集成特征分量的阴影多尺度分割方法
|
摘要
针对高分影像阴影检测精度易受水体、深色地物和暗色植被影响等问题,结合GF-1影像自身特点,提出一种结合特征分量构建和多尺度分割面向对象的阴影检测方法。首先,对GF-1影像多光谱数据、全色数据进行正射校正和信息融合,以达到光谱与空间分辨率信息最大化利用。其次,集成特征分量(主成分第一分量PC1、亮度分量V、绿光波段G、归一化植被指数NDVI)以增强阴影信息。最后,对集成后的影像进行多尺度分割,并利用特征分量构建规则集,最终实现阴影信息提取。实验表明,该方法既能准确地检测出GF-1影像中的阴影信息,又能有效削弱水体、深色地物和暗色植被的影响。
Shadow detection accuracy is likely to be influenced by water bodies,dark features and dark vegetation on highresolution remote sensing images.This paper proposes a new shadow detection method.Firstly,use multi-spectral image and panchromatic data to perform data correction and information fusion,in order to use spectral resolution and information maximumly.Next,protrude shadow information and increase the differences of the shadow and other features.Then,establish characteristic calculation PC1,V,G and NDVI,and use characteristic calculation to restructure band.Finally,make new image multi-scale segmentation and use the features to build rule set to realize shadow information extraction.The result indicates that this method can not only has high detection accuracy and efficiency for GF-1 images,but can also weaken the influences of water bodies,dark features and dark vegetation.
Shadow detection accuracy is likely to be influenced by water bodies,dark features and dark vegetation on highresolution remote sensing images.This paper proposes a new shadow detection method.Firstly,use multi-spectral image and panchromatic data to perform data correction and information fusion,in order to use spectral resolution and information maximumly.Next,protrude shadow information and increase the differences of the shadow and other features.Then,establish characteristic calculation PC1,V,G and NDVI,and use characteristic calculation to restructure band.Finally,make new image multi-scale segmentation and use the features to build rule set to realize shadow information extraction.The result indicates that this method can not only has high detection accuracy and efficiency for GF-1 images,but can also weaken the influences of water bodies,dark features and dark vegetation.
引文
[1]NAKAJIMA T,TAO G,YASOUKA Y.Simulated recovery of information in shadow areas on IKONOS image by combing ALS data[C].Proceeding of Asian Conference on Remote Sensing(ACRS),2002.
[2]郭海涛,徐青,张保明.多重约束卜的建筑物阴影提取[J].武汉大学学报:信息科学版,2005,30(12):1059-1062.
[3]TSAI V J D.A Comparative study on shadow compensation of color aerial images in invariant color models[J].IEEE Transactions on Ueoscience and Remote Sensing,2006,44(6):1661-1671.
[4]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.
[5]杨兴旺,杨树文,张黎明,等.高分辨率遥感影像阴影检测与补偿系统的设计与实现[J].国土资源遥感,2015,27(3):177-181.
[6]LEONE A,DISTANCE C,ANCONA N,et al.Texture analysis for shadow removing in video-surveillance systems[C].Systems,Man and Cybernetics,2004IEEE International Conference on IEEE,2004.
[7]SARABANDI P,YAMAZAKI F,MATSUOKA M,et al.Shadow detection and radiometric restoration in satellite high resolution images[C].IGARSS,2004.
[8]SUZUKI A,SHIO A,ARAI H,et al.Dynamic shadow compensation of aerial images based on color and spatial analysis[C].Pattern Recognition,2000.Proceedings.15th International Conference on.IEEE,2000.
[9]掳建宏,田庆久.一种IKONOS影像阴影检测与去除的方法[J].遥感信息,2005,20(4):32-34.
[10]王玥,王树根.高分辨率遥感影像阴影检测与补偿的主成分分析方法[J].应用科学学报,2010,28(2):136-141.
[11]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.
[12]姚花琴,杨树文,刘正军,等.基于QuickBird影像的城市高大地物阴影检测方法[J].国土资源遥感,2015,27(2):51-55.
[13]蒲智,杨辽,白洁.基于而向对象技术的高分辨率遥感影像的阴影检测与去除[J].遥感技术与应用,2008,23(6):735-737.
[14]LIU W,YAMAZAKI F.Object-based shadow extraction and correction of high-resolution optical satellite images[J].IEEE Journal of Applied Earth Observations and Remote Sensing,2012,5(4):1296-1302.
[15]帅滔,张洪艳,张良培.面向对象的高分辨遥感影像阴影探测方法[J].光子学报,2015,44(12):1-8.
[16]杨树文,董玉森,罗小波,等.遥感数字图像处理与分析-ENVI5.X实验教程[M].三河:电子工业出版社,2015.
[17]袁秀华,罗卫,王聪颖.赣州稀土矿山高分辨率遥感影像分割的最优尺度选取[J].测绘与空间地理信息,2013,36(9):48-50.
[2]郭海涛,徐青,张保明.多重约束卜的建筑物阴影提取[J].武汉大学学报:信息科学版,2005,30(12):1059-1062.
[3]TSAI V J D.A Comparative study on shadow compensation of color aerial images in invariant color models[J].IEEE Transactions on Ueoscience and Remote Sensing,2006,44(6):1661-1671.
[4]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.
[5]杨兴旺,杨树文,张黎明,等.高分辨率遥感影像阴影检测与补偿系统的设计与实现[J].国土资源遥感,2015,27(3):177-181.
[6]LEONE A,DISTANCE C,ANCONA N,et al.Texture analysis for shadow removing in video-surveillance systems[C].Systems,Man and Cybernetics,2004IEEE International Conference on IEEE,2004.
[7]SARABANDI P,YAMAZAKI F,MATSUOKA M,et al.Shadow detection and radiometric restoration in satellite high resolution images[C].IGARSS,2004.
[8]SUZUKI A,SHIO A,ARAI H,et al.Dynamic shadow compensation of aerial images based on color and spatial analysis[C].Pattern Recognition,2000.Proceedings.15th International Conference on.IEEE,2000.
[9]掳建宏,田庆久.一种IKONOS影像阴影检测与去除的方法[J].遥感信息,2005,20(4):32-34.
[10]王玥,王树根.高分辨率遥感影像阴影检测与补偿的主成分分析方法[J].应用科学学报,2010,28(2):136-141.
[11]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.
[12]姚花琴,杨树文,刘正军,等.基于QuickBird影像的城市高大地物阴影检测方法[J].国土资源遥感,2015,27(2):51-55.
[13]蒲智,杨辽,白洁.基于而向对象技术的高分辨率遥感影像的阴影检测与去除[J].遥感技术与应用,2008,23(6):735-737.
[14]LIU W,YAMAZAKI F.Object-based shadow extraction and correction of high-resolution optical satellite images[J].IEEE Journal of Applied Earth Observations and Remote Sensing,2012,5(4):1296-1302.
[15]帅滔,张洪艳,张良培.面向对象的高分辨遥感影像阴影探测方法[J].光子学报,2015,44(12):1-8.
[16]杨树文,董玉森,罗小波,等.遥感数字图像处理与分析-ENVI5.X实验教程[M].三河:电子工业出版社,2015.
[17]袁秀华,罗卫,王聪颖.赣州稀土矿山高分辨率遥感影像分割的最优尺度选取[J].测绘与空间地理信息,2013,36(9):48-50.