基于支持向量机的遥感影像薄云去除方法  

Thin cloud removing approach of remote sensing image based on support vector machine

作　　者：孔颉[1,2] 胡根生[1,2] 梁栋[1,2] 

机构地区：[1]安徽大学计算智能与信号处理教育部重点实验室,安徽合肥230039 [2]安徽大学电子科学与技术学院,安徽合肥230039

出　　处：《计算机工程与设计》2011年第2期599-602,共4页Computer Engineering and Design

基　　金：国家自然科学基金项目(60772121);安徽省自然科学基金项目(070412065);安徽省教育厅重点科研计划基金项目(KJ2010A021)

摘　　要：提出了一种基于支持向量机的遥感影像薄云去除方法。利用支持向量机对边缘点的极强捕捉能力,将含云遥感影像进行多尺度分解,获得不同尺度上的变换系数,再结合方向滤波器组得到丰富的高频信息。采用自适应阈值的图像增强方法处理这片区域,重构时通过对高频区域的增强和低频区域的抑制,得到去云图像。实验结果表明,采用该方法能有效地去除遥感影像中的薄云。A new thin cloud removing approach of remote sensing image based on support vector machine is introduced. Firstly, remote sensing image is decomposed in multi-scale by using strong edge capture ability of support vector machine, and the coefficients in different scales are obtained. Then abundant high frequency information is obtained by combining with directional filter bank. The high frequency information is enhanced based on adaptive threshold. Reconstructed image is obtained through enhancing coefficients of high frequency and suppressing coefficients of low frequency. Experiments show that thin cloud is removed efficiently based on the method.

关 键 词：遥感影像 支持向量机 方向滤波器组 图像增强 薄云去除 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]