Real time drowsiness detection using eye blink monitoring

Abstract

According to analysis reports on road accidents of recent years, it's renowned that the main cause of road accidents resulting in deaths, severe injuries and monetary losses, is due to a drowsy or a sleepy driver. Drowsy state may be caused by lack of sleep, medication, drugs or driving continuously for long time period. An increase rate of roadside accidents caused due to drowsiness during driving indicates a need of a system that detects such state of a driver and alerts him prior to the occurrence of any accident. During the recent years, many researchers have shown interest in drowsiness detection. Their approaches basically monitor either physiological or behavioral characteristics related to the driver or the measures related to the vehicle being used. A literature survey summarizing some of the recent techniques proposed in this area is provided. To deal with this problem we propose an eye blink monitoring algorithm that uses eye feature points to determine the open or closed state of the eye and activate an alarm if the driver is drowsy. Detailed experimental findings are also presented to highlight the strengths and weaknesses of our technique. An accuracy of 94% has been recorded for the proposed methodology.