基于SAR影像的变化检测技术研究
|
摘要
遥感影像变化检测是利用不同时段的遥感影像对感兴趣的地物、目标的变化情况进行辨别分析的过程。基于SAR影像的变化检测是遥感影像变化检测的重要分支。围绕其整个流程,本文对涉及的四个部分进行了深入研究,主要工作和创新点如下:
1.设计了基于SAR影像的变化检测的技术流程,包括图像滤波、图像匹配、变化区域提取和精度评价。完成了一套工程化的变化检测系统。
2.针对经典空域统计滤波器仅仅依靠滤波窗口大小来调节滤波能力的问题,引入并改进了相关邻域模型,更加合理地描述了SAR影像局部滤波窗口中的邻域信息,采用基于改进相关邻域模型的MAP滤波器,在抑制斑点噪声的同时很好的保留影像中的边缘信息。
3.针对像素级变化检测中构造差异影像的问题,改进了差异影像的构造方法,采用差值融合比值的方法使差异影像中的差异信息更加丰富。对于从差异影像中提取变化区域的问题,引入了Bayes决策理论,在基于高斯分布的假设下,以非监督的方式找出最优变化阈值,实现了阈值选取的自动化。对于传统阈值方法没有考虑差异影像中相邻像元之间关系的情况,引入了马尔可夫模型进行了描述,改进了Bayes提取的方法。有效减少了检测结果中孤立像素的存在,提高了变化检测的精度。
4.深入分析了像素级变化检测的不足,提出了面向对象的变化检测方法,引入了Mean Shift算法。Mean Shift算法是一种有效的非参数分割算法,其在基于色域-空间域的基础上,通过直接估计特征空间概率密度函数的局部最值获取未知类别的密度模式,并确定模式的未知,然后使之聚类到和这个模式有关的类别中去。实现影像的分割。这种面向对象的分割方法能够迅速、准确的划分出同质区域。为进一步的变化检测提供重要的依据。
论文中所提出的算法都利用SAR影像进行了实验,并取得了比较满意的实验效果,可靠性和有效性都优于现有的经典算法。
Remote sensing image change detection is the distinguishing and analyzing process of interested ground object or target changes, the change detection based on SAR image is an important branch of remote sensing image change detection. Around its entire process, this paper involves four parts and research depthly, the main point of the work and innovation are as follows:
1.Designed the overall process of change detection based on SAR image, including image filtering, image matching, changes in regional extraction and accuracy evaluation.Also Completed a set of process-oriented change detection system.
2.In order to solve the problem of the classical statistical filters relying solely on the window’s size of filtering to adjust the filtering capacity in the spatial, I introduce and improve the relevant neighborhood model, descripted a more reasonable of the neighborhood information SAR image in the local filtering window , using the relevant neighborhood model based on improved The MAP filter in suppressing speckle noise at the same time retain a good image of the edge information.
3.The problem of constructing differences image in the pixel-level change detection, I improve the method of constructing differences image, using the difference integration ratio make the differences information much richer in the difference image. And then how to obtain the change region from the difference image.This problem can be solved using the Bayes decision theory, at the assumption that the Gaussian distribution, finding the optimal change use non-supervised means,achieving the threshold selection automation. For the traditional threshold method does not take into account differences in image context information, the introduction of the Markov model described in the context of information, effectively reducing the test results in the presence of isolated pixels and improve the change detection accuracy.
4.Analysis of the lack of pixel-level change detection and the object-oriented change detection method is proposed, the introduction of Mean Shift Algorithm, Mean Shift algorithm is an effective non-parametric segmentation algorithm, and on the basis of the color gamut-spatial through direclyt estimated feature space probability density function of the local minimum value of the density model to obtain the unknown category, and determine the mode of the unknown, and then make it to the cluster, and this model to the relevant categories,achieving image segmentationThis object-oriented segmentation method to quickly and accurately classified into homogeneous regions. Providing an important basis for change detection in the further.
The proposed algorithms are applied to SAR images , and obtained satisfactory experimental results, the reliability and validity are superior to the existing classical algorithm.
1.设计了基于SAR影像的变化检测的技术流程,包括图像滤波、图像匹配、变化区域提取和精度评价。完成了一套工程化的变化检测系统。
2.针对经典空域统计滤波器仅仅依靠滤波窗口大小来调节滤波能力的问题,引入并改进了相关邻域模型,更加合理地描述了SAR影像局部滤波窗口中的邻域信息,采用基于改进相关邻域模型的MAP滤波器,在抑制斑点噪声的同时很好的保留影像中的边缘信息。
3.针对像素级变化检测中构造差异影像的问题,改进了差异影像的构造方法,采用差值融合比值的方法使差异影像中的差异信息更加丰富。对于从差异影像中提取变化区域的问题,引入了Bayes决策理论,在基于高斯分布的假设下,以非监督的方式找出最优变化阈值,实现了阈值选取的自动化。对于传统阈值方法没有考虑差异影像中相邻像元之间关系的情况,引入了马尔可夫模型进行了描述,改进了Bayes提取的方法。有效减少了检测结果中孤立像素的存在,提高了变化检测的精度。
4.深入分析了像素级变化检测的不足,提出了面向对象的变化检测方法,引入了Mean Shift算法。Mean Shift算法是一种有效的非参数分割算法,其在基于色域-空间域的基础上,通过直接估计特征空间概率密度函数的局部最值获取未知类别的密度模式,并确定模式的未知,然后使之聚类到和这个模式有关的类别中去。实现影像的分割。这种面向对象的分割方法能够迅速、准确的划分出同质区域。为进一步的变化检测提供重要的依据。
论文中所提出的算法都利用SAR影像进行了实验,并取得了比较满意的实验效果,可靠性和有效性都优于现有的经典算法。
Remote sensing image change detection is the distinguishing and analyzing process of interested ground object or target changes, the change detection based on SAR image is an important branch of remote sensing image change detection. Around its entire process, this paper involves four parts and research depthly, the main point of the work and innovation are as follows:
1.Designed the overall process of change detection based on SAR image, including image filtering, image matching, changes in regional extraction and accuracy evaluation.Also Completed a set of process-oriented change detection system.
2.In order to solve the problem of the classical statistical filters relying solely on the window’s size of filtering to adjust the filtering capacity in the spatial, I introduce and improve the relevant neighborhood model, descripted a more reasonable of the neighborhood information SAR image in the local filtering window , using the relevant neighborhood model based on improved The MAP filter in suppressing speckle noise at the same time retain a good image of the edge information.
3.The problem of constructing differences image in the pixel-level change detection, I improve the method of constructing differences image, using the difference integration ratio make the differences information much richer in the difference image. And then how to obtain the change region from the difference image.This problem can be solved using the Bayes decision theory, at the assumption that the Gaussian distribution, finding the optimal change use non-supervised means,achieving the threshold selection automation. For the traditional threshold method does not take into account differences in image context information, the introduction of the Markov model described in the context of information, effectively reducing the test results in the presence of isolated pixels and improve the change detection accuracy.
4.Analysis of the lack of pixel-level change detection and the object-oriented change detection method is proposed, the introduction of Mean Shift Algorithm, Mean Shift algorithm is an effective non-parametric segmentation algorithm, and on the basis of the color gamut-spatial through direclyt estimated feature space probability density function of the local minimum value of the density model to obtain the unknown category, and determine the mode of the unknown, and then make it to the cluster, and this model to the relevant categories,achieving image segmentationThis object-oriented segmentation method to quickly and accurately classified into homogeneous regions. Providing an important basis for change detection in the further.
The proposed algorithms are applied to SAR images , and obtained satisfactory experimental results, the reliability and validity are superior to the existing classical algorithm.
引文
[1]李德仁.利用遥感图像进行变化检测[J].武汉大学学报信息科学版,2003,28(5):7-12.
