A video quality assessment method based on multi-atlas configuration of spatiotemporal slices

Abstract

The invention discloses a video quality evaluation method based on time-space domain slice multi-map configuration and belongs to the technical field of image video analysis. The method uses the ideaof time-space domain slice to transform the original and distorted video sequences into a time-space slice representation form; a distortion-friendly edge map and a frame difference map are extractedon the space domain slice; then, a variation graph composed of gradient amplitude and gradient direction and a static graph corrected via Lapras are extracted from all the slice sequences, which formsa map with the original graph to complete the map configuration; then, the time-space domain stability of the video to be evaluated is introduced into the slice field to perform map generation calculation; the 2D image quality evaluation method is introduced to calculate and generate the difference value of a map reference-distortion pair; finally, the neural network method is applied to automatically determine the weight of the contribution of each map to video distortion in a learning manner. Compared with the prior art, the video quality evaluation method based on time-space domain slice multi-map configuration in the invention has the characteristics of high subjectivity, strong compatibility and high algorithm stability.

Description

technical field [0001] The invention relates to a video quality evaluation method, in particular to a video quality evaluation method based on time-space slice multi-map configuration, and belongs to the technical field of image and video analysis. Background technique [0002] With the development of science and technology, the cost of image and video generation and dissemination has become lower and lower, which makes image and video, as an excellent medium of information dissemination, more and more common in daily life, more and more The more indispensable. However, images and videos have the potential to introduce distortion at various stages of production and transmission. The generated distortion will affect people's experience when watching these multimedia materials, and seriously, it will also affect people's physical and mental health. [0003] In recent years, people have made great progress in the field of image quality evaluation research, but the development...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problems of low prediction accuracy, poor information representation ability, and unsuccessful application of 2D image quality evaluation methods in the field of video quality evaluation in existing video quality evaluation methods, and propose a multi-atlas configuration based on time-space domain slices video quality assessment method

The idea of ​​temporal-spatial domain slicing uses a joint temporal-spatial domain to re-represent the original video information, which effectively solves the contradiction between the extraction of video spatio-temporal information and high computational complexity

Images