Reference-free stereoscopic video quality objective evaluation method based on multi-view feature learning

Abstract

The invention discloses a reference-free stereoscopic video quality objective evaluation method based on multi-view feature learning. The method comprises the following steps: performing curvelet transform on an image sequence, and extracting a coefficient to serve as a texture feature; comparing eight adjacent pixels with a central pixel; generating ten output modes; calculating the occurrence frequency of each mode, and averaging the occurrence frequencies to obtain an average value to serve as an airspace texture feature; performing dimension reduction to obtain a space domain feature; acquiring motion strength features of adjacent images, and calculating the average value to serve as a time domain feature; performing DCT (Discrete Cosine Transformation) on a tridimensional perception domain view, performing DCT coefficient modeling, extracting shape parameters, and calculating the average value to serve as a stereoscopic perception domain feature; performing SVM (Support Vector Machine) training; performing prediction by using an evaluation model to obtain an objective quality score; and weighting to obtain a finial quality score. The influences of a space domain, a time domainand a tridimensional perception feature on the stereoscopic video quality are combined to perform stereoscopic video quality evaluation, so that the accuracy of stereoscopic video objective quality accuracy is improved.

Description

technical field [0001] The invention relates to the field of video processing, and more specifically relates to a method for objectively evaluating the quality of stereoscopic video without reference based on multi-view feature learning. Background technique [0002] Since 3D can bring audiences a sense of three-dimensionality and a more realistic viewing experience, 3D video technology has attracted widespread attention from industrial product manufacturers and electronic product consumers. However, any link in the process of video acquisition, encoding compression, transmission, processing, and display may cause video distortion, resulting in a decrease in video quality. Therefore, the research on video quality evaluation is of great importance to promote the development of image and video processing technology. significance. [0003] Stereoscopic video quality assessment methods are divided into two methods: subjective quality assessment and objective quality assessment....

AI Technical Summary

Problems solved by technology

Compared with the objective quality evaluation method, the subjective evaluation method is cumbersome, time-consuming, and expensive, and it is difficult to be applied in a system with high real-time requirements. Therefore, researchers have begun to devote themselves to the research of objective quality evaluation methods.

Most of today's stereoscopic video objective quality assessment methods have references and require original video information. However, in practical applications, the original video is difficult to obtain, so it is particularly important to explore objective stereoscopic video quality assessment methods without reference.

Images