Video quality evaluation method, device and apparatus and storage medium

A video quality and video technology, applied in video data retrieval, video data clustering/classification, television, etc., can solve problems such as simple, incapable of accurate and comprehensive description of video content, incapable of accurate evaluation of video quality, and achieve Improve timeliness and improve accuracy

Active Publication Date: 2020-07-10
BIGO TECH PTE LTD
View PDF12 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that the video content used is too simple to accurately and comprehe

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Video quality evaluation method, device and apparatus and storage medium
  • Video quality evaluation method, device and apparatus and storage medium
  • Video quality evaluation method, device and apparatus and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] figure 1 It is a flow chart of the video quality assessment method in Embodiment 1 of the present invention. This embodiment is applicable to the situation of evaluating video quality. The method can be performed by video quality assessment. The video quality assessment device can be composed of hardware and / or software accomplish. The video quality evaluation device may be composed of two or more physical entities, or may be composed of one physical entity, and is generally integrated in computer equipment.

[0030] Specifically, such as figure 1 As shown, the video quality assessment method provided in this embodiment mainly includes the following steps:

[0031] S110. Decode the video to be evaluated to obtain image sequence and audio information.

[0032] It should be noted that the video server receives a large number of videos produced and uploaded by users every day. The server needs to eliminate illegal videos from all videos uploaded by users, and screen ou...

Embodiment 2

[0052] image 3 It is the flowchart of the video quality assessment method in the second embodiment of the present invention; this embodiment is applicable to the situation of evaluating video quality, and this embodiment further optimizes the video quality assessment method, such as image 3 As shown, the optimized video quality assessment method mainly includes the following steps:

[0053] S310. Decode the video to be evaluated to obtain image sequence and audio information.

[0054] S320. Using the motion feature extraction network to perform feature extraction on each frame of image to obtain a motion feature vector.

[0055] In this embodiment, before using the motion feature extraction network to perform feature extraction for each frame of image, it is necessary to build and train the motion feature extraction network. Further, building and training the action feature extraction network mainly includes the following steps: obtaining a set of training videos, and obta...

Embodiment 3

[0081] On the basis of the foregoing embodiments, this embodiment provides a preferred example. Figure 4 It is a flow chart of the video quality assessment method in Embodiment 3 of the present invention; as Figure 4 As shown, the above-mentioned video quality assessment method mainly includes the following steps:

[0082] S401. Obtain a video to be evaluated. The video to be evaluated may be a video just recorded by the user and uploaded to the server, or a video stored in the server without quality evaluation. Preferably, the video to be evaluated in this embodiment is preferably a short video recorded by a user.

[0083] S402. Decode the video to be evaluated to obtain an image sequence composed of multiple images arranged in a certain order.

[0084] S403. After the video to be evaluated is decoded, audio information of the video to be evaluated may be obtained. Audio information includes background music and language information of characters in the video to be eval...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a video quality evaluation method, device and apparatus and a storage medium. The method comprises the following steps: firstly, decoding a video to obtain an image sequence and audio information, then extracting an action feature vector and a face feature vector in the image sequence, extracting an audio feature vector in the audio information, and constructing a video feature vector according to at least one of the action feature vector, the face feature vector and the audio feature vector; and finally, determining a quality score of a to-be-evaluated video accordingto the video feature vector. According to the embodiment, the quality score of the to-be-evaluated video can be determined according to at least one or more vectors of the action feature vector, the face feature vector and the audio feature vector extracted from the to-be-evaluated video, the real-time performance of video quality evaluation can be realized through the video, and the accuracy of high-quality video evaluation is improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of video detection, and in particular, to a video quality evaluation method, device, device, and storage medium. Background technique [0002] With the development of Internet technology, short video application programs (Application, APP) are more and more widely used. Short video apps create and upload a large number of short videos every day. After eliminating illegal videos, high-quality videos need to be selected from the remaining videos and pushed to the audience. A premium video is one that has the potential to be liked by viewers. Whether you can accurately and comprehensively select high-quality videos from the remaining videos to show the audience determines key indicators such as the viewing time, storage volume, and download volume of short video APPs. [0003] In the prior art, there are mainly two types of high-quality video evaluation methods commonly used. One is to ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/00G06T7/00G06T9/00H04N21/233H04N21/234
CPCG06T7/0002G06T9/00H04N21/23418H04N21/233G06T2207/10016G06T2207/30168G06V40/161G06V40/168G06V40/20G06V20/40G06V20/46G06F16/75G06F16/783H04N21/2743H04N17/00G06T2207/30201G06T2207/20084G06V10/993G06V20/41G06N3/08
Inventor 刘运刘汇川梁柱锦
Owner BIGO TECH PTE LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap