一种稳健的道路主方向提取算法

A Robust Main Direction Extraction Method for Road Segment

基于高分辨遥感影像下直线型道路段的形状特征,提出了一种稳健的道路主方向提取算法.该算法基于结构张量计算的方向直方图探测初始主方向,并根据矢量化的边缘计算精确的方向角,使得探测过程稳健、结果准确.在此基础上可以发展交互式的直线道路段或道路网提取算法.实验结果表明,该算法的结果为进一步的道路边线的准确提取提供了保障.

An algorithm of robust main direction extraction method for road segment is presented according to the shape feature of linear road segment in high-resolution remote sensing images. The robust and precise method consists of initial main direction extraction based on the direction histogram of structure tensor and precise direction detection on vectorized edge image. Further application based on the method is to develop active method to extract linear road segments or road network. Experiment results demonstrate that the proposed algorithm provides good mid-result for extracting road sides.