Automatic system for visual detection of dirt buildup on conveyor belts using convolutional neural networks

Página do item simplificado
dc.creatorAndré Santos
dc.creatorFilipe Rocha
dc.creatorAgnaldo Reis
dc.creatorFrederico Gadelha Guimarães
dc.date.accessioned2023-07-25T17:31:33Z
dc.date.accessioned2025-09-08T23:47:26Z
dc.date.available2023-07-25T17:31:33Z
dc.date.issued2020-10-12
dc.description.sponsorshipCNPq - Conselho Nacional de Desenvolvimento Científico e Tecnológico
dc.description.sponsorshipFAPEMIG - Fundação de Amparo à Pesquisa do Estado de Minas Gerais
dc.description.sponsorshipCAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
dc.format.mimetypepdf
dc.identifier.doihttps://doi.org/10.3390/s20205762
dc.identifier.issn1424-8220
dc.identifier.urihttps://hdl.handle.net/1843/56958
dc.languageeng
dc.publisherUniversidade Federal de Minas Gerais
dc.relation.ispartofSensors
dc.rightsAcesso Aberto
dc.subjectEngenharia elétrica
dc.subjectAprendizado do computador
dc.subject.otherConvolutional neural network
dc.subject.otherConveyor belt
dc.subject.otherMachine learning
dc.titleAutomatic system for visual detection of dirt buildup on conveyor belts using convolutional neural networks
dc.typeArtigo de periódico
local.citation.epage16
local.citation.issue20
local.citation.spage5762
local.citation.volume20
local.description.resumoConveyor belts are the most widespread means of transportation for large quantities of materials in the mining sector. Therefore, autonomous methods that can help human beings to perform the inspection of the belt conveyor system is a major concern for companies. In this context, we present in this work a novel and automatic visual detector that recognizes dirt buildup on the structures of conveyor belts, which is one of the tasks of the maintenance inspectors. This visual detector can be embedded as sensors in autonomous robots for the inspection activity. The proposed system involves training a convolutional neural network from RGB images. The use of the transfer learning technique, i.e., retraining consolidated networks for image classification with our collected images has shown very effective. Two different approaches for transfer learning have been analyzed. The best one presented an average accuracy of 0.8975 with an F-1 Score of 0.8773 for the dirt recognition. A field validation experiment served to evaluate the performance of the proposed system in a real time classification task.
local.identifier.orcidhttps://orcid.org/0000-0003-2167-1973
local.identifier.orcidhttps://orcid.org/0000-0001-9238-8839
local.publisher.countryBrasil
local.publisher.departmentENG - DEPARTAMENTO DE ENGENHARIA ELÉTRICA
local.publisher.departmentENGENHARIA - ESCOLA DE ENGENHARIA
local.publisher.initialsUFMG
local.url.externahttps://www.mdpi.com/1424-8220/20/20/5762

Arquivos

Pacote original

Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
Automatic System for Visual Detection of Dirt Buildup on Conveyor Belts Using Convolutional Neural Networks.pdf
Tamanho:
5.16 MB
Formato:
Adobe Portable Document Format
Baixar

Licença do pacote

Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
License.txt
Tamanho:
1.99 KB
Formato:
Plain Text
Descrição:
Baixar

Coleções

Artigo de Periódico

Logo UFMG