疲劳驾驶检测系统中若干关键技术研究
摘要
行车安全是交通运输业的永恒主题。近年来，随着道路汽车数量的急速增长，交通事故的发生率也越来越高，给人类社会带来日益严重的的危害。在这严峻的环境下，疲劳驾驶检测技术受到了最为广泛的关注。作为一种避免交通事故、减少事故损失的有效手段，它成为交通工程领域的研究热点，代表着未来车辆发展的趋势。
本文对疲劳驾驶检测系统中若干关键技术进行了研究，具体的研究工作如下：
1、人脸跟踪与检测。采用AdaBoost人脸检测算法对人脸进行检测，深入分析Camshift算法实现人脸跟踪，并针对它的不足进行改进：利用AdaBoost人脸检测算法实现人脸跟踪窗口的自动初始化，提出了基于双眼模板匹配的CamShift人脸跟踪算法，解决了场景中存在大面积类似肤色物体干扰时跟踪失误的问题。
2、首次引入基于LBP-TOP(Local Binary Patterns From Three Orthogonal Panels)的嘴部特征提取方法对嘴部状态进行识别。LBP(Local Binary Patterns)是一种很有效的纹理描述算子，可以对灰度图像中局部领域的纹理信息进行度量和提取，能捕捉图像中微量的细节特征，而LBP-TOP是在LBP的基础之上结合考虑时空域的角度，分别从三个正交平面上提取嘴部图像序列的纹理特征，目的是更好的表达嘴部运动的实质信息。
3、提出了基于SLBP-TOP(Synthesized Local Binary Patterns From Three OrthogonalPanels)的嘴部特征提取方法。该方法为了进一步改善LBP算子存在的一些缺陷，根据LBP-TOP中不同平面嘴部信息的差异性，引入CBP(Centralized Binary Patterns)算子，在二者基础之上将三个平面的特征分为两类，分别采用LBP和CBP算子，然后综合三个特征作为SLBP-TOP(Synthesized Local Binary Patterns From Three Orthogonal Panels)特征。
4、眼睛与嘴部疲劳识别。在人眼定位和人眼状态检测的基础之上，计算PERCLOS值并设定其阈值来识别人眼疲劳；完成对驾驶员嘴部特征提取之后，利用SVM分类器对提取的嘴部特征进行分类，完成对嘴部状态的识别，计算PERLVO值并设定其阈值，完成嘴部疲劳识别。
Traffic safety is an eternal theme in transportation industry. In recent years, with the rapidgrowth of the vehicle, the incidence of traffic accidents is more and more high, and it bringsabout the increasing serious harm to human beings. In the severe environment, traffic safetyassistive technology has been got the widespread attention. As an effective method to avoidtraffic accidents and reduce the loss of accident, it becomes a research hotspot in the field oftransportation engineering, and represents the development tendency of future vehicles.
The thesis carries on researching some key technologies of fatigue detection system.Specific research works are as follows:
1. Face detection and tracking. Using AdaBoost face detection algorithm for face detectionand analysing Camshift algorithms purpose to achieve the process of tracking face.In addition,improving the shortcomings. It achieves the face tracking window automatic initialization byusing AdaBoost face tracking algorithm and proposes a Camshift face tracking algorithms whichis based on eyes template matching. The algorithms solved the problem of tracking errors in thescene which exist in large skin colors.
2. Firstly, importing a new method of mouth feature extraction that is based on LBP-TOP(Local Binary Patterns From Three Orthogonal Panels). LBP is not only a kind of extraordinaryeffective operator of describing texture, which can measure and extract the information of thelocal field texture in gray image and capture little detail characteristics of the image, but alsobased on LBP and combines the temporal angle, which extracts the texture feature of the mouthimage through three orthogonal planes. The purpose is to express the substantial information ofmouth movements better.
3. Bring forward a method of mouth feature extraction based on CBP-TOP, which improvesthe operator of LBP feature extraction, and introducing CBP(Centralized Binary Patterns)operator in order to further improve the feature extraction of the LBP operator which exist some flaws, and divided the three panels into two classes, which use LBP operator and CBP operator,and extracted the mouth feature through synthesizing the three features as SLBP-TOP(Synthesized Binary Patterns From Three Orthogonal Panels).
