Method for full reference type video quality assessment, apparatus for full reference type video quality assessment and video quality testing device for full reference type video quality assessment

Abstract

The invention discloses a method for full reference type video quality assessments, an apparatus for full reference type video quality assessments and a video quality testing device for full reference type video quality assessments. The method includes that six different spatial parameters are extracted from each of video components of YUV of each ROI of referencing videos and testing videos, so that a pair of difference matrixes can be achieved, utilizing the pair of difference matrixes, time and brightness rough alignment is performed on the referencing videos and the testing videos, and the result of rough alignment can be achieved. According to the result of rough alignment, time, space, brightness and chromaticity precise alignment is performed on the referencing videos and the testing videos, and the result of precise alignment of the pair of video sequences can be achieved. According to the result of precise alignment of the pair of video sequences, the space distortion analysis and the time distortion analysis are conducted to the referencing videos and the testing videos, four space indexes and one time index can be achieved, and a quality assessment result can be achieved according to the four space indexes and the one time index. According to the method, the method for full reference type video quality assessments, the apparatus for full reference type video quality assessments and the video quality testing device for full reference type video quality assessments is capable of getting better result of rough alignment, and the accuracy of the video quality assessment results can be improved.

Description

technical field [0001] The invention relates to the field of video technology, in particular to a full-reference video quality evaluation method, device and video quality tester. Background technique [0002] With the development of mobile communication and multimedia communication, image service and video service are used more and more widely and frequently. In the process of video communication, lossless video (that is, source video, reference video) is processed by encoder, communication channel, decoder, etc., which will inevitably cause damage to video quality and have a negative impact on user quality of experience (Quality of Experience, QoE). Therefore, the evaluation of video image quality has always been an important component in communication systems. [0003] Video quality assessment methods are divided into subjective quality assessment (Subjective Quality Assessment, SQA) and objective quality assessment (Objective Quality Assessment, OQA). Although subjectiv...

AI Technical Summary

Problems solved by technology

[0006] The alignment of the above existing methods in the temporal domain of the video image is very rough, therefore, the difference between the subjective quality assessment result and the subjective quality assessment result is too large, which reduces the accuracy of the video quality assessment result

Images