Improved YOLOv5 for aerial images based on attention mechanism
Object detection based on unmanned aerial vehicle(UAV) platforms is essential for both engineering and research. Complex scale problems in UAV application scenarios require strong regression localization capabilities from target detection algorithms. Nonetheless, due to the constraints of UAV platfo...
Gespeichert in:
| Veröffentlicht in: | IEEE access 2023-01, Vol.11, p.1-1 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1 |
|---|---|
| container_issue | |
| container_start_page | 1 |
| container_title | IEEE access |
| container_volume | 11 |
| creator | Li, Zebin Fan, Bangkui Xu, Yulong Sun, Renwu |
| description | Object detection based on unmanned aerial vehicle(UAV) platforms is essential for both engineering and research. Complex scale problems in UAV application scenarios require strong regression localization capabilities from target detection algorithms. Nonetheless, due to the constraints of UAV platform, it is difficult to increase accuracy by deepening the network. Therefore, this paper presents an improved YOLOv5 with an attention mechanism, consisting a Convolution-Swin Transformer Block(CSTB) utilizing Swin Transformer as well as a Convolution-block Attention Module(CBAM) to improve network positioning accuracy. In addition, this paper incorporates Bidirectional Feature Pyramid Network(BiFPN) [1], Spatial Pyramid Pooling-Fast(SPPF) and some network components to increase the average precision while maintaining the limited size of the model. Experiments on Visdrone2019 dataset show that the proposed approach can raise the mean Average Precision(mAP) by 5.4% compared to YOLOv5, with only 18% increase in model size. |
| doi_str_mv | 10.1109/ACCESS.2023.3277931 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_ieee_primary_10129865</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10129865</ieee_id><doaj_id>oai_doaj_org_article_faaeb1a4209349c893ad52b734f40abf</doaj_id><sourcerecordid>2864343795</sourcerecordid><originalsourceid>FETCH-LOGICAL-c409t-8b7c4d679b85308cc519c4c40d75ec7ab291ee17b368e5686595df5b9c75a6f53</originalsourceid><addsrcrecordid>eNpNUE1Lw0AQDaJgqf0Fegh4Tt3PbPYilFC1UOihevC0zG4mNaVt6m5a8N-7NUU6lxlm5r0385LknpIxpUQ_TcpyulyOGWF8zJlSmtOrZMBorjMueX59Ud8moxDWJEYRW1INkufZdu_bI1bp52K-OMq0bn0K6BvYpM0WVhhSCyGO210KXYe7ronVFt0X7JqwvUtuatgEHJ3zMPl4mb6Xb9l88TorJ_PMCaK7rLDKiSpX2haSk8I5SbUTcVYpiU6BZZoiUmV5XqDMi1xqWdXSaqck5LXkw2TW81YtrM3ex9P8j2mhMX-N1q8M-K5xGzQ1AFoKghHNhXaF5lBJZhUXtSBg68j12HPFx78PGDqzbg9-F883rMgFF1zpkyLvt5xvQ_BY_6tSYk6-m953c_LdnH2PqIce1SDiBYIyHZ_iv6o1fTw</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2864343795</pqid></control><display><type>article</type><title>Improved YOLOv5 for aerial images based on attention mechanism</title><source>IEEE Open Access Journals</source><source>DOAJ Directory of Open Access Journals</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Li, Zebin ; Fan, Bangkui ; Xu, Yulong ; Sun, Renwu</creator><creatorcontrib>Li, Zebin ; Fan, Bangkui ; Xu, Yulong ; Sun, Renwu</creatorcontrib><description>Object detection based on unmanned aerial vehicle(UAV) platforms is essential for both engineering and research. Complex scale problems in UAV application scenarios require strong regression localization capabilities from target detection algorithms. Nonetheless, due to the constraints of UAV platform, it is difficult to increase accuracy by deepening the network. Therefore, this paper presents an improved YOLOv5 with an attention mechanism, consisting a Convolution-Swin Transformer Block(CSTB) utilizing Swin Transformer as well as a Convolution-block Attention Module(CBAM) to improve network positioning accuracy. In addition, this paper incorporates Bidirectional Feature Pyramid Network(BiFPN) [1], Spatial Pyramid Pooling-Fast(SPPF) and some network components to increase the average precision while maintaining the limited size of the model. Experiments on Visdrone2019 dataset show that the proposed approach can raise the mean Average Precision(mAP) by 5.4% compared to YOLOv5, with only 18% increase in model size.