Deep Learning Algorithm for Water Body Extraction from High-resolution Remote Sensing Images Based on Hierarchical Feature Extraction and Multi-scale Feature Fusion
Highly accurate water body extraction can be helpful for water resources monitoring and management.The current methods of water body extraction based on remote sensing images lack attention to boundary quality,resulting in inaccurate boundary delineation and low detail retention.To improve the bound...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Pearl River
2024-01-01
|
| Series: | Renmin Zhujiang |
| Subjects: | |
| Online Access: | http://www.renminzhujiang.cn/thesisDetails#10.3969/j.issn.1001-9235.2024.02.006 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841530706120933376 |
|---|---|
| author | SHENG Sheng WAN Fangqi LIN Kangling HU Zhaoyang CHEN Hua |
| author_facet | SHENG Sheng WAN Fangqi LIN Kangling HU Zhaoyang CHEN Hua |
| author_sort | SHENG Sheng |
| collection | DOAJ |
| description | Highly accurate water body extraction can be helpful for water resources monitoring and management.The current methods of water body extraction based on remote sensing images lack attention to boundary quality,resulting in inaccurate boundary delineation and low detail retention.To improve the boundary and detail accuracy of water body extraction for remote sensing images,this paper proposes a deep learning algorithm for water body extraction from high-resolution remote sensing images based on multi-scale feature fusion.The model includes a hierarchical feature extraction module and a stacked-connected decoder module that fuses multi-scale features.In the hierarchical feature extraction module,a channel attention structure is introduced for integrating shape,texture,and hue information of water bodies in high-resolution remote sensing images to better understand the shapes and boundaries of water bodies.In the stacked-connected decoder module that incorporates multi-scale features,the stacked connection of multi-level semantic information and enhanced feature extraction are performed.Meanwhile,broad background information and fine detail information are captured to achieve better water body extraction results.Experimental results on both self-annotated and publicly available datasets show that the model yields 98.37% and 91.23% accuracy,and extracts more complete edges of water bodies while retaining more details than existing semantic segmentation models.The proposed model improves the accuracy and generalization ability of water body extraction and provides references for water body extraction from high-resolution remote sensing images. |
| format | Article |
| id | doaj-art-d5544c5b68f94e2c927f0f0ea2074f37 |
| institution | Kabale University |
| issn | 1001-9235 |
| language | zho |
| publishDate | 2024-01-01 |
| publisher | Editorial Office of Pearl River |
| record_format | Article |
| series | Renmin Zhujiang |
| spelling | doaj-art-d5544c5b68f94e2c927f0f0ea2074f372025-01-15T03:00:25ZzhoEditorial Office of Pearl RiverRenmin Zhujiang1001-92352024-01-014550141964Deep Learning Algorithm for Water Body Extraction from High-resolution Remote Sensing Images Based on Hierarchical Feature Extraction and Multi-scale Feature FusionSHENG ShengWAN FangqiLIN KanglingHU ZhaoyangCHEN HuaHighly accurate water body extraction can be helpful for water resources monitoring and management.The current methods of water body extraction based on remote sensing images lack attention to boundary quality,resulting in inaccurate boundary delineation and low detail retention.To improve the boundary and detail accuracy of water body extraction for remote sensing images,this paper proposes a deep learning algorithm for water body extraction from high-resolution remote sensing images based on multi-scale feature fusion.The model includes a hierarchical feature extraction module and a stacked-connected decoder module that fuses multi-scale features.In the hierarchical feature extraction module,a channel attention structure is introduced for integrating shape,texture,and hue information of water bodies in high-resolution remote sensing images to better understand the shapes and boundaries of water bodies.In the stacked-connected decoder module that incorporates multi-scale features,the stacked connection of multi-level semantic information and enhanced feature extraction are performed.Meanwhile,broad background information and fine detail information are captured to achieve better water body extraction results.Experimental results on both self-annotated and publicly available datasets show that the model yields 98.37% and 91.23% accuracy,and extracts more complete edges of water bodies while retaining more details than existing semantic segmentation models.The proposed model improves the accuracy and generalization ability of water body extraction and provides references for water body extraction from high-resolution remote sensing images.http://www.renminzhujiang.cn/thesisDetails#10.3969/j.issn.1001-9235.2024.02.006water body extractionhigh-resolution remote sensing imagesdeep learningmulti-scale feature fusion |
| spellingShingle | SHENG Sheng WAN Fangqi LIN Kangling HU Zhaoyang CHEN Hua Deep Learning Algorithm for Water Body Extraction from High-resolution Remote Sensing Images Based on Hierarchical Feature Extraction and Multi-scale Feature Fusion Renmin Zhujiang water body extraction high-resolution remote sensing images deep learning multi-scale feature fusion |
| title | Deep Learning Algorithm for Water Body Extraction from High-resolution Remote Sensing Images Based on Hierarchical Feature Extraction and Multi-scale Feature Fusion |
| title_full | Deep Learning Algorithm for Water Body Extraction from High-resolution Remote Sensing Images Based on Hierarchical Feature Extraction and Multi-scale Feature Fusion |
| title_fullStr | Deep Learning Algorithm for Water Body Extraction from High-resolution Remote Sensing Images Based on Hierarchical Feature Extraction and Multi-scale Feature Fusion |
| title_full_unstemmed | Deep Learning Algorithm for Water Body Extraction from High-resolution Remote Sensing Images Based on Hierarchical Feature Extraction and Multi-scale Feature Fusion |
| title_short | Deep Learning Algorithm for Water Body Extraction from High-resolution Remote Sensing Images Based on Hierarchical Feature Extraction and Multi-scale Feature Fusion |
| title_sort | deep learning algorithm for water body extraction from high resolution remote sensing images based on hierarchical feature extraction and multi scale feature fusion |
| topic | water body extraction high-resolution remote sensing images deep learning multi-scale feature fusion |
| url | http://www.renminzhujiang.cn/thesisDetails#10.3969/j.issn.1001-9235.2024.02.006 |
| work_keys_str_mv | AT shengsheng deeplearningalgorithmforwaterbodyextractionfromhighresolutionremotesensingimagesbasedonhierarchicalfeatureextractionandmultiscalefeaturefusion AT wanfangqi deeplearningalgorithmforwaterbodyextractionfromhighresolutionremotesensingimagesbasedonhierarchicalfeatureextractionandmultiscalefeaturefusion AT linkangling deeplearningalgorithmforwaterbodyextractionfromhighresolutionremotesensingimagesbasedonhierarchicalfeatureextractionandmultiscalefeaturefusion AT huzhaoyang deeplearningalgorithmforwaterbodyextractionfromhighresolutionremotesensingimagesbasedonhierarchicalfeatureextractionandmultiscalefeaturefusion AT chenhua deeplearningalgorithmforwaterbodyextractionfromhighresolutionremotesensingimagesbasedonhierarchicalfeatureextractionandmultiscalefeaturefusion |