Proceedings of the 2018 3rd International Conference on Automation, Mechanical Control and Computational Engineering (AMCCE 2018)

Fast Intra CU Size Decision for HEVC Based on Machine Learning

Authors
Meng Wang, Junru Li, Xiaodong Xie, Yuan Li, Huizhu Jia
Corresponding Author
Meng Wang
Available Online May 2018.
DOI
https://doi.org/10.2991/amcce-18.2018.132How to use a DOI?
Keywords
HEVC, Intra prediction, CU size, Fast algorithm.
Abstract
High Efficiency Video Coding (HEVC) is the new generation of video coding standard. A quad-tree based Coding Unit (CTU) partitioning scheme is used to adapt to different video contents. However, it brings the dramatically increasing of coding complexity because there are a large amount of CU partition structure to traverse. In this paper, we proposed a fast CU size decision method based on machine learning. CU features is extracted and Support Vector Machine (SVM) model is trained to classify CU splitting or non-splitting. Experimental results show that our proposed method can achieve 40.23% encoding time saving on average and the BD-rate loss is only 0.83% under All Intra (AI) configuration.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Proceedings
2018 3rd International Conference on Automation, Mechanical Control and Computational Engineering (AMCCE 2018)
Part of series
Advances in Engineering Research
Publication Date
May 2018
ISBN
978-94-6252-508-5
ISSN
2352-5401
DOI
https://doi.org/10.2991/amcce-18.2018.132How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Meng Wang
AU  - Junru Li
AU  - Xiaodong Xie
AU  - Yuan Li
AU  - Huizhu Jia
PY  - 2018/05
DA  - 2018/05
TI  - Fast Intra CU Size Decision for HEVC Based on Machine Learning
BT  - 2018 3rd International Conference on Automation, Mechanical Control and Computational Engineering (AMCCE 2018)
PB  - Atlantis Press
SN  - 2352-5401
UR  - https://doi.org/10.2991/amcce-18.2018.132
DO  - https://doi.org/10.2991/amcce-18.2018.132
ID  - Wang2018/05
ER  -