</description><identifier>ISSN: 2169-3536</identifier><identifier>EISSN: 2169-3536</identifier><identifier>DOI: 10.1109/ACCESS.2023.3277931</identifier><identifier>CODEN: IAECCG</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Algorithms ; Attention ; Autonomous aerial vehicles ; Convolution ; Feature extraction ; Object detection ; Object recognition ; Target detection ; Training ; Transformers ; UAV ; Unmanned aerial vehicles ; YOLO</subject><ispartof>IEEE access, 2023-01, Vol.11, p.1-1</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c409t-8b7c4d679b85308cc519c4c40d75ec7ab291ee17b368e5686595df5b9c75a6f53</citedby><cites>FETCH-LOGICAL-c409t-8b7c4d679b85308cc519c4c40d75ec7ab291ee17b368e5686595df5b9c75a6f53</cites><orcidid>0000-0002-6552-2665 ; 0009-0001-6174-4762</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10129865$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,776,780,860,2096,27610,27901,27902,54908</link.rule.ids></links><search><creatorcontrib>Li, Zebin</creatorcontrib><creatorcontrib>Fan, Bangkui</creatorcontrib><creatorcontrib>Xu, Yulong</creatorcontrib><creatorcontrib>Sun, Renwu</creatorcontrib><title>Improved YOLOv5 for aerial images based on attention mechanism</title><title>IEEE access</title><addtitle>Access</addtitle><description>Object detection based on unmanned aerial vehicle(UAV) platforms is essential for both engineering and research. Complex scale problems in UAV application scenarios require strong regression localization capabilities from target detection algorithms. Nonetheless, due to the constraints of UAV platform, it is difficult to increase accuracy by deepening the network. Therefore, this paper presents an improved YOLOv5 with an attention mechanism, consisting a Convolution-Swin Transformer Block(CSTB) utilizing Swin Transformer as well as a Convolution-block Attention Module(CBAM) to improve network positioning accuracy. In addition, this paper incorporates Bidirectional Feature Pyramid Network(BiFPN) [1], Spatial Pyramid Pooling-Fast(SPPF) and some network components to increase the average precision while maintaining the limited size of the model. Experiments on Visdrone2019 dataset show that the proposed approach can raise the mean Average Precision(mAP) by 5.4% compared to YOLOv5, with only 18% increase in model size.</description><subject>Algorithms</subject><subject>Attention</subject><subject>Autonomous aerial vehicles</subject><subject>Convolution</subject><subject>Feature extraction</subject><subject>Object detection</subject><subject>Object recognition</subject><subject>Target detection</subject><subject>Training</subject><subject>Transformers</subject><subject>UAV</subject><subject>Unmanned aerial vehicles</subject><subject>YOLO</subject><issn>2169-3536</issn><issn>2169-3536</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><sourceid>DOA</sourceid><recordid>eNpNUE1Lw0AQDaJgqf0Fegh4Tt3PbPYilFC1UOihevC0zG4mNaVt6m5a8N-7NUU6lxlm5r0385LknpIxpUQ_TcpyulyOGWF8zJlSmtOrZMBorjMueX59Ud8moxDWJEYRW1INkufZdu_bI1bp52K-OMq0bn0K6BvYpM0WVhhSCyGO210KXYe7ronVFt0X7JqwvUtuatgEHJ3zMPl4mb6Xb9l88TorJ_PMCaK7rLDKiSpX2haSk8I5SbUTcVYpiU6BZZoiUmV5XqDMi1xqWdXSaqck5LXkw2TW81YtrM3ex9P8j2mhMX-N1q8M-K5xGzQ1AFoKghHNhXaF5lBJZhUXtSBg68j12HPFx78PGDqzbg9-F883rMgFF1zpkyLvt5xvQ_BY_6tSYk6-m953c_LdnH2PqIce1SDiBYIyHZ_iv6o1fTw</recordid><startdate>20230101</startdate><enddate>20230101</enddate><creator>Li, Zebin</creator><creator>Fan, Bangkui</creator><creator>Xu, Yulong</creator><creator>Sun, Renwu</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>7SC</scope><scope>7SP</scope><scope>7SR</scope><scope>8BQ</scope><scope>8FD</scope><scope>JG9</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-6552-2665</orcidid><orcidid>https://orcid.org/0009-0001-6174-4762</orcidid></search><sort><creationdate>20230101</creationdate><title>Improved