AVS-to-HEVC optimal video transcoding method based on support vector machine

Abstract

The invention discloses an AVS-to-HEVC optimal video transcoding method based on a support vector machine. The method comprises steps of collecting characteristic vectors of AVS code streams; learning the characteristic vectors through the support vector machine and obtaining a training model; classifying the extracted AVC characteristic vectors into two types comprising one type that CUs arranged at corresponding positions in the HEVC are divided, and the other type that the CUs arranged at the corresponding positions in the HEVC are not divided; predicting whether the CUs are required to be divided through the training model in a transcoding stage; performing 2N*2N mode calculation and SKIP mode calculation under the depth of the current HEVC when the current CUs are required to be divided, and selecting an optimum prediction mode from the two modes; and performing optimal mode selection according to an HEVC standard coding process when the current CUs are not required to be divided according to the prediction. The method combines basic ideas of machine learning, a whole transcoding process is divided into a training stage and the transcoding stage, the training model is obtained through learning, the division of the CUs in the HEVC is predicted, and a rapid mode selection algorithm is combined in the method, so that the transcoding speed is increased, and the whole video quality of transcoded videos is guaranteed.

Description

technical field [0001] The present invention relates to a technology in the field of video signal processing, in particular to an optimized video transcoding method from AVS to HEVC based on a support vector machine. Background technique [0002] Video transcoding technology is to decode and re-encode the compressed code stream to obtain the target code stream that meets the requirements. With the wide application and rapid development of multimedia technology and the Internet, the transmission of various video data on the network has become the development trend of network technology. At present, a variety of video coding standards have emerged, including MPEG‐4, MPEG‐2, H.264, AVS, HEVC, etc. Due to the variety of video resources, and the differences in the display capabilities, storage capabilities, and processing capabilities of different terminal devices, users have different requirements for video in different scenarios. Therefore, how to achieve efficient conversion ...

AI Technical Summary

Problems solved by technology

However, the input of this technology is the original code stream, and the encoding information contained in the compressed code stream cannot be used. Moreover, for HEVC’s more complex encoders, the encoding paths are diverse, and the implementation complexity will be relatively high.

Images