序列图像中动态手势跟踪与建模方法研究
|
摘要
随着计算机软、硬件技术的迅猛发展及广泛应用,人与计算机之间的交互活动也越来越密切。手势这一人与人之间除自然语言外最重要的人际交流方式也被引入人机交互中,使得人与计算机之间的交互以一种更加自然而直观的方式进行。
论文从自然人机交互的需求出发,对复杂背景下序列图像中的静态手形提取、动态手势建模及特征提取、动态手势跟踪识别进行了研究。并在此基础上,实现了从摄像头输入的5种鼠标手势的识别,以此来验证论文算法的正确性与有效性。针对复杂背景下利用单一线索对静态手形提取不准确的缺陷,提出了一种结合手势肤色、运动、轮廓等多线索的静态手形提取方法。该方法利用HSV颜色空间的H、S分量以及YCbCr颜色空间的Y分量实现了光照变化条件下手势的肤色检测,并且利用帧差分法进行运动检测去除类肤色背景,最后融合肤色、运动、轮廓等多种线索实现了复杂背景下静态手形的准确提取。
为了解决传统Mean shift算法在复杂背景和光照变化等情形下存在跟踪不稳定、跟踪失败无法恢复等问题,提出了一种融合手势肤色和结构等多特征的鲁棒的Mean shift手势跟踪算法。该算法将肤色检测和帧差分法相结合形成目标检测模块,实现了跟踪初始化时可自动检测目标,同时可自动根据跟踪结果来确定目标手势矩形域。经与传统Mean shift算法对比实验分析,该算法提高了手势跟踪的准确性和稳定性。当手势快速运动及遮挡等导致跟踪失败时,可利用目标检测恢复跟踪,提高了跟踪的连续性。
针对动态手势模型的准确性和使用速度不协调的矛盾,提出了一种动态手势建模及有效提取的方法。该方法利用动态手势开始手形、结束手形和中间运动轨迹建立动态手势模型,利用边界矩提取动态手势特征。实验表明,该方法可实现动态手势特征的有效提取。
最后,在Matlab7.0环境下编程进行了仿真实验,识别从USB摄像头输入的5种鼠标手势,结果证明了本文所提方法的有效性和正确性。
With the rapid development and wide application of the computer software and hardware technology, the interaction between human and computer are getting closer. People often get all kinds of information by computer, learning, research, communication and entertainment, promoting the presented and development of the advanced human-computer interaction technology. Hand gesture, the most important interpersonal communication way except the natural language among people, is also introduced into HCI (Human-Computer Interaction), making the interaction between people and computers can be in a more natural and intuitive manner.
From the requirement of natural human-computer interaction, this article studied the static hand shape extraction, dynamic hand gesture modeling and feature extraction, as well as hand gesture tracking and recognition in complex background. Finally, based on the simple nature hand gesture, 5 kinds of mouse hand gestures is realized to verify the feasibility of the algorithm.
According to the inaccuracy of extract hand shape based on the single clue, a method of hand shape extraction combined color, motion, contour is proposed. It uses H,S and Y component in the HSV and YCbCr color space to realize the skin detection with the illumination change conditions, remove skin background by using the method of frame difference based on motion detection, finally realize the accurate extraction static hand shape by using fusion clues include color, motion, and contour information.
In order to overcome the limitation of traditional Mean shift algorithm in complex background and illumination change such as tracking unstable, tracking failure problems can not be restored, we proposed a robust Mean shift hand gesture tracking algorithm fusing hand skin and structural feature. It combined frame difference and skin detection to form targets detection module, which could detect target automatically at the beginning of the tracking procedure and determine the rectangular areas of the target automatically according to tracking result. Compared with traditional Mean shift algorithm, this method improves the accuracy and stability of hand gesture tracking. When the gesture tracking fails caused by fast motion and occlusion, hand tracking can be restored by using object detection. This can improve tracking continuity.
Considering the accuracy of gesture modeling is inconsistent with its efficiency, a dynamic hand gesture modeling and real-time extraction method is proposed. It uses starting hand shape, end hand shape and middle trajectory as dynamic gestures model, using boundary moment to extract dynamic hand gesture features. Experiments show it can improve the speed of the dynamic gesture recognition.
At last, a simulation experiment which could identify 5 kings of mouse gestures captured from USB camera hava been made in Matlab7.0 programming environment. The experiment results demonstrated that the proposed method is more effective and accurate.
