Fatigue Detection Based on Multiple Visual Features in Virtual Driving System

Fatigue driving poses a significant hazard, leading to numerous traffic accidents annually. However, the fatigue detection algorithm based on visual features still has the problem of low accuracy, and it is difficult to test extreme fatigue driving conditions. This study proposes a fatigue detection method that exploits multiple visual features, including facial landmarks, mouth aspect ratio (MAR), eye aspect ratio (EAR), PERCLOS and head pose. Furthermore, we introduce a novel approach by developing a virtual driving system dedicated to fatigue detection. This system offers a rich driving environment and enables the exploration of fatigue-related boundary conditions. To validate our method and assess the potential of the virtual driving system in detecting fatigue driving, we conduct an experiment involving five healthy adults using the aforementioned system. In our final results, the detection accuracy of mild fatigue reached 0.94, and the detection accuracy of severe fatigue reached 0.97. The results confirm both the feasibility of our approach and the promising prospects of the virtual driving system in fatigue detection.