SVM-based state transition framework for dynamical human behavior identification

Chen Yu Chen; Jia Ching Wang; Jhing Fa Wang; Li Fang Shieh

doi:10.1109/ICASSP.2009.4959988

SVM-based state transition framework for dynamical human behavior identification

Chen Yu Chen, Jia Ching Wang, Jhing Fa Wang, Li Fang Shieh

Department of Computer Science and Information Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

This investigation proposes an SVM-based state transition framework (named as STSVM) to provide better performance of discriminability for human behavior identification. The STSVM consists of several state support vector machines (SSVM) and a state transition probability model (STPM). The intra-structure information and inter- structure information of a human activity are analyzed and correlated by the SSVM and STPM, respectively. The integration of the SSVM and the STPM effectively provides human behavior understanding. With a database consisting of five kinds of human behaviors: raising hand, standing up, squatting down, falling down, and sitting, the proposed algorithm has been demonstrated with a significant recognition rate of 88.6%.

Original language	English
Title of host publication	2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009
Pages	1933-1936
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2009.4959988
State	Published - 2009
Event	2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009 - Taipei, Taiwan Duration: 19 Apr 2009 → 24 Apr 2009

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)	1520-6149

Conference

Conference	2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009
Country/Territory	Taiwan
City	Taipei
Period	19/04/09 → 24/04/09

Keywords

Image processing
Pattern recognition
User interface human factors

Access to Document

10.1109/ICASSP.2009.4959988

Cite this

Chen, C. Y., Wang, J. C., Wang, J. F., & Shieh, L. F. (2009). SVM-based state transition framework for dynamical human behavior identification. In 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009 (pp. 1933-1936). Article 4959988 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2009.4959988

@inproceedings{22b2fbf31ac644a3b04eb7709b67b322,

title = "SVM-based state transition framework for dynamical human behavior identification",

abstract = "This investigation proposes an SVM-based state transition framework (named as STSVM) to provide better performance of discriminability for human behavior identification. The STSVM consists of several state support vector machines (SSVM) and a state transition probability model (STPM). The intra-structure information and inter- structure information of a human activity are analyzed and correlated by the SSVM and STPM, respectively. The integration of the SSVM and the STPM effectively provides human behavior understanding. With a database consisting of five kinds of human behaviors: raising hand, standing up, squatting down, falling down, and sitting, the proposed algorithm has been demonstrated with a significant recognition rate of 88.6%.",

keywords = "Image processing, Pattern recognition, User interface human factors",

author = "Chen, {Chen Yu} and Wang, {Jia Ching} and Wang, {Jhing Fa} and Shieh, {Li Fang}",

year = "2009",

doi = "10.1109/ICASSP.2009.4959988",

language = "???core.languages.en_GB???",

isbn = "9781424423545",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

pages = "1933--1936",

booktitle = "2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009",

note = "2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009 ; Conference date: 19-04-2009 Through 24-04-2009",

}

Chen, CY, Wang, JC, Wang, JF & Shieh, LF 2009, SVM-based state transition framework for dynamical human behavior identification. in 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009., 4959988, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 1933-1936, 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009, Taipei, Taiwan, 19/04/09. https://doi.org/10.1109/ICASSP.2009.4959988

SVM-based state transition framework for dynamical human behavior identification. / Chen, Chen Yu; Wang, Jia Ching; Wang, Jhing Fa et al.
2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009. 2009. p. 1933-1936 4959988 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - SVM-based state transition framework for dynamical human behavior identification

AU - Chen, Chen Yu

AU - Wang, Jia Ching

AU - Wang, Jhing Fa

AU - Shieh, Li Fang

PY - 2009

Y1 - 2009

N2 - This investigation proposes an SVM-based state transition framework (named as STSVM) to provide better performance of discriminability for human behavior identification. The STSVM consists of several state support vector machines (SSVM) and a state transition probability model (STPM). The intra-structure information and inter- structure information of a human activity are analyzed and correlated by the SSVM and STPM, respectively. The integration of the SSVM and the STPM effectively provides human behavior understanding. With a database consisting of five kinds of human behaviors: raising hand, standing up, squatting down, falling down, and sitting, the proposed algorithm has been demonstrated with a significant recognition rate of 88.6%.

AB - This investigation proposes an SVM-based state transition framework (named as STSVM) to provide better performance of discriminability for human behavior identification. The STSVM consists of several state support vector machines (SSVM) and a state transition probability model (STPM). The intra-structure information and inter- structure information of a human activity are analyzed and correlated by the SSVM and STPM, respectively. The integration of the SSVM and the STPM effectively provides human behavior understanding. With a database consisting of five kinds of human behaviors: raising hand, standing up, squatting down, falling down, and sitting, the proposed algorithm has been demonstrated with a significant recognition rate of 88.6%.

KW - Image processing

KW - Pattern recognition

KW - User interface human factors

UR - http://www.scopus.com/inward/record.url?scp=70349202160&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2009.4959988

DO - 10.1109/ICASSP.2009.4959988

M3 - 會議論文篇章

AN - SCOPUS:70349202160

SN - 9781424423545

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 1933

EP - 1936

BT - 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009

T2 - 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009

Y2 - 19 April 2009 through 24 April 2009

ER -

Chen CY, Wang JC, Wang JF, Shieh LF. SVM-based state transition framework for dynamical human behavior identification. In 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009. 2009. p. 1933-1936. 4959988. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2009.4959988

SVM-based state transition framework for dynamical human behavior identification

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this