Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226027146> ?p ?o ?g. }
- W4226027146 endingPage "10" @default.
- W4226027146 startingPage "1" @default.
- W4226027146 abstract "The application of computer vision technology in defect detection of industrial products is a popular research direction in recent years. This article presents the pyramid feature convolutional neural network (CNN) for defect detection of rail surfaces. First, multi-scale feature maps are extracted based on the characteristics of defects and backgrounds by the pyramid feature extraction module (PFEM). Then the feature maps are input to a lightweight network consisting of a small number of parameters. The network is trained with only 40% data of the dataset using binary cross-entropy loss function and the intersection of union (IOU) loss function. In the experiment, the performance of the proposed method is evaluated using the rail surface defect dataset (RSDD) dataset by comparing it with other methods. The experimental results show that the segmentation performance and real-time performance of the proposed method are better than those of other methods." @default.
- W4226027146 created "2022-05-05" @default.
- W4226027146 creator A5008326018 @default.
- W4226027146 creator A5013812123 @default.
- W4226027146 creator A5018073672 @default.
- W4226027146 creator A5051129986 @default.
- W4226027146 date "2022-01-01" @default.
- W4226027146 modified "2023-10-14" @default.
- W4226027146 title "A Rail Surface Defect Detection Method Based on Pyramid Feature and Lightweight Convolutional Neural Network" @default.
- W4226027146 cites W2022320998 @default.
- W4226027146 cites W2030222137 @default.
- W4226027146 cites W2069747077 @default.
- W4226027146 cites W2071448691 @default.
- W4226027146 cites W2171261408 @default.
- W4226027146 cites W2242952562 @default.
- W4226027146 cites W2408485741 @default.
- W4226027146 cites W2412782625 @default.
- W4226027146 cites W2560023338 @default.
- W4226027146 cites W2588607166 @default.
- W4226027146 cites W2736973763 @default.
- W4226027146 cites W2761216034 @default.
- W4226027146 cites W2884436604 @default.
- W4226027146 cites W2913074553 @default.
- W4226027146 cites W2913133337 @default.
- W4226027146 cites W2963163009 @default.
- W4226027146 cites W2963881378 @default.
- W4226027146 cites W2964899079 @default.
- W4226027146 cites W2999092781 @default.
- W4226027146 cites W3009013436 @default.
- W4226027146 cites W3112721793 @default.
- W4226027146 cites W3128847319 @default.
- W4226027146 cites W3195872781 @default.
- W4226027146 cites W3200236763 @default.
- W4226027146 doi "https://doi.org/10.1109/tim.2022.3165287" @default.
- W4226027146 hasPublicationYear "2022" @default.
- W4226027146 type Work @default.
- W4226027146 citedByCount "8" @default.
- W4226027146 countsByYear W42260271462022 @default.
- W4226027146 countsByYear W42260271462023 @default.
- W4226027146 crossrefType "journal-article" @default.
- W4226027146 hasAuthorship W4226027146A5008326018 @default.
- W4226027146 hasAuthorship W4226027146A5013812123 @default.
- W4226027146 hasAuthorship W4226027146A5018073672 @default.
- W4226027146 hasAuthorship W4226027146A5051129986 @default.
- W4226027146 hasConcept C106301342 @default.
- W4226027146 hasConcept C121332964 @default.
- W4226027146 hasConcept C124504099 @default.
- W4226027146 hasConcept C127413603 @default.
- W4226027146 hasConcept C138885662 @default.
- W4226027146 hasConcept C142575187 @default.
- W4226027146 hasConcept C146978453 @default.
- W4226027146 hasConcept C153180895 @default.
- W4226027146 hasConcept C154945302 @default.
- W4226027146 hasConcept C167981619 @default.
- W4226027146 hasConcept C2524010 @default.
- W4226027146 hasConcept C2776401178 @default.
- W4226027146 hasConcept C31972630 @default.
- W4226027146 hasConcept C33923547 @default.
- W4226027146 hasConcept C41008148 @default.
- W4226027146 hasConcept C41895202 @default.
- W4226027146 hasConcept C50644808 @default.
- W4226027146 hasConcept C52622490 @default.
- W4226027146 hasConcept C62520636 @default.
- W4226027146 hasConcept C64543145 @default.
- W4226027146 hasConcept C81363708 @default.
- W4226027146 hasConcept C89600930 @default.
- W4226027146 hasConceptScore W4226027146C106301342 @default.
- W4226027146 hasConceptScore W4226027146C121332964 @default.
- W4226027146 hasConceptScore W4226027146C124504099 @default.
- W4226027146 hasConceptScore W4226027146C127413603 @default.
- W4226027146 hasConceptScore W4226027146C138885662 @default.
- W4226027146 hasConceptScore W4226027146C142575187 @default.
- W4226027146 hasConceptScore W4226027146C146978453 @default.
- W4226027146 hasConceptScore W4226027146C153180895 @default.
- W4226027146 hasConceptScore W4226027146C154945302 @default.
- W4226027146 hasConceptScore W4226027146C167981619 @default.
- W4226027146 hasConceptScore W4226027146C2524010 @default.
- W4226027146 hasConceptScore W4226027146C2776401178 @default.
- W4226027146 hasConceptScore W4226027146C31972630 @default.
- W4226027146 hasConceptScore W4226027146C33923547 @default.
- W4226027146 hasConceptScore W4226027146C41008148 @default.
- W4226027146 hasConceptScore W4226027146C41895202 @default.
- W4226027146 hasConceptScore W4226027146C50644808 @default.
- W4226027146 hasConceptScore W4226027146C52622490 @default.
- W4226027146 hasConceptScore W4226027146C62520636 @default.
- W4226027146 hasConceptScore W4226027146C64543145 @default.
- W4226027146 hasConceptScore W4226027146C81363708 @default.
- W4226027146 hasConceptScore W4226027146C89600930 @default.
- W4226027146 hasFunder F4320335777 @default.
- W4226027146 hasLocation W42260271461 @default.
- W4226027146 hasOpenAccess W4226027146 @default.
- W4226027146 hasPrimaryLocation W42260271461 @default.
- W4226027146 hasRelatedWork W1631910785 @default.
- W4226027146 hasRelatedWork W1669643531 @default.
- W4226027146 hasRelatedWork W2059299633 @default.
- W4226027146 hasRelatedWork W2122581818 @default.
- W4226027146 hasRelatedWork W2159066190 @default.
- W4226027146 hasRelatedWork W2406522397 @default.