基于最佳尺度的面向对象高分辨率遥感影像分类及应用
|
摘要
以QuickBird, GeoEye-1为代表的高分辨率遥感影像数据在国土和规划等相关部门正得到越来越普及的应用,但无论是专业信息提取、动态变化检测,还是专题地图制作等应用都离不开对遥感影像分类。为了满足人们生产应用的要求,寻求一种高效的影像分类方式有着重要的意义。高分辨遥感影像具有更为丰富的光谱、形状、纹理、上下文、拓扑等信息,使得常规的基于像元的信息提取方法难以满足需求,而面向对象的方法弥补了基于像元信息提取技术在处理细节信息中的缺陷。但在面向对象的高分辨率遥感影像信息提取方法中,影像分割是基础,它直接决定着信息提取的精度。不同的分割参数和分割尺度会导致截然不同的分割结果(即影像对象),对于某种特定的地物目标,只有在合适的尺度上才能更有效、更准确的对其进行信息提取。
本文首先分析了基于像元和面向对象信息提取的理论和研究现状,总结出影像分辨率的不断提高是面向对象思想被引入到影像信息提取中的关键因素,并且通过对影像分割参数的定量实验,总结了各个分割参数在影像对象生成中所起的作用。然后利用分类后目视解译法和最佳分割效果原则,论证了改进面积对比法能快速计算出个地物最佳分割尺度。其次,本文总结了一套相对完整的面向对象的信息提取技术思路：针对细小地物建立较小的分割尺度,提取出影像中较小的地物；在较小的分割尺度上采用同质性对生成的影像对象进行合并,提取出较大的地物；针对纷繁复杂的提取规则,建立了先光谱信息后纹理信息的规则模式。最后,通过面向像元的信息提取技术和面向对象的信息提取技术对实验区数据进行影像分类,并采用混淆矩阵、Kappa系数等指标对各自分类结果进行了精度评价,验证了面向对象信息提取技术在处理高分辨率遥感影像上的优势。利用遥感机理和阴影校正模型理论对第二个研究子区域中基于面向对象分类结果中的阴影其进行补偿,使阴影中的信息得到恢复,并利用面向对象方法对其进行了重新分类,提高了分类结果的应用。
Now days, application of high resolution remote sensing image data, e.g. QuickBird, GeoEye-l,in land managing, planning and concerned application fields has been popularized increasingly. Generally, the classifacation of remote sensing images are significant to thematic information extraction, dynamic change detecting and thematic mapping. For actual demand in production, it's reasonable to introduce high-efficiency approaches in generating information from the high resolution images. Compared with low resolution images, more spectrum, shape, texture, context and topology information are included in high resolution images, leading to inadaption of conventional information extraction methods that are on basis of image pixels. However, the object oriented method is capable to conquer such drawbacks in conventional methods for its adaptive capability in dealing with scale parameters of high resolution images because of the strategy of image segmentation.image segmentation is the premise and basis in object oriented information classification and extraction, and it is possible for image segmentation to significantly influence the accuracy of extracted information. Dependently, different segmentation parameters and scales lead to distinct segmented results (calling image objects), thus the appropriate parameters and scales must be determined in order to make the information extracting more efficient and accurate.
In this paper, we analyze the pixel based and object oriented information extraction theory and their current research situation firstly, and indicate that the introducing of object oriented method in image analysis is to adapt the enhancement of image resolution. Based on the image segmentation parameter quantitative experiments, the role of each segmentation parameter in image object generating is summed up, and then the classification of visual interpretation method and optimal segmentation effect principle are used to demonstrate that the improved area contrast method can quickly calculate a feature optimal segmentation scale, furthermore, we produce an integrated strategy for information extraction with object oriented method: set a small scale for smaller features and the features are subsequently extracted; merge the smaller image objects in a small segmentation scale based on the homogeneity judgment standard, and the bigger features are then extracted; according to various extraction regulations, set up a rule mode based on spectral and texture information in sequence. Then, the classification of the study area is done used pixel oriented and object oriented technology,and the confusion matrix, Kappa coefficient and other indicators are examined to evaluate the accuracy of extraction results, respectively, verifying the advantages of object oriented information extraction technology in the processing of high resolution remote sensing images. Finally, we use the mechanism of remote sensing and the shadow correction method to compensate and restore the information in shadow areas, which is extracted by object-oriented information extraction technology from the second study area, Then use the object-oriented approach to re-image classification.from that it could improve the classification results of the application.
