Evolutionary joint selection to improve human action recognition with RGB-D devices
Empreu sempre aquest identificador per citar o enllaçar aquest ítem
http://hdl.handle.net/10045/33751
Registre complet
Camp Dublin Core | Valor | Idioma |
---|---|---|
dc.contributor | Informática Industrial y Redes de Computadores | es |
dc.contributor | Domótica y Ambientes Inteligentes | es |
dc.contributor.author | Chaaraoui, Alexandros Andre | - |
dc.contributor.author | Padilla López, José Ramón | - |
dc.contributor.author | Climent-Pérez, Pau | - |
dc.contributor.author | Flórez-Revuelta, Francisco | - |
dc.contributor.other | Universidad de Alicante. Departamento de Tecnología Informática y Computación | es |
dc.date.accessioned | 2013-11-08T13:43:01Z | - |
dc.date.available | 2013-11-08T13:43:01Z | - |
dc.date.issued | 2014-02-15 | - |
dc.identifier.citation | Expert Systems with Applications. 2014, 41(3): 786-794. doi:10.1016/j.eswa.2013.08.009 | es |
dc.identifier.issn | 0957-4174 (Print) | - |
dc.identifier.issn | 1873-6793 (Online) | - |
dc.identifier.uri | http://hdl.handle.net/10045/33751 | - |
dc.description.abstract | Interest in RGB-D devices is increasing due to their low price and the wide range of possible applications that come along. These devices provide a marker-less body pose estimation by means of skeletal data consisting of 3D positions of body joints. These can be further used for pose, gesture or action recognition. In this work, an evolutionary algorithm is used to determine the optimal subset of skeleton joints, taking into account the topological structure of the skeleton, in order to improve the final success rate. The proposed method has been validated using a state-of-the-art RGB action recognition approach, and applying it to the MSR-Action3D dataset. Results show that the proposed algorithm is able to significantly improve the initial recognition rate and to yield similar or better success rates than the state-of-the-art methods. | es |
dc.description.sponsorship | This work has been partially supported by the European Commission under project “caring4U – A study on people activity in private spaces: towards a multisensor network that meets privacy requirements” (PIEF-GA-2010-274649) and by the Spanish Ministry of Science and Innovation under project “Sistema de visión para la monitorización de la actividad de la vida diaria en el hogar” (TIN2010-20510-C04-02). Alexandros Andre Chaaraoui and José Ramón Padilla-López acknowledge financial support by the Conselleria d’Educació, Formació i Ocupació of the Generalitat Valenciana (fellowships ACIF/2011/160 and ACIF/2012/064 respectively). | es |
dc.language | eng | es |
dc.publisher | Elsevier | es |
dc.subject | RGB-D devices | es |
dc.subject | Human action recognition | es |
dc.subject | Evolutionary computation | es |
dc.subject | Instance selection | es |
dc.subject | Feature subset selection | es |
dc.subject.other | Arquitectura y Tecnología de Computadores | es |
dc.title | Evolutionary joint selection to improve human action recognition with RGB-D devices | es |
dc.type | info:eu-repo/semantics/article | es |
dc.peerreviewed | si | es |
dc.identifier.doi | 10.1016/j.eswa.2013.08.009 | - |
dc.relation.publisherversion | http://dx.doi.org/10.1016/j.eswa.2013.08.009 | es |
dc.rights.accessRights | info:eu-repo/semantics/restrictedAccess | es |
dc.relation.projectID | info:eu-repo/grantAgreement/MICINN//TIN2010-20510-C04-02 | - |
Apareix a la col·lecció: | INV - DAI - Artículos de Revistas INV - AmI4AHA - Artículos de Revistas |
Arxius per aquest ítem:
Arxiu | Descripció | Tamany | Format | |
---|---|---|---|---|
2013_Chaaraoui_etal_ESA-pre.pdf | Preprint (acceso abierto) | 6,29 MB | Adobe PDF | Obrir Vista prèvia |
2013_Chaaraoui_etal_ESA.pdf | Versión final (acceso restringido) | 1,71 MB | Adobe PDF | Obrir Sol·licitar una còpia |
Tots els documents dipositats a RUA estan protegits per drets d'autors. Alguns drets reservats.