MangroveSeg: Deep-Supervision-Guided Feature Aggregation Network for Mangrove Detection and Segmentation in Satellite Images

Mangrove forests are significant participants in coastal ecological environment systems. For the development of protection strategies, it is crucial to automatically and accurately detect the distribution and area of mangroves using satellite images. Although many deep-learning-based mangrove detect...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Forests 2024-01, Vol.15 (1), p.127
Hauptverfasser: Dong, Heng, Gao, Yifan, Chen, Riqing, Wei, Lifang
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 1
container_start_page 127
container_title Forests
container_volume 15
creator Dong, Heng
Gao, Yifan
Chen, Riqing
Wei, Lifang
description Mangrove forests are significant participants in coastal ecological environment systems. For the development of protection strategies, it is crucial to automatically and accurately detect the distribution and area of mangroves using satellite images. Although many deep-learning-based mangrove detection and segmentation algorithms have made notable progress, the complex regional structures and the great similarity between mangroves and the surrounding environment, as well as the diversity of mangroves, render the task still challenging. To cover these issues, we propose a novel deep-supervision-guided feature aggregation network for mangrove detection and segmentation called MangroveSeg, which is based on a U-shaped structure with ResNet, combining an attention mechanism and a multi-scale feature extraction framework. We also consider the detection and segmentation of mangroves as camouflage detection problems for the improvement and enhancement of accuracy. To determine more information from extracted feature maps in a hidden layer, a deep supervision model is introduced in up-sampling to enhance feature representation. The spatial attention mechanism with attention gates is utilized to highlight significant regions and suppress task-independent feature responses. The feature fusion module can obtain multi-scale information by binding each layer to the underlying information and update feature mappings. We validated our framework for mangrove detection and segmentation using a satellite image dataset, which includes 4000 images comprising 256 × 256 pixels; we used 3002 for training and 998 for testing. The satellite images dataset was obtained from the Dongzhaigang National Nature Reserve located in Haikou City, Hainan Province, China. The proposed method achieved a 89.58% overall accuracy, 89.02% precision, and 80.7% mIoU. We also used the trained MangroveSeg model to detect mangroves on satellite images from other regions. We evaluated the statistical square measure of some mangrove areas and found that the evaluation accuracy can reach 96% using MangroveSeg. The proposed MangroveSeg model can automatically and accurately detect the distribution and area of mangroves from satellite images, which provides a method for monitoring the ecological environment.
doi_str_mv 10.3390/f15010127
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2918759564</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2918759564</sourcerecordid><originalsourceid>FETCH-LOGICAL-c252t-21d12a18c0b06eeeb22a137e46bc1226139d9945be2efba480babf16e11258293</originalsourceid><addsrcrecordid>eNpNkMFOwzAQRC0EElXhwB9Y4sQh4HXiJOZWFVoqFTgUzpGdbKKUNg62U4TEx2MoIPayu5rRG2kIOQN2GceSXdUgGDDg2QEZgZQySiTLDv_dx-TUuTULI7Jc8mREPu5V11izwxU21_QGsY9WQ49217rWdNF8aCus6AyVHyzSSdNYbJQPEn1A_2bsC62Npb-QAPBYfsuqq2hgbrHze3_b0ZXyuNm0Huliqxp0J-SoVhuHpz97TJ5nt0_Tu2j5OF9MJ8uo5IL7iEMFXEFeMs1SRNQ8fHGGSapL4DyFWFZSJkIjx1qrJGda6RpSBOAi5zIek_M9t7fmdUDni7UZbBciCy4hz4QUaRJcF3tXaY1zFuuit-1W2fcCWPHVb_HXb_wJUnVtyg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2918759564</pqid></control><display><type>article</type><title>MangroveSeg: Deep-Supervision-Guided Feature Aggregation Network for Mangrove Detection and Segmentation in Satellite Images</title><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Dong, Heng ; Gao, Yifan ; Chen, Riqing ; Wei, Lifang</creator><creatorcontrib>Dong, Heng ; Gao, Yifan ; Chen, Riqing ; Wei, Lifang</creatorcontrib><description>Mangrove forests are significant participants in coastal ecological environment systems. For the development of protection strategies, it is crucial to automatically and accurately detect the distribution and area of mangroves using satellite images. Although many deep-learning-based mangrove detection and segmentation