Intra CTU depth decision for HEVC by using neural networks

Yanfen Li; Hanxiang Wang; L. Minh Dang; Khawar Islam; Hae Kwang Kim

doi:10.1117/12.2589191

13 March 2021 Intra CTU depth decision for HEVC by using neural networks

Yanfen Li, Hanxiang Wang, L. Minh Dang, Khawar Islam, Hae Kwang Kim

Proceedings Volume 11766, International Workshop on Advanced Imaging Technology (IWAIT) 2021; 1176630 (2021) https://doi.org/10.1117/12.2589191
Event: International Workshop on Advanced Imaging Technology 2021 (IWAIT 2021), 2021, Online Only

Abstract

As a video encoding standard, High Efficiency Video Coding (HEVC) achieves excellent performance while causing a dramatic increase in coding complexity. Especially, the coding tree unit (CTU) depth decision process is the most complicated section, which takes heavy computation complexity in the entire HEVC intra coding process. Therefore, a deep learning-based method is applied to directly predict the CTU depth level for each frame in this study. In addition, a large-scale dataset that contains the coding unit image files and the corresponding depths was generated by HM16.15 to train and test the deep learning model. Besides, a Convolutional Neural Network called LeNet is fine-tuned by modifying the original architecture, and then the model with a more complicated structure is evaluated and compared on an acquired dataset. The experiments show that the fine-tuned deep learning model has the ability to identify accurately the depth level of CTU, the recognition accuracy reaches over 98.6%.

Citation Download Citation

Yanfen Li, Hanxiang Wang, L. Minh Dang, Khawar Islam, and Hae Kwang Kim "Intra CTU depth decision for HEVC by using neural networks", Proc. SPIE 11766, International Workshop on Advanced Imaging Technology (IWAIT) 2021, 1176630 (13 March 2021); https://doi.org/10.1117/12.2589191

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available