Small target detection algorithm based on pyolo dynamic self-adaption
The invention relates to the technical field of target detection algorithms, and discloses a pyolo dynamic self-adaption-based small target detection algorithm, which comprises the following steps of: acquiring image data, performing data preprocessing, and dividing a data set into a training set an...
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 | LIU QINGBIN KONG SUOCAI ZHANG WEI DING HEQIANG ZHANG ZITENG |
| description | The invention relates to the technical field of target detection algorithms, and discloses a pyolo dynamic self-adaption-based small target detection algorithm, which comprises the following steps of: acquiring image data, performing data preprocessing, and dividing a data set into a training set and a test set by taking the data requirement of a YOLO model as a standard; performing optimization processing on the hyper-parameters in the training set by adopting a preset optimization search algorithm to obtain optimal parameters; wherein the hyper-parameters comprise the image size and the batch size; and training a preset pyolo target detection model by adopting the optimal parameters, and analyzing and verifying a result. According to the small target detection algorithm based on pyolo dynamic self-adaption, a search optimization algorithm is introduced into a YOLO structure, a unique pyolo target detection model is provided, self-adaption training of different types of data sets and target sizes is achieved |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118097118A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118097118A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118097118A3</originalsourceid><addsrcrecordid>eNrjZHANzk3MyVEoSSxKTy1RSEktSU0uyczPU0jMSc8vyizJyFVISixOTVEAChVU5ufkK6RU5iXmZiYrFKfmpOkmpiQWgJTzMLCmJeYUp_JCaW4GRTfXEGcP3dSC_PjU4oLE5NS81JJ4Zz9DQwsDS3Mg6WhMjBoAAAwzVQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Small target detection algorithm based on pyolo dynamic self-adaption</title><source>esp@cenet</source><creator>LIU QINGBIN ; KONG SUOCAI ; ZHANG WEI ; DING HEQIANG ; ZHANG ZITENG</creator><creatorcontrib>LIU QINGBIN ; KONG SUOCAI ; ZHANG WEI ; DING HEQIANG ; ZHANG ZITENG</creatorcontrib><description>The invention relates to the technical field of target detection algorithms, and discloses a pyolo dynamic self-adaption-based small target detection algorithm, which comprises the following steps of: acquiring image data, performing data preprocessing, and dividing a data set into a training set and a test set by taking the data requirement of a YOLO model as a standard; performing optimization processing on the hyper-parameters in the training set by adopting a preset optimization search algorithm to obtain optimal parameters; wherein the hyper-parameters comprise the image size and the batch size; and training a preset pyolo target detection model by adopting the optimal parameters, and analyzing and verifying a result. According to the small target detection algorithm based on pyolo dynamic self-adaption, a search optimization algorithm is introduced into a YOLO structure, a unique pyolo target detection model is provided, self-adaption training of different types of data sets and target sizes is achieved</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2024</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=20240528&DB=EPODOC&CC=CN&NR=118097118A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240528&DB=EPODOC&CC=CN&NR=118097118A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>LIU QINGBIN</creatorcontrib><creatorcontrib>KONG SUOCAI</creatorcontrib><creatorcontrib>ZHANG WEI</creatorcontrib><creatorcontrib>DING HEQIANG</creatorcontrib><creatorcontrib>ZHANG ZITENG</creatorcontrib><title>Small target detection algorithm based on pyolo dynamic self-adaption</title><description>The invention relates to the technical field of target detection algorithms, and discloses a pyolo dynamic self-adaption-based small target detection algorithm, which comprises the following steps of: acquiring image data, performing data preprocessing, and dividing a data set into a training set and a test set by taking the data requirement of a YOLO model as a standard; performing optimization processing on the hyper-parameters in the training set by adopting a preset optimization search algorithm to obtain optimal parameters; wherein the hyper-parameters comprise the image size and the batch size; and training a preset pyolo target detection model by adopting the optimal parameters, and analyzing and verifying a result. According to the small target detection algorithm based on pyolo dynamic self-adaption, a search optimization algorithm is introduced into a YOLO structure, a unique pyolo target detection model is provided, self-adaption training of different types of data sets and target sizes is achieved</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>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHANzk3MyVEoSSxKTy1RSEktSU0uyczPU0jMSc8vyizJyFVISixOTVEAChVU5ufkK6RU5iXmZiYrFKfmpOkmpiQWgJTzMLCmJeYUp_JCaW4GRTfXEGcP3dSC_PjU4oLE5NS81JJ4Zz9DQwsDS3Mg6WhMjBoAAAwzVQ</recordid><startdate>20240528</startdate><enddate>20240528</enddate><creator>LIU QINGBIN</creator><creator>KONG SUOCAI</creator><creator>ZHANG WEI</creator><creator>DING HEQIANG</creator><creator>ZHANG ZITENG</creator><scope>EVB</scope></search><sort><creationdate>20240528</creationdate><title>Small target detection algorithm based on pyolo dynamic self-adaption</title><author>LIU QINGBIN ; KONG SUOCAI ; ZHANG WEI ; DING HEQIANG ; ZHANG ZITENG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118097118A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</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>LIU QINGBIN</creatorcontrib><creatorcontrib>KONG SUOCAI</creatorcontrib><creatorcontrib>ZHANG WEI</creatorcontrib><creatorcontrib>DING HEQIANG</creatorcontrib><creatorcontrib>ZHANG ZITENG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>LIU QINGBIN</au><au>KONG SUOCAI</au><au>ZHANG WEI</au><au>DING HEQIANG</au><au>ZHANG ZITENG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Small target detection algorithm based on pyolo dynamic self-adaption</title><date>2024-05-28</date><risdate>2024</risdate><abstract>The invention relates to the technical field of target detection algorithms, and discloses a pyolo dynamic self-adaption-based small target detection algorithm, which comprises the following steps of: acquiring image data, performing data preprocessing, and dividing a data set into a training set and a test set by taking the data requirement of a YOLO model as a standard; performing optimization processing on the hyper-parameters in the training set by adopting a preset optimization search algorithm to obtain optimal parameters; wherein the hyper-parameters comprise the image size and the batch size; and training a preset pyolo target detection model by adopting the optimal parameters, and analyzing and verifying a result. According to the small target detection algorithm based on pyolo dynamic self-adaption, a search optimization algorithm is introduced into a YOLO structure, a unique pyolo target detection model is provided, self-adaption training of different types of data sets and target sizes is achieved</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN118097118A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | Small target detection algorithm based on pyolo dynamic self-adaption |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-25T16%3A39%3A46IST&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=LIU%20QINGBIN&rft.date=2024-05-28&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118097118A%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 |