SAR图像中道路检测方法研究

提出一种两步算法用于合成孔径雷达（SAR）图像中无监督地提取线性特征，特别是公路网的提取。第一步利用局部线特征检测算子提取线基元，为此本文提出一种改进的均值比率（RoA）算子，应用SAR图像的统计特性，保证较高的准确率；第二步引入公路结构特征的先验信息，构造方向势能函数（DPF）。通过DPF最小化，来对提取的线基元进行组织，获得宏观的线性结构，文中方法通过ERS－1图像加以验证。

A study of road network detection method for SAR images

Two step algorithm is proposed for unsupervised detection of linear structure from SAR image,in particular,the road network detection.The first step is to detect line element with local detector.A improved ratio of average (RoA) detector which takes into account the statistic property of SAR image is proposed,it can guarantee the detection accuracy.In the second step,the prior knowledge about the road structure to construct directional potential function is introduced.By minimizing the DPF,the line elements are so grouped to build macroscopical linear structure.The method proposed is identified in ERS 1 image.