Regional Prediction-Aware Network With Cross-Scale Self-Attention for Ship Detection in SAR Images
Deep learning algorithms have been widely used in ship detection with synthetic aperture radar (SAR). However, the complex background, clutter noise, and large span of ship sizes have adverse effects on the feature extraction, which seriously limits the ship detection accuracy. To address this issue...
Gespeichert in:
| Veröffentlicht in: | IEEE geoscience and remote sensing letters 2022, Vol.19, p.1-5 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 5 |
|---|---|
| container_issue | |
| container_start_page | 1 |
| container_title | IEEE geoscience and remote sensing letters |
| container_volume | 19 |
| creator | Zhang, Lili Liu, Yuxuan Huang, Yufeng Qu, Lele |
| description | Deep learning algorithms have been widely used in ship detection with synthetic aperture radar (SAR). However, the complex background, clutter noise, and large span of ship sizes have adverse effects on the feature extraction, which seriously limits the ship detection accuracy. To address this issue, a cross-scale regional prediction-aware network (CSRP-Net) is developed to advance the ship detection performance in SAR images. First, the cross-scale self-attention (CSSA) module is designed to suppress the influence of noise and complex backgrounds and enhance the ability to detect multiscale targets. Furthermore, a regional prediction-aware one-to-one (RPOTO) label assignment is proposed to select the foreground samples more conducive to classification and regression in the training stage. Extensive experiments have proved that the designed method can significantly improve the detection performance against several start-of-the-art algorithms on two classical benchmark datasets. |
| doi_str_mv | 10.1109/LGRS.2022.3212073 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_journals_2727046054</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9911650</ieee_id><sourcerecordid>2727046054</sourcerecordid><originalsourceid>FETCH-LOGICAL-c293t-a2ffea163a398e24b2b3d9c4ed9aff80e092c7b32324299d6ceb74387b96652f3</originalsourceid><addsrcrecordid>eNo9kF1LwzAUhoMoOKc_QLwJeJ2ZnPQrl2XqHAyVVdG7kLYnW2e3zqRj-O9t3fDqnAPP-8J5CLkWfCQEV3ezyTwbAQcYSRDAY3lCBiIME8bDWJz2exCyUCWf5-TC-xXnECRJPCD5HBdVszE1fXVYVkXbHSzdG4f0Gdt9477oR9Uu6dg13rOsMDXSDGvL0rbFTU9T2ziaLastvccW_wpotaFZOqfTtVmgvyRn1tQer45zSN4fH97GT2z2MpmO0xkrQMmWGbAWjYikkSpBCHLIZamKAEtlrE04cgVFnEuQEIBSZVRgHgcyiXMVRSFYOSS3h96ta7536Fu9anaue81riCHmQcTDoKPEgSr6jxxavXXV2rgfLbjuVepepe5V6qPKLnNzyFSI-M8rJUQUcvkLmthvZQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2727046054</pqid></control><display><type>article</type><title>Regional Prediction-Aware Network With Cross-Scale Self-Attention for Ship Detection in SAR Images</title><source>IEEE Electronic Library (IEL)</source><creator>Zhang, Lili ; Liu, Yuxuan ; Huang, Yufeng ; Qu, Lele</creator><creatorcontrib>Zhang, Lili ; Liu, Yuxuan ; Huang, Yufeng ; Qu, Lele</creatorcontrib><description>Deep learning algorithms have been widely used in ship detection with synthetic aperture radar (SAR). However, the complex background, clutter noise, and large span of ship sizes have adverse effects on the feature extraction, which seriously limits the ship detection accuracy. To address this issue, a cross-scale regional prediction-aware network (CSRP-Net) is developed to advance the ship detection performance in SAR images. First, the cross-scale self-attention (CSSA) module is designed to suppress the influence of noise and complex backgrounds and enhance the ability to detect multiscale targets. Furthermore, a regional prediction-aware one-to-one (RPOTO) label assignment is proposed to select the foreground samples more conducive to classification and regression in the training stage. Extensive experiments have proved that the designed method can significantly improve the detection performance against several start-of-the-art algorithms on two classical benchmark datasets.