Scattering-Keypoint-Guided Network for Oriented Ship Detection in High-Resolution and Large-Scale SAR Images

Ship detection in synthetic aperture radar (SAR) images is a significant and challenging task. Recently, deep convolutional neural networks have been applied to solve the detection problem and made a great breakthrough. Previous works mostly rely on the manually designed anchor boxes to search for t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE journal of selected topics in applied earth observations and remote sensing 2021, Vol.14, p.11162-11178
Hauptverfasser: Fu, Kun, Fu, Jiamei, Wang, Zhirui, Sun, Xian
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 11178
container_issue
container_start_page 11162
container_title IEEE journal of selected topics in applied earth observations and remote sensing
container_volume 14
creator Fu, Kun
Fu, Jiamei
Wang, Zhirui
Sun, Xian
description Ship detection in synthetic aperture radar (SAR) images is a significant and challenging task. Recently, deep convolutional neural networks have been applied to solve the detection problem and made a great breakthrough. Previous works mostly rely on the manually designed anchor boxes to search for the region of interests, which is less flexible and suffers from a heavy computational load. Moreover, these detectors have limited performance in large-scale and complex scenes due to the strong interference of inshore background and the variability of object imaging characteristics. In this article, a novel ship detection method based on the scattering-keypoint-guided network is proposed to remedy these problems. First, an anchor-free network is built to eliminate the effect of anchor boxes, in which a more robust representation scheme is designed for the arbitrary oriented objects. Second, a context-aware feature selection module is introduced to dynamically learn both local and context features. In this process, the semantic information of objects can be enhanced while suppressing the background interference. Third, according to the SAR imaging mechanism, a set of scattering keypoints is defined to describe the local scattering regions and reflect the discriminative structural characteristics of ships. Based on this conception, a novel feature adaption method is proposed with the purpose of dealing with the imaging variability issue. Furthermore, to demonstrate the effectiveness of the proposed improvements, we build the Gaofen-3 ship detection dataset. Meanwhile, the public SAR ship detection dataset is introduced to verify the robustness and generalization ability of the detector. Experimental results on these two datasets show that the proposed method achieves the state-of-the-art performance.
doi_str_mv 10.1109/JSTARS.2021.3109469
format Article
fullrecord <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_ieee_primary_9528024</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9528024</ieee_id><doaj_id>oai_doaj_org_article_7b60d98163dd47e4b1214bbd1ca6a2f9</doaj_id><sourcerecordid>2596786173</sourcerecordid><originalsourceid>FETCH-LOGICAL-c408t-35bac408d46b5a854c8b4dfd8bb25d6e8fa5f6d28ecb4e17442d3f0a8907987a3</originalsourceid><addsrcrecordid>eNo9kc1u2zAQhImiBeqmfYJcCPQsl_8ij0baJm6MBLDSM0GKK4WuIroUjSJvXzkKctrFh5nZBQahS0rWlBLz7VfzsNk3a0YYXfMZCGXeoRWjklZUcvkerajhpqKCiI_o0zQdCFGsNnyFhqZ1pUCOY1_dwvMxxbFU16cYIOA7KP9S_oO7lPF9jjCWGTaP8Yi_Q4G2xDTiOOKb2D9We5jScHpBbgx453IP1Zw9AG42e7x9cj1Mn9GHzg0TfHmdF-j3zx8PVzfV7v56e7XZVa0gulRcenfeglBeOi1Fq70IXdDeMxkU6M7JTgWmofUCaC0EC7wjThtSG107foG2S25I7mCPOT65_GyTi_YFpNxbl0tsB7C1VyQYTRUPQdQgPGVUeB9o65RjnZmzvi5Zx5z-nmAq9pBOeZzft0waVWtFaz6r-KJqc5qmDN3bVUrsuSK7VGTPFdnXimbX5eKKAPDmMJJpwgT_D5yTjb4</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2596786173</pqid></control><display><type>article</type><title>Scattering-Keypoint-Guided Network for Oriented Ship Detection in High-Resolution and Large-Scale SAR Images</title><source>DOAJ Directory of Open Access Journals</source><source>EZB-FREE-00999 freely available EZB journals</source><creator>Fu, Kun ; Fu, Jiamei ; Wang, Zhirui ; Sun, Xian</creator><creatorcontrib>Fu, Kun ; Fu, Jiamei ; Wang, Zhirui ; Sun, Xian</creatorcontrib><description>Ship detection in synthetic aperture radar (SAR) images is a significant and challenging task. Recently, deep convolutional neural networks have been applied to solve the detection problem and made a great breakthrough. Previous works mostly rely on the manually designed anchor boxes to search for the region of interests, which is less flexible and suffers from a heavy computational load. Moreover, these