SAR图像方向性目标检测与识别研究
|
摘要
合成孔径雷达(Synthetic Aperture Radar, SAR)凭其独特的优势在军事侦察和民用方面得到了广泛的应用,开展SAR图像的目标检测工作具有实际意义和应用前景。本文基于指数小波技术、扩展分形检测技术(Extended Fractal,EF)和扩展最大平均相关高度滤波器(Extended Maximum Average Correlation Height,EMACH)对SAR图像方向性目标的检测与识别展开研究,并基于方向滤波技术、非抽样Contourlet变换(Nonsubsampled Contourlet Transform, NSCT),开发了一款SAR图像多功能处理软件。
提出一种基于指数小波分形特征的SAR图像特定目标检测技术,算法依据指数小波特有的对边缘的选则性增强特性和方向敏感性,定义指数小波分形特征(Exponential Wavelet Fractal EWF)。利用该特征对特定姿态的目标进行检测实验,结果表明,该算法较传统算法能够更为准确的检测出方向性目标。
提出一种基于扩展分形检测技术与EMACH滤波器的SAR目标识别算法,利用扩展分形的准确定位功能,结合EMACH模板良好的识别性能,提出一种具有自动矫正功能的SAR目标识别方法。使用MSTAR数据库图像进行测试,获得了较好的识别效果。
介绍了NSCT变换原理和结构、以及本实验室基于NSCT变换已取得的应用成果,其中包括基于NSCT的图像纹理/形状检索和目标方位角估计算法;开发实现了NSCT变换C语言程序包,为开发SAR图像处理软件提供了必要的基础。
Synthetic Aperture Radar (SAR) has been widely used in both military reconnaissance and civil activity based on its unique advantages, so it’s meaningful and has application prospect to study target detection method of SAR images. In this dissertation, we detailedly analyze the exponential wavelet analysis method, Extended Fractal(EF)feature method, and the Extended Maximum Average Correlation Heigh(tEMACH) filters ways for target detection and recognition.We retrospect methods which our lib team has been made based on directional filter, Nonsubsampled Contourlet Transform (NSCT), and developed a multi-purpose SAR image processing software.
A new algorithm for special SAR target detection is proposed based on Exponential Wavelet Fractal(EWF).The Exponential Wavelet has a strong capacity to enhance the edges selectively according different scale. A novel Exponential Wavelet Fractal feature is defined in this dissertation. The effective performance using the new feature for special size and direction target detection is demonstrated and validated by the MSTAR data.
A novel method of fast automatic small target recognition in the huge scene SAR imagery is proposed. Firstly, the target model template is set up by EMACH filter method. Then, Extended Fractal method is used for target pre-location. In order to solve the problem that the target pre-location of SAR images is still not accurate enough, a new method of fine auto-rectified target location by using the EMACH filter was presented. The efficiency of the proposed method is evaluated based on the MSTAR data.
We detailedly introduced the theory and structure of the nonsubsampled contourlet transform, methods which our lib team has been made based on NSCT application. It includes the content-based retrieval system, and the SAR target pose estimating method, both of them are proposed based on NSCT tranform feature. Though that introduction, we details the progress of the NSCT VC program package developing, and implementation of the NSCT application.
提出一种基于指数小波分形特征的SAR图像特定目标检测技术,算法依据指数小波特有的对边缘的选则性增强特性和方向敏感性,定义指数小波分形特征(Exponential Wavelet Fractal EWF)。利用该特征对特定姿态的目标进行检测实验,结果表明,该算法较传统算法能够更为准确的检测出方向性目标。
提出一种基于扩展分形检测技术与EMACH滤波器的SAR目标识别算法,利用扩展分形的准确定位功能,结合EMACH模板良好的识别性能,提出一种具有自动矫正功能的SAR目标识别方法。使用MSTAR数据库图像进行测试,获得了较好的识别效果。
介绍了NSCT变换原理和结构、以及本实验室基于NSCT变换已取得的应用成果,其中包括基于NSCT的图像纹理/形状检索和目标方位角估计算法;开发实现了NSCT变换C语言程序包,为开发SAR图像处理软件提供了必要的基础。
Synthetic Aperture Radar (SAR) has been widely used in both military reconnaissance and civil activity based on its unique advantages, so it’s meaningful and has application prospect to study target detection method of SAR images. In this dissertation, we detailedly analyze the exponential wavelet analysis method, Extended Fractal(EF)feature method, and the Extended Maximum Average Correlation Heigh(tEMACH) filters ways for target detection and recognition.We retrospect methods which our lib team has been made based on directional filter, Nonsubsampled Contourlet Transform (NSCT), and developed a multi-purpose SAR image processing software.
A new algorithm for special SAR target detection is proposed based on Exponential Wavelet Fractal(EWF).The Exponential Wavelet has a strong capacity to enhance the edges selectively according different scale. A novel Exponential Wavelet Fractal feature is defined in this dissertation. The effective performance using the new feature for special size and direction target detection is demonstrated and validated by the MSTAR data.
A novel method of fast automatic small target recognition in the huge scene SAR imagery is proposed. Firstly, the target model template is set up by EMACH filter method. Then, Extended Fractal method is used for target pre-location. In order to solve the problem that the target pre-location of SAR images is still not accurate enough, a new method of fine auto-rectified target location by using the EMACH filter was presented. The efficiency of the proposed method is evaluated based on the MSTAR data.
We detailedly introduced the theory and structure of the nonsubsampled contourlet transform, methods which our lib team has been made based on NSCT application. It includes the content-based retrieval system, and the SAR target pose estimating method, both of them are proposed based on NSCT tranform feature. Though that introduction, we details the progress of the NSCT VC program package developing, and implementation of the NSCT application.
引文
[1]杰里L.伊伏斯、爱德华K.里迪,现代雷达原理,北京,电子工业出版社,1991
[2]星载合成孔径雷达军事应用论文集,国家863计划信息获取与处理专家组,1996
[3]郭华东主编。中国雷达遥感图像分析。北京:科学出版社。1999.1
[4]王超,张红,刘智,星载合成孔径雷达干涉测量,北京,科学出版社,2002
[5] Novak L M, Owirka GJ , Brower W S. Performance of 1D and 2D target MSE classifiers[J ] . IEEE Transactions on Aerospace and Elec2 tronic Systems , 2000 ,36 (4) :1279– 1289
[6] Novak L M, Owirka GJ , and Netishen CM. Performance of a high2 resolution polarimetric SAR automatic target recognition system[J ] .Lincoln Laboratory Journal , 1993 , 6 (1) : 11– 23
[7] Gandhi P P , and Kassam S A. Analysis of CFAR processors in non2 homogeneous background [J ] . IEEE Transactions on Aerospace and Electronic Systems , 1988 ,24(4) :427– 445
[8]陈嘉宇,徐新,孙红,管鲍,基于多分辨率统计能级的SAR图像点目标检测,系统工程与电子技术,2005,27(2):205~208
[9] Gagnon L , Oppenheim H. R&D activities in airborne SAR image processingPanalysis at lockheed martin canada[C]PPInternational Con2 ference on Application of Photonic Technology III , Ottawa , Ontario ,Canada. SPIE , 1998 ,3491 :998– 1003
[10] Abdelkaw E V , McGaughy D. Wavelet2based image tatget detection methods[C]PPInternational Conference on Sensors and Control Tech2 niques (1CSC) , SPIE , 2003 ,5094 :337– 347
[11]张伟,刘文波,张弓,时文华,基于NSCT域能量特征的SAR图像目标检测,中国雷达2008 Vol 01;pp:67~71
[12] Met R H. Synthetic aperture radar vehicle detection via subaperture coherence [DBPOL ] . 2002 , http :PPwww. asc2002. com Pmanuscripts PJP Jo - 02. PDF
[13]韩萍,SAR自动目标识别及相关技术研究,天津大学博士论文,2004
[14] Richardson D, Recognition Is Better[J], ARMADA International,1998 Vol.22 No.3:8~22
[15] Semi-AutomatedIMINTProcessing,http://www.fas.org/spp/military/docops/defense/actd_mp/SAIP.htm
[16] Moving and stationary target acquisition and recognition(MSTAR), http://www.alphatech.com/secondary/techpro/projects/master
[17] Robert L. Williams, Residual-based adaptive modeling for data, trajectory realignment toimprove model-based ATR performance, SPIE, july1997, Vol.3070:346~354
