基于可拓学与面部视觉特征的精神疲劳识别研究
|
摘要
随着脑力劳动在人类生产生活中所占的比重越来越大,精神疲劳所产生的负面影响也越来越大,涉及到社会经济、军事和日常生活等各个方面。信息技术的发展,为人体精神疲劳的动态测量和实时分析提供了可能。基于计算机视觉技术,以面部视频为基础,融合多种特征对驾驶疲劳进行非侵扰式识别已经取得了一些成果。但基于面部视觉特征的精神疲劳识别,目前研究还不多,主要存在两大难题需要解决,一是研究更有效的精神疲劳面部视觉特征,并提高特征提取的准确性；二是如何使多特征融合过程中的不相容问题形式化,建立问题求解的形式化过程,进而通过计算机自动智能地找到多特征融合的最优策略和方法。
本文围绕上述问题进行了研究,主要研究工作如下：
1、基于面部视觉特征的精神疲劳识别可拓模型研究
对人体精神疲劳的概念进行了界定,明确了本文的研究目标。分析了基于面部视觉特征进行精神疲劳识别中存在的不相容问题,研究了求解矛盾问题的可拓策略生成的一般方法,建立了精神疲劳识别的基元和基元拓展模型,研究了精神疲劳识别的可拓策略,建立了精神疲劳识别的可拓模型。
2、精神疲劳面部动态特征研究与识别
针对现有面部视觉特征提取方法中存在的无法对大角度的头部旋转和倾斜以及头发遮挡等情况进行有效处理的问题,研究了人眼、虹膜及嘴巴的定位与疲劳特征提取方法,提出了一种实时有效的虹膜分割与眨眼参数计算方法和基于嘴唇内轮廓特征点曲线拟合的张口度获取方法。
针对基于眨眼参数与张口度阈值法判别疲劳存在的适应性差,容易受到眨眼习惯、年龄、嘴巴大小和嘴唇厚度影响等问题,研究了不同年龄人群的眨眼参数的统计分布特性,提出了基于眨眼参数FR模型数字特征进行精神疲劳识别的方法,和结合张口度与张口持续时间双阈值进行哈欠判别的方法。
针对眨眼参数FR模型数字特征对精神疲劳的过渡状态识别率不高、双阈值法哈欠检测无法区别深哈欠和浅哈欠等问题,在研究时间序列及其分类算法的基础上,以眨眼持续时间为基础,构建了一种BD-时间序列,提出了相应的分段方法和HMM时序分类算法；以张口度为基础,构建了一种M-时间序列,提出了相应的分段和分类方法,提高了精神疲劳过渡状态的识别率,并能够对不同疲劳状态的哈欠进行区别。
3、精神疲劳的面部慢性疲态特征研究与识别
与中医科专家对工作生活压力等导致的伴有严重睡眠障碍的慢性疲劳(SD_CFS)者的面部视频进行研究后发现：SD CFS者存在肤色暗淡、卧蚕突出、印堂“川”字形纹理和嘴角下压等面部慢性疲态特征,提出了特征提取、融合、降维和面部慢性疲态识别的方法,为被测者工作生活压力信息的非侵扰式自动获取提供了一种有效的途径。
4、分层多特征多方法可拓融合的精神疲劳识别分析了本文所提出的各种精神疲劳面部特征与识别方法的优势和不足,以及多特征多方法融合过程中存在的矛盾,提出了一种分层多方法多特征可拓融合进行精神疲劳识别的方法。按照单特征、双特征、多特征分层给出了各层可拓融合的思路与机制、模态的定义、模态切换的规则和矛盾裁决的方法。
论文最后进行了总结,介绍了主要研究成果及创新点,指出了进
一步的研究方向。
With the increasing proportion of mental work in the human production and life, the negative effects arising from mental fatigue are growing, and involved inalmost every aspects ofsocio-economic, military, and daily life. Development of information technology makes it possible to perform real-time mental fatigue recognition. Multi-feature fusion non-intrusive recognition of driver fatigue based on facial visual cues and computer vision technology has achieved some results.However, facial visual cues based mental fatigue recognition faces two major challenges. The first one is thatmore effective mental fatigue facial visual cues should be studied, and the accuracy of the feature extraction must be improved. The second one is that we should find the way to formalizing contradiction problems existed in multi-feature fusion process, establish the formal solution model of contradiction problems, so we can use computer to automaticallyand intelligently find the optimal strategies and methods for multi-feature fusion.
This dissertationfocuses on the above issues to study, and the main research work are as follows:
1. Research of mental fatigue recognition extension model based on facial visual cues
The concept of human mental fatigue was defined to identifytheresearch target of this dissertation. Theincompatible problems existed in facial visual cues based mental fatigue recognition were analyzed, the general method to generate extension strategy for solving contradictions problems was introduced. Accordingly, this dissertation established the extension model for mental fatigue recognition, and the basic-element and extension model, extension strategy for the basic-element were studied.
2. Research of dynamic facial features based mental fatigue recognition
For the existing facial visual feature extraction methodscannot effectively deal with the large angle of head rotation and tilt, as well as hair cover, this dissertation proposed apractical iris segmentationand blink parameters calculation method, and a mouth inner contour corner point curve fitting based mouth open degree calculation method.
For the blink parameters threshold based mental fatigue recognition methods are susceptible to blink habits and age, and have poor adaptability, this dissertation proposed a mental fatigue recognition method base on theFRdigitalfeatures of the blink parameters according to the statistical features of blink parameters for different age groups. For the mouth open degree thresholdbased mental fatigue recognition methods are susceptible to size of the mouth and thickness of thelips, this dissertation proposed a yawning detection method based on dual-threshold of mouth open degree and mouth open duration.
For the recognition rate of mentalfatigue transition stage is not high based on theFR digitalfeatures of the blink parameters, this dissertation established a BD-time series based on blink duration,and proposed a segmentation method and a HMM based classification method for it. For the dual-threshold based yawning detection cannot distinguish deep yawn and light yawn, this dissertation established a M-time series based on mouth open degree and duration, and proposed a segmentation and classification method for it. Our methods improve the recognition accuracy of the transition stage and can distinguish yawning of different mental fatigue degree.
3. Research and recognition of the chronic facial fatiguefeatures of mental fagtigue
After a long time observation of the facial videos from the Sleep Disordered Chronic Fatigue Syndrome(SD_CFS) patients, whose CFS are mainly caused by work and life stress, we found that the SD_CFS patients have the chronic facial fatigue appearance, such as looking bleak, the sleep silkworm is prominent, frowning, and curl the lips. So, this dissertation proposed the feature extraction,feature fusion,feature selection and classification method for the chronic facial fatigue appearance,therefore provides an feasible way to non-intrusively estimate work and life stress.
4. Mental fatigue recognition based on hierarchical extension fusion of multi-featuresand multi-methods
This dissertation proposed a mental fatigue recognition method based on hierarchical extension fusion of multi-features and multi-methods after analyzingthe advantages and disadvantages of the mental fatigue features and recognition methods proposed above. From the single feature layer, dual-feature layer to multi-feature layer, this dissertation dissertate the ideal and mechanism of extension fusion, the definition of mode, mode switching rules, contradiction judge method in each layer hierarchically.
This dissertation finally summarized its main research results and innovations, pointed out the future research directions.
本文围绕上述问题进行了研究,主要研究工作如下：
1、基于面部视觉特征的精神疲劳识别可拓模型研究
对人体精神疲劳的概念进行了界定,明确了本文的研究目标。分析了基于面部视觉特征进行精神疲劳识别中存在的不相容问题,研究了求解矛盾问题的可拓策略生成的一般方法,建立了精神疲劳识别的基元和基元拓展模型,研究了精神疲劳识别的可拓策略,建立了精神疲劳识别的可拓模型。
2、精神疲劳面部动态特征研究与识别
针对现有面部视觉特征提取方法中存在的无法对大角度的头部旋转和倾斜以及头发遮挡等情况进行有效处理的问题,研究了人眼、虹膜及嘴巴的定位与疲劳特征提取方法,提出了一种实时有效的虹膜分割与眨眼参数计算方法和基于嘴唇内轮廓特征点曲线拟合的张口度获取方法。
针对基于眨眼参数与张口度阈值法判别疲劳存在的适应性差,容易受到眨眼习惯、年龄、嘴巴大小和嘴唇厚度影响等问题,研究了不同年龄人群的眨眼参数的统计分布特性,提出了基于眨眼参数FR模型数字特征进行精神疲劳识别的方法,和结合张口度与张口持续时间双阈值进行哈欠判别的方法。
针对眨眼参数FR模型数字特征对精神疲劳的过渡状态识别率不高、双阈值法哈欠检测无法区别深哈欠和浅哈欠等问题,在研究时间序列及其分类算法的基础上,以眨眼持续时间为基础,构建了一种BD-时间序列,提出了相应的分段方法和HMM时序分类算法；以张口度为基础,构建了一种M-时间序列,提出了相应的分段和分类方法,提高了精神疲劳过渡状态的识别率,并能够对不同疲劳状态的哈欠进行区别。
3、精神疲劳的面部慢性疲态特征研究与识别
与中医科专家对工作生活压力等导致的伴有严重睡眠障碍的慢性疲劳(SD_CFS)者的面部视频进行研究后发现：SD CFS者存在肤色暗淡、卧蚕突出、印堂“川”字形纹理和嘴角下压等面部慢性疲态特征,提出了特征提取、融合、降维和面部慢性疲态识别的方法,为被测者工作生活压力信息的非侵扰式自动获取提供了一种有效的途径。
4、分层多特征多方法可拓融合的精神疲劳识别分析了本文所提出的各种精神疲劳面部特征与识别方法的优势和不足,以及多特征多方法融合过程中存在的矛盾,提出了一种分层多方法多特征可拓融合进行精神疲劳识别的方法。按照单特征、双特征、多特征分层给出了各层可拓融合的思路与机制、模态的定义、模态切换的规则和矛盾裁决的方法。
论文最后进行了总结,介绍了主要研究成果及创新点,指出了进
一步的研究方向。
With the increasing proportion of mental work in the human production and life, the negative effects arising from mental fatigue are growing, and involved inalmost every aspects ofsocio-economic, military, and daily life. Development of information technology makes it possible to perform real-time mental fatigue recognition. Multi-feature fusion non-intrusive recognition of driver fatigue based on facial visual cues and computer vision technology has achieved some results.However, facial visual cues based mental fatigue recognition faces two major challenges. The first one is thatmore effective mental fatigue facial visual cues should be studied, and the accuracy of the feature extraction must be improved. The second one is that we should find the way to formalizing contradiction problems existed in multi-feature fusion process, establish the formal solution model of contradiction problems, so we can use computer to automaticallyand intelligently find the optimal strategies and methods for multi-feature fusion.
This dissertationfocuses on the above issues to study, and the main research work are as follows:
1. Research of mental fatigue recognition extension model based on facial visual cues
The concept of human mental fatigue was defined to identifytheresearch target of this dissertation. Theincompatible problems existed in facial visual cues based mental fatigue recognition were analyzed, the general method to generate extension strategy for solving contradictions problems was introduced. Accordingly, this dissertation established the extension model for mental fatigue recognition, and the basic-element and extension model, extension strategy for the basic-element were studied.
2. Research of dynamic facial features based mental fatigue recognition
For the existing facial visual feature extraction methodscannot effectively deal with the large angle of head rotation and tilt, as well as hair cover, this dissertation proposed apractical iris segmentationand blink parameters calculation method, and a mouth inner contour corner point curve fitting based mouth open degree calculation method.
For the blink parameters threshold based mental fatigue recognition methods are susceptible to blink habits and age, and have poor adaptability, this dissertation proposed a mental fatigue recognition method base on theFRdigitalfeatures of the blink parameters according to the statistical features of blink parameters for different age groups. For the mouth open degree thresholdbased mental fatigue recognition methods are susceptible to size of the mouth and thickness of thelips, this dissertation proposed a yawning detection method based on dual-threshold of mouth open degree and mouth open duration.
For the recognition rate of mentalfatigue transition stage is not high based on theFR digitalfeatures of the blink parameters, this dissertation established a BD-time series based on blink duration,and proposed a segmentation method and a HMM based classification method for it. For the dual-threshold based yawning detection cannot distinguish deep yawn and light yawn, this dissertation established a M-time series based on mouth open degree and duration, and proposed a segmentation and classification method for it. Our methods improve the recognition accuracy of the transition stage and can distinguish yawning of different mental fatigue degree.
3. Research and recognition of the chronic facial fatiguefeatures of mental fagtigue
After a long time observation of the facial videos from the Sleep Disordered Chronic Fatigue Syndrome(SD_CFS) patients, whose CFS are mainly caused by work and life stress, we found that the SD_CFS patients have the chronic facial fatigue appearance, such as looking bleak, the sleep silkworm is prominent, frowning, and curl the lips. So, this dissertation proposed the feature extraction,feature fusion,feature selection and classification method for the chronic facial fatigue appearance,therefore provides an feasible way to non-intrusively estimate work and life stress.
4. Mental fatigue recognition based on hierarchical extension fusion of multi-featuresand multi-methods
This dissertation proposed a mental fatigue recognition method based on hierarchical extension fusion of multi-features and multi-methods after analyzingthe advantages and disadvantages of the mental fatigue features and recognition methods proposed above. From the single feature layer, dual-feature layer to multi-feature layer, this dissertation dissertate the ideal and mechanism of extension fusion, the definition of mode, mode switching rules, contradiction judge method in each layer hierarchically.
This dissertation finally summarized its main research results and innovations, pointed out the future research directions.
引文
[1]曹炜.基于机器视觉的驾驶疲劳识别研究[D].南京：东南大学,2008.
[2]曹雪亮.脑力疲劳的注意特征及主观评定方法的实验研究[D].西安：第四军医大学,2003.
[3]径卫视觉科技.疲劳驾驶侦测系统发展状况分析[DB/OL]. http://www.roadefend.com/xinwenzhongxin/gongsixinwen/38.html.
[4]李永平.脉搏图像化检测方法对精神疲劳状态的识别[D].兰州：兰州理工大学,2008.
[5]陈云华,余永权,张灵,丁伍洋.基于面部视觉特征的精神疲劳可拓辨识模型.计算机科学.2013,2(40)：284-288.
[6]邓金城.基于人脸识别技术的驾驶员疲劳识别方法研究[D].重庆：重庆大学,2005.
[7]朱炳初,汪丰.疲劳识别研究现状与发展[DB\OL].中国科技论文在线.http://www.paper.edu.cn.
[8]Skosnik PD, Chatterton RT,S wisher T,Park S:Modulation of attentional inhibition by norepinephrine andcortisol after psychological stress [J]. International Journal of Psychophysiology,2000,36:59-68.
[9]江北,聂东.大学生上网导致CFF降低的研究[J].中国校医,2008,22(3)：272-273.
[10]Dinges DF, Powell JW. Microcomputer analysis of performance on a portable, simple visual ART taskduring sustained operations. Behavior Research Methods, Instruments and Computers 1985,17:652-655.
[11]Johns MW, et al. Eyelid Closure, Visual Suppression and Hypo vigilance in the Drowsy State:Lapses inPerformance With Eyes Open or Closed. Epworth Sleep Centre, Melbourne, Australia,2003.
[12]王楠,杨凯,沈莹.飞行员视觉神经行为功能测试系统[J].现代电子技术,2007,3：96-99.
[13]H. P. Greeley, S. Raghavan,J. Berg etc. Detecting Fatigue From Voice UsingSpeech Recognition[C]. Proceedings of 2006 IEEE International Symposium on Signal Processing and Information Technology, Vancouver, Canada,2006:567-571.
[14]张志斌.基于计算机视觉的驾驶员疲劳实时检测研究[D].北京：北京工业大学,2008.
[15]Qiang Ji, Peilin Lan, and Carl Looney.A Probabilistic Framework for Modeling and Real-Time Recognition Human Fatigue[J]. IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS,PART A: SYSTEMS AND HUMANS.2006,36 (5):862-875.
[16]Yang,G, Lin,Y.,Bhattacharya,P.:A driver fatigue recognition model using fusion of multiplefeatures[C],2005 IEEE International Conference on Systems,Man and Cybernetics,2005(2):1777-1784.
[17]Ji Q, Zhu Z W, Lan P L. Real-Time Nonintrusive Recognition and Prediction of Driver Fatigue[J]. IEEE Transaction on Vehicular Technology,2004,53(4):1052-1068.
[18]尹兵.基于红外技术的驾驶员脸部识别研究[D].吉林：吉林大学,2008.
[19]王磊,吴晓娟等.驾驶疲劳/瞌睡检测方法的研究进展[J].生物医学工程学杂志.2007,24(1)：245-248.
[20]Wen-Bing Horng, Chih-Yuan Chen, Yi Chang etc. Driver Fatigue Detection Based on Eye Tracking and Dynamic Template Matching[J].Proceedings of the 2004 IEEE International Conference on Networking,Sensing & Control, Taipei, Taiwan,2004:7-12.
[21]G.Y. Zhang, B. Cheng, R.J. Feng, X.B. Zhang, A Real-Time Adaptive Learning Method for Driver Eye Detection, Proceedings of Digital Image Computing:Techniques and Applications.2008:300-304.
[22]王琼,王欢,赵春霞等.基于眼睛状态识别的驾驶员疲劳识别[J].南京理工大学学报(自然科学版).2010,34(4)：448-453.
[23]江水郎,杨明.面向驾驶员疲劳识别的双空间人眼定位方法[J].计算机工程,2008,34(24)：180-182.
[24]Mandalapu Sarada Devi,Preeti R Bajaj.Driver Fatigue Detection Based on Eye Tracking[C]. Proceedings of 1th International Conference on Emerging Trends in Engineering and Technology.2008:649-652.
[25]Tayyaba Azim,M.Arfan Jaffa,Anwar Majid Mirza. Automatic Fatigue Detection of Drivers through Pupil Detection and YawningAnalysis[C]. Proceedings of 4th International Conference on Innovative Computing, Information and Control.2009:441-445.
[26]Ji Q, Yang X, Real time visual cues extraction for recognition driver vigilance[C].//Lecture Notes presented at the Proc. Int. Workshop Computer Vision Systems. Vancouver, Canada:Springer,2001:107-124.
[27]Lu Yufeng,Wang zengcai. Detecting Driver Yawning in Successive Images[C].Wuhan, China. In:Proc. of 1st International Conferrence on Bioinformatics and Biomedical Engineering,2007:581-583
[28]Shabnam Abtahi, Behnoosh Hariri, Shervin Shirmo hammadi. Driver Drowsiness Recognition based on Yawning Detection[C]. Hangzhou, China. International Instrumentation and Measurement Technology Conference,2011:1606-1610.
[29]M.Omidyeganeh, A.Javadtalab, S.Shirm ohammadi. Intellegent Driver Drowsiness Detection through Fusion of Yawning and Eye Closure[C]. Ottawa, Canada. IEEE International Conference on Virtual Environments Human-Computer Interfaces and Measurement Systems,2011:1-6.
[30]Tiesheng Wang, Pengfei Shi. Yawning Detection for Determining Driver Drowsiness. Suzhou, China. IEEE International Workshop on VLSI Design & Video Technology.2005:373-376.
[31]E. Vural, M. Bartlett, G. Littlewort, etc. Discrimination of Moderate and Acute Drowsiness Based on Spontaneous Facial Expressions[C]. International Conference on Pattern Recognition 2010:3874-3877.
[32]E. Vural, M. Cetin, A. Ercil, G. Littlewort, M. S. Bartlett, and J. R. Movellan, Drowsy driver detection through facial movement analysis. ICCV-HCI,2007:6-18.
[33]Chihang Zhao, Jie Lian, Jie He etc. Recognition of Driver's Fatigue Expressions by Gabor Wavelet Transform and Multilayer Perceptron Classifier. International Conference on Transportation, Mechanical, and Electrical Engineering (TMEE). Changchun, China.2011:617-620.
[34]蔡文,可拓集合和不相容问题[J].科学探索学报,1983,3(1)：83-97.
[35]蔡文,物元模型及其应用[M].北京：科学技术出版社,1994.
[36]蔡文,杨春燕,林伟初.可拓工程方法[M].北京：科学出版社,1997.
[37]蔡文,杨春燕,何斌.可拓逻辑初步[M].北京：科学出版社,2003.
[38]杨春燕,蔡文.可拓工程[M].北京：科学出版社,2007.
[39]余永权.可拓检测技术[J].中国工程科学2001,3(4)：88-93.
[40]陈前,王甦菁,刘小华等.一种快速的虹膜定位算法.吉林大学学报(理学版)[J].2011,49(6)：1095-1100.
[41]刘元宁,胡宗星,朱晓.基于轮廓跟踪的虹膜定位算法.吉林大学学报(理学版)[J].2011,49(2)：273-278.
[42]曹倩霞,罗大庸,朱明军,基于彩色分割的虹膜检测[J].计算机工程,2005,31(19)：173-175.
[43]夏思宇,夏良正.一种快速的彩色序列图像人脸检测算法[J].数据采集与处理,2005,20(2)：208-212.
[44]林庆,罗敏.基于颜色和几何关系的人脸检测方法[J].计算机工程与设计,2008,29(13)：3396-3398.
[45]赵明华,游志胜,穆万军等.基于肤色分割、数学形态学和几何方法的人脸检测[J].四川大学学报,2005,42(3)：617-620.
[46]耿新,周志华,陈世福.基于混合投影函数的眼睛定位[J].软件学报,2003,14(8)：1394-1399.
[47]van Kreveld M, van Ostrum R, Bajaj C L. Contour trees and small seed sets for isosurface traversal[C].//Proceedings of the 13thACM Symposium on Computational Geometry, Nice, France, ACM,1997:212-220.
[48]Gihad Rabi, Si WeiLu, Energy Minimization for Extracting Mouth Curves in Facial Image[C]. Grand Bahama Island. IEEE International Conference on Intelligent Information Systems,1997:381-385.
[49]Yuille A. Hallinan P, Cohen D S. Feature Extraction from Faces UsingDeformable Templates[J]. International Journal of Computer Visition,1992,8(2):99-111.
[50]Tian Y L, Kanade Cohn J E. Dual-state Parametric Eye Tracking. Proceedings of the 4th IEEE International Conference onAutomatic Face and Gesture Recognition (FG'00)[C],Grenoble,France.2000:110-115.
[51]John.A.Stern, D.Boyer, D.Schroeder. Blink Rate:a possible meature of fatigue[J].Human Factors,1994,36 (2):285-279.
[52]郑培民,宋正河,周一鸣.基于PERCLOS的机动车驾驶员驾驶疲劳的识别算法[J].中国农业大学学报,2002,7(2)：104-109.
[53]Miyakawa T, Takano H, Nakamura K. Development of Noncontact Real-time Blink Detection System for Doze Alarm[C].//Proceedings of SICE Annual Conference. Sapporo, Japan:IEEE,2004:1626-1631.
[54]Horak K. Fatigue Features Based on Eye Tracking for Driver Inattention System[C].//Proceedings of 34th International Conference on Telecommunications and Signal Processing. Budapest, Hungary:IEEE, 2011:593-597.
[55]朱振华,吴晓娟,王磊等.基于眨眼持续时间的司机疲劳识别方法[J].计算机工程,2008,34(5)：201-206.
[56]潘晓东,李君羡,徐小冬.基于眼部行为的驾驶疲劳评价指标的阈值[J].同济大学学报.自然科学版：2011,39(12)：1811-1815.
[57]李德毅,杜鹢.不确定性人工智能[M].北京：国防工业出版社,2005.
[58]付斌,李道国,王慕快.云模型研究的回顾与展望[J].计算机应用研究.2011,28(2)：420-426.
[59]李伟红.基于支持向量机的人脸特征选择及识别研究[D].重庆：重庆大学,2006.
[60]郁伟炜,吴卿.基于HMM的驾驶员疲劳识别在智能汽车空间的应用[J].计算机应用与软件.2011,28(10)：43-46.
[61]Shabnam Abtahi, Behnoosh Hariri, Shervin Shirmo hammadi. Driver Drowsiness Recognition based on Yawning Detection[C]. Hangzhou, China. International Instrumentation and Measurement Technology Conference,2011:1606-1610.
[62JKEOGH E. Datamining and machine learning in time series database[C]. Leipzig, Germany. The 5th Industrial Conference on Data Mining (IC-DM):2005.
[63]LIN Wei-qiang, ORGUN M A, WILLIAM SG J. An overview of temporal data-mining[C]//Procceedings of the 1st Australian Data Mining Work-shop. Canberra:University of Technology.2002:83-90.
[64]贾澎涛,何华灿,刘丽等.时间序列数据挖掘综述[J].计算机应用研究.2007,24(11)：15-18.
[65]Donald J. Berndt, James Clifford. Using Dynamic Time Warping to Find Patterns in Time Series[C].In Proceedings of the KDD Workshop,Seattle, WA.1994:359-370.
[66]尹锐,李雄飞,李军等.基于线性分段与HMM的时间序列分类算法[J].模式识别与人工智能.2011,24(4)：574-581.
[67]罗志增,严庭芳.基于HMM的表面肌电信号模式分类[J].华中科技大学学报(自然科学版).2008,36(4)：72-75.
[68]杨仕博.时序数据维归约方法的研究[D].兰州：兰州大学,2008.
[69]迪达(Duda,R,O)等著,李宏东等译.模式分类(原书第2版)[M].北京：机械工业出版社,2003.
[70]曹曼译.为什么觉得累[J]. Newton科学世界.2013,vo1(1)：68-73.
[71]Fukuda K, Straus SE, Hickie I, Sharpe MC, Dobbins JG, Komaroff A. The chronic fatigue syndrome:a comprehensive approach to its definition and study. International Chronic Fatigue Syndrome Study Group. Ann Intern Med.1994,121(12):953-959.
[72]伍光辉,吴佳奇.亚健康与青少年颈椎病的防治研究进展[J].西部医学,2008,20(6)：1301-1302.
[73]Wyller VB. The chronic fatigue syndrome-an update[J]. Acta Neurol Scand 2007,115 (Suppl.187):7-14.
[74]FATIGUE SCIENCE LAB INC [JP],UNIV OSAKA [JP]. Method And Device For Diagnosing Chronic Fatigue Syndrome By Using Near Infrared Spectrum[P]. US20060914755;20060515.
[75]许家佗,李蕾,张志枫等.基于图像处理的亚健康状态面色特征分析[DB/OL]. http://d.g. wanfangdata.com.cn/Conference_7175781.aspx
[76]李仕维,李乃民,王春燕等.人体疲劳面部变化观察[J].中国健康月 刊,2011,30(7)：70-71.
[77]Driver Drowsiness Recognition based on Yawning Detection[C]. Hangzhou, China. International Instrumentation and Measurement Technology Conference.2011:1606-1610.
[78]BEIJING INST TECHNOLOGY. Relational model of driver fatigue and vehicle riding trail[P]. CN20091079324; 20090306.
[79]BEIJING INST TECHNOLOGY.System for remote recognition and prewarning of driving fatigue state based on multielement network transmission[P]. CN20091079323;20090306.
[80]BEIJING INST TECHNOLOGY.Semi-physical driving fatigue vision simulation system platform[P]. CN20091079326;20090326.
[81]UNIV HUAZHONG NORMAL. Learning fatigue recognition interference method based on facial expression recognition[P]. CN20091062862; 20090626.
[82]Keiko.微笑密码眼袋VS卧蚕[J].医学美学美容(蜜.Me).2011(Z1).
[83]邓金城.基于人脸识别技术的驾驶员疲劳识别方法研究[D].重庆大学硕士学位论文,2005.
[84]P.Viola and M.J.Jones. Rapid object detection using a boosted cascade of simple features[C]. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2001,Vol.1: I-511-I-518.
[85]章毓晋.图像工程(上册)[M].北京：清华大学出版社,2012.
[86]M. van Kreveld, R. van Oostrum, C. L. Bajaj, etc., Contour trees and small seed sets for isosurface traversal, Proceedings of the 13th ACM Symposium on Computational Geometry,1997:212-220.
[87]林鸿飞,胡涛,李志远.基于局部多项式法的RGB到CIELab颜色空间转换算法的研究[J].广东印刷.2009(3)：11-13.
[88]Tsai DM, Wu SK, Chen MC. Optimal Gabor filter design for texture segmentation using stochastic optimization. Image and Vision Computing, 2001,19(5):299-316.
[89]何源,罗予频,胡东成.基于测地线活动区域模型的非监督式纹理分割[J].软件学报,2007,18(3)：592-599.
[90]张伟,夏利民,罗大庸.基于流形保持投影的驾驶疲劳识别[J].信息与控制,2011,40(1)：119-123.
[91]F Smarandache. Generalization of the Dependent Function in Extenics for Nested Sets with Common Endpoints to 2D-Space,3D-Space, and Genera-lly to n-D-Space [DB/OL]. https://globaljournals.org/GJSFR_Volumel2/ 1-Generalization-of-the-Dependent-Function.pdf
[92]李俊华,彭力.基于特征块主成分分析的人脸表情识别[J].计算机工程与设计2008,29(12)：3151-3153.
[93]叶吉祥,胡秀丽.基于Gabor小波与分形维的人脸情感特征提取[J].计算机工程,2008,34(4)：226-230.
[94]王晔,吴小俊,王士同等.基于改进主动形状模型的人脸表情识别[J].计算机工程与应用,2009,45(6)：197-200.
[95]Sandberg D.The performance of driver sleepiness indicators as a function of interval length[C]. Proceedings of 14th International Conference on Intelligent Transportation Systems. Washington, D C, USA. IEEE, 2011:1735-1740.
[96]李志春,何仁,何翠群.模糊神经网络在驾驶员疲劳识别中的应用[J].江苏大学学报(自然科学版).2008,29(2)：123-126.
[97]张恒,刘艳丽.基于视觉信息融合的驾驶员疲劳识别方法综述[J].信息技术.2008(6)：8-19.
[98]叶玮琼.基于可拓学的仿人控制及应用研究[D].广州：广东工业大学,2011.
[99]罗春玲.正态分布的性质及应用[J].才智.2010(17)：64-66.
[100]两变量关联性分析pearson相关系数介绍[DB/OL].百度文库.http://wenku.baidu.com/view/24f36106de80d4d8d15a4fad.html,2013-01-05.
[2]曹雪亮.脑力疲劳的注意特征及主观评定方法的实验研究[D].西安：第四军医大学,2003.
[3]径卫视觉科技.疲劳驾驶侦测系统发展状况分析[DB/OL]. http://www.roadefend.com/xinwenzhongxin/gongsixinwen/38.html.
[4]李永平.脉搏图像化检测方法对精神疲劳状态的识别[D].兰州：兰州理工大学,2008.
[5]陈云华,余永权,张灵,丁伍洋.基于面部视觉特征的精神疲劳可拓辨识模型.计算机科学.2013,2(40)：284-288.
[6]邓金城.基于人脸识别技术的驾驶员疲劳识别方法研究[D].重庆：重庆大学,2005.
[7]朱炳初,汪丰.疲劳识别研究现状与发展[DB\OL].中国科技论文在线.http://www.paper.edu.cn.
[8]Skosnik PD, Chatterton RT,S wisher T,Park S:Modulation of attentional inhibition by norepinephrine andcortisol after psychological stress [J]. International Journal of Psychophysiology,2000,36:59-68.
[9]江北,聂东.大学生上网导致CFF降低的研究[J].中国校医,2008,22(3)：272-273.
[10]Dinges DF, Powell JW. Microcomputer analysis of performance on a portable, simple visual ART taskduring sustained operations. Behavior Research Methods, Instruments and Computers 1985,17:652-655.
[11]Johns MW, et al. Eyelid Closure, Visual Suppression and Hypo vigilance in the Drowsy State:Lapses inPerformance With Eyes Open or Closed. Epworth Sleep Centre, Melbourne, Australia,2003.
[12]王楠,杨凯,沈莹.飞行员视觉神经行为功能测试系统[J].现代电子技术,2007,3：96-99.
[13]H. P. Greeley, S. Raghavan,J. Berg etc. Detecting Fatigue From Voice UsingSpeech Recognition[C]. Proceedings of 2006 IEEE International Symposium on Signal Processing and Information Technology, Vancouver, Canada,2006:567-571.
[14]张志斌.基于计算机视觉的驾驶员疲劳实时检测研究[D].北京：北京工业大学,2008.
[15]Qiang Ji, Peilin Lan, and Carl Looney.A Probabilistic Framework for Modeling and Real-Time Recognition Human Fatigue[J]. IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS,PART A: SYSTEMS AND HUMANS.2006,36 (5):862-875.
[16]Yang,G, Lin,Y.,Bhattacharya,P.:A driver fatigue recognition model using fusion of multiplefeatures[C],2005 IEEE International Conference on Systems,Man and Cybernetics,2005(2):1777-1784.
[17]Ji Q, Zhu Z W, Lan P L. Real-Time Nonintrusive Recognition and Prediction of Driver Fatigue[J]. IEEE Transaction on Vehicular Technology,2004,53(4):1052-1068.
[18]尹兵.基于红外技术的驾驶员脸部识别研究[D].吉林：吉林大学,2008.
[19]王磊,吴晓娟等.驾驶疲劳/瞌睡检测方法的研究进展[J].生物医学工程学杂志.2007,24(1)：245-248.
[20]Wen-Bing Horng, Chih-Yuan Chen, Yi Chang etc. Driver Fatigue Detection Based on Eye Tracking and Dynamic Template Matching[J].Proceedings of the 2004 IEEE International Conference on Networking,Sensing & Control, Taipei, Taiwan,2004:7-12.
[21]G.Y. Zhang, B. Cheng, R.J. Feng, X.B. Zhang, A Real-Time Adaptive Learning Method for Driver Eye Detection, Proceedings of Digital Image Computing:Techniques and Applications.2008:300-304.
[22]王琼,王欢,赵春霞等.基于眼睛状态识别的驾驶员疲劳识别[J].南京理工大学学报(自然科学版).2010,34(4)：448-453.
[23]江水郎,杨明.面向驾驶员疲劳识别的双空间人眼定位方法[J].计算机工程,2008,34(24)：180-182.
[24]Mandalapu Sarada Devi,Preeti R Bajaj.Driver Fatigue Detection Based on Eye Tracking[C]. Proceedings of 1th International Conference on Emerging Trends in Engineering and Technology.2008:649-652.
[25]Tayyaba Azim,M.Arfan Jaffa,Anwar Majid Mirza. Automatic Fatigue Detection of Drivers through Pupil Detection and YawningAnalysis[C]. Proceedings of 4th International Conference on Innovative Computing, Information and Control.2009:441-445.
[26]Ji Q, Yang X, Real time visual cues extraction for recognition driver vigilance[C].//Lecture Notes presented at the Proc. Int. Workshop Computer Vision Systems. Vancouver, Canada:Springer,2001:107-124.
[27]Lu Yufeng,Wang zengcai. Detecting Driver Yawning in Successive Images[C].Wuhan, China. In:Proc. of 1st International Conferrence on Bioinformatics and Biomedical Engineering,2007:581-583
[28]Shabnam Abtahi, Behnoosh Hariri, Shervin Shirmo hammadi. Driver Drowsiness Recognition based on Yawning Detection[C]. Hangzhou, China. International Instrumentation and Measurement Technology Conference,2011:1606-1610.
