高分二号卫星影像中城市建筑物阴影检测方法
|
摘要
针对阴影在检测过程中易与水体、深蓝色地物、深灰色道路混淆的问题,对高分二号卫星(GF-2)影像中的典型地物纹理和光谱信息进行统计分析,提出一种基于多尺度分割和随机森林分类的阴影提取算法。通过选取样本数据的阴影指数、亮度、逆差矩、熵、对比度等12个对象特征构建随机森林分类模型,精确提取阴影区域。实验结果显示,本文所提阴影提取算法可以有效地对阴影进行识别,对2个研究区的提取精度分别达到了95.26%和94.35%,可有效解决单一特征下阴影不易与其他地物区分以及阈值分割过程中阈值不易确定的问题。
In order to solve the problem of easily confusing with water,dark blue objects and dark grey roads in the process of shadow detection,the texture and spectral information of typical objects in high resolution satellite images(GF-2)were analyzed,and a shadow extraction algorithm based on multi-scale segmentation and random forest classification was proposed.The random forest classification model was constructed by selecting 12 object features of sample data,such as shadow index,brightness,deficit moment,entropy and contrast,to extract the shadow area accurately.The experimental results show that the proposed shadow extraction algorithm can effectively recognize the shadows.And the extraction precision of the two research areas reaches 95.26% and 94.35%,respectively.It can effectively solve the problem that the shadows are not easy to distinguish from other objects under a single feature and the threshold is not easy to determine in the process of threshold segmentation.
In order to solve the problem of easily confusing with water,dark blue objects and dark grey roads in the process of shadow detection,the texture and spectral information of typical objects in high resolution satellite images(GF-2)were analyzed,and a shadow extraction algorithm based on multi-scale segmentation and random forest classification was proposed.The random forest classification model was constructed by selecting 12 object features of sample data,such as shadow index,brightness,deficit moment,entropy and contrast,to extract the shadow area accurately.The experimental results show that the proposed shadow extraction algorithm can effectively recognize the shadows.And the extraction precision of the two research areas reaches 95.26% and 94.35%,respectively.It can effectively solve the problem that the shadows are not easy to distinguish from other objects under a single feature and the threshold is not easy to determine in the process of threshold segmentation.
引文
[1]葛乐．遥感影像高大建筑物阴影检测与去除算法研究[D]．长春：中国科学院长春光学精密机械与物理研究所,2018.GE Yue.Shadow detection and removal of tall buildings in remote sensing images[D].Changchun:Changchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Sciences,2018.(in Chinese)
[2]姚花琴,杨树文,刘正军,等．一种城市高大地物阴影检测方法[J]．测绘科学,2015,40(10):110-113.YAO Huaqin,YANG Shuwen,LIU Zhengjun,et al.Shadow detection method of city large objects based on WorldView-2image[J].Science of Surveying and Mapping,2015,40(10):110-113.(in Chinese)
[3]杨兴旺,杨树文,刘正军,等．资源三号影像中城市高大地物阴影检测方法[J]．测绘科学,2015,40(9):98-101.YANG Xingwang,YANG Shuwen,LIU Zhengjun,et al.Shadow detection for urban tall standing objects based on ZY-3satellite imagery[J].Science of Surveying and Mapping,2015,40(9):98-101.(in Chinese)
[4]赵显富,胡晓雯,赵轩．一种基于彩色模型的遥感影像阴影检测方法[J]．测绘通报,2014(5):20-22.ZHAO Xianfu,HU Xiaowen,ZHAO Xuan.A method of remote sensing images shadow detection based on color models[J].Bulletin of Surveying and Mapping,2014(5):20-22.(in Chinese)
[5]罗艳,辛俊伟,何海清．Worldview-Ⅱ遥感影像的阴影检测方法研究[J]．测绘科学,2017,42(9):132-137.LUO Yan,XIN Junwei,HE Haiqing,et al.Research on shadow detection method of Worldview-Ⅱremote sensing image[J].Science of Surveying and Mapping,2017,42(9):132-137.(in Chinese)
[6]胡蕾,侯鹏洋．一种基于光谱与纹理特征的多光谱遥感图像地物分类方法[J]．中国科技论文,2015,10(2):197-200.HU Lei,HOU Pengyang.A method of multispectral remote sensing imagery classification based on spectral and texture feature[J].China Sciencepapers,2015,10(02):197-200.(in Chinese)
[7]余孟泽,刘正熙,骆键,等．融合纹理特征和阴影属性的阴影检测方法[J]．计算机工程与设计,2011,32(10):3431-3434.YU Mengze,LIU Zhengxi,LUO Jian,et al.Moving cast shadow detection based on texture and shadow property[J].Computer Engineering and Design,2011,32(10):3431-3434.(in Chinese)
[8]夏怀英,郭平．基于统计混合模型的遥感影像阴影检测[J]．遥感学报,2011,15(4):778-791.XIA Huaiying,GUO Ping.A shadow detection of remote sensing images based on statistical texture features[J].Journal of Remote Sensing,2011,15(4):778-791.(in Chinese)
[9]郝虑远．基于纹理分析的高分辨率影像面向对象分类研究[D]．北京：北京师范大学,2014.HAO Lüyuan.Object-oriented classification of high resolution image based on texture analysis[D].Beijing:Beijing Normal University,2014.(in Chinese)
[10]段光耀,宫辉力,李小娟,等．结合特征分量构建和面向对象方法提取高分辨率卫星影像阴影[J]．遥感学报,2014,18(4):760-770.DUAN Guangyao,GONG Huili,LI Xiaojuan,et al.Shadow extraction based on characteristic components and obgect-oriented method for high-resolution images[J].Journal of Remote Sensing,2014,18(4):760-770.(in Chinese)
[11]杨猛,杨树文,雍万铃,等．集成特征分量的阴影多尺度分割方法[J]．遥感信息,2017,32(1):109-114.YANG Meng,YANG Shuwen,YONG Wanling,et al.Multi-scale shadow segmentation method based on characteristic component[J].Remote Sensing Information,2017,32(1):109-114.(in Chinese)
[12]SALVADOR E,CAVALLARO A,EBRAHIMI T.Shadow identification and classification using invariant color models[C]∥Acoustics,Speech,and Signal Processing,2001on IEEE International Conference.New York:IEEE Computer Society,2001:1545-1548．
[13]高程程,惠晓威．基于灰度共生矩阵的纹理特征提取[J]．计算机系统应用,2010,19(6):195-198.GAO Chengcheng,HUI Xiaowei.GLCM-based texture feature extraction[J].Computer Systems&Applications,2010,19(6):195-198.(in Chinese)
[14]吴樊,王超,张红．基于纹理特征的高分辨率SAR影像居民区提取[J]．遥感技术与应用,2005,20(1):148-152.WU Fan,WANG Chao,ZHANG Hong.Resident region extraction in high resolution SAR image based on texture features[J].Remote Sensing Technology and Application,2005,20(1):148-152.(in Chinese)
[15]陈美龙,戴声奎．基于GLCM算法的图像纹理特征分析[J]．通信技术,2012,45(2):108-111.CHEN Meilong,DAI Shengkui.Analysis on image texture based on gray-level co-occurrence matrix[J].Communications Technology,2012,45(2):108-111.(in Chinese)
[16]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.BO Hua,MA Fulong,JIAO Licheng.Research on computation of GLCM of image texture[J].Acta Electronica Sinica,2006,34(1):155-158.(in Chinese)
[17]王彩艳,王瑷玲,王介勇,等．基于面向对象的北京市区城市内部用地信息提取[J]．自然资源学报,2015,30(4):705-714.WANG Caiyan,WANG Ailing,WANG Jieyong,et al.Land use information extraction in the inner city of Beijing based on object-oriented classification method[J].Journal of Natural Resources,2015,30(4):705-714.(in Chinese)
[18]郭玉宝,池天河,彭玲,等．利用随机森林的高分一号遥感数据进行城市用地分类[J]．测绘通报,2016(5):73-76.GUO Yubao,CHI Tianhe,PENG Ling,et al.Classification of GF-1remote sensing image based on random forests for urban landuse[J].Bulletin of Surveying and Mapping,2016(5):73-76.(in Chinese)
[2]姚花琴,杨树文,刘正军,等．一种城市高大地物阴影检测方法[J]．测绘科学,2015,40(10):110-113.YAO Huaqin,YANG Shuwen,LIU Zhengjun,et al.Shadow detection method of city large objects based on WorldView-2image[J].Science of Surveying and Mapping,2015,40(10):110-113.(in Chinese)
[3]杨兴旺,杨树文,刘正军,等．资源三号影像中城市高大地物阴影检测方法[J]．测绘科学,2015,40(9):98-101.YANG Xingwang,YANG Shuwen,LIU Zhengjun,et al.Shadow detection for urban tall standing objects based on ZY-3satellite imagery[J].Science of Surveying and Mapping,2015,40(9):98-101.(in Chinese)
