Inter-frame fast prediction algorithm for multi-scene adaptive decision tree selection

Abstract

An inter-frame fast prediction algorithm for multi-scene adaptive decision tree selection comprises the following steps: 1) a preliminary part: inputting a video test sequence, and performing probability statistics on each PU mode of CU inter-frame prediction in the video sequence to obtain the probability of each PU mode of the inter-frame prediction; 2) a training part: inputting video test sequences into several scene categories, collecting relevant features of CU blocks for video sequences of each scene category, further filtering and optimizing the collected features, and generating 8x8,16x16, 32x32, 64x64 decision trees based on the optimized features for each scene category; and 3) an execution part: inputting a segment of video sequences composed of various scenes, dividing the input video according to the transformation of the scenes in the video, collecting and optimizing correlation features of the CU blocks of the respective divided video sequences, determining whether thePU prediction mode after the traversal is continued, and ending the inter-frame prediction.

Description

technical field [0001] The invention belongs to the field of HEVC video coding, and in particular relates to an inter-frame prediction optimization coding method using an adaptive selection decision tree between multi-scene HEVC coding units. Background technique [0002] With the diversification of multimedia services, such as the popularity of high-definition video and the emergence of ultra-high-definition resolutions (such as 4k x 2k, 8k x4k, etc.), the requirements for encoding performance have increasingly exceeded the capabilities of H.264, and gradually cannot Meet some technical or performance requirements. In order to solve the above problems, the Moving Picture Experts Group (MPEG) and the Video Coding Experts Group (VCEG) established the Joint Collaborative Team on Video Coding (JCT-VC) in 2013. In February, the High Efficiency Video Coding (HEVC) standard was officially released. [0003] The HEVC encoder framework adopts a hybrid coding framework of predictio...

AI Technical Summary

Problems solved by technology

[0006] The mode decision of the inter-frame image is related to the rate-distortion cost RDcost. The mode selection will traverse and calculate the RDcost of all modes, and finally select the mode that minimizes the RDcost as the final mode, which leads to a great increase in complexity.

Because even if the best PU prediction mode is among the first few modes, the encoder has to continue to measure all the remaining PU prediction modes, which adds some unnecessary calculations

Images