Assessment of the Degree of Building Damage Caused by Disaster Using Convolutional Neural Networks in Combination with Ordinal Regression

被引:45
作者
Ci, Tianyu [1 ,2 ]
Liu, Zhen [3 ]
Wang, Ying [1 ]
机构
[1] Beijing Normal Univ, Minist Educ, Key Lab Environm Change & Nat Disaster, Beijing 100875, Peoples R China
[2] Beijing Normal Univ, Coll Global Change & Earth Syst Sci, Beijing 100875, Peoples R China
[3] Beijing Normal Univ, Fac Educ, Beijing 100875, Peoples R China
关键词
earthquake; rapid mapping; damage assessment; deep learning; convolutional neural networks; ordinal regression; aerial image; LUDIAN EARTHQUAKE; 2003; BAM; IMAGERY; IRAN;
D O I
10.3390/rs11232858
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
We propose a new convolutional neural networks method in combination with ordinal regression aiming at assessing the degree of building damage caused by earthquakes with aerial imagery. The ordinal regression model and a deep learning algorithm are incorporated to make full use of the information to improve the accuracy of the assessment. A new loss function was introduced in this paper to combine convolutional neural networks and ordinal regression. Assessing the level of damage to buildings can be considered as equivalent to predicting the ordered labels of buildings to be assessed. In the existing research, the problem has usually been simplified as a problem of pure classification to be further studied and discussed, which ignores the ordinal relationship between different levels of damage, resulting in a waste of information. Data accumulated throughout history are used to build network models for assessing the level of damage, and models for assessing levels of damage to buildings based on deep learning are described in detail, including model construction, implementation methods, and the selection of hyperparameters, and verification is conducted by experiments. When categorizing the damage to buildings into four types, we apply the method proposed in this paper to aerial images acquired from the 2014 Ludian earthquake and achieve an overall accuracy of 77.39%; when categorizing damage to buildings into two types, the overall accuracy of the model is 93.95%, exceeding such values in similar types of theories and methods.
引用
收藏
页数:19
相关论文
共 63 条
[1]  
Abadi M., 2015, TENSORFLOW LARGESCAL
[2]   Earthquake damage mapping: An overall assessment of ground surveys and VHR image change detection after L'Aquila 2009 earthquake [J].
Anniballe, Roberta ;
Noto, Fabrizio ;
Scalia, Tanya ;
Bignami, Christian ;
Stramondo, Salvatore ;
Chini, Marco ;
Pierdicca, Nazzareno .
REMOTE SENSING OF ENVIRONMENT, 2018, 210 :166-178
[3]  
[Anonymous], IEEE I CONF COMP VIS, DOI DOI 10.1109/ICCV.2017.324
[4]  
[Anonymous], PROC CVPR IEEE
[5]  
[Anonymous], 2015, ARXIV PREPRINT ARXIV
[6]  
[Anonymous], DATA DRIVEN MODELLIN
[7]  
[Anonymous], 2015, P INT C LEARN REP IC
[8]  
[Anonymous], P ISPRS 20 C
[9]  
[Anonymous], BUILDING ASSESSMENT
[10]  
[Anonymous], 2008, SPAT DAT SRTUCT, DOI DOI 10.1007/978-3-540-74831-1_5