本文首先分析了基于像元和面向对象信息提取的理论和研究现状,总结出影像分辨率的不断提高是面向对象思想被引入到影像信息提取中的关键因素,并且通过对影像分割参数的定量实验,总结了各个分割参数在影像对象生成中所起的作用。然后利用分类后目视解译法和最佳分割效果原则,论证了改进面积对比法能快速计算出个地物最佳分割尺度。其次,本文总结了一套相对完整的面向对象的信息提取技术思路：针对细小地物建立较小的分割尺度,提取出影像中较小的地物；在较小的分割尺度上采用同质性对生成的影像对象进行合并,提取出较大的地物；针对纷繁复杂的提取规则,建立了先光谱信息后纹理信息的规则模式。最后,通过面向像元的信息提取技术和面向对象的信息提取技术对实验区数据进行影像分类,并采用混淆矩阵、Kappa系数等指标对各自分类结果进行了精度评价,验证了面向对象信息提取技术在处理高分辨率遥感影像上的优势。利用遥感机理和阴影校正模型理论对第二个研究子区域中基于面向对象分类结果中的阴影其进行补偿,使阴影中的信息得到恢复,并利用面向对象方法对其进行了重新分类,提高了分类结果的应用。
Now days, application of high resolution remote sensing image data, e.g. QuickBird, GeoEye-l,in land managing, planning and concerned application fields has been popularized increasingly. Generally, the classifacation of remote sensing images are significant to thematic information extraction, dynamic change detecting and thematic mapping. For actual demand in production, it's reasonable to introduce high-efficiency approaches in generating information from the high resolution images. Compared with low resolution images, more spectrum, shape, texture, context and topology information are included in high resolution images, leading to inadaption of conventional information extraction methods that are on basis of image pixels. However, the object oriented method is capable to conquer such drawbacks in conventional methods for its adaptive capability in dealing with scale parameters of high resolution images because of the strategy of image segmentation.image segmentation is the premise and basis in object oriented information classification and extraction, and it is possible for image segmentation to significantly influence the accuracy of extracted information. Dependently, different segmentation parameters and scales lead to distinct segmented results (calling image objects), thus the appropriate parameters and scales must be determined in order to make the information extracting more efficient and accurate.
In this paper, we analyze the pixel based and object oriented information extraction theory and their current research situation firstly, and indicate that the introducing of object oriented method in image analysis is to adapt the enhancement of image resolution. Based on the image segmentation parameter quantitative experiments, the role of each segmentation parameter in image object generating is summed up, and then the classification of visual interpretation method and optimal segmentation effect principle are used to demonstrate that the improved area contrast method can quickly calculate a feature optimal segmentation scale, furthermore, we produce an integrated strategy for information extraction with object oriented method: set a small scale for smaller features and the features are subsequently extracted; merge the smaller image objects in a small segmentation scale based on the homogeneity judgment standard, and the bigger features are then extracted; according to various extraction regulations, set up a rule mode based on spectral and texture information in sequence. Then, the classification of the study area is done used pixel oriented and object oriented technology,and the confusion matrix, Kappa coefficient and other indicators are examined to evaluate the accuracy of extraction results, respectively, verifying the advantages of object oriented information extraction technology in the processing of high resolution remote sensing images. Finally, we use the mechanism of remote sensing and the shadow correction method to compensate and restore the information in shadow areas, which is extracted by object-oriented information extraction technology from the second study area, Then use the object-oriented approach to re-image classification.from that it could improve the classification results of the application.
引文
[1]Jensen J R. Introductory digital image processing:A remote sensing perspective, Third edition [M]. London:prentice Hall,2004.
[2]杜培军,陈云浩,王行风等.遥感科学与进展[M].徐州：中国矿业大学出版社,2007.
[3]王燕波,罗伟,李名勇等.基于高分辨率遥感影像的矿山开发监测研究[J].热带地理,2011,31(4)：377-378.
[4]关元秀,程晓阳.高分辨率卫星影像处理指南[M].北京：科学出版社,2008.
[5]陈平生K-means和ISODATA聚类算法的比较研究[J].江西理工大学学报.2012,33(1)：78-80.
[6]张毅,朱鹏.基于遗传算法的改进K-mean遥感影像分类算法研究[J].企业技术开发.2010,29(13)：1-2.
[7]林颖,印桂生,杨耘.多相位水平集高分辨率遥感影像非监督分类[J].测绘通报,2009,(9)：22-25
[8]张凯,赵辽英,厉小润.基于约束线性判别分析的非监督高光谱影像分类方法[J].机电工程,2009,26(8)：41-43.
[9]潘建平,李治.数学形态学多结构元素的道路提取[J].计算机工程与应用.2010,46(11)：233-235.
[10]M.L.Zhu, P.S.Yeh.Automatic road network extraction on aerial photographs. IEEE Computer Society Press.1986:34 - 40
[11]Aiolli F, Sperduti A.An efficient SMO-like algorithm for multiclass SVM. Neural Networks for Signal Processing[J].2002:297-306.
[12]Basu A, Watters C, Shepherd M. Support vector machine for text categorization [A].Proceeding of the 36th annual Hawaii international conference on system science,6-9 2003:1:103-109.
[13]Ahmad A R, Khalid M, Yusof R. Kernel methods and support vector machines for handwriting recognition [A].Student Conference on Research and Development.2002.309-312.
[14]陶建斌,舒宁,沈照庆.利用互信息改进遥感影像朴素贝叶斯网络分类器[J].武汉大学学报信.息科学版,2010,35(2)：228-229.
[15]张建波,朱敏琛.基于监督学习的核拉普拉斯特征映射分类方法[J].福州大学学报.2011,39(1)：49-51.
[16]Ketting R.L., and Landgrebe, D.A. Computer Classification of remotely sensed multispectral image data by extraction and classification of homogeneous object [J]. IEEE transactions on geoscience electronics, 1976,14(1):19-26.
[17]Matsu yama, T. Knowledge-Based Aerial ImageUnderstanding Systems and expert systems for image processing [J].IEEE transactions on geoscience and remote sensing,1987,25(1):305-316.
[18]Arigialis, D.P., and Harlow, C.A. computation image interpretation models:An overview and a perspective [J]. Photogrammetric engineering and remote sensing,1990,56(6):871-886.
[19]Willhauck G, Benz, U Cand Siegert, F Semiautomatic classification procedures forfire monitoring using mufti-temporal SAR images and NOAH-AVHRR hotspot data [J]. Proceedings of the 4th European Conference, Synthetic Aperture Radar, Cologne, Germany, 2002,4-6.
[20]Hofmann,P. Detection informal settlements from IKONOS image data using methods of object oriented image analysis-an example from cape town (south africa) [J].Remote sensing of urban areas/Fernerkunding in urbanen raumen. Regensburg, ed. By JURGENS, C.,2001:41-42.
[21]石军南,李和顺,刘晓农等.面向对象分类方法在森林采伐遥感监测中的应用[J].中南林业科技大学学报,2010,30(11)6-10.
[22]杜凤兰、田庆久、夏学齐等.面向对象的地物分类法分析与评价[[J].遥感技术与应用,2004,19(1)：20-23.
[23]徐涛,谭宗坤,闫小平.面向对象的城市水体信息提取方法[J].地理空间信息,2010,第8卷第3期.
[24]田野,方涛.基于ART2技术的面向对象高分辨遥感影像分类[J].计算机应用与软件,2010,第27卷第4期.
