基于遥感影像认知理解的干旱半干旱地区土地利用/覆盖自动分类方法研究
|
摘要
遥感影像分类可以实时提取土地利用、地表覆盖情况,在环境变化研究中具有重要作用。但是,目前常规遥感信息提取与分类的方法和手段已不能满足现代科学研究依赖于高精度数据的发展要求。尤其是环境研究的重要领域—干旱区,其不同于湿润区的景观格局以及其自身成因的复杂性、地表覆盖的多元性等特点,使干旱区的遥感影像分类更加困难。很多成熟的遥感分类方法甚至一些新的遥感分类方法,在干旱区的应用和优势都受到了一定的限制。因此对适合于干旱区的高精度遥感分类方法的研究,不仅是遥感技术的必然发展方向之一,也是对干旱区、半干旱地区进行遥感影像分析与环境监测特别是LUCC研究和生态景观研究的需要。
本文以能够快速进行干旱半干旱地区土地利用/覆盖自动分类并兼具有较高精度为目标,围绕基于遥感影像认知理解的分类过程展开研究。研究区域位于兰州北部甘肃—宁夏—内蒙古三省区的交界地带。此研究,以覆盖研究区的2006年8月22日与2006年9月15日两景影像为基础遥感数据源,通过几何校正与90m-SRTM3的DEM数据严格配准,经辐射定标和大气校正后,与DEM数据、DEM派生的坡度坡向数据一起作为影像分割的图层,同时铁路、公路、河流、水渠专题数据作为专题层也参与影像的多尺度分割。
基于遥感影像认知理解的分类方法是从人类目视识别影像出发,利用计算机模拟人脑对影像的认知理解过程,使计算机对遥感影像的识别与分类更加接近于人的思维过程和认识角度。本文首先从目视解译的原理出发,分析了研究区土地利用/覆盖类型在遥感图像上的视觉特征,确定研究区土地利用/覆盖分类方案;其次,为了使认识单元从“单一像元”到“具有实际意义的对象”的转化,进行了遥感影像的多尺度分割研究,包括尺度效应、尺度优化选择以及尺度转换的初步探讨,实现了基于人脑认知理解的第一步。通过不同数量级的数据进行分割结果比较,认为进行大气校正后反射率乘10000之后的数据可以较好体现地物细微差异,分割尺度为15的分割效果最好。同时为弥补大面积相对均匀地物的过度分割即过于破碎,本文又进行了分割参数为200的大尺度分割,以作为超对象所在尺度。然后对分割成的影像对象的光谱特征、纹理特征、形状特征、空间分布特征和近似于人类语言的语义关系特征进行了分析;并构建了类别层次结构;最后在此基础上对研究区进行了遥感影像的模糊分类以及分类结果的评价。
通过上述研究,认为:
利用eCognition进行大面积复杂的干旱区土地利用/土地覆盖的自动分类是可行的。首先,在类别的划分上取得了明显的成效,分类数目达到21类;其次,在一定程度上解决了常规判读过程中常见的“同物异谱”、“异物同谱”等现象,分类总精度达到89.06%。
然而eCognition分类过程是多次人机交互对话试验的结果,特别在干旱区,地表覆盖的混合性使得分层分类形成的类别层次结构比较复杂,特性参数调整比较复杂。此外,研究发现对于同一区域,应用不同的变量建立不同的分类层次结构,结果可能会有细微差别。
并且在遥感分类过程中,合理而可靠的辅助数据对分类结果有着重要的影响。本文的研究区域较大,在进行精度评价时,主要对目视解译以及野外考察后地物类别很清楚的区域进行样本随机采集,这种方法在一定程度上可以体现分类结果的好坏,但还是缺乏一定的完善性。因此,样本采集的方式、样本的分布等对精度的影响需要进一步深化研究。同时,分类过程地物的尺度效应机理和新的分割算法成为以后进一步研究探讨的重要方向之一。
The classification of remotely sensed image, which can quickly obtain the spatial distribution and conduct the real-time change monitoring of land use/land cover, plays an important role in environmental change research. However, the conventional methods and means of remote sensing information extraction and classification can not meet modern scientific research depending on the high-precision data requirements. Particularly the important area for environmental studies-arid or semi arid area is different from the humid area, featuring by landscape patterns, complex causes of its own forming and the diversity of land cover. So its special characteristics made the classification more difficult than that in humid area. Many mature classification methods of remotely sensed image and even some new classification methods are subject to certain restrictions and the advantages of them are not fully used in the arid or semi arid area. So the study on high-precision classification of remotely sensed image that is suitable for arid or semi arid area, is not only a natural development direction of remote sensing technology, but also meets the needs of remote sensing image analysis and environmental monitoring, particularly LUCC and the ecological landscape research.
This article aimed at the automatic classification of high accuracy and efficiency. The study focused on the classification process based on remotely sensed image cognition and understanding. The study area lies in the intersection of Gansu province, Ningxia Hui nationality autonomous region and Inner Mongolia autonomous region. The data from Landsat5 Thematic Mapper sensor was used in this project. One of the two scenes was captured on 21 Aug. 2006 while the other one was captured on 15 Sep. 2006. The relative DEM was the 90m-SRTM3 DEM data. At first, it was to co-register the 30-meter Landsat TM data to 1:50,000 topographic maps and project the 90-meter DEM to match the TM data's projection. Then do topographic analysis on DEM to get slope as well as aspect images. Second, the reflectance image after calibration and atmospheric correction of TM data, the DEM, the aspect and slope images were taken as the layers for the segmentation. Additionally the river, railway, road and penstock collected in the study area were used as thematic layers for some line objects classification.
The classification based on remotely sensed image cognition and understanding was introduced to make a simulation for the human brain's remotely sensed image cognition and understanding, which comes of the visual interpretation and orients to be approximate to human's thinking process and point of cognition. To begin with, make an analysis for the image to draft the classification scheme of land use/land cover in the study area. Secondly, some aspects about remotely sensed image multi-segmentation, including the effect of scale, optimizing the scale and the transformation of scale, were preliminarily studied in order to convert the basic process unit "a single pixel" to "the real meaning object", realizing the first step of human brain's cognition and understanding. Through comparing the 15-scale segmentations of different magnitude data, the data that multiplied the reflectance image data by 10,000 and can reflect the subtle differences in ground covers, had the best subtle result. At the same time, a larger scale segmentation with 200 scale parameter labeling as the super objects level was done for the large and relatively well-proportioned area to make up the fragment caused by the segmentation with 15 scale parameter. Thirdly, the spectral features, texture features, shape features, spatial distribution features and semantic characteristics that are similar to human language expression were delineated. Following that, the class hierarchy was discussed and created. The last step is to automatically do the fuzzy classification and make the accuracy assessment.
Through the study above, the conclusions of this paper are as followings:
This study has demonstrated the potential of this multi-scale segmentation approach in large and complex arid and semi arid area. At first, this project classifies the area into 21 detailed classes. In a certain extent, some "the same class has different spectrum while different classes have the same spectrum" problems can be solved with the overall accuracy up to 89.06 %.
But the process of creating the class hierarchy is comparatively complicated and needs to explore much more information for this work. If the study area has a change, the adjustment may be more complicated. Another way, if the variables selected for labeling the objects are different, the class hierarchy may be different partly, the results may be different too.
Meanwhile, the rational and reliable assistant data take an important role in the eCognition classification. In this large study area, the random samples for the accuracy assessment are qualified in the exactly explored area by field working and visual interpretation. But it is not absolutely ideal to illuminate the classification result good or not. Different samples of different distribution may result in the different accuracy. So, the problems of how the way of sampling and the distribution of samples affect the accuracy of object-oriented multi-segmentation classification should be probed into for further study. In addition, the scale effect mechanism and new segmentation algorithm become one of the most important study directions.
本文以能够快速进行干旱半干旱地区土地利用/覆盖自动分类并兼具有较高精度为目标,围绕基于遥感影像认知理解的分类过程展开研究。研究区域位于兰州北部甘肃—宁夏—内蒙古三省区的交界地带。此研究,以覆盖研究区的2006年8月22日与2006年9月15日两景影像为基础遥感数据源,通过几何校正与90m-SRTM3的DEM数据严格配准,经辐射定标和大气校正后,与DEM数据、DEM派生的坡度坡向数据一起作为影像分割的图层,同时铁路、公路、河流、水渠专题数据作为专题层也参与影像的多尺度分割。
基于遥感影像认知理解的分类方法是从人类目视识别影像出发,利用计算机模拟人脑对影像的认知理解过程,使计算机对遥感影像的识别与分类更加接近于人的思维过程和认识角度。本文首先从目视解译的原理出发,分析了研究区土地利用/覆盖类型在遥感图像上的视觉特征,确定研究区土地利用/覆盖分类方案;其次,为了使认识单元从“单一像元”到“具有实际意义的对象”的转化,进行了遥感影像的多尺度分割研究,包括尺度效应、尺度优化选择以及尺度转换的初步探讨,实现了基于人脑认知理解的第一步。通过不同数量级的数据进行分割结果比较,认为进行大气校正后反射率乘10000之后的数据可以较好体现地物细微差异,分割尺度为15的分割效果最好。同时为弥补大面积相对均匀地物的过度分割即过于破碎,本文又进行了分割参数为200的大尺度分割,以作为超对象所在尺度。然后对分割成的影像对象的光谱特征、纹理特征、形状特征、空间分布特征和近似于人类语言的语义关系特征进行了分析;并构建了类别层次结构;最后在此基础上对研究区进行了遥感影像的模糊分类以及分类结果的评价。
通过上述研究,认为:
利用eCognition进行大面积复杂的干旱区土地利用/土地覆盖的自动分类是可行的。首先,在类别的划分上取得了明显的成效,分类数目达到21类;其次,在一定程度上解决了常规判读过程中常见的“同物异谱”、“异物同谱”等现象,分类总精度达到89.06%。
然而eCognition分类过程是多次人机交互对话试验的结果,特别在干旱区,地表覆盖的混合性使得分层分类形成的类别层次结构比较复杂,特性参数调整比较复杂。此外,研究发现对于同一区域,应用不同的变量建立不同的分类层次结构,结果可能会有细微差别。
并且在遥感分类过程中,合理而可靠的辅助数据对分类结果有着重要的影响。本文的研究区域较大,在进行精度评价时,主要对目视解译以及野外考察后地物类别很清楚的区域进行样本随机采集,这种方法在一定程度上可以体现分类结果的好坏,但还是缺乏一定的完善性。因此,样本采集的方式、样本的分布等对精度的影响需要进一步深化研究。同时,分类过程地物的尺度效应机理和新的分割算法成为以后进一步研究探讨的重要方向之一。
The classification of remotely sensed image, which can quickly obtain the spatial distribution and conduct the real-time change monitoring of land use/land cover, plays an important role in environmental change research. However, the conventional methods and means of remote sensing information extraction and classification can not meet modern scientific research depending on the high-precision data requirements. Particularly the important area for environmental studies-arid or semi arid area is different from the humid area, featuring by landscape patterns, complex causes of its own forming and the diversity of land cover. So its special characteristics made the classification more difficult than that in humid area. Many mature classification methods of remotely sensed image and even some new classification methods are subject to certain restrictions and the advantages of them are not fully used in the arid or semi arid area. So the study on high-precision classification of remotely sensed image that is suitable for arid or semi arid area, is not only a natural development direction of remote sensing technology, but also meets the needs of remote sensing image analysis and environmental monitoring, particularly LUCC and the ecological landscape research.
This article aimed at the automatic classification of high accuracy and efficiency. The study focused on the classification process based on remotely sensed image cognition and understanding. The study area lies in the intersection of Gansu province, Ningxia Hui nationality autonomous region and Inner Mongolia autonomous region. The data from Landsat5 Thematic Mapper sensor was used in this project. One of the two scenes was captured on 21 Aug. 2006 while the other one was captured on 15 Sep. 2006. The relative DEM was the 90m-SRTM3 DEM data. At first, it was to co-register the 30-meter Landsat TM data to 1:50,000 topographic maps and project the 90-meter DEM to match the TM data's projection. Then do topographic analysis on DEM to get slope as well as aspect images. Second, the reflectance image after calibration and atmospheric correction of TM data, the DEM, the aspect and slope images were taken as the layers for the segmentation. Additionally the river, railway, road and penstock collected in the study area were used as thematic layers for some line objects classification.