YOLOv5 for aerial images based on attention mechanism</title><author>Li, Zebin ; Fan, Bangkui ; Xu, Yulong ; Sun, Renwu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c409t-8b7c4d679b85308cc519c4c40d75ec7ab291ee17b368e5686595df5b9c75a6f53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Algorithms</topic><topic>Attention</topic><topic>Autonomous aerial vehicles</topic><topic>Convolution</topic><topic>Feature extraction</topic><topic>Object detection</topic><topic>Object recognition</topic><topic>Target detection</topic><topic>Training</topic><topic>Transformers</topic><topic>UAV</topic><topic>Unmanned aerial vehicles</topic><topic>YOLO</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Li, Zebin</creatorcontrib><creatorcontrib>Fan, Bangkui</creatorcontrib><creatorcontrib>Xu, Yulong</creatorcontrib><creatorcontrib>Sun, Renwu</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>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>IEEE access</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Li, Zebin</au><au>Fan, Bangkui</au><au>Xu, Yulong</au><au>Sun, Renwu</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Improved YOLOv5 for aerial images based on attention mechanism</atitle><jtitle>IEEE access</jtitle><stitle>Access</stitle><date>2023-01-01</date><risdate>2023</risdate><volume>11</volume><spage>1</spage><epage>1</epage><pages>1-1</pages><issn>2169-3536</issn><eissn>2169-3536</eissn><coden>IAECCG</coden><abstract>Object detection based on unmanned aerial vehicle(UAV) platforms is essential for both engineering and research. Complex scale problems in UAV application scenarios require strong regression localization capabilities from target detection algorithms. Nonetheless, due to the constraints of UAV platform, it is difficult to increase accuracy by deepening the network. Therefore, this paper presents an improved YOLOv5 with an attention mechanism, consisting a Convolution-Swin Transformer Block(CSTB) utilizing Swin Transformer as well as a Convolution-block Attention Module(CBAM) to improve network positioning accuracy. In addition, this paper incorporates Bidirectional Feature Pyramid Network(BiFPN) [1], Spatial Pyramid Pooling-Fast(SPPF) and some network components to increase the average precision while maintaining the limited size of the model. Experiments on Visdrone2019 dataset show that the proposed approach can raise the mean Average Precision(mAP) by 5.4% compared to YOLOv5, with only 18% increase in model size.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/ACCESS.2023.3277931</doi><tpages>1</tpages><orcidid>https://orcid.org/0000-0002-6552-2665</orcidid><orcidid>https://orcid.org/0009-0001-6174-4762</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2169-3536 |
| ispartof | IEEE access, 2023-01, Vol.11, p.1-1 |
| issn | 2169-3536 2169-3536 |
| language | eng |
| recordid | cdi_ieee_primary_10129865 |
| source | IEEE Open Access Journals; DOAJ Directory of Open Access Journals; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
| subjects | Algorithms Attention Autonomous aerial vehicles Convolution Feature extraction Object detection Object recognition Target detection Training Transformers UAV Unmanned aerial vehicles YOLO |
| title | Improved YOLOv5 for aerial images based on attention mechanism |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-09T01%3A52%3A38IST&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=Improved%20YOLOv5%20for%20aerial%20images%20based%20on%20attention%20mechanism&rft.jtitle=IEEE%20access&rft.au=Li,%20Zebin&rft.date=2023-01-01&rft.volume=11&rft.spage=1&rft.epage=1&rft.pages=1-1&rft.issn=2169-3536&rft.eissn=2169-3536&rft.coden=IAECCG&rft_id=info:doi/10.1109/ACCESS.2023.3277931&rft_dat=%3Cproquest_ieee_%3E2864343795%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=2864343795&rft_id=info:pmid/&rft_ieee_id=10129865&rft_doaj_id=oai_doaj_org_article_faaeb1a4209349c893ad52b734f40abf&rfr_iscdi=true |