Efficient HEVC inter prediction using SVM

Jia Kai Liu; Yinyi Lin

doi:10.1109/GCCE46687.2019.9015477

Efficient HEVC inter prediction using SVM

Jia Kai Liu, Yinyi Lin

Department of Communication Engineering

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

1 Scopus citations

Abstract

In this paper, we propose a fast and efficient inter mode decision using support vector machine (SVM) for HEVC inter prediction. In the proposed algorithm, we use information such as MV variance, neighboring CU depth level and coded block flag (CBF) as features for SVM-based CU size decision; while MV variance, SKIP flag and RDO ratio for SVM-based PU mode decision. The experimental results reveal that the proposed algorithm can achieve average 29.6% reduction of computation time with 0.09% bit rate increment only, compared to the original HEVC inter prediction.

Original language	English
Title of host publication	2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	354-358
Number of pages	5
ISBN (Electronic)	9781728135755
DOIs	https://doi.org/10.1109/GCCE46687.2019.9015477
State	Published - Oct 2019
Event	8th IEEE Global Conference on Consumer Electronics, GCCE 2019 - Osaka, Japan Duration: 15 Oct 2019 → 18 Oct 2019

Publication series

Name	2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019

Conference

Conference	8th IEEE Global Conference on Consumer Electronics, GCCE 2019
Country/Territory	Japan
City	Osaka
Period	15/10/19 → 18/10/19

Keywords

Computational complexity
High efficiency video coding (HEVC)
Inter prediction

Access to Document

10.1109/GCCE46687.2019.9015477

Cite this

@inproceedings{7cbaa5a011da47ada351f5eda9c80d1f,

title = "Efficient HEVC inter prediction using SVM",

abstract = "In this paper, we propose a fast and efficient inter mode decision using support vector machine (SVM) for HEVC inter prediction. In the proposed algorithm, we use information such as MV variance, neighboring CU depth level and coded block flag (CBF) as features for SVM-based CU size decision; while MV variance, SKIP flag and RDO ratio for SVM-based PU mode decision. The experimental results reveal that the proposed algorithm can achieve average 29.6% reduction of computation time with 0.09% bit rate increment only, compared to the original HEVC inter prediction.",

keywords = "Computational complexity, High efficiency video coding (HEVC), Inter prediction",

author = "Liu, {Jia Kai} and Yinyi Lin",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 8th IEEE Global Conference on Consumer Electronics, GCCE 2019 ; Conference date: 15-10-2019 Through 18-10-2019",

year = "2019",

month = oct,

doi = "10.1109/GCCE46687.2019.9015477",

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

series = "2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019",

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

pages = "354--358",

booktitle = "2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019",

}

Liu, JK & Lin, Y 2019, Efficient HEVC inter prediction using SVM. in 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019., 9015477, 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019, Institute of Electrical and Electronics Engineers Inc., pp. 354-358, 8th IEEE Global Conference on Consumer Electronics, GCCE 2019, Osaka, Japan, 15/10/19. https://doi.org/10.1109/GCCE46687.2019.9015477

Efficient HEVC inter prediction using SVM. / Liu, Jia Kai; Lin, Yinyi.
2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 354-358 9015477 (2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019).

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

TY - GEN

T1 - Efficient HEVC inter prediction using SVM

AU - Liu, Jia Kai

AU - Lin, Yinyi

PY - 2019/10

Y1 - 2019/10

N2 - In this paper, we propose a fast and efficient inter mode decision using support vector machine (SVM) for HEVC inter prediction. In the proposed algorithm, we use information such as MV variance, neighboring CU depth level and coded block flag (CBF) as features for SVM-based CU size decision; while MV variance, SKIP flag and RDO ratio for SVM-based PU mode decision. The experimental results reveal that the proposed algorithm can achieve average 29.6% reduction of computation time with 0.09% bit rate increment only, compared to the original HEVC inter prediction.

AB - In this paper, we propose a fast and efficient inter mode decision using support vector machine (SVM) for HEVC inter prediction. In the proposed algorithm, we use information such as MV variance, neighboring CU depth level and coded block flag (CBF) as features for SVM-based CU size decision; while MV variance, SKIP flag and RDO ratio for SVM-based PU mode decision. The experimental results reveal that the proposed algorithm can achieve average 29.6% reduction of computation time with 0.09% bit rate increment only, compared to the original HEVC inter prediction.

KW - Computational complexity

KW - High efficiency video coding (HEVC)

KW - Inter prediction

UR - http://www.scopus.com/inward/record.url?scp=85081965750&partnerID=8YFLogxK

U2 - 10.1109/GCCE46687.2019.9015477

DO - 10.1109/GCCE46687.2019.9015477

M3 - 會議論文篇章

AN - SCOPUS:85081965750

T3 - 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019

SP - 354

EP - 358

BT - 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 8th IEEE Global Conference on Consumer Electronics, GCCE 2019

Y2 - 15 October 2019 through 18 October 2019

ER -

Efficient HEVC inter prediction using SVM

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this