The classification based on remotely sensed image cognition and understanding was introduced to make a simulation for the human brain's remotely sensed image cognition and understanding, which comes of the visual interpretation and orients to be approximate to human's thinking process and point of cognition. To begin with, make an analysis for the image to draft the classification scheme of land use/land cover in the study area. Secondly, some aspects about remotely sensed image multi-segmentation, including the effect of scale, optimizing the scale and the transformation of scale, were preliminarily studied in order to convert the basic process unit "a single pixel" to "the real meaning object", realizing the first step of human brain's cognition and understanding. Through comparing the 15-scale segmentations of different magnitude data, the data that multiplied the reflectance image data by 10,000 and can reflect the subtle differences in ground covers, had the best subtle result. At the same time, a larger scale segmentation with 200 scale parameter labeling as the super objects level was done for the large and relatively well-proportioned area to make up the fragment caused by the segmentation with 15 scale parameter. Thirdly, the spectral features, texture features, shape features, spatial distribution features and semantic characteristics that are similar to human language expression were delineated. Following that, the class hierarchy was discussed and created. The last step is to automatically do the fuzzy classification and make the accuracy assessment.
Through the study above, the conclusions of this paper are as followings:
This study has demonstrated the potential of this multi-scale segmentation approach in large and complex arid and semi arid area. At first, this project classifies the area into 21 detailed classes. In a certain extent, some "the same class has different spectrum while different classes have the same spectrum" problems can be solved with the overall accuracy up to 89.06 %.
But the process of creating the class hierarchy is comparatively complicated and needs to explore much more information for this work. If the study area has a change, the adjustment may be more complicated. Another way, if the variables selected for labeling the objects are different, the class hierarchy may be different partly, the results may be different too.
Meanwhile, the rational and reliable assistant data take an important role in the eCognition classification. In this large study area, the random samples for the accuracy assessment are qualified in the exactly explored area by field working and visual interpretation. But it is not absolutely ideal to illuminate the classification result good or not. Different samples of different distribution may result in the different accuracy. So, the problems of how the way of sampling and the distribution of samples affect the accuracy of object-oriented multi-segmentation classification should be probed into for further study. In addition, the scale effect mechanism and new segmentation algorithm become one of the most important study directions.
引文
[1] A.S. Antonarakis, K.S. Richards, J. Brasington. Object-based land cover classification using airborne LiDAR[J]. Remote Sensing of Environment, 2008 (In Press)
[2] Andrea S. Laliberte, Albert Rango, et al. Classification of Arid Rangelands Using An Object-Oriented And Multi-Scale Approach With Quickbird Imagery. ASPRS 2005 Annual Conference "Geospatial Goes Global: From Your Neighborhood to the Whole Planet", March 7-11, 2005, Baltimore, Maryland.
[3] Anne Jacquin, Lucie Misakov, Michel Gay. A hybrid object-based classification approach for mapping urban sprawl in periurban environment[J]. Landscape and Urban Planning, 2008, 152-165.
[4] Baatz M. and Schape A. Multiresolution Segmentation: an optimization approach for high quality multi-scale image segmentation. In: Strobl, J. and Blaschke, T. (Eds.): Angewandte Geogr. Informationsverarbeitung XII, Wichmann, Heidelberg, 2000, pp: 12-23.
[5] Baatz M., Benz U., Dehghani S. and Heynen M. eCognition User Guide 4(2004), Definiens Imagine GmbH, Munchen, Germany.
[6] Benz U., Hofmann P., Willhauck G, Lingenfelder I. and Heynen M.. Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS Journal of Photogrammetry and Remote Sensing, 2004, 58, 239-258.
[7] Blaschke T,. A multi-scalar GIS/image processing approach for landscape monitoring of mountainous areas. In: Bottarin et al.(eds). Interdisciplinary Mountain Research. Blackwell Science, 2002, 12-25.
[8] Blaschke T. and Hay G. (2001): Object-oriented image analysis and scale-space: Theory and methods for modeling and evaluating multi-scale landscape structure. International Archives of Photogrammetry and Remote Sensing, vol. 34, 4/W5,22-29.
[9] Blaschke T., Burnett C, Pekkarinen A., New contextual approaches using image segmentation for object-based classification. In: De Meer, F. and de Jong, S. (eds.): Remote Sensing Image Analysis: Including the spatial domain, 2004, pp.211-236. Kluver Academic Publishers, Dordrecht.
[10] Bonan G B. Land-atmosphere interaction for climate system models: couping biophysical, biogeochemical, and ecosystem dynamic process[J]. Remote Sensing of Environment, 1995, 51:57-73.
[11] Borak J.S., Strahler AH. Feature selection and land cover classification of a MODIS like dataset for a semi arid environment. International Journal of Remote Sensing, 1999, 20:919-938
[12] Borak JS, Strahler AH. Feature selection and land cover classification of a MODIS2 likedataset for a semiarid environment. International Journal of Remote Sensing, 1999,20:919-938
[13] Burnett C, Blaschke T.. A Multi-scale segmentation/object relationship modeling methodology for landscape analysis [J]. Ecological Modeling, 2003,233-249.
[14] C.Huang, L.S.Davis, J.R.GTownshend. Anassessment of support vector machine for land cove rclassification[J]. International Journal of Remote Sensing, 2002, 23(4)725-749.
[15] DeFries RS, HansenMC, Townshend JRG, etal. Global land cover classifications at 8km spatial resolution:the use of training data derived from landsat imagery in decision tree classifiers. International Journal of Remote Sensing, 1998, 19:3141-3168.
[16] Franklin SE, Peddle DR. Spectrum texture for improved class discrimination in complex terrain[J]. International Journal of Remote Sensing, 1989, 10(8): 1437-1443.
[17] Friedl M A, Brodley C E. Decision tree classification of land coverfrom remotely sensed data[J]. Remote Sensing of Environment, 1999, 61: 399-409.
[18] Friedl MA, Brodley CE, Strahler AH. Maximizing land cover classification accuracies produced by decision trees at continental to global scales. IEEE Transactions on Geoscience and Remote Sensing, 1999, 37(2):969-977.
[19] Friedl MA, Mclver DK, Hodges JCF, etal. Global land cover mapping from MODIS:algorithms and early results. Remote Sensing of Environment, 2002,83:287-302
[20] Georgios Mallinis, Nikos Koutsias, Maria Tsakiri-Strati, Michael Karteris. Object-based classification using Quickbird imagery for delineating forest vegetation polygons in a Mediterranean test site[J]. ISPRS Journal of PHOTOGRAMMETRY & REMOTE SENSING 63 (2008)237-250.
[21] Gima D S, Galvin K A, Turner B L. The global impact of land-use change[J]. BioScience, 1994, 44(5):300-304.
