[1]王琼,王欢,赵春霞,等.基于眼睛状态识别的驾驶员疲劳监测[J].南京理工大学学报(自然科学版),2010,(04):448-453.
　WANG Qiong,WANG Huan,ZHAO Chun-xia,et al.Driver Fatigue Monitoring Based on Eye State Recognition[J].Journal of Nanjing University of Science and Technology,2010,(04):448-453.
点击复制

基于眼睛状态识别的驾驶员疲劳监测
分享到：

《南京理工大学学报》（自然科学版）[ISSN:1005-9830/CN:32-1397/N]

卷:
期数:
2010年04期
页码:
448-453
栏目:
出版日期:
2010-08-31

文章信息/Info

Title:
Driver Fatigue Monitoring Based on Eye State Recognition
作者:
王琼;王欢;赵春霞;杨静宇;
南京理工大学计算机科学与技术学院
Author(s):
WANG Qiong; WANG Huan; ZHAO Chun-xia; YANG Jing-yu
School of Computer Science and Technology,NUST,Nanjing 210094,China
关键词:
驾驶员疲劳监测;  人眼跟踪;  人脸跟踪;  眼睛状态识别
Keywords:
driver fatigue monitoring;  eye tracking;  face tracking;  eye state recognition
分类号:
TP274
摘要:
提出一种基于眼睛状态识别的驾驶员疲劳状态监测算法。在首帧定位人眼并在眼睛区域内提取多个具有互补性的特征,使用粒子滤波算法进行直接跟踪;在后续图像帧中利用CAMShift算法对初始检测到的人脸区域进行实时跟踪,在人脸区域中同步检测眼睛,检测结果用于粒子滤波器的后验确认和修正。在跟踪眼睛的同时检测每帧中的眼睛状态,通过连续帧中的眼睛状态判断出驾驶员精神状态。实验表明:该文算法对人脸旋转和尺度变化、摄像机抖动,以及遮挡的影响均具有较高的鲁棒性。
Abstract:
A driver fatigue monitoring algorithm based on eye state recognition is proposed here.In the first frame,eye windows are detected by face detection followed with an accurate eye localization algorithm.For eye tracking,several complementary features are extracted from the detected eye window and fused in probability form in particle filter tracking framework.The CAMShift algorithm is also exploited to track the face region,and the eye detection algorithm is still used to detect reliable eye pairs,so as to verify and correct the tracking result of the particle filter.The spirit status of drivers can be detected by analyzing eye states in continuous image frames.Experiments show that the proposed algorithm can well handle pose changes,camera jitter and partial occlusion.

参考文献/References:

[ 1] ?? 毛喆, 初秀民. 汽车驾驶员驾驶疲劳监测技术研究 进展[ J] . 中国安全科学学报, 2005, 15 ( 3) : 108 - 112. [ 2 ] 李力, 王飞跃, 郑南宁. 驾驶行为智能分析的研究 与发展[ J] . 自动化学报, 2007, 33 ( 10 ): 1014 - 1022.
[ 3] 李晓明, 何国红. 疲劳驾驶监控中的眼睛状态识别 方法[ J]. 电子工艺技术, 2007, 28( 2): 102- 105.
[ 4] 翁茂荣. 基于眼睛状态的驾驶员疲劳模糊识别研 究[ J] . 计算机仿真, 2008, ( 25) 6: 244- 247.
[ 5] FukunagaK, H ostetle rL D. The estim ation of the g ra?? d ient o f a density function w ith app lications in pattern recogn ition [ J ]. IEEE Transactions on Info rma tion Theory, 1975, 21( 1): 32- 40.
[ 6] Bradsk iG R. Rea l tim e face and ob ject tracking as a component o f a perceptual use r inte rface [ A ]. Pro?? ceedings of the WACV [ C ]. Pr ince ton, USA: IEEE Press, 1998: 214- 219.
[ 7] De D ios J, Garc ia N. Face detec tion based on a new co lor space YCgC r [ A ]. Proceed ings of IC IP [ C ]. Barcelona, Spa in: IEEE Press, 2003: 909- 912.
[ 8] 陈艳琴, 罗大庸. 基于Kalman滤波和M ean Shift算 法的人眼实时跟踪[ J]. 模式识别与人工智能, 2004, 17( 2): 173- 177.
[ 9] H orngW en??B ing, Chen Ch ih??Yuan, Chang Y,i et a.l Driver fa tigue detection based on eye track ing and dy?? nam ic, temp la tem atch ing[ A ]. Pro ceedings of ICNSC [ C ]. Taibe ,i Ta iw an, China: IEEE Press, 2004: 21- 23.

备注/Memo

备注/Memo:
基金项目: 国家自然科学基金( 60632050); 中国博士后基金; 江苏省科技计划高技术研究项目( BG2005008) 作者简介: 王琼( 1981- ), 女, 博士, 主要研究方向: 模式识别、图像处理、车辆主动安全, Email: w angqiong603@163.com。
更新日期/Last Update: 2012-11-02