基于全极化Radarsat-2影像的建筑物震害评估  

Assessment of Seismic Damage of Buildings Based on Full Polarimetric Radarsat-2 Image

作　　者：缪恒 王晓青[1] 丁玲[1] 邵乐 Miao Heng;Wang Xiaoqing;Ding Ling;Shao Le(Institute of Earthquake Forecasting,CEA,Beijing 100036,China)

机构地区：[1]中国地震局地震预测研究所,北京100036

出　　处：《中国地震》2022年第2期338-347,共10页Earthquake Research in China

基　　金：“十三五”国家重点研发计划课题“一带一路”重特大地震地质灾害协同监测应急响应示范(2017YFB0504104)资助。

摘　　要：利用震后灾区全极化SAR影像可快速提取建筑物震害信息,为应急救援的快速有效实施提供重要的灾情信息支持。本文建立基于极化散射矩阵的Pauli-Wishart监督极化分类的建筑物震害信息提取和以街区为尺度的震害程度评估方法,包括Pauli分解、Wishart监督分类和遥感震害指数提取,并利用玉树县城区2010年4月14日青海玉树7.1级地震震后全极化Radarsat-2影像,提取了建筑物震害信息。经统计,确定结果总体分类精度达到0.81,Kappa值为0.61,表明本文提取建筑物震害的方法是可行的。The application of fully polarimetric SAR images in the post-earthquake disaster area to quickly extract seismic damage information of buildings and estimate the seismic damage level can provide important disaster information for the support of the rapid and effective implementation of emergency rescue.Based on the polarization scattering mechanism,we establishe the Pauli-Wishart supervised polarimetric classification based on polarization scattering matrix to extract seismic damage information of buildings and estimate seismic damage level on a street block scale,including Pauli decomposition,Wishart supervised classification and remote sensing seismic index.Taking the full polarimetric Radarsat-2 images after the Yushu M_(S)7.1 earthquake on April 14,2010 in Qinghai,China as an example dataset,we extracted the seismic damage information of buildings.Through statistical analysis,we determined that the overall classification accuracy of the results reaches 0.81,with the Kappa value of 0.61,indicating that the method of extracting seismic damage of buildings in this paper is effective and feasible.

关 键 词：全极化SAR 建筑物震害 极化分解 监督分类 

分 类 号：P315[天文地球—地震学]