4. Recognizing eyes and mouth fatigue. Classifying the mouth feature which was extractedby SVM classifier and making the judge rules of mouth fatigue through a lot of experiments, andcompleting mouth fatigue recognition. Recognizing the driver eyes fatigue based on PERCLOS,through the eyes location and eyes state detection.
本文对疲劳驾驶检测系统中若干关键技术进行了研究，具体的研究工作如下：
1、人脸跟踪与检测。采用AdaBoost人脸检测算法对人脸进行检测，深入分析Camshift算法实现人脸跟踪，并针对它的不足进行改进：利用AdaBoost人脸检测算法实现人脸跟踪窗口的自动初始化，提出了基于双眼模板匹配的CamShift人脸跟踪算法，解决了场景中存在大面积类似肤色物体干扰时跟踪失误的问题。
2、首次引入基于LBP-TOP(Local Binary Patterns From Three Orthogonal Panels)的嘴部特征提取方法对嘴部状态进行识别。LBP(Local Binary Patterns)是一种很有效的纹理描述算子，可以对灰度图像中局部领域的纹理信息进行度量和提取，能捕捉图像中微量的细节特征，而LBP-TOP是在LBP的基础之上结合考虑时空域的角度，分别从三个正交平面上提取嘴部图像序列的纹理特征，目的是更好的表达嘴部运动的实质信息。
3、提出了基于SLBP-TOP(Synthesized Local Binary Patterns From Three OrthogonalPanels)的嘴部特征提取方法。该方法为了进一步改善LBP算子存在的一些缺陷，根据LBP-TOP中不同平面嘴部信息的差异性，引入CBP(Centralized Binary Patterns)算子，在二者基础之上将三个平面的特征分为两类，分别采用LBP和CBP算子，然后综合三个特征作为SLBP-TOP(Synthesized Local Binary Patterns From Three Orthogonal Panels)特征。
4、眼睛与嘴部疲劳识别。在人眼定位和人眼状态检测的基础之上，计算PERCLOS值并设定其阈值来识别人眼疲劳；完成对驾驶员嘴部特征提取之后，利用SVM分类器对提取的嘴部特征进行分类，完成对嘴部状态的识别，计算PERLVO值并设定其阈值，完成嘴部疲劳识别。
Traffic safety is an eternal theme in transportation industry. In recent years, with the rapidgrowth of the vehicle, the incidence of traffic accidents is more and more high, and it bringsabout the increasing serious harm to human beings. In the severe environment, traffic safetyassistive technology has been got the widespread attention. As an effective method to avoidtraffic accidents and reduce the loss of accident, it becomes a research hotspot in the field oftransportation engineering, and represents the development tendency of future vehicles.
The thesis carries on researching some key technologies of fatigue detection system.Specific research works are as follows:
1. Face detection and tracking. Using AdaBoost face detection algorithm for face detectionand analysing Camshift algorithms purpose to achieve the process of tracking face.In addition,improving the shortcomings. It achieves the face tracking window automatic initialization byusing AdaBoost face tracking algorithm and proposes a Camshift face tracking algorithms whichis based on eyes template matching. The algorithms solved the problem of tracking errors in thescene which exist in large skin colors.
2. Firstly, importing a new method of mouth feature extraction that is based on LBP-TOP(Local Binary Patterns From Three Orthogonal Panels). LBP is not only a kind of extraordinaryeffective operator of describing texture, which can measure and extract the information of thelocal field texture in gray image and capture little detail characteristics of the image, but alsobased on LBP and combines the temporal angle, which extracts the texture feature of the mouthimage through three orthogonal planes. The purpose is to express the substantial information ofmouth movements better.
3. Bring forward a method of mouth feature extraction based on CBP-TOP, which improvesthe operator of LBP feature extraction, and introducing CBP(Centralized Binary Patterns)operator in order to further improve the feature extraction of the LBP operator which exist some flaws, and divided the three panels into two classes, which use LBP operator and CBP operator,and extracted the mouth feature through synthesizing the three features as SLBP-TOP(Synthesized Binary Patterns From Three Orthogonal Panels).
4. Recognizing eyes and mouth fatigue. Classifying the mouth feature which was extractedby SVM classifier and making the judge rules of mouth fatigue through a lot of experiments, andcompleting mouth fatigue recognition. Recognizing the driver eyes fatigue based on PERCLOS,through the eyes location and eyes state detection.
