Real-time Action Recognition Using A Multilayer Descriptor With Variable Size

dc.creatorAlcantara
dc.creatorMF; Moreira
dc.creatorTP; Pedrini
dc.creatorH
dc.date2016
dc.date2016-12-06T18:30:56Z
dc.date2016-12-06T18:30:56Z
dc.date.accessioned2018-03-29T02:03:33Z
dc.date.available2018-03-29T02:03:33Z
dc.identifier1560-229X
dc.identifierJournal Of Electronic Imaging. IS&T & SPIE, n. 25, n. 1, p. .
dc.identifier1017-9909
dc.identifierWOS:000375930700021
dc.identifier10.1117/1.JEI.25.1.013020
dc.identifierhttp://electronicimaging.spiedigitallibrary.org/article.aspx?articleid=2491180
dc.identifierhttp://repositorio.unicamp.br/jspui/handle/REPOSIP/320172
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1310938
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.descriptionVideo analysis technology has become less expensive and more powerful in terms of storage resources and resolution capacity, promoting progress in a wide range of applications. Video-based human action detection has been used for several tasks in surveillance environments, such as forensic investigation, patient monitoring, medical training, accident prevention, and traffic monitoring, among others. We present a method for action identification based on adaptive training of a multilayer descriptor applied to a single classifier. Cumulative motion shapes (CMSs) are extracted according to the number of frames present in the video. Each CMS is employed as a self-sufficient layer in the training stage but belongs to the same descriptor. A robust classification is achieved through individual responses of classifiers for each layer, and the dominant result is used as a final outcome. Experiments are conducted on five public datasets (Weizmann, KTH, MuHAVi, IXMAS, and URADL) to demonstrate the effectiveness of the method in terms of accuracy in real time. (C) 2016 SPIE and IS&T
dc.description25
dc.description
dc.description
dc.description
dc.descriptionFAPESP
dc.descriptionCNPq
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.description
dc.description
dc.description
dc.languageEnglish
dc.publisherIS&T & SPIE
dc.publisherBELLINGHAM
dc.relationJournal of Electronic Imaging
dc.rightsfechado
dc.sourceWOS
dc.subjectAdaptive Learning
dc.subjectAction Detection
dc.subjectMotion Silhouettes
dc.subjectSurveillance Systems
dc.subjectReal-time Video Analysis
dc.titleReal-time Action Recognition Using A Multilayer Descriptor With Variable Size
dc.typeArtículos de revistas


Este ítem pertenece a la siguiente institución