Research on driver fatigue detection strategy based on human eye state

In order to reduce the traffic accidents caused by fatigue driving, on the basis of analyzing the current fatigue driving detection methods, the fatigue state detection technology based on human eye state detection is studied. Based on the characteristics of skin color, the color space transformation of YCbCr is used to achieve face location to improve the efficiency of image processing. The binary image of face region is processed, and the method of two times integral projection is adopted to detect the eyes' location. The eye pupil opening is analyzed and the close open ratios of eyes are measured to determine whether the driver is in a fatigue state or not. The experimental results show that this method can effectively carry out face location and eye location, and can determine the driver's fatigue state. When detecting the fatigue state, the system can provide warning information and improve traffic safety to a certain extent.