Optimization of Inter-Frame Coding Algorithm Based on Random Forest

Abstract

Versatile Video Coding (VVC) is the latest generation of video coding standards released to meet the arrival of the ultra-high-definition (UHD) video era. Compared with the quad-tree (QT) structure in High Efficiency Video Coding (HEVC), VVC obtains excellent coding performance by introducing the division structure of binary-tree (BT) and ternary-tree (TT), but at the same time, it also greatly improves the computational complexity in the coding process. In order to reduce the coding unit (CU) division traversal time in the inter-frame coding process, this paper proposes an algorithm for fast CU division using random forest for the VVC inter-frame coding process. The algorithm first calculates the eigenvalues of the current CU block, and then inputs them into the random forest model to obtain the predicted classification. At the same time, it decides whether to adopt the predicted result based on the decision rule. If adopted, the stack in the encoder is modified to jump over-redundant traversal operations. Experimental results show that the proposed algorithm reduces the encoding time by about 37.30% on average in random access mode, while the video quality loss is only 1.41%.