摘要
本文在“908海岛海岸带遥感调查”课题的支持下,引入数据挖掘技术,开展了海岸线提取方法和海岸带土地利用分类方法等研究。
对于海岸线提取方法研究,针对课题调查内容,海岸线划分为人工岸线、基岩岸线、砂质岸线、粉沙淤泥质岸线和生物岸线等五种类型,本文在设计海岸线提取方法时,首先分析了不同类型岸线的特征,然后基于数据挖掘中的关联规则技术,分别提出了相应五种岸线类型的提取方法。为了验证本文岸线提取方法的有效性,选取30m分辨率的Landsat TM/ETM+影像开展了实验研究,提取结果都优于3个像元。本文提出的岸线提取方法算法直观、容易实现,而且岸线提取连续。另外,为了对海岸线提取精度进行评价,提出了一种线段匹配精度评价方法。
对于海岸带地物分类方法研究,本文以课题调查中的土地利用调查分类体系为例开展研究,提出了两种地物分类方法,基于证据理论的面向对象的遥感影像海岸带地物分类方法和面向对象的高分辨率影像海岸带地物分层分类方法。
针对海岸带遥感调查中的土地利用II级地物分类需要,引入了证据理论的思想,提出了基于证据理论的面向对象的遥感影像海岸带地物分类方法。为了验证方法的有效性,选取10m分辨率的SPOT影像为数据源,综合考虑了光谱、纹理和形状等特征,在鸭绿江口区域进行了实验研究,分类精度达到了80%以上。该方法解决了单个特征属性类型识别时的不确定性问题,提高了分类精度。另外,为了能够处理研究区域已知样本空间不完备的情况,对基本的证据理论进行了推广。
针对调查中土地利用III级地物分类需要,提出了面向对象的高分辨率影像海岸带地物分层分类方法。为了验证方法的有效性,选取0.61m分辨率的Quickbird影像为数据源,在众多光谱、纹理、形状和邻居特征中,应用关联规则技术,首先找到最能够区分各种地物类型的特征属性及其相关规则,然后基于这些挖掘出来的规则实现最终的分类,分类结果精度超过了80%。该方法解决了分类结果精度对专家经验的依赖,实现了精细地物的自动分类。
Supposed by 908 Projects of Marine comprehensive investigation and assessment in China, in the view of data mining technique, coastline interpretation method and coastal land covers classification method from remote sensing images are studied.
For coastline interpretation method, since shoreline are divided several types, such as artificial shoreline, bedrock shoreline, arenaceous shoreline, silt soreline and biologic shoreline, characters of different shorelines are analysed firstly and five kinds of coastline interpretation methods of the corresponding five types are designed. To verify the presented methods, experiments are implemented by Landsat TM/ETM+ images with the image resolution 30m. The precisions overmatch three pixels. Our proposed methods are intuitionistic and easy to realize. Moreover, the interpretation coastlines are consecutive. In addition, a coastline interpretation accuracy assessment algorithm is proposed to evaluate the experiment results.
For coastal land covers classification method, aiming at the increasing resolution of remote sensing images, two classification methods are designed. One is object-oriented coastal land covers classification method based on evidence theory, the other is object-oriented fine land covers stratified classification method based on data mining.
Aiming at II-level land covers type of remote sensing investigation, introducing the idea of evidence theory, coastal land covers classification method based on evidence theory is presented. To verify the method, SPOT image with 10m resolution is used. Considering spectrum, texture, shape and neighbour features synthetically, an experiment is implemented. The accuracy beyonds 80%. The proposed method solves the uncertainty of classification by single attribute, which improve the accuracy of classification. In addition, the basic D_S evidence theory is extended to process the incompleted sample space.
