SAR图像港口目标提取方法研究
|
摘要
本文研究了合成孔径雷达(Synthetic Aperture Radar,SAR)图像的港口提取技术。考虑到港口SAR图像数据量大的特点,以及当前实际应用中的大场景图像处理的时效性需求,本文提出港口提取的分层处理思路,即首先从大场景图像中分离出海域(获取海陆二值图),然后在海陆二值图中检测出包含港口目标的感兴趣区域(RegionofInterest,ROI),进而在港口区域内部进行舰船的检测,最后对检测到的舰船进行鉴别。按照这一思路,在分析港口目标配置及成像特点的基础上,分别对海陆分割、港口检测、港口区域舰船检测及鉴别进行了深入的研究。开展的工作主要包括以下几个方面:
(1)港口的目标配置与其SAR图像的特性分析。归纳总结了港口的一般配置,建立了港口的一般模型,分析了港口的主要散射机制及港口在SAR图像中的影像特点。这些工作为后续研究的开展奠定了基础。
(2)SAR图像海陆分割。为提供海陆二值图给后续港口检测任务,以准确、高效地完成海陆分割为目标,提出了一种改进的二维OTSU分割方法。首先,二维直方图比一维直方图更容易区分目标与背景;其次,通过分析传统二维OTSU法中关于二维直方图主对角区域概率假设的缺陷,修正主对角区域概率计算,大大提高了分割精度;再次,在理论分析其计算量的基础上,推导出了相应的快速算法,提高了算法的实用性,能够达到为后续港口检测提供海陆二值图的目的。
(3)SAR图像港口检测。为提供港口ROI给后续港口区域舰船检测任务,以正确检测到港口且准确定位其边界轮廓为目标,提出了一种基于特征的粗精两级港口检测框架。同时利用港口突堤分布特征和岸线封闭性特征,二者的结合有效克服了在港口突堤分布相对松散、岸线形状复杂等情况下港口检测效果不佳的问题。新方法通过建立港口特征模型,重点解决了突堤合并中目标完整性要求及虚警的滤除、突堤特征点选择、特征点岸线封闭性计算等问题。实验结果证明新方法具有检测性能高、定位准确等优点。
(4)SAR图像港口区域舰船检测。为提供舰船ROI给后续港口区域舰船鉴别任务,以高检测性能为目标,提出了一种港口区域舰船检测新方法。首先,根据高精度港口检测结果得到扩展区域,将获取的港口扩展区域灰度图作为待检测图;其次,提出了一种基于G0分布的港口内舰船CFAR检测算法。该方法能够在一个广泛的均匀度变化范围内对杂波图像进行较为精确建模,通过有效杂波自动筛选的引入,使得该检测算法具有恒虚警率特性并能够取得较好的检测性能。
(5)SAR图像港口区域舰船鉴别。提出了一种港口区域舰船鉴别新方法。首先,针对舰船目标的特殊性,提出了一种新的形状特征;其次,利用冗余性、鲁棒性和可分离程度度量定量分析了目标切片常用的鉴别特征,给出了适合舰船目标的优选鉴别特征序列及其优选方法;再次,给出了加权最小距离分类器的设计,该分类器根据使优选鉴别特征矢量具有最大可分性对应的权重,修正已有分类器。实验结果证明新方法具有鉴别精度高、速度快等优点。
With the demand on harbor interpretation with SAR image, the techniques ofextracting harbor from SAR images are studied in this thesis. In order to deal withlarge-scene images in practical applications, this paper proposes a hierarchicalprocedure for harbor extraction. Firstly, the sea area is separated from the large-sceneimage (sea-land binary image extraction); secondly, harbor detection is implementedfrom the sea-land binary image (ROI extraction); then, the ship detection is realizedinsidethedetectedharbor;finally,theshipdiscriminationisimplementedforshipROIs.According to this procedure, this paper has a detailed research on the techniques ofsea-land segmentation, harbor extraction, ship detection and discrimination inside theharborarea.Themainworkofthisthesis includesthefollowingaspects.
(1) The disposal of the harbor and the characteristics of SAR images are firstlyanalyzed. The general disposal ofthe harbor is concluded and the general harbor modelis established. Then the main scattering mechanisms encountered in harbor areas andtheir characteristics in SAR images are analyzed. The above analysis on the harbor isthefoundationofthe subsequentresearch.
(2)Accordingtotherequirementofprovidingthe sea-landbinaryimageforharbordetection, an accurate and efficient method to segment the sea areas from SAR imagesis proposed. Firstly, the objects and the background are easier to distinguish in a 2Dhistogram than that in a 1D histogram. Secondly, the assumption about themain-diagonal probabilities is unreasonable, which is used with the 2D histogram in atraditional 2D OTSU method. We corrected the calculation of the probabilities at themain-diagonal region,andthesegmentationprecisionis greatlyimproved. Accordingtothe theoretical analysis, a fast recursive method for realizing modified 2D OTSU isobtained, which makes the sea-land segmentation algorithm more practical. Moreover,proposed method can meet the practical application demands of providing sea-landbinaryimageryforharbordetection.
(3) Since the existing methods of harbor detection from SAR images are notapplicable for images with different types of harbors, this paper proposes a method ofhabor detection based on features, in order to detect harbor and acquire correspondingboundaries accurately. This algorithm not only makes use of the characteristics ofharborjetty, which has longstrip in shape andconcentrative space distribution, but alsoutilizes the characteristics of the closed harbor coastline, which is surrounded by theland. The combination of the characteristics of harbor jetty and harbor coastline canovercome the problems, that the performance of harbor detection is worse when harborjetties has comparatively incompact distribution and the shape of coastline iscomplicated.Theexperimentalresultsshowthatthenewmethodiseffectivewithahigh detection rate, a low false-alarm rate and good localization performance. The detectionresults can meet the demands of providing harbor ROI for ship detection inside harborregion.
(4) According to the requirement of providing ship ROIs for ship discrimination,an effective and efficient method of detecting the ships inside the harbor region fromSAR images using a CFAR detector based on the G0distribution is proposed. Firstly,theSAR imageoftheharborcoastwise regionisextractedbasedontheharborcoastline.Then, a detailed analysis is presented on the clutter statistical properties of harborcoastwise region in SAR image. Further, the ship detection is completed based on theCFAR detector with the G0 distribution. The proposed method can precisely modelclutter data under different clutter environment statistically. By introducing theautomatic censoring of effective clutter pixels, our method has a constant false alarmrate and good performance of detection. The detection results can meet the applicationdemandsofprovidingshipROIsforshipdiscrimination.
(5) Aiming at higher precision for discrimination, a method of ship discriminationbased on feature extraction and selection is proposed. Firstly, a new shape feature isconstructed for ship discrimination. Then, the common features for discrmination arequantitatively analyzed by the redundancy, robustness and separability of features. Amethod of selecting the optimal features for target discrimination is given. Finally, aweighted minimum distance classifier is designed to improve the performance of theexistingclassifiers.Theexperimental results show that thenewmethodiseffectivewithhighclassificationaccuracy andexcellentdicriminationperformance.
(1)港口的目标配置与其SAR图像的特性分析。归纳总结了港口的一般配置,建立了港口的一般模型,分析了港口的主要散射机制及港口在SAR图像中的影像特点。这些工作为后续研究的开展奠定了基础。
(2)SAR图像海陆分割。为提供海陆二值图给后续港口检测任务,以准确、高效地完成海陆分割为目标,提出了一种改进的二维OTSU分割方法。首先,二维直方图比一维直方图更容易区分目标与背景;其次,通过分析传统二维OTSU法中关于二维直方图主对角区域概率假设的缺陷,修正主对角区域概率计算,大大提高了分割精度;再次,在理论分析其计算量的基础上,推导出了相应的快速算法,提高了算法的实用性,能够达到为后续港口检测提供海陆二值图的目的。
(3)SAR图像港口检测。为提供港口ROI给后续港口区域舰船检测任务,以正确检测到港口且准确定位其边界轮廓为目标,提出了一种基于特征的粗精两级港口检测框架。同时利用港口突堤分布特征和岸线封闭性特征,二者的结合有效克服了在港口突堤分布相对松散、岸线形状复杂等情况下港口检测效果不佳的问题。新方法通过建立港口特征模型,重点解决了突堤合并中目标完整性要求及虚警的滤除、突堤特征点选择、特征点岸线封闭性计算等问题。实验结果证明新方法具有检测性能高、定位准确等优点。
(4)SAR图像港口区域舰船检测。为提供舰船ROI给后续港口区域舰船鉴别任务,以高检测性能为目标,提出了一种港口区域舰船检测新方法。首先,根据高精度港口检测结果得到扩展区域,将获取的港口扩展区域灰度图作为待检测图;其次,提出了一种基于G0分布的港口内舰船CFAR检测算法。该方法能够在一个广泛的均匀度变化范围内对杂波图像进行较为精确建模,通过有效杂波自动筛选的引入,使得该检测算法具有恒虚警率特性并能够取得较好的检测性能。
(5)SAR图像港口区域舰船鉴别。提出了一种港口区域舰船鉴别新方法。首先,针对舰船目标的特殊性,提出了一种新的形状特征;其次,利用冗余性、鲁棒性和可分离程度度量定量分析了目标切片常用的鉴别特征,给出了适合舰船目标的优选鉴别特征序列及其优选方法;再次,给出了加权最小距离分类器的设计,该分类器根据使优选鉴别特征矢量具有最大可分性对应的权重,修正已有分类器。实验结果证明新方法具有鉴别精度高、速度快等优点。
With the demand on harbor interpretation with SAR image, the techniques ofextracting harbor from SAR images are studied in this thesis. In order to deal withlarge-scene images in practical applications, this paper proposes a hierarchicalprocedure for harbor extraction. Firstly, the sea area is separated from the large-sceneimage (sea-land binary image extraction); secondly, harbor detection is implementedfrom the sea-land binary image (ROI extraction); then, the ship detection is realizedinsidethedetectedharbor;finally,theshipdiscriminationisimplementedforshipROIs.According to this procedure, this paper has a detailed research on the techniques ofsea-land segmentation, harbor extraction, ship detection and discrimination inside theharborarea.Themainworkofthisthesis includesthefollowingaspects.