引文
[1]郭栋,熊自力.中国交通年鉴[M].北京:中国交通出版社,2009.
[2]李彤.驾驶警觉度测试:五成司机开车打过瞌睡. http://auto.sohu.com/98/08/article215370898.shtml.
[3] King L M, Nguyen H T, Lal S K L. Early Driver Fatigue Detection from Electroencephalography Signalsusing Artificial Neural Networks[C].Proceedings of the28th IEEE EMBS Annual InternationalConference,2006:2187-2190.
[4] Tran Y, Wijesuryia N, Thuraisingham R A, et al. Increase in Regularity and Decrease in Variability Seenin Electroencephalography(EEG) Signals from Alert to Fatigue During a Driving Simulated Task[C].Proceedings of the30th IEEE EMBS Annual International Conference,2008:1096-1099.
[5]房瑞雪,赵晓华,荣建,等.基于脑电信号的驾驶疲劳研究[J].公共交通科技,2009, S1(26):12-13.
[6]佚名.新西兰发明防止司机打瞌睡的报警器[J].河南科技.2005,(1):42.
[7] Canon KK. Brain wave linkage simulation generator, ornament with the same and information processingsystem: Japan, JP8229130[P].1996.
[8] Jeong I C, Lee D H, Park S W, et al. Automobile Driver’s Stress Index Provision System that UtilizesElectrocardiogram[J].IEEE Intelligent Vehicles Symposium,2007:652-656.
[9]焦昆,李增勇,陈铭,等.驾驶精神疲劳的心率变异性和血压变异性综合效应分析[J].生物医学工程杂志,2005,22(2):127-130.
[10] Wierwille W W, et al. Research on vehicle-based driver status/performance monitoring: development,validation, and refinement of algorithms for detection of driver drowsiness[M]. Washington, DC: NationalHighway Traffic Safety Administration,1994.
[11]李贞,冯晓毅.基于传感器技术的驾驶疲劳检测方法综述[J].测控技术,2007,26(4):1-3.
[12] Hostens I, Ramon H. Assessment of Muscle Fatigue in Low Level Monotonous Task Performance duringCar Driving [J].Journal of Electromyography and Kinesiology,2005,15(3):266-274.
[13]孙伟,张为公,张小瑞,陈刚.疲劳驾驶预警系统的研究进展[J].汽车电器,2009,1:4-9.
[14] Takei Y, Furukawa Y. Estimate of Driver’s Fatigue Through Steering Motion[C]. Proceeding of IEEEInternational Conference on System Man and Cybernetics,2005:1765-1770.
[15]石坚,吴远鹏,卓斌,等.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,2000,34(4):441-444.
[16]孙玮,李晓莹.避免疲劳驾驶的“驾驶员警示系统”[J].交通世界(运输·车辆),2006,(1):57-57.
[17] Sandberg D, Wahde M. Particle Swarm Optimization of Feedforward Neural Networks for the Detectionof Drowsy Driving [J].Neural Networks,2008:788-793.
[18]黄瀚敏.基于汽车驾驶疲劳状态检测技术的汽车主动安全系统研究[D].重庆大学,2009.
[19] Weng M C, Chen C T, Kao H C. Remote Surveillance System for Driver Drowsiness in Real-time UsingLow-cost Embedded Platform[C]. Proceeding of IEEE International Conference on Vehicular Electronicsand Safety,2008,288-292.
[20] Chang T H, Hsu C S, Wang C, et al. Onboard Measurement and Warning Module for Irregular VehicleBehavior[C]. Proceeding of IEEE Transaction on Intelligence Transportation and System,2008,501-513.
[21] Grace R., Byrne V E, Legrand J M, et al. A machine vision based drowsy driver detection system forheavy vehicles[C].Proceedings of The Ocular Measures of Driver Alertness Conference,1999,75-86.
[22] Qiang Ji, Xiaojie Yang. Real-Time Eye, Gaze, and Face Pose Tracking for Monitoring Driver Vigilance[J].Real-Time Imaging,2002,357-377.
[23]王磊,吴晓娟.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):1245-1248.
[24]毛喆,初秀民,严新平,等.汽车驾驶员驾驶疲劳监测技术研究进展[J].中国安全科学学报,2005,15(3):108-112.
[25] Wahlstrom E, Masoud O, Papanikotopoulos N P. Vision-Based Methods for Driver Monitoring[C].Proceeding of IEEE International Conference on Intelligent Transportation Systems,2003,903-908.
[26] Batista J. A Drowsiness and Point of Attention Monitoring System for Driver Vigilance[C]. Proceeding ofIEEE International Conference on Intelligent Transportation System,2007,702-708.
[27] Wang R B, Guo L, Tong B L, et al. Monitoring Mouth Movement for Driver Fatigue or Distraction withOne Camera[C]. Proceeding of IEEE International Conference on Intelligence Transport System,2004,314-319.
[28] Fan X, Yin B C, Sun Y F. Yawning Detection for Monitoring Driver Fatigue[C]. Proceeding of IEEEInternational Conference on Machine Learning and Cybernetics,2007:664-668.
[29]戴军,张进,姚洪略,等.基于信息融合技术的驾驶员疲劳度实时监控系统[J].广东技术师范学院学报,2006,6(6):29-31.
[30] Thomas Brandt, Ralf Stemmer, Andry Rakotonirainy. AffordableVisual Driver Monitoring System forFatigue and Monotony [C]. Proceeding of IEEE International Conference on Systems, Man andCybernetics,2004,6451-6456.
[31]魏明慧.基于视觉的驾驶疲劳监测关键技术研究[D].南京理工大学,2007.
[32] Voila P., Jones M. Rapid Object Detection using a Boosted Cascade of Simple Features[C]. Proceeding ofIEEE Conference on Computer Vision and Pattem Recognition,2001,511-518.
[33] Fukunaga K, Hostetler L D. The estimation ofthe gradient ofa density function, with applications inpattern recognition[J]. IEEE Information Theory Society,1975,21(1):32-40.
[34] Comaniciu D, Ramesh v, Meer P. Real-Time tracking of non-rigid objects using MeanShfit[C].Proceeding of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2000.2000,2:142-149.
[35] H. Rowley, S. Baluja, T. Kanade. Rotation invariant neural network-based face detection[C]. Proceedingof IEEE Computer Society Conference on Computer Vision and Pattern Recognition.1998,38-44.
[36] Gary R Bradski, Santa Clara. Computer Vision Face Tracking for Use in a Perceptual User Interface[J].IEEE Workshop on Applications of Computer Vision,1998,2(2):12-21.
[37]孔健.基于MLBP-TOP与光流多特征的人脸表情融合识别研究[D].江苏大学，2009.
[38] Chapelle, Haffner, Vapnik. Support vector machines for histogram-based Image classification[J]. IEEEComputational Intelligence Society.1999,10(5):1055-1064.
[39]李冯,姚莉秀,杨杰等.复杂背景下的彩色图像人脸检测[J].上海交通大学学报,2006,40(5):778-782.
[40]武勃等.基于连续AdaBoost算法的多视角人脸检测[J].计算机研究与发展,2005,42(9):1612-1621.
[41] MIT CBCL Face DataSet: http://www.ai.mit.edu/projects/cbc/software-datasets/FaceData2.html.
[42] CMU Test Set: http://vasc.ri.cmu.edu/idb/images/face/frontal_images/images.tar.
[43] ATT Laboratories, Cambridge, UK.“The ORL Database of Face”.http://www.uk.research.art.com/facedata-base.html.
[44] Kim H, Kang W, Shin J, etal. Face Detection Using Template Matching and Ellipse Fitting[J]. IEICETRANSACTIONS on Information and Systems,2000, E38-D (11):2008-2011.
[45] Ch Ren J and Vlachos T. Eficient detection of temporally impulsive dirt impairments in archived films[J].Signal Processing,2007,87(3):541-551.
[46] Karin Sobottka, Ioannis Pitas. A novel method for automatic face segmentation, facial feature extractionand tracking[J]. Signal Processing,1998,12(3):248-250.
[47] Xie XD, LamKM. Gabor-based kernel PCA with doubly nonlinear mapping for face recognition with asingle face image[J].IEEE Transactions on Image Processsing,2006,15(9):2481-2492.
[48] GAVRILA, D.M. Sensor-based pedestrian protection[J]. IEEE Intelligent Systems,2001,16(6),77-81.
[49] FengGC, YuenPC. Variance projection function and its application to eye detection for human facerecognition[J]. Patem Recognition Leters,1998,19(9):899-906.
[50] Waite J, V incent J, A probabilistic framework for neural network facial feature location[J]. BritishTelecom Technology Journa,1992,10(3):85-89.
[51]刘彩.一种改进的Sobel图像边缘检测算法[J].贵州工业大学学报,2004,3(5):77-79.
[52]孙英慧.基于Canny算子的边缘检测研究[J].鞍山师范学院学报,2010,12(2):48-50.
[53]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.
[54]叶文东,肖刚,程振波等.虹膜定位算法研究[J].浙江工业大学学报,2004,32(6):714-718.
[55]王磊,莫玉龙.基于霍夫变换和眼睑弹性模板的眼睛特征提取[J].红外与毫米波学报,1998,1(18):53-60.
[56]陈维义,罗晓沛.基于Hough变换和变形曲线技术的椭圆提取研究[J].微电子学与计算机,2004,21(9):91-95.
[57]于莉娜,胡正平,练秋生.基于改进随机Hough变换的混合圆/椭圆快速检测方法[J].电子测量与仪器学报,2004,18(2):92-97.
[58] Federal Highway Administration. Eye-activity measures of fatigue and napping as a fatiguecountermesure[J]. Washington D C:Federal Highway Administration Tech Brief,1999.
[59]郑培,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.
[60] ZHAO Guo-ying, Pietikainen M. Dynamic Texture Recognition Using Local Binary Patterns With anApplication to Facial Expressions[J]. IEEE Transactions on Patterns Analysis and Machine Intelligence,2007,29(6):915-928.
[61] Ahonen T, Hadid A, Pietikainen M. Face description with local binary patterns: Application to facerecognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(12):2037-2041.
[62] Xiaofeng Fu, Wei wei. Centralized binary pattems embedded with image euclidean distance for facialexpression recognition[C]. The4th International Conference on Natural Computation,2008,4:115-119.
[63]朱勇,詹永照.基于CBP-TOP特征的人脸表情识别[J].计算机应用研究,2011,28(5):1957-1960.
[2]李彤.驾驶警觉度测试:五成司机开车打过瞌睡. http://auto.sohu.com/98/08/article215370898.shtml.
[3] King L M, Nguyen H T, Lal S K L. Early Driver Fatigue Detection from Electroencephalography Signalsusing Artificial Neural Networks[C].Proceedings of the28th IEEE EMBS Annual InternationalConference,2006:2187-2190.
[4] Tran Y, Wijesuryia N, Thuraisingham R A, et al. Increase in Regularity and Decrease in Variability Seenin Electroencephalography(EEG) Signals from Alert to Fatigue During a Driving Simulated Task[C].Proceedings of the30th IEEE EMBS Annual International Conference,2008:1096-1099.
[5]房瑞雪,赵晓华,荣建,等.基于脑电信号的驾驶疲劳研究[J].公共交通科技,2009, S1(26):12-13.
[6]佚名.新西兰发明防止司机打瞌睡的报警器[J].河南科技.2005,(1):42.
[7] Canon KK. Brain wave linkage simulation generator, ornament with the same and information processingsystem: Japan, JP8229130[P].1996.
[8] Jeong I C, Lee D H, Park S W, et al. Automobile Driver’s Stress Index Provision System that UtilizesElectrocardiogram[J].IEEE Intelligent Vehicles Symposium,2007:652-656.
[9]焦昆,李增勇,陈铭,等.驾驶精神疲劳的心率变异性和血压变异性综合效应分析[J].生物医学工程杂志,2005,22(2):127-130.
[10] Wierwille W W, et al. Research on vehicle-based driver status/performance monitoring: development,validation, and refinement of algorithms for detection of driver drowsiness[M]. Washington, DC: NationalHighway Traffic Safety Administration,1994.
[11]李贞,冯晓毅.基于传感器技术的驾驶疲劳检测方法综述[J].测控技术,2007,26(4):1-3.
[12] Hostens I, Ramon H. Assessment of Muscle Fatigue in Low Level Monotonous Task Performance duringCar Driving [J].Journal of Electromyography and Kinesiology,2005,15(3):266-274.
