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.

No abstract

In this work-in-progress paper, we proposed using deep learning techniques, especially the deep Convolutional Neural Network (CNN) to perform critical tasks of video ending within the framework of H.265/HEVC. Deep CNNs have achieved breakthrough 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. In order to take advantage of the significant capabilities of deep CNN on image content detection, we proposed using deep CNN as the primary technique to perform critical tasks in video encoding that are relevant to the contents of one or multiple video frames. More specifically, we designed deep CNNs for the following tasks in H.265/HEVC encoder: partitioning CTU to CUs; partitioning CU to PUs; performing intra prediction; and performing inter predictions.