[18] Catherine E.Deardorf, The HEATR Project: ATR algorithm Parallelization, SPIE. April 1998,Vol.3370:420~427
[19] Leslie M.Novak,Gregory J.Owirka and William S.Brower, Performance of a 20-target MSE classifier, SPIE. April 1998,Vol.3395,pp.138~151
[20] Anne Marie P.Marneli, Lance M.Kaplan, and Nasrabadi, SAR ATR using a modified learning vector quantization algorithm. SPIE, April 1999,Vol.3721,pp.343~354
[21] Florence Tupin, Isabelle Bloch, Henri Maitre, A first step toward automatic interpretation of SAR images using evidential fusion of several structure detectors, IEEE Trans. on Geoscience RemoteSensing, 1999, Vol.37,no.3,pp.1327~1343
[22] QunZhao, Jose C.Principe,Support Vector Machines for SAR Automa -tic Target Recognition, IEEE Trans.on Aerospace and Electronic Sys -tems,Vol.37,No.2,April 2001 ,pp.643_654
[23] Dane P.Kottke,Paul D.Fiore,A design for HMM based SAR ATR ,SPIE, 1998 Vol.3370,
[24] A. Mahalanobis, B.V.K. Vijaya Kumar, and D. Casasent,“Minimum Average Correlation Energy Filters,”IEEE Trans.on Applied Optics, vol. 26, 1987. pp. 3633-3630.
[25] Singh Rajan , Kumar B V K V1 Performance of the ex tended maximum average correlation height ( EMACH) filter and the polynomial distance classifier correla tion filter ( PDCCF) for mul2ticlass SAR detection and classification [A] Proceedings of SPIE,Orlando,2002, 4727: 265-276
[26]焦李成,谭山.图像的多尺度几何分析:回顾和展望.电子学报,2003,31(12A):1975-1981.
[27] Candes E J, Ridgelet: Theory and Applications, Ph.D Dissertation, Palo Alto, USA, Stanford University, 1998
[28] Candes E J, Donoho D L, Curvelets—a surprisingly effective non-adaptive representation for objects with edges, Nashville, USA, Vanderbilt University Press, 2000
[29] Pennec E L, Mallat S, Image Copression with Geometrical Wavelets, Proceedings of the International Conference on Image Processing, Vancouver, CA, 2000: 661~664
[30] M N Do, Vetterli M, Contourlets: A directional multiresolution image representation, IEEE International Conference on Image Processing, New York, USA, 2002: 357~360
[31] Arthur L.da Cunha, Jianping Zhou, Minh N.Do, The Nonsubsampled Contourlet Transform: Theory, Design, and Applications, IEEE Transactions on Images Processing, 2006, 15(10): 3089~3101
[32] P J Burt, E H Adelson. The Laplacian Pyramid as a Compact Image Code[J]. IEEE Trans. Commun. April, 1983, 532-540
[33] R H Bamberger, M J T Smith. A Filter Bank for the Directional Decomposition of Images: Theory and Design[J]. IEEE Trans. Signal Proc. April, 1992, 882-893.
[34] Julesz B, Bergen JR , Textons. The Fundamental Elements in Preattentive Vision and Perception of Textures [R].1983.62: 1691 -1645.
[35] Gagalowicz A. A new method for texture fields synthesis: some applications to the study of human vision [J ]. IEEE Trans Pattern Anal Machine Intell ,1981, PAMI - 3:520– 533.
[36] Chen PC, Pavlidis T. Segmentation by texture using correlation [J]. IEEE Trans Pattern Anal Machine Intell, 1983, PAMI - 5:64 - 69.
[37] Kashyap RL, Chenllapa R. Estimation and Choice of Neighbors in Spatial-interaction Models of Images [J]. IEEE Trans Inform Theroy, 1985, IT - 29:60 - 72.
[38]靳华,王晓丹,赵荣椿,树型小波变换在纹理分析中的应用计算机应用研究.2001.3:91-93.
[39] Tianhorng Chang and C.-C.Jay Kuo, Texture Analysis and Classification with Tree-Structured Wavelet Transform. IEEE Transactins on Image Processing,1993: 2(4):429-442.
