Subspace analysis methods plus motion history image for human action recognition

Chunhua Du; Qiang Wu; Jie Yang; Xiangjian He; Yan Chen

doi:10.1109/DICTA.2008.20

Subspace analysis methods plus motion history image for human action recognition

Chunhua Du, Qiang Wu, Jie Yang, Xiangjian He, Yan Chen

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

2 Citations (Scopus)

Abstract

This paper proposes a new human action recognition method which deals with recognition task in a quite different way when compared with traditional methods which use sequence matching scheme. Our method compresses a sequence of an action into a Motion History Image (MHI) on which low-dimensional features are extracted using subspace analysis methods. Unlike other methods which use a sequence consisting of several frames for recognition, our method uses only a MHI per action sequence for recognition. Obviously, our method avoids the complexity as well as the large computation in sequence matching based methods. Encouraging experimental results on a widely used database demonstrate the effectiveness of the proposed method.

Original language	English
Title of host publication	Proceedings - Digital Image Computing
Subtitle of host publication	Techniques and Applications, DICTA 2008
Publisher	IEEE Computer Society
Pages	606-611
Number of pages	6
ISBN (Print)	9780769534565
DOIs	https://doi.org/10.1109/DICTA.2008.20
Publication status	Published - 2008
Externally published	Yes
Event	Digital Image Computing: Techniques and Applications, DICTA 2008 - Canberra, ACT, Australia Duration: 1 Dec 2008 → 3 Dec 2008

Publication series

Name	Proceedings - Digital Image Computing: Techniques and Applications, DICTA 2008

Conference

Conference	Digital Image Computing: Techniques and Applications, DICTA 2008
Country/Territory	Australia
City	Canberra, ACT
Period	1/12/08 → 3/12/08

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Computer Science Applications

Access to Document

10.1109/DICTA.2008.20

Cite this

Du, C., Wu, Q., Yang, J., He, X., & Chen, Y. (2008). Subspace analysis methods plus motion history image for human action recognition. In Proceedings - Digital Image Computing: Techniques and Applications, DICTA 2008 (pp. 606-611). Article 4700078 (Proceedings - Digital Image Computing: Techniques and Applications, DICTA 2008). IEEE Computer Society. https://doi.org/10.1109/DICTA.2008.20

@inproceedings{51b81baa829945238e61969da994883f,

title = "Subspace analysis methods plus motion history image for human action recognition",

abstract = "This paper proposes a new human action recognition method which deals with recognition task in a quite different way when compared with traditional methods which use sequence matching scheme. Our method compresses a sequence of an action into a Motion History Image (MHI) on which low-dimensional features are extracted using subspace analysis methods. Unlike other methods which use a sequence consisting of several frames for recognition, our method uses only a MHI per action sequence for recognition. Obviously, our method avoids the complexity as well as the large computation in sequence matching based methods. Encouraging experimental results on a widely used database demonstrate the effectiveness of the proposed method.",

author = "Chunhua Du and Qiang Wu and Jie Yang and Xiangjian He and Yan Chen",

year = "2008",

doi = "10.1109/DICTA.2008.20",

language = "English",

isbn = "9780769534565",

series = "Proceedings - Digital Image Computing: Techniques and Applications, DICTA 2008",

publisher = "IEEE Computer Society",

pages = "606--611",

booktitle = "Proceedings - Digital Image Computing",

address = "United States",

note = "Digital Image Computing: Techniques and Applications, DICTA 2008 ; Conference date: 01-12-2008 Through 03-12-2008",

}

Du, C, Wu, Q, Yang, J, He, X & Chen, Y 2008, Subspace analysis methods plus motion history image for human action recognition. in Proceedings - Digital Image Computing: Techniques and Applications, DICTA 2008., 4700078, Proceedings - Digital Image Computing: Techniques and Applications, DICTA 2008, IEEE Computer Society, pp. 606-611, Digital Image Computing: Techniques and Applications, DICTA 2008, Canberra, ACT, Australia, 1/12/08. https://doi.org/10.1109/DICTA.2008.20

Subspace analysis methods plus motion history image for human action recognition. / Du, Chunhua; Wu, Qiang; Yang, Jie et al.
Proceedings - Digital Image Computing: Techniques and Applications, DICTA 2008. IEEE Computer Society, 2008. p. 606-611 4700078 (Proceedings - Digital Image Computing: Techniques and Applications, DICTA 2008).

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

TY - GEN

T1 - Subspace analysis methods plus motion history image for human action recognition

AU - Du, Chunhua

AU - Wu, Qiang

AU - Yang, Jie

AU - He, Xiangjian

AU - Chen, Yan

PY - 2008

Y1 - 2008

N2 - This paper proposes a new human action recognition method which deals with recognition task in a quite different way when compared with traditional methods which use sequence matching scheme. Our method compresses a sequence of an action into a Motion History Image (MHI) on which low-dimensional features are extracted using subspace analysis methods. Unlike other methods which use a sequence consisting of several frames for recognition, our method uses only a MHI per action sequence for recognition. Obviously, our method avoids the complexity as well as the large computation in sequence matching based methods. Encouraging experimental results on a widely used database demonstrate the effectiveness of the proposed method.

AB - This paper proposes a new human action recognition method which deals with recognition task in a quite different way when compared with traditional methods which use sequence matching scheme. Our method compresses a sequence of an action into a Motion History Image (MHI) on which low-dimensional features are extracted using subspace analysis methods. Unlike other methods which use a sequence consisting of several frames for recognition, our method uses only a MHI per action sequence for recognition. Obviously, our method avoids the complexity as well as the large computation in sequence matching based methods. Encouraging experimental results on a widely used database demonstrate the effectiveness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=67549096784&partnerID=8YFLogxK

U2 - 10.1109/DICTA.2008.20

DO - 10.1109/DICTA.2008.20

M3 - Conference contribution

AN - SCOPUS:67549096784

SN - 9780769534565

T3 - Proceedings - Digital Image Computing: Techniques and Applications, DICTA 2008

SP - 606

EP - 611

BT - Proceedings - Digital Image Computing

PB - IEEE Computer Society

T2 - Digital Image Computing: Techniques and Applications, DICTA 2008

Y2 - 1 December 2008 through 3 December 2008

ER -

Subspace analysis methods plus motion history image for human action recognition

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this