Fast CU Size Decisions for HEVC Inter-Prediction Using Support Vector Machines
MetadataShow full item record
The brute force rate-distortion optimisation based approach used in the High Efficiency Video Coding (HEVC) encoders to determine the best block partitioning structure fora given content demands an excessive amount of computational resources. In this context, this paper proposes a novel algorithm to reduce the computational complexity of HEVC inter-prediction using Support Vector Machines. The proposed algorithm predicts the Coding Unit (CU) split decision of a particular block enabling the encoder to directly encode the selected block, avoiding the unnecessary evaluation of the remaining CU size combinations.Experimental results demonstrate encoding time reductions of~58% and ~50% with 2.27%, and 1.89% Bjøntegaard DeltaBit Rate (BDBR) losses for Random Access and Low-Delay B configurations, respectively.
27th European Signal Processing Conference;
Erabadda, B., Mallikarachchi, T., Kulupana, G. and Fernando, A. (2019) 'Fast CU Size Decisions for HEVC Inter-PredictionUsing Support Vector Machines', 27th European Signal Processing Conference, 2-6 September, Spain.
Paper presented at 27th European Signal Processing Conference, 2-6 September, 2019, Spain.
Cardiff Metropolitan University (Grant ID: Cardiff Metropolian (Internal))