驾驶员疲劳检测系统的研究
|
摘要
随着交通运输业的快速发展,交通事故已经成为各个国家面临的难题之一。统计分析表明,驾驶员疲劳为导致交通事故的重要原因之一。随着计算机的快速发展和应用,采用摄像头采集到的驾驶员头部图像通过各种算法来判断驾驶员的疲劳状态并加以提醒已经成为了现在疲劳检测的主流方向。
本文主要思想是通过对驾驶员脸部信息的获取和图像检测,进行疲劳判断。脸部信息的获取包括进行脸部位置的检测,眼睛的检测定位和嘴唇的检测定位。脸部位置的检测定位主要建立肤色模型以及计算肤色相似度图,通过阈值分割方法进行分类和定位。在得到了脸部位置的准确信息后,进行眼睛和嘴唇的检测。根据人的面部特征首先对检测目标进行粗略定位,然后通过边界提取的办法进行眼睛的定位和状态的计算以及利用Fisher线性分类器进行嘴唇的定位和状态的计算。在得到了脸部信息的状态值后,进行驾驶员疲劳程度的综合评判,制作模糊控制器定义输入输出以及模糊推理规则。本文对驾驶员疲劳的检测进行了系统的研究与设计,并通过实验测试其准确性和有效性。本文的主要研究工作主要分为以下几个部分:
第一,改善了传统的边缘检测定位眼睛位置噪声多,错误率高的方法,提出边界提取方法进行定位,实验证明此方法是快速和高准确率的。改善了由于受到外界诸多因素的影响而检测效果不好的情况。
第二,运用Kalman滤波方法实现了对跟踪目标物体的跟踪和对噪声的滤波,加快了检测速度,进一步的提高了检测的准确性。
第三,提出综合评判驾驶员疲劳程度的概念,利用模糊控制器制定控制规则对疲劳状态进行综合评判,给检测留有一定容错率。
With the rapid development of transport, traffic accidents have become one of the various problem our country is facing. Statistical analysis showed that driver fatigue is one of the important reasons which is leading to traffic accidents. With the rapid development and application of computer, using camera to collected images of the driver and to determine the fatigue level of the driver by many algorithm.
The main idea of this paper is to determine the fatigue level by getting the information of the driver face and image detecting. The information of driver face include detect and calculate the statement of the eye ,mouth head position. The method of face detection is establishment of skin color model and computation of similarity graph, then classify by threshold segmentation. After get the accurate head position, detecting the eye and mouth position. Using facial characteristics to get the rough area of the eye and mouth, then use border extraction method for eye location and calculations of status and use Fisher linear classifier to get lip position and calculate mouth status. Conduct a comprehensive evaluation driver fatigue by making the definition of input and output of fuzzy controller and fuzzy inference rules. The thesis introduced the software design proposal of driver fatigue detection system. And the capability and stability of detecting system is tested. The main work of the thesis could be summarized as follows:
Firstly, improve the traditional edge detection method which have more noise and higher wrong detect rate. Proposed to locate the boundary extraction method, experimental results show this method is fast and high accuracy.
Secondly, use of Kalman filtering method to achieve the object of tracing and noise filtering, speeding up the detection rate further to improve the detection accuracy.
Thirdly, comprehensive Evaluation of driver fatigue proposed the concept of the development control rules by using fuzzy controller on the comprehensive evaluation of fatigue, leaving a certain tolerance to the rate of detection.
本文主要思想是通过对驾驶员脸部信息的获取和图像检测,进行疲劳判断。脸部信息的获取包括进行脸部位置的检测,眼睛的检测定位和嘴唇的检测定位。脸部位置的检测定位主要建立肤色模型以及计算肤色相似度图,通过阈值分割方法进行分类和定位。在得到了脸部位置的准确信息后,进行眼睛和嘴唇的检测。根据人的面部特征首先对检测目标进行粗略定位,然后通过边界提取的办法进行眼睛的定位和状态的计算以及利用Fisher线性分类器进行嘴唇的定位和状态的计算。在得到了脸部信息的状态值后,进行驾驶员疲劳程度的综合评判,制作模糊控制器定义输入输出以及模糊推理规则。本文对驾驶员疲劳的检测进行了系统的研究与设计,并通过实验测试其准确性和有效性。本文的主要研究工作主要分为以下几个部分:
第一,改善了传统的边缘检测定位眼睛位置噪声多,错误率高的方法,提出边界提取方法进行定位,实验证明此方法是快速和高准确率的。改善了由于受到外界诸多因素的影响而检测效果不好的情况。
第二,运用Kalman滤波方法实现了对跟踪目标物体的跟踪和对噪声的滤波,加快了检测速度,进一步的提高了检测的准确性。
第三,提出综合评判驾驶员疲劳程度的概念,利用模糊控制器制定控制规则对疲劳状态进行综合评判,给检测留有一定容错率。
With the rapid development of transport, traffic accidents have become one of the various problem our country is facing. Statistical analysis showed that driver fatigue is one of the important reasons which is leading to traffic accidents. With the rapid development and application of computer, using camera to collected images of the driver and to determine the fatigue level of the driver by many algorithm.
The main idea of this paper is to determine the fatigue level by getting the information of the driver face and image detecting. The information of driver face include detect and calculate the statement of the eye ,mouth head position. The method of face detection is establishment of skin color model and computation of similarity graph, then classify by threshold segmentation. After get the accurate head position, detecting the eye and mouth position. Using facial characteristics to get the rough area of the eye and mouth, then use border extraction method for eye location and calculations of status and use Fisher linear classifier to get lip position and calculate mouth status. Conduct a comprehensive evaluation driver fatigue by making the definition of input and output of fuzzy controller and fuzzy inference rules. The thesis introduced the software design proposal of driver fatigue detection system. And the capability and stability of detecting system is tested. The main work of the thesis could be summarized as follows:
Firstly, improve the traditional edge detection method which have more noise and higher wrong detect rate. Proposed to locate the boundary extraction method, experimental results show this method is fast and high accuracy.
Secondly, use of Kalman filtering method to achieve the object of tracing and noise filtering, speeding up the detection rate further to improve the detection accuracy.
Thirdly, comprehensive Evaluation of driver fatigue proposed the concept of the development control rules by using fuzzy controller on the comprehensive evaluation of fatigue, leaving a certain tolerance to the rate of detection.
引文
[1] Randell N. A tool to improve driving safety, Society of Automotive Engineers[J]. 2006(7): 45-70.
[2] Gerry E, Warning system for fatigued divers nearing reality with new eye data,Science Daily Magazine[J].2007(7):25-30.
[3]潘峰.关注世界睡眠日:当凶险在梦想潜伏[EB/OL],2007.03.
[4] B.Roman,etal. Fatigue Indicators of Drowsy Drivers Based on Ananlysis of Physiological Signals[J].ISMDA 2001,LNCS 2199,2001,62-68.
[5] J.Empson. The Psychological Significance of the Electro encephalo gram [J].London,U.K.:Macmillan,1986.
[6] Masakazu IGUCHI. Intruduction of Advanced Satety Vehicle(ASV) Program[J]. http://www.ahsra.or.jp/demo2000/eng/demo_e/ahs_e7/iguchi/iguchi.html.
[7] A.Sadeh,K.M.Sharkey, M.A.Carskadon, Activity-based sleep-wake identification:An empirical test of methodological issues.Sleep[J].1994,7(3):201-207.
[8] E.Argen. Lateral position detection using a vehicle-mountd camera[D].Master Thesis of Linkopings Universitet,2003.
[9] Carlos H.Morimoto,Marcio R.M.Mimica, Eye gaze tracking techniques for interactive applications[J].Elsevier Science Inc. New York, NY, USA, April 2005:4-24.
[10] Fung W.K, He X.M, Liu L, Shi P. D. Dimension Reduction Based on Cnonical Correlation[J]. Statistica Sinica.2002,12(4):1093-1114.
[11]石坚,吴远鹏.卓斌,等.汽车驾驶员主动安全因素的辨识与分析[J].上海交通大学学报,2000,36(3):325-329.
[12]杜志刚,潘晓东,郭雪斌.公路隧道进出口行车安全评价指标应用研究[J].同济大学学报,2001(6):53-55.
[13]王荣本,郭克友,等.一种基于Gabor小波的驾驶员眼部状态识别方法的研究[J].中国图像图形学报.2003,8A(9):1043-1047.
[14]郑培,周一鸣.机动车驾驶员疲劳评测方法的研究现状及发展趋势[J].中国农业大学学报,2001(6):53-55.
[15]刘志强,汪旸 .基于机器视觉的驾驶疲劳检测方法[J].中国制造业信息化,2006,35(3):63-66.
[16]韩相军,关永,王雪立.基于DSP的实时人脸检测系统[J].微计算机信息,2005,21(12):82-84.
[17]李峰.机器视觉应用技术研究[D].浙江:浙江大学硕士论文.2003.
[18]陈艳琴.关于司机疲劳监测的人眼监测与跟踪研究[D].长沙:中南大学.2004
[19]张凯.视频运动检测算法的研究和分析[J].辽宁工学院学报.2007,27(1):26-28.
[20]高浩军,杜宇人.中值滤波在图像处理中的应用[J].电子工程师,2004,30(8):35-36.
[21]郭秀梅,赵秀艳,王玉亮,等.基于YCgCb新颜色空间的人脸检测算法的研究.电子测量技术.2008.31(4):97-80.
[22]邵丹,韩家信. YUV与RGB之间的转换[J].长春大学学报:2004,14(5):51-53.
[23] Yang M H,Ahuja N. Detecting human faces in color images.Proc,IEEE Conference on Image Processing,1998:127-139.
[24]杜飞涛,陈先桥,万勇.一种基于肤色分割的人脸检测方法[J].湖北工学院学报.04,19(5):36-37
[25]高建坡.视频序列中的人脸检测与跟踪算法研究[D].南京:东南大学博士学位论文,2007.
[26]张凯.视频运动检测算法的研究和分析[J].辽宁工学院学报.2007.27(1):26-28.
[27]冯浩,王冬欣,王宪保.基于肤色检测和灰度特征的人眼定位方法研究[J].计算机应用及软件.2009.26(1):234-236.
[28] Runsheng,Ji,Bin Kong,Fei Zheng. Color edge detection based on YUV space and mimimanl apsnning tree.IEEE ICIA 2006:941-945.
[29]欧阳.基于自适应边缘提取的人眼定位方法[J].微计算机信息.2008.24(5-3):100-101.
[30]张志刚,周明全,耿国华.基于改进对称变换的人眼定位[J].西北大学学报(自然科学版).2008.38(4):565-568.
[31]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.
[32]边肇祺,张学工.模式识别[M].北京:清华大学出版社,2000:212-230.
[33] Huiling Zhang, Baichuan Lu,Yong Yu. The Method of Ostu Used in the Video Detection of Vehicles[J].Intelligent Computation Technoligy and Automation,20082(20):547-551.
[34]卡斯而曼.数字图像处理[M].北京:电子工业出版社.2002.
[35]何斌. Visual C++数字图像处[M].北京:人民邮电出版社,2003.
[36] Qiang Ji,Xiaojie Yang. Real-time eye gaze and face pose tracking for monitoring driver vigilance. Academic Press Ltd. London,UK,Volume 8,2002(5):357-377.
[37] Comaniciu D, Ramesh V, Meer P.Kalman-based object tracking.IEEE,2003.
[38]万琴,高耀南.基于卡尔曼滤波器的运动目标检测与跟踪[J].湖南大学学报(自然科学版). 2007, 34(3):36-40.
[39]黄雄栋.人脸识别系统中的特征检测算法研究[D].哈尔滨:哈尔滨工业大学硕士学位论文. 2007年.
[40] Chen Xue-Wen, Huang Thomas. Facial Expression Recognition: A clustering-based approach Pattern[J]. Recognition letters. 2003, 24: 1295-1302.
[41]傅德胜,寿益禾.图形图像处理学[M].南京:东南大学出版社,2002:263-267.
[42] Koren Y and Carrnel L. Visualization of Labeled Data Using Linear Transformations. In Proc. IEEE Information Visualization(Info Vis03). 2003:121-128.
[43]张松兰.自适应模糊控制器设计[J].自动化技术与应用. 2009, 28(2): 12-14.
[44]吴康华.基于PERCLOS的驾驶疲劳检测系统设计[D].浙江:浙江大学硕士学位论文. 2008年.
[45]张乃尧.典型模糊控制器的结构分析[J].模糊系统与数学. 1997, 11(2): 10-21.
[2] Gerry E, Warning system for fatigued divers nearing reality with new eye data,Science Daily Magazine[J].2007(7):25-30.
[3]潘峰.关注世界睡眠日:当凶险在梦想潜伏[EB/OL],2007.03.
[4] B.Roman,etal. Fatigue Indicators of Drowsy Drivers Based on Ananlysis of Physiological Signals[J].ISMDA 2001,LNCS 2199,2001,62-68.
[5] J.Empson. The Psychological Significance of the Electro encephalo gram [J].London,U.K.:Macmillan,1986.
[6] Masakazu IGUCHI. Intruduction of Advanced Satety Vehicle(ASV) Program[J]. http://www.ahsra.or.jp/demo2000/eng/demo_e/ahs_e7/iguchi/iguchi.html.
[7] A.Sadeh,K.M.Sharkey, M.A.Carskadon, Activity-based sleep-wake identification:An empirical test of methodological issues.Sleep[J].1994,7(3):201-207.
[8] E.Argen. Lateral position detection using a vehicle-mountd camera[D].Master Thesis of Linkopings Universitet,2003.
[9] Carlos H.Morimoto,Marcio R.M.Mimica, Eye gaze tracking techniques for interactive applications[J].Elsevier Science Inc. New York, NY, USA, April 2005:4-24.
[10] Fung W.K, He X.M, Liu L, Shi P. D. Dimension Reduction Based on Cnonical Correlation[J]. Statistica Sinica.2002,12(4):1093-1114.
[11]石坚,吴远鹏.卓斌,等.汽车驾驶员主动安全因素的辨识与分析[J].上海交通大学学报,2000,36(3):325-329.
[12]杜志刚,潘晓东,郭雪斌.公路隧道进出口行车安全评价指标应用研究[J].同济大学学报,2001(6):53-55.
[13]王荣本,郭克友,等.一种基于Gabor小波的驾驶员眼部状态识别方法的研究[J].中国图像图形学报.2003,8A(9):1043-1047.
[14]郑培,周一鸣.机动车驾驶员疲劳评测方法的研究现状及发展趋势[J].中国农业大学学报,2001(6):53-55.
[15]刘志强,汪旸 .基于机器视觉的驾驶疲劳检测方法[J].中国制造业信息化,2006,35(3):63-66.
[16]韩相军,关永,王雪立.基于DSP的实时人脸检测系统[J].微计算机信息,2005,21(12):82-84.
[17]李峰.机器视觉应用技术研究[D].浙江:浙江大学硕士论文.2003.
[18]陈艳琴.关于司机疲劳监测的人眼监测与跟踪研究[D].长沙:中南大学.2004
[19]张凯.视频运动检测算法的研究和分析[J].辽宁工学院学报.2007,27(1):26-28.
[20]高浩军,杜宇人.中值滤波在图像处理中的应用[J].电子工程师,2004,30(8):35-36.
[21]郭秀梅,赵秀艳,王玉亮,等.基于YCgCb新颜色空间的人脸检测算法的研究.电子测量技术.2008.31(4):97-80.
[22]邵丹,韩家信. YUV与RGB之间的转换[J].长春大学学报:2004,14(5):51-53.
[23] Yang M H,Ahuja N. Detecting human faces in color images.Proc,IEEE Conference on Image Processing,1998:127-139.
[24]杜飞涛,陈先桥,万勇.一种基于肤色分割的人脸检测方法[J].湖北工学院学报.04,19(5):36-37
[25]高建坡.视频序列中的人脸检测与跟踪算法研究[D].南京:东南大学博士学位论文,2007.
[26]张凯.视频运动检测算法的研究和分析[J].辽宁工学院学报.2007.27(1):26-28.
[27]冯浩,王冬欣,王宪保.基于肤色检测和灰度特征的人眼定位方法研究[J].计算机应用及软件.2009.26(1):234-236.
[28] Runsheng,Ji,Bin Kong,Fei Zheng. Color edge detection based on YUV space and mimimanl apsnning tree.IEEE ICIA 2006:941-945.
[29]欧阳.基于自适应边缘提取的人眼定位方法[J].微计算机信息.2008.24(5-3):100-101.
[30]张志刚,周明全,耿国华.基于改进对称变换的人眼定位[J].西北大学学报(自然科学版).2008.38(4):565-568.
[31]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.
[32]边肇祺,张学工.模式识别[M].北京:清华大学出版社,2000:212-230.
[33] Huiling Zhang, Baichuan Lu,Yong Yu. The Method of Ostu Used in the Video Detection of Vehicles[J].Intelligent Computation Technoligy and Automation,20082(20):547-551.
[34]卡斯而曼.数字图像处理[M].北京:电子工业出版社.2002.
[35]何斌. Visual C++数字图像处[M].北京:人民邮电出版社,2003.
[36] Qiang Ji,Xiaojie Yang. Real-time eye gaze and face pose tracking for monitoring driver vigilance. Academic Press Ltd. London,UK,Volume 8,2002(5):357-377.
[37] Comaniciu D, Ramesh V, Meer P.Kalman-based object tracking.IEEE,2003.
[38]万琴,高耀南.基于卡尔曼滤波器的运动目标检测与跟踪[J].湖南大学学报(自然科学版). 2007, 34(3):36-40.
[39]黄雄栋.人脸识别系统中的特征检测算法研究[D].哈尔滨:哈尔滨工业大学硕士学位论文. 2007年.
[40] Chen Xue-Wen, Huang Thomas. Facial Expression Recognition: A clustering-based approach Pattern[J]. Recognition letters. 2003, 24: 1295-1302.
[41]傅德胜,寿益禾.图形图像处理学[M].南京:东南大学出版社,2002:263-267.
[42] Koren Y and Carrnel L. Visualization of Labeled Data Using Linear Transformations. In Proc. IEEE Information Visualization(Info Vis03). 2003:121-128.
[43]张松兰.自适应模糊控制器设计[J].自动化技术与应用. 2009, 28(2): 12-14.
[44]吴康华.基于PERCLOS的驾驶疲劳检测系统设计[D].浙江:浙江大学硕士学位论文. 2008年.
[45]张乃尧.典型模糊控制器的结构分析[J].模糊系统与数学. 1997, 11(2): 10-21.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |