Fast Intra Coding Algorithm for HEVC Based on Decision Tree

Jia QIN; Huihui BAI; Mengmeng ZHANG; Yao ZHAO

doi:10.1587/transfun.E100.A.1274

Fast Intra Coding Algorithm for HEVC Based on Decision Tree

Jia QIN, Huihui BAI, Mengmeng ZHANG, Yao ZHAO

Full Text Views

0

Share
Cite this

Summary :

High Efficiency Video Coding (HEVC) is the latest coding standard. Compared with Advanced Video coding (H.264/AVC), HEVC offers about a 50% bitrate reduction at the same reconstructed video quality. However, this new coding standard leads to enormous computational complexity, which makes it difficult to encode video in real time. Therefore, in this paper, aiming at the high complexity of intra coding in HEVC, a new fast coding unit (CU) splitting algorithm is proposed based on the decision tree. Decision tree, as a method of machine learning, can be designed to determine the size of CUs adaptively. Here, two significant features, Just Noticeable Difference (JND) values and coding bits of each CU can be extracted to train the decision tree, according to their relationships with the CUs' partitions. The experimental results have revealed that the proposed algorithm can save about 34% of time, on average, with only a small increase of BD-rate under the “All_Intra” setting, compared with the HEVC reference software.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E100-A No.5 pp.1274-1278

Publication Date: 2017/05/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1587/transfun.E100.A.1274

Type of Manuscript: LETTER

Category: Image

Authors

Jia QIN
  Beijing Jiaotong University
Huihui BAI
  Beijing Jiaotong University
Mengmeng ZHANG
  North China University of Technology
Yao ZHAO
  Beijing Jiaotong University

Keyword

HEVC, coding unit decision, intra prediction, decision tree, offline training

Cite this

Copy

Jia QIN, Huihui BAI, Mengmeng ZHANG, Yao ZHAO, "Fast Intra Coding Algorithm for HEVC Based on Decision Tree" in IEICE TRANSACTIONS on Fundamentals, vol. E100-A, no. 5, pp. 1274-1278, May 2017, doi: 10.1587/transfun.E100.A.1274.
Abstract: High Efficiency Video Coding (HEVC) is the latest coding standard. Compared with Advanced Video coding (H.264/AVC), HEVC offers about a 50% bitrate reduction at the same reconstructed video quality. However, this new coding standard leads to enormous computational complexity, which makes it difficult to encode video in real time. Therefore, in this paper, aiming at the high complexity of intra coding in HEVC, a new fast coding unit (CU) splitting algorithm is proposed based on the decision tree. Decision tree, as a method of machine learning, can be designed to determine the size of CUs adaptively. Here, two significant features, Just Noticeable Difference (JND) values and coding bits of each CU can be extracted to train the decision tree, according to their relationships with the CUs' partitions. The experimental results have revealed that the proposed algorithm can save about 34% of time, on average, with only a small increase of BD-rate under the “All_Intra” setting, compared with the HEVC reference software.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/transfun.E100.A.1274/_p

Copy

@ARTICLE{e100-a_5_1274,
author={Jia QIN, Huihui BAI, Mengmeng ZHANG, Yao ZHAO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Fast Intra Coding Algorithm for HEVC Based on Decision Tree},
year={2017},
volume={E100-A},
number={5},
pages={1274-1278},
abstract={High Efficiency Video Coding (HEVC) is the latest coding standard. Compared with Advanced Video coding (H.264/AVC), HEVC offers about a 50% bitrate reduction at the same reconstructed video quality. However, this new coding standard leads to enormous computational complexity, which makes it difficult to encode video in real time. Therefore, in this paper, aiming at the high complexity of intra coding in HEVC, a new fast coding unit (CU) splitting algorithm is proposed based on the decision tree. Decision tree, as a method of machine learning, can be designed to determine the size of CUs adaptively. Here, two significant features, Just Noticeable Difference (JND) values and coding bits of each CU can be extracted to train the decision tree, according to their relationships with the CUs' partitions. The experimental results have revealed that the proposed algorithm can save about 34% of time, on average, with only a small increase of BD-rate under the “All_Intra” setting, compared with the HEVC reference software.},
keywords={},
doi={10.1587/transfun.E100.A.1274},
ISSN={1745-1337},
month={May},}

Copy

TY - JOUR
TI - Fast Intra Coding Algorithm for HEVC Based on Decision Tree
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1274
EP - 1278
AU - Jia QIN
AU - Huihui BAI
AU - Mengmeng ZHANG
AU - Yao ZHAO
PY - 2017
DO - 10.1587/transfun.E100.A.1274
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E100-A
IS - 5
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - May 2017
AB - High Efficiency Video Coding (HEVC) is the latest coding standard. Compared with Advanced Video coding (H.264/AVC), HEVC offers about a 50% bitrate reduction at the same reconstructed video quality. However, this new coding standard leads to enormous computational complexity, which makes it difficult to encode video in real time. Therefore, in this paper, aiming at the high complexity of intra coding in HEVC, a new fast coding unit (CU) splitting algorithm is proposed based on the decision tree. Decision tree, as a method of machine learning, can be designed to determine the size of CUs adaptively. Here, two significant features, Just Noticeable Difference (JND) values and coding bits of each CU can be extracted to train the decision tree, according to their relationships with the CUs' partitions. The experimental results have revealed that the proposed algorithm can save about 34% of time, on average, with only a small increase of BD-rate under the “All_Intra” setting, compared with the HEVC reference software.
ER -