CN113949899B - Video quality assessment method and device - Google Patents
Video quality assessment method and device Download PDFInfo
- Publication number
- CN113949899B CN113949899B CN202111205034.0A CN202111205034A CN113949899B CN 113949899 B CN113949899 B CN 113949899B CN 202111205034 A CN202111205034 A CN 202111205034A CN 113949899 B CN113949899 B CN 113949899B
- Authority
- CN
- China
- Prior art keywords
- video
- original
- evaluated
- frame
- video frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001303 quality assessment method Methods 0.000 title claims abstract description 52
- 238000012545 processing Methods 0.000 claims abstract description 40
- 238000013441 quality evaluation Methods 0.000 claims description 42
- 238000000034 method Methods 0.000 claims description 34
- 238000011156 evaluation Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000009877 rendering Methods 0.000 description 2
- 241000023320 Luma <angiosperm> Species 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- OSWPMRLSEDHDFF-UHFFFAOYSA-N methyl salicylate Chemical compound COC(=O)C1=CC=CC=C1O OSWPMRLSEDHDFF-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
- H04N21/2343—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements
- H04N21/234381—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements by altering the temporal resolution, e.g. decreasing the frame rate by frame skipping
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
- H04N21/2343—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements
- H04N21/234309—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements by transcoding between formats or standards, e.g. from MPEG-2 to MPEG-4 or from Quicktime to Realvideo
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The application provides a video quality assessment method and a device, wherein the video quality assessment method comprises the following steps: acquiring an original video and a video to be evaluated corresponding to the original video; determining the frame rate to be evaluated of the video to be evaluated and the original frame rate of the original video; processing the original video based on a preset video frame processing strategy under the condition that the frame rate to be evaluated is inconsistent with the original frame rate, so as to obtain a target original video frame set, wherein the target original video frame set comprises at least one target original video frame; and determining the video score of the video to be evaluated according to the target original video frame set and the video frame set to be evaluated corresponding to the target original video frame set. According to the video quality assessment method, the video to be assessed is scored based on the target original video frame set and the video frame set to be assessed, so that an assessment result of the video to be assessed is obtained more accurately.
Description
Technical Field
The application relates to the technical field of Internet, in particular to a video quality assessment method. The present application is also directed to a video quality assessment apparatus, a computing device, and a computer-readable storage medium.
Background
Along with the continuous development of computer technology, in the video industry, the original video is transcoded, for example, the original video is transcoded to obtain videos with different resolutions, so that a user can conveniently select the resolution based on actual conditions; however, the situation that the picture quality of the video is affected will necessarily occur after the original video is transcoded, and in order to ensure the video quality of the transcoded video, the transcoded video needs to be evaluated.
Therefore, how to improve the accuracy of the video evaluation result is a problem to be solved by related technicians.
Disclosure of Invention
In view of this, embodiments of the present application provide a video quality assessment method. The application relates to a video evaluation device, a computing device and a computer readable storage medium, so as to solve the problem of low video quality evaluation accuracy in the prior art.
According to a first aspect of an embodiment of the present application, there is provided a video quality assessment method, including:
acquiring an original video and a video to be evaluated corresponding to the original video;
determining the frame rate to be evaluated of the video to be evaluated and the original frame rate of the original video;
Processing the original video based on a preset video frame processing strategy under the condition that the frame rate to be evaluated is inconsistent with the original frame rate, so as to obtain a target original video frame set, wherein the target original video frame set comprises at least one target original video frame;
and determining the video score of the video to be evaluated according to the target original video frame set and the video frame set to be evaluated corresponding to the target original video frame set.
According to a second aspect of embodiments of the present application, there is provided a video quality assessment apparatus, including:
the acquisition module is configured to acquire an original video and a video to be evaluated corresponding to the original video;
a first determination module configured to determine a frame rate to be evaluated of the video to be evaluated and an original frame rate of the original video;
the processing module is configured to process the original video based on a preset video frame processing strategy under the condition that the frame rate to be evaluated is inconsistent with the original frame rate, so as to obtain a target original video frame set, wherein the target original video frame set comprises at least one target original video frame;
and the second determining module is configured to determine a video score of the video to be evaluated according to the target original video frame set and the video frame set to be evaluated corresponding to the target original video frame set.
According to a third aspect of embodiments of the present application, there is provided a computing device comprising a memory, a processor and computer instructions stored on the memory and executable on the processor, the processor implementing the steps of the video quality assessment method when executing the computer instructions.
According to a fourth aspect of embodiments of the present application, there is provided a computer readable storage medium storing computer instructions which, when executed by a processor, implement the steps of the video quality assessment method.
According to the video quality evaluation method, an original video and a video to be evaluated corresponding to the original video are obtained; determining the frame rate to be evaluated of the video to be evaluated and the original frame rate of the original video; processing the original video based on a preset video frame processing strategy under the condition that the frame rate to be evaluated is inconsistent with the original frame rate, so as to obtain a target original video frame set, wherein the target original video frame set comprises at least one target original video frame; and determining the video score of the video to be evaluated according to the target original video frame set and the video frame set to be evaluated corresponding to the target original video frame set. The video quality evaluation method of the video quality evaluation system achieves that the original video is processed through a preset video frame processing strategy to obtain a target original video frame set, and then the video to be evaluated is scored based on the target original video frame set and the corresponding video frame set to be processed, so that a more accurate evaluation result aiming at the video to be evaluated is obtained.
Drawings
Fig. 1 is a flowchart of a first video quality assessment method according to an embodiment of the present application;
FIG. 2 is a flowchart of a second video quality assessment method according to an embodiment of the present application;
FIG. 3 is a process flow diagram of a video quality assessment method for a game video according to one embodiment of the present application;
FIG. 4 is a process flow diagram of a video quality assessment method for motion picture video according to one embodiment of the present application;
fig. 5 is a schematic structural diagram of a video quality assessment apparatus according to an embodiment of the present application;
FIG. 6 is a block diagram of a computing device according to one embodiment of the present application.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is, however, susceptible of embodiment in many other ways than those herein described and similar generalizations can be made by those skilled in the art without departing from the spirit of the application and the application is therefore not limited to the specific embodiments disclosed below.
The terminology used in one or more embodiments of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of one or more embodiments of the application. As used in this application in one or more embodiments and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present application refers to any or all possible combinations including one or more of the associated listed items.
It should be understood that, although the terms first, second, etc. may be used in one or more embodiments of the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, a first may also be referred to as a second, and similarly, a second may also be referred to as a first, without departing from the scope of one or more embodiments of the present application. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.
First, terms related to one or more embodiments of the present application will be explained.
Frame: each picture in a video or animation.
Video frame rate (fps): the number of frames displayed per second when the video is played.
Variable frame rate: the frame rates of the video at different times are not exactly the same and may float.
Constant frame rate: the frame rate of the video at all times is a certain constant value.
Rendering time stamp: the presentation time for each frame of video playback.
YUV: the data format of the original video, which is commonly used, is divided into three components, and Y represents brightness (luminence or Luma), that is, gray values; while U and V represent chromaticity (Chroma) to describe the image color and saturation for the color of the given pixel.
ffmpeg: is an open source computer program that can be used to record, convert digital audio, video, and convert it into streams.
