基于视频的驾驶员疲劳状态检测方法研究
|
摘要
驾驶员疲劳驾驶是引发交通事故的一个重要原因,因此,如何有效的监测和防止疲劳驾驶,对于减少交通事故有着十分重要的实用意义。驾驶员在车辆行驶过程中是否疲劳可以从眼睛的睁开程度反映出来,利用驾驶员眼睛的睁开程度来判断其疲劳状况是一种可行的方法。因此,如何快速、准确地确定驾驶员眼睛的睁开程度进而得到疲劳状态是本文研究的主要目标。
论文主要包括以下三个方面:
1.针对驾驶室内比较特定的背景环境,采用减背景的方法检测包含人脸区域的运动目标。本文主要考虑光线变化对运动目标检测效果的影响,提出了应对光线渐变和光线突变两种情形的背景更新策略。进一步采用椭圆拟合的方法定位人脸区域,并进行人脸区域验证。上述方法在定位人脸时简单、快速、准确。
2.在人脸定位的基础上,采用对称变换的方法先定位眉心,进而粗定位人眼,然后采用积分投影的方法进行人眼精确定位。对于戴眼镜、眼睛半睁半闭、有复杂背景、侧面、两眼连线与水平线有一定夹角的人脸图像,这种方法都可快速、准确地定位人眼,检测准确率高。
3.采用霍夫变换及Daugman算子提取出人眼黑眼球的轮廓,再求出轮廓内黑眼球面积与整个轮廓包围面积比值,由该比值确定人眼的睁开程度;参考PERCLOS提出POFECT检测驾驶疲劳的方法,应用该方法判定驾驶员是否疲劳。
本文采用MATLAB语言进行仿真,实现了算法的各项功能,并进行了相关的实验。实验结果达到了预定目标,证明了所研究算法的有效性。
Drivering fatigue is a major factor for traffic accidents.So,how to effectivly monitor and prevent of drivering fatigue is significant to reduce traffic accident.In the course of driving,whether fatigue or not can be reflected in driver eyes open degree,the use of their eyes open degree to determine status of driver fatigue is an efficent solution. How to detect the eyes' open degree fast,real-time,accurately is the main research objective in this paper.
The paper includes the following three aspects:
Firstly,under the special circumstance of the operator cabin,the motion object including the driver's face is detected by the method of background subtraction.The illuminance variation which affects the detection of the motion target is mainly considered in this paper.A new background updating method is proposed to solve the problem of the illuminance changing which takes place slowly or quickly.The face is located by ellipse fitting,and then the result is checked by the face's intensity character. The method described above can locate the face concisely,quickly and accurately.
Secondly,According to the result of face location,symmetry transform is used to search the glabellum and locate the eyes roughly.Then the method of integral projection is used to accurately locate the driver's eyes.In the case of the driver wearing glasses, the eyes semi-open,complex background existing and the head rotating,the method in this paper can locate the eyes quickly and accurately and the detection accuracy is high.
Thirdly,Hough transform and Daugman operator are used to extract the outline of the eyeball,then,the ratio between the area of the eyeball and the area in the outline is computed,the ratio can show the open degree of eyes.Finally,the proposed algorithm is combined with the POFECT method to decide whether the driver is fatigued.
The algorithm's simulation and relevant experiments are processed in the MATLAB environment.Experimental results show that the predetermined target is achieved and the algorithm presented in this paper is effective.
