摘要
当今社会经济发展迅猛,城市是人类现代生活的主体,其发展与变化日新月异。遥感技术具有快捷、便利的特征,适合于对城市扩展监测。实现基于遥感图像的城市扩展检测,有利于快速、准确地把握城市发展与变化,对城市的管理、规划与决策具有重要的意义。
基于遥感图像的城市空间扩展监测大多处于计算机分类与目视解译相结合的阶段,自动化程度较低,人为影响因素较重,不适合城市扩展监测的标准化、自动化与流程化。本文在概述国内外利用遥感图像进行扩展检测的发展现状和趋势后,对遥感图像城镇用地类型的多光谱特征分布、区域特征进行了分析,提出了基于区域多中心的城镇用地识别方法,在此基础之上研究了遥感图像城市扩展变化检测方法,并应用于长株潭城市扩展研究,取得了一些有价值的成果。
第二章首先概述了城市空间扩展的基本模式及其资源卫星图像特征,用最大最小法对土地利用/覆盖类别进行聚类,形成多个聚类中心,分析资源卫星遥感图像城镇用地像元到其中心距离的分布,计算分析城镇用地类型与其它土地覆盖/土地利用类别的多中心与单一聚类中心的类内、类间距,最后,探讨了C-均值法、最大似然法和模糊神经网络分类方法的分类机理。形成了一套较为完整的城镇用地多光谱特征分析方法。
第三章针对城区及其相关类别在遥感图像中光谱特征一般不满足正态分布,城区由多种地物组成的问题,用多中心表示城区模式特征,分析了城镇用地及与其相关的土地覆盖/土地利用类别区域多中心特征,提出了一种基于区域多中心的多光谱遥感图像城镇用地识别方法,该方法所提取的特征与其它类别之间的差异较大,可靠性高,把区域特征和多光谱特征有机的结合起来,有效地提高了城镇用地类型的识别精度。
第四章首先分析了遥感图像变化检测技术的发展形状和趋势,针对城市扩展变化具有多样性和区域性,以及通常采用的先分类后比较的方法,存在分类误差叠加的问题,提出一种先比较后分类的城市扩展变化检测方法,该方法减少了先分类后比较方法的分类次数,有效地解决了分类误差积累的问题,把基于区域多中心的方法应用于比较后的图像分类对于城市扩展变化检测取得了理想的效果。
第五章首先介绍了城市扩展检测结果的数据特征及处理方法,建立了RS与GIS集成的长株潭资源卫星遥感监测系统,利用该系统对长株潭城市群城市扩展的特征及趋势、影响因素和扩展中存在的问题进行了分析,为制定长株潭城市群的发展战略与规划提供参考。应用表明:所提出的遥感图像变化检测方法基本达到了生产实用的水平。
第六章对整个论文的工作进行了总结,并提出了一步研究的方向。
本文所形成的基于遥感图像的城市空间扩展监测方法,为城市发展与扩展研究探索提供了新的技术手段。
With the fast development of the society and economy ,cities have became the principal part of human's modern life,and it's developping and changing with each passing day. Remote sensing has the character of shotcut and convenient, and it's propitious to supervise the expand of cities. Monitoring on urban spatial expansion based on Remote Sensing (RS) images, it is useful to hold the development and change of city, and it is important to country resource manage, entironment supervising and urban planning.
The method of urban expand monitoring with remote sensing is in the phase of manual interpreting assisted by computer classification, so there are problems of lower efficiency, higher artificial factor, and unsuitable to standardization and automatization. After analysesing the development states and current developing of the urban expand monitoring with RS image, this paper analyses on the multi-spectrum distributing and region features of urban land-use class, presents a recognition methods based on Region Multi-Center (RMC) for urban land-used, studies a change detection methods of RS image for urban spatial expansion, and its' application on the Chang-sha, Zhu-zhou and Xiangtang Cities (CZTC) expand change dection. Some valuable achievevements are obtained. The contents of this thesis are organied as follow.
Chapter 2 summarizes the basic pattern of urban spatial expansion, and its' feature on the resource satellite image, firstly. forms multi-center of land use/cover class by clustered with max-min algorithmic ,and studies the distributions of the distance from the feature to the classificatory recognition. Analyses the distance distributing of urban land-used pixiel from its average centeral, calculates the urban land-use in-class's and between-class's distances from the Land Cover/ Use (LCU)recognition with multi-center and single clustering center, discusses the mechanism of the classification methods such as C-mean, maximum likelihood and fuzzy neural network in the end. A whole analysis method of multi-spectrum feature for urban land-used is presented.
Chapter 3 Aiming at the problem that the multi-spectrum feature of land use/cover class is not always normal distribution, because the class is made of multiple covered species, analyses the feature of region multi-center of urban land-use form the other LCU class, presents a recognition method of urban land-use with multi-spectrum remote sensing image based on RMC. The recognition feature of urban land-use has more difference than the feature of other class in the RMC, and RMC transacts preferably the combination of region and spectrum feature, so the method improves effectively the recognition precision of urban land-use.
Chapter 4 analyses the development states and current developing of the change detection technique of RS image, With a view to the multiformity and region character of urban expand, and the problem of the error piled up by the approach of classification after comparison, presents a change detection method of comparing before classification for city expand. This method has less classification numbers than the method of comparing after classification, deals with the problem of the classification accumulated. A perfect achievevement is obtained by the application of RMC method to class the compared RS image for city expand change detection.
Chapter 5 introdces the data character and disposal method of the results of the city change detection firsthly, sets up the RS Monitoring System of CZTC based on combination RS and GIS, with the system analyses the urban expansion character, current developing, influence factors and expanded problems of the CZTC, and gives the advice of the developing stratagem and city planning of the CZTC. The application indicate that the methods what the paper brings forward reaches basicly applied level.
Chapter 6 summarizes the general work of this paper, and points out the further research.
The approach of monitoring on urban spatial expansion based on remote sensing images provides a new technical means to study urban expansion and development.
引文
[1]杨重光.当前我国大城市发展的新特点[J].城市.2006,6:9-11.
[2]李迅.关于我国城市可持续发展的若干思考[J].规划师,2001.6
[3]梅安新,彭望琭,秦其明,刘慧平.遥感导论.北京:高等教育出版社,2001。
[4]#12
[5]孙家抦,舒宁,关泽群.遥感原理、方法和应用.北京:测绘出版社,1996。
[6]#12
[7]#12
[8]#12
[9]黄珍,段险峰.城市新区发展的经济学研究方法初探.城市规划,2004.
[10]M.P.Pards.Urban Ecology.Environment,2004,46(5),3-3.
[11]ZHIJUN CHEN,JIN CHEN,PEIJUN SHI,et al.An IHS-based change detection approach for assessment of urban expansion impact on arable land loss in China[J].INT.J.REMOTE SENSING,2003,24(6):1353-1360.
[12]黄亚平.城市空间理论与空间分析.南京:东南人学出版社,2002.5
[13]朱喜钢.城市空间集中与分散论.北京:中国建筑工业出版社,2002
[14]杨培峰.城乡空间生态规划理论与方法研究.博士学位论文,重庆大学,2002。
[15]程道平等编.现代城市规划.科学出版社,北京,2004。
[16]赵昕,胡召玲.遥感技术在城市扩展中的应用-以江苏省徐州市为例,徐州师范大学学报(自然科学版)Vol.24,No.2:67-70
[17]汤世华,樊风雷,王云鹏,等.1998-2003年东莞市开发区时空变化的遥感监测及驱动力分析,华南师范大学学报(自然科学版),2006,1(200):114-119.
[18]彭顺喜,等.长株潭城市群中巴资源卫星应用评价,国防科工委(科工计[2000]10号),2000年4月.
[19]盛辉,廖明生,张路.基于卫星遥感图像的城市扩展研究-以东营市为例,遥感信息2005.4:28-31.
[20]李晶皎,朱志良,王爱侠,等译.模式识别[M].北京:电子工业出版社,2004.
[21]李宏东,姚天翔,等译.模式分类[M].北京:机械工业出版社,2003.
[22]#12
[23]Changren Zhu,Runsheng Wang.A fast automatic extraction algorithm of elliptic object groups from remote sensing images[J].Pattern Recognition Letters,2004,25:1471-1478.
[24]M.Weis,S.Mu" ller,C.-E.Liedtke,et al.A framework for GIS and imagery data fusion in support of cartographic updating[J].Information Fusion,2005,6:311-317.
[25]F.Herreraa;_,E.Herrera-Viedmaa,Luis Martinez.A fusion approach for managing multi-granularity linguistic term sets in decision making[J].Fuzzy Sets and Systems,2000, 114:43-58.
[26]#12
[27]#12
[28]Christian Woler,Kia Hafezi.Ageneral frameworkfor three-dimensional surface reconstruction by self-consistent fusion of shading and shadowfeatures[J].Pattern Recognition,2005,38:965-983.
[29]Sheng Zheng,Jian Liu,Jin Wen Tian.A new efficient SVM-based edge detection method[J].Pattern Recognition Letters,2004,25:1143-1154.
[30]#12
[31]Xue-wen Chen.An improved branch and bound algorithm for feature selection[J].Pattern Recognition Letters,2003,24:1925-1933.
[32]Gemma Piella.A general framework for multiresolution image fusion:from pixels to regions[J].Information Fusion,2003,4:259-280.
[33]Xiaoying Jin,Curt H.Davis.An integrated system for automatic road mapping from high-resolution multi-spectral satellite imagery by information fusion[J].Information Fusion,2005,6:257-273.
[34]Topi Maenpaa,Matti Pietikainen.Classi cation with color and texture:jointly or separately?[J].Pattern Recognition,2004,37:1629-1640.
[35]Ursula C.Benz,Peter Hofmann,Gregor Willhauck,et al.Multi-resolution,object -oriented fuzzy analysis of remote sensing data for GIS-ready information.ISPRS Journal of Photogrammetry & Remote Sensing,2004,58:239-258.
[36]Stefan Voigt,Anke Tetzlaff,Jianzhong Zhang,et al.Integrating satellite remote sensing techniques for detection and analysis of uncontrolled coal seam fires in North China.International Journal of Coal Geology,2004,59:121-136.
[37]#12
[38]Dan Johan Weydahl,Frederic Bretar,Pal Bjerke.Comparison of RADARSAT-1 and IKONOS satellite images for urban features detection[J].Information Fusion,2005,6:243-249.
[39]Patrick Varmoorenberghe.On aggregating belief decision trees.Information Fusion,2004,5:179-188.
[40]#12
[41]N.Kwak,C.H.Choi.Input feature selection for classification problem[J].IEEE Transaction on Neural Networks,2002,13(1):143-159.
[42]H.Zhang,G.Sun.Feature selection using tabu search method[J].Pattern Recognition Vol.35,PP.701-711,2002.
[43]G.Simon,B.Horst.Feature selection algorithms for the generation of multiple classifier systems and their application to handwritten word recognition Pattern[J].Recognition Letters,2004,25:1323-1336.
[44]S.Mohammad Ya'allah,M.Reza Saradjian.Automatic normalization of satellite images using unchanged pixels within urban areas[J].Information Fusion,2005,6:235-241.
[45]#12
[46]Mercedes Berterretche,Andrew T.Hudak,Warren B.Cohen,et al.Comparison of regression and geostatistical methods for mapping Leaf Area Index(LAI)with Landsat ETM+ data over a boreal forest.Remote Sensing of Environment,2005,96:49-61.
[47]陈雪,戴芹,马建文,等.贝叶斯网络分类算法在遥感数据变化检测上的应用.北京师范大学学报(自然科学版).2005,41(1):97-100.
[48]Mehmet Nadir Kumaz,Zu"mray Dokur,Tamer O"lmez.Segmentation of remote-sensing images by incremental neural network.Pattern Recognition Letters,2005,26:1096-1104.
[49]Y.V.Venkatesh,S.Kumar Raja.On the classi cation of multispectral satellite images using the multilayer perceptron.Pattern Recognition,2003,36:2161-2175.
[50]#12
[51]Min Xu,Pakom Watanachaturaporn,Pramod K.Varshney,et.al.Decision tree regression for soft classification of remote sensing data[J],Remote Sensing of Environment,2005,97(3):322-336.
[52]Michael Bock,Panteleimon Xofis,Jonathan Mitchley,et.al.Object-oriented methods for habitat mapping at multiple scales - Case studies from Northern Germany and Wye Downs,UK[J],2005,13(2-3):75-89.
[53]Yafit Cohen,Maxim Shoshany.Analysis of convergent evidence in an evidential reasoning knowledge-based classification[J],Remote Sensing of Environment,2005,96(3-4):518-528.
[54]#12
[55]#12
[56]M.V.R.Ballester,D.C.Victoria,A.V.Krusche,et.al.A remote sensing/GIS-based physical template to understand the biogeochemistry of the Ji-Paraná river basin[J],Remote Sensing of Environment,2003,87(4):429-445.
[57]M.A.Lefsky,D.P.Turner,M.Guzy,et.al.Combining lidar estimates of aboveground biomass and Landsat estimates of stand age for spatially extensive validation of modeled forest productivity[j],Remote Sensing of Environment,2005,95(4):549-558.
[58]哈斯巴干,马建文,李启青,等.容差粗糙集与神经网络结合的遥感数据分类方法.中国科学D辑地球科学,2004,34(10):967-974.
[59]#12
[60]陈小春,陈鲸.一种变化检测新方法[J].宇航学报,2005,26(3):334-338.
[61]Changshan Wu.Normalized spectral mixture analysis for monitoring urban composition using ETM+ imagery[J].Remote sensing of environment,2004,93:480-492.
[62]R.Richard J.A.Srinivasl,A.Omarl.Image Change Detection Algorithms:A Systematic Survey[J].IEEE Transactions on Image Processing.2005,14(3):294-307.
[63]R.A.Weismiller,S.J.Kristof,et al.Change detection in coastal zone environments[J].Photography Engineering remote sensing,1977,43:1533-1539.
[64]胡岩峰,刘波,等.一种基于统计分析的图像变化检测方法[J].光子学报,2005,34(1):146-149
[65]B.Francescal,B.Lorenzol.Detail-Preserving Scale-Driven Approach to Change Detection in Multitemporal SAR Images[J].IEEE Transactions on Geoscience & Remote Sensing.2005,43(12):2963-2972.
[66]I.Jungho,J.John.A change detection model based on neighborhood correlation image analysis and decision tree classification[J].Remote Sensing of Environment;2005,99(3):326-340.
[67]L.Bruzzone,R.Cossu,G.Vernazza.Detection of land-cove transitions by combining multidate classifiers[J].Pattern recognition letters,2004,25:1491-1500.
[68]O.Hall,G.J.Hay.A multiscale object-specific approach to digital change detection[J].International journal of applied earth observation,2003,4:311-327.
[69]Lu,D.Mausel,P.Batistella,M.et al.Land-cover binary change detection methods for use in the moist tropical region of the Amazon:a comparative study[J].International Journal of Remote Sensing,2005,26(1):101-114.
[70]S.L.Hégarat-Mascle,R.Seltz.Automatic change detection by evidential fusion of change indices[J].Remote sensing of environment,2004,91:390-404.
[71]L.Castellana,A.D'Addabbo,G.Pasquariello,et.al.A composed supervised/un-super vised approach to improve change detection from remote sensing[j],Pattern Recognition Letters,2007,28(4):405-413.
[72]#12
[73]A.B.Scott.Urban Planning and Intergroup Conflict.Journal of the American Planning Association,2002,68(1):22-43.
[74]J.Shen,Y.H.Wu,H.W.Liu.Urban Planning Using Augmented Reality.Journal of Urban Planning & Development,2001,127(3):118-126.
[75]M.P.Parris.Urban Ecology.Environment,2004,46(5),3-3.
[76]李德华主编,城市规划原理.中国建筑工业出版社,北京,2001。
[77]张捷,赵民编.新城市规划理论与实践.中国建筑工业出版社,北京,2005。
[78]彭顺喜,等,湖南省国土资源遥感综合调查,国家计委(计国地[1997]20号),2001年11月完成
[79]A.Ahmad,D.Lipik.A feature selection technique for classificatory analysis[J].Pattern Recognition Letters,2005,26(1):43-56.
[80]B.Robert,G.O.Ricardo,Q.Francis.Attribute bagging:improving accuracy of classifier ensembles by using random feature subsets[J].Pattern Recognition,2003,36(6): 1291-1302.
[81]A.J.Walker.An efficient method for generating discrete random variables with general distribution[J],ACT transactions on mathematical software,1977,3(3):253-256.
[82]D.S.Bruin,B.G.H.Gorte.Probabilistic image classification using geological map units applied to land-cover change detection[J].International journal remote sensing.2000,21(12),2389-2402.
[83]Cohen,W.B.,Maiersperger,T.K.,Spies,T.A.,& Oetter,D.R.(2001).Modeling forest cover attributes as continuous variables in a regional context with Thematic Mapper data[J].International Journal of Remote Sensing,2001,22(12):2279-2310.
[84]J.K.Zhang,B.Rivard,S.A.Arturo,et al.Intra- and inter-class spectral variability of tropical tree species at La Selva,Costa Rica:Implications for species identification using HYDICE imagery[J],Remote Sensing of Environment,2006,105(1):129-141.
[85]M.A.Cochrane.Using vegetation reflectance variability for species level classification of hyperspectral data[J].International Journal of Remote Sensing,2000,21(10):2075-2087.
[86]F.A.Kruse,A.B.Lefkoff,J.W.Boardman,et al.The Spectral Image Processing System(SIPS)- interactive visualisation and analysis of imaging spectrometer data[J].Remote Sensing of Environment,1993,44(2-3):145-163.
[87]J.C.Price.How unique are spectral signatures?[J].Remote Sensing of Environment,1994,49(2):181-186.
[88]L.M.Bruce,J.Li,Y.Huang.Automated detection of subpixel hyperspectral targets with adaptive multichannel discrete wavelet transform[J].IEEE Transactions on Geoscience and Remote Sensing,2002,40(4):977-980.
[89]孙即祥,等.现代模式识别[M].长沙:国防科技大学出版社,2002.
[90]杨凯等.遥感图像处理原理和方法.北京:测绘出版社,1988。
[91]#12
[92]王萍,杨培龙,罗颖昕,译.统计模式识别[M].北京:电子工业出版社,2004.
[93]包约翰 编著.自适应模式识别与神经网络.北京:科学出版社,1992。
[94]张乃尧,阎平凡 编著.神经网络与模糊控制.北京:清华大学出版社,1998。
[95]Abhijit S.Pandya,Robert B.Macy,编著,徐勇,荆涛 等译.神经网络模式识别及其实现.北京:电子工业出版社,1999。
[96]焦李成 编著.神经网络计算.西安:西安电子科技大学出版社,1993。
[97]骆剑承,周成虎,梁怡,等.支撑向量机及其遥感影像空间特征提取和分类的应用研究.遥感学报,2002,6(1):50-55.
[98]刘志刚,史文中,李德仁,等.一种基于支撑向量机的遥感影像不完全监督分类新方法.遥感学报,2005,9(4):263-373.
[99]陈秋晓,骆剑承,周成虎,等.基于多特征的遥感影像分类方法.遥感学报,2004,8(3):239-245.
[100]张翊涛,陈洋,王润生.结合自动分区与分层分析的多光谱遥感图像地物分类方法.遥感技术与应用,2005,20(3):332-337.
[101]L.Bruzzone,R.Cossu,G.Vernazza.Detection of land -cover transitions by combining multidate classifiers[J],Pattern Recognition Letters,2004,25(13):1491-1500.
[102]Chen Yunhao,Shi Peijun,Li Xiaobing,et.al.A combined approach for estimating vegetation cover in urban/suburban environments from remotely sensed data[J],Computers & Geosciences,2006,32(9):1299-1309.
[103]#12
[104]#12
[105]王润生.图像理解.长沙:国防科技大学出版社,1995。
[106]Mahamadou Idrissa,Marc Acheroy.Texture classification using Gabor filters.Pattern Recognition Letters,2002,23:1095-1102.
[107]Antonio Bandera,et al.Scale-dependent hierarchical unsupervised segmentation of textured images.Pattern Recognition Letters,2001,22:171-181.
[108]Marina Mueller,Karl Segl,Hermann Kaufmann.Edge- and region-based segmentation technique for the extraction of large,man-made objects in high-resolution satellite imagery.Pattern Recognition,2004,37:1619-1628.
[109]Brijesh Verma,Michael Blumenstein,Moumita Ghosh.A novel approach for structural feature extraction:Contour vs.direction[J].Pattern Recognition Letters,2004,25:975-988.
[110]Edward J.Laurent,Haijin Shi,Demetrios Gatziolis,et.al.Using the spatial and spectral precision of satellite imagery to predict wildlife occurrence patterns[J],Remote Sensing of Environment_,2005,97(2):249-262.
[111]Christopher R.Butson,Richard A.Fernandes.A consistency analysis of surface reflectance and leaf area index retrieval from overlapping clear-sky Landsat ETM+imagery[J].Remote Sensing of Environment,2004,89:369-380.
[112]#12
[113]S.Kaya,P.J.Curran.Monitoring urban growth on the European side of the Istanbul metropolitan area:A case study[J],International Journal of Applied Earth Observation and Geoinformation,2006,8(1):18-25.
[114]Bethany A.Bradley,John F.Mustard.Identifying land cover variability distinct from land cover change:Cheatgrass in the Great Basin.Remote Sensing of Environment,2005,94:204-213.
[115]D.PALANDRO,S.ANDRE'FOUE" T,P.DUSTAN,et al.Change detection in coral reef communities using Ikonos satellite sensor imagery and historic aerial photographs[J].INT.J.REMOTE SENSING,2003,24(4):873-878.
[116]Volker Walter.Object-based classification of remote sensing data for change detection.ISPRS Journal of Photogrammetry & Remote Sensing,2004,58:225-238.
[117]#12
[118]Shui-sen Chen,Liang-fu Chen,Qin-huo Liu,et.al.Remote sensing and GIS-based integrated analysis of coastal changes and their environmental impacts in Lingding Bay, Pearl River Estuary,South China[J],Ocean & Coastal Management,2005,48(1):65-83.
[119]Andrea S.Laliberte,Albert Rango,Kris M:Havstad,et al.Object-oriented image analysis for mapping shrub encroachment from 1937 to 2003 in southern New Mexico.Remote Sensing of Environment,2004,93:198-210.
[120]Bjo"rn Prenzel,Paul Treitz.Remote sensing change detection for a watershed in north Sulawesi,Indonesia.Progress in Planning,2004,61:349-63.
[121]刘亚文,叶晓新.城区人工地物变化检测方法的研究.测绘通报,2001,7:9-11.
[122]廖明生,朱攀,龚健雅.基于典型相关分析的多元变化检测.遥感学报.2004,4(3):197-201.
[123]刘直芳,张剑清.城区变化检测的一种方法.测绘通报,2001,2:1-2.
[124]朱攀,廖明生,杨杰,等.M变换在NOAA/AVHRR数据变化检测中的应用.武汉测绘科技大学学报,2000,25(2):143-147.
[125]Changshan Wu.Normalized spectral mixture analysis for monitoring urban composition using ETM+ imagery.Remote Sensing of Environment,2004,93:480-492.
[126]L.Bruzzone,R.Cossu,G.Vernazza.Detection of land-cover transitions by combining multidate classifiers.Pattern Recognition Letters,2004,25:1491-1500.
[127]Adel Shalaby,Ryutaro Tateishi,Remote sensing and GIS for mapping and monitoring land cover and land -use changes in the Northwestern coastal zone of Egypt[J],Applied Geography,2007,27(1):28-41.
[128]#12
[129]Stefan Weiers,Michael Bock,Michael Wissen,et.al.Mapping and indicator approaches for the assessment of habitats at different scales using remote sensing and GIS methods[J],Landscape and Urban Planning,2004,67(1-4):43-65.
[130]Chunfang Kong,Kai Xu,Chonglong Wu.Classification and Extraction of Urban Land-Use Information from High-Resolution Image Based on Object Multi-features[J],Journal of China University of Geosciences,2006,17(2):151-157.
[131]J.F.Mas.Mapping land use/cover in a tropical coastal area using satellite sensor data,GIS and artificial neural networks[J],Estuarine,Coastal and Shelf Science,2004,59(2):219-230.