[40] Manesh: Kokare, P.K.Biswas, B,N. Chatterji. Texture Image Retrieval Using New Rotated Complex Wavelet Filters. IEEE Transactions on Systems, Man,and Cybernetics,2005.35 (6) : 1168-1179.
[41]韦娜,耿国华,周明全,Gabor滤波器的基于内容图像检索,计算机工程2005.31 (81): 10~12。
[42]顾春花基于Contourlet变换的SAR图像检索系统的研究与实现南京航空航天大学硕士学位论文2007 1028704 06-0113
[43] Shuang Fan, Shape Representation and Retrieval Using Di stance Histograms,Technical Report TR 01-14, Canada, 2001
[44] D.S. Zhang. Image Retrieval Based on Shape. Dissertation for Degree of Doctor of Philosophy. Monash University, 2002
[45]樊亚春,耿国华,周明全,用不变矩和边界方向进行形状检索.小型微型计算机系统.2004.25 (4):659-662.
[46]梁昕,张弓,基于Nonsubsampled Contourlet变换的SAR图像形状特征检索,雷达与对抗,2008,第1期
[47] Principe J C, Xu D, Fisher J W, Pose estimation in SAR using an information theoretic criterion, SPIE, 1998, 3370: 218~229
[48]贾承丽,计科峰,等,复杂SAR场景中机场跑道的提取,信号处理,2007,23(3):374~378
[49]徐牧,王雪松,肖顺平,基于Hough变换与目标主轴提取的SAR图像目标方位角估计方法,电子与信息学报,2007,29(2):370~374
[50] Goldstein, G. B. (1973)“False alarm regulation in log-normal and Weibull clutter”..IEEE Transactions on Aerospace and Electronic Systems,AES-9, 1(1973), pp:84—92.
[51] Kuttikkad, S., and Chellappa, R. (1994)“Non-Guassian CFAR techniques for target detection in high resolution SAR images”.In IEEE ICIP 94, Nov. 1994,pp: 910—914.
[52] Novak, L. M., Halversen, S. D., Owirka , G. J., and Hiett, M.(1997)“Effects of polarization and resolution on SAR ATR”. IEEE Transactions on Aerospace and Electronic Systems, 33 (Jan. 1997), pp:102—116.
[53] Lance M Kaplan.“Improved SAR Target Detection via Extended Fractal Feature”[J].IEEE Trans.on Aerospace and Electronic System,2001 pp:436-451.
[54] Kaplan L.M.,Romain Murenzi,Kameswara Namuduri.“Extended Fractal Feature for first stage SAR target detection”. SPIE,April 1999, vol.3721 pp : 35-46.
[55] Kaplan L.M.“Extended Fractal analysis for classification and segmentation.”IEEE Transactions on Image Processing, Nov,1999,vol.8,No.11 pp:1572- 1585.
[56] Charalampidis, D., and Kasparis, T.,“Wavelet- based rotational invariant roughness features for texture classification and segmentation,”IEEE Transactions on Image Processing, August 2002,Vol. 11, No. 8, pp: 825– 837.
[57] Stein,G.W.,Charalampidis,D.“Target detection using an improved fractal scheme”, SPIE proceedings,Algorithms for Synthetic Aperture Radar Imagery XIII,2006 ,vol.6237 pp :6237L1-6237L8.
[58] Robert Linnehan, Leonid Perlovsky, Chris W. Mutz, John Schindler“Detecting slow moving targets in SAR images”Radar Sensor Technology VIII and Passive Millimeter-Wave Imaging Technology VII Aug 2007 Proc. of SPIE Vol. 5410 pp: 64-73
[59] Steven Scarborough, Christopher Lemanski, Howard Nichols, Gregory Owirka, Michael Minardi, Todd Hale“SAR change detection MTI”Algorithms for Synthetic Aperture Radar Imagery XIII May 2006 Proc. of SPIE Vol. 6237 pp:1-11
[60] J. Arrault, A. Arneodo, A. Davis, and A. Marsak,“Wavelet based multifractal analysis of rough surfaces: Application to cloud models and satellite data,”Phys. Rev. Lett., July 2007.vol. 79, no. 1, pp. 75–79.