Aiming at III-level land covers type of remote sensing investigation, object-oriented fine land covers stratified classification method based on data mining is proposed. To verify the presented method, Quickbird image with 0.61m resolution is used. From numerous features of spectrum, texture, shape and neighbour, by using association rule technique, attributes that can distinguish each land covers type are discovered firstly. Then basing on the attributes knowledge, the classification is implemented, which the accuracy of result beyonds 80%. This method eliminates the dependence to systematizer, which is an automatic classification method.
引文
[1]邵峰晶,于忠清.数据挖掘原理与算法.北京:中国水利水电出版社,2003.
[2]程久苗.长江皖江段岸线资源的遥感调查及开发利用评价.资源科学, 1996, 18(3): 67~72.
[3]程久苗.长江芜湖港岸线资源的遥感调查研究.国土资源遥感, 1996, 3: 34~39.
[4]杨金中,李志中,赵玉灵.杭州湾南北两岸岸线变迁遥感动态调查.国土资源遥感, 2002, 1: 23~28.
[5] CHICKANOSKY, V., MIRCHANDANI, G. Wreath products for edge detection. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Seattle, 1998. 2953~2956.
[6] CANNY, J. A computational approach to edge detection. IEEE Trans. Pattern Anal. Machine Intell, 1986, 8: 679~698.
[7] LIU H. Automated extraction of coastline from satellite imagery by integrating Canny edge detection and locally adaptive thresholding methods. INT. J. REMOTE SENSING, 2004, 25(5): 937~958.
[8] LEE, J. S., JURKEVICH, I. Coastline detection and tracing in SAR images. IEEE Transactions on Geoscience and Remote Sensing, 1990, 28: 662~668。
[9] MASON, D. C., DAVENPORT, I. J. Accurate and ef?cient determination of the shoreline in ERS-1 SAR Images. IEEE Transactions on Geoscience and Remote Sensing, 1996, 34: 1243~1253.
[10]常军,刘高焕,刘庆生.黄河三角洲海岸线遥感动态监测.地球信息科学, 2004, 6(1): 94~98.
[11]张朝阳,冯伍法,张俊华.基于色差的遥感影像海岸线提取.测绘学院学报, 2005, 22(4): 259~262.
[12]杨虎,郭华东,王长林. TM-SAR数据融合在黄河口沙咀动态监测中的应用研究.地理学与国土研究, 2001, 17(4): 15~19.
[13] ANDREAS, N., EDZARD, R. and SUSANNE, L. Detection of coastlines in SAR images using wavelet methods. IEEE Transactions on Geoscience and Remote sensing, 2000, 38: 2270~2281.
[14] MARIVI, T., CARLOS, L.M., JORDI, J.M., RAMON, B. Automatic detection of Spots and extraction of frontiers in SAR images by means of the wavelet transform: application to ship and coastline detection. IEEE IGARSS 2006. 383~386.
[15] BUSCH, C. Wavelet based texture segmentation of multi-modal tomographic images, Comput. Graphics. 1997, 21: 347~358.
[16] CHANG, T., KUO, C.C. Texture analysis and classification with tree-structured wavelet transform. IEEE Trans. Image Process, 1993, 2: 429~440.
[17] SHIH, M.Y., TSENG, D.C. A wavelet-based multiresolution edge detection and tracking. Image and Vision Computing, 2005, 23: 441~451.
[18] Niedermeier, A., Romanee?en, E., Lenher, S. Detection of coastline in SAR images using wavelet methods. IEEE Trans. Geosci. Remote Sens., 2000, 38(5): 2270~2281.
[19]冯兰娣,孙效功,胥可辉.利用海岸线遥感图像提取岸线的小波变换方法.青岛海洋大学学报, 2002, 32(5): 777~781.
[20] Sarah F. Tebbens, Stephen M. Burroughs, and Eric E. Nelson. Wavelet analysis of shoreline change on theOuter Banks of North Carolina : an example of complexity in the marine sciences. PNAS, 2002, 99(1): 2554~2560.
