Reinforcement Learning for HEVC Screen Content Intra Coding on Heterogeneous Mobile Devices

Yuanyuan Xu; Quanping Zeng

Machine Learning and Intelligent Communications. 4th International Conference, MLICOM 2019, Nanjing, China, August 24–25, 2019, Proceedings

Research Article

Reinforcement Learning for HEVC Screen Content Intra Coding on Heterogeneous Mobile Devices

Download

70 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1007/978-3-030-32388-2_62,
    author={Yuanyuan Xu and Quanping Zeng},
    title={Reinforcement Learning for HEVC Screen Content Intra Coding on Heterogeneous Mobile Devices},
    proceedings={Machine Learning and Intelligent Communications. 4th International Conference, MLICOM 2019, Nanjing, China, August 24--25, 2019, Proceedings},
    proceedings_a={MLICOM},
    year={2019},
    month={10},
    keywords={Screen content coding Coding mode decision Reinforcement learning},
    doi={10.1007/978-3-030-32388-2_62}
}

Yuanyuan Xu
Quanping Zeng
Year: 2019
Reinforcement Learning for HEVC Screen Content Intra Coding on Heterogeneous Mobile Devices
MLICOM
Springer
DOI: 10.1007/978-3-030-32388-2_62

Yuanyuan Xu¹^,*, Quanping Zeng¹

1: Hohai University

*Contact email: yuanyuan_xu@hhu.edu.cn

Abstract

Intra coding of HEVC screen content coding has to evaluate HEVC intra coding modes and additional modes for screen contents, which poses a challenge for coding such a content on mobile devices. Furthermore, the heterogeneous mobile devices have varying complexity requirements. In this paper, a flexible screen content intra coding scheme is proposed, which can trade between encoding complexity and rate-distortion performance degradation via reinforcement learning (RL). Through the design of states, actions, and more importantly, the reward function for RL, the proposed scheme can learn a flexible coding policy offline. Experimental results show the effectiveness of the proposed scheme.

Keywords: Screen content coding Coding mode decision Reinforcement learning

Published: 2019-10-28
Appears in: SpringerLink

: http://dx.doi.org/10.1007/978-3-030-32388-2_62