algorithms have made notable progress, the complex regional structures and the great similarity between mangroves and the surrounding environment, as well as the diversity of mangroves, render the task still challenging. To cover these issues, we propose a novel deep-supervision-guided feature aggregation network for mangrove detection and segmentation called MangroveSeg, which is based on a U-shaped structure with ResNet, combining an attention mechanism and a multi-scale feature extraction framework. We also consider the detection and segmentation of mangroves as camouflage detection problems for the improvement and enhancement of accuracy. To determine more information from extracted feature maps in a hidden layer, a deep supervision model is introduced in up-sampling to enhance feature representation. The spatial attention mechanism with attention gates is utilized to highlight significant regions and suppress task-independent feature responses. The feature fusion module can obtain multi-scale information by binding each layer to the underlying information and update feature mappings. We validated our framework for mangrove detection and segmentation using a satellite image dataset, which includes 4000 images comprising 256 × 256 pixels; we used 3002 for training and 998 for testing. The satellite images dataset was obtained from the Dongzhaigang National Nature Reserve located in Haikou City, Hainan Province, China. The proposed method achieved a 89.58% overall accuracy, 89.02% precision, and 80.7% mIoU. We also used the trained MangroveSeg model to detect mangroves on satellite images from other regions. We evaluated the statistical square measure of some mangrove areas and found that the evaluation accuracy can reach 96% using MangroveSeg. The proposed MangroveSeg model can automatically and accurately detect the distribution and area of mangroves from satellite images, which provides a method for monitoring the ecological environment.</description><identifier>ISSN: 1999-4907</identifier><identifier>EISSN: 1999-4907</identifier><identifier>DOI: 10.3390/f15010127</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Accuracy ; Algorithms ; Annotations ; Coastal ecology ; Datasets ; Deep learning ; Ecological monitoring ; Feature extraction ; Feature maps ; Image processing ; Image segmentation ; Machine learning ; Mangrove swamps ; Mangroves ; Monitoring methods ; Nature reserves ; Remote sensing ; Satellite imagery ; Segmentation ; Semantics ; Supervision</subject><ispartof>Forests, 2024-01, Vol.15 (1), p.127</ispartof><rights>2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c252t-21d12a18c0b06eeeb22a137e46bc1226139d9945be2efba480babf16e11258293</cites><orcidid>0000-0001-6358-0274</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27901,27902</link.rule.ids></links><search><creatorcontrib>Dong, Heng</creatorcontrib><creatorcontrib>Gao, Yifan</creatorcontrib><creatorcontrib>Chen, Riqing</creatorcontrib><creatorcontrib>Wei, Lifang</creatorcontrib><title>MangroveSeg: Deep-Supervision-Guided Feature Aggregation Network for Mangrove Detection and Segmentation in Satellite Images</title><title>Forests</title><description>Mangrove forests are significant participants in coastal ecological environment systems. For the development of protection strategies, it is crucial to automatically and accurately detect the distribution and area of mangroves using satellite images. Although many deep-learning-based mangrove detection and segmentation algorithms have made notable progress, the complex regional structures and the great similarity between mangroves and the surrounding environment, as well as the diversity of mangroves, render the task still challenging. To cover these issues, we propose a novel deep-supervision-guided feature aggregation network for mangrove detection and segmentation called MangroveSeg, which is based on a U-shaped structure with ResNet, combining an attention mechanism and a multi-scale feature extraction framework. We also consider the detection and segmentation of mangroves as camouflage detection problems for the improvement and enhancement of accuracy. To determine more information from extracted feature maps in a hidden layer, a deep supervision model is introduced in up-sampling to enhance feature representation. The spatial attention mechanism with attention gates is utilized to highlight significant regions and suppress task-independent feature responses. The feature fusion module can obtain multi-scale information by binding each layer to