FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386001132> ?p ?o ?g. }

• W4386001132 abstract "ABSTRACTFast and accurate detection of airfield pavement damage is crucial to airport flight safety and airfield pavement maintenance. An efficient and lightweight detection algorithm that can be embedded into the mobile detection device has been in urgent demand. However, traditional Convolutional Neural Networks (CNNs) usually generate redundant feature maps during feature extraction or use extra operations during feature fusion to gain better performance, which greatly challenges the efficiency of the algorithm. We approached this issue by proposing an accurate and efficient detection algorithm, the YOLOv5-APD. The algorithm improves the model performance in two ways: Speeding up training and inferencing by using cheaper operations during feature extraction; Reducing the model complexity by removing redundant nodes during feature fusion. We verified the detection performance of YOLOv5-APD on a self-made dataset and compared it with the other state-of-the-art (SOTA) models. Then ablation experiments were carried out to investigate the effects of the proposed model design and the impact of image augmentation. Results showed that the proposed YOLOv5-APD model outperformed the SOTA algorithms in model performance and efficiency, which attained the optimal performance mean average precision (mAP) of 0.924. The proposed model also achieved the fastest inference speed of 142 frame-per-second (FPS), with a model footprint of 8.3 G FLOPs and 8 MB Parameters.KEYWORDS: Airfield pavementautomatic damage detectiondeep learningdata augmentationYOLO Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationFundingThis study is sponsored by the National Natural Science Foundation of China (No. 52008311 and No. 51878499), the Science and Technology Commission of Shanghai Municipality (No. 21ZR1465700 and No. 19DZ1204200), Shandong Province Transportation Science and Technology Plan Project (2021B47), the Fundamental Research Funds for the Central Universities (22120230196), and Shanghai Municipal Natural Science Foundation (21ZR1465700). The authors are grateful for their financial support." @default.
• W4386001132 created "2023-08-20" @default.
• W4386001132 creator A5009590736 @default.
• W4386001132 creator A5024917626 @default.
• W4386001132 creator A5030730843 @default.
• W4386001132 creator A5040805352 @default.
• W4386001132 creator A5061478390 @default.
• W4386001132 creator A5086356484 @default.
• W4386001132 creator A5090770627 @default.
• W4386001132 date "2023-08-19" @default.
• W4386001132 modified "2023-10-17" @default.
• W4386001132 title "Automated detection of airfield pavement damages: an efficient light-weight algorithm" @default.
• W4386001132 cites W1536680647 @default.
• W4386001132 cites W1544877491 @default.
• W4386001132 cites W1862829300 @default.
• W4386001132 cites W1960097882 @default.
• W4386001132 cites W1969393996 @default.
• W4386001132 cites W1977419602 @default.
• W4386001132 cites W1995130521 @default.
• W4386001132 cites W2008488233 @default.
• W4386001132 cites W2012876448 @default.
• W4386001132 cites W2020109627 @default.
• W4386001132 cites W2031703128 @default.
• W4386001132 cites W2033819500 @default.
• W4386001132 cites W2035006112 @default.
• W4386001132 cites W2075502112 @default.
• W4386001132 cites W2075935813 @default.
• W4386001132 cites W2079054397 @default.
• W4386001132 cites W2102605133 @default.
• W4386001132 cites W2109255472 @default.
• W4386001132 cites W2112796928 @default.
• W4386001132 cites W2132239597 @default.
• W4386001132 cites W2138014601 @default.
• W4386001132 cites W2144801789 @default.
• W4386001132 cites W2153812483 @default.
• W4386001132 cites W2158698691 @default.
• W4386001132 cites W2169303706 @default.
• W4386001132 cites W2289283324 @default.
• W4386001132 cites W2312405072 @default.
• W4386001132 cites W2395611524 @default.
• W4386001132 cites W2407692387 @default.
• W4386001132 cites W2511065100 @default.
• W4386001132 cites W2523358814 @default.
• W4386001132 cites W2588180165 @default.
• W4386001132 cites W2612363743 @default.
• W4386001132 cites W2748643398 @default.
• W4386001132 cites W2757455114 @default.
• W4386001132 cites W2760230021 @default.
• W4386001132 cites W2792636161 @default.
• W4386001132 cites W2795325883 @default.
• W4386001132 cites W2800343216 @default.
• W4386001132 cites W2899242765 @default.
• W4386001132 cites W2906977256 @default.
• W4386001132 cites W2913580266 @default.
• W4386001132 cites W2913742577 @default.
• W4386001132 cites W2919115771 @default.
• W4386001132 cites W2936766908 @default.
• W4386001132 cites W2963037989 @default.
• W4386001132 cites W2963351448 @default.
• W4386001132 cites W2963857746 @default.
• W4386001132 cites W2966612933 @default.
• W4386001132 cites W2978200937 @default.
• W4386001132 cites W2988916019 @default.
• W4386001132 cites W3001456352 @default.
• W4386001132 cites W3023417327 @default.
• W4386001132 cites W3035414587 @default.
• W4386001132 cites W3080819318 @default.
• W4386001132 cites W3093788378 @default.
• W4386001132 cites W3106250896 @default.
• W4386001132 cites W3113839682 @default.
• W4386001132 cites W3124942917 @default.
• W4386001132 cites W3163630086 @default.
• W4386001132 cites W3167866269 @default.
• W4386001132 cites W3177431918 @default.
• W4386001132 cites W3194583493 @default.
• W4386001132 cites W3196735949 @default.
• W4386001132 cites W4212764068 @default.
• W4386001132 cites W4213439603 @default.
• W4386001132 cites W4214838030 @default.
• W4386001132 cites W4214890985 @default.
• W4386001132 cites W4283215527 @default.
• W4386001132 cites W4283791591 @default.
• W4386001132 cites W4293071267 @default.
• W4386001132 cites W4297830339 @default.
• W4386001132 cites W4306963582 @default.
• W4386001132 cites W4307831534 @default.
• W4386001132 cites W4309688869 @default.
• W4386001132 cites W4310264525 @default.
• W4386001132 cites W4321785473 @default.
• W4386001132 cites W639708223 @default.
• W4386001132 doi "https://doi.org/10.1080/10298436.2023.2247135" @default.
• W4386001132 hasPublicationYear "2023" @default.
• W4386001132 type Work @default.
• W4386001132 citedByCount "0" @default.
• W4386001132 crossrefType "journal-article" @default.
• W4386001132 hasAuthorship W4386001132A5009590736 @default.
• W4386001132 hasAuthorship W4386001132A5024917626 @default.
• W4386001132 hasAuthorship W4386001132A5030730843 @default.
• W4386001132 hasAuthorship W4386001132A5040805352 @default.
• W4386001132 hasAuthorship W4386001132A5061478390 @default.

• next