基于融合边缘检测的SAR图像线性特征提取算法  

Linear Feature Extraction for SAR Image Based on Fused Edge Detector

作　　者：安成锦[1] 杜琳琳[1] 王卫华[1] 陈曾平[1] 

机构地区：[1]国防科技大学ATR重点实验室,长沙410073

出　　处：《电子与信息学报》2009年第6期1279-1282,共4页Journal of Electronics & Information Technology

基　　金：新世纪优秀人才支持计划项目(NCET-06-0921)资助课题

摘　　要：该文基于合成孔径雷达(SAR)图像低信噪比的特点,设计了一种基于融合边缘检测的线性特征提取算法。首先采用融合Canny算子及ROA算子得到边缘点,然后利用Radon变换得出线基元,最后根据启发式连接的思想连接了由于噪声引起的直线断裂。实测SAR图像的实验结果表明,该文提出的线性特征提取方法能够准确描述SAR图像的线性结构,可应用于自动目标识别和景象匹配等方面。A linear feature extraction algorithm for Synthetic Aperture Radar （SAR） image is proposed, which is based on the low signal-to-noise quality of SAR image. Firstly, a new edge detector, which fuses the Canny operator and Ratio Of Average （ROA） operator, is used to get the edge points. Then, radon transform is carried out to get the primitive line segments. Finally, the broken lines due to speckle noise are connected by means of the heuristic link idea. The experiment results which are based on the SAR images show, the proposed algorithm can describe the linear characteristic of SAR images precisely, and it can be used for SAR auto target recognition and scene matching.

关 键 词：合成孔径雷达 相干斑噪声 边缘检测 线基元提取 启发式连接 

分 类 号：TP753[自动化与计算机技术—检测技术与自动化装置]