论文从自然人机交互的需求出发,对复杂背景下序列图像中的静态手形提取、动态手势建模及特征提取、动态手势跟踪识别进行了研究。并在此基础上,实现了从摄像头输入的5种鼠标手势的识别,以此来验证论文算法的正确性与有效性。针对复杂背景下利用单一线索对静态手形提取不准确的缺陷,提出了一种结合手势肤色、运动、轮廓等多线索的静态手形提取方法。该方法利用HSV颜色空间的H、S分量以及YCbCr颜色空间的Y分量实现了光照变化条件下手势的肤色检测,并且利用帧差分法进行运动检测去除类肤色背景,最后融合肤色、运动、轮廓等多种线索实现了复杂背景下静态手形的准确提取。
为了解决传统Mean shift算法在复杂背景和光照变化等情形下存在跟踪不稳定、跟踪失败无法恢复等问题,提出了一种融合手势肤色和结构等多特征的鲁棒的Mean shift手势跟踪算法。该算法将肤色检测和帧差分法相结合形成目标检测模块,实现了跟踪初始化时可自动检测目标,同时可自动根据跟踪结果来确定目标手势矩形域。经与传统Mean shift算法对比实验分析,该算法提高了手势跟踪的准确性和稳定性。当手势快速运动及遮挡等导致跟踪失败时,可利用目标检测恢复跟踪,提高了跟踪的连续性。
针对动态手势模型的准确性和使用速度不协调的矛盾,提出了一种动态手势建模及有效提取的方法。该方法利用动态手势开始手形、结束手形和中间运动轨迹建立动态手势模型,利用边界矩提取动态手势特征。实验表明,该方法可实现动态手势特征的有效提取。
最后,在Matlab7.0环境下编程进行了仿真实验,识别从USB摄像头输入的5种鼠标手势,结果证明了本文所提方法的有效性和正确性。
With the rapid development and wide application of the computer software and hardware technology, the interaction between human and computer are getting closer. People often get all kinds of information by computer, learning, research, communication and entertainment, promoting the presented and development of the advanced human-computer interaction technology. Hand gesture, the most important interpersonal communication way except the natural language among people, is also introduced into HCI (Human-Computer Interaction), making the interaction between people and computers can be in a more natural and intuitive manner.
From the requirement of natural human-computer interaction, this article studied the static hand shape extraction, dynamic hand gesture modeling and feature extraction, as well as hand gesture tracking and recognition in complex background. Finally, based on the simple nature hand gesture, 5 kinds of mouse hand gestures is realized to verify the feasibility of the algorithm.
According to the inaccuracy of extract hand shape based on the single clue, a method of hand shape extraction combined color, motion, contour is proposed. It uses H,S and Y component in the HSV and YCbCr color space to realize the skin detection with the illumination change conditions, remove skin background by using the method of frame difference based on motion detection, finally realize the accurate extraction static hand shape by using fusion clues include color, motion, and contour information.
In order to overcome the limitation of traditional Mean shift algorithm in complex background and illumination change such as tracking unstable, tracking failure problems can not be restored, we proposed a robust Mean shift hand gesture tracking algorithm fusing hand skin and structural feature. It combined frame difference and skin detection to form targets detection module, which could detect target automatically at the beginning of the tracking procedure and determine the rectangular areas of the target automatically according to tracking result. Compared with traditional Mean shift algorithm, this method improves the accuracy and stability of hand gesture tracking. When the gesture tracking fails caused by fast motion and occlusion, hand tracking can be restored by using object detection. This can improve tracking continuity.
Considering the accuracy of gesture modeling is inconsistent with its efficiency, a dynamic hand gesture modeling and real-time extraction method is proposed. It uses starting hand shape, end hand shape and middle trajectory as dynamic gestures model, using boundary moment to extract dynamic hand gesture features. Experiments show it can improve the speed of the dynamic gesture recognition.
At last, a simulation experiment which could identify 5 kings of mouse gestures captured from USB camera hava been made in Matlab7.0 programming environment. The experiment results demonstrated that the proposed method is more effective and accurate.
