基于边缘特征的SAR图像目标检测方法

如何快速而准确地检测出SAR图像中的目标是一个极富挑战性的课题.利用图像边缘特征和模糊集理论设计了一种快速有效的SAR图像目标检测算法.该算法先利用模糊软阈值小波降噪方法去除相干斑噪声,然后用模糊边缘检测器检测出降噪图像的边缘,最后利用形态学操作算子提取出边缘图中的目标区域.与基于亮度特征以及基于纹理特征的检测算法相比,提出的检测算法能够快速、准确地检测出目标,而且产生的虚警数量较少.SAR实测数据的实验结果表明,提出的算法是有效的且具有很好的应用前景.

Target Detection Algorithm for SAR Image Using Edge Feature

How to fast and accurately detect the interesting targets in synthetic aperture radar（SAR）images is a challenging task.In this paper,a novel edge feature-based detection algorithm is proposed based on fuzzy set theory.The algorithm first uses the wavelet-based fuzzy soft-thresholding denoising technique to suppress the speckle,and then,detects edges in the denoised image using a fuzzy edge detector.At last,the morphological operators is utilized to extract the targets in the edge image.In contrast with the contrastbased and fractal feature-based detection algorithms,the proposed algorithm can fast and accurately detect the real targets and simultaneously yield few false alarms,which was verified by experiments with real SAR data.