A feature enhancement framework for landslide detection
Accurate landslide detection is essential for disaster mitigation and relief. In this study, we develop a feature enhancement framework that integrates attention and multiscale mechanisms with U-Net (AMU-Net) for landslide detection. The framework has four steps. First, the attention module in the c...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-11-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S156984322300345X |
| _version_ | 1797633271607066624 |
|---|---|
| author | Ruilong Wei Chengming Ye Tianbo Sui Huajun Zhang Yonggang Ge Yao Li |
| author_facet | Ruilong Wei Chengming Ye Tianbo Sui Huajun Zhang Yonggang Ge Yao Li |
| author_sort | Ruilong Wei |
| collection | DOAJ |
| description | Accurate landslide detection is essential for disaster mitigation and relief. In this study, we develop a feature enhancement framework that integrates attention and multiscale mechanisms with U-Net (AMU-Net) for landslide detection. The framework has four steps. First, the attention module in the convolutional block enhances the feature response of landslides when extracting high-level feature representations. Second, the multiscale module in skip connection captures more contextual information when concatenating fine and coarse features. Third, the U-Net architecture encodes feature mapping and decodes semantics representations. Fourth, the shifted window was applied to enhance the receptive field of pixels in the prediction process, which reduced the errors of landslide boundaries. Besides, we explored the effect of random split and regional split methods on model training. In the upper reach of the Jinsha River, data on unoccupied aerial vehicle (UAV) images and digital surface model (DSM) were prepared for landslide detection. The design of the framework and experiments considers the disparities in data between UAV and satellite remote sensing. The controlled experiments reported that the mean Intersection over Union (mIoU) for the proposed AMU-Net achieved 0.797, which was over 2% higher than other models. Furthermore, the visualized feature maps revealed that the proposed method can effectively restrain irrelevant feature responses in backgrounds and capture features from various receptive fields. Comparative studies on all the above experiments proved the superiority of the proposed framework for landslide detection. |
| first_indexed | 2024-03-11T11:51:44Z |
| format | Article |
| id | doaj.art-4567271bbc75474caa3d5ddfd8349790 |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-03-11T11:51:44Z |
| publishDate | 2023-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-4567271bbc75474caa3d5ddfd83497902023-11-09T04:11:44ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322023-11-01124103521A feature enhancement framework for landslide detectionRuilong Wei0Chengming Ye1Tianbo Sui2Huajun Zhang3Yonggang Ge4Yao Li5Key Laboratory of Earth Exploration and Information Technology of Ministry of Education, Chengdu University of Technology, Chengdu, 610059, ChinaKey Laboratory of Earth Exploration and Information Technology of Ministry of Education, Chengdu University of Technology, Chengdu, 610059, China; Corresponding author.Key Laboratory of Earth Exploration and Information Technology of Ministry of Education, Chengdu University of Technology, Chengdu, 610059, ChinaKey Laboratory of Earth Exploration and Information Technology of Ministry of Education, Chengdu University of Technology, Chengdu, 610059, ChinaInstitute of Mountain Hazards and Environment, Chinese Academy of Sciences, Chengdu, 610041, ChinaState Key Laboratory of Hydroscience and Engineering, Tsinghua University, Beijing, 100084, ChinaAccurate landslide detection is essential for disaster mitigation and relief. In this study, we develop a feature enhancement framework that integrates attention and multiscale mechanisms with U-Net (AMU-Net) for landslide detection. The framework has four steps. First, the attention module in the convolutional block enhances the feature response of landslides when extracting high-level feature representations. Second, the multiscale module in skip connection captures more contextual information when concatenating fine and coarse features. Third, the U-Net architecture encodes feature mapping and decodes semantics representations. Fourth, the shifted window was applied to enhance the receptive field of pixels in the prediction process, which reduced the errors of landslide boundaries. Besides, we explored the effect of random split and regional split methods on model training. In the upper reach of the Jinsha River, data on unoccupied aerial vehicle (UAV) images and digital surface model (DSM) were prepared for landslide detection. The design of the framework and experiments considers the disparities in data between UAV and satellite remote sensing. The controlled experiments reported that the mean Intersection over Union (mIoU) for the proposed AMU-Net achieved 0.797, which was over 2% higher than other models. Furthermore, the visualized feature maps revealed that the proposed method can effectively restrain irrelevant feature responses in backgrounds and capture features from various receptive fields. Comparative studies on all the above experiments proved the superiority of the proposed framework for landslide detection.http://www.sciencedirect.com/science/article/pii/S156984322300345XConvolutional neural networkDeep learningLandslide detectionRemote sensing |
| spellingShingle | Ruilong Wei Chengming Ye Tianbo Sui Huajun Zhang Yonggang Ge Yao Li A feature enhancement framework for landslide detection International Journal of Applied Earth Observations and Geoinformation Convolutional neural network Deep learning Landslide detection Remote sensing |
| title | A feature enhancement framework for landslide detection |
| title_full | A feature enhancement framework for landslide detection |
| title_fullStr | A feature enhancement framework for landslide detection |
| title_full_unstemmed | A feature enhancement framework for landslide detection |
| title_short | A feature enhancement framework for landslide detection |
| title_sort | feature enhancement framework for landslide detection |
| topic | Convolutional neural network Deep learning Landslide detection Remote sensing |
| url | http://www.sciencedirect.com/science/article/pii/S156984322300345X |
| work_keys_str_mv | AT ruilongwei afeatureenhancementframeworkforlandslidedetection AT chengmingye afeatureenhancementframeworkforlandslidedetection AT tianbosui afeatureenhancementframeworkforlandslidedetection AT huajunzhang afeatureenhancementframeworkforlandslidedetection AT yonggangge afeatureenhancementframeworkforlandslidedetection AT yaoli afeatureenhancementframeworkforlandslidedetection AT ruilongwei featureenhancementframeworkforlandslidedetection AT chengmingye featureenhancementframeworkforlandslidedetection AT tianbosui featureenhancementframeworkforlandslidedetection AT huajunzhang featureenhancementframeworkforlandslidedetection AT yonggangge featureenhancementframeworkforlandslidedetection AT yaoli featureenhancementframeworkforlandslidedetection |