贤,夏德深.基于几何模型的SAR图像斑点噪声的抑制.信号处理,第21卷第5期2005年10月.
[38]万朋,王建国等.SAR图像弱反射地物边缘提取方法.信号处理.第16卷4期2000年.
[39]张名成,吴秀清,王鹏伟.一种自适应的合成孔径雷达图像目标检测方法.计算机工程与应用,2006年10月.
[40]孙慕涵,周荫清,徐华平,刘慧.结合形态学理论与Hough变换的SAR图像线目标检测方法.遥测遥控,第28卷第6期2007年11月.
[41]潘卓,高鑫,王岩飞,范俐捷.基于聚类的SAR图像快速目标检测.计算机应用研究,第8期2008年.
[42]贾承丽,赵凌君.基于遗传算法的SAR图像道路网检测方法.计算机学报.第30卷第7期2007年7月.
[43] Novak L.M., Halversen Shawn D., Owirka Gregory J., and Hiett Margarita. Effects of polarization and resolution on the performance of a SAR automatic target recognition system. The Lincoln Laboratory Journal, 1995,8(1):49-67.
[44] Blacknell D. Contextual information in SAR target detection. IEE Proceedings: Radar, Sonar and Navigation, 2001,148(1):41-47.
[45] Runkle P., Nguyen L.H., McClellan J.H., Lawrence L. Multi-aspect target detectionfor SAR imagery using hidden Markov models. IEEE Transactions on Geoscience and Remote Sensing , 2001,39( 1 ):46-55.
[46] Tan Hwee H.P., Ramanathan U. Intelligent selection of useful features for optimal feature-based classification. Proceedings of IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2000), 2000, 7: 3012–3014.
[47] A. Freeman, D. Evans, J.J. VanZyl, SAR Applications in the 21st Century. European Conference on Synthetic Aperture Radar, Germany, 1996: 25-30
[48] R.L. Jordan. The Seasat-A Synthetic Aperture Radar System. IEEE J. of 1026- 1032 and Beam Sharpening. IEEE AES. 1968, 4(6): 879-885 Oceanic Engineering. 1980,5(2): 154-164
[49] R.L. Bernstein. Seasat Special Issue I of the J. Geophys. Res. 1982, 87(C5)
[50] Valenzuela G.R.,and Laing M.B. Point-Scatterer Formulation of Terrain Clutter Statistics. Naval Research Laboratory Report7459,Washington DC,1972.
[51] Schleher D.C. Radar Detection in Log Normal Clutter. Proc.IEEE Int.Radar Conf.Radar’75,1975, 262-267.
[52] M.T.Rey, T.Drosopoulos, and D.Petrovic,”A search procedure for ships in RADARSAT imagery”, DREO Report No.1305,1996.
[53] Qingshan Jiang, Shengrui Wang, Djemel Ziou, and Ali EI Zaart,”Automatic detection for ship targets in RADARSAT SAR images from coastal regions”,Vision Interface’99,May 1999,Trois-Tivieres,Canada,pp.131-137.
[54] Lee J S,Digital image enhancement and noise filtering by use of local statistics [J].IEEE Transaction Pattern Analysis and Machine Intelligence,1980,2(2):165—168.
[55] Kuan D.T., Sawchuk A.A., Strand T.C., and Chavel P. Adaptive Restoration of Images with Speckle. IEEE Trans. on Acoustics, Speech and Signal Processing, 1987,35(3): 373-383.
[56] Lopes A., Touzi R., Nezry E. Adaptive Speckle Filters and Scene Heterogeneity. IEEE Trans. on Geoscience and Remote Sensing,1990, 28(6): 992-1000.
[57] Lee J.S. Refined Filtering of Image Noise Using Local Statistics. Computer Graphic and Image Processing,1981,15:380-389.
[58]边肇棋等,模式识别,清华大学出版社,2000.
[59]何友、关键、彭应宁、陆大著,雷达自动检测与恒虚警处理,清华大学出版社,1999年5月.
[60] Oliver Chris and Quegan Shaun. Understanding Synthetic Aperture Radar Images. Boston : Artech House, 1998.
[61] Rafael C. Gonzalez and Richard E. Woods著,阮秋琦阮宇智等译,数字图像处理(第二版),电子工业出版社,2008年11月。
[62] Wang Lin-Cheng,Der S.Z., Nasrabadi N.M. Automatic target recognition using a feature-decomposition and data-decomposition modular neural network. IEEE Transactions on Image Processing, 1998, 7 (8): 1113-1121.
[63]沈庭芝方子文编著.数字图像处理及模式识别.北京:北京理工大学出版社,1998.
[64] H.Rohling,”Radar CFAR thresholding in clutter and multiple target situations”, IEEE Transactions on Aerospace and Electronic Systems,1983,Vol.19,No.4,pp.608- 621.
[65] Chitroub S, Houacine A, Sansal B. Statistical Characterization and Modelling of SAR Images. Signal Processing,2002,82:69-92.