一种基于HIS色彩空间的阴影检测和补偿算法
|
摘要
遥感影像,由于它的获取方便、快捷、信息量大而丰富,广泛应用于各个领域。随着科技的快速发展,我国的遥感技术水平也有大幅提升,而对所要应用的遥感影像的质量要求也越高。但是在成像过程中,受各种因素的限制和影响,影像形成后均会有不同程度的降质现象,阴影就是其中一种。因此,阴影检测是遥感影像重要的预处理工作。本文在对国内外不同的阴影检测算法的缺陷以及处理结果不理想等问题的研究基础上,改进了基于HIS色彩空间的阴影检测和补偿算法并通过MATLAB运行实验,实验表明本文方法增加了阴影区域的正检率,降低了非阴影区域的误检率,补偿之后阴影区域的细节保留的更为清晰,保持了非阴影区域的色彩信息,使得整幅影像的视觉效果更好,算法稳健性较好,检测过程自动化程度高,无需人工干预,可有效应用于城市建筑物阴影检测。
Remote sensing image is widely used in various fields because it is convenient,fast,and rich in information.With the rapid development of science and technology,the level of remote sensing technology in China has also been greatly improved,and the quality requirements for remote sensing images to be applied are also higher.However,in the imaging process,due to various factors and limitations,there will be different degrees of degradation after image formation,and shadow is one of them.Therefore,shadow detection is an important pre-processing work for remote sensing images.Based on the research on the defects of different shadow detection algorithms at home and abroad and the unsatisfactory processing results,the HIS color space based shadow detection and compensation algorithm is improved and the experiment is run by MATLAB.The experiment shows that the method increases the shadow.The positive detection rate of the area reduces the false detection rate of the non-shadow area.After the compensation,the details of the shadow area are kept more clearly,and the color information of the non-shadow area is maintained,so that the visual effect of the whole image is better and the algorithm is robust.Preferably,the detection process is highly automated and requires no manual intervention,and can be effectively applied to urban building shadow detection.
Remote sensing image is widely used in various fields because it is convenient,fast,and rich in information.With the rapid development of science and technology,the level of remote sensing technology in China has also been greatly improved,and the quality requirements for remote sensing images to be applied are also higher.However,in the imaging process,due to various factors and limitations,there will be different degrees of degradation after image formation,and shadow is one of them.Therefore,shadow detection is an important pre-processing work for remote sensing images.Based on the research on the defects of different shadow detection algorithms at home and abroad and the unsatisfactory processing results,the HIS color space based shadow detection and compensation algorithm is improved and the experiment is run by MATLAB.The experiment shows that the method increases the shadow.The positive detection rate of the area reduces the false detection rate of the non-shadow area.After the compensation,the details of the shadow area are kept more clearly,and the color information of the non-shadow area is maintained,so that the visual effect of the whole image is better and the algorithm is robust.Preferably,the detection process is highly automated and requires no manual intervention,and can be effectively applied to urban building shadow detection.
引文
[1]徐德政,唐新明,祝小勇,等.基于HIS色彩空间的资源三号影像阴影检测[J].测绘与空间地理信息,2017,40(1):56-58.
[2]杨俊,赵忠明,杨健.一种高分辨率遥感影像阴影去除方法[J].武汉大学学报(信息科学版),2008,33(1):17-20.
[3]徐秋红,叶勤.一种基于颜色恒常性理论的城市高分辨率遥感影像阴影消除方法[J].遥感信息,2010(4):13-16.
[4]ARVALO V,G ONZLEZ J,A MBROSIO G.Shadow Detection Incolour High Resolution Satellite Image[J].International Journal of Remote Sensing,2008,29(7):1945-1963.
[5]VICTOR J.D.Tsai.A Comparative Study on Shadow Compen-Sation of Color Aerial Images in Invariant Color Model[J].IEEE Transactions on Geoscience and Remote Sensing,2006,44(6):1661-1671.
[6]鲍海英,李艳,尹永宜.城市航空影像的阴影检测和阴影消除方法研究[J].遥感信息,2010(1):44-47.
[7]刘辉,杨晨晖,舒骁.一种基于边缘信息与HSV颜色空间相结合的阴影检测算法[J].现代计算机(专业版),2009(11):51-55.
[8]王理政,林祥国,宁晓刚.面向对象的高分辨率遥感影像阴影提取方法[J].测绘科学,2017,42(3):108-113.
[9]屈伟军.一种基于HIS色彩空间的阴影检测与补偿方法研究[EB/OL](2012-3-7)[2015-11-30].https://wenku.baidu.com/view/f18c9a7c1711cc7931b7169a.html.
[10]于东方.基于阴影的遥感图像中建筑物自动提取方法研究[D].湖南长沙:国防科学技术大学,2008.
[11]季顺平,袁修孝.一种基于阴影检测的建筑物变化检测方法[J].遥感学报,2007(3):323-329.
[12]闫琰,董秀兰,李燕.基于ENVI的遥感图像监督分类方法比较研究[J].北京测绘,2011(3):14-16.
[13]王树根,王军利,王爱萍.基于整体变分模型的影像阴影检测算法研究[J].武汉大学学报(信息科学版),2006,31(8):663-666.
[14]李艳,宫鹏.阴影检测图像分析[J].遥感学报,2005,4(9):357-360.
[15]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(9):132-137.
[16]王华,李艾华,崔智高,等.融合颜色和梯度直方图反投影的运动阴影检测[J].电光与控制,2017(4):8-11.
[17]王伟超,邹维宝.高分辨率遥感影像信息提取方法综述[J].北京测绘,2013(4):5-9.
[18]ADELINE K R M,CHEN M,BRIOTTET X,et al.Shadow de-in Very High Spatial Resolution Aerial Images:Acomparative Study[J].ISPRS Journal of Photogrammetryand Remote Sensing,2013(80):21-38.
[2]杨俊,赵忠明,杨健.一种高分辨率遥感影像阴影去除方法[J].武汉大学学报(信息科学版),2008,33(1):17-20.
[3]徐秋红,叶勤.一种基于颜色恒常性理论的城市高分辨率遥感影像阴影消除方法[J].遥感信息,2010(4):13-16.
[4]ARVALO V,G ONZLEZ J,A MBROSIO G.Shadow Detection Incolour High Resolution Satellite Image[J].International Journal of Remote Sensing,2008,29(7):1945-1963.
[5]VICTOR J.D.Tsai.A Comparative Study on Shadow Compen-Sation of Color Aerial Images in Invariant Color Model[J].IEEE Transactions on Geoscience and Remote Sensing,2006,44(6):1661-1671.
[6]鲍海英,李艳,尹永宜.城市航空影像的阴影检测和阴影消除方法研究[J].遥感信息,2010(1):44-47.
[7]刘辉,杨晨晖,舒骁.一种基于边缘信息与HSV颜色空间相结合的阴影检测算法[J].现代计算机(专业版),2009(11):51-55.
[8]王理政,林祥国,宁晓刚.面向对象的高分辨率遥感影像阴影提取方法[J].测绘科学,2017,42(3):108-113.
[9]屈伟军.一种基于HIS色彩空间的阴影检测与补偿方法研究[EB/OL](2012-3-7)[2015-11-30].https://wenku.baidu.com/view/f18c9a7c1711cc7931b7169a.html.
[10]于东方.基于阴影的遥感图像中建筑物自动提取方法研究[D].湖南长沙:国防科学技术大学,2008.
[11]季顺平,袁修孝.一种基于阴影检测的建筑物变化检测方法[J].遥感学报,2007(3):323-329.
[12]闫琰,董秀兰,李燕.基于ENVI的遥感图像监督分类方法比较研究[J].北京测绘,2011(3):14-16.
[13]王树根,王军利,王爱萍.基于整体变分模型的影像阴影检测算法研究[J].武汉大学学报(信息科学版),2006,31(8):663-666.
[14]李艳,宫鹏.阴影检测图像分析[J].遥感学报,2005,4(9):357-360.
[15]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(9):132-137.
[16]王华,李艾华,崔智高,等.融合颜色和梯度直方图反投影的运动阴影检测[J].电光与控制,2017(4):8-11.
[17]王伟超,邹维宝.高分辨率遥感影像信息提取方法综述[J].北京测绘,2013(4):5-9.
[18]ADELINE K R M,CHEN M,BRIOTTET X,et al.Shadow de-in Very High Spatial Resolution Aerial Images:Acomparative Study[J].ISPRS Journal of Photogrammetryand Remote Sensing,2013(80):21-38.