面向对象的遥感影像模糊分类方法研究
|
摘要
传统的基于像素的遥感影像处理方法都是基于遥感影像光谱信息极其丰富,地物间光谱差异较为明显的基础上进行的。对于只含有较少波段的高分辨率遥感影像,传统的分类方法,就会造成分类精度降低,空间数据的大量冗余,并且其分类结果常常是椒盐图像,不利于进行空间分析。
为解决这一传统难题,模糊分类技术应运而生。模糊分类是一种图像分类技术,它是把任意范围的特征值转换为0到1之间的模糊值,这个模糊值表明了隶属于一个指定类的程度。通过把特征值翻译为模糊值,即使对于不同的范围和维数的特征值组合,模糊分类能够标准化特征值。模糊分类也提供了一个清晰的和可调整的特征描述。
本文采用面向对象的影像分类方法。考虑了对象的不同特征值,例如光谱值,形状和纹理。结合上下文关系和语义的信息,这种分类技术不仅能够使用影像属性,而且能够利用不同影像对象之间的空间关系。在对诸多对象进行分类后,在进行精度分析。在此研究提出了一种面向对象的方法结合模糊理论把许多的对象块分成不同的类别。这一过程主要有两个步骤:第一个步骤是分割。图像分割将整个图像分割成若干个对象,在对所有对象进行分类,在这个过程中,分割尺度的选择会影响到后续的分类结果和精度;第二个步骤是分类。在这个步骤中,特征值的选择和隶属度函数的选择都对分类结果有着至关重要的影响。完成分类后,可以进行土地变换检测等后续工作。
The traditional pixel-based remote sensing image processing approaches exploit the features of abundant spatial information and explicit difference of spectrum between different objects. Applying the traditional classifying algorithms to the high resolution remote sensing image with few spectral bands will cause the low classification rate, redundancy spatial data, and output image with pepper-salt noise.
Fuzzy classification is a technique that basically translates feature value of arbitrary range into fuzzy values between 0 and 1, indicating the degree of membership to a specific class. By translating feature values into fuzzy values, fuzzy classification can standardize features and allows the combination of features, even of very different range and dimension. Fuzzy classification also provides a transparent and adaptable feature description.
Object-based image classification, which is based on fuzzy logic, allows the integration of a broad spectrum of different object features such as spectral values, shape, and texture. Such classification techniques, incorporating contextual and semantic information, can be performed using not only image object attributes, but also the relationship among different image objects.This research has main two steps. First step is segmentation. During this process, how to choose fine scale is very important. Second step is classification. In this step, two factors are very essential for classification. Creating feature space is one of the factors, another is fuzzy logic. After these two steps, we can extract some classes that we are interested in.
为解决这一传统难题,模糊分类技术应运而生。模糊分类是一种图像分类技术,它是把任意范围的特征值转换为0到1之间的模糊值,这个模糊值表明了隶属于一个指定类的程度。通过把特征值翻译为模糊值,即使对于不同的范围和维数的特征值组合,模糊分类能够标准化特征值。模糊分类也提供了一个清晰的和可调整的特征描述。
本文采用面向对象的影像分类方法。考虑了对象的不同特征值,例如光谱值,形状和纹理。结合上下文关系和语义的信息,这种分类技术不仅能够使用影像属性,而且能够利用不同影像对象之间的空间关系。在对诸多对象进行分类后,在进行精度分析。在此研究提出了一种面向对象的方法结合模糊理论把许多的对象块分成不同的类别。这一过程主要有两个步骤:第一个步骤是分割。图像分割将整个图像分割成若干个对象,在对所有对象进行分类,在这个过程中,分割尺度的选择会影响到后续的分类结果和精度;第二个步骤是分类。在这个步骤中,特征值的选择和隶属度函数的选择都对分类结果有着至关重要的影响。完成分类后,可以进行土地变换检测等后续工作。
The traditional pixel-based remote sensing image processing approaches exploit the features of abundant spatial information and explicit difference of spectrum between different objects. Applying the traditional classifying algorithms to the high resolution remote sensing image with few spectral bands will cause the low classification rate, redundancy spatial data, and output image with pepper-salt noise.