detectors have limited performance in large-scale and complex scenes due to the strong interference of inshore background and the variability of object imaging characteristics. In this article, a novel ship detection method based on the scattering-keypoint-guided network is proposed to remedy these problems. First, an anchor-free network is built to eliminate the effect of anchor boxes, in which a more robust representation scheme is designed for the arbitrary oriented objects. Second, a context-aware feature selection module is introduced to dynamically learn both local and context features. In this process, the semantic information of objects can be enhanced while suppressing the background interference. Third, according to the SAR imaging mechanism, a set of scattering keypoints is defined to describe the local scattering regions and reflect the discriminative structural characteristics of ships. Based on this conception, a novel feature adaption method is proposed with the purpose of dealing with the imaging variability issue. Furthermore, to demonstrate the effectiveness of the proposed improvements, we build the Gaofen-3 ship detection dataset. Meanwhile, the public SAR ship detection dataset is introduced to verify the robustness and generalization ability of the detector. Experimental results on these two datasets show that the proposed method achieves the state-of-the-art performance.</description><identifier>ISSN: 1939-1404</identifier><identifier>EISSN: 2151-1535</identifier><identifier>DOI: 10.1109/JSTARS.2021.3109469</identifier><identifier>CODEN: IJSTHZ</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Anchors ; Artificial neural networks ; Boxes ; Computer applications ; Context ; Context-aware feature selection (CFS) ; convolutional neural network (CNN) ; Datasets ; Detection ; Detectors ; Feature extraction ; Image resolution ; Imaging ; Imaging techniques ; Information processing ; Interference ; Marine vehicles ; Neural networks ; oriented ship detection ; Radar detection ; Radar imaging ; Radar polarimetry ; SAR (radar) ; Scattering ; scattering keypoints ; Ships ; Synthetic aperture radar ; synthetic aperture radar (SAR) ; Variability</subject><ispartof>IEEE journal of selected topics in applied earth observations and remote sensing, 2021, Vol.14, p.11162-11178</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c408t-35bac408d46b5a854c8b4dfd8bb25d6e8fa5f6d28ecb4e17442d3f0a8907987a3</citedby><cites>FETCH-LOGICAL-c408t-35bac408d46b5a854c8b4dfd8bb25d6e8fa5f6d28ecb4e17442d3f0a8907987a3</cites><orcidid>0000-0003-0180-6877 ; 0000-0002-0038-9816 ; 0000-0002-0397-3110 ; 0000-0003-2877-0384</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,864,2102,4024,27923,27924,27925</link.rule.ids></links><search><creatorcontrib>Fu, Kun</creatorcontrib><creatorcontrib>Fu, Jiamei</creatorcontrib><creatorcontrib>Wang, Zhirui</creatorcontrib><creatorcontrib>Sun, Xian</creatorcontrib><title>Scattering-Keypoint-Guided Network for Oriented Ship Detection in High-Resolution and Large-Scale SAR Images</title><title>IEEE journal of selected topics in applied earth observations and remote sensing</title><addtitle>JSTARS</addtitle><description>Ship detection in synthetic aperture radar (SAR) images is a significant and challenging task. Recently, deep convolutional neural networks have been applied to solve the detection problem and made a great breakthrough. Previous works mostly rely on the manually designed anchor boxes to search for the region of interests, which is less flexible and suffers from a heavy computational load. Moreover, these detectors have limited performance in large-scale and complex scenes due to the strong interference of inshore background and the variability of object imaging characteristics. In this article, a novel ship detection method based on the scattering-keypoint-guided network is proposed to remedy these problems. First, an anchor-free network is built to eliminate the effect of anchor boxes, in which a more robust representation scheme is designed for the arbitrary oriented objects. Second, a context-aware feature selection module is introduced to dynamically learn both local and context features. In this process, the semantic information of objects can be enhanced while suppressing the background interference. Third, according to the SAR imaging mechanism, a set of scattering keypoints is defined to describe the local scattering regions and reflect the discriminative structural characteristics of ships. Based on this conception, a novel feature adaption method is proposed with the purpose of dealing with the imaging variability issue. Furthermore, to demonstrate the effectiveness of the proposed improvements, we build the Gaofen-3 ship detection dataset. Meanwhile, the public SAR ship detection dataset is introduced to verify the robustness and generalization ability of the detector. Experimental results on these two datasets show that the proposed method achieves the state-of-the-art performance.