|本期目录/Table of Contents|

[1]雷雅婷,沈占锋,许泽宇,等.基于D-LinkNet的2014年云南鲁甸MS6.5地震建筑物损毁与重建评估[J].地震研究,2022,45(04):608-616.[doi:10.20015/j.cnki.ISSN1000-0666.2022.0063]
　LEI Yating,SHEN Zhanfeng,XU Zeyu,et al.Evaluation of the Damaged Buildings in the 2014 Ludian MS6.5 Earthquake in Yunnan and Their Post-earthquake Reconstruction Based on D-LinkNet[J].Journal of Seismological Research,2022,45(04):608-616.[doi:10.20015/j.cnki.ISSN1000-0666.2022.0063]
点击复制

基于D-LinkNet的2014年云南鲁甸MS6.5地震建筑物损毁与重建评估(PDF/HTML)

《地震研究》[ISSN:1000-0666/CN:53-1062/P]

卷:
45
期数:
2022年04期
页码:
608-616
栏目:
出版日期:
2022-08-20

文章信息/Info

Title:
Evaluation of the Damaged Buildings in the 2014 Ludian MS6.5 Earthquake in Yunnan and Their Post-earthquake Reconstruction Based on D-LinkNet
作者:
雷雅婷1; 2; 沈占锋1; 2; 许泽宇1; 3; 王浩宇1; 3; 李硕1; 2; 焦淑慧1; 2
(1.中国科学院空天信息创新研究院 国家遥感应用工程技术研究中心,北京 100101; 2.中国科学院大学 资源与环境学院,北京 100049; 3.中国科学院大学 电子电气与通信工程学院,北京 100049)
Author(s):
LEI Yating1; 2; SHEN Zhanfeng1; 2; XU Zeyu1; 3; WANG Haoyu1; 3; LI Shuo1; 2; JIAO Shuhui1; 2
(1.National Engineering Research Center for Geomatics,Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100101,China)(2.College of Resources and Environment,University of Chinese Academy of Sciences,Beijing 100049,China)(3.School of Electronic,Electrical and Communication Engineering,University of Chinese Academy of Sciences,Beijing 100049,China)
关键词:
遥感;  地震损毁;  重建评估;  深度学习;  D-LinkNet;  鲁甸MS6.5地震
Keywords:
remote sensing;  earthquake damage;  reconstruction assessment;  deep learning;  D-LinkNet;  the Ludian MS6.5 Earthquake
分类号:
P315.943
DOI:
10.20015/j.cnki.ISSN1000-0666.2022.0063
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MS6.5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。
Abstract:
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 MS6.5 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 Intensity Ⅷ area and Intensity Ⅸarea.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.

参考文献/References:


