基于高分辨率影像的改进分水岭算法影像分割参数优选研究
|
摘要
进入21世纪以来,卫星遥感技术发展的一个显著特点就是,遥感影像朝着空间分辨率越来越高的方向快速发展。高空间分辨率遥感影像最大的特点是具有丰富的地物空间细节信息和突出的结构纹理信息。经典的基于像元的遥感影像分析方法主要根据影像的光谱特征进行,难以有效地用于从高空间分辨率影像中提取必要的地物信息。基于对象的影像分析方法应运而生,它综合光谱特征、形状特征和纹理特征对影像进行分析,研究的最小单元不再是单个的像素,而是一个个的影像对象,后续的分析和处理也都基于影像对象进行。
本文以南京市建邺区及其周围地区IKONOS影像作为数据源,首先探讨了影像多尺度分割的几种常用算法,通过优度法和不一致性法两种评价影像分割结果的方法分别建立影像最优分割尺度选择模型,并对两者得到的影像最优分割尺度进行比较,最后利用影像最优分割尺度对影像进行分割,并进行分类及精度评价。
通过研究本文得出以下结论：
(1)本文采用Liu(2012)等人提出的基于不一致性法度量影像最优分割尺度的方法,它最显著的特点是综合考虑了参考对象与匹配分割对象之间的几何和算术差异,由于影像欠分割现象一定会导致分类误差,使用PSE指标能够较好地控制欠分割误差;考虑到影像可能的过分割现象,使用NSR指标保证影像上较小的过分割现象。该方法能够很好的衡量参考对象和匹配分割对象之间的差异,对选择影像最优分割尺度非常有效。
(2)本文提出的基于优度法度量影像最优分割尺度方法,它的最主要特点是在匹配分割对象基础上进行优度法实验,保证分割对象与参考对象的一致性,在研究匹配的分割对象时,提出了衡量对象内部同质性和邻接对象之间异质性的指标,其中衡量邻接对象之间的异质性的指标采用局部Moran's I指数能够很好的反映匹配分割对象在原始影像分割对象中与邻接对象之间的空间关系,综合衡量对象内部同质性指标提出了影像最优分割参数评价函数SEP,实验达到了预期效果。
(3)基于优度法和基于不一致性法度量影像最优分割尺度,这两种方法从两个不同的角度反映影像分割结果的优劣,基于优度法从分割对象形成的角度出发,基于不一致性法从分割对象与实际地物一致性的角度出发,两者虽然角度不同,但是都能较好地评价影像分割结果,所得影像最优分割尺度参数基本一致。
(4)不同地物在影像上具有的尺度是不同的,因此不同的分析目的所关注的尺度也会不同。针对一类地物得到的影像最优分割尺度只适合于提取该类地物,并不能很好的提取所有类型的地物。
Since the beginning of21st century, one of remarkable characteristics in the field of satellite remote sensing technology is quickly towards high spatial resolution. The greatest characteristic of high spatial resolution remote sensing imagery is rich detail information of feature space and prominent information of structure and texture. Classical pixel-based image analysis method is mainly based on the spectral characteristics of images, so it is difficult to effectively extract necessary object information from the high spatial resolution images. Object-based image analysis method arises at the historic moment. Spectral features, shape features and texture features of images were comprehensively analyzed, and the smallest unit of the study is no longer a single pixel but one object, and the subsequent analysis is also based on objects.
The paper takes Jianye District of Nanjing city and the surrounding area as the study area, and uses IKONOS image as the data source. Firstly several commonly used algorithms of multi-scale image segmentation were discussed. Secondly, two modules selecting optimal image segmentation scale through discrepancy measures and goodness measures were established, then the optimal image segmentation scales obtained by the two modules were compared. Finally, the image was segmented by using the optimal segment scale, then the segmented image was classified and accuracy assessment was obtained.