[25]龚健雅,姚璜,沈欣.利用AdaBoost算法进行高分辨率影像的面向对象分类[J].武汉大学学报.信息科学版,2010,第35卷第12期.
[26]张颖娜,张超,赵冬玲,杨建宇.利用ReliefFO和海明遗传算法的面向对象分类特征选择算法[J].武汉大学学报.信息科学版,2010,第35卷第12期.
[27]高海燕,吴波.结合像元形状特征分割的高分辨率影像面向对象分类[J].遥感应用,2010,6.
[28]Woodcock C E,Strahler A H.The factor of seale in remote sensing [J].Remote Sensing of Environment,1987,21:311-332.
[29]黄惠萍.面向对象影像分析中的尺度问题研究[D].中国科学院研究生院博士 学位论文,2003：103-112.
[30]Atkinson P M,Curran P J.Choosing an appropriate spatial resolution for remote sensing investigations[J].Photogrammetric Engineering and Remote-sensing,1997,63(12):1345-1351.
[31]柏延臣,王劲峰.遥感信息不确定性研究：分类与尺度效应模型[M].地质出版社,2003.
[32]韩鹏,龚健雅,李志林等.遥感影像分类中的空间尺度选择方法研究[J].遥感学报,2010,14(3)：507-518.
[33]章毓晋.图像分割[M].北京：科学出版社,2000.
[34]HARALICK R, SHAPIRO L G. Image segmentation technique[J]. Computer Vision, Graphics and Image Processing,1985,29:100-132.
[35]CHENG H D, JIANG H, SUN Y, et a.l Color image segmentation:Advances and prospects[J]. Pattern Re-cognition,2001,34(12):2071-2082.
[36]陈忠.高分辨率遥感图像分类技术研究[D].中国科学院研究生院理学博士学位论文,2006：58-61.
[37]F. Jing, M. J. Li, H. J. Zhang and B. Zhang. Unsupervised Image Segmentation Using Local Homogeneity Analysis. Proc.IEEE International Symposium on Circuits and Systems,2003.
[38]陈秋晓.高分辨率遥感图像分割方法研究[D].中国科学院地理科学与资源研究所博士论文.2004.
[39]林通,石青云.一种基于边缘生长的灰度和彩色图像分割方法[J].中国图象图形学报,2000,5(11)：911-915.
[40]G.M.ESPINDOLA,G.CAMARA,etc.Parameter selection for region-growing image segmentation algorithms using spatial autocorrelation[J].International Journal of Remote Sensing,2006,27(14):3035-3040.
[41]黄璟.面向对象遥感影像分类方法在土地利用信息提取中的应用研究[D].成都理工大学,2010：24-27.
[42]Bleau A, Leon L J. Watershed-based Segmentation and region merging [J]. Computer vision and image understanding,2000,77 (3):317-370.
[43]崔林丽.遥感影像解译特征的综合分析与评价[D].中国科学院研究生院博士论文,2005：30-32.
[44]Basu A, Watters C, Shepherd M. Support vector machine for text categorization [A].Proceeding of the 36th annual Hawaii international conference on system science,6-9 2003:1:103-109.
[45]Debeir, O., Van den steen, I. Latinne, P. Van Ham,P. & Wolff,E. Textural and contextual land-cover classification using single and multiple classifier systems[J]. Photogrammetric engineering and remote sensing. 2002.68:597-605.
[46]薄华,马缚龙,焦李成.图像纹理的灰度共生矩阵计算问题的分析[J].电子学报,2006,34(1)：155-158.
[47]祝振江.基于面向对象分类法的高分辨率遥感影像矿山信息提取应用研究[D].中国地质大学,2010：21-22.
[48]李鸿吉.模糊数学基础及实用算法[M].科学出版社,2005.
[49]别怀江.基于模糊集的遥感图像分类研究[D].哈尔滨工程大学：2005.
