基于圆形目标成像分析的人体头部姿态信息测量研究
|
摘要
头部姿态信息测量是机器视觉与模式识别领域中的重要研究课题，其主要研究目的是测量头部在三维空间中的姿态信息参数。现有的头部姿态信息测量技术多存在设备复杂和计算量大等缺点。本文基于光电信息测量原理，提出了一种基于单目视觉测量与几何目标相结合的动态头部姿态信息测量新方法。通过对固定于人体头部的几何目标进行光学成像分析，获得几何目标成像与姿态角度之间的关系，进而实现人体头部姿态信息的计算。本文提出并设计的头部姿态信息测量系统通过实验测量验证达到了预期效果。本文研究为使头部姿态信息测量更加简单实用提供了一种新的有效途径。全文的主要研究内容和创新性工作如下：
（1）提出了基于圆形目标成像分析的人体头部姿态信息测量方法。通过对现有头部姿态信息测量技术的分析，提出了基于单目视觉测量与几何目标相结合的头部姿态信息测量技术。研究了球形和圆形两种几何目标在头部姿态信息测量中的优缺点，并选择圆形作为头部姿态信息测量的附加几何目标。对圆形目标的设计方法及安装方式进行了研究。通过分析运动过程中圆形目标及标注其上的两条直径在摄像机成像平面的成像变化，实现对人体头部姿态信息的测量。
（2）提出了一种基于光学成像分析的圆形目标旋转角度计算方法。基于摄像机光学成像原理，分析了当圆形目标与摄像机处于不同相对姿态时圆形目标的成像。并在此基础上，分别分析了当人体头部做简单运动和复杂运动时标注于圆形目标上两条直径的成像变化情况。并通过几何推导给出了简单情况和复杂情况下圆形目标俯仰角、滚转角和偏航角的计算方法。
（3）提出了一种基于直径成像分析的圆形目标姿态二义性消除方法。从圆形目标图像中提取两条直径所成的像，通过分析直径所成像的斜率以及半径所成像的长度，判断圆形目标相对于初始位置的运动方向，进而实现确定圆形目标姿态，可以消除在计算圆形目标姿态时通常出现的姿态二义性现象。
（4）提出了一种普通光学成像条件下圆形目标图像的处理方法。在普通光学成像条件下，头部姿态信息测量系统所采集的圆形目标图像多属于弱成像质量图像。提出了小波降噪、灰度变换、直方图处理及图像二值化等弱成像质量图像处理的步骤。采用该方法，圆形目标图像质量得到提高，并且获得了圆形目标的二值图像。
（5）研究了基于圆形目标成像分析的人体头部姿态信息测量系统的结构，并设计了头部姿态信息测量的软件系统。提出了基于圆形目标直径的头部初始位置判定方法，并提出基于斜率的两条直径区分方法。对本文中设计的系统进行了实验研究，通过模拟实验和人体头部实验，验证了本系统的可行性。本项研究具有重要的理论和实用价值。
Measurement of human head pose is an important research topic in the fields of machine visionand pattern recognition. The main research purpose is to measure the pose parameters of the head inthree-dimensional space. There are shortcomings such as complex equipments and huge computationsin the existing technologies of head pose measurement. Based on the photoelectronic informationmeasurement principle, a new measurement method of dynamic head pose based on monocular visionmeasurement and geometric target is proposed. The relation between the geometric target’s imagingand pose angles is obtained by analyzing the optical imaging of the geometric target which is fixed onthe head, and then the head pose parameters are calculated. The system of head pose measurementproposed in this paper can meet the expected effect by the experiments. The research in this paper hasproposed a new effective approach to make the head pose measurement system simplier and morepractical. The main research and innovations are as follows:
(1) A measurement method of head pose using imaging analysis of circular target is proposed inthis paper. The measurement technology of head pose based on monocular vision measurement andgeometric target is proposed after analyzing the existing technologies of head pose measurement. Theadvantages and faults of two common geometric targets-sphere and circle, are studied in themeasurement of head pose and at last the circle is chosen as the additive geometric target. Thedesigning and installation of circular target are studied. The information of head pose can be measuredby analysing the imaging changes of circular target and two diameters marked on the circular target inthe camera image plane.
(2) The computation methods of rotation angles of circular target based on the optical imaginganalysis are proposed. Based on the principle of camera optical imaging, the imagings of circulartarget are analyzed when the circular target and the camera are in different poses. And on these bases,the imaging changes of the two diameters are studied separately when the head does simple andcomplex motions. The computation methods of pitch angle, roll angle and yaw angle in simple andcomplex situations are proposed separately by the geometric derivation method.
(3) A method of eliminating the pose duality of circular target based on imaging analysis ofdiameter is proposed. The imagings of the two diameters are extracted from the circular target images.The motion direction with respect to the initial position can be judged by analyzing the slopes of thetwo diameters’ imagings and the lengths of radii’s imagings. And then the pose of the circular targetcan be determined. This method can elimitate the pose duality which often occurs in the process ofcalculating the pose of circular target.
(4) The processing method of circular target images in the circumstance of common opticalimaging is studied. The circular targer images are often with poor imaging quality when the head posemeasurement system works in the circumstance of common optical imaging. The processingprocedures of wavelet denosing, gray level transformation, histogram processing, and imagebinarization are proposed for the images with poor imaging quality. The quality of the image isimproved after the processing. And binary images of circular target are obtained.
(5) The composition of the measurement system of head pose based on imaging analysis ofcircular target is studied. The software system of the measurement of head pose is also designed. Thedecision method of head’s initial position based on the diameters of the circular target is proposed.
The method of distinguishing the two diameters based on the slopes of the diameters is also proposed.Experimental research is also done using the system we proposed in this paper. The fesiblity of thesystem is verified by simulated experiment and head experiment. The research in this paper is ofsignificant theoretical and practical value.
（1）提出了基于圆形目标成像分析的人体头部姿态信息测量方法。通过对现有头部姿态信息测量技术的分析，提出了基于单目视觉测量与几何目标相结合的头部姿态信息测量技术。研究了球形和圆形两种几何目标在头部姿态信息测量中的优缺点，并选择圆形作为头部姿态信息测量的附加几何目标。对圆形目标的设计方法及安装方式进行了研究。通过分析运动过程中圆形目标及标注其上的两条直径在摄像机成像平面的成像变化，实现对人体头部姿态信息的测量。
（2）提出了一种基于光学成像分析的圆形目标旋转角度计算方法。基于摄像机光学成像原理，分析了当圆形目标与摄像机处于不同相对姿态时圆形目标的成像。并在此基础上，分别分析了当人体头部做简单运动和复杂运动时标注于圆形目标上两条直径的成像变化情况。并通过几何推导给出了简单情况和复杂情况下圆形目标俯仰角、滚转角和偏航角的计算方法。
（3）提出了一种基于直径成像分析的圆形目标姿态二义性消除方法。从圆形目标图像中提取两条直径所成的像，通过分析直径所成像的斜率以及半径所成像的长度，判断圆形目标相对于初始位置的运动方向，进而实现确定圆形目标姿态，可以消除在计算圆形目标姿态时通常出现的姿态二义性现象。
（4）提出了一种普通光学成像条件下圆形目标图像的处理方法。在普通光学成像条件下，头部姿态信息测量系统所采集的圆形目标图像多属于弱成像质量图像。提出了小波降噪、灰度变换、直方图处理及图像二值化等弱成像质量图像处理的步骤。采用该方法，圆形目标图像质量得到提高，并且获得了圆形目标的二值图像。
（5）研究了基于圆形目标成像分析的人体头部姿态信息测量系统的结构，并设计了头部姿态信息测量的软件系统。提出了基于圆形目标直径的头部初始位置判定方法，并提出基于斜率的两条直径区分方法。对本文中设计的系统进行了实验研究，通过模拟实验和人体头部实验，验证了本系统的可行性。本项研究具有重要的理论和实用价值。
Measurement of human head pose is an important research topic in the fields of machine visionand pattern recognition. The main research purpose is to measure the pose parameters of the head inthree-dimensional space. There are shortcomings such as complex equipments and huge computationsin the existing technologies of head pose measurement. Based on the photoelectronic informationmeasurement principle, a new measurement method of dynamic head pose based on monocular visionmeasurement and geometric target is proposed. The relation between the geometric target’s imagingand pose angles is obtained by analyzing the optical imaging of the geometric target which is fixed onthe head, and then the head pose parameters are calculated. The system of head pose measurementproposed in this paper can meet the expected effect by the experiments. The research in this paper hasproposed a new effective approach to make the head pose measurement system simplier and morepractical. The main research and innovations are as follows:
(1) A measurement method of head pose using imaging analysis of circular target is proposed inthis paper. The measurement technology of head pose based on monocular vision measurement andgeometric target is proposed after analyzing the existing technologies of head pose measurement. Theadvantages and faults of two common geometric targets-sphere and circle, are studied in themeasurement of head pose and at last the circle is chosen as the additive geometric target. Thedesigning and installation of circular target are studied. The information of head pose can be measuredby analysing the imaging changes of circular target and two diameters marked on the circular target inthe camera image plane.
(2) The computation methods of rotation angles of circular target based on the optical imaginganalysis are proposed. Based on the principle of camera optical imaging, the imagings of circulartarget are analyzed when the circular target and the camera are in different poses. And on these bases,the imaging changes of the two diameters are studied separately when the head does simple andcomplex motions. The computation methods of pitch angle, roll angle and yaw angle in simple andcomplex situations are proposed separately by the geometric derivation method.
(3) A method of eliminating the pose duality of circular target based on imaging analysis ofdiameter is proposed. The imagings of the two diameters are extracted from the circular target images.The motion direction with respect to the initial position can be judged by analyzing the slopes of thetwo diameters’ imagings and the lengths of radii’s imagings. And then the pose of the circular targetcan be determined. This method can elimitate the pose duality which often occurs in the process ofcalculating the pose of circular target.
(4) The processing method of circular target images in the circumstance of common opticalimaging is studied. The circular targer images are often with poor imaging quality when the head posemeasurement system works in the circumstance of common optical imaging. The processingprocedures of wavelet denosing, gray level transformation, histogram processing, and imagebinarization are proposed for the images with poor imaging quality. The quality of the image isimproved after the processing. And binary images of circular target are obtained.
(5) The composition of the measurement system of head pose based on imaging analysis ofcircular target is studied. The software system of the measurement of head pose is also designed. Thedecision method of head’s initial position based on the diameters of the circular target is proposed.
The method of distinguishing the two diameters based on the slopes of the diameters is also proposed.Experimental research is also done using the system we proposed in this paper. The fesiblity of thesystem is verified by simulated experiment and head experiment. The research in this paper is ofsignificant theoretical and practical value.
引文
[1] Y. Mitelman, J. Enderle. Building a mathematical model of the head-neck system; modelingand simulation of the6-degree of freedom head movement. Proceedings of the IEEE27th AnnualNortheast Bioengineering Conference,2001:81-82.
[2]陶忠祥.位置敏感探测器在头位跟踪中的应用研究,[博士学位论文].长春：中国科学院长春光学精密机械与物理研究所，2004.
[3]赵刚强.基于视觉的大范围头部姿态跟踪关键技术研究，[博士学位论文].浙江：浙江大学，2009.
[4]孟举.基于视频图像处理的头部位置跟踪算法研究，[硕士学位论文].西安：西北工业大学，2007.
[5]田晓焱.基于机器视觉的头盔瞄准具转动角度的测量，[硕士学位论文].西安：西北大学，2006.
[6]戚建中.头盔瞄准/显示系统研究.电光与控制，1997，（3）：33-36.
[7]刘涛，赵国荣，李冀鑫.头盔显示器的光电技术发展研究.光电技术应用，2005，20（3）：1-10.
[8]刘红漫. HMS/HMD关键技术指标及发展方向的预测与研究，[硕士学位论文].北京：北京航空航天大学，2000.
[9] C. H. Morimoto, M. R.M. Mimica. Eye gaze tracking techniques for interactive applications.Computer Vision and Image Understanding,2005,98(1):4-24.
[10] G. Kuhn, V. Benson, S. Fletcher-Watson, et al. Eye movements affirm: automatic overt gazeand arrow cueing for typical adults and adults with autism spectrum disorder. Experimental BrainResearch,2010,201(2):155-165.
[11] E. Schneider, M. Maruyama, S. Dehaene, et al. Eye gaze reveals a fast, parallel extraction ofthe syntax of arithmetic formulas. Cognition,2012,125(3):475-490.
[12] R. Valenti, N. Sebe, T. Gevers. Combining head pose and eye location information for gazeestimation. IEEE Transactions on Image Processing,2012,21(2):802-815.
[13] R. Valenti, A. Lablack, N. Sebe. Visual gaze estimation by joint head and eye information.Proceedings of the20th International Conference on Pattern Recognition (ICPR),2010:3870-3873.
[14] K. Sankaranarayanan, M. C. Chang, N. Krahnstoever. Tracking gaze direction from far-fieldsurveillance cameras. IEEE Workshop on Applications of Computer Vision (WACV),2011:519-526.
[15] A. Doshi, M. M. Trivedi. Head and eye gaze dynamics during visual attention shifts incomplex environments. Journal of Vision,2012,12(2):1-16.
[16] W. P. Medendorp, B.J.M. Melis, C.C.A.M.Gielen, et al. Off-centric rotation axes in naturalhead movements: Implications for the vestibular reafference and kinematic redundancy. Journal ofNeurophysiology,1998,79(4):2025-2039.
[17] R. Goldenberg, R. Kimmel, E. Rivlin, et al. Behavior classification by eigendecompositionof periodic motion. Pattern Recognition,2005,38(7):1033-1043.
[18] O. C. Jenkins, M. J. Mataric. Deriving action and behavior primitives from human motiondata. Proceedings of2002IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS-2002),2002,3:2551-2556.
[19] L. Itti. Quantifying the contribution of low-level saliency to human eye movements indynamic scenes. Visual Cognition,2005,12(6):1093-1123.
[20] J Hy n. The use of eye movements in the study of multimedia learning. Learning andInstruction,2010,20(2):172-176.
[21] S. R. H. Langton, H. Honeyman, E. Tessler. The influence of head contour and nose angleon the perception of eye-gaze direction. Perception&Psychophysics,2004,66(5):752-771.
[22]郑兵，宋福群.远程医疗应用中无线便携式头盔的设计.医疗卫生设备，2007，28（9）：9-10，13.
[23] Q. J. Zhao, X. M. Shi, Y. X. Wang. Head-pose recognition for a game system based onnose's relative position. Human-computer interaction: users and applications, LNCS,2011,6764:694-701.
[24] Y. Zhu, K. Fujimura. Head pose estimation for driver monitoring. Proceedings of IEEEIntelligent Vehicles Symposium,2004:501-506.
[25] P. Smith, M. Shah, N. D. V. Lobo. Monitoring head/eye motion for driver alertness with onecamera. Proceedings of the15th International Conference on Pattern Recognition.2000,4:636-642.
[26] Q. Ji, X. J. Yang. Real-time eye, gaze, and face pose tracking for monitoring driver vigilance.Real-Time Imaging,2002,8(5):357-377.
[27] E. Murphy-Chutorian, M. M. Trivedi. Head pose estimation and augmented reality tracking:an integrated system and evaluation for monitoring driver awareness. IEEE Transactions on IntelligentTransportation Systems,2010,11(2):300-311.
[28] Y. C. Dong, Z. C. Hu, K. Uchimura, et al. Driver inattention monitoring system forintelligent vehicles: A review. IEEE Transactions on Intelligent Transportation Systems,2011,12(2):596-614.
[29] A. Doshi, S. Y. Cheng, M. M. Trivedi. A novel active heads-up display for driver assistance.IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics,2009,39(1):85-93.
[30] S. J. Lee, J. Jo, H. G. Jung, et al. Real-time gaze estimator based on driver's head orientationfor forward collision warning system. IEEE Transactions on Intelligent Transportation Systems,2011,12(1):254-267.
[31] A. Schulz, N. Damer, M. Fischer, et al. Combined head localization and head poseestimation for video–based advanced driver assistance systems. Pattern Recognition,2011,6835:51-60.
[32]王永年，祝梁生，孙隆和.头盔显示/瞄准系统.北京：国防工业出版社，1994.
[33]王永年.头盔显示器的任务、现状和研究方向.电光与控制，1999，（2）：1-9.
[34] X. Z. Zhang, Y. S. Gao. Face recognition across pose: A review. Pattern recognition,2009,42(1):2876-2896.
[35] X. X. Zhu, D. Ramanan. Face detection, pose estimation, and landmark localization in thewild. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2012:2879-2886.
[36] D. Huang, M. Storer, F. De la Torre, et al. Supervised local subspace learning for continuoushead pose estimation. Proceedings of the IEEE Conference on Computer Vision and PatternRecognition (CVPR),2011:2921-2928.
[37] S. I. Choi, C. H. Choi, N. Kwak. Face recognition based on2D images under illuminationand pose variations. Pattern Recognition Letters,2011,32(4):561-571.
[38] G. Fanelli, J. Gall, L. Van Gool. Real time3D head pose estimation: Recent achievementsand future challenges. Proceedings of the5th International Symposium on Communications Controland Signal Processing (ISCCSP),2012:1-4.
[39] C.S. Chang, C.C. Chen, C.F. Juang. Vision-based3D head pose tracking using fuzzyclassifier-based face segmentation and silhouette volume intersection. Proceedings of the InternationalConference on Fuzzy Theory and it's Applications (iFUZZY),2012:363-368.
[40] A. Schulz, R. Stiefelhagen. Video-based pedestrian head pose estimation for risk assessment.Proceedings of the15th International IEEE Conference on Intelligent Transportation Systems (ITSC),2012:1771-1776.
[40] S. J. Ray, J. Teizer. Coarse head pose estimation of construction equipment operators toformulate dynamic blind spots. Advanced Engineering Informatics,2012,26(1):117-130.
[41] M. B. Holte, C. Tran, M. M. Trivedi, et al. Human pose estimation and activity recognitionfrom multi-view videos: comparative explorations of recent developments. IEEE Journal of SelectedTopics in Signal Processing,2012,6(5):538-552.
[42] S. C. Chen, C. H. Wu, S. Y. Lin, et al.2D face alignment and pose estimation based on3Dfacial models. Proceedings of the IEEE International Conference on Multimedia and Expo (ICME),2012:128-133.
[43] E. Murphy-Chutorian, M. M. Trivedi. Head pose estimation in computer vision: a survey.IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(4):607-626.
[44] D. J. Beymer. Face recognition under varying pose. Proceedings of the IEEE ComputerSociety Conference on Computer Vision and Pattern Recognition,1994:756-761.
[45] D. O. Gorodnichy, S. Malik, G. Roth. Affordable3D face tracking using projective vision.Proceedings of the International Conference on Vision Interfaces，2002:383-390.
[46] R. Ruddarraju, A. Haro, I. Essa. Fast multiple camera head pose tracking. Proceedings of theInternational Conference on Vision Interfaces,2003:1-7.
[47] R. G. Yang, Z. Y. Zhang. Model-based head pose tracking with stereo vision. Proceedings ofthe IEEE International Conference on Automatic Face and Gesture Recognition,2002:255-260.
[48] L. P. Morency, T. Darrell. Stereo tracking using ICP and normal flow constraint.Proceedings of the16th International Conference on Pattern Recognition,2002,4:367-372.
[49] K. Terada, A. Oba, A. Ito.3D human head tracking using hypothesized polygon model.Proceedings of the2005IEEE International Conference on Systems, Man and Cybernetics,2005,2:1396-1401.
[50] Q. Ji.3D Face pose estimation and tracking from a monocular camera. Image and VisionComputing,2002,20(7):499-511.
[51] S. Birchfield. Elliptical head tracking using intensity gradients and color histograms.Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,1998:232-237.
[52] R. Wooju, K. Daijin. Real-time3D head tracking and head gesture recognition. Proceedingof the16th IEEE International Symposium on Robot and Human interactive Communication,2007:169-172.
[53] T. Maurer, C. V. D. Malsburg. Tracking and learning graphs on image sequences of faces.Artificial Neural Networks—ICANN96, LNCS,1996,1112:323-328.
[54] T. Horprasert, Y. Yacoob, L. S. Davis. Computing3-D head orientation from a monocularimage sequence. Proceedings of the SPIE2962, the25th AIPR Workshop: Emerging Applications ofComputer Vision,1997:244-249.
[55] D. Machin. Real-time facial analysis for virtual teleconferencing. Proceedings of the SecondInternational Conference on Automatic Face and Gesture Recognition,1996:340–344.
[56] A. Zelinsky, J. Heinzmann. Real-time visual recognition of facial gestures forhuman-computer interaction. Proceedings of the Second International Conference on Automatic Faceand Gesture Recognition,1996:351-356.
[57] E. Petajean, H. P. Graf. Robust face feature analysis for automatic speech reading andcharacter animation. Proceedings of the Second International Conference on Automatic Facial andGesture Recognition,1996:357–362.
[58] A. Bleiweiss, M. Werman. Robust head pose estimation by fusing time-of-flight depth andcolor. IEEE International Workshop on Multimedia Signal Processing (MMSP),2010:116-121.
[59]陆钧昀.基于图像处理的无人机姿态测量，[硕士学位论文].西安：西安电子科技大学，2007.
[60]曹万鹏.基于立体视觉的三维运动测量若干关键技术研究，[博士学位论文].哈尔滨：哈尔滨工业大学，2007.
[61] L. P. Morency, J. Whitehill, J. Movellan. Monocular head pose estimation using generalizedadaptive view-based appearance model. Image and Vision Computing,2010,28(5):754-761.
[62] S. Niyogi, W. T. Freeman. Example-based head tracking. Proceedings of the SecondInternational Conference on Automatic Face and Gesture Recognition.1996:374-378.
[63] M. Romero, A. Bobick. Tracking head yaw by interpolation of template responses.Proceedings of the conference on computer vision and pattern recognition workshop (CVPRW’04),2004:83.
[64] J. Ng, S. G. Gong. Composite support vector machines for detection of faces across viewsand pose estimation. Image and Vision Computing,2002,20(5-6):359-368.
[65] J. Ng, S. G. Gong. Multi-view face detection and pose estimation using a composite supportvector machine across the view sphere. Proceedings of the International Workshop on Recognition,Analysis, and Tracking of Faces and Gestures in Real-Time Systems,1999:14-21.
[66] R. Gonzalez, R. Woods. Digital image processing. London: Prentice-Hall,2002:582-584.
[67] J. Sherrah, S. Gong, E. J. Ong. Understanding pose discrimination in similarity space.Proceedings of the10th British Machine Vision Conference,1999:523-532.
[68] J. Sherrah, S. Gong, E. J. Ong. Face distributions in similarity space under varying headpose. Image and Vision Computing,2001,19(12):807-819.
[69] E. Osuna, R. Freund, F. Girosi. Training support vector machines: An application to facedetection. Proceedings of the IEEE Computer Society Conference on Computer Vision and PatternRecognition,1997:130-136.
[70] H.A. Rowley, S. Baluja, T. Kanade. Neural network-based face detection. IEEETransactions on Pattern Analysis and Machine Intelligence,1998,20(1):23-38.
[71] P. Viola, M. Jones. Rapid object detection using a boosted cascade of simple features.Proceedings of the2011IEEE Computer Society Conference on Computer Vision and PatternRecognition,2001,1:511-518.
[72] J. Huang, X. H. Shao, H. Wechsler. Face pose discrimination using support vector machines(SVM). Proceedings of the14th International Conference on Pattern Recognition,1998,1:154-156.
[73] Z. Q. Zhang, Y.X. Hu, M. Liu, et al. Head pose estimation in seminar room using multi viewface detectors. Proceedings of the CLEAR2006,2007:299-304.
[74] H. A. Rowley, S. Baluja, T. Kanade. Rotation invariant neural network-based face detection.Proceedings of the1998IEEE Computer Society Conference on Computer Vision and PatternRecognition,1998:38-44.
[75] Y. M. Li, S. G. Gong, H. Liddell. Support vector regression and classification basedmulti-view face detection and recognition. Proceedings of the Fourth IEEE International Conferenceon Automatic Face and Gesture Recognition,2000:300-305.
[76] Y. M. Li, S. G. Gong, J. Sherrah, et al. Support vector machine based multi-view facedetection and recognition. Image and Vision Computing,2004,22(5):413-427.
[77] E. Murphy-Chutorian, A. Doshi, M. M. Trivedi. Head pose estimation for driver assistancesystems: a robust algorithm and experimental evaluation. Proceedings of IEEE IntelligentTransportation Systems Conference,2007:709-714.
[78] Y. Ma, Y. Konishi, K. Kinoshita, et al. Sparse bayesian regression for head pose estimation.Proceedings of the18th International Conference on Pattern Recognition,2006,3:507-510.
[79] H. Moon, M. L. Miller. Estimating facial pose from a sparse representation (face recognitionapplications). Proceedings of the2004International Conference on Image Processing,2004,1:75-78.
[80] C. Bishop. Neural networks for pattern recognition. London: Oxford Univ. Press,1995.
[81] R. O. Duda, P. E. Hart, D. G. Stork. Pattern classification (2nd edition). New York: JohnWiley&Sons,2001.
[82] L. M. Brown, Y. L. Tian. Comparative study of coarse head pose estimation. Proceedings ofthe IEEE Workshop on Motion and Video Computing,2002:125-130.
[83] B. Schiele, A. Waibel. Gaze tracking based on face-color. Proceedings of IEEE InternationalWorkshop on Automatic Face-and Gesture-Recognition,1995:344-349.
[84] L. Zhao, G. Pingali, I. Carlbom. Real-time head orientation estimation using neural networks.Proceedings of the2002International Conference on Image Processing,2002,1:297-300.
[85] E. Seemann, K. Nickel, R. Stiefelhagen. Head pose estimation using stereo vision forhuman-robot interaction. Proceedings of the sixth IEEE International Conference on Automatic Faceand Gesture Recognition,2004:626-631.
[86] R. Stiefelhagen, L. Yang, A. Waibel. Modeling focus of attention for meeting indexing basedon multiple cues. IEEE Transactions on Neural Networks,2002,13(4):928-938.
[87] R. Stiefelhagen. Estimating head pose with neural networks-results on the pointing04ICPRworkshop evaluation data. Proceedings of ICPR Workshop on Visual Observation of Deictic Gestures,2004.
[88] M. Voit, K. Nickel, R. Stiefelhagen. Neural network-based head pose estimation andmulti-view fusion. Multimodal Technologies for Perception of Humans, LNCS,2007,4122:291-298.
[89] M. Voit, K. Nickel, R. Stiefelhagen. Head pose estimation in single-and multi-viewenvironments results on the CLEAR’07Benchmarks. Multimodal Technologies for Perception ofHumans, LNCS,2008,4625:307-316.
[90] Y. L. Tian, L. Brown, J. Connell, et al. Absolute head pose estimation from overheadwide-angle cameras. Proceedings of the IEEE International Workshop on Analysis and Modeling ofFaces and Gestures,2003:92-99.
[91] M. Voit, K. Nickel, R. Stiefelhagen. A bayesian approach for multi-view head poseestimation. Proceedings of the2006IEEE International Conference on Multisensor Fusion andIntegration for Intelligent Systems,2006:31-34.
[92] R. Rae, H. J. Ritter. Recognition of human head orientation based on artificial neuralnetworks. IEEE Transactions on Neural Networks,1998,9(2):257-265.
[93] V. Krüger, G. Sommer. Gabor wavelet networks for efficient head pose estimation. Imageand Vision Computing,2002,20(9-10):665-672.
[94] J. Bruske, E. Abraham-Mumm, J. Pauli, et al. Head-pose estimation from facial images withsubspace neural networks. Proceedings of International Conference on Neural Networks and Brain,1998:528-531.
[95] N. Gourier, D. Hall, J. L. Crowley. Estimating face orientation from robust detection ofsalient facial structures. Proceedings of ICPR Workshop on Visual Observation of Deictic Gestures,2004:17-25.
[96] N. Gourier, J. Maisonnasse, D. Hall, et al. Head pose estimation on low resolution images.Multimodal Technologies for Perception of Humans, LNCS,2007,4122:270-280.
[97] Y. L. Cun, L. Bottou, Y. Bengio, et al. Gradient-based learning applied to documentrecognition. Proceedings of IEEE,1998,86(11):2278-2324.
[98] M. Osadchy, M. L. Miller, Y. L. Cun. Synergistic face detection and pose estimation withenergy-based models. The Journal of Machine Learning Research,2007,8:1197-1215.
[99] M. Osadchy, Y. L. Cun, M.L. Miller, et al. Synergistic face detection and pose estimationwith energy-based model. Proceedings of Advances in Neural Information Processing Systems,2005:1017-1024.
[100] C. BenAbdelkader. Robust head pose estimation using supervised manifold learning.Computer Vision–ECCV2010, LNCS,2010,6316:518-531.
[101] J. Wu, M. M. Trivedi. A two-stage head pose estimation framework and evaluation. PatternRecognition,2008,41(3):1138-1158.
[102] S. J. McKenna, S. Gong. Real-time face pose estimation. Real-Time Imaging,1998,4(5):333-347.
[103] S. Srinivasan, K. L. Boyer. Head pose estimation using view based eigenspaces.Proceedings of the16th International Conference on Pattern Recognition,2002,4:302-305.
[104] S. Z. Li, Q. D. Fu, L. Gu, et al. Kernel machine based learning for multi-view facedetection and pose estimation. Proceedings of the8th IEEE International Conference on ComputerVision,2001,2:674-679.
[105] B. P. Ma, W. C. Zhang, S. G. Shan, et al. Robust head pose estimation using LGBP.Proceedings of the18th International Conference on Pattern Recognition,2006,2:512-515.
[106] L. B. Chen, L. Zhang, Y. X. Hu, et al. Head pose estimation using fisher manifold learning.Proceedings of the IEEE International Workshop on Analysis and Modeling of Faces and Gestures,2003:203-207.
[107] B. Raytchev, I. Yoda, K. Sakaue. Head pose estimation by nonlinear manifold learning.Proceedings of the17th International Conference on Pattern Recognition,2004,4:462-466.
[108] J. B. Tenenbaum, V. D. Silva, J. C. Langford. A global geometric framework for nonlineardimensionality reduction. Science,2000,290:2319-2323.
[109] S. T. Roweis, L. K. Saul. Nonlinear dimensionality reduction by locally linear embedding.Science,2000,290:2323-2326.
[110] M. Belkin, P. Niyogi. Laplacian eigenmaps for dimensionality reduction and datarepresentation. Neural Computation,2003,15(6):1373-1396.
[111] V. Balasubramanian, J. Ye, S. Panchanathan. Biased manifold embedding: a framework forperson-independent head pose estimation. Proceedings of the IEEE Conference on Computer Visionand Pattern Recognition,2007:1-7.
