Deep object segmentation and classification networks for building damage detection using the xBD dataset
ABSTRACTDeep learning has been extensively utilized in the assessment of building damage after disasters. However, the field of building damage segmentation faces challenges, such as misjudged regions, high network complexity, and long running times. Hence, this paper proposes a two-stage building d...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | International Journal of Digital Earth |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/17538947.2024.2302577 |
| _version_ | 1797361794373648384 |
|---|---|
| author | Zongze Zhao Fenglei Wang Shiyu Chen Hongtao Wang Gang Cheng |
| author_facet | Zongze Zhao Fenglei Wang Shiyu Chen Hongtao Wang Gang Cheng |
| author_sort | Zongze Zhao |
| collection | DOAJ |
| description | ABSTRACTDeep learning has been extensively utilized in the assessment of building damage after disasters. However, the field of building damage segmentation faces challenges, such as misjudged regions, high network complexity, and long running times. Hence, this paper proposes a two-stage building damage assessment network called the Efficient Channel Attention and Depthwise Separable Convolutional Neural Network (ECADS-CNN). It aims to quickly detect the types of disaster damage in buildings. Deep object segmentation and deep damage classification networks were integrated into a unified building damage detection network. In this study, the efficient channel attention (ECA) module was used to enhance the performance of building semantic segmentation, and a depthwise separable (DS) module was added to the dimension upscaling process. Finally, untrained disaster dataset images were used to test the robustness of the proposed model by comparing the evaluation results of each disaster. The experiments involve testing a total of five common deep learning models, and the results indicate that the ECADS-CNN model improves the speed by 7.4% and the overall F1 score by 5.2% compared with the baseline model. The comprehensive performance is better than that of mainstream deep learning models. |
| first_indexed | 2024-03-08T15:58:30Z |
| format | Article |
| id | doaj.art-5c792ecb4737435a9ff5073c07994504 |
| institution | Directory Open Access Journal |
| issn | 1753-8947 1753-8955 |
| language | English |
| last_indexed | 2024-03-08T15:58:30Z |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | International Journal of Digital Earth |
| spelling | doaj.art-5c792ecb4737435a9ff5073c079945042024-01-08T12:14:59ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552024-12-0117110.1080/17538947.2024.2302577Deep object segmentation and classification networks for building damage detection using the xBD datasetZongze Zhao0Fenglei Wang1Shiyu Chen2Hongtao Wang3Gang Cheng4School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo, People’s Republic of ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo, People’s Republic of ChinaSchool of Geographic Sciences, Xinyang Normal University, Xinyang, People’s Republic of ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo, People’s Republic of ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo, People’s Republic of ChinaABSTRACTDeep learning has been extensively utilized in the assessment of building damage after disasters. However, the field of building damage segmentation faces challenges, such as misjudged regions, high network complexity, and long running times. Hence, this paper proposes a two-stage building damage assessment network called the Efficient Channel Attention and Depthwise Separable Convolutional Neural Network (ECADS-CNN). It aims to quickly detect the types of disaster damage in buildings. Deep object segmentation and deep damage classification networks were integrated into a unified building damage detection network. In this study, the efficient channel attention (ECA) module was used to enhance the performance of building semantic segmentation, and a depthwise separable (DS) module was added to the dimension upscaling process. Finally, untrained disaster dataset images were used to test the robustness of the proposed model by comparing the evaluation results of each disaster. The experiments involve testing a total of five common deep learning models, and the results indicate that the ECADS-CNN model improves the speed by 7.4% and the overall F1 score by 5.2% compared with the baseline model. The comprehensive performance is better than that of mainstream deep learning models.https://www.tandfonline.com/doi/10.1080/17538947.2024.2302577Building damageconvolutional neural networksatellite imagerydamage assessment |
| spellingShingle | Zongze Zhao Fenglei Wang Shiyu Chen Hongtao Wang Gang Cheng Deep object segmentation and classification networks for building damage detection using the xBD dataset International Journal of Digital Earth Building damage convolutional neural network satellite imagery damage assessment |
| title | Deep object segmentation and classification networks for building damage detection using the xBD dataset |
| title_full | Deep object segmentation and classification networks for building damage detection using the xBD dataset |
| title_fullStr | Deep object segmentation and classification networks for building damage detection using the xBD dataset |
| title_full_unstemmed | Deep object segmentation and classification networks for building damage detection using the xBD dataset |
| title_short | Deep object segmentation and classification networks for building damage detection using the xBD dataset |
| title_sort | deep object segmentation and classification networks for building damage detection using the xbd dataset |
| topic | Building damage convolutional neural network satellite imagery damage assessment |
| url | https://www.tandfonline.com/doi/10.1080/17538947.2024.2302577 |
| work_keys_str_mv | AT zongzezhao deepobjectsegmentationandclassificationnetworksforbuildingdamagedetectionusingthexbddataset AT fengleiwang deepobjectsegmentationandclassificationnetworksforbuildingdamagedetectionusingthexbddataset AT shiyuchen deepobjectsegmentationandclassificationnetworksforbuildingdamagedetectionusingthexbddataset AT hongtaowang deepobjectsegmentationandclassificationnetworksforbuildingdamagedetectionusingthexbddataset AT gangcheng deepobjectsegmentationandclassificationnetworksforbuildingdamagedetectionusingthexbddataset |