自适应圆形模板及显著图的高分辨遥感图像道路提取

Road Extraction from High-resolution Remote Sensing Images Based on Adaptive Circular Template and Saliency Map

针对现有基于圆形模板匹配算法需要人工设定模板尺寸的问题,提出一种自适应圆形模板的高分辨遥感图像道路提取算法。首先引入一种改进的局部形态学梯度图,基于形态学梯度图设计了一种自动生成模板尺寸的算法;接着借助改进的道路显著图,按迭代内插的方式搜索起始点与终止点之间其他道路点,搜索过程综合利用了显著图信息和几何夹角信息,使得算法具有更好的识别效果。试验结果表明,本文算法可适用于多种不同条件的遥感图像,能更加有效地从高分辨遥感图像中提取道路信息。

In order to solve the problem that the existing template matching algorithms need to manually set template sizes,it is proposed that an adaptive circular template algorithm for extracting the road information in a high-resolution remote sensing image.Firstly,an improved local morphological gradient map is constructed to calculate the size of the circular template automatically;then,a modified road saliency map is made.It is designed that a new algorithm to search for the most likely center points of a road between the start and the end points by the way of iterative interpolation.The comprehensive utilization of the saliency information and the angles of geometric during the search process make the algorithm have the better recognition effect.The experimental results show that the proposed algorithm can be applied to high-resolution remote sensing images of different conditions,to extract the road information more effectively.