[4]赵显富,胡晓雯,赵轩．一种基于彩色模型的遥感影像阴影检测方法[J]．测绘通报,2014(5):20-22.ZHAO Xianfu,HU Xiaowen,ZHAO Xuan.A method of remote sensing images shadow detection based on color models[J].Bulletin of Surveying and Mapping,2014(5):20-22.(in Chinese)
[5]罗艳,辛俊伟,何海清．Worldview-Ⅱ遥感影像的阴影检测方法研究[J]．测绘科学,2017,42(9):132-137.LUO Yan,XIN Junwei,HE Haiqing,et al.Research on shadow detection method of Worldview-Ⅱremote sensing image[J].Science of Surveying and Mapping,2017,42(9):132-137.(in Chinese)
[6]胡蕾,侯鹏洋．一种基于光谱与纹理特征的多光谱遥感图像地物分类方法[J]．中国科技论文,2015,10(2):197-200.HU Lei,HOU Pengyang.A method of multispectral remote sensing imagery classification based on spectral and texture feature[J].China Sciencepapers,2015,10(02):197-200.(in Chinese)
[7]余孟泽,刘正熙,骆键,等．融合纹理特征和阴影属性的阴影检测方法[J]．计算机工程与设计,2011,32(10):3431-3434.YU Mengze,LIU Zhengxi,LUO Jian,et al.Moving cast shadow detection based on texture and shadow property[J].Computer Engineering and Design,2011,32(10):3431-3434.(in Chinese)
[8]夏怀英,郭平．基于统计混合模型的遥感影像阴影检测[J]．遥感学报,2011,15(4):778-791.XIA Huaiying,GUO Ping.A shadow detection of remote sensing images based on statistical texture features[J].Journal of Remote Sensing,2011,15(4):778-791.(in Chinese)
[9]郝虑远．基于纹理分析的高分辨率影像面向对象分类研究[D]．北京：北京师范大学,2014.HAO Lüyuan.Object-oriented classification of high resolution image based on texture analysis[D].Beijing:Beijing Normal University,2014.(in Chinese)
[10]段光耀,宫辉力,李小娟,等．结合特征分量构建和面向对象方法提取高分辨率卫星影像阴影[J]．遥感学报,2014,18(4):760-770.DUAN Guangyao,GONG Huili,LI Xiaojuan,et al.Shadow extraction based on characteristic components and obgect-oriented method for high-resolution images[J].Journal of Remote Sensing,2014,18(4):760-770.(in Chinese)
[11]杨猛,杨树文,雍万铃,等．集成特征分量的阴影多尺度分割方法[J]．遥感信息,2017,32(1):109-114.YANG Meng,YANG Shuwen,YONG Wanling,et al.Multi-scale shadow segmentation method based on characteristic component[J].Remote Sensing Information,2017,32(1):109-114.(in Chinese)
[12]SALVADOR E,CAVALLARO A,EBRAHIMI T.Shadow identification and classification using invariant color models[C]∥Acoustics,Speech,and Signal Processing,2001on IEEE International Conference.New York:IEEE Computer Society,2001:1545-1548．
[13]高程程,惠晓威．基于灰度共生矩阵的纹理特征提取[J]．计算机系统应用,2010,19(6):195-198.GAO Chengcheng,HUI Xiaowei.GLCM-based texture feature extraction[J].Computer Systems&Applications,2010,19(6):195-198.(in Chinese)
[14]吴樊,王超,张红．基于纹理特征的高分辨率SAR影像居民区提取[J]．遥感技术与应用,2005,20(1):148-152.WU Fan,WANG Chao,ZHANG Hong.Resident region extraction in high resolution SAR image based on texture features[J].Remote Sensing Technology and Application,2005,20(1):148-152.(in Chinese)
[15]陈美龙,戴声奎．基于GLCM算法的图像纹理特征分析[J]．通信技术,2012,45(2):108-111.CHEN Meilong,DAI Shengkui.Analysis on image texture based on gray-level co-occurrence matrix[J].Communications Technology,2012,45(2):108-111.(in Chinese)
[16]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.BO Hua,MA Fulong,JIAO Licheng.Research on computation of GLCM of image texture[J].Acta Electronica Sinica,2006,34(1):155-158.(in Chinese)
[17]王彩艳,王瑷玲,王介勇,等．基于面向对象的北京市区城市内部用地信息提取[J]．自然资源学报,2015,30(4):705-714.WANG Caiyan,WANG Ailing,WANG Jieyong,et al.Land use information extraction in the inner city of Beijing based on object-oriented classification method[J].Journal of Natural Resources,2015,30(4):705-714.(in Chinese)
[18]郭玉宝,池天河,彭玲,等．利用随机森林的高分一号遥感数据进行城市用地分类[J]．测绘通报,2016(5):73-76.GUO Yubao,CHI Tianhe,PENG Ling,et al.Classification of GF-1remote sensing image based on random forests for urban landuse[J].Bulletin of Surveying and Mapping,2016(5):73-76.(in Chinese)