A probabilistic, discriminative and distributed system for the recognition of human actions from multiple views

e-Archivo Repository

Show simple item record

dc.contributor.author Cilla, Rodrigo
dc.contributor.author Patricio Guisado, Miguel Ángel
dc.contributor.author Berlanga, Antonio
dc.contributor.author Molina, José M.
dc.date.accessioned 2014-06-02T10:52:37Z
dc.date.available 2014-06-02T10:52:37Z
dc.date.issued 2012-01
dc.identifier.bibliographicCitation Neurocomputing, (2012), 75 (1), 78-87
dc.identifier.issn 0925-2312
dc.identifier.uri http://hdl.handle.net/10016/18928
dc.description.abstract This paper presents a distributed system for the recognition of human actions using views of the scene grabbed by different cameras. 2D frame descriptors are extracted for each available view to capture the variability in human motion. These descriptors are projected into a lower dimensional space and fed into a probabilistic classifier to output a posterior distribution of the action performed according to the descriptor computed at each camera. Classifier fusion algorithms are then used to merge the posterior distributions into a single distribution. The generated single posterior distribution is fed into a sequence classifier to make the final decision on the performed activity. The system can instantiate different algorithms for the different tasks, as the interfaces between modules are clearly defined. Results on the classification of the actions in the IXMAS dataset are reported. The accuracy of the proposed system is similar to state-of-the-art 3D methods, even though it uses only well-known 2D pattern recognition techniques and does not need to project the data into a 3D space or require camera calibration parameters.
dc.description.sponsorship This work was supported in part by Projects CICYT TIN 2008-06742-C02-02/TSI, CICYT TEC2008-06732-C02-02/TEC, CAM CONTEXTS (S2009/TIC1485) and DPS2008-07029-C02-02.
dc.format.extent 9 p.
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher Elsevier
dc.rights © 2011 Elsevier B.V.
dc.subject.other Human Action Recognition
dc.subject.other Bayesian networks
dc.subject.other Computer Vision
dc.subject.other Machine learning
dc.title A probabilistic, discriminative and distributed system for the recognition of human actions from multiple views
dc.type article
dc.description.status publicado
dc.relation.publisherversion http://dx.doi.org/10.1016/j.neucom.2011.03.051
dc.subject.eciencia Informática
dc.identifier.doi 10.1016/j.neucom.2011.03.051
dc.rights.accessRights openAccess
dc.relation.projectID Comunidad de Madrid. S2009/TIC-1485/CONTEXTS
dc.type.version acceptedVersion
dc.identifier.publicationfirstpage 78
dc.identifier.publicationissue 1
dc.identifier.publicationlastpage 87
dc.identifier.publicationtitle Neurocomputing
dc.identifier.publicationvolume 75
dc.identifier.uxxi AR/0000009580
 Find Full text

Files in this item

*Click on file's image for preview. (Embargoed files's preview is not supported)

This item appears in the following Collection(s)

Show simple item record