Matches in SemOpenAlex for { <https://semopenalex.org/work/W2795998052> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2795998052 endingPage "674" @default.
- W2795998052 startingPage "653" @default.
- W2795998052 abstract "This study conducts crack identification from real-world images containing complicated disturbance information (cracks, handwriting scripts, and background) inside steel box girders of bridges. Considering the multilevel and multi-scale features of the input images, a modified fusion convolutional neural network architecture is proposed. As input, 350 raw images are taken with a consumer-grade camera and divided into sub-images with resolution of 64 × 64 pixels (67,200 in total). A regular convolutional neural network structure is employed as baseline to demonstrate the accuracy benefits from the proposed fusion convolutional neural network structure. The confusion matrix is defined for prediction performance evaluation on the test set. A total of six additional entire raw images are used to investigate the robustness and feasibility of the proposed approach. A binary conversion process based on the optimal entropy threshold method is applied and closely followed to identify the crack pixels in the sub-images. The effect of the super-resolution inputs on accuracy is investigated. Results show that the trained modified fusion convolutional neural network can automatically detect the cracks, handwriting, and background from the raw images. The recognition errors of the fusion convolutional neural network in both the training and validation processes are smaller than those of the regular convolutional neural network. The super-resolution process hurts the general identification accuracy." @default.
- W2795998052 created "2018-04-13" @default.
- W2795998052 creator A5018318136 @default.
- W2795998052 creator A5045958583 @default.
- W2795998052 creator A5066602975 @default.
- W2795998052 creator A5070569173 @default.
- W2795998052 date "2018-04-02" @default.
- W2795998052 modified "2023-10-12" @default.
- W2795998052 title "Surface fatigue crack identification in steel box girder of bridges by a deep fusion convolutional neural network based on consumer-grade camera images" @default.
- W2795998052 cites W1523493493 @default.
- W2795998052 cites W1806891645 @default.
- W2795998052 cites W1842439412 @default.
- W2795998052 cites W1844128389 @default.
- W2795998052 cites W1856933006 @default.
- W2795998052 cites W1885185971 @default.
- W2795998052 cites W1955857676 @default.
- W2795998052 cites W1995130521 @default.
- W2795998052 cites W2009684145 @default.
- W2795998052 cites W2017826892 @default.
- W2795998052 cites W2018168021 @default.
- W2795998052 cites W2022909534 @default.
- W2795998052 cites W2023920199 @default.
- W2795998052 cites W2048152057 @default.
- W2795998052 cites W2061599165 @default.
- W2795998052 cites W2083970667 @default.
- W2795998052 cites W2096579040 @default.
- W2795998052 cites W2102328597 @default.
- W2795998052 cites W2107455488 @default.
- W2795998052 cites W2117552096 @default.
- W2795998052 cites W2126052502 @default.
- W2795998052 cites W2133059825 @default.
- W2795998052 cites W2139591342 @default.
- W2795998052 cites W2145023731 @default.
- W2795998052 cites W2169900910 @default.
- W2795998052 cites W2261304198 @default.
- W2795998052 cites W2283608459 @default.
- W2795998052 cites W2292575562 @default.
- W2795998052 cites W2530917347 @default.
- W2795998052 cites W2552338564 @default.
- W2795998052 cites W2598457882 @default.
- W2795998052 cites W2744548708 @default.
- W2795998052 cites W2765854388 @default.
- W2795998052 cites W2919115771 @default.
- W2795998052 cites W4255949318 @default.
- W2795998052 doi "https://doi.org/10.1177/1475921718764873" @default.
- W2795998052 hasPublicationYear "2018" @default.
- W2795998052 type Work @default.
- W2795998052 sameAs 2795998052 @default.
- W2795998052 citedByCount "163" @default.
- W2795998052 countsByYear W27959980522018 @default.
- W2795998052 countsByYear W27959980522019 @default.
- W2795998052 countsByYear W27959980522020 @default.
- W2795998052 countsByYear W27959980522021 @default.
- W2795998052 countsByYear W27959980522022 @default.
- W2795998052 countsByYear W27959980522023 @default.
- W2795998052 crossrefType "journal-article" @default.
- W2795998052 hasAuthorship W2795998052A5018318136 @default.
- W2795998052 hasAuthorship W2795998052A5045958583 @default.
- W2795998052 hasAuthorship W2795998052A5066602975 @default.
- W2795998052 hasAuthorship W2795998052A5070569173 @default.
- W2795998052 hasConcept C138602881 @default.
- W2795998052 hasConcept C153180895 @default.
- W2795998052 hasConcept C154945302 @default.
- W2795998052 hasConcept C160633673 @default.
- W2795998052 hasConcept C31972630 @default.
- W2795998052 hasConcept C41008148 @default.
- W2795998052 hasConcept C50644808 @default.
- W2795998052 hasConcept C81363708 @default.
- W2795998052 hasConceptScore W2795998052C138602881 @default.
- W2795998052 hasConceptScore W2795998052C153180895 @default.
- W2795998052 hasConceptScore W2795998052C154945302 @default.
- W2795998052 hasConceptScore W2795998052C160633673 @default.
- W2795998052 hasConceptScore W2795998052C31972630 @default.
- W2795998052 hasConceptScore W2795998052C41008148 @default.
- W2795998052 hasConceptScore W2795998052C50644808 @default.
- W2795998052 hasConceptScore W2795998052C81363708 @default.
- W2795998052 hasFunder F4320321001 @default.
- W2795998052 hasFunder F4320321540 @default.
- W2795998052 hasFunder F4320324778 @default.
- W2795998052 hasIssue "3" @default.
- W2795998052 hasLocation W27959980521 @default.
- W2795998052 hasOpenAccess W2795998052 @default.
- W2795998052 hasPrimaryLocation W27959980521 @default.
- W2795998052 hasRelatedWork W121273120 @default.
- W2795998052 hasRelatedWork W2002009170 @default.
- W2795998052 hasRelatedWork W2034462085 @default.
- W2795998052 hasRelatedWork W2090093270 @default.
- W2795998052 hasRelatedWork W2136485282 @default.
- W2795998052 hasRelatedWork W2141888456 @default.
- W2795998052 hasRelatedWork W2337415362 @default.
- W2795998052 hasRelatedWork W2740820121 @default.
- W2795998052 hasRelatedWork W3005455252 @default.
- W2795998052 hasRelatedWork W317572212 @default.
- W2795998052 hasVolume "18" @default.
- W2795998052 isParatext "false" @default.
- W2795998052 isRetracted "false" @default.
- W2795998052 magId "2795998052" @default.
- W2795998052 workType "article" @default.