FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208019692> ?p ?o ?g. }

• W3208019692 endingPage "4209" @default.
• W3208019692 startingPage "4209" @default.
• W3208019692 abstract "Due to its great application value in the military and civilian fields, ship detection in synthetic aperture radar (SAR) images has always attracted much attention. However, ship targets in High-Resolution (HR) SAR images show the significant characteristics of multi-scale, arbitrary directions and dense arrangement, posing enormous challenges to detect ships quickly and accurately. To address these issues above, a novel YOLO-based arbitrary-oriented SAR ship detector using bi-directional feature fusion and angular classification (BiFA-YOLO) is proposed in this article. First of all, a novel bi-directional feature fusion module (Bi-DFFM) tailored to SAR ship detection is applied to the YOLO framework. This module can efficiently aggregate multi-scale features through bi-directional (top-down and bottom-up) information interaction, which is helpful for detecting multi-scale ships. Secondly, to effectively detect arbitrary-oriented and densely arranged ships in HR SAR images, we add an angular classification structure to the head network. This structure is conducive to accurately obtaining ships’ angle information without the problem of boundary discontinuity and complicated parameter regression. Meanwhile, in BiFA-YOLO, a random rotation mosaic data augmentation method is employed to suppress the impact of angle imbalance. Compared with other conventional data augmentation methods, the proposed method can better improve detection performance of arbitrary-oriented ships. Finally, we conduct extensive experiments on the SAR ship detection dataset (SSDD) and large-scene HR SAR images from GF-3 satellite to verify our method. The proposed method can reach the detection performance with precision = 94.85%, recall = 93.97%, average precision = 93.90%, and F1-score = 0.9441 on SSDD. The detection speed of our method is approximately 13.3 ms per 512 × 512 image. In addition, comparison experiments with other deep learning-based methods and verification experiments on large-scene HR SAR images demonstrate that our method shows strong robustness and adaptability." @default.
• W3208019692 created "2021-11-08" @default.
• W3208019692 creator A5030795703 @default.
• W3208019692 creator A5062810392 @default.
• W3208019692 creator A5080019802 @default.
• W3208019692 creator A5082887216 @default.
• W3208019692 creator A5089424445 @default.
• W3208019692 creator A5089794328 @default.
• W3208019692 date "2021-10-20" @default.
• W3208019692 modified "2023-10-16" @default.
• W3208019692 title "BiFA-YOLO: A Novel YOLO-Based Method for Arbitrary-Oriented Ship Detection in High-Resolution SAR Images" @default.
• W3208019692 cites W2090991102 @default.
• W3208019692 cites W2551083396 @default.
• W3208019692 cites W2619158701 @default.
• W3208019692 cites W2783266131 @default.
• W3208019692 cites W2805839151 @default.
• W3208019692 cites W2889346359 @default.
• W3208019692 cites W2904480641 @default.
• W3208019692 cites W2913527107 @default.
• W3208019692 cites W2919011445 @default.
• W3208019692 cites W2921103930 @default.
• W3208019692 cites W2928007866 @default.
• W3208019692 cites W2945368469 @default.
• W3208019692 cites W2955454611 @default.
• W3208019692 cites W2960301618 @default.
• W3208019692 cites W2961699889 @default.
• W3208019692 cites W2970277117 @default.
• W3208019692 cites W2982932271 @default.
• W3208019692 cites W2997747012 @default.
• W3208019692 cites W2998017713 @default.
• W3208019692 cites W2998974772 @default.
• W3208019692 cites W3017373943 @default.
• W3208019692 cites W3031154432 @default.
• W3208019692 cites W3032837604 @default.
• W3208019692 cites W3033996275 @default.
• W3208019692 cites W3035559754 @default.
• W3208019692 cites W3037440390 @default.
• W3208019692 cites W3041525128 @default.
• W3208019692 cites W3049361954 @default.
• W3208019692 cites W3112594048 @default.
• W3208019692 cites W3117374221 @default.
• W3208019692 cites W3118944910 @default.
• W3208019692 cites W3125381463 @default.
• W3208019692 cites W3126212272 @default.
• W3208019692 cites W3127811628 @default.
• W3208019692 cites W3134517928 @default.
• W3208019692 cites W3136239039 @default.
• W3208019692 cites W3136518870 @default.
• W3208019692 cites W3162189777 @default.
• W3208019692 cites W3163510280 @default.
• W3208019692 cites W3165629794 @default.
• W3208019692 cites W3166561508 @default.
• W3208019692 cites W3180954604 @default.
• W3208019692 cites W3184737818 @default.
• W3208019692 cites W3184820801 @default.
• W3208019692 cites W3184840388 @default.
• W3208019692 cites W3190238140 @default.
• W3208019692 cites W3198862447 @default.
• W3208019692 cites W3205196764 @default.
• W3208019692 cites W639708223 @default.
• W3208019692 doi "https://doi.org/10.3390/rs13214209" @default.
• W3208019692 hasPublicationYear "2021" @default.
• W3208019692 type Work @default.
• W3208019692 sameAs 3208019692 @default.
• W3208019692 citedByCount "55" @default.
• W3208019692 countsByYear W32080196922021 @default.
• W3208019692 countsByYear W32080196922022 @default.
• W3208019692 countsByYear W32080196922023 @default.
• W3208019692 crossrefType "journal-article" @default.
• W3208019692 hasAuthorship W3208019692A5030795703 @default.
• W3208019692 hasAuthorship W3208019692A5062810392 @default.
• W3208019692 hasAuthorship W3208019692A5080019802 @default.
• W3208019692 hasAuthorship W3208019692A5082887216 @default.
• W3208019692 hasAuthorship W3208019692A5089424445 @default.
• W3208019692 hasAuthorship W3208019692A5089794328 @default.
• W3208019692 hasBestOaLocation W32080196921 @default.
• W3208019692 hasConcept C127313418 @default.
• W3208019692 hasConcept C127413603 @default.
• W3208019692 hasConcept C138885662 @default.
• W3208019692 hasConcept C146978453 @default.
• W3208019692 hasConcept C154945302 @default.
• W3208019692 hasConcept C19269812 @default.
• W3208019692 hasConcept C2776401178 @default.
• W3208019692 hasConcept C31972630 @default.
• W3208019692 hasConcept C41008148 @default.
• W3208019692 hasConcept C41895202 @default.
• W3208019692 hasConcept C62649853 @default.
• W3208019692 hasConcept C76155785 @default.
• W3208019692 hasConcept C87360688 @default.
• W3208019692 hasConcept C94915269 @default.
• W3208019692 hasConceptScore W3208019692C127313418 @default.
• W3208019692 hasConceptScore W3208019692C127413603 @default.
• W3208019692 hasConceptScore W3208019692C138885662 @default.
• W3208019692 hasConceptScore W3208019692C146978453 @default.
• W3208019692 hasConceptScore W3208019692C154945302 @default.
• W3208019692 hasConceptScore W3208019692C19269812 @default.
• W3208019692 hasConceptScore W3208019692C2776401178 @default.
• W3208019692 hasConceptScore W3208019692C31972630 @default.

• next