(1) The disposal of the harbor and the characteristics of SAR images are firstlyanalyzed. The general disposal ofthe harbor is concluded and the general harbor modelis established. Then the main scattering mechanisms encountered in harbor areas andtheir characteristics in SAR images are analyzed. The above analysis on the harbor isthefoundationofthe subsequentresearch.
(2)Accordingtotherequirementofprovidingthe sea-landbinaryimageforharbordetection, an accurate and efficient method to segment the sea areas from SAR imagesis proposed. Firstly, the objects and the background are easier to distinguish in a 2Dhistogram than that in a 1D histogram. Secondly, the assumption about themain-diagonal probabilities is unreasonable, which is used with the 2D histogram in atraditional 2D OTSU method. We corrected the calculation of the probabilities at themain-diagonal region,andthesegmentationprecisionis greatlyimproved. Accordingtothe theoretical analysis, a fast recursive method for realizing modified 2D OTSU isobtained, which makes the sea-land segmentation algorithm more practical. Moreover,proposed method can meet the practical application demands of providing sea-landbinaryimageryforharbordetection.
(3) Since the existing methods of harbor detection from SAR images are notapplicable for images with different types of harbors, this paper proposes a method ofhabor detection based on features, in order to detect harbor and acquire correspondingboundaries accurately. This algorithm not only makes use of the characteristics ofharborjetty, which has longstrip in shape andconcentrative space distribution, but alsoutilizes the characteristics of the closed harbor coastline, which is surrounded by theland. The combination of the characteristics of harbor jetty and harbor coastline canovercome the problems, that the performance of harbor detection is worse when harborjetties has comparatively incompact distribution and the shape of coastline iscomplicated.Theexperimentalresultsshowthatthenewmethodiseffectivewithahigh detection rate, a low false-alarm rate and good localization performance. The detectionresults can meet the demands of providing harbor ROI for ship detection inside harborregion.
(4) According to the requirement of providing ship ROIs for ship discrimination,an effective and efficient method of detecting the ships inside the harbor region fromSAR images using a CFAR detector based on the G0distribution is proposed. Firstly,theSAR imageoftheharborcoastwise regionisextractedbasedontheharborcoastline.Then, a detailed analysis is presented on the clutter statistical properties of harborcoastwise region in SAR image. Further, the ship detection is completed based on theCFAR detector with the G0 distribution. The proposed method can precisely modelclutter data under different clutter environment statistically. By introducing theautomatic censoring of effective clutter pixels, our method has a constant false alarmrate and good performance of detection. The detection results can meet the applicationdemandsofprovidingshipROIsforshipdiscrimination.
(5) Aiming at higher precision for discrimination, a method of ship discriminationbased on feature extraction and selection is proposed. Firstly, a new shape feature isconstructed for ship discrimination. Then, the common features for discrmination arequantitatively analyzed by the redundancy, robustness and separability of features. Amethod of selecting the optimal features for target discrimination is given. Finally, aweighted minimum distance classifier is designed to improve the performance of theexistingclassifiers.Theexperimental results show that thenewmethodiseffectivewithhighclassificationaccuracy andexcellentdicriminationperformance.
引文
[1]田巳睿,王超,张红.星载SAR舰船检测技术及其在海洋渔业监测中的应用[J].遥感技术与应用.2007,22(4):503-512.
[2]邹焕新. SAR图像舰船目标与航迹检测方法研究[D].长沙:国防科技大学.2003.1.
[3] Liu Y J and Feng Q. Sea surface ship detection in SAR images[A]. 2004 IEEEInternational Geoscience and Remote Sensing Symposium (IGARSS’04). Alaska,USA.2004.4723-4725.
[4] Huang S Q, Liu D Z, and Gao G Q, et al. A novel method for speckle noisereduction and ship target detection in SAR images[J]. Pattern Recognition. 2009,42:1533-1542.
[5]王培. SAR图象中船舶目标的提取及分形方法在SAR图象分类中的应用[D].北京:中国科学院电子学研究所.2000.2.
[6] Gamba P and Mecocci A. Harbour images sequence analysis for control andmonitoring[A]. 1997 IEEE International Conference on Acoustics, Speech, andSignalProcessing.Munich,Germany.1997.2877-2880.
[7] YangHM and Wu M M. A new type of harbour surveillance radar with diversityprocessing[A]. CIE International Conference of Radar. Beijing, China. 1996.614-619.
[8]吴建华.遥感图像中港口识别与毁伤分析研究[D].南京:南京理工大学.2005.1-2,16,37-41.
[9]周拥军,朱兆达,丁全心.遥感图像中港口目标识别技术[J].南京航空航天大学学报.2008,40(3):350-353.
[10]种劲松.合成孔径雷达图像舰船目标检测算法与应用研究[D].北京:中国科学院电子学研究所.2002.5,23-32,43-44.
[11] Mandal D P, Murthy C A, Pal S K. Analysis of IRS Imagery for DetectingMan-Made Objects With a Multi-valued Recognition System[J]. IEEE Trans onsystems,ManandCybernetics.Parta:systemsandhumans.1996.26(2):241-247.
[12] Li Y. and Peng J. Feature extraction and recognition of harbor contour[J]. SPIEProceedings on Image Extraction, Segmentation, and Recognition. 2001, 4550:234-238.
[13]郑孝娟.高分辨率可见光遥感图像的港口变化检测方法研究[D].合肥:中国科学技术大学.2008.45-48.
[14]陈琨,陈学佺.一种基于几何特征的舰船与码头目标分割的新方法[J].计算机工程与应用.2004,31:197-200.
[15]张志龙.基于遥感图像的重要目标特征提取与识别方法研究[D].长沙:国防科技大学.2005.146-155.
[16]邢坤,付宜利.基于内港区域的港口目标识别[J].电子与信息学报.2009,31(6):1275-1278.
[17] Zhu B, Li J Z and Cheng A J. Knowledge based recognition of harbor target[J].JournalofSystemsEngineeringandElectronics.2006,17(4):755-759.
[18]魏军伟.遥感图像中港口目标检测研究与实现[D].西安:西安电子科技大学.2007.22-24.
[19]赵波.遥感图像目标识别算法研究[D].长沙:国防科技大学.2004.45-50.
[20]杨耘,王树根,邱丹丹.基于规则的高分辨率影像港口识别模型[J].测绘信息与工程.2005,30(5):40-42.
[21]方晓芙.遥感图像中战略目标识别方法研究[D].西安:西北工业大学.2004.15-19.
[22]李艳,彭嘉雄.港口目标特征提取与识别[J].华中科技大学学报. 2001, 29(6):10-12.
[23]周静.典型地海背景下目标识别方法研究[D].武汉:华中科技大学. 2005.54-59.
[24]侯彪,刘芳,焦李成.基于小波变换的高分辨SAR港口目标自动分割[J].红外与毫米波学报.2002,21(5):385-389.
[25] Vachon P W, Adlaldaa P, Edel H, et a1. Canadian progress toward marine andcoastal applications of synthetic aperture radar[J].Johns Hopkins APL TechnicalDigest.2000,21(1):33-40.
[26] WackermanC C, Friedman K S, Pichel W G,et a1. Automatic detection of shipsin radarsat-l Sar imagery[J]. Canadian Journal of Remote Sensing. 2001, 27(5):568-577.
[27] Schwartz G, Alvarez M, Varfis A, et a1. Elimination of false positives in vesselsdetection and identification by remote sensing[A]. IEEE International GeoscienceandRemoteSensingSymposium[C].Toronto,Canada.2002,1:116-118.
[28] Crisp D J. The State-of-the-Art in Ship Detection in Synthetic Aperture RadarImagery[R]. Edinburgh, South Australia, Australia: Australia DSTO InformationSciencesLaboratory.2004.86.
[29] EldhusetK. Principlesandperformanceofanautomatedshipdetectionsystemforsat image[A]. IEEE Intemational Geoscience and Remote SensingSymposium[C].Vancouver,Canada.1989.358-361.
[30] Tunaley J K E. Algorithms for ship detection and tracking using satelliteimagery[A]. IEEE Intemational Geoscience and Remote Sensing Symposium[C].Anchorage,Alaska,USA.2004,3:1804-1807.
