CN106303515B - A kind of online live video quality detecting method and device - Google Patents
A kind of online live video quality detecting method and device Download PDFInfo
- Publication number
- CN106303515B CN106303515B CN201610852837.8A CN201610852837A CN106303515B CN 106303515 B CN106303515 B CN 106303515B CN 201610852837 A CN201610852837 A CN 201610852837A CN 106303515 B CN106303515 B CN 106303515B
- Authority
- CN
- China
- Prior art keywords
- video
- image
- terminal
- scoring
- video image
- 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
Classifications
-
- 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]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
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)
Abstract
The invention discloses a kind of online live video quality detecting method and devices, belong to internet arena, the quality of the live video on various different terminals is tested with cross-terminal.The method includes:Every specified time interval, the predetermined number frame video image of each terminal transmission that starts broadcasting is obtained;The predetermined number frame video image is tested using evaluation of video images algorithm.The present invention is tested for video image.
Description
Technical field
The present invention relates to internet arena, more particularly to a kind of online live video quality detecting method and device.
Background technology
With the development of computer and Internet technology, net cast has had been to be concerned by more and more people.Actually answering
In, for optimization live video quality or other purposes, it is often necessary to test the quality of online live video.
The relevant technologies are all based on single terminal (for example, personal computer or mobile phone when testing live video quality
Deng) test live video quality, this test mode can only test the live video quality on present terminal, on other-end
Live video quality need additionally to take time to be tested again.
Invention content
An embodiment of the present invention provides a kind of online live video quality detecting method and devices, are tested with cross-terminal various
The quality of live video on different terminals.
On the one hand, a kind of online live video quality detecting method is provided, the method includes:
Every specified time interval, the predetermined number frame video image of each terminal transmission that starts broadcasting is obtained;
The predetermined number frame video image is tested using evaluation of video images algorithm.
Optionally, in one embodiment, it is to the scoring that video image is tested using evaluation of video images algorithm
First scoring, the method may also include:Obtain the video parameter that terminal reports that starts broadcasting, the video parameter include resolution ratio,
Code check, frame per second;According to the video parameter and first scoring, obtains starting broadcasting and the second of the online live video image of terminal comment
Point.
Wherein, the video parameter that terminal reports that starts broadcasting that obtains may include:Reception starts broadcasting terminal when just starting live streaming
And/or within the specified time after starting broadcasting active reporting video parameter;
Alternatively, the acquisition is started broadcasting, the video parameter that terminal reports may include:Start broadcasting terminal just started live streaming when and/or
Within the specified time after starting broadcasting, sends video parameter to the terminal that starts broadcasting and report instruction, and the terminal root that starts broadcasting described in reception
The video parameter for reporting instruction according to the video parameter and reporting.
Optionally, in one embodiment, using evaluation of video images algorithm to the predetermined number frame video image into
The scoring that row test obtains is the first scoring, and the method may also include:By the predetermined number frame video image and its first
Scoring is added in image training library.
Optionally, when image trains the video image frame number in library to reach threshold value, the method may also include:When again
It is secondary when getting predetermined number frame video image and its first scoring, the video figure that will be got again based at least one dimension
As training immediate video image in library to be compared with image;Based on comparing result, the predetermined number got again is obtained
The revised scoring of mesh frame video image, and the predetermined number frame video image and revised scoring that get again are added to image
In training library;
Wherein, the dimension includes brightness, colorfulness and contrast.
On the other hand, a kind of online live video quality test device is provided, described device may include acquisition module and place
Manage module.Wherein:
Acquisition module, for every specified time interval, obtaining the predetermined number of frames video figure of each terminal transmission that starts broadcasting
Picture;
Processing module, for being tested the predetermined number frame video image using evaluation of video images algorithm.
Optionally, in one embodiment, it is to the scoring that video image is tested using evaluation of video images algorithm
First scoring, the acquisition module can be additionally used in:The video parameter that the terminal that starts broadcasting reports is obtained, the video parameter includes differentiating
Rate, code check, frame per second.The processing module can be additionally used in:According to the video parameter and first scoring, the terminal that starts broadcasting is obtained
Second scoring of online live video image.
