Anisotropic Green Tide Patch Information Extraction Based on Deformable Convolution
Green tides are marine disasters caused by the explosive proliferation or high concentration of certain large algae in seawater, which causes discoloration of the water body. Accurate monitoring of its distribution area is highly important for early warning and the protection of marine ecology. Howe...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-03-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/16/7/1162 |
_version_ | 1797212037613355008 |
---|---|
author | Binge Cui Mengting Liu Ruipeng Chen Haoqing Zhang Xiaojun Zhang |
author_facet | Binge Cui Mengting Liu Ruipeng Chen Haoqing Zhang Xiaojun Zhang |
author_sort | Binge Cui |
collection | DOAJ |
description | Green tides are marine disasters caused by the explosive proliferation or high concentration of certain large algae in seawater, which causes discoloration of the water body. Accurate monitoring of its distribution area is highly important for early warning and the protection of marine ecology. However, existing deep learning methods have difficulty in effectively identifying green tides with anisotropic characteristics due to the complex and variable shapes of the patches and the wide range of scales. To address this issue, this paper presents an anisotropic green tide patch extraction network (AGE-Net) based on deformable convolution. The main structure of AGE-Net consists of stacked anisotropic feature extraction (AFEB) modules. Each AFEB module contains two branches for extracting green tide patches. The first branch consists of multiple connected dense blocks. The second branch introduces a deformable convolution module and a depth residual module based on a multiresolution feature extraction network for extracting anisotropic features of green tide patches. Finally, an irregular green tide patch feature enhancement module is used to fuse the high-level semantic features extracted from the two branches. To verify the effectiveness of the AGE-Net model, experiments were conducted on the MODIS Green Tide dataset. The results show that AGE-Net has better recognition performance, with F1-scores and IoUs reaching 0.8317 and 71.19% on multi-view test images, outperforming other comparison methods. |
first_indexed | 2024-04-24T10:36:01Z |
format | Article |
id | doaj.art-ba050b53d2e841a886ca0994653ed645 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-04-24T10:36:01Z |
publishDate | 2024-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-ba050b53d2e841a886ca0994653ed6452024-04-12T13:25:29ZengMDPI AGRemote Sensing2072-42922024-03-01167116210.3390/rs16071162Anisotropic Green Tide Patch Information Extraction Based on Deformable ConvolutionBinge Cui0Mengting Liu1Ruipeng Chen2Haoqing Zhang3Xiaojun Zhang4College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaGreen tides are marine disasters caused by the explosive proliferation or high concentration of certain large algae in seawater, which causes discoloration of the water body. Accurate monitoring of its distribution area is highly important for early warning and the protection of marine ecology. However, existing deep learning methods have difficulty in effectively identifying green tides with anisotropic characteristics due to the complex and variable shapes of the patches and the wide range of scales. To address this issue, this paper presents an anisotropic green tide patch extraction network (AGE-Net) based on deformable convolution. The main structure of AGE-Net consists of stacked anisotropic feature extraction (AFEB) modules. Each AFEB module contains two branches for extracting green tide patches. The first branch consists of multiple connected dense blocks. The second branch introduces a deformable convolution module and a depth residual module based on a multiresolution feature extraction network for extracting anisotropic features of green tide patches. Finally, an irregular green tide patch feature enhancement module is used to fuse the high-level semantic features extracted from the two branches. To verify the effectiveness of the AGE-Net model, experiments were conducted on the MODIS Green Tide dataset. The results show that AGE-Net has better recognition performance, with F1-scores and IoUs reaching 0.8317 and 71.19% on multi-view test images, outperforming other comparison methods.https://www.mdpi.com/2072-4292/16/7/1162green tide monitoringmarine disastersdeformable convolutionsemantic segmentation |
spellingShingle | Binge Cui Mengting Liu Ruipeng Chen Haoqing Zhang Xiaojun Zhang Anisotropic Green Tide Patch Information Extraction Based on Deformable Convolution Remote Sensing green tide monitoring marine disasters deformable convolution semantic segmentation |
title | Anisotropic Green Tide Patch Information Extraction Based on Deformable Convolution |
title_full | Anisotropic Green Tide Patch Information Extraction Based on Deformable Convolution |
title_fullStr | Anisotropic Green Tide Patch Information Extraction Based on Deformable Convolution |
title_full_unstemmed | Anisotropic Green Tide Patch Information Extraction Based on Deformable Convolution |
title_short | Anisotropic Green Tide Patch Information Extraction Based on Deformable Convolution |
title_sort | anisotropic green tide patch information extraction based on deformable convolution |
topic | green tide monitoring marine disasters deformable convolution semantic segmentation |
url | https://www.mdpi.com/2072-4292/16/7/1162 |
work_keys_str_mv | AT bingecui anisotropicgreentidepatchinformationextractionbasedondeformableconvolution AT mengtingliu anisotropicgreentidepatchinformationextractionbasedondeformableconvolution AT ruipengchen anisotropicgreentidepatchinformationextractionbasedondeformableconvolution AT haoqingzhang anisotropicgreentidepatchinformationextractionbasedondeformableconvolution AT xiaojunzhang anisotropicgreentidepatchinformationextractionbasedondeformableconvolution |