</description><identifier>ISSN: 1545-598X</identifier><identifier>EISSN: 1558-0571</identifier><identifier>DOI: 10.1109/LGRS.2022.3212073</identifier><identifier>CODEN: IGRSBY</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Algorithms ; Background noise ; Classification algorithms ; Clutter ; Cross-scale self-attention (CSSA) ; Deep learning ; Detection ; Feature extraction ; label assignment ; Machine learning ; Marine vehicles ; object detection ; Prediction algorithms ; Predictions ; Radar detection ; Radar polarimetry ; Regional development ; SAR (radar) ; Synthetic aperture radar ; synthetic aperture radar (SAR) ; Target detection ; Training</subject><ispartof>IEEE geoscience and remote sensing letters, 2022, Vol.19, p.1-5</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c293t-a2ffea163a398e24b2b3d9c4ed9aff80e092c7b32324299d6ceb74387b96652f3</citedby><cites>FETCH-LOGICAL-c293t-a2ffea163a398e24b2b3d9c4ed9aff80e092c7b32324299d6ceb74387b96652f3</cites><orcidid>0000-0002-2794-8892 ; 0000-0002-9287-3612 ; 0000-0003-2852-8555</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9911650$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,4010,27900,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9911650$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Zhang, Lili</creatorcontrib><creatorcontrib>Liu, Yuxuan</creatorcontrib><creatorcontrib>Huang, Yufeng</creatorcontrib><creatorcontrib>Qu, Lele</creatorcontrib><title>Regional Prediction-Aware Network With Cross-Scale Self-Attention for Ship Detection in SAR Images</title><title>IEEE geoscience and remote sensing letters</title><addtitle>LGRS</addtitle><description>Deep learning algorithms have been widely used in ship detection with synthetic aperture radar (SAR). However, the complex background, clutter noise, and large span of ship sizes have adverse effects on the feature extraction, which seriously limits the ship detection accuracy. To address this issue, a cross-scale regional prediction-aware network (CSRP-Net) is developed to advance the ship detection performance in SAR images. First, the cross-scale self-attention (CSSA) module is designed to suppress the influence of noise and complex backgrounds and enhance the ability to detect multiscale targets. Furthermore, a regional prediction-aware one-to-one (RPOTO) label assignment is proposed to select the foreground samples more conducive to classification and regression in the training stage. Extensive experiments have proved that the designed method can significantly improve the detection performance against several start-of-the-art algorithms on two classical benchmark datasets.</description><subject>Algorithms</subject><subject>Background noise</subject><subject>Classification algorithms</subject><subject>Clutter</subject><subject>Cross-scale self-attention (CSSA)</subject><subject>Deep learning</subject><subject>Detection</subject><subject>Feature extraction</subject><subject>label assignment</subject><subject>Machine learning</subject><subject>Marine vehicles</subject><subject>object detection</subject><subject>Prediction algorithms</subject><subject>Predictions</subject><subject>Radar detection</subject><subject>Radar polarimetry</subject><subject>Regional development</subject><subject>SAR (radar)</subject><subject>Synthetic aperture radar</subject><subject>synthetic aperture radar (SAR)</subject><subject>Target detection</subject><subject>Training</subject><issn>1545-598X</issn><issn>1558-0571</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kF1LwzAUhoMoOKc_QLwJeJ2ZnPQrl2XqHAyVVdG7kLYnW2e3zqRj-O9t3fDqnAPP-8J5CLkWfCQEV3ezyTwbAQcYSRDAY3lCBiIME8bDWJz2exCyUCWf5-TC-xXnECRJPCD5HBdVszE1fXVYVkXbHSzdG4f0Gdt9477oR9Uu6dg13rOsMDXSDGvL0rbFTU9T2ziaLastvccW_wpotaFZOqfTtVmgvyRn1tQer45zSN4fH97GT2z2MpmO0xkrQMmWGbAWjYikkSpBCHLIZamKAEtlrE04cgVFnEuQEIBSZVRgHgcyiXMVRSFYOSS3h96ta7536Fu9anaue81riCHmQcTDoKPEgSr6jxxavXXV2rgfLbjuVepepe5V6qPKLnNzyFSI-M8rJUQUcvkLmthvZQ</recordid><startdate>2022</startdate><enddate>2022</enddate><creator>Zhang, Lili</creator><creator>Liu, Yuxuan</creator><creator>Huang, Yufeng</creator><creator>Qu, Lele</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TG</scope><scope>7UA</scope><scope>8FD</scope><scope>C1K</scope><scope>F1W</scope><scope>FR3</scope><scope>H8D</scope><scope>H96</scope><scope>JQ2</scope><scope>KL.</scope><scope>KR7</scope><scope>L.G</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-2794-8892</orcidid><orcidid>https://orcid.org/0000-0002-9287-3612</orcidid><orcidid>https://orcid.org/0000-0003-2852-8555</orcidid></search><sort><creationdate>2022</creationdate><title>Regional Prediction-Aware Network With Cross-Scale Self-Attention for Ship Detection in SAR Images</title><author>Zhang, Lili ; Liu, Yuxuan ; Huang, Yufeng ; Qu, Lele</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c293t-a2ffea163a398e24b2b3d9c4ed9aff80e092c7b32324299d6ceb74387b96652f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Algorithms</topic><topic>Background noise</topic><topic>Classification algorithms</topic><topic>Clutter</topic><topic>Cross-scale