基于多源遥感影像的2021年云南漾濞MS6.4地震灾区建筑物信息识别与震害分析

(1.云南省地震局,云南 昆明 650224; 2.中国地震局工程力学研究所,黑龙江 哈尔滨 150080)

漾濞MS6.4地震; 建筑物震害识别; 灾害损失评估; DSM数字表面模型; 高分辨率影像

Recognition of the Earthquake Damage to Buildings in the 2021 Yangbi,Yunnan MS6.4 Earthquake Area Based on Multi-source Remote Sensing Images
DU Haoguo1,ZHANG Fanghao1,LU Yongkun1,LIN Xuchuan2,DENG Shurong1,CAO Yanbo1

(1.Yunnan Earthquake Agency,Kunming 650224,Yunnan,China)(2.Institute of Engineering Mechanics,China Earthquake Administration,Harbin 150080,Heilongjiang,China)

the Yangbi MS6.4 earthquake; identification of earthquake-damage to buildings; assessment on the disaster losses; digital surface model; high-resolution image

备注

以无人机获取的震后区域高分辨率遥感影像、DSM数字表面模型为基础,提出多源遥感影像的建筑物震害精细化识别方法。对影像中的地物进行多尺度分割,剔除其它地物,提取出建筑物,并依据光谱、纹理、形状特征进行震后建筑物震害、结构类型以及楼层数识别。将该方法应用于2021年云南漾濞MS6.4地震灾区建筑物震害识别,为灾害损失评估工作提供基础数据。结果表明,与传统的人工震害调查相比,基于多源遥感影像的建筑物信息识别方法速度快、准确率高。
Rapid identification of the earthquake damage to buildings in the earthquake-stricken area is of great significance for scientific and effective assessment of losses from earthquake disasters.Based on the high-resolution,remote-sensing images of post-earthquake field investigation obtained by UAV and digital surface model(DSM),we propose an identification method of earthquake damage to buildings based on multi-source,remote-sensing images.In the light of this method,we first do the multi-scale segmentation of the surface feature,then extract buildings' information,and weed out other features.Further,we identify the damage,structures and the floors of the buildings according to the spectrum,texture and shape of the buildings on the images.We apply our method to the identification of the damage to the buildings in the Yangbi MS6.4 earthquake on 21th,May 2021.The results show that,compared with the traditional manual investigation of the damage in the earthquake-affected areas,our method is more effective and more accurate.