[2]范海生,马蔼乃.采用图像差值法提取土地利用变化信息方法-以攀枝花仁和区为例[J].遥感学报,2001,5(1):75-80
[3]张路.基于多元统计分析的遥感影像变化检测方法研究[D].武汉大学博士学位论文,2004
[4]邵芸,宫华泽,王世昂,张风丽,田维.多元雷达遥感数据汶川地震灾情应急检测与评价[J].遥感学报,2008.11,12(6):865-869
[5]孙曼利.基于遥感影像的机场区域检测和毁伤分析研究[D].南京理工大学学位论文,2007
[6]王海兵.基于遥感影像的子母弹机场毁伤效果分析探究[D].南京理工大学学位论文,2007
[7] EI-Raey M,S.M Nasr,M.M.EI-Hattab,Change Detection of Rosetta Promontory OverPromontory Last FortyYears[J].Remote Sensing,1995,Vol.16:825-834
[8] Rignot E J M,van Zyle J J,Change detection techniques for ERS-1 SAR data[J].IEEE Trans, Geoscience and Remote Sensing,1993,31 (4):896-906
[9] Villasenor J D,Fatland D R,hinzman L D,Change detection on Alaska’s north slope using repeatpass ERS-1 SAR imagery[J].IEEE Trans.Geoscience and Remote Sensing,1993,31(1):227-236
[10]陈志鹏.基于纹理特征的差值变化检测方法研究[D].中国科学院电子学研究所硕士论文,2002
[11]赵小杰.成孔径雷达图像变化检测方法研究[D].中国科学院电子学研究所硕士论文,2001
[12]朱朝杰.基于特征分析的遥感图像变化检测方法研究[D].解放军信息工程大学测绘学院硕士论文,2007
[13]莫华.遥感影像上军事目标变化检测相关关键技术研究[D].解放军信息工程大学测绘学院硕士论文,2007
[14]陈科.基于判别分析的遥感图像变化检测方法研究[D].解放军信息工程大学测绘学院硕士论文2009
[15]马国锐.一种遥感影像核变化检测方法[J].武汉大学学报信息科学版,2007,32(7);579-600
[16] Lu D.P.Mausel,E.Brondizio,E Moran.Change detection techniques.International Journal of Remote Sensing[M].2004,25(12):2365-2407
[17] Bovolo F,Lorenzo bruzzone.A detail-perserving scale-driven approach to unsupervised change detection in remotely sensed imagery[J].IEEE Geoscience and Remote Sensing Letters,2006,3(4):457-461
[18] Jensen,J.R.Introductory Digital Image Processing:A Remote Sensing Perspective[M].2nd Edition Prentice Hall Press.,Upper Saddel River,NJ,1996
[19] Richard J.Radke,Srinivas Andra,Omar AI-Kofahi,Badrinath Roysam.Image Change Detection Algorithms:A Systematic Survey[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING VOL14,NO.3:294-307,MARCH 2005
[20]蔡纯,孙洪,曹永峰.基于区域似然比的SAR图像变化检测[J] .武汉大学学报理学版,2005,51(1):109-113
[21]焦李成,张向荣,候彪,王爽,刘芳.智能SAR图像处理与解译[M].北京:科学出版社,2008.6
[22] Baudouin Desclee,Patrick Bogaert,Pierre Defourny,Frost,Change detection by stistical object-based method[J].Remote Sensing of Environment,102(2006):1-11
[23] David L,Donoho.De-noising by soft-thresholding[J].IEEE Tran.On Information Theory,1995,41(3):617-627
[24] Lee J.S.Digital image enhancement and noise filtering by use of local statistics[J].IEEE Transactionon Pattern Analysis and Machine Intelligence,1980,2(2):165-168
[25] Lee S J.Refined filtering of image noise using local statistics[J].Computer graphic and image processing,1981,15(4):380-389b
[26] Kuan T D..et al.Adaptive restoration of images with speckle[J].IEEE Tran,ASSP,1987,35(3):373-383
[27] Lopes ,Nezry E,Touzi R.Structure detection and statiscal adaptive speckle filtering in SAR image[J].Int J,Remote Sensing,1993,14(9):1735-1758
[28] Lopes,Touzi R,Nezzy E.Adaptive speckle filters and scene hoterogeneity[J].IEEE Transactions on Geoscience and Remoted Sensing,1990,28(6):992-1000
[29] Frost S V.et al,A Model for radar images and its application to adaptive digital filtering of multi-plicative noise[J].IEEE Trans Pattern Analysis and Machine Intelligence,1982,4(2):157-166
[30] Touzi R,Lopes A,Bousquet P.A statistical and geometrical edge detector for SAR images[J].IEEE Trans,On Geoscience and Remote Sensing,1994,32(5):1110-1114
[31] Witkin A.Scale-space filtering[J].Int,joint Conf,on AL,Karlsruhe,1983:1019-1022
[32] Lopes A Nezry E,Touzi R.Maximum a posteriori speckle filtering and frist order texture model in SAR image [J].Proc.of the IGASS’90,1990:2409-2412
[33] Y Sheng,Z G Xia.A comprehensive evalution of filters forradar speckle suppression[J].IEEE IGARSS Proc.May 1996,Vol3;1559-1561
[34]张继贤.论土地利用与覆盖变化遥感信息提取技术框架[J].中国土地科学,2003.17(4):31-36
[35] Rignot E J M,van Zyle J J.Change detection techniques for ERS-1 SAR data[J].IEEE Trans Geoscience and Remote Sensing 1993,31 (4):896-906
[36] Bazi Y,Bruzzone L,Melgani F.An unsupervised approach based on the generalized Gaussian model to automatic change detection in multitemporal SAR image[J].IEEE Trans Geoscience Remote Sensing,2005,43(4):874-887
[37] Bruzzone.L.An approach to feature selection and classification of remote-sensing images based on the Bayes rule for minimum cost [J]. IEEE Transactions on Geoscience and Remote Sensing,,38(1):429-438,2000a
[38]余旭初.模式识别与图像分类[M].北京:解放军出版社,2000.3:29-31
[39]廖明生,朱攀,龚键雅.基于典型相关分析的多元变化检测[J].遥感学报,2000.4(3):197-201
[40]郑肇葆.基于蚁群行为仿真的影像分割[J].武汉大学学报信息科学版,2004,29(8):669-673
[41] D.Comanicu.P.Mean Shift;A robust approach toward feature space analysis[J] .IEEE Trans Pattern Anel Machine intell,24,603-619,May 2002
[42] Cheng Y.Mean Shift Mode Seeking and Clustering[J].IEEE Trans Pattern Anal Mach Intell,1995,17(8):790-799
[43] Fukunaga K,Hostetler.L.D.The estimation of the gradient of a density function with applications in pattern recognition[J].IEEE Trans Informatioon Theory,1975,21:32-40
[44]陈世荣,马海建,范一大,徐丰,连键.基于高分辨率遥感影像的汶川地震道路损毁评估[J].遥感学报,2008.11 12(6):949-954
[45]苏风环,刘洪江,韩用顺.汶川地震山地灾害遥感快速提取及其分布特色分析[J].遥感学报,2008.11, 12(6):956-963
[46] Chen F,Luo L,Jin Y Q.Automatic analysis of change detection of multi-temporal ERS-2 SAR images by using two-threshold EM and MRF algorithms[J].Pross in Natural Science,2004,14(3):269-275
[47] Jin Y Q.A two-thresholds EM-MRF algorithm for change detection of mutl-temporal ERS2-SAR images[J].Proc. ISPRS joint conference on the 3rd International Symposium Remote Sensing and Data Fusion Over Urban Areas and the 5th International Symposium Remote Sensing of Urban Areas,Tempe,AZ,USA,2005
[48]唐永鹤.基于特征点的匹配算法研究[D].国防科学技术大学硕士论文,2007.11
[49]从王杰,王加银.Mean Shift算法的收敛性讨论[J].北京师范大学学报(自然科学版),2008,44(5):472-475
[50] Richard O.Duda,Peter E.Hart,David G.Stork..模式分类[M].李宏东,姚天翔译,北京:机械出版社,2003
[51] Winkler.G.Image Analysis,Random Fields and Dynamic Monte Carlo Method[M].Berlin:Springer- Verlag,1995
[52]郑肇葆.图像分析的马尔可夫随机场方法[M].武汉:武汉测绘科技大学出版社,2000
[53] Tso.B.P.M.Muther.Classification Methods for Remotely Sensed Data[M].New York,Taylor&Francis, 2001
[54] Besag.Spatial interaction anf the statistical analysis of lattice systems[J].Journal of the Royal Statistcal Society, 1974,Series B,36;192-236
[55] Besag.On the statistical analysis of dirty pictures[J].Journal of the Royal Statistcal Society, 1986,Series B,48(3):259-302
[56] Comaniciu D,Meer P.Mean Shift: A Robust Approach toward Feature Space Analysis [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002.24(5) :603-619
[57] David Lowe.Local feature view clustering for 3D object recognition[EB/OL]
[58] David Lowe.Obect recognition from local scale-invariant features[EB/OL]
[59] David Lowe.Distinctive image features from scale-invariant keypoints[M].2001.2[EB/OL]
[60]赵辉.SIFT算法讲义[R]
[61] Xiaolong Dai,Siamak Khorram.A Feature-based Image Registration Algorithm Using Improved Chain-Code Representation Combined With Invariant Moments[J].IEEE Trans.On GRS:Vol37,No.5,Sep 1999
[62]张祖勋,张剑清.数字摄影测量学[M].武汉武汉大学出版社,2002:120-122
[63] Koenderink,J.J,andA.J.van Doom.The internal representation of solid shape with respect to vision[J].Biological Cybernetics:32(1979),211-216
[64] Lindeberg,Tony.Detecting salient blob-like image structures and their scales with a scale-space primal sketh:a method for focus-of-attention.[J].International Journal of Computer Vision,11,3(1993),283-318
[2]范海生,马蔼乃.采用图像差值法提取土地利用变化信息方法-以攀枝花仁和区为例[J].遥感学报,2001,5(1):75-80
[3]张路.基于多元统计分析的遥感影像变化检测方法研究[D].武汉大学博士学位论文,2004
[4]邵芸,宫华泽,王世昂,张风丽,田维.多元雷达遥感数据汶川地震灾情应急检测与评价[J].遥感学报,2008.11,12(6):865-869
[5]孙曼利.基于遥感影像的机场区域检测和毁伤分析研究[D].南京理工大学学位论文,2007
[6]王海兵.基于遥感影像的子母弹机场毁伤效果分析探究[D].南京理工大学学位论文,2007
[7] EI-Raey M,S.M Nasr,M.M.EI-Hattab,Change Detection of Rosetta Promontory OverPromontory Last FortyYears[J].Remote Sensing,1995,Vol.16:825-834
[8] Rignot E J M,van Zyle J J,Change detection techniques for ERS-1 SAR data[J].IEEE Trans, Geoscience and Remote Sensing,1993,31 (4):896-906
[9] Villasenor J D,Fatland D R,hinzman L D,Change detection on Alaska’s north slope using repeatpass ERS-1 SAR imagery[J].IEEE Trans.Geoscience and Remote Sensing,1993,31(1):227-236
[10]陈志鹏.基于纹理特征的差值变化检测方法研究[D].中国科学院电子学研究所硕士论文,2002
[11]赵小杰.成孔径雷达图像变化检测方法研究[D].中国科学院电子学研究所硕士论文,2001
[12]朱朝杰.基于特征分析的遥感图像变化检测方法研究[D].解放军信息工程大学测绘学院硕士论文,2007
[13]莫华.遥感影像上军事目标变化检测相关关键技术研究[D].解放军信息工程大学测绘学院硕士论文,2007
[14]陈科.基于判别分析的遥感图像变化检测方法研究[D].解放军信息工程大学测绘学院硕士论文2009
[15]马国锐.一种遥感影像核变化检测方法[J].武汉大学学报信息科学版,2007,32(7);579-600
[16] Lu D.P.Mausel,E.Brondizio,E Moran.Change detection techniques.International Journal of Remote Sensing[M].2004,25(12):2365-2407
[17] Bovolo F,Lorenzo bruzzone.A detail-perserving scale-driven approach to unsupervised change detection in remotely sensed imagery[J].IEEE Geoscience and Remote Sensing Letters,2006,3(4):457-461
[18] Jensen,J.R.Introductory Digital Image Processing:A Remote Sensing Perspective[M].2nd Edition Prentice Hall Press.,Upper Saddel River,NJ,1996
[19] Richard J.Radke,Srinivas Andra,Omar AI-Kofahi,Badrinath Roysam.Image Change Detection Algorithms:A Systematic Survey[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING VOL14,NO.3:294-307,MARCH 2005
[20]蔡纯,孙洪,曹永峰.基于区域似然比的SAR图像变化检测[J] .武汉大学学报理学版,2005,51(1):109-113
[21]焦李成,张向荣,候彪,王爽,刘芳.智能SAR图像处理与解译[M].北京:科学出版社,2008.6
[22] Baudouin Desclee,Patrick Bogaert,Pierre Defourny,Frost,Change detection by stistical object-based method[J].Remote Sensing of Environment,102(2006):1-11
[23] David L,Donoho.De-noising by soft-thresholding[J].IEEE Tran.On Information Theory,1995,41(3):617-627
[24] Lee J.S.Digital image enhancement and noise filtering by use of local statistics[J].IEEE Transactionon Pattern Analysis and Machine Intelligence,1980,2(2):165-168
[25] Lee S J.Refined filtering of image noise using local statistics[J].Computer graphic and image processing,1981,15(4):380-389b
[26] Kuan T D..et al.Adaptive restoration of images with speckle[J].IEEE Tran,ASSP,1987,35(3):373-383
[27] Lopes ,Nezry E,Touzi R.Structure detection and statiscal adaptive speckle filtering in SAR image[J].Int J,Remote Sensing,1993,14(9):1735-1758
[28] Lopes,Touzi R,Nezzy E.Adaptive speckle filters and scene hoterogeneity[J].IEEE Transactions on Geoscience and Remoted Sensing,1990,28(6):992-1000
[29] Frost S V.et al,A Model for radar images and its application to adaptive digital filtering of multi-plicative noise[J].IEEE Trans Pattern Analysis and Machine Intelligence,1982,4(2):157-166
[30] Touzi R,Lopes A,Bousquet P.A statistical and geometrical edge detector for SAR images[J].IEEE Trans,On Geoscience and Remote Sensing,1994,32(5):1110-1114
[31] Witkin A.Scale-space filtering[J].Int,joint Conf,on AL,Karlsruhe,1983:1019-1022
[32] Lopes A Nezry E,Touzi R.Maximum a posteriori speckle filtering and frist order texture model in SAR image [J].Proc.of the IGASS’90,1990:2409-2412
[33] Y Sheng,Z G Xia.A comprehensive evalution of filters forradar speckle suppression[J].IEEE IGARSS Proc.May 1996,Vol3;1559-1561
[34]张继贤.论土地利用与覆盖变化遥感信息提取技术框架[J].中国土地科学,2003.17(4):31-36
[35] Rignot E J M,van Zyle J J.Change detection techniques for ERS-1 SAR data[J].IEEE Trans Geoscience and Remote Sensing 1993,31 (4):896-906
[36] Bazi Y,Bruzzone L,Melgani F.An unsupervised approach based on the generalized Gaussian model to automatic change detection in multitemporal SAR image[J].IEEE Trans Geoscience Remote Sensing,2005,43(4):874-887
[37] Bruzzone.L.An approach to feature selection and classification of remote-sensing images based on the Bayes rule for minimum cost [J]. IEEE Transactions on Geoscience and Remote Sensing,,38(1):429-438,2000a
[38]余旭初.模式识别与图像分类[M].北京:解放军出版社,2000.3:29-31
[39]廖明生,朱攀,龚键雅.基于典型相关分析的多元变化检测[J].遥感学报,2000.4(3):197-201
[40]郑肇葆.基于蚁群行为仿真的影像分割[J].武汉大学学报信息科学版,2004,29(8):669-673
[41] D.Comanicu.P.Mean Shift;A robust approach toward feature space analysis[J] .IEEE Trans Pattern Anel Machine intell,24,603-619,May 2002
[42] Cheng Y.Mean Shift Mode Seeking and Clustering[J].IEEE Trans Pattern Anal Mach Intell,1995,17(8):790-799
[43] Fukunaga K,Hostetler.L.D.The estimation of the gradient of a density function with applications in pattern recognition[J].IEEE Trans Informatioon Theory,1975,21:32-40
[44]陈世荣,马海建,范一大,徐丰,连键.基于高分辨率遥感影像的汶川地震道路损毁评估[J].遥感学报,2008.11 12(6):949-954
[45]苏风环,刘洪江,韩用顺.汶川地震山地灾害遥感快速提取及其分布特色分析[J].遥感学报,2008.11, 12(6):956-963
[46] Chen F,Luo L,Jin Y Q.Automatic analysis of change detection of multi-temporal ERS-2 SAR images by using two-threshold EM and MRF algorithms[J].Pross in Natural Science,2004,14(3):269-275
[47] Jin Y Q.A two-thresholds EM-MRF algorithm for change detection of mutl-temporal ERS2-SAR images[J].Proc. ISPRS joint conference on the 3rd International Symposium Remote Sensing and Data Fusion Over Urban Areas and the 5th International Symposium Remote Sensing of Urban Areas,Tempe,AZ,USA,2005
[48]唐永鹤.基于特征点的匹配算法研究[D].国防科学技术大学硕士论文,2007.11
[49]从王杰,王加银.Mean Shift算法的收敛性讨论[J].北京师范大学学报(自然科学版),2008,44(5):472-475
[50] Richard O.Duda,Peter E.Hart,David G.Stork..模式分类[M].李宏东,姚天翔译,北京:机械出版社,2003
[51] Winkler.G.Image Analysis,Random Fields and Dynamic Monte Carlo Method[M].Berlin:Springer- Verlag,1995
[52]郑肇葆.图像分析的马尔可夫随机场方法[M].武汉:武汉测绘科技大学出版社,2000
[53] Tso.B.P.M.Muther.Classification Methods for Remotely Sensed Data[M].New York,Taylor&Francis, 2001
[54] Besag.Spatial interaction anf the statistical analysis of lattice systems[J].Journal of the Royal Statistcal Society, 1974,Series B,36;192-236
[55] Besag.On the statistical analysis of dirty pictures[J].Journal of the Royal Statistcal Society, 1986,Series B,48(3):259-302
[56] Comaniciu D,Meer P.Mean Shift: A Robust Approach toward Feature Space Analysis [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002.24(5) :603-619
[57] David Lowe.Local feature view clustering for 3D object recognition[EB/OL]
[58] David Lowe.Obect recognition from local scale-invariant features[EB/OL]
[59] David Lowe.Distinctive image features from scale-invariant keypoints[M].2001.2[EB/OL]
[60]赵辉.SIFT算法讲义[R]
[61] Xiaolong Dai,Siamak Khorram.A Feature-based Image Registration Algorithm Using Improved Chain-Code Representation Combined With Invariant Moments[J].IEEE Trans.On GRS:Vol37,No.5,Sep 1999
[62]张祖勋,张剑清.数字摄影测量学[M].武汉武汉大学出版社,2002:120-122
[63] Koenderink,J.J,andA.J.van Doom.The internal representation of solid shape with respect to vision[J].Biological Cybernetics:32(1979),211-216
[64] Lindeberg,Tony.Detecting salient blob-like image structures and their scales with a scale-space primal sketh:a method for focus-of-attention.[J].International Journal of Computer Vision,11,3(1993),283-318