[31] Eldhuset K. Principles And Performance Of An Automated Ship DetectionSystem For Sar Images[A]. IEEE International Geoscience and Remote SensingSymposium[C].Vancouver,Canada.1989.358-361.
[32]李海艳.极化SAR图像海面船只监测方法研究[D].青岛:中国科学院海洋研究所.2007.10.
[33] Greidanus H, Clayton P, Indregard M,et al.Benchmarking operational SAR shipdetection[A].IEEE InternationalGeoscienceandRemoteSensingSymposium[C].Anchorage,Alaska,USA.2004.4215-4218.
[34] Lombardo P and Sciotti M. Segmentation-based technique for ship detection inSARimages[J].IEEProc-RadarSonarNaving.2001,148(3):147-159.
[35] Sciotti M and Lombardo P. Ship detection in SAR images a segmentation-basedapproach[A].IEEERadarConference[C]. Atlanta,Georgia,USA.2001.81-87.
[36] Wang P, Chong J and Wang H. Ship detection of the airborne SAR images[A].IEEE 2000 International Geoscience and Remote Sensing Symposium(IGARSS'00).Honolulu,Hawaii.2000.348-350.
[37]种劲松,朱敏慧.高分辨率合成孔径雷达图像舰船检测方法[J].测试技术学报.2003,17(1):15-18.
[38]张天序,赵广州,王飞.一种快速递归红外舰船图像分割新算法[J].红外与毫米波学报.2006,25(4):295-300.
[39]宿丁,张启衡,谢盛华.一种强海杂波多目标分形分割算法[J].计算机工程与应用.2006,16:12-14.
[40]张风丽,吴炳方,张磊.基于小波分析的SAR图像船舶目标检测[J].计算机工程.2007,33(6):33-34.
[41] BenelliG,Garzelli A andMecocciA.Completeprocessingsystemthatusesfuzzylogic for ship detection in SAR images[J]. IEE Proc-Radar,Sonar Naving. 1994,141(4):181-186.
[42] Argenti F,Benelli Gand Garzelli A. AutomaticshipdetectioninSAR images[A].IEEInternationalConferenceRadar[C].Brighton,UK.1992.465-468.
[43]邹焕新,匡纲要,郁文贤.基于特征矢量匹配的SAR海洋图像舰船目标检测[J].现代雷达.2004,26(8):25-29.
[44]李文武,李智勇,粟毅.一种联合灰度和纹理特征的光学图像舰船目标检测方法[A].第十四届全国图象图形学学术会议[C].福州,福建.2008.293-296.
[45] Jiang Q S, WangS R, Ziou D, et al. Ship detection in RadarsatSAR imagery[A].IEEE International Conference on Systems, Man, and Cybernetics[C].San Diego,USA.1998.4562-4566.
[46] Ouchi K, Tamaki S, Yaguchi H, et al.Ship detection based on coherence imagesderivedfrom cross correlationofmultilookSAR images[J].IEEE GeoscienceandRemoteSensingLetters.2004,1(3):184-187.
[47]田巳睿,王超,张红. EnvisatAP图像P-CFAR舰船检测方法研究[J].遥感技术与应用.2007,22(2):183-187.
[48]雷琳,粟毅.一种基于轮廓匹配的近岸舰船检测方法[J].遥感技术与应用.2007,22(5):622-627.
[49]李长军,陈学佳,丁洽国.一种港口区域舰船目标变化检测新方法[J].计算机工程.2006,32(14):190-192.
[50]隆刚,陈学佺.高分辨率遥感图像港内舰船的自动检测方法[J].计算机仿真.2007,24(5):118-201.
[51]蒋李兵,王壮,胡卫东.一种基于可变夹角链码的靠岸舰船目标检测方法[J].遥感技术与应用.2007,22(1):88-94.
[52] http://data.ekejian.com/viewstaticres/SysContent4/d0/dd0/ddd121/702415679321/702415679321.doc[EB/OL],2007-3-21/2009-4-6.
[53]李增军.世界第三大集装箱港口-中国台湾高雄港[J].港口经济. 2001, (1):56-56.
[54] http://www.buildbook.com.cn/ebook/2007/B10035414/7.htm[EB/OL],2007-4-14/2009-4-6.
[55] http://www.fpa.gov.cn/WEB1/OTHER/k3.doc[EB/OL],2008-5-23/2009-4-6.
[56]洪承礼.港口规划与布置[M].北京:人民交通出版社.1999.118.
[57] http://col.njtu.edu.cn/zskj/3013/9/main-3.htm[EB/OL],2007-9-2/2009-04-06.
[58]韩理安.港口水工建筑物[M].北京:人民交通出版社.2000.1.
[59] http://bbs3.zhulong.com/forum/detail3822297_1.html[EB/OL],2003-8-29/2009-04-06.
[60] [美]赫尔别克主编.[译]李玉成等.海岸及海洋工程手册(第一卷)[M].大连:大连理工大学出版社.1992.730.
[61] Abraham D M, et al. Modeling and simulation of breakwater construction[A].Proceedings of Winter Simulation Conference[C]. Arlington, VA, USA 1995.1017-1023.
[62] Carpenter R N, Cray B A, and Levine E R. Broadband Ocean Acoustic (BOA)Laboratory in Narragansett Bay: preliminary in-situ harbor securitymeasurements[J]. Procedings of SPIE the International Society for OpticalEngineering.2006.6204: 620409.
[63] Nakamichi M, Sugaya M, and Sezaki Y, et al. Design and construction ofembedded steel-plate cell breakwater[A]. IEEE TECHNO-OCEAN’04. Japan.2004.59-65.
[64] Abraham D M. Modeling and simulation of breakwater construction[A].Proceedings of the 1995 Winter Simulation Conference. Hyatt Regency CrystalCity,Arlington,VA.1995.1017-1023.
[65] http://col.njtu.edu.cn/zskj/3013/9/Main-6.htm[EB/OL],2007-9-2/2009-4-6.
[66]雷松林,郑永来.防波堤结构型式及其应用探讨[J].中国水运. 2007, 7(6):131-132.
[67]陈万佳.港口水工建筑物[M].北京:人民交通出版社.1995.350.
[68]赵凌君.高分辨率SAR图像建筑物提取方法研究[D].长沙:国防科技大学.2009.19,99.
[69]舒士畏,赵立平.雷达图象及其应用[M].北京:中国铁道出版社. 1988.171-173.
[70] Xie H, Li L L, and Bo H, et al. A Novel Method for Ship Detection Based onNSCT and ACO[A]. The 2nd International Conference on Image and SignalProcessing.Tianjin,China.2009.1-4.
[71]李娟.基于模糊理论的图像分割算法研究[D].武汉:武汉科技大学.2005.12.
[72] Kim D J, Park S E, andMoon W M, et al. Effect of radar frequency on waterlinemapping from airborne SAR image in the intertidal zone[A]. 2005 IEEEInternational Geoscience and Remote Sensing Symposium (IGARSS'05). Seoul,Korea.2005.999-1001.
[73]迂学峰,吴庆洪.美元图像的自适应阈值分割方法[J].现代电子技术. 2007,(8):96-100.
[74]梁华为.直接从双峰直方图确定二值化阈值[J].模式识别与人工智能. 2002,15(2):253-256.
[75]王文宁,王汇源,牟文英.一种新的灰度直方图分割阈值的自动检测方法[J].计算机工程与应用.2005,26:89-91.
[76]程杰.一种基于直方图的分割方法[J].华中理工大学学报.1999,27(1):84-86.
[77]冯慧扬,王申康,王宏伟.人脸定位算法的研究[J].计算机工程与应用.2003,30:101-104.
[78]梁栋,李新华.一种基于人工智能的阈值自动选择方法[J].微电子学与计算机.1999,(1):2-5.
[79] Yin P Y and Chen L H. A new method for multilevel thresholding usingsymmetry and duality of the histogram[A]. IEEE 1994 International Symposiumon Speech, Image Processing and Neural Networks[C]. Hong Kong, China. 1994.45-48.
[80] Cheng H D, Jiang X H, Sun Y, et al. Color image segmentation: advances andprospects[J].PatternRecognition.2001,34:2259-2281.
[81]吴一全,朱兆达.图像处理中阈值选取方法30年(1962—1992)的进展(一)[J].数据采集与处理.1993,8(3):193-201.
[82]左奇,史忠科.一种基于直方图评价函数的快速图像分割方法[J].计算机工程与应用.2003,19:5-7.
[83]吴一全,朱兆达.图像处理中阈值选取方法30年(1962—1992)的进展(二)[J].数据采集与处理.1993,8(4):268-282.
[84]韩思奇,王蕾.图像分割的阈值法综述[J].系统工程与电子技术. 2002, 24(6):91-95.
[85]罗希平,田捷,诸葛婴等.图像分割方法综述[J].模式识别与人工智能1999,12(3):300-312.
[86]张龙,余玲玲,刘京南.一种改进的最大熵阈值分割方法[J].电子工程师.2006,32(11):40-43.
[87]修春波,刘向东,张宇河.基于混沌优化的最佳熵阈值的图像分割[J].计算机工程与应用.2004,27:76-78.