[61] S. Mallat and W. L. Hwang,“Singularity detection and processing with wavelets,”IEEE Trans. Inform. Theory, vol. 38, , Mar. 1992. pp. 617–643
[62] Goodman J W, Some fundamental properties of speckle, Journal of the Optical Society of America, 1976, 66(11): 1145~1150
[63] K.Rily,&A.J.Devaney, Wavelet processing of images for target detection, International Journal of Imaging sys.&Technology,vol.7,1996,404-420
[64] R.N.Strickland.&H.Hahn,Wavelet transform methods for object detection and recovery,IEEE Trans.on Image Processing,vol.6,No.5,May 1997,724-735
[65] S.Park,&R.Murenzi,&M.J.T.Smith, Multidimensional wavelets for target detection and recognition,Proceeding of SPIE,vol.22762.1996,177-187
[66] S.Mallat, A Wavelet tour of signal processing, New York Academic,1998
[67] E. Abdelkawy“Wavelet-based image target detection methods”Automatic Target Recognition SPIE,Sep 2006,vol.5094 : p. 337-347
[68] Qun Zhao,Jose C.Principe,Support Vector Machines for SAR Automa -tic Target Recognition, IEEE Trans.on Aerospace and Electronic Systems,Vol.37,No.2,April 2001,pp.643_654
[69] Dane P.Kottke,Paul D.Fiore,A design for HMM based SAR ATR ,SPIE, 1998 Vol.3370
[70] A. Mahalanobis, B.V.K. Vijaya Kumar, and D. Casasent,“Minimum Average Correlation Energy Filters,”IEEE Trans.on Applied Optics, vol. 26, 1987. pp. 3633-3630.
[71] M. Savvides, B.V.K. Vijaya Kumar, and P. Khosla,“Face Verification Using Correlation Filters,”Proc. Third IEEE Automatic Identification Advanced Technologies, 2002.pp. 56-61.
[72] Kaplan L M,Murenzi R,Namuduri K R.SAR Target Detection by Fusion of CFAR , Variance,and Fractal Statistics.In Proceedings of SPIE, 1998,3374:167～178.
[73] Kaplan L M,Murenzi R.Evaluation of CFAR and Texture Based Target Detection Statistics on SAR Imagery .Acoustics , Speech and Signal Processing 1998 . Proceedings of the 1998 IEEE International Conference on,1998,4:2141～2144.
[74] Correlation Filter: An Accurate Approach to Detect and Locate Low Contrast Character Strings in Complex Table Environment IEEE TRAN -SACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGEN–CE,VOL. 26, NO.12, DECEMBER 2005 pp:1639-1644
[75] An P.N. Vo, Truong T. Nguyen and Soontorn Oraintara .Texture Image Retrieval Using Complex Directional Filter Bank[J]. IEEE International Symposium on Circuits and Systems, Island of Kos, Greece, May 2006
[76]张伟,SAR图像特定目标检测技术研究,南京航空航天大学硕士论文,2008 1028703 08
[2]星载合成孔径雷达军事应用论文集,国家863计划信息获取与处理专家组,1996
[3]郭华东主编。中国雷达遥感图像分析。北京:科学出版社。1999.1
[4]王超,张红,刘智,星载合成孔径雷达干涉测量,北京,科学出版社,2002
[5] Novak L M, Owirka GJ , Brower W S. Performance of 1D and 2D target MSE classifiers[J ] . IEEE Transactions on Aerospace and Elec2 tronic Systems , 2000 ,36 (4) :1279– 1289
[6] Novak L M, Owirka GJ , and Netishen CM. Performance of a high2 resolution polarimetric SAR automatic target recognition system[J ] .Lincoln Laboratory Journal , 1993 , 6 (1) : 11– 23
[7] Gandhi P P , and Kassam S A. Analysis of CFAR processors in non2 homogeneous background [J ] . IEEE Transactions on Aerospace and Electronic Systems , 1988 ,24(4) :427– 445
[8]陈嘉宇,徐新,孙红,管鲍,基于多分辨率统计能级的SAR图像点目标检测,系统工程与电子技术,2005,27(2):205~208
[9] Gagnon L , Oppenheim H. R&D activities in airborne SAR image processingPanalysis at lockheed martin canada[C]PPInternational Con2 ference on Application of Photonic Technology III , Ottawa , Ontario ,Canada. SPIE , 1998 ,3491 :998– 1003