[50]黄恩兴.遥感影像分类结果的不确定性研究[J].中国农学通报,2010,26(5)：322-325.
[51]李五夫.遥感数据分类结果分析及分类算法评价[J].黑龙江测绘.1995,4：56-64.
[52]孙波中.多尺度分割技术在高分辨率影像信息提取中的应用研究[D].西安科技大学,2003：16-25.
[53]Haralick Robert M. Statistical and structural approaches to texture[J]. Proceedings of the IEEE,1979,67(5):786-804.
[54]J.K.Hawkins. Textural Properties for pattern recognition[J].Picture processing and psychpictorics,1970,347-370.
.[55]魏金明.面向对象信息提取的共性技术研究[J].城市勘测,2010,5：56-57.
[56]游丽平.面向对象的高分辨率遥感影像分类方法研究[D].福建：福建师范大学,2007.
[57]张俊,于庆国,侯家槐.面向对象的高分辨率影像分类与信息提取[J].遥感技术与应用,2010,25(1)：112-117.
[58]高丽萍.基于面向对象遥感技术的地理本体推理研究[D].武汉理工大学,2009：33-35.
[59]何敏.面向对象的遥感影像土地利用信息提取[D].西南科技大学硕士学位论文,2009：38-41.
[60]万里红,杨武年,李天华等.浅谈QuickBird遥感卫星影像几何精校正[J].测绘与空间地理信息,2007,30(2)：12-15.
[61]Ren Dianwei, Abdelsalam Mohamed Cz. Optimum Index Factor (OIF) for ASTER Data:Examples from the Neoproterozoic Allaqi Suture,Egypt[C]. GSA (Geological Society ofAmerica) Annual Meeting, November 5-8,2001.
[62]杨希.基于神经网络的高分辨率遥感影像分类研究[D].西南交通大学硕士学位论文,2006：9-12.
[63]黄婷.快鸟影像融合方法对比研究及正射校正处理[J].现代测绘,2011,34(2)：7-8.
[64]高华龙.基于QuickBird影像的阴影校正模型研究[J].重庆邮电学院学报,2005,17(2)：226-228.
[2]杜培军,陈云浩,王行风等.遥感科学与进展[M].徐州：中国矿业大学出版社,2007.
[3]王燕波,罗伟,李名勇等.基于高分辨率遥感影像的矿山开发监测研究[J].热带地理,2011,31(4)：377-378.
[4]关元秀,程晓阳.高分辨率卫星影像处理指南[M].北京：科学出版社,2008.
[5]陈平生K-means和ISODATA聚类算法的比较研究[J].江西理工大学学报.2012,33(1)：78-80.
[6]张毅,朱鹏.基于遗传算法的改进K-mean遥感影像分类算法研究[J].企业技术开发.2010,29(13)：1-2.
[7]林颖,印桂生,杨耘.多相位水平集高分辨率遥感影像非监督分类[J].测绘通报,2009,(9)：22-25
[8]张凯,赵辽英,厉小润.基于约束线性判别分析的非监督高光谱影像分类方法[J].机电工程,2009,26(8)：41-43.
[9]潘建平,李治.数学形态学多结构元素的道路提取[J].计算机工程与应用.2010,46(11)：233-235.
[10]M.L.Zhu, P.S.Yeh.Automatic road network extraction on aerial photographs. IEEE Computer Society Press.1986:34 - 40
[11]Aiolli F, Sperduti A.An efficient SMO-like algorithm for multiclass SVM. Neural Networks for Signal Processing[J].2002:297-306.
[12]Basu A, Watters C, Shepherd M. Support vector machine for text categorization [A].Proceeding of the 36th annual Hawaii international conference on system science,6-9 2003:1:103-109.
[13]Ahmad A R, Khalid M, Yusof R. Kernel methods and support vector machines for handwriting recognition [A].Student Conference on Research and Development.2002.309-312.
[14]陶建斌,舒宁,沈照庆.利用互信息改进遥感影像朴素贝叶斯网络分类器[J].武汉大学学报信.息科学版,2010,35(2)：228-229.