the underlying information and update feature mappings. We validated our framework for mangrove detection and segmentation using a satellite image dataset, which includes 4000 images comprising 256 × 256 pixels; we used 3002 for training and 998 for testing. The satellite images dataset was obtained from the Dongzhaigang National Nature Reserve located in Haikou City, Hainan Province, China. The proposed method achieved a 89.58% overall accuracy, 89.02% precision, and 80.7% mIoU. We also used the trained MangroveSeg model to detect mangroves on satellite images from other regions. We evaluated the statistical square measure of some mangrove areas and found that the evaluation accuracy can reach 96% using MangroveSeg. The proposed MangroveSeg model can automatically and accurately detect the distribution and area of mangroves from satellite images, which provides a method for monitoring the ecological environment.</description><subject>Accuracy</subject><subject>Algorithms</subject><subject>Annotations</subject><subject>Coastal ecology</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>Ecological monitoring</subject><subject>Feature extraction</subject><subject>Feature maps</subject><subject>Image processing</subject><subject>Image segmentation</subject><subject>Machine learning</subject><subject>Mangrove swamps</subject><subject>Mangroves</subject><subject>Monitoring methods</subject><subject>Nature reserves</subject><subject>Remote sensing</subject><subject>Satellite imagery</subject><subject>Segmentation</subject><subject>Semantics</subject><subject>Supervision</subject><issn>1999-4907</issn><issn>1999-4907</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpNkMFOwzAQRC0EElXhwB9Y4sQh4HXiJOZWFVoqFTgUzpGdbKKUNg62U4TEx2MoIPayu5rRG2kIOQN2GceSXdUgGDDg2QEZgZQySiTLDv_dx-TUuTULI7Jc8mREPu5V11izwxU21_QGsY9WQ49217rWdNF8aCus6AyVHyzSSdNYbJQPEn1A_2bsC62Npb-QAPBYfsuqq2hgbrHze3_b0ZXyuNm0Huliqxp0J-SoVhuHpz97TJ5nt0_Tu2j5OF9MJ8uo5IL7iEMFXEFeMs1SRNQ8fHGGSapL4DyFWFZSJkIjx1qrJGda6RpSBOAi5zIek_M9t7fmdUDni7UZbBciCy4hz4QUaRJcF3tXaY1zFuuit-1W2fcCWPHVb_HXb_wJUnVtyg</recordid><startdate>20240101</startdate><enddate>20240101</enddate><creator>Dong, Heng</creator><creator>Gao, Yifan</creator><creator>Chen, Riqing</creator><creator>Wei, Lifang</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7SN</scope><scope>7SS</scope><scope>7X2</scope><scope>8FE</scope><scope>8FH</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AEUYN</scope><scope>AFKRA</scope><scope>ATCPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BHPHI</scope><scope>BKSAR</scope><scope>C1K</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>M0K</scope><scope>PATMY</scope><scope>PCBAR</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PYCSY</scope><orcidid>https://orcid.org/0000-0001-6358-0274</orcidid></search><sort><creationdate>20240101</creationdate><title>MangroveSeg: Deep-Supervision-Guided Feature Aggregation Network for Mangrove Detection and Segmentation in Satellite Images</title><author>Dong, Heng ; Gao, Yifan ; Chen, Riqing ; Wei, Lifang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c252t-21d12a18c0b06eeeb22a137e46bc1226139d9945be2efba480babf16e11258293</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Algorithms</topic><topic>Annotations</topic><topic>Coastal ecology</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>Ecological monitoring</topic><topic>Feature extraction</topic><topic>Feature maps</topic><topic>Image processing</topic><topic>Image segmentation</topic><topic>Machine learning</topic><topic>Mangrove swamps</topic><topic>Mangroves</topic><topic>Monitoring methods</topic><topic>Nature reserves</topic><topic>Remote sensing</topic><topic>Satellite imagery</topic><topic>Segmentation</topic><topic>Semantics</topic><topic>Supervision</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Dong, Heng</creatorcontrib><creatorcontrib>Gao, Yifan</creatorcontrib><creatorcontrib>Chen, Riqing</creatorcontrib><creatorcontrib>Wei, Lifang</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Ecology Abstracts</collection><collection>Entomology Abstracts (Full archive)</collection><collection>Agricultural Science Collection</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest One Sustainability</collection><collection>ProQuest Central UK/Ireland</collection><collection>Agricultural &amp; Environmental Science Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Natural Science Collection</collection><collection>Earth, Atmospheric &amp; Aquatic Science Collection</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>Agricultural