Learning-based high efficiency video coding method

Abstract

The invention discloses a learning-based high efficiency video coding method. The method comprises the following steps: coding a video sequence by a high efficiency video coder, and extracting feature vectors corresponding to coding unit blocks; inputting the extracted feature vectors and an optimal coding unit size into a three-value-output learning machine, and building a learning model; adding an early-abort strategy structure into a selection process of coding unit sizes in the high efficiency video coder, executing a skip mode current block and a merge mode current block firstly, and extracting feature vectors corresponding to corresponding current coding; inputting the feature vectors into a learned learning machine model, outputting a prediction value, and executing the current coding unit size according to the corresponding early-abort strategy structure till all coding unit layers in coding tree units are coded; and performing repeated execution till the coding tree units in all video frames are coded. By adoption of the method, an optimal coding process can be output correspondingly according to a rate-distortion cost and calculation complexity; the learning performance and classifying performance of a classifier are improved; and the coding efficiency of video coding is increased.

Description

technical field [0001] The invention relates to an image signal processing method, in particular to an efficient learning-based high-efficiency video coding method. Background technique [0002] High Definition (High Definition, HD) and Ultra High Definition (Ultra High Definition) videos are becoming more and more popular and loved by people because they can provide better perceptual quality and more realistic visual experience. These high-definition and ultra-high-definition videos have a broad application market, including high-definition TV broadcasting, MAX movies, immersive video communications, network video on demand, and high-definition video surveillance. However, due to the higher definition and video frame rate of HD and UHD video, the amount of video data has also increased tremendously. For example, an 8K×4K@120 frame per second HD / UHD video has 11.5GB per second of raw video data, and its effective storage and transmission requires very efficient video compre...

AI Technical Summary

Problems solved by technology

In general, the existing coding unit mode prediction methods based on machine learning are very dependent on feature selection and the classification accuracy of the learning machine. Once the prediction is inaccurate, it will lead to a huge drop in compression efficiency.

At the same time, once the traditional method is determined, it is difficult to achieve the conversion of coding efficiency and computational complexity through parameter adjustment, so it is difficult to apply to the coding requirements of different video systems

Images