Wherein, the acquisition module, which obtains the video parameter that terminal reports that starts broadcasting, to be specially:The reception terminal that starts broadcasting exists
Just start live streaming when and/or within the specified time after starting broadcasting active reporting video parameter;
Alternatively, the acquisition module acquisition is started broadcasting, the video parameter that terminal reports can be specially:Starting broadcasting, terminal has just been opened
When beginning to be broadcast live and/or within the specified time after starting broadcasting, sends video parameter to the terminal that starts broadcasting and report instruction, and receive institute
It states the terminal that starts broadcasting and reports the video parameter for instructing and reporting according to the video parameter.
Optionally, in one embodiment, using evaluation of video images algorithm to the predetermined number frame video image into
The scoring that row test obtains is the first scoring, and the processing module can be additionally used in:By the predetermined number frame video image and its
First scoring is added in image training library.
Optionally, it trains the video image frame number in library to reach threshold value and get predetermined number of frames again when image to regard
When frequency image and its first scoring, the processing module can be additionally used in:Based at least one dimension by the acquisition module again
The video image got trains immediate video image in library to be compared with image;Based on comparing result, obtain again
The revised scoring of the predetermined number frame video image got, and by the predetermined number frame video image got again and amendment
Scoring is added in image training library;
Wherein, the dimension includes brightness, colorfulness and contrast.
On the other hand, a kind of terminal device is also provided, the terminal device includes:It is at least one processor, at least one
Memory, communication interface and bus.Processor, memory and communication interface are connected by bus and complete mutual communication.
For memory for storing executable program code, which includes computer-managed instruction.Memory can be high-speed RAM
Memory, it is also possible to be nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.
Processor is run and the executable program code by reading the executable program code stored in memory
Corresponding program, for executing any online live video quality detecting method recited above.
Online live video quality detecting method, device and terminal device provided in an embodiment of the present invention are utilized in main broadcaster
After terminal starts broadcasting, pass through the unified predetermined number of frames video figure for obtaining the various terminal that starts broadcasting (for example, mobile phone, notebook etc.) transmission
Picture, and the predetermined number frame video image is tested using evaluation of video images algorithm, without single on each terminal
Solely video image is tested, the quality for the live video that cross-terminal is uniformly tested on various different terminals may be implemented.
Description of the drawings
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, other are can also be obtained according to these attached drawings
Attached drawing.
Fig. 1 is a kind of flow chart of online live video quality detecting method provided in an embodiment of the present invention;
Fig. 2 is the display interface design sketch using online live video quality detecting method provided in an embodiment of the present invention;
Fig. 3 is the flow chart of another online live video quality detecting method provided in an embodiment of the present invention;
Fig. 4 is a kind of structure diagram of online live video quality test device provided in an embodiment of the present invention.
Specific implementation mode
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention
Formula is described in further detail.
Fig. 1 is the flow chart of online live video quality detecting method provided in an embodiment of the present invention.Referring to Fig.1, this hair
The online live video quality detecting method that bright embodiment provides can be described based on server, and may include:
11, every specified time interval, the predetermined number frame video image of each terminal transmission that starts broadcasting is obtained.
Wherein, the specified time interval can be set as needed, for example, 20 minutes, 10 minutes etc..When specified
When time interval is 20 minutes, i.e., obtained primary video image every 20 minutes.Certainly, examining in mitigation server stress
Consider, a relatively large interval, such as 20 minutes or more can be set.
The specific frame number of the predetermined number frame video image can also be set as needed, for example, 4 frames, 3 frames,
5 frames etc..When predetermined number is 4 frame, when reaching time interval, that is, 4 frame video images are obtained.
For example, when being divided between specified time 20 minutes and predetermined number is 4 frame, each open was obtained every 20 minutes
Broadcast 4 frame video images of terminal.
In embodiments of the present invention, can video image be obtained in several ways.A kind of side obtaining video image
Formula is:The terminal that starts broadcasting acquiescence meeting active reporting video image, can be regarded by receiving the predetermined number of frames that each terminal that starts broadcasting report
Frequency image obtains video image.Another kind obtain video image mode be:Server after the information for knowing the terminal that starts broadcasting,
Video image can be sent to the terminal that starts broadcasting report instruction, the terminal that starts broadcasting reports instruction to report video image according to this video image,
Server starts broadcasting predetermined number frame video image that terminal reports and obtains video image by receiving.
Wherein, the terminal that starts broadcasting refers to following terminal:Main broadcaster proceeds by live streaming using the terminal.In the embodiment of the present invention
In, the terminal that starts broadcasting can be mobile phone, video camera, laptop, tablet computer etc..
12, the predetermined number frame video image is tested using evaluation of video images algorithm.
Wherein, evaluation of video images algorithm can be full reference picture evaluation algorithms or non-reference picture evaluation algorithms, when
So or other suitable algorithms.Full reference picture evaluation algorithms are configurable, and tid2013 algorithms can be used.Without reference chart
As evaluation algorithms can also be configured.
After being tested the predetermined number frame video image using evaluation of video images algorithm, one can be obtained and commented
Point, the front end of this scoring back to the online website of video quality evaluation can be shown.
Online live video quality detecting method provided in an embodiment of the present invention passes through after main broadcaster is started broadcasting using terminal
It is unified to obtain the predetermined number frame video image of the various terminal that starts broadcasting (for example, mobile phone, notebook etc.) transmission, and utilize video figure
As assessment algorithm tests the predetermined number frame video image, without individually being carried out on each terminal to video image
Test, may be implemented the quality for the live video that cross-terminal is uniformly tested on various different terminals.
In embodiments of the present invention, the scoring obtained using evaluation of video images algorithm is properly termed as the first scoring, can base
The second scoring is obtained in the first scoring and video parameter.Wherein, video parameter may include resolution ratio, code check, frame per second etc..Such as
This can more fully reflecting video using the second scoring since the second scoring has considered the Video parameter informations such as resolution ratio
The quality of image.Manager can be based on the first scoring and the second scoring two indices are appreciated more fully various different terminals and upload
Video image quality.Specifically, obtaining the concrete mode of the second scoring can be:Obtain the video ginseng that the terminal that starts broadcasting reports
Number, the video parameter may include resolution ratio, code check, frame per second etc., and according to the video parameter and first scoring, obtain
Second scoring of the online live video image of the terminal that starts broadcasting.
Wherein, it obtains the video parameter that terminal reports that starts broadcasting and different modes can also be used.A kind of side obtaining video parameter
Formula is:Receive start broadcasting terminal when just starting live streaming and/or within the specified time after starting broadcasting (for example, 3 minutes after starting broadcasting
Moment) active reporting video parameter.Wherein, main broadcaster " can start to be broadcast live " by click button triggering report video parameter.That is,
Main broadcaster hits " starting to be broadcast live " button in each endpoint, and the video parameter to start broadcasting is just reported to server, and server can join video
The front end that number is distributed to the online website of video quality evaluation is shown.
Another kind obtain video parameter mode be:It is specified when the terminal that starts broadcasting just has started live streaming and/or after starting broadcasting
In time, sends video parameter to the terminal that starts broadcasting and report instruction, and terminal is started broadcasting according to the video parameter described in reception
The video parameter for reporting instruction and reporting.Wherein, after can for example, starting broadcasting in the specified time after starting broadcasting in 5 minutes.It starts broadcasting
Terminal can report video parameter when starting broadcasting incipient, can be after starting broadcasting if video parameter is reported to fail
(such as in five minutes after starting broadcasting) continue to report video parameter in specified time.If it exceeds specified time does not report into yet
Work(, the terminal that starts broadcasting at this time do not continue to report video parameter.Server also can send video when the terminal that starts broadcasting just has started live streaming
Reporting parameters instruct, if the terminal that starts broadcasting reports video parameter to fail, server can within a specified time (such as 5 minutes)
Continue to report instruction to the terminal transmission video parameter that starts broadcasting.If it exceeds specified time (such as the 5 minutes) terminal that starts broadcasting not yet on
It reports successfully, server does not continue to report instruction to the terminal transmission video parameter that starts broadcasting at this time.
It in embodiments of the present invention, can also will be described after obtaining predetermined number frame video image and its first scoring
Predetermined number frame video image and its first scoring are added in image training library, and library is trained in order to establish image.It is follow-up to be
The first obtained scoring is finely adjusted using the image training library of foundation, with more accurately reflecting video picture quality.