[112] Y. Fu, T. S. Huang. Graph embedded analysis for head pose estimation. Proceedings of theIEEE International Conference on Automatic Face and Gesture Recognition,2006:3-8.
[113] X. F. He, S. C. Yan, Y. X. Hu, et al. Learning a locality preserving subspace for visualrecognition. Proceedings of the Ninth IEEE International Conference on Computer Vision,2003,1:385-392.
[114] Z. Li, Y. Fu, J. S. Yuan, et al. Query driven localized linear discriminant models for headpose estimation. Proceedings of the IEEE International Conference on Multimedia and Expo,2007:1810-1813.
[115] M. Lades, J. C. Vorbrüggen, J. Buhmann, et al. Distortion invariant object recognition inthe dynamic link architecture. IEEE Transactions on Computers,1993,42(3):300-311.
[116] N. Krüger, M. P tzsch, C. von der Malsburg. Determination of face position and pose witha learned representation based on labeled graphs. Image and Vision Computing,1997,15(8):665-673.
[117] T. F. Cootes, G. J. Edwards, C. J. Taylor. Active appearance models. IEEE Transactions onPattern Analysis and Machine Intelligence,2001,23(6):681-685.
[118] T. F. Cootes, C. J. Taylor, D. H. Cooper, et al. Active shape models—their training andapplication. Computer Vision and Image Understanding,1995,61(1):38-59.
[119] M. Jiang, L. Deng, L. Zhang, et al. Head pose estimation based on Active Shape Model andRelevant Vector Machine. Proceedings of the IEEE International Conference on Systems, Man, andCybernetics (SMC),2012:1035-1038.
[120] A. Lanitis, C. J. Taylor, T. F. Cootes, et al. Automatic interpretation of human faces andhand gestures using flexible models. Proceedings of the International Workshop on Automatic Face-and Gesture-Recognition,1995:98-103.
[121] A. Lanitis, C. J. Taylor, T. F. Cootes. Automatic interpretation and coding of face imagesusing flexible models. IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):743-756.
[122] I. Matthews, S. Baker. Active appearance models revisited. International Journal ofComputer Vision,2004,60(2):135-164.
[123] J. Xiao, S. Baker, I. Matthews, et al. Real-time combined2D+3D active appearancemodels. Proceedings of the IEEE Conference Computer Vision and Pattern Recognition,2004,2:535-542.
[124] Z. Gui, C. Zhang.3D head pose estimation using non-rigid structure-from-motion andpoint correspondence. Proceedings of the IEEE Region10Conference,2006:1-3.
[125] S. Baker, I. Matthews, J. Xiao, et al. Real-time non-rigid driver head tracking for drivermental state estimation. Proceedings of the11th World Congress Intelligent Transportation Systems,2004:1-18.
[126] C. B. Hu, J. Xiao, I. Matthews, et al. Fitting a single active appearance modelsimultaneously to multiple images. Proceedings of the British Machine Vision Conference,2004:437-446.
[127] H. R. Wilson, F. Wilkinson, L. M. Lin, et al. Perception of head orientation. VisionResearch,2000,40(5):459-472.
[128] A. Gee, R. Cipolla. Determining the gaze of faces in images. Image and Vision Computing,1994,12(10):639-647.
[129] J. G. Wang, E. Sung. EM enhancement of3D head pose estimated by point at infinity.Image and Vision Computing,2007,25(12):1864-1874.
[130] Q. Chen, H. Y. Wu, T. Fukumoto, et al.3D head pose estimation without feature tracking.Proceedings of the third IEEE International Conference on Automatic Face and Gesture Recognition,1998:88-93.
[131] K. Mase, Y. Watanabe, Y. Suenaga. Headreader: realtime motion detection of human headfrom image sequence. Systems and Computers in Japan,1992,23(7):78-88.
[132] S. Ohayon, E. Rivlin. Robust3D head tracking using camera pose estimation. Proceedingsof the International Conference on Pattern Recognition,2006,1:1063-1066.
[133]宋杰.基于三维模型的单目图像序列头部姿态跟踪，[硕士学位论文].杭州：浙江大学，2008.
[134]张林.基于单目视频的头部三维运动模拟算法的研究与实现，[硕士学位论文].长春：东北师范大学，2009.
[135] M. D. Cordea, E. M. Petriu, N. D. Georganas, et al. Real-time2(1/2)-D head pose recoveryfor model-based video-coding. IEEE Transactions on Instrumentation and Measurement,2001,50(4):1007-1013.
[136] A. Nikolaidis, I. Pitas. Facial feature extraction and pose determination. PatternRecognition,2000,33(11):1783-1791.
[137] C. Canton-Ferrer, J. R. Casas, M. Pardàs. Head Pose Detection Based on Fusion ofMultiple Viewpoint Information. Multimodal Technologies for Perception of Humans, LNCS,2007,4122:305-310.
[138] C. Canton-Ferrer, J. R. Casas, M. Pardàs. Head orientation estimation using particlefiltering in multiview scenarios. Multimodal Technologies for Perception of Humans, LNCS,2008,4625:317-327.
[139] B. A. Efraty, M. Papadakis, A. Profitt, et al. Facial component-landmark detection.Proceedings of the2011IEEE International Conference on Automatic Face&Gesture Recognitionand Workshops (FG2011),2011:278-285.
[140] A. Gee, R. Cipolla. Fast visual tracking by temporal consensus. Image and VisionComputing,1996,14(2):105-114.
[141] P. Yao, G. Evans, A. Calway. Using affine correspondence to estimate3-D facial pose.Proceedings of the2001International Conference on Image Processing,2001,3:919-922.
[142] T. Maurer, C. von der Malsburg. Tracking and learning graphs and pose on imagesequences of faces. Proceedings of the Second International Conference on Automatic Face andGesture Recognition,1996:176-181.
[143] K. Toyama.“look, ma—no hands!” Hands-free cursor control with real-time3D facetracking. Proceedings of Workshop on Perceptual User Interfaces,1998:49-54.
[144] D. G. Lowe. Distinctive image features from scale-invariant key-points. InternationalJournal of Computer Vision,2004,60(2):91-110.
[145] S. Ohayon, E. Rivlin. Robust3D head tracking using camera pose estimation. Proceedingsof the18th International Conference on Pattern Recognition,2006,1:1063-1066.
[146] R. G. Yang, Z. Y. Zhang. Model-based head pose tracking with stereovision. Proceedings ofthe Fifth IEEE International Conference on Automatic Face and Gesture Recognition,2002:255-260.
[147] G. Q. Zhao, L. Chen, J. Song, et al. Large head movement tracking using SIFT-basedregistration. Proceedings of the15th International Conference on Multimedia,2007:807-810.
[148] R. Pappu, P. A. Beardsley. A qualitative approach to classifying gaze direction. Proceedingsof the third IEEE International Conference on Automatic Face and Gesture Recognition,1998:160-165.
[149] A. Sch dl, A. Haro, I. A. Essa. Head tracking using a textured polygonal model.Proceedings of Workshop on Perceptual User Interfaces,1998:43-48.
[150] M. Malciu, F. Preteux. A robust model-based approach for3D head tracking in videosequences. Proceedings of the Fourth IEEE International Conference on Automatic Face and GestureRecognition,2000:169-174.
[151] Y. Wu, K. Toyama. Wide-range, person-and illumination-insensitive head orientationestimation. Proceedings of the Fourth IEEE International Conference on Automatic Face and GestureRecognition,2000:183-188.
[152] M. L. Cascia, S. Sclaroff, V. Athitsos. Fast, reliable head tracking under varyingillumination: An approach based on registration of texture-mapped3D models. IEEE Transactions onPattern Analysis and Machine Intelligence,2000,22(4):322-336.
[153] D. DeCarlo, D. Metaxas. Optical flow constraints on deformable models with applicationsto face tracking. International Journal of Computer Vision,2000,38(2):231-238.
[154] J. Xiao, T. Moriyama, T. Kanade, et al. Robust full-motion recovery of head by dynamictemplates and re-registration techniques. International Journal of Imaging Systems and Technology,2003,13(1):85-94.
[155] J. Heinzmann, A. Zelinsky.3-D facial pose and gaze point estimation using a robustreal-time tracking paradigm. Proceedings of the Third IEEE International Conference on AutomaticFace and Gesture Recognition,1998:142-147.
[156] T. Horprasert, Y. Yacoob, L. Davis. An anthropometric shape model for estimating headorientation. Proceedings of the Third International Workshop on Visual Form,1997:247-256.
[157] Y. X. Hu, L. B. Chen, Y. Zhou, et al. Estimating face pose by facial asymmetry andgeometry. Proceedings of the Sixth IEEE International Conference on Automatic Face and GestureRecognition,2004:651-656.
[158] T. S. Jebara, A. Pentland. Parametrized structure from motion for3D adaptive feedbacktracking of faces. Proceedings of the1997IEEE Computer Society Conference on Computer Visionand Pattern Recognition,1997:144-150.
[159] R. Newman, Y. Matsumoto, S. Rougeaux, et al. Real-time stereo tracking for head poseand gaze estimation. Proceedings of the Fourth IEEE International Conference on Automatic Face andGesture Recognition,2000:122-128.
[160] Y. D. Zhu, K. Fujimura. Head pose estimation for driver monitoring. Proceedings of theIEEE Intelligent Vehicles Symposium,2004:501-506.
[161] K. S. Huang, M. M. Trivedi. Robust real-time detection, tracking, and pose estimation offaces in video streams. Proceedings of the17th International Conference on Pattern Recognition,2004,3:965-968.
[162] L.P. Morency, A. Rahimi, T. Darrell. Adaptive view-based appearance models. Proceedingsof the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2003,1:803-810.
[163] S. O. Ba, J. M. Odobez. A probabilistic framework for joint head tracking and poseestimation. Proceedings of the17th International Conference on Pattern Recognition (ICPR),2004,4:264-267.
[164] J. Sherrah, S. G. Gong. Fusion of perceptual cues for robust tracking of head pose andposition. Pattern Recognition,2001,34(8):1565-1572.
[165] J. Wu, J. M. Pedersen, D. Putthividhya, et al. A two-level pose estimation framework usingmajority voting of Gabor wavelets and bunch graph analysis. Proceedings of Pointing’04, ICPRWorkshop on Visual Observation of Deictic Gestures,2004:4-12.
[166] V. C. Abrahams. The physiology of neck muscles; their role in head movement andmaintenance of posture. Canadian Journal of Physiology and Pharmacology,1977,55(3):332-338.
[167] V. F. Ferrario, C. Sforza, G. Serrao, et al. Active range of motion of the head and cervicalspine: a three-dimensional investigation in healthy young adults. Journal of Orthopaedic Research,2002,20(1):122–129.
[168]于起峰，尚洋.摄像测量学原理与应用研究.北京：科学出版社，2009：22-29.
[169]杨改学，孙万银.摄影教程（第2版）.北京：国防工业出版社，2006：18-21.
[170]徐德，谭民，李原.机器人视觉测量与控制（第2版）.北京：国防工业出版社，2011：5-9.
[171] J. Harguess, C. B. Hu, J. K. Aggarwal. Full-motion recovery from multiple video camerasapplied to face tracking and recognition. Proceedings of the2011IEEE International Conference onComputer Vision Workshops (ICCV Workshops),2011:1889-1896.
[172] J. Harguess, C. B. Hu, J. K. Aggarwal. Occlusion robust multi-camera face tracking.Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern RecognitionWorkshops (CVPRW),2011:31-38.
[173] S. Gurbuz, E. Oztop, N. Inoue. Model free head pose estimation using stereovision. PatternRecognition,2012,45(1):33-42.
[174] E. Foxlin, Y. Altshuler, L. Naimark, et al. FlightTracker: A novel optical/inertial tracker forcockpit enhanced vision. Proceedings of the3rd IEEE/ACM International Symposium on Mixed andAugmented Reality,2004:212-221.
[175] J. F. Wang, V. Chi, H. Fuchs. A Real-time Optical3D Tracker For Head-mounted DisplaySystems. Proceedings of the1990symposium on Interactive3D graphics, New York,1992:205-215.
[176] R. Safaee-Rad, I. Tchoukanov, K. C. Smith, et al. Three-dimensional location estimation ofcircular features for machine vision. IEEE transactions on Robotics and Automation,1992,8(5):624-640.
[177] C. B. Madsen. A comparative study of the robustness of two pose estimation technique.Machine Vision and Applications, LNCS,1997,9(5-6):291-303．
[178]周富强，邾继贵，杨学友，等.CCD摄像机快速标定技术.光学精密工程，2000，8（1）：96-100.
[179] H. C. Lee, K. S. Fu.3-D shape from contour and selective confirmation. Computer Vision,Graphics, and Image Processing,1983,22(1):177-193.
[180] H. S. Sawhney, J. Oliensis, A. R. Hanson. Description and reconstruction from imagetrajectories of rotational motion. Proceedings of the third International Conference on ComputerVision,1990:494-498.
[181] R. Safaee-Rad, B. Benhabib, K. C. Smith, et al. Pre-marking methods for3D objectrecognition. Proceedings of IEEE International Conference on Systems, Man and Cybernetics,1989,2:592-595.
[182]魏振忠，赵征，张广军.空间圆姿态识别二义性的角度约束消除.光学精密工程，2010，18（3）：685-691.
[183] L. Zhang, W. S. Dong, D. Zhang, et al. Two-stage image denoising by principal componentanalysis with local pixel grouping. Pattern Recognition,2010,43(4):1531-1549.
[184] F. Luisier, T. Blu, M. Unser. Image denoising in mixed Poisson–Gaussian noise. IEEETransactions on Image Processing,2011,20(3):696-708.
[185] W. S. Dong, X. Li, L. Zhang, et al. Sparsity-based image denoising via dictionary learningand structural clustering. Proceedings of the IEEE Conference on Computer Vision and Pattern,2011:457-464.
[186] M. C. Motwani, M. C. Gadiya, R. C. Motwani, et al. Survey of image denoising techniques.Proceedings of GSPX2004, Santa Clara (CA),2004:27-30.
[187] R. C. Gonzalez, R. E. Woods, S. L. Eddins著，阮秋琦等译.数字图像处理（MATLAB版）.北京：电子工业出版社，2005：46-60，255-270.
[188] Y. W. Xie, L. L. Li, H. Y. Wang, et al. The application of threshold methods for imagesegmentation in oasis vegetation extraction. Proceedings of the18th International Conference onGeoinformatics,2010:1-4.
[189]阴国富.基于阈值法的图像分割技术.现代电子技术，2007，23：107-108.
[190]赵永志，彭国华.一种有效的图像二值化方法.科学技术与工程，2007，7（1）：139-141，144.
[191] M. X. Huang, W. J. Yu, D. H. Zhu. An improved image segmentation algorithm based onthe Otsu method. Proceedings of the13th ACIS International Conference on Software Engineering,Artificial Intelligence, Networking and Parallel&Distributed Computing (SNPD),2012:135-139.
[192] L. Zhang, Y. K. Xu, C. Y. Wu. Features extraction for structured light stripe image based onOtsu threshold. Proceedings of the4th International Symposium on Knowledge Acquisition andModeling (KAM),2011:92-95.
[193] Q. Wang, H. Zhang, Q. Dong, et al. Otsu thresholding segmentation algorithm based onMarkov Random Field. Proceedings of the7th International Conference on Natural Computation(ICNC),2011,2:969-972.
[194] L. Liu, Z. M. Zhao. Morphological image processing in the speckle metrology. TheImaging Science Journal,2011,59(5):303-310.
[195] Lei Liu, Zhimin Zhao. A new approach for measurement of pitch, roll and yaw anglesbased on a circular feature. Transactions of the Institute of Measurement and Control, publishedonline20July2012, DOI:10.1177/0142331212451991.
[2]陶忠祥.位置敏感探测器在头位跟踪中的应用研究,[博士学位论文].长春：中国科学院长春光学精密机械与物理研究所，2004.
[3]赵刚强.基于视觉的大范围头部姿态跟踪关键技术研究，[博士学位论文].浙江：浙江大学，2009.
[4]孟举.基于视频图像处理的头部位置跟踪算法研究，[硕士学位论文].西安：西北工业大学，2007.
[5]田晓焱.基于机器视觉的头盔瞄准具转动角度的测量，[硕士学位论文].西安：西北大学，2006.
[6]戚建中.头盔瞄准/显示系统研究.电光与控制，1997，（3）：33-36.
[7]刘涛，赵国荣，李冀鑫.头盔显示器的光电技术发展研究.光电技术应用，2005，20（3）：1-10.
[8]刘红漫. HMS/HMD关键技术指标及发展方向的预测与研究，[硕士学位论文].北京：北京航空航天大学，2000.
[9] C. H. Morimoto, M. R.M. Mimica. Eye gaze tracking techniques for interactive applications.Computer Vision and Image Understanding,2005,98(1):4-24.
[10] G. Kuhn, V. Benson, S. Fletcher-Watson, et al. Eye movements affirm: automatic overt gazeand arrow cueing for typical adults and adults with autism spectrum disorder. Experimental BrainResearch,2010,201(2):155-165.
[11] E. Schneider, M. Maruyama, S. Dehaene, et al. Eye gaze reveals a fast, parallel extraction ofthe syntax of arithmetic formulas. Cognition,2012,125(3):475-490.
[12] R. Valenti, N. Sebe, T. Gevers. Combining head pose and eye location information for gazeestimation. IEEE Transactions on Image Processing,2012,21(2):802-815.
[13] R. Valenti, A. Lablack, N. Sebe. Visual gaze estimation by joint head and eye information.Proceedings of the20th International Conference on Pattern Recognition (ICPR),2010:3870-3873.
[14] K. Sankaranarayanan, M. C. Chang, N. Krahnstoever. Tracking gaze direction from far-fieldsurveillance cameras. IEEE Workshop on Applications of Computer Vision (WACV),2011:519-526.
[15] A. Doshi, M. M. Trivedi. Head and eye gaze dynamics during visual attention shifts incomplex environments. Journal of Vision,2012,12(2):1-16.
[16] W. P. Medendorp, B.J.M. Melis, C.C.A.M.Gielen, et al. Off-centric rotation axes in naturalhead movements: Implications for the vestibular reafference and kinematic redundancy. Journal ofNeurophysiology,1998,79(4):2025-2039.
[17] R. Goldenberg, R. Kimmel, E. Rivlin, et al. Behavior classification by eigendecompositionof periodic motion. Pattern Recognition,2005,38(7):1033-1043.
[18] O. C. Jenkins, M. J. Mataric. Deriving action and behavior primitives from human motiondata. Proceedings of2002IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS-2002),2002,3:2551-2556.
[19] L. Itti. Quantifying the contribution of low-level saliency to human eye movements indynamic scenes. Visual Cognition,2005,12(6):1093-1123.
[20] J Hy n. The use of eye movements in the study of multimedia learning. Learning andInstruction,2010,20(2):172-176.
[21] S. R. H. Langton, H. Honeyman, E. Tessler. The influence of head contour and nose angleon the perception of eye-gaze direction. Perception&Psychophysics,2004,66(5):752-771.
[22]郑兵，宋福群.远程医疗应用中无线便携式头盔的设计.医疗卫生设备，2007，28（9）：9-10，13.
[23] Q. J. Zhao, X. M. Shi, Y. X. Wang. Head-pose recognition for a game system based onnose's relative position. Human-computer interaction: users and applications, LNCS,2011,6764:694-701.
[24] Y. Zhu, K. Fujimura. Head pose estimation for driver monitoring. Proceedings of IEEEIntelligent Vehicles Symposium,2004:501-506.
[25] P. Smith, M. Shah, N. D. V. Lobo. Monitoring head/eye motion for driver alertness with onecamera. Proceedings of the15th International Conference on Pattern Recognition.2000,4:636-642.
[26] Q. Ji, X. J. Yang. Real-time eye, gaze, and face pose tracking for monitoring driver vigilance.Real-Time Imaging,2002,8(5):357-377.
[27] E. Murphy-Chutorian, M. M. Trivedi. Head pose estimation and augmented reality tracking:an integrated system and evaluation for monitoring driver awareness. IEEE Transactions on IntelligentTransportation Systems,2010,11(2):300-311.
[28] Y. C. Dong, Z. C. Hu, K. Uchimura, et al. Driver inattention monitoring system forintelligent vehicles: A review. IEEE Transactions on Intelligent Transportation Systems,2011,12(2):596-614.
[29] A. Doshi, S. Y. Cheng, M. M. Trivedi. A novel active heads-up display for driver assistance.IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics,2009,39(1):85-93.