[88]王毅,牛奕龙,董建园等.基于改进遗传算法的最佳熵多阈值三维医学图像分割算法[J].西北工业大学学报.2007,25(3):442-445.
[89]王栋,朱明.低对比度图像中改进的二维熵阈值分割法[J].仪器仪表学报.2004,25A(4):355-359.
[90]张家树,李北川.灰度图象的二维最大熵阈值分割研究[J].西南师范大学学报.1995,20(6):643-647.
[91] Pal N R and Pal S K. Object-background segmentation using new definitions ofentropy[J].1989IEEProceddings.1989,136(4):284-295.
[92] ChenH D andChen J R.Automaticallydeterminethemembershipfunctionbasedonthemaximumentropyprinciple[J].InformationScience.1997,96:163-182.
[93] Ullah A. Entropy, divergence and distance measures with econometricapplications[J].JournalofStatisticalplanningandinference.1996,49:137-162.
[94] PalSKandPal NR. Objectextractionfromimageusinghigherorderentropy[A].9th International Conference on Pattern Recognition[C]. Rome, Italy. 1988.348-350.
[95] Pal N R and Pal S K. Entropy: a new definition and its applications[J]. IEEETransactionsonSystemManandCybernetics.1991,21(5):1260-1270.
[96] Abutaleb A S. Automatic thresholding of gray-level pictures usingtwo-dimensional entropy[J]. Computer Vision,Graphics and Image Process, 1989,47:22-32.
[97]金永镐,崔荣一,金小峰.基于交叉熵极小化的图像边缘检测算法[J].吉林大学学报(自然科学版).2006,24(6):656-660.
[98]黄春艳,杨国胜,侯艳丽.基于熵的图像二值化方法比较研究[J].河南大学学报.2005,35(2):76-78.
[99]范立生,杨健,彭应宁.基于交叉熵的特征提取与河流区域的目标检测[J].系统工程与电子技术.2006,28(3):339-341.
[100]Pal N R. On minimum cross-entropy thresholding[J]. Pattern Recognition. 1996,29(4):575-580.
[101]Brink A D and Pendock N E. Minimum cross-entropy threshold selection[J].PatternRecognition.1996,29(1):179-188.
[102]乔韦华韦华,吴成茂.二维最大类间交叉熵阈值分割法[J].西北大学学报(自然科学版).2008,38(3):374-378.
[103]Tseng D C and Shieh W S. Plume segmentation using local entropicthresholding[A].11thInternationalConferenceonPatternRecognition[C].Hague,Netherlands.1992.156-159.
[104]薛景浩,章毓晋,林行刚.图像分割中的交叉熵和模糊散度算法[J].电子学报.1999,27(10):131-134.
[105]郑毅,刘上乾.基于模糊指数熵和模拟退火的图像分割[J].红外技术. 2006,28(7):395-399.
[106]陈涛,司锡才.基于直方图的模糊最大指数熵图像分割方法[J].哈尔滨工程大学学报.2004,25(4):521-524.
[107]张昆辉,曹兰英,夏良正.基于遗传算法的二维模糊C-划分最大熵SAR图像分割[J].信号处理.2005,21(2):199-201.
[108]王正勇,陶青川,吴晓红等.基于模糊散度的图象分割[J].四川大学学报.2002,39(2):228-231.
[109]赵立兴,唐英干,刘冬等.基于直方图指数平滑的模糊散度图像分割[J].系统工程与电子技术.2005,27(7):1182-1185.
[110]李弼程,柳葆芳.基于二维直方图的模糊门限分割方法[J].数据采集与处理.2000,15(3):324-329.
[111]薛景浩,章毓晋,林行刚.基于最大类间后验交叉熵的阈值比分割算法[J].中国图象图形学报.1999,4A(2):110-114.
[112]Bhatt R B. Image Segmentation by Histogram Adaptive Fuzzification[A]. IEEEIndicon2005Conference[C].Chennai,India.2005.535-538.
[113]FanJ L andXie WX.Distance measure andinducedfuzzyentropy[J].Fuzzysetsandsystems.1999.(104):305-314.
[114]Montes S, Couso I, Gil P, et al. Divergence measure between fuzzy sets[J].InternationJournalofapproximatereasoning.2002.(30):91-105.
[115]Sen D and Pal S K. Image Segmentation using Global and Local FuzzyStatistics[A].IEEEIndiaConference[C].NewDelhi,India.2006.1-6.
[116]Cheng H D, Chen Y H and Sun Y. A novel fuzzy entropy approach to imageenhancementandthresholding[J].SignalProcessing.1999,75:277-301.
[117]Avci E and Avci D. An expert system based on fuzzy entropy for automaticthreshold selection in image processing[J]. Expert Systems and Applications.2008,36(2):3077-3085.
[118]Huang L K and WANG M J. Image thresholding by minimizing the measures offuzziness[J].PatternRecognition.1995,28(1):41-51.
[119]Benabdelkader S and Boulemden M. Recursive algorithm based on fuzzy2-partition entropy for 2-level image thresholding[J]. Pattern Recognition. 2005,38:1289-1294.
[120]Forero-Vargas M G and Rojas-Camacho O. New formulation in imagethresholding using fuzzy logic[A]. 11th Portuguese Conference on PatternRecognition[C]. Porto,Portugal.2000.117–124.
[121]翟辉琴.基于数学形态学的遥感影像水域提取方法[J].测绘科学. 2006, 31(1):22-24.
[122]朱俊杰.高分辨率SAR图像的水体边缘快速自动与精确检测[J].遥感信息应用技术.2005,5:29-31.
[123]胡正磊.基于小波边缘提取和脊线跟踪技术的SAR图像河流检测算法[J].电子与信息学报.2007,29(3):524-527.
[124]孙光灵,周庆松,方传刚.基于最小类内方差的快速阈值分割算法[J].安徽理工大学学报(自然科学版).2005,25(1):39-42.
[125]肖超云,朱伟兴.基于Otsu准则及图像熵的阈值分割算法[J].计算机工程.2007,33(14):188-190.
[126]Liu J Z, Li W Q, and Tian Y P. Automatic thresholding of gray-level picturesusing two-dimension Otsu method[A]. International Conference on Circuits andSystems[C].Shenzhen,China,1991.325-327.
[127]刘建庄,粟文青.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.
[128]Gong J, Li L Y and Chen W N. Fast recursivealgorithmfortwo-dimensionalthresholding[J].PatternRecognition,1998,31(3): 295-300.
[129]赵凤,范九伦.一种结合二维熵和模糊熵的图像分割方法[J].计算机工程与应用.2006,32:17-20.
[130]范九伦,赵凤.灰度图像的二维Otsu曲线阈值分割法[J].电子学报. 2007,35(4):751-755.
[131]郝颖明,朱枫.2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.
[132]吴一全,潘喆，吴文怡.二维直方图区域斜分阈值分割及快速递推算法[J].通信学报.2008,29(4):77-84.
[133]吴一全,潘喆，吴文怡.二维直方图斜分Tsallis-Havrda-Charvt熵图像阈值分割[J].光电工程.2008,35(7):53-58.
[134]贾承丽. SAR图像道路和机场提取方法研究[D].长沙:国防科技大学. 2006.65-66.
[135]Lopes A, Touzi R, and Nezry E. Adaptive speckle filters and sceneheterogeneity[J]. IEEE Transactions on Geoscience and Remote Sensing. 1990,28(6):992-1000.
[136]Zhang Y J. A survey on evaluation methods for image segmentation[J]. PatternRecoynition.1996,29(8):1335-1346.
[137]朱兵,李金宗,陈爱军.基于知识的快速港口识别[J].计算机应用.2006,26(3):729-732.
[138]Paes R L, Lorenzzetti J A, and Gherardi D F M. Ship Detection UsingTerraSAR-X Images in the Campos Basin[J]. IEEE Geoscience and RemoteSensingLetters.2010,7(3):545-548.
[139]TuellGH, Lucas J R,andGraham DB.Anaccuracyassessmentofshorelinedatafor Castle Bay Alaska compiled from synthetic aperture radar[A]. OCEANS '99MTS/IEEE. Riding the Crest into the 21st Century. Seattle, WA , USA. 1999.1325-1332.
[140]Eldhuset K. An automatic ship and ship wake detection system for spaceborneSAR images incoastal regions[J].IEEETrans. GeoscienceRemoteSensing.1996,34(4):1010–1019.
[141]Wang J and Sun L J. Study on Ship Target Detection and Recognition in SARimagery[A]. IEEE International Conference on Information Science andEngineering[C].Nanjing,China. 2009.1456-1459.
[142]Zhu C R, Zhou H, Wang R S, et al. A Novel Hierarchical Method of ShipDetection from Spaceborne Optical Image Based on Shape and TextureFeatures[J]. IEEE Transactions on Geoscience and Remote Sensing. 2010, 48(9):3446-3456.
[143]Hwang S and Ouchi K. On a Novel Approach Using MLCC and CFAR for theImprovement of Ship Detection by Synthetic Aperture Radar[J]. IEEETransactionsonGeoscienceandRemoteSensingletters.2010,7(2):391-395.
