Research Article
Using Deep Learning Neural Network for Block Partitioning in H.265/HEVC
@INPROCEEDINGS{10.4108/eai.21-6-2018.2276639, author={Ming Yang and Ying Xie and Jian Yu and Zhe Wang and Tao Wu}, title={Using Deep Learning Neural Network for Block Partitioning in H.265/HEVC}, proceedings={11th EAI International Conference on Mobile Multimedia Communications}, publisher={EAI}, proceedings_a={MOBIMEDIA}, year={2018}, month={9}, keywords={deep learning deep cnn h265 hevc video encoding}, doi={10.4108/eai.21-6-2018.2276639} }- Ming Yang
Ying Xie
Jian Yu
Zhe Wang
Tao Wu
Year: 2018
Using Deep Learning Neural Network for Block Partitioning in H.265/HEVC
MOBIMEDIA
EAI
DOI: 10.4108/eai.21-6-2018.2276639
Abstract
Abstract: dividing video frames into Coding Tree Units (CTUs) and Coding Units (CUs) is a critical task of video compression in H.265/HEVC video coding standard. In this paper, we utilize deep learning techniques, especially the deep Convolutional Neural Network (CNN) to speed up the block partitioning process. Deep CNNs have achieved break-through improvements on image recognition tasks such as image classifications, object identifications, and image annotations. However, very few work has been done in applying deep CNN to video encoding. Block partitioning in video coding is highly dependent on the content of the video frames, and thus it is natural to take advantage of the significant capabilities of deep CNN on image content detection and recognition to perform block partitioning and avoid the time-consuming iterative Rate-Distortion-Optimization (RDO) process. Experimental results have shown that the proposed methodology has largely speed up the coding process and has also achieved coding efficiency comparable to the reference software of H.265/HEVC.