程希萌,沈占锋,邢廷炎,等.2016.基于高分遥感影像的地震受灾建筑物提取与倒损情况快速评估[J].自然灾害学报,25(3):22-31.
杜浩国,张方浩,卢永坤,等.2021,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[J].地震研究,44(3):490-498.
杜妍开,龚丽霞,李强.2020.基于最优分割的高分辨率遥感影像震害建筑物识别技术[J].地震学报,42(6):760-768.
和嘉吉,卢永坤,代博洋,等.2015.鲁甸MS6.5与景谷MS6.6地震灾区房屋抗震能力差异分析[J].地震研究,38(1):137-142.
庞卫东,杨润海,陈俊磊,等.2016.2014年鲁甸MS6.5地震龙头山镇场地高密度电法勘探[J].地震研究,39(4):622-629.
朴永军.2013.云南省青海省房屋地震易损性研究[D].哈尔滨:中国地震局工程力学研究所.
眭海刚,刘超贤,黄立洪,等.2019.遥感技术在震后建筑物损毁检测中的应用[J].武汉大学学报(信息科学版),44(7):1008-1019.
田枥文.2020.基于深度学习的遥感地图多目标分割检测研究[D].成都:成都理工大学.
王树华,于会臻,谭绍泉,等.2020.基于深度卷积神经网络的地震相识别技术研究[J].物探化探计算技术,42(4):475-480.
王泽泓,刘厚泉.2019.基于迁移学习与自适应特征融合的建筑物识别[J].计算机技术与发展,29(12):40-43.
张德成.1993.建筑物震害航空照片目视判读标志的初步研究[J].地震,(1):26-30.
张立恒,王浩,薛博维,等.2021.基于改进D-LinkNet模型的高分遥感影像道路提取研究[J].计算机工程,47(9):288-296.
赵妍,张景发,姚磊华.2016.基于面向对象的高分辨率遥感建筑物震害信息提取与评估[J].地震学报,38(6):942-951.
朱祺琪,李真,张亚男,等.2021.全局局部细节感知条件随机场的高分辨率遥感影像建筑物提取[J].遥感学报,25(7):1422-1433.
Bialas J,Oommen T,Rebbapragada U,et al.2016.Object-based classification of earthquake damage from high-resolution optical imagery using machine learning[J].Journal of Applied Remote Sensing,10(3):036025.
Cooner A J,Shao Y,Campbell J B.2016.Detection of urban damage using remote sensing and machine learning algorithms:revisiting the 2010 Haiti Earthquake[J].Remote Sensing,8(10):868.
Davari M R,Momeni M,Moallem P.2019.Transferable object-based framework based on deep convolutional neural networks for building extraction[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,12(8):2627-2635.
Li Y,Zhang H,Xue X,et al.2018.Deep learning for remote sensing image classification:A survey[J].Wires Data Mining and Knowledge Discovery,8(6):E1264.
Liu P,Wei Y,Wang Q,et al.2020.Research on post-earthquake landslide extraction algorithm based on improved U-Net model[J].Remote Sensing,12(5):894-894.
Masarczyk W,Gomb P,Grabowski B,et al.2020.Effective training of deep convolutional neural networks for hyperspectral image classification through artificial labeling[J].Remote Sensing,12(16):2653.
Matin S S,Pradhan B.2021.Challenges and limitations of earthquake-induced building damage mapping techniques using remote sensing images-A systematic review[J].Geocarto International:1-27.
Song D,Tan X,Wang B,et al.2020.Integration of super-pixel segmentation and deep-learning methods for evaluating earthquake-damaged buildings using single-phase remote sensing imagery[J].International Journal of Remote Sensing,41(3):1040-1066.
Sorrentino L,Cattari S,Da Porto F,et al.2018.Seismic behaviour of ordinary masonry buildings during the 2016 Central Italy Earthquakes[J].Bulletin of Earthquake Engineering,17(10):5583-5607.
Taskin K G,Musaoglu N,Ersoy O K.2011.Damage assessment of 2010 Haiti Earthquake with post-earthquake satellite image by support vector selection and adaptation[J].Photogrammetric Engineering & Remote Sensing,77(10):1025-1035.
Uros M,Novak M S,Atalic J,et al.2020.Post-earthquake damage assessment of buildings—procedure for conducting building inspections[J].Gradevinar,72(12):1089-1115.
Xia L,Zhang X,Zhang J,et al.2021.Building extraction from very-High-resolution remote sensing images using semi-supervised semantic edge detection[J].Remote Sensing,13(11):2187.
Xiong C,Li Q S,Lu X Z.2020.Automated regional seismic damage assessment of buildings using an unmanned aerial vehicle and a convolutional neural network[J].Automation in Construction,109:102994.
Xu Y,Wu L,Xie Z,et al.2018.Building extraction in very high resolution remote sensing imagery using deep learning and guided filters[J].Remote Sensing,10(1):144.
Yang W T,Zhang X F,Luo P.2021.Transferability of convolutional neural network models for identifying damaged buildings due to earthquake[J].Remote Sensing,13(3):504.
Yuan S G,Yang K,Li X,et al.2020.Automatic seamline determination for urban image mosaicking based on road probability map from he D-LinkNet neural network[J].Sensors,20(7):1832.
Zhai W,Zhang J F,Xiao X L,et al.2021.Damaged building extraction from post-earthquake polsar data based on the fourier transform[J].Remote Sensing Letters,12(6):594-603.
Zhou L,Zhang C,Wu M.2018.D-LinkNet:Linknet with pretrained encoder and dilated convolution for high resolution satellite imagery Road extraction[C]//IEEE Proceedings of the 31st IEEE/Cvf Conference on Computer Vision and Pattern Recognition,Salt Lake City:192-196.
Zhu Q,Li Z,Zhang Y,et al.2020.Building extraction from high spatial resolution remote sensing images via multiscale-aware and segmentation-prior conditional random fields[J].Remote Sensing,12(23):3983.
GB/T 17742—2020,中国地震烈度表[S].

备注/Memo

备注/Memo:
收稿日期:2022-01-24
基金项目:国家自然科学基金项目(41971375)和国家重点研发计划项目(2018YFB0505000)联合资助.

更新日期/Last Update: 2022-08-01