基于模式识别的驾驶员疲劳状态检测系统研究
|
摘要
在道路交通事故中,驾驶员疲劳驾驶是重要的原因。如果能在驾驶员出现疲劳状态之前就给驾驶员以及时的预警提醒,那么就可以使驾驶员意识到危险并采取相应的措施避免事故的发生,这是汽车主动安全技术的重要方面,所以对驾驶员疲劳状态检测系统的研究具有重要的理论意义与现实意义。
本文利用模式识别技术,重点利用其在二类问题分类方面的优势,通过分析驾驶员脸部肤色信息特征,提取驾驶员肤色纹理特征构成特征向量匹配分类器完成驾驶员脸部图像的识别,在此基础上构建准则函数分类器实现眼睛定位识别,从而构建了驾驶员疲劳状态检测系统。本文的核心内容包括驾驶员图像的预处理、驾驶员脸部图像识别、驾驶员脸部追踪、驾驶员眼睛定位,并且选择PERCLOS算法最终实现了疲劳状态检测的预警工作。
在驾驶员图像预处理方面利用泛函分析的知识构建了关于真图表面积最小的数学模型实现对驾驶员图像的初步去噪,在此基础上结合形态学腐蚀和膨胀原理完成了驾驶员图像最终去噪工作。为了给后面的眼睛定位工作带来方便,在图像预处理的时候还使用了频域增强、直方图均衡化、傅里叶变换等技术。在驾驶员脸部识别方面提出了利用共生矩阵计算得到的肤色纹理特征构建特征向量匹配分类器的方法将肤色与非肤色进行分类处理,从而实现脸部图像与背景图像的分离;在驾驶员脸部追踪方面利用了camshift算法使得即使在驾驶员头部轻微运动的情况下也能很好的跟踪识别出驾驶员的脸部图像。
在驾驶员眼睛定位方面利用纹理特征向量构建了准则函数分类器,并且综合利用了Tanimoto测度的原理最终实现了驾驶员眼睛的识别;最终应用PERCLOS算法完成了驾驶员疲劳状态检测系统的研究。
最后,文章对驾驶员疲劳状态检测系统进行了置信度分析,包括识别能力和计算复杂度;还利用ROC曲线对系统进行了有效性验证,结果表明系统基本符合要求。
Driver’s fatigue driving is an important reason in the traffic accidents. If we can give the driver warning in time, they can be aware of the dangers and take the according measures to avoid the accidents; this is also an important part of automotive positive safety technology. So, it is very important to study the driver fatigue detection system no matter in theory or practice.
This paper takes advantage of pattern recognition especially in dichotomizer to gain the skin vein character based on analyzing driver’s face character and construct the classifier to recognize the face of driver; and then driver’s eye is recognized through functional classifier and pattern recognition technology. At last, the driver fatigue detect system is completed. The centre content of this paper includes image processing, face recognition, tracing face and eye recognition; the PERCLOS algorithm is chosen to realize the driver fatigue detect system.
The functional analysis is combined with the morphology to get rid of image noise. During the image processing, enhanced frequency, histogram equalization and Fourier transform are used for convenient of eye recognition.
Taking advantage of character vector classifier based on Co-occurrence Matrix Algorithm to distinguish the color of skin and others; and then the face image and the background are separated. Because Camshift algorithm is chosen to realize face tracking, the moving driver face is recognized.
The function classifier and the tanimoto measure are used to get the eye of driver. In the end, the driver fatigue detect system is finished by PERCLOS algorithm.
At last, the error evaluation is analyzed; including recognition ability and computational complexity, and also the system’s accuracy is checked by ROC curve, the result is satisfying.
本文利用模式识别技术,重点利用其在二类问题分类方面的优势,通过分析驾驶员脸部肤色信息特征,提取驾驶员肤色纹理特征构成特征向量匹配分类器完成驾驶员脸部图像的识别,在此基础上构建准则函数分类器实现眼睛定位识别,从而构建了驾驶员疲劳状态检测系统。本文的核心内容包括驾驶员图像的预处理、驾驶员脸部图像识别、驾驶员脸部追踪、驾驶员眼睛定位,并且选择PERCLOS算法最终实现了疲劳状态检测的预警工作。
在驾驶员图像预处理方面利用泛函分析的知识构建了关于真图表面积最小的数学模型实现对驾驶员图像的初步去噪,在此基础上结合形态学腐蚀和膨胀原理完成了驾驶员图像最终去噪工作。为了给后面的眼睛定位工作带来方便,在图像预处理的时候还使用了频域增强、直方图均衡化、傅里叶变换等技术。在驾驶员脸部识别方面提出了利用共生矩阵计算得到的肤色纹理特征构建特征向量匹配分类器的方法将肤色与非肤色进行分类处理,从而实现脸部图像与背景图像的分离;在驾驶员脸部追踪方面利用了camshift算法使得即使在驾驶员头部轻微运动的情况下也能很好的跟踪识别出驾驶员的脸部图像。
在驾驶员眼睛定位方面利用纹理特征向量构建了准则函数分类器,并且综合利用了Tanimoto测度的原理最终实现了驾驶员眼睛的识别;最终应用PERCLOS算法完成了驾驶员疲劳状态检测系统的研究。
最后,文章对驾驶员疲劳状态检测系统进行了置信度分析,包括识别能力和计算复杂度;还利用ROC曲线对系统进行了有效性验证,结果表明系统基本符合要求。
Driver’s fatigue driving is an important reason in the traffic accidents. If we can give the driver warning in time, they can be aware of the dangers and take the according measures to avoid the accidents; this is also an important part of automotive positive safety technology. So, it is very important to study the driver fatigue detection system no matter in theory or practice.
This paper takes advantage of pattern recognition especially in dichotomizer to gain the skin vein character based on analyzing driver’s face character and construct the classifier to recognize the face of driver; and then driver’s eye is recognized through functional classifier and pattern recognition technology. At last, the driver fatigue detect system is completed. The centre content of this paper includes image processing, face recognition, tracing face and eye recognition; the PERCLOS algorithm is chosen to realize the driver fatigue detect system.
The functional analysis is combined with the morphology to get rid of image noise. During the image processing, enhanced frequency, histogram equalization and Fourier transform are used for convenient of eye recognition.
Taking advantage of character vector classifier based on Co-occurrence Matrix Algorithm to distinguish the color of skin and others; and then the face image and the background are separated. Because Camshift algorithm is chosen to realize face tracking, the moving driver face is recognized.
The function classifier and the tanimoto measure are used to get the eye of driver. In the end, the driver fatigue detect system is finished by PERCLOS algorithm.
At last, the error evaluation is analyzed; including recognition ability and computational complexity, and also the system’s accuracy is checked by ROC curve, the result is satisfying.
引文
[1]中华人民共和国国家统计局.《中国统计年鉴》[M].北京:中国统计出版社,2009:125-130.
[2] R,J. Technical Conference on Proceedings FHWA Technical Report [C]. Federal Highway Administration,1997:132-133.
[3] Randell. A tool to improve driving safety [J]. society of automotive engineers. 2006:35-70.
[4] Transport Research laboratory. Driver fatigue-a kill on the roads [J]. Loughborough University. 2006:231-233.
[5] S,A. Nobe,F.Y.Wang. An Overview of Recent Developments in Automated lateral and longitudinal Vehicle controls [C]. IEEE International conference on SMC. 2001:3337-3352.
[6] Knipling, R.R.,Wang J.S.&Kanianthra, J.N. Current NHTSA drowsy driver R&D [C]. Proceedings of the fifteenths International Conference on the enhanced safety of vehicles. Melbourne, Australia. 1996:332-331.
[7] Carrol, R.J.Ocular Measures of Driver Alertness [C]. Federal Highway Administration. Technical Conference on Proceedings FHWA Technical Report,Washington, DC,1999. Federal Highway Administration:521-523.
[8]于兴玲,王民,张立才.基于PERCLOS的驾驶员眼睛状态检测方法[J].微型计算机信息,2007:119-122.
[9]陈勇飞,刘新明.基于肤色和类Harr特征的人脸图像的人眼检测[J].计算机工程与应用,2008,33(33):173-176.
[10]钟国,钟幼强,金施群.基于红外差分图像的驾驶员疲劳检测系统[J].现代显示,2008:31-35.
[11]石坚,吴远鹏,卓斌.汽车驾驶员主动安全性因素的辨识与分析[J].上海交通大学学报,2000:331-333.
[12]杨渝书.驾驶疲劳的人机工程学分析和定量评价实验研究[J].上海交通大学学报,2002:103-107.
[13]蔡笑岳.驾驶心理学[M].北京:中国劳动出版社,1998:201-213.
[14]郑培.机动车驾驶员驾驶疲劳测评方法的研究[D].北京:中国农业大学车辆工程学科博士学位论文,2001:30-32.
[15]李志春.驾驶员疲劳状态检测技术研究与工程实现[D].江苏:江苏大学车辆工程学科博士学位论文,2008:15-17.
[16]江水郎,杨明.面向驾驶员疲劳检测的双空间人眼定位方法[J].计算机工程,2008,33(23):180-181.
[17]钟国.驾驶疲劳检测技术的研究[D].安徽:合肥工业大学精密仪器及机械学科硕士学位论文,2009:37-39.
[18]黄瀚敏.基于汽车驾驶员疲劳状态监测技术的汽车主动安全系统研究[D].重庆:重庆大学控制理论与控制工程学科博士学位论文,2007:71-73.
[19]刘松岩.基于计算机视觉的驾驶员驾驶疲劳监测系统的设计[D].河北:燕山大学检测技术与自动化装置学科硕士学位论文,2009:38-32.
[20] Keating C F, Keating E G. Monkeys and Mug Shots Cues Used By Rhesus monkeys (Macaca mulatta) To Recognize a Human Face [J]. Comparative Psychology, 1993, 107(2):131-139.
[21] Gerry E.Warning System for Fatigued Drivers Nearing Reality with New Eye Data [N]. Science Daily, 1999.7.27.
[22] LIJ CHENG, CHIZ. A Fuzzy Image Metric With Application to Fractal Coding [J]. IEEE Transactions on Image Processing, 2002, 11(6):636-633.
[23] FISHER Y. Fractal Image Compression-Theory and Application [J]. New York Springer, 1993:18-21.
[24]周玉斌,俞梦孙.疲劳驾驶检测方法的研究[J].医疗卫生装备,2003,23(6):25-28.
[25] BO MAN O, IRANIM. Detecting Irregularities in Images and in Video [J]. International Journal of Computer Vision, 2005, 73(1):17-31.
[26] Drowsy. Driver Monitor and Warning System [R]. Richard Grace Robotics Institute.Carnegie Mellon University.Pittsburgh, Pennsylvania.
[27] Barron J, Fleet D, Beauchemin. Performance of optical Flow techniques [J]. International Journal of Computer Vision, 1993, 12(1):33-77.
[28] Saroj KLLal, Ashley Craig. Physiological Indicators of Driver Fatigue [J]. 2000Road safety Research, Policing&Education Conference:137-139.
[29] Lee W.S, Magnenat, Thalmann. Fast head modeling for animation [J]. Image and Vision Computing, 2000, 18(7):355-363.
[30] M.Kass, A.Witlcin, D. Terzopoulos. Snake: Active Contour Models [J]. International Journal of Computer Vision, 1998:321-331.
[31] Anneke H, Rainer G, Acacia A. Technologies for the Monitoring and Prevention of Driver Fatigue [J]. Traing and Vehicle Design, 2001:81-86.
[32] Kyung-min cho, Jeong-hun Jang, Ki-sang Hong. Adaptive skin-color Filter [J].Pattern Recognition, 2001:1067-1073.
[33] Shen Chen, Shen Xian Yang, Ma Song De. A Survey of Image Based illumination Model [J]. Chinese Journal of Computers, 2000, 23(12):1-9.
[34] Shafer S.A. Using color to Separate reflection components [J]. Color Research Application, 1985, 10(3):210-218.
[35] L.Bar, N.Kiryati, N.Sochen. Image deblurring in the presence of impulsive noise [J]. International Journal of Computer Vision, 2006, 70(3):279-298.
[36] T.Chan, C.Wong. Total variation blind disconsolation [J]. IEEE Transactions on Image Processing, 1998, 7(3):370-395.
[37]苏鹏宇,任艳宏,徐丹.基于视频图像的人脸定位方法[J].云南大学学报,2007, 29(s2):223-227.