论文主要包括以下三个方面:
1.针对驾驶室内比较特定的背景环境,采用减背景的方法检测包含人脸区域的运动目标。本文主要考虑光线变化对运动目标检测效果的影响,提出了应对光线渐变和光线突变两种情形的背景更新策略。进一步采用椭圆拟合的方法定位人脸区域,并进行人脸区域验证。上述方法在定位人脸时简单、快速、准确。
2.在人脸定位的基础上,采用对称变换的方法先定位眉心,进而粗定位人眼,然后采用积分投影的方法进行人眼精确定位。对于戴眼镜、眼睛半睁半闭、有复杂背景、侧面、两眼连线与水平线有一定夹角的人脸图像,这种方法都可快速、准确地定位人眼,检测准确率高。
3.采用霍夫变换及Daugman算子提取出人眼黑眼球的轮廓,再求出轮廓内黑眼球面积与整个轮廓包围面积比值,由该比值确定人眼的睁开程度;参考PERCLOS提出POFECT检测驾驶疲劳的方法,应用该方法判定驾驶员是否疲劳。
本文采用MATLAB语言进行仿真,实现了算法的各项功能,并进行了相关的实验。实验结果达到了预定目标,证明了所研究算法的有效性。
Drivering fatigue is a major factor for traffic accidents.So,how to effectivly monitor and prevent of drivering fatigue is significant to reduce traffic accident.In the course of driving,whether fatigue or not can be reflected in driver eyes open degree,the use of their eyes open degree to determine status of driver fatigue is an efficent solution. How to detect the eyes' open degree fast,real-time,accurately is the main research objective in this paper.
The paper includes the following three aspects:
Firstly,under the special circumstance of the operator cabin,the motion object including the driver's face is detected by the method of background subtraction.The illuminance variation which affects the detection of the motion target is mainly considered in this paper.A new background updating method is proposed to solve the problem of the illuminance changing which takes place slowly or quickly.The face is located by ellipse fitting,and then the result is checked by the face's intensity character. The method described above can locate the face concisely,quickly and accurately.
Secondly,According to the result of face location,symmetry transform is used to search the glabellum and locate the eyes roughly.Then the method of integral projection is used to accurately locate the driver's eyes.In the case of the driver wearing glasses, the eyes semi-open,complex background existing and the head rotating,the method in this paper can locate the eyes quickly and accurately and the detection accuracy is high.
Thirdly,Hough transform and Daugman operator are used to extract the outline of the eyeball,then,the ratio between the area of the eyeball and the area in the outline is computed,the ratio can show the open degree of eyes.Finally,the proposed algorithm is combined with the POFECT method to decide whether the driver is fatigued.
The algorithm's simulation and relevant experiments are processed in the MATLAB environment.Experimental results show that the predetermined target is achieved and the algorithm presented in this paper is effective.
引文
[1]http://www.miningaustralia.com.au/Article/Dealing-with-driver-fatigue
[2]陈艳琴.关于司机疲劳监测的人眼检测与跟踪研究:(硕士学位论文).湖南:中南大学,2004.
[3]Qiang Ji,Zhiwei Zhu,Peilin Lan.Real-Time Nonintrusive Monitoring and Prediction of Driver Fatigue[J].IEEE Transactions on Vehicular Technology,2004,53(4).
[4]Tim H,Laurence H,Gerald P K et al.Fatigue Detection Technologies for Drivers:A Review of Existing Operator-Centred Systems.IEE 2001 Conference Publication,2001,481.
[5]李治春,何仁,林谋有.驾驶员疲劳检测预警技术研究现状及发展趋势.第四届亚太可持续发展交通与环境技术大会,中国西安,2005.
[6]Qiong W,Jingyu Y,MingwuR et al.Driver Fatigue Detection:h Survey.Intelligent Control and Automation,2006,2:8587-8591.
[7]Philip W,Roger D,John M.Development of Driver Alertness Detection System Using Overhead Capacitive Sensor Array.SAE Technical Paper Series 982292,SAE International,1998.
[8]Anneke H,Rainer G,Acacia A.Technologies For The Monitoring and Prevention of Driver Fatigue.Proceedings of the First International Driving Symposium on Human Factor in Driver Assessment,Training and Vehicle Design[C],2001.8.
[9]Fletcher L,Apostoloff N,petersson L.Vision in and out of Vehicles.IEEE Trans.Intelligent Transportation Systems,2003:12-17.
[10]张伦维.疲劳驾驶的克星-防疲劳驾驶系统让驾驶更安全.当代汽车,2008.
