地震研究

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.

引言
1 研究方法及技术路线
2 区域震害提取试验
3 讨论与分析
4 结论

图1 基于多源遥感影像的建筑物震害精细化识别流程<br/>Fig.1 Flow chart of refined identification and analysis of buildings' damages by earthquakes based on multi-source,remote sensing images

图1 基于多源遥感影像的建筑物震害精细化识别流程
Fig.1 Flow chart of refined identification and analysis of buildings' damages by earthquakes based on multi-source,remote sensing images

图2 震害识别规则<br/>Fig.2 Identification rules of seismic damage

图2 震害识别规则
Fig.2 Identification rules of seismic damage

表1 精度级别分类<br/>Tab.1 Classification of accuracy level

表1 精度级别分类
Tab.1 Classification of accuracy level

图3 淮安村高分辨率影像图(a)和数字表面模型(b)<br/>Fig.3 High-resolution images(a)and digital surface model(b)of Huai'an village

图3 淮安村高分辨率影像图(a)和数字表面模型(b)
Fig.3 High-resolution images(a)and digital surface model(b)of Huai'an village

图4 部分样本震害等级识别<br/>Fig.4 Identification of the degree of earthquake damage of some samples

图4 部分样本震害等级识别
Fig.4 Identification of the degree of earthquake damage of some samples

表2 训练样本和验证样本<br/>Tab.2 Training data and test data

表2 训练样本和验证样本
Tab.2 Training data and test data

图5 不同震害等级的建筑物样本(a)、建筑物轮廓检测结果(b)和部分训练样本震害规则提取结果(c)<br/>Fig.5 Sample of buildings with different damage levels(a),building contour test results(b),extraction results of seismic damage rules from some training samples(c)

图5 不同震害等级的建筑物样本(a)、建筑物轮廓检测结果(b)和部分训练样本震害规则提取结果(c)
Fig.5 Sample of buildings with different damage levels(a),building contour test results(b),extraction results of seismic damage rules from some training samples(c)

图6 训练样本平均灰度值与建筑物数量统计<br/>Fig.6 Average grayscale value of training samples and statistics of buildings

图6 训练样本平均灰度值与建筑物数量统计
Fig.6 Average grayscale value of training samples and statistics of buildings

表3 部分震害识别规则<br/>Tab.3 Identification rules of seismic damage

表3 部分震害识别规则
Tab.3 Identification rules of seismic damage

图7 震害识别结果(a)、目视解译与实地调查结果(b)、建筑物结构类型识别结果(c)以及建筑物层高识别结果(d)<br/>Fig.7 Earthquake damage identification results(a),visual interpretation and field investigation results(b),building structure identification result(c),and building height identification results(d)

图7 震害识别结果(a)、目视解译与实地调查结果(b)、建筑物结构类型识别结果(c)以及建筑物层高识别结果(d)
Fig.7 Earthquake damage identification results(a),visual interpretation and field investigation results(b),building structure identification result(c),and building height identification results(d)

表4 淮安村震害识别结果精度评价<br/>Tab.4 Evaluation of accuracy of earthquake damage identification in Huai'an village

表4 淮安村震害识别结果精度评价
Tab.4 Evaluation of accuracy of earthquake damage identification in Huai'an village

表5 淮安村建筑物结构类型和震害统计<br/>Tab.5 Statistics of earthquake damage of buildings in Huai'an village

表5 淮安村建筑物结构类型和震害统计
Tab.5 Statistics of earthquake damage of buildings in Huai'an village

表6 淮安村建筑物楼层数震害统计<br/>Tab.6 Statistics of earthquake damage of building storey in Huai'an village

表6 淮安村建筑物楼层数震害统计
Tab.6 Statistics of earthquake damage of building storey in Huai'an village

代沁伶,罗斌,郑晨,等.2020.区域多尺度马尔可夫随机场的遥感影像分类[J].遥感学报,24(3):245-253.
丁胜,袁修孝,陈黎.2010.粒子群优化算法用于高光谱遥感影像分类的自动波段选择[J].测绘学报,39(3):257-263.
杜浩国,陈亮,林旭川,等.2019.云南红河县城区房屋地震灾害三维仿真模拟方法[J].地震研究,42(2):218-229.
杜浩国,林旭川,张方浩,等.2021.基于蚁群优化算法的应急避难场所选址模型研究[J].自然灾害学报,30(2):89-101.
杜浩国,张方浩,邓树荣,等.2018.震后极灾区无人机最优航拍区域选择[J].地震研究,41(2):209-215.
杜妍开,龚丽霞,李强,等.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.
和仕芳,邓树荣,张方浩,等.2016.旋翼无人机在建筑物抗震能力调查中的应用[J].地震研究,39(4):673-679.
李强,张景发.2016.不同特征融合的震后损毁建筑物识别研究[J].地震研究,39(3):486-493.
卢永坤,周洋,代博洋,等.2019.2018年云南墨江5.9级地震房屋震害特征与烈度评定[J].地震研究,42(2):172-178.
马燕妮,明冬萍,杨海平.2017.面向对象影像多尺度分割最大异质性参数估计[J].遥感学报,21(4):566-578.
王昶,张永生,纪松,等.2021.建筑物变化的多特征融和及随机多图综合检测法[J].测绘学报,50(2):235-247.
曾涛.2010.汶川地震重灾区多源影像处理及震害信息提取方法研究[D].成都:成都理工大学.
张方浩,卢永坤,邓树荣,等.2020.云南地区区域地震灾害特征[J].地震研究,43(1):134-143.
张建国.2014.地震烈度的评定及其意义[J].中国减灾,(17):42-43.
张雪华,王晓青,杜晓霞,等.2019.基于无人机遥感影像及其点云特征的建筑物震害提取[J].地震研究,42(2):230-235.

备注

引言

1 研究方法及技术路线

2 区域震害提取试验

3 讨论与分析

4 结论

期刊信息