基于单时相高分辨率遥感影像的震后道路提取研究

地震发生后,道路是生命救援及运输物资的重要通道,因此,快速有效地获取道路的信息是震后抢险救灾非常关键的一步。在震前影像及矢量数据等缺失的情况下,本文基于2014年8月3日云南鲁甸地震的单时相高分辨率World View-2遥感影像进行了震后毁损道路提取方法研究。在提出的一个震后毁损道路提取方法中,先在e Cognition软件中对影像进行多尺度分割和最邻近分类,然后在Matlab软件平台下对分类结果进行二值化,并用数学形态学技术去除偏大和偏小的地物,最后利用Hough变换进行道路检测得到毁损的路段。实验结果证明:该方法能够快速有效地提取出震后的山区道路毁损信息,可为地震应急提供信息支持。

Damaged Road Extraction from Semi-Post High Resolution Remote Sensing Imagery

After an earthquake,roads act as important transportation junctions and facilitate post-disaster rescue and transportation of goods.It is critical to efficiently identify semi-post damaged roads.In this paper,an extraction method for semi-post damaged roads is established,based on single-temporal high resolution remote Sensing Imagery.In this method,the image is initially multi-scale segmented with eCognition package and classified using the nearest neighbor approach,the resulting classification is re-classified into two classes,the small and large patterns in the binary classification map are morphologically removed,and finally,Hough transform is applied to extract damaged roads.In an experiment using a semi-post WorldView-2 Image of the earthquake occurred in Ludian County,Yunnan Province,on August 3,2014,the proposed method efficiently offered damaged roads for earthquake rescue.