Repository logo
 
Publication

Computer vision intelligent approaches to extract human pose and Its activity from image sequences

2020Journal article Open access
Simple item page
dc.contributor.authorGonçalves, Paulo
dc.contributor.authorLourenço, Bernardo
dc.contributor.authorSantos, Samuel
dc.contributor.authorBarlogis, Rodolphe
dc.contributor.authorMisson, Alexandre
dc.date.accessioned2020-12-21T12:31:10Z
dc.date.available2020-12-21T12:31:10Z
dc.date.issued2020
dc.description.abstractThe purpose of this work is to develop computational intelligence models based on neural networks (NN), fuzzy models (FM), support vector machines (SVM) and long short-term memory networks (LSTM) to predict human pose and activity from image sequences, based on computer vision approaches to gather the required features. To obtain the human pose semantics (output classes), based on a set of 3D points that describe the human body model (the input variables of the predictive model), prediction models were obtained from the acquired data, for example, video images. In the same way, to predict the semantics of the atomic activities that compose an activity, based again in the human body model extracted at each video frame, prediction models were learned using LSTM networks. In both cases the best learned models were implemented in an application to test the systems. The SVM model obtained 95.97% of correct classification of the six different human poses tackled in this work, during tests in different situations from the training phase. The implemented LSTM learned model achieved an overall accuracy of 88%, during tests in different situations from the training phase. These results demonstrate the validity of both approaches to predict human pose and activity from image sequences. Moreover, the system is capable of obtaining the atomic activities and quantifying the time interval in which each activity takes place.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationGONÇALVES, P.J.S [et al.] (2020] - Computer vision intelligent approaches to extract human pose and Its activity from image sequences. Electronics. ISSN 2079-9292. 9(1), 159. DOI: 10.3390/electronics9010159pt_PT
dc.identifier.doi10.3390/electronics9010159pt_PT
dc.identifier.issn2079-9292
dc.identifier.urihttp://hdl.handle.net/10400.11/7372
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherMDPIpt_PT
dc.relationPrograma Interreg V-A Spain-Portugalpt_PT
dc.relation0043- EUROAGE-4-Ept_PT
dc.relationSAICT-POL/23811/2016 (GMovE+)pt_PT
dc.relationAssociate Laboratory of Energy, Transports and Aeronautics
dc.relation.publisherversionhttps://www.mdpi.com/2079-9292/9/1/159pt_PT
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/pt_PT
dc.subjectComputer visionpt_PT
dc.subjectSupport vector machinespt_PT
dc.subjectFuzzy modellingpt_PT
dc.subjectNeural networkpt_PT
dc.subjectDeep learningpt_PT
dc.subjectHuman activity estimationpt_PT
dc.subjectComputer visionpt_PT
dc.subjectHuman pose estimationpt_PT
dc.titleComputer vision intelligent approaches to extract human pose and Its activity from image sequencespt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleAssociate Laboratory of Energy, Transports and Aeronautics
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UID%2FEMS%2F50022%2F2019/PT
oaire.citation.issue1pt_PT
oaire.citation.startPage159pt_PT
oaire.citation.titleElectronicspt_PT
oaire.citation.volume9pt_PT
oaire.fundingStream6817 - DCRRNI ID
person.familyNameGonçalves
person.givenNamePaulo
person.identifier.ciencia-id2816-A2FA-C5A3
person.identifier.orcid0000-0002-8692-7338
person.identifier.ridE-5640-2012
person.identifier.scopus-author-id35853838000
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublication86a6a234-d690-4c2b-8bee-d58005eebba2
relation.isAuthorOfPublication.latestForDiscovery86a6a234-d690-4c2b-8bee-d58005eebba2
relation.isProjectOfPublicationfac75ef9-84a8-4440-9c6d-2cf8cdc6ff78
relation.isProjectOfPublication.latestForDiscoveryfac75ef9-84a8-4440-9c6d-2cf8cdc6ff78

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Computer Vision Intelligent Approaches to Extract Human Pose and Its Activity from Image Sequences_A.pdf
Size:
3.12 MB
Format:
Adobe Portable Document Format
Download

Collections

ESTCB - Artigos em revistas com arbitragem científica