Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319985874> ?p ?o ?g. }
- W4319985874 endingPage "546" @default.
- W4319985874 startingPage "546" @default.
- W4319985874 abstract "Automated crack detection technologies based on deep learning have been extensively used as one of the indicators of performance degradation of concrete structures. However, there are numerous drawbacks of existing methods in crack segmentation due to the fine and microscopic properties of cracks. Aiming to address this issue, a crack segmentation method is proposed. First, a pyramidal residual network based on encoder–decoder using Omni-Dimensional Dynamic Convolution is suggested to explore the network suitable for the task of crack segmentation. Additionally, the proposed method uses the mean intersection over union as the network evaluation index to lessen the impact of background features on the network performance in the evaluation and adopts a multi-loss calculation of positive and negative sample imbalance to weigh the negative impact of sample imbalance. As a final step in performance evaluation, a dataset for concrete cracks is developed. By using our dataset, the proposed method is validated to have an accuracy of 99.05% and an mIoU of 87.00%. The experimental results demonstrate that the concrete crack segmentation method is superior to the well-known networks, such as SegNet, DeeplabV3+, and Swin-unet." @default.
- W4319985874 created "2023-02-11" @default.
- W4319985874 creator A5080224606 @default.
- W4319985874 creator A5084183291 @default.
- W4319985874 date "2023-02-10" @default.
- W4319985874 modified "2023-10-09" @default.
- W4319985874 title "Pixel-Level Concrete Crack Segmentation Using Pyramidal Residual Network with Omni-Dimensional Dynamic Convolution" @default.
- W4319985874 cites W2013563330 @default.
- W4319985874 cites W2062644120 @default.
- W4319985874 cites W2089266401 @default.
- W4319985874 cites W2093303892 @default.
- W4319985874 cites W2106309274 @default.
- W4319985874 cites W2194775991 @default.
- W4319985874 cites W2395611524 @default.
- W4319985874 cites W2412782625 @default.
- W4319985874 cites W2499316477 @default.
- W4319985874 cites W2560023338 @default.
- W4319985874 cites W2565639579 @default.
- W4319985874 cites W2598457882 @default.
- W4319985874 cites W2598666589 @default.
- W4319985874 cites W2736982298 @default.
- W4319985874 cites W2752782242 @default.
- W4319985874 cites W2799213142 @default.
- W4319985874 cites W2808500492 @default.
- W4319985874 cites W2840807046 @default.
- W4319985874 cites W2884001105 @default.
- W4319985874 cites W2884561390 @default.
- W4319985874 cites W2899242765 @default.
- W4319985874 cites W2909008955 @default.
- W4319985874 cites W2912350898 @default.
- W4319985874 cites W2913580266 @default.
- W4319985874 cites W2920768970 @default.
- W4319985874 cites W2941356554 @default.
- W4319985874 cites W2956776634 @default.
- W4319985874 cites W2962914239 @default.
- W4319985874 cites W2962971773 @default.
- W4319985874 cites W2963516811 @default.
- W4319985874 cites W2963881378 @default.
- W4319985874 cites W2964308596 @default.
- W4319985874 cites W2964309882 @default.
- W4319985874 cites W2982083293 @default.
- W4319985874 cites W3093870111 @default.
- W4319985874 cites W3104370314 @default.
- W4319985874 cites W4206309809 @default.
- W4319985874 cites W4245530061 @default.
- W4319985874 cites W4282966364 @default.
- W4319985874 cites W4307957701 @default.
- W4319985874 cites W4311988062 @default.
- W4319985874 cites W4312443924 @default.
- W4319985874 cites W4313452645 @default.
- W4319985874 doi "https://doi.org/10.3390/pr11020546" @default.
- W4319985874 hasPublicationYear "2023" @default.
- W4319985874 type Work @default.
- W4319985874 citedByCount "3" @default.
- W4319985874 countsByYear W43199858742023 @default.
- W4319985874 crossrefType "journal-article" @default.
- W4319985874 hasAuthorship W4319985874A5080224606 @default.
- W4319985874 hasAuthorship W4319985874A5084183291 @default.
- W4319985874 hasBestOaLocation W43199858741 @default.
- W4319985874 hasConcept C108583219 @default.
- W4319985874 hasConcept C11413529 @default.
- W4319985874 hasConcept C127413603 @default.
- W4319985874 hasConcept C146978453 @default.
- W4319985874 hasConcept C153180895 @default.
- W4319985874 hasConcept C154945302 @default.
- W4319985874 hasConcept C155512373 @default.
- W4319985874 hasConcept C185592680 @default.
- W4319985874 hasConcept C198531522 @default.
- W4319985874 hasConcept C41008148 @default.
- W4319985874 hasConcept C43617362 @default.
- W4319985874 hasConcept C45347329 @default.
- W4319985874 hasConcept C50644808 @default.
- W4319985874 hasConcept C64543145 @default.
- W4319985874 hasConcept C89600930 @default.
- W4319985874 hasConceptScore W4319985874C108583219 @default.
- W4319985874 hasConceptScore W4319985874C11413529 @default.
- W4319985874 hasConceptScore W4319985874C127413603 @default.
- W4319985874 hasConceptScore W4319985874C146978453 @default.
- W4319985874 hasConceptScore W4319985874C153180895 @default.
- W4319985874 hasConceptScore W4319985874C154945302 @default.
- W4319985874 hasConceptScore W4319985874C155512373 @default.
- W4319985874 hasConceptScore W4319985874C185592680 @default.
- W4319985874 hasConceptScore W4319985874C198531522 @default.
- W4319985874 hasConceptScore W4319985874C41008148 @default.
- W4319985874 hasConceptScore W4319985874C43617362 @default.
- W4319985874 hasConceptScore W4319985874C45347329 @default.
- W4319985874 hasConceptScore W4319985874C50644808 @default.
- W4319985874 hasConceptScore W4319985874C64543145 @default.
- W4319985874 hasConceptScore W4319985874C89600930 @default.
- W4319985874 hasFunder F4320321001 @default.
- W4319985874 hasIssue "2" @default.
- W4319985874 hasLocation W43199858741 @default.
- W4319985874 hasOpenAccess W4319985874 @default.
- W4319985874 hasPrimaryLocation W43199858741 @default.
- W4319985874 hasRelatedWork W2738221750 @default.
- W4319985874 hasRelatedWork W2790662084 @default.
- W4319985874 hasRelatedWork W2954384599 @default.
- W4319985874 hasRelatedWork W2960184797 @default.