</description><subject>Anchors</subject><subject>Artificial neural networks</subject><subject>Boxes</subject><subject>Computer applications</subject><subject>Context</subject><subject>Context-aware feature selection (CFS)</subject><subject>convolutional neural network (CNN)</subject><subject>Datasets</subject><subject>Detection</subject><subject>Detectors</subject><subject>Feature extraction</subject><subject>Image resolution</subject><subject>Imaging</subject><subject>Imaging techniques</subject><subject>Information processing</subject><subject>Interference</subject><subject>Marine vehicles</subject><subject>Neural networks</subject><subject>oriented ship detection</subject><subject>Radar detection</subject><subject>Radar imaging</subject><subject>Radar polarimetry</subject><subject>SAR (radar)</subject><subject>Scattering</subject><subject>scattering keypoints</subject><subject>Ships</subject><subject>Synthetic aperture radar</subject><subject>synthetic aperture radar (SAR)</subject><subject>Variability</subject><issn>1939-1404</issn><issn>2151-1535</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><sourceid>DOA</sourceid><recordid>eNo9kc1u2zAQhImiBeqmfYJcCPQsl_8ij0baJm6MBLDSM0GKK4WuIroUjSJvXzkKctrFh5nZBQahS0rWlBLz7VfzsNk3a0YYXfMZCGXeoRWjklZUcvkerajhpqKCiI_o0zQdCFGsNnyFhqZ1pUCOY1_dwvMxxbFU16cYIOA7KP9S_oO7lPF9jjCWGTaP8Yi_Q4G2xDTiOOKb2D9We5jScHpBbgx453IP1Zw9AG42e7x9cj1Mn9GHzg0TfHmdF-j3zx8PVzfV7v56e7XZVa0gulRcenfeglBeOi1Fq70IXdDeMxkU6M7JTgWmofUCaC0EC7wjThtSG107foG2S25I7mCPOT65_GyTi_YFpNxbl0tsB7C1VyQYTRUPQdQgPGVUeB9o65RjnZmzvi5Zx5z-nmAq9pBOeZzft0waVWtFaz6r-KJqc5qmDN3bVUrsuSK7VGTPFdnXimbX5eKKAPDmMJJpwgT_D5yTjb4</recordid><startdate>2021</startdate><enddate>2021</enddate><creator>Fu, Kun</creator><creator>Fu, Jiamei</creator><creator>Wang, Zhirui</creator><creator>Sun, Xian</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7UA</scope><scope>8FD</scope><scope>C1K</scope><scope>F1W</scope><scope>FR3</scope><scope>H8D</scope><scope>H96</scope><scope>KR7</scope><scope>L.G</scope><scope>L7M</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0003-0180-6877</orcidid><orcidid>https://orcid.org/0000-0002-0038-9816</orcidid><orcidid>https://orcid.org/0000-0002-0397-3110</orcidid><orcidid>https://orcid.org/0000-0003-2877-0384</orcidid></search><sort><creationdate>2021</creationdate><title>Scattering-Keypoint-Guided Network for Oriented Ship Detection in High-Resolution and Large-Scale SAR Images</title><author>Fu, Kun ; Fu, Jiamei ; Wang, Zhirui ; Sun, Xian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c408t-35bac408d46b5a854c8b4dfd8bb25d6e8fa5f6d28ecb4e17442d3f0a8907987a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Anchors</topic><topic>Artificial neural networks</topic><topic>Boxes</topic><topic>Computer applications</topic><topic>Context</topic><topic>Context-aware feature selection (CFS)</topic><topic>convolutional neural network (CNN)</topic><topic>Datasets</topic><topic>Detection</topic><topic>Detectors</topic><topic>Feature extraction</topic><topic>Image resolution</topic><topic>Imaging</topic><topic>Imaging techniques</topic><topic>Information processing</topic><topic>Interference</topic><topic>Marine vehicles</topic><topic>Neural networks</topic><topic>oriented ship detection</topic><topic>Radar detection</topic><topic>Radar imaging</topic><topic>Radar polarimetry</topic><topic>SAR (radar)</topic><topic>Scattering</topic><topic>scattering keypoints</topic><topic>Ships</topic><topic>Synthetic aperture radar</topic><topic>synthetic aperture radar (SAR)</topic><topic>Variability</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Fu, Kun</creatorcontrib><creatorcontrib>Fu, Jiamei</creatorcontrib><creatorcontrib>Wang, Zhirui</creatorcontrib><creatorcontrib>Sun, Xian</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Water Resources Abstracts</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ASFA: Aquatic Sciences and Fisheries Abstracts</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy &amp; Non-Living Resources</collection><collection>Civil Engineering Abstracts</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) Professional</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>IEEE