The main conclusions of this paper are as follows:
(1) This paper uses the method based on the inconsistency measure proposed by Liu. et al(2012) to select optimal image segmentation scale. Its significant feature is that the geometric and arithmetical difference between reference objects and corresponding segmented objects are both considered. Because under-segmentation will lead to classification error, PSE index is used to better control under-segmentation error; considering over-segmentation, NSR index ensures less over-segmentation. This method can well measure the difference between reference objects and corresponding segmented objects, and it is very effective to select optimal image segmentation scale.
(2) This paper proposes a method of goodness measures for selecting optimal image segmentation scale. Its main characteristic is that goodness measures are based on corresponding segmented objects in order to ensure consistency of segmented objects and reference objects. The paper proposes new indexes to measure internal homogeneity in objects and heterogeneity between adjacent objects. The index to measure heterogeneity between adjacent objects uses local Moran's Ⅰ,and it can reflect spatial relationships between corresponding objects and their adjacent objects in the segmented image well. Compared with the internal homogeneity index, the paper proposes function of SEP to select optimal image segmentation parameter. The experiment has achieved the anticipated effect.
(3) The two methods of discrepancy measures and goodness measures for select optimal image segmentation scale have two different angles. Discrepancy measure is based on the angle of discrepancy between segments and actual features, and goodness measure is based on the angle of the formation of segments. Though the angles are different, both can well evaluate image segmentation results, and the optimal segmentation scales are almost consistent.
(4) Different features in the image have different scales, so the concerned scale for special aims is distinct. The optimal segmentation scale for one feature is only fit for this one, but not for all others.
本文以南京市建邺区及其周围地区IKONOS影像作为数据源,首先探讨了影像多尺度分割的几种常用算法,通过优度法和不一致性法两种评价影像分割结果的方法分别建立影像最优分割尺度选择模型,并对两者得到的影像最优分割尺度进行比较,最后利用影像最优分割尺度对影像进行分割,并进行分类及精度评价。
通过研究本文得出以下结论：
(1)本文采用Liu(2012)等人提出的基于不一致性法度量影像最优分割尺度的方法,它最显著的特点是综合考虑了参考对象与匹配分割对象之间的几何和算术差异,由于影像欠分割现象一定会导致分类误差,使用PSE指标能够较好地控制欠分割误差;考虑到影像可能的过分割现象,使用NSR指标保证影像上较小的过分割现象。该方法能够很好的衡量参考对象和匹配分割对象之间的差异,对选择影像最优分割尺度非常有效。
(2)本文提出的基于优度法度量影像最优分割尺度方法,它的最主要特点是在匹配分割对象基础上进行优度法实验,保证分割对象与参考对象的一致性,在研究匹配的分割对象时,提出了衡量对象内部同质性和邻接对象之间异质性的指标,其中衡量邻接对象之间的异质性的指标采用局部Moran's I指数能够很好的反映匹配分割对象在原始影像分割对象中与邻接对象之间的空间关系,综合衡量对象内部同质性指标提出了影像最优分割参数评价函数SEP,实验达到了预期效果。
(3)基于优度法和基于不一致性法度量影像最优分割尺度,这两种方法从两个不同的角度反映影像分割结果的优劣,基于优度法从分割对象形成的角度出发,基于不一致性法从分割对象与实际地物一致性的角度出发,两者虽然角度不同,但是都能较好地评价影像分割结果,所得影像最优分割尺度参数基本一致。
(4)不同地物在影像上具有的尺度是不同的,因此不同的分析目的所关注的尺度也会不同。针对一类地物得到的影像最优分割尺度只适合于提取该类地物,并不能很好的提取所有类型的地物。
Since the beginning of21st century, one of remarkable characteristics in the field of satellite remote sensing technology is quickly towards high spatial resolution. The greatest characteristic of high spatial resolution remote sensing imagery is rich detail information of feature space and prominent information of structure and texture. Classical pixel-based image analysis method is mainly based on the spectral characteristics of images, so it is difficult to effectively extract necessary object information from the high spatial resolution images. Object-based image analysis method arises at the historic moment. Spectral features, shape features and texture features of images were comprehensively analyzed, and the smallest unit of the study is no longer a single pixel but one object, and the subsequent analysis is also based on objects.
