A kind of video quality evaluation method and device

Abstract

This specification discloses a video quality evaluation method and device, which can firstly divide the video data to be evaluated into several video segments based on a preset sampling interval, and determine the feature points of each frame image in each video segment. Then, for each frame of image in each video segment, feature point matching is performed according to the feature points in the frame image and adjacent frame images, and according to the position information of the matched feature points in the two frames of images, respectively, Determine the motion intensity of the frame image, so as to determine the key frame according to the motion intensity of each frame image. Finally, the quality score of the video data is determined according to the quality score of each key frame, so as to display the video according to the quality score. The motion intensity of each frame image is determined by the position information of the matching feature points in each adjacent two frame images, and the key frame is screened based on the motion intensity of each frame image, which improves the selection quality of key frames and makes the video The quality evaluation is more accurate.

Description

technical field [0001] The present application relates to the field of video technology, and in particular, to a video quality evaluation method and device. Background technique [0002] With the development of short videos, more and more business platforms have launched short video services. Users can upload the short videos they shoot to the platform and publish them to display daily entertainment, commodity information and other content. [0003] In order to display high-quality short videos to platform users, the business platform also needs to conduct quality audits on the short videos uploaded by users, so as to push high-quality short videos to platform users according to the audit results to improve the platform user experience. [0004] At present, when evaluating the quality of a video, several key frames in the video are usually collected at equal intervals, and according to the collected key frames, the image quality evaluation model is used to determine the qual...

AI Technical Summary

Problems solved by technology

[0005] However, when shooting a short video, the movement of the user's camera and the movement of objects in the video scene often occur, so that the equal interval sampling may collect blurred key frames in the process of motion, resulting in a low accuracy rate of video quality evaluation

Images