大屏幕人机互动中若干关键技术研究
|
摘要
大屏幕多媒体的展示系统越来越多地应用在各种场合,例如科技馆、展览馆等场所,而目前大屏幕人机交互还没有完善的解决方案。手势交互具有交互自然、体验性好等优势,更符合人类交互的的需求,已经成为大屏幕人机交互方案的研究热点。
大屏幕人机交互主要涉及三个方面的内容,人机交互时交互人体的跟踪,交互手势的跟踪与识别,以及交互时涉及到的文字输入问题。本文论文主要贡献如下：
在物体检测方面提出了一种高斯背景模型快速更新背景机制,利用即时背景差分和高斯混合模型相结合的方法,解决在光线瞬间变化等情况下,高斯背景由于更新背景速度慢,导致前景误检测问题。
在人体跟踪方面探讨了基于Meanshift的跟踪算法,针对Meanshift的单一颜色特征和整体目标区域建立模型,在目标尺度变化、光线变化情况下鲁棒性差的问题,提出基于分模块和对每个模块采用纹理和颜色特征建立模型,大大提高了算法的鲁棒性。并探讨了人体遮挡情况下的人体跟踪算法,结合卡尔曼滤波预测算法,在人体完全遮挡的情况下取得了良好的跟踪效果。
提出了一种简单的双目视觉定位方法,利用摄像头的投影几何原理和空间直线的关系,避免了传统双目视觉定位的复杂的摄像头标定流程,不利于实际场合使用。在精度不变的情况下,提高了实用性。
提出了一种通过识别静态手势,向拼音输入法输入拼音,以达到利用手势向系统输入汉字功能。利用深度图像分割出静态手势,避免了传统RGB摄像头采集手势时,受惯性、背景复杂性以及光照等影响,提高了鲁棒性。在提取静态手势特征上,采用SIFT特征提取方法,既保留了轮廓的各种旋转,缩放不变形,又加强了局部区域特征,提高识别率。手势分类则采用了SVM方法,构造一个多分类树结合汉字拼音的规则,能提供一分钟十个汉字左右的输入方法,可以有效地满足搜索等需要关键字的文字输入需求。
在动态手势交互方面,动态手势跟踪利用粒子滤波能够处理非线性目标以及非高斯分布系统的特性,使用粒子滤波算法对手势进行跟踪,获取手势轨迹。传统的粒子滤波在样本重采样过程中,会造成样本的“贫化”问题,本文利用样本周围像素产生样本,利用Hausdorff距离计算个各样本的权值,利用随机平均分布获得随机数,通过周围像素产生的样本获得伪随机样本,解决重采样造成的样本“贫化”问题。得到手势的轨迹,利用16方向角进行离散量化,作为手势识别的输入向量。由于隐式马尔科夫链(HMM)可以同时对空间和时间相关关系建立模型,适用于动态手势识别。传统的HMM初始状态个数是根据经验值,而本文提出一种利用关键点算法对不同的手势初始状态设定不同的值,使得初始状态设定有个参考机制。在选择训练样本时,利用混沌算法,找出训练样本的最优值,使得训练出的HMM模型具有全局最优特性。利用一种阈值的方法,对传统HMM方法进行改进,使得HMM具有一定的拒识率,最大可能地排除输入的错误手势,提高识别率,实验验证了方法的有效性,可以进行人机交互。
通过实验可以验证,本文有效地解决了的大屏幕多媒体交互中出现的三个问题,可以使用户在大屏幕人机交互中有较好的,更自然的用户体验。
While large Screen multimedia display system is increasingly being used in various occasions, such as science and technology museum, exhibition hall and other places, there isn't a perfect solution for large screen human-computer interaction. Gesture-based interaction has become a research focus in large screen human-computer interaction program, as a result of the advantages of natural operation, well experience and more in line with the requirements of human interaction.
Large screen human-computer interaction mainly involves three aspects of content, man-machine interactive human body tracking, gesture interaction tracking and identification, as well as the interaction involving text input problem. The main contributions of this paper are listed as follows:
Firstly, this paper proposed a fast mechanism of updating background based on Gaussian background model for object detection. In the case of instantaneous illumination changing, Gaussian background lead to the problem of foreground error detection because of slow speed of updating background. The method in this paper has resolved it by using the method of combining the background subtraction and gaussian mixture model.
Secondly, this paper has discussed and improved the tracking algorithm based on Meanshift,and improved its robustness. Aiming at the bad robustness,leaded by building model with the single color feature and single whole target area of Meanshift, in the situation of target scale changing and light changing, this paper presents a model based on modules and the features of texture and color in each model, so that improves the robustness of the algorithm greatly. It also discusses the algorithm of body tracking under the condition of body block in this paper. Combining with Kalman filter prediction algorithm, a good tracking effect is obtained in the case of body blocked completely.
Thirdly, this paper presents a simple method of binocular vision positioning. In traditional binocular vision positioning method, the way of camera demarcation is complex and is unfit for actual situations. But in precision, we can use the camera projection geometry and spatial linear relationship to improve the computational efficiency, and make it convenient for practical use.
Forthly, this paper puts forward a way of static gesture recognition to input Chinese characters to the system according to Pinyin input method. When we collect gestures with traditional RGB camera, they are often effected by inertia, complex background and lighting. We can avoid it by using depth image to segment image and get a static gesture, so that it improves the robustness. Extracting the static gesture feature with the way of extracting features of sift, on one hand, it retains the contours of all kinds of ratating and keeps zooming deformation, and stregthens local regional characteristics and improves the recognition rate on the other hand. The method of gesture classification is based on SVM. Constructing a classification tree combining with the rules of Pinyin, we can provide a way to input ten Chinese characters per minute and can effectively meet the needs of searching, where we want to input key Chinese characters.
Finally, in the dynamic gesture interaction, dynamic gesture tracking with particle filter can deal with nonlinear target and characteristics of non-Gauss distribution system, using particle filter algorithm to track the gesture for gesture trajectory. The color feature is generally used for the traditional particle filter, and the partic' number is fixed. This paper uses gesture contour line according to the current state of motion gestures to dynamically determine the number of particles, and prevent the particles from degradation by the dynamic allocation of the particle weights. Get the gesture trajectories, the discrete quantization using16direction angle as input vector quantization of the gesture recognition. Since the Hidden Markov models (HMM) can be related to space and time model, it can be suitable for dynamic gesture recognition. Although the number of traditional HMM initial states is based on the value of experience, this paper uses the key point algorithm for gesture with different initial states to set different values, which makes the initial state setting have a reference mechanism. In the selection of training samples, using chaos algorithm to find the best training samples can make the HMM model is trained have the global optimal characteristics. Using the method of threshold to improve the traditional HMM method make the HMM have certain rejection rate, exclude the error gesture input, improve the recognition rate, prove that the method is effective, and be interactive.
As verified by experiments, this paper solves the three problems appeared in large screen multimedia interaction effectively. So the users can get better and more natural experiences during the process of interaction with large screen.
大屏幕人机交互主要涉及三个方面的内容,人机交互时交互人体的跟踪,交互手势的跟踪与识别,以及交互时涉及到的文字输入问题。本文论文主要贡献如下：
在物体检测方面提出了一种高斯背景模型快速更新背景机制,利用即时背景差分和高斯混合模型相结合的方法,解决在光线瞬间变化等情况下,高斯背景由于更新背景速度慢,导致前景误检测问题。
在人体跟踪方面探讨了基于Meanshift的跟踪算法,针对Meanshift的单一颜色特征和整体目标区域建立模型,在目标尺度变化、光线变化情况下鲁棒性差的问题,提出基于分模块和对每个模块采用纹理和颜色特征建立模型,大大提高了算法的鲁棒性。并探讨了人体遮挡情况下的人体跟踪算法,结合卡尔曼滤波预测算法,在人体完全遮挡的情况下取得了良好的跟踪效果。
提出了一种简单的双目视觉定位方法,利用摄像头的投影几何原理和空间直线的关系,避免了传统双目视觉定位的复杂的摄像头标定流程,不利于实际场合使用。在精度不变的情况下,提高了实用性。
提出了一种通过识别静态手势,向拼音输入法输入拼音,以达到利用手势向系统输入汉字功能。利用深度图像分割出静态手势,避免了传统RGB摄像头采集手势时,受惯性、背景复杂性以及光照等影响,提高了鲁棒性。在提取静态手势特征上,采用SIFT特征提取方法,既保留了轮廓的各种旋转,缩放不变形,又加强了局部区域特征,提高识别率。手势分类则采用了SVM方法,构造一个多分类树结合汉字拼音的规则,能提供一分钟十个汉字左右的输入方法,可以有效地满足搜索等需要关键字的文字输入需求。
在动态手势交互方面,动态手势跟踪利用粒子滤波能够处理非线性目标以及非高斯分布系统的特性,使用粒子滤波算法对手势进行跟踪,获取手势轨迹。传统的粒子滤波在样本重采样过程中,会造成样本的“贫化”问题,本文利用样本周围像素产生样本,利用Hausdorff距离计算个各样本的权值,利用随机平均分布获得随机数,通过周围像素产生的样本获得伪随机样本,解决重采样造成的样本“贫化”问题。得到手势的轨迹,利用16方向角进行离散量化,作为手势识别的输入向量。由于隐式马尔科夫链(HMM)可以同时对空间和时间相关关系建立模型,适用于动态手势识别。传统的HMM初始状态个数是根据经验值,而本文提出一种利用关键点算法对不同的手势初始状态设定不同的值,使得初始状态设定有个参考机制。在选择训练样本时,利用混沌算法,找出训练样本的最优值,使得训练出的HMM模型具有全局最优特性。利用一种阈值的方法,对传统HMM方法进行改进,使得HMM具有一定的拒识率,最大可能地排除输入的错误手势,提高识别率,实验验证了方法的有效性,可以进行人机交互。
通过实验可以验证,本文有效地解决了的大屏幕多媒体交互中出现的三个问题,可以使用户在大屏幕人机交互中有较好的,更自然的用户体验。
While large Screen multimedia display system is increasingly being used in various occasions, such as science and technology museum, exhibition hall and other places, there isn't a perfect solution for large screen human-computer interaction. Gesture-based interaction has become a research focus in large screen human-computer interaction program, as a result of the advantages of natural operation, well experience and more in line with the requirements of human interaction.
Large screen human-computer interaction mainly involves three aspects of content, man-machine interactive human body tracking, gesture interaction tracking and identification, as well as the interaction involving text input problem. The main contributions of this paper are listed as follows:
Firstly, this paper proposed a fast mechanism of updating background based on Gaussian background model for object detection. In the case of instantaneous illumination changing, Gaussian background lead to the problem of foreground error detection because of slow speed of updating background. The method in this paper has resolved it by using the method of combining the background subtraction and gaussian mixture model.
Secondly, this paper has discussed and improved the tracking algorithm based on Meanshift,and improved its robustness. Aiming at the bad robustness,leaded by building model with the single color feature and single whole target area of Meanshift, in the situation of target scale changing and light changing, this paper presents a model based on modules and the features of texture and color in each model, so that improves the robustness of the algorithm greatly. It also discusses the algorithm of body tracking under the condition of body block in this paper. Combining with Kalman filter prediction algorithm, a good tracking effect is obtained in the case of body blocked completely.
Thirdly, this paper presents a simple method of binocular vision positioning. In traditional binocular vision positioning method, the way of camera demarcation is complex and is unfit for actual situations. But in precision, we can use the camera projection geometry and spatial linear relationship to improve the computational efficiency, and make it convenient for practical use.
Forthly, this paper puts forward a way of static gesture recognition to input Chinese characters to the system according to Pinyin input method. When we collect gestures with traditional RGB camera, they are often effected by inertia, complex background and lighting. We can avoid it by using depth image to segment image and get a static gesture, so that it improves the robustness. Extracting the static gesture feature with the way of extracting features of sift, on one hand, it retains the contours of all kinds of ratating and keeps zooming deformation, and stregthens local regional characteristics and improves the recognition rate on the other hand. The method of gesture classification is based on SVM. Constructing a classification tree combining with the rules of Pinyin, we can provide a way to input ten Chinese characters per minute and can effectively meet the needs of searching, where we want to input key Chinese characters.
Finally, in the dynamic gesture interaction, dynamic gesture tracking with particle filter can deal with nonlinear target and characteristics of non-Gauss distribution system, using particle filter algorithm to track the gesture for gesture trajectory. The color feature is generally used for the traditional particle filter, and the partic' number is fixed. This paper uses gesture contour line according to the current state of motion gestures to dynamically determine the number of particles, and prevent the particles from degradation by the dynamic allocation of the particle weights. Get the gesture trajectories, the discrete quantization using16direction angle as input vector quantization of the gesture recognition. Since the Hidden Markov models (HMM) can be related to space and time model, it can be suitable for dynamic gesture recognition. Although the number of traditional HMM initial states is based on the value of experience, this paper uses the key point algorithm for gesture with different initial states to set different values, which makes the initial state setting have a reference mechanism. In the selection of training samples, using chaos algorithm to find the best training samples can make the HMM model is trained have the global optimal characteristics. Using the method of threshold to improve the traditional HMM method make the HMM have certain rejection rate, exclude the error gesture input, improve the recognition rate, prove that the method is effective, and be interactive.
As verified by experiments, this paper solves the three problems appeared in large screen multimedia interaction effectively. So the users can get better and more natural experiences during the process of interaction with large screen.
引文
[1]A. Mittal, N. Paragios. Motionr-based background subtraction using adaptive kernel density estimation [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2004.
[2]N. Ohta. A statistical approach to background subtraction for surveillance systems [C]. Proceedings of IEEE International Conference on Computer Vision,2001.
[3]C. Stauffer, W. Grimson. Adaptive background mixture models for real-time tracking [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,1999.
[4]E. Stringa, C. Regazzoni. Real-time video-shot detection for scene surveillance applications [J]. IEEE Transactions on Image Processing,2000,9(1):69-79.
[5]G. Foresti. Object recognition and tracking for remote video surveillance [J]. IEEE Transactions on Circuits and Systems for Video Technology,1999,9(7): 1045-1062.
[6]A. Lipton, H. Fujiyoshi, R. Patil. Moving target classification and tracking from real-time video [C]. Proceedings of IEEE Workshop on Applications of Compute Vision,1998.
[7]F. Moscheni, S. Bhattacharjee, M. Kunt. Spatio-temporal segmentation based on region merging [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998,20(9):897-915.
[8]A. Neri, S. Colonnese, G. Russo, P. Talone. Automatic moving object and background separation [J]. Signal Processing,1998,66(2):219-232.
[9]J. Barron, D. Fleet, S. Beauchemin. Performance of optical flow techniques [J]. International Journal of Computer Vision,1994,12(1):43-77.
[10]A. Verri, S. Uras, E. DeMicheli. Motion Segmentation from optical flow [C]. Proceedings of the 5th Alvey Vision Conference,1989.
[11]N. Friedman, S. Russell. Image segmentation in video sequences:a probabilistic approach[C]. Proceedings of the Thirteenth Conference on Uncertainty in Artificial Intelligence,1997.
[12]G. McLachlan, T. Krishnan. The EM algorithm and extensions [M]. New York:Wiley, 1997.
[13]E. Stringa. Morphological change detection algorithms for surveillance applications [C]. Proceedings of British Machine Vision Conference,2000.
[14]Y. Kuno, T. Watanabe, Y. Shimosakoda, S. Nakagawa. Automated detection of human for visual surveillance systemh [C]. Proceedings of IEEE International Conference on Pattern Recognition,1996.
[15]R. Cutler, L. Davis. Robust real-time periodic motion detection, analysis, andapplications [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(8):781-796.
[16]0. Javed, M. Shah. Tracking and Object Classification for Automated Surveillance [C]. Proceedings of European Conference on Computer Vision,2002.
[17]T. Kanade, R. Collins, A. Lipton, P. Burt, L. Wixson. Advances in cooperative multi-sensor video surveillance [C]. Proceedings of DAPRA Image Understanding Workshop,1998.
[18]A. Selinger, L. Wixson. Classifying moving objects as rigid or non-rigid without correspondences [C]. Proceedings of DAPRA Image Understanding Workshop,1998.
[19]C. Stauffer. Automatic hierarchical classification using time-basedco-occurrences [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Rcognition,1999.
[20]E. Cuevas, D. Zaldivar, R Rojas. Kalman filter for vision tracking [J]. Measurement,2005.
[21]S. K. Zhou, R. Chellappa, B. Monghaddam. Visual tracking and recognition using appearance-adaptive models in particle filters [J], IEEE Trans. Image Processing, vol.13-11, pp.1491-1506, Nov.2004.
[22]B. Ristic, S, Arulampalam, and N. Gordon, Beyond the Kalman filter; Particle filters for tracking applications [M]. Artech House Publishers 2004.
[23]M. S. Arulampalam, and S. Maskell, and N. Gordon, and T. Clapp. A tutorial on particle filters for online nonliriear/non-Gaussian Bayesian tracking [J], IEEE Transactions on Signal Processing, vol.50, no.2,2002.
[24]K Okuma, A.Taleghani, N Freitas, J. J Little, and David G. Lowe. A Boosted Particle Filter:Multitarget Detection and Tracking [C] ECCV 2004.
[25]D Ross, J. Lims and M. H. Yang. Adaptive probabilistic visual tracking with incremental subspace update [C]. in Proc. European Conf. Computer Vision, pp. 470-482,2004
[26]'B Liu, J. Huang, L Yang, C. Kulikowsk. Robust tracking using local sparse appearance model and k-selection [C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2011.
[27]K. Sakabe, T. Taguchi, T. Shakunaga. Automatic Eigentemplate Learning for Sparse Template Tracker [M]. In:Wada, T., Huang, F.'Lin, S. (eds.) PSIVT 2009. LNCS,vol.5414, pp.714-725.. Springer, Heidelberg (2009).
[28]D. Comaniciu, V. Ramesh and P. Meet. Kernel-based object tracking [J]. IEEE Transactions on PAMI,25:564-577,2003.
[29]H Zhou, and Y Yuan, and C Shi, Object tracking using SIFT features and mean shift [J] Computer Vision and Image Understanding, vol 113'no 3, pp 345-352,2009
[30]L. Fan. A feature-based object tracking method using online template switching and feature adaptation [C].6th International Conference on Image and Graphics, 2011(1CIG 2011).
[31]Liu, W. Zhou, H. Yin,N. Yu. Tracking based on SURF and superpixel [C].6th International Conference on Image and Graphics,2011.
[32]王春立.面向大词汇量的连续中国手语识别系统的研究与实现[D].大连：大连理工大学,2003.
[33]Liang R H, Ouhyoung M. A sign Language Recognitions System Using Hidden Markov Model and Context Sensitive Search[C] Proc. of the ACM Symposium on Virtual Reality Software and Technology二[5.1,]:[s. n.],1996:59-66.
[34]吴江琴,高文,陈熙霖.基于数据手套的汉语手指字母的识别[J1.模式识别与人工智能, 1999,12(1)：74-78.
[35]付永刚,张凤军,戴国忠.双手交互界面研究进展[J].计算机研究与发展,2005,42(4)：604-13.
[36]Starrner T, Pentland A. Real-time American Sign Language recognition from video using Hidden Markov Models[C]. CoralGables, FL, USA:[s.n.],1995:265-270
[37]Rigoll, G, Kosmala A, Eickeler S. High Performance real-time gesture recognition using hidden markov models [C] [s.1.]:[s. n.],1997:69-80.
[38]Park H, Kim E, Jang s,An HMM-based gesture recognition for perceptual user interface[C] proc. Of the 5th Pacific-Rim Conf. on Multimedia[s.1.]:[s. n.], 2004:1027-1034.
[39]Bobick A, Wilson A.A state-based approach to the representation and recognition of gesture [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,1997,19(12).
[40]Lee H K, Kim J. An HMM-based threshold model approach for gesture recognition [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,1999,21 (10).
[41]任海兵,祝远新,徐光枯,等.连续动态手势的时空表观建模及识别[J].计算机学报,2000,23(8)
[42]王西颖,戴国忠,张习文,等.基于HMM-FNN模型的复杂动态手势识别汇[J].软件学报,2008,19(9)：2302-312.
[43]Bao P. T, Binh N. T, Khoa T. D. A New Approach to Hand Tracking and Gesture Recognition by a New Feature Type and HMM[A]. Sixth International Conference on Fuzzy Systems and Knowledge Discovery[C]. USA:IEEE,2009:3-6
[44]Asaari M. S. M, Suandi S. A. Hand gesture tracking system using Adaptive Kalman Filter[A].10th International Conference on the Intelligent Systems Design and Applications(ISDA) [C]. USA:IEEE,2010:166-171
[45]罗元,李玲,张百胜,等.基于CamShift和Kalman滤波混合的视频手势跟踪算法[J].计算机应用研究,2009,03：1163-1165
[46]Park S, Yu S, Kim J, et al.3D hand tracking using Kalman filter in depth space [J]. EURASIP Journal on Advances in Signal Processing,2012:36-84
[47]张良国,吴江琴,高文,姚鸿勋.基于Hausdorff距离的手势识别.中国图象图形学报A,2002,7(11)：1144-1150.
[48]Jain A K, Ross A, Pankanti S, A prototype hand geometry-based verification system. In:2nd International Conference on Audio- and Video-Based Biometric Person Authentication, Washington D. C. USA,1999,166-171.
[49]邓志国.基于BP神经网络的静态手势识别方法.华东交通大学学报.2005,22(5)：86-88.
[50]江立,阮秋琦.基于神经网络的手势识别技术研究.北京交通大学学报,2006,30(5)：32-36.
[51]Nolker C, Ritter H. Illumination Independent Recognition of Deictic ArmPostures, In:Proceedings of the 24th Annual Conference of Industrial Electronics
[52]Munib Q, Habeeb M, Takruri B, Ai-Malik HA. American sign language (ASL) recognition based on Hough transform and neural networks[J]. Expert Systems with Applications,2007,32:24-37.
[53]T. Horprasert, D. Harwood, L. S. Davis. A statistical approach for real-time robust background subtraction and shadow detection. Proc. of IEEE ICCV' 99 Frame-Rate Workshop,1999.
[54]A. Elgammal, R. Duraiswami, D. Harrwood, L. S. Davis. Background and foreground modeling using nonparametric Kernel density estimation for visual surveillance. Proc. of the IEEE,90(7),1151-1163,2002.
[55]M. Harville, G. Gordon, and J. Woodfill. Foreground segmentation using adaptive mixture models in color and depth. Proc. of IEEE Events Workshop,2001.
[56]C. Stauffer, W. E. L. Grimson. Learning Pattons of Activity Using Real-Time Tracking. IEEE Trans. On PAMI,22(8),2000.
[57]G. Welch, G. Bishop. An introduction to the Kalman filter. UNC-Chapel Hill Technial Report:TR95-041,2000.
[58]K. Karmann, A. Brandt, R. Gerl, Moving object segmentation based on adaptive reference images.Signal Processing, Vol.5,1990, pp951-954.
[59]Guo Jing, Chng Eng Siong and Deepu Rajan. Foreground Motion Detection by Difference-Based Spatial Temporal Entropy Image. IEEE,2004.
[60]Collins R T, Lipton A J.Kanade T.1999. A System for Vedio Sureilliance and Monitoring. Proc.Am[C]. Nuclear Soc. Eighth Int'1 Topical Meeting Robotic and Romote System.
[61]Stringa E,Regazzoni C S.2000. Real-time video-shot detection for scene surveillance applications. IEEE Transactions on Image Processing, vol 9, no.1 pp.69-79.
[62]S. Ribaric, G. Adrinek, S. Segvic. Real-Time Active Visual Tracking System. IEEE Melecon 2004
[63]J. L. Barron, S. S. Beauchemin, D. J. Fleet. On Optical Flow.6th Int. Conf. on Artificial Intelligence and Information-Control Systems of Robots, Bratislava, Slovakia, Sept 12-16, pp3-14,1994.
[64]伏思华,张小虎.2004.基于序列图像的运动目标实时检测方法.光学技术.30(2)：215-217
[65]B. K. P Horn, B. G. Schunch, Detemining Optical Flow, AI 17(1981),185-203.
[66]D. Gutchess, M. Trajkovic, E. Cohen-Solal, D. Lyons, A. K. Jain, A Background Model Initialization Algorithm for Video Surveillance, IEEE 2001
[67]张旭东,高隽,方廷健。基于色彩与高斯混合模型的运动阴影检测[C].第十四届中国神经网络学术会议论文集.合肥.合肥工业大学出版社,2004：578-583
[68]冈萨雷斯等著;阮秋琦,阮宇智等译.数字图像处理(第二版)[M].北京：电子工业出版社,2007.8.
[69]M. Oren, C. Papageorgiou, P. Sinha, et al:Pedestrian Detection Using Wavelet Templates[C]. IEEE Conference on Computer Vision and Pattern Recognition. 1997:193-199.
[70]C. Papageorgiou, T. Poggio:Trainable Pedestrian Detection[C]. International Conference on Image Processing. Kobe, Japan,1999,4:35-39.
[71]C.Papageorgiou, T. Poggio. A Trainable System for Object Detection[J]. International Journal of Computer Vision,2000,38(1):15-33.
[72]A. Mohan, C. Papageorgiou, T. Poggio. Example-based Object Detection in Images by Components [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001,23(4):349-361.
[73]P.Viola, M. J. Jones, D. Snow:Detecting Pedestrians Using Patterns of Motion andAppearance[C]. IEEE International Conference on Computer Vision. Nice, France,2003,2:734-741.
[74]A. Broggi, M. Bertozzi, A. Fascioli, et al:Shape-based Pedestrian Detection [C]. IEEEIntelligent Vehicles Symposium.2000:215-220.
[75]D. M. Gavrila:Pedestrian Detection from a Moving Vehicle[C]. European Conference on Computer Vision. Dublin, Ireland,2000,2:37-49.
[76]P. F. Felzenszwalb:Learning Models for Object Recognition[C]. IEEE International Conference on Computer Vision and Pattern Recognition. Kauai, USA, 2001,1:56-62.
[77]D. M. Gavrila, S. Munder. Multi-cue Pedestrian Detection and Tracking from a Moving Vehicle[J]. International Journal of Computer Vision,2007,73(1).
[78]V. Ferrari, T. Tuytelaars, L. V. Gool:Object Detection by Contour Segment Networks[C]. European Conference on Computer Vision.2006,3:14-28.
[79]Z. Lin, L. S. Davis, D. Doermann, et al:Hierarchical Part-template Matching for Human Detection and Segmentation[C]. IEEE International Conference on Computer Vision.2007.
[80]Z. Lin, L. S. Davis:A Pose-invariant Descriptor for Human Detection and Segmentation[C]. European Conference on Computer Vision.2008:423-436.
[81]B. Wu. Part Based Object Detection, Segmentation and Tracking by Boosting Simple Shape Feature Based Weak Classifiers[D]. University of Southern California,2008.
[82]D. G. Lowe:Object Recognition from Local Scale-invariant Features[C]. IEEE International Conference on Computer Vision.1999:1150-1157.
[83]B. Leibe, E. Seemann, B. Schiele:Pedestrian Detection in Crowded Scenes[C]. IEEE Conference on Computer Vision and Pattern Recognition.2005,1:878-885.
[84]N. Dalal, B. Triggs:Histograms of Oriented Gradients for Human Detection[C]. C. Schmid, S. Soatto, C. Tomasi. International Conference on Computer Vision and Pattern Recognition.2005,2:886-893.
[85]Q. Zhu, S. Avidan, M. C. Yeh, et al:Fast Human Detection Using a Cascade of Histograms of Oriented Gradients[C]. IEEE Conference on Computer Vision and Pattern Recognition.2006:1491-1498.
[86]P. Felzenszwalb, D. McAllester, D. Ramanan:A Discriminatively Trained, Multi-scale, Deformable Part Model[C]. IEEE Conference on Computer Vision and Pattern Recognition.2008.
[87]I. P. Alonso, D. F. Llorca, M. A. Sotelo, et al. Combination of Feature Extraction Methods for Svm Pedestrian Detection[J]. IEEE Transactions on Intelligent Transportation Systems,2007,8(2):292-307.
[88]L. Nanni, A. Lumini. Ensemble of Multiple Pedestrian Representations [J]. IEEE Transactions on Intelligent Transportation Systems,2008,9(2):365-369.
[89]C. Wojek, S. Walk, B. Schiele:Multi-cue Onboard Pedestrian Detection[C]. IEEE Conference on Computer Vision and Pattern Recognition.2009.
[90]S. Ju, M. Black, Y. Yacoob. Cardboard people:A Parameterized Model of Articulated Image Motion. Intemational conference on Face and Gesture Analysis, 1996
[91]C. R.Wren, A. Azarbaye jani, T. Darrell, A. P. Pentland. Pfinder:real-time tracking of the human body. Transactions on Pattern Analysis and Machine Intelligence, 19(7), July 1997.
[92]Polana R, Nelson R. Low Level Recognition of Human Motion. Proc IEEE Workshop on Motionof Non-Rigid and Articulated Objects,1994,77-82.
[93]J. Segen and S. Pingali. A Camera-based System for Tracking People in Real Time. InternationalConference on Pattern Recognition, pages 63-67, Vienna, Austria, August 1996.
[94]郑红。基于自适应背景更新和色彩特征的运动人体检测与跟踪[D]。上海：上海交通大学计算机科学与工程系,2009
[95]Bertalmio M, Sapiroo G,Randll G.Morphing active contours. IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(7):733-737
[96]Paragios N, Deriche R. Geodesicractive contours and levelsets for the detection and-Tracking of moving objects. IEEE Trans Pattern-Analysis and Machine Intelligence,2000,22(3):266-280
[97]Peterfreund N. Robust tracking of Position and velocity with kalman snakes. IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(6):564-569
[98]Fukanaga K, Hostetler L. D. The estimation of the gradient of a density function, with applications in Pattern recognition[J]. IEEE Trans Information Theory,1975, 21(1):32-40.
[99]吴喜之.非参数统计[M].北京：中国统计出版社,1999.
[100]王星.非参数统计[M].北京：中国人民大学出版社,2005.
[101]朱胜利.Meanshift及相关算法在视频跟踪中的研究[Dl.博士学位论文,浙江大学,2006
[102]Comaniciu D, Meer P. Mean Shift Analysis and Application[A]. In:Proeofthe7th IEEE International Conference on Computer Vision[C].Kerkyra, Greece:IEEE Computer
[103]Comaniciu D, Ramesh V.. Kernel-based object tracking [J] IEEE International Transactions on Pattern Analysis and Machine Intelligenee,2003,25(5):564 - 575
[104]Isard M and Blake A. Contour Tracking by Stochastic Propagation of Conditional Density. In:Proc European Conference on Computer Vision, Cambridge,1996.343～356.
[105]陈远祥.视频图像运动目标跟踪技术的研究[D].江苏：江苏大学,2010
[106]方颖,王汇源等.适用于多目标之间遮挡问题的跟踪算法.计算机应用,2007,vol(27)：62-65
[107]Tsai R Y. A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses[J]. IEEE Journal of Robotics and Automation,1987,3(4):323-344.
[108]Weng J, Cohen P, Herniou M. Camera calibration with distortion models and accuracy evaluation [J].IEEE Trans, on PAMI,1992,14(10):965-980.
[109]Zhang Z. A flexible new technique for camera calibration [J]. IEEE Trans. On Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334.
[110]Michael A. Penna. Camera Calibration:A Quick and Easy Way to Determine the Scale actor. IEEE Tpansactions on Pattern Analysis and Machine Intelligence[J].1991,13(12):1240-1245.
[111]R. K. Lenz and R. Y. Tsai. Techinques for calibration of the scale factor and image center for high accuracy 3-D machine metrology[J]. IEEE rans. Patt. Anal. MachineIntell.1988,10(5):713-720.
[112]Donald Hearn, M. Pauline BakerComputer Graphics with OpenGL Third Edition[M]. London:Prentice Hall,2003:438～455.
[113]郭星,刘政怡,李炜,吴建国.基于双目视觉的大屏幕人机交互方式[J].计算机工程与应用,2012,48(1)：176-179.
[114]Lee J, Kunii T L. Model-based analysis of hand posture. IEEE Computer Graphic and Applications,1995,15(5):77-86.
[115]B. D. Zarit, B. J. Super. Comparison of five color models in skin pixel classification[J]. In:Proceedings of the International Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-time Systems, Corfu, Greece, 1999,58-63.
[116]S. Jayaram, S. Schmugge. Effect of color space transformation, the illuminance component and color modeling on skin detection[J]. In:Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR'04), Washington, DC. USA,2004,813-818.
[117]J. C. Tenilion, M. N. Shirazi, H. Fukamachi. Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images [J]. In:Proc Conference of Automatic Face and Gesture Recognition, Grenoble, France,2003:54-61.
[118]夏振宇.人体皮肤分割技术的研究和应用[D].长沙：中南大学硕士学位论文,2009.
[119]周星,高志军.立体视觉技术的应用与发展[J].工程图学学报,2010,31(4)：50-55
[120]Dancter, Rich-tie, Khazar, et al. Time-of- flight camera. http://en. wikipedia. org/wiki/-Time-of- flight_camera.15, March,2012
[121]Loren Schwarz N N. Depth Imaging with Time-of-Flight Cameras and the Kinect[J]. 3D Computer Vision II Winter Term 2011,2012
[122]Stowers J, Hayes M, Bainbridge-Smith A. Altitude control of a quad rotor helicopter using depth map from Microsoft Kinect sensor. IEEE International Conference on Mechatronics (ICM)[C]. USA:IEEE,2011:358-362
[123]Hu M K. Visual Pattern Recognition by Moment Invariant. IRE Trans Information Theory,1962, (8):179-187.
[124]刘寅,滕晓龙,刘重庆.复杂背景下基于傅里叶描述子的手势识别[J].计算机仿真,2005,22(12)：158-161.
[125]王涛,刘文印,孙家广,张宏江.傅立叶描述子识别物体的形状[J].计算机研究与发展,2002,39(12).
[126]Lowe D G. Distinctive image features from scale-invariantkeypoints[J]. International Journal of Computer Vision,2004,60(2):91-110.
[l27]Cipolla R, Holling Hurst N J. Human robot interface by pointing with uncelebrated stereovision[J].Image and Vision Computing,1993(14):171-178.
[128]Hyeon Kyu Lee, J IN H KIM. An HMM-based threshold model approach for gesture recognition [J]. IEEE, Pattern nalysis and Machine Intelligence,1999,21 (10):961-973.
[129]陶霖密,彭振云,徐光祐.人体的肤色特征.软件学报,2001,12(7)：1032-1040.
[130]Arulampalam S., Maskell S., Gordon N., and Clapp T., A Tutorial on Particle Filters foronline Non-linear/Non-Gaussian Bayesian Tracking, IEEE Transactions on Signal Processing,2002,50 (2):174-188.
[131]K. Ishibuchi, H. Takemutra, and F. Kishino. Real Time Hand Gesture Recognition using 3D Prediction Model. International Conference on Systems,1993,5 (17):324-328.
[132]刘志明,基于动态手势识别的人机交互技术研究[D].2007,浙江大学.
[133]LiuJ. S. and ChenR. Sequential Monte Carlo Methods for Dynamical Systems, Journal of the American Statistieal Assoeiation,1998,93(5):1032 - 1044.
[134]GordonN. J. SalmondD. J., and SmithA.F. M., Novel Approach to Nonlinear Non-Gaussian Bayesian State Estimation, In IEEE Proceedings on Radar and SignalProcessing,1993,140(2):107-113.
[135]Kitagawa G. Monie Carlo Filter and Smoother for Non-Gaussian Nonlinear State Space Models, Journal of Computational and Graphical Statisties,1996,5(1):1-25.
[136]Higuchi T., Monte Carlo Filtering Using Genetics Algorithm Operator. Journal of Statistical Computation and Simulation,1997,59(1):1-23.
[137]MoY. W. and Xiao D. Y. Hybrid System Monitoring and Diagnosing Based on Particle Filter Algorithm, Acta Automation Siniea,2003,29(3):641-648.
[138]胡昭华.基于粒子滤波的视频目标跟踪技术研究.南京：南京理工大学.2008
[139]Kahol K, Tripathi P, et al. Gesture segmentation in complex motion sequences [C]. Proc. IEEE Int'l Conf.on Image Processing(ICIP' 03),2003,11:105-108.
[140]Lee H, Kim J. An HMM-based threshold model approach for gesture recognition[J].IEEE Trans. Pattern Anal. Machine Intell.,1999,21 (10):961-973.
[141]Mori T. Visual motion perception[J],Circulars of the Electro technical Laboratory,1982,207 (10):1-78.
[142]Kahol K, Tripathi P, et al. Gesture segmentation in complex motion sequences[C]. Proc. IEEE Int'l Conf.on Image Processing(ICIP' 03),2003,11:105-108.
[143]Sakoe H. Two level DP matching-A dynamic programming base pattern matching algorithm for connected word recognition[J]. IEEE Trans on A SSP,1979, ASSP-27 (6):588-595
[144]Sakoe, H. and Chiba, S. Dynamic programming algorithm optimization for spoken word recognition [J]. IEEE Transactions on Acoustics, Speech and Signal Processing, 26(1) pp.43-49,1978, ISSN:0096-3518
[145]Sminchisescu, C., A. Kanaujia, and D. Metaxas, Conditional models for contextual human motion recognition. Computer Vision and Image Understanding, 2006.104(2-3):p.210-220.
[146]Murphy, K.. Dynamic Bayesian networks:representation, inference and learning. 2002, Citeseer.
[147]Yamato, J., J. Ohya, and K. Ishii. Recognizing human action in time-sequential images using hidden Markov model.1992.
[148]Brand, M.,N.Oliver, and A. Pentland. Coupled hidden Markov models for complex action recognition.1997:INSTITUTE OF ELECTRICAL ENGINEERS INC (IEEE).
[149]Kristjansson, T., B. Frey, and T. Huang. Event-coupled hidden Markov models.2000:Citeseer.
[150]Fine, S., Y. Singer, and N. Tishby, The hierarchical hidden Markov model:Analysis and applications.Machine learning,1998.32(1):p.41-62.
[151]马振华,等.现代应用数学手册,概率统计与随机过程卷.北京：清华大学出社,2000.440-457
[152]刘克编.《实用马尔可夫决策过程》.清华大学出版社.2004.11.1
[153]A. B. Poritz. Hidden Markov Modelsr:a guided tour. Proc. of IEEE Intl. Conf. on Acoustic Speech and Signal Processing.1988, PP.7-13
[154 L. R. Rabiner. Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition, in Proc. IEEE, vol.77, pp.257-285
[2]N. Ohta. A statistical approach to background subtraction for surveillance systems [C]. Proceedings of IEEE International Conference on Computer Vision,2001.
[3]C. Stauffer, W. Grimson. Adaptive background mixture models for real-time tracking [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,1999.
[4]E. Stringa, C. Regazzoni. Real-time video-shot detection for scene surveillance applications [J]. IEEE Transactions on Image Processing,2000,9(1):69-79.
[5]G. Foresti. Object recognition and tracking for remote video surveillance [J]. IEEE Transactions on Circuits and Systems for Video Technology,1999,9(7): 1045-1062.
[6]A. Lipton, H. Fujiyoshi, R. Patil. Moving target classification and tracking from real-time video [C]. Proceedings of IEEE Workshop on Applications of Compute Vision,1998.
[7]F. Moscheni, S. Bhattacharjee, M. Kunt. Spatio-temporal segmentation based on region merging [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998,20(9):897-915.
[8]A. Neri, S. Colonnese, G. Russo, P. Talone. Automatic moving object and background separation [J]. Signal Processing,1998,66(2):219-232.
[9]J. Barron, D. Fleet, S. Beauchemin. Performance of optical flow techniques [J]. International Journal of Computer Vision,1994,12(1):43-77.
[10]A. Verri, S. Uras, E. DeMicheli. Motion Segmentation from optical flow [C]. Proceedings of the 5th Alvey Vision Conference,1989.