[21]杜涛,张斌.用小波技术分析遥感图像确定岸线位置的研究.海洋科学, 1999, 4: 19~21.
[22]林桂兰.遥感在海岸线修测中对应于技术探讨.福建水产, 2005, 8(3): 59~63.
[23] Alesheikh, A.A., Ghorbanali, A., Nouri, N. Coastline change detection using remote sensing. Int. J.Environ. Sci. Tech., 2007, 4(1): 61~66.
[24] Gathot Winarso, Judijanto, Syarif Budhinan. The potential application remote sensing data for coastal study. 2001, http://www.crisp.nus.edu.sg/~acrs2001/pdf/084Winar.pdf
[25] RYAN, T. W., SEMENTILLI, P. J., YUEN, P., and HUNT, B. R. Extraction of shoreline features by neural nets and image processing. Photogrammetric Engineering and Remote Sensing, 1991, 57: 947~955.
[26] Dellepiane S,Laurentiis R D,Giordano F. Coastline extraction from SAR images and a method for the evaluation of the coastline precision. Pattern Recognition Letters, 2004, 25: 1461~1470.
[27]陶明刚. Landsat-TM遥感影像岸线变迁解译研究——以九龙江河口地区为例.水文地质工程地质, 2006, 1: 107~110.
[28]孙美仙,张伟.福建省海岸线遥感调查方法及其应用研究.台湾海峡, 2004, 23(2): 213~219.
[29]崔步礼,常学礼,陈雅琳,等.黄河口海岸线遥感动态监测.测绘科学, 2007, 32(3): 108 ~110.
[30]罗仁燕,陈刚.基于遥感解译的罗源湾地区岸线变迁调查.内江科技, 2006, 2: 128~129.
[31]周建军,陈刚,胡成,等.闽江河口地区河道演变及其影响因素分析.海洋工程, 2004, 23(1): 13~20.
[32]王琳,徐涵秋,李胜.厦门岛及其邻域海岸线变化的遥感动态监测.遥感技术与应用, 2005, 20(4): 404~410.
[33]翟继双,王超,王正志.一种基于多阈值的形态学提取遥感图像海岸线特征方法.中国图像图形学报, 2003, 8A(7): 805~809.
[34]张景奇,介冬梅,刘杰.海岸线不同解译标志对解译结果的影响研究.吉林师范大学学报, 2006, 2: 54~56.
[35] Elizabeth H. Boak and Ian L. Turner. Shoreline definition and detection: A review. Journal of Coastal Research, 2005, 21(4): 688~703.
[36]黄海军,李成治,郭建军.卫星影像在黄河三角洲岸线变化研究中的应用.海洋地质与第四纪地质, 1994, 14(2): 29~37.
[37]马小峰,赵东至,邢小罡,等.海岸线卫星遥感提取方法研究.海洋环境科学, 2007, 26(2): 185~189.
[38]杜凤兰,田庆久,夏学齐.遥感图像分类方法评析与展望.遥感技术与应用, 2004, 19(6): 521~525.
[39] Baatz M , Schabpe A. Object Oriented and Multi-Scale Image Analysis in Semantic Networks. In: Proc. of the 2nd International Symposium on Operationalization of Remote Sensing August 16th- 20th 1999. Enschede. ITC.
[40]万建,王继成.基于ISODATA算法的彩色图像分割.计算机工程, 2002, 28(5): 135~137.
[41]郭欣,赵淑清.概率模型下的K-mesng算法在SAR图像分类中的应用.遥感技术与应用, 2005, 20(2): 295~297.
[42]饶雄,高振宇.多分类器联合监督分类方法研究.四川测绘, 2006, 29(1): 15~16.
[43]李玉榕,项国波.一种基于马氏距离的线性判别分析分类算法.计算机仿真, 2006, 8: 91~93.
[44] Richards J A. Remote Sensing Digital Image Analysis, Springer Verlag. Berlin, 1994.