[10] Abdelkaw E V , McGaughy D. Wavelet2based image tatget detection methods[C]PPInternational Conference on Sensors and Control Tech2 niques (1CSC) , SPIE , 2003 ,5094 :337– 347
[11]张伟,刘文波,张弓,时文华,基于NSCT域能量特征的SAR图像目标检测,中国雷达2008 Vol 01;pp:67~71
[12] Met R H. Synthetic aperture radar vehicle detection via subaperture coherence [DBPOL ] . 2002 , http :PPwww. asc2002. com Pmanuscripts PJP Jo - 02. PDF
[13]韩萍,SAR自动目标识别及相关技术研究,天津大学博士论文,2004
[14] Richardson D, Recognition Is Better[J], ARMADA International,1998 Vol.22 No.3:8~22
[15] Semi-AutomatedIMINTProcessing,http://www.fas.org/spp/military/docops/defense/actd_mp/SAIP.htm
[16] Moving and stationary target acquisition and recognition(MSTAR), http://www.alphatech.com/secondary/techpro/projects/master
[17] Robert L. Williams, Residual-based adaptive modeling for data, trajectory realignment toimprove model-based ATR performance, SPIE, july1997, Vol.3070:346~354
[18] Catherine E.Deardorf, The HEATR Project: ATR algorithm Parallelization, SPIE. April 1998,Vol.3370:420~427
[19] Leslie M.Novak,Gregory J.Owirka and William S.Brower, Performance of a 20-target MSE classifier, SPIE. April 1998,Vol.3395,pp.138~151
[20] Anne Marie P.Marneli, Lance M.Kaplan, and Nasrabadi, SAR ATR using a modified learning vector quantization algorithm. SPIE, April 1999,Vol.3721,pp.343~354
[21] Florence Tupin, Isabelle Bloch, Henri Maitre, A first step toward automatic interpretation of SAR images using evidential fusion of several structure detectors, IEEE Trans. on Geoscience RemoteSensing, 1999, Vol.37,no.3,pp.1327~1343
[22] QunZhao, Jose C.Principe,Support Vector Machines for SAR Automa -tic Target Recognition, IEEE Trans.on Aerospace and Electronic Sys -tems,Vol.37,No.2,April 2001 ,pp.643_654
[23] Dane P.Kottke,Paul D.Fiore,A design for HMM based SAR ATR ,SPIE, 1998 Vol.3370,
[24] A. Mahalanobis, B.V.K. Vijaya Kumar, and D. Casasent,“Minimum Average Correlation Energy Filters,”IEEE Trans.on Applied Optics, vol. 26, 1987. pp. 3633-3630.
[25] Singh Rajan , Kumar B V K V1 Performance of the ex tended maximum average correlation height ( EMACH) filter and the polynomial distance classifier correla tion filter ( PDCCF) for mul2ticlass SAR detection and classification [A] Proceedings of SPIE,Orlando,2002, 4727: 265-276
[26]焦李成,谭山.图像的多尺度几何分析:回顾和展望.电子学报,2003,31(12A):1975-1981.
[27] Candes E J, Ridgelet: Theory and Applications, Ph.D Dissertation, Palo Alto, USA, Stanford University, 1998
[28] Candes E J, Donoho D L, Curvelets—a surprisingly effective non-adaptive representation for objects with edges, Nashville, USA, Vanderbilt University Press, 2000
[29] Pennec E L, Mallat S, Image Copression with Geometrical Wavelets, Proceedings of the International Conference on Image Processing, Vancouver, CA, 2000: 661~664
[30] M N Do, Vetterli M, Contourlets: A directional multiresolution image representation, IEEE International Conference on Image Processing, New York, USA, 2002: 357~360
[31] Arthur L.da Cunha, Jianping Zhou, Minh N.Do, The Nonsubsampled Contourlet Transform: Theory, Design, and Applications, IEEE Transactions on Images Processing, 2006, 15(10): 3089~3101
[32] P J Burt, E H Adelson. The Laplacian Pyramid as a Compact Image Code[J]. IEEE Trans. Commun. April, 1983, 532-540
[33] R H Bamberger, M J T Smith. A Filter Bank for the Directional Decomposition of Images: Theory and Design[J]. IEEE Trans. Signal Proc. April, 1992, 882-893.
[34] Julesz B, Bergen JR , Textons. The Fundamental Elements in Preattentive Vision and Perception of Textures [R].1983.62: 1691 -1645.
[35] Gagalowicz A. A new method for texture fields synthesis: some applications to the study of human vision [J ]. IEEE Trans Pattern Anal Machine Intell ,1981, PAMI - 3:520– 533.
[36] Chen PC, Pavlidis T. Segmentation by texture using correlation [J]. IEEE Trans Pattern Anal Machine Intell, 1983, PAMI - 5:64 - 69.
[37] Kashyap RL, Chenllapa R. Estimation and Choice of Neighbors in Spatial-interaction Models of Images [J]. IEEE Trans Inform Theroy, 1985, IT - 29:60 - 72.
[38]靳华,王晓丹,赵荣椿,树型小波变换在纹理分析中的应用计算机应用研究.2001.3:91-93.
[39] Tianhorng Chang and C.-C.Jay Kuo, Texture Analysis and Classification with Tree-Structured Wavelet Transform. IEEE Transactins on Image Processing,1993: 2(4):429-442.
[40] Manesh: Kokare, P.K.Biswas, B,N. Chatterji. Texture Image Retrieval Using New Rotated Complex Wavelet Filters. IEEE Transactions on Systems, Man,and Cybernetics,2005.35 (6) : 1168-1179.
[41]韦娜,耿国华,周明全,Gabor滤波器的基于内容图像检索,计算机工程2005.31 (81): 10~12。
[42]顾春花基于Contourlet变换的SAR图像检索系统的研究与实现南京航空航天大学硕士学位论文2007 1028704 06-0113
[43] Shuang Fan, Shape Representation and Retrieval Using Di stance Histograms,Technical Report TR 01-14, Canada, 2001
[44] D.S. Zhang. Image Retrieval Based on Shape. Dissertation for Degree of Doctor of Philosophy. Monash University, 2002
[45]樊亚春,耿国华,周明全,用不变矩和边界方向进行形状检索.小型微型计算机系统.2004.25 (4):659-662.
[46]梁昕,张弓,基于Nonsubsampled Contourlet变换的SAR图像形状特征检索,雷达与对抗,2008,第1期
[47] Principe J C, Xu D, Fisher J W, Pose estimation in SAR using an information theoretic criterion, SPIE, 1998, 3370: 218~229
[48]贾承丽,计科峰,等,复杂SAR场景中机场跑道的提取,信号处理,2007,23(3):374~378
[49]徐牧,王雪松,肖顺平,基于Hough变换与目标主轴提取的SAR图像目标方位角估计方法,电子与信息学报,2007,29(2):370~374
[50] Goldstein, G. B. (1973)“False alarm regulation in log-normal and Weibull clutter”..IEEE Transactions on Aerospace and Electronic Systems,AES-9, 1(1973), pp:84—92.
[51] Kuttikkad, S., and Chellappa, R. (1994)“Non-Guassian CFAR techniques for target detection in high resolution SAR images”.In IEEE ICIP 94, Nov. 1994,pp: 910—914.
[52] Novak, L. M., Halversen, S. D., Owirka , G. J., and Hiett, M.(1997)“Effects of polarization and resolution on SAR ATR”. IEEE Transactions on Aerospace and Electronic Systems, 33 (Jan. 1997), pp:102—116.
[53] Lance M Kaplan.“Improved SAR Target Detection via Extended Fractal Feature”[J].IEEE Trans.on Aerospace and Electronic System,2001 pp:436-451.
[54] Kaplan L.M.,Romain Murenzi,Kameswara Namuduri.“Extended Fractal Feature for first stage SAR target detection”. SPIE,April 1999, vol.3721 pp : 35-46.
[55] Kaplan L.M.“Extended Fractal analysis for classification and segmentation.”IEEE Transactions on Image Processing, Nov,1999,vol.8,No.11 pp:1572- 1585.
[56] Charalampidis, D., and Kasparis, T.,“Wavelet- based rotational invariant roughness features for texture classification and segmentation,”IEEE Transactions on Image Processing, August 2002,Vol. 11, No. 8, pp: 825– 837.
