针对常规Radon变换域中尾迹峰值检测的不确定性问题,提出了一种基于特征空间决策的尾迹检测算法.该算法首先门限化图像的Radon变换系数,提取出所有可能的峰值点;然后对这些相应的局部峰值的"截面"进行连续小波变换峰值匹配,再根据提取到的参数形成决策矢量在特征空间中进行决策.对仿真和实际数据处理的结果表明,该方法能有效、准确地检测到SAR图像中的舰船尾迹.

Aiming at the problem of uncertainty in detecting the ship wake peaks in the conventional Radon transform domain,an algorithm for detecting the ship wakes in SAR ocean imagery,which makes decision in the feature space,is developed in this paper.The algorithm extracts all possible peaks by thresholding the Radon coefficients firstly,then performs the continuous wavelet transform to peak-match all these local peak sections,and finally makes decision in the feature space using the decision vectors formed by th...

TN957.52