人体目标跟踪和表情识别中的若干问题研究
|
摘要
论文对目标跟踪和表情识别这两个计算机视觉中的核心任务进行了研究。在目标跟踪方面，对于简单场景，建立了根据人体目标的运动和变化情况进行视频处理的基本框架；对于复杂场景则以Mean-Shift跟踪算法和粒子滤波算法为主要研究对象，从多特征的有效融合和目标模型更新等方面提出改进，用于解决复杂环境下的目标跟踪问题。在表情识别方面，本文将重点放在特征提取关键算法的研究上，将近年来在图像分类中应用广泛的局部二值模式(Local Binary Pattern,LBP)特征以及梯度直方图(Histogram of Oriented Gradient, HOG)特征引入表情识别中，针对表情特征融合、笑脸表情的二分类问题等进行了深入研究。论文取得了以下主要研究成果：
1．研究了目标检测跟踪的基本方法，以此为基础建立了两种通用的视频处理框架，(1)提出一种基于区域特征的人体异常行为检测方法，首先采用基本的高宽比和质心等特征进行聚类，建立正常和异常行为特征库，然后根据目标区域的变化信息检测运动人体的异常行为；(2)提出一种基于运动特征的人数统计方法，采用改进的质心法对多目标进行跟踪，通过对目标的运动轨迹分析得到目标的运动区域和方向，由此实现对通道出入人数的统计。以上两种方法不需要对目标进行精确检测跟踪，因此可用于监控视频的在线检测。
2．针对复杂场景下的目标跟踪问题，研究了基于多特征融合的均值迁移和粒子滤波目标跟踪方法。考虑到纹理特征描述了局部区域的灰度空间分布规律，而颜色特征缺少空间分布的描述，二者之间正好可以相互补充，因此引入LBP纹理特征用于和颜色特征一起对目标进行建模。在此基础上，针对目前跟踪方法存在的不足，将Mean-shift和粒子滤波两种跟踪方法结合，并对这两种算法选择不同的多特征融合策略，有效提高了多特征融合跟踪的稳定性及精度。
3．为了提升在光照变化、目标遮挡、外观变化以及背景干扰等复杂情况下目标跟踪的性能，对多特征融合跟踪算法的关键技术进行了深入研究。完成的主要工作是：（1）针对以往的多特征融合策略的不足，提出了一种粒子滤波框架下的多特征自适应融合方法，该方法采用加权融合的方式对目标进行多特征观测和相似性度量，通过分析粒子的空间集中度和权值分布建立了一种有效的融合系数计算方法，使融合结果更加准确可靠；（2）针对传统模型更新策略的不足，设计了多特征模型的动态分层更新策略，根据各特征的退化程度选择不同的更新速度，同时选取可信度高的特征检测遮挡，有效降低了遮挡和目标外观变化对算法的影响，在一定程度上避免了更新过程导致的模型漂移问题。
4．针对表情识别算法中的特征提取和分类器设计这两个关键问题进行研究。在表情特征提取环节，分析总结了传统的基于局部二元模式(LBP)的表情识别方法存在的不足，提出采用LBP的改进算子提取表情特征，通过实验证明与传统的LBP算子比较，改进算子所提取的纹理特征更为有效且维数较小，更适用于人脸表情识别。在分类器设计环节，重点研究了二对二多分类SVM方法，以四类别分类为基础，将其应用于六种表情的分类，有效提高了训练和检测的速度，同时减小了分类误差和误差积累的影响。
5．针对笑脸识别这类较为特殊的表情识别问题，研究利用融合特征提高真实环境中笑脸分类的有效性。比较了利用局部二元模式（LBP）和梯度方向直方图（HOG）进行笑脸识别的性能，提出构建融合人脸纹理特征和嘴部区域特征的笑脸分类器。通过基于串联融合，基于CCA，基于DCCA等不同融合策略的比较实验，结果表明特征融合有利于发挥表情纹理和形状信息的互补性，提高了笑脸表情识别的可靠性和准确性。
The thesis focuses on the object tracking and the facial expression recognitionresearch in computer vision. In the object tracking under simple conditions, two basicframeworks of video events detection are established based on the motion or the changeof the targets; under complex conditions, the research is focused on mean-shift andparticle filter tracking framework in two major components: multi-feature fusing andobject model update, several new effective methods have been proposed whose aims areto deal with the difficult problems in object tracking. For the expression classificationproblem, we focus on the key algorithms for feature extraction. We introduce HOG(Histogram of Oriented Gradients) feature and LBP (Local Binary Patterns) feature tothe expression recognition that are widely used in images classification recently years.Besides, this paper is in-depth study of the smile facial expression classification,features fusion, etc. Generally, the main contributions of the thesis are as follows.
1. In the moving targets detection and tracking，two novel frameworks areproposed to process the video for events detection：(1) A region based abnormalbehaviors detection approach of the human body is proposed by simple informations ofthe targets such as the minimum bounding rectangle and center mass of object. Thenormal and abnormal features databases are established throught K-means clusteralgorithm, while the abnormal behaviors in video are detected by using the changedinformation of the targets.(2) A motion based detection approach to count the numberof pedestrians crossing in the gungway scene is proposed by using the improvedcentroid algorithm for multiple objects tracking． With the study on movingtrajectories，the approach can get the regions and the moving direction of the movingobject，then count the number of people．These two approaches need no precisedetection and tracking of object, so they can satisfy the on-1ine video-processrequirement．
2. Object tracking algorithom results in a poor performance in complex scenes. Tosolve this problem, an object tracking method based on multi-features fusion ispresented. For the disadvantage of the color distributions that it omits spatialinformation, while the text feature describes the spatial distributions of local region ingray, they are complementry. So the algorithm builds the object model that includes thecolor distributions and the texture features extracted by Local Binary Pattern (LBP).Meanwhile, the robustness of the tracking is strengthened by integrating the mean-shiftinto particle filter, and performs a feature fusion in both of them with two common used fusion rules are employed respectively, thus overcoming the degeneracy problem andresulting in low computational cost.
3. To improve the object tracking performance under complex scenes such asillumination changes, target appearance changes and when occlusion occurs, theresearch focuses on the two major components of tracking algorithoms:(1) Accordingto the shortages of multiple features fusion with fixed-weighting policy, an algorithmfor fusing multiple features adaptively under particle filter tracking framework isproposed. The tracked object is represented by the fusion of all features under linearweighting, and a new method to estimate the fusion coefficient is also proposedaccording to the weight distribution of all particles as well as their spatial concentrations,thus improve the reliability of multi features fusion.(2)To overcome the shortage oftraditional template update strategy, a dynamic template updating strategy is designedfor multiple features template. According to the degeneracy of each feature，this strategyis used to adjust the update speed of each feature template adaptively. Besides, featurewith high confidence is used to detect occlusions thus decreasing the influence of partialocclusion and appearance changes, partially avoids the model drift caused by updateprocedure.
4. The main technologies of facial expression feature extraction and classificationare generally described. Considering the three deficiencies of local binary pattern (LBP),the approved LBP is adopted at the stage of feature extraction, which reduces the featuredimensions and experiment results show that the method has a fast speed and goodability to classify the face expressions. After an in-depth study of themulti-classification SVM, the expression classification method based ontwo-against-two SVM is proposed for the defects of the traditional classificationmethods. Based on the research of four-category classification method, thetwo-against-two classification method realizes fast classification of six basic facialexpressions with a relatively fast speed and a high performance, reducing theaccumulation of classification error.
5. To the question of smile expression recognition，a novel method base on featurefusion is studied. A comparative study of LBP features and HOG features was presented.Thus the fusing of the two features for smile expression classification was conducted.The research about the fusion algorithms based on series connection, canonicalcorrelation analysis (CCA), and the discriminative CCA (DCCA) are discussed in detail.The experimental results demonstrate that the fusion features can use the complementary between texture features and shape features of facial expression, thussignificantly improve the effectiveness and superiority of smile expressionclassification.
1．研究了目标检测跟踪的基本方法，以此为基础建立了两种通用的视频处理框架，(1)提出一种基于区域特征的人体异常行为检测方法，首先采用基本的高宽比和质心等特征进行聚类，建立正常和异常行为特征库，然后根据目标区域的变化信息检测运动人体的异常行为；(2)提出一种基于运动特征的人数统计方法，采用改进的质心法对多目标进行跟踪，通过对目标的运动轨迹分析得到目标的运动区域和方向，由此实现对通道出入人数的统计。以上两种方法不需要对目标进行精确检测跟踪，因此可用于监控视频的在线检测。
2．针对复杂场景下的目标跟踪问题，研究了基于多特征融合的均值迁移和粒子滤波目标跟踪方法。考虑到纹理特征描述了局部区域的灰度空间分布规律，而颜色特征缺少空间分布的描述，二者之间正好可以相互补充，因此引入LBP纹理特征用于和颜色特征一起对目标进行建模。在此基础上，针对目前跟踪方法存在的不足，将Mean-shift和粒子滤波两种跟踪方法结合，并对这两种算法选择不同的多特征融合策略，有效提高了多特征融合跟踪的稳定性及精度。
3．为了提升在光照变化、目标遮挡、外观变化以及背景干扰等复杂情况下目标跟踪的性能，对多特征融合跟踪算法的关键技术进行了深入研究。完成的主要工作是：（1）针对以往的多特征融合策略的不足，提出了一种粒子滤波框架下的多特征自适应融合方法，该方法采用加权融合的方式对目标进行多特征观测和相似性度量，通过分析粒子的空间集中度和权值分布建立了一种有效的融合系数计算方法，使融合结果更加准确可靠；（2）针对传统模型更新策略的不足，设计了多特征模型的动态分层更新策略，根据各特征的退化程度选择不同的更新速度，同时选取可信度高的特征检测遮挡，有效降低了遮挡和目标外观变化对算法的影响，在一定程度上避免了更新过程导致的模型漂移问题。
4．针对表情识别算法中的特征提取和分类器设计这两个关键问题进行研究。在表情特征提取环节，分析总结了传统的基于局部二元模式(LBP)的表情识别方法存在的不足，提出采用LBP的改进算子提取表情特征，通过实验证明与传统的LBP算子比较，改进算子所提取的纹理特征更为有效且维数较小，更适用于人脸表情识别。在分类器设计环节，重点研究了二对二多分类SVM方法，以四类别分类为基础，将其应用于六种表情的分类，有效提高了训练和检测的速度，同时减小了分类误差和误差积累的影响。
5．针对笑脸识别这类较为特殊的表情识别问题，研究利用融合特征提高真实环境中笑脸分类的有效性。比较了利用局部二元模式（LBP）和梯度方向直方图（HOG）进行笑脸识别的性能，提出构建融合人脸纹理特征和嘴部区域特征的笑脸分类器。通过基于串联融合，基于CCA，基于DCCA等不同融合策略的比较实验，结果表明特征融合有利于发挥表情纹理和形状信息的互补性，提高了笑脸表情识别的可靠性和准确性。
The thesis focuses on the object tracking and the facial expression recognitionresearch in computer vision. In the object tracking under simple conditions, two basicframeworks of video events detection are established based on the motion or the changeof the targets; under complex conditions, the research is focused on mean-shift andparticle filter tracking framework in two major components: multi-feature fusing andobject model update, several new effective methods have been proposed whose aims areto deal with the difficult problems in object tracking. For the expression classificationproblem, we focus on the key algorithms for feature extraction. We introduce HOG(Histogram of Oriented Gradients) feature and LBP (Local Binary Patterns) feature tothe expression recognition that are widely used in images classification recently years.Besides, this paper is in-depth study of the smile facial expression classification,features fusion, etc. Generally, the main contributions of the thesis are as follows.
1. In the moving targets detection and tracking，two novel frameworks areproposed to process the video for events detection：(1) A region based abnormalbehaviors detection approach of the human body is proposed by simple informations ofthe targets such as the minimum bounding rectangle and center mass of object. Thenormal and abnormal features databases are established throught K-means clusteralgorithm, while the abnormal behaviors in video are detected by using the changedinformation of the targets.(2) A motion based detection approach to count the numberof pedestrians crossing in the gungway scene is proposed by using the improvedcentroid algorithm for multiple objects tracking． With the study on movingtrajectories，the approach can get the regions and the moving direction of the movingobject，then count the number of people．These two approaches need no precisedetection and tracking of object, so they can satisfy the on-1ine video-processrequirement．
2. Object tracking algorithom results in a poor performance in complex scenes. Tosolve this problem, an object tracking method based on multi-features fusion ispresented. For the disadvantage of the color distributions that it omits spatialinformation, while the text feature describes the spatial distributions of local region ingray, they are complementry. So the algorithm builds the object model that includes thecolor distributions and the texture features extracted by Local Binary Pattern (LBP).Meanwhile, the robustness of the tracking is strengthened by integrating the mean-shiftinto particle filter, and performs a feature fusion in both of them with two common used fusion rules are employed respectively, thus overcoming the degeneracy problem andresulting in low computational cost.
3. To improve the object tracking performance under complex scenes such asillumination changes, target appearance changes and when occlusion occurs, theresearch focuses on the two major components of tracking algorithoms:(1) Accordingto the shortages of multiple features fusion with fixed-weighting policy, an algorithmfor fusing multiple features adaptively under particle filter tracking framework isproposed. The tracked object is represented by the fusion of all features under linearweighting, and a new method to estimate the fusion coefficient is also proposedaccording to the weight distribution of all particles as well as their spatial concentrations,thus improve the reliability of multi features fusion.(2)To overcome the shortage oftraditional template update strategy, a dynamic template updating strategy is designedfor multiple features template. According to the degeneracy of each feature，this strategyis used to adjust the update speed of each feature template adaptively. Besides, featurewith high confidence is used to detect occlusions thus decreasing the influence of partialocclusion and appearance changes, partially avoids the model drift caused by updateprocedure.
4. The main technologies of facial expression feature extraction and classificationare generally described. Considering the three deficiencies of local binary pattern (LBP),the approved LBP is adopted at the stage of feature extraction, which reduces the featuredimensions and experiment results show that the method has a fast speed and goodability to classify the face expressions. After an in-depth study of themulti-classification SVM, the expression classification method based ontwo-against-two SVM is proposed for the defects of the traditional classificationmethods. Based on the research of four-category classification method, thetwo-against-two classification method realizes fast classification of six basic facialexpressions with a relatively fast speed and a high performance, reducing theaccumulation of classification error.
5. To the question of smile expression recognition，a novel method base on featurefusion is studied. A comparative study of LBP features and HOG features was presented.Thus the fusing of the two features for smile expression classification was conducted.The research about the fusion algorithms based on series connection, canonicalcorrelation analysis (CCA), and the discriminative CCA (DCCA) are discussed in detail.The experimental results demonstrate that the fusion features can use the complementary between texture features and shape features of facial expression, thussignificantly improve the effectiveness and superiority of smile expressionclassification.
引文
[1]孙即祥．图像处理[M]．北京：科学出版社，2004．
[2] Marr D.,姚国正等译.视觉计算理论[M].北京:科学出版社,1988
[3] Blake A., Yuille A. Active Vision[M]. Cambridge: MIT Press,1992
[4] Gavrila D. M. The visual analysis of human movement: a survey[J]. ComputerVision and Image Understanding.1999,73(1):82-98.
[5] Alberto S., Juan J. V. An approach of visual motion analysis[J]. PatternRecognition Letters.2005,26(3):355-368
[6] Pentland A. Looking at people: sensing for ubiquitous and wearable computing[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.2000,22(1):107-119.
[7] Comaniciu D, Ramesh V, Meer P. Real-time tracking of non-rigid objects usingmean shift[A]. Computer Vision and Pattern Recognition[C]. Hilton Head, SC,USA: IEEE Computer Society, June2000,142-149.
[8] Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577.
[9] Katja N, Esther K M, Luc V G. An adaptive color-based filter[J]. Image VisionComputing,2003,21(1):99-110.
[10] M. Isard and A. Blake. Condensation-conditional density propagation for visualtracking[J]. International Journal on Computer Vision,1998,29(1):5-28.
[11]王永忠,梁彦,赵春晖等.基于多特征自适应融合的核跟踪方法[J].自动化学报,2008,34(4):393-399.
[12] ZhangHeng, Li，Liehun. A scale rotation adaptive new Mean shift trackingmethod[J]. Electronic Imaging and Multimedia Teehnology, vol.6833,2008.
[13] Lindeberg T. Scale-space for discrete signals [J]. IEEE Trans. on Pattern Analysisand Machine Intelligence,1990,12(3):234-254.
[14] Lindeberg T. Feature detection with automatic scale selection [J]. InternationalJournal of Computer Vision,1998,30(2):79-116.
[15] Lowe, David G. Object recognition from local scale-invariant features[C]. In Proc.of IEEE Conf. on Computer Vision,1999, Vol.2,1150-1157.
[16] Collins R. Mean-shift blob tracking through scale space[C]. In Proc. Of IEEE Conf.on CVPR, Vol.2, pp.234-240,2003.
[17] Zhang Li-Ke, Zhao Hongguang. Real time mean shift tracking using the Gaborwavelet[J]. Proceedings of the2007IEEE International Conference onMechatronics and Automation, ICMA,1617-1621.2007.
[18] Shen, C. Brooks, M. J. van den Hengel, A. Fast Global Kernel Density ModeSeeking:Applications to Localization and Tracing[J]. IEEE Transactions on ImageProcessing, Vol.16,1457-1469,2007.
[19] Jie Zhao, Wen Qiao, Guo-zun Men. An Approach Based on Mean Shift andKalman Filter For Target Tracking Under Occlusion, Proceedings of the EighthInternational Conference on Machine Learning and Cybernetics,2058-2062,2009.
[20] Babu RV, Pérez P, Bouthemy P. Robust tracking with motion estimation and localkernel-based color modeling. Image and Vision Computing, vol.25,1205-1216,2007.
[21] Jeyakar J, Babu RV, Ramakrishnan KR. Robust object tracking using local kernelsand background information. In: ICIP2007, IEEE international conference onimage processing, vol.5,49-52,2007.
[22] Isard M., Blake A. A Mixed-State Condensation Tracker with AutomaticModel-Switching, Proceedings of IEEE Conference on Computer Vision.Bombay,India: IEEE,1998:107-112.
[23] Jiang Li C.-S. C. Transductive local exploration particle filter for object tracking.Image and Vision Computing.2007,25(5):544-552.
[24] K. Pittm, N. Shephard. Filtering via Simulation: Auxiliary Particle Filtering.American Statistical Association.1999,94(446):590-599.
[25]王洪有.基于辅助粒子滤波算法的红外目标跟踪应用[J].光学学报.2010,1(31):132-135.
[26] D. FREITAS J F G. Bayesian Methods for LONDON Neural Networks. CambridgeUniversity,1999.
[27] A. Doucet, S. Godsill, C. Andrieu. On Sequential Monte Carlo Sampling Methodsfor Bayesian Filtering[J]. Statistics and Computing.2000,10(3):197-208.
[28] G. Liu, X. Tang, J. Huang, J. Liu, D. Sun. Hierarchical Model-Based HumanMotion Tracking Via Unscented Kalman Filter. IEEE International Conference onComputer Vision.2007, Rio de Janeiro, Brazil:1-8.
[29] Liu J S and Chen R． Sequential Monte Carlo Methods of DynamicSystem[J]．Joumal of American Statistician，1998，83：1032-1044．
[30] G kitagawa. Monte Carlo Filter and Smoother for Non-Gaussian Non linear StateSpace Models. Journal of Computational and Graphical Statistics，1996，5(l):l-25.
[31] T Higuchi. Monte Carlo Filtering Using Genetics Algorithm Operator. Journal ofStatistical Computation and Simulation，1997，59(l):l-23.
[32]马丽,常发亮,乔谊正.基于遗传算法和粒子滤波器的非刚性目标跟踪.山东大学学报(工学版).2006,36(3):26-29.
[33]袁泽剑,郑南宁,贾新春.高斯-厄米特粒子滤波器.电子学报.2003,31(7):970-973.
[34] Y. Rui, Y. Chen. Better Proposal Distributions: Object Tracking Using theUnscented Particle Filter. Proceedings of IEEE Conference on Computer Visionand Pattern Recognition.2001,2:786-793.
[35] P. Li, T. Zhang, B. Ma. Unscented Kalman Filter for Visual Curve Tracking. Imageand Vision Computing.2004,22(2):157-164.
[36] T. Cham, J.M. Rehg. A Multiple Hypothesis Approach to Figure Tracking.Proceedings of IEEE Conference on CVPR.1999:239-245.
[37] J. Deutscher, A. Blake, I. Reid. Articulated Body Motion Capture by AnnealledParticle Filtering. Proceedings of IEEE Conference on CVPR.2000, South Carolina:126-133.
[38] L. Zhu, J. Zhou, J. Song. Tracking Multiple Objects through Occlusion with OnlineSampling and Position Estimation. Pattern Recognition.2008,41(8):2447-2460.
[39] S. K. Zhou, R. Chellappa, B. Moghaddam. Appearance Tracking using AdaptiveModels in a Particle Filter. Proceedings of the6th Asian Conference on ComputerVision.2004, Jeju Island, Korea.
[40] S.K.Zhou, R. Chellappa, and B. Moghaddam. Visual tracking and recognition usingappearance-adaptive models for particle filters[J]. IEEE Trans. on Image Processing,2004,13(11):1491-1506.
[41] S.Wang，Z. Liu，S.Lv，et al., A Natural Visible and Infrared Faeial ExpressionDatabase for Expression Recognition and Emotion Inference[J].IEEE Transactionson Multimedia，2010，12(7):682-691.
[42] S.Dubuisson，F.Davoine，M.Masson.A solution for facial expression representationand reeognition[J].Signal Processing:Image Communication，2002，17(9):657-73.
[43] I.Bueiu， C.Kotropoulos， I.Pitas.Comparison of ICA approaches for facialexpression reeognition[J].Signal，Image andVideo Proeessing，2009，3(4):345-361.
[44] HeX，Niyogi P. Locality Preserving Projections. ProC.Conf. Advances in NeuralInformation Processing Systems，2003.
[45] X.W.Chen， T.Huang. Facial expression recognition:a clustering-basedapproach[J].Pattern Reeognition Letters，2003，24(9):1295-1302.
[46] Mattew N.D.，Garrison W.C.. A Six-Unit Network is All You Need to DiseoverHappiness[A]. In:Proeeedings of the Twenty-Seeond Annual Conference of theCognitive Science Soeiet[C]，2000:101-106.
[47] Littlewort G., Bartlett M. S., Fasel I., et al. Dynamics of facial expression extractedautomatieally from video [J]. Image and Vision Computing,2006,24(6):615-625.
[48] Ye Jingfu, Zhan Yongzhao, Song Shunlin. Facial expression features extractionbased on Gabor wavelet transformation [J]. IEEE International Conference onSystems, Man and Cybernetics,2004,3:2215-2219.
[49] S.U. Jung，D.H. Kim，K.H. An， et al., Effieient rectangle feature extractionfor rea-time facial expression recognition based on AdabBoost[C].IEEE/R SJInternational Conference on Intelligent Robots and Systems，2005，1941-1946.
[50] X.Feng，M.Pietikinen，A.Hadid. Facial expression recognition with local binaryPattens and1inear Programming[J].Pattern Recognition and Image Analysis，2005，15(2):546-548.
[51] Liao S,Chung A C S. Texture Classification by Using Advanced Local BinaryPatterns and Spatial Distribution of Dominant Patterns[A]. In: Proc of the IEEEInternational Conference on Acoustics, Speech and Signal Processing[C].Honolulu, USA,2007,1221-1224.
[52] Shan C., Gong S., McOwan P. W.. Robust facial expression recognition using localbinary patterns [A]. IEEE International Conference on Image Proeessing [C].2005:370-373.
[53]付晓峰,韦巍.基于多尺度中心化二值模式的人脸表情识别[J].控制理论与应用,2009,26(6):629-633.
[54] Lyons M，Akamatsu S，Kamachi M，et al.Coding facial Expression with GaborWavelets[A]. In:3th IEEE International Conference on Automatie Face and GestureReeognition[C]，Nara JaPan，1998:200-205.
[55] Guo GD, Dyer C. R. Learning from Examples in the Small Sample Case FaceExpression Recognition[J]. IEEE Transactions on Systems, Man and Cybernetics,2005,35(3):477-488.
[56] Xue W. Facial Expression Recognition Based on Gabor Filter and SVM [J].Chinese Journal of Electronics,2006,15(4A):809-812.
[57] BashyalS，Venayagamoorthy G K. Reeognition of Facial Expressions Using GaborWavelets and Leaming Vector Quantization[J].Engineering Applications ofArtificial Intelligenee，2008，21(7):1056-1064.
[58] Tewes A，Wurtz R P，et.al.A Flexible Object Model for Recognising andSynthesising Facial ExPressions[J].Lecture Notes in Computer Seienee，2005，3546:81-90.
[59] Yu J.G. Bhanu B. Evolutionary Feature Synthesis for Facial ExPressionReeognition[J].Pattern Recognition Letters，2006，27(11):1289-1298.
[60] Kotsial，Buciul，et al.An Analysis of Facial Expression Recognition under PartialFacial Image Occlusion[J]. Lmage and Vision Computing，2008，26(7):1052-1067.
[61] G Zhao，M.Pietikainen. Dynamic texture recognition using local binary Patternswith an application to facial expressions[J].IEEE Transactions on Pattern Analysisand Machine Intelligence，2007，29(6):915-928.
[62] Mase K.，PentlandA.Reeognition of Facial Expression from Optical flow[J].IEICETrans.E，1991，74(10):3474-3483.
[63] Liang D, yang J, et al.. A Facial Expression Recognition System Based onSupervised Locally Linear Embedding[J]. Pattern Recognition Letters,2005,26(15):2374-2389.
[64] Gokturk S.B.，Bouguet J.Y.，Tomasi C. Model-Based Face Tracking for view-Independent Faeial Expression Recognition[A].In:Proceedings of the Fifth IEEEInternational Conference on Automatie Face and Gesture Reeognition[C]，2002，287-294.
[65] Hong J.W.， Song K.T..Facial Expression Recognition under Illuminationvariation[A]，In:IEEE Workshop on Advanced Robotics and ItsSocial Impacs[C]，2007，l-6.
[66] Lu H. C.， HuangYJetal.Real-time Facial Expression Reeognition Based onPixel-Pattern-Based Texture Feature[J]. Eleetronics Letters，2007，43(17):916-918.
[67] Kobayashi H.，Hara F. Facial Interaction Between Animated3D Face Robot andHuman Beings[A].In:Proeeedings of the International Conference on Systems，Manand Cybemeties[C], Orlando，FL，USA，1997，3732-3737.
[68] Rosenblum M.，Ycoob Y.，Davis L. Human ExPression Reeognition from MotionUsing a Redial Basis Function Network Architecture[J]. IEEE Trans. NeuralNetworks，1996，7(5):1121-1138.
[69] Christine L.Lisetri，David E.Rumelhart. Facial expression Reeognition Using aNeural Network[A].In:Proceedings of the11th International Flairs Conferenee[C]，1998，328-332.
[70] M.Matsugu， K.Mori， Y.Mitari， et al..Subject independent facial expressionrecognition with robust face detection using a convolutional neural network[J].Neural Networks，2003，16(5):555-559.
[71] Collins R, Lipton A and Kanade T．A System for Video Surveillance andMonitoring：VSAM Final Report[Cmuri-Tr-00-12][R]．Robotic Institute CarnegieMellon Univercity，2000．
[72] I. Haritaoglu, D. Harwood, L. S. Davis. W4: Real-time Surveillance of People andTheir Activities. IEEE Trans. on Pattern Analysis and Machine Intelligence.2000:22:809-830.
[73] Siebel N. T., Mayband S. J. The ADVISOR visual surveillance system,Proceedings of the ECCV2004workshop on Applications of Computer Vision.Prague, Czech Republic:2004:103-111.
[74] Hu W., Tan T., Wang L., et al. A survey on visual surveillance of object motionand behaviors. IEEE Transactions on Systems, Man, and Cybernetics, Part C:Applications and Reviews.2004,34(3):334-352.
[75] http://ftp.pets.rdg.ac.uk/PETS2002/
[76] http://www.cvg.cs.rdg.ac.uk/PETS-CVS/pets-icvs-db.html
[77] http://www.cvg.cs.rdg.ae.uk/VSPETS//vspets-db.html
[78] http://homepages.inf.ed.ac.uk/rbf/CAVIAR/.
[79] http://www.cs.technion.ac.il/Labs/Isl/rudzsky/site/db.htm
[80] http://www.wisdom.weizmami.ac.il/~vision/SpaceTimeActions.html
[81] M.Suwa, N.Sugie, K.Fujimorea. A Preliminary note on Pattern recognition ofhuman emotional expression[C]. Proeeedings of the4thInternational JointConference on Patter Recognition. Kyoto,1978,408-410.
[82] M.Hussein, F.porikli, L.Davis. A Comprehensive Evaluation Framework and aComparative Study for Human Detectors[J]. IEEE Transactions on Intelligent TransPortation Systems,2009，10(3):417-427.
[83] M.Eckhardt, I.Fasel, J.Movellan. Towards practical Facial Feature Detection[J].International Journal of Pattern Recognition and Artificial Intelligence，2009，23(3):379-400.
[84]高文,金辉.面部表情图像的分析与识别[J].计算机学报，1997，20(9):782-789.
[85] Michael J., Julien B., Shigeru A.. Automatic classifcation of single facial images.IEEE Trans on PAMI.1999,21(12),1357–1362.
[86] Kanade T., Cohn J., Tian Y.. Comprehensive database for facial expression analysis.Proceedings of the fourth International Conference on Automatic Face and GestureRecognition,2000,46-53.
[87] Chang C J, Hsieh J W, Chen Y S, et a1. Tracking Multiple Moving Objects Using aLevel-Set Method[J]．International Journal of Pattern Recognition and ArtificialIntelligence，2004,18(2):101-125．
[88] Rajagopalan R, Orchard M T and Brandt R D. Motion Field Modeling for VideoSequences[J]. IEEE Transactions on Image Processing,1997,6(11): l503-1516.
[89] Paragons N and Tziritas C. Detection and Location of Moving Objects UsingDeterministic Relocation Algorithms[C]. International Conference on PatternRecognition.1996:201-205.
[90]李晓亮.基于小波变换和数学形态学的运动物体检测[J].南昌大学学报,2006,30(6):624-626.
[91] Haritaoglu I, Harwood D, Davis L. W4:Real-time surveillance of people and theiractivities. IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(8):809-830．
[92] Mckenna S let all. Tracking group of people. Computer Vision and ImageUnderstanding,2000,80(1):42-56.
[93] Karmann K, Brandt A. Moving object recognition using an adaptive backgroundmemory. In: Cappellinied. Time-varying Image Processing and Moving ObjectRecognition. Elsevier, Amsterdam, The Netherlands,1990.
[94] Kilger M. A shadow handler in a vedio-based real-time traffic monitoring system.In: Proc IEEE Workshop on Applications of Computer Vision, Palm Springs, CA,1992,1060-1066.
[95] Stauffer C, Grimson W. Adaptive background mixture models for real-timetracking. In: Proc IEEE Conference on Computer Vision and Pattern Recognition,Fort Collins, Colorado,1999,2:246-252.
[96] Hu W, Tan T, Wang L, et a1. A Survey on Video Surveillance of Object Motionand Behaviors[J]. IEEE Transactions on Systems, Man, and Cybernetics-PART C:Applications and Reviews,2004,34(3):334-351.
[97]侯志强,韩崇昭.视觉跟踪技术综述[J].自动化学报,2006,32(4):603-617.
[98] Coifman B, Beymer D, Mclauchlan P, et a1. A Real-Time Computer Vision Systemfor Vehicle Tracking and Traffic Surveillance[J]. Transportation Research Part C,1998,6(4):271-288.
[99] Johnson N. and Hogg D. Learning the distribution of object trajectories for eventrecognition. Image and Vision Computing Journal,1996,14:609-615.
[100] Sun X., Chen C. and Manjunath B.S. Probabilistic motion parameter models foractivity recognition. International Conference on Pattern Recognition,2002.
[101] Bobick A.F., Davis J.W. The recognition of human movement using temporaltemplates. IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(3):257-267.
[102] Blank M., Gorelick L., Shechtman E., Irani M. and Basri R. Action as space timeshapes. International Conference on Computer Vision,2005.
[103] Diamantopoulos G and Spann M. Event Detection for Intelligent Car Park VideoSurveillance[J]. Real-Time Imaging,2005,11:233-243.
[104] Chan M T, Hoogs A, Sun Z, et a1. Event Recognition with Fragmented ObjectTracks[C]. International Conference on Pattern Recognition,2006.
[105] Xiang T and Gong S. Incremental and Adaptive A bnormal Behaviour Detection[J].Computer Vision and Image Understanding,2008,111:59-73.
[106] Wang T，Li J，Diao Q，et al. Semantic Event Detection Using Conditional RandomFields[C]．International Conference on Computer Vision and Patter RecognitionWorkshop(CVPRW’06)，2006．
[107] Duan L, Xu M, Chua T S, et a1. A Mid-Level Representation Framework forSemantic Sports Video Analysis[C]. ACM Multimedia Conference.2003.
[108] Wang J, Xu C, et a1. Automatic Replay Generation for Soccer VideoBroadcasting[C]. ACM Multimedia Conference,2004.
[109] Ekin A, Tekalp A M and Mehrotr R. Automatic Soccer Video Analysis andSummarization[J]. IEEE Transactions on Image processing,2003,12(7):796-807.
[110] Phung D Q, Duong T V, S. Venkatesh, et a1. Topic Transition Detection UsingHierarchical Hidden Markov and Semi-Markov Models[C]. ACM multimedia,2005:11-20.
[111] Zhang D, Perez D G, Bengio Sm, et a1. Semisupervised Adapted Hmms forUnusual Event Detection[C]. IEEE Conference on Computer Vision and PatternRecognition.2005:611-618. Vision,2005: l-8.
[112] Oliver N, Rosario B and Pentland A. A Bayesian Computer Vision System forModeling Human Interactions[J]. IEEE Transactions on Pattern Analysis andMachine Intelligence,2000,22(8):831-843.
[113] Dee H and Hogg D. Detecting Inexplicable Behavior[C]. British Machine VisionConference,2004:477-486.
[114] Shet V, Harwood D and Davis L. Multivalued Default Logic for IdentityMaintenance in Visual Surveillance[C]. European Conference on Computer Vision,2006: l19-132.
[115] Wang X, Tieu K and Grimson E. Learning Semantic Scene Models by TrajectoryAnalysis[C]. European Conference on Computer Vision,2006:111-123.
[116] Xiang T and S. Gong. Video Behavior Profiling and Abnormality Detectionwithout Manual Labeling[C]. IEEE International Conference on Computer Vision.2005:1238-1245.
[117] Zhong H, Shi J and M, Visontai. Detecting Unusual Activity in Video[C]. IEEEConference on Computer Vision and Pattern Recognition,2004:819-826.
[118] Boiman O and Irani M. Detecting Irregularities in Images and in Video[C]. IEEEInternational Conference on Computer Vision.2005:462-469.
[119]李和平，胡占义，吴毅红，吴福朝．基于半监督学习的行为建模与异常检测[J]．软件学报，2007，l8(3)：527-537．
[120]郁映卓．基于人体运动特征的异常行为检测和姿态识别．西安电子科技大学硕士学位论文．2011.
[121]徐向阳．K-均值聚类算法在关系数据库中的应用[J].桂林电子科技大学学报,2008,28(4):313-316．
[122] Amit Kale, Rajagopalan AN et a1. Identification of Humans Using Gait[J]. Centerfor Automation Research University of Maryland at College Park,2002.
[123] Lily Lee. Gait Analysis for Classification[R]. AI Technical Report Massachusettsinstitute of technology-artificial intelligence laboratory.2003.06.
[124] Cunado D, Nash J M, Nixon M S et a1. Gait Extraction and Description byEvidence Gathedng[C]. In:Proc of the International Conference on Audio all VideoBased Biometric Person Authentication,1995:43-48.
[125]王江涛．基于视频的目标检测、跟踪及其行为识别研究．南京理工大学博士学位论文．87-89．
[126] Wang X, Ma X and Grimson W E L. Unsupervised Activity Perception in Crowdedand Complicated Scenes Using Hierarchical Bayesian Models[J]. IEEETransactionson Pattern Analysis and Machine Intelligence,2009,31(3):39-555.
[127]胡洪涛,敬忠良,胡士强.基于辅助粒子滤波的红外小目标检测前跟踪算法[J].控制与决策.2005,20(11):1208-1211.
[128] Kumar A, Bar-Shalom Y, and Oron E. Precision Tracking based on Segmentationwith Optimal Layering for Imaging Sensors. IEEE Transactions on Pattern Analysisand Machine Intelligence.1995,17(2).182-188.
[129]龙腾,崔智社,张岩.图像序列中机动目标的形心跟踪[J].航空学报.2001,22(4).312-316.
[130] Shan Cai-feng, Wei Yu-cheng, Tan Tie-niu, Ojardias F. Real time hand tracking bycombining particle filtering and mean-shift[C].Sixth IEEE International Conferenceon Automatic Face and Gesture Recogniton. Seoul,Korea:IEEE Computer Society,2004.669-674.
[131] Wang Zhao-wen, Yang Xiao-kang, Xu Yi,et al..Camshift guided particle filter forvisual tracking[C]. IEEE Workshop on Signal Processing Systems, Shanghai, China,2007:301-306.
[132] Maggio E, Cavallaro A. Hybrid particle filter and mean shift tracker with adaptivetransition model. Acoustics, peech, and Signal Processing, PennsylvaniaConvention Center/Marriott Hotel Philadelphia, PA, USA2005,II-221-224.
[133] Haralick R M, Shanmugam K, Dinstein I. Texture features for image classification.IEEE Trans. on Sys, Man, and Cyb,1973,3(6):610-621.
[134] Wang Junqiu, Integrating color and shape texture features for adaptive real-timeobject tracking[J]. IEEE Trans on Image Proeessing,2008,17(2):235-240.
[135] Fukunaga K, Hostetler L. The Estimation of the Gradient of a Density Function,with Applications in Pattern Recognition[J]. IEEE Trans. On Inform. Theory,1975,21(l):32.
[136] Yizong Cheng. Mean Shift, Mode Seeking, and Clustering[J]. IEEE Transactionson PAMI, Vol.17, No.8, August1995,790-799.
[137] D.Comaniciu, P.Meer. Mean shift analysis and application [J]. Proceedings of theSeventh IEEE International Conference Computer Vision.1999(2):1197-1203.
[138] Bradski G. Computer vision face tracking for use in a perceptual user interface [J].Interl. Technology Journal.1998,2(2).12-21.
[139] C Hue，J Cadre，P Perez. Sequential Monte Carlo Methods for Multiple TargetTracking and Data Fusion[J]. IEEE Trans on Signal Processing，2002，50(2):309-325.
[140] M Isard, A Blake. Contour Tracking by Stochastic Propagation of ConditionalDensity[C]. In Proceedings of European Conference on Computer Vision,1996:343-356.
[141] A.Doucet, S.Godsill, C.Andrieu. On Sequential Monte Carlo Methods for BayesianFiltering[J]. Statistics and Computing.2000,10:197-208.
[142]胡士强,敬忠良.粒子滤波原理及其应用[M].北京:科学出版社,2010.
[143]张俊根.粒子滤波及其在目标跟踪中的应用研究[D].博士论文,西安电子科技大学,2011.
[144]朱志宇.粒子滤波算法及其应用[M].北京:科学出版社,2010.
[145] N Gordon, D Salmond, A Smith. Novel Approach to Nonlinear/Non-GaussianBayesian State Estimation. IEE Proceedings on Radar and Signal processing,1993,140(2):107-113.
[146] Mo Y，Xiao D. Hybrid System Monitoring and Diagnosing Based on Particle FilterAlgorithm. Acta Automation Sinica,2003,29(3):642-648.
[147] Zhaowen W., Xiaokang Y., Yi Xu. Camshift Guided Particle Filter for VisualTracking[J]. Pattern Recognition Letters, March2009,30(4):407-413.
[148]卢晓鹏，殷学民，邹谋炎.一种基于颜色分布的混合视频跟踪方法[J].电子与信息学报，2008，30(2):259-262.
[149]常发亮，马丽，刘增晓等.复杂环境下基于自适应粒子滤波器的目标跟踪[J].电子学报，2006.34(12):2150-2153。
[150] Birchfield S, Elliptical head tracking using intensity gradients and colorhistograms[A]In: Proceedings of the International Conference on Computer Visionand Pattern Recognition[C], Santa Barbara, CA, USA,1998:232-237.
[151] Conaire C, Connor N. Thermo-visual feature fusion for object tracking usingmultiple spatiogram trackers[A]. In: Proceedings of Conference on Machine Visionand Applications[C], New York, NY, USA,2007:483-494.
[152] Perez P, Vermaak J, Blake A. Data fusion for visual tracking with particles[J].Proceedings of the IEEE,2004,92(3):495-513.
[153] Brasnett P, Mihayhova L, Bull D. Sequential Monte Carlo tracking by fusingmultiple cues in video sequences[J].Image Vision Computing,2007,25(8):1217-1227.
[154] Serby D, Koller-Meier E, Van-Gool L. Probabilistic object tracking using multiplefeatures[A]. In: Proceedings of17th International Conference on PatternRecognition, Cambridge, UK,2004:184-187.
[155] Ojala T, Pietikainen M, Maenpaa T. Multi-resolution grayscale and rotationinvariant texture classification with local binary patterns. IEEE Transactions onPattern Analysis and Machine Intelligence,2002,24(7):971-987.
[156] Jacobs R. What determines visual cue reliability? Trends in Cognitive Sciences,2002,6(8):345-350.
[157] Shen C H, Hengel A, and Dick A. Probabilistic multiple cue integration for particlefilter based tracking. Proc. VIIth Digital Image Computing: Techniques andApplications, Melbourne, Australia,2003, I:399-408.
[158] Leichter I, Lindenbaum M, and Rivlin E. A Probabilistic framework for combiningtracking algorithms. Proceedings of IEEE Conference on Computer Vision andPattern Recognition, Washington, USA,2004,(2):445-51.
[159] Spengler M and Schiele B. Towards robust multi-cue integration for visual tracking.International Journal of Machine Vision and Applications,2003,(14):50-58.
[160] R T Collins, Y X Liu, M. Leordeanu. On-line selection of discriminative trackingfeatures[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(10):1631-1643.
[161] G. R. Bradski. Computer Vision Face Tracking as a Component of a PerceptualUser lnterfaee. In Proceedings of IEEE Workshop on Applications of ComputerVision, October,1998,214-219.
[162] Xu X, Li B. Head tracking using particle flter with intensity gradient and colorhistogram[C]. In: Proceedings of IEEE Conference on Multimedia and Expo. IEEE,2005,888-891.
[163] X.Tao, D.Christian. Monte Carlo Visual Tracking Using Color Histograms and aSpatially Weighted Oriented Hausdorff Measure. In Proceedings of the Conferenceon Analysis of Images and Patterns, August,2003,190-197.
[164] Maggio E., Smeraldi F. A Cavallaro. Adaptive multi-feature tracking in a particlefiltering framework[J]. IEEE Transactions on Circuits and Systems for VideoTechnology,2007,vol.17(10):1348-1359.
[165] J.Kang, L.Cohen, G.Medioni. Object Reacquisition Using Geometric InvariantAppearance Model. International Conference on Pattern Recognition.2004,Cambridge,759-762.
[166] M.Spengler, B.Sehiele. Towards Robust Multi-cue Integration for Visual Tracking.Machine Vision and Applications,2003,14:50-58.
[167] J.Triesch, C.vonder Malsburg. Self-organized Integration of Adaptive Vis sualCues for Face Tracking. IEEE Conf. on Automatie Face and Gesture Reeognition.2000, Grenoble, France:102-107.
[168] P.Brasnett, L.M.lova, D.Bull.N.Canagarajah. Sequential Monte Carlo Tracking byFusing Multiple Cues in Video Sequences. Image and Vision Computing.2007,25:1217-1227.
[169] Matthews I, Ishikawa T, Baker S. The template update problem. IEEE Trans onPattern Analysis and Machine Intelligence,2004,26(6):810-815.
[170] M. Suwa, N. Sugie, and K. Fujimora. A preliminary note on pattern recognition ofhuman emotional expression. Proceedings of the Fourth International JointConference on Pattern Recognition.1978.408-410.
[171] B. Fasel, J. Luettin. Automatic facial expression analysis: a survey. PatternRecognition.2003.36(1):259-275.
[172] Corinna Cortes, Vladimir Vapnik. Support vector networks. Machine Learning.1995.20(3):273-297.
[173] Paul P. P., Monwar M. M., Gavrilova M. L., et al.. Rotation invariant multi-viewface detection using skin color regressive model and SVR. International Journal ofPattern Recognition and Artificial Intelligence.2010,24(8).1261-1280.
[174]阮锦新,尹俊勋.基于人脸特征和AdaBoost算法的多姿态人脸检测.计算机应用.2010,(04).967-970.
[175] Viola P., Jones M.. Rapid object detection using a boosted cascade of simplefeatures. IEEE Conference on CVPR.2001:511-518.
[176] Freund Y., Schapire R. E.. A decision-theoretic generalization of online learningand an application to boosting. The Second European Conference onComputational Learning Theory.1995:23-37.
[177]于清,赵晖.一种2_a_2支持向量机多类分类新方法.计算机工程与应用.2008.44(25):186-188.
[178] Bai Y., Guo L. H., Jin L. W., et al.. A novel feature extraction method usingpyramid histogram of orientation gradients for smile recognition. IEEEInternational Conference on Image Processing.2009.3305–3308.
[179] Dalal N.D., Triggs B.. Histograms of oriented gradients for human detection.IEEE Computer Society Conference on CVPR.2005.886–893.
[180] Q. Zhu, M.-C. Yeh, K.-T. Cheng, et al. Fast Human Detection Using a Cascade ofHistograms of Oriented Gradients[C]. IEEE Computer Society Conference onCVPR: University of California at Santa Barbara, CA, USA,2007:1491-1498.
[181]孙权森,曾生根,王平安等.典型相关分析的理论及其在特征融合中的应用.计算机学报.2005,28(9).1524-1533.
[182]严新平.基于特征融合的笑脸识别算法研究.西安电子科技大学硕士学位论文．2012.
[183] Hotelling H.. Relations between two sets of variates. Biometrika.1936,34(4),321–377.
[184] Sun T. K., Chen, S. C., Jin Z., et al.. Kernelized discriminative canonicalcorrelation analysis. IEEE International Conference on Wavelet Analysis andPattern Recognition.2007.1283–1287.
[185] Krebel U.. Pairwise classification and support vector machines. Advances in KernelMethods: Support Vector Learning.1999.255-268.
[2] Marr D.,姚国正等译.视觉计算理论[M].北京:科学出版社,1988
[3] Blake A., Yuille A. Active Vision[M]. Cambridge: MIT Press,1992
[4] Gavrila D. M. The visual analysis of human movement: a survey[J]. ComputerVision and Image Understanding.1999,73(1):82-98.
[5] Alberto S., Juan J. V. An approach of visual motion analysis[J]. PatternRecognition Letters.2005,26(3):355-368
[6] Pentland A. Looking at people: sensing for ubiquitous and wearable computing[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.2000,22(1):107-119.
[7] Comaniciu D, Ramesh V, Meer P. Real-time tracking of non-rigid objects usingmean shift[A]. Computer Vision and Pattern Recognition[C]. Hilton Head, SC,USA: IEEE Computer Society, June2000,142-149.
[8] Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577.
[9] Katja N, Esther K M, Luc V G. An adaptive color-based filter[J]. Image VisionComputing,2003,21(1):99-110.
[10] M. Isard and A. Blake. Condensation-conditional density propagation for visualtracking[J]. International Journal on Computer Vision,1998,29(1):5-28.
[11]王永忠,梁彦,赵春晖等.基于多特征自适应融合的核跟踪方法[J].自动化学报,2008,34(4):393-399.
[12] ZhangHeng, Li，Liehun. A scale rotation adaptive new Mean shift trackingmethod[J]. Electronic Imaging and Multimedia Teehnology, vol.6833,2008.
[13] Lindeberg T. Scale-space for discrete signals [J]. IEEE Trans. on Pattern Analysisand Machine Intelligence,1990,12(3):234-254.
[14] Lindeberg T. Feature detection with automatic scale selection [J]. InternationalJournal of Computer Vision,1998,30(2):79-116.
[15] Lowe, David G. Object recognition from local scale-invariant features[C]. In Proc.of IEEE Conf. on Computer Vision,1999, Vol.2,1150-1157.
[16] Collins R. Mean-shift blob tracking through scale space[C]. In Proc. Of IEEE Conf.on CVPR, Vol.2, pp.234-240,2003.
[17] Zhang Li-Ke, Zhao Hongguang. Real time mean shift tracking using the Gaborwavelet[J]. Proceedings of the2007IEEE International Conference onMechatronics and Automation, ICMA,1617-1621.2007.
[18] Shen, C. Brooks, M. J. van den Hengel, A. Fast Global Kernel Density ModeSeeking:Applications to Localization and Tracing[J]. IEEE Transactions on ImageProcessing, Vol.16,1457-1469,2007.
