Stereoscopic video quality evaluation method based on binocular minimum discernible distortion model

Abstract

The invention discloses a stereoscopic video quality evaluation method based on a binocular minimum discernible distortion model, which includes: firstly building a binocular stereoscopic brightness relation model, and researching respective pixel brightness of a left viewpoint video and a right viewpoint video and the brightness relation of the pixel brightness of the left viewpoint video and the right viewpoint video when they integrate to form a stereoscopic video ; building a stereoscopic image just noticeable difference (JND) model according to background brightness and texture masking, and building a stereoscopic video JND model according to a visual threshold value masked by video interframe; obtaining a visual threshold value of a function based on space-time contrast sensitivity through the function based on space-time contrast sensitivity and relative parameters of a display device; obtaining a binocular JND model by combining the stereoscopic video JND model and the visual threshold value of the function based on space-time contrast sensitivity; and finally building a binocular perception peak signal-to-noise ratio based on stereoscopic video quality for evaluating stereoscopic video quality. The method is based on the binocular JND model, leads evaluation of stereoscopic video quality to be identical with video quality subjectively perceived by human eyes, and correctly reflects human eye visual stereoscopic video perception quality.

Description

Technical field [0001] The present invention involves a three -dimensional video quality evaluation method, especially a stereo video quality evaluation method based on Just noticeable distribution. Background technique [0002] At present, in order to meet the needs of people's real and natural reproduction of the scene, a three -dimensional TV (3DTV) that can display a three -dimensional video (3DTV), which uses dual -road videos to shoot with dual cameras and dual -road videos to be used as a 3DTV system for display terminals.When watching stereo video, the changes in the quality of the left and right videos of the three -dimensional video have an impact on the quality of the synthetic stereo video.To what extent the two videos or one of the video distortion, the changes in the quality of stereo video are perceived by people. The degree of video distortion is an indicator of the three -dimensional video quality evaluation.For the indicators of single -road video quality evalua...

AI Technical Summary

Problems solved by technology

[0006]However, the above-mentioned peak signal-to-noise ratio based on video independent pixel difference and perceptual peak signal-to-noise ratio PSPNR based on background brightness and texture masking are only applicable to single-channel video evaluation , because stereoscopic video is different from single-channel video, the fusion of two-channel video used in stereoscopic video is not simple superposition, so the JND model of single-channel video is not suitable for stereoscopic video quality evaluation of two-channel video

[0007] At present, stereoscopic video quality evaluation is divided into stereoscopic video quality subjective and stereoscopic video quality objective evaluation methods, and the stereoscopic video quality subjective evaluation method requires testers to score the test stereoscopic video , re-statistics, time-consuming, evaluation results cannot be given immediately

Stereoscopic video quality objective evaluation methods are mainly divided into two types, one is to evaluate each video with a single-channel video evaluation method, and finally obtain a stereoscopic video quality evaluation by averaging each video quality evaluation, because stereoscopic video is a dual-channel video Fusion rather than simple superposition, does not reflect the visual perception of the human eye

The other is to quantify the distortion of the edge area and smooth area of ​​the left and right viewpoints, and then use the logistic function fitting to predict the quality of the stereoscopic image. This objective evaluation method is based on statistical features, and its evaluation is easily affected by the video content. In addition, the impact of the depth perception of the real scene on the quality of the stereoscopic video is not considered, and the evaluation results cannot fully reflect the subjective perception of human vision.

So far, there are few studies on the quality evaluation methods of stereoscopic videos, and there is no commonly used method

Images