Driving fatigue is one of the main reasons of traffic accidents. In this paper, we apply the multitask cascaded convolutional networks to face detection and alignment in order to ensure the accuracy and real-time of the algorithm. Afterwards another convolution neural network (CNN) is used for eye state recognition. Finally, we calculate the percentage of eyelid closure (PERCLOS) to detect the fatigue. The experimental results show that the proposed method has high recognition accuracy of eye state and can detect the fatigue effectively in real- time.
CITATION STYLE
Liu, X., Fang, Z., Liu, X., Zhang, X., Gu, J., & Xu, Q. (2017). Driver fatigue detection using multitask cascaded convolutional networks. In IFIP Advances in Information and Communication Technology (Vol. 510, pp. 143–152). Springer New York LLC. https://doi.org/10.1007/978-3-319-68121-4_15
Mendeley helps you to discover research relevant for your work.