[13]孙伟,张为公,张小瑞,陈刚.疲劳驾驶预警系统的研究进展[J].汽车电器,2009,1:4-9.
[14] Takei Y, Furukawa Y. Estimate of Driver’s Fatigue Through Steering Motion[C]. Proceeding of IEEEInternational Conference on System Man and Cybernetics,2005:1765-1770.
[15]石坚,吴远鹏,卓斌,等.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,2000,34(4):441-444.
[16]孙玮,李晓莹.避免疲劳驾驶的“驾驶员警示系统”[J].交通世界(运输·车辆),2006,(1):57-57.
[17] Sandberg D, Wahde M. Particle Swarm Optimization of Feedforward Neural Networks for the Detectionof Drowsy Driving [J].Neural Networks,2008:788-793.
[18]黄瀚敏.基于汽车驾驶疲劳状态检测技术的汽车主动安全系统研究[D].重庆大学,2009.
[19] Weng M C, Chen C T, Kao H C. Remote Surveillance System for Driver Drowsiness in Real-time UsingLow-cost Embedded Platform[C]. Proceeding of IEEE International Conference on Vehicular Electronicsand Safety,2008,288-292.
[20] Chang T H, Hsu C S, Wang C, et al. Onboard Measurement and Warning Module for Irregular VehicleBehavior[C]. Proceeding of IEEE Transaction on Intelligence Transportation and System,2008,501-513.
[21] Grace R., Byrne V E, Legrand J M, et al. A machine vision based drowsy driver detection system forheavy vehicles[C].Proceedings of The Ocular Measures of Driver Alertness Conference,1999,75-86.
[22] Qiang Ji, Xiaojie Yang. Real-Time Eye, Gaze, and Face Pose Tracking for Monitoring Driver Vigilance[J].Real-Time Imaging,2002,357-377.
[23]王磊,吴晓娟.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):1245-1248.
[24]毛喆,初秀民,严新平,等.汽车驾驶员驾驶疲劳监测技术研究进展[J].中国安全科学学报,2005,15(3):108-112.
[25] Wahlstrom E, Masoud O, Papanikotopoulos N P. Vision-Based Methods for Driver Monitoring[C].Proceeding of IEEE International Conference on Intelligent Transportation Systems,2003,903-908.
[26] Batista J. A Drowsiness and Point of Attention Monitoring System for Driver Vigilance[C]. Proceeding ofIEEE International Conference on Intelligent Transportation System,2007,702-708.
[27] Wang R B, Guo L, Tong B L, et al. Monitoring Mouth Movement for Driver Fatigue or Distraction withOne Camera[C]. Proceeding of IEEE International Conference on Intelligence Transport System,2004,314-319.
[28] Fan X, Yin B C, Sun Y F. Yawning Detection for Monitoring Driver Fatigue[C]. Proceeding of IEEEInternational Conference on Machine Learning and Cybernetics,2007:664-668.
[29]戴军,张进,姚洪略,等.基于信息融合技术的驾驶员疲劳度实时监控系统[J].广东技术师范学院学报,2006,6(6):29-31.
[30] Thomas Brandt, Ralf Stemmer, Andry Rakotonirainy. AffordableVisual Driver Monitoring System forFatigue and Monotony [C]. Proceeding of IEEE International Conference on Systems, Man andCybernetics,2004,6451-6456.
[31]魏明慧.基于视觉的驾驶疲劳监测关键技术研究[D].南京理工大学,2007.
[32] Voila P., Jones M. Rapid Object Detection using a Boosted Cascade of Simple Features[C]. Proceeding ofIEEE Conference on Computer Vision and Pattem Recognition,2001,511-518.
[33] Fukunaga K, Hostetler L D. The estimation ofthe gradient ofa density function, with applications inpattern recognition[J]. IEEE Information Theory Society,1975,21(1):32-40.
[34] Comaniciu D, Ramesh v, Meer P. Real-Time tracking of non-rigid objects using MeanShfit[C].Proceeding of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2000.2000,2:142-149.
[35] H. Rowley, S. Baluja, T. Kanade. Rotation invariant neural network-based face detection[C]. Proceedingof IEEE Computer Society Conference on Computer Vision and Pattern Recognition.1998,38-44.