[19] Jie Zhao, Wen Qiao, Guo-zun Men. An Approach Based on Mean Shift andKalman Filter For Target Tracking Under Occlusion, Proceedings of the EighthInternational Conference on Machine Learning and Cybernetics,2058-2062,2009.
[20] Babu RV, Pérez P, Bouthemy P. Robust tracking with motion estimation and localkernel-based color modeling. Image and Vision Computing, vol.25,1205-1216,2007.
[21] Jeyakar J, Babu RV, Ramakrishnan KR. Robust object tracking using local kernelsand background information. In: ICIP2007, IEEE international conference onimage processing, vol.5,49-52,2007.
[22] Isard M., Blake A. A Mixed-State Condensation Tracker with AutomaticModel-Switching, Proceedings of IEEE Conference on Computer Vision.Bombay,India: IEEE,1998:107-112.
[23] Jiang Li C.-S. C. Transductive local exploration particle filter for object tracking.Image and Vision Computing.2007,25(5):544-552.
[24] K. Pittm, N. Shephard. Filtering via Simulation: Auxiliary Particle Filtering.American Statistical Association.1999,94(446):590-599.
[25]王洪有.基于辅助粒子滤波算法的红外目标跟踪应用[J].光学学报.2010,1(31):132-135.
[26] D. FREITAS J F G. Bayesian Methods for LONDON Neural Networks. CambridgeUniversity,1999.
[27] A. Doucet, S. Godsill, C. Andrieu. On Sequential Monte Carlo Sampling Methodsfor Bayesian Filtering[J]. Statistics and Computing.2000,10(3):197-208.
[28] G. Liu, X. Tang, J. Huang, J. Liu, D. Sun. Hierarchical Model-Based HumanMotion Tracking Via Unscented Kalman Filter. IEEE International Conference onComputer Vision.2007, Rio de Janeiro, Brazil:1-8.
[29] Liu J S and Chen R． Sequential Monte Carlo Methods of DynamicSystem[J]．Joumal of American Statistician，1998，83：1032-1044．
[30] G kitagawa. Monte Carlo Filter and Smoother for Non-Gaussian Non linear StateSpace Models. Journal of Computational and Graphical Statistics，1996，5(l):l-25.
[31] T Higuchi. Monte Carlo Filtering Using Genetics Algorithm Operator. Journal ofStatistical Computation and Simulation，1997，59(l):l-23.
[32]马丽,常发亮,乔谊正.基于遗传算法和粒子滤波器的非刚性目标跟踪.山东大学学报(工学版).2006,36(3):26-29.
[33]袁泽剑,郑南宁,贾新春.高斯-厄米特粒子滤波器.电子学报.2003,31(7):970-973.
[34] Y. Rui, Y. Chen. Better Proposal Distributions: Object Tracking Using theUnscented Particle Filter. Proceedings of IEEE Conference on Computer Visionand Pattern Recognition.2001,2:786-793.
[35] P. Li, T. Zhang, B. Ma. Unscented Kalman Filter for Visual Curve Tracking. Imageand Vision Computing.2004,22(2):157-164.
[36] T. Cham, J.M. Rehg. A Multiple Hypothesis Approach to Figure Tracking.Proceedings of IEEE Conference on CVPR.1999:239-245.
[37] J. Deutscher, A. Blake, I. Reid. Articulated Body Motion Capture by AnnealledParticle Filtering. Proceedings of IEEE Conference on CVPR.2000, South Carolina:126-133.
[38] L. Zhu, J. Zhou, J. Song. Tracking Multiple Objects through Occlusion with OnlineSampling and Position Estimation. Pattern Recognition.2008,41(8):2447-2460.
[39] S. K. Zhou, R. Chellappa, B. Moghaddam. Appearance Tracking using AdaptiveModels in a Particle Filter. Proceedings of the6th Asian Conference on ComputerVision.2004, Jeju Island, Korea.
[40] S.K.Zhou, R. Chellappa, and B. Moghaddam. Visual tracking and recognition usingappearance-adaptive models for particle filters[J]. IEEE Trans. on Image Processing,2004,13(11):1491-1506.
[41] S.Wang，Z. Liu，S.Lv，et al., A Natural Visible and Infrared Faeial ExpressionDatabase for Expression Recognition and Emotion Inference[J].IEEE Transactionson Multimedia，2010，12(7):682-691.
[42] S.Dubuisson，F.Davoine，M.Masson.A solution for facial expression representationand reeognition[J].Signal Processing:Image Communication，2002，17(9):657-73.
[43] I.Bueiu， C.Kotropoulos， I.Pitas.Comparison of ICA approaches for facialexpression reeognition[J].Signal，Image andVideo Proeessing，2009，3(4):345-361.
[44] HeX，Niyogi P. Locality Preserving Projections. ProC.Conf. Advances in NeuralInformation Processing Systems，2003.
[45] X.W.Chen， T.Huang. Facial expression recognition:a clustering-basedapproach[J].Pattern Reeognition Letters，2003，24(9):1295-1302.
[46] Mattew N.D.，Garrison W.C.. A Six-Unit Network is All You Need to DiseoverHappiness[A]. In:Proeeedings of the Twenty-Seeond Annual Conference of theCognitive Science Soeiet[C]，2000:101-106.
[47] Littlewort G., Bartlett M. S., Fasel I., et al. Dynamics of facial expression extractedautomatieally from video [J]. Image and Vision Computing,2006,24(6):615-625.
[48] Ye Jingfu, Zhan Yongzhao, Song Shunlin. Facial expression features extractionbased on Gabor wavelet transformation [J]. IEEE International Conference onSystems, Man and Cybernetics,2004,3:2215-2219.
[49] S.U. Jung，D.H. Kim，K.H. An， et al., Effieient rectangle feature extractionfor rea-time facial expression recognition based on AdabBoost[C].IEEE/R SJInternational Conference on Intelligent Robots and Systems，2005，1941-1946.
[50] X.Feng，M.Pietikinen，A.Hadid. Facial expression recognition with local binaryPattens and1inear Programming[J].Pattern Recognition and Image Analysis，2005，15(2):546-548.
[51] Liao S,Chung A C S. Texture Classification by Using Advanced Local BinaryPatterns and Spatial Distribution of Dominant Patterns[A]. In: Proc of the IEEEInternational Conference on Acoustics, Speech and Signal Processing[C].Honolulu, USA,2007,1221-1224.
[52] Shan C., Gong S., McOwan P. W.. Robust facial expression recognition using localbinary patterns [A]. IEEE International Conference on Image Proeessing [C].2005:370-373.
[53]付晓峰,韦巍.基于多尺度中心化二值模式的人脸表情识别[J].控制理论与应用,2009,26(6):629-633.
[54] Lyons M，Akamatsu S，Kamachi M，et al.Coding facial Expression with GaborWavelets[A]. In:3th IEEE International Conference on Automatie Face and GestureReeognition[C]，Nara JaPan，1998:200-205.
[55] Guo GD, Dyer C. R. Learning from Examples in the Small Sample Case FaceExpression Recognition[J]. IEEE Transactions on Systems, Man and Cybernetics,2005,35(3):477-488.
[56] Xue W. Facial Expression Recognition Based on Gabor Filter and SVM [J].Chinese Journal of Electronics,2006,15(4A):809-812.
[57] BashyalS，Venayagamoorthy G K. Reeognition of Facial Expressions Using GaborWavelets and Leaming Vector Quantization[J].Engineering Applications ofArtificial Intelligenee，2008，21(7):1056-1064.
[58] Tewes A，Wurtz R P，et.al.A Flexible Object Model for Recognising andSynthesising Facial ExPressions[J].Lecture Notes in Computer Seienee，2005，3546:81-90.
[59] Yu J.G. Bhanu B. Evolutionary Feature Synthesis for Facial ExPressionReeognition[J].Pattern Recognition Letters，2006，27(11):1289-1298.
[60] Kotsial，Buciul，et al.An Analysis of Facial Expression Recognition under PartialFacial Image Occlusion[J]. Lmage and Vision Computing，2008，26(7):1052-1067.
[61] G Zhao，M.Pietikainen. Dynamic texture recognition using local binary Patternswith an application to facial expressions[J].IEEE Transactions on Pattern Analysisand Machine Intelligence，2007，29(6):915-928.
[62] Mase K.，PentlandA.Reeognition of Facial Expression from Optical flow[J].IEICETrans.E，1991，74(10):3474-3483.
[63] Liang D, yang J, et al.. A Facial Expression Recognition System Based onSupervised Locally Linear Embedding[J]. Pattern Recognition Letters,2005,26(15):2374-2389.
[64] Gokturk S.B.，Bouguet J.Y.，Tomasi C. Model-Based Face Tracking for view-Independent Faeial Expression Recognition[A].In:Proceedings of the Fifth IEEEInternational Conference on Automatie Face and Gesture Reeognition[C]，2002，287-294.
[65] Hong J.W.， Song K.T..Facial Expression Recognition under Illuminationvariation[A]，In:IEEE Workshop on Advanced Robotics and ItsSocial Impacs[C]，2007，l-6.
[66] Lu H. C.， HuangYJetal.Real-time Facial Expression Reeognition Based onPixel-Pattern-Based Texture Feature[J]. Eleetronics Letters，2007，43(17):916-918.
[67] Kobayashi H.，Hara F. Facial Interaction Between Animated3D Face Robot andHuman Beings[A].In:Proeeedings of the International Conference on Systems，Manand Cybemeties[C], Orlando，FL，USA，1997，3732-3737.
[68] Rosenblum M.，Ycoob Y.，Davis L. Human ExPression Reeognition from MotionUsing a Redial Basis Function Network Architecture[J]. IEEE Trans. NeuralNetworks，1996，7(5):1121-1138.
[69] Christine L.Lisetri，David E.Rumelhart. Facial expression Reeognition Using aNeural Network[A].In:Proceedings of the11th International Flairs Conferenee[C]，1998，328-332.
[70] M.Matsugu， K.Mori， Y.Mitari， et al..Subject independent facial expressionrecognition with robust face detection using a convolutional neural network[J].Neural Networks，2003，16(5):555-559.