The embodiment of the present invention can train image the number given threshold of the video image in library, this threshold value can be according to reality
It needs to set.When image trains the number of video image in library not reach this threshold value, will can directly acquire
Video image and its first scoring are added in image training library;When image trains the number of the video image in library to reach this threshold value
When using such as under type subtle adjustment is carried out to the first scoring of the predetermined number frame video image that subsequently gets:Based on extremely
The video image got again and image are trained immediate video image in library to compare by a few dimension;Based on pair
Than as a result, obtain the revised scoring of the predetermined number frame video image got again, and the predetermined number that will be got again
Frame video image and revised scoring are added in image training library.Wherein, the dimension includes brightness, colorfulness and contrast,
The revised scoring is for the first scoring, is the amendment to the first scoring.It should be pointed out that based at least
One dimension will be during immediate video image be compared in the video image that got again and image training library
The full reference picture evaluation algorithms or non-reference picture evaluation algorithms mentioned before.
Online live video quality detecting method provided in an embodiment of the present invention can be complete with cross-terminal, real-time automatically display
The video image quality that platform main broadcaster starts broadcasting goes selection video source without artificial, the machine that starts broadcasting is selected without manually going.It is all
The video image quality to start broadcasting online can check online, video quality can be accomplished it is very clear, as shown in Figure 2.Wherein, on
" the first scoring " mentioned by face can be that tid2013 shown in Fig. 2 scores, and the second scoring can be mark shown in Fig. 2
Quasi- scoring or live scorings.As shown in Figure 2, manager can check that resolution ratio, frame per second, code check, the picture quality of full platform are commented
Divide (including the scoring of the picture quality of PC and mobile phone terminal).Wherein, scale and live scorings higher can be shown that picture quality more
Good, tid2013 scorings are lower to show that picture quality is better.
Fig. 3 is the flow chart of online live video quality detecting method provided in an embodiment of the present invention.With reference to Fig. 2, this hair
The online live video quality detecting method that bright embodiment provides may include:
31, every specified time interval, the predetermined number frame video image of each terminal transmission that starts broadcasting is obtained.
32, the predetermined number frame video image is tested using evaluation of video images algorithm, it is described pre- to obtain
First scoring of fixed number mesh frame video image.
33, the predetermined number frame video image and its first scoring are added in image training library.
34, when getting predetermined number frame video image and its first scoring again, judge regarding in image training library
Whether frequency picture frame number reaches threshold value.Wherein, it is to determine the need for calculating predetermined number of frames video that the threshold value, which is arranged,
The revised scoring of image.
35, when not up to threshold value, image is added in the predetermined number frame video image acquired and its first scoring
In training library.At this point, the revised scoring of the predetermined number frame video image acquired need not be calculated.
It 36, when a threshold is reached, will be in the video image that got again and image training library based at least one dimension
Immediate video image is compared, and is based on comparing result, obtains the predetermined number frame video image got again
Revised scoring.
37, the predetermined number frame video image and revised scoring that get again are added in image training library.
It should be pointed out that in embodiments of the present invention, the scoring obtained using evaluation of video images algorithm is commented for first
Point, the first scoring can be based on and video parameter obtains the second scoring.Wherein, video parameter may include resolution ratio, code check, frame per second
Deng.In this way, since the second scoring has considered the Video parameter informations such as resolution ratio, can more fully be reflected using the second scoring
The quality of video image.Manager can be based on the first scoring and various different terminals are appreciated more fully in the second scoring two indices
The quality of the video image of upload.Specifically, obtaining the concrete mode of the second scoring can be:Obtain regarding of starting broadcasting that terminal reports
Frequency parameter, the video parameter may include resolution ratio, code check, frame per second etc., and be scored according to the video parameter and described first,
Obtain starting broadcasting the second scoring of the online live video image of terminal.Wherein, obtaining the video parameter that terminal reports that starts broadcasting can also adopt
Differently.The concrete mode for obtaining the video parameter that terminal reports of starting broadcasting can refer to above, and details are not described herein.
In addition, in embodiments of the present invention, can also be arranged and train the video image setting one in library critical image
Value, this critical value are generally large.It, can be according to certain rule when image trains the video image in library to reach this critical value
Remove some images in image training library.For example, the image being put into earliest in image training library can be removed, figure can be removed
As the worst video image etc. of picture quality in training library.
Online live video quality detecting method provided in an embodiment of the present invention, can not only the various differences of cross-terminal test
The quality of live video in terminal, and library is trained by establishing image, it can not only eliminate to image general in the world
The dependence in training library, can also allow picture appraisal more accurate.
Fig. 4 is a kind of structure diagram of online live video quality test device provided in an embodiment of the present invention.With reference to figure
4, the device 400 of the direct broadcasting room switching may include acquisition module 401 and processing module 402.Wherein:
Acquisition module 401, for every specified time interval, obtaining the predetermined number of frames video of each terminal transmission that starts broadcasting
Image;
Processing module 402, for being tested the predetermined number frame video image using evaluation of video images algorithm.
Online live video quality test device provided in an embodiment of the present invention passes through after main broadcaster is started broadcasting using terminal
It is unified to obtain the predetermined number frame video image of the various terminal that starts broadcasting (for example, mobile phone, notebook etc.) transmission, and utilize video figure
As assessment algorithm tests the predetermined number frame video image, without individually being carried out on each terminal to video image
Test, may be implemented the quality for the live video that cross-terminal is uniformly tested on various different terminals.
Optionally, it is the first scoring to the scoring that video image is tested using evaluation of video images algorithm, it is described to obtain
Modulus block 401 can be additionally used in:The video parameter that the terminal that starts broadcasting reports is obtained, the video parameter includes resolution ratio, code check, frame
Rate;
The processing module 402 can be additionally used in:According to the video parameter and first scoring, the terminal that obtains starting broadcasting exists
Second scoring of line live video image.
Optionally, the acquisition module 401 is specifically used for:
Receive the video ginseng for the terminal active reporting when just starting live streaming and/or within the specified time after starting broadcasting that starts broadcasting
Number;
Alternatively,
When the terminal that starts broadcasting just has started live streaming and/or within the specified time after starting broadcasting, regarded to the terminal transmission of starting broadcasting
Frequency reporting parameters instruct, and the terminal that starts broadcasting described in reception reports the video parameter for instructing and reporting according to the video parameter.
Optionally, the scoring predetermined number frame video image tested using evaluation of video images algorithm
For the first scoring, the processing module 402 can be additionally used in:
The predetermined number frame video image and its first scoring are added in image training library.
Optionally, it trains the video image frame number in library to reach threshold value and get predetermined number of frames again when image to regard
When frequency image and its first scoring, the processing module 402 is additionally operable to:
It is trained in library most with image based on the video image that at least one dimension gets the acquisition module 401 again
Close video image is compared;
Based on comparing result, the revised scoring of the predetermined number frame video image got again is obtained, and will obtain again
The predetermined number frame video image and revised scoring got are added in image training library;
Wherein, the dimension includes brightness, colorfulness and contrast.
Online live video quality test device provided in an embodiment of the present invention, can not only the various differences of cross-terminal test
The quality of live video in terminal, and library is trained by establishing image, it can not only eliminate to image general in the world
The dependence in training library, can also allow picture appraisal more accurate.
It should be noted that:The online live video quality test device that above-described embodiment provides is only with above-mentioned each function mould
The division progress of block, can be as needed and by above-mentioned function distribution by different function modules for example, in practical application
It completes, i.e., the internal structure of the device of direct broadcasting room switching is divided into different function modules, to complete whole described above
Or partial function.In addition, the embodiment of the method category of the device and direct broadcasting room switching for the direct broadcasting room switching that above-described embodiment provides
In same design, specific implementation process refers to embodiment of the method, and which is not described herein again.
In addition, the embodiment of the present invention also provides a kind of terminal device, the terminal device includes:At least one processor,
At least one processor, communication interface and bus.Processor, memory and communication interface are connected by bus and are completed each other
Communication.For memory for storing executable program code, which includes computer-managed instruction.Memory can be
High-speed RAM memory, it is also possible to be nonvolatile memory (non-volatile memory), a for example, at least disk is deposited
Reservoir.
