Multi-scale target detection method based on anchor frame position guidance and detail enhancement
The invention discloses a multi-scale target detection method based on anchor frame position guidance and detail enhancement. The method comprises the following steps: step 1, obtaining a test sample set A and a training sample set B; the training module is used for training a multi-scale target det...
Saved in:
Main Authors | , , , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
16.08.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The invention discloses a multi-scale target detection method based on anchor frame position guidance and detail enhancement. The method comprises the following steps: step 1, obtaining a test sample set A and a training sample set B; the training module is used for training a multi-scale target detection network S based on anchor frame position guidance and detail enhancement and testing a multi-scale target detection network S * based on anchor frame position guidance and detail enhancement; 2, constructing a multi-scale target detection network model S based on anchor frame position guidance and detail enhancement, wherein the model is used for obtaining a trained multi-scale target detection network S * based on anchor frame position guidance and detail enhancement; step 3, carrying out iterative training on the anchor frame position guided and detail enhanced multi-scale target detection network model S to obtain a trained anchor frame position guided and detail enhanced multi-scale target detection netw |
---|---|
AbstractList | The invention discloses a multi-scale target detection method based on anchor frame position guidance and detail enhancement. The method comprises the following steps: step 1, obtaining a test sample set A and a training sample set B; the training module is used for training a multi-scale target detection network S based on anchor frame position guidance and detail enhancement and testing a multi-scale target detection network S * based on anchor frame position guidance and detail enhancement; 2, constructing a multi-scale target detection network model S based on anchor frame position guidance and detail enhancement, wherein the model is used for obtaining a trained multi-scale target detection network S * based on anchor frame position guidance and detail enhancement; step 3, carrying out iterative training on the anchor frame position guided and detail enhanced multi-scale target detection network model S to obtain a trained anchor frame position guided and detail enhanced multi-scale target detection netw |
Author | WU LINGFAN CHEN WEI ZHU MINGZHE LU WEN DING XUHUI HE LIHUO WANG YING |
Author_xml | – fullname: WANG YING – fullname: CHEN WEI – fullname: ZHU MINGZHE – fullname: WU LINGFAN – fullname: HE LIHUO – fullname: DING XUHUI – fullname: LU WEN |
BookMark | eNqNizsOwjAQRF1Awe8OywEiJeIjWhSBaKCijzb2JLbk2FG8uT8J4gBUo5n3Zq0WIQasVP0cvbgsafYg4aGFkIFAi4uBOoiNhmpOMDR1DtrGgZqBO1Afk_ta7ejMRDBhM5_ZeUKw89QhyFYtG_YJu19u1P5-e5ePDH2skHrWCJCqfBXF5ZSfi2N-PfzjfACckT_F |
ContentType | Patent |
DBID | EVB |
DatabaseName | esp@cenet |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: EVB name: esp@cenet url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP sourceTypes: Open Access Repository |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Medicine Chemistry Sciences Physics |
DocumentTitleAlternate | 基于锚框位置引导和细节增强的多尺度目标检测方法 |
ExternalDocumentID | CN118506140A |
GroupedDBID | EVB |
ID | FETCH-epo_espacenet_CN118506140A3 |
IEDL.DBID | EVB |
IngestDate | Fri Nov 01 05:40:25 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | Chinese English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-epo_espacenet_CN118506140A3 |
Notes | Application Number: CN202410598797 |
OpenAccessLink | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240816&DB=EPODOC&CC=CN&NR=118506140A |
ParticipantIDs | epo_espacenet_CN118506140A |
PublicationCentury | 2000 |
PublicationDate | 20240816 |
PublicationDateYYYYMMDD | 2024-08-16 |
PublicationDate_xml | – month: 08 year: 2024 text: 20240816 day: 16 |
PublicationDecade | 2020 |
PublicationYear | 2024 |
RelatedCompanies | SUZHOU GAIDE OPTOELECTRONIC TECHNOLOGY CO., LTD KUNSHAN INNOVATION RESEARCH INSTITUTE OF XIDIAN UNIVERSITY |
RelatedCompanies_xml | – name: SUZHOU GAIDE OPTOELECTRONIC TECHNOLOGY CO., LTD – name: KUNSHAN INNOVATION RESEARCH INSTITUTE OF XIDIAN UNIVERSITY |
Score | 3.6932793 |
Snippet | The invention discloses a multi-scale target detection method based on anchor frame position guidance and detail enhancement. The method comprises the... |
SourceID | epo |
SourceType | Open Access Repository |
SubjectTerms | CALCULATING COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
Title | Multi-scale target detection method based on anchor frame position guidance and detail enhancement |
URI | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240816&DB=EPODOC&locale=&CC=CN&NR=118506140A |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LT8JAEJ4gPm9aNYqPrInprbGlpS6HxsgWQkwoxKDhRvrYAh4KoSUm_npnliJe9NjZZLM7m9n5ZvrNLMA9t3k95PXYMHkzNRxXxga33dhIrTiRTujYPKV6517gdt-cl1FjVIGPTS2M6hP6qZojokXFaO-Fuq8X2ySWr7iV-UM0Q9H8qTP0fL2Mjqlfl-XqfstrD_p-X-hCeCLQg1cPcXSDgh_zeQd2EUY_kjW031tUlbL47VI6x7A3wNmy4gQqX1MNDsXm5TUNDnrlD28N9hVDM85RWFphfgqRqpo1clSvZGsqN0tkoUhVGVu_Cc3IPSUMv_FYp_MlS4mFxTYcLTZZzRI6cBxO2JpHymQ2JRHlC8_grtMeiq6Byx7_6Ggsgu0O7XOoZvNMXgCLMAKVJoKuEGFe07EjFyGCHYYptULkMr2E2t_z1P4bvIIj0jelVy33GqrFciVv0D8X0a1S7Df7-5Ws |
link.rule.ids | 230,309,783,888,25576,76876 |
linkProvider | European Patent Office |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LT8JAEJ4gPvCmKFF8rYnprZHSUpdDY2QLQYVCDBpupI-t4KEQWmLir3dmAfGix84mm93ZzM43029mAW64yas-r4Z6hddj3bJlqHPTDvXYCCNp-ZbJY6p37np2-9V6GtaGOfhY18KoPqGfqjkiWlSI9p6p-3q2SWK5iluZ3gYTFE3vWwPH1VbRMfXrMmzNbTjNfs_tCU0IR3ia9-Igjq5R8FN52IJthNh3ZA3NtwZVpcx-u5TWAez0cbYkO4Tc17gIBbF-ea0Ie93VD-8i7CqGZpiicGWF6REEqmpWT1G9ki2p3CySmSJVJWz5JjQj9xQx_MZjHU_nLCYWFltztNj7YhLRgeNwxJY8UiaTMYkoX3gM163mQLR1XPboR0cj4W12aJYgn0wTeQIswAhUVhB0-Qjz6pYZ2AgRTN-PqRUil_EplP-ep_zf4BUU2oNuZ9R59J7PYJ90T6lWwz6HfDZfyAv01VlwqZT8DS3emJ8 |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=Multi-scale+target+detection+method+based+on+anchor+frame+position+guidance+and+detail+enhancement&rft.inventor=WANG+YING&rft.inventor=CHEN+WEI&rft.inventor=ZHU+MINGZHE&rft.inventor=WU+LINGFAN&rft.inventor=HE+LIHUO&rft.inventor=DING+XUHUI&rft.inventor=LU+WEN&rft.date=2024-08-16&rft.externalDBID=A&rft.externalDocID=CN118506140A |