[71] Collins R, Lipton A and Kanade T．A System for Video Surveillance andMonitoring：VSAM Final Report[Cmuri-Tr-00-12][R]．Robotic Institute CarnegieMellon Univercity，2000．
[72] I. Haritaoglu, D. Harwood, L. S. Davis. W4: Real-time Surveillance of People andTheir Activities. IEEE Trans. on Pattern Analysis and Machine Intelligence.2000:22:809-830.
[73] Siebel N. T., Mayband S. J. The ADVISOR visual surveillance system,Proceedings of the ECCV2004workshop on Applications of Computer Vision.Prague, Czech Republic:2004:103-111.
[74] Hu W., Tan T., Wang L., et al. A survey on visual surveillance of object motionand behaviors. IEEE Transactions on Systems, Man, and Cybernetics, Part C:Applications and Reviews.2004,34(3):334-352.
[75] http://ftp.pets.rdg.ac.uk/PETS2002/
[76] http://www.cvg.cs.rdg.ac.uk/PETS-CVS/pets-icvs-db.html
[77] http://www.cvg.cs.rdg.ae.uk/VSPETS//vspets-db.html
[78] http://homepages.inf.ed.ac.uk/rbf/CAVIAR/.
[79] http://www.cs.technion.ac.il/Labs/Isl/rudzsky/site/db.htm
[80] http://www.wisdom.weizmami.ac.il/~vision/SpaceTimeActions.html
[81] M.Suwa, N.Sugie, K.Fujimorea. A Preliminary note on Pattern recognition ofhuman emotional expression[C]. Proeeedings of the4thInternational JointConference on Patter Recognition. Kyoto,1978,408-410.
[82] M.Hussein, F.porikli, L.Davis. A Comprehensive Evaluation Framework and aComparative Study for Human Detectors[J]. IEEE Transactions on Intelligent TransPortation Systems,2009，10(3):417-427.
[83] M.Eckhardt, I.Fasel, J.Movellan. Towards practical Facial Feature Detection[J].International Journal of Pattern Recognition and Artificial Intelligence，2009，23(3):379-400.
[84]高文,金辉.面部表情图像的分析与识别[J].计算机学报，1997，20(9):782-789.
[85] Michael J., Julien B., Shigeru A.. Automatic classifcation of single facial images.IEEE Trans on PAMI.1999,21(12),1357–1362.
[86] Kanade T., Cohn J., Tian Y.. Comprehensive database for facial expression analysis.Proceedings of the fourth International Conference on Automatic Face and GestureRecognition,2000,46-53.
[87] Chang C J, Hsieh J W, Chen Y S, et a1. Tracking Multiple Moving Objects Using aLevel-Set Method[J]．International Journal of Pattern Recognition and ArtificialIntelligence，2004,18(2):101-125．
[88] Rajagopalan R, Orchard M T and Brandt R D. Motion Field Modeling for VideoSequences[J]. IEEE Transactions on Image Processing,1997,6(11): l503-1516.
[89] Paragons N and Tziritas C. Detection and Location of Moving Objects UsingDeterministic Relocation Algorithms[C]. International Conference on PatternRecognition.1996:201-205.
[90]李晓亮.基于小波变换和数学形态学的运动物体检测[J].南昌大学学报,2006,30(6):624-626.
[91] Haritaoglu I, Harwood D, Davis L. W4:Real-time surveillance of people and theiractivities. IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(8):809-830．
[92] Mckenna S let all. Tracking group of people. Computer Vision and ImageUnderstanding,2000,80(1):42-56.
[93] Karmann K, Brandt A. Moving object recognition using an adaptive backgroundmemory. In: Cappellinied. Time-varying Image Processing and Moving ObjectRecognition. Elsevier, Amsterdam, The Netherlands,1990.
[94] Kilger M. A shadow handler in a vedio-based real-time traffic monitoring system.In: Proc IEEE Workshop on Applications of Computer Vision, Palm Springs, CA,1992,1060-1066.
[95] Stauffer C, Grimson W. Adaptive background mixture models for real-timetracking. In: Proc IEEE Conference on Computer Vision and Pattern Recognition,Fort Collins, Colorado,1999,2:246-252.
[96] Hu W, Tan T, Wang L, et a1. A Survey on Video Surveillance of Object Motionand Behaviors[J]. IEEE Transactions on Systems, Man, and Cybernetics-PART C:Applications and Reviews,2004,34(3):334-351.
[97]侯志强,韩崇昭.视觉跟踪技术综述[J].自动化学报,2006,32(4):603-617.
[98] Coifman B, Beymer D, Mclauchlan P, et a1. A Real-Time Computer Vision Systemfor Vehicle Tracking and Traffic Surveillance[J]. Transportation Research Part C,1998,6(4):271-288.
[99] Johnson N. and Hogg D. Learning the distribution of object trajectories for eventrecognition. Image and Vision Computing Journal,1996,14:609-615.
[100] Sun X., Chen C. and Manjunath B.S. Probabilistic motion parameter models foractivity recognition. International Conference on Pattern Recognition,2002.
[101] Bobick A.F., Davis J.W. The recognition of human movement using temporaltemplates. IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(3):257-267.
[102] Blank M., Gorelick L., Shechtman E., Irani M. and Basri R. Action as space timeshapes. International Conference on Computer Vision,2005.
[103] Diamantopoulos G and Spann M. Event Detection for Intelligent Car Park VideoSurveillance[J]. Real-Time Imaging,2005,11:233-243.
[104] Chan M T, Hoogs A, Sun Z, et a1. Event Recognition with Fragmented ObjectTracks[C]. International Conference on Pattern Recognition,2006.
[105] Xiang T and Gong S. Incremental and Adaptive A bnormal Behaviour Detection[J].Computer Vision and Image Understanding,2008,111:59-73.
[106] Wang T，Li J，Diao Q，et al. Semantic Event Detection Using Conditional RandomFields[C]．International Conference on Computer Vision and Patter RecognitionWorkshop(CVPRW’06)，2006．
[107] Duan L, Xu M, Chua T S, et a1. A Mid-Level Representation Framework forSemantic Sports Video Analysis[C]. ACM Multimedia Conference.2003.
[108] Wang J, Xu C, et a1. Automatic Replay Generation for Soccer VideoBroadcasting[C]. ACM Multimedia Conference,2004.
[109] Ekin A, Tekalp A M and Mehrotr R. Automatic Soccer Video Analysis andSummarization[J]. IEEE Transactions on Image processing,2003,12(7):796-807.
[110] Phung D Q, Duong T V, S. Venkatesh, et a1. Topic Transition Detection UsingHierarchical Hidden Markov and Semi-Markov Models[C]. ACM multimedia,2005:11-20.
[111] Zhang D, Perez D G, Bengio Sm, et a1. Semisupervised Adapted Hmms forUnusual Event Detection[C]. IEEE Conference on Computer Vision and PatternRecognition.2005:611-618. Vision,2005: l-8.
[112] Oliver N, Rosario B and Pentland A. A Bayesian Computer Vision System forModeling Human Interactions[J]. IEEE Transactions on Pattern Analysis andMachine Intelligence,2000,22(8):831-843.
[113] Dee H and Hogg D. Detecting Inexplicable Behavior[C]. British Machine VisionConference,2004:477-486.
[114] Shet V, Harwood D and Davis L. Multivalued Default Logic for IdentityMaintenance in Visual Surveillance[C]. European Conference on Computer Vision,2006: l19-132.
[115] Wang X, Tieu K and Grimson E. Learning Semantic Scene Models by TrajectoryAnalysis[C]. European Conference on Computer Vision,2006:111-123.
[116] Xiang T and S. Gong. Video Behavior Profiling and Abnormality Detectionwithout Manual Labeling[C]. IEEE International Conference on Computer Vision.2005:1238-1245.
[117] Zhong H, Shi J and M, Visontai. Detecting Unusual Activity in Video[C]. IEEEConference on Computer Vision and Pattern Recognition,2004:819-826.
[118] Boiman O and Irani M. Detecting Irregularities in Images and in Video[C]. IEEEInternational Conference on Computer Vision.2005:462-469.
[119]李和平，胡占义，吴毅红，吴福朝．基于半监督学习的行为建模与异常检测[J]．软件学报，2007，l8(3)：527-537．
[120]郁映卓．基于人体运动特征的异常行为检测和姿态识别．西安电子科技大学硕士学位论文．2011.
[121]徐向阳．K-均值聚类算法在关系数据库中的应用[J].桂林电子科技大学学报,2008,28(4):313-316．
[122] Amit Kale, Rajagopalan AN et a1. Identification of Humans Using Gait[J]. Centerfor Automation Research University of Maryland at College Park,2002.
[123] Lily Lee. Gait Analysis for Classification[R]. AI Technical Report Massachusettsinstitute of technology-artificial intelligence laboratory.2003.06.
[124] Cunado D, Nash J M, Nixon M S et a1. Gait Extraction and Description byEvidence Gathedng[C]. In:Proc of the International Conference on Audio all VideoBased Biometric Person Authentication,1995:43-48.
[125]王江涛．基于视频的目标检测、跟踪及其行为识别研究．南京理工大学博士学位论文．87-89．
[126] Wang X, Ma X and Grimson W E L. Unsupervised Activity Perception in Crowdedand Complicated Scenes Using Hierarchical Bayesian Models[J]. IEEETransactionson Pattern Analysis and Machine Intelligence,2009,31(3):39-555.
[127]胡洪涛,敬忠良,胡士强.基于辅助粒子滤波的红外小目标检测前跟踪算法[J].控制与决策.2005,20(11):1208-1211.
[128] Kumar A, Bar-Shalom Y, and Oron E. Precision Tracking based on Segmentationwith Optimal Layering for Imaging Sensors. IEEE Transactions on Pattern Analysisand Machine Intelligence.1995,17(2).182-188.
[129]龙腾,崔智社,张岩.图像序列中机动目标的形心跟踪[J].航空学报.2001,22(4).312-316.