Fuzzy classification is a technique that basically translates feature value of arbitrary range into fuzzy values between 0 and 1, indicating the degree of membership to a specific class. By translating feature values into fuzzy values, fuzzy classification can standardize features and allows the combination of features, even of very different range and dimension. Fuzzy classification also provides a transparent and adaptable feature description.
Object-based image classification, which is based on fuzzy logic, allows the integration of a broad spectrum of different object features such as spectral values, shape, and texture. Such classification techniques, incorporating contextual and semantic information, can be performed using not only image object attributes, but also the relationship among different image objects.This research has main two steps. First step is segmentation. During this process, how to choose fine scale is very important. Second step is classification. In this step, two factors are very essential for classification. Creating feature space is one of the factors, another is fuzzy logic. After these two steps, we can extract some classes that we are interested in.
引文
[1]陈述彭.航天遥感应用的世纪畅想[J].计算机世界报,2004,(1):5-12
[2]陈述彭,赵英时.遥感地学分析[M].北京:测绘出版社,1990.(2):2-5
[3]阳松.面向对象的遥感影像的模糊分类:[学位论文].徐州.中国矿业大学,2007
[4]周春艳.面向对象的高分辨率遥感影像信息提取技术:[学问论文].济南.科技大学.2006
[5]Willhauck, G., Benz, U. C., and Siegert, F. Semiautomatic classification procedures forfire monitoring using mufti-temporal SAR images and NOAA-AVHRR hotspot data [J],Proceedings of the 4th European Conference n ,Synthetic Aperture Radar, Cologne, Germany,2002, 4-6.
[6]Huang Huiping,Wu Bingfang, Fan Jinlong. Analysis to the Relationship of ClassificationAccuracy Segmentation Scale Image Resolution[C].IEEE Trans, IGARSS, 2003, 6: 3671-3673
[7] eCognition: object oriented image classification [EB/OL]. http://www.definiens-imaging.comldocuments/reference2000.htm
[8]梅安新,彭望录,秦其明.遥感导论.北京:高等教育出版社,2001.
[9]Pierce E, Ulaby F T, Sarabandi K,et al. Knowledge-Based Classification of Polarimetric SAR Images〔J〕. IEEE Transac- tions on Geosciences and Remote Sensing,1994,32(5): 1081~1086.
[10]陈丹峰,林陪,汲长远.自组织网络与模糊规则结合在遥感土地覆盖分类中的应用.中国土地科学,1998,12(5):42～44.
[11]毛建旭,王耀南,孙炜.基于模糊小脑模型神经网络的遥感影像分类算法.测绘学报,2002,31(4):327～332.
[12]杨玉静.遥感影像的计算机分类技术研究:[学位论文].昆明.昆明理工大学,2005
[13]许磊.支持向量机和模糊理论在遥感影像分类中的应用:[学位论文].江南大学,2006
[14]C.S.Lu,P.C.Chung and C.F.Chen.Unsupervised texture segmentation via wavelet transform.Pattern Recongnition.1997,30(5)
[15]郭德军,宋蛰存,基于灰度共生矩阵的纹理影像分类研究.林业机械与木工设备,2005.(7)
[16]田艳琴,郭平,卢汉清,基于灰度共生矩阵的多波段遥感影像纹理特征的提取,计算机科学,2004.(12)
[17]安斌,簿书海,球华,严卫东,孙煌,纹理特征在多光谱影像分类中的应用,激光与红外,2002.(6)
[18]段宏.一种基于 Web 挖掘的信息自动分类系统.华中科技大学学报(自然科学版),2003(7).
[19]王伟等.自动分类模型及算法研究.微电子学与计算机,2004(5).
[20]方兰等.文本自动分类技术及其应用.计算机与现代化,2004(7).
[21]王永庆.人工智能原理与方法.西安:西安交通大学出版社.1998.
