摘要
疲劳驾驶是造成交通事故的重要原因之一。基于机器视觉技术通过对驾驶人面部表情特征的分析可实现疲劳状态的有效估计。由于该方法具有非侵入、准确、实时的特点而成为疲劳驾驶在线辨识中最具潜力的技术手段。然而，受实际行车环境中光照条件的复杂性、驾驶人面部姿态的不确定性、疲劳表征的隐匿性、驾驶人的个体差异性等诸因素影响，高鲁棒、全天候的的驾驶人疲劳状态在线辨识仍存在众多技术瓶颈。本文围绕光照与姿态变化条件下眼部特征的定位提取、驾驶人姿态估计与校准、疲劳特征空间建模及疲劳模式推断等核心问题展开研究，开发了可适用于实际交通环境的疲劳驾驶实时辨识系统并进行了实验验证。
论文深入分析了实际行车环境中光照条件、驾驶人姿态变化对眼睛定位算法适应性的影响，建立了基于层叠式形状模型和自商图局部纹理模型的主动形状模型算法，实现了眼睛局部邻域的有效分割和可靠跟踪。在此基础上，充分利用自商图、色度以及梯度的统计分布等光照不变特征，建立了光照不变量约束下的参数化模板算法，实现了眼睛轮廓的精确定位。另外，设计了采用偏振光照明的双光谱互补照明光路，有效解决了夜晚在辅助光源照明下眼镜片的反光问题。
充分考虑了行车过程中驾驶环境的时域稳定性，提出了一种综合利用机器学习、在线自适应肤色建模、纯背景建模技术的面部区域分割算法，并通过对面部区域内角点的跟踪，基于外极线约束方程建立了驾驶人相对姿态角解算模型。同时，基于Candide模型实现了驾驶人头部的个体三维重建，并通过三维模型配准完成了驾驶人初始姿态角的确定。
采用统计学方法分析论证了不同疲劳水平下眼睛动作参数差异的显著性，建立了基于眼睛动作特征的疲劳特征空间，并模拟人的认知过程，提出了在驾驶任务初期采用基于训练样本得到的先验知识对疲劳模式进行分类，并在自学习基础上基于贝叶斯置信网络对驾驶人疲劳状态进行推断的辨识方法。
Decreased vehicle control due to driver drowsiness is one of the major causes ofroad accidents. Computer vision based methods have shown the possibility ofdrowsiness detection through driver eye movement analysis. Camera monitoring of agiven driver’s eye status has proved to be the most promising technology due to goodaccuracy, real-time performance and non-intrusiveness. However, there are still manychallenges posed by illumination, driver postures and unapparent facial appearancechanges when a driver becomes drowsy. This paper focuses on the key issues in highaccuracy contour extraction methods across illumination and face orientation,orientation estimation and registration, drowsiness feature space modeling anddrowsiness state inferring. Real on-road experiments are performed to testify theaccuracy and robustness of the proposed methods as well.
According to a thorough analysis on the influence of dynamic illumination andorientation in eye location, an improved Active Shape Model (ASM) involving twocontributions is introduced for face alignment. First, a novel local texture modelmaximizes the ASM tolerance to illumination changes by learning from theSelf-Quotient image instead of the original image. Second, a cascading overall shapemodel is proposed to enhance ASM orientation adaptability. On the basis of facialfeature alignment using ASM, a more precise eye contour location parameterizationmodel is performed by introducing some illumination insensitive features such aschromaticity information and gradient distribution characteristics. Furthermore, a twolayer cascaded illumination system is presented to eliminate reflections ofglasses. A polarized lighting method is adopted in the first layer, and a doublechannel narrow band multi-spectral imaging system is set up in the secondlayer.
Based on the assumption that the features extracted from sequential imagesresemble each other, this paper presents a face detection algorithm which combines alearning-based approach with adaptive skin color segmentation and background modeling methods. The driver’s attitude angles are calculated by tracking corners inthe facial region. Moreover, the initial attitude angles are determined by matching thethree dimensional model of the driver’s head, which is reconstructed from acombination of the Candide model and the driver’s facial image.
The changes of each measure with varying drowsiness levels were comparedwith the analysis of variance (ANOVA), and those with statistically significantdifferences are introduced into the drowsiness feature space. Imitating cognitivebehavior of human beings, an identification method is proposed where prioriknowledge obtained from train data sets are used to classify different drowsinessstates during the initial phase of a driving task and then Bayesian networks areintroduced to drowsiness assessment after a period of real-time learning.