[11]N. Friedman, S. Russell. Image segmentation in video sequences:a probabilistic approach[C]. Proceedings of the Thirteenth Conference on Uncertainty in Artificial Intelligence,1997.
[12]G. McLachlan, T. Krishnan. The EM algorithm and extensions [M]. New York:Wiley, 1997.
[13]E. Stringa. Morphological change detection algorithms for surveillance applications [C]. Proceedings of British Machine Vision Conference,2000.
[14]Y. Kuno, T. Watanabe, Y. Shimosakoda, S. Nakagawa. Automated detection of human for visual surveillance systemh [C]. Proceedings of IEEE International Conference on Pattern Recognition,1996.
[15]R. Cutler, L. Davis. Robust real-time periodic motion detection, analysis, andapplications [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(8):781-796.
[16]0. Javed, M. Shah. Tracking and Object Classification for Automated Surveillance [C]. Proceedings of European Conference on Computer Vision,2002.
[17]T. Kanade, R. Collins, A. Lipton, P. Burt, L. Wixson. Advances in cooperative multi-sensor video surveillance [C]. Proceedings of DAPRA Image Understanding Workshop,1998.
[18]A. Selinger, L. Wixson. Classifying moving objects as rigid or non-rigid without correspondences [C]. Proceedings of DAPRA Image Understanding Workshop,1998.
[19]C. Stauffer. Automatic hierarchical classification using time-basedco-occurrences [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Rcognition,1999.
[20]E. Cuevas, D. Zaldivar, R Rojas. Kalman filter for vision tracking [J]. Measurement,2005.
[21]S. K. Zhou, R. Chellappa, B. Monghaddam. Visual tracking and recognition using appearance-adaptive models in particle filters [J], IEEE Trans. Image Processing, vol.13-11, pp.1491-1506, Nov.2004.
[22]B. Ristic, S, Arulampalam, and N. Gordon, Beyond the Kalman filter; Particle filters for tracking applications [M]. Artech House Publishers 2004.
[23]M. S. Arulampalam, and S. Maskell, and N. Gordon, and T. Clapp. A tutorial on particle filters for online nonliriear/non-Gaussian Bayesian tracking [J], IEEE Transactions on Signal Processing, vol.50, no.2,2002.
[24]K Okuma, A.Taleghani, N Freitas, J. J Little, and David G. Lowe. A Boosted Particle Filter:Multitarget Detection and Tracking [C] ECCV 2004.
[25]D Ross, J. Lims and M. H. Yang. Adaptive probabilistic visual tracking with incremental subspace update [C]. in Proc. European Conf. Computer Vision, pp. 470-482,2004
[26]'B Liu, J. Huang, L Yang, C. Kulikowsk. Robust tracking using local sparse appearance model and k-selection [C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2011.
[27]K. Sakabe, T. Taguchi, T. Shakunaga. Automatic Eigentemplate Learning for Sparse Template Tracker [M]. In:Wada, T., Huang, F.'Lin, S. (eds.) PSIVT 2009. LNCS,vol.5414, pp.714-725.. Springer, Heidelberg (2009).
[28]D. Comaniciu, V. Ramesh and P. Meet. Kernel-based object tracking [J]. IEEE Transactions on PAMI,25:564-577,2003.
[29]H Zhou, and Y Yuan, and C Shi, Object tracking using SIFT features and mean shift [J] Computer Vision and Image Understanding, vol 113'no 3, pp 345-352,2009
[30]L. Fan. A feature-based object tracking method using online template switching and feature adaptation [C].6th International Conference on Image and Graphics, 2011(1CIG 2011).
[31]Liu, W. Zhou, H. Yin,N. Yu. Tracking based on SURF and superpixel [C].6th International Conference on Image and Graphics,2011.
[32]王春立.面向大词汇量的连续中国手语识别系统的研究与实现[D].大连：大连理工大学,2003.
[33]Liang R H, Ouhyoung M. A sign Language Recognitions System Using Hidden Markov Model and Context Sensitive Search[C] Proc. of the ACM Symposium on Virtual Reality Software and Technology二[5.1,]:[s. n.],1996:59-66.
[34]吴江琴,高文,陈熙霖.基于数据手套的汉语手指字母的识别[J1.模式识别与人工智能, 1999,12(1)：74-78.
[35]付永刚,张凤军,戴国忠.双手交互界面研究进展[J].计算机研究与发展,2005,42(4)：604-13.
[36]Starrner T, Pentland A. Real-time American Sign Language recognition from video using Hidden Markov Models[C]. CoralGables, FL, USA:[s.n.],1995:265-270
[37]Rigoll, G, Kosmala A, Eickeler S. High Performance real-time gesture recognition using hidden markov models [C] [s.1.]:[s. n.],1997:69-80.
[38]Park H, Kim E, Jang s,An HMM-based gesture recognition for perceptual user interface[C] proc. Of the 5th Pacific-Rim Conf. on Multimedia[s.1.]:[s. n.], 2004:1027-1034.
[39]Bobick A, Wilson A.A state-based approach to the representation and recognition of gesture [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,1997,19(12).
[40]Lee H K, Kim J. An HMM-based threshold model approach for gesture recognition [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,1999,21 (10).
[41]任海兵,祝远新,徐光枯,等.连续动态手势的时空表观建模及识别[J].计算机学报,2000,23(8)
[42]王西颖,戴国忠,张习文,等.基于HMM-FNN模型的复杂动态手势识别汇[J].软件学报,2008,19(9)：2302-312.
[43]Bao P. T, Binh N. T, Khoa T. D. A New Approach to Hand Tracking and Gesture Recognition by a New Feature Type and HMM[A]. Sixth International Conference on Fuzzy Systems and Knowledge Discovery[C]. USA:IEEE,2009:3-6
[44]Asaari M. S. M, Suandi S. A. Hand gesture tracking system using Adaptive Kalman Filter[A].10th International Conference on the Intelligent Systems Design and Applications(ISDA) [C]. USA:IEEE,2010:166-171
[45]罗元,李玲,张百胜,等.基于CamShift和Kalman滤波混合的视频手势跟踪算法[J].计算机应用研究,2009,03：1163-1165
[46]Park S, Yu S, Kim J, et al.3D hand tracking using Kalman filter in depth space [J]. EURASIP Journal on Advances in Signal Processing,2012:36-84
[47]张良国,吴江琴,高文,姚鸿勋.基于Hausdorff距离的手势识别.中国图象图形学报A,2002,7(11)：1144-1150.
[48]Jain A K, Ross A, Pankanti S, A prototype hand geometry-based verification system. In:2nd International Conference on Audio- and Video-Based Biometric Person Authentication, Washington D. C. USA,1999,166-171.
[49]邓志国.基于BP神经网络的静态手势识别方法.华东交通大学学报.2005,22(5)：86-88.
[50]江立,阮秋琦.基于神经网络的手势识别技术研究.北京交通大学学报,2006,30(5)：32-36.
[51]Nolker C, Ritter H. Illumination Independent Recognition of Deictic ArmPostures, In:Proceedings of the 24th Annual Conference of Industrial Electronics
[52]Munib Q, Habeeb M, Takruri B, Ai-Malik HA. American sign language (ASL) recognition based on Hough transform and neural networks[J]. Expert Systems with Applications,2007,32:24-37.
[53]T. Horprasert, D. Harwood, L. S. Davis. A statistical approach for real-time robust background subtraction and shadow detection. Proc. of IEEE ICCV' 99 Frame-Rate Workshop,1999.
[54]A. Elgammal, R. Duraiswami, D. Harrwood, L. S. Davis. Background and foreground modeling using nonparametric Kernel density estimation for visual surveillance. Proc. of the IEEE,90(7),1151-1163,2002.
[55]M. Harville, G. Gordon, and J. Woodfill. Foreground segmentation using adaptive mixture models in color and depth. Proc. of IEEE Events Workshop,2001.
[56]C. Stauffer, W. E. L. Grimson. Learning Pattons of Activity Using Real-Time Tracking. IEEE Trans. On PAMI,22(8),2000.
