| 基于模糊和最小二乘的SAR图像线特征提取 |
| |
| 引用本文： | 王艳丽,陈哲.基于模糊和最小二乘的SAR图像线特征提取[J].北京航空航天大学学报,2003,29(4):342-345. |
| |
| 作者姓名： | 王艳丽 陈哲 |
| |
| 作者单位： | 北京航空航天大学 自动化科学与电气工程学院 |
| |
| 基金项目： | 航空基础科学基金;99E51018; |
| |
| 摘 要： | 针对合成孔径雷达(SAR, Synthetic Aperture Radar)图像的特点,提出一种线特征提取算法.该算法首先抑制相干斑噪声,然后对SAR图像进行模糊变换和增强,再基于假设的SAR图像灰度模型,用最小二乘法设计出低通和高通滤波器,最后检测出线特征散点,并进行连接,得到SAR图像的线特征图.实验证明本算法抗噪声干扰,边缘定位精度达到1个像素.
|
| 关 键 词： | 合成孔径雷达 特征抽取 最小二乘法 线特征 模糊增强 |
| 文章编号： | 1001-5965(2003)04-0342-04 |
| 收稿时间： | 2002-01-16 |
| 修稿时间： | 2002年1月16日 |
Extraction of Linear Features of SAR Images Based on Fuzzy and Least Square |
| |
| Wang Yanli,Chen Zhe.Extraction of Linear Features of SAR Images Based on Fuzzy and Least Square[J].Journal of Beijing University of Aeronautics and Astronautics,2003,29(4):342-345. |
| |
| Authors: | Wang Yanli Chen Zhe |
| |
| Institution: | School of Automation Science and Electrical Engineering, Beijing University of Aeronautics and Astronautics |
| |
| Abstract: | A linear feature extraction method is proposed for SAR image. Firstly, the speckle noise in the radar image is filtered out. Secondly, the SAR image is processed by fuzzy transition and enhancement. Then, the low-pass and high-pass filters are designed by the least squares methods and the gradient strength map and direction map are acquired. Lastly, the gradient profile maximum method is adopted to detect feature points, which are connected to form the linear feature map of the SAR image. Simulation results show that the proposed method has the characteristic of anti-noise, the precision of positioning can reach 1 pixel. |
| |
| Keywords: | synthetic aperture radar feature extraction least squares methods linear feature fuzzy enhancement |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《北京航空航天大学学报》浏览原始摘要信息 |
| 点击此处可从《北京航空航天大学学报》下载免费的PDF全文 |
