基于数学形态学和相位编组SAR影像道路自动提取  

Automatic Road Extraction from SAR Images Based on Mathematical Morphology and Phase Group

作　　者：窦建方[1] 陈鹰[1] 

机构地区：[1]同济大学遥感与空间信息技术研究中心,上海200092

出　　处：《遥感信息》2008年第5期16-20,共5页Remote Sensing Information

基　　金：国家科技支撑计划:2006BAJ091300

摘　　要：某些对光学图像有很好效果的边缘检测算子,对于SAR图像来说,由于其固有的斑点噪声的强烈影响,效果不佳。为了从SAR图像上提取线特征,利用局部线特征检测线基元,为此本文提出一种改进的基于图像统计信息的局部线特征检测方法,然后使用数学形态学去除内部空隙并细化得到道路段,将道路段进行相位编组,进而自动提取出道路。Some edge detection operators have a good effect on optical image, but not on SAR image because of the impact of inherent speckle of it. In order to extract the linear structure from SAR image and use the local detector to detect line element, an improwed local linear structure detecting method which takes into account the statistic information of image is proposed, then the road sections can be obtained with mathematical morphology through removing internal gaps and thinning and can be phase groupped, finally the road can be automatically extracted.

关 键 词：SAR图像 边缘检测 数学形态学 相位编组 细化 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]