人手粒子滤波跟踪器的研究与设计
作者:
基金项目:

Supported by the National Natural Science Foundation of China under Grant No.60773109 (国家自然科学基金); the Natural Science Foundation of Shandong Province of China under Grant No.Y2007G39 (山东省自然科学基金); the Key Project of Natural Science Foundation of Shandong Province of China under Grant No.2006G03 (山东省自然科学重点基金); the Natural Science Foundation of Shandong Province of China for Distinguished Young Scholars under Grant No.JQ200820 (山东省自然科学杰出青年基金); the Science and Technology Plan of Shandong Province Education Department of China under Grant No.J07YJ18 (山东省教育厅科技计划); the Ph.D. Scientific Research Foundation of University of Ji'nan of China under Grant No.XBS0705 (济南大学博士科研启动基金)

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [17]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    提出一种粒子滤波方法中粒子样本采样方法,旨在用较少的粒子数描述高维状态变量的后验概率分布.首先,研究特定人机交互条件下操作者的认知心理特点和人手运动特点,在此基础上提出了状态变量微观结构的基本概念;然后,进一步探讨描述微观结构的一般方法;最后,提出了基于状态变量微观结构的粒子采样方法和改进的粒子滤波跟踪算法.状态变量的微观结构为采样算法的设计提供了一种统一、高效的数学模型,以此为基础的采样算法可以有效避免对质量比较差的粒子样本进行大量采样.为了验证算法的有效性和性能,进行了大量实验,结果表明,与传统的粒子滤波方法相比,采用少量的粒子样本就可以达到较高的跟踪精度.

    Abstract:

    Aiming at describing post probability distribution of the state with high dimensionality by using of a small amount of particles, a sampling in particle filtering for human hand 3D tracking is put forward in this paper. First of all, with the specific human-computer conditions, both cognitive psychology features of operators and motion features of the operators' hands are studied, upon which a novel concept, microstructure of state variable, is proposed. Then, a general method to describe the microstructure of state variable is further discussed. At last, a sampling algorithm based on the microstructure of state variable is put forward. The microstructure of state variable provide an unite and efficient mathematic model upon which the sampling algorithm may avoid sampling mass particles with poor quality. In order to validate validity and performance of sampling algorithm, a great deal of experiments are completed, and just fewer particles, compared with conventional particle filtering, may achieve better tracking precision.

    参考文献
    [1] Rehg JM, Kanade T. Visual tracking of high DOF articulated structures: An application to human tracking. In: Eklundh JO, ed. Proc. of the 3rd European Conf. on Computer Vision, Vol.801. Heidelberg: Springer-Verlag, 1994. 35(46.
    [2] Chen R, Liu GY, Zhao GY, Zhang J, Li H. 3D Human motion tracking based on sequential Monte Carlo method. Journal of Computer-Aided Design & Computer Graphics, 2005,17(1):85(92 (in Chinese with English abstract).
    [3] MacCormick J, Isard M. Partitioned sampling, articulated objects, and interface-quality hand tracking. In: Vernon D, ed. Proc. of the 6th European Conf. on Computer Vision, Vol.2. LNCS 4247, Heidelberg: Springer-Verlag, 2000. 13(19.
    [4] Deutscher J, Davidson A, Reid I. Automatic articulated partitioning of high dimensional search spaces associated with articulated body motion capture. In: Proc. of the Int'l Conf. on Computer Vision and Pattern Recognition, Vol.2. New York: IEEE Computer Society Press, 2001. 669(676.
    [5] Wu Y, Huang TS. Capturing articulated human hand motion: A divide-and-conquer approach. In: Zucker S, ed. Proc. of the 7th IEEE Int'l Conf. on Computer Vision. New York: IEEE Computer Society Press, 1999. 606(611.
    [6] Zhou HN, Huang TS. Tracking articulated hand motion with eigen dynamics analysis. In: Proc. of the 9th IEEE Int'l Conf. on Computer Vision. New York: IEEE Computer Society Press, 2003. 1102(1109.
    [7] Wachs J, Kartoun U, Edan Y, Stem H. Real-Time hand gesture telerobotic system using the fuzzy c-means clustering algorithm. In: Jamshidi M, ed. World Automation Congress (WAC). Albuquerque: TSI Press, 2002. 403(410.
    [8] Rehg JM, Kanade T. Digiteyes: Vision-Based human hand tracking. Technical Report, CMU-CS-93-220, School of Computer Science, Carnegie Mellon University, 1993.
    [9] Pan CH, Ma SD. Region-Based 3D motion tracking of hand. Journal of Image and Graphics, 2003,8(10):1205(1210 (in Chinese with English abstract).
    [10] Cui JS. Studies on three-dimensional model based posture estimation and tracking of articulated objects [Ph.D. Thesis]. Beijing: Tsinghua University, 2004 (in Chinese with English abstract).
    [11] Feng ZQ, Yang B, Chen YH, Zheng YW, Li Y, Wang ZH. Research on sampling methods in particle filtering based upon microstructure of state variable. Lecture Notes in Computer Science, 2008,5226:251(257.
    [12] Feng ZQ, Yang B, Li Y, Wang ZH, Zheng YW. Research on human hand tracking aiming at improving its accurateness. Journal of Computer Research and Development, 2008,45(7):1239(1248 (in Chinese with English abstract).
    [13] Gordon N, Salmond DJ, Smith AFM. Novel approach to nonlinear and non-Gaussian Bayesian state estimation. IEE Proc.-F, 1993,140(2):107(113. 附中文参考文献:
    [2] 陈睿,刘国翌,赵国英,张俊,李华.基于序列蒙特卡罗方法的3D人体运动跟踪.计算机辅助设计与图形学学报,2005,17(1):85(92.
    [9] 潘春洪,马颂德.基于区域的手指三维运动跟踪.中国图像图形学报,2003,8(10):1205(1210.
    [10] 崔锦实.基于三维模型的关节式物体姿态估计与跟踪方法研究[博士学位论文].北京:清华大学,2004.
    [12] 冯志全,杨波,李毅,王中华,郑艳伟.以改善精度为目标的人手跟踪方法研究.计算机研究与发展,2008,45(7):1239(1248.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

冯志全,杨 波,郑艳伟,唐好魁,徐 涛,李 毅.人手粒子滤波跟踪器的研究与设计.软件学报,2008,19(zk):87-95

复制
分享
文章指标
  • 点击次数:3585
  • 下载次数: 6076
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2008-05-01
  • 最后修改日期:2008-11-25
文章二维码
您是第19793870位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号