SVM-Based Fast Intra CU Depth Decision for HEVC

Yen Chun Liu, Zong Yi Chen, Jiunn Tsair Fang, Pao Chi Chang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

13 Scopus citations


In this paper, a fast CU depth decision algorithm based on support vector machine (SVM) is proposed to reduce the computational complexity of HEVC intra coding. It is systematic to develop the criterion of early CU splitting and termination by applying SVM. Appropriate features for training SVM models are extracted from spatial domain and pixel domain. Artificial neural network is used to analyze the impact of each extracted feature on CU size decision, and different weights are assigned to the output of SVMs. The experimental results show that the proposed fast algorithm provides 58.9% encoding time saving at most, and 46.5% time saving on average compared with HM 12.1.

Original languageEnglish
Title of host publicationProceedings - DCC 2015
Subtitle of host publication2015 Data Compression Conference
EditorsJoan Serra-Sagrista, Michael W. Marcellin, Ali Bilgin, James A. Storer
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages1
ISBN (Electronic)9781479984305
StatePublished - 2 Jul 2015
Event2015 Data Compression Conference, DCC 2015 - Snowbird, United States
Duration: 7 Apr 20159 Apr 2015

Publication series

NameData Compression Conference Proceedings
ISSN (Print)1068-0314


Conference2015 Data Compression Conference, DCC 2015
Country/TerritoryUnited States


Dive into the research topics of 'SVM-Based Fast Intra CU Depth Decision for HEVC'. Together they form a unique fingerprint.

Cite this