Logo do repositório
 
Publicação

Low-Cost CNN for Automatic Violence Recognition on Embedded System

2022Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorVieira, J. C.
dc.contributor.authorSartori, Andreza
dc.contributor.authorStefenon, Stéfano Frizzo
dc.contributor.authorPerez, Fabio Luis
dc.contributor.authorSchneider De Jesus, Gabriel
dc.contributor.authorLEITHARDT, VALDERI
dc.date.accessioned2023-02-01T18:43:24ZPT
dc.date.available2023-02-01T18:43:24ZPT
dc.date.issued2022PT
dc.date.updated2022-03-12T11:13:49Z
dc.description.abstractDue to the increasing number of violence cases, there is a high demand for efficient monitoring systems, however, these systems can be susceptible to failure. Therefore, this work proposes the analysis and application of low-cost Convolutional Neural Networks (CNNs) techniques to automatically recognize and classify suspicious events. Thus, it is possible to alert and assist the monitoring process with a reduced deployment cost. For this purpose, a dataset with violence and non-violence actions in scenes of crowded and non-crowded environments was assembled. The mobile CNNs architectures were adapted and obtained a classification accuracy of up to 92.05%, with a low number of parameters. To demonstrate the models validity, a prototype was developed by using an embedded Raspberry Pi platform, able to execute a model in real-time with 4 frames-per-second of speed. In addition, a warning system was developed to recognize pre-fight behavior and anticipate violent acts, alerting security to potential situations.pt_PT
dc.description.versionN/Apt_PT
dc.identifier.doi10.1109/ACCESS.2022.3155123pt_PT
dc.identifier.slugcv-prod-2950384
dc.identifier.urihttp://hdl.handle.net/10400.26/43566PT
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.relationResearch Center for Endogenous Resource Valorization
dc.relationCOPELABS - Cognitive and People-centric Computing R&D Unit
dc.subjectNeural networks,pt_PT
dc.subjectartificial neural networks,pt_PT
dc.subjectimage processing,pt_PT
dc.subjectimage classificationpt_PT
dc.titleLow-Cost CNN for Automatic Violence Recognition on Embedded Systempt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleResearch Center for Endogenous Resource Valorization
oaire.awardTitleCOPELABS - Cognitive and People-centric Computing R&D Unit
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F05064%2F2020/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F04111%2F2020/PT
oaire.citation.endPage1pt_PT
oaire.citation.startPage1pt_PT
oaire.citation.titleIEEE Accesspt_PT
oaire.fundingStream6817 - DCRRNI ID
oaire.fundingStream6817 - DCRRNI ID
person.familyNameVieira
person.familyNameSartori
person.familyNameStefenon
person.familyNamePerez
person.familyNameSchneider de Jesus
person.familyNameREIS QUIETINHO LEITHARDT
person.givenNameJoelton Cezar
person.givenNameAndreza
person.givenNameStefano Frizzo
person.givenNameFabio Luis
person.givenNameGabriel
person.givenNameVALDERI
person.identifier916543
person.identifierJsOq45sAAAAJ&hl=pt-PT
person.identifier.ciencia-id4019-BB36-7F74
person.identifier.ciencia-id0614-5834-E7F3
person.identifier.orcid0000-0002-4677-7160
person.identifier.orcid0000-0002-3982-8767
person.identifier.orcid0000-0002-3723-616X
person.identifier.orcid0000-0001-5223-1562
person.identifier.orcid0000-0001-9357-1248
person.identifier.orcid0000-0003-0446-9271
person.identifier.ridAAD-7639-2019
person.identifier.scopus-author-id57194147390
person.identifier.scopus-author-id55813849500
person.identifier.scopus-author-id35303109600
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.cv.cienciaid0614-5834-E7F3 | Valderi Reis Quietinho Leithardt
rcaap.rightsopenAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublication4124607a-344c-4834-a138-a4a1a4b7efac
relation.isAuthorOfPublication9c24ac3c-b7ec-48e9-abb0-8f9485e3b4f1
relation.isAuthorOfPublicationae8b0861-1e25-47fb-bcdb-a44c98768634
relation.isAuthorOfPublication7389294a-3bc2-4d00-976e-d0122ddfb1b6
relation.isAuthorOfPublicationf7e006ba-9c58-4cbf-a8aa-68f2dacd783a
relation.isAuthorOfPublicationab15f7c6-e882-406e-813d-2629e9cec5c8
relation.isAuthorOfPublication.latestForDiscovery7389294a-3bc2-4d00-976e-d0122ddfb1b6
relation.isProjectOfPublication05110dfa-e1d5-4a80-ad88-5c36b9c4552f
relation.isProjectOfPublication7a9b4ee8-2a94-4a7b-bd54-c01b8971564a
relation.isProjectOfPublication.latestForDiscovery7a9b4ee8-2a94-4a7b-bd54-c01b8971564a

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
Low-Cost_CNN_for_Automatic_Violence_Recognition_on_Embedded_System.pdf
Tamanho:
2.13 MB
Formato:
Adobe Portable Document Format
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
license.txt
Tamanho:
1.89 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir

Coleções

VALORIZA - Artigos em Revistas Científicas