一种高分辨率遥感影像阴影去除方法  

A Shadow Removal Method for High Resolution Remote Sensing Image

作　　者：杨俊[1] 赵忠明[2] 杨健[2] 

机构地区：[1]中国气象科学研究院雷电物理与防护工程实验室,北京市100081 [2]中国科学院遥感应用研究所,北京市100101

出　　处：《武汉大学学报（信息科学版）》2008年第1期17-20,共4页Geomatics and Information Science of Wuhan University

基　　金：国家863计划资助项目(2003AA135010);国家科技部科研院所技术开发研究专项基金资助项目

摘　　要：基于阴影属性提出了一种全自动彩色影像阴影去除算法。首先将影像变换到HSI空间,依据阴影区域亮度值低和饱和度高的特性,结合小区域去除和数学形态学处理,得到精确的阴影区域。然后,分别对I、H、S分量图上各个独立阴影区域与其邻近的非阴影区域进行匹配补偿,再反变换回RGB空间,完成阴影去除操作。实验结果表明,该方法能在不改变非阴影区域信息的情况下,有效地去除阴影的影响。The shadow on the high resolution remote sensing image influences the image quality badly. An automatic property-based approach is presented for shadow removal of color image. The RGB image is first transformed into HSI color space, according as shadow regions has lower luminance and higher saturation than non-shadowed regions, threshold detection and small regions removal and morphological algorithm are performed to get accurate shadow mask. Then the shadow regions are matched to their adjacent non-shadowed regions on I component, S component and H component respectively, and by inverse HSI transform to finish shadow removal. The experiment result shows that this method can remove the influence of shadow effectively and does not change the pixel value of non-shadowed regions.

关 键 词：HSI变换 阴影检测 阴影去除 

分 类 号：P237.3[天文地球—摄影测量与遥感] TP751[天文地球—测绘科学与技术]