Garden engineering small target pest detection method based on super-resolution reconstruction and data enhancement
The invention provides a garden engineering small target pest detection method based on super-resolution reconstruction and data enhancement, and the method comprises the following steps: S1, carrying out the collection and screening of small target pest image data, and forming a small target pest d...
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | ZHANG TAO PANG MIN LIU MINGLONG JIN YAN QUAN HOUFA CUI LUYUN XIAO TIANHONG ZHANG JI |
| description | The invention provides a garden engineering small target pest detection method based on super-resolution reconstruction and data enhancement, and the method comprises the following steps: S1, carrying out the collection and screening of small target pest image data, and forming a small target pest database; s2, performing mirror image flipping and random rotation on the small target pest database to form a training set; s3, performing super-resolution reconstruction and data enhancement on the target pictures in the training set; s4, inputting the data obtained in S3 into a trunk network based on transfer learning for feature extraction, and predicting the category and position information of the small target pests so as to obtain a small target pest detector; and S5, inputting the collected picture into a pest detector to obtain a small target pest detection result. According to the invention, the identification capability of the backbone network is improved; the problem of sample imbalance is solved; and th |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115147646A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115147646A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115147646A3</originalsourceid><addsrcrecordid>eNqNzT0KwkAQxfE0FqLeYTxAimCMtQQ_Kiv7MO4-k8BmdtmZ3F9RD2D1-MMP3rLQC2cPIUg_CpBH6UknDoGMcw-jBDXyMDgbo9AEG6KnBys8vVvnhFxmaAzzB2S4KGp5_noWT56N3wcDi8MEsXWxeHJQbH67Krbn0729lkixgyZ2EFjX3qpqX9WHpm6Ou3_MC6r6RVk</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Garden engineering small target pest detection method based on super-resolution reconstruction and data enhancement</title><source>esp@cenet</source><creator>ZHANG TAO ; PANG MIN ; LIU MINGLONG ; JIN YAN ; QUAN HOUFA ; CUI LUYUN ; XIAO TIANHONG ; ZHANG JI</creator><creatorcontrib>ZHANG TAO ; PANG MIN ; LIU MINGLONG ; JIN YAN ; QUAN HOUFA ; CUI LUYUN ; XIAO TIANHONG ; ZHANG JI</creatorcontrib><description>The invention provides a garden engineering small target pest detection method based on super-resolution reconstruction and data enhancement, and the method comprises the following steps: S1, carrying out the collection and screening of small target pest image data, and forming a small target pest database; s2, performing mirror image flipping and random rotation on the small target pest database to form a training set; s3, performing super-resolution reconstruction and data enhancement on the target pictures in the training set; s4, inputting the data obtained in S3 into a trunk network based on transfer learning for feature extraction, and predicting the category and position information of the small target pests so as to obtain a small target pest detector; and S5, inputting the collected picture into a pest detector to obtain a small target pest detection result. According to the invention, the identification capability of the backbone network is improved; the problem of sample imbalance is solved; and th</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2022</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20221004&DB=EPODOC&CC=CN&NR=115147646A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20221004&DB=EPODOC&CC=CN&NR=115147646A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHANG TAO</creatorcontrib><creatorcontrib>PANG MIN</creatorcontrib><creatorcontrib>LIU MINGLONG</creatorcontrib><creatorcontrib>JIN YAN</creatorcontrib><creatorcontrib>QUAN HOUFA</creatorcontrib><creatorcontrib>CUI LUYUN</creatorcontrib><creatorcontrib>XIAO TIANHONG</creatorcontrib><creatorcontrib>ZHANG JI</creatorcontrib><title>Garden engineering small target pest detection method based on super-resolution reconstruction and data enhancement</title><description>The invention provides a garden engineering small target pest detection method based on super-resolution reconstruction and data enhancement, and the method comprises the following steps: S1, carrying out the collection and screening of small target pest image data, and forming a small target pest database; s2, performing mirror image flipping and random rotation on the small target pest database to form a training set; s3, performing super-resolution reconstruction and data enhancement on the target pictures in the training set; s4, inputting the data obtained in S3 into a trunk network based on transfer learning for feature extraction, and predicting the category and position information of the small target pests so as to obtain a small target pest detector; and S5, inputting the collected picture into a pest detector to obtain a small target pest detection result. According to the invention, the identification capability of the backbone network is improved; the problem of sample imbalance is solved; and th</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNzT0KwkAQxfE0FqLeYTxAimCMtQQ_Kiv7MO4-k8BmdtmZ3F9RD2D1-MMP3rLQC2cPIUg_CpBH6UknDoGMcw-jBDXyMDgbo9AEG6KnBys8vVvnhFxmaAzzB2S4KGp5_noWT56N3wcDi8MEsXWxeHJQbH67Krbn0729lkixgyZ2EFjX3qpqX9WHpm6Ou3_MC6r6RVk</recordid><startdate>20221004</startdate><enddate>20221004</enddate><creator>ZHANG TAO</creator><creator>PANG MIN</creator><creator>LIU MINGLONG</creator><creator>JIN YAN</creator><creator>QUAN HOUFA</creator><creator>CUI LUYUN</creator><creator>XIAO TIANHONG</creator><creator>ZHANG JI</creator><scope>EVB</scope></search><sort><creationdate>20221004</creationdate><title>Garden engineering small target pest detection method based on super-resolution reconstruction and data enhancement</title><author>ZHANG TAO ; PANG MIN ; LIU MINGLONG ; JIN YAN ; QUAN HOUFA ; CUI LUYUN ; XIAO TIANHONG ; ZHANG JI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115147646A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>ZHANG TAO</creatorcontrib><creatorcontrib>PANG MIN</creatorcontrib><creatorcontrib>LIU MINGLONG</creatorcontrib><creatorcontrib>JIN YAN</creatorcontrib><creatorcontrib>QUAN HOUFA</creatorcontrib><creatorcontrib>CUI LUYUN</creatorcontrib><creatorcontrib>XIAO TIANHONG</creatorcontrib><creatorcontrib>ZHANG JI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHANG TAO</au><au>PANG MIN</au><au>LIU MINGLONG</au><au>JIN YAN</au><au>QUAN HOUFA</au><au>CUI LUYUN</au><au>XIAO TIANHONG</au><au>ZHANG JI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Garden engineering small target pest detection method based on super-resolution reconstruction and data enhancement</title><date>2022-10-04</date><risdate>2022</risdate><abstract>The invention provides a garden engineering small target pest detection method based on super-resolution reconstruction and data enhancement, and the method comprises the following steps: S1, carrying out the collection and screening of small target pest image data, and forming a small target pest database; s2, performing mirror image flipping and random rotation on the small target pest database to form a training set; s3, performing super-resolution reconstruction and data enhancement on the target pictures in the training set; s4, inputting the data obtained in S3 into a trunk network based on transfer learning for feature extraction, and predicting the category and position information of the small target pests so as to obtain a small target pest detector; and S5, inputting the collected picture into a pest detector to obtain a small target pest detection result. According to the invention, the identification capability of the backbone network is improved; the problem of sample imbalance is solved; and th</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN115147646A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | Garden engineering small target pest detection method based on super-resolution reconstruction and data enhancement |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T19%3A51%3A37IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=ZHANG%20TAO&rft.date=2022-10-04&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115147646A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |