Eye Movement Detection for Assessing Driver Drowsiness by Electrooculography

摘要: Many studies show that driver drowsiness is one of the main reasons for road accidents. To prevent such car crashes, systems are needed to monitor and characterize based on driving information. In order have highly reliable assistant systems, reference measurements required. Among different physiological measures, previous introduced eye movements, particularly blinking, as a measure with high correlation drowsiness. Hence, in this study, movements 14 drivers been observed using electrooculography (EOG) at moving-base simulator Mercedes Benz assess Based measured signals, an adaptive detection approach simultaneously detect not only blinks, but also other driving-relevant saccades micro sleep events. Moreover, spite fact influences movement patterns, proposed algorithm distinguishes between often-confused driving-related decreased amplitude blinks drowsy driver. The evaluation results shows presented outperforms common methods so detected correctly during both awake phases.