FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312790920> ?p ?o ?g. }

• W4312790920 endingPage "128578" @default.
• W4312790920 startingPage "128562" @default.
• W4312790920 abstract "Currently, deep learning-based synthetic aperture radar (SAR) image ship target detection methods have been widely used in the field of SAR image ship detection. However, these methods suffer from high model complexity and poor performance when detecting small dense targets. To address this problem, this paper proposes a ship target detection algorithm based on the improved YOLO (You Only Look Once) algorithm. In addition, considering the real-time requirements and computational constraints in mobile applications, the YOLOv4 network is modified to make it more lightweight. Moreover, decoupled head and coordinate attention are introduced to preserve YOLOv4’s superb detection performance as much as possible after lightweighting it. First, as the detection head of the YOLOv4 degrades the performance, this study decouples the classification and regression tasks. Second, since the channel attention mechanism ignores the spatial position information, coordinate attention is used to obtain long-range dependencies and accurate position information in the spatial domain. Moreover, the effects of the coordinate attention mechanism in different hierarchical YOLOv4 structures are analyzed. Furthermore, on the basis of the YOLOv4 backbone, another lightweight backbone is added to the model structure to improve model detection performance. Experimental results on the SAR ship detection dataset (SSDD) and the high-resolution SAR images dataset (HRSID) demonstrate that the proposed method can achieve high detection accuracy in complex scenes. The proposed lightweight model has fewer parameters compared to the original YOLOv4 structure. Furthermore, two massive SAR images are used to confirm the proposed model’s migration application performance. The experimental results demonstrate that the proposed model has a strong migration ability and can be used in maritime monitoring." @default.
• W4312790920 created "2023-01-05" @default.
• W4312790920 creator A5034366973 @default.
• W4312790920 creator A5070321865 @default.
• W4312790920 creator A5070568717 @default.
• W4312790920 date "2022-01-01" @default.
• W4312790920 modified "2023-10-01" @default.
• W4312790920 title "A Decoupled Head and Coordinate Attention Detection Method for Ship Targets in SAR Images" @default.
• W4312790920 cites W1536680647 @default.
• W4312790920 cites W2042729642 @default.
• W4312790920 cites W2064675550 @default.
• W4312790920 cites W2086754696 @default.
• W4312790920 cites W2102605133 @default.
• W4312790920 cites W2179352600 @default.
• W4312790920 cites W2564429410 @default.
• W4312790920 cites W2601564443 @default.
• W4312790920 cites W2883780447 @default.
• W4312790920 cites W2884561390 @default.
• W4312790920 cites W2888493720 @default.
• W4312790920 cites W2904480641 @default.
• W4312790920 cites W2919318018 @default.
• W4312790920 cites W2928007866 @default.
• W4312790920 cites W2955058313 @default.
• W4312790920 cites W2961699889 @default.
• W4312790920 cites W2963037989 @default.
• W4312790920 cites W2963125010 @default.
• W4312790920 cites W2963163009 @default.
• W4312790920 cites W2963420686 @default.
• W4312790920 cites W2963857746 @default.
• W4312790920 cites W2964121718 @default.
• W4312790920 cites W2964231884 @default.
• W4312790920 cites W2966926453 @default.
• W4312790920 cites W2967733054 @default.
• W4312790920 cites W2970987838 @default.
• W4312790920 cites W2975079793 @default.
• W4312790920 cites W2981408784 @default.
• W4312790920 cites W2982083293 @default.
• W4312790920 cites W3032837604 @default.
• W4312790920 cites W3034580371 @default.
• W4312790920 cites W3035473155 @default.
• W4312790920 cites W3035502324 @default.
• W4312790920 cites W3035559754 @default.
• W4312790920 cites W3038948729 @default.
• W4312790920 cites W3042011474 @default.
• W4312790920 cites W3083305230 @default.
• W4312790920 cites W3089780760 @default.
• W4312790920 cites W3106250896 @default.
• W4312790920 cites W3110760540 @default.
• W4312790920 cites W3119205652 @default.
• W4312790920 cites W3177052299 @default.
• W4312790920 cites W3184840388 @default.
• W4312790920 cites W3200733355 @default.
• W4312790920 cites W3202691929 @default.
• W4312790920 cites W3208019692 @default.
• W4312790920 cites W3212787682 @default.
• W4312790920 cites W3214630121 @default.
• W4312790920 cites W4285135634 @default.
• W4312790920 cites W4312443924 @default.
• W4312790920 cites W639708223 @default.
• W4312790920 doi "https://doi.org/10.1109/access.2022.3222364" @default.
• W4312790920 hasPublicationYear "2022" @default.
• W4312790920 type Work @default.
• W4312790920 citedByCount "1" @default.
• W4312790920 countsByYear W43127909202022 @default.
• W4312790920 crossrefType "journal-article" @default.
• W4312790920 hasAuthorship W4312790920A5034366973 @default.
• W4312790920 hasAuthorship W4312790920A5070321865 @default.
• W4312790920 hasAuthorship W4312790920A5070568717 @default.
• W4312790920 hasBestOaLocation W43127909201 @default.
• W4312790920 hasConcept C10138342 @default.
• W4312790920 hasConcept C108583219 @default.
• W4312790920 hasConcept C153180895 @default.
• W4312790920 hasConcept C154945302 @default.
• W4312790920 hasConcept C162324750 @default.
• W4312790920 hasConcept C198082294 @default.
• W4312790920 hasConcept C202444582 @default.
• W4312790920 hasConcept C2776151529 @default.
• W4312790920 hasConcept C31972630 @default.
• W4312790920 hasConcept C33923547 @default.
• W4312790920 hasConcept C41008148 @default.
• W4312790920 hasConcept C87360688 @default.
• W4312790920 hasConcept C9652623 @default.
• W4312790920 hasConceptScore W4312790920C10138342 @default.
• W4312790920 hasConceptScore W4312790920C108583219 @default.
• W4312790920 hasConceptScore W4312790920C153180895 @default.
• W4312790920 hasConceptScore W4312790920C154945302 @default.
• W4312790920 hasConceptScore W4312790920C162324750 @default.
• W4312790920 hasConceptScore W4312790920C198082294 @default.
• W4312790920 hasConceptScore W4312790920C202444582 @default.
• W4312790920 hasConceptScore W4312790920C2776151529 @default.
• W4312790920 hasConceptScore W4312790920C31972630 @default.
• W4312790920 hasConceptScore W4312790920C33923547 @default.
• W4312790920 hasConceptScore W4312790920C41008148 @default.
• W4312790920 hasConceptScore W4312790920C87360688 @default.
• W4312790920 hasConceptScore W4312790920C9652623 @default.
• W4312790920 hasFunder F4320321001 @default.
• W4312790920 hasLocation W43127909201 @default.
• W4312790920 hasLocation W43127909202 @default.

• next