Citation

Mohammad F, Mahadas K, Hung GK. Comput. Biol. Med. 2017; 89: 76-83.

Affiliation

Department of Biomedical Engineering, Rutgers University, 599 Taylor Road, Piscataway, NJ 08854, USA. Electronic address: shoane@soe.rutgers.edu.

Copyright

(Copyright © 2017, Elsevier Publishing)

DOI

10.1016/j.compbiomed.2017.07.027

PMID

28787648

Abstract

A reliable and practical app for mobile devices was developed to detect driver drowsiness. It consisted of two main components: a Haar cascade classifier, provided by a computer vision framework called OpenCV, for face/eye detection; and a dedicated JAVA software code for image processing that was applied over a masked region circumscribing the eye. A binary threshold was performed over the masked region to provide a quantitative measure of the number of white pixels in the sclera, which represented the state of eye opening. A continuously low white-pixel count would indicate drowsiness, thereby triggering an alarm to alert the driver. This system was successfully implemented on: (1) a static face image, (2) two subjects under laboratory conditions, and (3) a subject in a vehicle environment.

Copyright © 2017 Elsevier Ltd. All rights reserved.

Language: en

Keywords

Distraction; Drowsy; Face/eye detection; Fatigue; OpenCV; Scleral area