特征变换的延安建筑物提取研究
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:High-resolution images and feature transformation:building extraction in the Yan'an district
  • 作者:丁辉 ; 张茂省
  • 英文作者:DING Hui;ZHANG Maosheng;Xi'an Center of Geological Survey;Key Laboratory for Geo-hazard in Losses Area,Ministry of Land and Resources;
  • 关键词:缨帽变换 ; 快鸟 ; 建筑物 ; 面向对象 ; 信息识别
  • 英文关键词:Tasseled cap transformation;;Quickbird;;building;;object-oriented;;information identification
  • 中文刊名:CHKD
  • 英文刊名:Science of Surveying and Mapping
  • 机构:中国地质调查局西安地质调查中心;国土资源部黄土地质灾害重点实验室;
  • 出版日期:2018-12-07 11:05
  • 出版单位:测绘科学
  • 年:2019
  • 期:v.44;No.247
  • 基金:国家自然科学基金项目(41502338,41530640);; 中国地质调查局地质调查项目(12120114025701)
  • 语种:中文;
  • 页:CHKD201901022
  • 页数:9
  • CN:01
  • ISSN:11-4415/P
  • 分类号:128-135+147
摘要
针对高空间分辨率卫星遥感数据多光谱波段数较少和原始波段组合光谱特征利用有限等问题,该文提出了一种基于特征变换的建筑物信息提取方法。以陕西省延安市宝塔地区为研究区,基于快鸟数据采取特征变换、波段选择、数据融合等解决高空间分辨率原始光谱特征利用有限等问题,采用知识规则的面向对象分类方法进行建筑物识别研究。实验表明,缨帽变换波段能有效地突出建筑物信息,4种融合算法中主成分变换融合适用进一步面向对象分类,建筑物识别的总体精度达到89.3%。此方法能有效识别沿坡脚或滑坡体分散分布的建筑物,为快速获取居民空间分布信息和辅助灾害应急评估等提供参考。
        According to the problem of the fewer original spectral bands and limited spectral characteristics of high spatial resolution satellite remote sensing data,this paper proposed a method for building extraction based on feature transformation.In this study,we examined how building identification can be realized through object-oriented classification based on knowledge rules by bands selection and feature transformation to the Quickbird multispectral data of Yan'an Baota,Shaanxi province,Northwest China,and then applied data fusion by using four different algorithms.The experimental results suggested that the tasseled cap(TC)transformation effectively highlights the spectral information features of buildings;furthermore,principal component fusion can be applied to object-oriented classification with an overall accuracy of 89.3%.This method effectively identifies buildings irregularly distributed along slope toes or landslide masses,provided reference for quickly acquiring the spatial distribution information of local residents,and supported disaster emergency response assessment.
引文
[1]王俊,秦其明,叶昕,等.高分辨率光学遥感图像建筑物提取研究进展[J].遥感技术与应用,2016,31(4):653-662.(WANG Jun,QIN Qiming,YE Xin,et al.Asurvey of building extraction methods from optical high resolution remote imagery[J].Remote Sensing Technology and Application,2016,31(4):653-662.)
    [2]谭衢霖.高分辨率多光谱影像城区建筑物提取研究[J].测绘学报,2010,39(6):618-623.(TAN Qulin.Urban building extraction from VHR multi-spectral image using objection-based classification[J].Acta Geodaetica et Cartographica Sinica,2010,39(6):618-623.)
    [3]SIRMACEK B,UNSALAN C.A Probabilistic framework to detect buildings in aerial and satellite image[J].IEEE Transaction on Geoscience and Remote Sensing,2011,49(1):211-221.
    [4]IZADI M,SAEEDI P.Three-dimensional polygonal building model estimation from single satellite image[J].IEEE Transaction on Geoscience and Remote Sensing,2012,50(6):2254-2272.
    [5]AYTEKIN O,ERENER A,ULUSOY I,et al.Unsupervised building detection in complex urban environments from multi-spectral satellite imagery[J].International Journal of Remote Sensing,2012,33(7):2151-2177.
    [6]吴炜,骆剑承,沈占锋,等.光谱和形状特征相结合的高分辨率遥感图像建筑物提取方法[J].武汉大学学报(信息科学版),2012,37(7):800-805.(WU Wei,LUOJiancheng,SHEN Zhanfeng,et al.Building extraction from high resolution remote sensing imagery based on spatial-spectral method[J].Geomatics and Information Science of Wuhan University,2012,37(7):800-805.)
    [7]OK A O,SENARAS C,YUKSEL B.Automated detection of arbitrarily shaped building in complex environments from monocular VHR optical satellite imagery[J].IEEE Transaction on Geoscience and Remote Sensing,2013,51(3):1701-1717.
    [8]COTE M,SAEEDI P.Automatic roof top extraction in Nadir aerial image of suburban regions using corners and variational level set evolution[J].IEEE Transaction on Geoscience and Remote Sensing,2013,51(1):313-328.
    [9]刘海飞,常庆瑞,李粉玲.高分辨率影像城区建筑物提取研究[J].西北农林科技大学学报(自然科学版),2013,41(10):221-227.(LIU Haifei,CHANG Qingrui,LI Fenling.Urban building extraction from highresolution multi-spectral image with object-oriented classification[J].Journal of Northwest A&F University(Natural Science Edition),2013,41(10):221-227.)
    [10]郑文武,邓运员,罗亮,等.一种传统居民遥感提取方法[J].测绘科学,2015,40(10):93-97.(ZHENG Wenwu,DENG Yunyuan,LUO Lang,et al.Traditional residence extraction from high-resolution imagery based on morphological building index and texture[J].Science of Surveying and Mapping,2015,40(10):93-97.)
    [11]张庆云,赵冬.高空间分辨率遥感影像提取建筑物方法综述[J].测绘与空间地理信息,2015,38(4):74-78.(ZHANG Qingyun,ZHAO Dong.Research on method of building extraction from high resolution remote sensing images[J].Geomatics&Spatial Information Technology,2015,38(4):74-78.)
    [12]王正伟,杨灿灿,艾泽天,等.面向对象的多源数据建筑物提取[J].测绘与空间地理信息,2015,38(9):75-80,83.(WANG Zhengwei,YANG Cancan,AI Zetian,et al.Building extraction based on multi-source data[J].Geomatics&Spatial Information Technology,2015,38(9):75-80,83.)
    [13]沈安生.利用高分辨率遥感影像提取建筑物方法研究[J].测绘与空间地理信息,2015,38(10):109-115.(SHEN Ansheng.State-of-the-art in building extraction from high-resolution remote sensing image[J].Geomatics&Spatial Information Technology,2015,38(10):109-115.)
    [14]刘玲,王国锋,李建成,等.基于对象分析策略的航空激光扫描数据建筑物自动提取方法[J].长安大学学报(自然科学版),2015,35(S1):135-139.(LIU Ling,WANG Guofeng,LI Jiancheng,et al.Building extraction method of airborne laser scanning based on object analysis strategy[J].Journal of Chang’an University(Natural Science Edition),2015,35(S1):135-139.)
    [15]朱俊杰,范湘涛,杜小平.几何特征表达及基于几何特征的建筑物提取[J].应用科学学报,2015,33(1):9-20.(ZHU Junjie,FAN Xiangtao,Du Xiaoping.Geometric feature representation and building extraction based on geometric feature[J].Journal of Application Sciences-Electronics and Information Engineering,2015,33(1):9-20.)
    [16]LIASIS G,STAVROU S.Building extraction in satellite images using active contours and colour feature[J].International Journal of Remote Sensing,2016,37(5):1127-1135.
    [17]徐昌荣,葛山运.基于面向对象的高分辨率遥感影像建筑物提取研究[J].城市勘测,2011(1):84-86.(XUChangrong,GE Shanyun.Object-oriented remote sensing image of building extraction[J].Urban Geotechnical Investigation&Surveying,2011(1):84-86.)
