Driver Fatigue State Detection Based on Facial Key Points

Abstract

The proportion of drivers causing traffic accidents due to fatigue driving has been increasing year by year, which has become one of the main causes of traffic accidents. Therefore, accurate and effective detection of driver fatigue is a hot research topic at present. In this article, the driver's head posture estimation based on face key points is used to judge fatigue. Firstly, the face image is collected from the camera in real time. The model-based method is used to estimate the head posture of the person. The face key points method based on the Dlib library is used to judge the eye state, the mouth state, the head turning posture of the person. The experimental results show that the head pose estimation method based on face key points can accurately judge the fatigue state, and has good real-time and accuracy.