[11]盛敬.驾驶员疲劳监控系统中人脸检测与识别研究:(硕士学位论文).辽宁:东北大学,2006.
[12]http://www.safeluck.com/pro_info.asp?id=156
[13]http://www.kj.zjg.gov.cn/Article/ShowArticle.asp?ArticleID=9066
[14]Sung K K,Poggio T.Example-based learning for view-based human face detection.IEEE Transactions on Pattern Analysis and Machine Intelligence.1998,20(1):39-51.
[15]Yang G Z,Huang T S.Human Face Detection in a complex background.Patten Recognition,1994,27(1):53-63.
[16]Yuille A,Hallinan P,Cohen D.Feature Extraction from Faces Using Deformable Templates[J].International Journal of Computer Vision,1992,8(2):99-111.
[17]卢春雨,张长水,闻芳等.基于区域特征的快速人脸检测法[J].清华大学学报(自然科学版),1999,39(1):101-105.
[18]Turk M.and Pentland A.Eigenfaces for Recognition.Journal of Cognitive Neuroscience,1991,3(1):72-86.
[19]王良民,张建明,詹永照等.人脸检测研究现状和发展.江苏大学学报,2003,24(3).
[20]Zhou Q,Aggarwal J.Tracking and classifying moving objects from videos.Proceedings of IEEE Workshop on Performance Evaluation of Tracking and Surveillance,2001.
[21]Stauffer C,Grimson W.Learning patterns of activity using real-time tracking.IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):747-757.
[22]GanderW,Golub G H,Strebel R,et al Least-squares fitting of circles and ellip ses[J].B IT Numerical Mathematics,1994,34(4):558-578.
[23]Rosin P L.Ellipse fitting by accumulating five-point fits[J].Pattern Recognition Letters,1993,14(8):661-669.
[24]邸巍.驾驶员头部检测算法研究:(硕士学位论文).吉林:吉林大学,2007.
[25]Fitzgibbon A,Pile U M,Fisher R B.Direct least square fitting of ellipses[J].Pattern analysis and machine intelligence,1999,21(5):476-480.
[26]Yuille A.L.,Cohen D.S.,Halliman P.W.Feature Extraction From Faces using Deformable Templates[A],In:Proc.Computer Vision and Pattern Recognition[C],1989:104-109.
[27]Fu H C,Lai P S,Lou R Set al,Face Detection and Eye Localization by Neural Network Based Color Segmentation[A],In:Proc.Neural Networks for Signal Processing[C],2000(2):507-516.
[28]Zhang L M,Lenders P,Knowledge-based eye detection for human face recognition[A],In:Proc.Knowledge-Based Intelligent Engineering Systems and Allied Technologies[C],2000(1):117-120.
[29]Ebisawa Y,Saton S.Effectiveness of pupil area detection tech-nique using two lightsources and images difference method[C].Procof the 15~(th) Annual Int Conference of IEEE Eng in Medicine and Bio-logy Society,1993:1268-1269.
[30]宋加涛,刘济林,池哲儒.人脸正面图像中眼睛的精确定位[J].计算机辅助设计与图形学学报,2005,17(3):540-545.
[31]林维训,潘纲,吴朝晖,潘云鹤.脸部特征定位方法综述.中国图象图形学报,2003,8(8),849-859.
[32]陈春波,王元庆.基于红眼效应的人眼探测.计算机工程与应用,2007,43(9):198-222
[33]周杰,等.基于方向对称变换的人脸定位方法.电子学报,1999,27(8),12-15.
[34]王忠,胡步发,严世榕.一种改进的对称变换应用于人脸图像眼睛定位.计算机应用,2004,24(11).
[35]杜平,张燕昆,刘重庆.基于广义对称变换的人脸检测和面部特征提取.计算机仿真,2003,20(2).
[36]宋海娜,匡纲要,郁文贤.基于对称变换与高斯微分的人脸定位新方法.2003(9).
[37]胡步发,王忠.基于对称变换与自评估的人眼定位新方法.电路与系统学报.2006,11(1).
[38]Arasanathan A,Nishan C.Afine Invariant Feature Extraction Using Symmetry.Second IEEE Workshop on Visual Surveillance Fort Collins,Colorado,1999(6):74-81.
[39]Loy G,Eklundh J O.Detecting Symmetry and Symmetric Constellations of Features.Proceedings of the 12th International Conference on Pattern Recognition,1994:126-131.
[40]Reisfeld D,Wolfsont H,Yeshurun Y.Detection of Interest Points Using Symmetry.Proceedings of the 4th Asian Conference on Computer Vision,1990:62-65.
[41]Reisfeld D,Wolfson H,Yeshurun Y.Context-free attentional operators:the generalizes symmetry transform[J].Computer Vision,1995,14:119-130.
[42]彭进业,俞卞章,王大凯.多尺度对称变换及其应用于定位人脸特征点.电子学报,2002(3).
[43]陈维斌,陈启泉,邱文宇.人脸图像自动检测与识别.计算机应用研究,2003(3).
[44]http://www.uk.research.att.com
[45]Dieckmann U,Plankensteiner P,Schamburger.A biometric person identification system using sensor fusion[C].In:Proceedings of First International Conference of Audio and Video-Based Biometric Person Authentication,1997:301-323.
[46]Karin S,Ioannis P.A fully automatic approach to facial feature detection and tracking[C].Avbpa Department of Informatics,1997:77-84.
[47]辛国江.基于视频的运动物体检测与提取方法研究:(硕士学位论文).湖南:湖南大学,2006.
[48]KanadeT,Picture Processing by computer complex and recognition of human faces [Ph.D.Thesis].Kyoto:Kyoto University,1973.
[49]郑南宁.计算机视觉与模式识别[M].北京:国防工业出版社,1998:45-67.
[50]叶文东,肖刚,程振波等.虹膜定位算法研究.浙江工业大学学报,2004,32(6):714-718
[51]Canny J.A.Computional Approach to Edge detection.IEEE Trans.Pattern Analysis and Machine Intelligence,1986,8(6):679-698.
[52]冈萨雷斯R C著.阮球琦译.数字图像处理学(第二版).北京:电子工业出版社,2001:475-477.
[53]John.G.Daugman.High confidence visual recognition of persons by a test of statistical independence[J].IEEE Tractions on Pat-tern Analysis and Machine Intelligence,1993,15(ll):1148-1161.
[54]何家峰,廖曙铮,叶虎年.虹膜定位[J].中国图像图形学报,2000,5(3):253-255.
[55]Bishop R.Survey of Intelligent Vehicle Applications worldwide[C].Proceedings of the IEEE intelligent Vehicles symposium 2000,25-30.
[56]Dinges D F,Grace R.PERCLOS:A Valid Psycho physiological Measure of Alertness as Assessed by Psychomotor vigilance[R].Washington:Federal Highway Administration,Office of Motor Carriers,1998.
[57]夏芹,宋义伟,朱学峰.基于PERCLOS的驾驶疲劳监控方法进展.自动化技术与应用,2008(11):81-83.
[2]陈艳琴.关于司机疲劳监测的人眼检测与跟踪研究:(硕士学位论文).湖南:中南大学,2004.
[3]Qiang Ji,Zhiwei Zhu,Peilin Lan.Real-Time Nonintrusive Monitoring and Prediction of Driver Fatigue[J].IEEE Transactions on Vehicular Technology,2004,53(4).
[4]Tim H,Laurence H,Gerald P K et al.Fatigue Detection Technologies for Drivers:A Review of Existing Operator-Centred Systems.IEE 2001 Conference Publication,2001,481.
[5]李治春,何仁,林谋有.驾驶员疲劳检测预警技术研究现状及发展趋势.第四届亚太可持续发展交通与环境技术大会,中国西安,2005.
