Skip to Main Content
This study presents a novel approach to detect driver's drowsiness by applying two distinct methods in computer vision and image processing. The objective of this study is to combine both methods under one single profile instead of relied solely on a detection method to enhance the driver's drowsiness detection resolution. Therefore a non-intrusive drowsy-monitoring system is developed to alert the driver if driver falls into low arousal state. In physiological part, photoplethysmography (PPG) is analysed for its changes in signals waveform from awake to drowsy state. Meanwhile, eyes pattern or motion in image processing is addressed to detect driver fatigue. Genetic algorithm with template-matching approach is designed to detect eye region and estimate the drowsiness in different metric standard based on eyes behaviour. Moreover, PPG drowsy signals are integrated with eyes motion to derive the final probability model for delivering valid and reliable drowsiness detection system. Indeed, the proposed system provides high competitive edge over existing arbitrary drowsiness detection system where the driver's health and mental states can be monitored in real-time without constraints.