摘要
基于谷歌影像和无人机遥感影像,利用D-LinkNet神经网络提取2014年云南鲁甸M_(S)6.5地震震中龙头山镇建筑物灾害信息,并计算平均震害指数的统计值,得出此次地震的烈度。基于D-LinkNet模型进行检测,将损毁建筑物的提取结果与建筑物群变化的检测结果进行相交,构建重建评估系数,确定研究区的重建程度。评估结果为研究区的地震烈度既有Ⅷ度又有Ⅸ度。2015年的重建恢复等级为“一般恢复”,2018年为基本“完全恢复”。将损毁及重建评估结果与中国地震局等相关部门发布的相关信息进行对比,证实了本方法的准确性。
Based on Google and UAV remote sensing images,the D-LinkNet neural network was used to extract the information of the damaged buildings in Longtoushan Town caused by the 2014,Ludian,Yunnan M_(S)6.5 earthquake.Then the intensity in Longtongshan Town was calculated according to the statistical value of the mean earthquake-damage index.A detection of the advances in the reconstruction of the buildings in Longtoushan Town was carried out based on D-LinkNet model.Then the extracted results of the damaged buildings were intersected with the detection results of the reconstructed buildings,and the evaluation coefficients of building reconstruction were set up and the reconstruction degree of the damaged buildings was determined.The results showed that Longtoushan Town was located both in IntensityⅧarea and IntensityⅨarea.In 2015,the buildings in Longtoushan Town wereevaluated as“basically restored”,while in 2018,they were evaluated as“completely restored”.The extracted results and evaluated results in this paper were compared with the information released by the China Earthquake Administration and other relevant departments.The consistency of the results given in this paper with the results released by authorities proved that the proposed method in this paper is accurate.
作者
雷雅婷
沈占锋
许泽宇
王浩宇
李硕
焦淑慧
LEI Yating;SHEN Zhanfeng;XU Zeyu;WANG Haoyu;LI Shuo;JIAO Shuhui(National Engineering Research Center for Geomatics,Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100101,China;College of Resources and Environment,University of Chinese Academy of Sciences,Beijing 100049,China;School of Electronic,Electrical and Communication Engineering,University of Chinese Academy of Sciences,Beijing 100049,China)
出处
《地震研究》
CSCD
北大核心
2022年第4期608-616,共9页
Journal of Seismological Research
基金
国家自然科学基金项目(41971375)
国家重点研发计划项目(2018YFB0505000)联合资助。
