FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3049361954> ?p ?o ?g. }

• W3049361954 endingPage "2619" @default.
• W3049361954 startingPage "2619" @default.
• W3049361954 abstract "In recent years, with the improvement of synthetic aperture radar (SAR) imaging resolution, it is urgent to develop methods with higher accuracy and faster speed for ship detection in high-resolution SAR images. Among all kinds of methods, deep-learning-based algorithms bring promising performance due to end-to-end detection and automated feature extraction. However, several challenges still exist: (1) standard deep learning detectors based on anchors have certain unsolved problems, such as tuning of anchor-related parameters, scale-variation and high computational costs. (2) SAR data is huge but the labeled data is relatively small, which may lead to overfitting in training. (3) To improve detection speed, deep learning detectors generally detect targets based on low-resolution features, which may cause missed detections for small targets. In order to address the above problems, an anchor-free convolutional network with dense attention feature aggregation is proposed in this paper. Firstly, we use a lightweight feature extractor to extract multiscale ship features. The inverted residual blocks with depth-wise separable convolution reduce the network parameters and improve the detection speed. Secondly, a novel feature aggregation scheme called dense attention feature aggregation (DAFA) is proposed to obtain a high-resolution feature map with multiscale information. By combining the multiscale features through dense connections and iterative fusions, DAFA improves the generalization performance of the network. In addition, an attention block, namely spatial and channel squeeze and excitation (SCSE) block is embedded in the upsampling process of DAFA to enhance the salient features of the target and suppress the background clutters. Third, an anchor-free detector, which is a center-point-based ship predictor (CSP), is adopted in this paper. CSP regresses the ship centers and ship sizes simultaneously on the high-resolution feature map to implement anchor-free and nonmaximum suppression (NMS)-free ship detection. The experiments on the AirSARShip-1.0 dataset demonstrate the effectiveness of our method. The results show that the proposed method outperforms several mainstream detection algorithms in both accuracy and speed." @default.
• W3049361954 created "2020-08-21" @default.
• W3049361954 creator A5018461433 @default.
• W3049361954 creator A5042241049 @default.
• W3049361954 creator A5062211930 @default.
• W3049361954 creator A5066119228 @default.
• W3049361954 creator A5085382296 @default.
• W3049361954 date "2020-08-13" @default.
• W3049361954 modified "2023-10-10" @default.
• W3049361954 title "Anchor-free Convolutional Network with Dense Attention Feature Aggregation for Ship Detection in SAR Images" @default.
• W3049361954 cites W1964313985 @default.
• W3049361954 cites W2025025456 @default.
• W3049361954 cites W2042729642 @default.
• W3049361954 cites W2086754696 @default.
• W3049361954 cites W2137782143 @default.
• W3049361954 cites W2149492639 @default.
• W3049361954 cites W2516172563 @default.
• W3049361954 cites W2564429410 @default.
• W3049361954 cites W2747165560 @default.
• W3049361954 cites W2770947844 @default.
• W3049361954 cites W2783266131 @default.
• W3049361954 cites W2797610275 @default.
• W3049361954 cites W2809742058 @default.
• W3049361954 cites W2884367402 @default.
• W3049361954 cites W2891190453 @default.
• W3049361954 cites W2892719431 @default.
• W3049361954 cites W2898090956 @default.
• W3049361954 cites W2913527107 @default.
• W3049361954 cites W2919318018 @default.
• W3049361954 cites W2922891743 @default.
• W3049361954 cites W2928870406 @default.
• W3049361954 cites W2941889397 @default.
• W3049361954 cites W2946589087 @default.
• W3049361954 cites W2961699889 @default.
• W3049361954 cites W2963785947 @default.
• W3049361954 cites W2973531547 @default.
• W3049361954 cites W2981864880 @default.
• W3049361954 cites W2984372632 @default.
• W3049361954 cites W3014224354 @default.
• W3049361954 doi "https://doi.org/10.3390/rs12162619" @default.
• W3049361954 hasPublicationYear "2020" @default.
• W3049361954 type Work @default.
• W3049361954 sameAs 3049361954 @default.
• W3049361954 citedByCount "45" @default.
• W3049361954 countsByYear W30493619542020 @default.
• W3049361954 countsByYear W30493619542021 @default.
• W3049361954 countsByYear W30493619542022 @default.
• W3049361954 countsByYear W30493619542023 @default.
• W3049361954 crossrefType "journal-article" @default.
• W3049361954 hasAuthorship W3049361954A5018461433 @default.
• W3049361954 hasAuthorship W3049361954A5042241049 @default.
• W3049361954 hasAuthorship W3049361954A5062211930 @default.
• W3049361954 hasAuthorship W3049361954A5066119228 @default.
• W3049361954 hasAuthorship W3049361954A5085382296 @default.
• W3049361954 hasBestOaLocation W30493619541 @default.
• W3049361954 hasConcept C108583219 @default.
• W3049361954 hasConcept C110384440 @default.
• W3049361954 hasConcept C115961682 @default.
• W3049361954 hasConcept C127162648 @default.
• W3049361954 hasConcept C138885662 @default.
• W3049361954 hasConcept C153180895 @default.
• W3049361954 hasConcept C154945302 @default.
• W3049361954 hasConcept C22019652 @default.
• W3049361954 hasConcept C2524010 @default.
• W3049361954 hasConcept C2776401178 @default.
• W3049361954 hasConcept C2777210771 @default.
• W3049361954 hasConcept C31258907 @default.
• W3049361954 hasConcept C31972630 @default.
• W3049361954 hasConcept C33923547 @default.
• W3049361954 hasConcept C41008148 @default.
• W3049361954 hasConcept C41895202 @default.
• W3049361954 hasConcept C50644808 @default.
• W3049361954 hasConcept C52622490 @default.
• W3049361954 hasConcept C59404180 @default.
• W3049361954 hasConcept C81363708 @default.
• W3049361954 hasConcept C87360688 @default.
• W3049361954 hasConceptScore W3049361954C108583219 @default.
• W3049361954 hasConceptScore W3049361954C110384440 @default.
• W3049361954 hasConceptScore W3049361954C115961682 @default.
• W3049361954 hasConceptScore W3049361954C127162648 @default.
• W3049361954 hasConceptScore W3049361954C138885662 @default.
• W3049361954 hasConceptScore W3049361954C153180895 @default.
• W3049361954 hasConceptScore W3049361954C154945302 @default.
• W3049361954 hasConceptScore W3049361954C22019652 @default.
• W3049361954 hasConceptScore W3049361954C2524010 @default.
• W3049361954 hasConceptScore W3049361954C2776401178 @default.
• W3049361954 hasConceptScore W3049361954C2777210771 @default.
• W3049361954 hasConceptScore W3049361954C31258907 @default.
• W3049361954 hasConceptScore W3049361954C31972630 @default.
• W3049361954 hasConceptScore W3049361954C33923547 @default.
• W3049361954 hasConceptScore W3049361954C41008148 @default.
• W3049361954 hasConceptScore W3049361954C41895202 @default.
• W3049361954 hasConceptScore W3049361954C50644808 @default.
• W3049361954 hasConceptScore W3049361954C52622490 @default.
• W3049361954 hasConceptScore W3049361954C59404180 @default.
• W3049361954 hasConceptScore W3049361954C81363708 @default.
• W3049361954 hasConceptScore W3049361954C87360688 @default.
• W3049361954 hasFunder F4320334627 @default.

• next