No-reference video quality evaluation method aiming at video conference

Abstract

The invention discloses a no-reference video quality evaluation method aiming at a video conference. The no-reference video quality evaluation method aiming at the video conference comprises confirming ROI of an image; computing quantization influencing parameters of the image; computing code rate control influencing parameters of the image; and computing a video quality evaluating value. The no-reference video quality evaluation method aiming at the video conference which is formulated according to video conference characteristics such as simple conference scenes and special areas human eye interested in has the advantages of enabling a video quality evaluation result to be obtained just with videos to be evaluated, being good in the flexibility and the adaptability and high in the evaluation result accuracy, satisfying subjective perception of human eyes to the videos, being capable of obtaining accurate evaluation results of videos with different scenes and being good in universality.

Description

technical field [0001] The invention belongs to the technical field of video quality evaluation, and in particular relates to a no-reference video quality evaluation method for video conferences. Background technique [0002] With the rapid development of computer and network communication technology, people's demand for multimedia information is increasingly strong. In recent years, video-related applications cover various fields, such as video conferencing, video surveillance, and mobile TV. Among them, video conferencing is a multi-party communication that mainly transmits visual information. Human cost has very important practical application value. In video conferencing applications, video information needs to be compressed and transmitted before reaching the receiver, and these processes often result in loss of video quality. In order to obtain a better subjective effect, it is necessary to evaluate the video quality, and adjust the parameters of the encoder and tra...

AI Technical Summary

Problems solved by technology

[0004] Although the existing video quality assessment methods have achieved certain results, some relatively mature models have been formed; for example, in the literature titled Image quality assessment: From error visibility to structural similarity (IEEE Transactios on Image Processing) by Wang Zhou et al. Two video quality evaluation models based on PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity) are proposed, but there are still some problems in these two models, such as: HVS (Human Visual System) is not considered in video quality evaluation It ignores the impact of video content features on video quality, and does not consider the particularity of video conferencing scenarios, so the accuracy needs to be improved.

Images