Matches in SemOpenAlex for { <https://semopenalex.org/work/W2904480641> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2904480641 endingPage "755" @default.
- W2904480641 startingPage "751" @default.
- W2904480641 abstract "Synthetic aperture radar (SAR) ship detection is an important part of marine monitoring. With the development in computer vision, deep learning has been used for ship detection in SAR images such as the faster region-based convolutional neural network (R-CNN), single-shot multibox detector, and densely connected network. In SAR ship detection field, deep learning has much better detection performance than traditional methods on nearshore areas. This is because traditional methods need sea-land segmentation before detection, and inaccurate sea-land mask decreases its detection performance. Though current deep learning SAR ship detection methods still have many false detections in land areas, and some ships are missed in sea areas. In this letter, a new network architecture based on the faster R-CNN is proposed to further improve the detection performance by using squeeze and excitation mechanism. In order to improve performance, first, the feature maps are extracted and concatenated to obtain multiscale feature maps with ImageNet pretrained VGG network. After region of interest pooling, an encoding scale vector which has values between 0 and 1 is generated from subfeature maps. The scale vector is ranked, and only top K values will be preserved. Other values will be set to 0. Then, the subfeature maps are recalibrated by this scale vector. The redundant subfeature maps will be suppressed by this operation, and the detection performance of detector can be improved. The experimental results based on Sentinel-1 images show that the detection performance of the proposed method achieves 0.836 which is 9.7% better than the state-of-the-art method when using F1 as matric and executes 14% faster." @default.
- W2904480641 created "2018-12-22" @default.
- W2904480641 creator A5008778016 @default.
- W2904480641 creator A5082887216 @default.
- W2904480641 creator A5089424445 @default.
- W2904480641 creator A5089794328 @default.
- W2904480641 date "2019-05-01" @default.
- W2904480641 modified "2023-10-16" @default.
- W2904480641 title "Squeeze and Excitation Rank Faster R-CNN for Ship Detection in SAR Images" @default.
- W2904480641 cites W1984670836 @default.
- W2904480641 cites W2001546612 @default.
- W2904480641 cites W2102605133 @default.
- W2904480641 cites W2117287331 @default.
- W2904480641 cites W2120066054 @default.
- W2904480641 cites W2410591237 @default.
- W2904480641 cites W2432917172 @default.
- W2904480641 cites W2613063417 @default.
- W2904480641 cites W2632026579 @default.
- W2904480641 cites W2747165560 @default.
- W2904480641 cites W2799646862 @default.
- W2904480641 cites W2962992847 @default.
- W2904480641 cites W2963068995 @default.
- W2904480641 cites W2964115968 @default.
- W2904480641 doi "https://doi.org/10.1109/lgrs.2018.2882551" @default.
- W2904480641 hasPublicationYear "2019" @default.
- W2904480641 type Work @default.
- W2904480641 sameAs 2904480641 @default.
- W2904480641 citedByCount "236" @default.
- W2904480641 countsByYear W29044806412019 @default.
- W2904480641 countsByYear W29044806412020 @default.
- W2904480641 countsByYear W29044806412021 @default.
- W2904480641 countsByYear W29044806412022 @default.
- W2904480641 countsByYear W29044806412023 @default.
- W2904480641 crossrefType "journal-article" @default.
- W2904480641 hasAuthorship W2904480641A5008778016 @default.
- W2904480641 hasAuthorship W2904480641A5082887216 @default.
- W2904480641 hasAuthorship W2904480641A5089424445 @default.
- W2904480641 hasAuthorship W2904480641A5089794328 @default.
- W2904480641 hasConcept C108583219 @default.
- W2904480641 hasConcept C127313418 @default.
- W2904480641 hasConcept C138885662 @default.
- W2904480641 hasConcept C153180895 @default.
- W2904480641 hasConcept C154945302 @default.
- W2904480641 hasConcept C2776151529 @default.
- W2904480641 hasConcept C2776401178 @default.
- W2904480641 hasConcept C31972630 @default.
- W2904480641 hasConcept C41008148 @default.
- W2904480641 hasConcept C41895202 @default.
- W2904480641 hasConcept C52622490 @default.
- W2904480641 hasConcept C62649853 @default.
- W2904480641 hasConcept C76155785 @default.
- W2904480641 hasConcept C81363708 @default.
- W2904480641 hasConcept C87360688 @default.
- W2904480641 hasConcept C89600930 @default.
- W2904480641 hasConcept C94915269 @default.
- W2904480641 hasConceptScore W2904480641C108583219 @default.
- W2904480641 hasConceptScore W2904480641C127313418 @default.
- W2904480641 hasConceptScore W2904480641C138885662 @default.
- W2904480641 hasConceptScore W2904480641C153180895 @default.
- W2904480641 hasConceptScore W2904480641C154945302 @default.
- W2904480641 hasConceptScore W2904480641C2776151529 @default.
- W2904480641 hasConceptScore W2904480641C2776401178 @default.
- W2904480641 hasConceptScore W2904480641C31972630 @default.
- W2904480641 hasConceptScore W2904480641C41008148 @default.
- W2904480641 hasConceptScore W2904480641C41895202 @default.
- W2904480641 hasConceptScore W2904480641C52622490 @default.
- W2904480641 hasConceptScore W2904480641C62649853 @default.
- W2904480641 hasConceptScore W2904480641C76155785 @default.
- W2904480641 hasConceptScore W2904480641C81363708 @default.
- W2904480641 hasConceptScore W2904480641C87360688 @default.
- W2904480641 hasConceptScore W2904480641C89600930 @default.
- W2904480641 hasConceptScore W2904480641C94915269 @default.
- W2904480641 hasFunder F4320321001 @default.
- W2904480641 hasIssue "5" @default.
- W2904480641 hasLocation W29044806411 @default.
- W2904480641 hasOpenAccess W2904480641 @default.
- W2904480641 hasPrimaryLocation W29044806411 @default.
- W2904480641 hasRelatedWork W2970686063 @default.
- W2904480641 hasRelatedWork W3029198973 @default.
- W2904480641 hasRelatedWork W3034745255 @default.
- W2904480641 hasRelatedWork W3133861977 @default.
- W2904480641 hasRelatedWork W3167935049 @default.
- W2904480641 hasRelatedWork W3193565141 @default.
- W2904480641 hasRelatedWork W4226493464 @default.
- W2904480641 hasRelatedWork W4254103348 @default.
- W2904480641 hasRelatedWork W4312417841 @default.
- W2904480641 hasRelatedWork W2969228573 @default.
- W2904480641 hasVolume "16" @default.
- W2904480641 isParatext "false" @default.
- W2904480641 isRetracted "false" @default.
- W2904480641 magId "2904480641" @default.
- W2904480641 workType "article" @default.