[6]Qiong W,Jingyu Y,MingwuR et al.Driver Fatigue Detection:h Survey.Intelligent Control and Automation,2006,2:8587-8591.
[7]Philip W,Roger D,John M.Development of Driver Alertness Detection System Using Overhead Capacitive Sensor Array.SAE Technical Paper Series 982292,SAE International,1998.
[8]Anneke H,Rainer G,Acacia A.Technologies For The Monitoring and Prevention of Driver Fatigue.Proceedings of the First International Driving Symposium on Human Factor in Driver Assessment,Training and Vehicle Design[C],2001.8.
[9]Fletcher L,Apostoloff N,petersson L.Vision in and out of Vehicles.IEEE Trans.Intelligent Transportation Systems,2003:12-17.
[10]张伦维.疲劳驾驶的克星-防疲劳驾驶系统让驾驶更安全.当代汽车,2008.
[11]盛敬.驾驶员疲劳监控系统中人脸检测与识别研究:(硕士学位论文).辽宁:东北大学,2006.
[12]http://www.safeluck.com/pro_info.asp?id=156
[13]http://www.kj.zjg.gov.cn/Article/ShowArticle.asp?ArticleID=9066
[14]Sung K K,Poggio T.Example-based learning for view-based human face detection.IEEE Transactions on Pattern Analysis and Machine Intelligence.1998,20(1):39-51.
[15]Yang G Z,Huang T S.Human Face Detection in a complex background.Patten Recognition,1994,27(1):53-63.
[16]Yuille A,Hallinan P,Cohen D.Feature Extraction from Faces Using Deformable Templates[J].International Journal of Computer Vision,1992,8(2):99-111.
[17]卢春雨,张长水,闻芳等.基于区域特征的快速人脸检测法[J].清华大学学报(自然科学版),1999,39(1):101-105.
[18]Turk M.and Pentland A.Eigenfaces for Recognition.Journal of Cognitive Neuroscience,1991,3(1):72-86.
[19]王良民,张建明,詹永照等.人脸检测研究现状和发展.江苏大学学报,2003,24(3).
[20]Zhou Q,Aggarwal J.Tracking and classifying moving objects from videos.Proceedings of IEEE Workshop on Performance Evaluation of Tracking and Surveillance,2001.
[21]Stauffer C,Grimson W.Learning patterns of activity using real-time tracking.IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):747-757.
[22]GanderW,Golub G H,Strebel R,et al Least-squares fitting of circles and ellip ses[J].B IT Numerical Mathematics,1994,34(4):558-578.
[23]Rosin P L.Ellipse fitting by accumulating five-point fits[J].Pattern Recognition Letters,1993,14(8):661-669.
[24]邸巍.驾驶员头部检测算法研究:(硕士学位论文).吉林:吉林大学,2007.
[25]Fitzgibbon A,Pile U M,Fisher R B.Direct least square fitting of ellipses[J].Pattern analysis and machine intelligence,1999,21(5):476-480.
[26]Yuille A.L.,Cohen D.S.,Halliman P.W.Feature Extraction From Faces using Deformable Templates[A],In:Proc.Computer Vision and Pattern Recognition[C],1989:104-109.
[27]Fu H C,Lai P S,Lou R Set al,Face Detection and Eye Localization by Neural Network Based Color Segmentation[A],In:Proc.Neural Networks for Signal Processing[C],2000(2):507-516.
[28]Zhang L M,Lenders P,Knowledge-based eye detection for human face recognition[A],In:Proc.Knowledge-Based Intelligent Engineering Systems and Allied Technologies[C],2000(1):117-120.
[29]Ebisawa Y,Saton S.Effectiveness of pupil area detection tech-nique using two lightsources and images difference method[C].Procof the 15~(th) Annual Int Conference of IEEE Eng in Medicine and Bio-logy Society,1993:1268-1269.
[30]宋加涛,刘济林,池哲儒.人脸正面图像中眼睛的精确定位[J].计算机辅助设计与图形学学报,2005,17(3):540-545.
[31]林维训,潘纲,吴朝晖,潘云鹤.脸部特征定位方法综述.中国图象图形学报,2003,8(8),849-859.
[32]陈春波,王元庆.基于红眼效应的人眼探测.计算机工程与应用,2007,43(9):198-222
[33]周杰,等.基于方向对称变换的人脸定位方法.电子学报,1999,27(8),12-15.
[34]王忠,胡步发,严世榕.一种改进的对称变换应用于人脸图像眼睛定位.计算机应用,2004,24(11).
[35]杜平,张燕昆,刘重庆.基于广义对称变换的人脸检测和面部特征提取.计算机仿真,2003,20(2).
[36]宋海娜,匡纲要,郁文贤.基于对称变换与高斯微分的人脸定位新方法.2003(9).
[37]胡步发,王忠.基于对称变换与自评估的人眼定位新方法.电路与系统学报.2006,11(1).
[38]Arasanathan A,Nishan C.Afine Invariant Feature Extraction Using Symmetry.Second IEEE Workshop on Visual Surveillance Fort Collins,Colorado,1999(6):74-81.
[39]Loy G,Eklundh J O.Detecting Symmetry and Symmetric Constellations of Features.Proceedings of the 12th International Conference on Pattern Recognition,1994:126-131.
[40]Reisfeld D,Wolfsont H,Yeshurun Y.Detection of Interest Points Using Symmetry.Proceedings of the 4th Asian Conference on Computer Vision,1990:62-65.
[41]Reisfeld D,Wolfson H,Yeshurun Y.Context-free attentional operators:the generalizes symmetry transform[J].Computer Vision,1995,14:119-130.
[42]彭进业,俞卞章,王大凯.多尺度对称变换及其应用于定位人脸特征点.电子学报,2002(3).
[43]陈维斌,陈启泉,邱文宇.人脸图像自动检测与识别.计算机应用研究,2003(3).
[44]http://www.uk.research.att.com
[45]Dieckmann U,Plankensteiner P,Schamburger.A biometric person identification system using sensor fusion[C].In:Proceedings of First International Conference of Audio and Video-Based Biometric Person Authentication,1997:301-323.
[46]Karin S,Ioannis P.A fully automatic approach to facial feature detection and tracking[C].Avbpa Department of Informatics,1997:77-84.
[47]辛国江.基于视频的运动物体检测与提取方法研究:(硕士学位论文).湖南:湖南大学,2006.
[48]KanadeT,Picture Processing by computer complex and recognition of human faces [Ph.D.Thesis].Kyoto:Kyoto University,1973.
[49]郑南宁.计算机视觉与模式识别[M].北京:国防工业出版社,1998:45-67.
[50]叶文东,肖刚,程振波等.虹膜定位算法研究.浙江工业大学学报,2004,32(6):714-718
[51]Canny J.A.Computional Approach to Edge detection.IEEE Trans.Pattern Analysis and Machine Intelligence,1986,8(6):679-698.
[52]冈萨雷斯R C著.阮球琦译.数字图像处理学(第二版).北京:电子工业出版社,2001:475-477.
[53]John.G.Daugman.High confidence visual recognition of persons by a test of statistical independence[J].IEEE Tractions on Pat-tern Analysis and Machine Intelligence,1993,15(ll):1148-1161.
[54]何家峰,廖曙铮,叶虎年.虹膜定位[J].中国图像图形学报,2000,5(3):253-255.
[55]Bishop R.Survey of Intelligent Vehicle Applications worldwide[C].Proceedings of the IEEE intelligent Vehicles symposium 2000,25-30.
[56]Dinges D F,Grace R.PERCLOS:A Valid Psycho physiological Measure of Alertness as Assessed by Psychomotor vigilance[R].Washington:Federal Highway Administration,Office of Motor Carriers,1998.
[57]夏芹,宋义伟,朱学峰.基于PERCLOS的驾驶疲劳监控方法进展.自动化技术与应用,2008(11):81-83.