self-attention (CSSA)</topic><topic>Deep learning</topic><topic>Detection</topic><topic>Feature extraction</topic><topic>label assignment</topic><topic>Machine learning</topic><topic>Marine vehicles</topic><topic>object detection</topic><topic>Prediction algorithms</topic><topic>Predictions</topic><topic>Radar detection</topic><topic>Radar polarimetry</topic><topic>Regional development</topic><topic>SAR (radar)</topic><topic>Synthetic aperture radar</topic><topic>synthetic aperture radar (SAR)</topic><topic>Target detection</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Lili</creatorcontrib><creatorcontrib>Liu, Yuxuan</creatorcontrib><creatorcontrib>Huang, Yufeng</creatorcontrib><creatorcontrib>Qu, Lele</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Meteorological & Geoastrophysical Abstracts</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 & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources</collection><collection>ProQuest Computer Science Collection</collection><collection>Meteorological & Geoastrophysical Abstracts - Academic</collection><collection>Civil Engineering Abstracts</collection><collection>Aquatic Science & Fisheries Abstracts (ASFA) Professional</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE geoscience and remote sensing letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zhang, Lili</au><au>Liu, Yuxuan</au><au>Huang, Yufeng</au><au>Qu, Lele</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Regional Prediction-Aware Network With Cross-Scale Self-Attention for Ship Detection in SAR Images</atitle><jtitle>IEEE geoscience and remote sensing letters</jtitle><stitle>LGRS</stitle><date>2022</date><risdate>2022</risdate><volume>19</volume><spage>1</spage><epage>5</epage><pages>1-5</pages><issn>1545-598X</issn><eissn>1558-0571</eissn><coden>IGRSBY</coden><abstract>Deep learning algorithms have been widely used in ship detection with synthetic aperture radar (SAR). However, the complex background, clutter noise, and large span of ship sizes have adverse effects on the feature extraction, which seriously limits the ship detection accuracy. To address this issue, a cross-scale regional prediction-aware network (CSRP-Net) is developed to advance the ship detection performance in SAR images. First, the cross-scale self-attention (CSSA) module is designed to suppress the influence of noise and complex backgrounds and enhance the ability to detect multiscale targets. Furthermore, a regional prediction-aware one-to-one (RPOTO) label assignment is proposed to select the foreground samples more conducive to classification and regression in the training stage. Extensive experiments have proved that the designed method can significantly improve the detection performance against several start-of-the-art algorithms on two classical benchmark datasets.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/LGRS.2022.3212073</doi><tpages>5</tpages><orcidid>https://orcid.org/0000-0002-2794-8892</orcidid><orcidid>https://orcid.org/0000-0002-9287-3612</orcidid><orcidid>https://orcid.org/0000-0003-2852-8555</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1545-598X |
| ispartof | IEEE geoscience and remote sensing letters, 2022, Vol.19, p.1-5 |
| issn | 1545-598X 1558-0571 |
| language | eng |
| recordid | cdi_proquest_journals_2727046054 |
| source | IEEE Electronic Library (IEL) |
| subjects | Algorithms Background noise Classification algorithms Clutter Cross-scale self-attention (CSSA) Deep learning Detection Feature extraction label assignment Machine learning Marine vehicles object detection Prediction algorithms Predictions Radar detection Radar polarimetry Regional development SAR (radar) Synthetic aperture radar synthetic aperture radar (SAR) Target detection Training |
| title | Regional Prediction-Aware Network With Cross-Scale Self-Attention for Ship Detection in SAR Images |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T09%3A26%3A49IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Regional%20Prediction-Aware%20Network%20With%20Cross-Scale%20Self-Attention%20for%20Ship%20Detection%20in%20SAR%20Images&rft.jtitle=IEEE%20geoscience%20and%20remote%20sensing%20letters&rft.au=Zhang,%20Lili&rft.date=2022&rft.volume=19&rft.spage=1&rft.epage=5&rft.pages=1-5&rft.issn=1545-598X&rft.eissn=1558-0571&rft.coden=IGRSBY&rft_id=info:doi/10.1109/LGRS.2022.3212073&rft_dat=%3Cproquest_RIE%3E2727046054%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2727046054&rft_id=info:pmid/&rft_ieee_id=9911650&rfr_iscdi=true |