[29]M.Omidyeganeh, A.Javadtalab, S.Shirm ohammadi. Intellegent Driver Drowsiness Detection through Fusion of Yawning and Eye Closure[C]. Ottawa, Canada. IEEE International Conference on Virtual Environments Human-Computer Interfaces and Measurement Systems,2011:1-6.
[30]Tiesheng Wang, Pengfei Shi. Yawning Detection for Determining Driver Drowsiness. Suzhou, China. IEEE International Workshop on VLSI Design & Video Technology.2005:373-376.
[31]E. Vural, M. Bartlett, G. Littlewort, etc. Discrimination of Moderate and Acute Drowsiness Based on Spontaneous Facial Expressions[C]. International Conference on Pattern Recognition 2010:3874-3877.
[32]E. Vural, M. Cetin, A. Ercil, G. Littlewort, M. S. Bartlett, and J. R. Movellan, Drowsy driver detection through facial movement analysis. ICCV-HCI,2007:6-18.
[33]Chihang Zhao, Jie Lian, Jie He etc. Recognition of Driver's Fatigue Expressions by Gabor Wavelet Transform and Multilayer Perceptron Classifier. International Conference on Transportation, Mechanical, and Electrical Engineering (TMEE). Changchun, China.2011:617-620.
[34]蔡文,可拓集合和不相容问题[J].科学探索学报,1983,3(1)：83-97.
[35]蔡文,物元模型及其应用[M].北京：科学技术出版社,1994.
[36]蔡文,杨春燕,林伟初.可拓工程方法[M].北京：科学出版社,1997.
[37]蔡文,杨春燕,何斌.可拓逻辑初步[M].北京：科学出版社,2003.
[38]杨春燕,蔡文.可拓工程[M].北京：科学出版社,2007.
[39]余永权.可拓检测技术[J].中国工程科学2001,3(4)：88-93.
[40]陈前,王甦菁,刘小华等.一种快速的虹膜定位算法.吉林大学学报(理学版)[J].2011,49(6)：1095-1100.
[41]刘元宁,胡宗星,朱晓.基于轮廓跟踪的虹膜定位算法.吉林大学学报(理学版)[J].2011,49(2)：273-278.
[42]曹倩霞,罗大庸,朱明军,基于彩色分割的虹膜检测[J].计算机工程,2005,31(19)：173-175.
[43]夏思宇,夏良正.一种快速的彩色序列图像人脸检测算法[J].数据采集与处理,2005,20(2)：208-212.
[44]林庆,罗敏.基于颜色和几何关系的人脸检测方法[J].计算机工程与设计,2008,29(13)：3396-3398.
[45]赵明华,游志胜,穆万军等.基于肤色分割、数学形态学和几何方法的人脸检测[J].四川大学学报,2005,42(3)：617-620.
[46]耿新,周志华,陈世福.基于混合投影函数的眼睛定位[J].软件学报,2003,14(8)：1394-1399.
[47]van Kreveld M, van Ostrum R, Bajaj C L. Contour trees and small seed sets for isosurface traversal[C].//Proceedings of the 13thACM Symposium on Computational Geometry, Nice, France, ACM,1997:212-220.
[48]Gihad Rabi, Si WeiLu, Energy Minimization for Extracting Mouth Curves in Facial Image[C]. Grand Bahama Island. IEEE International Conference on Intelligent Information Systems,1997:381-385.
[49]Yuille A. Hallinan P, Cohen D S. Feature Extraction from Faces UsingDeformable Templates[J]. International Journal of Computer Visition,1992,8(2):99-111.
[50]Tian Y L, Kanade Cohn J E. Dual-state Parametric Eye Tracking. Proceedings of the 4th IEEE International Conference onAutomatic Face and Gesture Recognition (FG'00)[C],Grenoble,France.2000:110-115.
[51]John.A.Stern, D.Boyer, D.Schroeder. Blink Rate:a possible meature of fatigue[J].Human Factors,1994,36 (2):285-279.
[52]郑培民,宋正河,周一鸣.基于PERCLOS的机动车驾驶员驾驶疲劳的识别算法[J].中国农业大学学报,2002,7(2)：104-109.
[53]Miyakawa T, Takano H, Nakamura K. Development of Noncontact Real-time Blink Detection System for Doze Alarm[C].//Proceedings of SICE Annual Conference. Sapporo, Japan:IEEE,2004:1626-1631.
[54]Horak K. Fatigue Features Based on Eye Tracking for Driver Inattention System[C].//Proceedings of 34th International Conference on Telecommunications and Signal Processing. Budapest, Hungary:IEEE, 2011:593-597.
[55]朱振华,吴晓娟,王磊等.基于眨眼持续时间的司机疲劳识别方法[J].计算机工程,2008,34(5)：201-206.
[56]潘晓东,李君羡,徐小冬.基于眼部行为的驾驶疲劳评价指标的阈值[J].同济大学学报.自然科学版：2011,39(12)：1811-1815.
[57]李德毅,杜鹢.不确定性人工智能[M].北京：国防工业出版社,2005.
[58]付斌,李道国,王慕快.云模型研究的回顾与展望[J].计算机应用研究.2011,28(2)：420-426.
[59]李伟红.基于支持向量机的人脸特征选择及识别研究[D].重庆：重庆大学,2006.
[60]郁伟炜,吴卿.基于HMM的驾驶员疲劳识别在智能汽车空间的应用[J].计算机应用与软件.2011,28(10)：43-46.
[61]Shabnam Abtahi, Behnoosh Hariri, Shervin Shirmo hammadi. Driver Drowsiness Recognition based on Yawning Detection[C]. Hangzhou, China. International Instrumentation and Measurement Technology Conference,2011:1606-1610.
[62JKEOGH E. Datamining and machine learning in time series database[C]. Leipzig, Germany. The 5th Industrial Conference on Data Mining (IC-DM):2005.