引文
[1] Christos P, Chen Zhe, Chrysoula K P, et al. Monitoring sleepiness with on-boardelectrophysiological recordings for preventing sleep-deprived traffic accidents. ClinicalNeurophysiology,2007,118(9):1906-1922.
[2]王正国.道路交通伤研究和思考.中国医学科学院学报,2007,29(4):455-458.
[3] Bergasa L M, Nuevo J, Sotelo M A, et al. Real-time system for monitoring drivervigilance. IEEE Transactions on Intelligent Transportation Systems,2006,7(1):63-77.
[4]中国交通年鉴1999-2008,中国交通年鉴社,1999-2008.
[5] Khushaba R N, Kodagoda S, Lal S, et al. Driver drowsiness classification using fuzzywavelet-packet-based feature-extraction algorithm. IEEE Transactions on BiomedicalEngineering,2011,58(1):121-131.
[6] Horne J, Reyner L. Vehicle accidents related to sleep: a review. Occupational andEnvironmental Medicine,1998,57(5):289-294.
[7]胡兴军.瞌睡:交通安全的大敌.湖南农机,2004(2):24-24.
[8]王磊,吴晓娟.驾驶疲劳/瞌睡检测方法的研究进展.生物医学工程学杂志,2007,24(1):245-248
[9] Culp J, El-Gindy M, Haque A. Driver alertness monitoring techniques: a literature review.International Journal of Heavy Vehicle Systems,2008,15(2):255-271.
[10] Wang Qiong, Yang Jingyu, Ren Mingwu, et al. Driver fatigue detection: a survey.Proceedings of the6th World Congress on Intelligent Control and Automation, Dalian,China,2006:8587-8591.
[11] Hu Shuyan, Zheng Gangtie. Driver drowsiness detection with eyelid related parameters bysupport vector machine. Expert Systems with Applications,2009,36(4):7651-7658.
[12] Smith, P, Shah M, da Vitoria Lobo N. Determining driver visual attention with one camera.IEEE Transactions on Intelligent Transportation Systems,2003,4(4):205-218.
[13] Cario G, Casavola A, Franz`e G, et al. A hybrid observer approach for driver drowsinessdetection.19th Mediterranean Conference on Control and Automation Aquis CorfuHoliday Palace, Corfu, Greece: IEEE,2011:1331-1336
[14] Liu C C, Hosking S G, Lenné M G. Predicting driver drowsiness using vehicle measures:recent insights and future challenges. Journal of Safety Research,2009,40(4):239-245.
[15] Zilberg E, Burton D, Xu Ming, et al. Methodology and initial analysis results fordevelopment of non-invasive and hybrid driver drowsiness detection systems. The2ndInternational Conference on Wireless Broadband and Ultra Wideband Communications,Sydney, Australia: IEEE,2007:16-16
[16]林维训,潘纲,吴朝晖，等.脸部特征定位方法综述.中国图象图形学报,2003,8(8):849-859.
[17]梁路宏,艾海舟,徐光佑，等.人脸检测研究综述.计算机学报,2002，25（5）：449-458.
[18]周杰，卢春雨，张长水，等.人脸自动识别方法综述.电子学报，2000，28（4）:102-106.
[19] Yang M H, Kriegman D J, Ahuja N. Detecting faces in images: a survey. IEEETransactions on Pattern Analysis and Machine Intelligence,2002,24(1):34-58.
[20] Zou Xuan, Kittler J, Messer K. Illumination invariant face recognition: a survey. FirstIEEE International Conference on Biometrics: Theory, Applications, and Systems, CrystalCity, VA,2007:1-8.
[21] Nikolaidis A, Pitas I. Facial feature extraction and pose determination, PatternRecognition,2000,33(1):1783-1791.
[22] Hong Tianyi, Qin Huabiao, Sun Qianshu. An improved real time eye state identificationsystem in driver drowsiness detection. IEEE International Conference on Control andAutomation, Guangzhou, China: IEEE,2007:1449-1453.
[23] Fasel B, Luettin J. Automatic facial expression analysis: a survey. Pattern Recognition,2003,36(1):259-275.
[24] Lal S K, Craig A. Reproducibility of the spectral components of the electroencephalogramduring driver fatigue. International Journal of Psychophysiology,2005,55(2):137-143.
[25] Lal S K, Craig A. Driver fatigue: electroencephalography and psychological assessment.Psychophysiology,2002,39(3):313-321.
[26] Yeo M V M, Li Xiaoping, Shen Kaiquan, et al. Can SVM be used for automatic EEGdetection of drowsiness during car driving. Safety Science,2009,47(1):115-124.
[27] Eoh H J, Chung M K, Kim S H. Electroencephalographic study of drowsiness insimulated driven with sleep deprivation. International Journal of Industrial Ergonomics,2005,35(4):307-320.
[28] Lin C T, Wu R C, Liang S F, et al. EEG-based drowsiness estimation for safety drivingusing independent component analysis. IEEE Transaction on Circuits and Systems,2005,52(12):2726-2738.
[29] Tsuchida A, Bhuiyan S, Oguri K. Estimation of drowsiness level based on eyelid closureand heart rate variability. Annual International Conference of the IEEE on Engineering inMedicine and Biology Society, Minneapolis, MN,2009:2543-2546.
[30] Furman G D, Baharav A, Cahan C. Early detection of falling asleep at the wheel: a heartrate variability approach. Computers in Cardiology, Bologna,2008:1109-1112.
[31] Tasaki M, Sakai M, Watanabe M. Evaluation of drowsiness during driving usingelectrocardiogram-a driving simulation study.10th International Conference on Computerand Information Technology, IEEE, Bradford,2010:1480-1485.
[32] Nilsson T, Nelson T M, Carlson D. Development of fatigue symptoms during simulateddriving. Accid. Anal. Prev.,1997,29(4):479-488.
[33] Ramesh M V, Nair A K, Kunnathu A T. Intelligent steering wheel sensor network forreal-time monitoring and detection of driver drowsiness. International Journal ofComputer Science and Security,2011,1(3):1-9.
[34] Baronti F, Lenzi F, Roncella R, et al. Distributed sensor for steering wheel rip forcemeasurement in driver fatigue detection. Design, Automation&Test in EuropeConference&Exhibition, Nice: IEEE,2009:894-897.
[35] May J F, Baldwin C L. Driver fatigue: The importance of identifying causal factors offatigue when considering detection and countermeasure technologies. TransportationResearch Part F: Traffic Psychology and Behaviour,2009,12(3):218-224.
[36] Desai A V, Haque M A. Vigilance monitoring for operator safety: A simulation study onhighway driving. Journal of Safety Research,2006,37(2):139-147.
[37] Friedrichs F, Yang Bin. Drowsiness monitoring by steering and lane data based featuresunder real driving conditions.18thEuropean Signal Processing Conference, Aalborg,Denmark,2010:209-213.
[38] Wang Tiesheng, Shi Pengfei. Yawning detection for determining driver drowsiness.Proceedings of2005IEEE International Workshop on VLSI Design and Video Technology,Suzhou, China: IEEE,2005:373-376.
[39] Tabrizi P R, Zoroofi R A. Open/closed eye analysis for drowsiness detection. FirstWorkshops on Image Processing Theory, Tools and Applications, Sousse: IEEE,2008:1-7.
[40] Malla A M, Davidson P R, Bones P J. Automated video-based measurement of eye closurefor detecting behavioral microsleep.2010Annual International Conference of the IEEE onEngineering in Medicine and Biology Society, Buenos Aires: IEEE,2010:6741-6744.
[41] Hirata Y, Nishiyama J, Kinoshita S. Detection and prediction of drowsiness by reflexiveeye movements. Annual International Conference of the IEEE on Engineering in Medicineand Biology Society, Minneapolis, MN: IEEE,2009:4015-4018.
[42] Vural E, Bartlett M, Littlewort G. Discrimination of moderate and acute drowsiness basedon spontaneous facial expressions.20th International Conference on Pattern Recognition,Istanbul, Turkey: IEEE,2010:3874-3877.
[43] Devi M S, Bajaj P R. Driver fatigue detection based on eye tracking.1st InternationalConference on Emerging Trends in Engineering and Technology, Washington, DC: IEEE,2008:649-652.
[44] Zhang Guangyuan, Cheng Bo, Feng Ruijia, et al. Real-time driver eye detection methodusing support vector machine with Hu invariant moments.2008International Conferenceon Machine Learning and Cybernetics, Kunming, China: IEEE,2008:2999-3004.
[45] Zhang Guangyuan, Cheng Bo, Feng Ruijia. A real-time adaptive learning method fordriver eye detection. Computing: Techniques and Applications, Canberra, ACT: IEEE,2008:300-304.
[46] Dinges D F, Grace R. PERCLOS: A valid psychophysiological measure of alertness asassessed by psychomotor vigilance, US Department of Transportation, Federal highwayAdministration. Publication Number FHWA-MCRT-98-006,1998.
[47] Grace R. A drowsy driver detection system for heavy vehicle.17th Digital AvionicsSystems Conference, Bellevue, USA,1998: I36/1-I36/8.
[48] Gu Haisong, Ji Qiang, Zhu Zhiwei. Active facial tracking for fatigue detection.Proceedings of the Sixth IEEE Workshop on Applications of Computer Vision(WACV’02), Orlando, Florida: IEEE,2002:137-142.
[49] Hizem W, Krichen E, Ni Y, et al. Specific sensors for face recognition. Internationalconference on biometrics, Hong Kong, China,2006:47-54.
[50] Jin Zhong, Lou Zhen, Yang Jingyu, et al. Face detection using template matching andskin-color information. Neurocomputing,2007,70(4-6):794-800.
[51] Lin C. Face detection in complicated backgrounds and different illumination conditionsby using YCbCr color space and neural network. Pattern Recognition Letters,2007,28(16):2190-2200.
[52] Kakumanu P, Makrogiannis S, Bourbakis N. A survey of skin-color modeling anddetection methods. Pattern Recognition,2007,40(3):1106-1122.
[53] Liu Yuanyuan, Yu Haibin, He Zhiwei, et al. Fast robust face detection under a skin colormodel with geometry constraints.2009International Conference on ComputationalIntelligence and Security, Beijing, China,2009:515-519.
[54] Singh S, Papanikolopoulos N P. Monitoring driver fatigue using facial analysis techniques.International Conference on Intelligent Transportation Systems, Tokyo, Japan: IEEE,1999:314-318.
[55] Wahlstrom E, Masoud O, Papanikotopoulos N P. Vision-based methods for drivermonitoring. Proceedings of the6th IEEE International Conference on IntelligentTransportation Systems, Shanghai, China,2003:903-908.
[56] Sing J K, Basu D K, Nasipuri M. Face recognition using point symmetry distance-basedRBF network. Applied Soft Computing,2007,7(1):58-70.
[57] Bai Li, Shen Linlin, Wang Yan. A novel eye location algorithm based on radial symmetrytransform.18th International Conference on Pattern Recognition, Hong Kong, China:IEEE,2006:511-514.
[58] Magee J J, Betke M, Gips J, et al. A human–computer interface using symmetry betweeneyes to detect gaze direction.IEEE Transactions on Systems, Man and Cybernetics, Part A:Systems and Humans,2008,38(6):1248-1261.
[59] Cootes T F, Twining C J, Babalola K O, et al. Diffeomorphic statistical shape models.Image and Vision Computing,2008,26(3):326-332.
[60] Cristinacce D, Cootes T F. Feature detection and tracking with constrained local models.Pattern Recognition,2008,41(10):3054-3067.
[61] Turk M, Pentland A. Eigen-faces for recognition. Journal of cognitive neuroscience,1991,3(1):71-86.
[62] Belhumeur P N, Hespanha J P, Kriegman D J. Eigenfaces vs.fisherfaces: recognition usingclass specific linear projection. IEEE Transactions on Pattern Analysis and MachineIntelligence,1997,19(7):711-720.
[63] Rowley H A, Baluja S, Kanade T. Neural network-based face detection. IEEETransactions on Pattern Analysis and Machine Intelligence,1998,20(1):23-38.
[64] El-Bakry H M, Stoyan H. Fast neural networks for sub-matrix (object/face) detection.Proceedings of the2004International Symposium on Circuits and Systems, VancouverBC, Canada,2004:764-767.
[65] Shih P, Liu Chengjun. Face detection using discriminating feature analysis and supportvector machine. Pattern Recognition,2006,39(2):260-276.
[66] Osuna E, Freund R, Girosi F. Training support vector machines: an application to facedetection.1997IEEE Computer Society Conference on Computer Vision and PatternRecognition, Puerto Rico: IEEE,1997:130-137.
[67] Nefian A V, Hayes M H. Face detection and recognition using hidden Markov models.1998International Conference on Image Processing, Chicago, USA: IEEE,1998:141-145.
