CN109831663B - Video quality evaluation method, terminal and storage medium - Google Patents
Video quality evaluation method, terminal and storage medium Download PDFInfo
- Publication number
- CN109831663B CN109831663B CN201711181351.7A CN201711181351A CN109831663B CN 109831663 B CN109831663 B CN 109831663B CN 201711181351 A CN201711181351 A CN 201711181351A CN 109831663 B CN109831663 B CN 109831663B
- Authority
- CN
- China
- Prior art keywords
- value
- target
- current
- deduction
- model
- 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
Images
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The embodiment of the invention discloses a method for evaluating video quality, which comprises the following steps: a terminal obtains a target deduction calculation model; the target deduction model is used for determining the mean opinion value of the video quality; acquiring a current transmission mode, a current code rate, an actual value of a preset calculation factor and a current target value of the preset calculation factor corresponding to the current transmission mode and the current code rate; and determining the current mean opinion value according to the current target value, the actual value and the target deduction calculation model.
Description
Technical Field
The invention relates to the technical field of video quality of an interactive network television, in particular to a method, a terminal and a storage medium for evaluating video quality.
Background
With the rapid development of information technology, the Internet Protocol Television (IPTV) technology utilizes a broadband network, integrates Internet, communication, multimedia and other technologies, and realizes the functions of video on demand and the like through a set-top box and a Television, so as to present videos to be watched for users. And the video quality presented by IPTV is the most interesting aspect for users.
In the prior art, methods for evaluating video quality are mainly divided into two types: subjective quality evaluation method and objective quality evaluation method. The subjective quality evaluation method is to directly score played videos by viewers watching the videos. In the subjective quality evaluation method, the video is evaluated by the visual perception of human eyes, and the lateral emphasis of the human and the cognitive degree of the video quality are possibly in large difference, so that the deviation is easy to occur and the fluctuation is high. The objective quality evaluation method is to calculate certain characteristics of images in the video through operation and determine the video quality according to some specific quantitative indexes. The objective quality evaluation method is rapid, convenient and fast, and is convenient to implement.
However, although the evaluation of the video quality can be quickly achieved by the objective quality evaluation method, the evaluation result determined by the objective quality evaluation method often has a certain difference from the subjective perception of people, and only the approximate quality of the video can be reflected, and the accuracy of the video quality evaluation result cannot be ensured.
Disclosure of Invention
In order to solve the existing technical problem, embodiments of the present invention desirably provide an evaluation method, a terminal and a storage medium for video quality, where the terminal can calculate a mean opinion value of video quality according to a deduction calculation model, thereby improving accuracy of a video quality evaluation result.
In order to achieve the above purpose, the technical solution of the embodiment of the present invention is realized as follows:
the embodiment of the invention provides a method for evaluating video quality, which comprises the following steps:
acquiring a target deduction calculation model; the target deduction model is used for determining the mean opinion value of the video quality;
acquiring a current transmission mode, a current code rate, an actual value of a preset calculation factor and a current target value of the preset calculation factor corresponding to the current transmission mode and the current code rate;
and determining the current mean opinion value according to the current target value, the actual value and the target deduction calculation model.
In the above scheme, the obtaining of the preset deduction calculation model includes:
acquiring a sample transmission mode, a sample code rate, a sample value of the preset calculation factor, a sample target value of the preset calculation factor corresponding to the sample transmission mode and the sample code rate, and a first target mean opinion value;
inputting the sample value and the sample target value into a preset first deduction calculation model to obtain a sample mean opinion value;
adjusting coefficients corresponding to the preset calculation factors in the preset first deduction calculation model until the sample mean opinion value and the first target mean opinion value meet a preset error, and obtaining a second deduction calculation model;
and adjusting the second deduction calculation model to obtain the target deduction calculation model.
In the foregoing solution, the adjusting the second deduction calculation model to obtain the target deduction calculation model includes:
acquiring a detection transmission mode, a detection code rate, a detection value of the preset calculation factor, a detection target value of the preset calculation factor corresponding to the detection transmission mode and the detection code rate, and a second target mean opinion value;
and adjusting coefficients corresponding to the preset calculation factors in the second deduction calculation model according to the detection values, the detection target values and the second target mean opinion values to obtain the target deduction calculation model.
In the above solution, the determining a current mean opinion value according to the current target value, the actual value and the target deduction calculation model includes:
when the actual value is smaller than or equal to the current target value, inputting the actual value and the current target value into the first target model to obtain a first deduction value corresponding to the preset calculation factor;
and inputting the first deduction value into the third target model to obtain the current mean opinion value.
In the above solution, the determining a current mean opinion value according to the current target value, the actual value and the target deduction calculation model further includes:
when the actual value is larger than the current target value, inputting the actual value and the current target value into the second target model to obtain a second deduction value corresponding to the preset calculation factor;
and inputting the second deduction value into the third target model to obtain the current mean opinion value.
In the above scheme, the preset calculation factor at least includes one of the following: packet loss rate, jitter displacement, and delay time.
An embodiment of the present invention further provides a terminal, where the terminal includes: a processor, a memory, and a communication bus;
the communication bus is used for realizing connection communication between the processor and the memory;
the processor is used for executing the evaluation program of the video quality stored in the memory so as to realize the following steps:
acquiring a target deduction calculation model; the target deduction model is used for determining the mean opinion value of the video quality; acquiring a current transmission mode, a current code rate, an actual value of a preset calculation factor and a current target value of the preset calculation factor corresponding to the current transmission mode and the current code rate; and determining the current mean opinion value according to the current target value, the actual value and the target deduction calculation model.
In the above terminal, the processor is specifically configured to execute the evaluation program of the video quality, so as to implement the following steps:
acquiring a sample transmission mode, a sample code rate, a sample value of the preset calculation factor, a sample target value of the preset calculation factor corresponding to the sample transmission mode and the sample code rate, and a first target mean opinion value; inputting the sample value and the sample target value into a preset first deduction calculation model to obtain a sample mean opinion value; adjusting coefficients corresponding to the preset calculation factors in the preset first deduction calculation model until the sample mean opinion value and the first target mean opinion value meet a preset error, and obtaining a second deduction calculation model; adjusting the second deduction calculation model to obtain the target deduction calculation model; acquiring a detection transmission mode, a detection code rate, a detection value of the preset calculation factor, a detection target value of the preset calculation factor corresponding to the detection transmission mode and the detection code rate, and a second target mean opinion value; and adjusting coefficients corresponding to the preset calculation factors in the second deduction calculation model according to the detection values, the detection target values and the second target mean opinion values to obtain the target deduction calculation model.
In the above terminal, the target deduction calculation model includes a first target model, a second target model and a third target model, and the processor is specifically configured to execute the evaluation program of the video quality, so as to implement the following steps:
when the actual value is smaller than or equal to the current target value, inputting the actual value and the current target value into the first target model to obtain a first deduction value corresponding to the preset calculation factor; inputting the first deduction value into the third target model to obtain the current mean opinion value;
when the actual value is larger than the current target value, inputting the actual value and the current target value into the second target model to obtain a second deduction value corresponding to the preset calculation factor; and inputting the second deduction value into the third target model to obtain the current mean opinion value.
In the above terminal, the preset calculation factor at least includes one of the following: packet loss rate, jitter displacement, and delay time.
An embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores one or more programs, and the one or more programs are executable by one or more processors to implement the above-mentioned method for evaluating video quality.
Therefore, in the technical scheme of the embodiment of the invention, the terminal acquires the target deduction calculation model; the target deduction model is used for determining the mean opinion value of the video quality; acquiring a current transmission mode, a current code rate, an actual value of a preset calculation factor and a current target value of the preset calculation factor corresponding to the current transmission mode and the current code rate; and determining the current mean opinion value according to the current target value, the actual value and the target deduction calculation model. In the technical scheme of the invention, the deduction calculation model close to the subjective quality evaluation result is established, and the terminal can calculate the average opinion value of the video quality according to the deduction calculation model, so that the accuracy of the video quality evaluation result is improved.
Drawings
Fig. 1 is a flowchart of a method for evaluating video quality according to an embodiment of the present invention;
fig. 2 is a flowchart of an obtaining method of a target deduction calculation model according to an embodiment of the present invention;
fig. 3 is a flowchart of an adjusting method of a second deduction calculation model according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a terminal according to an embodiment of the present invention.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
Example one
An embodiment of the present invention provides a method for evaluating video quality, as shown in fig. 1, the method may include:
s101, obtaining a target deduction calculation model; wherein the target scoring model is used to determine a mean opinion value for video quality.
In the embodiment of the invention, the terminal can firstly acquire the target deduction calculation model and determine the mean opinion value of the video quality according to the target deduction calculation model.
It should be noted that, in the embodiment of the present invention, the terminal needs to adjust the coefficient corresponding to the calculation factor in the preset deduction calculation model according to a large number of sample values of the calculation factor, so as to determine the target deduction calculation model with accuracy.