[22]T.M.Cover, P.E.Hart, Nearest Neighbor Pattern Classification, IEEE Trans, Information Theory, 12:21-27, 1967
[23] Richard O. Duda, Peter E.Hart, David G.Stork, Pattern Classification, Wiley, New York, 2001
[24]Bandemer,H.,Gottwald, S.: Fuzzy Sets,Fuzzy Logic,Fuzzy Methods with Applications.New York : Wiley Press, 1995.
[25]Civanlar, R., Trussell, H.: Constructing Membership Functions Using Statistical Data,Fuzzy Sets and Systems ,1986 ,18, 1-13.
[26]李楠.面向对象的高分辨率遥感影像分割方法研究:[学位论文].西安.西安科技大学.2007
[27]黄慧苹.面向对象影像分析中的尺度问题研究:[学位论文].北京.中国科学院遥感应用研究所.2003
[28]罗来平.遥感影像分类中模糊模式识别和决策树方法的应用研究:[学位论文].北京.首都师范大学硕士学位论文.2006
[29] Haralick,R.Shanmugan, K.I. Dinstein: Textural features for image classification. IEEE Transactions on Systems,Man and Cybernetics. 1973,3(1),610-621.
[30] 译陆(ELU)V1.0 操作手册.上海:上海交通大学图像处理与模式识别研究所遥感科学研究室,2007
[31]王人潮,试论土地分类,浙江大学学报(农业与生命科学版),2002.28: 355-361
[32]Civanlar, R., Trussel, H.. Constructing membership functions using statistical data. IEEE Fuzzy Sets and Systems ,1986, 18, 1 –14.
[33]Bezdek, J, Pal, S.Fuzzy Models for Pattern Recognition,Methods that Search for Structures in Data. New,York :IEEE Press, 1992.
[34]Manjunath, B., Chellappa, R.. Unsupervised texture segmentation using Markov random field models. IEEE Transactions on Pattern Analysis and Machine Intelligence , 1991, 13 (5), 478– 482.
[35]Jianping Fan,David.K.Y. Yau,A.K. Elmagarmid,Walid G. Aref. Automatic Image Segmentation by Integrating Color-Edge Extraction and Seeded Region Growing.IEEE Transactions on Image Processing,2001,10(10):1454~1466
[36] U.C. Benz,P. Hofmann,G. Willhauck,Iris Lingenfelder,M. Heynen . Multi-resolution, Object-oriented Fuzzy Analysis of Remote Sensing Data for GIS-ready Information. ISPRS Journal of Photogrammetry & Remote Sensing,2004,58:239~258
[37] Alain Trémeau, Philippe Colantoni. Regions Adjacency Graph Applied to Color Image Segmentation. IEEE Transactions on Image Processing,2000,9(4):735~744
[38] K. Haris,S.N. Efstratiadis,N. Maglaveras, A.K. Katsaggelos. Hybrid Image Segmentation Using Watersheds and Fast Region Merging. IEEE Transactions on Image Processing,1998,12(7):1684~1699
[39] Pieczynski W,Tebbache A N. Pairwise Markov Random Fields and Its Application in Textured Images Segmentation. In: Proceedings 2000 of 4th IEEE,1987.259～268.
[40] Z. Wu, R. Leahy, An optimal graph theoretic approach to data clustering: theory and its application to image segmentation,IEEE Trans. on PAMI,1993,15(11):1101-1113
[41] S. Sarkar, P. Soundararajan,Supervised learning of large perceptual organization: Graph spectral partitioning and learning automata,IEEE Trans. on PAMI, 2000,22(5): 504-525
[42] Yining Deng,B.S. Manjunath. Unsupervised Segmentation of Color-Texture Regions in Images and Video. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001,23(8):800~810
[43] Dileep K. Panjwanni, Glenn Healey. Markov Random Field Models for Unsupervised Segmentation of Textured Color Images. IEEE Transactions on Pattern and Machine Intelligence,1995,17(10):939~954
[44] Gauch J M. Image Segmentation and Analysis via Multiscale Gradient Watershed Hierarchies. IEEE Trans on Image Processing, 1999, 8(1): 69~79
[45] Chun D N, Yang H S. Robust Image Segmentation Using Genetic Algorithm with A Fuzzy Measure. Pattern Recognition, 1996, 29(7): 1195~1211
[46] Bhandarkar, Zhang H. Image Segmentation Using Evolutionary computation. IEEE Trans on Evolutionary Computation, 1999, 3(1): 1~21
[47] S.W.Zucker and D.Terzopoulos. Finding Structure in Co-occurrence matrices for Texture Analysis. CGIP. 1980,12(3):286-308
[48] Hawkins J K. Textural Properties for Pattern Recognition Picture Processing and Psychpictorics. New York: Academic Press. 1970: 347-370
[2]陈述彭,赵英时.遥感地学分析[M].北京:测绘出版社,1990.(2):2-5
[3]阳松.面向对象的遥感影像的模糊分类:[学位论文].徐州.中国矿业大学,2007
[4]周春艳.面向对象的高分辨率遥感影像信息提取技术:[学问论文].济南.科技大学.2006
[5]Willhauck, G., Benz, U. C., and Siegert, F. Semiautomatic classification procedures forfire monitoring using mufti-temporal SAR images and NOAA-AVHRR hotspot data [J],Proceedings of the 4th European Conference n ,Synthetic Aperture Radar, Cologne, Germany,2002, 4-6.
[6]Huang Huiping,Wu Bingfang, Fan Jinlong. Analysis to the Relationship of ClassificationAccuracy Segmentation Scale Image Resolution[C].IEEE Trans, IGARSS, 2003, 6: 3671-3673
[7] eCognition: object oriented image classification [EB/OL]. http://www.definiens-imaging.comldocuments/reference2000.htm
[8]梅安新,彭望录,秦其明.遥感导论.北京:高等教育出版社,2001.
[9]Pierce E, Ulaby F T, Sarabandi K,et al. Knowledge-Based Classification of Polarimetric SAR Images〔J〕. IEEE Transac- tions on Geosciences and Remote Sensing,1994,32(5): 1081~1086.
[10]陈丹峰,林陪,汲长远.自组织网络与模糊规则结合在遥感土地覆盖分类中的应用.中国土地科学,1998,12(5):42～44.
[11]毛建旭,王耀南,孙炜.基于模糊小脑模型神经网络的遥感影像分类算法.测绘学报,2002,31(4):327～332.
[12]杨玉静.遥感影像的计算机分类技术研究:[学位论文].昆明.昆明理工大学,2005
[13]许磊.支持向量机和模糊理论在遥感影像分类中的应用:[学位论文].江南大学,2006
[14]C.S.Lu,P.C.Chung and C.F.Chen.Unsupervised texture segmentation via wavelet transform.Pattern Recongnition.1997,30(5)
[15]郭德军,宋蛰存,基于灰度共生矩阵的纹理影像分类研究.林业机械与木工设备,2005.(7)
[16]田艳琴,郭平,卢汉清,基于灰度共生矩阵的多波段遥感影像纹理特征的提取,计算机科学,2004.(12)
[17]安斌,簿书海,球华,严卫东,孙煌,纹理特征在多光谱影像分类中的应用,激光与红外,2002.(6)
[18]段宏.一种基于 Web 挖掘的信息自动分类系统.华中科技大学学报(自然科学版),2003(7).
[19]王伟等.自动分类模型及算法研究.微电子学与计算机,2004(5).
[20]方兰等.文本自动分类技术及其应用.计算机与现代化,2004(7).
[21]王永庆.人工智能原理与方法.西安:西安交通大学出版社.1998.
[22]T.M.Cover, P.E.Hart, Nearest Neighbor Pattern Classification, IEEE Trans, Information Theory, 12:21-27, 1967
[23] Richard O. Duda, Peter E.Hart, David G.Stork, Pattern Classification, Wiley, New York, 2001
[24]Bandemer,H.,Gottwald, S.: Fuzzy Sets,Fuzzy Logic,Fuzzy Methods with Applications.New York : Wiley Press, 1995.
[25]Civanlar, R., Trussell, H.: Constructing Membership Functions Using Statistical Data,Fuzzy Sets and Systems ,1986 ,18, 1-13.
[26]李楠.面向对象的高分辨率遥感影像分割方法研究:[学位论文].西安.西安科技大学.2007
[27]黄慧苹.面向对象影像分析中的尺度问题研究:[学位论文].北京.中国科学院遥感应用研究所.2003
[28]罗来平.遥感影像分类中模糊模式识别和决策树方法的应用研究:[学位论文].北京.首都师范大学硕士学位论文.2006
[29] Haralick,R.Shanmugan, K.I. Dinstein: Textural features for image classification. IEEE Transactions on Systems,Man and Cybernetics. 1973,3(1),610-621.
[30] 译陆(ELU)V1.0 操作手册.上海:上海交通大学图像处理与模式识别研究所遥感科学研究室,2007
[31]王人潮,试论土地分类,浙江大学学报(农业与生命科学版),2002.28: 355-361
[32]Civanlar, R., Trussel, H.. Constructing membership functions using statistical data. IEEE Fuzzy Sets and Systems ,1986, 18, 1 –14.
[33]Bezdek, J, Pal, S.Fuzzy Models for Pattern Recognition,Methods that Search for Structures in Data. New,York :IEEE Press, 1992.
[34]Manjunath, B., Chellappa, R.. Unsupervised texture segmentation using Markov random field models. IEEE Transactions on Pattern Analysis and Machine Intelligence , 1991, 13 (5), 478– 482.
[35]Jianping Fan,David.K.Y. Yau,A.K. Elmagarmid,Walid G. Aref. Automatic Image Segmentation by Integrating Color-Edge Extraction and Seeded Region Growing.IEEE Transactions on Image Processing,2001,10(10):1454~1466
[36] U.C. Benz,P. Hofmann,G. Willhauck,Iris Lingenfelder,M. Heynen . Multi-resolution, Object-oriented Fuzzy Analysis of Remote Sensing Data for GIS-ready Information. ISPRS Journal of Photogrammetry & Remote Sensing,2004,58:239~258
[37] Alain Trémeau, Philippe Colantoni. Regions Adjacency Graph Applied to Color Image Segmentation. IEEE Transactions on Image Processing,2000,9(4):735~744
[38] K. Haris,S.N. Efstratiadis,N. Maglaveras, A.K. Katsaggelos. Hybrid Image Segmentation Using Watersheds and Fast Region Merging. IEEE Transactions on Image Processing,1998,12(7):1684~1699
[39] Pieczynski W,Tebbache A N. Pairwise Markov Random Fields and Its Application in Textured Images Segmentation. In: Proceedings 2000 of 4th IEEE,1987.259～268.
[40] Z. Wu, R. Leahy, An optimal graph theoretic approach to data clustering: theory and its application to image segmentation,IEEE Trans. on PAMI,1993,15(11):1101-1113
[41] S. Sarkar, P. Soundararajan,Supervised learning of large perceptual organization: Graph spectral partitioning and learning automata,IEEE Trans. on PAMI, 2000,22(5): 504-525
[42] Yining Deng,B.S. Manjunath. Unsupervised Segmentation of Color-Texture Regions in Images and Video. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001,23(8):800~810
[43] Dileep K. Panjwanni, Glenn Healey. Markov Random Field Models for Unsupervised Segmentation of Textured Color Images. IEEE Transactions on Pattern and Machine Intelligence,1995,17(10):939~954
[44] Gauch J M. Image Segmentation and Analysis via Multiscale Gradient Watershed Hierarchies. IEEE Trans on Image Processing, 1999, 8(1): 69~79
[45] Chun D N, Yang H S. Robust Image Segmentation Using Genetic Algorithm with A Fuzzy Measure. Pattern Recognition, 1996, 29(7): 1195~1211
[46] Bhandarkar, Zhang H. Image Segmentation Using Evolutionary computation. IEEE Trans on Evolutionary Computation, 1999, 3(1): 1~21
[47] S.W.Zucker and D.Terzopoulos. Finding Structure in Co-occurrence matrices for Texture Analysis. CGIP. 1980,12(3):286-308
[48] Hawkins J K. Textural Properties for Pattern Recognition Picture Processing and Psychpictorics. New York: Academic Press. 1970: 347-370