[22] Hansen MC, DeFriesRS, Townshend JRG, etal. Global land cover classification at 1km resolution using a decision treec lassifier. International Journal of Remote Sensing, 2000, 21:1331-1364.
[23] Hanson MC, DubayahR, DefriesRS. Classification trees:analternative to traditional land cover classifers. International Journal of Remote Sensing, 1996,17:1075-1081.
[24] Hay G J, Niemann K O, Goodenough D G, 1997. Spatial thresholds, image -object methods for the multi-scale evaluation. Remote Sensing of Environment, 62(1):1-19.
[25] IGBP/HDP. Land use and Land cover change science/Research Plan[R]. IGBP Rep, 1995(35)and HDP Rep, 1995(7).
[26] J.Zhang, GM.Foody. A Fuzzy classification of sub-urban land cover form remotely sensed imagery[J]. International Journal of Remote Sening, 1998,19(14):2721-2738.
[27] Jochen Grandell, Jouni Pullianinen, Martti Hallikainen. Subpixel Land Use Classification and Retrieval of Forest Steminthe Boreal Forest Zone by Employing SSM/IData[J]. RemoteSensingof Environment, 1998(63): 140-154.
[28] Kavzoglu T, Mather PM. The use of back propagating artificial neuralnet workd in land cover classification. International. Journal of Remote Sensing, 2003,24(23):4907-4938.
[29] Kettig R. L., Landgrebe D.A., 1976.Classification of multispectral image data by extraction and classification of homogeneous objects. IEEE Transactions on Geoscience Electronics, GE-14,19-26.
[30] Leland E.Pierce, Kathleen M.Bergen, M.Craig Dobson, Fawwaz T.Ulaby. Multitemporal Land-Cover Classification Using SIR-C/X-SAR Imagery[J]. Remote Sensing of Environment, 1998 (64):20-33.
[31] Liu Jiyuan, Liu Mingliang, Deng Xiangzheng, et al. The land use and land cover change database and its relative studies in China[J]. Journal of Geographical Science, 2002, 12(2): 275-282.
[32] Liu Yongxue, Li Manchun, Mao Liang, et at. Review of Remotely Sensed Imagery Classification Patterns Based on Object-oriented Image Analysis[J]. Chinese Geographical Science, 2006,16(3)282-288.
[33] Loveland TR, Reed BC, Brown JF, et al. Development of a global land cover characteristics database and IGBPDIS Cover from lkm AVHRR data. International Journal of Remote Sensing, 2000,21:1303-1330.
[34] Murthy C.S., RajuPV, Bardrinath KVS. Classification of wheat crop with multi-temperoral images: performance of maximum likelihood and artificial neuralnetworks[J]. International Journal of Remote Sensing, 2003, 24(23): 4871-4890.
[35] Olivier Debeir, Isabelle Vandensteen, Patrice Latinne, PhilippeVanHam,and Eleonore Wolff. Texturaland Contextual Land Cover Classification Using Single and Multiple Classifier System[J].Photogrammetric Engineering & Remote Sensing,2002(7):597-605.
[36]Road J M,Lam N S L.Spatial methods for characterising land cover and detecting land-cover changes for the tropics[J].INT.J.Remote Sensing,2002,23(12):2457-2474.
[37]Ruvimbo Gamanya,Philippe De Maeyer,Morgan De Dapper.An automated satellite image classification design using object-oriented segmentation algorithms:A move towards standardization[J].Expert Systems with Applications 32(2007)616-624.
[38]Sobrino J A,Raissouni N.Toward remote sensing methods for land cover dynamic monitoring:application to Morocco[J].INT.J.Remote Sensing,2002,21(2):353-366.
[39]T.Whiteside and W.Ahmad.A comparison of object-oriented and pixel-based classification methods for mapping land cover in northern Australia.Proceedings of SSC2005 Spatial intelligence,innovation and praxis:The national biennial Conference of the Spatial Sciences Institute,September 2005.Melbourne:Spatial Sciences Institute.ISBN 0-9581366-2-9.
[40]T.Duda,M.Canty.Unsupervised classification of satellite imagery:choosing a good algorithm[J].International Journal of Remote Sensing,2002,23(11):2193-2212.
[41]Townshend JGR.Global datasets for land application from Advanced Very High Resolution Radiometer:an introduction.International Journal of Remote Sensing,1994,15:3319-3332
[42]Ursula C.Benz~*,Peter Hofmann,Gregor Willhauck,et al.Multi-resolution,object-oriented fuzzy analysis of remote sensing data for GIS-ready information[J].ISPRS Journal of Photogrammetry & Remote Sensing 58(2004)239-258.
[43]Van Beurden A U C J,Douven W J A M.Aggregation issues of spatial.
[44]陈玉敏.基于神经网络的遥感影像分类研究[J].测绘信息与工程,2002,27(3):6-8.
[45]陈忠.高分辨率遥感图像分类技术研究.2006中国科学院遥感应用研究所博士论文.
[46]程国栋,肖笃宁,王根绪.论干旱区景观生态特征与景观生态建设[J].地球科学进展,1999,14(1):11-15.]
[47]高红山,潘保田等.祁连山东段冲积扇的发育时代及其成因[J].兰州大学学报(自然科学版),2005,41(5):1-4.
[48]关丽.基于空间语义模型的OuickBird影像城市房屋信息自动提取研究.2006年东北师范大学硕士论文.
[49]黄端琼.多尺度纹理特征分析及其在遥感影像分类中的应用.2006福州大学硕士论文.
[50]贾永红,李德仁.多源遥感影像象素级融合分类与决策级分类融合法的研究[J].武汉大学学报信息科学版,2001(5):430-434.
[51]靳文戟,刘正凯.多类别遥感图像的复合分类方法[J].环境遥感,1995,10(4):298-302
[52]孔丽娟,沈吉庆.腾格里沙漠东南边缘植物群落物种多样性分析[J].宁夏农学院学报,2003,24(4):25-28.
[53]匡霞,陈贻运,戴昌达.专家系统在TM图像分类中的应用[J].环境遥感,1986,4(4):257-266.
[54]李爱生,黄铁侠.基于知识的遥感图像分类系统[J].华中理工大学学报,1992,20(4):29-36.
[55]李后强,王宜主,刘政凯.一种适用于多类别遥感图像分类的新方法——复合神经网络分类方法[J].遥感学报,1997,1(4):257-261.
