基于高斯混合模型的建筑物QuickBird多光谱影像数据分类研究
|
摘要
针对任何一种遥感影像数据的信息提取都有其无法逾越的理论极限,正确认识这种极限有利于明确相关算法研究的方向,降低工程应用成本。制约影像信息提取精度的"同物异谱"现象以及与之相关的影像对象"光谱异质性"问题正是科学认识这种极限的关键和切入点。城市下垫面中的建筑物屋顶材料不同,光谱反射率也不同,"同物异谱"现象严重。基于高斯混合模型的期望最大(Expectation Maximization,EM)估计算法,能为分析建筑物类内以及同一建筑物对象内部光谱异质性程度提供科学依据,进而提高分类精度。本文以QuickBird多光谱影像为实证研究数据,利用高斯混合模型及其EM估计算法拟合出不同材料屋顶的密度分布,实现建筑物影像对象分类,得到优于传统监督、非监督分类的结果。
The extraction of information from any remote sensing imagery has its own unavoidable theoretical limitation.Facing this problem properly can make clear the direction of research on related algorithms and reduce the cost of application.It is the Spectral Confusion within the Same Object or Similar Objects(SCSO) and the related problem of image objects with heterogeneous spectra that seriously restrict the precision of image information extraction.To understand this is the key to the awareness of such a limitation.There exist different spectral reflective rates in different roof materials,which results in the serious SCSO phenomenon for different architecture objects in remote sensing imagery of urban areas.The Gaussian-mixture-model-based EM(Expectation Maximization) estimate algorithm can provide a scientific basis for analyzing the degree of spectral heterogeneity within a building and in an object of architecture category and hence improve the classification precision.Taking the multi-spectral QuickBird image as the sample data,this paper introduces the basic principle of Gaussian-mixture-model-based EM estimate algorithm,by means of which the density distribution of the different material roofs can be imitated and sub-classes of architecture be recognized.It turns out that the EM algorithm is superior to the traditional supervised and unsupervised classification in terms of the classification result of architecture image objects.
The extraction of information from any remote sensing imagery has its own unavoidable theoretical limitation.Facing this problem properly can make clear the direction of research on related algorithms and reduce the cost of application.It is the Spectral Confusion within the Same Object or Similar Objects(SCSO) and the related problem of image objects with heterogeneous spectra that seriously restrict the precision of image information extraction.To understand this is the key to the awareness of such a limitation.There exist different spectral reflective rates in different roof materials,which results in the serious SCSO phenomenon for different architecture objects in remote sensing imagery of urban areas.The Gaussian-mixture-model-based EM(Expectation Maximization) estimate algorithm can provide a scientific basis for analyzing the degree of spectral heterogeneity within a building and in an object of architecture category and hence improve the classification precision.Taking the multi-spectral QuickBird image as the sample data,this paper introduces the basic principle of Gaussian-mixture-model-based EM estimate algorithm,by means of which the density distribution of the different material roofs can be imitated and sub-classes of architecture be recognized.It turns out that the EM algorithm is superior to the traditional supervised and unsupervised classification in terms of the classification result of architecture image objects.
引文
[1]宁宝坤,曲国胜,张宁,等.IKONOS卫星影像在城市防震减灾及震害评价中的应用研究[J].地震地质,2004,26(1):161-168.
[2]叶发茂,苏林,等.高分辨率遥感影像提取道路的方法综述与思考[J].国土资源遥感,2006,(1):11-17.
[3]陈光.遥感图像中建筑物识别与变化检测[D].南京:南京理工大学,2005.
[4]莫登奎,林辉,等.基于高分辨率遥感影像的土地覆盖信息提取[J].遥感技术与应用,2005,20(4):411-414.
[5]Guindon Bert,Zhang Ying,Dillabaugh Craig.Landsat UrbanMapping Based on a Combined Spectral-spatial Methodology[J].Remote Sensing of Environment,2004,(92),218-232.
[6]李述,刘勇.基于多特征的遥感影像土地利用/覆盖分类——以腾格里沙漠东南边缘地区为例[J].遥感技术与应用,2006,21(2):154-158.
[7]毛政元.高空间分辨率光学卫星影像数据挖掘的策略[A].中国重要会议论文全文数据库(CN11-9251/G)[DB].北京:同方光盘电子出版社,2007.
[8]程曦冉,张剑清,张祖勋.航空影像多直角平顶房屋的半自动提取[J].武汉大学学报,2004,29(12):1097-1100.
[9]骆剑承,周成虎.有限混合密度模型及遥感影像EM聚类算法[J].中国图象图形学报,2002,7(4):336-341.
[10]Stein A,Gorte B.Spatial Statistics for Remote Sensing[M].New York:Kluwer Academic Publishers,1999.
[11]Dempster AP,Laird NM,Rubin D B.MaximumLikelihood Es-timation from Incomplete Data via EM Algorithm[J].Journal ofRoyal Statistical Society,1977,39(1):1-38.
[12]McLachlan G J,Basford K E.Mixture Models:Inference andApplications to Clustering[M].New York:Marcel Dekker,1988.
[13]Jeff A,Bilmes.A Gentle Tutorial of the EM Algorithm and ItsApplication to Parameter Estimation for Gaussian Mixture andHidden Markov Models[Z].International Computer Science In-stitute,1998.
[14]Mcachlan G,Peel D.Finite Mixture Models[M].New York:John Wiley&Sons.,2000.
[2]叶发茂,苏林,等.高分辨率遥感影像提取道路的方法综述与思考[J].国土资源遥感,2006,(1):11-17.
[3]陈光.遥感图像中建筑物识别与变化检测[D].南京:南京理工大学,2005.
[4]莫登奎,林辉,等.基于高分辨率遥感影像的土地覆盖信息提取[J].遥感技术与应用,2005,20(4):411-414.
[5]Guindon Bert,Zhang Ying,Dillabaugh Craig.Landsat UrbanMapping Based on a Combined Spectral-spatial Methodology[J].Remote Sensing of Environment,2004,(92),218-232.
[6]李述,刘勇.基于多特征的遥感影像土地利用/覆盖分类——以腾格里沙漠东南边缘地区为例[J].遥感技术与应用,2006,21(2):154-158.
[7]毛政元.高空间分辨率光学卫星影像数据挖掘的策略[A].中国重要会议论文全文数据库(CN11-9251/G)[DB].北京:同方光盘电子出版社,2007.
[8]程曦冉,张剑清,张祖勋.航空影像多直角平顶房屋的半自动提取[J].武汉大学学报,2004,29(12):1097-1100.
[9]骆剑承,周成虎.有限混合密度模型及遥感影像EM聚类算法[J].中国图象图形学报,2002,7(4):336-341.
[10]Stein A,Gorte B.Spatial Statistics for Remote Sensing[M].New York:Kluwer Academic Publishers,1999.
[11]Dempster AP,Laird NM,Rubin D B.MaximumLikelihood Es-timation from Incomplete Data via EM Algorithm[J].Journal ofRoyal Statistical Society,1977,39(1):1-38.
[12]McLachlan G J,Basford K E.Mixture Models:Inference andApplications to Clustering[M].New York:Marcel Dekker,1988.
[13]Jeff A,Bilmes.A Gentle Tutorial of the EM Algorithm and ItsApplication to Parameter Estimation for Gaussian Mixture andHidden Markov Models[Z].International Computer Science In-stitute,1998.
[14]Mcachlan G,Peel D.Finite Mixture Models[M].New York:John Wiley&Sons.,2000.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心