VMAF: VMAF (Video Multimethod Assessment Fusion) developed by Netflix and developed from Netflix, a large amount of subjective data is used as a training set, and algorithms with different evaluation dimensions are fused by means of machine learning, so that an image quality evaluation standard capable of accurately reflecting subjective intention is obtained.
VMAF score: the score of VMAF standard evaluation, the higher the score, the more similar the video to be evaluated and the original video, 100 is the highest score, and 0 is the lowest score.
In the video industry, the original film of a user can be transcoded, so that different definition can be obtained through transcoding, the user can conveniently select the original film, parameters of the video can be regulated, and the suitability of the player is improved. However, transcoding necessarily results in a loss of video picture quality, and video quality assessment standards and tools are needed. The video quality evaluation requires that the frame rates of the two videos to be compared are identical, otherwise, the VMAF score is lower and the actual look and feel difference from the video is larger because the time stamps of the compared video frames are not identical. However, the frame rate of many transcoded videos to be evaluated is inconsistent with that of the original video, and the error of video quality evaluation by directly using VMAF is large.
In order to solve the problem of low accuracy of video quality assessment caused by different video frame rates, in the present application, a video quality assessment method is provided, and the present application relates to a video quality assessment apparatus, a computing device, and a computer readable storage medium, which are described in detail in the following embodiments one by one.
Fig. 1 shows a flowchart of a first video quality assessment method according to an embodiment of the present application, specifically including the following steps:
step 102: and acquiring an original video and a video to be evaluated corresponding to the original video.
The video platform generally adjusts videos played by the platform, and the video platform refers to a server for processing the videos, and specifically comprises: the server receives the original video and adjusts partial parameters of the original video, so that the suitability of the player is improved. However, the adjustment process necessarily causes a loss of video picture quality, so that the video quality of the adjusted video needs to be evaluated based on the original video.
Wherein, the original video refers to the video which is not adjusted; the video to be evaluated refers to a video obtained after the original video is adjusted.
In a specific embodiment of the present application, taking video a as an example, after a video publishing user publishes video a to a video platform, the video platform adjusts the video a to obtain an adjusted video A1, and in order to evaluate the quality of the video A1, the video a and the video A1 are obtained for subsequent evaluation of the video A1.
In practical application, the method for acquiring the original video and the video to be evaluated corresponding to the original video comprises the following steps:
receiving an original video;
transcoding the original video to obtain a video to be evaluated corresponding to the original video.
Specifically, the original video after transcoding can be obtained, and the transcoded original video can be used as the video to be evaluated, wherein video transcoding refers to converting a video code stream which is already compressed and encoded into another video code stream so as to adapt to different network bandwidths, different terminal processing capacities and different user demands.
In a specific embodiment of the present application, taking a movie video as an example, receiving the movie video, and transcoding the movie video with a video frame rate of 30fps into a video with a video frame rate of 24fps, then the video with the video frame rate of 24fps obtained by transcoding may be used as the video to be evaluated corresponding to the movie video.
Step 104: and determining the frame rate to be evaluated of the video to be evaluated and the original frame rate of the original video.
Wherein, the frame rate to be evaluated refers to the video frame rate of the video to be evaluated; the original frame rate refers to the video frame rate of the original video; the video frame rate refers to the number of frames displayed per second when the video is played, and generally the video frame rate of the original video may be a constant frame rate (i.e. the frame rate of the video is a constant value in all times), or may be a variable frame rate (i.e. the frame rates of the video may not completely coincide with each other in different times and may float), for example, in the live game, the frame rate of the live game may float due to different network speeds, but the video frame rate of the transcoded original video is a constant frame rate.
Specifically, extracting the video frame rate of the original video from the video attribute information of the original video as the original frame rate; and extracting the video frame rate of the video to be evaluated from the video attribute information of the video to be evaluated as the frame rate to be evaluated.
In a specific embodiment of the present application, taking an original video as an example of an animation video, extracting a video frame rate of 25fps (fps refers to the number of frames displayed per second when the video is played) of the animation video from video attribute information of the animation video, and extracting a video frame rate of 30fps of the video to be evaluated from video attribute information of the video to be evaluated.
By determining the video frame rate of the original video and the video frame rate of the video to be evaluated, different video quality evaluation modes are conveniently determined based on the video frame rate.
Step 106: and under the condition that the frame rate to be evaluated is inconsistent with the original frame rate, processing the original video based on a preset video frame processing strategy to obtain a target original video frame set, wherein the target original video frame set comprises at least one target original video frame.
The preset video frame processing strategy is a strategy for obtaining a target original video frame set according to the original video; in this embodiment, the target original video frame set refers to a set composed of target original video frames.
The specific method for processing the original video based on the preset video processing strategy to obtain the target original video frame set comprises the following steps:
and adjusting the video frame number of the original video based on a preset video frame adjustment strategy to obtain a target original video, wherein the target original frame rate of the target original video frame is consistent with the frame rate to be evaluated.
And comparing the frame rate to be evaluated determined in the step 104 with the original frame rate, and adjusting the video frame rate of the original video, namely the original frame rate, based on a preset video frame adjustment strategy to obtain the target original video under the condition that the frame rate to be evaluated is inconsistent with the value of the original frame rate.
The target original video is a video with the video frame rate consistent with the frame rate to be evaluated, wherein the video frame rate is obtained by adjusting the video frame rate of the original video; the target original frame rate refers to the video frame rate of the target original video; the preset video frame adjustment strategy refers to a strategy for adjusting the number of video frames of the original video.
The video frame rate of the original video is automatically adjusted to be consistent with the video to be evaluated, the video to be evaluated is subsequently evaluated based on the adjusted original video, and the obtained evaluation result aiming at the video to be evaluated is more accurate and accords with the actual look and feel of the video.
In a specific embodiment of the present application, taking an animated video as an example, a user uploads the animated video to a video platform, and the video platform transcodes the animated video to obtain a video to be evaluated with a frame rate different from an original frame rate of the animated video; and comparing the frame rate to be evaluated with the original frame rate, namely comparing the video frame rate of the animation video with the video frame rate of the video to be evaluated, and adjusting the animation video based on a preset video frame after determining that the frame rates are inconsistent to obtain the target animation video.
In practical application, the specific method for adjusting the original video based on the preset video frame adjustment strategy comprises the following steps:
determining a preset video frame adjustment strategy;
and adjusting the number of original video frames of the original video based on the preset video frame adjustment strategy and the frame rate to be evaluated.
The number of the original video frames refers to the total number of the video frames contained in the original video.
Specifically, based on a preset video frame adjustment strategy and a frame rate to be evaluated, the original frame rate of the original video is adjusted to be consistent with the frame rate to be evaluated, namely, the number of video frames played by the original video per second is adjusted to be consistent with the number of video frames played by the video per second to be evaluated.
In a specific embodiment of the present application, taking an animated video as an example, determining a preset video frame adjustment policy to adjust the number of video frames of the original video; and adjusting the number of video frames of the animation video according to a preset video frame adjustment strategy and the frame rate to be evaluated of the video to be evaluated until the video frame rate of the animation video is consistent with the video frame rate of the video to be evaluated.
In an actual application, adjusting the number of original video frames of the original video based on the preset video frame adjustment strategy and the frame rate to be evaluated includes:
under the condition that the original frame rate is smaller than the frame rate to be evaluated, determining a target original video frame in the original video according to a video frame selection rule, and adding the target original video frame to the original video;
and under the condition that the original frame rate is larger than the frame rate to be evaluated, determining a target original video frame in the original video according to a video frame selection rule, and deleting the target original video frame from the original video.
