Vision-based Human Action Classification Using Adaptive Boosting Algorithm

Handle URI:
http://hdl.handle.net/10754/627907
Title:
Vision-based Human Action Classification Using Adaptive Boosting Algorithm
Authors:
Zerrouki, Nabil; Harrou, Fouzi; Sun, Ying ( 0000-0001-6703-4270 ) ; Houacine, Amrane
Abstract:
Precise recognition of human action is a key enabler for the development of many applications including autonomous robots for medical diagnosis and surveillance of elderly people in home environment. This paper addresses the human action recognition based on variation in body shape. Specifically, we divide the human body into five partitions that correspond to five partial occupancy areas. For each frame, we calculated area ratios and used them as input data for recognition stage. Here, we consider six classes of activities namely: walking, standing, bending, lying, squatting, and sitting. In this paper, we proposed an efficient human action recognition scheme, which takes advantages of superior discrimination capacity of AdaBoost algorithm. We validated the effectiveness of this approach by using experimental data from two publicly available databases fall detection databases from the University of Rzeszow’s and the Universidad de Málaga fall detection datasets. We provided comparisons of the proposed approach with state-of-the-art classifiers based on the neural network, K-nearest neighbor, support vector machine and naïve Bayes and showed that we achieve better results in discriminating human gestures.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Statistics Program
Citation:
Zerrouki N, Harrou F, Sun Y, Houacine A (2018) Vision-based Human Action Classification Using Adaptive Boosting Algorithm. IEEE Sensors Journal: 1–1. Available: http://dx.doi.org/10.1109/JSEN.2018.2830743.
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
IEEE Sensors Journal
KAUST Grant Number:
OSR2015-CRG4-2582
Issue Date:
7-May-2018
DOI:
10.1109/JSEN.2018.2830743
Type:
Article
ISSN:
1530-437X; 1558-1748; 2379-9153
Sponsors:
This publication is based upon work supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No: OSR2015-CRG4-2582. We are grateful to the two referees, the Associate Editor, and the Editor-in-Chief for their comments.
Additional Links:
https://ieeexplore.ieee.org/document/8355489
Appears in Collections:
Articles; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Statistics Program

Full metadata record

DC FieldValue Language
dc.contributor.authorZerrouki, Nabilen
dc.contributor.authorHarrou, Fouzien
dc.contributor.authorSun, Yingen
dc.contributor.authorHouacine, Amraneen
dc.date.accessioned2018-05-17T06:24:06Z-
dc.date.available2018-05-17T06:24:06Z-
dc.date.issued2018-05-07en
dc.identifier.citationZerrouki N, Harrou F, Sun Y, Houacine A (2018) Vision-based Human Action Classification Using Adaptive Boosting Algorithm. IEEE Sensors Journal: 1–1. Available: http://dx.doi.org/10.1109/JSEN.2018.2830743.en
dc.identifier.issn1530-437Xen
dc.identifier.issn1558-1748en
dc.identifier.issn2379-9153en
dc.identifier.doi10.1109/JSEN.2018.2830743en
dc.identifier.urihttp://hdl.handle.net/10754/627907-
dc.description.abstractPrecise recognition of human action is a key enabler for the development of many applications including autonomous robots for medical diagnosis and surveillance of elderly people in home environment. This paper addresses the human action recognition based on variation in body shape. Specifically, we divide the human body into five partitions that correspond to five partial occupancy areas. For each frame, we calculated area ratios and used them as input data for recognition stage. Here, we consider six classes of activities namely: walking, standing, bending, lying, squatting, and sitting. In this paper, we proposed an efficient human action recognition scheme, which takes advantages of superior discrimination capacity of AdaBoost algorithm. We validated the effectiveness of this approach by using experimental data from two publicly available databases fall detection databases from the University of Rzeszow’s and the Universidad de Málaga fall detection datasets. We provided comparisons of the proposed approach with state-of-the-art classifiers based on the neural network, K-nearest neighbor, support vector machine and naïve Bayes and showed that we achieve better results in discriminating human gestures.en
dc.description.sponsorshipThis publication is based upon work supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No: OSR2015-CRG4-2582. We are grateful to the two referees, the Associate Editor, and the Editor-in-Chief for their comments.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.relation.urlhttps://ieeexplore.ieee.org/document/8355489en
dc.rights(c) 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works. Released under the IEEE Open Access Publishing Agreement.en
dc.subjectcascade classifieren
dc.subjectFall detectionen
dc.subjectFeature extractionen
dc.subjectgesture recognitionen
dc.subjectImage segmentationen
dc.subjectMonitoringen
dc.subjectShapeen
dc.subjectVideo sequencesen
dc.subjectvision computingen
dc.subjectWearable sensorsen
dc.titleVision-based Human Action Classification Using Adaptive Boosting Algorithmen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentStatistics Programen
dc.identifier.journalIEEE Sensors Journalen
dc.eprint.versionPost-printen
dc.contributor.institutionUniversity of Sciences and Technology Houari Boumédienne (USTHB), LCPTS, Faculty of Electronics and Computer Science, Algiers, Algeria.en
kaust.authorHarrou, Fouzien
kaust.authorSun, Yingen
kaust.grant.numberOSR2015-CRG4-2582en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.