[30] S. J. Lee, J. Jo, H. G. Jung, et al. Real-time gaze estimator based on driver's head orientationfor forward collision warning system. IEEE Transactions on Intelligent Transportation Systems,2011,12(1):254-267.
[31] A. Schulz, N. Damer, M. Fischer, et al. Combined head localization and head poseestimation for video–based advanced driver assistance systems. Pattern Recognition,2011,6835:51-60.
[32]王永年，祝梁生，孙隆和.头盔显示/瞄准系统.北京：国防工业出版社，1994.
[33]王永年.头盔显示器的任务、现状和研究方向.电光与控制，1999，（2）：1-9.
[34] X. Z. Zhang, Y. S. Gao. Face recognition across pose: A review. Pattern recognition,2009,42(1):2876-2896.
[35] X. X. Zhu, D. Ramanan. Face detection, pose estimation, and landmark localization in thewild. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2012:2879-2886.
[36] D. Huang, M. Storer, F. De la Torre, et al. Supervised local subspace learning for continuoushead pose estimation. Proceedings of the IEEE Conference on Computer Vision and PatternRecognition (CVPR),2011:2921-2928.
[37] S. I. Choi, C. H. Choi, N. Kwak. Face recognition based on2D images under illuminationand pose variations. Pattern Recognition Letters,2011,32(4):561-571.
[38] G. Fanelli, J. Gall, L. Van Gool. Real time3D head pose estimation: Recent achievementsand future challenges. Proceedings of the5th International Symposium on Communications Controland Signal Processing (ISCCSP),2012:1-4.
[39] C.S. Chang, C.C. Chen, C.F. Juang. Vision-based3D head pose tracking using fuzzyclassifier-based face segmentation and silhouette volume intersection. Proceedings of the InternationalConference on Fuzzy Theory and it's Applications (iFUZZY),2012:363-368.
[40] A. Schulz, R. Stiefelhagen. Video-based pedestrian head pose estimation for risk assessment.Proceedings of the15th International IEEE Conference on Intelligent Transportation Systems (ITSC),2012:1771-1776.
[40] S. J. Ray, J. Teizer. Coarse head pose estimation of construction equipment operators toformulate dynamic blind spots. Advanced Engineering Informatics,2012,26(1):117-130.
[41] M. B. Holte, C. Tran, M. M. Trivedi, et al. Human pose estimation and activity recognitionfrom multi-view videos: comparative explorations of recent developments. IEEE Journal of SelectedTopics in Signal Processing,2012,6(5):538-552.
[42] S. C. Chen, C. H. Wu, S. Y. Lin, et al.2D face alignment and pose estimation based on3Dfacial models. Proceedings of the IEEE International Conference on Multimedia and Expo (ICME),2012:128-133.
[43] E. Murphy-Chutorian, M. M. Trivedi. Head pose estimation in computer vision: a survey.IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(4):607-626.
[44] D. J. Beymer. Face recognition under varying pose. Proceedings of the IEEE ComputerSociety Conference on Computer Vision and Pattern Recognition,1994:756-761.
[45] D. O. Gorodnichy, S. Malik, G. Roth. Affordable3D face tracking using projective vision.Proceedings of the International Conference on Vision Interfaces，2002:383-390.
[46] R. Ruddarraju, A. Haro, I. Essa. Fast multiple camera head pose tracking. Proceedings of theInternational Conference on Vision Interfaces,2003:1-7.
[47] R. G. Yang, Z. Y. Zhang. Model-based head pose tracking with stereo vision. Proceedings ofthe IEEE International Conference on Automatic Face and Gesture Recognition,2002:255-260.
[48] L. P. Morency, T. Darrell. Stereo tracking using ICP and normal flow constraint.Proceedings of the16th International Conference on Pattern Recognition,2002,4:367-372.
[49] K. Terada, A. Oba, A. Ito.3D human head tracking using hypothesized polygon model.Proceedings of the2005IEEE International Conference on Systems, Man and Cybernetics,2005,2:1396-1401.
[50] Q. Ji.3D Face pose estimation and tracking from a monocular camera. Image and VisionComputing,2002,20(7):499-511.
[51] S. Birchfield. Elliptical head tracking using intensity gradients and color histograms.Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,1998:232-237.
[52] R. Wooju, K. Daijin. Real-time3D head tracking and head gesture recognition. Proceedingof the16th IEEE International Symposium on Robot and Human interactive Communication,2007:169-172.
[53] T. Maurer, C. V. D. Malsburg. Tracking and learning graphs on image sequences of faces.Artificial Neural Networks—ICANN96, LNCS,1996,1112:323-328.
[54] T. Horprasert, Y. Yacoob, L. S. Davis. Computing3-D head orientation from a monocularimage sequence. Proceedings of the SPIE2962, the25th AIPR Workshop: Emerging Applications ofComputer Vision,1997:244-249.
[55] D. Machin. Real-time facial analysis for virtual teleconferencing. Proceedings of the SecondInternational Conference on Automatic Face and Gesture Recognition,1996:340–344.
[56] A. Zelinsky, J. Heinzmann. Real-time visual recognition of facial gestures forhuman-computer interaction. Proceedings of the Second International Conference on Automatic Faceand Gesture Recognition,1996:351-356.
[57] E. Petajean, H. P. Graf. Robust face feature analysis for automatic speech reading andcharacter animation. Proceedings of the Second International Conference on Automatic Facial andGesture Recognition,1996:357–362.
[58] A. Bleiweiss, M. Werman. Robust head pose estimation by fusing time-of-flight depth andcolor. IEEE International Workshop on Multimedia Signal Processing (MMSP),2010:116-121.
[59]陆钧昀.基于图像处理的无人机姿态测量，[硕士学位论文].西安：西安电子科技大学，2007.
[60]曹万鹏.基于立体视觉的三维运动测量若干关键技术研究，[博士学位论文].哈尔滨：哈尔滨工业大学，2007.
[61] L. P. Morency, J. Whitehill, J. Movellan. Monocular head pose estimation using generalizedadaptive view-based appearance model. Image and Vision Computing,2010,28(5):754-761.
[62] S. Niyogi, W. T. Freeman. Example-based head tracking. Proceedings of the SecondInternational Conference on Automatic Face and Gesture Recognition.1996:374-378.
[63] M. Romero, A. Bobick. Tracking head yaw by interpolation of template responses.Proceedings of the conference on computer vision and pattern recognition workshop (CVPRW’04),2004:83.
[64] J. Ng, S. G. Gong. Composite support vector machines for detection of faces across viewsand pose estimation. Image and Vision Computing,2002,20(5-6):359-368.
[65] J. Ng, S. G. Gong. Multi-view face detection and pose estimation using a composite supportvector machine across the view sphere. Proceedings of the International Workshop on Recognition,Analysis, and Tracking of Faces and Gestures in Real-Time Systems,1999:14-21.
[66] R. Gonzalez, R. Woods. Digital image processing. London: Prentice-Hall,2002:582-584.
[67] J. Sherrah, S. Gong, E. J. Ong. Understanding pose discrimination in similarity space.Proceedings of the10th British Machine Vision Conference,1999:523-532.
[68] J. Sherrah, S. Gong, E. J. Ong. Face distributions in similarity space under varying headpose. Image and Vision Computing,2001,19(12):807-819.
[69] E. Osuna, R. Freund, F. Girosi. Training support vector machines: An application to facedetection. Proceedings of the IEEE Computer Society Conference on Computer Vision and PatternRecognition,1997:130-136.
[70] H.A. Rowley, S. Baluja, T. Kanade. Neural network-based face detection. IEEETransactions on Pattern Analysis and Machine Intelligence,1998,20(1):23-38.
[71] P. Viola, M. Jones. Rapid object detection using a boosted cascade of simple features.Proceedings of the2011IEEE Computer Society Conference on Computer Vision and PatternRecognition,2001,1:511-518.
[72] J. Huang, X. H. Shao, H. Wechsler. Face pose discrimination using support vector machines(SVM). Proceedings of the14th International Conference on Pattern Recognition,1998,1:154-156.
[73] Z. Q. Zhang, Y.X. Hu, M. Liu, et al. Head pose estimation in seminar room using multi viewface detectors. Proceedings of the CLEAR2006,2007:299-304.
[74] H. A. Rowley, S. Baluja, T. Kanade. Rotation invariant neural network-based face detection.Proceedings of the1998IEEE Computer Society Conference on Computer Vision and PatternRecognition,1998:38-44.
[75] Y. M. Li, S. G. Gong, H. Liddell. Support vector regression and classification basedmulti-view face detection and recognition. Proceedings of the Fourth IEEE International Conferenceon Automatic Face and Gesture Recognition,2000:300-305.
[76] Y. M. Li, S. G. Gong, J. Sherrah, et al. Support vector machine based multi-view facedetection and recognition. Image and Vision Computing,2004,22(5):413-427.
[77] E. Murphy-Chutorian, A. Doshi, M. M. Trivedi. Head pose estimation for driver assistancesystems: a robust algorithm and experimental evaluation. Proceedings of IEEE IntelligentTransportation Systems Conference,2007:709-714.
[78] Y. Ma, Y. Konishi, K. Kinoshita, et al. Sparse bayesian regression for head pose estimation.Proceedings of the18th International Conference on Pattern Recognition,2006,3:507-510.
[79] H. Moon, M. L. Miller. Estimating facial pose from a sparse representation (face recognitionapplications). Proceedings of the2004International Conference on Image Processing,2004,1:75-78.
[80] C. Bishop. Neural networks for pattern recognition. London: Oxford Univ. Press,1995.
[81] R. O. Duda, P. E. Hart, D. G. Stork. Pattern classification (2nd edition). New York: JohnWiley&Sons,2001.
[82] L. M. Brown, Y. L. Tian. Comparative study of coarse head pose estimation. Proceedings ofthe IEEE Workshop on Motion and Video Computing,2002:125-130.
[83] B. Schiele, A. Waibel. Gaze tracking based on face-color. Proceedings of IEEE InternationalWorkshop on Automatic Face-and Gesture-Recognition,1995:344-349.
[84] L. Zhao, G. Pingali, I. Carlbom. Real-time head orientation estimation using neural networks.Proceedings of the2002International Conference on Image Processing,2002,1:297-300.
[85] E. Seemann, K. Nickel, R. Stiefelhagen. Head pose estimation using stereo vision forhuman-robot interaction. Proceedings of the sixth IEEE International Conference on Automatic Faceand Gesture Recognition,2004:626-631.
