Human action recognition optimization based on evolutionary feature subset selection

Please use this identifier to cite or link to this item:
Información del item - Informació de l'item - Item information
Title: Human action recognition optimization based on evolutionary feature subset selection
Authors: Chaaraoui, Alexandros Andre | Flórez-Revuelta, Francisco
Research Group/s: Informática Industrial y Redes de Computadores | Domótica y Ambientes Inteligentes
Center, Department or Service: Universidad de Alicante. Departamento de Tecnología Informática y Computación
Keywords: Feature subset selection | Genetic algorithm | Human action recognition | Multi-view recognition | Bag-of-key-poses
Knowledge Area: Arquitectura y Tecnología de Computadores
Issue Date: Jul-2013
Publisher: ACM
Citation: Chaaraoui, Alexandros Andre; Flórez-Revuelta, Francisco. “Human action recognition optimization based on evolutionary feature subset selection”. En: GECCO '13 Proceeding of the Fifteenth Annual Conference on Genetic and Evolutionary Computation Conference. New York : ACM, 2013. ISBN 978-1-4503-1963-8, pp. 1229-1236
Abstract: Human action recognition constitutes a core component of advanced human behavior analysis. The detection and recognition of basic human motion enables to analyze and understand human activities, and to react proactively providing different kinds of services from human-computer interaction to health care assistance. In this paper, a feature-level optimization for human action recognition is proposed. The resulting recognition rate and computational cost are significantly improved by means of a low-dimensional radial summary feature and evolutionary feature subset selection. The introduced feature is computed using only the contour points of human silhouettes. These are spatially aligned based on a radial scheme. This definition shows to be proficient for feature subset selection, since different parts of the human body can be selected by choosing the appropriate feature elements. The best selection is sought using a genetic algorithm. Experimentation has been performed on the publicly available MuHAVi dataset. Promising results are shown, since state-of-the-art recognition rates are considerably outperformed with a highly reduced computational cost.
Sponsor: 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 acknowledges financial support by the Conselleria d'Educació, Formació i Ocupació of the Generalitat Valenciana (fellowship ACIF/20-11/160).
ISBN: 978-1-4503-1963-8
DOI: 10.1145/2463372.2463529
Language: eng
Type: info:eu-repo/semantics/conferenceObject
Rights: © 2013 ACM, Inc.
Peer Review: si
Publisher version:
Appears in Collections:INV - DAI - Comunicaciones a Congresos, Conferencias, etc.

Files in This Item:
Files in This Item:
File Description SizeFormat 
Thumbnailgecco2013.pdfVersión final (acceso restringido)1,9 MBAdobe PDFOpen    Request a copy

Items in RUA are protected by copyright, with all rights reserved, unless otherwise indicated.