[144]AiJ Q,QiX Y,Yu WD,etal.ANewCFARShipDetectionAlgorithmBasedon2-D Joint Log-Normal Distribution in SAR Images[J]. IEEE Transactions onGeoscienceandRemoteSensingletters.2010,7(4):806-810.
[145]Chen P, HuangW G, Yang J S, et al.Comparison of ship detection algorithms inspaceborneSARimagery[A].IEEE International GeoscienceandRemote SensingSymposium[C].Seoul,Korea.2005.1750-1752.
[146]Xing X W, Chen Z L, Zou H X. A fast algorithm based on two-stage CFAR fordetecting ships in SAR images[A]. Asian-Pacific Conference on SyntheticApertureRadar[C].Xian, China.2009.506-509.
[147]Yanga C S and Kang C G. Ship detection experiments using RADARSAT SARimages[A].2005IEEE International Geoscience and Remote SensingSymposium(IGARSS'05).Seoul,Korea.2005.1177-1180.
[148]Vachon P W, Thomas S J, Cranton J, et al. Validation of Ship Detection by theRADARSAT Synthetic Aperture and the Ocean Monitoring Workstation[J]CanadianJournalofRemoteSensing,2000,26(3):200-212.
[149]高贵. SAR图像目标ROI自动获取技术研究[D].长沙:国防科技大学. 2007.43-45,102.
[150]张琦.基于统计模型的SAR图像车辆目标检测方法研究[D].长沙:国防科技大学.2005.6-7.
[151]MengesC, Marre F, and Dhar T. Sea-clutter analysis at multiple wavelengths (L,C, X) for target-clutter contrast assessment in littoral waters[A]. 2009 IEEEInternational Geoscience and Remote Sensing Symposium (IGARSS’09). CapeTown,SouthAfrica.2009.713-716.
[152]李晓玮,种劲松.基于小波分解的K-分布SAR图像舰船检测[J].测试技术学报.2007,21(4):350-354.
[153]Frery A C, et al. A model for extremely heterogeneous clutter[J]. IEEETransactionsonGeoscienceandRemoteSensing.1997,35(3):648-659.
[154]DeVore M D. Analytical performance evaluation of SAR ATR with inaccurate orestimated models[A]. In: Proc. of theSPIE on Algorithms for Synthetic ApertureRadarImagery[C],Orlando,Florida,USA,2004,5427:407-417.
[155]Tison C, Nicolas J M and Tupin F, et al. A new statistical model for Markovianclassification of urban areas in high-resolution SAR images[J]. IEEE Trans. onGeoscienceandRemoteSensing,2004,42(10):2046-2057.
[156]DeVore M D and O’Sullivan J A. Quantitative statistical assessment ofconditional models for synthetic aperture radar[J]. IEEE Trans. on ImagingProcessing,2004,13(2):113-124.
[157]时公涛,高贵,周晓光等.基于Mellin变换的G0分布参数估计方法[J].自然科学进展.2009,19(6):677-690.
[158]贺志国,周晓光,陆军等.一种基于G0分布的SAR图像快速CFAR检测方法[J].国防科技大学学报.2009,31(1):47-51.
[159]时公涛.基于干涉图的多通道SAR地面慢动目标自动检测技术研究[D].长沙:国防科技大学.2009.129-130.
[160]Gao G, Liu L, Zhao L J et al. An Adaptive and Fast CFAR Algorithm Based onAutomatic Censoring for Target Detection in High-Resolution SAR Images[J].IEEETransactionsonGeoscienceandRemoteSensing.2008,46(12):1-13.
[161]Bhanu B and Lin Y Q. Genetic algorithm based feature selection for targetdetectioninSARimages[J].ImageandVisionComputing.2003,(2): 591–608.
[162]李禹. SAR图像机动目标检测与鉴别技术研究[D].长沙:国防科技大学.2007.67,75-76,89-90.
[163]高贵,匡纲要,李德仁.高分辨率SAR图像分割及目标特征提取[J].宇航学报.2006,27(3):238-244.
[164]Lin H and Venetsanopoulos A N. A weighted minimum distance classifier forpattern recognition[A]. Proceedings of the 6th CanadianConference on ElectricalandComputerEngineering[C].Vancouver,BC,Canada.1993.904-907.
[165]Chiang H C, Moses R L andPotter L C.Model-based Bayesian feature matchingwith application to synthetic aperture radar target recognition[J]. PatternRecognition.2001,(34): 1539-1553.
[166]王一达,沈熙玲,谢炯.遥感图像分类方法综述[J].遥感信息. 2006, (5):67-71.
[167]Anagnostopoulos G C. SVM-based target recognition from synthetic apertureradar images using target region outline descriptors[J]. Nonlinear Analysis. 2009,(71):e2934-e2939.
[168]Burl M C,et al. Texture Discrimination in Synthetic Aperture Radar Imagery[A].Twenty-Third Asilomar Conference on Signals, Systems and Computers[C].PacificGrove,CA.1989.399-404.
[169]Kreithen D E, et al. Discriminating Targets from Clutter[J]. The LincolnLaboratoryJournal.1993,6(1):25-51.
[170]Verbout S M, et al. New Image Features for Discriminating Targets fromClutter[J].SPIEProceedingonRadarSensorTechnology.1998,3395:120-137.
[171]Lin Y Q, et al. Evolutionary Feature Synthesis for Object Recognition[J]. IEEETrans. Systems, Man, And Cybernetics-Part C: Applications and Reviews. 2005,35(2):156-171.
[172]Gao G, et al. Fast Detecting and Locating Groups of Targets in High-ResolutionSARimages[J].PatternRecognition, 2007,40(4):1378-1384.
[173]周俊.城市大比例尺航空影像建筑物提取技术的研究[D].郑州:信息工程大学.2004.30-31.
[174]Walker E L and Kang H B. Fuzzy measures of uncertainty in perceptualgrouping[A]. Proceedings of the Third IEEE Conference on Fuzzy Systems.Orlando,FL,USA.1994.2020-2024.
[175]匡纲要,高贵,蒋咏梅等.合成孔径雷达目标检测理论、算法及应用[M].长沙:国防科技大学出版社.2007.344-345.
[176]Zhang H, Fritts J E and Sally A. Goldman. Image segmentation evaluation: Asurvey of unsupervised methods[J]. Computer Vision and Image Understanding.2008,110:260-280.
[177]关新平,刘冬,唐英干.基于可分离性判据的自适应加权纹理图像分割[J].计算机应用研究.2005,(11):233-235.
[178]陈绵书,付萍,张春雨.基于最小距离最大原则的模式分类[J].计算机工程.2004,30(9):28-30.
[179]庄哲民,张阿妞,李芬兰.基于优化的LDA算法人脸识别研究[J].电子与信息学报.2007,29(9):2047-2049.
[180]郭亚琴,王正群.基于类内类间离散度的分类器设计方法[J].信息技术.2010,(5):35-37.
[2]邹焕新. SAR图像舰船目标与航迹检测方法研究[D].长沙:国防科技大学.2003.1.
[3] Liu Y J and Feng Q. Sea surface ship detection in SAR images[A]. 2004 IEEEInternational Geoscience and Remote Sensing Symposium (IGARSS’04). Alaska,USA.2004.4723-4725.
[4] Huang S Q, Liu D Z, and Gao G Q, et al. A novel method for speckle noisereduction and ship target detection in SAR images[J]. Pattern Recognition. 2009,42:1533-1542.
[5]王培. SAR图象中船舶目标的提取及分形方法在SAR图象分类中的应用[D].北京:中国科学院电子学研究所.2000.2.
[6] Gamba P and Mecocci A. Harbour images sequence analysis for control andmonitoring[A]. 1997 IEEE International Conference on Acoustics, Speech, andSignalProcessing.Munich,Germany.1997.2877-2880.
[7] YangHM and Wu M M. A new type of harbour surveillance radar with diversityprocessing[A]. CIE International Conference of Radar. Beijing, China. 1996.614-619.
[8]吴建华.遥感图像中港口识别与毁伤分析研究[D].南京:南京理工大学.2005.1-2,16,37-41.
[9]周拥军,朱兆达,丁全心.遥感图像中港口目标识别技术[J].南京航空航天大学学报.2008,40(3):350-353.
[10]种劲松.合成孔径雷达图像舰船目标检测算法与应用研究[D].北京:中国科学院电子学研究所.2002.5,23-32,43-44.
[11] Mandal D P, Murthy C A, Pal S K. Analysis of IRS Imagery for DetectingMan-Made Objects With a Multi-valued Recognition System[J]. IEEE Trans onsystems,ManandCybernetics.Parta:systemsandhumans.1996.26(2):241-247.
[12] Li Y. and Peng J. Feature extraction and recognition of harbor contour[J]. SPIEProceedings on Image Extraction, Segmentation, and Recognition. 2001, 4550:234-238.
[13]郑孝娟.高分辨率可见光遥感图像的港口变化检测方法研究[D].合肥:中国科学技术大学.2008.45-48.
[14]陈琨,陈学佺.一种基于几何特征的舰船与码头目标分割的新方法[J].计算机工程与应用.2004,31:197-200.
[15]张志龙.基于遥感图像的重要目标特征提取与识别方法研究[D].长沙:国防科技大学.2005.146-155.
