Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/79235
Registo completo
Campo DC | Valor | Idioma |
---|---|---|
dc.contributor.author | Gomes, Luís Filipe | por |
dc.contributor.author | Analide, Cesar | por |
dc.contributor.author | Freitas, E. F. | por |
dc.date.accessioned | 2022-08-05T10:08:03Z | - |
dc.date.available | 2022-08-05T10:08:03Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | Gomes, L.F., Analide, C., Freitas, E. (2022). Distress Detection in Road Pavements Using Neural Networks. In: , et al. Distributed Computing and Artificial Intelligence, Volume 2: Special Sessions 18th International Conference. DCAI 2021. Lecture Notes in Networks and Systems, vol 332. Springer, Cham. https://doi.org/10.1007/978-3-030-86887-1_14 | por |
dc.identifier.isbn | 9783030868864 | por |
dc.identifier.issn | 2367-3370 | - |
dc.identifier.uri | https://hdl.handle.net/1822/79235 | - |
dc.description.abstract | Combining Computer Vision (CV) and Anomaly Detection (AD), there is a convergence of methodologies using convolutional layers in AD architectures, which we consider an innovation in the field. The main goal of this work is to present different Artificial Neural Networks (ANN) architectures, applying them to distress detection in road pavements and comparing the results obtained in each approach. The experimented methods for AD in images include a binary classifier as a baseline, an Autoencoder (AE) and a Variational Autoencoder (VAE). Supervised and unsupervised practises are also compared, proving their utility in scenarios where there is no labelled data available. Using the VAE model in a supervised setting, it presents an excellent distinction between good and bad pavement. When labelled data is not available, using the AE model and the distribution of similarities of good pavement reconstructions to calculate the threshold is the best option with accuracy and precision above 94%. The development of these models shows that it is possible to develop an alternative solution to reduce operating costs compared to expensive commercial systems and to improve the usability compared to conventional methods of classifying road surfaces. | por |
dc.description.sponsorship | This work has been supported by FCT – Fundação para a Ciência e Tecnologia within the R&D Units Project Scope: UIDB/00319/2020. | por |
dc.language.iso | eng | por |
dc.publisher | Springer | por |
dc.relation | info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F00319%2F2020/PT | por |
dc.rights | openAccess | por |
dc.subject | Anomaly detection | por |
dc.subject | Artificial neural networks | por |
dc.subject | Autoencoders | por |
dc.subject | Automatic pavement monitoring | por |
dc.subject | Computer vision | por |
dc.title | Distress detection in road pavements using neural networks | por |
dc.type | conferencePaper | por |
dc.peerreviewed | yes | por |
dc.relation.publisherversion | https://link.springer.com/chapter/10.1007/978-3-030-86887-1_14 | por |
oaire.citationStartPage | 151 | por |
oaire.citationEndPage | 160 | por |
oaire.citationVolume | 332 | por |
dc.date.updated | 2022-08-05T09:17:49Z | - |
dc.identifier.doi | 10.1007/978-3-030-86887-1_14 | por |
sdum.export.identifier | 12312 | - |
sdum.journal | Lecture Notes in Networks and Systems | por |
Aparece nas coleções: | ISISE - Capítulos/Artigos em Livros Internacionais |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
distress-detection.pdf | 3,13 MB | Adobe PDF | Ver/Abrir |