[68] Brubaker S C, Wu Jianxin, Sun Jie. On the design of cascades of boosted ensembles forface detection. International journal of computer vision,2008,77(1-3):65-86.
[69] Chen H Y, Huang C L, Fu C M. Hybrid-boost learning for multi-pose face detection andfacial expression recognition. Pattern Recognition,2008,41(3):1173-1185.
[70] Pham M T, Chain T J. Fast training and selection of Haar features using statistics inboosting-based face detection.11th International Conference on Computer Vision, Rio deJaneiro, Brazil: IEEE,2007:1-7.
[71] Violas P, Jones M. Rapid object detection using a boosted cascade of simple features.2001IEEE Computer Society Conference on Computer Vision and Pattern Recognition,Kauai, Hawaii: IEEE,2001:511-518.
[72] Li S Z, Zhang Zhenqiu. FloatBoost learning and statistical face detection. IEEETransactions on Pattern Analysis and Machine Intelligence,2004,26(9)：1112-1123.
[73] Huang Dengyuan, Lin Tawei, Ho Chun-Ying, et al. Face detection based on featureanalysis and edge detection against skin color-like backgrounds.2010Fourth InternationalConference on Genetic and Evolutionary Computing, Shenzhen, China: IEEE,2010:687-690.
[74] Hidaka A, Kurita T. Co-occurrence of intensity and gradient features for object detection.Proceedings of the16th International Conference on Neural Information Processing: PartII, Bangkok, Thailand,2009:38-46.
[75] Shashua A, Riklin-Raviv T. The quotient image: class-based re-rendering and recognitionwith varying illuminations. IEEE Transactions on Pattern Analysis and MachineIntelligence.2001,23(2):129-139.
[76] Wang Yinghui, Ning Xiaojuan, Yang Chunxia. A method of illumination compensation forhuman face image based on quotient image. Information Sciences,2008,178(12):2705-2721.
[77] Xie Xiaohua, Lai Jianhuang, Suen C Y, et al. Non-ideal class non-point light sourcequotient image for face relighting. Signal Processing,2011,91(4):1048-1053.
[78] Lee S W, Moon S H, Lee S W. Face recognition under arbitrary illumination usingilluminated exemplars. Pattern Recognition,2007,40(5):1605-1620.
[79] Wang Haitao, Li S Z, Wang Yangsheng, et al. Illumination modeling and normalization forface recognition. IEEE International Workshop on Analysis and Modeling of Faces andGestures, Nice, France,2003:104-111.
[80] Wang Haitao, Li S Z, Wang Yangsheng. Generalized quotient image. Proceedings of the2004IEEE Computer Society Conference on Computer Vision and Pattern Recognition,Washington, DC, USA,2004:498-505.
[81] Georghiades A S, Kriegman D J, Belhurneur P N. Illumination cones for recognition undervariable lighting: faces.1998IEEE Computer Society Conference on Computer Visionand Pattern Recognition, Santa Barbara, CA, USA: IEEE,1998:52-58.
[82] Georghiades A S, Belhurneur P N, Kriegman D J. Illumination-based image synthesis:creating novel images of human faces under differing pose and lighting. IEEE Workshopon Multi-View Modeling and Analysis of Visual Scenes, Fort Collins, CO, USA: IEEE,1999:47-54.
[83] Ramamoorthi R, Hanrahan P. On the relationship between radiance and irradiance:determining the illumination from images of a convex Lambertian object. Journal of theOptical Society of America A: Optics, Image Science, and Vision,2001,18(10):2448-2459.
[84] Amberg B, Knothe R, Vetter T. Expression invariant3D face recognition with amorphable model.8th IEEE International Conference on Automatic Face&GestureRecognition, Amsterdam: IEEE,2008:1-6.
[85] Bustard J D, Nixon M S.3D morphable model construction for robust ear and facerecognition.2010IEEE Computer Society Conference on Computer Vision and PatternRecognition, San Francisco, CA, USA,2010:2582-2589.
[86] Paysan P, Knothe R, Amberg B. A3D face model for pose and illumination invariant facerecognition.6th IEEE International Conference on Advanced Video and Signal BasedSurveillance, Genova: IEEE,2009:296-301.
[87] Choi H C, Kim S Y, Oh S H. Pose invariant face recognition with3D morphable modeland neural network. IEEE International Joint Conference on Neural Networks, HongKong, China: IEEE,2008:4131-4136.
[88] Murphy-Chutorian E, Trivedi M M. Head pose estimation in computer vision: a survey.IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(4):607-626.
[89] Ng J, Gong S. Composite support vector machines for detection of faces across views andfose estimation. Image and Vision Computing,2002,20(5-6):359-368.
[90] Sherrah J, Gong S, Ong E J. Face distributions in similarity space under varying head pose.Image and Vision Computing,2001,19(12):807-819.
[91] Kohli P, Rihan J, Bray M, et al. Simultaneous segmentation and pose estimation ofhumans using dynamic graph cuts. International Journal of Computer Vision,2008,79(3):285-298.
[92] Ma Bingpeng, Zhang Wenchao, Shiguang Shan, et al. Robust head pose estimation usingLGBP. Proceedings of the18th International Conference on Pattern Recognition-Volume02, Hong Kong, China,2006:512-515.
[93] Li Yongmin, Gong Shaogang, Sherrah J, et al. Support vector machine based multi-viewface detection and recognition. Image and Vision Computing,2004,22(5):413-427.
[94] Zhang Zhenqiu, Hu Yuxiao, Liu Ming, et al. Head pose estimation in seminar room usingmulti-view face detectors. Proceedings of the1st international evaluation conference onClassification of events, activities and relationships, Southampton, UK,2007:299-304.
[95] Okada R, Soatto S. Relevant feature selection for human pose estimation and localizationin cluttered images. Proceedings of the10th European Conference on Computer Vision:Part II, Marseille, France,2008:434-445.
[96] Bissacco A, Yang M H, Soatto S. Fast human pose estimation using appearance andmotion via multi-dimensional boosting regression.2007IEEE Conference on ComputerVision and Pattern Recognition, Minneapolis, MN, USA: IEEE,2007:1-8.
[97] Gourier N, Maisonnasse J, Hall D, et al. Head pose estimation on low resolution images.Proceedings of the1st international evaluation conference on Classification of events,activities and relationships, Southampton, UK,2007:270-280.
[98] Ma Yong, Konishi Y, Kinoshita K, et al. Sparse bayesian regression for head poseestimation.18th International Conference on Pattern Recognition, Hong Kong, China:IEEE,2006:507-510.
[99] Moon H, Miller M L. Estimating facial pose from sparse representation. InternationalConference on Image Processing, Singapore,2004:75-78.
[100] Balasubramanian V N, Ye Jieping, Panchanathan S. Biased manifold embedding: aframework for person-independent head pose estimation. IEEE Conference on ComputerVision and Pattern Recognition, Minneapolis, MN: IEEE,2007:1-7.
[101] Gui Zhenghui, Zhang Chao.3D head pose estimation using non-rigidstructure-from-motion and point correspondence. IEEE Region10Conference TENCON,Hong Kong, China: IEEE,2006:1-3.
[102] Matthews I, Baker S. Active appearance models revisited. International Journal ofComputer Vision,2004,60(2):135-164.
[103] Wu J, Trivedi M. A two-stage head pose estimation framework and evaluation. PatternRecognition,2008,41(3):1138-1158.
[104] XIAO JING, Simon B, Iain M. Real-time combined2D+3D active appearance models.proceedings of the2004IEEE Computer Society Conference on Computer Vision andPattern Recognition, Washington, DC, USA: IEEE,2004:535-542.
[105] Schweighofer G, Pinz A. Robust pose estimation from a planar target. IEEE Transactionson Pattern Analysis and Machine Intelligence,2006,28(12):2024-2030.
[106] Ho S Y, Huang H L. An analytic solution for the pose determination of human faces froma monocular image. Pattern Recognition Letters,1998,19(11):1045-1054.
[107] Ji Qiang.3D Face pose estimation and tracking from a monocular camera. Image andVision Computing,2002,20(7):499-511.
[108] Yilmaz A, Shah M A. Automatic feature detection and pose recovery for faces. The5thAsian Conference on Computer Vision, Melbourne, Australia,2002:23-25.
[109] Horprasert T, Yacoob Y, Davis L S. Computing3-D head orientation from a monocularimage sequence. Second IEEE International Conference on Automatic Face and GestureRecognition, Killington, Vermont,1996:242-250.
