基于空间分割的影像条带噪声去除方法  

Remove of Random Strip Noise Based on Image Segmentation

作　　者：林宏宇[1] 关晨辉 张炳先[1,2] 赵兴成 LIN Hongyu;GUAN Chenhui;ZHANG Bingxian;ZHAO Xingcheng(Beijing Institute of Space Mechanics&Electricity,Beijing 100094,China;Key Laboratory for Advanced Optical Remote Sensing Technology of Beijing,Beijing 100094,China)

机构地区：[1]北京空间机电研究所,北京100094 [2]先进光学遥感技术北京市重点实验室,北京100094

出　　处：《航天返回与遥感》2023年第2期109-117,共9页Spacecraft Recovery & Remote Sensing

摘　　要：光学遥感卫星影像中包含系统条带噪声和随机条带噪声,由于多种因素的干扰,即使进行系统条带噪声去除后,仍残留部分随机条带噪声。文章通过分析现有卫星遥感影像中的随机条带噪声特性,基于常规的随机条带噪声去除方法,提出一种新的基于空间分割的条带噪声去除算法。该方法以影像的均值、中值以及梯度值构建判定准则,将影像分为动态范围变化较小的多个区域,同时将地物边缘单独提取出来予以保留;然后采用标准矩匹配的方法对单独区域进行处理,在剔除噪声的同时抑制灰度畸变的产生;最后采用中巴地球资源卫星04星(CBERS-04)数据作为试验对象进行了随机噪声去除试验,试验结果表明新方法在去除随机条带噪声的同时很好的保持了原始影像的纹理信息。Optical satellite images contain two types of striping noise,one is system striping noise,the other is random striping noise,that is,due to the interference of various factors.After the systematic stripe noise removal,the random stripe noise still remains in the image.The paper analysed the characteristics of stripe noise and proposed a new destriping method based on image segmentation,divided images into many parts based on the mean value,median value and gradient value and extract edge information during the process above,and then standard moment matching method can be used to eliminate the noise in each part respectively.Finally CBERS-04 images were used to verify the performance of our proposed method,and the results show that our proposed method basically maintains the texture information of original image,and play a better performance.

关 键 词：遥感成像 随机条带噪声 影像分割 标准矩匹配 噪声去除 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]