[15]张建波,朱敏琛.基于监督学习的核拉普拉斯特征映射分类方法[J].福州大学学报.2011,39(1)：49-51.
[16]Ketting R.L., and Landgrebe, D.A. Computer Classification of remotely sensed multispectral image data by extraction and classification of homogeneous object [J]. IEEE transactions on geoscience electronics, 1976,14(1):19-26.
[17]Matsu yama, T. Knowledge-Based Aerial ImageUnderstanding Systems and expert systems for image processing [J].IEEE transactions on geoscience and remote sensing,1987,25(1):305-316.
[18]Arigialis, D.P., and Harlow, C.A. computation image interpretation models:An overview and a perspective [J]. Photogrammetric engineering and remote sensing,1990,56(6):871-886.
[19]Willhauck G, Benz, U Cand Siegert, F Semiautomatic classification procedures forfire monitoring using mufti-temporal SAR images and NOAH-AVHRR hotspot data [J]. Proceedings of the 4th European Conference, Synthetic Aperture Radar, Cologne, Germany, 2002,4-6.
[20]Hofmann,P. Detection informal settlements from IKONOS image data using methods of object oriented image analysis-an example from cape town (south africa) [J].Remote sensing of urban areas/Fernerkunding in urbanen raumen. Regensburg, ed. By JURGENS, C.,2001:41-42.
[21]石军南,李和顺,刘晓农等.面向对象分类方法在森林采伐遥感监测中的应用[J].中南林业科技大学学报,2010,30(11)6-10.
[22]杜凤兰、田庆久、夏学齐等.面向对象的地物分类法分析与评价[[J].遥感技术与应用,2004,19(1)：20-23.
[23]徐涛,谭宗坤,闫小平.面向对象的城市水体信息提取方法[J].地理空间信息,2010,第8卷第3期.
[24]田野,方涛.基于ART2技术的面向对象高分辨遥感影像分类[J].计算机应用与软件,2010,第27卷第4期.
[25]龚健雅,姚璜,沈欣.利用AdaBoost算法进行高分辨率影像的面向对象分类[J].武汉大学学报.信息科学版,2010,第35卷第12期.
[26]张颖娜,张超,赵冬玲,杨建宇.利用ReliefFO和海明遗传算法的面向对象分类特征选择算法[J].武汉大学学报.信息科学版,2010,第35卷第12期.
[27]高海燕,吴波.结合像元形状特征分割的高分辨率影像面向对象分类[J].遥感应用,2010,6.
[28]Woodcock C E,Strahler A H.The factor of seale in remote sensing [J].Remote Sensing of Environment,1987,21:311-332.
[29]黄惠萍.面向对象影像分析中的尺度问题研究[D].中国科学院研究生院博士 学位论文,2003：103-112.
[30]Atkinson P M,Curran P J.Choosing an appropriate spatial resolution for remote sensing investigations[J].Photogrammetric Engineering and Remote-sensing,1997,63(12):1345-1351.
[31]柏延臣,王劲峰.遥感信息不确定性研究：分类与尺度效应模型[M].地质出版社,2003.
[32]韩鹏,龚健雅,李志林等.遥感影像分类中的空间尺度选择方法研究[J].遥感学报,2010,14(3)：507-518.
[33]章毓晋.图像分割[M].北京：科学出版社,2000.
[34]HARALICK R, SHAPIRO L G. Image segmentation technique[J]. Computer Vision, Graphics and Image Processing,1985,29:100-132.
[35]CHENG H D, JIANG H, SUN Y, et a.l Color image segmentation:Advances and prospects[J]. Pattern Re-cognition,2001,34(12):2071-2082.
[36]陈忠.高分辨率遥感图像分类技术研究[D].中国科学院研究生院理学博士学位论文,2006：58-61.
[37]F. Jing, M. J. Li, H. J. Zhang and B. Zhang. Unsupervised Image Segmentation Using Local Homogeneity Analysis. Proc.IEEE International Symposium on Circuits and Systems,2003.
[38]陈秋晓.高分辨率遥感图像分割方法研究[D].中国科学院地理科学与资源研究所博士论文.2004.
[39]林通,石青云.一种基于边缘生长的灰度和彩色图像分割方法[J].中国图象图形学报,2000,5(11)：911-915.
[40]G.M.ESPINDOLA,G.CAMARA,etc.Parameter selection for region-growing image segmentation algorithms using spatial autocorrelation[J].International Journal of Remote Sensing,2006,27(14):3035-3040.
[41]黄璟.面向对象遥感影像分类方法在土地利用信息提取中的应用研究[D].成都理工大学,2010：24-27.
[42]Bleau A, Leon L J. Watershed-based Segmentation and region merging [J]. Computer vision and image understanding,2000,77 (3):317-370.
[43]崔林丽.遥感影像解译特征的综合分析与评价[D].中国科学院研究生院博士论文,2005：30-32.
[44]Basu A, Watters C, Shepherd M. Support vector machine for text categorization [A].Proceeding of the 36th annual Hawaii international conference on system science,6-9 2003:1:103-109.
[45]Debeir, O., Van den steen, I. Latinne, P. Van Ham,P. & Wolff,E. Textural and contextual land-cover classification using single and multiple classifier systems[J]. Photogrammetric engineering and remote sensing. 2002.68:597-605.
[46]薄华,马缚龙,焦李成.图像纹理的灰度共生矩阵计算问题的分析[J].电子学报,2006,34(1)：155-158.
[47]祝振江.基于面向对象分类法的高分辨率遥感影像矿山信息提取应用研究[D].中国地质大学,2010：21-22.
[48]李鸿吉.模糊数学基础及实用算法[M].科学出版社,2005.
[49]别怀江.基于模糊集的遥感图像分类研究[D].哈尔滨工程大学：2005.
[50]黄恩兴.遥感影像分类结果的不确定性研究[J].中国农学通报,2010,26(5)：322-325.
[51]李五夫.遥感数据分类结果分析及分类算法评价[J].黑龙江测绘.1995,4：56-64.
[52]孙波中.多尺度分割技术在高分辨率影像信息提取中的应用研究[D].西安科技大学,2003：16-25.
[53]Haralick Robert M. Statistical and structural approaches to texture[J]. Proceedings of the IEEE,1979,67(5):786-804.
[54]J.K.Hawkins. Textural Properties for pattern recognition[J].Picture processing and psychpictorics,1970,347-370.
.[55]魏金明.面向对象信息提取的共性技术研究[J].城市勘测,2010,5：56-57.
[56]游丽平.面向对象的高分辨率遥感影像分类方法研究[D].福建：福建师范大学,2007.
[57]张俊,于庆国,侯家槐.面向对象的高分辨率影像分类与信息提取[J].遥感技术与应用,2010,25(1)：112-117.
[58]高丽萍.基于面向对象遥感技术的地理本体推理研究[D].武汉理工大学,2009：33-35.
[59]何敏.面向对象的遥感影像土地利用信息提取[D].西南科技大学硕士学位论文,2009：38-41.
[60]万里红,杨武年,李天华等.浅谈QuickBird遥感卫星影像几何精校正[J].测绘与空间地理信息,2007,30(2)：12-15.
[61]Ren Dianwei, Abdelsalam Mohamed Cz. Optimum Index Factor (OIF) for ASTER Data:Examples from the Neoproterozoic Allaqi Suture,Egypt[C]. GSA (Geological Society ofAmerica) Annual Meeting, November 5-8,2001.
[62]杨希.基于神经网络的高分辨率遥感影像分类研究[D].西南交通大学硕士学位论文,2006：9-12.
[63]黄婷.快鸟影像融合方法对比研究及正射校正处理[J].现代测绘,2011,34(2)：7-8.
[64]高华龙.基于QuickBird影像的阴影校正模型研究[J].重庆邮电学院学报,2005,17(2)：226-228.