[38]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].计算机应用与软件,2009, 26(1):233-235.
[39]胡德轩,冯玉田,宁萍强.一种有效的用于疲劳驾驶检测的人眼定位算法[J].计算机技术与发展,2009, 19(12):10-12.
[40]刘瑞华.数字图像去模糊的理论研究及应用[D].上海:华东师范大学基础数学学科博士学位论文,2008:1-11.
[41] Anneke Heitmann, Rainer Guttkuhn. Technologies for the Monitoring and Prevention of Driver Fatigue [J]. Training and Vehicle Design, 2000:81-86.
[42] Mailis, M. Experiment on Performance-Based Validation of Fatigue-Tracking Technologies [D]. Evaluation of Techniques for Drowsiness Detection, Drexel University, Philadelphia, PA. 1997:71-73.
[43] BOMANO, IRANIM. Detecting irregularities in images and in video [J]. International Journal of Computer Vision, 2005, 74(1):16-20.
[44] RAOS, SASTRYPS. Abnormal activity Detection in video sequences using leant probability densities [J]. Conference on Convergent Technologies for Asia Pacific Region, 2003:369-371.
[45] WUXY, QANHH. A detection system for human abnormal behavior [J]. IEEE International Conference on Intelligent Robots and Systems, 2005:1204-1206.
[2] R,J. Technical Conference on Proceedings FHWA Technical Report [C]. Federal Highway Administration,1997:132-133.
[3] Randell. A tool to improve driving safety [J]. society of automotive engineers. 2006:35-70.
[4] Transport Research laboratory. Driver fatigue-a kill on the roads [J]. Loughborough University. 2006:231-233.
[5] S,A. Nobe,F.Y.Wang. An Overview of Recent Developments in Automated lateral and longitudinal Vehicle controls [C]. IEEE International conference on SMC. 2001:3337-3352.
[6] Knipling, R.R.,Wang J.S.&Kanianthra, J.N. Current NHTSA drowsy driver R&D [C]. Proceedings of the fifteenths International Conference on the enhanced safety of vehicles. Melbourne, Australia. 1996:332-331.
[7] Carrol, R.J.Ocular Measures of Driver Alertness [C]. Federal Highway Administration. Technical Conference on Proceedings FHWA Technical Report,Washington, DC,1999. Federal Highway Administration:521-523.
[8]于兴玲,王民,张立才.基于PERCLOS的驾驶员眼睛状态检测方法[J].微型计算机信息,2007:119-122.
[9]陈勇飞,刘新明.基于肤色和类Harr特征的人脸图像的人眼检测[J].计算机工程与应用,2008,33(33):173-176.
[10]钟国,钟幼强,金施群.基于红外差分图像的驾驶员疲劳检测系统[J].现代显示,2008:31-35.
[11]石坚,吴远鹏,卓斌.汽车驾驶员主动安全性因素的辨识与分析[J].上海交通大学学报,2000:331-333.
[12]杨渝书.驾驶疲劳的人机工程学分析和定量评价实验研究[J].上海交通大学学报,2002:103-107.
[13]蔡笑岳.驾驶心理学[M].北京:中国劳动出版社,1998:201-213.
[14]郑培.机动车驾驶员驾驶疲劳测评方法的研究[D].北京:中国农业大学车辆工程学科博士学位论文,2001:30-32.
[15]李志春.驾驶员疲劳状态检测技术研究与工程实现[D].江苏:江苏大学车辆工程学科博士学位论文,2008:15-17.
[16]江水郎,杨明.面向驾驶员疲劳检测的双空间人眼定位方法[J].计算机工程,2008,33(23):180-181.
[17]钟国.驾驶疲劳检测技术的研究[D].安徽:合肥工业大学精密仪器及机械学科硕士学位论文,2009:37-39.
[18]黄瀚敏.基于汽车驾驶员疲劳状态监测技术的汽车主动安全系统研究[D].重庆:重庆大学控制理论与控制工程学科博士学位论文,2007:71-73.
[19]刘松岩.基于计算机视觉的驾驶员驾驶疲劳监测系统的设计[D].河北:燕山大学检测技术与自动化装置学科硕士学位论文,2009:38-32.
[20] Keating C F, Keating E G. Monkeys and Mug Shots Cues Used By Rhesus monkeys (Macaca mulatta) To Recognize a Human Face [J]. Comparative Psychology, 1993, 107(2):131-139.
[21] Gerry E.Warning System for Fatigued Drivers Nearing Reality with New Eye Data [N]. Science Daily, 1999.7.27.
[22] LIJ CHENG, CHIZ. A Fuzzy Image Metric With Application to Fractal Coding [J]. IEEE Transactions on Image Processing, 2002, 11(6):636-633.
[23] FISHER Y. Fractal Image Compression-Theory and Application [J]. New York Springer, 1993:18-21.
[24]周玉斌,俞梦孙.疲劳驾驶检测方法的研究[J].医疗卫生装备,2003,23(6):25-28.
[25] BO MAN O, IRANIM. Detecting Irregularities in Images and in Video [J]. International Journal of Computer Vision, 2005, 73(1):17-31.
[26] Drowsy. Driver Monitor and Warning System [R]. Richard Grace Robotics Institute.Carnegie Mellon University.Pittsburgh, Pennsylvania.
[27] Barron J, Fleet D, Beauchemin. Performance of optical Flow techniques [J]. International Journal of Computer Vision, 1993, 12(1):33-77.
[28] Saroj KLLal, Ashley Craig. Physiological Indicators of Driver Fatigue [J]. 2000Road safety Research, Policing&Education Conference:137-139.
[29] Lee W.S, Magnenat, Thalmann. Fast head modeling for animation [J]. Image and Vision Computing, 2000, 18(7):355-363.
[30] M.Kass, A.Witlcin, D. Terzopoulos. Snake: Active Contour Models [J]. International Journal of Computer Vision, 1998:321-331.
[31] Anneke H, Rainer G, Acacia A. Technologies for the Monitoring and Prevention of Driver Fatigue [J]. Traing and Vehicle Design, 2001:81-86.
[32] Kyung-min cho, Jeong-hun Jang, Ki-sang Hong. Adaptive skin-color Filter [J].Pattern Recognition, 2001:1067-1073.
[33] Shen Chen, Shen Xian Yang, Ma Song De. A Survey of Image Based illumination Model [J]. Chinese Journal of Computers, 2000, 23(12):1-9.
[34] Shafer S.A. Using color to Separate reflection components [J]. Color Research Application, 1985, 10(3):210-218.
[35] L.Bar, N.Kiryati, N.Sochen. Image deblurring in the presence of impulsive noise [J]. International Journal of Computer Vision, 2006, 70(3):279-298.
[36] T.Chan, C.Wong. Total variation blind disconsolation [J]. IEEE Transactions on Image Processing, 1998, 7(3):370-395.
[37]苏鹏宇,任艳宏,徐丹.基于视频图像的人脸定位方法[J].云南大学学报,2007, 29(s2):223-227.
[38]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].计算机应用与软件,2009, 26(1):233-235.
[39]胡德轩,冯玉田,宁萍强.一种有效的用于疲劳驾驶检测的人眼定位算法[J].计算机技术与发展,2009, 19(12):10-12.
[40]刘瑞华.数字图像去模糊的理论研究及应用[D].上海:华东师范大学基础数学学科博士学位论文,2008:1-11.
[41] Anneke Heitmann, Rainer Guttkuhn. Technologies for the Monitoring and Prevention of Driver Fatigue [J]. Training and Vehicle Design, 2000:81-86.
[42] Mailis, M. Experiment on Performance-Based Validation of Fatigue-Tracking Technologies [D]. Evaluation of Techniques for Drowsiness Detection, Drexel University, Philadelphia, PA. 1997:71-73.
[43] BOMANO, IRANIM. Detecting irregularities in images and in video [J]. International Journal of Computer Vision, 2005, 74(1):16-20.
[44] RAOS, SASTRYPS. Abnormal activity Detection in video sequences using leant probability densities [J]. Conference on Convergent Technologies for Asia Pacific Region, 2003:369-371.
[45] WUXY, QANHH. A detection system for human abnormal behavior [J]. IEEE International Conference on Intelligent Robots and Systems, 2005:1204-1206.
© 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 |