Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896969435> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W2896969435 abstract "Performance Comparison of Pretrained Convolutional Neural Networks on Crack Detection in Buildings Ç.F. Özgenel and Arzu Gönenç Sorguç Pages 693-700 (2018 Proceedings of the 35th ISARC, Berlin, Germany, ISBN 978-3-00-060855-1, ISSN 2413-5844) Abstract: Crack detection has vital importance for structural health monitoring and inspection of buildings. The task is challenging for computer vision methods as cracks have only low-level features for detection which are easily confused with background texture, foreign objects and/ or irregularities in construction. In addition, difficulties such as inhomogeneous illumination and irregularities in construction present an obstacle for fully autonomous crack detection in the course of building inspection and monitoring. Convolutional neural networks (CNNs) are promising frameworks for crack detection with high accuracy and precision. Furthermore, being able to adapt pretrained networks to custom tasks by means of transfer learning enables users to utilize CNNs without the requirement of deep understanding and knowledge of algorithms. Yet, acknowledging the limitations and points to consider in the course of employing CNNs have great importance especially in fields which the results have vital importance such as crack detection in buildings. Within the scope of this study, a multidimensional performance analysis of highly acknowledged pretrained networks with respect to the size of training dataset, depth of networks, number of epochs for training and expandability to other material types utilized in buildings is conducted. By this means, it is aimed to develop an insight for new researchers and highlight the points to consider while applying CNNs for crack detection task. Keywords: Crack Detection in Buildings, Convolutional Neural Networks, Transfer Learning DOI: https://doi.org/10.22260/ISARC2018/0094 Download fulltext Download BibTex Download Endnote (RIS) TeX Import to Mendeley" @default.
- W2896969435 created "2018-10-26" @default.
- W2896969435 creator A5023337085 @default.
- W2896969435 creator A5059718777 @default.
- W2896969435 date "2018-07-22" @default.
- W2896969435 modified "2023-10-16" @default.
- W2896969435 title "Performance Comparison of Pretrained Convolutional Neural Networks on Crack Detection in Buildings" @default.
- W2896969435 doi "https://doi.org/10.22260/isarc2018/0094" @default.
- W2896969435 hasPublicationYear "2018" @default.
- W2896969435 type Work @default.
- W2896969435 sameAs 2896969435 @default.
- W2896969435 citedByCount "91" @default.
- W2896969435 countsByYear W28969694352019 @default.
- W2896969435 countsByYear W28969694352020 @default.
- W2896969435 countsByYear W28969694352021 @default.
- W2896969435 countsByYear W28969694352022 @default.
- W2896969435 countsByYear W28969694352023 @default.
- W2896969435 crossrefType "proceedings-article" @default.
- W2896969435 hasAuthorship W2896969435A5023337085 @default.
- W2896969435 hasAuthorship W2896969435A5059718777 @default.
- W2896969435 hasConcept C108583219 @default.
- W2896969435 hasConcept C119857082 @default.
- W2896969435 hasConcept C127413603 @default.
- W2896969435 hasConcept C150899416 @default.
- W2896969435 hasConcept C153180895 @default.
- W2896969435 hasConcept C154945302 @default.
- W2896969435 hasConcept C17744445 @default.
- W2896969435 hasConcept C199360897 @default.
- W2896969435 hasConcept C199539241 @default.
- W2896969435 hasConcept C201995342 @default.
- W2896969435 hasConcept C2776151529 @default.
- W2896969435 hasConcept C2776650193 @default.
- W2896969435 hasConcept C2778012447 @default.
- W2896969435 hasConcept C2780451532 @default.
- W2896969435 hasConcept C31972630 @default.
- W2896969435 hasConcept C41008148 @default.
- W2896969435 hasConcept C50644808 @default.
- W2896969435 hasConcept C81363708 @default.
- W2896969435 hasConceptScore W2896969435C108583219 @default.
- W2896969435 hasConceptScore W2896969435C119857082 @default.
- W2896969435 hasConceptScore W2896969435C127413603 @default.
- W2896969435 hasConceptScore W2896969435C150899416 @default.
- W2896969435 hasConceptScore W2896969435C153180895 @default.
- W2896969435 hasConceptScore W2896969435C154945302 @default.
- W2896969435 hasConceptScore W2896969435C17744445 @default.
- W2896969435 hasConceptScore W2896969435C199360897 @default.
- W2896969435 hasConceptScore W2896969435C199539241 @default.
- W2896969435 hasConceptScore W2896969435C201995342 @default.
- W2896969435 hasConceptScore W2896969435C2776151529 @default.
- W2896969435 hasConceptScore W2896969435C2776650193 @default.
- W2896969435 hasConceptScore W2896969435C2778012447 @default.
- W2896969435 hasConceptScore W2896969435C2780451532 @default.
- W2896969435 hasConceptScore W2896969435C31972630 @default.
- W2896969435 hasConceptScore W2896969435C41008148 @default.
- W2896969435 hasConceptScore W2896969435C50644808 @default.
- W2896969435 hasConceptScore W2896969435C81363708 @default.
- W2896969435 hasLocation W28969694351 @default.
- W2896969435 hasOpenAccess W2896969435 @default.
- W2896969435 hasPrimaryLocation W28969694351 @default.
- W2896969435 hasRelatedWork W2951211570 @default.
- W2896969435 hasRelatedWork W3133861977 @default.
- W2896969435 hasRelatedWork W3167935049 @default.
- W2896969435 hasRelatedWork W3183901164 @default.
- W2896969435 hasRelatedWork W3192840557 @default.
- W2896969435 hasRelatedWork W3193565141 @default.
- W2896969435 hasRelatedWork W4206357785 @default.
- W2896969435 hasRelatedWork W4226493464 @default.
- W2896969435 hasRelatedWork W4281381188 @default.
- W2896969435 hasRelatedWork W4312417841 @default.
- W2896969435 isParatext "false" @default.
- W2896969435 isRetracted "false" @default.
- W2896969435 magId "2896969435" @default.
- W2896969435 workType "article" @default.