Processor is run and the executable program code by reading the executable program code stored in memory
Corresponding program, for executing any online live video quality detecting method described in above example.
Online live video quality detecting method, device and terminal device provided in an embodiment of the present invention can cross-terminal tests
Live video picture quality, and following advantageous effect can be brought to user:
1) time for saving the single direct broadcasting room video image quality of user test, video quality is checked at any time.
2) can establish and cultivate company oneself image training library, make picture appraisal more accurate, and without always according to
Image general in the world is relied to train library.
It should be noted that each embodiment in this specification is described in a progressive manner, each embodiment weight
Point explanation is all difference from other examples, and the same or similar parts between the embodiments can be referred to each other.
For device class embodiment, since it is basically similar to the method embodiment, so fairly simple, the related place ginseng of description
See the part explanation of embodiment of the method.
It should be noted that herein, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or equipment including a series of elements includes not only those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or equipment institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including institute
State in the process, method, article or equipment of element that there is also other identical elements.
One of ordinary skill in the art will appreciate that realizing that all or part of step of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, the program can be stored in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent replacement, improvement and so on should all be included in the protection scope of the present invention.
Claims (5)
1. a kind of online live video quality detecting method, which is characterized in that the method is executed by server, and includes:
Every specified time interval, the predetermined number frame video image of each terminal transmission that starts broadcasting is obtained;
The predetermined number frame video image is tested using evaluation of video images algorithm;Wherein, the video figure is utilized
The scoring tested the predetermined number frame video image as assessment algorithm is scored for first, and the method is also wrapped
It includes:
The video parameter that the terminal that starts broadcasting described in acquisition reports, the video parameter include resolution ratio, code check, frame per second;According to described
Video parameter and first scoring, obtain the second scoring of the online live video image of terminal that starts broadcasting;
The method further includes:
When the video image frame number during image trains library is not up to threshold value, by the predetermined number frame video image and its
One scoring is added in image training library;
When the video image frame number during described image trains library reaches the threshold value, regarded when getting predetermined number of frames again
When frequency image and its first scoring, the video image got again is trained with image in library based at least one dimension and is most connect
Close video image is compared;Based on comparing result, show that the amendment of the predetermined number frame video image got again is commented
Point, and the predetermined number frame video image and revised scoring that get again are added in image training library;
Wherein, the dimension includes brightness, colorfulness and contrast.
2. according to the method described in claim 1, the video parameter that terminal reports includes it is characterized in that, the acquisition is started broadcasting:
Receive the video parameter for the terminal active reporting when just starting live streaming and/or within the specified time after starting broadcasting that starts broadcasting;
Alternatively,
When the terminal that starts broadcasting just has started live streaming and/or within the specified time after starting broadcasting, video ginseng is sent to the terminal that starts broadcasting
Number reports instruction, and the terminal that starts broadcasting described in reception reports the video parameter for instructing and reporting according to the video parameter.
3. a kind of online live video quality test device, which is characterized in that described device includes:
Acquisition module, for every specified time interval, obtaining the predetermined number frame video image of each terminal transmission that starts broadcasting;
Processing module, for being tested the predetermined number frame video image using evaluation of video images algorithm;
Wherein, the scoring tested the predetermined number frame video image using the evaluation of video images algorithm is
First scoring, the acquisition module are additionally operable to:The video parameter that the terminal that starts broadcasting described in acquisition reports, the video parameter include point
Resolution, code check, frame per second;
The processing module is additionally operable to:According to the video parameter and first scoring, it is straight online to obtain the terminal that starts broadcasting
Broadcast the second scoring of video image;
The processing module is additionally operable to:It, will be described predetermined when the video image frame number during image trains library is not up to threshold value
Number frame video image and its first scoring are added in image training library;When image trains the video image frame number in library to reach
It, will be described based at least one dimension when getting to the threshold value and again predetermined number frame video image and its first scoring
The video image that acquisition module is got again trains immediate video image in library to be compared with image;It is tied based on comparison
Fruit obtains the revised scoring of the predetermined number frame video image got again, and the predetermined number of frames got again is regarded
Frequency image and revised scoring are added in image training library;
Wherein, the dimension includes brightness, colorfulness and contrast.
4. device according to claim 3, which is characterized in that the acquisition module is specifically used for:
Receive the video parameter for the terminal active reporting when just starting live streaming and/or within the specified time after starting broadcasting that starts broadcasting;
Alternatively,
When the terminal that starts broadcasting just has started live streaming and/or within the specified time after starting broadcasting, video ginseng is sent to the terminal that starts broadcasting
Number reports instruction, and the terminal that starts broadcasting described in reception reports the video parameter for instructing and reporting according to the video parameter.
5. a kind of storage medium, it is stored with computer instruction on the storage medium, when the computer instruction is run, is held
Any method in row claim 1-2.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610852837.8A CN106303515B (en) | 2016-09-26 | 2016-09-26 | A kind of online live video quality detecting method and device |
PCT/CN2017/103006 WO2018054360A1 (en) | 2016-09-26 | 2017-09-22 | Method and device for testing quality of online live video |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610852837.8A CN106303515B (en) | 2016-09-26 | 2016-09-26 | A kind of online live video quality detecting method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106303515A CN106303515A (en) | 2017-01-04 |
CN106303515B true CN106303515B (en) | 2018-08-07 |
Family
ID=57715148
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610852837.8A Active CN106303515B (en) | 2016-09-26 | 2016-09-26 | A kind of online live video quality detecting method and device |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN106303515B (en) |
WO (1) | WO2018054360A1 (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106303515B (en) * | 2016-09-26 | 2018-08-07 | 广州华多网络科技有限公司 | A kind of online live video quality detecting method and device |
CN107404656B (en) * | 2017-06-26 | 2019-01-29 | 武汉斗鱼网络科技有限公司 | Live video recommended method, device and server |
CN108040253A (en) * | 2017-12-26 | 2018-05-15 | 百度在线网络技术(北京)有限公司 | Monitor method, apparatus, equipment and the storage medium of net cast performance |
CN110381308B (en) * | 2019-07-01 | 2021-06-15 | 北京字节跳动网络技术有限公司 | System for testing live video processing effect |
CN111479161B (en) * | 2020-04-15 | 2022-04-12 | 广州虎牙科技有限公司 | Live broadcast quality data reporting method and device |
CN112752146A (en) * | 2020-05-25 | 2021-05-04 | 腾讯科技(深圳)有限公司 | Video quality evaluation method and device, computer equipment and storage medium |
CN113194306B (en) * | 2021-04-27 | 2022-07-08 | 广州虎牙科技有限公司 | Frame rate fluctuation evaluation method and device, mobile terminal, system and storage medium |
CN114222066A (en) * | 2021-12-23 | 2022-03-22 | 上海商米科技集团股份有限公司 | System, method and computer readable medium for detecting network video quality |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1809838A (en) * | 2003-06-18 | 2006-07-26 | 英国电讯有限公司 | Method and system for video quality assessment |
CN1859584A (en) * | 2005-11-14 | 2006-11-08 | 华为技术有限公司 | Video frequency broadcast quality detecting method for medium broadcast terminal device |
CN103856771A (en) * | 2012-12-03 | 2014-06-11 | 智易科技股份有限公司 | Image signal testing method and device |
CN103988500A (en) * | 2011-11-24 | 2014-08-13 | 汤姆逊许可公司 | Video quality measurement |
CN104009890A (en) * | 2014-06-10 | 2014-08-27 | 江苏省邮电规划设计院有限责任公司 | Test system and method for network quality in Internet |
CN105320598A (en) * | 2015-11-24 | 2016-02-10 | 广州华多网络科技有限公司 | Software testing method and device |
CN105472385A (en) * | 2015-11-26 | 2016-04-06 | 深圳创维数字技术有限公司 | Video decoding and image output quality detection method and system |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102413357A (en) * | 2010-09-24 | 2012-04-11 | 富泰华工业(深圳)有限公司 | Testing apparatus and testing method thereof |
CN103974061B (en) * | 2014-05-27 | 2016-05-25 | 合一网络技术(北京)有限公司 | A kind of method of testing and system play |
CN105933735A (en) * | 2016-06-20 | 2016-09-07 | 徐汕 | Automatic sorting method of live broadcast program source videos |
CN106303515B (en) * | 2016-09-26 | 2018-08-07 | 广州华多网络科技有限公司 | A kind of online live video quality detecting method and device |
-
2016
- 2016-09-26 CN CN201610852837.8A patent/CN106303515B/en active Active
-
2017
- 2017-09-22 WO PCT/CN2017/103006 patent/WO2018054360A1/en active Application Filing
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1809838A (en) * | 2003-06-18 | 2006-07-26 | 英国电讯有限公司 | Method and system for video quality assessment |
CN1859584A (en) * | 2005-11-14 | 2006-11-08 | 华为技术有限公司 | Video frequency broadcast quality detecting method for medium broadcast terminal device |
CN103988500A (en) * | 2011-11-24 | 2014-08-13 | 汤姆逊许可公司 | Video quality measurement |
CN103856771A (en) * | 2012-12-03 | 2014-06-11 | 智易科技股份有限公司 | Image signal testing method and device |
CN104009890A (en) * | 2014-06-10 | 2014-08-27 | 江苏省邮电规划设计院有限责任公司 | Test system and method for network quality in Internet |
CN105320598A (en) * | 2015-11-24 | 2016-02-10 | 广州华多网络科技有限公司 | Software testing method and device |
CN105472385A (en) * | 2015-11-26 | 2016-04-06 | 深圳创维数字技术有限公司 | Video decoding and image output quality detection method and system |
Also Published As
Publication number | Publication date |
---|---|
WO2018054360A1 (en) | 2018-03-29 |
CN106303515A (en) | 2017-01-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106303515B (en) | A kind of online live video quality detecting method and device | |
CN107027023B (en) | Based on the VoIP of neural network without reference video communication quality method for objectively evaluating | |
CN105684038B (en) | For replacing the image buffer storage of the part of image | |
CN102420712B (en) | Testing method and equipment | |
CN107071399B (en) | A kind of method for evaluating quality and device of encrypted video stream | |
US20200082199A1 (en) | Method and apparatus for inspecting burrs of electrode slice | |
CN113038287A (en) | Method and device for realizing multi-user video live broadcast service and computer equipment | |
CN108337563A (en) | Video evaluation method, apparatus, equipment and storage medium | |
CN105487970B (en) | A kind of method for showing interface and device | |
CN108495329A (en) | A kind of evaluation method and device of base station reliability | |
DE102012222185B4 (en) | Method, apparatus and computer readable medium for image registration and display | |
CN111724310B (en) | Training method of image restoration model, image restoration method and device | |
CN104935563B (en) | Method and apparatus for managing meeting | |
CN105338564B (en) | A kind of client adaptation method, client, server and system | |
CN104717670B (en) | A kind of measure of the quality of service method, apparatus and system | |
Leszczuk et al. | Determining image quality requirements for recognition tasks in generalized public safety video applications: Definitions, testing, standardization, and current trends | |
CN110505490A (en) | Multi-medium data recognition methods and system | |
CN109525877A (en) | Information acquisition method and device based on video | |
CN110427998A (en) | Model training, object detection method and device, electronic equipment, storage medium | |
CN110428368A (en) | A kind of algorithm evaluation method, device, electronic equipment and readable storage medium storing program for executing | |
CN114064445A (en) | Test method, device, equipment and computer readable storage medium | |
US20220415046A1 (en) | Method for determining video coding test sequence, electronic device and computer storage medium | |
CN110245696A (en) | Illegal incidents monitoring method, equipment and readable storage medium storing program for executing based on video | |
CN108833752A (en) | Picture Generation Method and electronic equipment | |
CN106656725B (en) | Intelligent terminal, server and information updating system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20210107 Address after: 511442 3108, 79 Wanbo 2nd Road, Nancun Town, Panyu District, Guangzhou City, Guangdong Province Patentee after: GUANGZHOU CUBESILI INFORMATION TECHNOLOGY Co.,Ltd. Address before: 511449 29 / F, building B-1, Wanda Plaza, Wanbo business district, Nancun Town, Panyu District, Guangzhou City, Guangdong Province Patentee before: GUANGZHOU HUADUO NETWORK TECHNOLOGY Co.,Ltd. |