The paper takes Jianye District of Nanjing city and the surrounding area as the study area, and uses IKONOS image as the data source. Firstly several commonly used algorithms of multi-scale image segmentation were discussed. Secondly, two modules selecting optimal image segmentation scale through discrepancy measures and goodness measures were established, then the optimal image segmentation scales obtained by the two modules were compared. Finally, the image was segmented by using the optimal segment scale, then the segmented image was classified and accuracy assessment was obtained.
The main conclusions of this paper are as follows:
(1) This paper uses the method based on the inconsistency measure proposed by Liu. et al(2012) to select optimal image segmentation scale. Its significant feature is that the geometric and arithmetical difference between reference objects and corresponding segmented objects are both considered. Because under-segmentation will lead to classification error, PSE index is used to better control under-segmentation error; considering over-segmentation, NSR index ensures less over-segmentation. This method can well measure the difference between reference objects and corresponding segmented objects, and it is very effective to select optimal image segmentation scale.
(2) This paper proposes a method of goodness measures for selecting optimal image segmentation scale. Its main characteristic is that goodness measures are based on corresponding segmented objects in order to ensure consistency of segmented objects and reference objects. The paper proposes new indexes to measure internal homogeneity in objects and heterogeneity between adjacent objects. The index to measure heterogeneity between adjacent objects uses local Moran's Ⅰ,and it can reflect spatial relationships between corresponding objects and their adjacent objects in the segmented image well. Compared with the internal homogeneity index, the paper proposes function of SEP to select optimal image segmentation parameter. The experiment has achieved the anticipated effect.
(3) The two methods of discrepancy measures and goodness measures for select optimal image segmentation scale have two different angles. Discrepancy measure is based on the angle of discrepancy between segments and actual features, and goodness measure is based on the angle of the formation of segments. Though the angles are different, both can well evaluate image segmentation results, and the optimal segmentation scales are almost consistent.
(4) Different features in the image have different scales, so the concerned scale for special aims is distinct. The optimal segmentation scale for one feature is only fit for this one, but not for all others.
引文
[1]梅安新,彭望碌,秦其明等.遥感导论[M].北京：高等教育出版社,2001.
[2]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.
[3]赵英时.遥感应用分析原理与方法[M].北京：科学出版社,2003.
[4]JENSEN J R. Introductory Digital Image Processing:A Remote Sensing Perspective[M]北京：科学出版社,2007.
[5]朱述龙,张占睦.遥感图像获取与分析[M].北京：科学出版社,2000.
[6]安培浚,高峰,曲建升.对地观测系统未来发展趋势及其技术需求[J].遥感技术与应用,2007(06)：762-767.
[7]常睿春.基于模糊遗传算法和核主成份分析的遥感图像处理研究[D].成都：成都理工大学,2008.
[8]周成虎,骆剑承.高分辨率卫星影像地学计算[M].北京：科学出版社,2009.
[9]张春晓,侯伟,刘翔等.基于面向对象和影像认知的遥感影像分类方法——以都江堰向峨乡区域为例[J].测绘通报,2010(04)：11-14.
[10]罗希平,田捷,诸葛婴等.图像分割方法综述[J].模式识别与人工智能,1999(03)：300-312.
[11]刘周周.遥感影像分割最优参数选择研究[D].兰州：兰州大学,2012.
[12]章毓晋.图像工程[M].北京：清华大学出版社,2005.
[13]明冬萍,骆剑承,周成虎等.高分辨率遥感影像特征分割及算法评价分析[J].地球信息科学,2006(01)：103-109.
[14]陈春雷,武刚.面向对象的遥感影像最优分割尺度评价[J].遥感技术与应用,2011(01)：96-102.
[15]黄慧萍.面向对象影像分析中的尺度间题研究[D].北京：中国科学院研究生院(遥感应用研究所),2003.
[16]陈秋晓,陈述彭,周成虎.基于局域同质性梯度的遥感图像分割方法及其评价[J].遥感学报,2006(03)：357-365.
[17]罗林.图像分割算法研究[D].武汉：武汉科技大学,2007.
[18]张振勇,王萍,朱鲁等eCognition技术在高分辨率遥感影像信息提取中的应用[J].国土资源信息化,2007(02)：15-17+33.
[19]李晓飞,马大玮,胡焰智.基于形态学和小波的遥感图像边缘检测[J].微计算机信息,2008(12)：307-309.
[20]陈婷婷,程小平.采用模糊形态学和形态学分水岭算法的图像分割[J].西南大学学报(自然科学版),2008(03)：142-145.
[21]谭玉敏,槐建柱,唐中实.一种融合边缘信息的面向对象遥感图像分割方法[J].光谱学与光谱分析,2010(06)：1624-1627.
[22]蒋璐璐,王适,王宝成等.一种改进的标记分水岭遥感图像分割方法[J].计算机技术与发展,2010(01)：39-42.
[23]林卉,刘培,夏俊士等.基于分水岭变换的遥感影像面向对象多尺度分割算法研究[J].测绘通报,2011(10)：17-19.
[24]Baatz M, Schape A. Multiresolution segmentation:an optimization approach for high quality multi-scale image segmentation[J]. Angewandte Geographische lnformationsverarbeitung ⅩⅡ,2000:12-23.
[25]Xiaoying J. Segmentation-based image processing system:U.S. Patent Application 11/984,222[P].2007-11-14.
[26]TREMEAU, ALAIN. A region growing and merging algorithm to color segmentation[J]. Pattern Recognition,0,30(7):1191-1203.
[27]DERIVAUX, S.. Supervised image segmentation using watershed transform, fuzzy classification and evolutionary computation[J]. Pattern Recognition Letters,0,31(15): 2364-2374.
[28]MUNOZ, X. Strategies for image segmentation combining region and boundary information[J]. Pattern Recognition Letters,0,24(1):375-392.
[29]YINING DENG. Unsupervised segmentation of color-texture regions in images and video[J]. Pattern Analysis and Machine Intelligence, IEEE TR,0,23(8):800-810.
[30]TRIAS-SANZ, ROGER. Using colour, texture, and hierarchial segmentation for high-resolution remote sensing[J]. Isprs Journal of Photogrammetry and Remote Sensing,0, 63(2):156-168.
[31]LIU, TING. Multiscale SAR image segmentation using support vector machines[C]//会议/论文集缺失,0：706-709.
[32]何敏,张文君,王卫红.面向对象的最优分割尺度计算模型[J].大地测量与地球动力学,2009(1)：106-109.
[33]张俊,汪云甲,李妍等.一种面向对象的高分辨率影像最优分割尺度选择算法[J].科技导报,2009(21)：91-94.
[34]于欢,张树清,孔博等.面向对象遥感影像分类的最优分割尺度选择研究[J].中国图象图形学报,2010(2)：352-360.
[35]胡文亮,赵萍,董张玉.一种改进的遥感影像面向对象最优分割尺度计算模型[J].地理与地理信息科学,2010,26(6)：15-18.
[36]林先成,李永树.成都平原高分辨率遥感影像分割尺度研究[J].国土资源遥感,2010(2)：7-11.
[37]齐义娜.面向对象的高分辨率遥感影像信息提取与尺度效应分析[D].长春：东北师范大学,2009.
[38]陈忠.高分辨率遥感图像分类技术研究[D].北京：中国科学院研究生院(遥感应用研究所),2006.
[39]汪求来.面向对象遥感影像分类方法及其应用研究[D].南京：南京林业大学,2008.
[40]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：西安科技大学,2011.
[41]WOODCOCK, CURTIS E.. The factor of scale in remote sensing[J]. Remote Sensing of Environment,0,21(3):311-332.
[42]Clinton N, Holt A, Scarborough J, et al. Accuracy assessment measures for object-based image segmentation goodness[J]. Photogrammetric engineering and remote sensing,2010, 76(3):289-299.
