Generalized Model-Based Human Motion Recognition with Body Partition Index Maps

被引:10
作者
Deng, Liqun [1 ,2 ,3 ]
Leung, Howard [1 ,2 ]
Gu, Naijie [2 ,3 ]
Yang, Yang [1 ,2 ,3 ]
机构
[1] City Univ Hong Kong, Dept Comp Sci, Hong Kong, Hong Kong, Peoples R China
[2] USTC CityU Joint Res Ctr, Suzhou, Peoples R China
[3] Univ Sci & Technol China, Dept Comp Sci & Technol, Hefei, Peoples R China
关键词
motion capture; motion pattern; generalized model; content-based indexing; real-time recognition; CLASSIFICATION; RETRIEVAL;
D O I
10.1111/j.1467-8659.2011.02095.x
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Content-based human motion analysis has captured extensive concerns of researchers from the domains of computer animation, human-machine interaction, entertainment, etc. However, it is a non-trivial task due to the spatial and temporal variations in the motion data. In this paper, we propose a generalized model (GM)-based approach to model the variations and accurately recognize motion patterns. We partition the human character model into five parts, and extract the features of the submotions of each specific body part using clustering techniques. These features from the training trials in each class are combined to build the GM. We propose a new penalty based similarity measure for DTW to be used with the GMs for isolated motion recognition. On the other hand, from the GMs five body partition index maps are constructed and used for matching together with a flexible end point detection scheme during continuous motion recognition. In the experiments, we examine the effectiveness and efficiency of the approach in both isolated motion and continuous motion recognition. The results show that our proposed method has good performance compared with other state-of-the-art methods in recognition accuracy and processing speed.
引用
收藏
页码:202 / 215
页数:14
相关论文
共 27 条
  • [1] Alon J, 2005, LECT NOTES COMPUT SC, V3766, P189, DOI 10.1007/11573425_19
  • [2] [Anonymous], 2007, Computer Graphics Technical Report CG-2007-2
  • [3] Motion synthesis from annotations
    Arikan, O
    Forsyth, DA
    O'Brien, JF
    [J]. ACM TRANSACTIONS ON GRAPHICS, 2003, 22 (03): : 402 - 408
  • [4] A survey of longest common subsequence algorithms
    Bergroth, L
    Hakonen, H
    Raita, T
    [J]. SPIRE 2000: SEVENTH INTERNATIONAL SYMPOSIUM ON STRING PROCESSING AND INFORMATION RETRIEVAL - PROCEEDINGS, 2000, : 39 - 48
  • [5] Performance animation from low-dimensional control signals
    Chai, JX
    Hodgins, JK
    [J]. ACM TRANSACTIONS ON GRAPHICS, 2005, 24 (03): : 686 - 696
  • [6] Chang C.-C., LIBSVM: a Library for Support Vector Machines
  • [7] Content-based retrieval for human motion data
    Chiu, CY
    Chao, SP
    Wu, MY
    Yang, SN
    Lin, HC
    [J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2004, 15 (03) : 446 - 466
  • [8] Deng LQ, 2010, LECT NOTES COMPUT SC, V6184, P250, DOI 10.1007/978-3-642-14246-8_26
  • [9] Forbes K., 2005, P ACM SIGGRAPH EUR S, P67, DOI [10.1145/1073368.1073377, DOI 10.1145/1073368.1073377]
  • [10] Compression of Human Motion Capture Data Using Motion Pattern Indexing
    Gu, Qin
    Peng, Jingliang
    Deng, Zhigang
    [J]. COMPUTER GRAPHICS FORUM, 2009, 28 (01) : 1 - 12