Decision tree based fast CU partition for HEVC lossless compression of medical image sequences

Abstract

In this paper, we proposed a fast coding unit (CU) size decision algorithm for High Efficiency Video Coding (HEVC) medical image lossless coding. In detailed, we used the coding information obtained after checking the first two prediction unit (PU) modes inter 2N×2N and Skip to determine whether or not to continue partitioning the current CU. Eight features are extracted from the coding information of coded inter 2N×2N and Skip modes and three decision tree based classifier are trained off-line for CU depth level 0, 1, and 2, to early terminate CU partition respectively. The experimental results show that the proposed algorithm achieves about 51.28% reduction in encoding time compared to the HEVC test model 16.8 encoder under the Random Access Main RExt configuration with only a negligible loss of coding efficiency.