A Deep Learning-Based System for Driver Fatigue Detection

Driver fatigue is still a principal cause of traffic accidents.While many ways allowing fatigue detection, a diversity of obstacles such as head position, luminosity, and facial expressions make it a very challenging problem.In this paper, we propose a hybrid approach using deep learning techniques to detect driver drowsiness by combining between structural and global classification methods.The structural method tracks eyes, eyebrows, and mouth movements to assess blink and yawning, for this purpose we calculate eye-opening and mouth-opening ratios relative to their width.Five parameters are extracted LEM (left eye movement), REM (right eye movement), LEB M (left eyebrow movement), REBM (right eyebrow movement), and MM (mouth movement), whereas the global method is based on Convolutional Neural Network (CNN) to describe the whole face.Eight-layer pre-trained Alexnet network is used to extract features and make classification of each frame.To do video classification, the five structural parameters, along with the global classification decision, are combined into a single vector to be input into Long-Short-Term Memory (LSTM) networks that is an improved version of Recurrent Networks.LSTM decision score is determined after running 150 steps, providing information about driver state Extensive Experiments are performed on a Driver Drowsiness Detection Dataset that contains subjects of different ethnicities.The experimental results show that the proposed method with the combined features improves drowsiness detection significantly as well as outperforms the state-of-the-art models in terms of drowsiness scores.