An adaptive dictionary learning approach for modeling dynamical textures

Xian Wei; Hao Shen; Martin Kleinsteuber

doi:10.1109/ICASSP.2014.6854265

An adaptive dictionary learning approach for modeling dynamical textures

Xian Wei, Hao Shen, Martin Kleinsteuber

Technical University of Munich

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

10 Scopus citations

Abstract

Video representation is an important and challenging task in the computer vision community. In this paper, we assume that image frames of a moving scene can be modeled as a Markov random process. We propose a sparse coding framework, named adaptive video dictionary learning (AVDL), to model a video adaptively. The developed framework is able to capture the dynamics of a moving scene by exploring both sparse properties and the temporal correlations of consecutive video frames. The proposed method is compared with state of the art video processing methods on several benchmark data sequences, which exhibit appearance changes and heavy occlusions.

Original language	English
Title of host publication	2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3567-3571
Number of pages	5
ISBN (Print)	9781479928927
DOIs	https://doi.org/10.1109/ICASSP.2014.6854265
State	Published - 2014
Externally published	Yes
Event	2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 - Florence, Italy Duration: 4 May 2014 → 9 May 2014

Publication series

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

Conference

Conference	2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
Country/Territory	Italy
City	Florence
Period	4/05/14 → 9/05/14

Keywords

Dynamic textures modeling
dictionary learning
linear dynamical systems
sparse representation

Access to Document

10.1109/ICASSP.2014.6854265

Cite this

Wei, X., Shen, H., & Kleinsteuber, M. (2014). An adaptive dictionary learning approach for modeling dynamical textures. In 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 (pp. 3567-3571). Article 6854265 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2014.6854265

Wei, Xian ; Shen, Hao ; Kleinsteuber, Martin. / An adaptive dictionary learning approach for modeling dynamical textures. 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 3567-3571 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{147e99966ff54e81a08b1a2fa12ffc2c,

title = "An adaptive dictionary learning approach for modeling dynamical textures",

abstract = "Video representation is an important and challenging task in the computer vision community. In this paper, we assume that image frames of a moving scene can be modeled as a Markov random process. We propose a sparse coding framework, named adaptive video dictionary learning (AVDL), to model a video adaptively. The developed framework is able to capture the dynamics of a moving scene by exploring both sparse properties and the temporal correlations of consecutive video frames. The proposed method is compared with state of the art video processing methods on several benchmark data sequences, which exhibit appearance changes and heavy occlusions.",

keywords = "Dynamic textures modeling, dictionary learning, linear dynamical systems, sparse representation",

author = "Xian Wei and Hao Shen and Martin Kleinsteuber",

year = "2014",

doi = "10.1109/ICASSP.2014.6854265",

language = "英语",

isbn = "9781479928927",

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

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "3567--3571",

booktitle = "2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014",

address = "美国",

note = "2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 ; Conference date: 04-05-2014 Through 09-05-2014",

}

Wei, X, Shen, H & Kleinsteuber, M 2014, An adaptive dictionary learning approach for modeling dynamical textures. in 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014., 6854265, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 3567-3571, 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014, Florence, Italy, 4/05/14. https://doi.org/10.1109/ICASSP.2014.6854265

An adaptive dictionary learning approach for modeling dynamical textures. / Wei, Xian; Shen, Hao; Kleinsteuber, Martin.
2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 3567-3571 6854265 (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 - An adaptive dictionary learning approach for modeling dynamical textures

AU - Wei, Xian

AU - Shen, Hao

AU - Kleinsteuber, Martin

PY - 2014

Y1 - 2014

N2 - Video representation is an important and challenging task in the computer vision community. In this paper, we assume that image frames of a moving scene can be modeled as a Markov random process. We propose a sparse coding framework, named adaptive video dictionary learning (AVDL), to model a video adaptively. The developed framework is able to capture the dynamics of a moving scene by exploring both sparse properties and the temporal correlations of consecutive video frames. The proposed method is compared with state of the art video processing methods on several benchmark data sequences, which exhibit appearance changes and heavy occlusions.

AB - Video representation is an important and challenging task in the computer vision community. In this paper, we assume that image frames of a moving scene can be modeled as a Markov random process. We propose a sparse coding framework, named adaptive video dictionary learning (AVDL), to model a video adaptively. The developed framework is able to capture the dynamics of a moving scene by exploring both sparse properties and the temporal correlations of consecutive video frames. The proposed method is compared with state of the art video processing methods on several benchmark data sequences, which exhibit appearance changes and heavy occlusions.

KW - Dynamic textures modeling

KW - dictionary learning

KW - linear dynamical systems

KW - sparse representation

UR - https://www.scopus.com/pages/publications/84905222845

U2 - 10.1109/ICASSP.2014.6854265

DO - 10.1109/ICASSP.2014.6854265

M3 - 会议稿件

AN - SCOPUS:84905222845

SN - 9781479928927

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

SP - 3567

EP - 3571

BT - 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014

Y2 - 4 May 2014 through 9 May 2014

ER -

Wei X, Shen H, Kleinsteuber M. An adaptive dictionary learning approach for modeling dynamical textures. In 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 3567-3571. 6854265. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2014.6854265

An adaptive dictionary learning approach for modeling dynamical textures

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this