[63]LIN Wei-qiang, ORGUN M A, WILLIAM SG J. An overview of temporal data-mining[C]//Procceedings of the 1st Australian Data Mining Work-shop. Canberra:University of Technology.2002:83-90.
[64]贾澎涛,何华灿,刘丽等.时间序列数据挖掘综述[J].计算机应用研究.2007,24(11)：15-18.
[65]Donald J. Berndt, James Clifford. Using Dynamic Time Warping to Find Patterns in Time Series[C].In Proceedings of the KDD Workshop,Seattle, WA.1994:359-370.
[66]尹锐,李雄飞,李军等.基于线性分段与HMM的时间序列分类算法[J].模式识别与人工智能.2011,24(4)：574-581.
[67]罗志增,严庭芳.基于HMM的表面肌电信号模式分类[J].华中科技大学学报(自然科学版).2008,36(4)：72-75.
[68]杨仕博.时序数据维归约方法的研究[D].兰州：兰州大学,2008.
[69]迪达(Duda,R,O)等著,李宏东等译.模式分类(原书第2版)[M].北京：机械工业出版社,2003.
[70]曹曼译.为什么觉得累[J]. Newton科学世界.2013,vo1(1)：68-73.
[71]Fukuda K, Straus SE, Hickie I, Sharpe MC, Dobbins JG, Komaroff A. The chronic fatigue syndrome:a comprehensive approach to its definition and study. International Chronic Fatigue Syndrome Study Group. Ann Intern Med.1994,121(12):953-959.
[72]伍光辉,吴佳奇.亚健康与青少年颈椎病的防治研究进展[J].西部医学,2008,20(6)：1301-1302.
[73]Wyller VB. The chronic fatigue syndrome-an update[J]. Acta Neurol Scand 2007,115 (Suppl.187):7-14.
[74]FATIGUE SCIENCE LAB INC [JP],UNIV OSAKA [JP]. Method And Device For Diagnosing Chronic Fatigue Syndrome By Using Near Infrared Spectrum[P]. US20060914755;20060515.
[75]许家佗,李蕾,张志枫等.基于图像处理的亚健康状态面色特征分析[DB/OL]. http://d.g. wanfangdata.com.cn/Conference_7175781.aspx
[76]李仕维,李乃民,王春燕等.人体疲劳面部变化观察[J].中国健康月 刊,2011,30(7)：70-71.
[77]Driver Drowsiness Recognition based on Yawning Detection[C]. Hangzhou, China. International Instrumentation and Measurement Technology Conference.2011:1606-1610.
[78]BEIJING INST TECHNOLOGY. Relational model of driver fatigue and vehicle riding trail[P]. CN20091079324; 20090306.
[79]BEIJING INST TECHNOLOGY.System for remote recognition and prewarning of driving fatigue state based on multielement network transmission[P]. CN20091079323;20090306.
[80]BEIJING INST TECHNOLOGY.Semi-physical driving fatigue vision simulation system platform[P]. CN20091079326;20090326.
[81]UNIV HUAZHONG NORMAL. Learning fatigue recognition interference method based on facial expression recognition[P]. CN20091062862; 20090626.
[82]Keiko.微笑密码眼袋VS卧蚕[J].医学美学美容(蜜.Me).2011(Z1).
[83]邓金城.基于人脸识别技术的驾驶员疲劳识别方法研究[D].重庆大学硕士学位论文,2005.
[84]P.Viola and M.J.Jones. Rapid object detection using a boosted cascade of simple features[C]. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2001,Vol.1: I-511-I-518.
[85]章毓晋.图像工程(上册)[M].北京：清华大学出版社,2012.
[86]M. van Kreveld, R. van Oostrum, C. L. Bajaj, etc., Contour trees and small seed sets for isosurface traversal, Proceedings of the 13th ACM Symposium on Computational Geometry,1997:212-220.
[87]林鸿飞,胡涛,李志远.基于局部多项式法的RGB到CIELab颜色空间转换算法的研究[J].广东印刷.2009(3)：11-13.
[88]Tsai DM, Wu SK, Chen MC. Optimal Gabor filter design for texture segmentation using stochastic optimization. Image and Vision Computing, 2001,19(5):299-316.
[89]何源,罗予频,胡东成.基于测地线活动区域模型的非监督式纹理分割[J].软件学报,2007,18(3)：592-599.
[90]张伟,夏利民,罗大庸.基于流形保持投影的驾驶疲劳识别[J].信息与控制,2011,40(1)：119-123.
[91]F Smarandache. Generalization of the Dependent Function in Extenics for Nested Sets with Common Endpoints to 2D-Space,3D-Space, and Genera-lly to n-D-Space [DB/OL]. https://globaljournals.org/GJSFR_Volumel2/ 1-Generalization-of-the-Dependent-Function.pdf
[92]李俊华,彭力.基于特征块主成分分析的人脸表情识别[J].计算机工程与设计2008,29(12)：3151-3153.
[93]叶吉祥,胡秀丽.基于Gabor小波与分形维的人脸情感特征提取[J].计算机工程,2008,34(4)：226-230.
[94]王晔,吴小俊,王士同等.基于改进主动形状模型的人脸表情识别[J].计算机工程与应用,2009,45(6)：197-200.
[95]Sandberg D.The performance of driver sleepiness indicators as a function of interval length[C]. Proceedings of 14th International Conference on Intelligent Transportation Systems. Washington, D C, USA. IEEE, 2011:1735-1740.
[96]李志春,何仁,何翠群.模糊神经网络在驾驶员疲劳识别中的应用[J].江苏大学学报(自然科学版).2008,29(2)：123-126.
[97]张恒,刘艳丽.基于视觉信息融合的驾驶员疲劳识别方法综述[J].信息技术.2008(6)：8-19.
[98]叶玮琼.基于可拓学的仿人控制及应用研究[D].广州：广东工业大学,2011.
[99]罗春玲.正态分布的性质及应用[J].才智.2010(17)：64-66.
[100]两变量关联性分析pearson相关系数介绍[DB/OL].百度文库.http://wenku.baidu.com/view/24f36106de80d4d8d15a4fad.html,2013-01-05.