어텐션 적용 YOLOv4 기반 SAR 영상 표적 탐지 및 인식SAR Image Target Detection based on Attention YOLOv4

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 203
  • Download : 0
DC FieldValueLanguage
dc.contributor.author박종민ko
dc.contributor.author육근혁ko
dc.contributor.author김문철ko
dc.date.accessioned2022-12-04T04:00:11Z-
dc.date.available2022-12-04T04:00:11Z-
dc.date.created2022-12-03-
dc.date.created2022-12-03-
dc.date.issued2022-12-
dc.identifier.citation한국군사과학기술학회지, v.25, no.5, pp.443 - 461-
dc.identifier.issn1598-9127-
dc.identifier.urihttp://hdl.handle.net/10203/301559-
dc.description.abstractTarget Detection in synthetic aperture radar(SAR) image is critical for military and national defense. In this paper, we propose YOLOv4-Attention architecture which adds attention modules to YOLOv4 backbone architecture to complement the feature extraction ability for SAR target detection with high accuracy. For training and testing our framework, we present new SAR embedding datasets based on MSTAR SAR public datasets which are about poor environments for target detection such as various clutter, crowded objects, various object size, close to buildings, and weakness of signal-to-clutter ratio. Experiments show that our Attention YOLOv4 architecture outperforms original YOLOv4 architecture in SAR image target detection tasks in poor environments for target detection.-
dc.languageKorean-
dc.publisher한국군사과학기술학회-
dc.title어텐션 적용 YOLOv4 기반 SAR 영상 표적 탐지 및 인식-
dc.title.alternativeSAR Image Target Detection based on Attention YOLOv4-
dc.typeArticle-
dc.type.rimsART-
dc.citation.volume25-
dc.citation.issue5-
dc.citation.beginningpage443-
dc.citation.endingpage461-
dc.citation.publicationname한국군사과학기술학회지-
dc.identifier.kciidART002887372-
dc.contributor.localauthor김문철-
dc.description.isOpenAccessN-
dc.subject.keywordAuthorTarget Detection(표적 탐지)-
dc.subject.keywordAuthorSynthetic Aperture Radar(합성 개구면 레이더)-
dc.subject.keywordAuthorYOLOv4-
dc.subject.keywordAuthorAttention Algorithm (어텐션 알고리즘)-
dc.subject.keywordAuthorDeep Learning(딥러닝)-
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0