Presuming the Driver's Drowsiness by Image Processing and a Trial of Application to a Driving Support System

Abstract

Nowadays, driving support systems, such as car navigation systems, are getting common and they support drivers in several aspects. It is important for driving support systems to detect the state of drivers' consciousness. Particularly, detecting drivers' drowsiness could protect drivers from danger of collisions caused by drowsy driving. In this paper, we discuss a system and a method for detecting driver's drowsiness, which use a property of blink waveforms that drivers' eye-closing time is strongly connected to their drowsiness. Moreover, our system detects the drowsiness robustly for individual differences by using three factors extracted from the individual blink waveform.