Target detection method based on multi-scale regional convolutional network
The invention belongs to the technical field of target detection, and particularly relates to a target detection method based on a multi-scale regional convolutional network. According to the method, a target detection frame is identified by constructing a multi-scale regional convolutional network,...
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 | XU ZEYING XIE QIYANG ZHOU DAIYING |
| description | The invention belongs to the technical field of target detection, and particularly relates to a target detection method based on a multi-scale regional convolutional network. According to the method, a target detection frame is identified by constructing a multi-scale regional convolutional network, and the multi-scale regional convolutional network comprises a feature extraction backbone network, a regional suggestion network and a target detection network; wherein the feature extraction backbone network is used for extracting features of an input image to obtain a feature map; the input of the region suggestion network is a feature map, and three region suggestion boxes with different scales are respectively obtained, the input of the target detection network comprises the feature map and the three region suggestion boxes with different scales, and finally a target detection box is obtained. According to the invention, target detection in a detection scene with targets of different sizes is facilitated, and |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116452815A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116452815A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116452815A3</originalsourceid><addsrcrecordid>eNrjZPAOSSxKTy1RSEktSU0uyczPU8hNLcnIT1FISixOTVEA8UtzSjJ1i5MTc1IVilLTgUoScxSS8_PK8nNKSyC8vNSS8vyibB4G1rTEnOJUXijNzaDo5hri7KGbWpAfn1pckJicClQZ7-xnaGhmYmpkYWjqaEyMGgCUFjX_</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Target detection method based on multi-scale regional convolutional network</title><source>esp@cenet</source><creator>XU ZEYING ; XIE QIYANG ; ZHOU DAIYING</creator><creatorcontrib>XU ZEYING ; XIE QIYANG ; ZHOU DAIYING</creatorcontrib><description>The invention belongs to the technical field of target detection, and particularly relates to a target detection method based on a multi-scale regional convolutional network. According to the method, a target detection frame is identified by constructing a multi-scale regional convolutional network, and the multi-scale regional convolutional network comprises a feature extraction backbone network, a regional suggestion network and a target detection network; wherein the feature extraction backbone network is used for extracting features of an input image to obtain a feature map; the input of the region suggestion network is a feature map, and three region suggestion boxes with different scales are respectively obtained, the input of the target detection network comprises the feature map and the three region suggestion boxes with different scales, and finally a target detection box is obtained. According to the invention, target detection in a detection scene with targets of different sizes is facilitated, and</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2023</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=20230718&DB=EPODOC&CC=CN&NR=116452815A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230718&DB=EPODOC&CC=CN&NR=116452815A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>XU ZEYING</creatorcontrib><creatorcontrib>XIE QIYANG</creatorcontrib><creatorcontrib>ZHOU DAIYING</creatorcontrib><title>Target detection method based on multi-scale regional convolutional network</title><description>The invention belongs to the technical field of target detection, and particularly relates to a target detection method based on a multi-scale regional convolutional network. According to the method, a target detection frame is identified by constructing a multi-scale regional convolutional network, and the multi-scale regional convolutional network comprises a feature extraction backbone network, a regional suggestion network and a target detection network; wherein the feature extraction backbone network is used for extracting features of an input image to obtain a feature map; the input of the region suggestion network is a feature map, and three region suggestion boxes with different scales are respectively obtained, the input of the target detection network comprises the feature map and the three region suggestion boxes with different scales, and finally a target detection box is obtained. According to the invention, target detection in a detection scene with targets of different sizes is facilitated, and</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZPAOSSxKTy1RSEktSU0uyczPU8hNLcnIT1FISixOTVEA8UtzSjJ1i5MTc1IVilLTgUoScxSS8_PK8nNKSyC8vNSS8vyibB4G1rTEnOJUXijNzaDo5hri7KGbWpAfn1pckJicClQZ7-xnaGhmYmpkYWjqaEyMGgCUFjX_</recordid><startdate>20230718</startdate><enddate>20230718</enddate><creator>XU ZEYING</creator><creator>XIE QIYANG</creator><creator>ZHOU DAIYING</creator><scope>EVB</scope></search><sort><creationdate>20230718</creationdate><title>Target detection method based on multi-scale regional convolutional network</title><author>XU ZEYING ; XIE QIYANG ; ZHOU DAIYING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116452815A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</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>XU ZEYING</creatorcontrib><creatorcontrib>XIE QIYANG</creatorcontrib><creatorcontrib>ZHOU DAIYING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>XU ZEYING</au><au>XIE QIYANG</au><au>ZHOU DAIYING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Target detection method based on multi-scale regional convolutional network</title><date>2023-07-18</date><risdate>2023</risdate><abstract>The invention belongs to the technical field of target detection, and particularly relates to a target detection method based on a multi-scale regional convolutional network. According to the method, a target detection frame is identified by constructing a multi-scale regional convolutional network, and the multi-scale regional convolutional network comprises a feature extraction backbone network, a regional suggestion network and a target detection network; wherein the feature extraction backbone network is used for extracting features of an input image to obtain a feature map; the input of the region suggestion network is a feature map, and three region suggestion boxes with different scales are respectively obtained, the input of the target detection network comprises the feature map and the three region suggestion boxes with different scales, and finally a target detection box is obtained. According to the invention, target detection in a detection scene with targets of different sizes is facilitated, and</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN116452815A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | Target detection method based on multi-scale regional convolutional network |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-29T08%3A34%3A24IST&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=XU%20ZEYING&rft.date=2023-07-18&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116452815A%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 |