Fig. 2 is a flowchart of a method for obtaining a target deduction calculation model according to an embodiment of the present invention. As shown in fig. 2, the calculation model for determining the target deduction by the terminal mainly includes the following steps:
s201, obtaining a sample transmission mode, a sample code rate, a sample value of a preset calculation factor, a sample target value of the preset calculation factor corresponding to the sample transmission mode and the sample code rate, and a first target mean opinion value.
In the embodiment of the present invention, when the player plays the video sample in the sample transmission mode and the sample rate, the terminal may directly obtain the sample rate, the sample transmission mode, and the sample value of the preset calculation factor from the network environment, and the first target mean opinion value may be provided by a viewer watching the video sample and input to the terminal for storage, that is, the terminal may also directly obtain the first target mean opinion value.
It can be understood that the first target average opinion value is actually a subjective quality evaluation of video quality by viewers watching video samples, the first target average value may be a scoring average of videos watched by a large number of viewers, and the larger the number of viewers is, the more accurate the first target average value obtained by the terminal is.
It should be noted that, in the embodiment of the present invention, the preset calculation factor is a factor that affects video quality, and a plurality of calculation factors may be preset on the terminal. That is, the preset calculation factor is not limited in the embodiments of the present invention.
Optionally, the preset calculation factor at least includes one of the following: packet loss rate, jitter displacement, and delay time.
It should be noted that, in the embodiment of the present invention, the video sample may be played by using a transmission mode, that is, unicast, multicast, and a combination of different code rates, and the specific sample transmission mode and the sample code rate are not limited in the embodiment of the present invention. Therefore, in the target deduction calculation model finally determined by the terminal, deduction methods under different scenes are actually included.
Specifically, in the embodiment of the present invention, the terminal firstly determines that a fixed video sample is used, obtains the sample transmission mode, the sample code rate, and the sample value of the preset calculation factor, and then determines the sample target value of the preset calculation factor corresponding to the sample code rate and the sample transmission mode according to the corresponding relationship between the preset transmission mode and the code rate and the target value of the preset calculation factor.
Illustratively, the preset calculation factors are a packet loss rate, a delay time and a jitter displacement, a sample transmission mode in which a terminal can directly acquire a video sample in a network is unicast, the sample rate is a, a is greater than or equal to a1 and less than or equal to a2, a sample value of the packet loss rate is X0, a sample value of the delay time is Y0, and a sample value of the jitter displacement is Z0. Then, the terminal may determine unicast according to a table of correspondence between preset transmission modes and code rates and target values of preset calculation factors, where a sample target value of packet loss rate corresponding to a code rate is X1, a sample target value of delay time is Y1, and a sample target value of jitter displacement is Z1. Table 1 shows a correspondence table between the preset transmission mode and the code rate and the target value of the preset calculation factor.
TABLE 1
S202, inputting the sample value and the sample target value into a preset first deduction calculation model to obtain a sample mean opinion value.
In the embodiment of the invention, after the terminal acquires the sample value and the sample target value of the preset calculation factor, the sample value and the sample target value of the preset calculation factor are input into the preset first deduction calculation model, and the sample mean opinion value is acquired.
Specifically, in the embodiment of the present invention, a first deduction calculation model is preset on the terminal, and is as in formulas (1), (2) and (3):
the deducted point value is (sample value/sample target value) × b0 (1)
Sample mean opinion value 5-point value 1-point value 2- … point value T (3)
Wherein T is a natural number greater than or equal to 1, and b0, k0 and c0 in the formulas (1) and (2) are coefficients corresponding to preset calculation factors in the first deduction calculation model.
It should be noted that, when the sample value of the preset calculation factor is less than or equal to the sample target value of the preset calculation factor, the formula (1) and the formula (3) in the preset first deduction calculation model are used to determine the sample mean opinion value, and when the sample value of the preset calculation factor is greater than the sample target value of the preset calculation factor, the formula (2) and the formula (3) in the preset first deduction calculation model are used to determine the sample mean opinion value.
It is to be understood that, in the embodiment of the present invention, since the preset calculation factors may include a plurality of types, such as a packet loss rate, a delay time, and a jitter displacement, for the preset first deduction calculation model, the deduction value of each calculation factor may be calculated according to the formula (1) and the formula (2), and finally the sample mean opinion value is determined according to the formula (3).
S203, adjusting coefficients corresponding to preset calculation factors in the preset first deduction calculation model until the sample mean opinion value and the first target mean opinion value meet preset errors, and obtaining a second deduction calculation model.
In the embodiment of the invention, after obtaining the sample mean opinion value, the terminal compares the sample mean opinion value with the first target mean opinion value, adjusts the coefficient corresponding to the preset calculation factor in the preset first deduction calculation model until the sample mean opinion value and the first target mean opinion value meet the preset error, and determines the preset first deduction calculation model after the coefficient is adjusted as the second deduction calculation model.
