Discrimination of Earthquake-Induced Building Destruction from Space Using a Pretrained CNN Model
The building is an indispensable part of human life which provides a place for people to live, study, work, and engage in various cultural and social activities. People are exposed to earthquakes, and damaged buildings caused by earthquakes are one of the main threats. It is essential to retrieve th...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/2/602 |
| _version_ | 1811194128045703168 |
|---|---|
| author | Min Ji Lanfa Liu Rongchun Zhang Manfred F. Buchroithner |
| author_facet | Min Ji Lanfa Liu Rongchun Zhang Manfred F. Buchroithner |
| author_sort | Min Ji |
| collection | DOAJ |
| description | The building is an indispensable part of human life which provides a place for people to live, study, work, and engage in various cultural and social activities. People are exposed to earthquakes, and damaged buildings caused by earthquakes are one of the main threats. It is essential to retrieve the detailed information of affected buildings after earthquakes. Very high-resolution satellite imagery plays a key role in retrieving building damage information since it captures imagery quickly and effectively after the disaster. In this paper, the pretrained Visual Geometry Group (VGG)Net model was applied for identifying collapsed buildings induced by the 2010 Haiti earthquake using pre- and post-event remotely sensed space imagery, and the fine-tuned pretrained VGGNet model was compared with the VGGNet model trained from scratch. The effects of dataset augmentation and freezing different intermediate layers were also explored. The experimental results demonstrated that the fine-tuned VGGNet model outperformed the VGGNet model trained from scratch with increasing overall accuracy (OA) from 83.38% to 85.19% and Kappa from 60.69% to 67.14%. By taking advantage of dataset augmentation, OA and Kappa went up to 88.83% and 75.33% respectively, and the collapsed buildings were better recognized with a larger producer accuracy of 86.31%. The present study showed the potential of using the pretrained Convolutional Neural Network (CNN) model to identify collapsed buildings caused by earthquakes using very high-resolution satellite imagery. |
| first_indexed | 2024-04-12T00:20:44Z |
| format | Article |
| id | doaj.art-ebe688b0c5d845939297f7c6f2f03032 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-04-12T00:20:44Z |
| publishDate | 2020-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-ebe688b0c5d845939297f7c6f2f030322022-12-22T03:55:44ZengMDPI AGApplied Sciences2076-34172020-01-0110260210.3390/app10020602app10020602Discrimination of Earthquake-Induced Building Destruction from Space Using a Pretrained CNN ModelMin Ji0Lanfa Liu1Rongchun Zhang2Manfred F. Buchroithner3School of Earth Sciences and Engineering, Hohai University, Nanjing 210098, ChinaSchool of Earth Sciences and Engineering, Hohai University, Nanjing 210098, ChinaSchool of Geographic and Biologic Information, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaInstitute of Cartography, Dresden University of Technology, 01069 Dresden, GermanyThe building is an indispensable part of human life which provides a place for people to live, study, work, and engage in various cultural and social activities. People are exposed to earthquakes, and damaged buildings caused by earthquakes are one of the main threats. It is essential to retrieve the detailed information of affected buildings after earthquakes. Very high-resolution satellite imagery plays a key role in retrieving building damage information since it captures imagery quickly and effectively after the disaster. In this paper, the pretrained Visual Geometry Group (VGG)Net model was applied for identifying collapsed buildings induced by the 2010 Haiti earthquake using pre- and post-event remotely sensed space imagery, and the fine-tuned pretrained VGGNet model was compared with the VGGNet model trained from scratch. The effects of dataset augmentation and freezing different intermediate layers were also explored. The experimental results demonstrated that the fine-tuned VGGNet model outperformed the VGGNet model trained from scratch with increasing overall accuracy (OA) from 83.38% to 85.19% and Kappa from 60.69% to 67.14%. By taking advantage of dataset augmentation, OA and Kappa went up to 88.83% and 75.33% respectively, and the collapsed buildings were better recognized with a larger producer accuracy of 86.31%. The present study showed the potential of using the pretrained Convolutional Neural Network (CNN) model to identify collapsed buildings caused by earthquakes using very high-resolution satellite imagery.https://www.mdpi.com/2076-3417/10/2/602vggnetbuildingsearthquakedataset augmentationpretrained cnns |
| spellingShingle | Min Ji Lanfa Liu Rongchun Zhang Manfred F. Buchroithner Discrimination of Earthquake-Induced Building Destruction from Space Using a Pretrained CNN Model Applied Sciences vggnet buildings earthquake dataset augmentation pretrained cnns |
| title | Discrimination of Earthquake-Induced Building Destruction from Space Using a Pretrained CNN Model |
| title_full | Discrimination of Earthquake-Induced Building Destruction from Space Using a Pretrained CNN Model |
| title_fullStr | Discrimination of Earthquake-Induced Building Destruction from Space Using a Pretrained CNN Model |
| title_full_unstemmed | Discrimination of Earthquake-Induced Building Destruction from Space Using a Pretrained CNN Model |
| title_short | Discrimination of Earthquake-Induced Building Destruction from Space Using a Pretrained CNN Model |
| title_sort | discrimination of earthquake induced building destruction from space using a pretrained cnn model |
| topic | vggnet buildings earthquake dataset augmentation pretrained cnns |
| url | https://www.mdpi.com/2076-3417/10/2/602 |
| work_keys_str_mv | AT minji discriminationofearthquakeinducedbuildingdestructionfromspaceusingapretrainedcnnmodel AT lanfaliu discriminationofearthquakeinducedbuildingdestructionfromspaceusingapretrainedcnnmodel AT rongchunzhang discriminationofearthquakeinducedbuildingdestructionfromspaceusingapretrainedcnnmodel AT manfredfbuchroithner discriminationofearthquakeinducedbuildingdestructionfromspaceusingapretrainedcnnmodel |