[110] Dinges D F, Mallis M, Maislin G, et al. Evaluation of techniques for ocular measurementas an index of fatigue and the basis for alertness management, Dept. Transp. HighwaySafety, pub.808762,1998.
[111] Ito T, Mita S, Kozuka K, et al. Driver blink measurement by the motion picture processingand its application to drowsiness detection. The IEEE5th International Conference onIntelligent Transportation Systems, Nagoya, Japan: IEEE,2002:168-173.
[112] Benedetto S, Pedrotti M, Minin L, et al. Driver workload and eye blink duration.Transportation Research Part F: Traffic Psychology and Behaviour,2010,14(3):199-208
[113] Fan Xiao, Yin Baocai, Sun Yanfeng. Yawning detection for monitoring driver fatigue.International Conference on Machine Learning and Cybernetics, Hong Kong, China,2007:664-668.
[114] Vural E, Cetin M, Ercil A, et al. Drowsy driver detection through facial movementanalysis. IEEE International Conference on Computer Vision, Human ComputerInteraction Workshop, Springer Berlin/Heidelberg,2007:6-18
[115] D'Orazio T, Leo M, Guaragnella C, et al. A visual approach for driver inattention detection.Pattern Recognition,2007,40(8):2341-2355.
[116] Saradadevi M, Bajaj P. Driver fatigue detection using mouth and yawning analysis.International Journal of Computer Science and Network Security,2008,8(6):183-188.
[117] Sigari M H. Driver hypo-vigilance detection based on eyelid behavior.2009SeventhInternational Conference on Advances in Pattern Recognition, Kolkata,2009:426-429.
[118] Liu Danghui, Sun Peng, Xiao YanQing. Drowsiness detection based on eyelid movement.2010Second International Workshop on Education Technology and Computer Science(ETCS), Wuhan, China,2010:49-52.
[119]梁铨廷.物理光学.北京：机械工业出版社，1980.
[120]张广军.机器视觉.北京：科学出版社，2005.
[121] Otsu N A. Threshold selection method from gray-level histograms. IEEE Transactions onSystems Man and Cybernetics,1979,9(1):62-66.
[122] Zhou Huiyu, Yuan Yuan, Shi Chunmei. Object tracking using SIFT features and meanshift. Computer Vision and Image Understanding,2009,113(3):345-352.
[123] Spagnoloa P, Orazio T D, Leoa M, et al. Moving object segmentation by backgroundsubtraction and temporal analysis. Image and Vision Computing,2006,24(5):411-423.
[124] Stauffer C, Grimson W E L. Learning patterns of activity using real-time tracking. IEEETransactions on Pattern Analysis and Machine Intelligence,2000,22(8):747-757.
[125] Kim K, Chalidabhongse T H, Harwood D, et al. Real-time foreground–backgroundsegmentation using codebook model. Real-Time Imaging,2005,11(3):172-185.
[126] Tsai R, Huang T S. Uniqueness and estimation of3D motion parameters of rigid objectswith curved surfaces. IEEE Transactions on Pattern Analysis and Machine Intelligence,1984,6(1):13-27.
[127]于洪川,唐泽圣,唐龙.运动参数估计与图像校正.模式识别与人工智能,2003,16(1):22-27
[128] Wang Xunheng, Huang Haiqing, Ruan Zongcai, et al. Fast face orientation estimationfrom an uncalibrated monocular camera. Congress on Image and Signal Processing, Sanya,China,2008:186-190.
[129]李雄飞，张存利，李鸿鹏，等.医学图像配准技术进展.计算机科学,2010,37(7):27-33.
[130] Dinges D F, Arora S, Darwish M, et al. Pharmacodynamic effects on alertness of singledoses of armodafinil in healthy subjects during a nocturnal period of acute sleep loss.Current Medical Research and Opinion,2006,22(1):159-167.
[131] Carroll J S, Blisewise D L, Dement W C. A method for checking interobserver reliabilityin observational sleep studies. Sleep,1989,12(4):363-367.
[132] Wierwille W W, Ellsworth L A. Evaluation of driver drowsiness by trained observers.Accident Analysis and Prevention,1994,26(5):571-581.
[133]张连文，郭海鹏.贝叶斯网引论.北京：科学出版社，2006.
[134]王双成.贝叶斯网络学习、推理与应用.上海：立信会计出版社，2009.
[135] Landis J R, Koch G G. The measurement of observer agreement for categorical data.Biometrics,1977,33(1):159-174.