Robust real-time driver drowsiness detection based on image processing and feature extraction methods

Recently, the human lifestyle has strongly been affected by the novel technological equipment. The applications of Artificial Intelligence are widely being utilised to improve the performance and quality of the modern life. One of the important applications of these techniques is to seek to improve public safety, including the safety of driving. The statistics indicate that the mortality of car accidents yearly constitutes a significant proportion of the overall deaths. A number of strategies have been studied to materialise driver drowsiness detection systems. One of the best strategies relies on image processing and computer vision methods. In this paper, a novel real-time method for driver drowsiness detection is presented. This method uses Haar wavelet-based features for face detection. The eye state determination has been performed using PCA feature extraction along with an SVM classifier. The proposed method has been implemented and tested on a real-time ARM based embedded system, with a camera installed in front of the driver. Results show that the presented intelligent system has a high detection accuracy, compared to the methods presented thus far, on the standard datasets such as BioID and RS-DMV.