Comparative Study to Detect Driver Drowsiness

Abstract

Driver Drowsiness is one of the major causes of road accidents which leads to fatal and non-fatal injuries, sudden deaths and substantial monetary losses. Recently, various approaches have been identified to detect the driver drowsiness by research community due to advancement in the area of Artificial Intelligence (AI) and Machine Learning (ML). This further assists with saving the precious human life and reduces the monetary losses. Many researchers have proposed different techniques and methods to detect the driver drowsiness. The most common methods are subjective measures, vehicle-based measures, physiological measures, behavioural measures and hybrid measures. The detailed review of these measures, working of the existing systems, limitations associated with these systems are discussed in the paper. This paper also highlights the comparative analysis of the hybrid measures and its effectiveness. Hybrid measures is state of the art and it is the combination of two or more measures to detect driver drowsiness with higher accuracy. We conclude that developing a driver drowsiness detection system by using hybrid measures would be more efficient and it is highly recommended.