基于人脸特征点的疲劳驾驶检测方法研究

Research on Fatigue Driving Detection Method Based on Facial Landmark

在当今车辆日益增多的时代,驾驶员长时间驾驶车辆会出现注意力下降,从而会增加出行风险,极易造成严重的交通事故。因此,设计预防疲劳驾驶的系统是非常必要的。基于此,笔者提出基于视频进行疲劳驾驶检测的方法。该方法通过人脸识别定位眼睛和嘴,计算眼睛的横纵比判断睁眼或是闭眼,同样利用嘴部的横纵比确定嘴的张度,根据张度和持续时长判断驾驶员处于打哈欠的状态。实验结果表明,本文提出的方法能够准确检测出疲劳驾驶。

In today’s era of increasing numbers of vehicles,drivers’attention will decrease when they drive for a long time,which will increase the risk of travel and can easily cause serious traffic accidents.Therefore,it is very necessary to design a system to prevent fatigue driving.Based on this,the author proposes a method for fatigue driving detection based on video.This method locates the eyes and mouth through face recognition,calculates the aspect ratio of the eyes to determine whether the eyes are open or closed.It also uses the aspect ratio of the mouth to determine the mouth opening,and judges that the driver is hitting according to the opening and duration.The state of yawning.Experimental results show that the method proposed in this paper can accurately detect fatigue driving.