[57]G. Welch, G. Bishop. An introduction to the Kalman filter. UNC-Chapel Hill Technial Report:TR95-041,2000.
[58]K. Karmann, A. Brandt, R. Gerl, Moving object segmentation based on adaptive reference images.Signal Processing, Vol.5,1990, pp951-954.
[59]Guo Jing, Chng Eng Siong and Deepu Rajan. Foreground Motion Detection by Difference-Based Spatial Temporal Entropy Image. IEEE,2004.
[60]Collins R T, Lipton A J.Kanade T.1999. A System for Vedio Sureilliance and Monitoring. Proc.Am[C]. Nuclear Soc. Eighth Int'1 Topical Meeting Robotic and Romote System.
[61]Stringa E,Regazzoni C S.2000. Real-time video-shot detection for scene surveillance applications. IEEE Transactions on Image Processing, vol 9, no.1 pp.69-79.
[62]S. Ribaric, G. Adrinek, S. Segvic. Real-Time Active Visual Tracking System. IEEE Melecon 2004
[63]J. L. Barron, S. S. Beauchemin, D. J. Fleet. On Optical Flow.6th Int. Conf. on Artificial Intelligence and Information-Control Systems of Robots, Bratislava, Slovakia, Sept 12-16, pp3-14,1994.
[64]伏思华,张小虎.2004.基于序列图像的运动目标实时检测方法.光学技术.30(2)：215-217
[65]B. K. P Horn, B. G. Schunch, Detemining Optical Flow, AI 17(1981),185-203.
[66]D. Gutchess, M. Trajkovic, E. Cohen-Solal, D. Lyons, A. K. Jain, A Background Model Initialization Algorithm for Video Surveillance, IEEE 2001
[67]张旭东,高隽,方廷健。基于色彩与高斯混合模型的运动阴影检测[C].第十四届中国神经网络学术会议论文集.合肥.合肥工业大学出版社,2004：578-583
[68]冈萨雷斯等著;阮秋琦,阮宇智等译.数字图像处理(第二版)[M].北京：电子工业出版社,2007.8.
[69]M. Oren, C. Papageorgiou, P. Sinha, et al:Pedestrian Detection Using Wavelet Templates[C]. IEEE Conference on Computer Vision and Pattern Recognition. 1997:193-199.
[70]C. Papageorgiou, T. Poggio:Trainable Pedestrian Detection[C]. International Conference on Image Processing. Kobe, Japan,1999,4:35-39.
[71]C.Papageorgiou, T. Poggio. A Trainable System for Object Detection[J]. International Journal of Computer Vision,2000,38(1):15-33.
[72]A. Mohan, C. Papageorgiou, T. Poggio. Example-based Object Detection in Images by Components [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001,23(4):349-361.
[73]P.Viola, M. J. Jones, D. Snow:Detecting Pedestrians Using Patterns of Motion andAppearance[C]. IEEE International Conference on Computer Vision. Nice, France,2003,2:734-741.
[74]A. Broggi, M. Bertozzi, A. Fascioli, et al:Shape-based Pedestrian Detection [C]. IEEEIntelligent Vehicles Symposium.2000:215-220.
[75]D. M. Gavrila:Pedestrian Detection from a Moving Vehicle[C]. European Conference on Computer Vision. Dublin, Ireland,2000,2:37-49.
[76]P. F. Felzenszwalb:Learning Models for Object Recognition[C]. IEEE International Conference on Computer Vision and Pattern Recognition. Kauai, USA, 2001,1:56-62.
[77]D. M. Gavrila, S. Munder. Multi-cue Pedestrian Detection and Tracking from a Moving Vehicle[J]. International Journal of Computer Vision,2007,73(1).
[78]V. Ferrari, T. Tuytelaars, L. V. Gool:Object Detection by Contour Segment Networks[C]. European Conference on Computer Vision.2006,3:14-28.
[79]Z. Lin, L. S. Davis, D. Doermann, et al:Hierarchical Part-template Matching for Human Detection and Segmentation[C]. IEEE International Conference on Computer Vision.2007.
[80]Z. Lin, L. S. Davis:A Pose-invariant Descriptor for Human Detection and Segmentation[C]. European Conference on Computer Vision.2008:423-436.
[81]B. Wu. Part Based Object Detection, Segmentation and Tracking by Boosting Simple Shape Feature Based Weak Classifiers[D]. University of Southern California,2008.
[82]D. G. Lowe:Object Recognition from Local Scale-invariant Features[C]. IEEE International Conference on Computer Vision.1999:1150-1157.
[83]B. Leibe, E. Seemann, B. Schiele:Pedestrian Detection in Crowded Scenes[C]. IEEE Conference on Computer Vision and Pattern Recognition.2005,1:878-885.
[84]N. Dalal, B. Triggs:Histograms of Oriented Gradients for Human Detection[C]. C. Schmid, S. Soatto, C. Tomasi. International Conference on Computer Vision and Pattern Recognition.2005,2:886-893.
[85]Q. Zhu, S. Avidan, M. C. Yeh, et al:Fast Human Detection Using a Cascade of Histograms of Oriented Gradients[C]. IEEE Conference on Computer Vision and Pattern Recognition.2006:1491-1498.
[86]P. Felzenszwalb, D. McAllester, D. Ramanan:A Discriminatively Trained, Multi-scale, Deformable Part Model[C]. IEEE Conference on Computer Vision and Pattern Recognition.2008.
[87]I. P. Alonso, D. F. Llorca, M. A. Sotelo, et al. Combination of Feature Extraction Methods for Svm Pedestrian Detection[J]. IEEE Transactions on Intelligent Transportation Systems,2007,8(2):292-307.
[88]L. Nanni, A. Lumini. Ensemble of Multiple Pedestrian Representations [J]. IEEE Transactions on Intelligent Transportation Systems,2008,9(2):365-369.
[89]C. Wojek, S. Walk, B. Schiele:Multi-cue Onboard Pedestrian Detection[C]. IEEE Conference on Computer Vision and Pattern Recognition.2009.
[90]S. Ju, M. Black, Y. Yacoob. Cardboard people:A Parameterized Model of Articulated Image Motion. Intemational conference on Face and Gesture Analysis, 1996
[91]C. R.Wren, A. Azarbaye jani, T. Darrell, A. P. Pentland. Pfinder:real-time tracking of the human body. Transactions on Pattern Analysis and Machine Intelligence, 19(7), July 1997.
[92]Polana R, Nelson R. Low Level Recognition of Human Motion. Proc IEEE Workshop on Motionof Non-Rigid and Articulated Objects,1994,77-82.
[93]J. Segen and S. Pingali. A Camera-based System for Tracking People in Real Time. InternationalConference on Pattern Recognition, pages 63-67, Vienna, Austria, August 1996.
[94]郑红。基于自适应背景更新和色彩特征的运动人体检测与跟踪[D]。上海：上海交通大学计算机科学与工程系,2009
[95]Bertalmio M, Sapiroo G,Randll G.Morphing active contours. IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(7):733-737
[96]Paragios N, Deriche R. Geodesicractive contours and levelsets for the detection and-Tracking of moving objects. IEEE Trans Pattern-Analysis and Machine Intelligence,2000,22(3):266-280
[97]Peterfreund N. Robust tracking of Position and velocity with kalman snakes. IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(6):564-569
[98]Fukanaga K, Hostetler L. D. The estimation of the gradient of a density function, with applications in Pattern recognition[J]. IEEE Trans Information Theory,1975, 21(1):32-40.
[99]吴喜之.非参数统计[M].北京：中国统计出版社,1999.
[100]王星.非参数统计[M].北京：中国人民大学出版社,2005.
[101]朱胜利.Meanshift及相关算法在视频跟踪中的研究[Dl.博士学位论文,浙江大学,2006
[102]Comaniciu D, Meer P. Mean Shift Analysis and Application[A]. In:Proeofthe7th IEEE International Conference on Computer Vision[C].Kerkyra, Greece:IEEE Computer
[103]Comaniciu D, Ramesh V.. Kernel-based object tracking [J] IEEE International Transactions on Pattern Analysis and Machine Intelligenee,2003,25(5):564 - 575
[104]Isard M and Blake A. Contour Tracking by Stochastic Propagation of Conditional Density. In:Proc European Conference on Computer Vision, Cambridge,1996.343～356.