Science Database</collection><collection>Environmental Science Database</collection><collection>Earth, Atmospheric &amp; Aquatic Science Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Environmental Science Collection</collection><jtitle>Forests</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Dong, Heng</au><au>Gao, Yifan</au><au>Chen, Riqing</au><au>Wei, Lifang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>MangroveSeg: Deep-Supervision-Guided Feature Aggregation Network for Mangrove Detection and Segmentation in Satellite Images</atitle><jtitle>Forests</jtitle><date>2024-01-01</date><risdate>2024</risdate><volume>15</volume><issue>1</issue><spage>127</spage><pages>127-</pages><issn>1999-4907</issn><eissn>1999-4907</eissn><abstract>Mangrove forests are significant participants in coastal ecological environment systems. For the development of protection strategies, it is crucial to automatically and accurately detect the distribution and area of mangroves using satellite images. Although many deep-learning-based mangrove detection and segmentation algorithms have made notable progress, the complex regional structures and the great similarity between mangroves and the surrounding environment, as well as the diversity of mangroves, render the task still challenging. To cover these issues, we propose a novel deep-supervision-guided feature aggregation network for mangrove detection and segmentation called MangroveSeg, which is based on a U-shaped structure with ResNet, combining an attention mechanism and a multi-scale feature extraction framework. We also consider the detection and segmentation of mangroves as camouflage detection problems for the improvement and enhancement of accuracy. To determine more information from extracted feature maps in a hidden layer, a deep supervision model is introduced in up-sampling to enhance feature representation. The spatial attention mechanism with attention gates is utilized to highlight significant regions and suppress task-independent feature responses. The feature fusion module can obtain multi-scale information by binding each layer to the underlying information and update feature mappings. We validated our framework for mangrove detection and segmentation using a satellite image dataset, which includes 4000 images comprising 256 × 256 pixels; we used 3002 for training and 998 for testing. The satellite images dataset was obtained from the Dongzhaigang National Nature Reserve located in Haikou City, Hainan Province, China. The proposed method achieved a 89.58% overall accuracy, 89.02% precision, and 80.7% mIoU. We also used the trained MangroveSeg model to detect mangroves on satellite images from other regions. We evaluated the statistical square measure of some mangrove areas and found that the evaluation accuracy can reach 96% using MangroveSeg. The proposed MangroveSeg model can automatically and accurately detect the distribution and area of mangroves from satellite images, which provides a method for monitoring the ecological environment.</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/f15010127</doi><orcidid>https://orcid.org/0000-0001-6358-0274</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1999-4907
ispartof Forests, 2024-01, Vol.15 (1), p.127
issn 1999-4907
1999-4907
language eng
recordid cdi_proquest_journals_2918759564
source MDPI - Multidisciplinary Digital Publishing Institute; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals
subjects Accuracy
Algorithms
Annotations
Coastal ecology
Datasets
Deep learning
Ecological monitoring
Feature extraction
Feature maps
Image processing
Image segmentation
Machine learning
Mangrove swamps
Mangroves
Monitoring methods
Nature reserves
Remote sensing
Satellite imagery
Segmentation
Semantics
Supervision
title MangroveSeg: Deep-Supervision-Guided Feature Aggregation Network for Mangrove Detection and Segmentation in Satellite Images
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-16T23%3A43%3A40IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=MangroveSeg:%20Deep-Supervision-Guided%20Feature%20Aggregation%20Network%20for%20Mangrove%20Detection%20and%20Segmentation%20in%20Satellite%20Images&rft.jtitle=Forests&rft.au=Dong,%20Heng&rft.date=2024-01-01&rft.volume=15&rft.issue=1&rft.spage=127&rft.pages=127-&rft.issn=1999-4907&rft.eissn=1999-4907&rft_id=info:doi/10.3390/f15010127&rft_dat=%3Cproquest_cross%3E2918759564%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2918759564&rft_id=info:pmid/&rfr_iscdi=true