[16]邢坤,付宜利.基于内港区域的港口目标识别[J].电子与信息学报.2009,31(6):1275-1278.
[17] Zhu B, Li J Z and Cheng A J. Knowledge based recognition of harbor target[J].JournalofSystemsEngineeringandElectronics.2006,17(4):755-759.
[18]魏军伟.遥感图像中港口目标检测研究与实现[D].西安:西安电子科技大学.2007.22-24.
[19]赵波.遥感图像目标识别算法研究[D].长沙:国防科技大学.2004.45-50.
[20]杨耘,王树根,邱丹丹.基于规则的高分辨率影像港口识别模型[J].测绘信息与工程.2005,30(5):40-42.
[21]方晓芙.遥感图像中战略目标识别方法研究[D].西安:西北工业大学.2004.15-19.
[22]李艳,彭嘉雄.港口目标特征提取与识别[J].华中科技大学学报. 2001, 29(6):10-12.
[23]周静.典型地海背景下目标识别方法研究[D].武汉:华中科技大学. 2005.54-59.
[24]侯彪,刘芳,焦李成.基于小波变换的高分辨SAR港口目标自动分割[J].红外与毫米波学报.2002,21(5):385-389.
[25] Vachon P W, Adlaldaa P, Edel H, et a1. Canadian progress toward marine andcoastal applications of synthetic aperture radar[J].Johns Hopkins APL TechnicalDigest.2000,21(1):33-40.
[26] WackermanC C, Friedman K S, Pichel W G,et a1. Automatic detection of shipsin radarsat-l Sar imagery[J]. Canadian Journal of Remote Sensing. 2001, 27(5):568-577.
[27] Schwartz G, Alvarez M, Varfis A, et a1. Elimination of false positives in vesselsdetection and identification by remote sensing[A]. IEEE International GeoscienceandRemoteSensingSymposium[C].Toronto,Canada.2002,1:116-118.
[28] Crisp D J. The State-of-the-Art in Ship Detection in Synthetic Aperture RadarImagery[R]. Edinburgh, South Australia, Australia: Australia DSTO InformationSciencesLaboratory.2004.86.
[29] EldhusetK. Principlesandperformanceofanautomatedshipdetectionsystemforsat image[A]. IEEE Intemational Geoscience and Remote SensingSymposium[C].Vancouver,Canada.1989.358-361.
[30] Tunaley J K E. Algorithms for ship detection and tracking using satelliteimagery[A]. IEEE Intemational Geoscience and Remote Sensing Symposium[C].Anchorage,Alaska,USA.2004,3:1804-1807.
[31] Eldhuset K. Principles And Performance Of An Automated Ship DetectionSystem For Sar Images[A]. IEEE International Geoscience and Remote SensingSymposium[C].Vancouver,Canada.1989.358-361.
[32]李海艳.极化SAR图像海面船只监测方法研究[D].青岛:中国科学院海洋研究所.2007.10.
[33] Greidanus H, Clayton P, Indregard M,et al.Benchmarking operational SAR shipdetection[A].IEEE InternationalGeoscienceandRemoteSensingSymposium[C].Anchorage,Alaska,USA.2004.4215-4218.
[34] Lombardo P and Sciotti M. Segmentation-based technique for ship detection inSARimages[J].IEEProc-RadarSonarNaving.2001,148(3):147-159.
[35] Sciotti M and Lombardo P. Ship detection in SAR images a segmentation-basedapproach[A].IEEERadarConference[C]. Atlanta,Georgia,USA.2001.81-87.
[36] Wang P, Chong J and Wang H. Ship detection of the airborne SAR images[A].IEEE 2000 International Geoscience and Remote Sensing Symposium(IGARSS'00).Honolulu,Hawaii.2000.348-350.
[37]种劲松,朱敏慧.高分辨率合成孔径雷达图像舰船检测方法[J].测试技术学报.2003,17(1):15-18.
[38]张天序,赵广州,王飞.一种快速递归红外舰船图像分割新算法[J].红外与毫米波学报.2006,25(4):295-300.
[39]宿丁,张启衡,谢盛华.一种强海杂波多目标分形分割算法[J].计算机工程与应用.2006,16:12-14.
[40]张风丽,吴炳方,张磊.基于小波分析的SAR图像船舶目标检测[J].计算机工程.2007,33(6):33-34.
[41] BenelliG,Garzelli A andMecocciA.Completeprocessingsystemthatusesfuzzylogic for ship detection in SAR images[J]. IEE Proc-Radar,Sonar Naving. 1994,141(4):181-186.
[42] Argenti F,Benelli Gand Garzelli A. AutomaticshipdetectioninSAR images[A].IEEInternationalConferenceRadar[C].Brighton,UK.1992.465-468.
[43]邹焕新,匡纲要,郁文贤.基于特征矢量匹配的SAR海洋图像舰船目标检测[J].现代雷达.2004,26(8):25-29.
[44]李文武,李智勇,粟毅.一种联合灰度和纹理特征的光学图像舰船目标检测方法[A].第十四届全国图象图形学学术会议[C].福州,福建.2008.293-296.
[45] Jiang Q S, WangS R, Ziou D, et al. Ship detection in RadarsatSAR imagery[A].IEEE International Conference on Systems, Man, and Cybernetics[C].San Diego,USA.1998.4562-4566.
[46] Ouchi K, Tamaki S, Yaguchi H, et al.Ship detection based on coherence imagesderivedfrom cross correlationofmultilookSAR images[J].IEEE GeoscienceandRemoteSensingLetters.2004,1(3):184-187.
[47]田巳睿,王超,张红. EnvisatAP图像P-CFAR舰船检测方法研究[J].遥感技术与应用.2007,22(2):183-187.
[48]雷琳,粟毅.一种基于轮廓匹配的近岸舰船检测方法[J].遥感技术与应用.2007,22(5):622-627.
[49]李长军,陈学佳,丁洽国.一种港口区域舰船目标变化检测新方法[J].计算机工程.2006,32(14):190-192.
[50]隆刚,陈学佺.高分辨率遥感图像港内舰船的自动检测方法[J].计算机仿真.2007,24(5):118-201.
[51]蒋李兵,王壮,胡卫东.一种基于可变夹角链码的靠岸舰船目标检测方法[J].遥感技术与应用.2007,22(1):88-94.
[52] http://data.ekejian.com/viewstaticres/SysContent4/d0/dd0/ddd121/702415679321/702415679321.doc[EB/OL],2007-3-21/2009-4-6.
[53]李增军.世界第三大集装箱港口-中国台湾高雄港[J].港口经济. 2001, (1):56-56.
[54] http://www.buildbook.com.cn/ebook/2007/B10035414/7.htm[EB/OL],2007-4-14/2009-4-6.
[55] http://www.fpa.gov.cn/WEB1/OTHER/k3.doc[EB/OL],2008-5-23/2009-4-6.
[56]洪承礼.港口规划与布置[M].北京:人民交通出版社.1999.118.
[57] http://col.njtu.edu.cn/zskj/3013/9/main-3.htm[EB/OL],2007-9-2/2009-04-06.
[58]韩理安.港口水工建筑物[M].北京:人民交通出版社.2000.1.
[59] http://bbs3.zhulong.com/forum/detail3822297_1.html[EB/OL],2003-8-29/2009-04-06.
[60] [美]赫尔别克主编.[译]李玉成等.海岸及海洋工程手册(第一卷)[M].大连:大连理工大学出版社.1992.730.
[61] Abraham D M, et al. Modeling and simulation of breakwater construction[A].Proceedings of Winter Simulation Conference[C]. Arlington, VA, USA 1995.1017-1023.
[62] Carpenter R N, Cray B A, and Levine E R. Broadband Ocean Acoustic (BOA)Laboratory in Narragansett Bay: preliminary in-situ harbor securitymeasurements[J]. Procedings of SPIE the International Society for OpticalEngineering.2006.6204: 620409.
[63] Nakamichi M, Sugaya M, and Sezaki Y, et al. Design and construction ofembedded steel-plate cell breakwater[A]. IEEE TECHNO-OCEAN’04. Japan.2004.59-65.
[64] Abraham D M. Modeling and simulation of breakwater construction[A].Proceedings of the 1995 Winter Simulation Conference. Hyatt Regency CrystalCity,Arlington,VA.1995.1017-1023.
[65] http://col.njtu.edu.cn/zskj/3013/9/Main-6.htm[EB/OL],2007-9-2/2009-4-6.
[66]雷松林,郑永来.防波堤结构型式及其应用探讨[J].中国水运. 2007, 7(6):131-132.
[67]陈万佳.港口水工建筑物[M].北京:人民交通出版社.1995.350.
[68]赵凌君.高分辨率SAR图像建筑物提取方法研究[D].长沙:国防科技大学.2009.19,99.
[69]舒士畏,赵立平.雷达图象及其应用[M].北京:中国铁道出版社. 1988.171-173.
[70] Xie H, Li L L, and Bo H, et al. A Novel Method for Ship Detection Based onNSCT and ACO[A]. The 2nd International Conference on Image and SignalProcessing.Tianjin,China.2009.1-4.
[71]李娟.基于模糊理论的图像分割算法研究[D].武汉:武汉科技大学.2005.12.
