Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376636680> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4376636680 endingPage "085405" @default.
- W4376636680 startingPage "085405" @default.
- W4376636680 abstract "Abstract Efficient and accurate visual inspection of products is of great significance for intelligent manufacturing. In this paper, a visual inspection framework based on a lightweight Transformer is proposed for the pixel-level inspection of tire defects. A dual-path-Transformer feature encoder was proposed based on a hybrid architecture of convolutional neural network and Transformer, which is used to learn the local and global relationship of defect features. Moreover, multi-scale fusion Transformer (MFT) and spatial cross Transformer (SCT) were proposed, based on which a feature decoder was built. In the decoder, the MFT provides valuable spatial information for SCT, such that different levels of feature maps can refine the dependency of pixels through SCT. The proposed method is tested on the tire radiographic image dataset. Experimental results show that the proposed method reaches a detection accuracy of 98.57% and mIoU of 85.56%. Moreover, the method achieves the balance between accuracy and efficiency with satisfactory characterization ability for the defect geometric shape, and provides theoretical support for the future industrial deployment of Transformer." @default.
- W4376636680 created "2023-05-17" @default.
- W4376636680 creator A5005604923 @default.
- W4376636680 creator A5035032519 @default.
- W4376636680 creator A5040161004 @default.
- W4376636680 creator A5040643591 @default.
- W4376636680 creator A5052324354 @default.
- W4376636680 creator A5068112632 @default.
- W4376636680 creator A5081722152 @default.
- W4376636680 date "2023-05-23" @default.
- W4376636680 modified "2023-10-16" @default.
- W4376636680 title "Automatic pixel-level detection of tire defects based on a lightweight Transformer architecture" @default.
- W4376636680 cites W2110764733 @default.
- W4376636680 cites W2132083787 @default.
- W4376636680 cites W2209436463 @default.
- W4376636680 cites W2525076183 @default.
- W4376636680 cites W2741224071 @default.
- W4376636680 cites W2886037842 @default.
- W4376636680 cites W2897495768 @default.
- W4376636680 cites W2919115771 @default.
- W4376636680 cites W2926743806 @default.
- W4376636680 cites W2944303778 @default.
- W4376636680 cites W2998234644 @default.
- W4376636680 cites W3002180883 @default.
- W4376636680 cites W3029172569 @default.
- W4376636680 cites W3035841695 @default.
- W4376636680 cites W3092600573 @default.
- W4376636680 cites W3124186538 @default.
- W4376636680 cites W3176427953 @default.
- W4376636680 cites W3177301635 @default.
- W4376636680 cites W3182843231 @default.
- W4376636680 cites W3213693699 @default.
- W4376636680 cites W4211022959 @default.
- W4376636680 cites W4223999830 @default.
- W4376636680 cites W4225113999 @default.
- W4376636680 cites W4255391993 @default.
- W4376636680 doi "https://doi.org/10.1088/1361-6501/acd5f2" @default.
- W4376636680 hasPublicationYear "2023" @default.
- W4376636680 type Work @default.
- W4376636680 citedByCount "0" @default.
- W4376636680 crossrefType "journal-article" @default.
- W4376636680 hasAuthorship W4376636680A5005604923 @default.
- W4376636680 hasAuthorship W4376636680A5035032519 @default.
- W4376636680 hasAuthorship W4376636680A5040161004 @default.
- W4376636680 hasAuthorship W4376636680A5040643591 @default.
- W4376636680 hasAuthorship W4376636680A5052324354 @default.
- W4376636680 hasAuthorship W4376636680A5068112632 @default.
- W4376636680 hasAuthorship W4376636680A5081722152 @default.
- W4376636680 hasConcept C111919701 @default.
- W4376636680 hasConcept C118505674 @default.
- W4376636680 hasConcept C119599485 @default.
- W4376636680 hasConcept C127413603 @default.
- W4376636680 hasConcept C153180895 @default.
- W4376636680 hasConcept C154945302 @default.
- W4376636680 hasConcept C160633673 @default.
- W4376636680 hasConcept C165801399 @default.
- W4376636680 hasConcept C31972630 @default.
- W4376636680 hasConcept C41008148 @default.
- W4376636680 hasConcept C66322947 @default.
- W4376636680 hasConcept C81363708 @default.
- W4376636680 hasConceptScore W4376636680C111919701 @default.
- W4376636680 hasConceptScore W4376636680C118505674 @default.
- W4376636680 hasConceptScore W4376636680C119599485 @default.
- W4376636680 hasConceptScore W4376636680C127413603 @default.
- W4376636680 hasConceptScore W4376636680C153180895 @default.
- W4376636680 hasConceptScore W4376636680C154945302 @default.
- W4376636680 hasConceptScore W4376636680C160633673 @default.
- W4376636680 hasConceptScore W4376636680C165801399 @default.
- W4376636680 hasConceptScore W4376636680C31972630 @default.
- W4376636680 hasConceptScore W4376636680C41008148 @default.
- W4376636680 hasConceptScore W4376636680C66322947 @default.
- W4376636680 hasConceptScore W4376636680C81363708 @default.
- W4376636680 hasIssue "8" @default.
- W4376636680 hasLocation W43766366801 @default.
- W4376636680 hasOpenAccess W4376636680 @default.
- W4376636680 hasPrimaryLocation W43766366801 @default.
- W4376636680 hasRelatedWork W121273120 @default.
- W4376636680 hasRelatedWork W2002009170 @default.
- W4376636680 hasRelatedWork W2034462085 @default.
- W4376636680 hasRelatedWork W2090093270 @default.
- W4376636680 hasRelatedWork W2152301642 @default.
- W4376636680 hasRelatedWork W2337415362 @default.
- W4376636680 hasRelatedWork W2740820121 @default.
- W4376636680 hasRelatedWork W3005455252 @default.
- W4376636680 hasRelatedWork W317572212 @default.
- W4376636680 hasRelatedWork W4312857205 @default.
- W4376636680 hasVolume "34" @default.
- W4376636680 isParatext "false" @default.
- W4376636680 isRetracted "false" @default.
- W4376636680 workType "article" @default.