[56]李厚强,刘政凯,林峰.基于分性理论的航空图像分类方法[J].遥感学报,2001,5(5):353-357.
[57]李剑平.气象卫星混合像元分解研究综述[J].气象科技,1999,(2):7-9.
[58]李陇堂.宁夏中部干旱风沙区生态环境的演变与修复研究[J].水土保持研究,2003,10(4):162-164.
[59]李述.干旱、半干旱区土地利用/覆盖变化与荒漠化的遥感综合研究.2006兰州大学硕士论文.
[60]李爽,丁圣彦,许叔明.遥感影像分类方法比较研究[J].河南大学学报(自然科学版),2002,32(2):70-73.
[61]李爽,钱乐祥,丁圣彦.遥感影像土地覆盖专题信息提取方法研究[J].中国土地科学,2002,16(2):30-33.
[62]李爽,张二勋.基于决策树的遥感影像分类方法研究[J].地域研究与开发,2003,22(1):17-21.
[63]李新荣,贾晓红.腾格里沙漠东南缘荒漠植被格局与土壤资源关系[J].草地学报,2005,13:37-42.
[64]刘伟强,胡静,夏德深.基于核空间的多光谱遥感图像分类方法[J].国土资源遥感,2002(3):44-47.
[65]刘正军,王长耀,延昊等.基于FuzzyARTMAP神经网络的高分辨率图象土地覆盖分类及其评价[J].中国图象图形学报,2003,8(2):151-154.
[66]罗格平,周成虎,陈曦.干旱区绿洲土地利用与土地覆盖变化过程[J].地理学报,2003,58(1):64-72.
[67]骆剑承,周成虎,杨艳.具有部分监督的遥感影像模糊聚类方法研究及应用[J].遥感技术与应用,1999,14(4):37-43.
[68]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[J].遥感学报,2002,6(1):50-55.
[69]骆剑承.遥感影像智能图解及其地学认知问题探索[J].地理科学进展,2000,19(4)289-296.
[70]满多清,吴春荣等.腾格里沙漠东南缘荒漠植被盖度月变化特征及生态恢复[J].2005,25(1):140-144.
[71]毛建旭,王耀南,孙炜.基于模糊小脑模型神经网络的遥感图像分类算法[J]测绘学报,2002,31(4):327-332.
[72]莫登奎.中高分辨率遥感影像分割与信息提取研究.2006年中南林业科技大学硕士论文.
[73]潘保田,李吉均等.青藏高原:全球气候变化的驱动器与放大器[J].兰州大学学报(自然科学版),1995,31(3):120-128.
[74]潘江,霍福臣,曹景轩等.宁夏陆相泥盆系及其生物群[M].北京:地质出版社,1987,1-237.
[75]濮静娟.遥感图像目视解译原理和方法[M].北京:中国科学技术出版社,1992.
[76]沙占江,马海州,李玲琴等.利用TM数据提取干旱区土地覆被信息的方法比较[J].干旱区地理,2005,59-64.
[77]沙占江,曾永年,马海州等.土地沙漠化动态监测的遥感与GIS一体化探讨—以龙羊峡库区为例[J].干旱区地理,2000,23(2):274-278.
[78]沙占江,曾永年,马海州等.遥感和GIS支持下的龙羊峡库区土地沙漠化动态研究[J].中国沙漠,2000,20(1):51-54.
[79]师庆东,吕光辉,潘晓玲等.遥感影像中分区分类法及在新疆北部植被分类中的应用[J]干旱区地理,2003,26(3):264-268.
[80]孙丹峰,汲长远,林培.自组织网络在遥感土地覆盖分类中应用研究[J].遥感学报,1999,3(2):139-143.
[81]孙丹峰,李红.遥感影像融合与分类在城市边缘带扩展研究中应用监测[J].中国农业大学学报,2002,7(1):65-70.
[82]孙晓霞,张继贤,刘正军.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[J].测绘科学,2006,61-63.
[83]王惠林.基于知识的遥感图像分类方法研究——以腾格里沙漠南部地区为例.2007兰州大学硕士论文.
[84]王建,董光荣,李文君.利用遥感信息决策树方法分层提取荒漠化土地类型的研究探讨[J].中国沙漠,2000,20(3):243-247.
[85]王立海,赵正勇,杨旗.利用GIS对吉林针阔混交林TM遥感图像分类方法的初探[J].应用生态学报,2006,17(4):577-582.
[86]王萍,张继贤,林宗坚.基于多源遥感数据融合的土地利用土地覆盖变化信息提取试验[J].测绘通报,2003,4:14-17.
[87]王圆圆,李京.遥感影像土地利用/覆盖分类方法研究综述[J].遥感信息,2004,1
[88]阎金凤,陈曦.基于GIS的干旱区LUCC分析和模拟方法探讨[J].干旱区地理,2003,26(2):185-191.
[89]阎满村,董光荣等.腾格里沙漠东南缘沙漠演化的初步研究[J].中国沙漠,1998,18(2):111-117.
[90]阎守邕,王涛,刘亚岚等.遥感影像人机交互判读系统及基技术特点[J].遥感学报,2002,6(3).
[91]于兴修,杨桂山.土地利用/覆被变化研究的现状与问题[J].地理科学进展,2002,21(1):51-57.
[92]于秀兰,钱国蕙,贾晓光.多光谱和SAR遥感图像融合分类的特征选取[J].红外与毫米波学报,2000,19(6):449-453.
[93]张宝光.数学形态学在遥感数字图像分类处理中的应用[J].测绘信息与工程,2000(2):1-5.
[94]张勃.干旱区土地利用/覆盖变换模拟、土壤水盐空间异质性及水资源开发潜力研究—以黑河流域为例.中国科学院寒区旱区环紧与工程研究所博士后研究工作报告,2005.
[95]张丰,熊桢,寇宁.高光谱遥感数据用于水稻精细分类研究[J].武汉理工大学学报,2002,24(10):36-39.
[96]张虎,温娅丽等.祁连山北坡中部气候特征及垂直气候带的划分[J].山地学报,2001,19(6):497-502.
[97]张继贤.论土地利用与覆盖变化遥感信息提取技术框架[J].测绘科学,2003,28(3):13-17.
[98]张培栋,马金宝.天祝县林草植被恢复的思考[J].中国林业,2005,(10):40-41.
[99]张永生.遥感图像信息系统[M].北京:科学出版社,2000.31-106.
[100]章毓晋.图像分割[M].北京:科学出版社,2000,77-107.
