Research on Deep Learning-based Driver Fatigue Driving Behavior Recognition Methods

Aiming at the problem of motor vehicle drivers' fatigue driving, this paper proposes a deep learning-based fatigue driving behavior recognition method. The four parameters of PERCLOS parameter, blinking frequency, continuous eye closure time and continuous mouth opening time are used as the recognition indexes to establish a driver fatigue driving recognition model based on deep learning, and the experimental results show that the method proposed in this paper has a better recognition effect in different light environments.