Video compression method based on convolutional neural network and HEVC compressed domain significant information

Abstract

The invention discloses a video compression method based on a convolutional neural network and HEVC compressed domain significant information. The video compression method based on the convolutional neural network and the HEVC compressed domain significant information improves and strengthens the HEVC from two aspects of a video saliency algorithm based on an attention mechanism and a perception preferred video compression algorithm; in the aspect of the video saliency, the method combines motion estimation results of each CU in the HEVC compression process on the basis of the convolutional neural network to adaptively integrate the two in a dynamic condition, so as to complete the saliency detection of an input video; in the aspect of the perception preferred video compression algorithm,a corresponding QP is selected according to a significant value of the CU, so that the CU with a higher significant value can be encoded with a smaller QP, and the saliency feature of the current CU block is incorporated into a traditional rate distortion calculation method, so as to achieve the purpose of perception priority. The video compression method based on the convolutional neural networkand the HEVC compressed domain significant information reduces the perception redundancy of the video and thus obtains a better compression effect.

Description

technical field [0001] The present invention relates to the technical field of video processing, and more specifically relates to a video compression method based on convolutional neural network and salient information in HEVC compression domain. Background technique [0002] At present, with the continuous development of video compression technology, people have higher and higher requirements for high-quality and high-real-time video, and a new generation of video coding standard HEVC (High Efficiency Video Coding) emerged as the times require. Applied to high-definition video processing. [0003] However, HEVC, a new generation of video coding standard, has greatly increased its coding complexity while its coding performance has improved, so that when it is applied to the video compression process, its compression efficiency is difficult to guarantee, especially when high-definition video applications are becoming more and more popular. In this case, the problems arising ...

AI Technical Summary

Problems solved by technology

[0003] However, HEVC, a new generation of video coding standard, has greatly increased its coding complexity while its coding performance has improved, so that when it is applied to the video compression process, its compression efficiency is difficult to guarantee, especially when high-definition video applications are becoming more and more popular. In this case, the problems arising from the limited bandwidth have brought huge challenges to the video compression technology, and the requirements for high-definition video in modern society are also getting higher and higher, from the original QCIF to 4K (with a resolution of 3840× 2160), and soon developed into 8K (resolution 7680×4320) ultra-high-definition video, which puts forward higher requirements for video compression, storage and transmission, especially how to improve the compression efficiency so that the human eye The image quality of the part of interest is clearer, more realistic, etc.

The existing video coding standard HEVC can no longer meet the needs of high-quality high-definition video transmission and improve the subjective visual quality of the human eye, while also improving the compression efficiency and making the picture quality of the part that the human eye pays attention to clearer and more realistic. Require

Images