[57] Stein,G.W.,Charalampidis,D.“Target detection using an improved fractal scheme”, SPIE proceedings,Algorithms for Synthetic Aperture Radar Imagery XIII,2006 ,vol.6237 pp :6237L1-6237L8.
[58] Robert Linnehan, Leonid Perlovsky, Chris W. Mutz, John Schindler“Detecting slow moving targets in SAR images”Radar Sensor Technology VIII and Passive Millimeter-Wave Imaging Technology VII Aug 2007 Proc. of SPIE Vol. 5410 pp: 64-73
[59] Steven Scarborough, Christopher Lemanski, Howard Nichols, Gregory Owirka, Michael Minardi, Todd Hale“SAR change detection MTI”Algorithms for Synthetic Aperture Radar Imagery XIII May 2006 Proc. of SPIE Vol. 6237 pp:1-11
[60] J. Arrault, A. Arneodo, A. Davis, and A. Marsak,“Wavelet based multifractal analysis of rough surfaces: Application to cloud models and satellite data,”Phys. Rev. Lett., July 2007.vol. 79, no. 1, pp. 75–79.
[61] S. Mallat and W. L. Hwang,“Singularity detection and processing with wavelets,”IEEE Trans. Inform. Theory, vol. 38, , Mar. 1992. pp. 617–643
[62] Goodman J W, Some fundamental properties of speckle, Journal of the Optical Society of America, 1976, 66(11): 1145~1150
[63] K.Rily,&A.J.Devaney, Wavelet processing of images for target detection, International Journal of Imaging sys.&Technology,vol.7,1996,404-420
[64] R.N.Strickland.&H.Hahn,Wavelet transform methods for object detection and recovery,IEEE Trans.on Image Processing,vol.6,No.5,May 1997,724-735
[65] S.Park,&R.Murenzi,&M.J.T.Smith, Multidimensional wavelets for target detection and recognition,Proceeding of SPIE,vol.22762.1996,177-187
[66] S.Mallat, A Wavelet tour of signal processing, New York Academic,1998
[67] E. Abdelkawy“Wavelet-based image target detection methods”Automatic Target Recognition SPIE,Sep 2006,vol.5094 : p. 337-347
[68] Qun Zhao,Jose C.Principe,Support Vector Machines for SAR Automa -tic Target Recognition, IEEE Trans.on Aerospace and Electronic Systems,Vol.37,No.2,April 2001,pp.643_654
[69] Dane P.Kottke,Paul D.Fiore,A design for HMM based SAR ATR ,SPIE, 1998 Vol.3370
[70] A. Mahalanobis, B.V.K. Vijaya Kumar, and D. Casasent,“Minimum Average Correlation Energy Filters,”IEEE Trans.on Applied Optics, vol. 26, 1987. pp. 3633-3630.
[71] M. Savvides, B.V.K. Vijaya Kumar, and P. Khosla,“Face Verification Using Correlation Filters,”Proc. Third IEEE Automatic Identification Advanced Technologies, 2002.pp. 56-61.
[72] Kaplan L M,Murenzi R,Namuduri K R.SAR Target Detection by Fusion of CFAR , Variance,and Fractal Statistics.In Proceedings of SPIE, 1998,3374:167～178.
[73] Kaplan L M,Murenzi R.Evaluation of CFAR and Texture Based Target Detection Statistics on SAR Imagery .Acoustics , Speech and Signal Processing 1998 . Proceedings of the 1998 IEEE International Conference on,1998,4:2141～2144.
[74] Correlation Filter: An Accurate Approach to Detect and Locate Low Contrast Character Strings in Complex Table Environment IEEE TRAN -SACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGEN–CE,VOL. 26, NO.12, DECEMBER 2005 pp:1639-1644
[75] An P.N. Vo, Truong T. Nguyen and Soontorn Oraintara .Texture Image Retrieval Using Complex Directional Filter Bank[J]. IEEE International Symposium on Circuits and Systems, Island of Kos, Greece, May 2006
[76]张伟,SAR图像特定目标检测技术研究,南京航空航天大学硕士论文,2008 1028703 08
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |