基于实时检测眼睛状态的一种安全驾驶方法  

A safe driving method based on real-time detection of eyes condition

作　　者：冀翀晓 吕青 李何 JI Chongxiao;LüQing;LI He(College of Electrical and Power Engineering,Taiyuan University of Technology,Taiyuan 030024,China)

机构地区：[1]太原理工大学电气与动力工程学院，山西太原030024

出　　处：《现代电子技术》2019年第20期133-138,144,共7页Modern Electronics Technique

基　　金：国家自然科学基金项目(61271249)

摘　　要：为预防及减少机动车驾驶过程中交通事故的发生,提出一种基于实时检测眼睛状态的安全驾驶方法。首先,在机动车驾驶空间安装并初始化摄像头,获取驾驶员的实时视频,然后采用基于肤色的人脸识别算法保留感兴趣区域(ROI),再用Viola?Jones算法眼睛分类器进行眼睛检测,最后对图像进行直方图均衡化以及中值滤波,利用Hough变换的圆形检测技术实现虹膜检测以完成眼睛的实时状态检测。实验结果表明,该方法能成功检测眼睛状态,检测准确率为99%,Kappa一致性为95.3%,具有较高的实时性。A safe driving method based on real?time detection of eye state is proposed to prevent and reduce the occur?rence of traffic accidents in the course of motor vehicle driving.Firstly,the camera is installed in motor vehicle driving space and initialized to obtain the real?time video of the driver,the region?of?interest(ROI)is reserved by means of the face recogni?tion algorithm based on cuticolor,and then the eyes are detected by the eyes classifier of Viola?Jones algorithm.Finally,histo?gram equalization and median filtering are adopted for the image,the iris detection is realized by using Hough transformational circular measurement technique to complete the real?time detection of eyes condition.The experimental results show that the method can successfully detect the eyes condition,and has higher real?time performance than other methods,whose the detec?tion accuracy is 99%and the Kappa consistency is 95.3%.

关 键 词：机动车驾驶 眼睛检测 图像预处理 虹膜检测 Viola-Jones算法 实时状态 

分 类 号：TN911.23?34[电子电信—通信与信息系统] TP391.4[电子电信—信息与通信工程]