Seismic urban damage map generation based on satellite images and Gabor convolutional neural networks
Rapid assessment of urban damages after a strong earthquake is a necessary and crucial task to reduce the number of fatalities and recover socioeconomic services. In this paper, a novel deep-learning-based framework is proposed for detecting and mapping damages in urban buildings and roads using pos...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-08-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843223002741 |
| _version_ | 1827861385161211904 |
|---|---|
| author | Heidar Rastiveis Seyd Teymoor Seydi ZhiQiang Chen Jonathan Li |
| author_facet | Heidar Rastiveis Seyd Teymoor Seydi ZhiQiang Chen Jonathan Li |
| author_sort | Heidar Rastiveis |
| collection | DOAJ |
| description | Rapid assessment of urban damages after a strong earthquake is a necessary and crucial task to reduce the number of fatalities and recover socioeconomic services. In this paper, a novel deep-learning-based framework is proposed for detecting and mapping damages in urban buildings and roads using post-earthquake high-resolution satellite imagery. The method begins with overlaying a pre-event vector map on an input image to extract the building and road objects. The core machine learning components include two separate convolutional neural networks (CNN), integrated with Gabor filters, which extract debris pixels associated with building and road objects. These debris pixels are analyzed to generate the final damage maps, which show multiple damage degrees for buildings and roads. Two different datasets were used to thoroughly evaluate the proposed method's overall effectiveness. The overall accuracy of 95% for detecting the debris pixels in building and road areas proves the effectiveness of the proposed CNN models for debris detection in comparison to the traditional Machine Learning (ML) methods. The proposed method successfully labelled 84% of the buildings and 87% of the roads when compared with a manually generated multiple damage map. |
| first_indexed | 2024-03-12T13:37:07Z |
| format | Article |
| id | doaj.art-2e7d6f0970934b24b210d0018ad8a372 |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-03-12T13:37:07Z |
| publishDate | 2023-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-2e7d6f0970934b24b210d0018ad8a3722023-08-24T04:34:23ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322023-08-01122103450Seismic urban damage map generation based on satellite images and Gabor convolutional neural networksHeidar Rastiveis0Seyd Teymoor Seydi1ZhiQiang Chen2Jonathan Li3Dept. of Photogrammetry and Remote Sensing, School of Surveying and Geospatial Engineering, University of Tehran, Tehran, Iran; Lyles School of Civil Engineering, Purdue University, West Lafayette, USA; Corresponding author at: Dept. of Photogrammetry and Remote Sensing, School of Surveying and Geospatial Eng., University of Tehran, Tehran, Iran.Dept. of Photogrammetry and Remote Sensing, School of Surveying and Geospatial Engineering, University of Tehran, Tehran, IranSchool of Science and Engineering, University of Missouri-Kansas City, USADepartments of Geography and Environmental Management and Systems Design Engineering, University of Waterloo, 200 University Avenue West, Waterloo, Ontario N2L 3G1, CanadaRapid assessment of urban damages after a strong earthquake is a necessary and crucial task to reduce the number of fatalities and recover socioeconomic services. In this paper, a novel deep-learning-based framework is proposed for detecting and mapping damages in urban buildings and roads using post-earthquake high-resolution satellite imagery. The method begins with overlaying a pre-event vector map on an input image to extract the building and road objects. The core machine learning components include two separate convolutional neural networks (CNN), integrated with Gabor filters, which extract debris pixels associated with building and road objects. These debris pixels are analyzed to generate the final damage maps, which show multiple damage degrees for buildings and roads. Two different datasets were used to thoroughly evaluate the proposed method's overall effectiveness. The overall accuracy of 95% for detecting the debris pixels in building and road areas proves the effectiveness of the proposed CNN models for debris detection in comparison to the traditional Machine Learning (ML) methods. The proposed method successfully labelled 84% of the buildings and 87% of the roads when compared with a manually generated multiple damage map.http://www.sciencedirect.com/science/article/pii/S1569843223002741Remote sensingEarthquakeBuildingsRoadsDamageDeep learning |
| spellingShingle | Heidar Rastiveis Seyd Teymoor Seydi ZhiQiang Chen Jonathan Li Seismic urban damage map generation based on satellite images and Gabor convolutional neural networks International Journal of Applied Earth Observations and Geoinformation Remote sensing Earthquake Buildings Roads Damage Deep learning |
| title | Seismic urban damage map generation based on satellite images and Gabor convolutional neural networks |
| title_full | Seismic urban damage map generation based on satellite images and Gabor convolutional neural networks |
| title_fullStr | Seismic urban damage map generation based on satellite images and Gabor convolutional neural networks |
| title_full_unstemmed | Seismic urban damage map generation based on satellite images and Gabor convolutional neural networks |
| title_short | Seismic urban damage map generation based on satellite images and Gabor convolutional neural networks |
| title_sort | seismic urban damage map generation based on satellite images and gabor convolutional neural networks |
| topic | Remote sensing Earthquake Buildings Roads Damage Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S1569843223002741 |
| work_keys_str_mv | AT heidarrastiveis seismicurbandamagemapgenerationbasedonsatelliteimagesandgaborconvolutionalneuralnetworks AT seydteymoorseydi seismicurbandamagemapgenerationbasedonsatelliteimagesandgaborconvolutionalneuralnetworks AT zhiqiangchen seismicurbandamagemapgenerationbasedonsatelliteimagesandgaborconvolutionalneuralnetworks AT jonathanli seismicurbandamagemapgenerationbasedonsatelliteimagesandgaborconvolutionalneuralnetworks |