[101]赵成义,王玉潮,李子良等.荒漠绿洲植被变化与景观格局耦合关系的研究——以新疆三工河流域为例[J].干旱区地理,2003,26(4):297-304.
[102]赵国忱,杜明义.基于形态学的土地荒漠化遥感图像纹理分析[J].辽宁工程技术大学学报(自然科学版),2002(2):148-150.
[103]赵萍,冯学智,林广发.SPOT卫星影像居民地信息自动提取的决策树方法研究[J].遥感学报,2003,7(4):309-315.
[104]郑明国,蔡强国,秦明周等.一种遥感影像分类精度检验的新方法[J].遥感学报,2006,10(1):39-48.
[105]周春艳.面向对象的高分辨率遥感影像信息提取技术.2006年山东科技大学硕士论文.
[106]朱长青,杨启和,朱文忠.基于小波变换特征的遥感地貌影像纹理分析和分类[J].测绘学报,1996,25(4):252-255.
[107]朱述龙,张占睦.遥感图像获取与分析[M].北京:科学出版社,2000.
[2] Andrea S. Laliberte, Albert Rango, et al. Classification of Arid Rangelands Using An Object-Oriented And Multi-Scale Approach With Quickbird Imagery. ASPRS 2005 Annual Conference "Geospatial Goes Global: From Your Neighborhood to the Whole Planet", March 7-11, 2005, Baltimore, Maryland.
[3] Anne Jacquin, Lucie Misakov, Michel Gay. A hybrid object-based classification approach for mapping urban sprawl in periurban environment[J]. Landscape and Urban Planning, 2008, 152-165.
[4] Baatz M. and Schape A. Multiresolution Segmentation: an optimization approach for high quality multi-scale image segmentation. In: Strobl, J. and Blaschke, T. (Eds.): Angewandte Geogr. Informationsverarbeitung XII, Wichmann, Heidelberg, 2000, pp: 12-23.
[5] Baatz M., Benz U., Dehghani S. and Heynen M. eCognition User Guide 4(2004), Definiens Imagine GmbH, Munchen, Germany.
[6] Benz U., Hofmann P., Willhauck G, Lingenfelder I. and Heynen M.. Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS Journal of Photogrammetry and Remote Sensing, 2004, 58, 239-258.
[7] Blaschke T,. A multi-scalar GIS/image processing approach for landscape monitoring of mountainous areas. In: Bottarin et al.(eds). Interdisciplinary Mountain Research. Blackwell Science, 2002, 12-25.
[8] Blaschke T. and Hay G. (2001): Object-oriented image analysis and scale-space: Theory and methods for modeling and evaluating multi-scale landscape structure. International Archives of Photogrammetry and Remote Sensing, vol. 34, 4/W5,22-29.
[9] Blaschke T., Burnett C, Pekkarinen A., New contextual approaches using image segmentation for object-based classification. In: De Meer, F. and de Jong, S. (eds.): Remote Sensing Image Analysis: Including the spatial domain, 2004, pp.211-236. Kluver Academic Publishers, Dordrecht.
[10] Bonan G B. Land-atmosphere interaction for climate system models: couping biophysical, biogeochemical, and ecosystem dynamic process[J]. Remote Sensing of Environment, 1995, 51:57-73.
[11] Borak J.S., Strahler AH. Feature selection and land cover classification of a MODIS like dataset for a semi arid environment. International Journal of Remote Sensing, 1999, 20:919-938
[12] Borak JS, Strahler AH. Feature selection and land cover classification of a MODIS2 likedataset for a semiarid environment. International Journal of Remote Sensing, 1999,20:919-938
[13] Burnett C, Blaschke T.. A Multi-scale segmentation/object relationship modeling methodology for landscape analysis [J]. Ecological Modeling, 2003,233-249.
[14] C.Huang, L.S.Davis, J.R.GTownshend. Anassessment of support vector machine for land cove rclassification[J]. International Journal of Remote Sensing, 2002, 23(4)725-749.
[15] DeFries RS, HansenMC, Townshend JRG, etal. Global land cover classifications at 8km spatial resolution:the use of training data derived from landsat imagery in decision tree classifiers. International Journal of Remote Sensing, 1998, 19:3141-3168.
[16] Franklin SE, Peddle DR. Spectrum texture for improved class discrimination in complex terrain[J]. International Journal of Remote Sensing, 1989, 10(8): 1437-1443.
[17] Friedl M A, Brodley C E. Decision tree classification of land coverfrom remotely sensed data[J]. Remote Sensing of Environment, 1999, 61: 399-409.
[18] Friedl MA, Brodley CE, Strahler AH. Maximizing land cover classification accuracies produced by decision trees at continental to global scales. IEEE Transactions on Geoscience and Remote Sensing, 1999, 37(2):969-977.
[19] Friedl MA, Mclver DK, Hodges JCF, etal. Global land cover mapping from MODIS:algorithms and early results. Remote Sensing of Environment, 2002,83:287-302
[20] Georgios Mallinis, Nikos Koutsias, Maria Tsakiri-Strati, Michael Karteris. Object-based classification using Quickbird imagery for delineating forest vegetation polygons in a Mediterranean test site[J]. ISPRS Journal of PHOTOGRAMMETRY & REMOTE SENSING 63 (2008)237-250.
[21] Gima D S, Galvin K A, Turner B L. The global impact of land-use change[J]. BioScience, 1994, 44(5):300-304.
[22] Hansen MC, DeFriesRS, Townshend JRG, etal. Global land cover classification at 1km resolution using a decision treec lassifier. International Journal of Remote Sensing, 2000, 21:1331-1364.
[23] Hanson MC, DubayahR, DefriesRS. Classification trees:analternative to traditional land cover classifers. International Journal of Remote Sensing, 1996,17:1075-1081.
[24] Hay G J, Niemann K O, Goodenough D G, 1997. Spatial thresholds, image -object methods for the multi-scale evaluation. Remote Sensing of Environment, 62(1):1-19.
[25] IGBP/HDP. Land use and Land cover change science/Research Plan[R]. IGBP Rep, 1995(35)and HDP Rep, 1995(7).
[26] J.Zhang, GM.Foody. A Fuzzy classification of sub-urban land cover form remotely sensed imagery[J]. International Journal of Remote Sening, 1998,19(14):2721-2738.
[27] Jochen Grandell, Jouni Pullianinen, Martti Hallikainen. Subpixel Land Use Classification and Retrieval of Forest Steminthe Boreal Forest Zone by Employing SSM/IData[J]. RemoteSensingof Environment, 1998(63): 140-154.
