Exploiting visual quasi-periodicity for real-time chewing event detection using active appearance models and support vector machines

Steven Cadavid, Mohamed Abdel-Mottaleb, Abdelsalam Helal

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Steady increases in healthcare costs and obesity have inspired recent studies into cost-effective, assistive systems capable of monitoring dietary habits. Few researchers, though, have investigated the use of video as a means of monitoring dietary activities. Video possesses several inherent qualities, such as passive acquisition, that merits its analysis as an input modality for such an application. To this end, we propose a method to automatically detect chewing events in surveillance video of a subject. Firstly, an Active Appearance Model (AAM) is used to track a subject's face across the video sequence. It is observed that the variations in the AAM parameters across chewing events demonstrate a distinct periodicity. We utilize this property to discriminate between chewing and non-chewing facial actions such as talking. A feature representation is constructed by applying spectral analysis to a temporal window of model parameter values. The estimated power spectra subsequently undergo non-linear dimensionality reduction. The low-dimensional embedding of the power spectra are employed to train a binary Support Vector Machine classifier to detect chewing events. To emulate the gradual onset and offset of chewing, smoothness is imposed over the class predictions of neighboring video frames in order to deter abrupt changes in the class labels. Experiments are conducted on a dataset consisting of 37 subjects performing each of five actions, namely, open- and closed-mouth chewing, clutter faces, talking, and still face. Experimental results yielded a cross-validated percentage agreement of 93.0%, indicating that the proposed system provides an efficient approach to automated chewing detection.

Original languageEnglish
Pages (from-to)729-739
Number of pages11
JournalPersonal and Ubiquitous Computing
Volume16
Issue number6
DOIs
StatePublished - Aug 1 2012

Fingerprint

Mastication
Support vector machines
Power spectrum
Monitoring
Support vector machine
Periodicity
Event detection
Spectrum analysis
Labels
Costs
Classifiers

Keywords

  • Active appearance models
  • Behavior detection
  • Dietary monitoring
  • Manifold learning
  • Support vector machines

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Science Applications
  • Management Science and Operations Research

Cite this

Exploiting visual quasi-periodicity for real-time chewing event detection using active appearance models and support vector machines. / Cadavid, Steven; Abdel-Mottaleb, Mohamed; Helal, Abdelsalam.

In: Personal and Ubiquitous Computing, Vol. 16, No. 6, 01.08.2012, p. 729-739.

Research output: Contribution to journalArticle

@article{141a4316036047b1b583defb730fbef9,
title = "Exploiting visual quasi-periodicity for real-time chewing event detection using active appearance models and support vector machines",
abstract = "Steady increases in healthcare costs and obesity have inspired recent studies into cost-effective, assistive systems capable of monitoring dietary habits. Few researchers, though, have investigated the use of video as a means of monitoring dietary activities. Video possesses several inherent qualities, such as passive acquisition, that merits its analysis as an input modality for such an application. To this end, we propose a method to automatically detect chewing events in surveillance video of a subject. Firstly, an Active Appearance Model (AAM) is used to track a subject's face across the video sequence. It is observed that the variations in the AAM parameters across chewing events demonstrate a distinct periodicity. We utilize this property to discriminate between chewing and non-chewing facial actions such as talking. A feature representation is constructed by applying spectral analysis to a temporal window of model parameter values. The estimated power spectra subsequently undergo non-linear dimensionality reduction. The low-dimensional embedding of the power spectra are employed to train a binary Support Vector Machine classifier to detect chewing events. To emulate the gradual onset and offset of chewing, smoothness is imposed over the class predictions of neighboring video frames in order to deter abrupt changes in the class labels. Experiments are conducted on a dataset consisting of 37 subjects performing each of five actions, namely, open- and closed-mouth chewing, clutter faces, talking, and still face. Experimental results yielded a cross-validated percentage agreement of 93.0{\%}, indicating that the proposed system provides an efficient approach to automated chewing detection.",
keywords = "Active appearance models, Behavior detection, Dietary monitoring, Manifold learning, Support vector machines",
author = "Steven Cadavid and Mohamed Abdel-Mottaleb and Abdelsalam Helal",
year = "2012",
month = "8",
day = "1",
doi = "10.1007/s00779-011-0425-x",
language = "English",
volume = "16",
pages = "729--739",
journal = "Personal and Ubiquitous Computing",
issn = "1617-4909",
publisher = "Springer London",
number = "6",

}

TY - JOUR

T1 - Exploiting visual quasi-periodicity for real-time chewing event detection using active appearance models and support vector machines

AU - Cadavid, Steven

AU - Abdel-Mottaleb, Mohamed

AU - Helal, Abdelsalam

PY - 2012/8/1

Y1 - 2012/8/1

N2 - Steady increases in healthcare costs and obesity have inspired recent studies into cost-effective, assistive systems capable of monitoring dietary habits. Few researchers, though, have investigated the use of video as a means of monitoring dietary activities. Video possesses several inherent qualities, such as passive acquisition, that merits its analysis as an input modality for such an application. To this end, we propose a method to automatically detect chewing events in surveillance video of a subject. Firstly, an Active Appearance Model (AAM) is used to track a subject's face across the video sequence. It is observed that the variations in the AAM parameters across chewing events demonstrate a distinct periodicity. We utilize this property to discriminate between chewing and non-chewing facial actions such as talking. A feature representation is constructed by applying spectral analysis to a temporal window of model parameter values. The estimated power spectra subsequently undergo non-linear dimensionality reduction. The low-dimensional embedding of the power spectra are employed to train a binary Support Vector Machine classifier to detect chewing events. To emulate the gradual onset and offset of chewing, smoothness is imposed over the class predictions of neighboring video frames in order to deter abrupt changes in the class labels. Experiments are conducted on a dataset consisting of 37 subjects performing each of five actions, namely, open- and closed-mouth chewing, clutter faces, talking, and still face. Experimental results yielded a cross-validated percentage agreement of 93.0%, indicating that the proposed system provides an efficient approach to automated chewing detection.

AB - Steady increases in healthcare costs and obesity have inspired recent studies into cost-effective, assistive systems capable of monitoring dietary habits. Few researchers, though, have investigated the use of video as a means of monitoring dietary activities. Video possesses several inherent qualities, such as passive acquisition, that merits its analysis as an input modality for such an application. To this end, we propose a method to automatically detect chewing events in surveillance video of a subject. Firstly, an Active Appearance Model (AAM) is used to track a subject's face across the video sequence. It is observed that the variations in the AAM parameters across chewing events demonstrate a distinct periodicity. We utilize this property to discriminate between chewing and non-chewing facial actions such as talking. A feature representation is constructed by applying spectral analysis to a temporal window of model parameter values. The estimated power spectra subsequently undergo non-linear dimensionality reduction. The low-dimensional embedding of the power spectra are employed to train a binary Support Vector Machine classifier to detect chewing events. To emulate the gradual onset and offset of chewing, smoothness is imposed over the class predictions of neighboring video frames in order to deter abrupt changes in the class labels. Experiments are conducted on a dataset consisting of 37 subjects performing each of five actions, namely, open- and closed-mouth chewing, clutter faces, talking, and still face. Experimental results yielded a cross-validated percentage agreement of 93.0%, indicating that the proposed system provides an efficient approach to automated chewing detection.

KW - Active appearance models

KW - Behavior detection

KW - Dietary monitoring

KW - Manifold learning

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=84864598321&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864598321&partnerID=8YFLogxK

U2 - 10.1007/s00779-011-0425-x

DO - 10.1007/s00779-011-0425-x

M3 - Article

AN - SCOPUS:84864598321

VL - 16

SP - 729

EP - 739

JO - Personal and Ubiquitous Computing

JF - Personal and Ubiquitous Computing

SN - 1617-4909

IS - 6

ER -