Multi-Type Tree Partition Decision for H.266/VVC Inter Coding Based on Random Forest Classifiers

Chih Ming Lien; Mei Juan Chen; Chieh Ming Yang; Rui Hong Hong; Yuan Hong Lin; Chia Hung Yeh

doi:10.1049/icp.2023.3208

Multi-Type Tree Partition Decision for H.266/VVC Inter Coding Based on Random Forest Classifiers

Chih Ming Lien^*, Mei Juan Chen, Chieh Ming Yang, Rui Hong Hong, Yuan Hong Lin, Chia Hung Yeh

^*Corresponding author for this work

Department of Electrical Engineering

Research output: Contribution to journal › Conference article › peer-review

Abstract

The flexible coding unit block partition structure of the quadtree with nested multi-type tree (MTT) for the newest video coding standard H.266/versatile video coding (VVC) can provide better coding efficiency than that of H.265/high efficiency video coding (HEVC). However, the computational complexity increases markedly. This paper proposes a fast MTT partition algorithm based on machine learning for the inter prediction of the H.266/VVC encoder. The proposed approach utilizes Random Forest classifiers to skip the least necessary MTT split. Experimental results show that the proposed algorithm reduces the encoding time with negligible Bjontegaard delta bitrate (BDBR) under the random access configuration. The proposed method outperforms the previous work.

Original language	English
Pages (from-to)	97-98
Number of pages	2
Journal	IET Conference Proceedings
Volume	2023
Issue number	35
DOIs	https://doi.org/10.1049/icp.2023.3208
Publication status	Published - 2023
Event	2023 IET International Conference on Engineering Technologies and Applications, ICETA 2023 - Yunlin, Taiwan Duration: 2023 Oct 21 → 2023 Oct 23

Keywords

H.266
Inter Prediction
Multi-type Tree
Random Forest Classifiers
Versatile Video Coding

ASJC Scopus subject areas

General Engineering

Access to Document

10.1049/icp.2023.3208

Cite this

@article{177a80de3e264667be2d4798fbdc54a8,

title = "Multi-Type Tree Partition Decision for H.266/VVC Inter Coding Based on Random Forest Classifiers",

abstract = "The flexible coding unit block partition structure of the quadtree with nested multi-type tree (MTT) for the newest video coding standard H.266/versatile video coding (VVC) can provide better coding efficiency than that of H.265/high efficiency video coding (HEVC). However, the computational complexity increases markedly. This paper proposes a fast MTT partition algorithm based on machine learning for the inter prediction of the H.266/VVC encoder. The proposed approach utilizes Random Forest classifiers to skip the least necessary MTT split. Experimental results show that the proposed algorithm reduces the encoding time with negligible Bjontegaard delta bitrate (BDBR) under the random access configuration. The proposed method outperforms the previous work.",

keywords = "H.266, Inter Prediction, Multi-type Tree, Random Forest Classifiers, Versatile Video Coding",

author = "Lien, {Chih Ming} and Chen, {Mei Juan} and Yang, {Chieh Ming} and Hong, {Rui Hong} and Lin, {Yuan Hong} and Yeh, {Chia Hung}",

note = "Publisher Copyright: {\textcopyright} The Institution of Engineering & Technology 2023.; 2023 IET International Conference on Engineering Technologies and Applications, ICETA 2023 ; Conference date: 21-10-2023 Through 23-10-2023",

year = "2023",

doi = "10.1049/icp.2023.3208",

language = "English",

volume = "2023",

pages = "97--98",

journal = "IET Conference Proceedings",

issn = "2732-4494",

publisher = "Institution of Engineering and Technology",

number = "35",

}

TY - JOUR

T1 - Multi-Type Tree Partition Decision for H.266/VVC Inter Coding Based on Random Forest Classifiers

AU - Lien, Chih Ming

AU - Chen, Mei Juan

AU - Yang, Chieh Ming

AU - Hong, Rui Hong

AU - Lin, Yuan Hong

AU - Yeh, Chia Hung

N1 - Publisher Copyright: © The Institution of Engineering & Technology 2023.

PY - 2023

Y1 - 2023

N2 - The flexible coding unit block partition structure of the quadtree with nested multi-type tree (MTT) for the newest video coding standard H.266/versatile video coding (VVC) can provide better coding efficiency than that of H.265/high efficiency video coding (HEVC). However, the computational complexity increases markedly. This paper proposes a fast MTT partition algorithm based on machine learning for the inter prediction of the H.266/VVC encoder. The proposed approach utilizes Random Forest classifiers to skip the least necessary MTT split. Experimental results show that the proposed algorithm reduces the encoding time with negligible Bjontegaard delta bitrate (BDBR) under the random access configuration. The proposed method outperforms the previous work.

AB - The flexible coding unit block partition structure of the quadtree with nested multi-type tree (MTT) for the newest video coding standard H.266/versatile video coding (VVC) can provide better coding efficiency than that of H.265/high efficiency video coding (HEVC). However, the computational complexity increases markedly. This paper proposes a fast MTT partition algorithm based on machine learning for the inter prediction of the H.266/VVC encoder. The proposed approach utilizes Random Forest classifiers to skip the least necessary MTT split. Experimental results show that the proposed algorithm reduces the encoding time with negligible Bjontegaard delta bitrate (BDBR) under the random access configuration. The proposed method outperforms the previous work.

KW - H.266

KW - Inter Prediction

KW - Multi-type Tree

KW - Random Forest Classifiers

KW - Versatile Video Coding

UR - http://www.scopus.com/inward/record.url?scp=85188472681&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85188472681&partnerID=8YFLogxK

U2 - 10.1049/icp.2023.3208

DO - 10.1049/icp.2023.3208

M3 - Conference article

AN - SCOPUS:85188472681

SN - 2732-4494

VL - 2023

SP - 97

EP - 98

JO - IET Conference Proceedings

JF - IET Conference Proceedings

IS - 35

T2 - 2023 IET International Conference on Engineering Technologies and Applications, ICETA 2023

Y2 - 21 October 2023 through 23 October 2023

ER -

Multi-Type Tree Partition Decision for H.266/VVC Inter Coding Based on Random Forest Classifiers

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this