[43]Weidner U. Contribution to the assessment of segmentation quality for remote sensing applications[J]. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences,2008,37.
[44]LIU, YONG. Discrepancy measures for selecting optimal combination of parameter values in object-based image analysis[J]. Isprs Journal of Photogrammetry and Remote Sensing,0, 68(0):144-156.
[45]ZHANG, Y.J.. A survey on evaluation methods for image segmentation[J]. Pattern Recognition,0,29(8):1335-1346.
[46]ZHANG, HUI. Image segmentation evaluation:A survey of unsupervised methods[J]. Computer Vision and Image Understanding,0,110(2):260-280.
[47]章毓晋.图象分割[M].北京：科学出版社,2001.
[48]李弼程,彭天强,彭渡.智能图像处理技术[M].北京：电子工业出版社,2004.
[49]孙即祥.图像分析[M].北京：科学出版社,2005.
[50]王爱民,沈兰荪.图像分割研究综述[J].测控技术,2000(05)：1-6+16.
[51]蔡涛,徐国华,徐筱龙.基于模糊C均值与Markov随机场的图像分割[J].计算机工程,2007,33(20)：34-36.
[52]蒋志勇,陈晓玲,秦前清.一种基于淹没的分水岭变换算法[J].武汉大学学报(信息科学版),2009(05)：509-513.
[53]蒋志勇,陈晓玲,秦前清.一种基于重构算子的分水岭变换算法[J].中国图象图肜学报,2009(12)：2527-2533.
[54]阮秋琦.数字图像处理学[M].电子工业出版社,2007.
[55]慈秀丽,陈广告.图像边缘检测方法分析与研究[J].红外,2008(07)：20-23.
[56]Robinson D J, Redding N J, Crisp D J. Implementation of a fast algorithm for segmenting SAR imagery[R]. ELECTRONICS RESEARCH LAB SALISBURY (AUSTRALIA),2002.
[57]陈瑞,张德锋,薛原等.基于遥感影像中电磁特性的地物提取方法[J].电光与控制,2009(01)：71-74+97.
[58]NEUBERT, M.. Assessing image segmentation quality-concepts, methods and application[G]. Object-based image analysis. Springer Berlin Heidelberg.2008:769-784.
[59]CASTILLA, G.. Image objects and geographic objects[G]. Springer Berlin Heidelberg.2008: 91-110.
[60]陈雅淑.局部空间自相关指标的适用性研究[D].华东师范大学,2009.
[61]阎殿武.IDL可视化入门与提高[M].北京：机械工业出版社,2003.
[62]李霞.一种新型的可视化软件—IDL简介[J].新疆气象.2002,25(4)：44-45.
[63]韩培友.IDL可视化分析和应用[M].西安：西北工业大学出版社,2006.
[64]李强.基于IDL遥感图像数据库的设计与实现[硕士论文].兰州大学,2008.
[65]樊疆.基于IDL的遥感影像数据库的研究与实现[硕士论文].兰州大学,2009.
[66]ENVI二次开发指南[M].北京：航天星图(北京)有限公司,2006.
[67]汤泉,牛铮.基于IDL与ENVI二次开发的遥感系统开发方法[J].计算机应用,2008,28(zl)：270-272,276.
[68]陈建强.基于IDL的遥感—综合地学信息三维可视化研究[硕士论文].桂林工学院,2006.
[69]吴秀芹,张洪岩等ArcGIS 9地理信息系统应用与实践[M].北京：清华大学出版社.
[70]Hetland, M.E著.司维,曾军崴,谭颖华译Python基础教程(第2版)[M].北京：人民邮电出版社.
[71]Esri中国信息技术有限公司.遥感GIS一体化[EB/OL].[2012-3-12].http://www.esrichina.com.cn/softwareproduct/EI/RSGIS/.
[72]ArcGIS中自定义ENVI/IDL图像处理工具[EB/OL].[2012-3-12].http://blog.sina.com.cn/s/blog_764b 1 e9d0100pqii.html.
[73]田新光.面向对象高分辨率遥感影像信息提取[硕士论文].北京：中国测绘科学研究院.2007.
[74]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[硕士论文].北京：中国地质大学.2010.
[75]杨长保,丁继红.面向对象的遥感图像分类方法研究[J].吉林大学学报(地球科学版).2006,36(4)：642-646.
[76]马文.高分辨率遥感影像道路分割算法研究[硕士论文].南京：河海大学.2006.
[77]张俊,朱国龙,李妍.而向对象高分辨率影像信息提取中的尺度效应及最优尺度研究[J].测绘科学.2011,36(2)：107-109.
[78]韩鹏,龚健雅.遥感尺度选择问题研究进展[J].遥感信息.2008,1：96-99.
[79]王鹏伟.基于多尺度理论的图像分割方法研究[博士论文].中国科学技术大学,2007.
[80]工鹏伟,吴秀清,张名成等.基于多尺度形态学融合的分水岭图像分割方法[J].数据采集与处理,2006,21(4)：398-402.
[2]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.
[3]赵英时.遥感应用分析原理与方法[M].北京：科学出版社,2003.
[4]JENSEN J R. Introductory Digital Image Processing:A Remote Sensing Perspective[M]北京：科学出版社,2007.
[5]朱述龙,张占睦.遥感图像获取与分析[M].北京：科学出版社,2000.
[6]安培浚,高峰,曲建升.对地观测系统未来发展趋势及其技术需求[J].遥感技术与应用,2007(06)：762-767.
[7]常睿春.基于模糊遗传算法和核主成份分析的遥感图像处理研究[D].成都：成都理工大学,2008.
[8]周成虎,骆剑承.高分辨率卫星影像地学计算[M].北京：科学出版社,2009.
[9]张春晓,侯伟,刘翔等.基于面向对象和影像认知的遥感影像分类方法——以都江堰向峨乡区域为例[J].测绘通报,2010(04)：11-14.
[10]罗希平,田捷,诸葛婴等.图像分割方法综述[J].模式识别与人工智能,1999(03)：300-312.
[11]刘周周.遥感影像分割最优参数选择研究[D].兰州：兰州大学,2012.
[12]章毓晋.图像工程[M].北京：清华大学出版社,2005.
[13]明冬萍,骆剑承,周成虎等.高分辨率遥感影像特征分割及算法评价分析[J].地球信息科学,2006(01)：103-109.
[14]陈春雷,武刚.面向对象的遥感影像最优分割尺度评价[J].遥感技术与应用,2011(01)：96-102.
[15]黄慧萍.面向对象影像分析中的尺度间题研究[D].北京：中国科学院研究生院(遥感应用研究所),2003.
[16]陈秋晓,陈述彭,周成虎.基于局域同质性梯度的遥感图像分割方法及其评价[J].遥感学报,2006(03)：357-365.
[17]罗林.图像分割算法研究[D].武汉：武汉科技大学,2007.
[18]张振勇,王萍,朱鲁等eCognition技术在高分辨率遥感影像信息提取中的应用[J].国土资源信息化,2007(02)：15-17+33.
[19]李晓飞,马大玮,胡焰智.基于形态学和小波的遥感图像边缘检测[J].微计算机信息,2008(12)：307-309.
[20]陈婷婷,程小平.采用模糊形态学和形态学分水岭算法的图像分割[J].西南大学学报(自然科学版),2008(03)：142-145.
[21]谭玉敏,槐建柱,唐中实.一种融合边缘信息的面向对象遥感图像分割方法[J].光谱学与光谱分析,2010(06)：1624-1627.
[22]蒋璐璐,王适,王宝成等.一种改进的标记分水岭遥感图像分割方法[J].计算机技术与发展,2010(01)：39-42.
[23]林卉,刘培,夏俊士等.基于分水岭变换的遥感影像面向对象多尺度分割算法研究[J].测绘通报,2011(10)：17-19.
[24]Baatz M, Schape A. Multiresolution segmentation:an optimization approach for high quality multi-scale image segmentation[J]. Angewandte Geographische lnformationsverarbeitung ⅩⅡ,2000:12-23.
[25]Xiaoying J. Segmentation-based image processing system:U.S. Patent Application 11/984,222[P].2007-11-14.
[26]TREMEAU, ALAIN. A region growing and merging algorithm to color segmentation[J]. Pattern Recognition,0,30(7):1191-1203.
[27]DERIVAUX, S.. Supervised image segmentation using watershed transform, fuzzy classification and evolutionary computation[J]. Pattern Recognition Letters,0,31(15): 2364-2374.
[28]MUNOZ, X. Strategies for image segmentation combining region and boundary information[J]. Pattern Recognition Letters,0,24(1):375-392.
[29]YINING DENG. Unsupervised segmentation of color-texture regions in images and video[J]. Pattern Analysis and Machine Intelligence, IEEE TR,0,23(8):800-810.
[30]TRIAS-SANZ, ROGER. Using colour, texture, and hierarchial segmentation for high-resolution remote sensing[J]. Isprs Journal of Photogrammetry and Remote Sensing,0, 63(2):156-168.
[31]LIU, TING. Multiscale SAR image segmentation using support vector machines[C]//会议/论文集缺失,0：706-709.
[32]何敏,张文君,王卫红.面向对象的最优分割尺度计算模型[J].大地测量与地球动力学,2009(1)：106-109.
[33]张俊,汪云甲,李妍等.一种面向对象的高分辨率影像最优分割尺度选择算法[J].科技导报,2009(21)：91-94.
[34]于欢,张树清,孔博等.面向对象遥感影像分类的最优分割尺度选择研究[J].中国图象图形学报,2010(2)：352-360.
[35]胡文亮,赵萍,董张玉.一种改进的遥感影像面向对象最优分割尺度计算模型[J].地理与地理信息科学,2010,26(6)：15-18.
[36]林先成,李永树.成都平原高分辨率遥感影像分割尺度研究[J].国土资源遥感,2010(2)：7-11.
[37]齐义娜.面向对象的高分辨率遥感影像信息提取与尺度效应分析[D].长春：东北师范大学,2009.
[38]陈忠.高分辨率遥感图像分类技术研究[D].北京：中国科学院研究生院(遥感应用研究所),2006.
[39]汪求来.面向对象遥感影像分类方法及其应用研究[D].南京：南京林业大学,2008.
[40]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：西安科技大学,2011.
[41]WOODCOCK, CURTIS E.. The factor of scale in remote sensing[J]. Remote Sensing of Environment,0,21(3):311-332.
[42]Clinton N, Holt A, Scarborough J, et al. Accuracy assessment measures for object-based image segmentation goodness[J]. Photogrammetric engineering and remote sensing,2010, 76(3):289-299.
[43]Weidner U. Contribution to the assessment of segmentation quality for remote sensing applications[J]. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences,2008,37.
[44]LIU, YONG. Discrepancy measures for selecting optimal combination of parameter values in object-based image analysis[J]. Isprs Journal of Photogrammetry and Remote Sensing,0, 68(0):144-156.
[45]ZHANG, Y.J.. A survey on evaluation methods for image segmentation[J]. Pattern Recognition,0,29(8):1335-1346.
[46]ZHANG, HUI. Image segmentation evaluation:A survey of unsupervised methods[J]. Computer Vision and Image Understanding,0,110(2):260-280.
[47]章毓晋.图象分割[M].北京：科学出版社,2001.
[48]李弼程,彭天强,彭渡.智能图像处理技术[M].北京：电子工业出版社,2004.
[49]孙即祥.图像分析[M].北京：科学出版社,2005.
[50]王爱民,沈兰荪.图像分割研究综述[J].测控技术,2000(05)：1-6+16.