The video frame selection rule refers to a rule for selecting a target original video frame from an original video; the target original video frame refers to a video frame selected from the original video according to a video frame selection rule.
Specifically, in the case that the video frame rate of the original video is smaller than the video frame rate of the video to be evaluated, video frames need to be added to the original video so as to increase the video frame rate of the original video and thereby increase the frame rate of the original video to be consistent with the video frame rate of the video to be evaluated; under the condition that the video frame rate of the original video is larger than that of the video to be evaluated, partial video frames in the original video need to be deleted, so that the video frame rate of the original video can be reduced to be consistent with that of the video to be evaluated.
In a specific embodiment of the present application, taking an original frame rate of an original video as an example, the original frame rate of the original video is 25fps, in this embodiment, the frame rate to be evaluated of the video to be evaluated is 30fps, a target original video frame is determined in the original video based on a preset selection rule, and the target original video frame is added to the original video.
In another embodiment of the present application, taking the original frame rate of the original video as 25fps as an example, the original frame rate is 25fps in this embodiment, and the frame rate to be evaluated is 24fps, then the target original video frame determined based on the video frame selection rule is in the original video, and the determined target original video frame is deleted from the original video.
By adjusting the video frame rate of the original video to be consistent with the video frame rate of the video to be evaluated, the follow-up more accurate quality evaluation of the video to be evaluated based on the adjusted original video and the video to be evaluated is facilitated.
In practical application, determining a target original video frame in the original video according to a video frame selection rule includes:
calculating a video frame interval according to the original frame rate and the frame rate to be evaluated;
determining at least one set of video frames in the original video based on the video frame interval;
and determining a target original video frame corresponding to each video frame interval in each video frame set according to the video frame selection rule.
The video frame interval refers to the number of video frames calculated according to the original frame rate and the frame rate to be evaluated; a set of video frames refers to a set of video frames in an original video that is determined based on video frame intervals. The method for calculating the video frame interval comprises the following steps: under the condition that the number of frames of the video played by the original video in a certain second is smaller than that of the video to be evaluated, dividing the number of frames of the video played by the original video in the second by the difference value between the number of frames of the original video and the number of frames of the video to be evaluated to obtain a video frame interval, wherein if the original frame rate is z and the frame rate to be evaluated is x, the video frame interval is z/(x-z); in the case that the number of frames of the video played by the original video in a certain second is larger than that of the video to be evaluated, dividing the number of frames of the video to be evaluated played by the original video in the second by the difference between the number of frames of the video to be evaluated and the number of frames of the original video in the second to obtain a video frame interval, for example, the original frame rate is z, and the frame rate to be evaluated is x, and then the video frame interval is z/(z-x).
Specifically, calculating to obtain a video frame interval based on an original frame rate and a frame rate to be evaluated, namely deleting or adding a video frame every few video frames, and determining a video frame set in an original video based on the calculated video frame interval; and selecting the video frames from each determined video frame set according to the video frame selection rule as target original video frames corresponding to each video frame interval.
In a specific embodiment of the present application, taking an example that a video frame rate of an original video is 24fps, determining that a video frame number played in each second of the original video is 24, determining that a video frame number played in each second of a video to be evaluated is 25, calculating to obtain a value of a video frame interval to be 24 according to a video frame interval calculation method, forming a video frame time interval by every 24 video frames, forming a video frame set by every 24 video frames in the original video according to the video frame interval, and obtaining a plurality of video frame sets; and determining a target original video frame corresponding to each video frame interval in each video frame set according to a preset video frame selection rule.
And determining the target original video in the original video, so that the video frame rate of the original video is adjusted based on the target original video to be consistent with the video frame rate of the video to be evaluated.
In practical application, the specific method for determining the target original video frame corresponding to each video frame interval in each video frame set according to the video frame selection rule comprises the following steps:
determining a video frame to be evaluated of the video to be evaluated, and determining an original video frame set in the original video based on timestamp information of the video frame to be evaluated;
obtaining an original video frame score of each original video frame to be processed in the original video frame set based on the video frames to be evaluated and the original video frame set;
under the condition that the original frame rate is smaller than the frame rate to be evaluated, determining an original video frame to be processed with the highest original video frame score in the video frame set as a target original video frame;
and under the condition that the original frame rate is larger than the frame rate to be evaluated, determining the original video frame with the lowest score in the video frame set as a target original video frame.
The video frame to be evaluated refers to a video frame determined in the video to be evaluated; the time stamp information refers to the presentation time of each frame of the video playing, namely a rendering time stamp; the original video frame set refers to a set composed of original video frames, and the original video frames refer to video frames determined in the original video; the original video frames to be processed refer to video frames in an original video frame set; the original video frame score refers to a quality score of the original video frame obtained based on the video frame to be evaluated and the original video frame set.
In a specific embodiment of the present application, taking the video to be evaluated as a news video as an example, in this embodiment, the video frame rate of the news video is 25fps, and the video frame rate of the original video is 24fps; the news video includes a news video frame set { E1, E2, and }, each video frame in the news video frame set is used as a video frame to be evaluated, for example, the news video frame E2 is used as a video frame to be evaluated, the timestamp information of the news video frame E2 is determined to be 1 minute and 25 seconds, 3 original video frames near 1 minute and 25 seconds are acquired in the original video based on the timestamp information to form the original video frame set, the video frame scores of each original video frame in the news video frame 2 and the original video frame set are calculated respectively to obtain a video frame score set {92, 93, 96}, a plurality of original video frame sets are determined according to the timestamp information of each news video frame in the news video frame set, and the video frame score of each original video frame is calculated, and the calculated video frame score of each original video is shown in the following table 1.
TABLE 1
| C1 | C2 | C3 | C4 | C5 | ... | Cn | |
| E1 | 92 | 93 | 96 | 0 | 0 | ... | 0 |
| E2 | 0 | 93 | 97 | 93 | 0 | 0 | |
| E3 | 0 | 0 | 94 | 95 | 93 | 0 | |
| ... | ... | ||||||
| En | 0 | 0 | 0 | 0 | 0 | ... | n |
Where E1, E2..en represents a news video frame and C1, C2...cn represents an original video frame. The video frame rate 24fps of the original video is less than the video frame rate 25fps of the news video, the video frame interval 24 is calculated, the video frame set is determined to be { C1, C2,..c24 } according to the video frame interval, the video frame score 97 of the original video frame C3 is determined to be the highest video frame score in the video frame set, and then the original video frame C3 is taken as the target original video frame.
In practical application, after the video frame rate of the original video is adjusted to be consistent with the video to be evaluated, the timestamp information is required to be correspondingly modified, specifically, the original video is adjusted based on a preset video frame adjustment strategy, and the method for obtaining the target original video comprises the following steps:
adjusting the original video based on a preset video frame adjustment strategy to obtain an original video to be adjusted, wherein the video frame rate of the original video to be adjusted is consistent with the frame rate to be evaluated;
and adjusting the time stamp information in the original video to be adjusted according to the video to be evaluated to obtain a target original video.
Wherein, the original video to be adjusted refers to the video with the adjusted video frame rate but without the adjustment of the timestamp information.
In a specific embodiment of the present application, taking an animated video as an example, adjusting a video frame rate of the animated video to be consistent with a frame rate to be evaluated, to obtain an animated video to be adjusted; and adjusting the time stamp information of the animation video to be adjusted based on the time stamp information of the video to be evaluated, and obtaining the adjusted animation video.
The video frame rate and the time stamp information of the original video are adjusted to obtain the target original video, and the quality score of the video to be evaluated can be calculated more accurately based on the target original video and the video to be evaluated.
Step 108: and determining the video score of the video to be evaluated according to the target original video frame set and the video frame set to be evaluated corresponding to the target original video frame set.
Wherein, the video score refers to the quality score of the video to be evaluated.
Specifically, in this embodiment, a video score of a video to be evaluated is determined according to a target original video corresponding to a target original video frame set and a video to be evaluated corresponding to a video frame set to be evaluated.
In practical application, the method for calculating the video score of the video to be evaluated based on the target original video comprises the following steps:
acquiring a target original video stream of the target original video and a video stream to be evaluated of the video to be evaluated;
inputting the target original video stream and the video stream to be evaluated to a video quality evaluation module, and obtaining the video score of the video to be evaluated output by the video quality evaluation module.
The target original video stream refers to a video stream obtained by decoding an original video, for example, a YUV video stream is obtained by decoding the original video; the video stream to be evaluated refers to a video stream obtained by decoding the video to be evaluated; the video quality evaluation module refers to a module for performing quality evaluation on videos, for example, a YUV video stream of a target original video and a YUV video stream of a video to be evaluated are uploaded to a VMAF integrated by ffmpeg for performing quality evaluation, so as to obtain a video score of the video to be evaluated.
In a specific embodiment of the application, taking a target original video as a target animation video as an example, decoding the target animation video to obtain a YUV video stream of the target animation video, and decoding a video to be evaluated to obtain a YUV video stream of the video to be evaluated; and uploading the YUV video stream of the target animation video and the YUV video stream of the video to be evaluated to the VMAF integrated by the ffmpeg for quality evaluation, and obtaining the video score of the video to be evaluated.
The video evaluation module is convenient for evaluating the quality of the video stream obtained by decoding the original video and the video to be processed.
In practical application, after determining the frame rate to be evaluated of the video to be evaluated and the original frame rate of the original video, determining that the frame rate to be evaluated is consistent with the original frame rate through comparison, and if the frame rates are consistent, the processing method of the video to be evaluated includes:
acquiring a video stream to be evaluated of the video to be evaluated and an original video stream of the original video under the condition that the frame rate to be evaluated is consistent with the original frame rate;
inputting the video stream to be evaluated and the original video stream to a video quality evaluation module, and obtaining the video score of the video to be evaluated output by the video quality evaluation module.
The original video stream refers to a video stream obtained by decoding an original video.
In a specific embodiment of the application, taking an original video as an animation video as an example, decoding the animation video to obtain a YUV video stream of the animation video, and decoding a video to be evaluated to obtain a YUV video stream of the video to be evaluated; and uploading YUV video streams of the animation video and YUV video streams of the video to be evaluated to VMAF integrated by ffmpeg for quality evaluation, and outputting VMAF score by a video quality evaluation module to obtain video scores of the video to be evaluated.
According to the video quality evaluation method, the video frame rate of the original video is adjusted to be consistent with the video frame rate of the video to be evaluated, and then the video quality of the video to be evaluated is calculated based on the adjusted original video, so that the accuracy of evaluating the video to be evaluated is improved, the comparison among videos with different frame rates is realized, and the video quality evaluation system of on-demand transcoding is optimized.
Fig. 2 shows a flowchart of a second video quality assessment method according to an embodiment of the present application, specifically including the following steps:
step 202: and acquiring an original video and a video to be evaluated corresponding to the original video.
Specifically, an original video is determined, and transcoding is carried out on the original video to obtain a video to be evaluated corresponding to the original video.
Step 204: the frame rate to be evaluated of the video to be evaluated and the original frame rate of the original video are determined.
Specifically, the video frame rate of the video to be evaluated and the video frame rate of the original video are determined, namely, the number of video frames played per second of the video to be evaluated and the number of video frames played per second of the original video are determined.
Step 206: and under the condition that the frame rate to be evaluated is inconsistent with the original frame rate, determining a frame of the video to be evaluated in the video to be evaluated, and determining a target original video frame set corresponding to the frame of the video to be evaluated in the original video based on the timestamp information of the frame of the video to be evaluated.
Specifically, comparing the acquired frame rate to be evaluated of the video to be evaluated with the original frame rate of the original video, and selecting the video frame to be evaluated from the video frames to be evaluated under the condition that the frame rate to be evaluated is inconsistent with the original frame rate; and determining the time stamp information of the video frames to be evaluated, and determining the original video frames near the time stamp information in the original video based on the time stamp information to form a target original video frame set. The target original video frame set in this embodiment refers to a video frame set composed of original video frames determined in an original video based on time stamp information.
In practical application, the method for determining the target original video frame set in the original video based on the timestamp information of the video frame to be evaluated comprises the following steps:
determining at least one original video frame in the original video based on a preset video frame number threshold and timestamp information of the video frame to be evaluated;
a target set of original video frames is composed of the at least one original video frame.
The preset video frame number threshold is a predetermined number of original video frames obtained from an original video, for example, 3 original video frames are selected from the original video.
In a specific embodiment of the present application, taking a preset threshold 2 of the number of video frames as an example, if the timestamp information of the video to be evaluated is 3 points and 10 minutes, two original video frames near the time 3 points and 10 minutes are determined in the original video according to the timestamp information to form a target original video frame set.
Step 208: and calculating the video frame score of each video frame to be evaluated based on each video frame to be evaluated in the video to be evaluated and a target original video frame set corresponding to each video frame to be evaluated.
The video frame score of the video frame to be evaluated refers to a quality score of the video frame to be evaluated calculated based on the original video frame and the video frame to be evaluated.
In practical applications, the method for obtaining the video frame score of the video frame to be evaluated based on the video frame to be evaluated and the target original video frame set includes:
calculating video frame scores of each original video frame in each video frame to be evaluated and a target original video frame set corresponding to each video frame to be evaluated to form a video frame score set;
and selecting a target video frame score from the video frame score set as the video frame score of the video frame to be evaluated.
Wherein, the video frame scoring set refers to a set composed of video frame scores of original video frames; the target video frame score refers to one of the video frame scores of the original video in the video frame score set, and the video frame score with the highest score can be selected directly in the video frame score set or directly selected based on actual requirements as the video frame score of the video frame to be evaluated.
In a specific embodiment of the present application, taking the video frame score of the target original video frame as the highest video frame score in the video frame frequency-division set as an example, calculating the video frame score of each original video { original video frame 1, original video frame 2..original video frame n } in the video frame to be evaluated and the target original video frame set, and obtaining a video frame score set {95, 93..n }; and determining that the video frame score 95 of the original video frame 1 is the highest video frame score in the video frame score set, and taking the video frame score of the original video frame 1 as the video frame score of the video frame to be evaluated.
Step 210: and calculating the video score of the video to be evaluated according to the video frame score of each video frame to be evaluated.
The video score refers to a video quality score of the video to be evaluated.
Specifically, each video frame in the video to be evaluated is taken as the video frame to be evaluated, and the video frame score of each video frame to be evaluated is calculated and determined; a video frame score for the video under evaluation is calculated based on the video frame score for each video frame under evaluation.
In practical application, calculating the video score of the video to be evaluated according to the video frame score of each video frame to be evaluated in the video to be evaluated includes:
counting video frame scores of each video frame to be evaluated to form a video frame score set to be evaluated;
and calculating the video score of the video to be evaluated based on a preset video scoring rule and the video frame score set to be evaluated.
The video frame scoring set to be evaluated refers to a set formed by video frame scores of each video frame to be evaluated in the video to be evaluated; the preset video scoring rule refers to a preset video scoring rule, for example, an average value of video frame scores in a video frame scoring set to be evaluated is calculated, and the calculated average value is used as a video scoring rule of the video scoring of the video to be evaluated.
In a specific embodiment of the present application, taking a video to be evaluated as an example of an animation video, the animation video includes a video frame set { video frame 1, video frame 2..video frame n }, and counting video frame scores of each video frame in the video frame set to form a video frame score set {93, 95..n } to be evaluated; the preset video scoring rule is that an average value of video frame scores in a video frame scoring set to be evaluated is used as a video score of the video to be evaluated, the average value of video frame scores is calculated to be 95 based on the video frame scoring set {93, 95..n } to be evaluated, and the average value of video frame scores is used as a video score of the animation video.
According to the video quality evaluation method, the video frame scoring set is obtained by calculating the video frame score of each video to be evaluated in the video to be evaluated, and the score of the video to be evaluated is determined based on the video frame scoring set, so that the accuracy of scoring the video to be evaluated is improved.
The video quality evaluation method provided in the present application is further described below with reference to fig. 3 by taking an application of the video evaluation method to game video as an example. Fig. 3 shows a process flow chart of a video quality evaluation method applied to a game video according to an embodiment of the present application, which specifically includes the following steps:
Step 302: and receiving an original video, and transcoding the original video to obtain a video to be evaluated corresponding to the original video.
In a specific embodiment of the present application, taking an original video as a game video, receiving the game video, and transcoding the game video to obtain a game video to be evaluated corresponding to the original game video.
Step 304: and determining the frame rate to be evaluated of the video to be evaluated and the original frame rate of the original video.
In a specific embodiment of the present application, in the above example, the video frame rate of the game video is obtained as 24fps in the video attribute information of the game video, and the video frame rate of the game video to be evaluated is determined as 25fps in the video attribute information of the game video to be evaluated.
Step 306: comparing the frame rate to be evaluated with the original frame rate, and adjusting the original frame rate under the condition that the frame rate to be evaluated is inconsistent with the original frame rate.
Comparing the frame rate to be evaluated with the original frame rate, and adjusting the number of original video frames of the original video based on a preset video frame adjustment strategy and the frame rate to be evaluated under the condition that the frame rate to be evaluated is inconsistent with the original frame rate, wherein the specific mode is as follows: under the condition that the original frame rate is smaller than the frame rate to be evaluated, determining a target original video frame in the original video according to a video frame selection rule, and adding the target original video frame to the original video; and under the condition that the original frame rate is larger than the frame rate to be evaluated, determining a target original video frame in the original video according to a video frame selection rule, and deleting the target original video frame from the original video.
The specific method for determining the target original video frame in the original video comprises the following steps: calculating a video frame interval according to the original frame rate and the frame rate to be evaluated; determining at least one set of video frames in the original video based on the video frame interval; determining a video frame to be evaluated in the video to be evaluated, and determining an original video frame set in the original video based on timestamp information of the video frame to be evaluated; obtaining an original video frame score of each original video frame to be processed in the original video frame set based on the video frames to be evaluated and the original video frame set; under the condition that the original frame rate is smaller than the frame rate to be evaluated, determining an original video frame to be processed with the highest original video frame score in the video frame set as a target original video frame; and under the condition that the original frame rate is larger than the frame rate to be evaluated, determining the original video frame with the lowest score in the video frame set as a target original video frame.
In a specific embodiment of the present application, the above example is used to compare the video frame rate of the game video 24fps with the video frame rate of the game video to be evaluated 25fps, determine that the video frame rate of the game video is smaller than the video frame rate of the video to be evaluated, determine the target game video frame in the video frames of the game video according to the video frame selection rule, calculate the video frame interval to be 24 based on the video frames of the game video and the video frame rate of the game video to be evaluated, copy one target game video frame every 24 game video frames in the game video, and add the target game video frame to the game video. The method for determining the target game video frame in the original video specifically comprises the following steps: video frame interval 24 is calculated and a set of video frames is determined in the game video based on video frame interval 24, including { X1, X2,..x24 }, { X25, X26,..x48 } and the like. Determining each video frame in the video to be evaluated as a video frame of the game to be evaluated, and determining a set of video frames of the game corresponding to each video frame to be evaluated in the video of the game based on each video frame to be evaluated; acquiring video frame scores of each game video frame in a game video frame set based on each video frame to be evaluated and a game video frame set corresponding to each video frame to be evaluated; every 24 game video frames in the game video, determining the game video frame with the highest video frame score in the 24 game video frames as a target game video frame, copying the target game video frame and adding the target game video frame into the game video frame, and adjusting the video frame rate of the game video to be consistent with the video frame rate of the game video to be evaluated after the video frame is added into the game video, so as to obtain the game video to be adjusted.
Step 308: and adjusting the time stamp information in the original video to be adjusted according to the video to be evaluated to obtain the target original video.
In a specific embodiment of the present application, along the above example, the timestamp information of the game video to be adjusted is modified based on the timestamp information of the game video to be evaluated, so that the correspondence between the timestamp information of the game video to be evaluated and the video frame is consistent with the correspondence between the timestamp information of the game video to be adjusted and the video frame, and the target game video, that is, the game video with the consistent video frame rate with the game video to be evaluated, is obtained.
Step 310: acquiring a target original video stream of the target original video and a video stream to be evaluated of the video to be evaluated; inputting the target original video stream and the video stream to be evaluated to a video quality evaluation module, and obtaining the video score of the video to be evaluated output by the video quality evaluation module.
In a specific embodiment of the present application, along with the above example, decoding a target game video to obtain a target game video stream, and decoding a game video to be evaluated to obtain a game video stream to be evaluated; and uploading the target game video stream and the game video stream to be evaluated to the VMAF integrated by the ffmpeg for quality evaluation, and obtaining the video score of the game video to be evaluated.
According to the video quality assessment method, the video frame rate of the original video is automatically adjusted to be consistent with the video frame rate of the video to be assessed, and then the quality assessment is carried out on the video to be assessed, so that a more accurate assessment result is obtained.
The video quality evaluation method provided in the present application is further described below with reference to fig. 4 by taking an application of the video quality evaluation method to movie video as an example. Fig. 4 shows a process flow chart of a video quality evaluation method applied to a movie video according to an embodiment of the present application, which specifically includes the following steps:
step 402: and acquiring an original video and a video to be evaluated corresponding to the original video.
In a specific embodiment of the present application, taking a movie video as an example, a movie video is obtained, and the movie video is transcoded to obtain a movie video to be evaluated corresponding to the movie video.
Step 404: the frame rate to be evaluated of the video to be evaluated and the original frame rate of the original video are determined.