[28] Kavzoglu T, Mather PM. The use of back propagating artificial neuralnet workd in land cover classification. International. Journal of Remote Sensing, 2003,24(23):4907-4938.
[29] Kettig R. L., Landgrebe D.A., 1976.Classification of multispectral image data by extraction and classification of homogeneous objects. IEEE Transactions on Geoscience Electronics, GE-14,19-26.
[30] Leland E.Pierce, Kathleen M.Bergen, M.Craig Dobson, Fawwaz T.Ulaby. Multitemporal Land-Cover Classification Using SIR-C/X-SAR Imagery[J]. Remote Sensing of Environment, 1998 (64):20-33.
[31] Liu Jiyuan, Liu Mingliang, Deng Xiangzheng, et al. The land use and land cover change database and its relative studies in China[J]. Journal of Geographical Science, 2002, 12(2): 275-282.
[32] Liu Yongxue, Li Manchun, Mao Liang, et at. Review of Remotely Sensed Imagery Classification Patterns Based on Object-oriented Image Analysis[J]. Chinese Geographical Science, 2006,16(3)282-288.
[33] Loveland TR, Reed BC, Brown JF, et al. Development of a global land cover characteristics database and IGBPDIS Cover from lkm AVHRR data. International Journal of Remote Sensing, 2000,21:1303-1330.
[34] Murthy C.S., RajuPV, Bardrinath KVS. Classification of wheat crop with multi-temperoral images: performance of maximum likelihood and artificial neuralnetworks[J]. International Journal of Remote Sensing, 2003, 24(23): 4871-4890.
[35] Olivier Debeir, Isabelle Vandensteen, Patrice Latinne, PhilippeVanHam,and Eleonore Wolff. Texturaland Contextual Land Cover Classification Using Single and Multiple Classifier System[J].Photogrammetric Engineering & Remote Sensing,2002(7):597-605.
[36]Road J M,Lam N S L.Spatial methods for characterising land cover and detecting land-cover changes for the tropics[J].INT.J.Remote Sensing,2002,23(12):2457-2474.
[37]Ruvimbo Gamanya,Philippe De Maeyer,Morgan De Dapper.An automated satellite image classification design using object-oriented segmentation algorithms:A move towards standardization[J].Expert Systems with Applications 32(2007)616-624.
[38]Sobrino J A,Raissouni N.Toward remote sensing methods for land cover dynamic monitoring:application to Morocco[J].INT.J.Remote Sensing,2002,21(2):353-366.
[39]T.Whiteside and W.Ahmad.A comparison of object-oriented and pixel-based classification methods for mapping land cover in northern Australia.Proceedings of SSC2005 Spatial intelligence,innovation and praxis:The national biennial Conference of the Spatial Sciences Institute,September 2005.Melbourne:Spatial Sciences Institute.ISBN 0-9581366-2-9.
[40]T.Duda,M.Canty.Unsupervised classification of satellite imagery:choosing a good algorithm[J].International Journal of Remote Sensing,2002,23(11):2193-2212.
[41]Townshend JGR.Global datasets for land application from Advanced Very High Resolution Radiometer:an introduction.International Journal of Remote Sensing,1994,15:3319-3332
[42]Ursula C.Benz~*,Peter Hofmann,Gregor Willhauck,et al.Multi-resolution,object-oriented fuzzy analysis of remote sensing data for GIS-ready information[J].ISPRS Journal of Photogrammetry & Remote Sensing 58(2004)239-258.
[43]Van Beurden A U C J,Douven W J A M.Aggregation issues of spatial.
[44]陈玉敏.基于神经网络的遥感影像分类研究[J].测绘信息与工程,2002,27(3):6-8.
[45]陈忠.高分辨率遥感图像分类技术研究.2006中国科学院遥感应用研究所博士论文.
[46]程国栋,肖笃宁,王根绪.论干旱区景观生态特征与景观生态建设[J].地球科学进展,1999,14(1):11-15.]
[47]高红山,潘保田等.祁连山东段冲积扇的发育时代及其成因[J].兰州大学学报(自然科学版),2005,41(5):1-4.
[48]关丽.基于空间语义模型的OuickBird影像城市房屋信息自动提取研究.2006年东北师范大学硕士论文.
[49]黄端琼.多尺度纹理特征分析及其在遥感影像分类中的应用.2006福州大学硕士论文.
[50]贾永红,李德仁.多源遥感影像象素级融合分类与决策级分类融合法的研究[J].武汉大学学报信息科学版,2001(5):430-434.
[51]靳文戟,刘正凯.多类别遥感图像的复合分类方法[J].环境遥感,1995,10(4):298-302
[52]孔丽娟,沈吉庆.腾格里沙漠东南边缘植物群落物种多样性分析[J].宁夏农学院学报,2003,24(4):25-28.
[53]匡霞,陈贻运,戴昌达.专家系统在TM图像分类中的应用[J].环境遥感,1986,4(4):257-266.
[54]李爱生,黄铁侠.基于知识的遥感图像分类系统[J].华中理工大学学报,1992,20(4):29-36.
[55]李后强,王宜主,刘政凯.一种适用于多类别遥感图像分类的新方法——复合神经网络分类方法[J].遥感学报,1997,1(4):257-261.
[56]李厚强,刘政凯,林峰.基于分性理论的航空图像分类方法[J].遥感学报,2001,5(5):353-357.
[57]李剑平.气象卫星混合像元分解研究综述[J].气象科技,1999,(2):7-9.
[58]李陇堂.宁夏中部干旱风沙区生态环境的演变与修复研究[J].水土保持研究,2003,10(4):162-164.
[59]李述.干旱、半干旱区土地利用/覆盖变化与荒漠化的遥感综合研究.2006兰州大学硕士论文.
[60]李爽,丁圣彦,许叔明.遥感影像分类方法比较研究[J].河南大学学报(自然科学版),2002,32(2):70-73.
[61]李爽,钱乐祥,丁圣彦.遥感影像土地覆盖专题信息提取方法研究[J].中国土地科学,2002,16(2):30-33.
[62]李爽,张二勋.基于决策树的遥感影像分类方法研究[J].地域研究与开发,2003,22(1):17-21.
[63]李新荣,贾晓红.腾格里沙漠东南缘荒漠植被格局与土壤资源关系[J].草地学报,2005,13:37-42.
[64]刘伟强,胡静,夏德深.基于核空间的多光谱遥感图像分类方法[J].国土资源遥感,2002(3):44-47.
[65]刘正军,王长耀,延昊等.基于FuzzyARTMAP神经网络的高分辨率图象土地覆盖分类及其评价[J].中国图象图形学报,2003,8(2):151-154.
[66]罗格平,周成虎,陈曦.干旱区绿洲土地利用与土地覆盖变化过程[J].地理学报,2003,58(1):64-72.
[67]骆剑承,周成虎,杨艳.具有部分监督的遥感影像模糊聚类方法研究及应用[J].遥感技术与应用,1999,14(4):37-43.
[68]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[J].遥感学报,2002,6(1):50-55.
[69]骆剑承.遥感影像智能图解及其地学认知问题探索[J].地理科学进展,2000,19(4)289-296.
[70]满多清,吴春荣等.腾格里沙漠东南缘荒漠植被盖度月变化特征及生态恢复[J].2005,25(1):140-144.
[71]毛建旭,王耀南,孙炜.基于模糊小脑模型神经网络的遥感图像分类算法[J]测绘学报,2002,31(4):327-332.
[72]莫登奎.中高分辨率遥感影像分割与信息提取研究.2006年中南林业科技大学硕士论文.
[73]潘保田,李吉均等.青藏高原:全球气候变化的驱动器与放大器[J].兰州大学学报(自然科学版),1995,31(3):120-128.
[74]潘江,霍福臣,曹景轩等.宁夏陆相泥盆系及其生物群[M].北京:地质出版社,1987,1-237.
[75]濮静娟.遥感图像目视解译原理和方法[M].北京:中国科学技术出版社,1992.
[76]沙占江,马海州,李玲琴等.利用TM数据提取干旱区土地覆被信息的方法比较[J].干旱区地理,2005,59-64.
[77]沙占江,曾永年,马海州等.土地沙漠化动态监测的遥感与GIS一体化探讨—以龙羊峡库区为例[J].干旱区地理,2000,23(2):274-278.
[78]沙占江,曾永年,马海州等.遥感和GIS支持下的龙羊峡库区土地沙漠化动态研究[J].中国沙漠,2000,20(1):51-54.
[79]师庆东,吕光辉,潘晓玲等.遥感影像中分区分类法及在新疆北部植被分类中的应用[J]干旱区地理,2003,26(3):264-268.
[80]孙丹峰,汲长远,林培.自组织网络在遥感土地覆盖分类中应用研究[J].遥感学报,1999,3(2):139-143.
[81]孙丹峰,李红.遥感影像融合与分类在城市边缘带扩展研究中应用监测[J].中国农业大学学报,2002,7(1):65-70.
[82]孙晓霞,张继贤,刘正军.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[J].测绘科学,2006,61-63.
[83]王惠林.基于知识的遥感图像分类方法研究——以腾格里沙漠南部地区为例.2007兰州大学硕士论文.
[84]王建,董光荣,李文君.利用遥感信息决策树方法分层提取荒漠化土地类型的研究探讨[J].中国沙漠,2000,20(3):243-247.
[85]王立海,赵正勇,杨旗.利用GIS对吉林针阔混交林TM遥感图像分类方法的初探[J].应用生态学报,2006,17(4):577-582.
[86]王萍,张继贤,林宗坚.基于多源遥感数据融合的土地利用土地覆盖变化信息提取试验[J].测绘通报,2003,4:14-17.
[87]王圆圆,李京.遥感影像土地利用/覆盖分类方法研究综述[J].遥感信息,2004,1
[88]阎金凤,陈曦.基于GIS的干旱区LUCC分析和模拟方法探讨[J].干旱区地理,2003,26(2):185-191.
[89]阎满村,董光荣等.腾格里沙漠东南缘沙漠演化的初步研究[J].中国沙漠,1998,18(2):111-117.
[90]阎守邕,王涛,刘亚岚等.遥感影像人机交互判读系统及基技术特点[J].遥感学报,2002,6(3).
[91]于兴修,杨桂山.土地利用/覆被变化研究的现状与问题[J].地理科学进展,2002,21(1):51-57.
[92]于秀兰,钱国蕙,贾晓光.多光谱和SAR遥感图像融合分类的特征选取[J].红外与毫米波学报,2000,19(6):449-453.
[93]张宝光.数学形态学在遥感数字图像分类处理中的应用[J].测绘信息与工程,2000(2):1-5.
[94]张勃.干旱区土地利用/覆盖变换模拟、土壤水盐空间异质性及水资源开发潜力研究—以黑河流域为例.中国科学院寒区旱区环紧与工程研究所博士后研究工作报告,2005.
[95]张丰,熊桢,寇宁.高光谱遥感数据用于水稻精细分类研究[J].武汉理工大学学报,2002,24(10):36-39.
[96]张虎,温娅丽等.祁连山北坡中部气候特征及垂直气候带的划分[J].山地学报,2001,19(6):497-502.
[97]张继贤.论土地利用与覆盖变化遥感信息提取技术框架[J].测绘科学,2003,28(3):13-17.
[98]张培栋,马金宝.天祝县林草植被恢复的思考[J].中国林业,2005,(10):40-41.
[99]张永生.遥感图像信息系统[M].北京:科学出版社,2000.31-106.
[100]章毓晋.图像分割[M].北京:科学出版社,2000,77-107.
[101]赵成义,王玉潮,李子良等.荒漠绿洲植被变化与景观格局耦合关系的研究——以新疆三工河流域为例[J].干旱区地理,2003,26(4):297-304.
[102]赵国忱,杜明义.基于形态学的土地荒漠化遥感图像纹理分析[J].辽宁工程技术大学学报(自然科学版),2002(2):148-150.
[103]赵萍,冯学智,林广发.SPOT卫星影像居民地信息自动提取的决策树方法研究[J].遥感学报,2003,7(4):309-315.
[104]郑明国,蔡强国,秦明周等.一种遥感影像分类精度检验的新方法[J].遥感学报,2006,10(1):39-48.
[105]周春艳.面向对象的高分辨率遥感影像信息提取技术.2006年山东科技大学硕士论文.
[106]朱长青,杨启和,朱文忠.基于小波变换特征的遥感地貌影像纹理分析和分类[J].测绘学报,1996,25(4):252-255.
[107]朱述龙,张占睦.遥感图像获取与分析[M].北京:科学出版社,2000.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |