融合图像恢复的遥感数据变分分割方法研究  

Research on Variational Segmentation Method of Remote Sensing Data Combined with Image Restoration

作　　者：田佑仕 黄宝香 姜涛 李亚静 TIAN You-shi;HUANG Bao-xiang;JIANG Tao;LI Ya-jing(School of Computer Science,Qingdao University,Qingdao 266071,China;Navy Unit 91033, Qingdao 266034, China)

机构地区：[1]青岛大学计算机科学技术学院,青岛266071 [2]海军91033部队,青岛266034

出　　处：《青岛大学学报（自然科学版）》2020年第4期1-8,共8页Journal of Qingdao University(Natural Science Edition)

基　　金：国家自然科学基金(批准号:61602269)资助;中国博士后科学基金(批准号:2015M571993)资助;山东省自然科学基金面上项目(批准号:ZR2017MD004)资助。

摘　　要：由于合成孔径雷达(SAR)图像中存在大量的乘性斑点噪声,导致在使用现有的变分分割方法进行SAR图像分割时无法得到理想的结果。为此,设计了针对SAR图像斑点噪声的数据项,并将其引入到SAR图像分割中,提出了一种新的融合乘性噪声去除的SAR图像分割模型,然后采用交替方向乘子法(ADMM)对其进行了有效地求解。在多幅合成图像和真实SAR图像上开展的实验表明,该方法具有良好的抗噪性,能够获得更准确的分割结果。Due to the large amount of multiplicative speckle noise in synthetic aperture radar(SAR)images,it is impossible to obtain ideal results when using existing variational segmentation methods for SAR image segmentation.For this reason,a data item for speckle noise in SAR image was designed and introduced into SAR image segmentation,a new SAR image segmentation model combined with multiplicative noise removal is proposed,and then the alternating direction multiplier method(ADMM)is used to effectively solve it.Finally,experiments carried out on multiple synthetic images and real SAR images show that the method proposed in this paper has good noise resistance and can obtain more accurate segmentation results.

关 键 词：SAR图像分割 乘性斑点噪声 变分水平集方法 GAMMA分布 ADMM方法 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]