In a specific embodiment of the present application, along with the above example, the video frame rate of the movie video is determined to be 25fps, and the video frame rate of the video to be evaluated is determined to be 30fps.
Step 406: and under the condition that the frame rate to be evaluated is inconsistent with the original frame rate, determining the video frames to be evaluated in the video to be evaluated, and determining a target original video frame set in the original video based on a preset video frame quantity threshold value and timestamp information of the video frames to be evaluated.
In a specific embodiment of the present application, following the above example, a frame of a movie video to be evaluated is determined in the movie video to be evaluated, timestamp information of the frame of the movie video to be evaluated is determined for 5 minutes and 12 seconds, and 3 game video frames near the time corresponding to the timestamp information are determined in the game video according to the timestamp information to form a game video frame set.
Step 408: calculating video frame scores of each original video frame in the video frame to be evaluated and the target original video frame set to form a video frame score set; and selecting a target video frame score from the video frame score set as the video frame score of the video to be evaluated.
In a specific embodiment of the present application, along the above example, calculating a video frame score of each game video in a set { game video frame 1, game video frame 2, game video frame 3} of a movie video frame to be evaluated, and obtaining a set {95, 93, 97} of video frame scores; the highest video frame score 97 is selected from the set of video frame scores as the video frame score for the video frame of the movie to be evaluated.
Step 410: counting video frame scores of each video frame to be evaluated to form a video frame score set to be evaluated; and calculating the video score of the video to be evaluated based on a preset video scoring rule and the video frame score set to be evaluated.
In a specific embodiment of the present application, the above example is used, and video frame scores of each game video in the game video to be evaluated are calculated according to step 408 to form a game video frame score set to be evaluated; and calculating the average value of the video frame scores in the video frame score set of the game to be evaluated, and taking the average value as the game score of the video of the game to be evaluated.
According to the video quality assessment method, the original video frames near the time stamp information in the original video are determined to be subjected to video frame scoring based on the time stamp information of the video frames to be assessed, the highest video frame scoring is selected to be used as the video frame scoring of the video frames to be assessed, and the average value of the video frame scoring of each video frame in the video frames to be assessed is calculated to be used as the video scoring of the video to be assessed, so that the accuracy of video quality assessment of videos with different frame rates is improved.
Corresponding to the above method embodiment, the present application further provides an embodiment of a video quality evaluation device, and fig. 5 shows a schematic structural diagram of a video quality evaluation device according to an embodiment of the present application. As shown in fig. 5, the apparatus includes:
the acquisition module 502 is configured to acquire an original video and a video to be evaluated corresponding to the original video;
A first determining module 504 configured to determine a frame rate to be evaluated of the video to be evaluated and an original frame rate of the original video;
a processing module 506, configured to process the original video based on a preset video frame processing policy to obtain a target original video frame set, where the target original video frame set includes at least one target original video frame, where the frame rate to be evaluated is inconsistent with the original frame rate;
a second determination module 508 is configured to determine a video score of the video to be evaluated from the set of target original video frames and the set of video frames to be evaluated corresponding to the set of target original video frames.
In a specific embodiment of the present application, the processing module 506 is further configured to:
and adjusting the number of video frames of the original video based on a preset video frame adjustment strategy to obtain a target original video, wherein the target original frame rate of the target original video is consistent with the frame rate to be evaluated.
Optionally, the acquisition module 502 is further configured to:
receiving an original video;
transcoding the original video to obtain a video to be evaluated corresponding to the original video.
Optionally, the processing module 506 is further configured to:
determining a preset video frame adjustment strategy;
and adjusting the number of original video frames of the original video based on the preset video frame adjustment strategy and the frame rate to be evaluated.
Optionally, the processing module 506 is further configured to:
under the condition that the original frame rate is smaller than the frame rate to be evaluated, determining a target original video frame in the original video according to a video frame selection rule, and adding the target original video frame to the original video;
and under the condition that the original frame rate is larger than the frame rate to be evaluated, determining a target original video frame in the original video according to a video frame selection rule, and deleting the target original video frame from the original video.
Optionally, the processing module 506 is further configured to:
calculating a video frame interval according to the original frame rate and the frame rate to be evaluated;
determining at least one set of video frames in the original video based on the video frame interval;
and determining a target original video frame corresponding to each video frame interval in each video frame set according to the video frame selection rule.
Optionally, the processing module 506 is further configured to:
determining a video frame to be evaluated in the video to be evaluated, and determining an original video frame set in the original video based on timestamp information of the video frame to be evaluated;
obtaining an original video frame score of each original video frame to be processed in the original video frame set based on the video frames to be evaluated and the original video frame set;
under the condition that the original frame rate is smaller than the frame rate to be evaluated, determining an original video frame to be processed with the highest original video frame score in the video frame set as a target original video frame;
and under the condition that the original frame rate is larger than the frame rate to be evaluated, determining the original video frame with the lowest score in the video frame set as a target original video frame.
Optionally, the processing module 506 is further configured to:
adjusting the original video based on a preset video frame adjustment strategy to obtain an original video to be adjusted, wherein the video frame rate of the original video to be adjusted is consistent with the frame rate to be evaluated;
and adjusting the time stamp information in the original video to be adjusted according to the video to be evaluated to obtain a target original video.
Optionally, the second determining module 508 is further configured to:
acquiring a target original video stream of the target original video and a video stream to be evaluated of the video to be evaluated;
inputting the target original video stream and the video stream to be evaluated to a video quality evaluation module, and obtaining the video score of the video to be evaluated output by the video quality evaluation module.
The apparatus further includes an acquisition sub-module configured to:
acquiring a video stream to be evaluated of the video to be evaluated and an original video stream of the original video under the condition that the frame rate to be evaluated is consistent with the original frame rate;
inputting the video stream to be evaluated and the original video stream to a video quality evaluation module, and obtaining the video score of the video to be evaluated output by the video quality evaluation module.
Optionally, the processing module 506 is further configured to:
determining a video frame to be evaluated in the video to be evaluated;
and determining a target original video frame set corresponding to the video frame to be evaluated in the original video based on the timestamp information of the video frame to be evaluated.
Optionally, the second determining module 508 is further configured to:
Calculating a video frame score of each video frame to be evaluated based on each video frame to be evaluated in the video to be evaluated and a target original video frame set corresponding to each video frame to be evaluated;
and calculating the video score of the video to be evaluated according to the video frame score of each video frame to be evaluated.
Optionally, the processing module 506 is further configured to: :
determining at least one original video frame in the original video based on a preset video frame number threshold and timestamp information of the video frame to be evaluated;
a target set of original video frames is composed of the at least one original video frame.
Optionally, the processing module 506 is further configured to: :
calculating video frame scores of each original video frame in each video frame to be evaluated and a target original video frame set corresponding to each video frame to be evaluated to form a video frame score set;
and selecting a target video frame score from the video frame score set as the video frame score of the video to be evaluated.
Optionally, the second determining module 508 is further configured to:
counting video frame scores of each video frame to be evaluated to form a video frame score set to be evaluated;
And calculating the video score of the video to be evaluated based on a preset video scoring rule and the video frame score set to be evaluated.
According to the video quality evaluation device, an acquisition module acquires an original video and a video to be evaluated corresponding to the original video; a first determining module for determining a frame rate to be evaluated of the video to be evaluated and an original frame rate of the original video; the processing module is used for processing the original video based on a preset video frame processing strategy under the condition that the frame rate to be evaluated is inconsistent with the original frame rate, so as to obtain a target original video frame set, wherein the target original video frame set comprises at least one target original video frame; and the second determining module is used for determining the video score of the video to be evaluated according to the target original video frame set and the video frame set to be evaluated corresponding to the target original video frame set. According to the video quality assessment device, the original video is processed through the preset video frame processing strategy to obtain the target original video frame set, and the video to be assessed is scored based on the target original video frame set and the corresponding video frame set to be treated, so that a more accurate assessment result aiming at the video to be assessed is obtained
The above is a schematic scheme of a video quality evaluation apparatus of the present embodiment. It should be noted that, the technical solution of the video quality assessment device and the technical solution of the video quality assessment method belong to the same concept, and details of the technical solution of the video quality assessment device, which are not described in detail, can be referred to the description of the technical solution of the video quality assessment method.
Fig. 6 illustrates a block diagram of a computing device 600 provided in accordance with an embodiment of the present application. The components of computing device 600 include, but are not limited to, memory 610 and processor 620. The processor 620 is coupled to the memory 610 via a bus 630 and a database 650 is used to hold data.
Computing device 600 also includes access device 640, access device 640 enabling computing device 600 to communicate via one or more networks 660. Examples of such networks include the Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. The access device 640 may include one or more of any type of network interface (e.g., a Network Interface Card (NIC)) whether wired or wireless, such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, a worldwide interoperability for microwave access (Wi-MAX) interface, an ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC) interface, and so forth.
In one embodiment of the present application, the above-described components of computing device 600, as well as other components not shown in FIG. 6, may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device illustrated in FIG. 6 is for exemplary purposes only and is not intended to limit the scope of the present application. Those skilled in the art may add or replace other components as desired.
Computing device 600 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), mobile phone (e.g., smart phone), wearable computing device (e.g., smart watch, smart glasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or PC. Computing device 600 may also be a mobile or stationary server.
Wherein the processor 620, when executing the computer instructions, implements the steps of the video quality assessment method.
The foregoing is a schematic illustration of a computing device of this embodiment. It should be noted that, the technical solution of the computing device and the technical solution of the video quality assessment method belong to the same concept, and details of the technical solution of the computing device, which are not described in detail, can be referred to the description of the technical solution of the video quality assessment method.
An embodiment of the present application also provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the steps of the video quality assessment method as described above.
The above is an exemplary version of a computer-readable storage medium of the present embodiment. It should be noted that, the technical solution of the storage medium and the technical solution of the video quality assessment method belong to the same concept, and details of the technical solution of the storage medium, which are not described in detail, can be referred to the description of the technical solution of the video quality assessment method.
The foregoing describes specific embodiments of the present application. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The computer instructions include computer program code that may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, randomAccess Memory), an electrical carrier signal, a telecommunication signal, a software distribution medium, and so forth. It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.
It should be noted that, for the sake of simplicity of description, the foregoing method embodiments are all expressed as a series of combinations of actions, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily all necessary for the present application.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
The above-disclosed preferred embodiments of the present application are provided only as an aid to the elucidation of the present application. Alternative embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the teaching of this application. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. This application is to be limited only by the claims and the full scope and equivalents thereof.
Claims (17)
1. A video quality assessment method, comprising:
acquiring an original video and a video to be evaluated corresponding to the original video;
determining the frame rate to be evaluated of the video to be evaluated and the original frame rate of the original video;
processing the original video based on a preset video frame processing strategy under the condition that the frame rate to be evaluated is inconsistent with the original frame rate, and obtaining a target original video frame set, wherein the target original video frame set comprises at least one target original video frame, and the target original video frame is determined based on the following mode: determining a video frame to be evaluated in the video to be evaluated, and determining an original video frame set in the original video based on timestamp information of the video frame to be evaluated; obtaining an original video frame score of each original video frame to be processed in the original video frame set based on the video frames to be evaluated and the original video frame set; under the condition that the original frame rate is smaller than the frame rate to be evaluated, determining an original video frame to be processed with the highest original video frame score in a video frame set as a target original video frame; under the condition that the original frame rate is larger than the frame rate to be evaluated, determining an original video frame to be processed with the lowest original video frame score in a video frame set as a target original video frame;
And determining the video score of the video to be evaluated according to the target original video frame set and the video frame set to be evaluated corresponding to the target original video frame set.
2. The video quality assessment method according to claim 1, wherein processing the original video based on a preset video frame processing policy to obtain a target set of original video frames, comprises:
and adjusting the number of video frames of the original video based on a preset video frame adjustment strategy to obtain a target original video, wherein the target original frame rate of the target original video is consistent with the frame rate to be evaluated.
3. The method for evaluating video quality according to claim 1, wherein obtaining an original video and a video to be evaluated corresponding to the original video comprises:
receiving an original video;
transcoding the original video to obtain a video to be evaluated corresponding to the original video.
4. The video quality assessment method according to claim 2, wherein adjusting the number of video frames of the original video based on a preset video frame adjustment strategy comprises:
determining a preset video frame adjustment strategy;
and adjusting the number of original video frames of the original video based on the preset video frame adjustment strategy and the frame rate to be evaluated.
5. The video quality assessment method according to claim 4, wherein adjusting the number of original video frames of the original video based on the preset video frame adjustment strategy and the frame rate to be assessed comprises:
under the condition that the original frame rate is smaller than the frame rate to be evaluated, determining a target original video frame in the original video according to a video frame selection rule, and adding the target original video frame to the original video;
and under the condition that the original frame rate is larger than the frame rate to be evaluated, determining a target original video frame in the original video according to a video frame selection rule, and deleting the target original video frame from the original video.
6. The video quality assessment method according to claim 5, wherein determining a target original video frame in said original video according to a video frame selection rule comprises:
calculating a video frame interval according to the original frame rate and the frame rate to be evaluated;
determining at least one set of video frames in the original video based on the video frame interval;
and determining a target original video frame corresponding to each video frame interval in each video frame set according to the video frame selection rule.
7. The video quality assessment method according to claim 2, wherein adjusting the number of video frames of the original video based on a preset video frame adjustment strategy to obtain a target original video comprises:
adjusting the original video based on a preset video frame adjustment strategy to obtain an original video to be adjusted, wherein the video frame rate of the original video to be adjusted is consistent with the frame rate to be evaluated;
and adjusting the time stamp information in the original video to be adjusted according to the video to be evaluated to obtain a target original video.
8. The video quality assessment method according to claim 2, wherein determining a video score of the video to be assessed from the target set of original video frames and a set of video frames to be assessed corresponding to the target set of original video frames, comprises:
acquiring a target original video stream of the target original video and a video stream to be evaluated of the video to be evaluated;
inputting the target original video stream and the video stream to be evaluated to a video quality evaluation module, and obtaining the video score of the video to be evaluated output by the video quality evaluation module.
9. The video quality assessment method according to any one of claims 1 to 7, further comprising, after determining a frame rate to be assessed of the video to be assessed and an original frame rate of the original video:
acquiring a video stream to be evaluated of the video to be evaluated and an original video stream of the original video under the condition that the frame rate to be evaluated is consistent with the original frame rate;
inputting the video stream to be evaluated and the original video stream to a video quality evaluation module, and obtaining the video score of the video to be evaluated output by the video quality evaluation module.
10. The video quality assessment method according to claim 1, wherein processing the original video based on a preset video frame processing policy to obtain a target set of original video frames, comprises:
determining a video frame to be evaluated in the video to be evaluated;
and determining a target original video frame set corresponding to the video frame to be evaluated in the original video based on the timestamp information of the video frame to be evaluated.
11. The video quality assessment method according to claim 10, wherein determining a video score of the video to be assessed from the target set of original video frames and a set of video frames to be assessed corresponding to the target set of original video frames comprises:
Calculating a video frame score of each video frame to be evaluated based on each video frame to be evaluated in the video to be evaluated and a target original video frame set corresponding to each video frame to be evaluated;
and calculating the video score of the video to be evaluated according to the video frame score of each video frame to be evaluated.
12. The video quality assessment method according to claim 10, wherein determining a target original video frame set corresponding to the video frame to be assessed in the original video based on the time stamp information of the video frame to be assessed, comprises:
determining at least one original video frame in the original video based on a preset video frame number threshold and timestamp information of the video frame to be evaluated;
a target set of original video frames is composed of the at least one original video frame.
13. The video quality assessment method according to claim 11, wherein calculating a video frame score for each video frame under assessment based on each video frame under assessment in the video under assessment and a set of target raw video frames corresponding to each video frame under assessment, comprises:
calculating video frame scores of each original video frame in each video frame to be evaluated and a target original video frame set corresponding to each video frame to be evaluated to form a video frame score set;
And selecting a target video frame score from the video frame score set as the video frame score of the video to be evaluated.
14. The video quality assessment method according to claim 11, wherein calculating a video score of each video frame under assessment from the video frame score of the video under assessment comprises:
counting video frame scores of each video frame to be evaluated to form a video frame score set to be evaluated;
and calculating the video score of the video to be evaluated based on a preset video scoring rule and the video frame score set to be evaluated.
15. A video quality assessment apparatus, comprising:
the acquisition module is configured to acquire an original video and a video to be evaluated corresponding to the original video;
a first determination module configured to determine a frame rate to be evaluated of the video to be evaluated and an original frame rate of the original video;
the processing module is configured to process the original video based on a preset video frame processing strategy under the condition that the frame rate to be evaluated is inconsistent with the original frame rate, so as to obtain a target original video frame set, wherein the target original video frame set comprises at least one target original video frame, and the target original video frame is determined based on the following modes: determining a video frame to be evaluated in the video to be evaluated, and determining an original video frame set in the original video based on timestamp information of the video frame to be evaluated; obtaining an original video frame score of each original video frame to be processed in the original video frame set based on the video frames to be evaluated and the original video frame set; under the condition that the original frame rate is smaller than the frame rate to be evaluated, determining an original video frame to be processed with the highest original video frame score in a video frame set as a target original video frame; under the condition that the original frame rate is larger than the frame rate to be evaluated, determining an original video frame to be processed with the lowest original video frame score in a video frame set as a target original video frame;
And the second determining module is configured to determine a video score of the video to be evaluated according to the target original video frame set and the video frame set to be evaluated corresponding to the target original video frame set.
16. A computing device comprising a memory, a processor, and computer instructions stored on the memory and executable on the processor, wherein the processor, when executing the computer instructions, performs the steps of the method of any one of claims 1-14.
17. A computer readable storage medium storing computer instructions which, when executed by a processor, implement the steps of the method of any one of claims 1 to 14.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111205034.0A CN113949899B (en) | 2021-10-15 | 2021-10-15 | Video quality assessment method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111205034.0A CN113949899B (en) | 2021-10-15 | 2021-10-15 | Video quality assessment method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113949899A CN113949899A (en) | 2022-01-18 |
| CN113949899B true CN113949899B (en) | 2024-03-12 |
Family
ID=79330877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111205034.0A Active CN113949899B (en) | 2021-10-15 | 2021-10-15 | Video quality assessment method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113949899B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114760506B (en) * | 2022-04-11 | 2024-02-09 | 北京字跳网络技术有限公司 | Video transcoding evaluation method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016096396A (en) * | 2014-11-12 | 2016-05-26 | 日本電信電話株式会社 | Video quality identity determination device, method, and program |
| CN109743591A (en) * | 2019-01-04 | 2019-05-10 | 广州虎牙信息科技有限公司 | The method of video frame alignment |
| CN110290421A (en) * | 2019-08-01 | 2019-09-27 | 北京达佳互联信息技术有限公司 | Frame per second method of adjustment, device, computer equipment and storage medium |
| CN112714309A (en) * | 2020-12-22 | 2021-04-27 | 北京百度网讯科技有限公司 | Video quality evaluation method, device, apparatus, medium, and program product |
-
2021
- 2021-10-15 CN CN202111205034.0A patent/CN113949899B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016096396A (en) * | 2014-11-12 | 2016-05-26 | 日本電信電話株式会社 | Video quality identity determination device, method, and program |
| CN109743591A (en) * | 2019-01-04 | 2019-05-10 | 广州虎牙信息科技有限公司 | The method of video frame alignment |
| CN110290421A (en) * | 2019-08-01 | 2019-09-27 | 北京达佳互联信息技术有限公司 | Frame per second method of adjustment, device, computer equipment and storage medium |
| CN112714309A (en) * | 2020-12-22 | 2021-04-27 | 北京百度网讯科技有限公司 | Video quality evaluation method, device, apparatus, medium, and program product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113949899A (en) | 2022-01-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP3793142B2 (en) | Moving image processing method and apparatus | |
| JP2020010331A (en) | Method for improving image quality | |
| CN110267098B (en) | Video processing method and terminal | |
| US10354394B2 (en) | Dynamic adjustment of frame rate conversion settings | |
| Yu et al. | Predicting the quality of compressed videos with pre-existing distortions | |
| JP2003087785A (en) | Method of converting format of encoded video data and apparatus therefor | |
| US11290345B2 (en) | Method for enhancing quality of media | |
| CN110225340B (en) | Control method and device for video coding, computing equipment and storage medium | |
| Zhang et al. | Satisfied-user-ratio modeling for compressed video | |
| US20220188357A1 (en) | Video generating method and device | |
| US12003782B2 (en) | Pixel filtering for content | |
| CN112435244A (en) | Live video quality evaluation method and device, computer equipment and storage medium | |
| CN113949899B (en) | Video quality assessment method and device | |
| CN116170650A (en) | Video frame inserting method and device | |
| Saha et al. | Perceptual video quality assessment: The journey continues! | |
| CN112565887A (en) | Video processing method, device, terminal and storage medium | |
| CN113316001B (en) | Video alignment method and device | |
| CN111340101A (en) | Stability evaluation method and device, electronic equipment and computer readable storage medium | |
| US20220078447A1 (en) | Method and apparatus for assessing quality of vr video | |
| US10764578B2 (en) | Bit rate optimization system and method | |
| CN114387440A (en) | Video clipping method and device and storage medium | |
| CN108933945B (en) | GIF picture compression method, device and storage medium | |
| CN114494037A (en) | Image data processing method, image data processing device, electronic device, and storage medium | |
| CN115396700B (en) | Data processing method and device, computing equipment and storage medium | |
| US20240119637A1 (en) | Image synthesis method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |