Transferability of Convolutional Neural Network Models for Identifying Damaged Buildings Due to Earthquake
The collapse of buildings caused by earthquakes can lead to a large loss of life and property. Rapid assessment of building damage with remote sensing image data can support emergency rescues. However, current studies indicate that only a limited sample set can usually be obtained from remote sensin...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/3/504 |
| _version_ | 1797417415857930240 |
|---|---|
| author | Wanting Yang Xianfeng Zhang Peng Luo |
| author_facet | Wanting Yang Xianfeng Zhang Peng Luo |
| author_sort | Wanting Yang |
| collection | DOAJ |
| description | The collapse of buildings caused by earthquakes can lead to a large loss of life and property. Rapid assessment of building damage with remote sensing image data can support emergency rescues. However, current studies indicate that only a limited sample set can usually be obtained from remote sensing images immediately following an earthquake. Consequently, the difficulty in preparing sufficient training samples constrains the generalization of the model in the identification of earthquake-damaged buildings. To produce a deep learning network model with strong generalization, this study adjusted four Convolutional Neural Network (CNN) models for extracting damaged building information and compared their performance. A sample dataset of damaged buildings was constructed by using multiple disaster images retrieved from the xBD dataset. Using satellite and aerial remote sensing data obtained after the 2008 Wenchuan earthquake, we examined the geographic and data transferability of the deep network model pre-trained on the xBD dataset. The result shows that the network model pre-trained with samples generated from multiple disaster remote sensing images can extract accurately collapsed building information from satellite remote sensing data. Among the adjusted CNN models tested in the study, the adjusted DenseNet121 was the most robust. Transfer learning solved the problem of poor adaptability of the network model to remote sensing images acquired by different platforms and could identify disaster-damaged buildings properly. These results provide a solution to the rapid extraction of earthquake-damaged building information based on a deep learning network model. |
| first_indexed | 2024-03-09T06:18:28Z |
| format | Article |
| id | doaj.art-0efd088e9dda4644923263e81fab62eb |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T06:18:28Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-0efd088e9dda4644923263e81fab62eb2023-12-03T11:50:16ZengMDPI AGRemote Sensing2072-42922021-01-0113350410.3390/rs13030504Transferability of Convolutional Neural Network Models for Identifying Damaged Buildings Due to EarthquakeWanting Yang0Xianfeng Zhang1Peng Luo2Institute of Remote Sensing and Geographic Information System, Peking University, 5 Summer Palace Road, Beijing 100871, ChinaInstitute of Remote Sensing and Geographic Information System, Peking University, 5 Summer Palace Road, Beijing 100871, ChinaDepartment of Aerospace and Geodesy, Technical University of Munich, 80333 Munich, GermanyThe collapse of buildings caused by earthquakes can lead to a large loss of life and property. Rapid assessment of building damage with remote sensing image data can support emergency rescues. However, current studies indicate that only a limited sample set can usually be obtained from remote sensing images immediately following an earthquake. Consequently, the difficulty in preparing sufficient training samples constrains the generalization of the model in the identification of earthquake-damaged buildings. To produce a deep learning network model with strong generalization, this study adjusted four Convolutional Neural Network (CNN) models for extracting damaged building information and compared their performance. A sample dataset of damaged buildings was constructed by using multiple disaster images retrieved from the xBD dataset. Using satellite and aerial remote sensing data obtained after the 2008 Wenchuan earthquake, we examined the geographic and data transferability of the deep network model pre-trained on the xBD dataset. The result shows that the network model pre-trained with samples generated from multiple disaster remote sensing images can extract accurately collapsed building information from satellite remote sensing data. Among the adjusted CNN models tested in the study, the adjusted DenseNet121 was the most robust. Transfer learning solved the problem of poor adaptability of the network model to remote sensing images acquired by different platforms and could identify disaster-damaged buildings properly. These results provide a solution to the rapid extraction of earthquake-damaged building information based on a deep learning network model.https://www.mdpi.com/2072-4292/13/3/504earthquakedisaster-damaged buildingstransfer learningCNNVHR images |
| spellingShingle | Wanting Yang Xianfeng Zhang Peng Luo Transferability of Convolutional Neural Network Models for Identifying Damaged Buildings Due to Earthquake Remote Sensing earthquake disaster-damaged buildings transfer learning CNN VHR images |
| title | Transferability of Convolutional Neural Network Models for Identifying Damaged Buildings Due to Earthquake |
| title_full | Transferability of Convolutional Neural Network Models for Identifying Damaged Buildings Due to Earthquake |
| title_fullStr | Transferability of Convolutional Neural Network Models for Identifying Damaged Buildings Due to Earthquake |
| title_full_unstemmed | Transferability of Convolutional Neural Network Models for Identifying Damaged Buildings Due to Earthquake |
| title_short | Transferability of Convolutional Neural Network Models for Identifying Damaged Buildings Due to Earthquake |
| title_sort | transferability of convolutional neural network models for identifying damaged buildings due to earthquake |
| topic | earthquake disaster-damaged buildings transfer learning CNN VHR images |
| url | https://www.mdpi.com/2072-4292/13/3/504 |
| work_keys_str_mv | AT wantingyang transferabilityofconvolutionalneuralnetworkmodelsforidentifyingdamagedbuildingsduetoearthquake AT xianfengzhang transferabilityofconvolutionalneuralnetworkmodelsforidentifyingdamagedbuildingsduetoearthquake AT pengluo transferabilityofconvolutionalneuralnetworkmodelsforidentifyingdamagedbuildingsduetoearthquake |