CN106341683A - Panoramic video quality judgment method and panoramic video quality judgment system - Google Patents
Panoramic video quality judgment method and panoramic video quality judgment system Download PDFInfo
- Publication number
- CN106341683A CN106341683A CN201610717604.7A CN201610717604A CN106341683A CN 106341683 A CN106341683 A CN 106341683A CN 201610717604 A CN201610717604 A CN 201610717604A CN 106341683 A CN106341683 A CN 106341683A
- Authority
- CN
- China
- Prior art keywords
- score value
- panoramic video
- judged
- evaluation
- quality
- 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.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/154—Measured or subjectively estimated visual quality after decoding, e.g. measurement of distortion
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/004—Diagnosis, testing or measuring for television systems or their details for digital television systems
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 panoramic video quality judgment method and a panoramic video quality judgment system. The method comprises the following steps: acquiring multiple sub evaluation score groups of a to-be-judged panoramic video, wherein each sub evaluation score group includes multiple sub evaluation scores of the to-be-judged panoramic video in multiple dimensions; determining multiple evaluation scores corresponding to the multiple sub evaluation score groups based on the weighted sum of the multiple sub evaluation scores in each sub evaluation score group; and determining a measure score for judging the quality of the to-be-judged panoramic video at least according to the multiple evaluation scores. According to the panoramic video quality judgment method and the panoramic video quality judgment system of the invention, the quality of a panoramic video can be judged more accurately by comprehensively considering the influence of different dimensions of different panoramic videos on the quality of panoramic videos.
Description
Technical field
The present invention relates to areas of information technology, particularly to a kind of panoramic video Quality estimation method and system.
Background technology
In the near future, traditional single-view videos service will be replaced by the panoramic video service of various visual angles, because
Panoramic video can give people the visual experience of more immersion by band.At present, in the new coded system for panoramic video not
Before out, panoramic video is still encoded using traditional planar video coded system.Although existing Video coding skill
Art is very advanced, but the particularity due to panoramic video own characteristic, yet suffer from much urgently to be resolved hurrily in panorama video code
Problem.One of problem is exactly the establishment of the quality evaluation system with regard to panoramic video.
At present, because panoramic video is just popular, it is specifically designed for quality evaluating method the imperfection of panoramic video, each
Standards body does not set up the effective quality evaluation system of panoramic video yet.Therefore, traditional Y-PSNR (psnr,
It is the abbreviation of " peak signal to noise ratio ") it is still the method for evaluating video quality of main flow.
But inventor finds during realizing the present invention, it is not particularly suited for the method that psnr carries out quality evaluation
Panoramic video, because the distortion of each of video pixel all can be to the overall quality evaluation of video in this appraisement system
Produce impact.
Content of the invention
The disclosure provides a kind of panoramic video Quality estimation method and system, can not accurately be sentenced with least solving prior art
The technical problem of disconnected panoramic video quality.
In a first aspect, providing a kind of panoramic video Quality estimation method, methods described includes:
Obtain the many height for panoramic video to be judged and evaluate score value group, described sub- evaluation score value group is included for described
Panoramic video to be judged evaluates score value in many height of multiple dimensions；
The weighted sum determination being evaluated the many height evaluation score values in score value group based on every height is commented corresponding to the plurality of son
Multiple evaluation score values of valency score value group；
Determine that the tolerance of the quality for panoramic video to be judged described in judging is divided according at least to the plurality of score value of evaluating
Value.
Second aspect, provides a kind of panoramic video Quality estimation system, and described system includes:
Evaluation information acquisition module, the many height for obtaining for panoramic video to be judged evaluate score value group, described son
Evaluate score value group to include evaluating score value for described panoramic video to be judged in many height of multiple dimensions；
Evaluation of estimate determining module, the weighted sum evaluating score value for being evaluated the many height in score value group based on every height is determined
Multiple evaluation score values corresponding to the plurality of sub- evaluation score value group；
Tolerance score value determining module is complete for waiting described in judging to judge for determining according at least to the plurality of evaluation score value
The tolerance score value of the quality of scape video.
The third aspect, provides a kind of computer-readable non-transient storage medium, is stored with one in described storage medium
Individual or multiple programs including execute instruction, described execute instruction can be by electronic equipment (including but not limited to computer, service
Device, or the network equipment etc.) read and execute, for executing the correlation step in said method embodiment, for example:
Obtain the many height for panoramic video to be judged and evaluate score value group, described sub- evaluation score value group is included for described
Panoramic video to be judged evaluates score value in many height of multiple dimensions；
The weighted sum determination being evaluated the many height evaluation score values in score value group based on every height is commented corresponding to the plurality of son
Multiple evaluation score values of valency score value group；
Determine that the tolerance of the quality for panoramic video to be judged described in measuring is divided according at least to the plurality of score value of evaluating
Value.
Fourth aspect, provides a kind of electronic equipment, comprising:
At least one memorizer, for storage running instruction；
At least one processor, for executing the operating instruction of described memory storage, to execute:
Obtain the many height for panoramic video to be judged and evaluate score value group, described sub- evaluation score value group is included for described
Panoramic video to be judged evaluates score value in many height of multiple dimensions；
The weighted sum determination being evaluated the many height evaluation score values in score value group based on every height is commented corresponding to the plurality of son
Multiple evaluation score values of valency score value group；
Determine that the tolerance of the quality for panoramic video to be judged described in measuring is divided according at least to the plurality of score value of evaluating
Value.
The panoramic video Quality estimation method of the embodiment of the present invention, system, storage medium and electronic equipment, right by obtaining
Panoramic video is in the evaluation score value of different dimensions, and the score value of evaluating of each dimension comprehensive achieves the degree to panoramic video quality
Amount.Especially, it is weighted summation to determine to whole aphorama by score values are evaluated to the many height of panoramic video different dimensions
The design of the overall merit score value of frequency can targetedly increase the son evaluation of the dimension larger on the quality impact of panoramic video
The weight of score value, thus more accurately judge the quality of panoramic video.
Brief description
In order to be illustrated more clearly that the technical scheme of the embodiment of the present invention, below will be to required use in embodiment description
Accompanying drawing be briefly described it should be apparent that, drawings in the following description are some embodiments of the present invention, for ability
For the those of ordinary skill of domain, on the premise of not paying creative work, can also be obtained other attached according to these accompanying drawings
Figure.
Fig. 1 is the flow chart of an embodiment of panoramic video Quality estimation method of the present invention；
Fig. 2 is the flow chart of another embodiment of panoramic video Quality estimation method of the present invention；
Fig. 3 is the flow chart of the embodiment of step s23 in Fig. 2；
Fig. 4 is the schematic diagram of an embodiment of panoramic video Quality estimation system of the present invention；
Fig. 5 is the signal of the embodiment of tolerance score value determining module in the panoramic video Quality estimation system of the present invention
Figure；
Fig. 6 is the schematic diagram of another embodiment of panoramic video Quality estimation system of the present invention；
Fig. 7 is the flow process of another embodiment of tolerance score value determining module of the panoramic video Quality estimation system of the present invention
Figure；
Fig. 8 is the hardware architecture diagram of the electronic equipment of panoramic video Quality estimation method of the execution present invention.
Specific embodiment
Purpose, technical scheme and advantage for making the embodiment of the present invention are clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described it is clear that described embodiment is
The a part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment being obtained under the premise of not making creative work, broadly falls into the scope of protection of the invention.
It should be noted that in the case of not conflicting, the embodiment in the application and the feature in embodiment can phases
Mutually combine.
The present invention can be used in numerous general or special purpose computing system environment or configuration.For example: personal computer, service
Device computer, handheld device or portable set, laptop device, multicomputer system, the system based on microprocessor, top set
Box, programmable consumer-elcetronics devices, network pc, minicomputer, mainframe computer, include any of the above system or equipment
Distributed computing environment etc..
The present invention can be described in the general context of computer executable instructions, such as program
Module.Usually, program module includes execution particular task or the routine realizing particular abstract data type, program, object, group
Part, data structure etc..The present invention can also be put into practice in a distributed computing environment, in these distributed computing environment, by
The remote processing devices connected by communication network are executing task.In a distributed computing environment, program module is permissible
It is located in the local and remote computer-readable storage medium including storage device.
Last in addition it is also necessary to explanation, herein, such as first and second or the like relational terms be used merely to by
One entity or operation are made a distinction with another entity or operation, and not necessarily require or imply these entities or operation
Between there is any this actual relation or order.And, term " inclusion ", "comprising", not only include those key elements, and
And also include other key elements of being not expressly set out, or also include intrinsic for this process, method, article or equipment institute
Key element.In the absence of more restrictions, the key element being limited by sentence " including ... " is it is not excluded that including described wanting
Also there is other identical element in the process of element, method, article or equipment.
As shown in figure 1, the panoramic video Quality estimation method of one embodiment of the invention, methods described includes:
S11, the many height obtaining for panoramic video to be judged evaluate score value group, and described sub- evaluation score value group includes being directed to
Described panoramic video to be judged evaluates score value in many height of multiple dimensions；
The weighted sum that s12, the many height evaluated based on every height in score value group evaluate score value determines corresponding to the plurality of
Son evaluates multiple evaluation score values of score value group；
S13, evaluate, according at least to the plurality of, the degree that score value determines the quality for panoramic video to be judged described in judging
Amount score value.
The panoramic video Quality estimation method of the present embodiment pass through obtain to panoramic video different dimensions evaluation score value,
And the score value of evaluating of each dimension of synthesis achieves the tolerance to panoramic video quality.Especially, will be to panoramic video different dimensional
Many height of degree are evaluated score value and are weighted summation to determine that the design of the overall merit score value to whole panoramic video can be with pin
The son of the dimension larger on the quality impact of panoramic video on the increasing of property evaluates the weight of score value, thus more accurately judging
The quality of panoramic video.
Many height in the present embodiment evaluate each of score value groups evaluate score value group respectively by a user to institute
Viewing panoramic video to be judged different dimensions evaluation beaten score value composition.For example, the multiple dimensions in the present embodiment
Degree can include but is not limited to panoramic video total quality dimension, panoramic video seriality dimension, the dizzy degree of panoramic video
Dimension, panoramic video visible distortion block dimension.User is watched can be according to right in watching process after judging panoramic video
The perception of panoramic video total quality is given a mark in panoramic video total quality dimension.User is watching aphorama to be judged
Can be given a mark according to the seriality of panoramic video in watching process after frequency.User is watched can after judging panoramic video
To be given a mark to panoramic video to self-inflicted dizzy degree according to panoramic video in watching process.User can also be
Watch the number of the distortion block in panoramic video according to what is observed in watching process after judging panoramic video to carry out
The marking of panoramic video visible distortion block dimension.
Evaluate score value group in the son obtaining the many height evaluation score values including different dimensions coming from different user
Afterwards, the many height evaluation score values each height evaluated in score value group are weighted suing for peace, and determine each user couple with final
The evaluation score value that the quality of panoramic video to be judged is judged.Can be by adjusting the son evaluation of different dimensions in the present embodiment
The weight coefficient of score value evaluates the size of the impact to panoramic video Quality estimation for the score value come the son to determine different dimensions.For example,
When judging that panoramic video quality mainly considers the seriality of panoramic video then by the son corresponding to panoramic video seriality dimension
The weight coefficient evaluating score value increases.When the equal son considering different dimensions evaluates the impact to panoramic video Quality estimation for the score value
When, then it is that the many height corresponding to different dimensions evaluate the equal weight coefficient of score value configuration.
By above-mentioned steps can determine multiple different users to the evaluation score value of same panoramic video to be judged and with
One user multiple evaluation score values to multiple differences panoramic video to be judged.
It can be by statistics at random that treating of obtaining in the present embodiment judges that many height of panoramic video evaluate score value groups
User's viewing be uploaded to the marking acquisition it being carried out in multiple dimensions after judging panoramic video of the Internet.For example, will
Panoramic video to be judged is uploaded to the video website of a certain online viewing, when user has watched online can after judging panoramic video
Carry out the marking of different dimensions with the panoramic video watched faced by broadcast page.Numerous due to the network user, using this
Mode will obtain the evaluation score value of magnanimity, judge more accurately judging of panoramic video quality thus ensure that and treating.
It can also be by selecting survey that treating of obtaining in the present embodiment judges that many height of panoramic video evaluate score value groups
The mode that examination person is tested is watched and after judging panoramic video, the panoramic video to be judged watched being carried out in multiple dimensions
After marking, statistics obtains.For example, process of the test includes:
Tester selectes: selectes a number of tester (quantity should be no less than 15 people), and they can not be this
The expert in field.The range of age of experimenter should be sufficiently large, should include masculinity and femininity in sex simultaneously, and men and women
Number should equalize as far as possible.The vision of experimenter should be normal, this normal inclusion normal stereoscopic vision ability and distinguishing
Color ability.Simultaneously it is contemplated that experimenter needs to wear the helmet and tested, therefore it is required that all of experimenter can not wear myopia
Glasses participate in test.
Tester's training process: experimenter needs to inform purpose and the flow process of this experiment of experimenter (that is, tester),
Then experimenter needs to watch preprepared training video to be familiar with the process of test and marking, the quality model of training video
The mass range enclosing the test video watched with experimenter of trying one's best in part of detecting is consistent.Watch training video
Afterwards, it will have the clear one's mind of doubt time of 3～10 minutes, during this period, experimenter will be responsible for answering experimenter with regard in experiment
Hold the query with experiment flow aspect, so that they more fully understand this experiment.
Training result proof procedure: the main purpose of checking link is whether checking experimenter can after training link
Correctly understand that experiment is intended to, and effective, with a high credibility subjective scores are provided.In this link, experimenter will be wanted
Seek the panoramic video of the different distortion level of viewing and given a mark after viewing.Note the panoramic video of experimenter's viewing here not
It is same as the panoramic video that they watch in official testing link.After this link, have the correction time of 3～5 minutes, such as
Fruit experimenter needs again to explain experimental rules and experiment content not over checking link, experimenter, treats that experimenter understands
Afterwards, re-start the proof procedure of checking link, until be verified, experimenter is allowed for access next link.
Test process: after experimenter after verifying link, be put into formal test link.In test link, it is subject to
Examination person is required to watch a series of panoramic video, and carries out subjective marking after completely having watched a video.In general,
Test video is divided into two classes, and a class is reference video, and this class video is generally undistorted video；Another kind of video is by joining
Examine the video that video obtains after treatment, this class video typically has different degrees of distortion.This two classes video is placed in
Together, playing sequence is random order.In order to avoid the memory effect of experimenter, by same reference video obtain different
Distortion video can not continuously be play.Test link is made up of several annelets, and each annelet is by t1, t2 and marking three
It is grouped into, t1 is generally 10s, is video playback and viewing time, after video playback, have the of short duration blank screen time, one
As be t2=3s, its objective is to remind this video of experimenter to play and terminate, link of giving a mark please be prepared to enter into, after t2, just
Enter the subjective marking time for this video, marking is put into next annelet after terminating, that is, watch next test video.
In order to avoid the visual fatigue effect of experimenter is it is proposed that be entirely less than 30 minutes the total time of test link, if test regards
Frequently excessively it is proposed that being classified as multiple test links, after a test link, after experimenter should be by sufficient rest
The next one of being allowed for access tests link.
Scoring process: experimenter needs from different dimensions, panoramic video to be given a mark.For example, overall from panoramic video
Quality dimensions and two dimensions of panoramic video seriality dimension.We represent that with a of panoramic video total quality dimension is commented
Valency score value, b evaluates score value come the son to represent panoramic video seriality dimension.The son of panoramic video total quality dimension evaluates score value
It is up to 5 points, be divided into five class: very well (4-5 divides), good (3-4 divides), general (2-3 divides), poor (1-2 divides), very poor (0-1
Point).The son of panoramic video seriality dimension is evaluated score value highest and is divided into 5 points, is divided into 5 class: very continuous (4-5 divides), continuously
(3-4 divides), general (2-3 divides), discontinuous (1-2 divides), very discontinuous (0-1 divides).Note, these fractions are continuous, that is, be subject to
Examination person can get the fraction of similar 4.3 or 3.2 etc according to the impression of oneself, and not necessarily is the fraction of integer.When certain
When the average value that fraction that one experimenter is beaten substantially is graded with all experimenters is very remote, it is tested that we will give up this
The fraction that person is beaten to panoramic video.
In certain embodiments, determine for panoramic video to be judged described in measuring according at least to the plurality of evaluation score value
The tolerance score value of quality be:
Determine that the plurality of arithmetic mean of instantaneous value evaluating score value is the quality for panoramic video to be judged described in judging
Tolerance score value.
By multiple users, the arithmetic mean of instantaneous value of the tolerance score value to same panoramic video judges aphorama to the present embodiment
The quality of frequency, it is to avoid the fluctuation of the tolerance score value that unique user leads to because of individual reason cause to panoramic video Quality estimation
Distortion.
In the present embodiment, only need to be judged panoramic video sequences without reference to panoramic video sequences in test video.?
In this case, we can only get the absolute subjective scores of each test video, and referred to as (Mean Opinion Score is Mean Opinion Score
One tolerance score value).Here, we set sijRepresent the evaluation score value that experimenter i is beaten, test video j to test video j
Mean Opinion Score can be calculated by below equation.
In formula (1), njFor watching the quantity of the experimenter of video j, Mean Opinion Score is higher, shows the master of this video
Appearance quality is better.
As shown in Fig. 2 in certain embodiments, panoramic video Quality estimation method also includes:
S21, the multiple evaluation with reference to son of reference panoramic video corresponding to described panoramic video to be judged for the acquisition are divided
Value group, described reference son evaluation score value group includes dividing with reference to sub evaluation in the multiple of multiple dimensions with reference to panoramic video for described
Value；
S22, based on every group with reference to son evaluate score value group in multiple with reference to son evaluate score values weighted sums determine correspond to
The plurality of multiple reference evaluation score values evaluating score value group with reference to son；
S23, described determine the quality for panoramic video to be judged described in measuring according at least to the plurality of score value of evaluating
Tolerance score value be: according to the plurality of evaluation score value with multiple determine for panorama to be judged described in measuring with reference to evaluating score value
The tolerance score value of the quality of video.
In the present embodiment, refer to undistorted panoramic video with reference to panoramic video.Treating with reference to corresponding to panoramic video
Judge that panoramic video is then to have different degrees of distortion video by obtain after treatment with reference to panoramic video.The present embodiment
In consider different user treat the evaluation score value judging panoramic video and corresponding reference video and with reference to evaluate score value can
More accurately to judge the quality of panoramic video to be judged.
In certain embodiments, the evaluation that multiple evaluation score values include multiple users panoramic video to be judged to difference divides
Value, the plurality of reference is evaluated score value and is included multiple users to the reference panoramic video corresponding to difference panoramic video to be judged
With reference to evaluation score value.
As shown in figure 3, according to the plurality of evaluation score value and multiple determining for waiting to sentence described in measuring with reference to evaluating score value
The tolerance score value of the quality of disconnected panoramic video includes:
S31, it is based respectively on the evaluation score value of each of the plurality of user user panoramic video to be judged to difference
With with reference to evaluating score value, measure score values with the many height determining the quality for measuring a certain panoramic video to be judged；
S32, determine quality for measuring described a certain panoramic video to be judged based on the plurality of sub- tolerance score value
Tolerance score value.
In the present embodiment, include in test video including panoramic video sequences to be judged (mistake with reference to panoramic video again
True video).Can judge different by calculating panoramic video to be judged and with reference to the average suggestion difference between panoramic video
The subjective quality height of panoramic video to be judged, its calculation process is as follows:
Calculate difference d with reference to the Mean Opinion Score between panoramic video and distortion video firstij.
In formula (2), sijIt is the evaluation score value that experimenter i is beaten to distortion video j,It is that experimenter i regards to distortion
Score value is evaluated in the reference that the corresponding reference video of frequency j is beaten.
Wherein, miThe number of the video watched by testee i.Same testee i is obtained to being watched by formula (3)
Multipair difference distortion videos and the reference evaluation score value to reference video beaten of corresponding reference video and distortion video
Evaluate difference d between score valueijArithmetic mean of instantaneous value μi.Obtain testee i by formula (4) evaluation of distortion video j is divided
Difference d between score value is evaluated in the reference of value and the corresponding reference video of distortion video jijStandard deviation sigmai.Combined by formula (5)
Arithmetic mean of instantaneous value that formula (3) determines and the standard deviation that formula (4) determines determine the score value z of tolerance distortion video j massij
(corresponding to the son tolerance score value of the quality for measuring a certain panoramic video to be judged determining in step s31).
Afterwards, by zijValue Linear Mapping to [0,100], the value after mapping is usedTo represent.In the present embodiment, each is subject to
The z value of survey person i marking gained obeys standard normal distribution (σ=1), and 99% z value can fall between scope [- 3,3].In order to allow
Result is more directly perceived and obeys hundred-mark system, by formula (6) by zijValue Linear Mapping to [0,100]:
Finally, corresponding average suggestion difference dmos of j-th distortion videoj(in step s32, it is based on the plurality of sub- degree
The tolerance score value of the quality by measuring described a certain panoramic video to be judged that amount score value determines) can be by based on below equation
Obtain:
In formula (7), njRepresent the number of the experimenter of j-th distortion video of viewing.It is apparent that distortion video
Dmos fraction is less, shows that distortion video is less with respect to the distortion of reference video, distortion video quality is higher.
Correlation function mould can be realized by hardware processor (hardware processor) in the embodiment of the present invention
Block.
It should be noted that for aforesaid each method embodiment, in order to be briefly described, therefore it is all expressed as a series of
Action merge, but those skilled in the art should know, the present invention is not limited by described sequence of movement because
According to the present invention, some steps can be carried out using other orders or simultaneously.Secondly, those skilled in the art also should know
Know, embodiment described in this description belongs to preferred embodiment, involved action and the module not necessarily present invention
Necessary.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and does not have the portion described in detail in certain embodiment
Point, may refer to the associated description of other embodiment.
As shown in figure 4, the another aspect present invention also provides a kind of panoramic video Quality estimation system 400, described system bag
Include:
Evaluation information acquisition module 410, the many height for obtaining for panoramic video to be judged evaluate score value group, described
Son is evaluated score value group and is included evaluating score value for described panoramic video to be judged in many height of multiple dimensions；
Evaluation of estimate determining module 420, evaluates the weighted sum of score value for evaluating the many height in score value group based on every height
Determine the multiple evaluation score values corresponding to the plurality of sub- evaluation score value group；
Tolerance score value determining module 430, for determining for waiting to sentence described in measuring according at least to the plurality of evaluation score value
The tolerance score value of the quality of disconnected panoramic video.
The panoramic video Quality estimation system of the present embodiment, is divided in the evaluation of different dimensions to panoramic video by obtaining
Value, and the score value of evaluating of each dimension comprehensive achieves the tolerance to panoramic video quality.Especially, will be different to panoramic video
It is permissible to determine the design of the overall merit score value to whole panoramic video that many height evaluation score values of dimension are weighted summation
The son targetedly increasing the dimension larger on the quality impact of panoramic video evaluates the weight of score value, thus more accurately sentencing
The quality of disconnected panoramic video.
As shown in figure 5, in certain embodiments, tolerance score value determining module 430 includes:
Average calculation unit 431, for calculating the plurality of arithmetic mean of instantaneous value evaluating score value；
First tolerance score value determining unit 432, for determining that described arithmetic mean of instantaneous value is complete for waiting described in measuring to judge
The tolerance score value of the quality of scape video.
As shown in fig. 6, also including in some embodiments of panoramic video Quality estimation system 400 ' of the present invention:
With reference to evaluation information acquisition module 410 ', complete for reference corresponding to described panoramic video to be judged for the acquisition
The multiple of scape video evaluate score value group with reference to sub, and described reference is evaluated score value group and included for described reference panoramic video many
The multiple of individual dimension evaluate score value with reference to son；
With reference to evaluation of estimate determining module 420 ', evaluate for evaluating multiple reference in score value group with reference to son based on every group
The weighted sum determination of score value evaluates score value corresponding to the plurality of with reference to multiple references that son evaluates score value group；
Described tolerance score value determining module 430 ' is used for true according to the plurality of evaluation score value and multiple reference evaluation score value
Calmly it is used for the tolerance score value of the quality of panoramic video to be judged described in measuring.
In certain embodiments, the plurality of evaluation score value includes the evaluation of multiple users panoramic video to be judged to difference
Score value, the plurality of reference is evaluated score value and is included multiple users to the reference panoramic video corresponding to difference panoramic video to be judged
Reference evaluate score value；
As shown in fig. 7, tolerance score value determining module 430 includes:
Son tolerance score value determining unit 431 ', is used for being based respectively on each of the plurality of user user and difference is treated
Judge the evaluation score value of panoramic video and with reference to evaluating score value, be used for determination measuring the quality of a certain panoramic video to be judged
Many height measure score value；
Second tolerance score value determining unit 432 ', for based on the plurality of sub- tolerance score value determine for measure described certain
The tolerance score value of the quality of one panoramic video to be judged.
In certain embodiments, multiple dimensions at least include: panoramic video total quality dimension, and panoramic video seriality is tieed up
Degree, panoramic video dizzy degree dimension, panoramic video visible distortion block dimension.
The panoramic video Quality estimation system of the embodiments of the present invention can be used for executing the aphorama of the embodiment of the present invention
Frequency Quality estimation method, and reach the technology that the panoramic video Quality estimation method of the embodiments of the present invention is reached accordingly
Effect, repeats no more here.
The embodiment of the present application additionally provides a kind of nonvolatile computer storage media, described computer-readable storage medium storage
There are computer executable instructions, this computer executable instructions can perform the panoramic video quality in above-mentioned any means embodiment
Determination methods.
Fig. 8 is the hardware knot of the electronic equipment of execution panoramic video Quality estimation method that another embodiment of the application provides
Structure schematic diagram, as shown in figure 8, this equipment includes:
One or more processors 810 and memorizer 820, in Fig. 8 taking a processor 810 as a example.
The equipment of execution panoramic video Quality estimation method can also include: input equipment 830 and output device 840.
Processor 810, memorizer 820, input equipment 830 and output device 840 can pass through bus or other modes
Connect, in Fig. 8 taking connected by bus as a example.
Memorizer 820, as a kind of non-volatile computer readable storage medium storing program for executing, can be used for storing non-volatile software journey
Panoramic video Quality estimation method pair in sequence, non-volatile computer executable program and module, such as the embodiment of the present application
Programmed instruction/module (for example, the evaluation information acquisition module 410 shown in accompanying drawing 4, evaluation of estimate determining module 420 and the tolerance answered
Score value determining module 430).Processor 810 pass through to run the non-volatile software program in memorizer 820 of being stored in, instruction with
And module, thus the various function application of execute server and data processing, that is, realize said method embodiment panoramic video
Quality estimation method.
Memorizer 820 can include storing program area and storage data field, and wherein, storing program area can store operation system
Application program required for system, at least one function；Storage data field can store making according to panoramic video Quality estimation device
With data of being created etc..Additionally, memorizer 820 can include high-speed random access memory, can also include non-volatile
Memorizer, for example, at least one disk memory, flush memory device or other non-volatile solid state memory parts.Real at some
Apply in example, memorizer 820 is optional to include the memorizer remotely located with respect to processor 810, and these remote memories can lead to
Cross network connection to panoramic video Quality estimation device.The example of above-mentioned network include but is not limited to the Internet, intranet,
LAN, mobile radio communication and combinations thereof.
Input equipment 830 can the numeral of receives input or character information, and produce the processing meanss with list items operation
User setup and function control relevant key signals input.Output device 840 may include the display devices such as display screen.
One or more of module stores in described memorizer 820, when by one or more of processors
During 810 execution, execute the panoramic video Quality estimation method in above-mentioned any means embodiment.
The said goods can perform the method that the embodiment of the present application is provided, and possesses the corresponding functional module of execution method and has
Beneficial effect.The not ins and outs of detailed description in the present embodiment, can be found in the method that the embodiment of the present application is provided.
The electronic equipment of the embodiment of the present application exists in a variety of forms, including but not limited to:
(1) mobile communication equipment: the feature of this kind equipment is that possess mobile communication function, and to provide speech, data
Communicate as main target.This Terminal Type includes: smart mobile phone (such as iphone), multimedia handset, feature mobile phone, and low
End mobile phone etc..
(2) super mobile personal computer equipment: this kind equipment belongs to the category of personal computer, has calculating and processes work(
Can, typically also possess mobile Internet access characteristic.This Terminal Type includes: pda, mid and umpc equipment etc., such as ipad.
(3) portable entertainment device: this kind equipment can show and play content of multimedia.This kind equipment includes: audio frequency,
Video player (such as ipod), handheld device, e-book, and intelligent toy and portable car-mounted navigator.
(4) server: provide the equipment of the service of calculating, it is total that the composition of server includes processor, hard disk, internal memory, system
Line etc., server is similar with general computer architecture, but due to needing to provide highly reliable service, is therefore processing energy
The aspects such as power, stability, reliability, safety, extensibility, manageability require higher.
(5) other have the electronic installation of data interaction function.
Device embodiment described above is only that schematically the wherein said unit illustrating as separating component can
To be or to may not be physically separate, as the part that unit shows can be or may not be physics list
Unit, you can with positioned at a place, or can also be distributed on multiple NEs.Can be selected it according to the actual needs
In the purpose to realize this embodiment scheme for some or all of module.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
Mode by software plus general hardware platform to be realized naturally it is also possible to pass through hardware.Based on such understanding, above-mentioned technology
What scheme substantially contributed to correlation technique in other words partly can be embodied in the form of software product, this computer
Software product can store in a computer-readable storage medium, such as rom/ram, magnetic disc, CD etc., including some instructions in order to
Make a computer equipment (can be personal computer, server, or network equipment etc.) execute each embodiment or
Some partly described methods of embodiment.
Finally it is noted that above example, only in order to the technical scheme of the application to be described, is not intended to limit；Although
With reference to the foregoing embodiments the application is described in detail, it will be understood by those within the art that: it still may be used
To modify to the technical scheme described in foregoing embodiments, or equivalent is carried out to wherein some technical characteristics；
And these modification or replace, do not make appropriate technical solution essence depart from the application each embodiment technical scheme spirit and
Scope.
Claims (10)
1. a kind of panoramic video Quality estimation method, comprising:
Obtain the many height for panoramic video to be judged and evaluate score value group, described sub- evaluation score value group includes waiting to sentence for described
Disconnected panoramic video evaluates score value in many height of multiple dimensions；
The weighted sum determination being evaluated the many height evaluation score values in score value group based on every height is divided corresponding to the plurality of sub- evaluation
Multiple evaluation score values of value group；
Evaluate the tolerance score value that score value determines the quality for panoramic video to be judged described in judging according at least to the plurality of.
2. method according to claim 1, wherein, described according at least to the plurality of evaluation score value determine for judging
The tolerance score value stating the quality of panoramic video to be judged is:
Determine the tolerance that the plurality of arithmetic mean of instantaneous value evaluating score value is the quality for panoramic video to be judged described in judging
Score value.
3. method according to claim 1, wherein, also includes:
Obtain the multiple of the reference panoramic video corresponding to described panoramic video to be judged and evaluate score value group with reference to son, described
Evaluate score value group with reference to son to include evaluating score value in the multiple of multiple dimensions with reference to son with reference to panoramic video for described；
Determined corresponding to the plurality of based on the sub weighted sum evaluating score value of multiple references that every group is evaluated with reference to son in score value group
Evaluate score value with reference to multiple references that son evaluates score value group；
Described determine that the tolerance of the quality for panoramic video to be judged described in judging is divided according at least to the plurality of score value of evaluating
It is worth and is: evaluate score value and multiple determine the matter for panoramic video to be judged described in judging with reference to evaluating score value according to the plurality of
The tolerance score value of amount.
4. method according to claim 3, wherein, the plurality of evaluation score value includes multiple users to be waited to difference to judge entirely
The evaluation score value of scape video, the plurality of reference is evaluated score value and is included multiple users to corresponding to difference panoramic video to be judged
Score value is evaluated in reference with reference to panoramic video；
Described according to the plurality of evaluation score value with multiple determine for panoramic video to be judged described in judging with reference to evaluating score value
The tolerance score value of quality include:
It is based respectively on the evaluation score value of each of the plurality of user user panoramic video to be judged to difference and reference is commented
Valency score value, to determine many height tolerance score values of the quality for judging a certain panoramic video to be judged；
Determine the tolerance score value of the quality for judging described a certain panoramic video to be judged based on the plurality of sub- tolerance score value.
5. the method according to any one of claim 1-4, wherein, the plurality of dimension at least includes: panoramic video is overall
Quality dimensions, panoramic video seriality dimension, panoramic video dizzy degree dimension, panoramic video visible distortion block dimension.
6. a kind of panoramic video Quality estimation system, comprising:
Evaluation information acquisition module, the many height for obtaining for panoramic video to be judged evaluate score value group, described sub- evaluation
Score value group includes evaluating score value for described panoramic video to be judged in many height of multiple dimensions；
Evaluation of estimate determining module, the weighted sum evaluating score value for being evaluated the many height in score value group based on every height is determined accordingly
Multiple evaluation score values in the plurality of sub- evaluation score value group；
Tolerance score value determining module, for determining for aphorama to be judged described in judging according at least to the plurality of evaluation score value
The tolerance score value of the quality of frequency.
7. system according to claim 6, wherein, described tolerance score value determining module includes:
Average calculation unit, for calculating the plurality of arithmetic mean of instantaneous value evaluating score value；
First tolerance score value determining unit, for determining that described arithmetic mean of instantaneous value is for panoramic video to be judged described in judging
The tolerance score value of quality.
8. system according to claim 6, wherein, also includes:
With reference to evaluation information acquisition module, for reference panoramic video corresponding to described panoramic video to be judged for the acquisition
Multiple references are sub to evaluate score value groups, and described reference son evaluation score value group is included for described reference panoramic video in multiple dimensions
Multiple reference evaluate score value；
With reference to evaluation of estimate determining module, for evaluating adding of score value based on every group with reference to sub multiple reference evaluated in score value group
Power and determination evaluate score value corresponding to the plurality of with reference to multiple references that son evaluates score value group；
Described tolerance score value determining module is used for being determined according to the plurality of evaluation score value and multiple reference evaluation score value and is used for sentencing
The tolerance score value of the quality of panoramic video to be judged described in disconnected.
9. system according to claim 8, wherein,
The plurality of evaluation score value includes the evaluation score value of multiple users panoramic video to be judged to difference, and the plurality of reference is commented
Valency score value includes multiple users and evaluates score value to the reference of the reference panoramic video corresponding to difference panoramic video to be judged；
Described tolerance score value determining module includes:
Son tolerance score value determining unit, is used for being based respectively on each of the plurality of user user panorama to be judged to difference
Score value is evaluated in the evaluation score value of video and reference, to determine many height degree of the quality for judging a certain panoramic video to be judged
Amount score value；
Second tolerance score value determining unit, for being determined for judging described a certain to wait to judge based on the plurality of sub- tolerance score value
The tolerance score value of the quality of panoramic video.
10. the system according to any one of claim 6-10, wherein, the plurality of dimension at least includes: panoramic video is whole
Weight dimension, panoramic video seriality dimension, panoramic video dizzy degree dimension, panoramic video visible distortion block dimension.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610717604.7A CN106341683A (en) | 2016-08-24 | 2016-08-24 | Panoramic video quality judgment method and panoramic video quality judgment system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610717604.7A CN106341683A (en) | 2016-08-24 | 2016-08-24 | Panoramic video quality judgment method and panoramic video quality judgment system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106341683A true CN106341683A (en) | 2017-01-18 |
Family
ID=57824450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610717604.7A Pending CN106341683A (en) | 2016-08-24 | 2016-08-24 | Panoramic video quality judgment method and panoramic video quality judgment system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106341683A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020000522A1 (en) * | 2018-06-27 | 2020-01-02 | 深圳看到科技有限公司 | Method and device for picture quality assessment after dynamic panoramic video stream cropping |
| CN110691236A (en) * | 2019-09-18 | 2020-01-14 | 宁波大学 | Panoramic video quality evaluation method |
| CN110730342A (en) * | 2019-11-06 | 2020-01-24 | 腾讯科技（深圳）有限公司 | Video quality analysis method and device, server and terminal |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020071614A1 (en) * | 2000-12-12 | 2002-06-13 | Philips Electronics North America Corporation | System and method for providing a scalable dynamic objective metric for automatic video quality evaluation |
| CN1416651A (en) * | 2001-01-10 | 2003-05-07 | 皇家菲利浦电子有限公司 | Reducable and enlargable objective measurement of evaluating automatic video quality |
| US20080143837A1 (en) * | 2004-10-18 | 2008-06-19 | Nippon Telegraph And Telephone Corporation | Video Quality Objective Assessment Device, Assessment Method, and Program |
| CN101783971A (en) * | 2010-01-26 | 2010-07-21 | 深圳市融创天下科技发展有限公司 | Method for subjective testing of video quality |
| WO2011082719A1 (en) * | 2010-01-11 | 2011-07-14 | Telefonaktiebolaget L M Ericsson (Publ) | Technique for video quality estimation |
| CN103379358A (en) * | 2012-04-23 | 2013-10-30 | 华为技术有限公司 | Method and device for assessing multimedia quality |
| CN103458267A (en) * | 2013-09-04 | 2013-12-18 | 中国传媒大学 | Video picture quality subjective evaluation method and system |
| CN103501434A (en) * | 2013-09-17 | 2014-01-08 | 北京奇艺世纪科技有限公司 | Method and device for analyzing quality of video |
| CN103686145A (en) * | 2013-11-15 | 2014-03-26 | 悉地（北京）国际建筑设计顾问有限公司 | Method and device for determining image quality |
| CN103988500A (en) * | 2011-11-24 | 2014-08-13 | 汤姆逊许可公司 | Video quality measurement |
| CN104506894A (en) * | 2014-12-22 | 2015-04-08 | 合一网络技术(北京)有限公司 | Method and device for evaluating multi-media resources |
-
2016
- 2016-08-24 CN CN201610717604.7A patent/CN106341683A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020071614A1 (en) * | 2000-12-12 | 2002-06-13 | Philips Electronics North America Corporation | System and method for providing a scalable dynamic objective metric for automatic video quality evaluation |
| CN1416651A (en) * | 2001-01-10 | 2003-05-07 | 皇家菲利浦电子有限公司 | Reducable and enlargable objective measurement of evaluating automatic video quality |
| US20080143837A1 (en) * | 2004-10-18 | 2008-06-19 | Nippon Telegraph And Telephone Corporation | Video Quality Objective Assessment Device, Assessment Method, and Program |
| WO2011082719A1 (en) * | 2010-01-11 | 2011-07-14 | Telefonaktiebolaget L M Ericsson (Publ) | Technique for video quality estimation |
| CN101783971A (en) * | 2010-01-26 | 2010-07-21 | 深圳市融创天下科技发展有限公司 | Method for subjective testing of video quality |
| CN103988500A (en) * | 2011-11-24 | 2014-08-13 | 汤姆逊许可公司 | Video quality measurement |
| CN103379358A (en) * | 2012-04-23 | 2013-10-30 | 华为技术有限公司 | Method and device for assessing multimedia quality |
| CN103458267A (en) * | 2013-09-04 | 2013-12-18 | 中国传媒大学 | Video picture quality subjective evaluation method and system |
| CN103501434A (en) * | 2013-09-17 | 2014-01-08 | 北京奇艺世纪科技有限公司 | Method and device for analyzing quality of video |
| CN103686145A (en) * | 2013-11-15 | 2014-03-26 | 悉地（北京）国际建筑设计顾问有限公司 | Method and device for determining image quality |
| CN104506894A (en) * | 2014-12-22 | 2015-04-08 | 合一网络技术(北京)有限公司 | Method and device for evaluating multi-media resources |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020000522A1 (en) * | 2018-06-27 | 2020-01-02 | 深圳看到科技有限公司 | Method and device for picture quality assessment after dynamic panoramic video stream cropping |
| US11438651B2 (en) | 2018-06-27 | 2022-09-06 | Kandao Technology Co., Ltd. | Method and device for picture quality assessment after dynamic panoramic video stream cropping |
| CN110691236A (en) * | 2019-09-18 | 2020-01-14 | 宁波大学 | Panoramic video quality evaluation method |
| CN110730342A (en) * | 2019-11-06 | 2020-01-24 | 腾讯科技（深圳）有限公司 | Video quality analysis method and device, server and terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | Binocular responses for no-reference 3D image quality assessment | |
| CN109118470B (en) | Image quality evaluation method and device, terminal and server | |
| Gu et al. | A new reduced-reference image quality assessment using structural degradation model | |
| US10026418B2 (en) | Abnormal frame detection method and apparatus | |
| CN108090902A (en) | A kind of non-reference picture assessment method for encoding quality based on multiple dimensioned generation confrontation network | |
| CN101783971B (en) | Method for subjective testing of video quality | |
| CN105516138B (en) | A kind of verification method and device based on login log analysis | |
| CN105912500A (en) | Machine learning model generation method and machine learning model generation device | |
| Gupta et al. | A novel full reference image quality index for color images | |
| CN109496334A (en) | For assessing the device and method of voice quality | |
| CN106341683A (en) | Panoramic video quality judgment method and panoramic video quality judgment system | |
| CN108322317A (en) | A kind of account identification correlating method and server | |
| CN101950422A (en) | Singular value decomposition(SVD)-based image quality evaluation method | |
| CN107368696B (en) | Question analysis method and device and terminal equipment | |
| CN104954778A (en) | Objective stereo image quality assessment method based on perception feature set | |
| US8412694B2 (en) | Colorblind accessible image search | |
| CN111200607B (en) | Online user behavior analysis method based on multilayer LSTM | |
| CN115174250A (en) | Network asset safety assessment method and device, electronic equipment and storage medium | |
| CN108055533A (en) | A kind of subjective quality assessment method for panoramic video | |
| Jeoung | Objective control skills among students with intellectual disability at special school in Korea | |
| Sinharay | How to compare parametric and nonparametric person‐fit statistics using real data | |
| CN103077514B (en) | A kind of visual perception image quality evaluation method based on full variation | |
| Cunningham et al. | Factor structure and psychometric properties of the muscularity‐oriented eating test in university women in Australia | |
| Mumford | A comprehensive review of group level model performance in the presence of heteroscedasticity: Can a single model control Type I errors in the presence of outliers? | |
| CN106388833A (en) | Virtual reality mental quality assessment method and 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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170118 |