Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225861569> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4225861569 abstract "Computer vision (CV) based inspection has recently attracted considerable attention and is progressively replacing traditional visual inspection which is subject to poor accuracy, high subjectivity and inefficiency. This paper, benefiting from hybrid structures of multichannel parallel convolutional neural networks (pCNNs), introduces a unique deep learning framework for road crack detection. Ideally, CNN-based frameworks require a relatively huge computing resources for accurate image analysis. However, the portability objective of this work necessitates the utilization of low power processing units. To that purpose, we propose robust deep representation learning for RoadCrackDetection (RoCDe) which uses a multichannel pCNNs. Bayesian optimization algorithm (BOA) was used to optimize the multichannel pCNNs training with the fewest possible neural network (NN) layers to achieve the maximum accuracy, improved efficiency and minimum processing time. The CV training was done using two distinct optimizers namely Adam and RELU on a sufficiently available datasets through image preprocessing and data augmentation. Experimental results show that, the proposed algorithm can achieve high accuracy around 95% in crack detection, which is good enough to replace human inspections normally conducted on-site. This is largely due to well-calibrated predictive uncertainty estimates (WPUE). Effectiveness of the proposed model is demonstrated and validated empirically via extensive experiments and rigorous evaluation on large scale real world datasets. Furthermore, the performance of hybrid CNNs is compared with state-of-the art NN models and the results provides remarkable difference in success level, proving the strength of multichannel pCNNs." @default.
- W4225861569 created "2022-05-05" @default.
- W4225861569 creator A5045892797 @default.
- W4225861569 creator A5057107096 @default.
- W4225861569 creator A5068345672 @default.
- W4225861569 date "2021-12-22" @default.
- W4225861569 modified "2023-10-17" @default.
- W4225861569 title "Robust Deep Representation Learning for Road Crack Detection" @default.
- W4225861569 cites W1969393996 @default.
- W4225861569 cites W1970370303 @default.
- W4225861569 cites W2008935780 @default.
- W4225861569 cites W2034272359 @default.
- W4225861569 cites W2090926585 @default.
- W4225861569 cites W2128880484 @default.
- W4225861569 cites W2144801789 @default.
- W4225861569 cites W2511065100 @default.
- W4225861569 cites W2598457882 @default.
- W4225861569 cites W2748643398 @default.
- W4225861569 cites W2751802138 @default.
- W4225861569 cites W2757455114 @default.
- W4225861569 cites W2884143694 @default.
- W4225861569 cites W2884657849 @default.
- W4225861569 cites W2889494142 @default.
- W4225861569 cites W2963037989 @default.
- W4225861569 cites W2981493332 @default.
- W4225861569 cites W2997546679 @default.
- W4225861569 cites W3000110218 @default.
- W4225861569 cites W3022492425 @default.
- W4225861569 cites W3043155291 @default.
- W4225861569 cites W3074321338 @default.
- W4225861569 cites W3139096236 @default.
- W4225861569 cites W3163634295 @default.
- W4225861569 cites W639708223 @default.
- W4225861569 doi "https://doi.org/10.1145/3511176.3511195" @default.
- W4225861569 hasPublicationYear "2021" @default.
- W4225861569 type Work @default.
- W4225861569 citedByCount "1" @default.
- W4225861569 countsByYear W42258615692022 @default.
- W4225861569 crossrefType "proceedings-article" @default.
- W4225861569 hasAuthorship W4225861569A5045892797 @default.
- W4225861569 hasAuthorship W4225861569A5057107096 @default.
- W4225861569 hasAuthorship W4225861569A5068345672 @default.
- W4225861569 hasConcept C108583219 @default.
- W4225861569 hasConcept C119857082 @default.
- W4225861569 hasConcept C153180895 @default.
- W4225861569 hasConcept C154945302 @default.
- W4225861569 hasConcept C162324750 @default.
- W4225861569 hasConcept C175444787 @default.
- W4225861569 hasConcept C199360897 @default.
- W4225861569 hasConcept C2778049539 @default.
- W4225861569 hasConcept C2778869765 @default.
- W4225861569 hasConcept C34736171 @default.
- W4225861569 hasConcept C41008148 @default.
- W4225861569 hasConcept C50644808 @default.
- W4225861569 hasConcept C63000827 @default.
- W4225861569 hasConcept C81363708 @default.
- W4225861569 hasConceptScore W4225861569C108583219 @default.
- W4225861569 hasConceptScore W4225861569C119857082 @default.
- W4225861569 hasConceptScore W4225861569C153180895 @default.
- W4225861569 hasConceptScore W4225861569C154945302 @default.
- W4225861569 hasConceptScore W4225861569C162324750 @default.
- W4225861569 hasConceptScore W4225861569C175444787 @default.
- W4225861569 hasConceptScore W4225861569C199360897 @default.
- W4225861569 hasConceptScore W4225861569C2778049539 @default.
- W4225861569 hasConceptScore W4225861569C2778869765 @default.
- W4225861569 hasConceptScore W4225861569C34736171 @default.
- W4225861569 hasConceptScore W4225861569C41008148 @default.
- W4225861569 hasConceptScore W4225861569C50644808 @default.
- W4225861569 hasConceptScore W4225861569C63000827 @default.
- W4225861569 hasConceptScore W4225861569C81363708 @default.
- W4225861569 hasLocation W42258615691 @default.
- W4225861569 hasOpenAccess W4225861569 @default.
- W4225861569 hasPrimaryLocation W42258615691 @default.
- W4225861569 hasRelatedWork W2337926734 @default.
- W4225861569 hasRelatedWork W2732542196 @default.
- W4225861569 hasRelatedWork W2738221750 @default.
- W4225861569 hasRelatedWork W2977314777 @default.
- W4225861569 hasRelatedWork W3003536130 @default.
- W4225861569 hasRelatedWork W4225304418 @default.
- W4225861569 hasRelatedWork W4311257506 @default.
- W4225861569 hasRelatedWork W4319994054 @default.
- W4225861569 hasRelatedWork W4327499916 @default.
- W4225861569 hasRelatedWork W564581980 @default.
- W4225861569 isParatext "false" @default.
- W4225861569 isRetracted "false" @default.
- W4225861569 workType "article" @default.