Estimation of Driver Vigilance Status Using Real-Time Facial Expression and Deep Learning

Drowsiness is responsible for many fatal accidents on highways. Accuracy and performance are key metrics related to many researched techniques for the detection of drivers' drowsiness. To improve these metrics, a new driver's vigilance detection system based on deep learning is proposed based on facial region diagnosis using the Haar-cascade method and convolutional neural network for drowsiness detection. Evaluation analysis of the proposed system on the University of Texas at Arlington-Real-Life Drowsiness Dataset (UTA-RLDD) dataset with stratified five-fold cross-validation showed a high accuracy of 96.8% at a speed of 8.4 frames per second, which is higher than most algorithms previously reported in the literature. For further investigation, a custom dataset including ten participants in different light conditions was collected. The conducted experiments showed the great potential of the proposed system for practical applications in intelligent transportation systems.