摘要
针对高分辨率SAR图像中道路目标难以有效提取的问题,提出一种新的高分辨率SAR图像道路提取算法,它结合了参数化内核图割和数学形态学算法。利用参数化内核图割对高分辨率SAR图像中的道路目标进行初级分割,用数学形态学填充空洞,平滑道路边缘;基于道路的几何特征,使用矩阵度、改进的长宽比、复杂度等因子去除虚警;针对处理过程中出现的道路断裂情况,利用数学形态学提取道路目标的中心线,同时根据线段邻近性、方向一致性准则对其断裂部分进行连接,用数学形态学还原道路宽度,得到道路提取结果。实验结果表明该算法不用进行SAR图像预处理,也可以有效抑制相干斑噪声,并且能准确、较为完整地提取道路目标。
In view of the fact that roads in high resolution SAR image are hard to effectively extract, this paper proposesa new algorithm for road extraction in high resolution SAR image, which combines parametric kernel gragh cuts andmathematical morphology. First of all, the roads in the SAR image are initially segmented using parametric kernel graghcuts, and void spots are filled and road edge is smoothed by mathematical morphology; secondly, road extraction is obtainedby the degree of matrix, the improved length-width ratio, complexity and other factors to remove the false alarm based onthe geometrical characteristics of the road. Finally, road centerline is extracted using mathematical morphology, and thebroken road is connected by the segment proximity and directional consistency, and then the road width is restored bymathematical morphology so now a perfect road extraction of high-resolution SAR images is achieved. The results showthat the algorithm can effectively suppress speckle noise and extract the road accurately and completely without performingSAR image preprocessing.
作者
肖红光
文俊
陈立福
史长琼
XIAO Hongguang;WEN Jun;CHEN Lifu;SHI Changqiong(School of Computer & Communication Engineering, Changsha University of Science & Technology, Changsha 410114, China;College of Electrical & Information Engineering, Changsha University of Science & Technology, Changsha 410114, China)
出处
《计算机工程与应用》
CSCD
北大核心
2016年第15期198-202,207,共6页
Computer Engineering and Applications
基金
国家自然科学基金青年项目(No.41201468)