journal of selected topics in applied earth observations and remote sensing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Fu, Kun</au><au>Fu, Jiamei</au><au>Wang, Zhirui</au><au>Sun, Xian</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Scattering-Keypoint-Guided Network for Oriented Ship Detection in High-Resolution and Large-Scale SAR Images</atitle><jtitle>IEEE journal of selected topics in applied earth observations and remote sensing</jtitle><stitle>JSTARS</stitle><date>2021</date><risdate>2021</risdate><volume>14</volume><spage>11162</spage><epage>11178</epage><pages>11162-11178</pages><issn>1939-1404</issn><eissn>2151-1535</eissn><coden>IJSTHZ</coden><abstract>Ship detection in synthetic aperture radar (SAR) images is a significant and challenging task. Recently, deep convolutional neural networks have been applied to solve the detection problem and made a great breakthrough. Previous works mostly rely on the manually designed anchor boxes to search for the region of interests, which is less flexible and suffers from a heavy computational load. Moreover, these detectors have limited performance in large-scale and complex scenes due to the strong interference of inshore background and the variability of object imaging characteristics. In this article, a novel ship detection method based on the scattering-keypoint-guided network is proposed to remedy these problems. First, an anchor-free network is built to eliminate the effect of anchor boxes, in which a more robust representation scheme is designed for the arbitrary oriented objects. Second, a context-aware feature selection module is introduced to dynamically learn both local and context features. In this process, the semantic information of objects can be enhanced while suppressing the background interference. Third, according to the SAR imaging mechanism, a set of scattering keypoints is defined to describe the local scattering regions and reflect the discriminative structural characteristics of ships. Based on this conception, a novel feature adaption method is proposed with the purpose of dealing with the imaging variability issue. Furthermore, to demonstrate the effectiveness of the proposed improvements, we build the Gaofen-3 ship detection dataset. Meanwhile, the public SAR ship detection dataset is introduced to verify the robustness and generalization ability of the detector. Experimental results on these two datasets show that the proposed method achieves the state-of-the-art performance.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/JSTARS.2021.3109469</doi><tpages>17</tpages><orcidid>https://orcid.org/0000-0003-0180-6877</orcidid><orcidid>https://orcid.org/0000-0002-0038-9816</orcidid><orcidid>https://orcid.org/0000-0002-0397-3110</orcidid><orcidid>https://orcid.org/0000-0003-2877-0384</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1939-1404
ispartof IEEE journal of selected topics in applied earth observations and remote sensing, 2021, Vol.14, p.11162-11178
issn 1939-1404
2151-1535
language eng
recordid cdi_ieee_primary_9528024
source DOAJ Directory of Open Access Journals; EZB-FREE-00999 freely available EZB journals
subjects Anchors
Artificial neural networks
Boxes
Computer applications
Context
Context-aware feature selection (CFS)
convolutional neural network (CNN)
Datasets
Detection
Detectors
Feature extraction
Image resolution
Imaging
Imaging techniques
Information processing
Interference
Marine vehicles
Neural networks
oriented ship detection
Radar detection
Radar imaging
Radar polarimetry
SAR (radar)
Scattering
scattering keypoints
Ships
Synthetic aperture radar
synthetic aperture radar (SAR)
Variability
title Scattering-Keypoint-Guided Network for Oriented Ship Detection in High-Resolution and Large-Scale SAR Images
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T23%3A14%3A21IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Scattering-Keypoint-Guided%20Network%20for%20Oriented%20Ship%20Detection%20in%20High-Resolution%20and%20Large-Scale%20SAR%20Images&rft.jtitle=IEEE%20journal%20of%20selected%20topics%20in%20applied%20earth%20observations%20and%20remote%20sensing&rft.au=Fu,%20Kun&rft.date=2021&rft.volume=14&rft.spage=11162&rft.epage=11178&rft.pages=11162-11178&rft.issn=1939-1404&rft.eissn=2151-1535&rft.coden=IJSTHZ&rft_id=info:doi/10.1109/JSTARS.2021.3109469&rft_dat=%3Cproquest_ieee_%3E2596786173%3C/proquest_ieee_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2596786173&rft_id=info:pmid/&rft_ieee_id=9528024&rft_doaj_id=oai_doaj_org_article_7b60d98163dd47e4b1214bbd1ca6a2f9&rfr_iscdi=true