Decomposition in hidden Markov models for activity recognition

被引:0
作者
Zhang, Weidong [1 ]
Chen, Feng [1 ]
Xu, Wenli [1 ]
Cao, Zisheng [1 ]
机构
[1] Tsinghua Univ, Dept Automat, Beijing 100084, Peoples R China
来源
MULTIMEDIA CONTENT ANALYSIS AND MINING, PROCEEDINGS | 2007年 / 4577卷
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Dynamic probabilistic networks have been widely used in activity recognition. However, few models are competent for long-term complex activities involving multi-person interactions. Based on the study of activity characteristics, this paper proposes a decomposed hidden Markov model (DHMM) to capture the structures of activity both in time and space. The model combines spatial decomposition and hierarchical abstraction to reduce the complexity of state space as well as the number of parameters greatly, with consequent computational benefits in efficiency and accuracy. Experiments on two-person interactions and individual activities demonstrate that DHMMs are more powerful than Coupled HMMs and Hierarchical HMMs.
引用
收藏
页码:232 / +
页数:3
相关论文
共 50 条
[31]   Object trajectory-based activity classification and recognition using hidden Markov models [J].
Bashir, Faisal I. ;
Khokhar, Ashfaq A. ;
Schonfeld, Dan .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2007, 16 (07) :1912-1919
[32]   Hierarchical multi-channel hidden semi Markov graphical models for activity recognition [J].
Natarajan, Pradeep ;
Nevatia, Ramakant .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2013, 117 (10) :1329-1344
[33]   Large margin hidden Markov models for speech recognition [J].
Jiang, Hui ;
Li, Xinwei ;
Liu, Chaojun .
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2006, 14 (05) :1584-1595
[34]   Using Hidden Markov Models for paper currency recognition [J].
Hassanpour, Hamid ;
Farahabadi, Payam M. .
EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (06) :10105-10111
[35]   Automatic speech recognition using hidden Markov models [J].
Botros, N.M. ;
Teh, C.K. .
Microcomputer Applications, 1994, 13 (01) :6-12
[36]   Object recognition of robot based on hidden Markov models [J].
Cui, BM ;
von Seelen, W .
2000 5TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS I-III, 2000, :851-854
[37]   Skull recognition based on Embedded Hidden Markov models [J].
Zhang, Yanfang ;
Xu, Saicong ;
Sun, Nongliang .
2008 7TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-23, 2008, :1153-1158
[38]   Squat Movement Recognition Using Hidden Markov Models [J].
Rungsawasdisap, Nantana ;
Yimit, Adiljan ;
Lu, Xin ;
Hagihara, Yoshihiro .
2018 INTERNATIONAL WORKSHOP ON ADVANCED IMAGE TECHNOLOGY (IWAIT), 2018,
[39]   Automatic Phoneme Recognition with Segmental Hidden Markov Models [J].
Baghdasaryan, Areg G. ;
Beex, A. A. .
2011 CONFERENCE RECORD OF THE FORTY-FIFTH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS (ASILOMAR), 2011, :569-574
[40]   Automatic keyword recognition using Hidden Markov models [J].
Kuo, Shyh-Shiaw ;
Agazzi, Oscar E. .
Journal of Visual Communication and Image Representation, 1994, 5 (03) :265-272