Construction of Multi-Scale Fusion Attention Unified Perceptual Parsing Networks for Semantic Segmentation of Mangrove Remote Sensing Images
Mangrove forests play a crucial role in coastal ecosystem protection and carbon sequestration processes. However, monitoring remains challenging due to the forests’ complex spatial distribution characteristics. This study addresses three key challenges in mangrove monitoring: limited high-quality da...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/976 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589177058754560 |
|---|---|
| author | Xin Wang Yu Zhang Wenquan Xu Hanxi Wang Jingye Cai Qin Qin Qin Wang Jing Zeng |
| author_facet | Xin Wang Yu Zhang Wenquan Xu Hanxi Wang Jingye Cai Qin Qin Qin Wang Jing Zeng |
| author_sort | Xin Wang |
| collection | DOAJ |
| description | Mangrove forests play a crucial role in coastal ecosystem protection and carbon sequestration processes. However, monitoring remains challenging due to the forests’ complex spatial distribution characteristics. This study addresses three key challenges in mangrove monitoring: limited high-quality datasets, the complex spatial characteristics of mangrove distribution, and technical difficulties in high-resolution image processing. To address these challenges, we present two main contributions. (1) Using multi-source high-resolution satellite imagery from China’s new generation of Earth observation satellites, we constructed the Mangrove Semantic Segmentation Dataset of Beihai, Guangxi (MSSDBG); (2) We propose a novel Multi-scale Fusion Attention Unified Perceptual Network (MFA-UperNet) for precise mangrove segmentation. This network integrates Cascade Pyramid Fusion Modules, a Multi-scale Selective Kernel Attention Module, and an Auxiliary Edge Neck to process the unique characteristics of mangrove remote sensing images, particularly addressing issues of scale variation, complex backgrounds, and boundary accuracy. The experimental results demonstrate that our approach achieved a mean Intersection over Union (mIoU) of 94.54% and a mean Pixel Accuracy (mPA) of 97.14% on the MSSDBG dataset, significantly outperforming existing methods. This study provides valuable tools and methods for monitoring and protecting mangrove ecosystems, contributing to the preservation of these critical coastal environments. |
| format | Article |
| id | doaj-art-3d3c6ccef4064def9c43e692cc30cfd6 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-3d3c6ccef4064def9c43e692cc30cfd62025-01-24T13:21:33ZengMDPI AGApplied Sciences2076-34172025-01-0115297610.3390/app15020976Construction of Multi-Scale Fusion Attention Unified Perceptual Parsing Networks for Semantic Segmentation of Mangrove Remote Sensing ImagesXin Wang0Yu Zhang1Wenquan Xu2Hanxi Wang3Jingye Cai4Qin Qin5Qin Wang6Jing Zeng7School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaSchool of Computer Science and Information Security, Guilin University of Electronic Science and Technology, Guilin 541004, ChinaSchool of Marine Engineering, Guilin University of Electronic Technology, Beihai 536000, ChinaSchool of Geographical Sciences, Harbin Normal University, Harbin 150025, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaSchool of Marine Engineering, Guilin University of Electronic Technology, Beihai 536000, ChinaBasic Teaching Department, Guilin University of Electronic Technology, Beihai 536000, ChinaSchool of Marine Engineering, Guilin University of Electronic Technology, Beihai 536000, ChinaMangrove forests play a crucial role in coastal ecosystem protection and carbon sequestration processes. However, monitoring remains challenging due to the forests’ complex spatial distribution characteristics. This study addresses three key challenges in mangrove monitoring: limited high-quality datasets, the complex spatial characteristics of mangrove distribution, and technical difficulties in high-resolution image processing. To address these challenges, we present two main contributions. (1) Using multi-source high-resolution satellite imagery from China’s new generation of Earth observation satellites, we constructed the Mangrove Semantic Segmentation Dataset of Beihai, Guangxi (MSSDBG); (2) We propose a novel Multi-scale Fusion Attention Unified Perceptual Network (MFA-UperNet) for precise mangrove segmentation. This network integrates Cascade Pyramid Fusion Modules, a Multi-scale Selective Kernel Attention Module, and an Auxiliary Edge Neck to process the unique characteristics of mangrove remote sensing images, particularly addressing issues of scale variation, complex backgrounds, and boundary accuracy. The experimental results demonstrate that our approach achieved a mean Intersection over Union (mIoU) of 94.54% and a mean Pixel Accuracy (mPA) of 97.14% on the MSSDBG dataset, significantly outperforming existing methods. This study provides valuable tools and methods for monitoring and protecting mangrove ecosystems, contributing to the preservation of these critical coastal environments.https://www.mdpi.com/2076-3417/15/2/976remote sensing imagemangrove monitoringsemantic segmentationFeature Pyramid Network (FPN)attention mechanism |
| spellingShingle | Xin Wang Yu Zhang Wenquan Xu Hanxi Wang Jingye Cai Qin Qin Qin Wang Jing Zeng Construction of Multi-Scale Fusion Attention Unified Perceptual Parsing Networks for Semantic Segmentation of Mangrove Remote Sensing Images Applied Sciences remote sensing image mangrove monitoring semantic segmentation Feature Pyramid Network (FPN) attention mechanism |
| title | Construction of Multi-Scale Fusion Attention Unified Perceptual Parsing Networks for Semantic Segmentation of Mangrove Remote Sensing Images |
| title_full | Construction of Multi-Scale Fusion Attention Unified Perceptual Parsing Networks for Semantic Segmentation of Mangrove Remote Sensing Images |
| title_fullStr | Construction of Multi-Scale Fusion Attention Unified Perceptual Parsing Networks for Semantic Segmentation of Mangrove Remote Sensing Images |
| title_full_unstemmed | Construction of Multi-Scale Fusion Attention Unified Perceptual Parsing Networks for Semantic Segmentation of Mangrove Remote Sensing Images |
| title_short | Construction of Multi-Scale Fusion Attention Unified Perceptual Parsing Networks for Semantic Segmentation of Mangrove Remote Sensing Images |
| title_sort | construction of multi scale fusion attention unified perceptual parsing networks for semantic segmentation of mangrove remote sensing images |
| topic | remote sensing image mangrove monitoring semantic segmentation Feature Pyramid Network (FPN) attention mechanism |
| url | https://www.mdpi.com/2076-3417/15/2/976 |
| work_keys_str_mv | AT xinwang constructionofmultiscalefusionattentionunifiedperceptualparsingnetworksforsemanticsegmentationofmangroveremotesensingimages AT yuzhang constructionofmultiscalefusionattentionunifiedperceptualparsingnetworksforsemanticsegmentationofmangroveremotesensingimages AT wenquanxu constructionofmultiscalefusionattentionunifiedperceptualparsingnetworksforsemanticsegmentationofmangroveremotesensingimages AT hanxiwang constructionofmultiscalefusionattentionunifiedperceptualparsingnetworksforsemanticsegmentationofmangroveremotesensingimages AT jingyecai constructionofmultiscalefusionattentionunifiedperceptualparsingnetworksforsemanticsegmentationofmangroveremotesensingimages AT qinqin constructionofmultiscalefusionattentionunifiedperceptualparsingnetworksforsemanticsegmentationofmangroveremotesensingimages AT qinwang constructionofmultiscalefusionattentionunifiedperceptualparsingnetworksforsemanticsegmentationofmangroveremotesensingimages AT jingzeng constructionofmultiscalefusionattentionunifiedperceptualparsingnetworksforsemanticsegmentationofmangroveremotesensingimages |