Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385569832> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4385569832 endingPage "22762" @default.
- W4385569832 startingPage "22754" @default.
- W4385569832 abstract "In recent years, civil infrastructure from roads to tunnels has boomed and many deep learning based methods have been proposed to monitor their structural safety. However, most of these methods are dedicated to develop deeper convolutional neural networks to achieve better performance. This results in the models being unable to be deployed to sensors, cameras, and other devices used for monitoring. Meanwhile, some environments, such as deep buried tunnels, are usually dim and complex. To reduce computational costs while ensuring the method can be effectively deployed on those monitoring devices in complex environments, we propose a lightweight model based on the Ghost module to identify cracks. Specifically, we introduce a lightweight multi-branch network building module through the Ghost module. Then, we build a lightweight network structure for crack identification based on the network building unit. We also use structural re-parameterization to improve model performance and reduce inference time. We conducted experiments on concrete crack datasets and on datasets with complex scenario processing done. The results show that our model’s accuracy is the best compared to other baseline methods. It also uses nearly 3 times fewer floating-point operations and nearly 16 times fewer parameters compared to GhostNet." @default.
- W4385569832 created "2023-08-05" @default.
- W4385569832 creator A5015843783 @default.
- W4385569832 creator A5018077554 @default.
- W4385569832 creator A5029607765 @default.
- W4385569832 creator A5062853168 @default.
- W4385569832 creator A5075021616 @default.
- W4385569832 date "2023-10-01" @default.
- W4385569832 modified "2023-10-06" @default.
- W4385569832 title "A lightweight crack detection model based on multi-branch Ghost module in Complex Scenes" @default.
- W4385569832 cites W1925745898 @default.
- W4385569832 cites W1995130521 @default.
- W4385569832 cites W2531409750 @default.
- W4385569832 cites W2752782242 @default.
- W4385569832 cites W2883780447 @default.
- W4385569832 cites W2885146443 @default.
- W4385569832 cites W2963125010 @default.
- W4385569832 cites W2963163009 @default.
- W4385569832 cites W2970332685 @default.
- W4385569832 cites W2982083293 @default.
- W4385569832 cites W3034468979 @default.
- W4385569832 cites W3034552520 @default.
- W4385569832 cites W3035414587 @default.
- W4385569832 cites W3167386507 @default.
- W4385569832 cites W3197712350 @default.
- W4385569832 cites W4226293680 @default.
- W4385569832 cites W4285248944 @default.
- W4385569832 cites W4309047390 @default.
- W4385569832 cites W4309102516 @default.
- W4385569832 doi "https://doi.org/10.1109/jsen.2023.3300715" @default.
- W4385569832 hasPublicationYear "2023" @default.
- W4385569832 type Work @default.
- W4385569832 citedByCount "0" @default.
- W4385569832 crossrefType "journal-article" @default.
- W4385569832 hasAuthorship W4385569832A5015843783 @default.
- W4385569832 hasAuthorship W4385569832A5018077554 @default.
- W4385569832 hasAuthorship W4385569832A5029607765 @default.
- W4385569832 hasAuthorship W4385569832A5062853168 @default.
- W4385569832 hasAuthorship W4385569832A5075021616 @default.
- W4385569832 hasConcept C108583219 @default.
- W4385569832 hasConcept C116834253 @default.
- W4385569832 hasConcept C154945302 @default.
- W4385569832 hasConcept C2524010 @default.
- W4385569832 hasConcept C2776214188 @default.
- W4385569832 hasConcept C28719098 @default.
- W4385569832 hasConcept C33923547 @default.
- W4385569832 hasConcept C41008148 @default.
- W4385569832 hasConcept C59822182 @default.
- W4385569832 hasConcept C79403827 @default.
- W4385569832 hasConcept C81363708 @default.
- W4385569832 hasConcept C86803240 @default.
- W4385569832 hasConceptScore W4385569832C108583219 @default.
- W4385569832 hasConceptScore W4385569832C116834253 @default.
- W4385569832 hasConceptScore W4385569832C154945302 @default.
- W4385569832 hasConceptScore W4385569832C2524010 @default.
- W4385569832 hasConceptScore W4385569832C2776214188 @default.
- W4385569832 hasConceptScore W4385569832C28719098 @default.
- W4385569832 hasConceptScore W4385569832C33923547 @default.
- W4385569832 hasConceptScore W4385569832C41008148 @default.
- W4385569832 hasConceptScore W4385569832C59822182 @default.
- W4385569832 hasConceptScore W4385569832C79403827 @default.
- W4385569832 hasConceptScore W4385569832C81363708 @default.
- W4385569832 hasConceptScore W4385569832C86803240 @default.
- W4385569832 hasIssue "19" @default.
- W4385569832 hasLocation W43855698321 @default.
- W4385569832 hasOpenAccess W4385569832 @default.
- W4385569832 hasPrimaryLocation W43855698321 @default.
- W4385569832 hasRelatedWork W2055243143 @default.
- W4385569832 hasRelatedWork W2611989081 @default.
- W4385569832 hasRelatedWork W3029198973 @default.
- W4385569832 hasRelatedWork W3133861977 @default.
- W4385569832 hasRelatedWork W3167935049 @default.
- W4385569832 hasRelatedWork W3193565141 @default.
- W4385569832 hasRelatedWork W4226493464 @default.
- W4385569832 hasRelatedWork W4293226380 @default.
- W4385569832 hasRelatedWork W4312417841 @default.
- W4385569832 hasRelatedWork W4375867731 @default.
- W4385569832 hasVolume "23" @default.
- W4385569832 isParatext "false" @default.
- W4385569832 isRetracted "false" @default.
- W4385569832 workType "article" @default.