[36] Gary R Bradski, Santa Clara. Computer Vision Face Tracking for Use in a Perceptual User Interface[J].IEEE Workshop on Applications of Computer Vision,1998,2(2):12-21.
[37]孔健.基于MLBP-TOP与光流多特征的人脸表情融合识别研究[D].江苏大学，2009.
[38] Chapelle, Haffner, Vapnik. Support vector machines for histogram-based Image classification[J]. IEEEComputational Intelligence Society.1999,10(5):1055-1064.
[39]李冯,姚莉秀,杨杰等.复杂背景下的彩色图像人脸检测[J].上海交通大学学报,2006,40(5):778-782.
[40]武勃等.基于连续AdaBoost算法的多视角人脸检测[J].计算机研究与发展,2005,42(9):1612-1621.
[41] MIT CBCL Face DataSet: http://www.ai.mit.edu/projects/cbc/software-datasets/FaceData2.html.
[42] CMU Test Set: http://vasc.ri.cmu.edu/idb/images/face/frontal_images/images.tar.
[43] ATT Laboratories, Cambridge, UK.“The ORL Database of Face”.http://www.uk.research.art.com/facedata-base.html.
[44] Kim H, Kang W, Shin J, etal. Face Detection Using Template Matching and Ellipse Fitting[J]. IEICETRANSACTIONS on Information and Systems,2000, E38-D (11):2008-2011.
[45] Ch Ren J and Vlachos T. Eficient detection of temporally impulsive dirt impairments in archived films[J].Signal Processing,2007,87(3):541-551.
[46] Karin Sobottka, Ioannis Pitas. A novel method for automatic face segmentation, facial feature extractionand tracking[J]. Signal Processing,1998,12(3):248-250.
[47] Xie XD, LamKM. Gabor-based kernel PCA with doubly nonlinear mapping for face recognition with asingle face image[J].IEEE Transactions on Image Processsing,2006,15(9):2481-2492.
[48] GAVRILA, D.M. Sensor-based pedestrian protection[J]. IEEE Intelligent Systems,2001,16(6),77-81.
[49] FengGC, YuenPC. Variance projection function and its application to eye detection for human facerecognition[J]. Patem Recognition Leters,1998,19(9):899-906.
[50] Waite J, V incent J, A probabilistic framework for neural network facial feature location[J]. BritishTelecom Technology Journa,1992,10(3):85-89.
[51]刘彩.一种改进的Sobel图像边缘检测算法[J].贵州工业大学学报,2004,3(5):77-79.
[52]孙英慧.基于Canny算子的边缘检测研究[J].鞍山师范学院学报,2010,12(2):48-50.
[53]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.
[54]叶文东,肖刚,程振波等.虹膜定位算法研究[J].浙江工业大学学报,2004,32(6):714-718.
[55]王磊,莫玉龙.基于霍夫变换和眼睑弹性模板的眼睛特征提取[J].红外与毫米波学报,1998,1(18):53-60.
[56]陈维义,罗晓沛.基于Hough变换和变形曲线技术的椭圆提取研究[J].微电子学与计算机,2004,21(9):91-95.
[57]于莉娜,胡正平,练秋生.基于改进随机Hough变换的混合圆/椭圆快速检测方法[J].电子测量与仪器学报,2004,18(2):92-97.
[58] Federal Highway Administration. Eye-activity measures of fatigue and napping as a fatiguecountermesure[J]. Washington D C:Federal Highway Administration Tech Brief,1999.
[59]郑培,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.
[60] ZHAO Guo-ying, Pietikainen M. Dynamic Texture Recognition Using Local Binary Patterns With anApplication to Facial Expressions[J]. IEEE Transactions on Patterns Analysis and Machine Intelligence,2007,29(6):915-928.
[61] Ahonen T, Hadid A, Pietikainen M. Face description with local binary patterns: Application to facerecognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(12):2037-2041.
[62] Xiaofeng Fu, Wei wei. Centralized binary pattems embedded with image euclidean distance for facialexpression recognition[C]. The4th International Conference on Natural Computation,2008,4:115-119.
[63]朱勇,詹永照.基于CBP-TOP特征的人脸表情识别[J].计算机应用研究,2011,28(5):1957-1960.