    [18]彭令,徐素宁,彭军还.多源遥感数据支持下区域滑坡灾害风险评价[J].吉林大学学报(地球科学版),2016,46(1):175-186.(PENG Ling,XU Suning,PENG Junhuan.Regional landslides risk assessment using multisource remote sensing data[J].Journal of Jilin University(Earth Science Edition),2016,46(1):175-186.)
    [19]刘丹丹,刘江,张玉娟,等.面向对象的多尺度高分影像建筑物提取方法研究[J].测绘与空间地理信息,2016,39(6):17-20.(LIU Dandan,LIU Jang,ZHANG Yujuan,et al.Research on the extracting buildings from the high spatial resolution images based on the objectoriented and multi-scale method[J].Geomatics&Spatial Information Technology,2016,39(6):17-20.)
    [20]程希萌,沈占锋,刑延炎,等.基于高分遥感影像的地震受灾建筑物提取与倒损情况快速评估[J].自然灾害学报,2016,25(3):22-31.(CHENG Ximeng,SHENZhanfeng,XING Yanyan,et al.Damaged building extraction and rapid assessment for earthquake disasters based on high-resolution remote sensing image[J].Journal of Nature Disasters,2016,25(3):22-31.)
    [21]陈行,卓莉,陶海燕.基于MMBI的高分辨率影像建筑物提取研究[J].遥感技术与应用,2016,31(5):930-938.(CHEN Hang,ZHUO Li,TAO Haiyan.Study on building extraction from high spatial resolution images using MMBI[J].Remote Sensing Technology and Application,2016,31(5):930-938.)
    [22]施文灶,毛政元.基于图像与阴影邻接关系的高分辨率遥感影像建筑物提取方法[J].电子学报,2016,44(12):2849-2854.(SHI Wenzao,MAO Zhengyuan.Building extraction from high resolution remotely sensed imagery based on shadows and graph-cut segmentation[J].Acta Electronica Sinica,2016,44(12):2849-2854.)
    [23]吕凤华,舒宁,龚龑,等.利用多特征进行航空影像建筑物提取[J].武汉大学学报(信息科学版),2017,42(5):656-660.(LYU Fenghua,SHU Ning,GONG Yan,et al.Regular building extraction from high resolution image based on multileve-features[J].Geomatics and Information Science of Wuhan University,2017,42(5):656-660.)
    [24]王旭东,段福州,屈新原,等.面向对象和SVM结合的无人机数据建筑物提取[J].国土资源遥感,2017,29(1):97-103.(WANG Xudong,DUAN Fuzhou,QU Xinyuan,et al.Building extraction based on UAV imagery data with the synergistic use of objected-based method and SVM classifier[J].Remote Sensing for Land and Resources,2017,29(1):97-103.)
    [25]高贤君,郑学东,刘子潇,等.基于偏移阴影分析的高分可见光影像建筑物全自动提取[J].光学学报,2017,37(4):0428002.(GAO Xianjun,ZHENG Xuedong,LIU Zixiao,et al.Automatic building extraction from very high resolution visible images on basis of shifted shadow analysis[J].Acta Optica Sinica,2017,37(4):307-316.)
    [26]VIJAY E P,NICOLAS H,ROGER L,et a1.An efficient pan-sharpening method via a combined adaptive CAapproach and contourlets[J].IEEE Transactions on Geoscience and Remote Sensing,2008,46(5):1323-1335.
    [27]丁辉.基于遥感技术滑坡灾害区划研究[D].西安:长安大学,2011.(DING Hui.Study on landslides geo-hazard zoning based on remote sensing[D].Xi’an:Chang’an University,2011.)
    [28]丁华,丁辉.遥感技术在滑坡灾害解译中的应用:以陕西省延安市子长县为例[J].自然灾害学报,2013,22(4):229-233.(DING Hua,DING Hui.Application of remote sensing technology to interpretation of landslides disaster:a case study of Zichang country,Shaanxi province[J].Journal of Natural Disasters,2013,22(4):229-233.)
    [29]QuickBird卫星(快鸟卫星)[EB/OL].[2017-05-22].http:∥www.kosmos-image.com/product/html/?99.html.
    [30]GROVES P,TIAN L F,BAJCSY P,et a1.Hyperspectral image data mining for band selection in agricultural applications[J].Transactions of the American Society of Agricultural Engineers,2004,47(3):895-907.
    [31]胡建忠,龚文峰,孙龙,等.砒砂岩地区土地利用与土地覆盖动态变化分析[J].林业科技情报,2010,42(4):32-34.(HU Jianzhong,GONG Wenfeng,SUN Long,et al.Land utilization and land coverage dynamic analysis in Arsenic sandstone area[J].Forestry Science and Technology Information,2010,42(4):32-34.)
    [32]赵春晖,陈万海,杨雷.高光谱遥感图像最优波段选择方法的研究进展与分析[J].黑龙江大学自然科学学报,2007,24(5):592-602.(ZHAO Chunhui,CHENWanhai,YANG Lei.Research advances and analysis of hyperspectral remote sensing band selection[J].Journal of natural science of Heilongjiang university,2007,24(5):592-602.)
    [33]许榕峰,徐涵秋.多步骤分类法在土地利用覆盖专题提取中的应用[J].福州大学学报,2003,31(4):408-412.(XU Rongfeng,XU Hanqiu.Application of multi-stage classification approach in the extraction of land use/land cover thematic information[J].Journal of Fuzhou University(Nature Science Edition),2003,31(4):408-412.)
    [34]汤国安,张友顺,刘咏梅,等.遥感数字图像处理[M]北京:科学出版社,2010.(TANG Guoan,ZHANGYoushun,LIU Yongmeia,et al.Remote sensing image processing[M].Peking:Science Press,2010.)
    [35]杨丽萍.基于遥感与DEM的“吉兰泰-河套”古大湖重建研究[D].兰州:兰州大学,2008.(YANG Liping.Reconstruction of paleo-megalake‘Jilantai-hetao’based on remote sensing and DEM[D].Lanzhou:Lanzhou University,2008.)
    [36]杨存建,刘纪远,黄河,等.热带森林植被生物量与遥感地学数据之间的相关性分析[J].地理研究,2005,24(3):473-479.(YANG Cunjian,LIU Jiyuan,HUANG He,et al.Correlation analysis of the biomass of the tropical forest vegetation,meteorogical data and topographical data[J].Geographical Research,2005,24(3):473-479.)
    [37]何晓宁,莫毅君,童俊涛.快鸟影像用于泥石流冲毁区自动提取[J].遥感信息,2015,30(5):77-82.(HE Xiaoning,MO Yijun,TONG Juntao.Application of Quickbird remote sensing imagery in automatic extraction of debris flow destroyed area[J].Remote Sensing Information,2015,30(5):77-82.)
    [38]贾永红.基于像元的遥感影像融合方法的比较[J].测绘信息与工程,1997(4):29-31.(JIA Yonghong.Comparison of image fusion methods base on pixel[J].Journal of Geomatics,1997(4):29-31.)
    [39]董广军,张永生,戴晨光.高分辨率遥感影像融合处理技术的对比分析研究[J].光学技术,2006,32(6):827-830.(DONG Guangjun,ZHANG Yongsheng,DAIChenguang.Comparison of fusion algorithms of high resolution imagery[J].Optical Technique,2006,32(6):827-830.)
    [40]何祺胜,塔西甫拉提·特依拜,丁建丽.主成分融合在干旱区盐渍地信息提取中的应用研究[J].土壤通报,2007,38(5):848-852.(HE Qisheng,TASHPOLATTiyip,DING Jianli.The application of principle component fusion in the extraction of saline soil information in arid area[J].Chinese Journal of Soil Science,2007,38(5):848-852.)
    [41]杨丽坤,付翔宇.多源遥感影像数据融合理论与技术[J].北京测绘,2014(3):101-104.(YANG Likun,FUXiangyu.The theory and techniques for data fusion of multi-sources remote sensing image.[J]Beijing Surveying and Mapping,2014(3):101-104.)
    [42]李艳芳,程新文,金彪,等.几种常见影像融合方法的比较[J].地理空间信息,2009,7(2):102-105.(LI Yanfang,CHENG Xinwen,JIN Biao,et al.Comparison of several common image fusion methods[J].Geospatial Information,2009,7(2):102-105.)
    [43]全雪贞.浅析SPOT5卫星数据在西部测图项目中融合及制作模拟真彩色的方法和应用[J].青海国土经略,2012(4):56-58.(QUAN Xuezhen.A survey on method and application of data fusion and making true color for SPOT5image in western survey and mapping project[J].Management&Strategy of Qinghai Land&Resources,2012(4):56-58.)
    [44]崔亚琴,骆有庆,宗世详.Quickbird遥感影像数据融合方法比较研究[C]∥2010年国际遥感会议论文集[出版地不详:出版者不详],2010.(CUI Yaqin,LUO Youqing,ZONG Shixiang.Comparison of image fusion algorithms for Quickbird image[C]∥Proceedings of2010International Conference on Remote Sensing.[S.l.:s.n.],2010.)
    [45]张庆河,邹峥嵘,余加勇.遥感影像像素级融合方法比较研究[J].测绘工程,2008,17(4):35-38,42.(ZHANG Qinghe,ZOU Zhengrong,YU Jiayong.Research on the pixel fusion method of remote sensing image[J].Engineering of Survey and Mapping,2008,17(4):35-38,42.)
    [46]胡平香,张鹰,王进华.基于主成分融合的盐田水体遥感分类研究[J].河海大学学报(自然科学版),2004,32(5):519-522.(HU Pingxiang,ZHANG Ying,WANG Jinhua.Principle component fusion-based classification of salt field water bodies with remote sensing technique[J].Journal of Hohai University(Natural Sciences),2004,32(5):519-522.)
    [47]党安荣,王晓栋,陈晓峰,等.遥感数字图像方法[M].北京:清华大学出版社,2009.(DANG Anrong,WANGXiaodong,CHEN Xiaofeng,et al.The method of remote sensing image processing[M].Beijing:Tsinghua University Press,2009.)
    [48]余坤勇,刘健,缪丽娟,等.基于地物特征的遥感图像融合效果[J].福建农林大学学报(自然科学版),2010,39(2):196-201.(YU Kunyong,LIU Jian,MIULijuan.Fusion effect of remote sensing image based on object feature[J].Journal of Fujian Agriculture and Forestry University(Natural Science Edition),2010,39(2):196-201.)
    [49]王力彦.多源光学遥感影像融合方法研究[D].北京:中国地质大学,2014.(WANG Liyan.Study on fusion methods of multisource optical remote sensing image[D].Beijing:China University of Geosciences,2014.)
    [50]邓磊,孙晨.ERDAS图像处理基础实验教程[M].北京:测绘出版社,2014.(DENG Lei,SUN Cheng.Guide to ERDAS image processing[M].Beijing:Surveying and Mapping Press,2014.)
    [51]王耀南,李树涛,毛建旭.计算机图像处理与识别技术[M].北京:高等教育出版社,2001.(WANG Yaonan,LI Shutao,MAO Jianxu.Computer image processing and identification technology[M].Beijing:Higher Education Press,2001.)
    [52]丁辉,张茂省,李林.基于多特征面向对象区域滑坡现象识别[J].遥感技术与应用,2013,28(6):1107-1113.(DINGHui,ZHANG Maosheng,LI Lin.Regional landslides identification based on Multi-feature object-oriented image classification[J].Remote Sensing Technology and Application,2013,28(6):1107-1113.)

© 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