[86] R. Stiefelhagen, L. Yang, A. Waibel. Modeling focus of attention for meeting indexing basedon multiple cues. IEEE Transactions on Neural Networks,2002,13(4):928-938.
[87] R. Stiefelhagen. Estimating head pose with neural networks-results on the pointing04ICPRworkshop evaluation data. Proceedings of ICPR Workshop on Visual Observation of Deictic Gestures,2004.
[88] M. Voit, K. Nickel, R. Stiefelhagen. Neural network-based head pose estimation andmulti-view fusion. Multimodal Technologies for Perception of Humans, LNCS,2007,4122:291-298.
[89] M. Voit, K. Nickel, R. Stiefelhagen. Head pose estimation in single-and multi-viewenvironments results on the CLEAR’07Benchmarks. Multimodal Technologies for Perception ofHumans, LNCS,2008,4625:307-316.
[90] Y. L. Tian, L. Brown, J. Connell, et al. Absolute head pose estimation from overheadwide-angle cameras. Proceedings of the IEEE International Workshop on Analysis and Modeling ofFaces and Gestures,2003:92-99.
[91] M. Voit, K. Nickel, R. Stiefelhagen. A bayesian approach for multi-view head poseestimation. Proceedings of the2006IEEE International Conference on Multisensor Fusion andIntegration for Intelligent Systems,2006:31-34.
[92] R. Rae, H. J. Ritter. Recognition of human head orientation based on artificial neuralnetworks. IEEE Transactions on Neural Networks,1998,9(2):257-265.
[93] V. Krüger, G. Sommer. Gabor wavelet networks for efficient head pose estimation. Imageand Vision Computing,2002,20(9-10):665-672.
[94] J. Bruske, E. Abraham-Mumm, J. Pauli, et al. Head-pose estimation from facial images withsubspace neural networks. Proceedings of International Conference on Neural Networks and Brain,1998:528-531.
[95] N. Gourier, D. Hall, J. L. Crowley. Estimating face orientation from robust detection ofsalient facial structures. Proceedings of ICPR Workshop on Visual Observation of Deictic Gestures,2004:17-25.
[96] N. Gourier, J. Maisonnasse, D. Hall, et al. Head pose estimation on low resolution images.Multimodal Technologies for Perception of Humans, LNCS,2007,4122:270-280.
[97] Y. L. Cun, L. Bottou, Y. Bengio, et al. Gradient-based learning applied to documentrecognition. Proceedings of IEEE,1998,86(11):2278-2324.
[98] M. Osadchy, M. L. Miller, Y. L. Cun. Synergistic face detection and pose estimation withenergy-based models. The Journal of Machine Learning Research,2007,8:1197-1215.
[99] M. Osadchy, Y. L. Cun, M.L. Miller, et al. Synergistic face detection and pose estimationwith energy-based model. Proceedings of Advances in Neural Information Processing Systems,2005:1017-1024.
[100] C. BenAbdelkader. Robust head pose estimation using supervised manifold learning.Computer Vision–ECCV2010, LNCS,2010,6316:518-531.
[101] J. Wu, M. M. Trivedi. A two-stage head pose estimation framework and evaluation. PatternRecognition,2008,41(3):1138-1158.
[102] S. J. McKenna, S. Gong. Real-time face pose estimation. Real-Time Imaging,1998,4(5):333-347.
[103] S. Srinivasan, K. L. Boyer. Head pose estimation using view based eigenspaces.Proceedings of the16th International Conference on Pattern Recognition,2002,4:302-305.
[104] S. Z. Li, Q. D. Fu, L. Gu, et al. Kernel machine based learning for multi-view facedetection and pose estimation. Proceedings of the8th IEEE International Conference on ComputerVision,2001,2:674-679.
[105] B. P. Ma, W. C. Zhang, S. G. Shan, et al. Robust head pose estimation using LGBP.Proceedings of the18th International Conference on Pattern Recognition,2006,2:512-515.
[106] L. B. Chen, L. Zhang, Y. X. Hu, et al. Head pose estimation using fisher manifold learning.Proceedings of the IEEE International Workshop on Analysis and Modeling of Faces and Gestures,2003:203-207.
[107] B. Raytchev, I. Yoda, K. Sakaue. Head pose estimation by nonlinear manifold learning.Proceedings of the17th International Conference on Pattern Recognition,2004,4:462-466.
[108] J. B. Tenenbaum, V. D. Silva, J. C. Langford. A global geometric framework for nonlineardimensionality reduction. Science,2000,290:2319-2323.
[109] S. T. Roweis, L. K. Saul. Nonlinear dimensionality reduction by locally linear embedding.Science,2000,290:2323-2326.
[110] M. Belkin, P. Niyogi. Laplacian eigenmaps for dimensionality reduction and datarepresentation. Neural Computation,2003,15(6):1373-1396.
[111] V. Balasubramanian, J. Ye, S. Panchanathan. Biased manifold embedding: a framework forperson-independent head pose estimation. Proceedings of the IEEE Conference on Computer Visionand Pattern Recognition,2007:1-7.
[112] Y. Fu, T. S. Huang. Graph embedded analysis for head pose estimation. Proceedings of theIEEE International Conference on Automatic Face and Gesture Recognition,2006:3-8.
[113] X. F. He, S. C. Yan, Y. X. Hu, et al. Learning a locality preserving subspace for visualrecognition. Proceedings of the Ninth IEEE International Conference on Computer Vision,2003,1:385-392.
[114] Z. Li, Y. Fu, J. S. Yuan, et al. Query driven localized linear discriminant models for headpose estimation. Proceedings of the IEEE International Conference on Multimedia and Expo,2007:1810-1813.
[115] M. Lades, J. C. Vorbrüggen, J. Buhmann, et al. Distortion invariant object recognition inthe dynamic link architecture. IEEE Transactions on Computers,1993,42(3):300-311.
[116] N. Krüger, M. P tzsch, C. von der Malsburg. Determination of face position and pose witha learned representation based on labeled graphs. Image and Vision Computing,1997,15(8):665-673.
[117] T. F. Cootes, G. J. Edwards, C. J. Taylor. Active appearance models. IEEE Transactions onPattern Analysis and Machine Intelligence,2001,23(6):681-685.
[118] T. F. Cootes, C. J. Taylor, D. H. Cooper, et al. Active shape models—their training andapplication. Computer Vision and Image Understanding,1995,61(1):38-59.
[119] M. Jiang, L. Deng, L. Zhang, et al. Head pose estimation based on Active Shape Model andRelevant Vector Machine. Proceedings of the IEEE International Conference on Systems, Man, andCybernetics (SMC),2012:1035-1038.
[120] A. Lanitis, C. J. Taylor, T. F. Cootes, et al. Automatic interpretation of human faces andhand gestures using flexible models. Proceedings of the International Workshop on Automatic Face-and Gesture-Recognition,1995:98-103.
[121] A. Lanitis, C. J. Taylor, T. F. Cootes. Automatic interpretation and coding of face imagesusing flexible models. IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):743-756.
[122] I. Matthews, S. Baker. Active appearance models revisited. International Journal ofComputer Vision,2004,60(2):135-164.
[123] J. Xiao, S. Baker, I. Matthews, et al. Real-time combined2D+3D active appearancemodels. Proceedings of the IEEE Conference Computer Vision and Pattern Recognition,2004,2:535-542.
[124] Z. Gui, C. Zhang.3D head pose estimation using non-rigid structure-from-motion andpoint correspondence. Proceedings of the IEEE Region10Conference,2006:1-3.
[125] S. Baker, I. Matthews, J. Xiao, et al. Real-time non-rigid driver head tracking for drivermental state estimation. Proceedings of the11th World Congress Intelligent Transportation Systems,2004:1-18.
[126] C. B. Hu, J. Xiao, I. Matthews, et al. Fitting a single active appearance modelsimultaneously to multiple images. Proceedings of the British Machine Vision Conference,2004:437-446.
[127] H. R. Wilson, F. Wilkinson, L. M. Lin, et al. Perception of head orientation. VisionResearch,2000,40(5):459-472.
[128] A. Gee, R. Cipolla. Determining the gaze of faces in images. Image and Vision Computing,1994,12(10):639-647.
[129] J. G. Wang, E. Sung. EM enhancement of3D head pose estimated by point at infinity.Image and Vision Computing,2007,25(12):1864-1874.
[130] Q. Chen, H. Y. Wu, T. Fukumoto, et al.3D head pose estimation without feature tracking.Proceedings of the third IEEE International Conference on Automatic Face and Gesture Recognition,1998:88-93.
[131] K. Mase, Y. Watanabe, Y. Suenaga. Headreader: realtime motion detection of human headfrom image sequence. Systems and Computers in Japan,1992,23(7):78-88.
[132] S. Ohayon, E. Rivlin. Robust3D head tracking using camera pose estimation. Proceedingsof the International Conference on Pattern Recognition,2006,1:1063-1066.
[133]宋杰.基于三维模型的单目图像序列头部姿态跟踪，[硕士学位论文].杭州：浙江大学，2008.
[134]张林.基于单目视频的头部三维运动模拟算法的研究与实现，[硕士学位论文].长春：东北师范大学，2009.
[135] M. D. Cordea, E. M. Petriu, N. D. Georganas, et al. Real-time2(1/2)-D head pose recoveryfor model-based video-coding. IEEE Transactions on Instrumentation and Measurement,2001,50(4):1007-1013.
[136] A. Nikolaidis, I. Pitas. Facial feature extraction and pose determination. PatternRecognition,2000,33(11):1783-1791.
[137] C. Canton-Ferrer, J. R. Casas, M. Pardàs. Head Pose Detection Based on Fusion ofMultiple Viewpoint Information. Multimodal Technologies for Perception of Humans, LNCS,2007,4122:305-310.
[138] C. Canton-Ferrer, J. R. Casas, M. Pardàs. Head orientation estimation using particlefiltering in multiview scenarios. Multimodal Technologies for Perception of Humans, LNCS,2008,4625:317-327.
[139] B. A. Efraty, M. Papadakis, A. Profitt, et al. Facial component-landmark detection.Proceedings of the2011IEEE International Conference on Automatic Face&Gesture Recognitionand Workshops (FG2011),2011:278-285.
[140] A. Gee, R. Cipolla. Fast visual tracking by temporal consensus. Image and VisionComputing,1996,14(2):105-114.
