A MultiScale Coordinate Attention Feature Fusion Network for Province-Scale Aquatic Vegetation Mapping From High-Resolution Remote Sensing Imagery
Aquatic vegetation plays a crucial role in the sustainable development of water resources. Although high-resolution remote sensing imagery has been used to develop methods for the automatic extraction of aquatic vegetation, these methods are usually limited to specific areas (such as a lake or a riv...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10769032/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850113968225386496 |
|---|---|
| author | Yuzhe Wang Yunfei Sun Peng Zhang Yanlan Wu Hui Yang |
| author_facet | Yuzhe Wang Yunfei Sun Peng Zhang Yanlan Wu Hui Yang |
| author_sort | Yuzhe Wang |
| collection | DOAJ |
| description | Aquatic vegetation plays a crucial role in the sustainable development of water resources. Although high-resolution remote sensing imagery has been used to develop methods for the automatic extraction of aquatic vegetation, these methods are usually limited to specific areas (such as a lake or a river). Extracting aquatic vegetation on a large scale faces numerous challenges, including high environmental complexity, significant seasonal variations, and poor cross-regional adaptability. Currently, relying solely on either prior knowledge-based methods or classifier methods makes it difficult to comprehensively capture the complex characteristics and variations of aquatic vegetation. To address this issue, we propose an expert feature embedded deep semantic segmentation model. This model uses an attention mechanism to fuse expert features with deep features, dynamically adjusting and optimizing the weight allocation between them. This enables the model to better capture the subtle differences among various types of aquatic vegetation and environmental changes. Specifically, we propose a feature fusion module based on the squeeze-and-excitation coordinate attention mechanism. This module initially employs the squeeze and-excitation mechanism to compress spectral and index features, generating adjusted weights <bold><inline-formula><tex-math notation="LaTeX">$\alpha$</tex-math></inline-formula></bold> and <bold><inline-formula><tex-math notation="LaTeX">$\beta$</tex-math></inline-formula></bold>. Subsequently, it dynamically adjusts the combined weights of these features through the coordinate attention mechanism. We selected eight regions in Anhui Province for evaluation. Compared to HRNet, our method improved Precision and IoU by 10.91% and 20.72%, respectively. Finally, using Anhui Province as the study area, we produced a province-scale aquatic vegetation density map. The results indicate that there are approximately 25.78 km<inline-formula><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula> of aquatic vegetation in Anhui Province. |
| format | Article |
| id | doaj-art-8ec5d024bf994f8fb68741699b61a246 |
| institution | OA Journals |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-8ec5d024bf994f8fb68741699b61a2462025-08-20T02:37:01ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01181752176510.1109/JSTARS.2024.350702310769032A MultiScale Coordinate Attention Feature Fusion Network for Province-Scale Aquatic Vegetation Mapping From High-Resolution Remote Sensing ImageryYuzhe Wang0https://orcid.org/0009-0006-3398-8512Yunfei Sun1Peng Zhang2https://orcid.org/0000-0002-9062-9448Yanlan Wu3https://orcid.org/0000-0002-8983-3150Hui Yang4https://orcid.org/0000-0002-6701-6766School of Resources and Environmental Engineering, Anhui University, Hefei, ChinaSecond Surveying and Mapping Institute of Anhui Province, Hefei, ChinaSchool of Artificial Intelligence, Anhui University, Hefei, ChinaSchool of Artificial Intelligence, Anhui University, Hefei, ChinaInstitutes of Physical Science and Information Technology, Anhui University, Hefei, ChinaAquatic vegetation plays a crucial role in the sustainable development of water resources. Although high-resolution remote sensing imagery has been used to develop methods for the automatic extraction of aquatic vegetation, these methods are usually limited to specific areas (such as a lake or a river). Extracting aquatic vegetation on a large scale faces numerous challenges, including high environmental complexity, significant seasonal variations, and poor cross-regional adaptability. Currently, relying solely on either prior knowledge-based methods or classifier methods makes it difficult to comprehensively capture the complex characteristics and variations of aquatic vegetation. To address this issue, we propose an expert feature embedded deep semantic segmentation model. This model uses an attention mechanism to fuse expert features with deep features, dynamically adjusting and optimizing the weight allocation between them. This enables the model to better capture the subtle differences among various types of aquatic vegetation and environmental changes. Specifically, we propose a feature fusion module based on the squeeze-and-excitation coordinate attention mechanism. This module initially employs the squeeze and-excitation mechanism to compress spectral and index features, generating adjusted weights <bold><inline-formula><tex-math notation="LaTeX">$\alpha$</tex-math></inline-formula></bold> and <bold><inline-formula><tex-math notation="LaTeX">$\beta$</tex-math></inline-formula></bold>. Subsequently, it dynamically adjusts the combined weights of these features through the coordinate attention mechanism. We selected eight regions in Anhui Province for evaluation. Compared to HRNet, our method improved Precision and IoU by 10.91% and 20.72%, respectively. Finally, using Anhui Province as the study area, we produced a province-scale aquatic vegetation density map. The results indicate that there are approximately 25.78 km<inline-formula><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula> of aquatic vegetation in Anhui Province.https://ieeexplore.ieee.org/document/10769032/Aquatic vegetationattention mechanismfeature fusionhigh-resolution imageryprovince-scale mapping |
| spellingShingle | Yuzhe Wang Yunfei Sun Peng Zhang Yanlan Wu Hui Yang A MultiScale Coordinate Attention Feature Fusion Network for Province-Scale Aquatic Vegetation Mapping From High-Resolution Remote Sensing Imagery IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Aquatic vegetation attention mechanism feature fusion high-resolution imagery province-scale mapping |
| title | A MultiScale Coordinate Attention Feature Fusion Network for Province-Scale Aquatic Vegetation Mapping From High-Resolution Remote Sensing Imagery |
| title_full | A MultiScale Coordinate Attention Feature Fusion Network for Province-Scale Aquatic Vegetation Mapping From High-Resolution Remote Sensing Imagery |
| title_fullStr | A MultiScale Coordinate Attention Feature Fusion Network for Province-Scale Aquatic Vegetation Mapping From High-Resolution Remote Sensing Imagery |
| title_full_unstemmed | A MultiScale Coordinate Attention Feature Fusion Network for Province-Scale Aquatic Vegetation Mapping From High-Resolution Remote Sensing Imagery |
| title_short | A MultiScale Coordinate Attention Feature Fusion Network for Province-Scale Aquatic Vegetation Mapping From High-Resolution Remote Sensing Imagery |
| title_sort | multiscale coordinate attention feature fusion network for province scale aquatic vegetation mapping from high resolution remote sensing imagery |
| topic | Aquatic vegetation attention mechanism feature fusion high-resolution imagery province-scale mapping |
| url | https://ieeexplore.ieee.org/document/10769032/ |
| work_keys_str_mv | AT yuzhewang amultiscalecoordinateattentionfeaturefusionnetworkforprovincescaleaquaticvegetationmappingfromhighresolutionremotesensingimagery AT yunfeisun amultiscalecoordinateattentionfeaturefusionnetworkforprovincescaleaquaticvegetationmappingfromhighresolutionremotesensingimagery AT pengzhang amultiscalecoordinateattentionfeaturefusionnetworkforprovincescaleaquaticvegetationmappingfromhighresolutionremotesensingimagery AT yanlanwu amultiscalecoordinateattentionfeaturefusionnetworkforprovincescaleaquaticvegetationmappingfromhighresolutionremotesensingimagery AT huiyang amultiscalecoordinateattentionfeaturefusionnetworkforprovincescaleaquaticvegetationmappingfromhighresolutionremotesensingimagery AT yuzhewang multiscalecoordinateattentionfeaturefusionnetworkforprovincescaleaquaticvegetationmappingfromhighresolutionremotesensingimagery AT yunfeisun multiscalecoordinateattentionfeaturefusionnetworkforprovincescaleaquaticvegetationmappingfromhighresolutionremotesensingimagery AT pengzhang multiscalecoordinateattentionfeaturefusionnetworkforprovincescaleaquaticvegetationmappingfromhighresolutionremotesensingimagery AT yanlanwu multiscalecoordinateattentionfeaturefusionnetworkforprovincescaleaquaticvegetationmappingfromhighresolutionremotesensingimagery AT huiyang multiscalecoordinateattentionfeaturefusionnetworkforprovincescaleaquaticvegetationmappingfromhighresolutionremotesensingimagery |