基于人眼状态的驾驶员疲劳检测

吉林大学学报(信息科学版) ›› 2015, Vol. 33 ›› Issue (4): 449-.

基于人眼状态的驾驶员疲劳检测

赵晓琳, 王世刚, 姜秀红, 王晓燕, 赵文婷

吉林大学通信工程学院, 长春130012

出版日期:2015-07-24 发布日期:2015-12-02
作者简介:赵晓琳(1990—), 女, 山东聊城人, 吉林大学硕士研究生, 主要从事驾驶员疲劳检测研究, (Tel)86-15714404874 (E-mail)zhaoxl2009@126. com; 王世刚(1962—), 男, 长春人, 吉林大学教授, 博士生导师, 主要从事图像与视频信号智能处理研究, (Tel)86-13504325626(E-mail)wangshigang@ vip. sina. com。
基金资助:
博士点基金资助项目(20120061110091)

Driver Fatigue Detection Based on Eye State

ZHAO Xiaolin, WANG Shigang, JIANG Xiuhong, WANG Xiaoyan, ZHAO Wenting

College of Telecommunication Engineering, Jilin University, Changchun 130012, China

Online:2015-07-24 Published:2015-12-02

摘要/Abstract

摘要：

为提高驾驶员疲劳检测的准确性, 提出一种改进的眼睛状态检测方法。利用“参考白冶算法对原始帧图像做光照补偿处理, 基于肤色特征检测出人脸; 利用积分投影法将人脸和眼睛分割出来, 结合眉毛和眼睫毛之间距离的变化、眼睛区域黑色像素点的个数变化这两个参数对眼睛的状态做出判断。若连续5 帧图像眼睛均为闭合状态, 则系统给出疲劳警报。实验结果表明, 利用两个参数检测的准确率高于单个参数检测的准确率。

关键词: 疲劳检测, 肤色特征, 眼睛状态

Abstract:

To improve the accuracy of driver fatigue detection, presents an improved eye state detection method.Firstly, we use reference white algorithm for the processing of illumination compensation on original frame image, then segment the skin region from background based on color feature. Secondly, we use gray-scale integral projection method to segment face and eyes, combining two parameters that change in the distance between eyebrow and eyelash the change in the number of black pixels in the eye region to judge the state of eyes. If the eyes are found closed for 5 consecutive frame images, the system will give a fatigue alert. The results show that the use of two parameters is better than the use of a single parameter.

Key words: fatigue detection, color feature, eye state

中图分类号:

TP391

赵晓琳, 王世刚, 姜秀红, 王晓燕, 赵文婷. 基于人眼状态的驾驶员疲劳检测[J]. 吉林大学学报(信息科学版), 2015, 33(4): 449-.

ZHAO Xiaolin, WANG Shigang, JIANG Xiuhong, WANG Xiaoyan, ZHAO Wenting. Driver Fatigue Detection Based on Eye State[J]. Journal of Jilin University(Information Science Ed, 2015, 33(4): 449-.