Graph-based transform for data decorrelation

Junhui Hou; Hui Liu; Lap Pui Chau

doi:10.1109/ICDSP.2016.7868540

Graph-based transform for data decorrelation

Junhui Hou, Hui Liu, Lap Pui Chau

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

8 Citations (Scopus)

Abstract

Transform coding can decorrelate data, and is widely used for data compression. The recent graph-based signal processing has been attracting an increasing amount of interest. In this paper, we investigate how to effectively explore the intercorrelation of a set of images as well as the spatial correlation of human motion capture data using graph-based transform (GT). Specifically, the graph structure (or matrix is first estimated by an optimization algorithm, and then the data is projected onto an orthogonal matrix consisting of eigenvectors of the estimated graph matrix, leading to sparse coefficients. Experimental results demonstrate that the GT-based method can decorrelate much better than DCT at an almost negligible price of overhead for the extremely sparse graph matrix.

Original language	English
Title of host publication	Proceedings - 2016 IEEE International Conference on Digital Signal Processing, DSP 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	177-180
Number of pages	4
ISBN (Electronic)	9781509041657
DOIs	https://doi.org/10.1109/ICDSP.2016.7868540
Publication status	Published - 2 Jul 2016
Externally published	Yes
Event	2016 IEEE International Conference on Digital Signal Processing, DSP 2016 - Beijing, China Duration: 16 Oct 2016 → 18 Oct 2016

Publication series

Name	International Conference on Digital Signal Processing, DSP
Volume	0

Conference

Conference	2016 IEEE International Conference on Digital Signal Processing, DSP 2016
Country/Territory	China
City	Beijing
Period	16/10/16 → 18/10/16

Keywords

Graph signal processing
motion capture
transform coding

ASJC Scopus subject areas

Signal Processing

More information

10.1109/ICDSP.2016.7868540

Cite this

Hou, J., Liu, H., & Chau, L. P. (2016). Graph-based transform for data decorrelation. In Proceedings - 2016 IEEE International Conference on Digital Signal Processing, DSP 2016 (pp. 177-180). Article 7868540 (International Conference on Digital Signal Processing, DSP; Vol. 0). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICDSP.2016.7868540

@inproceedings{bcde395c75144cd68c1d3ceaf9d9ef6d,

title = "Graph-based transform for data decorrelation",

abstract = "Transform coding can decorrelate data, and is widely used for data compression. The recent graph-based signal processing has been attracting an increasing amount of interest. In this paper, we investigate how to effectively explore the intercorrelation of a set of images as well as the spatial correlation of human motion capture data using graph-based transform (GT). Specifically, the graph structure (or matrix is first estimated by an optimization algorithm, and then the data is projected onto an orthogonal matrix consisting of eigenvectors of the estimated graph matrix, leading to sparse coefficients. Experimental results demonstrate that the GT-based method can decorrelate much better than DCT at an almost negligible price of overhead for the extremely sparse graph matrix.",

keywords = "Graph signal processing, motion capture, transform coding",

author = "Junhui Hou and Hui Liu and Chau, {Lap Pui}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 IEEE International Conference on Digital Signal Processing, DSP 2016 ; Conference date: 16-10-2016 Through 18-10-2016",

year = "2016",

month = jul,

day = "2",

doi = "10.1109/ICDSP.2016.7868540",

language = "English",

series = "International Conference on Digital Signal Processing, DSP",

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

pages = "177--180",

booktitle = "Proceedings - 2016 IEEE International Conference on Digital Signal Processing, DSP 2016",

}

Hou, J, Liu, H & Chau, LP 2016, Graph-based transform for data decorrelation. in Proceedings - 2016 IEEE International Conference on Digital Signal Processing, DSP 2016., 7868540, International Conference on Digital Signal Processing, DSP, vol. 0, Institute of Electrical and Electronics Engineers Inc., pp. 177-180, 2016 IEEE International Conference on Digital Signal Processing, DSP 2016, Beijing, China, 16/10/16. https://doi.org/10.1109/ICDSP.2016.7868540

Graph-based transform for data decorrelation. / Hou, Junhui; Liu, Hui; Chau, Lap Pui.
Proceedings - 2016 IEEE International Conference on Digital Signal Processing, DSP 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 177-180 7868540 (International Conference on Digital Signal Processing, DSP; Vol. 0).

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Graph-based transform for data decorrelation

AU - Hou, Junhui

AU - Liu, Hui

AU - Chau, Lap Pui

PY - 2016/7/2

Y1 - 2016/7/2

N2 - Transform coding can decorrelate data, and is widely used for data compression. The recent graph-based signal processing has been attracting an increasing amount of interest. In this paper, we investigate how to effectively explore the intercorrelation of a set of images as well as the spatial correlation of human motion capture data using graph-based transform (GT). Specifically, the graph structure (or matrix is first estimated by an optimization algorithm, and then the data is projected onto an orthogonal matrix consisting of eigenvectors of the estimated graph matrix, leading to sparse coefficients. Experimental results demonstrate that the GT-based method can decorrelate much better than DCT at an almost negligible price of overhead for the extremely sparse graph matrix.

AB - Transform coding can decorrelate data, and is widely used for data compression. The recent graph-based signal processing has been attracting an increasing amount of interest. In this paper, we investigate how to effectively explore the intercorrelation of a set of images as well as the spatial correlation of human motion capture data using graph-based transform (GT). Specifically, the graph structure (or matrix is first estimated by an optimization algorithm, and then the data is projected onto an orthogonal matrix consisting of eigenvectors of the estimated graph matrix, leading to sparse coefficients. Experimental results demonstrate that the GT-based method can decorrelate much better than DCT at an almost negligible price of overhead for the extremely sparse graph matrix.

KW - Graph signal processing

KW - motion capture

KW - transform coding

UR - http://www.scopus.com/inward/record.url?scp=85016167915&partnerID=8YFLogxK

U2 - 10.1109/ICDSP.2016.7868540

DO - 10.1109/ICDSP.2016.7868540

M3 - Conference article published in proceeding or book

AN - SCOPUS:85016167915

T3 - International Conference on Digital Signal Processing, DSP

SP - 177

EP - 180

BT - Proceedings - 2016 IEEE International Conference on Digital Signal Processing, DSP 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 IEEE International Conference on Digital Signal Processing, DSP 2016

Y2 - 16 October 2016 through 18 October 2016

ER -

Graph-based transform for data decorrelation

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this