Online Machine Learning for Fast Coding Unit Decisions in HEVC

The High Efficiency Video Coding standard introduced a flexible frame partitioning process that increased significantly compression rates in comparison to previous standards at the cost of a high computational cost. To accelerate frame partitioning decisions, this paper proposes a method that replaces the usual Rate-Distortion Optimization employed in Coding Unit size decision by a set of simpler decision tree models, which are built during encoding time by the C5 machine learning algorithm. The algorithm and the set of attributes employed in the model training process were chosen based on an extensive analysis that compared several options in terms of decision accuracy and training complexity. Experimental results show that the proposed method is capable of building accurate models for each video sequence, decreasing the HEVC encoding complexity in 34.4% on average with a compression efficiency loss of only 0.2% in comparison to the original HEVC reference encoder.