[130] Shan Cai-feng, Wei Yu-cheng, Tan Tie-niu, Ojardias F. Real time hand tracking bycombining particle filtering and mean-shift[C].Sixth IEEE International Conferenceon Automatic Face and Gesture Recogniton. Seoul,Korea:IEEE Computer Society,2004.669-674.
[131] Wang Zhao-wen, Yang Xiao-kang, Xu Yi,et al..Camshift guided particle filter forvisual tracking[C]. IEEE Workshop on Signal Processing Systems, Shanghai, China,2007:301-306.
[132] Maggio E, Cavallaro A. Hybrid particle filter and mean shift tracker with adaptivetransition model. Acoustics, peech, and Signal Processing, PennsylvaniaConvention Center/Marriott Hotel Philadelphia, PA, USA2005,II-221-224.
[133] Haralick R M, Shanmugam K, Dinstein I. Texture features for image classification.IEEE Trans. on Sys, Man, and Cyb,1973,3(6):610-621.
[134] Wang Junqiu, Integrating color and shape texture features for adaptive real-timeobject tracking[J]. IEEE Trans on Image Proeessing,2008,17(2):235-240.
[135] Fukunaga K, Hostetler L. The Estimation of the Gradient of a Density Function,with Applications in Pattern Recognition[J]. IEEE Trans. On Inform. Theory,1975,21(l):32.
[136] Yizong Cheng. Mean Shift, Mode Seeking, and Clustering[J]. IEEE Transactionson PAMI, Vol.17, No.8, August1995,790-799.
[137] D.Comaniciu, P.Meer. Mean shift analysis and application [J]. Proceedings of theSeventh IEEE International Conference Computer Vision.1999(2):1197-1203.
[138] Bradski G. Computer vision face tracking for use in a perceptual user interface [J].Interl. Technology Journal.1998,2(2).12-21.
[139] C Hue，J Cadre，P Perez. Sequential Monte Carlo Methods for Multiple TargetTracking and Data Fusion[J]. IEEE Trans on Signal Processing，2002，50(2):309-325.
[140] M Isard, A Blake. Contour Tracking by Stochastic Propagation of ConditionalDensity[C]. In Proceedings of European Conference on Computer Vision,1996:343-356.
[141] A.Doucet, S.Godsill, C.Andrieu. On Sequential Monte Carlo Methods for BayesianFiltering[J]. Statistics and Computing.2000,10:197-208.
[142]胡士强,敬忠良.粒子滤波原理及其应用[M].北京:科学出版社,2010.
[143]张俊根.粒子滤波及其在目标跟踪中的应用研究[D].博士论文,西安电子科技大学,2011.
[144]朱志宇.粒子滤波算法及其应用[M].北京:科学出版社,2010.
[145] N Gordon, D Salmond, A Smith. Novel Approach to Nonlinear/Non-GaussianBayesian State Estimation. IEE Proceedings on Radar and Signal processing,1993,140(2):107-113.
[146] Mo Y，Xiao D. Hybrid System Monitoring and Diagnosing Based on Particle FilterAlgorithm. Acta Automation Sinica,2003,29(3):642-648.
[147] Zhaowen W., Xiaokang Y., Yi Xu. Camshift Guided Particle Filter for VisualTracking[J]. Pattern Recognition Letters, March2009,30(4):407-413.
[148]卢晓鹏，殷学民，邹谋炎.一种基于颜色分布的混合视频跟踪方法[J].电子与信息学报，2008，30(2):259-262.
[149]常发亮，马丽，刘增晓等.复杂环境下基于自适应粒子滤波器的目标跟踪[J].电子学报，2006.34(12):2150-2153。
[150] Birchfield S, Elliptical head tracking using intensity gradients and colorhistograms[A]In: Proceedings of the International Conference on Computer Visionand Pattern Recognition[C], Santa Barbara, CA, USA,1998:232-237.
[151] Conaire C, Connor N. Thermo-visual feature fusion for object tracking usingmultiple spatiogram trackers[A]. In: Proceedings of Conference on Machine Visionand Applications[C], New York, NY, USA,2007:483-494.
[152] Perez P, Vermaak J, Blake A. Data fusion for visual tracking with particles[J].Proceedings of the IEEE,2004,92(3):495-513.
[153] Brasnett P, Mihayhova L, Bull D. Sequential Monte Carlo tracking by fusingmultiple cues in video sequences[J].Image Vision Computing,2007,25(8):1217-1227.
[154] Serby D, Koller-Meier E, Van-Gool L. Probabilistic object tracking using multiplefeatures[A]. In: Proceedings of17th International Conference on PatternRecognition, Cambridge, UK,2004:184-187.
[155] Ojala T, Pietikainen M, Maenpaa T. Multi-resolution grayscale and rotationinvariant texture classification with local binary patterns. IEEE Transactions onPattern Analysis and Machine Intelligence,2002,24(7):971-987.
[156] Jacobs R. What determines visual cue reliability? Trends in Cognitive Sciences,2002,6(8):345-350.
[157] Shen C H, Hengel A, and Dick A. Probabilistic multiple cue integration for particlefilter based tracking. Proc. VIIth Digital Image Computing: Techniques andApplications, Melbourne, Australia,2003, I:399-408.
[158] Leichter I, Lindenbaum M, and Rivlin E. A Probabilistic framework for combiningtracking algorithms. Proceedings of IEEE Conference on Computer Vision andPattern Recognition, Washington, USA,2004,(2):445-51.
[159] Spengler M and Schiele B. Towards robust multi-cue integration for visual tracking.International Journal of Machine Vision and Applications,2003,(14):50-58.
[160] R T Collins, Y X Liu, M. Leordeanu. On-line selection of discriminative trackingfeatures[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(10):1631-1643.
[161] G. R. Bradski. Computer Vision Face Tracking as a Component of a PerceptualUser lnterfaee. In Proceedings of IEEE Workshop on Applications of ComputerVision, October,1998,214-219.
[162] Xu X, Li B. Head tracking using particle flter with intensity gradient and colorhistogram[C]. In: Proceedings of IEEE Conference on Multimedia and Expo. IEEE,2005,888-891.
[163] X.Tao, D.Christian. Monte Carlo Visual Tracking Using Color Histograms and aSpatially Weighted Oriented Hausdorff Measure. In Proceedings of the Conferenceon Analysis of Images and Patterns, August,2003,190-197.
[164] Maggio E., Smeraldi F. A Cavallaro. Adaptive multi-feature tracking in a particlefiltering framework[J]. IEEE Transactions on Circuits and Systems for VideoTechnology,2007,vol.17(10):1348-1359.
[165] J.Kang, L.Cohen, G.Medioni. Object Reacquisition Using Geometric InvariantAppearance Model. International Conference on Pattern Recognition.2004,Cambridge,759-762.
[166] M.Spengler, B.Sehiele. Towards Robust Multi-cue Integration for Visual Tracking.Machine Vision and Applications,2003,14:50-58.
[167] J.Triesch, C.vonder Malsburg. Self-organized Integration of Adaptive Vis sualCues for Face Tracking. IEEE Conf. on Automatie Face and Gesture Reeognition.2000, Grenoble, France:102-107.
[168] P.Brasnett, L.M.lova, D.Bull.N.Canagarajah. Sequential Monte Carlo Tracking byFusing Multiple Cues in Video Sequences. Image and Vision Computing.2007,25:1217-1227.
[169] Matthews I, Ishikawa T, Baker S. The template update problem. IEEE Trans onPattern Analysis and Machine Intelligence,2004,26(6):810-815.
[170] M. Suwa, N. Sugie, and K. Fujimora. A preliminary note on pattern recognition ofhuman emotional expression. Proceedings of the Fourth International JointConference on Pattern Recognition.1978.408-410.
[171] B. Fasel, J. Luettin. Automatic facial expression analysis: a survey. PatternRecognition.2003.36(1):259-275.
[172] Corinna Cortes, Vladimir Vapnik. Support vector networks. Machine Learning.1995.20(3):273-297.
[173] Paul P. P., Monwar M. M., Gavrilova M. L., et al.. Rotation invariant multi-viewface detection using skin color regressive model and SVR. International Journal ofPattern Recognition and Artificial Intelligence.2010,24(8).1261-1280.
[174]阮锦新,尹俊勋.基于人脸特征和AdaBoost算法的多姿态人脸检测.计算机应用.2010,(04).967-970.
[175] Viola P., Jones M.. Rapid object detection using a boosted cascade of simplefeatures. IEEE Conference on CVPR.2001:511-518.
[176] Freund Y., Schapire R. E.. A decision-theoretic generalization of online learningand an application to boosting. The Second European Conference onComputational Learning Theory.1995:23-37.
[177]于清,赵晖.一种2_a_2支持向量机多类分类新方法.计算机工程与应用.2008.44(25):186-188.
[178] Bai Y., Guo L. H., Jin L. W., et al.. A novel feature extraction method usingpyramid histogram of orientation gradients for smile recognition. IEEEInternational Conference on Image Processing.2009.3305–3308.
[179] Dalal N.D., Triggs B.. Histograms of oriented gradients for human detection.IEEE Computer Society Conference on CVPR.2005.886–893.
[180] Q. Zhu, M.-C. Yeh, K.-T. Cheng, et al. Fast Human Detection Using a Cascade ofHistograms of Oriented Gradients[C]. IEEE Computer Society Conference onCVPR: University of California at Santa Barbara, CA, USA,2007:1491-1498.
[181]孙权森,曾生根,王平安等.典型相关分析的理论及其在特征融合中的应用.计算机学报.2005,28(9).1524-1533.
[182]严新平.基于特征融合的笑脸识别算法研究.西安电子科技大学硕士学位论文．2012.
[183] Hotelling H.. Relations between two sets of variates. Biometrika.1936,34(4),321–377.
[184] Sun T. K., Chen, S. C., Jin Z., et al.. Kernelized discriminative canonicalcorrelation analysis. IEEE International Conference on Wavelet Analysis andPattern Recognition.2007.1283–1287.
[185] Krebel U.. Pairwise classification and support vector machines. Advances in KernelMethods: Support Vector Learning.1999.255-268.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |