序列图像中手势跟踪与识别技术的研究
|
摘要
基于动态序列图像的生物特征识别已成为近年来计算机视觉领域中备受关注的研究内容,它主要从图像序列中检测、识别、跟踪人及对其生物特征理解和描述加以研究。人的生物特征识别在虚拟现实、人机交互、视觉监控等领域均有着广阔的应用,基于视觉的手势跟踪与识别研究就是其重要内容。由于手势具有多样性、多义性、手的复杂变形性、视觉本身的不适定性以及手势在时间和空间上的差异性等特点,因此基于视觉的的手势跟踪与识别是一个多学科交叉的富有挑战性的研究课题。
一个完整的基于视觉的图像序列中手势跟踪与识别系统,通常包含下面三个部分:手的检测、分割,手势跟踪与手势识别。
手势分割就是将有意义的区域(手)从手势图像中划分出来,是基于视觉的手势识别过程中的最为关键的一步,手势分割的好坏直接影响后续的手势跟踪、手势特征提取及手势识别结果。对图像序列中包含的手势进行跟踪(二维跟踪),即对投影到图像平面的手进行定位和跟踪,是手势识别的关键。手势识别则是把模型参数空间中的轨迹(或点)分类到该空间中某个子集的过程。
本文主要研究了用于人机交互的手势跟踪与识别,分别对目标分割算法,手势跟踪算法与识别算法进行深入研究。主要工作总结如下:
1.首先提出了一种基于肤色信息的自适应轮廓模型和一种自适应形状模型,实现了具有凸形与凹形两种边界轮廓的准确提取。
这种自适应活动轮廓模型是一种改进的Snake模型,它使轮廓线能够自适应地收缩或膨胀,降低了对初始轮廓的敏感性,在视觉跟踪中不需在当前帧中重新初始化,只需进行目标定位,较好地解决了Snake模型及Snake跳跃模型的不足,保证了对目标轮廓的准确提取。鉴于这种自适应轮廓模型对于具有凹形边界的轮廓不能实现准确提取,本文又提出一种自适应形状模型,并运用拆分和聚合技术对该形状模型表示的‘中间轮廓’进行修正,实现具有凸形与凹形两类边界轮廓的准确提取。
2.提出了一种基于各向异性核函数的均值漂移跟踪算法,实现图像序列中区域跟踪的稳健性、有效性和实时性。并且,融合均值漂移算法与自适应轮廓模型实现了图像序列中的手部轮廓跟踪。
该算法提出了一种形状、大小、方向能自适应于目标局部结构的变化的各向异性核函数,将其应用于均值漂移算法实现目标跟踪,保证了跟踪效果的稳定性和鲁棒性。而均值漂移与自适应轮廓模型的融合算法,能够根据跟踪区域模板与目标模板的相似性度量Bhattacaryya系数给出在跟踪目标被遮挡时的处理方法,有效地解决了目标跟踪的这一难题。
3.基于上述区域跟踪结果,利用手轮廓的方向直方图实现用于人机交互的静态手势识别;基于上述轮廓跟踪结果,利用隐马尔可夫模型实现用于人机交互的动态手势识别。
方向直方图满足手势识别中对光照变化的不敏感性和手势平移、旋转不变性等要求,并且可有效的表示手势特征。基于区域跟踪结果,利用手轮廓的方向直方图本文实现了用于人机交互的静态手势识别;基于轮廓跟踪结果,同时应用手形及手部运动两大特征作为隐马尔可夫模型的输入实现了动态手势识别,提高了手势识别率,也达到了实时性的效果,且不必依赖数据手套等设备。
4.提出一种新的基于范例集的跟踪器(CEE(CAMSHIFT Embedded Exemplar))跟踪器,在图像序列中同时实现手势跟踪与识别。
为克服基于范例集的手势跟踪不能实现复杂场景下手部轮廓特征的精确提取及手部动作的不准确预测,本文提出一种新的基于范例集的跟踪器(CEE跟踪器),充分利用跟踪目标的运动信息与颜色信息实现复杂场景下手势的准确跟踪,而且能够同时实现手势识别。
As a frontier orientation, biological feature recognition based on the dynamic image sequence has received much attention in the field of computer vision in recent years. It detects, recognizes and tracks the human from the image sequence. It also understands and describes the biological feature of human from the image sequence. The biological feature recognition of human can be applied widely to various areas like virtual reality, human-computer interaction and visual surveillance etc. Vision-based recognition of hand gestures is an extremely challenging interdisciplinary project due to the following three reasons: (1) hand gestures are rich in diversities, meanings, and space-time varieties; (2) human hands are complex non-rigid objects; (3) computer vision itself is an ill-posed problem.
Special gesture set is usually defined according to the application before the system of hand tracking and gesture recognition is implemented. A full system of hand tracking and gesture recognition is composed of three parts: (1) detection and segmentation of hand; (2) hand tracking; (3) gesture recognition.
Hand segmentation is to partition off the significant area (hand) from the sequence. It is the most critical step of the system in that its quality influences the results of hand tracking, hand feature extraction and gesture recognition. Tracking the hand in the image sequence, i.e. tracking in the two-dimension space, is to locate and track the hand which is projected to the image plane. It is the prerequisite to gesture recognition. Gesture recognition is to classify the tracks or the dots of modal reference space into a certain subset.
The goal of this thesisis to study of hand tracking and gesture recognition for the human-computer interaction, and to focus on object segmentation algorithms, hand tracking algorithms and gesture recognition algorithms. Contributions of this thesis are summarized as follows:
(1) A self-adaptive contour modal based on skin information is proposed. Because the concave contour can not be extracted accurately by this modal, a self-adaptive shape modal is also proposed to implement extraction of both convex and concave contours.
This self-adaptive contour modal is an improved snake modal, which makes the contour lines lengthen or shorten adaptively and decreases the sensitivity to the initial contour. Thus in vision tracking the re-initialization of the contour is not necessary in the current frame. This overcomes the shortcomings of snake modal and snake’s jump modal and ensures the precise extracting of the object contour. Because the concave contour can not be extracted accurately by this modal, a self-adaptive shape modal is also proposed. And the semi-contour obtained by this self-adaptive shape modal is revised, which can help to implement extraction of the convex and concave contours.
(2) An anisotropic kernel mean shift tracker is proposed, which ensures the steady, valid, real-time region tracking.
The algorithm proposes an anisotropic kernel, in which the shape, scale, and orientation of the kernels can be adapted to the changing object structure. The kernel is applied to mean shift algorithm to implement the object tracking, which ensures the steadiness and robustness of tracking. Based on the similarity measure of candidate modal and object modal, i.e. Bhattacaryya coefficient, the joint effects of mean shift algorithm and the adaptive contour modal can help to solve the difficulty in object tracking while the object is occluded.
(3) On the basis of the above results in region tracking, static gesture recognition for human-computer interaction is implemented by using the orientation histograms of the hand contour. And on the basis of the above results in contour tracking results, dynamic gesture recognition for human-computer interaction is implemented by using HMM modal.
The orientation histogram is the feature vector to represent hand gesture, which is robust to lighting changes and satisfies translational invariance and can be calculated quickly. Based on the region tracking results, static gesture recognition for human-computer interaction is implemented interface with the orientation histograms. Based on the contour tracking results, dynamic gesture recognition for human-computer interaction is implemented by taking both hand shapes and hand motion as the input into HMM modal.
(4) A new exemplar-based tracker, i.e. CEE(CAMSHIFT Embedded Exemplar) tracker, is proposed to implement hand tracking and gesture recognition simultaneously in the image sequence.
Traditional Exemplar-based tracker is unable to acquire the accurate extraction of hand silhouette and the accurate predication of the hand motion in complex background. Thus this thesis proposes a new exemplar-based tracker, i.e. CEE(CAMSHIFT Embedded Exemplar) tracker, which makes the best of motion information and color information of the object to implement precise tracking of hand and to aquire simultaneous gesture recognition in complex background.
一个完整的基于视觉的图像序列中手势跟踪与识别系统,通常包含下面三个部分:手的检测、分割,手势跟踪与手势识别。
手势分割就是将有意义的区域(手)从手势图像中划分出来,是基于视觉的手势识别过程中的最为关键的一步,手势分割的好坏直接影响后续的手势跟踪、手势特征提取及手势识别结果。对图像序列中包含的手势进行跟踪(二维跟踪),即对投影到图像平面的手进行定位和跟踪,是手势识别的关键。手势识别则是把模型参数空间中的轨迹(或点)分类到该空间中某个子集的过程。
本文主要研究了用于人机交互的手势跟踪与识别,分别对目标分割算法,手势跟踪算法与识别算法进行深入研究。主要工作总结如下:
1.首先提出了一种基于肤色信息的自适应轮廓模型和一种自适应形状模型,实现了具有凸形与凹形两种边界轮廓的准确提取。
这种自适应活动轮廓模型是一种改进的Snake模型,它使轮廓线能够自适应地收缩或膨胀,降低了对初始轮廓的敏感性,在视觉跟踪中不需在当前帧中重新初始化,只需进行目标定位,较好地解决了Snake模型及Snake跳跃模型的不足,保证了对目标轮廓的准确提取。鉴于这种自适应轮廓模型对于具有凹形边界的轮廓不能实现准确提取,本文又提出一种自适应形状模型,并运用拆分和聚合技术对该形状模型表示的‘中间轮廓’进行修正,实现具有凸形与凹形两类边界轮廓的准确提取。
2.提出了一种基于各向异性核函数的均值漂移跟踪算法,实现图像序列中区域跟踪的稳健性、有效性和实时性。并且,融合均值漂移算法与自适应轮廓模型实现了图像序列中的手部轮廓跟踪。
该算法提出了一种形状、大小、方向能自适应于目标局部结构的变化的各向异性核函数,将其应用于均值漂移算法实现目标跟踪,保证了跟踪效果的稳定性和鲁棒性。而均值漂移与自适应轮廓模型的融合算法,能够根据跟踪区域模板与目标模板的相似性度量Bhattacaryya系数给出在跟踪目标被遮挡时的处理方法,有效地解决了目标跟踪的这一难题。
3.基于上述区域跟踪结果,利用手轮廓的方向直方图实现用于人机交互的静态手势识别;基于上述轮廓跟踪结果,利用隐马尔可夫模型实现用于人机交互的动态手势识别。
方向直方图满足手势识别中对光照变化的不敏感性和手势平移、旋转不变性等要求,并且可有效的表示手势特征。基于区域跟踪结果,利用手轮廓的方向直方图本文实现了用于人机交互的静态手势识别;基于轮廓跟踪结果,同时应用手形及手部运动两大特征作为隐马尔可夫模型的输入实现了动态手势识别,提高了手势识别率,也达到了实时性的效果,且不必依赖数据手套等设备。
4.提出一种新的基于范例集的跟踪器(CEE(CAMSHIFT Embedded Exemplar))跟踪器,在图像序列中同时实现手势跟踪与识别。
为克服基于范例集的手势跟踪不能实现复杂场景下手部轮廓特征的精确提取及手部动作的不准确预测,本文提出一种新的基于范例集的跟踪器(CEE跟踪器),充分利用跟踪目标的运动信息与颜色信息实现复杂场景下手势的准确跟踪,而且能够同时实现手势识别。
As a frontier orientation, biological feature recognition based on the dynamic image sequence has received much attention in the field of computer vision in recent years. It detects, recognizes and tracks the human from the image sequence. It also understands and describes the biological feature of human from the image sequence. The biological feature recognition of human can be applied widely to various areas like virtual reality, human-computer interaction and visual surveillance etc. Vision-based recognition of hand gestures is an extremely challenging interdisciplinary project due to the following three reasons: (1) hand gestures are rich in diversities, meanings, and space-time varieties; (2) human hands are complex non-rigid objects; (3) computer vision itself is an ill-posed problem.
Special gesture set is usually defined according to the application before the system of hand tracking and gesture recognition is implemented. A full system of hand tracking and gesture recognition is composed of three parts: (1) detection and segmentation of hand; (2) hand tracking; (3) gesture recognition.
Hand segmentation is to partition off the significant area (hand) from the sequence. It is the most critical step of the system in that its quality influences the results of hand tracking, hand feature extraction and gesture recognition. Tracking the hand in the image sequence, i.e. tracking in the two-dimension space, is to locate and track the hand which is projected to the image plane. It is the prerequisite to gesture recognition. Gesture recognition is to classify the tracks or the dots of modal reference space into a certain subset.
The goal of this thesisis to study of hand tracking and gesture recognition for the human-computer interaction, and to focus on object segmentation algorithms, hand tracking algorithms and gesture recognition algorithms. Contributions of this thesis are summarized as follows:
(1) A self-adaptive contour modal based on skin information is proposed. Because the concave contour can not be extracted accurately by this modal, a self-adaptive shape modal is also proposed to implement extraction of both convex and concave contours.
This self-adaptive contour modal is an improved snake modal, which makes the contour lines lengthen or shorten adaptively and decreases the sensitivity to the initial contour. Thus in vision tracking the re-initialization of the contour is not necessary in the current frame. This overcomes the shortcomings of snake modal and snake’s jump modal and ensures the precise extracting of the object contour. Because the concave contour can not be extracted accurately by this modal, a self-adaptive shape modal is also proposed. And the semi-contour obtained by this self-adaptive shape modal is revised, which can help to implement extraction of the convex and concave contours.
(2) An anisotropic kernel mean shift tracker is proposed, which ensures the steady, valid, real-time region tracking.
The algorithm proposes an anisotropic kernel, in which the shape, scale, and orientation of the kernels can be adapted to the changing object structure. The kernel is applied to mean shift algorithm to implement the object tracking, which ensures the steadiness and robustness of tracking. Based on the similarity measure of candidate modal and object modal, i.e. Bhattacaryya coefficient, the joint effects of mean shift algorithm and the adaptive contour modal can help to solve the difficulty in object tracking while the object is occluded.
(3) On the basis of the above results in region tracking, static gesture recognition for human-computer interaction is implemented by using the orientation histograms of the hand contour. And on the basis of the above results in contour tracking results, dynamic gesture recognition for human-computer interaction is implemented by using HMM modal.
The orientation histogram is the feature vector to represent hand gesture, which is robust to lighting changes and satisfies translational invariance and can be calculated quickly. Based on the region tracking results, static gesture recognition for human-computer interaction is implemented interface with the orientation histograms. Based on the contour tracking results, dynamic gesture recognition for human-computer interaction is implemented by taking both hand shapes and hand motion as the input into HMM modal.
(4) A new exemplar-based tracker, i.e. CEE(CAMSHIFT Embedded Exemplar) tracker, is proposed to implement hand tracking and gesture recognition simultaneously in the image sequence.
Traditional Exemplar-based tracker is unable to acquire the accurate extraction of hand silhouette and the accurate predication of the hand motion in complex background. Thus this thesis proposes a new exemplar-based tracker, i.e. CEE(CAMSHIFT Embedded Exemplar) tracker, which makes the best of motion information and color information of the object to implement precise tracking of hand and to aquire simultaneous gesture recognition in complex background.
引文
[1] Wren C, Azarbayejani A, Darrel T, Pentland A. Pfinder: Real-time 3-d tracking of the human body [J]. IEEE Transactions PAMI, 1997, 19(7): 780-785.
[2] Schlegel C, Illmann J, Jaberg H, et al. Vision based person tracking with a mobile robot [C]. British Machine Vision Conference, Southampton, UK, 1998: 418-427.
[3] Pavlovic V, Sharma R, Huang T S. Visual interpretation of hand gesture for human-computer interaction: A Rreview [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1997, 19 (7): 677-695.
[4]任海兵,祝远新,徐光佑.基于视觉手势识别的研究---综述[J].电子学报,2000,Vol. 28 No. 2.
[5]魏育成.智能服务型机器人的视觉感知接口与导航[D].北京:中国科学院自动化研究所, 2004.
[6] Isard M, Blake A. ICONDENSATION: Unifyinglow-level tracking in a stochastic framework [C]. Proc. European Conf. On Computer Vision (ECCV'98), 1998: 893-908.
[7] Isard M, Blake A. A mixed-state condensation tracker with automatic model-switching [C]. Proc 6th Int. Conf. Computer Vision (ICCV'98), 1998: 107-112.
[8] Isard M, Blake A. CONDENSATION: conditional density propagation for visual tracking [J]. International of Computer Vision, 1998, 29 (1): 5-28.
[9] McAllister G, McKenna S J, Ricketts I W. Hand tracking for behaviour understanding [J], Image and Vision Computing, 2002, 20(12): 827-840.
[10] Blake A, Isard M. Active contours [M]. Springer-Verlag, 1998.
[11] Wah Ng C, Ranganath S. Real-time gesture recognition system and application [J]. Image and Vision Computing, 2002, 20(13): 993-1007.
[12] Oka K, Sato Y, Koike H. Real-time tracking of multiple fingertips and gesturerecognition for augmented desk interface systems [C]. IEEE Int. Conf. on Automated Face and Gesture Recognition (FG'02), 2002: 411-416.
[13] Mammen J, Chaudhuri S, Agrawal T. Simultaneous tracking of both hands by estimation of erroneous observations [C]. Proc of BMVC’, 2001: 83-92.
[14] Laptev I, Lindeberg T. Tracking of multi-state hand models using particle filtering and a hierarchy of multi-scale image features [C]. Proc. IEEE Workshop on Scale-Space and Morphology, 2001: 63-74.
[15] Triesch J, Malsburg C V. A system for person-independent hand posture recognition against complex backgrounds [J]. IEEE Trans. Pattern Anal. Machine Intell. 2001, 23(12): 1449-1453.
[16] Terrillon J, Akamatsu S. Comparative performance of diferent skin chrominance models and chrominance spaces for the automatic detection of human faces in color images [C]. Proc. IEEE Int. Conf. on Automated Face and Gesture Recognition (FG'00), 2000: 54-61.
[17] Jones M, Rehg J M. Statistical color models with application to skin detection [J]. Int'1 Journal of Computer Vision, 2002, 46(1): 81-96.
[18] Wu Y. Vision and learning for intelligent human-computer interaction [D]. U S: University of Illinois at Urbanar Champaign, 2001.
[19] Wu Y, Liu Q, Huang T. An adaptive self organizing color segmentation algorithm with application to robust real-time human hand localization [C]. Proc. Asian Conference on Computer Vision (ACCV'00), 2000: 1106-1111.
[20] Raja Y, McKenna S, Gong S. Colour model selection and adaptation in dynamic scenes [C]. Proc. European Conf. on Computer Vision (ECCV'98), 1998:460-474.
[21] Tsap L. Gesture-tracking in real time with dynamic regional range computation [J]. Real Time Imaging, 2002, 8(2): 115-126.
[22] Shan C, Wei Y, et al. Real time hand tracking by combining particle filtering and mean shift [C]. Proc. IEEE Int'1 Conf. on Automated Face and Gesture Recognition (FG'04), 2004: 669-674.
[23] Wu Y, Huang T. Vision-based gesture recognition: A review [A]. Lecture Notes in Artificial Intelligence 1739, Gesture-Based Communication in Human-Computer Interaction (Int'l Gesture Workshop, GW99), 1999: 103-115.
[24] Freeman W, Roth M. Orientation histograms for hand gesture recognition [C]. Proc. IEEE Int'1 Conf. on Automated Face and Gesture recognition (FG'95), 1995: 296-301.
[25] Yang M, Ahuja N, Tabb M. Extraction of 2d motion trajectories and its application to hand gesture recognition [J]. IEEE Trans. Pattern Anal.Machine Intell., 2002, 24(8):1061-1074.
[26] Fei H, Reid I. Probabilistic tracking and recognition of non-rigid hand motion [C]. Proc. IEEE Int'1 Workshop on Analysis and Modeling of Faces and Gestures (AMFG'03), 2003: 60-67.
[27] Starner T, W eaver J, Pentland A. Realtime American sign language recognition using desk and wearable computerbased video [J]. IEEE Transations on P attern A naly sis and M ach ine Intellig ence, 1998, 20 (12): 1371-1375.
[28] Lee H K, Kim J H. An HMM-based threshold model approach for gesture recognition [J]. IEEET ransationson Pattern Analysis and Machine Intelligence, 1999, 21(10): 961-973.
[29]李清水,方志刚等.手势识别技术及其在人机交互中的应用[J].人类工效学, 2002, 8(1): 27-33.
[30] Kass M, Witkin A P, Terzopoulos D. Snakes: active contour models [J]. International Journal of Computer Vision, 1987, l (4): 321- 331.
[31]杜威,李华.基于单目视觉的手势识别系统[J].工程图学学报, 2000, 3: 133-138.
[32]丁海洋,阮秋琦.多尺度模型与矩描绘子相结合的手势识别算法[J].北京交通大学学报, 2004, 28(2): 41-45.
[33] Chai D, Ngan K. Automatic Face Location for Videophone Images [A]. IEEE TENCON Digital Signal Processing Applications Proceedings, 1996: 137-140.
[34] Habili N, Lim C C. Hand and face segmentation using motion and color cues in digital image sequences [A]. Proceedings of IEEE International Conference on Multimedia & Expo2001, 2001: 261 - 264.
[35] Du W, Li H. Vision based gesture recognition system with single camera [A]. 2000 5th International Conference on Signal Processing Proceedings, 2000:1351- 1357.
[36] Lew Y P, Ramli A R, Koay S Y, et al. A Hand segmentation scheme using clustering technique in homegeneous background [C]. Student Conference on Research and Development Proceedings, 2002:305- 308.
[37] Chaparro A, et al. Colour is what the eye sees best [J]. Nature, 1993, 361(6410): 349- 350.
[38] Yang J, Lu W, Waibel. A. Skin- Color Modeling and Adaptation [A]. Proc. ACCV, Hong Kong, 1998: 687-694.
[39] Bradski G. Computer vision face tracking for use in a perceptual user interface [J]. Intelligence Technology Journal, 1998, 2: 1-15.
[40] D. Comaniciu, V. Ramesh, and P. Meer. Real-time tracking of non-rigid objects using mean shift [C]. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'00), 2000: 142-149.
[41] Perez P, Hue C, Vermaak J, and Gangnet M. Color-based probabilistic tracking [C]. Proc. European Conf. on Computer Vision (ECCV'02), 2002, 1: 661-675.
[42] Nummiaro K, Koller-Meier E, Van Gool L. An adaptive color-based particle filter [J]. Image and Vision Computing, 2003, 21(1): 99-110.
[43] Shamaie A, Sutherland A. A dynamic model for real-time tracking of hands in bimanual movements [C]. Gesture-Based Communication in Human-Computer Interaction (Int'l Gesture Workshop, GW03), 2003:172-179.
[44] Bretzner L, Laptev I, Lindeberg T. Hand gesture recognition using multi-scale colour features, hierarchical models and particle filtering [C]. Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition,2002: 423-428.
[45] Zhou H, Huang T. Tracking articulated hand motion with eigen dynamics analysis [C]. Proceedings Ninth IEEE International Conference on Computer Vision, 2003:1102-1109.
[46] Hong P, Turk M, Huang T. Gesture modeling and recognition using finite state machines [C]. Proc. IEEE Int'l Conf. on Automated Face and Gesture Recognition (FG'00), 2000: 410-415
[47] Pavlovic V. Dynamic bayesian networks for information fusion with applications to human-computer interfaces [D]. America: University of Illinois at UrbanarChampaign, 1999.
[48] Wu Y. Vision and learning for intelligent human-computer interaction [D]. Americal: University of Illinois at UrbanarChampaign, 2001.
[49] Wu Y, Huang T S. View-independent recognition of hand posture [C]. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'00), 2000:88-94.
[50] Lockton R. Fitzqibbon A W. Real-time gesture recognition using deterministic boosting [C]. Proc. British Machine Vision Conference (BMVC'02), 2002: 817-826.
[51] Deng J, Tsui H. A PCA/MDA scheme for hand posture recognition [C]. Proc. IEEE Int'l Conf. on Automated Face and Gesture Recognition (FG'02), 2002: 279-284.
[52] Triesch J, vonder Malsburg C. A gesture interface for human-robotinteraction [C]. Proc. IEEE Int'1 Conf. on Automated Face and Gesture Recognition (FG'98), 1998: 546-551.
[53] Freeman W, Anderson D, et al. Computer vision for interactive computer graphics [J]. IEEE Comput. Graph Appl., 1998, 18(3): 42-53.
[54] Liu N, Lovell B. Gesture classification using hidden markov models and viterbi path counting [C]. Proc. Int'1 Conf. on Digital Image Computing: Techniques and Applications (DICTA'03), 2003: 273-28.
[55] Cui Y, Swets D, Weng J. Learning-based Hand Sign Recognition using SHOSLIF-M [C]. Proceedings of 5" International Conference on Computer Vision, 1995: 631-636.
[56] Triesch J, Vonder Malsburg C. A System for Person-independent Hand Posture Recognition against Complex Backgrounds [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2001, 23(12):1449-1453.
[57] Nolker C, Ritter H. Illumination Independent Recognition of Deietiec ArmPostures [C]. Proc. 24th Annual Conference of the IEEE Industrial Electronics Society, 1998: 2006-2011.
[58] Mori T. Visual motion perception [J], Circulars of the Electrotechnical Laboratory, 1982, 207(10):1-78.
[59] 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.
[60] Kahol K, Tripathi P, et al. Gesture segmentation in complex motion sequences [C]. Proc. IEEE Int'l Conf. on Image Processing (ICIP'03), 2003, II: 105-108.
[61] McKenna S, Gong S. Gesture recognition for visualy mediated interaction using probabilistic event trajectories [C]. Proc. British Machine Vision Conference (BMVC'98), 1998: 498–507.
[62] Gong S, Walter M, Psarrou A. Recognition of temporal structures: Learning prior and propagating observation augmented densities via hidden markov states [C]. Proc. IEEE Int'l Conf. on Computer Vision (ICCV'99), 1999:157-162.
[63] Psarrou A, Gong S, Walter M. Recognition of human gestures and behaviour based on motion trajectories [J]. Image and Vision Computing, 2002, 20(5): 349-358.
[64] Isard M, Blake A. Visual tracking by stochastic propagation of conditional density [C]. Proc. European Conf. on Computer Vision (ECCV'96), 1996: 343-356.
[65] Eoler-Meier E B, Gool L V. Modeling and recognition of human actions using astochastic approach [C], Proc. 2nd European Workshop on Advanced Video-based Surveilance Systems, 2001:17-28.
[66] Black M J, Jepson A D. Recognition temporal trajectories using the CONDENSATION algorithm [J]. Proc. IEEE Int'1 Conf. on Automated Face and Gesture Recognition (FG'98), 1998:16-21.
[67] Black M, Jepson A. A probabilistic framework for matching temporal trajectories: CONDENSATION-based recognition of gestures and expressions [C]. Proc. European Conf, on Computer Vision (ECCV'98), 1998: 909-924.
[68] Shin M C, Tsap L V, Goldgof D B. Towards perceptual interface for visualization navigation of large data sets [J/OL]. http://marathon.csee.usf.edu/tsap/papers/cvpr-hci03.pdf.
[69] Shin M C, Tsap L V, Goldgof D B. Gesture recognition using bezier curves for visualization navigation from registered 3d data [J]. Pattern Recognition, 2004, 37(5):1011-1024.
[70] Deng J W, Tsui H T. An HMM-based approach for gesture segmentation and recognition [C]. Proc. IEEE Conf. on Pattern Recognition (ICPR'00), 2000, 3: 679-682.
[71] Ran H, Xu G. Human action recognition with primitive-based coupled- HMM [C]. Proc. IEEE Conf. on Pattern Recognition (ICPR'02), 2002, II: 494-498.
[72] Starner T, Weaver J, Pentland A. Real-time american sign language recognition using desk and wearable computer based video [J]. IEEE Trans. Pattern Anal. Machine Intel., 1998, 20(12): 1371-1375.
[73] Rabiner L. A tutorial on hidden markov model and selected applications in speech recognition [J]. Proceedings of the IEEE, 1989, 77(2):257-286.
[74] Davis J, Shah M. Visual gesture recognition [J]. Vision, Image and Signal Processing, 1994, 141(2): 101-106.
[75] Yeasin M, Chaudhuri S. Dynamic hand gesture understanding---a new approach [C]. Proc. IEEE Int'l Conf. on Acoustics, Speech, and Sigal Processing(ICASSP'99), 1999: 3073-3076.
[76] Yang M H, Ahuja N. Recognizing hand gesture using motion trajectories [C]. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'99), 1999, I: 466-472.
[77] Takahashi T, Shino F K. Hand gesture coding based on experiments using a hand gesture interface device [J]. SIGCHI Bulletin, 1991, 23(2):67-74.
[78] O'Toole A J, Millward R B, Anderson J A. A physical system approach to recognition memory for spatially transformed faces [J]. Neural Network, 1998, 1(3):179-199.
[79] Starner T. Visual recognition of American Sign Language using hidden markov models [D]. USA: Media Lab, MIT, 1995.
[80] Starner T, Pentland A. Real-time American Sign Language Recogniton from Video Using Hidden Markov Models [D]. USA: Media Lab, MIT, 1996.
[81] Grobel K, Assam M. Isolated sign language recognition using hidden Mardove models [C]. Proceeedings of the IEEE International Conference on Systems, Man and Cybernetics, 1997: 162-167.
[82] Vogler C, Metaxas D. Adapting Hidden Markov Models for ASL recogniton by using three-dimensional computer vision methods [C]. SMC'97, 1997: 156-161.
[83] Gao W. Enhanced user interface by using hand gesture recognition [J]. Chinese Journal of Advanced Software Research, 1996, 3(1): 30-42.
[84]吴江琴,高文,陈熙霖.基于数据手套的汉语手指字母的识别[J].模式识别与人工智能, 1999, 12(1): 74-78.
[85]任海兵,祝远新,徐光,林学,张晓平.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) : 824~828.
[86]周志宇,汪亚明,黄文清.基于动态图像序列的运动目标跟踪[J].浙江工程学院学报, 2002, 19(3): 165-170.
[87] Kim W, Lee C Y, Lee J J. Tracking moving object using Snake’s jump based on image flow [J]. Mechatronics, 2001, 11(2): 119-216.
[88] Cheng Yizong. Mean shift, mode seeking, and clustering [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(8).
[89] Comaniciu D, Meer P. Mean shift: A robust approach toward feature space analysis [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2002, 24 (5):603-619.
[90] Chen F S, Fu C M, Huang C L. Hand gesture recognition using a real-time tracking method and hidden Markov models [J]. Image and Vision Computing, 2003, 21(8): 745-58.
[91] Huang F, Ian R. Probabilistic tracking and recognition of non-rigid hand motion [C]. The 8th European Conference on Computer Vision, Prague, 2004(3): 497-508.
[92] Utsumi A, Ohya J. Image segmentation for human tracking using sequential-image based hierarchical adaptation [C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1998:911-916.
[93] Narang S, Narang N K, Biswas K K. Segmentation of non_rigid bodies in affine motion: a new framework [C]. IEEE Interneational Conference on Acousitcs, Speech, and Signal Processing, 1999, 4:2219-2222.
[94] Liyama M, Kameda Y, Minoh M. Estimation of the location of joint points of human body from successive volume data [C]. Proceedings of 15th International Conference on Pattern Recogniton, 2000, 3: 695-698.
[95] Kim M, Jeon J G, Kwak J S, Lee M H, Ahn C. Moving object segmentation in video sequences by user interaction and qutiomatic object tracking [J]. Image and Vision Computing, 2001, 19(5): 245-260.
[96] Vass J, Palaniappan K, Zhuang X. Automatic spatio-temporal video sequence segmentation [C]. International Conference on Image Processing, 1998, 1: 958-962.
[97] Song Yang, Perona P. A computational model for motion detection and direction discrimination in humans [C]. Proceedings. Workshop on Human Motion,2000:11-16.
[98] Yamamoto M, Yagishita K. Scene constraints-aided tracking of human body [C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2000, 1:151-156.
[99] Eveland C, Konolige K, Bolles R C. Background modeling for segmentation of videorate stereo sequences [C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1998, Page(s):266-271.
[100] Cai Q, Aggarwal J K. Tracking human motion in structured environments using a distributed-camera system [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999, 21(11): 1241-1247.
[101] Collins R T, Lipton A J, Fujiyoshi H, Kanade T. Algorithms for cooperative multisensor surveillance [J]. Proceedings of the IEEE, 2001, 89(10): 1456-1477.
[102]吴晓娟,翟海亭,王磊,徐力群.一种改进的CAMSHIFT手势跟踪算法[J].山东大学学报(工学版), 2004, 34(6): 121-124
[103]田欣.基于不同色彩空间的肤色模型[J].西安科技学院学院. 2001, 24(4): 370-371.
[104] Chen F S, Fu C M, Huang C L. Hand gesture recognition using a real-time tracking method and hidden Markov models [J]. Image and Vision Computing, 2003, 21(8): 745-758.
[105] Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-577.
[106] Kim W, Lee C Y, Lee J J. Tracking moving object using Snake’s jump based on image flow [J]. Mechatronics. 2001, 11(2): 119-216.
[107] Cohen L D. On active contour models and balloons [J]. Computer Vision, Graphics and Image Processing (CVGIP): Image Understanding. 1991, 53 (2): 211-218.
[108] Kass M, Witkinm A, Terzopoulos D. Snakes: Active contour models [C]. Proceedings of First International Conference on Computer Vision, London, 1987:259-269.
[109] Williams D J, Shah M. A fast algorithm for active contours and curvature estimation [J]. CVGIP: Image Understanding, 1992, 55(1): 14-26.
[110] Lannizzotto G, Vita L. On-line object tracking for colour video analysis [J]. Real-time Imaging, 2002, 8(2):145-155.
[111] Hou Z, Han C. Force field analysis snake: an improved parametric active contour model [J]. Pattern Recognition Letters, 2005, 26(5): 513-526.
[112]杨枝灵. Visual C++数字图像获取、处理及实践应用[M].北京:人民邮电出版社, 2003: 457-458.
[113] Haritaoglu I, Harwood D, Davis L S. W4: Real-time surveillance of people and their activities [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2000, 22(7): 809-830.
[114] McKenna S, Jabri S, Duric Z, et al. Tracking groups of people [J]. Computer Vision and Image Understanding, 2000, 80(1): 42-56.
[115] Staufer C, Grimson W E L. Adaptive background mixture models for real-time tracking [C]. IEEE Conf. on Computer Vision and Pattern Recognition, 1999: 246-252.
[116] Comaniciu D, Meer P. Mean Shift Analysis and Applications [C]. IEEE Int. Conf. Computer Vision (ICCV'99), 1999:1197-1203.
[117] Chen H, Meer P. Robust computer vision through kernel density estimation [C]. Computer Vision - ECCV 2002. 7th European Conference on Computer Vision. Proceedings, Part I (Lecture Notes in Computer Science Vol.2350), 2002: 236-50.
[118] Thiesson B, Xu Y, Cohen M. Image and video segmentation by anisotropic kernel mean shift [C]. Computer Vision - ECCV 2004. 8th European Conference on Computer Vision. Proceedings (Lecture Notes in Comput. Sci. Vol.3022), 2004, 2: 238-492.
[119] Bretznerand L, Lindeberg T. Feature tracking with automatic selection of spatial scales [J]. Computer Vision and Image Understanding, 1998, 71(3): 385-392.
[120]边肇祺,张学工.模式识别[M].北京:清华大学出版社, 2000: 180?181.
[121] Zivkovic Z, Krose B. An EM-like algorithm for color-histogram-based object tracking [C]. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004, 1: 798-803.
[122] Bradski G R. Computer vision face tracking as a component of a perceptual user interface [C]. Proc. IEEE Workshop Applications of Computer Vision, 1998: 214-219.
[123] Nummiaro K, Koller-Meier E, Van Gool L. An adaptive color-based particle filter [J]. Image and Vision Computing, 2002, 21(1): 99-110.
[124] Gordon N J, Salmond D J, Smith A F M. Novel approach to nonlinear non-Gaussian Bayesian state estimation [J]. IEE Proc. F, Radar Signal Process, 1993, 140(2): 107-113.
[125]康健,司锡才,芮国胜.基于贝叶斯原理的粒子滤波技术概述[J].现代雷达, 2004, 6(1): 34-36.
[126] Nummiaro K. Object Tracking with an Adaptive Color-based Particle Filter [J]. Pattern Recognition, 24th DAGM Symposium, Proceedings (Lecture Notes in Computr Science Vol.2449), Berlin, Germany, 2002: 353-360.
[127] Freeman W, Roth M. Orientation histograms for hand gesture recognition [C]. Proc. IEEE Int'1 Conf. on Automated Face and Gesture recognition (FG'95), 1995: 296-301.
[128] Freeman W, Weissman C. Television control by hand gestures [C]. Proc IEEE Int'I Conf. on Automated Face and Gesture Recognition (FG'95), 1995: 179-183.
[129] Freeman W, Adelson E. The design and use of steerable filters [J]. IEEE Trans. Pattern Anal. Machine IntelL, 1991: 13(9): 891-906.
[130] Grandlund G h. In search of a general picture processing operator [J]. Comp.Graphics, Image Proc., 1978, 8: 155-173.
[131]段洪伟.基于视觉的手势识别及其应用[D].上海:上海大学, 2004.
[132]孔晓明.人机交互系统中动态手势识别的研究[D].上海:上海大学, 2005.
[133] Ramamoorthy A, vaswani N, etl.all. Recognition of dynamic hand gestures [J]. Pattern Recognition, 36(9): 2069-2081.
[134] Huang F, Ian R. Probabilistic tracking and recognition of non-rigid hand motion [C]. The 8th European Conference on Computer Vision, 2004(3): 497-508.
[135] Kentaro T, Andrew B. Probabilistic tracking with exemplars in a metric space [J]. International Journal of Computer Vision, 2002, 48(1): 9-19.
[2] Schlegel C, Illmann J, Jaberg H, et al. Vision based person tracking with a mobile robot [C]. British Machine Vision Conference, Southampton, UK, 1998: 418-427.
[3] Pavlovic V, Sharma R, Huang T S. Visual interpretation of hand gesture for human-computer interaction: A Rreview [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1997, 19 (7): 677-695.
[4]任海兵,祝远新,徐光佑.基于视觉手势识别的研究---综述[J].电子学报,2000,Vol. 28 No. 2.
[5]魏育成.智能服务型机器人的视觉感知接口与导航[D].北京:中国科学院自动化研究所, 2004.
[6] Isard M, Blake A. ICONDENSATION: Unifyinglow-level tracking in a stochastic framework [C]. Proc. European Conf. On Computer Vision (ECCV'98), 1998: 893-908.
[7] Isard M, Blake A. A mixed-state condensation tracker with automatic model-switching [C]. Proc 6th Int. Conf. Computer Vision (ICCV'98), 1998: 107-112.
[8] Isard M, Blake A. CONDENSATION: conditional density propagation for visual tracking [J]. International of Computer Vision, 1998, 29 (1): 5-28.
[9] McAllister G, McKenna S J, Ricketts I W. Hand tracking for behaviour understanding [J], Image and Vision Computing, 2002, 20(12): 827-840.
[10] Blake A, Isard M. Active contours [M]. Springer-Verlag, 1998.
[11] Wah Ng C, Ranganath S. Real-time gesture recognition system and application [J]. Image and Vision Computing, 2002, 20(13): 993-1007.
[12] Oka K, Sato Y, Koike H. Real-time tracking of multiple fingertips and gesturerecognition for augmented desk interface systems [C]. IEEE Int. Conf. on Automated Face and Gesture Recognition (FG'02), 2002: 411-416.
[13] Mammen J, Chaudhuri S, Agrawal T. Simultaneous tracking of both hands by estimation of erroneous observations [C]. Proc of BMVC’, 2001: 83-92.
[14] Laptev I, Lindeberg T. Tracking of multi-state hand models using particle filtering and a hierarchy of multi-scale image features [C]. Proc. IEEE Workshop on Scale-Space and Morphology, 2001: 63-74.
[15] Triesch J, Malsburg C V. A system for person-independent hand posture recognition against complex backgrounds [J]. IEEE Trans. Pattern Anal. Machine Intell. 2001, 23(12): 1449-1453.
[16] Terrillon J, Akamatsu S. Comparative performance of diferent skin chrominance models and chrominance spaces for the automatic detection of human faces in color images [C]. Proc. IEEE Int. Conf. on Automated Face and Gesture Recognition (FG'00), 2000: 54-61.
[17] Jones M, Rehg J M. Statistical color models with application to skin detection [J]. Int'1 Journal of Computer Vision, 2002, 46(1): 81-96.
[18] Wu Y. Vision and learning for intelligent human-computer interaction [D]. U S: University of Illinois at Urbanar Champaign, 2001.
[19] Wu Y, Liu Q, Huang T. An adaptive self organizing color segmentation algorithm with application to robust real-time human hand localization [C]. Proc. Asian Conference on Computer Vision (ACCV'00), 2000: 1106-1111.
[20] Raja Y, McKenna S, Gong S. Colour model selection and adaptation in dynamic scenes [C]. Proc. European Conf. on Computer Vision (ECCV'98), 1998:460-474.
[21] Tsap L. Gesture-tracking in real time with dynamic regional range computation [J]. Real Time Imaging, 2002, 8(2): 115-126.
[22] Shan C, Wei Y, et al. Real time hand tracking by combining particle filtering and mean shift [C]. Proc. IEEE Int'1 Conf. on Automated Face and Gesture Recognition (FG'04), 2004: 669-674.
[23] Wu Y, Huang T. Vision-based gesture recognition: A review [A]. Lecture Notes in Artificial Intelligence 1739, Gesture-Based Communication in Human-Computer Interaction (Int'l Gesture Workshop, GW99), 1999: 103-115.
[24] Freeman W, Roth M. Orientation histograms for hand gesture recognition [C]. Proc. IEEE Int'1 Conf. on Automated Face and Gesture recognition (FG'95), 1995: 296-301.
[25] Yang M, Ahuja N, Tabb M. Extraction of 2d motion trajectories and its application to hand gesture recognition [J]. IEEE Trans. Pattern Anal.Machine Intell., 2002, 24(8):1061-1074.
[26] Fei H, Reid I. Probabilistic tracking and recognition of non-rigid hand motion [C]. Proc. IEEE Int'1 Workshop on Analysis and Modeling of Faces and Gestures (AMFG'03), 2003: 60-67.
[27] Starner T, W eaver J, Pentland A. Realtime American sign language recognition using desk and wearable computerbased video [J]. IEEE Transations on P attern A naly sis and M ach ine Intellig ence, 1998, 20 (12): 1371-1375.
[28] Lee H K, Kim J H. An HMM-based threshold model approach for gesture recognition [J]. IEEET ransationson Pattern Analysis and Machine Intelligence, 1999, 21(10): 961-973.
[29]李清水,方志刚等.手势识别技术及其在人机交互中的应用[J].人类工效学, 2002, 8(1): 27-33.
[30] Kass M, Witkin A P, Terzopoulos D. Snakes: active contour models [J]. International Journal of Computer Vision, 1987, l (4): 321- 331.
[31]杜威,李华.基于单目视觉的手势识别系统[J].工程图学学报, 2000, 3: 133-138.
[32]丁海洋,阮秋琦.多尺度模型与矩描绘子相结合的手势识别算法[J].北京交通大学学报, 2004, 28(2): 41-45.
[33] Chai D, Ngan K. Automatic Face Location for Videophone Images [A]. IEEE TENCON Digital Signal Processing Applications Proceedings, 1996: 137-140.
[34] Habili N, Lim C C. Hand and face segmentation using motion and color cues in digital image sequences [A]. Proceedings of IEEE International Conference on Multimedia & Expo2001, 2001: 261 - 264.
[35] Du W, Li H. Vision based gesture recognition system with single camera [A]. 2000 5th International Conference on Signal Processing Proceedings, 2000:1351- 1357.
[36] Lew Y P, Ramli A R, Koay S Y, et al. A Hand segmentation scheme using clustering technique in homegeneous background [C]. Student Conference on Research and Development Proceedings, 2002:305- 308.
[37] Chaparro A, et al. Colour is what the eye sees best [J]. Nature, 1993, 361(6410): 349- 350.
[38] Yang J, Lu W, Waibel. A. Skin- Color Modeling and Adaptation [A]. Proc. ACCV, Hong Kong, 1998: 687-694.
[39] Bradski G. Computer vision face tracking for use in a perceptual user interface [J]. Intelligence Technology Journal, 1998, 2: 1-15.
[40] D. Comaniciu, V. Ramesh, and P. Meer. Real-time tracking of non-rigid objects using mean shift [C]. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'00), 2000: 142-149.
[41] Perez P, Hue C, Vermaak J, and Gangnet M. Color-based probabilistic tracking [C]. Proc. European Conf. on Computer Vision (ECCV'02), 2002, 1: 661-675.
[42] Nummiaro K, Koller-Meier E, Van Gool L. An adaptive color-based particle filter [J]. Image and Vision Computing, 2003, 21(1): 99-110.
[43] Shamaie A, Sutherland A. A dynamic model for real-time tracking of hands in bimanual movements [C]. Gesture-Based Communication in Human-Computer Interaction (Int'l Gesture Workshop, GW03), 2003:172-179.
[44] Bretzner L, Laptev I, Lindeberg T. Hand gesture recognition using multi-scale colour features, hierarchical models and particle filtering [C]. Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition,2002: 423-428.
[45] Zhou H, Huang T. Tracking articulated hand motion with eigen dynamics analysis [C]. Proceedings Ninth IEEE International Conference on Computer Vision, 2003:1102-1109.
[46] Hong P, Turk M, Huang T. Gesture modeling and recognition using finite state machines [C]. Proc. IEEE Int'l Conf. on Automated Face and Gesture Recognition (FG'00), 2000: 410-415
[47] Pavlovic V. Dynamic bayesian networks for information fusion with applications to human-computer interfaces [D]. America: University of Illinois at UrbanarChampaign, 1999.
[48] Wu Y. Vision and learning for intelligent human-computer interaction [D]. Americal: University of Illinois at UrbanarChampaign, 2001.
[49] Wu Y, Huang T S. View-independent recognition of hand posture [C]. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'00), 2000:88-94.
[50] Lockton R. Fitzqibbon A W. Real-time gesture recognition using deterministic boosting [C]. Proc. British Machine Vision Conference (BMVC'02), 2002: 817-826.
[51] Deng J, Tsui H. A PCA/MDA scheme for hand posture recognition [C]. Proc. IEEE Int'l Conf. on Automated Face and Gesture Recognition (FG'02), 2002: 279-284.
[52] Triesch J, vonder Malsburg C. A gesture interface for human-robotinteraction [C]. Proc. IEEE Int'1 Conf. on Automated Face and Gesture Recognition (FG'98), 1998: 546-551.
[53] Freeman W, Anderson D, et al. Computer vision for interactive computer graphics [J]. IEEE Comput. Graph Appl., 1998, 18(3): 42-53.
[54] Liu N, Lovell B. Gesture classification using hidden markov models and viterbi path counting [C]. Proc. Int'1 Conf. on Digital Image Computing: Techniques and Applications (DICTA'03), 2003: 273-28.
[55] Cui Y, Swets D, Weng J. Learning-based Hand Sign Recognition using SHOSLIF-M [C]. Proceedings of 5" International Conference on Computer Vision, 1995: 631-636.
[56] Triesch J, Vonder Malsburg C. A System for Person-independent Hand Posture Recognition against Complex Backgrounds [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2001, 23(12):1449-1453.
[57] Nolker C, Ritter H. Illumination Independent Recognition of Deietiec ArmPostures [C]. Proc. 24th Annual Conference of the IEEE Industrial Electronics Society, 1998: 2006-2011.
[58] Mori T. Visual motion perception [J], Circulars of the Electrotechnical Laboratory, 1982, 207(10):1-78.
[59] 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.
[60] Kahol K, Tripathi P, et al. Gesture segmentation in complex motion sequences [C]. Proc. IEEE Int'l Conf. on Image Processing (ICIP'03), 2003, II: 105-108.
[61] McKenna S, Gong S. Gesture recognition for visualy mediated interaction using probabilistic event trajectories [C]. Proc. British Machine Vision Conference (BMVC'98), 1998: 498–507.
[62] Gong S, Walter M, Psarrou A. Recognition of temporal structures: Learning prior and propagating observation augmented densities via hidden markov states [C]. Proc. IEEE Int'l Conf. on Computer Vision (ICCV'99), 1999:157-162.
[63] Psarrou A, Gong S, Walter M. Recognition of human gestures and behaviour based on motion trajectories [J]. Image and Vision Computing, 2002, 20(5): 349-358.
[64] Isard M, Blake A. Visual tracking by stochastic propagation of conditional density [C]. Proc. European Conf. on Computer Vision (ECCV'96), 1996: 343-356.
[65] Eoler-Meier E B, Gool L V. Modeling and recognition of human actions using astochastic approach [C], Proc. 2nd European Workshop on Advanced Video-based Surveilance Systems, 2001:17-28.
[66] Black M J, Jepson A D. Recognition temporal trajectories using the CONDENSATION algorithm [J]. Proc. IEEE Int'1 Conf. on Automated Face and Gesture Recognition (FG'98), 1998:16-21.
[67] Black M, Jepson A. A probabilistic framework for matching temporal trajectories: CONDENSATION-based recognition of gestures and expressions [C]. Proc. European Conf, on Computer Vision (ECCV'98), 1998: 909-924.
[68] Shin M C, Tsap L V, Goldgof D B. Towards perceptual interface for visualization navigation of large data sets [J/OL]. http://marathon.csee.usf.edu/tsap/papers/cvpr-hci03.pdf.
[69] Shin M C, Tsap L V, Goldgof D B. Gesture recognition using bezier curves for visualization navigation from registered 3d data [J]. Pattern Recognition, 2004, 37(5):1011-1024.
[70] Deng J W, Tsui H T. An HMM-based approach for gesture segmentation and recognition [C]. Proc. IEEE Conf. on Pattern Recognition (ICPR'00), 2000, 3: 679-682.
[71] Ran H, Xu G. Human action recognition with primitive-based coupled- HMM [C]. Proc. IEEE Conf. on Pattern Recognition (ICPR'02), 2002, II: 494-498.
[72] Starner T, Weaver J, Pentland A. Real-time american sign language recognition using desk and wearable computer based video [J]. IEEE Trans. Pattern Anal. Machine Intel., 1998, 20(12): 1371-1375.
[73] Rabiner L. A tutorial on hidden markov model and selected applications in speech recognition [J]. Proceedings of the IEEE, 1989, 77(2):257-286.
[74] Davis J, Shah M. Visual gesture recognition [J]. Vision, Image and Signal Processing, 1994, 141(2): 101-106.
[75] Yeasin M, Chaudhuri S. Dynamic hand gesture understanding---a new approach [C]. Proc. IEEE Int'l Conf. on Acoustics, Speech, and Sigal Processing(ICASSP'99), 1999: 3073-3076.
[76] Yang M H, Ahuja N. Recognizing hand gesture using motion trajectories [C]. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'99), 1999, I: 466-472.
[77] Takahashi T, Shino F K. Hand gesture coding based on experiments using a hand gesture interface device [J]. SIGCHI Bulletin, 1991, 23(2):67-74.
[78] O'Toole A J, Millward R B, Anderson J A. A physical system approach to recognition memory for spatially transformed faces [J]. Neural Network, 1998, 1(3):179-199.
[79] Starner T. Visual recognition of American Sign Language using hidden markov models [D]. USA: Media Lab, MIT, 1995.
[80] Starner T, Pentland A. Real-time American Sign Language Recogniton from Video Using Hidden Markov Models [D]. USA: Media Lab, MIT, 1996.
[81] Grobel K, Assam M. Isolated sign language recognition using hidden Mardove models [C]. Proceeedings of the IEEE International Conference on Systems, Man and Cybernetics, 1997: 162-167.
[82] Vogler C, Metaxas D. Adapting Hidden Markov Models for ASL recogniton by using three-dimensional computer vision methods [C]. SMC'97, 1997: 156-161.
[83] Gao W. Enhanced user interface by using hand gesture recognition [J]. Chinese Journal of Advanced Software Research, 1996, 3(1): 30-42.
[84]吴江琴,高文,陈熙霖.基于数据手套的汉语手指字母的识别[J].模式识别与人工智能, 1999, 12(1): 74-78.
[85]任海兵,祝远新,徐光,林学,张晓平.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) : 824~828.
[86]周志宇,汪亚明,黄文清.基于动态图像序列的运动目标跟踪[J].浙江工程学院学报, 2002, 19(3): 165-170.
[87] Kim W, Lee C Y, Lee J J. Tracking moving object using Snake’s jump based on image flow [J]. Mechatronics, 2001, 11(2): 119-216.
[88] Cheng Yizong. Mean shift, mode seeking, and clustering [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(8).
[89] Comaniciu D, Meer P. Mean shift: A robust approach toward feature space analysis [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2002, 24 (5):603-619.
[90] Chen F S, Fu C M, Huang C L. Hand gesture recognition using a real-time tracking method and hidden Markov models [J]. Image and Vision Computing, 2003, 21(8): 745-58.
[91] Huang F, Ian R. Probabilistic tracking and recognition of non-rigid hand motion [C]. The 8th European Conference on Computer Vision, Prague, 2004(3): 497-508.
[92] Utsumi A, Ohya J. Image segmentation for human tracking using sequential-image based hierarchical adaptation [C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1998:911-916.
[93] Narang S, Narang N K, Biswas K K. Segmentation of non_rigid bodies in affine motion: a new framework [C]. IEEE Interneational Conference on Acousitcs, Speech, and Signal Processing, 1999, 4:2219-2222.
[94] Liyama M, Kameda Y, Minoh M. Estimation of the location of joint points of human body from successive volume data [C]. Proceedings of 15th International Conference on Pattern Recogniton, 2000, 3: 695-698.
[95] Kim M, Jeon J G, Kwak J S, Lee M H, Ahn C. Moving object segmentation in video sequences by user interaction and qutiomatic object tracking [J]. Image and Vision Computing, 2001, 19(5): 245-260.
[96] Vass J, Palaniappan K, Zhuang X. Automatic spatio-temporal video sequence segmentation [C]. International Conference on Image Processing, 1998, 1: 958-962.
[97] Song Yang, Perona P. A computational model for motion detection and direction discrimination in humans [C]. Proceedings. Workshop on Human Motion,2000:11-16.
[98] Yamamoto M, Yagishita K. Scene constraints-aided tracking of human body [C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2000, 1:151-156.
[99] Eveland C, Konolige K, Bolles R C. Background modeling for segmentation of videorate stereo sequences [C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1998, Page(s):266-271.
[100] Cai Q, Aggarwal J K. Tracking human motion in structured environments using a distributed-camera system [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999, 21(11): 1241-1247.
[101] Collins R T, Lipton A J, Fujiyoshi H, Kanade T. Algorithms for cooperative multisensor surveillance [J]. Proceedings of the IEEE, 2001, 89(10): 1456-1477.
[102]吴晓娟,翟海亭,王磊,徐力群.一种改进的CAMSHIFT手势跟踪算法[J].山东大学学报(工学版), 2004, 34(6): 121-124
[103]田欣.基于不同色彩空间的肤色模型[J].西安科技学院学院. 2001, 24(4): 370-371.
[104] Chen F S, Fu C M, Huang C L. Hand gesture recognition using a real-time tracking method and hidden Markov models [J]. Image and Vision Computing, 2003, 21(8): 745-758.
[105] Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-577.
[106] Kim W, Lee C Y, Lee J J. Tracking moving object using Snake’s jump based on image flow [J]. Mechatronics. 2001, 11(2): 119-216.
[107] Cohen L D. On active contour models and balloons [J]. Computer Vision, Graphics and Image Processing (CVGIP): Image Understanding. 1991, 53 (2): 211-218.
[108] Kass M, Witkinm A, Terzopoulos D. Snakes: Active contour models [C]. Proceedings of First International Conference on Computer Vision, London, 1987:259-269.
[109] Williams D J, Shah M. A fast algorithm for active contours and curvature estimation [J]. CVGIP: Image Understanding, 1992, 55(1): 14-26.
[110] Lannizzotto G, Vita L. On-line object tracking for colour video analysis [J]. Real-time Imaging, 2002, 8(2):145-155.
[111] Hou Z, Han C. Force field analysis snake: an improved parametric active contour model [J]. Pattern Recognition Letters, 2005, 26(5): 513-526.
[112]杨枝灵. Visual C++数字图像获取、处理及实践应用[M].北京:人民邮电出版社, 2003: 457-458.
[113] Haritaoglu I, Harwood D, Davis L S. W4: Real-time surveillance of people and their activities [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2000, 22(7): 809-830.
[114] McKenna S, Jabri S, Duric Z, et al. Tracking groups of people [J]. Computer Vision and Image Understanding, 2000, 80(1): 42-56.
[115] Staufer C, Grimson W E L. Adaptive background mixture models for real-time tracking [C]. IEEE Conf. on Computer Vision and Pattern Recognition, 1999: 246-252.
[116] Comaniciu D, Meer P. Mean Shift Analysis and Applications [C]. IEEE Int. Conf. Computer Vision (ICCV'99), 1999:1197-1203.
[117] Chen H, Meer P. Robust computer vision through kernel density estimation [C]. Computer Vision - ECCV 2002. 7th European Conference on Computer Vision. Proceedings, Part I (Lecture Notes in Computer Science Vol.2350), 2002: 236-50.
[118] Thiesson B, Xu Y, Cohen M. Image and video segmentation by anisotropic kernel mean shift [C]. Computer Vision - ECCV 2004. 8th European Conference on Computer Vision. Proceedings (Lecture Notes in Comput. Sci. Vol.3022), 2004, 2: 238-492.
[119] Bretznerand L, Lindeberg T. Feature tracking with automatic selection of spatial scales [J]. Computer Vision and Image Understanding, 1998, 71(3): 385-392.
[120]边肇祺,张学工.模式识别[M].北京:清华大学出版社, 2000: 180?181.
[121] Zivkovic Z, Krose B. An EM-like algorithm for color-histogram-based object tracking [C]. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004, 1: 798-803.
[122] Bradski G R. Computer vision face tracking as a component of a perceptual user interface [C]. Proc. IEEE Workshop Applications of Computer Vision, 1998: 214-219.
[123] Nummiaro K, Koller-Meier E, Van Gool L. An adaptive color-based particle filter [J]. Image and Vision Computing, 2002, 21(1): 99-110.
[124] Gordon N J, Salmond D J, Smith A F M. Novel approach to nonlinear non-Gaussian Bayesian state estimation [J]. IEE Proc. F, Radar Signal Process, 1993, 140(2): 107-113.
[125]康健,司锡才,芮国胜.基于贝叶斯原理的粒子滤波技术概述[J].现代雷达, 2004, 6(1): 34-36.
[126] Nummiaro K. Object Tracking with an Adaptive Color-based Particle Filter [J]. Pattern Recognition, 24th DAGM Symposium, Proceedings (Lecture Notes in Computr Science Vol.2449), Berlin, Germany, 2002: 353-360.
[127] Freeman W, Roth M. Orientation histograms for hand gesture recognition [C]. Proc. IEEE Int'1 Conf. on Automated Face and Gesture recognition (FG'95), 1995: 296-301.
[128] Freeman W, Weissman C. Television control by hand gestures [C]. Proc IEEE Int'I Conf. on Automated Face and Gesture Recognition (FG'95), 1995: 179-183.
[129] Freeman W, Adelson E. The design and use of steerable filters [J]. IEEE Trans. Pattern Anal. Machine IntelL, 1991: 13(9): 891-906.
[130] Grandlund G h. In search of a general picture processing operator [J]. Comp.Graphics, Image Proc., 1978, 8: 155-173.
[131]段洪伟.基于视觉的手势识别及其应用[D].上海:上海大学, 2004.
[132]孔晓明.人机交互系统中动态手势识别的研究[D].上海:上海大学, 2005.
[133] Ramamoorthy A, vaswani N, etl.all. Recognition of dynamic hand gestures [J]. Pattern Recognition, 36(9): 2069-2081.
[134] Huang F, Ian R. Probabilistic tracking and recognition of non-rigid hand motion [C]. The 8th European Conference on Computer Vision, 2004(3): 497-508.
[135] Kentaro T, Andrew B. Probabilistic tracking with exemplars in a metric space [J]. International Journal of Computer Vision, 2002, 48(1): 9-19.