[105]陈远祥.视频图像运动目标跟踪技术的研究[D].江苏：江苏大学,2010
[106]方颖,王汇源等.适用于多目标之间遮挡问题的跟踪算法.计算机应用,2007,vol(27)：62-65
[107]Tsai R Y. A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses[J]. IEEE Journal of Robotics and Automation,1987,3(4):323-344.
[108]Weng J, Cohen P, Herniou M. Camera calibration with distortion models and accuracy evaluation [J].IEEE Trans, on PAMI,1992,14(10):965-980.
[109]Zhang Z. A flexible new technique for camera calibration [J]. IEEE Trans. On Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334.
[110]Michael A. Penna. Camera Calibration:A Quick and Easy Way to Determine the Scale actor. IEEE Tpansactions on Pattern Analysis and Machine Intelligence[J].1991,13(12):1240-1245.
[111]R. K. Lenz and R. Y. Tsai. Techinques for calibration of the scale factor and image center for high accuracy 3-D machine metrology[J]. IEEE rans. Patt. Anal. MachineIntell.1988,10(5):713-720.
[112]Donald Hearn, M. Pauline BakerComputer Graphics with OpenGL Third Edition[M]. London:Prentice Hall,2003:438～455.
[113]郭星,刘政怡,李炜,吴建国.基于双目视觉的大屏幕人机交互方式[J].计算机工程与应用,2012,48(1)：176-179.
[114]Lee J, Kunii T L. Model-based analysis of hand posture. IEEE Computer Graphic and Applications,1995,15(5):77-86.
[115]B. D. Zarit, B. J. Super. Comparison of five color models in skin pixel classification[J]. In:Proceedings of the International Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-time Systems, Corfu, Greece, 1999,58-63.
[116]S. Jayaram, S. Schmugge. Effect of color space transformation, the illuminance component and color modeling on skin detection[J]. In:Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR'04), Washington, DC. USA,2004,813-818.
[117]J. C. Tenilion, M. N. Shirazi, H. Fukamachi. Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images [J]. In:Proc Conference of Automatic Face and Gesture Recognition, Grenoble, France,2003:54-61.
[118]夏振宇.人体皮肤分割技术的研究和应用[D].长沙：中南大学硕士学位论文,2009.
[119]周星,高志军.立体视觉技术的应用与发展[J].工程图学学报,2010,31(4)：50-55
[120]Dancter, Rich-tie, Khazar, et al. Time-of- flight camera. http://en. wikipedia. org/wiki/-Time-of- flight_camera.15, March,2012
[121]Loren Schwarz N N. Depth Imaging with Time-of-Flight Cameras and the Kinect[J]. 3D Computer Vision II Winter Term 2011,2012
[122]Stowers J, Hayes M, Bainbridge-Smith A. Altitude control of a quad rotor helicopter using depth map from Microsoft Kinect sensor. IEEE International Conference on Mechatronics (ICM)[C]. USA:IEEE,2011:358-362
[123]Hu M K. Visual Pattern Recognition by Moment Invariant. IRE Trans Information Theory,1962, (8):179-187.
[124]刘寅,滕晓龙,刘重庆.复杂背景下基于傅里叶描述子的手势识别[J].计算机仿真,2005,22(12)：158-161.
[125]王涛,刘文印,孙家广,张宏江.傅立叶描述子识别物体的形状[J].计算机研究与发展,2002,39(12).
[126]Lowe D G. Distinctive image features from scale-invariantkeypoints[J]. International Journal of Computer Vision,2004,60(2):91-110.
[l27]Cipolla R, Holling Hurst N J. Human robot interface by pointing with uncelebrated stereovision[J].Image and Vision Computing,1993(14):171-178.
[128]Hyeon Kyu Lee, J IN H KIM. An HMM-based threshold model approach for gesture recognition [J]. IEEE, Pattern nalysis and Machine Intelligence,1999,21 (10):961-973.
[129]陶霖密,彭振云,徐光祐.人体的肤色特征.软件学报,2001,12(7)：1032-1040.
[130]Arulampalam S., Maskell S., Gordon N., and Clapp T., A Tutorial on Particle Filters foronline Non-linear/Non-Gaussian Bayesian Tracking, IEEE Transactions on Signal Processing,2002,50 (2):174-188.
[131]K. Ishibuchi, H. Takemutra, and F. Kishino. Real Time Hand Gesture Recognition using 3D Prediction Model. International Conference on Systems,1993,5 (17):324-328.
[132]刘志明,基于动态手势识别的人机交互技术研究[D].2007,浙江大学.
[133]LiuJ. S. and ChenR. Sequential Monte Carlo Methods for Dynamical Systems, Journal of the American Statistieal Assoeiation,1998,93(5):1032 - 1044.
[134]GordonN. J. SalmondD. J., and SmithA.F. M., Novel Approach to Nonlinear Non-Gaussian Bayesian State Estimation, In IEEE Proceedings on Radar and SignalProcessing,1993,140(2):107-113.
[135]Kitagawa G. Monie Carlo Filter and Smoother for Non-Gaussian Nonlinear State Space Models, Journal of Computational and Graphical Statisties,1996,5(1):1-25.
[136]Higuchi T., Monte Carlo Filtering Using Genetics Algorithm Operator. Journal of Statistical Computation and Simulation,1997,59(1):1-23.
[137]MoY. W. and Xiao D. Y. Hybrid System Monitoring and Diagnosing Based on Particle Filter Algorithm, Acta Automation Siniea,2003,29(3):641-648.
[138]胡昭华.基于粒子滤波的视频目标跟踪技术研究.南京：南京理工大学.2008
[139]Kahol K, Tripathi P, et al. Gesture segmentation in complex motion sequences [C]. Proc. IEEE Int'l Conf.on Image Processing(ICIP' 03),2003,11:105-108.
[140]Lee H, Kim J. An HMM-based threshold model approach for gesture recognition[J].IEEE Trans. Pattern Anal. Machine Intell.,1999,21 (10):961-973.
[141]Mori T. Visual motion perception[J],Circulars of the Electro technical Laboratory,1982,207 (10):1-78.
[142]Kahol K, Tripathi P, et al. Gesture segmentation in complex motion sequences[C]. Proc. IEEE Int'l Conf.on Image Processing(ICIP' 03),2003,11:105-108.
[143]Sakoe H. Two level DP matching-A dynamic programming base pattern matching algorithm for connected word recognition[J]. IEEE Trans on A SSP,1979, ASSP-27 (6):588-595
[144]Sakoe, H. and Chiba, S. Dynamic programming algorithm optimization for spoken word recognition [J]. IEEE Transactions on Acoustics, Speech and Signal Processing, 26(1) pp.43-49,1978, ISSN:0096-3518
[145]Sminchisescu, C., A. Kanaujia, and D. Metaxas, Conditional models for contextual human motion recognition. Computer Vision and Image Understanding, 2006.104(2-3):p.210-220.
[146]Murphy, K.. Dynamic Bayesian networks:representation, inference and learning. 2002, Citeseer.
[147]Yamato, J., J. Ohya, and K. Ishii. Recognizing human action in time-sequential images using hidden Markov model.1992.
[148]Brand, M.,N.Oliver, and A. Pentland. Coupled hidden Markov models for complex action recognition.1997:INSTITUTE OF ELECTRICAL ENGINEERS INC (IEEE).
[149]Kristjansson, T., B. Frey, and T. Huang. Event-coupled hidden Markov models.2000:Citeseer.
[150]Fine, S., Y. Singer, and N. Tishby, The hierarchical hidden Markov model:Analysis and applications.Machine learning,1998.32(1):p.41-62.
[151]马振华,等.现代应用数学手册,概率统计与随机过程卷.北京：清华大学出社,2000.440-457
[152]刘克编.《实用马尔可夫决策过程》.清华大学出版社.2004.11.1
[153]A. B. Poritz. Hidden Markov Modelsr:a guided tour. Proc. of IEEE Intl. Conf. on Acoustic Speech and Signal Processing.1988, PP.7-13
[154 L. R. Rabiner. Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition, in Proc. IEEE, vol.77, pp.257-285