[72] Kim D J, Park S E, andMoon W M, et al. Effect of radar frequency on waterlinemapping from airborne SAR image in the intertidal zone[A]. 2005 IEEEInternational Geoscience and Remote Sensing Symposium (IGARSS'05). Seoul,Korea.2005.999-1001.
[73]迂学峰,吴庆洪.美元图像的自适应阈值分割方法[J].现代电子技术. 2007,(8):96-100.
[74]梁华为.直接从双峰直方图确定二值化阈值[J].模式识别与人工智能. 2002,15(2):253-256.
[75]王文宁,王汇源,牟文英.一种新的灰度直方图分割阈值的自动检测方法[J].计算机工程与应用.2005,26:89-91.
[76]程杰.一种基于直方图的分割方法[J].华中理工大学学报.1999,27(1):84-86.
[77]冯慧扬,王申康,王宏伟.人脸定位算法的研究[J].计算机工程与应用.2003,30:101-104.
[78]梁栋,李新华.一种基于人工智能的阈值自动选择方法[J].微电子学与计算机.1999,(1):2-5.
[79] Yin P Y and Chen L H. A new method for multilevel thresholding usingsymmetry and duality of the histogram[A]. IEEE 1994 International Symposiumon Speech, Image Processing and Neural Networks[C]. Hong Kong, China. 1994.45-48.
[80] Cheng H D, Jiang X H, Sun Y, et al. Color image segmentation: advances andprospects[J].PatternRecognition.2001,34:2259-2281.
[81]吴一全,朱兆达.图像处理中阈值选取方法30年(1962—1992)的进展(一)[J].数据采集与处理.1993,8(3):193-201.
[82]左奇,史忠科.一种基于直方图评价函数的快速图像分割方法[J].计算机工程与应用.2003,19:5-7.
[83]吴一全,朱兆达.图像处理中阈值选取方法30年(1962—1992)的进展(二)[J].数据采集与处理.1993,8(4):268-282.
[84]韩思奇,王蕾.图像分割的阈值法综述[J].系统工程与电子技术. 2002, 24(6):91-95.
[85]罗希平,田捷,诸葛婴等.图像分割方法综述[J].模式识别与人工智能1999,12(3):300-312.
[86]张龙,余玲玲,刘京南.一种改进的最大熵阈值分割方法[J].电子工程师.2006,32(11):40-43.
[87]修春波,刘向东,张宇河.基于混沌优化的最佳熵阈值的图像分割[J].计算机工程与应用.2004,27:76-78.
[88]王毅,牛奕龙,董建园等.基于改进遗传算法的最佳熵多阈值三维医学图像分割算法[J].西北工业大学学报.2007,25(3):442-445.
[89]王栋,朱明.低对比度图像中改进的二维熵阈值分割法[J].仪器仪表学报.2004,25A(4):355-359.
[90]张家树,李北川.灰度图象的二维最大熵阈值分割研究[J].西南师范大学学报.1995,20(6):643-647.
[91] Pal N R and Pal S K. Object-background segmentation using new definitions ofentropy[J].1989IEEProceddings.1989,136(4):284-295.
[92] ChenH D andChen J R.Automaticallydeterminethemembershipfunctionbasedonthemaximumentropyprinciple[J].InformationScience.1997,96:163-182.
[93] Ullah A. Entropy, divergence and distance measures with econometricapplications[J].JournalofStatisticalplanningandinference.1996,49:137-162.
[94] PalSKandPal NR. Objectextractionfromimageusinghigherorderentropy[A].9th International Conference on Pattern Recognition[C]. Rome, Italy. 1988.348-350.
[95] Pal N R and Pal S K. Entropy: a new definition and its applications[J]. IEEETransactionsonSystemManandCybernetics.1991,21(5):1260-1270.
[96] Abutaleb A S. Automatic thresholding of gray-level pictures usingtwo-dimensional entropy[J]. Computer Vision,Graphics and Image Process, 1989,47:22-32.
[97]金永镐,崔荣一,金小峰.基于交叉熵极小化的图像边缘检测算法[J].吉林大学学报(自然科学版).2006,24(6):656-660.
[98]黄春艳,杨国胜,侯艳丽.基于熵的图像二值化方法比较研究[J].河南大学学报.2005,35(2):76-78.
[99]范立生,杨健,彭应宁.基于交叉熵的特征提取与河流区域的目标检测[J].系统工程与电子技术.2006,28(3):339-341.
[100]Pal N R. On minimum cross-entropy thresholding[J]. Pattern Recognition. 1996,29(4):575-580.
[101]Brink A D and Pendock N E. Minimum cross-entropy threshold selection[J].PatternRecognition.1996,29(1):179-188.
[102]乔韦华韦华,吴成茂.二维最大类间交叉熵阈值分割法[J].西北大学学报(自然科学版).2008,38(3):374-378.
[103]Tseng D C and Shieh W S. Plume segmentation using local entropicthresholding[A].11thInternationalConferenceonPatternRecognition[C].Hague,Netherlands.1992.156-159.
[104]薛景浩,章毓晋,林行刚.图像分割中的交叉熵和模糊散度算法[J].电子学报.1999,27(10):131-134.
[105]郑毅,刘上乾.基于模糊指数熵和模拟退火的图像分割[J].红外技术. 2006,28(7):395-399.
[106]陈涛,司锡才.基于直方图的模糊最大指数熵图像分割方法[J].哈尔滨工程大学学报.2004,25(4):521-524.
[107]张昆辉,曹兰英,夏良正.基于遗传算法的二维模糊C-划分最大熵SAR图像分割[J].信号处理.2005,21(2):199-201.
[108]王正勇,陶青川,吴晓红等.基于模糊散度的图象分割[J].四川大学学报.2002,39(2):228-231.
[109]赵立兴,唐英干,刘冬等.基于直方图指数平滑的模糊散度图像分割[J].系统工程与电子技术.2005,27(7):1182-1185.
[110]李弼程,柳葆芳.基于二维直方图的模糊门限分割方法[J].数据采集与处理.2000,15(3):324-329.
[111]薛景浩,章毓晋,林行刚.基于最大类间后验交叉熵的阈值比分割算法[J].中国图象图形学报.1999,4A(2):110-114.
[112]Bhatt R B. Image Segmentation by Histogram Adaptive Fuzzification[A]. IEEEIndicon2005Conference[C].Chennai,India.2005.535-538.
[113]FanJ L andXie WX.Distance measure andinducedfuzzyentropy[J].Fuzzysetsandsystems.1999.(104):305-314.
[114]Montes S, Couso I, Gil P, et al. Divergence measure between fuzzy sets[J].InternationJournalofapproximatereasoning.2002.(30):91-105.
[115]Sen D and Pal S K. Image Segmentation using Global and Local FuzzyStatistics[A].IEEEIndiaConference[C].NewDelhi,India.2006.1-6.
[116]Cheng H D, Chen Y H and Sun Y. A novel fuzzy entropy approach to imageenhancementandthresholding[J].SignalProcessing.1999,75:277-301.
[117]Avci E and Avci D. An expert system based on fuzzy entropy for automaticthreshold selection in image processing[J]. Expert Systems and Applications.2008,36(2):3077-3085.
[118]Huang L K and WANG M J. Image thresholding by minimizing the measures offuzziness[J].PatternRecognition.1995,28(1):41-51.
[119]Benabdelkader S and Boulemden M. Recursive algorithm based on fuzzy2-partition entropy for 2-level image thresholding[J]. Pattern Recognition. 2005,38:1289-1294.
[120]Forero-Vargas M G and Rojas-Camacho O. New formulation in imagethresholding using fuzzy logic[A]. 11th Portuguese Conference on PatternRecognition[C]. Porto,Portugal.2000.117–124.
[121]翟辉琴.基于数学形态学的遥感影像水域提取方法[J].测绘科学. 2006, 31(1):22-24.
[122]朱俊杰.高分辨率SAR图像的水体边缘快速自动与精确检测[J].遥感信息应用技术.2005,5:29-31.
[123]胡正磊.基于小波边缘提取和脊线跟踪技术的SAR图像河流检测算法[J].电子与信息学报.2007,29(3):524-527.
[124]孙光灵,周庆松,方传刚.基于最小类内方差的快速阈值分割算法[J].安徽理工大学学报(自然科学版).2005,25(1):39-42.
[125]肖超云,朱伟兴.基于Otsu准则及图像熵的阈值分割算法[J].计算机工程.2007,33(14):188-190.
[126]Liu J Z, Li W Q, and Tian Y P. Automatic thresholding of gray-level picturesusing two-dimension Otsu method[A]. International Conference on Circuits andSystems[C].Shenzhen,China,1991.325-327.
[127]刘建庄,粟文青.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.
[128]Gong J, Li L Y and Chen W N. Fast recursivealgorithmfortwo-dimensionalthresholding[J].PatternRecognition,1998,31(3): 295-300.
[129]赵凤,范九伦.一种结合二维熵和模糊熵的图像分割方法[J].计算机工程与应用.2006,32:17-20.
[130]范九伦,赵凤.灰度图像的二维Otsu曲线阈值分割法[J].电子学报. 2007,35(4):751-755.
[131]郝颖明,朱枫.2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.
[132]吴一全,潘喆，吴文怡.二维直方图区域斜分阈值分割及快速递推算法[J].通信学报.2008,29(4):77-84.
[133]吴一全,潘喆，吴文怡.二维直方图斜分Tsallis-Havrda-Charvt熵图像阈值分割[J].光电工程.2008,35(7):53-58.
[134]贾承丽. SAR图像道路和机场提取方法研究[D].长沙:国防科技大学. 2006.65-66.
[135]Lopes A, Touzi R, and Nezry E. Adaptive speckle filters and sceneheterogeneity[J]. IEEE Transactions on Geoscience and Remote Sensing. 1990,28(6):992-1000.
[136]Zhang Y J. A survey on evaluation methods for image segmentation[J]. PatternRecoynition.1996,29(8):1335-1346.
[137]朱兵,李金宗,陈爱军.基于知识的快速港口识别[J].计算机应用.2006,26(3):729-732.
[138]Paes R L, Lorenzzetti J A, and Gherardi D F M. Ship Detection UsingTerraSAR-X Images in the Campos Basin[J]. IEEE Geoscience and RemoteSensingLetters.2010,7(3):545-548.
[139]TuellGH, Lucas J R,andGraham DB.Anaccuracyassessmentofshorelinedatafor Castle Bay Alaska compiled from synthetic aperture radar[A]. OCEANS '99MTS/IEEE. Riding the Crest into the 21st Century. Seattle, WA , USA. 1999.1325-1332.
[140]Eldhuset K. An automatic ship and ship wake detection system for spaceborneSAR images incoastal regions[J].IEEETrans. GeoscienceRemoteSensing.1996,34(4):1010–1019.
[141]Wang J and Sun L J. Study on Ship Target Detection and Recognition in SARimagery[A]. IEEE International Conference on Information Science andEngineering[C].Nanjing,China. 2009.1456-1459.
[142]Zhu C R, Zhou H, Wang R S, et al. A Novel Hierarchical Method of ShipDetection from Spaceborne Optical Image Based on Shape and TextureFeatures[J]. IEEE Transactions on Geoscience and Remote Sensing. 2010, 48(9):3446-3456.
[143]Hwang S and Ouchi K. On a Novel Approach Using MLCC and CFAR for theImprovement of Ship Detection by Synthetic Aperture Radar[J]. IEEETransactionsonGeoscienceandRemoteSensingletters.2010,7(2):391-395.
[144]AiJ Q,QiX Y,Yu WD,etal.ANewCFARShipDetectionAlgorithmBasedon2-D Joint Log-Normal Distribution in SAR Images[J]. IEEE Transactions onGeoscienceandRemoteSensingletters.2010,7(4):806-810.
[145]Chen P, HuangW G, Yang J S, et al.Comparison of ship detection algorithms inspaceborneSARimagery[A].IEEE International GeoscienceandRemote SensingSymposium[C].Seoul,Korea.2005.1750-1752.
[146]Xing X W, Chen Z L, Zou H X. A fast algorithm based on two-stage CFAR fordetecting ships in SAR images[A]. Asian-Pacific Conference on SyntheticApertureRadar[C].Xian, China.2009.506-509.
[147]Yanga C S and Kang C G. Ship detection experiments using RADARSAT SARimages[A].2005IEEE International Geoscience and Remote SensingSymposium(IGARSS'05).Seoul,Korea.2005.1177-1180.
[148]Vachon P W, Thomas S J, Cranton J, et al. Validation of Ship Detection by theRADARSAT Synthetic Aperture and the Ocean Monitoring Workstation[J]CanadianJournalofRemoteSensing,2000,26(3):200-212.
[149]高贵. SAR图像目标ROI自动获取技术研究[D].长沙:国防科技大学. 2007.43-45,102.
[150]张琦.基于统计模型的SAR图像车辆目标检测方法研究[D].长沙:国防科技大学.2005.6-7.
[151]MengesC, Marre F, and Dhar T. Sea-clutter analysis at multiple wavelengths (L,C, X) for target-clutter contrast assessment in littoral waters[A]. 2009 IEEEInternational Geoscience and Remote Sensing Symposium (IGARSS’09). CapeTown,SouthAfrica.2009.713-716.
[152]李晓玮,种劲松.基于小波分解的K-分布SAR图像舰船检测[J].测试技术学报.2007,21(4):350-354.
[153]Frery A C, et al. A model for extremely heterogeneous clutter[J]. IEEETransactionsonGeoscienceandRemoteSensing.1997,35(3):648-659.
[154]DeVore M D. Analytical performance evaluation of SAR ATR with inaccurate orestimated models[A]. In: Proc. of theSPIE on Algorithms for Synthetic ApertureRadarImagery[C],Orlando,Florida,USA,2004,5427:407-417.
[155]Tison C, Nicolas J M and Tupin F, et al. A new statistical model for Markovianclassification of urban areas in high-resolution SAR images[J]. IEEE Trans. onGeoscienceandRemoteSensing,2004,42(10):2046-2057.
[156]DeVore M D and O’Sullivan J A. Quantitative statistical assessment ofconditional models for synthetic aperture radar[J]. IEEE Trans. on ImagingProcessing,2004,13(2):113-124.
[157]时公涛,高贵,周晓光等.基于Mellin变换的G0分布参数估计方法[J].自然科学进展.2009,19(6):677-690.
[158]贺志国,周晓光,陆军等.一种基于G0分布的SAR图像快速CFAR检测方法[J].国防科技大学学报.2009,31(1):47-51.
[159]时公涛.基于干涉图的多通道SAR地面慢动目标自动检测技术研究[D].长沙:国防科技大学.2009.129-130.
[160]Gao G, Liu L, Zhao L J et al. An Adaptive and Fast CFAR Algorithm Based onAutomatic Censoring for Target Detection in High-Resolution SAR Images[J].IEEETransactionsonGeoscienceandRemoteSensing.2008,46(12):1-13.
[161]Bhanu B and Lin Y Q. Genetic algorithm based feature selection for targetdetectioninSARimages[J].ImageandVisionComputing.2003,(2): 591–608.
[162]李禹. SAR图像机动目标检测与鉴别技术研究[D].长沙:国防科技大学.2007.67,75-76,89-90.
[163]高贵,匡纲要,李德仁.高分辨率SAR图像分割及目标特征提取[J].宇航学报.2006,27(3):238-244.
[164]Lin H and Venetsanopoulos A N. A weighted minimum distance classifier forpattern recognition[A]. Proceedings of the 6th CanadianConference on ElectricalandComputerEngineering[C].Vancouver,BC,Canada.1993.904-907.
[165]Chiang H C, Moses R L andPotter L C.Model-based Bayesian feature matchingwith application to synthetic aperture radar target recognition[J]. PatternRecognition.2001,(34): 1539-1553.
[166]王一达,沈熙玲,谢炯.遥感图像分类方法综述[J].遥感信息. 2006, (5):67-71.
[167]Anagnostopoulos G C. SVM-based target recognition from synthetic apertureradar images using target region outline descriptors[J]. Nonlinear Analysis. 2009,(71):e2934-e2939.
[168]Burl M C,et al. Texture Discrimination in Synthetic Aperture Radar Imagery[A].Twenty-Third Asilomar Conference on Signals, Systems and Computers[C].PacificGrove,CA.1989.399-404.
[169]Kreithen D E, et al. Discriminating Targets from Clutter[J]. The LincolnLaboratoryJournal.1993,6(1):25-51.
[170]Verbout S M, et al. New Image Features for Discriminating Targets fromClutter[J].SPIEProceedingonRadarSensorTechnology.1998,3395:120-137.
[171]Lin Y Q, et al. Evolutionary Feature Synthesis for Object Recognition[J]. IEEETrans. Systems, Man, And Cybernetics-Part C: Applications and Reviews. 2005,35(2):156-171.
[172]Gao G, et al. Fast Detecting and Locating Groups of Targets in High-ResolutionSARimages[J].PatternRecognition, 2007,40(4):1378-1384.
[173]周俊.城市大比例尺航空影像建筑物提取技术的研究[D].郑州:信息工程大学.2004.30-31.
[174]Walker E L and Kang H B. Fuzzy measures of uncertainty in perceptualgrouping[A]. Proceedings of the Third IEEE Conference on Fuzzy Systems.Orlando,FL,USA.1994.2020-2024.
[175]匡纲要,高贵,蒋咏梅等.合成孔径雷达目标检测理论、算法及应用[M].长沙:国防科技大学出版社.2007.344-345.
[176]Zhang H, Fritts J E and Sally A. Goldman. Image segmentation evaluation: Asurvey of unsupervised methods[J]. Computer Vision and Image Understanding.2008,110:260-280.
[177]关新平,刘冬,唐英干.基于可分离性判据的自适应加权纹理图像分割[J].计算机应用研究.2005,(11):233-235.
[178]陈绵书,付萍,张春雨.基于最小距离最大原则的模式分类[J].计算机工程.2004,30(9):28-30.
[179]庄哲民,张阿妞,李芬兰.基于优化的LDA算法人脸识别研究[J].电子与信息学报.2007,29(9):2047-2049.
[180]郭亚琴,王正群.基于类内类间离散度的分类器设计方法[J].信息技术.2010,(5):35-37.