Research on Lightweight Citrus Flowering Rate Statistical Model Combined with Anchor Frame Clustering Optimization
At present, learning-based citrus blossom recognition models based on deep learning are highly complicated and have a large number of parameters. In order to estimate citrus flower quantities in natural orchards, this study proposes a lightweight citrus flower recognition model based on improved YOL...
Gespeichert in:
| Veröffentlicht in: | Sensors (Basel, Switzerland) Switzerland), 2021-11, Vol.21 (23), p.7929 |
|---|---|
| Hauptverfasser: | , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | 23 |
| container_start_page | 7929 |
| container_title | Sensors (Basel, Switzerland) |
| container_volume | 21 |
| creator | Lu, Jianqiang Lin, Weize Chen, Pingfu Lan, Yubin Deng, Xiaoling Niu, Hongyu Mo, Jiawei Li, Jiaxing Luo, Shengfu |
| description | At present, learning-based citrus blossom recognition models based on deep learning are highly complicated and have a large number of parameters. In order to estimate citrus flower quantities in natural orchards, this study proposes a lightweight citrus flower recognition model based on improved YOLOv4. In order to compress the backbone network, we utilize MobileNetv3 as a feature extractor, combined with deep separable convolution for further acceleration. The Cutout data enhancement method is also introduced to simulate citrus in nature for data enhancement. The test results show that the improved model has an mAP of 84.84%, 22% smaller than that of YOLOv4, and approximately two times faster. Compared with the Faster R-CNN, the improved citrus flower rate statistical model proposed in this study has the advantages of less memory usage and fast detection speed under the premise of ensuring a certain accuracy. Therefore, our solution can be used as a reference for the edge detection of citrus flowering. |
| doi_str_mv | 10.3390/s21237929 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_proquest_journals_2608140694</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_5210d0deff2b4afb99c756ace1a4562b</doaj_id><sourcerecordid>2608534632</sourcerecordid><originalsourceid>FETCH-LOGICAL-c446t-117f700bb5a2524935fe6675ff95f3e6563a662674dd9ab16d0882c400bcabd53</originalsourceid><addsrcrecordid>eNpdkl2L1DAUhoso7ode-A8C3ujFaL7b3AhLcdaFkYVVr0OanEwztM2YpA766-3sLIvrTRKS533IOZyqekPwB8YU_pgpoaxWVD2rzgmnfNVQip__cz6rLnLeYUwZY83L6ozxpmGK0fMq3UEGk2yP4oQ2YduXAxxX1IaS5ozWQzxACtMW3ZkC6FsxJeQSrBnQ1-hgQG0cuzCBQ4dQenQ12T4mtE5mBNQOcy6n8O2-hDH8WcJxelW98GbI8Pphv6x-rD9_b7-sNrfXN-3VZmU5l2VFSO1rjLtOGCooV0x4kLIW3ivhGUghmZGSypo7p0xHpMNNQy1fItZ0TrDL6ubkddHs9D6F0aTfOpqg7y9i2mqTllIG0IIS7LAD72nHje-UsrWQxgIxXEjaLa5PJ9d-7kZwFqaSzPBE-vRlCr3exl-6kUJxQRfBuwdBij9nyEWPIVsYBjNBnLOmEjeCccmO6Nv_0F2c07S06p4iHEvFF-r9ibIp5pzAP36GYH2cCv04FewvqEmpaw</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2608140694</pqid></control><display><type>article</type><title>Research on Lightweight Citrus Flowering Rate Statistical Model Combined with Anchor Frame Clustering Optimization</title><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>DOAJ Directory of Open Access Journals</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>PubMed Central</source><source>Free Full-Text Journals in Chemistry</source><creator>Lu, Jianqiang ; Lin, Weize ; Chen, Pingfu ; Lan, Yubin ; Deng, Xiaoling ; Niu, Hongyu ; Mo, Jiawei ; Li, Jiaxing ; Luo, Shengfu</creator><creatorcontrib>Lu, Jianqiang ; Lin, Weize ; Chen, Pingfu ; Lan, Yubin ; Deng, Xiaoling ; Niu, Hongyu ; Mo, Jiawei ; Li, Jiaxing ; Luo, Shengfu</creatorcontrib><description>At present, learning-based citrus blossom recognition models based on deep learning are highly complicated and have a large number of parameters. In order to estimate citrus flower quantities in natural orchards, this study proposes a lightweight citrus flower recognition model based on improved YOLOv4. In order to compress the backbone network, we utilize MobileNetv3 as a feature extractor, combined with deep separable convolution for further acceleration. The Cutout data enhancement method is also introduced to simulate citrus in nature for data enhancement. The test results show that the improved model has an mAP of 84.84%, 22% smaller than that of YOLOv4, and approximately two times faster. Compared with the Faster R-CNN, the improved citrus flower rate statistical model proposed in this study has the advantages of less memory usage and fast detection speed under the premise of ensuring a certain accuracy. Therefore, our solution can be used as a reference for the edge detection of citrus flowering.</description><identifier>ISSN: 1424-8220</identifier><identifier>EISSN: 1424-8220</identifier><identifier>DOI: 10.3390/s21237929</identifier><identifier>PMID: 34883932</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Acceleration ; Accuracy ; Algorithms ; citrus flowering rate ; Clustering ; Data collection ; Datasets ; Deep learning ; edge computing ; Edge detection ; Flowering ; Flowers & plants ; light weight ; Lightweight ; Methods ; Neural networks ; Orchards ; Recognition ; Statistical models ; YOLOv4</subject><ispartof>Sensors (Basel, Switzerland), 2021-11, Vol.21 (23), p.7929</ispartof><rights>2021 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><rights>2021 by the authors. 2021</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c446t-117f700bb5a2524935fe6675ff95f3e6563a662674dd9ab16d0882c400bcabd53</citedby><cites>FETCH-LOGICAL-c446t-117f700bb5a2524935fe6675ff95f3e6563a662674dd9ab16d0882c400bcabd53</cites><orcidid>0000-0002-6417-4646 ; 0000-0001-5588-3443</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8659452/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8659452/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,723,776,780,860,881,2096,27901,27902,53766,53768</link.rule.ids></links><search><creatorcontrib>Lu, Jianqiang</creatorcontrib><creatorcontrib>Lin, Weize</creatorcontrib><creatorcontrib>Chen, Pingfu</creatorcontrib><creatorcontrib>Lan, Yubin</creatorcontrib><creatorcontrib>Deng, Xiaoling</creatorcontrib><creatorcontrib>Niu, Hongyu</creatorcontrib><creatorcontrib>Mo, Jiawei</creatorcontrib><creatorcontrib>Li, Jiaxing</creatorcontrib><creatorcontrib>Luo, Shengfu</creatorcontrib><title>Research on Lightweight Citrus Flowering Rate Statistical Model Combined with Anchor Frame Clustering Optimization</title><title>Sensors (Basel, Switzerland)</title><description>At present, learning-based citrus blossom recognition models based on deep learning are highly complicated and have a large number of parameters. In order to estimate citrus flower quantities in natural orchards, this study proposes a lightweight citrus flower recognition model based on improved YOLOv4. In order to compress the backbone network, we utilize MobileNetv3 as a feature extractor, combined with deep separable convolution for further acceleration. The Cutout data enhancement method is also introduced to simulate citrus in nature for data enhancement. The test results show that the improved model has an mAP of 84.84%, 22% smaller than that of YOLOv4, and approximately two times faster. Compared with the Faster R-CNN, the improved citrus flower rate statistical model proposed in this study has the advantages of less memory usage and fast detection speed under the premise of ensuring a certain accuracy. Therefore, our solution can be used as a reference for the edge detection of citrus flowering.</description><subject>Acceleration</subject><subject>Accuracy</subject><subject>Algorithms</subject><subject>citrus flowering rate</subject><subject>Clustering</subject><subject>Data collection</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>edge computing</subject><subject>Edge detection</subject><subject>Flowering</subject><subject>Flowers & plants</subject><subject>light weight</subject><subject>Lightweight</subject><subject>Methods</subject><subject>Neural networks</subject><subject>Orchards</subject><subject>Recognition</subject><subject>Statistical models</subject><subject>YOLOv4</subject><issn>1424-8220</issn><issn>1424-8220</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><sourceid>DOA</sourceid><recordid>eNpdkl2L1DAUhoso7ode-A8C3ujFaL7b3AhLcdaFkYVVr0OanEwztM2YpA766-3sLIvrTRKS533IOZyqekPwB8YU_pgpoaxWVD2rzgmnfNVQip__cz6rLnLeYUwZY83L6ozxpmGK0fMq3UEGk2yP4oQ2YduXAxxX1IaS5ozWQzxACtMW3ZkC6FsxJeQSrBnQ1-hgQG0cuzCBQ4dQenQ12T4mtE5mBNQOcy6n8O2-hDH8WcJxelW98GbI8Pphv6x-rD9_b7-sNrfXN-3VZmU5l2VFSO1rjLtOGCooV0x4kLIW3ivhGUghmZGSypo7p0xHpMNNQy1fItZ0TrDL6ubkddHs9D6F0aTfOpqg7y9i2mqTllIG0IIS7LAD72nHje-UsrWQxgIxXEjaLa5PJ9d-7kZwFqaSzPBE-vRlCr3exl-6kUJxQRfBuwdBij9nyEWPIVsYBjNBnLOmEjeCccmO6Nv_0F2c07S06p4iHEvFF-r9ibIp5pzAP36GYH2cCv04FewvqEmpaw</recordid><startdate>20211127</startdate><enddate>20211127</enddate><creator>Lu, Jianqiang</creator><creator>Lin, Weize</creator><creator>Chen, Pingfu</creator><creator>Lan, Yubin</creator><creator>Deng, Xiaoling</creator><creator>Niu, Hongyu</creator><creator>Mo, Jiawei</creator><creator>Li, Jiaxing</creator><creator>Luo, Shengfu</creator><general>MDPI AG</general><general>MDPI</general><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>K9.</scope><scope>M0S</scope><scope>M1P</scope><scope>PHGZM</scope><scope>PHGZT</scope><scope>PIMPY</scope><scope>PJZUB</scope><scope>PKEHL</scope><scope>PPXIY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-6417-4646</orcidid><orcidid>https://orcid.org/0000-0001-5588-3443</orcidid></search><sort><creationdate>20211127</creationdate><title>Research on Lightweight Citrus Flowering Rate Statistical Model Combined with Anchor Frame Clustering Optimization</title><author>Lu, Jianqiang ; Lin, Weize ; Chen, Pingfu ; Lan, Yubin ; Deng, Xiaoling ; Niu, Hongyu ; Mo, Jiawei ; Li, Jiaxing ; Luo, Shengfu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c446t-117f700bb5a2524935fe6675ff95f3e6563a662674dd9ab16d0882c400bcabd53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Acceleration</topic><topic>Accuracy</topic><topic>Algorithms</topic><topic>citrus flowering rate</topic><topic>Clustering</topic><topic>Data collection</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>edge computing</topic><topic>Edge detection</topic><topic>Flowering</topic><topic>Flowers & plants</topic><topic>light weight</topic><topic>Lightweight</topic><topic>Methods</topic><topic>Neural networks</topic><topic>Orchards</topic><topic>Recognition</topic><topic>Statistical models</topic><topic>YOLOv4</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lu, Jianqiang</creatorcontrib><creatorcontrib>Lin, Weize</creatorcontrib><creatorcontrib>Chen, Pingfu</creatorcontrib><creatorcontrib>Lan, Yubin</creatorcontrib><creatorcontrib>Deng, Xiaoling</creatorcontrib><creatorcontrib>Niu, Hongyu</creatorcontrib><creatorcontrib>Mo, Jiawei</creatorcontrib><creatorcontrib>Li, Jiaxing</creatorcontrib><creatorcontrib>Luo, Shengfu</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>ProQuest Health and Medical</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Medical Database</collection><collection>ProQuest Central (New)</collection><collection>ProQuest One Academic (New)</collection><collection>Publicly Available Content Database</collection><collection>ProQuest Health & Medical Research Collection</collection><collection>ProQuest One Academic Middle East (New)</collection><collection>ProQuest One Health & Nursing</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>Sensors (Basel, Switzerland)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lu, Jianqiang</au><au>Lin, Weize</au><au>Chen, Pingfu</au><au>Lan, Yubin</au><au>Deng, Xiaoling</au><au>Niu, Hongyu</au><au>Mo, Jiawei</au><au>Li, Jiaxing</au><au>Luo, Shengfu</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Research on Lightweight Citrus Flowering Rate Statistical Model Combined with Anchor Frame Clustering Optimization</atitle><jtitle>Sensors (Basel, Switzerland)</jtitle><date>2021-11-27</date><risdate>2021</risdate><volume>21</volume><issue>23</issue><spage>7929</spage><pages>7929-</pages><issn>1424-8220</issn><eissn>1424-8220</eissn><abstract>At present, learning-based citrus blossom recognition models based on deep learning are highly complicated and have a large number of parameters. In order to estimate citrus flower quantities in natural orchards, this study proposes a lightweight citrus flower recognition model based on improved YOLOv4. In order to compress the backbone network, we utilize MobileNetv3 as a feature extractor, combined with deep separable convolution for further acceleration. The Cutout data enhancement method is also introduced to simulate citrus in nature for data enhancement. The test results show that the improved model has an mAP of 84.84%, 22% smaller than that of YOLOv4, and approximately two times faster. Compared with the Faster R-CNN, the improved citrus flower rate statistical model proposed in this study has the advantages of less memory usage and fast detection speed under the premise of ensuring a certain accuracy. Therefore, our solution can be used as a reference for the edge detection of citrus flowering.</abstract><cop>Basel</cop><pub>MDPI AG</pub><pmid>34883932</pmid><doi>10.3390/s21237929</doi><orcidid>https://orcid.org/0000-0002-6417-4646</orcidid><orcidid>https://orcid.org/0000-0001-5588-3443</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1424-8220 |
| ispartof | Sensors (Basel, Switzerland), 2021-11, Vol.21 (23), p.7929 |
| issn | 1424-8220 1424-8220 |
| language | eng |
| recordid | cdi_proquest_journals_2608140694 |
| source | MDPI - Multidisciplinary Digital Publishing Institute; DOAJ Directory of Open Access Journals; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; PubMed Central; Free Full-Text Journals in Chemistry |
| subjects | Acceleration Accuracy Algorithms citrus flowering rate Clustering Data collection Datasets Deep learning edge computing Edge detection Flowering Flowers & plants light weight Lightweight Methods Neural networks Orchards Recognition Statistical models YOLOv4 |
| title | Research on Lightweight Citrus Flowering Rate Statistical Model Combined with Anchor Frame Clustering Optimization |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-18T21%3A43%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Research%20on%20Lightweight%20Citrus%20Flowering%20Rate%20Statistical%20Model%20Combined%20with%20Anchor%20Frame%20Clustering%20Optimization&rft.jtitle=Sensors%20(Basel,%20Switzerland)&rft.au=Lu,%20Jianqiang&rft.date=2021-11-27&rft.volume=21&rft.issue=23&rft.spage=7929&rft.pages=7929-&rft.issn=1424-8220&rft.eissn=1424-8220&rft_id=info:doi/10.3390/s21237929&rft_dat=%3Cproquest_doaj_%3E2608534632%3C/proquest_doaj_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2608140694&rft_id=info:pmid/34883932&rft_doaj_id=oai_doaj_org_article_5210d0deff2b4afb99c756ace1a4562b&rfr_iscdi=true |