Machine learning-based coding decision making in H.265/HEVC CTU division and intra prediction
Software Engineering and Game Development
Copyright © 2020, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited. High efficiency video coding (HEVC) has been deemed as the newest video coding standard of the ITU-T Video Coding Experts Group and the ISO/IEC Moving Picture Experts Group. In this research project, in compliance with H.265 standard, the authors focused on improving the performance of encode/decode by optimizing the partition of prediction block in coding unit with the help of supervised machine learning. The authors used Keras library as the main tool to implement the experiments. Key parameters were tuned for the model in the convolution neuron network. The coding tree unit mode decision time produced in the model was compared with that produced in the reference software for HEVC, and it was proven to have improved significantly. The intra-picture prediction mode decision was also investigated with modified model and yielded satisfactory results.
International Journal of Mobile Computing and Multimedia Communications
Digital Object Identifier (DOI)
Jiang, Wenchan; Yang, Ming; Xie, Ying; and Li, Zhigang, "Machine learning-based coding decision making in H.265/HEVC CTU division and intra prediction" (2020). Faculty Publications. 4654.