|本期目录/Table of Contents|

[1]杨述斌,金璐,章振保.疲劳驾驶检测中的快速人眼定位方法[J].武汉工程大学学报,2013,(06):67-72.[doi:103969/jissn16742869201306013]
　YANG Shu bin,JIN Lu,ZHANG Zhen bao.Fast eye location method in driver fatigue detection[J].Journal of Wuhan Institute of Technology,2013,(06):67-72.[doi:103969/jissn16742869201306013]
点击复制

疲劳驾驶检测中的快速人眼定位方法(/HTML)
分享到：

《武汉工程大学学报》[ISSN:1674-2869/CN:42-1779/TQ]

卷:
期数:
2013年06期
页码:
67-72
栏目:
机电与信息工程
出版日期:
2013-06-30

文章信息/Info

Title:
Fast eye location method in driver fatigue detection
文章编号:
16742869(2013)06006706
作者:
杨述斌; 金璐; 章振保
武汉工程大学电气信息学院，湖北 武汉 430205
Author(s):
YANG Shubin; JIN Lu; ZHANG Zhenbao
Electrical and Information College of Wuhan Institute of Technology，Wuhan 430205,China
关键词:
疲劳驾驶; 人眼定位; 多摄像头; 灰度投影; LMS模板匹配
Keywords:
fatigue driving;  eye location;  multicamera; gray projection;  LMS template matching
分类号:
TP391
DOI:
103969/jissn16742869201306013
文献标志码:
A
摘要:
为了减少因疲劳驾驶所引发的交通事故的发生，人眼定位在疲劳驾驶检测技术中起着重要的作用.对人眼定位的过程中，采用多摄像头获取图像并对这些图像进行筛选，将检测到的人脸面积最大，将能够完整检测到双眼状态的图像做为最佳输入图像，采用Adaboost（迭代级联分类器）算法对其进行人脸定位以减小检测区域，再对其进行灰度投影将检测范围缩小在眉眼区域，然后进行一种新的LMS（最小均方误差）模板匹配，精确定位眼睛区域.在人脸成功定位的基础上，该算法经过二次眼睛定位，较传统的模板匹配方法，平均模板匹配检测时间提高到了30.5ms，准确率提高到了97%.实验表明：将灰度投影法和改进的LMS（最小均方误差）模板匹配两种人眼定位的方法相结合来进行人眼的定位，与传统的模板匹配相比，提高了检测的效率和检测的准确率，使得疲劳驾驶检测系统能更准确地进行实时检测，该方法能适用于疲劳驾驶检测等需要快速人眼定位的场合.
Abstract:
Eye location plays an important role in the fatigue driving detection to reduce the traffic accident. During the process of the eye location, the images were got by multicamera and chosen the best to input. At first, the face was located by Adaboost method. Second, the area was narrowed in facial features by the gray projection and applied a new LMS template matching. Then the area of eye was located accurately. Based on the face location accurately, the efficiency of this algorithm increased to 30.5ms and the accuracy of the eye location was improved to 97% through the twice eye location The experiment shows that the efficiency and the accuracy are improved greatly after the combination of the gray projection and the LMS template matching. So it is suitable for the fatigue driving detection which needs rapid eye location.

参考文献/References:

［1］甄轶佳．基于眼部特征的疲劳驾驶检测技术研究\[D\]．沈阳：沈阳工业大学，2009．ZHEN Yijia.Detection of fatigue driving based on eye features\[D\]. Shenyang ：Shenyang University of Technology,2009.（in Chinese）［2］王荣本．驾驶员驾驶行为监测中的面部定位方法的研究\[J\] ．公路交通科技，2003（2）：9699．WANG Rongben. Research of the driving face location method in driver behavior surveillance\[J\]. Highway traffic science and technology,2003（2）：9699.（in Chinese）［3］李逢博．人脸检测与标定技术的实现与研究\[D\]．西安：西北大学，2004．LI Fengbo. Research and implementation of face detection and calibration technology\[D\]. Xian:Northwestern University,2004.（in Chinese）［4］范一峰，颜志英． 基于Adaboost算法和肤色验证的人脸检测研究\[J\]．微计算机信息，2010（26）：231233.FAN Yifeng,YAN Zhiying.Research on face detection algorithm based on Adaboost and skin color verification\[J\].Micro computer information,2010（26）：231233.（in Chinese）［5］刘念，苏杭，郭纯宏，等．基于Hough变换圆检测的人眼定位方法改进\[J\]．计算机工程与设计,2011（4）：13591362．LIU Nian,SU Hang,GUO Chunhong, et al. Improved eye location method based on Hough transform circle detection\[J\].Computer engineering and design, 2011（4）:13591362.（in Chinese）［6］舒梅，董秀成．基于肤色和模板匹配的人眼定位\[J\]．计算机工程与应用，2009，45(2)：237239．SHU Mei,DONG Xiucheng. Eye location based on skin color and template matching\[J\]. Computer engineering and Applications,2009,45(2)：237239.（in Chinese）［7］冯建强 , 刘文波 ,于盛林．基于灰度积分投影的人眼定位\[J\]．计算机仿真，2005（4）：7577．FENG Jianqiang,LIU Wenbo,YU Shenglin. Eye location based on gray integral projection\[J\]. computer simulation, 2005（4）：7577．（in Chinese）［8］曹珩，杨述斌，罗帆，等．多尺度全方位复合广义形态边缘检测的算法\[J\]．武汉工程大学学报，2010，32(9)：7881．CAO Heng，YANG Shubin，LUO Fan，et al.General edge detection algorithm of compound mathematic morphology based on mulitscale and omnidirection structure\[J\].Journal of Wuhan Institute of Technology,2010,32(9):7881.(in chinese)［9］甄巍松,李国强,鲁统伟. 基于特征点相似度的匹配定位算法\[J\]．武汉工程大学学报，2011,33(4)：8588.ZHEN Weisong，LI Guoqiang，LU Tongwei. Match and location algorithm based on similarity of feature point\[J\]. Journal of Wuhan Institute of Technology,2011,33(4):8588.(in chinese)［10］刘鹏，江朝晖，熊进，等．用于驾驶疲劳检测的人眼定位及状态判别算法\[J\]．计算机工程与应用， 2010，46（24）：185188．LIU Peng,JIANG Chaohui,XIONG Jin,et al.Discriminant algorithm for eyes location and status of driver fatigue detection\[J\].Computer engineering and Applications,2010,46(24):185188.（in Chinese）

相似文献/References:

备注/Memo

备注/Memo:
收稿日期：20130322作者简介：杨述斌（1971），男，湖北武汉人，教授，硕士.研究方向：信号与图像处理模式识别及多媒体通信等.
更新日期/Last Update: 2013-07-11