SAR图像稀疏优化滤波.pdfVIP

第 17 卷第11 期 中国图象图形学报 Vol. 17 , No. l1 2012 年 11 月 Journal of Image and Graphics Nov. , 2012 中图法分类号:TP75 1. 1 文献标识码:A 文章编号: 1∞6-8961(2012)11-1439-05 论文引用格式:杨萌.张弓 .SAR 图像稀疏优化滤波Ul 中国图象图形学报，2012 ， 17 (11) ; 1439-1443. SAR 图像稀疏优化滤波 杨萌，张弓 南京航空航天大学电子信息工程学院，南京 21∞16 摘 要:提出一种基于稀疏优化模型的 SAR 图像滤波算法。该算法建立在超完备字典稀疏表示基础上，具有较强 的数据稀疏性和稳健的建模假设。首先依据SAR 图像的结构特征，运用正则化方法建立多目标稀疏优化模型，然 后通过冗余字典稀疏优化变换系数，利用冗余字典以及具有点奇异性的小波和线奇异性的剪切波构造超完备字 典，最后通过对优化问题的求解，重建 SAR 图像场景分辨单元的平均强度，实现了 SAR 图像的滤波。实验结果表 明，该算法对 SAR 图像相干斑噪声具有很好的抑制效果，并且具有增强滤波图像纹理细节特征的优点。 关键词:滤波;合成孔径雷达图像;稀疏优化;小波;剪切波 SAR images filtering via sparse optimization Yang Meng , Zhang Gong College 01 Electronics Engineering , Nα， njing University 01Aeronauûcs and Astronautics , NanJÏng 21∞16 ， China Abstract: In this paper , a new method for filtering SAR images using sparse optimiz础ion model is proposed. The algo- rithm based on sparse representation via an over-complete dictionary h嗣 a strong data sparseness and provides solid model- ing assumptíons for the data sets. First , a sp町se optimization model based on structural properties of then SAR image is built by regulation. Second , a practical optimization strategy is used to design a redundancy dictionary. Then , an over- complete dictionary is constructed by employing a combined dictionarγconsisting of wavelets , shearlets , and a redundancy dictionary. Finally , the filtering process is realized through the solution of the rnulti-objective optimìzatìon problem in which the mean backscatter power is reconstructed.ηle experimental results demonstrate that 由e proposed