| 一种SAR图像空间域自适应滤波算法 |
| |
| 引用本文： | 张绍明,林怡,邱振戈,陈映鹰.一种SAR图像空间域自适应滤波算法[J].同济大学学报(自然科学版),2010,38(5):758-761. |
| |
| 作者姓名： | 张绍明 林怡 邱振戈 陈映鹰 |
| |
| 作者单位： | 1. 同济大学遥感与空间信息技术研究中心,上海,200092
2. 中国测绘科学研究院,北京,100854 |
| |
| 基金项目： | 国家高技术研究发展计划资助项目(863) |
| |
| 摘 要： | 针对合成孔径雷达(SAR)图像相干斑噪声抑制问题,提出了一种基于支持向量回归(SVR)分析的空间域自适应滤波方法.将SAR图像看作连续二维函数,利用SVR方法对其进行逼近.基于图像的逼近结果描述像素关联性,并基于关联性破坏程度对噪声进行类型分析,对不同类型的噪声采取确定性的抑制算法.为了保证精度,选择小波核函数构建支持向量回归机.实验结果表明该方法是有效的并对经典方法进行了改进.
|
| 关 键 词： | 合成孔径雷达 自适应滤波 支持向量回归 小波核函数 |
| 收稿时间： | 3/19/2009 3:47:12 PM |
| 修稿时间： | 3/29/2010 6:27:10 PM |
A SAR Speckle Adaptive Filtering Algorithm in Spatial Domain |
| |
| Zhang Shaoming,Lin Yi,QiuZhenge and Chen Yingying.A SAR Speckle Adaptive Filtering Algorithm in Spatial Domain[J].Journal of Tongji University(Natural Science),2010,38(5):758-761. |
| |
| Authors: | Zhang Shaoming Lin Yi QiuZhenge and Chen Yingying |
| |
| Institution: | Tongji University,Tongji University,Chinese Academy of Surveying and Mapping,Tongji University |
| |
| Abstract: | To suppress the speckle in Synthetic Aperture Radar (SAR) images, a novel adaptive algorithm based on SVR is proposed in this paper. A SAR image is regarded as a 2-D continuous function and is approximated by support vector regression (SVR). The result of regression is used to describe the relationship between pixels and the one in its neighborhood. Based on the relationship, the noise was classified to different kinds and suppressed. In the procedure of regression, the wavelet kernel function is used to improve the accuracy. The result of experiments show that this method is effective. |
| |
| Keywords: | |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《同济大学学报(自然科学版)》浏览原始摘要信息 |
| 点击此处可从《同济大学学报(自然科学版)》下载免费的PDF全文 |
|