[141] P. Yao, G. Evans, A. Calway. Using affine correspondence to estimate3-D facial pose.Proceedings of the2001International Conference on Image Processing,2001,3:919-922.
[142] T. Maurer, C. von der Malsburg. Tracking and learning graphs and pose on imagesequences of faces. Proceedings of the Second International Conference on Automatic Face andGesture Recognition,1996:176-181.
[143] K. Toyama.“look, ma—no hands!” Hands-free cursor control with real-time3D facetracking. Proceedings of Workshop on Perceptual User Interfaces,1998:49-54.
[144] D. G. Lowe. Distinctive image features from scale-invariant key-points. InternationalJournal of Computer Vision,2004,60(2):91-110.
[145] S. Ohayon, E. Rivlin. Robust3D head tracking using camera pose estimation. Proceedingsof the18th International Conference on Pattern Recognition,2006,1:1063-1066.
[146] R. G. Yang, Z. Y. Zhang. Model-based head pose tracking with stereovision. Proceedings ofthe Fifth IEEE International Conference on Automatic Face and Gesture Recognition,2002:255-260.
[147] G. Q. Zhao, L. Chen, J. Song, et al. Large head movement tracking using SIFT-basedregistration. Proceedings of the15th International Conference on Multimedia,2007:807-810.
[148] R. Pappu, P. A. Beardsley. A qualitative approach to classifying gaze direction. Proceedingsof the third IEEE International Conference on Automatic Face and Gesture Recognition,1998:160-165.
[149] A. Sch dl, A. Haro, I. A. Essa. Head tracking using a textured polygonal model.Proceedings of Workshop on Perceptual User Interfaces,1998:43-48.
[150] M. Malciu, F. Preteux. A robust model-based approach for3D head tracking in videosequences. Proceedings of the Fourth IEEE International Conference on Automatic Face and GestureRecognition,2000:169-174.
[151] Y. Wu, K. Toyama. Wide-range, person-and illumination-insensitive head orientationestimation. Proceedings of the Fourth IEEE International Conference on Automatic Face and GestureRecognition,2000:183-188.
[152] M. L. Cascia, S. Sclaroff, V. Athitsos. Fast, reliable head tracking under varyingillumination: An approach based on registration of texture-mapped3D models. IEEE Transactions onPattern Analysis and Machine Intelligence,2000,22(4):322-336.
[153] D. DeCarlo, D. Metaxas. Optical flow constraints on deformable models with applicationsto face tracking. International Journal of Computer Vision,2000,38(2):231-238.
[154] J. Xiao, T. Moriyama, T. Kanade, et al. Robust full-motion recovery of head by dynamictemplates and re-registration techniques. International Journal of Imaging Systems and Technology,2003,13(1):85-94.
[155] J. Heinzmann, A. Zelinsky.3-D facial pose and gaze point estimation using a robustreal-time tracking paradigm. Proceedings of the Third IEEE International Conference on AutomaticFace and Gesture Recognition,1998:142-147.
[156] T. Horprasert, Y. Yacoob, L. Davis. An anthropometric shape model for estimating headorientation. Proceedings of the Third International Workshop on Visual Form,1997:247-256.
[157] Y. X. Hu, L. B. Chen, Y. Zhou, et al. Estimating face pose by facial asymmetry andgeometry. Proceedings of the Sixth IEEE International Conference on Automatic Face and GestureRecognition,2004:651-656.
[158] T. S. Jebara, A. Pentland. Parametrized structure from motion for3D adaptive feedbacktracking of faces. Proceedings of the1997IEEE Computer Society Conference on Computer Visionand Pattern Recognition,1997:144-150.
[159] R. Newman, Y. Matsumoto, S. Rougeaux, et al. Real-time stereo tracking for head poseand gaze estimation. Proceedings of the Fourth IEEE International Conference on Automatic Face andGesture Recognition,2000:122-128.
[160] Y. D. Zhu, K. Fujimura. Head pose estimation for driver monitoring. Proceedings of theIEEE Intelligent Vehicles Symposium,2004:501-506.
[161] K. S. Huang, M. M. Trivedi. Robust real-time detection, tracking, and pose estimation offaces in video streams. Proceedings of the17th International Conference on Pattern Recognition,2004,3:965-968.
[162] L.P. Morency, A. Rahimi, T. Darrell. Adaptive view-based appearance models. Proceedingsof the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2003,1:803-810.
[163] S. O. Ba, J. M. Odobez. A probabilistic framework for joint head tracking and poseestimation. Proceedings of the17th International Conference on Pattern Recognition (ICPR),2004,4:264-267.
[164] J. Sherrah, S. G. Gong. Fusion of perceptual cues for robust tracking of head pose andposition. Pattern Recognition,2001,34(8):1565-1572.
[165] J. Wu, J. M. Pedersen, D. Putthividhya, et al. A two-level pose estimation framework usingmajority voting of Gabor wavelets and bunch graph analysis. Proceedings of Pointing’04, ICPRWorkshop on Visual Observation of Deictic Gestures,2004:4-12.
[166] V. C. Abrahams. The physiology of neck muscles; their role in head movement andmaintenance of posture. Canadian Journal of Physiology and Pharmacology,1977,55(3):332-338.
[167] V. F. Ferrario, C. Sforza, G. Serrao, et al. Active range of motion of the head and cervicalspine: a three-dimensional investigation in healthy young adults. Journal of Orthopaedic Research,2002,20(1):122–129.
[168]于起峰，尚洋.摄像测量学原理与应用研究.北京：科学出版社，2009：22-29.
[169]杨改学，孙万银.摄影教程（第2版）.北京：国防工业出版社，2006：18-21.
[170]徐德，谭民，李原.机器人视觉测量与控制（第2版）.北京：国防工业出版社，2011：5-9.
[171] J. Harguess, C. B. Hu, J. K. Aggarwal. Full-motion recovery from multiple video camerasapplied to face tracking and recognition. Proceedings of the2011IEEE International Conference onComputer Vision Workshops (ICCV Workshops),2011:1889-1896.
[172] J. Harguess, C. B. Hu, J. K. Aggarwal. Occlusion robust multi-camera face tracking.Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern RecognitionWorkshops (CVPRW),2011:31-38.
[173] S. Gurbuz, E. Oztop, N. Inoue. Model free head pose estimation using stereovision. PatternRecognition,2012,45(1):33-42.
[174] E. Foxlin, Y. Altshuler, L. Naimark, et al. FlightTracker: A novel optical/inertial tracker forcockpit enhanced vision. Proceedings of the3rd IEEE/ACM International Symposium on Mixed andAugmented Reality,2004:212-221.
[175] J. F. Wang, V. Chi, H. Fuchs. A Real-time Optical3D Tracker For Head-mounted DisplaySystems. Proceedings of the1990symposium on Interactive3D graphics, New York,1992:205-215.
[176] R. Safaee-Rad, I. Tchoukanov, K. C. Smith, et al. Three-dimensional location estimation ofcircular features for machine vision. IEEE transactions on Robotics and Automation,1992,8(5):624-640.
[177] C. B. Madsen. A comparative study of the robustness of two pose estimation technique.Machine Vision and Applications, LNCS,1997,9(5-6):291-303．
[178]周富强，邾继贵，杨学友，等.CCD摄像机快速标定技术.光学精密工程，2000，8（1）：96-100.
[179] H. C. Lee, K. S. Fu.3-D shape from contour and selective confirmation. Computer Vision,Graphics, and Image Processing,1983,22(1):177-193.
[180] H. S. Sawhney, J. Oliensis, A. R. Hanson. Description and reconstruction from imagetrajectories of rotational motion. Proceedings of the third International Conference on ComputerVision,1990:494-498.
[181] R. Safaee-Rad, B. Benhabib, K. C. Smith, et al. Pre-marking methods for3D objectrecognition. Proceedings of IEEE International Conference on Systems, Man and Cybernetics,1989,2:592-595.
[182]魏振忠，赵征，张广军.空间圆姿态识别二义性的角度约束消除.光学精密工程，2010，18（3）：685-691.
[183] L. Zhang, W. S. Dong, D. Zhang, et al. Two-stage image denoising by principal componentanalysis with local pixel grouping. Pattern Recognition,2010,43(4):1531-1549.
[184] F. Luisier, T. Blu, M. Unser. Image denoising in mixed Poisson–Gaussian noise. IEEETransactions on Image Processing,2011,20(3):696-708.
[185] W. S. Dong, X. Li, L. Zhang, et al. Sparsity-based image denoising via dictionary learningand structural clustering. Proceedings of the IEEE Conference on Computer Vision and Pattern,2011:457-464.
[186] M. C. Motwani, M. C. Gadiya, R. C. Motwani, et al. Survey of image denoising techniques.Proceedings of GSPX2004, Santa Clara (CA),2004:27-30.
[187] R. C. Gonzalez, R. E. Woods, S. L. Eddins著，阮秋琦等译.数字图像处理（MATLAB版）.北京：电子工业出版社，2005：46-60，255-270.
[188] Y. W. Xie, L. L. Li, H. Y. Wang, et al. The application of threshold methods for imagesegmentation in oasis vegetation extraction. Proceedings of the18th International Conference onGeoinformatics,2010:1-4.
[189]阴国富.基于阈值法的图像分割技术.现代电子技术，2007，23：107-108.
[190]赵永志，彭国华.一种有效的图像二值化方法.科学技术与工程，2007，7（1）：139-141，144.
[191] M. X. Huang, W. J. Yu, D. H. Zhu. An improved image segmentation algorithm based onthe Otsu method. Proceedings of the13th ACIS International Conference on Software Engineering,Artificial Intelligence, Networking and Parallel&Distributed Computing (SNPD),2012:135-139.
[192] L. Zhang, Y. K. Xu, C. Y. Wu. Features extraction for structured light stripe image based onOtsu threshold. Proceedings of the4th International Symposium on Knowledge Acquisition andModeling (KAM),2011:92-95.
[193] Q. Wang, H. Zhang, Q. Dong, et al. Otsu thresholding segmentation algorithm based onMarkov Random Field. Proceedings of the7th International Conference on Natural Computation(ICNC),2011,2:969-972.
[194] L. Liu, Z. M. Zhao. Morphological image processing in the speckle metrology. TheImaging Science Journal,2011,59(5):303-310.
[195] Lei Liu, Zhimin Zhao. A new approach for measurement of pitch, roll and yaw anglesbased on a circular feature. Transactions of the Institute of Measurement and Control, publishedonline20July2012, DOI:10.1177/0142331212451991.