[45] Kruse F A , Lefkoff A B, Boardman J B, et al. The Spectral Image Processing System (SIPS)– Interactive Visualization and Analysis of Imaging spectrometer Data. Remote Sensing of Environment, 1993, 44: 145~163.
[46] Laine A , Fan J. Texture Classification by Wavelet Packet Signatures. IEEE Trans on Pattern Anal, And Machine Intell, 1993, 11: 1186~1191.
[47] Hans Bandemer, With Siegfried Gottwald. Fuzzy Sets, Fuzzy Logic, Fuzzy Methods with Applications. New York: Wiley Press New York, 1995.
[48] Purnima Pandey, Suju M , George P, et al. Alternate Neural Network Tools for Pattern Classification in Satellite Imageries. National Environmental Engineering Research Institute.
[49] John R., Jensen. Introductory Digital Image Processing—A Remote Sensing Perspective, 2005.
[50] Batistella, M., Robenson, S., et al. Settlement Design, Forest Fragmentation, and Landscape Change in Rondonia, Amazonia, Photogrammetric Engineering & Remote Sensing, 2003, 69(7): 805~812.
[51] Huang Xueqiao and John R.Jensen.A Machine—Learning Approach to Automated Knowledge Based Building for Remote Sensing Image Analysis with GIS Data. Photogrammetry Engineering and Remote Sensing, 1997, 63(10): 1185~1184.
[52]郭小卫,官小平.一种多尺度无监督遥感影像分割方法.遥感信息, 2006, 6: 20~54.
[53] Qin Kun,Guan Zequn,Li Deren.The Methods of Remote Sensing Image Mining Based on Co ncept Lattice.Proceedings of SPIE—The International Society for Optical Engineering, 2003, 5286(1): 254~259.
[54]李祚泳.用BP神经网络实现多波段遥感图像的监督分类.红外与毫米波学报, 1998, 17(2): 153~156.
[55]惠文华.基于支持向量机的遥感图像分类方法.地球科学与环境学报, 2006, 6: 93~95.
[56] Yafit Cohen, Maxim Shoshany. Analysis of convergent evidence in an evidential reasoning knowledge-based classification. Remote Sensing of Environment, 2005, 96: 518~528.
[57] Chunyu Zhao,Lingkui Meng,Changqing Huang.The study of relevant techniques for intelectual integration of GIS and RS.Proc.ACRS 2001～22nd Asian Conference on Remote Sensing, 2001, 2: 1285~1290.
[58]居云红,张俊本,李朝峰,等.基于K-means与SVM结合的遥感图像全自动分类方法.计算机应用研究, 2007, 11: 318~320.
[59]郭春燕,赵春晖.研究了基于模糊支持向量机的超光谱遥感图像分类.应用科技, 2007, 3: 36~43.
[60]王文宇,李博.基于eCognition的高分辨率遥感图像的自动识别分类技术.北京建筑工程学院学报, 2006, 22(4): 26~29.
[61]胡进刚,张晓东等.一种面向对象的高分辨率影像道路提取方法.遥感技术与应用, 2006, 21(3): 184~188.
[62]孙晓霞,张继贤等.利用面向对象的分类方法从IKONOS全色影像中提取河流和道路.测绘科学,2006, 31(1): 62~63.
[63]丁晓英. eCognition在土地利用项目中的应用.测绘与空间地理信息, 2005, 28(6): 117~120.
[64]杜凤兰,田庆久,夏学齐.面向对象的地物分类法分析与评价,遥感技术与应用, 2004, 19(1): 20~23.
[65] Z. CHEN, Z. ZHAO, et al. A new process for the segmentation of high resolution remote sensing imagery. International Journal of Remote Sensing, 2006, 27(22): 4991~5001.
[66] GUO Li-hua, LI Jian-hua, et al. Image segmentation using an improved watershed algorithm. Journal of shanghai jiaotong university (science), 2004, 9(2): 16~19.