引文
[1] Robert J K Jacob,Keith S Karn.Eye tracking in human computer interaction and usability research:Ready to deliver the promises[J].Computer Vision and Image Understanding,2003,24:682-701
[2]黄乔.视线跟踪技术与视线输入的人机系统研究[D].湖北:武汉理工大学,2008
[3] Alejandro Jaimes, Nicu Sebe.Multimodal human-computer interaction:A survey[J]. Computer Vision and Image Understanding 2007,108:116-134
[4]郭兴伟.基于视觉的手势识别算法研究[D].上海:上海海运学院,2003
[5] Enrico Bertini,Giuseppe Santucci.Automatic Interface Generation Through Interaction,Users,And Devices Modeling[J].Computer-Aided Design Of User Interfaces,2007,10:191-200
[6]吴巾一,周德龙.人脸识别方法综述[J].计算机应用研究,2009,26(9):3205-3209
[7] Md Hasanuzzamana, T Zhanga,V Ampornaramvetha,et al.Adaptive visual gesture recognition for human-robot interaction using a knowledge-based software platform[J].Robotics and Autonomous Systems,2007,55(8):643-657
[8] S Malassiotis,M G Strintzis.Real-time hand posture recognition using range data[J]. Image and Vision Computing,2008,26(7):1027-1037
[9]滕晓龙.用于人机交互的手势识别研究[D].上海:上海交通大学,2006
[10] Shunji Uchino, Norihiro Abe,Yoshihiro Tabuchi Hirokazu Taki,et al.VR interactive dialog system with verbal and nonverbal communication[J].Artif Life Robotics, 2009,13(2):512-516
[11] Lee C, Xu Y.Online interactive learning of gestures for human/robot interfaces[C] //Proc of IEEE Int Conf on Robotics and Automation.Minneapolis, MN,USA:IEEE, 1996,4:2982-2987
[12] Je H, Kim J, Kim D.Hand Gesture Recognition To Understand Musical Conducting Action[C]//The 16th IEEE Int Symp on Robot and Human Interactive Communication.Jeju:IEEE,2007:163-168
[13] Liya Ding,Aleix M.Martinez.Modeling and recognition of the linguistic components in American Sign Language[J].Image and Vision Computing,2009, 27(12):1826-1844
[14] Pavlovic V I,Sharma R,Huang T S.Visual Interpretation of Hand Gestures for Human-Computer Interaction:A Review[J].IEEE Transactions on Pattern Analysis
and Machine Intelligence,1997,19(7):677-695
[15]任海兵,祝远新,徐光佑等.基于视觉手势识别的研究-综述[J].电子学报, 2000,28(2):118-121
[16] Liang R-H.anduohyoung,M.A real-time Continuous AIPhabetic Sign Language to Speech Conversion VR System[J].Computer Graphics Forum,1995,14(3):C67-C77
[17]吴江琴,高文,等.中国手语手势词识别的一种快速方法[J].高技术通讯,2001,11(6):23-27
[18]吴江琴,高文.基于DGMM的中国手语识别系统[J].计算机研究与发展,2000,37(5):551-558
[19] Wang R, Popovic J.Real-Time Hand-Tracking with a Color Glove. ACM Trans on Graphics[J], 2009,28(3):1-8
[20] Starner T, Weaver J, Pentland A. Real-time American Sign Language Recognition Using Desk and Wearable Computer Based Video[J].IEEE Transactions on Pattern Analysis and Machine Intelligence(PAMD),1998,20(12):1371-1375
[21]周宇,陈熙霖,赵德斌,等.基于数据生成的手语识别自适应方法[J].高技术通讯,2009,19(12):1258-1264
[22]李勇,高文,姚鸿勋.基于颜色手套的中国手指语字母的动静态识别[J].计算机工程与应用,2002, 38(17):55-58
[23]张良国,高文,陈熙霖,等.面向中等词汇量的中国手语视觉识别系统[J].计算机研究与发展,2006,43(3):476-482
[24]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[J].软件学报,2008,19(9):2302-2312
[25]任海兵,祝远新,徐光祐,林学訚,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
[26] Yun Liu,Zhijie Gan,Yu Sun.Static Hand Gesture Recognition and its Application based on Support Vector Machines[C]// Proc of the Ninth ACIS Int Conf on Software Engineering,Artificial Intelligence,Networking,and Parallel/Distributed Computing. Phuket, 2008:517-521
[27] Priyal S P, Bora P K.A study on static hand gesture recognition using moments[C] //Proc of IEEE SPCOM’10.Bangalore:IEEE,2010:1-5
[28] Aditya Ramamoorthya, Namrata Vaswania.Recognition of dynamic hand gestures [J].Pattern Recognition, 2003,36:2069–2081
[29] Darrell T J, Essa I A,Pentland A P. Task-specific gesture analysis in real-time using interpolated views[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1996,18(12):1236-1242
[30]冯志全.运动人手的三维跟踪方法研究[D].山东:山东大学,2006
[31] Bobick A F,Davis J W. An Appearance-Based Representation of Action[C]//Proc of the 13th International Conference on Pattern Recognition.Vienna, Austria,1996,1: 307-312
[32] Cui Y, Weng J. Hand sign recognition from intensity image sequence with complex backgrounds[C]//Proc of the 2th Int Conf on Automatic Face and Gesture Recognition. Killington,VT,USA,1996:259-264
[33]刘俊梅,阮秋琦.一种复杂背景下的手势分割新方法[J].北京电子科技学院学报, 2006,14(2):23-27
[34]齐苏敏,黄贤武,刘家盛.利用基于颜色的自适应形状模型实现手势跟踪[J].计算机应用研究,2008,25(2):485-487,474
[35]樊亚春,周明全,耿国华.消除光照影响的背景减除算法[J].中国图象图形学报,2009,14(7):1413-1417
[36]王小华,王波.一种有效的动态背景更新方法[J].杭州电子科技大学学报,2009,29(3):56-59
[37]刘昌盛,厉树忠,赵姝颖,等.一种复杂背景下的手部图像分割方法[J].河北科技师范学院学报,2007, 21(3):46-49,62
[38] Yingen Xing,Bing Fang.Extraction of Hand Gestures with Adaptive Skin Color Models and its Applications to Meeting Analysis[C]//The 8th IEEE Int Symp on Multimedia .San Diego,CA,2006:647-651
[39] Howe LW, Farrah W.Comparison of hand segmentation methodologies for hand gesture recognition[C]//2008 International Symposium on Information Technology. Kuala Lumpur, MAS,2008,2:1-7
[40]周航,阮秋琦,岳建海.基于肤色的CIELab空间的视觉窗口手势跟踪[J].兰州交通大学学报(自然科学版),2004,23(3):230-234
[41]姜威,陈援非,孔勇.一种在复杂背景彩色图像中划分手部图像的方法[J].山东大学学报(工学版).2003,33(4):410-412
[42]吕东辉,王滨.YCbCr空间中一种基于贝叶斯判决的肤色检测方法[J].中国图形图像学报,2006,11(1):47-52
[43]路凯,李小坚,周金祥.基于肤色和边缘轮廓检测的手势识别[J].北方工业大学学报,2006,18(3):212-215
[44] Lu S,Metaxas D,Samaras D,et al.Using multiple cues for hand tracking and model refinement[C]//Proc of IEEE CVPR’03,Madison,USA, 2003,2:443-450
[45]王西颖,张习文,戴国忠.一种面向实时交互的变形手势跟踪方法[J].软件学报, 2007,18(10):2423-2433
[46] Kristan M, Pers J,Kovacic S,Leonardis A.A local-motion-based probabilistic model for visual tracking[J]. Pattern Recognition, 2009,42(9):2160-2168
[47]何文媛,韩斌,徐之,等.基于粒子滤波和均值漂移的目标跟踪[J].计算机工程与应用,2008,44(11):61-64
[48]罗元,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,2009,26(3),1163-1165
[49] Hee-Sung Kim, Kurillo G, Bajcsy R.Hand Tracking and Motion Detection from the Sequence of Stereo Color Image Frames[C]//Proc of IEEE ICIT’08.Chengdu,CN, 2008:1-6
[50] Donoser M, Bischof H.Real Time Appearance Based Hand Tracking[C]//Proc of IEEE ICPR’08.Tampa, FL,2008:1-4
[51]王志堂,蔡淋波.隐马尔可夫模型(HMM)及其应用[J].湖南科技学院学报,2009,30(4):42-44
[52] Faundez-Zanuy M.On-line signature recognition based on VQ-DTW[J].Pattern Recognition.2007,40(3):981-992
[53] Weng C, Tseng C.A vision-Based hand motion parameter capturing for HCI[C]// Proc of IEEE ICALIP’08. Shanghai,CN,2008:1219-1224
[54] Yang M H,Ahuja N,Tabb M.Extraction of 2D motion trajectories and its application to hand gesture recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(8):1061-1074
[55] K Kim JH.An HMM-based threshold model approach for gesture recognition[J]. IEEE Trans on Pattern Analysis and Machine Intelligence,1999,21(10): 961-973
[56]陶霖密,彭振云,徐光枯.人体的肤色特征[J].软件学报, 2001,12(7):1032-1041
[57] Barron J,Beauchemin S S.Performance of optical flow techniques[J].International Journal of Computer Vision,1994,12(1):43-77
[58]段先华,吴小俊.联合光流技术和区域轮廓模型跟踪运动目标[J].江南大学学报, 2007,6(6):669-674
[59] IKushi Yoda,Katsuhiko Sakaue.Utilization of stereo disparity and optical flow information for the computer analysis of human interactions[J].Machine Vision and Applications.2003,13(4):185-193
[60] Matsuda M,Nonaka T.Correction of Optical Flow using Characteristic of Wrinkles on Palms[J].Consumer Electronics,2006,2(10):1-4
[61] Kalman,R E A New Approach to Linear Filtering and Prediction Problems[J]. Transaction of the ASME-Journal of Basic Engineering,1960,35-45
[62] Fukunaga K, Hostetler L.The estimation of the gradient of a density function,with applications in pattern recognition[J].IEEE Trans on Information Theory, 1975,21(1):32-40
[63] Cheng Y.Mean shift,mode seeking,and clustering[J].IEEE Trans on pattern analysis and machine intelligence,1995,17(8):790-799
[64]文志强,蔡自兴.Mean shift算法的收敛性分析[J].软件学报,2007,18(2): 205-212
[65]王晓卫,马晓军,周启煌.基于DESO的Mean Shift目标跟踪算法研究[J].控制与决策, 2009,24(2):212-216
[66]许海霞.一种分Mean shift目标跟踪算法[J].自动化学报,2009,35(4):401- 409
[67] Comaniciu D.Image segmentation using clustering with saddle point detection[C] //Proc of IEEE International Conference on Image Processing.New York,USA 2002,III:297-300
[68] Wua K,Yang M.Mean shift-based clustering[J].Pattern Recognition,2007,40(11): 3035-3052
[69] Comaniciu D, Ramesh V, Meer P. Real-time tracking of non-rigid objects using mean shift[C]//Proc of IEEE International Conference on Computer Vision and Pattern Recognition.Hilton Head,SC,USA,2000,2:142-149
[70] Comaniciu D, Ramesh V, Meer P.Kernel-Based object tracking[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2003,25(5):564-575
[71]彭宁嵩,杨杰,刘志,等.Mean-Shift跟踪算法中核函数窗宽的自动选取[J].软件学报,2005,16(9):1542-1550
[72]何小诚,黄凯.基于Mean Shift的自适应尺度变化跟踪算法研究[J].微电子学与计算机,2010,27(4):69-74
[73] Gorden N, Salmond D, Smith A. Novel approach to non-linear and non-Gaussian Bayesian state estimation[J]. Proc of Institute Electric Engineering,1993,140(2): 107-113
[74] Wang Z,Bovik A C,Sheikh H R,et al.Image quality assessment:from error visibility to structural similarity[J].IEEE Trans on Image Processing,2004,13(4): 600-612
[75] Loza A,Mihaylova L.Structural Similarity-Based Object Tracking in Video Sequences[C]//2006 9th Int Conf on Information Fusion, Florence,2006:1-6
[76]张笑微.结合颜色和结构信息的粒子滤波跟踪算法[J].光电工程,2008,35(10):1-5
[77] Jacek Czyz,Branko Ristic,Benoit Macq.A particle filter for joint detection and tracking of color objects[J].Image and Vision Computing,2007,25:1271-1281
[78] Ahmad T,Taylor C,Lanitis A,et al.Tracking and recognition of hand gesturesusing statistical shape models[J].Image Vision Computer,1997,15(5):345-352
[79] Stergiopoulou E, Papamarkos N.Hand gesture recognition using a neural network shape fitting technique[J].Engineering Applications of Artificial Intelligence, 2009,22(8):1141-1158
[80] Elmezain M, Al-Hamadi A, Appenrod J t,et al.A hidden markov model-based continuous gesture recognition system for hand motion trajectory[C]//Proc of IEEE ICPR’08. Tampa, FL,2008:1-4
[81] Reifinger S,Wallhoff F,Abla?meier M,et al,Static and dynamic hand-gesture recognition for augmented reality applications[C]//Proc of the Int Conf on Human-Computer Interaction.Beijing:Springer, July 2007: 728-737
[82] Alon J, Athitsos V, Sclaroff S.Accurate and efficient gesture spotting via pruning and subgesture reasoning[G]//LNCS 3766:Proc of Int Conf on Human-Computer Interaction, Berlin:Springer,2005:189-198
[83] Lee HK, Kim JH.An HMM-based threshold model approach for gesture recognition[J].IEEE Trans Pattern Anal.Mach.Intell,1999,21(10):961-973
[84] Barbic J, Pollard NS, Hodgins JK.Segmenting motion capture data into distinct behaviors[C]//Proc of Int Conf on Graphics Interface.2004:17-19
[85] Kendon A.Current issues in the study of gesture, in The Biological Foundations of Gestures:Motor and Semiotic Aspects,J-L Nespoulous,P Perron,and A R Lecours,Eds.Hillsdale,NJ,USA 1986:23-47
[86] F K H Quek.Toward a vision-based hand gesture inter-face[C]// Proc of Virtual Reality Software and Technology Conference(VRST’94), Singapore,1994:17-29
[87]顾立忠.基于表观的手势识别及人机交互研究[D].上海:上海交通大学2008.5
[88]王斌.一种基于多级弦长函数的傅立叶形状描述子[J].计算机学报2010,33(12):2387-2396
[89]胡同森,周维,蒋成成.一种基于DCT系数和Fourier描述子的人脸识别方法[J].计算机应用,2010,38(5):557-560,579
[90] Hu M K.Visual Pattern Recognition by Moment Invariant[J].IRE Trans Information Theory,1962,8 (2):179-187
[91] CHEN C C.Improved Moment Invariants for Shape Discrimination[J].Pattern Recognition,1993,26(5):683-686
[2]黄乔.视线跟踪技术与视线输入的人机系统研究[D].湖北:武汉理工大学,2008
[3] Alejandro Jaimes, Nicu Sebe.Multimodal human-computer interaction:A survey[J]. Computer Vision and Image Understanding 2007,108:116-134
[4]郭兴伟.基于视觉的手势识别算法研究[D].上海:上海海运学院,2003
[5] Enrico Bertini,Giuseppe Santucci.Automatic Interface Generation Through Interaction,Users,And Devices Modeling[J].Computer-Aided Design Of User Interfaces,2007,10:191-200
[6]吴巾一,周德龙.人脸识别方法综述[J].计算机应用研究,2009,26(9):3205-3209
[7] Md Hasanuzzamana, T Zhanga,V Ampornaramvetha,et al.Adaptive visual gesture recognition for human-robot interaction using a knowledge-based software platform[J].Robotics and Autonomous Systems,2007,55(8):643-657
[8] S Malassiotis,M G Strintzis.Real-time hand posture recognition using range data[J]. Image and Vision Computing,2008,26(7):1027-1037
[9]滕晓龙.用于人机交互的手势识别研究[D].上海:上海交通大学,2006
[10] Shunji Uchino, Norihiro Abe,Yoshihiro Tabuchi Hirokazu Taki,et al.VR interactive dialog system with verbal and nonverbal communication[J].Artif Life Robotics, 2009,13(2):512-516
[11] Lee C, Xu Y.Online interactive learning of gestures for human/robot interfaces[C] //Proc of IEEE Int Conf on Robotics and Automation.Minneapolis, MN,USA:IEEE, 1996,4:2982-2987
[12] Je H, Kim J, Kim D.Hand Gesture Recognition To Understand Musical Conducting Action[C]//The 16th IEEE Int Symp on Robot and Human Interactive Communication.Jeju:IEEE,2007:163-168
[13] Liya Ding,Aleix M.Martinez.Modeling and recognition of the linguistic components in American Sign Language[J].Image and Vision Computing,2009, 27(12):1826-1844
[14] Pavlovic V I,Sharma R,Huang T S.Visual Interpretation of Hand Gestures for Human-Computer Interaction:A Review[J].IEEE Transactions on Pattern Analysis
and Machine Intelligence,1997,19(7):677-695
[15]任海兵,祝远新,徐光佑等.基于视觉手势识别的研究-综述[J].电子学报, 2000,28(2):118-121
[16] Liang R-H.anduohyoung,M.A real-time Continuous AIPhabetic Sign Language to Speech Conversion VR System[J].Computer Graphics Forum,1995,14(3):C67-C77
[17]吴江琴,高文,等.中国手语手势词识别的一种快速方法[J].高技术通讯,2001,11(6):23-27
[18]吴江琴,高文.基于DGMM的中国手语识别系统[J].计算机研究与发展,2000,37(5):551-558
[19] Wang R, Popovic J.Real-Time Hand-Tracking with a Color Glove. ACM Trans on Graphics[J], 2009,28(3):1-8
[20] Starner T, Weaver J, Pentland A. Real-time American Sign Language Recognition Using Desk and Wearable Computer Based Video[J].IEEE Transactions on Pattern Analysis and Machine Intelligence(PAMD),1998,20(12):1371-1375
[21]周宇,陈熙霖,赵德斌,等.基于数据生成的手语识别自适应方法[J].高技术通讯,2009,19(12):1258-1264
[22]李勇,高文,姚鸿勋.基于颜色手套的中国手指语字母的动静态识别[J].计算机工程与应用,2002, 38(17):55-58
[23]张良国,高文,陈熙霖,等.面向中等词汇量的中国手语视觉识别系统[J].计算机研究与发展,2006,43(3):476-482
[24]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[J].软件学报,2008,19(9):2302-2312
[25]任海兵,祝远新,徐光祐,林学訚,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
[26] Yun Liu,Zhijie Gan,Yu Sun.Static Hand Gesture Recognition and its Application based on Support Vector Machines[C]// Proc of the Ninth ACIS Int Conf on Software Engineering,Artificial Intelligence,Networking,and Parallel/Distributed Computing. Phuket, 2008:517-521
[27] Priyal S P, Bora P K.A study on static hand gesture recognition using moments[C] //Proc of IEEE SPCOM’10.Bangalore:IEEE,2010:1-5
[28] Aditya Ramamoorthya, Namrata Vaswania.Recognition of dynamic hand gestures [J].Pattern Recognition, 2003,36:2069–2081
[29] Darrell T J, Essa I A,Pentland A P. Task-specific gesture analysis in real-time using interpolated views[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1996,18(12):1236-1242
[30]冯志全.运动人手的三维跟踪方法研究[D].山东:山东大学,2006
[31] Bobick A F,Davis J W. An Appearance-Based Representation of Action[C]//Proc of the 13th International Conference on Pattern Recognition.Vienna, Austria,1996,1: 307-312
[32] Cui Y, Weng J. Hand sign recognition from intensity image sequence with complex backgrounds[C]//Proc of the 2th Int Conf on Automatic Face and Gesture Recognition. Killington,VT,USA,1996:259-264
[33]刘俊梅,阮秋琦.一种复杂背景下的手势分割新方法[J].北京电子科技学院学报, 2006,14(2):23-27
[34]齐苏敏,黄贤武,刘家盛.利用基于颜色的自适应形状模型实现手势跟踪[J].计算机应用研究,2008,25(2):485-487,474
[35]樊亚春,周明全,耿国华.消除光照影响的背景减除算法[J].中国图象图形学报,2009,14(7):1413-1417
[36]王小华,王波.一种有效的动态背景更新方法[J].杭州电子科技大学学报,2009,29(3):56-59
[37]刘昌盛,厉树忠,赵姝颖,等.一种复杂背景下的手部图像分割方法[J].河北科技师范学院学报,2007, 21(3):46-49,62
[38] Yingen Xing,Bing Fang.Extraction of Hand Gestures with Adaptive Skin Color Models and its Applications to Meeting Analysis[C]//The 8th IEEE Int Symp on Multimedia .San Diego,CA,2006:647-651
[39] Howe LW, Farrah W.Comparison of hand segmentation methodologies for hand gesture recognition[C]//2008 International Symposium on Information Technology. Kuala Lumpur, MAS,2008,2:1-7
[40]周航,阮秋琦,岳建海.基于肤色的CIELab空间的视觉窗口手势跟踪[J].兰州交通大学学报(自然科学版),2004,23(3):230-234
[41]姜威,陈援非,孔勇.一种在复杂背景彩色图像中划分手部图像的方法[J].山东大学学报(工学版).2003,33(4):410-412
[42]吕东辉,王滨.YCbCr空间中一种基于贝叶斯判决的肤色检测方法[J].中国图形图像学报,2006,11(1):47-52
[43]路凯,李小坚,周金祥.基于肤色和边缘轮廓检测的手势识别[J].北方工业大学学报,2006,18(3):212-215
[44] Lu S,Metaxas D,Samaras D,et al.Using multiple cues for hand tracking and model refinement[C]//Proc of IEEE CVPR’03,Madison,USA, 2003,2:443-450
[45]王西颖,张习文,戴国忠.一种面向实时交互的变形手势跟踪方法[J].软件学报, 2007,18(10):2423-2433
[46] Kristan M, Pers J,Kovacic S,Leonardis A.A local-motion-based probabilistic model for visual tracking[J]. Pattern Recognition, 2009,42(9):2160-2168
[47]何文媛,韩斌,徐之,等.基于粒子滤波和均值漂移的目标跟踪[J].计算机工程与应用,2008,44(11):61-64
[48]罗元,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,2009,26(3),1163-1165
[49] Hee-Sung Kim, Kurillo G, Bajcsy R.Hand Tracking and Motion Detection from the Sequence of Stereo Color Image Frames[C]//Proc of IEEE ICIT’08.Chengdu,CN, 2008:1-6
[50] Donoser M, Bischof H.Real Time Appearance Based Hand Tracking[C]//Proc of IEEE ICPR’08.Tampa, FL,2008:1-4
[51]王志堂,蔡淋波.隐马尔可夫模型(HMM)及其应用[J].湖南科技学院学报,2009,30(4):42-44
[52] Faundez-Zanuy M.On-line signature recognition based on VQ-DTW[J].Pattern Recognition.2007,40(3):981-992
[53] Weng C, Tseng C.A vision-Based hand motion parameter capturing for HCI[C]// Proc of IEEE ICALIP’08. Shanghai,CN,2008:1219-1224
[54] Yang M H,Ahuja N,Tabb M.Extraction of 2D motion trajectories and its application to hand gesture recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(8):1061-1074
[55] K Kim JH.An HMM-based threshold model approach for gesture recognition[J]. IEEE Trans on Pattern Analysis and Machine Intelligence,1999,21(10): 961-973
[56]陶霖密,彭振云,徐光枯.人体的肤色特征[J].软件学报, 2001,12(7):1032-1041
[57] Barron J,Beauchemin S S.Performance of optical flow techniques[J].International Journal of Computer Vision,1994,12(1):43-77
[58]段先华,吴小俊.联合光流技术和区域轮廓模型跟踪运动目标[J].江南大学学报, 2007,6(6):669-674
[59] IKushi Yoda,Katsuhiko Sakaue.Utilization of stereo disparity and optical flow information for the computer analysis of human interactions[J].Machine Vision and Applications.2003,13(4):185-193
[60] Matsuda M,Nonaka T.Correction of Optical Flow using Characteristic of Wrinkles on Palms[J].Consumer Electronics,2006,2(10):1-4
[61] Kalman,R E A New Approach to Linear Filtering and Prediction Problems[J]. Transaction of the ASME-Journal of Basic Engineering,1960,35-45
[62] Fukunaga K, Hostetler L.The estimation of the gradient of a density function,with applications in pattern recognition[J].IEEE Trans on Information Theory, 1975,21(1):32-40
[63] Cheng Y.Mean shift,mode seeking,and clustering[J].IEEE Trans on pattern analysis and machine intelligence,1995,17(8):790-799
[64]文志强,蔡自兴.Mean shift算法的收敛性分析[J].软件学报,2007,18(2): 205-212
[65]王晓卫,马晓军,周启煌.基于DESO的Mean Shift目标跟踪算法研究[J].控制与决策, 2009,24(2):212-216
[66]许海霞.一种分Mean shift目标跟踪算法[J].自动化学报,2009,35(4):401- 409
[67] Comaniciu D.Image segmentation using clustering with saddle point detection[C] //Proc of IEEE International Conference on Image Processing.New York,USA 2002,III:297-300
[68] Wua K,Yang M.Mean shift-based clustering[J].Pattern Recognition,2007,40(11): 3035-3052
[69] Comaniciu D, Ramesh V, Meer P. Real-time tracking of non-rigid objects using mean shift[C]//Proc of IEEE International Conference on Computer Vision and Pattern Recognition.Hilton Head,SC,USA,2000,2:142-149
[70] Comaniciu D, Ramesh V, Meer P.Kernel-Based object tracking[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2003,25(5):564-575
[71]彭宁嵩,杨杰,刘志,等.Mean-Shift跟踪算法中核函数窗宽的自动选取[J].软件学报,2005,16(9):1542-1550
[72]何小诚,黄凯.基于Mean Shift的自适应尺度变化跟踪算法研究[J].微电子学与计算机,2010,27(4):69-74
[73] Gorden N, Salmond D, Smith A. Novel approach to non-linear and non-Gaussian Bayesian state estimation[J]. Proc of Institute Electric Engineering,1993,140(2): 107-113
[74] Wang Z,Bovik A C,Sheikh H R,et al.Image quality assessment:from error visibility to structural similarity[J].IEEE Trans on Image Processing,2004,13(4): 600-612
[75] Loza A,Mihaylova L.Structural Similarity-Based Object Tracking in Video Sequences[C]//2006 9th Int Conf on Information Fusion, Florence,2006:1-6
[76]张笑微.结合颜色和结构信息的粒子滤波跟踪算法[J].光电工程,2008,35(10):1-5
[77] Jacek Czyz,Branko Ristic,Benoit Macq.A particle filter for joint detection and tracking of color objects[J].Image and Vision Computing,2007,25:1271-1281
[78] Ahmad T,Taylor C,Lanitis A,et al.Tracking and recognition of hand gesturesusing statistical shape models[J].Image Vision Computer,1997,15(5):345-352
[79] Stergiopoulou E, Papamarkos N.Hand gesture recognition using a neural network shape fitting technique[J].Engineering Applications of Artificial Intelligence, 2009,22(8):1141-1158
[80] Elmezain M, Al-Hamadi A, Appenrod J t,et al.A hidden markov model-based continuous gesture recognition system for hand motion trajectory[C]//Proc of IEEE ICPR’08. Tampa, FL,2008:1-4
[81] Reifinger S,Wallhoff F,Abla?meier M,et al,Static and dynamic hand-gesture recognition for augmented reality applications[C]//Proc of the Int Conf on Human-Computer Interaction.Beijing:Springer, July 2007: 728-737
[82] Alon J, Athitsos V, Sclaroff S.Accurate and efficient gesture spotting via pruning and subgesture reasoning[G]//LNCS 3766:Proc of Int Conf on Human-Computer Interaction, Berlin:Springer,2005:189-198
[83] Lee HK, Kim JH.An HMM-based threshold model approach for gesture recognition[J].IEEE Trans Pattern Anal.Mach.Intell,1999,21(10):961-973
[84] Barbic J, Pollard NS, Hodgins JK.Segmenting motion capture data into distinct behaviors[C]//Proc of Int Conf on Graphics Interface.2004:17-19
[85] Kendon A.Current issues in the study of gesture, in The Biological Foundations of Gestures:Motor and Semiotic Aspects,J-L Nespoulous,P Perron,and A R Lecours,Eds.Hillsdale,NJ,USA 1986:23-47
[86] F K H Quek.Toward a vision-based hand gesture inter-face[C]// Proc of Virtual Reality Software and Technology Conference(VRST’94), Singapore,1994:17-29
[87]顾立忠.基于表观的手势识别及人机交互研究[D].上海:上海交通大学2008.5
[88]王斌.一种基于多级弦长函数的傅立叶形状描述子[J].计算机学报2010,33(12):2387-2396
[89]胡同森,周维,蒋成成.一种基于DCT系数和Fourier描述子的人脸识别方法[J].计算机应用,2010,38(5):557-560,579
[90] Hu M K.Visual Pattern Recognition by Moment Invariant[J].IRE Trans Information Theory,1962,8 (2):179-187
[91] CHEN C C.Improved Moment Invariants for Shape Discrimination[J].Pattern Recognition,1993,26(5):683-686