.png){kind=icon}
.png){kind=icon}
Return
A fast intra coding algorithm for HEVC by jointly utilizing naive Bayesian and SVM
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-020-08882-x.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The current video coding standard HEVC has very high coding efficiency. However, its coding complexity is also very high, which leads to a negative impact on its wide applications. Therefore, how to improve the coding speed of HEVC has been a research focus recently. In this research, by applying machine learning methodology into video compression, we propose a novel fast intra coding algorithm for HEVC so as to improve the intra encoding speed. We first adopt Naive Bayesian to calculate each depth's probability based on correlations. Then, to speed up coding, we combine textural features and possibilities with support vector machine (SVM) to further predict depth early skip and early termination. Experiments demonstrate that the proposed algorithm can significantly improve the coding speed with negligible loss of coding efficiency.
Keywords:
Depth prediction
Correlation
Naive Bayesian
Support vector machine
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3
Papers:
1.9W
Citations:
3.2W
View more organizations