[67] Elizabeth H., Boak and Ian L. Turner. Shoreline definition and detection: A review. Journal of Coastal Research, 2005, 21(4): 688~703.
[68] Agrawal R, Imelinski T,Swani A. Mining in Association Rules Between Sets of items in large database. Proceedings ACM-SIGMOD International Conference. 1993, 207~216.
[69] Bing Liu, Wynne Hsu, Yiming Ma. Integrating Classification and Association Rule Mining. Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining (KDD-98, Plenary Presentation), New York, USA, 1998.
[70] Deren LI , Kaichang DI, Deyi LI.. Land use classification of remote sensing image with GIS data based on spatial data mining techniques. International Archives of Photogrammetry and Remote Sensing, Vol. XXXIII, Part B3. Amsterdam 2000..
[71]杜新远,戚浩平,孙永军. ETM+影像湿地遥感信息提取的最佳波段选择——以扎陵湖、鄂陵湖地区为例. http://old.cgs.gov.cn/NEWS/Geology%20News/2007/20070124/24.pdf
[72]王旭红.遥感影像数据挖掘技术研究.西北大学博士学位论文. 2005.
[73]詹艳梅,曾向阳,孙进才.基于粗糙集理论的目标特征选择方法.自然科学进展, 2004, 14(12): 1483~1487.
[74] M.Dash,H.Liu. Feature selection for classification. Intelligent Data Analysis, 1997, 131~156.
[75] Dougherty,J., Kohavi,R. Sahami,M. Supervised and unsupervised discretization of continuous features. ICML-95. 1995.
[76] Quinlan,J.R. C4.5:Programs for machine learning. Morgan Kaufmann,Los Altos, California. 1993.
[77]韩震,恽才兴.伶仃洋大铲湾潮滩冲淤遥感反演研究.海洋学报,2003, 25(5): 58~64.
[78] Dempster A. Upper and lower probabilities induced by multivalued mapping. Annals of Mathematical Statistics, 1967, 38(2): 325~339.
[79]诸葛建伟,王大为,陈昱,等.基于D-S证据理论的网络异常检查方法.软件学报, 2006, 17(3): 463~471.
[80]杨莘元,卓志敏,赵坤,等.基于D-S证据理论的红外小目标识别方法.弹箭与制导学报, 2007, 1: 63~66.
[81]王永庆.人工智能原理与方法.西安交通大学出版社. 1998.
[82]王海晖,卢炎生.基于D-S证据理论的纹理图像分类方法.华中科技大学学报(自然科学版), 2006, 34(4): 49~51.
[83]刘卫国,龚建华,方红亮.地理信息系统支持下的知识获取及其在遥感影像植被分类中的应用研究.遥感学报, 1998, 2(3): 234~240.
[84]李石华,王金亮,陈姚.独龙江流域TM图像的分区分类方法探讨.遥感信息. 2006, 3: 40~43.
[85]陈君颖,田庆久.高分辨率遥感植被分类研究.遥感学报. 2007, 11(2): 221~227.
[86] Kasper Johnansen, NichoCas C.Coops, Sarah E. Gergel, Yulia Stange. Application of high spatial resolution satellite imagery for riparian and forest ecosystem classification. Remote Sensing of Environment, 2007, 110: 29~44.
[87] Andrei Kobler, Saso Dzeroski, Iphigenia Keramitsoglou. Habitat mapping using machine learning-extended kernel-based reclassification of an Ikonos satellite image. Ecological Modeling, 2006, 191: 83~95.
[88] Quinlan, J. R. C4.5: program for machine learning. Morgan Kaufmann. 1992.
[89]闪四清,陈茵,程雁等译.数据挖掘——概念、模型、方法和算法.清华大学出版社. 2003.
[90]刘礼,于强.分层分类与监督分类相结合的遥感分类法研究.林业调查规划, 2007, 32(4): 37~39.
