Human Activity Recognition in a Car with Embedded Devices

  • Danilo Burbano University of Neuchâtel and University of Fribourg, Switzerland
  • Jose Luis Carrera University of Neuchâtel and University of Fribourg, Switzerland
Keywords: drowsiness, cascadeclassifier, Viola-Jones method, FACS, AU

Abstract

Detection and prediction of drowsiness is key for the implementation of intelligent vehicles aimed to prevent highway crashes. There are several approaches for such solution.
In thispaper the computer vision approach will be analysed, where embedded devices (e.g.videocameras) are used along with machine learning and pattern recognition techniques for implementing suitable solutions for detecting driver fatigue.
Most of the research in computer vision systems focused on the analysis of blinks, this is a notable solution when it is combined with additional patterns like yawing or head motion for the recognition of drowsiness. The first step in this approach is the face recognition, where AdaBoost algorithm shows accurate results for the feature extraction, whereas regarding the detection of drowsiness the data-driven classifiers such as Support Vector Machine (SVM) yields remarkable results.
One underlying component for implementing a computer vision technology for detection of drowsiness is a database of spontaneous images from the Facial Action Coding System (FACS), where the classifier can be trained accordingly.
This paper introduces a straightforward prototype for detection of drowsiness, where the Viola-Jones method is used for face recognition and cascade classifier is used for the detection of a contiguous sequence of eyes closed, which a reconsidered as drowsiness.

DOI

Downloads

Download data is not yet available.

References

Esra Vural, Mujdat Cetin, Aytul Ercil, Gwen Littlewort, Marian Bartlett and Javier Movellan; Automated Drowsiness Detection For Improved Driving Safety

David F. Dinges and Melissa M. Mallis; Managing Fatigue by Drowsiness Detection: Can Technological Promises be Realized?, 1998

Esra Vural, Mujdat Cetin, Aytul Ercil, Gwen Littlewort, Marian Bartlett and Javier Movellan; Machine Learning Systems for Detecting Driver Drowsiness

Grace, R., Byrne, V., Bierman, D., Legrand, J.M., Gricourt, D., Davis, B., Staszewski, J., Carnahan, B.; A Drowsy Driver Detection System For Heavy Vehicles

Richard Grace, Sonya Steward; Drowsy Driver Monitor and Warning System

Bartlett, M., Littlewort, G., Frank, M., Lainscsek, C., Fasel, I., Movellan, J.; Automatic recognition of facial actions in spontaneous expressions. Journal of Multimedia., 2006

Kanade, T., Cohn, J., Tian, Y.; Comprehensive database for facial expression analysis.

Fasel I., Fortenberry B., M.J.; A generative framework for real-time object detection and classification., 2005

Ole Helvig Jensen; Implementing the Viola-Jones Face Detection Algorithm., 2008

Andrew King; A Survey of Methods for Face Detection, 2003

Patrick Lucey, Jeffrey F. Cohn, Takeo Kanade, Jason Saragih, Zara Ambadar; The Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression, 2010

Yi-Qing Wang; An Analysis of the Viola-Jones Face Detection Algorithm, 2013

Rohan Putta, Gayatri N Shinde, Punit Lohani; Real Time Drowsiness Detection System using Viola Jones Algorithm, 2014

University of Pittsburgh, Cohn-Kanade database [Online]. Available: http://www.pitt.edu/~emotion/ck-spread.htm

Published
2015-11-30
How to Cite
[1]
D. Burbano and J. Carrera, “Human Activity Recognition in a Car with Embedded Devices”, LAJC, vol. 2, no. 2, Nov. 2015.
Section
Research Articles for the Regular Issue