[51]蔡涛,徐国华,徐筱龙.基于模糊C均值与Markov随机场的图像分割[J].计算机工程,2007,33(20)：34-36.
[52]蒋志勇,陈晓玲,秦前清.一种基于淹没的分水岭变换算法[J].武汉大学学报(信息科学版),2009(05)：509-513.
[53]蒋志勇,陈晓玲,秦前清.一种基于重构算子的分水岭变换算法[J].中国图象图肜学报,2009(12)：2527-2533.
[54]阮秋琦.数字图像处理学[M].电子工业出版社,2007.
[55]慈秀丽,陈广告.图像边缘检测方法分析与研究[J].红外,2008(07)：20-23.
[56]Robinson D J, Redding N J, Crisp D J. Implementation of a fast algorithm for segmenting SAR imagery[R]. ELECTRONICS RESEARCH LAB SALISBURY (AUSTRALIA),2002.
[57]陈瑞,张德锋,薛原等.基于遥感影像中电磁特性的地物提取方法[J].电光与控制,2009(01)：71-74+97.
[58]NEUBERT, M.. Assessing image segmentation quality-concepts, methods and application[G]. Object-based image analysis. Springer Berlin Heidelberg.2008:769-784.
[59]CASTILLA, G.. Image objects and geographic objects[G]. Springer Berlin Heidelberg.2008: 91-110.
[60]陈雅淑.局部空间自相关指标的适用性研究[D].华东师范大学,2009.
[61]阎殿武.IDL可视化入门与提高[M].北京：机械工业出版社,2003.
[62]李霞.一种新型的可视化软件—IDL简介[J].新疆气象.2002,25(4)：44-45.
[63]韩培友.IDL可视化分析和应用[M].西安：西北工业大学出版社,2006.
[64]李强.基于IDL遥感图像数据库的设计与实现[硕士论文].兰州大学,2008.
[65]樊疆.基于IDL的遥感影像数据库的研究与实现[硕士论文].兰州大学,2009.
[66]ENVI二次开发指南[M].北京：航天星图(北京)有限公司,2006.
[67]汤泉,牛铮.基于IDL与ENVI二次开发的遥感系统开发方法[J].计算机应用,2008,28(zl)：270-272,276.
[68]陈建强.基于IDL的遥感—综合地学信息三维可视化研究[硕士论文].桂林工学院,2006.
[69]吴秀芹,张洪岩等ArcGIS 9地理信息系统应用与实践[M].北京：清华大学出版社.
[70]Hetland, M.E著.司维,曾军崴,谭颖华译Python基础教程(第2版)[M].北京：人民邮电出版社.
[71]Esri中国信息技术有限公司.遥感GIS一体化[EB/OL].[2012-3-12].http://www.esrichina.com.cn/softwareproduct/EI/RSGIS/.
[72]ArcGIS中自定义ENVI/IDL图像处理工具[EB/OL].[2012-3-12].http://blog.sina.com.cn/s/blog_764b 1 e9d0100pqii.html.
[73]田新光.面向对象高分辨率遥感影像信息提取[硕士论文].北京：中国测绘科学研究院.2007.
[74]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[硕士论文].北京：中国地质大学.2010.
[75]杨长保,丁继红.面向对象的遥感图像分类方法研究[J].吉林大学学报(地球科学版).2006,36(4)：642-646.
[76]马文.高分辨率遥感影像道路分割算法研究[硕士论文].南京：河海大学.2006.
[77]张俊,朱国龙,李妍.而向对象高分辨率影像信息提取中的尺度效应及最优尺度研究[J].测绘科学.2011,36(2)：107-109.
[78]韩鹏,龚健雅.遥感尺度选择问题研究进展[J].遥感信息.2008,1：96-99.
[79]王鹏伟.基于多尺度理论的图像分割方法研究[博士论文].中国科学技术大学,2007.
[80]工鹏伟,吴秀清,张名成等.基于多尺度形态学融合的分水岭图像分割方法[J].数据采集与处理,2006,21(4)：398-402.
© 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 |