基于张量投票算法的SAR图像道路提取方法  

Road networks detection in SAR images using tensor voting algorithm

作　　者：沈大江[1,2] 王峥[3] 田金文[2] 

机构地区：[1]武汉市国土资源房产信息中心,湖北武汉430015 [2]华中科技大学图像识别与人工智能研究所,湖北武汉430074 [3]长江空间信息技术工程有限公司遥感数字工程院,湖北武汉430010

出　　处：《华中科技大学学报（自然科学版）》2009年第4期51-54,共4页Journal of Huazhong University of Science and Technology(Natural Science Edition)

摘　　要：阐述了张量投票算法基本原理,提出了一种利用张量投票算法从合成孔径雷达(SAR)图像中提取道路网的方法.首先利用一个比值算子和一个相关算子的融合检测算子将道路基元检测出来;然后再利用方向可调滤波器进行SAR图像的局部方向估计;最后对方向估计结果进行张量编码,并采用张量投票算法构建道路网.基于真实SAR图像的实验结果显示,此方法对斑点噪声不敏感,不需对SAR图像进行复杂的预处理,就能快速、准确地检测SAR图像中的道路网.The main principal of tensor voting was expounded. A method to extract roads from synthetic aperture radar （SAR） images using tensor voting is presented. The road segments are obtained by a detector which is fused from a ratio detector and a correlation detector. The local orientation of SAR images was estimated using steerable filters. Results and construct road networks were encoded by means of tensor voting. Based on real SAR images, the experimental results show that the proposed method is insensitive to speckle noise and can extract road networks fast and accurately from SAR images without complex preprocessing.

关 键 词：合成孔径雷达 张量投票 局部方向估计 方向可调滤波器 道路提取 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]