It should be understood that, in the embodiment of the present invention, in order to make the average opinion value of the terminal on the video quality and the average opinion value of the viewer on the video quality approximate to each other, based on the score of the viewer on the video sample, that is, the first target average opinion value, the coefficient corresponding to the preset calculation factor in the preset first deduction calculation model is adjusted, so that the obtained sample average opinion value is consistent with the first target average opinion value.
It should be noted that, in the embodiment of the present invention, a preset error is stored in the terminal, and the smaller the preset error is, the more accurately the second deduction calculation model is obtained. The specific preset error is not limited in the embodiments of the present invention.
Illustratively, the preset calculation factor is a packet loss rate, the terminal inputs a sample value of the packet loss rate and a sample target value into a preset first deduction calculation model, the obtained sample mean opinion value is 3.8, the error from the first target mean opinion value 3.2 is 0.6, and the preset error is 0.2, so that the obtained sample mean opinion value is changed by adjusting a coefficient corresponding to the packet loss rate in the preset first deduction calculation model until the error between the obtained sample mean opinion value and the first target mean opinion value is less than or equal to 0.2. And the preset first deduction calculation model after the coefficient is adjusted is the second deduction calculation model.
And S204, adjusting the second deduction calculation model to obtain a target deduction calculation model.
In the embodiment of the present invention, after obtaining the second deduction calculation model, the terminal further needs to verify and further adjust the second deduction calculation model according to a large amount of data, so as to finally obtain the target deduction calculation model.
Fig. 3 is a flowchart of an adjusting method of a second deduction calculation model according to an embodiment of the present invention. As shown in fig. 3, the method mainly comprises the following steps:
s301, obtaining a detection transmission mode, a detection code rate, a detection value of a preset calculation factor, a detection target value of the preset calculation factor corresponding to the detection transmission mode and the detection code rate, and a second target mean opinion value.
In the embodiment of the present invention, the terminal may obtain the detection transmission mode, the detection code rate, the detection value of the preset calculation factor, the detection target value of the preset calculation factor corresponding to the detection transmission mode and the detection code rate, and the second target mean opinion value. And the terminal directly acquires the detection value of the preset calculation factor from the network environment in the scene of playing the test video, and the second target mean opinion value is the score of the audience according to the test video.
It should be noted that, the method for the terminal to obtain the detection target values of the preset calculation factors corresponding to the detection transmission mode and the detection code rate is the same as the method for the terminal to obtain the sample target values of the preset calculation factors corresponding to the sample transmission mode and the sample code rate in step S201, and can also be determined according to the lookup table 1.
It can be understood that, in the embodiment of the present invention, the second deduction calculation model can be determined by the above method, but a large amount of detection data is required for verification and further adjustment, so that a more accurate target deduction calculation model is obtained.
S302, adjusting coefficients corresponding to preset calculation factors in the second deduction calculation model according to the detection values, the detection target values and the second target mean opinion values to obtain a target deduction calculation model.
In the embodiment of the present invention, the terminal may input the detection value and the detection target value of the preset calculation factor into the second deduction calculation model to obtain a mean opinion value, compare the mean opinion value with the second target mean opinion value to verify whether a preset error is satisfied, and adjust a coefficient corresponding to the preset calculation factor in the second deduction calculation model to obtain the target deduction calculation model.
It can be understood that, adjusting the coefficient corresponding to the preset calculation factor in the preset first deduction calculation model actually determines the target deduction calculation model, and adjusting the coefficient corresponding to the preset calculation factor in the second deduction calculation model actually further verifies and fine-tunes the target deduction calculation model, so that the finally obtained target deduction calculation model is more accurate.
It should be noted that, in the embodiment of the present invention, the target deduction calculation model determined by the terminal includes coefficients of preset calculation factors in different scenarios, as shown in table 2.
TABLE 2
It should be noted that, when the actual value of the preset calculation factor and the current target value of the preset calculation factor are input into the target deduction calculation model, the target deduction calculation model automatically determines the parameters to be used according to the current transmission mode and the current code rate.
S102, obtaining the current transmission mode, the current code rate, the actual value of the preset calculation factor and the current target value of the preset calculation factor corresponding to the current transmission mode and the current code rate.
In the embodiment of the invention, after the terminal acquires the target deduction calculation model, the terminal can use the target deduction calculation model to grade the currently played video. The terminal can obtain the current transmission mode, the current code rate and the actual value of the preset calculation factor from the network environment, and obtain the current target value of the preset calculation factor according to the corresponding relation between the preset transmission mode and the code rate and the target value of the preset calculation factor.
It can be understood that the terminal implements the obtaining of the target deduction calculation model in step S101, and the following steps implement the application process of the target deduction calculation model, so as to implement the scoring of the currently played video.
Illustratively, the preset calculation factor includes: the packet loss rate, the delay time and the jitter displacement are obtained, the terminal obtains the current transmission mode and the current code rate, and the current transmission mode and the current code rate can be searched in the table 1, so that the current target value corresponding to the packet loss rate, the current target value corresponding to the delay time and the current target value corresponding to the jitter displacement are determined.
S103, determining the current mean opinion value according to the current target value, the actual value and the target deduction calculation model.
In the embodiment of the invention, after the terminal acquires the current target value and the actual value of the preset calculation factor, the current target value and the actual value of the preset calculation factor are input into the target deduction calculation model, so that the current mean opinion value is determined.
It should be noted that the target deduction calculation model includes three models, which are respectively: a first object model, a second object model, and a third object model. The first object model is as in formula (4), the second object model is as in formula (5), and the third object model is as in formula (6):
the deducted point value is (actual value/current target value) × b (4)
Current mean opinion value 5-deducted score 1-deducted score 2- … deducted score T (6)
It should be noted that b, k, and c in equations (4) and (5) are coefficients corresponding to the preset calculation factors in the target deduction calculation model, and the coefficients have been determined when the target deduction calculation model is obtained, as shown in table 2.
Specifically, in the embodiment of the present invention, when the actual value of the preset calculation factor is less than or equal to the current target value of the preset calculation factor, the actual value of the preset calculation factor and the current target value of the preset calculation factor are input into the first target model, a first deduction value corresponding to the preset calculation factor is obtained, and then the first deduction value is input into the third target model, so as to obtain the current mean opinion value. And when the actual value of the preset calculation factor is larger than the current target value of the preset calculation factor, inputting the actual value of the preset calculation factor and the current target value of the preset calculation factor into a second target model to obtain a second deduction value corresponding to the preset calculation factor, and then inputting the second deduction value into a third target model to obtain the current mean opinion value.
Illustratively, when the actual value of the packet loss rate is less than or equal to the current target value of the packet loss rate, the actual value of the packet loss rate and the current target value of the packet loss rate are input into a first target model to obtain a first deduction value corresponding to the packet loss rate, and then the first deduction value is input into a third target model to obtain a current mean opinion value. And when the actual value of the packet loss rate is larger than the current target value of the packet loss rate, inputting the actual value of the packet loss rate and the current target value of the packet loss rate into a second target model to obtain a second deduction value corresponding to the packet loss rate, and then inputting the second deduction value into a third target model to obtain a current mean opinion value.
For example, the current transmission mode of the current video acquired by the terminal is unicast, the current bit rate is B, B is greater than or equal to A3 and less than or equal to a4, the actual value of the packet loss rate is U, the actual value of the delay time is V, and the actual value of the jitter displacement is W. Then, the terminal may determine unicast according to a table of correspondence between preset transmission modes and code rates and target values of preset calculation factors, where the current target value of packet loss rate corresponding to the code rate B is X5, the current target value of delay time is Y5, and the current target value of jitter displacement is Z5. If U is less than or equal to X5, inputting U and X5 into a first target model to obtain a first deduction value corresponding to the packet loss rate, if V is greater than Y5, inputting V and Y5 into a second target model to obtain a second deduction value corresponding to the delay time, if W is less than or equal to Z5, inputting W and Z5 into the first target model to obtain a first deduction value corresponding to the jitter displacement, and finally, inputting the first deduction value corresponding to the packet loss rate, the second deduction value corresponding to the delay time and the first deduction value corresponding to the jitter displacement into a third model to obtain the current average opinion value.
It should be noted that the target deduction calculation model already includes different parameters in different cases in table 2, U and X5 are input into the first target model, and the target deduction calculation model automatically matches corresponding coefficients according to the current transmission mode and the current code rate, that is, the first target model automatically matches coefficient b13 in table 2. Similarly, V and Y5 are input to the second target model, which automatically matches coefficients k14, b14, and c14, W and Z5 are input to the first target model, which automatically matches coefficient b 15.
According to the method for evaluating the video quality provided by the embodiment of the invention, a terminal obtains a target deduction calculation model; the target deduction model is used for determining the mean opinion value of the video quality; acquiring a current transmission mode, a current code rate, an actual value of a preset calculation factor and a current target value of the preset calculation factor corresponding to the current transmission mode and the current code rate; and determining the current mean opinion value according to the current target value, the actual value and the target deduction calculation model. In the technical scheme of the invention, the deduction calculation model close to the subjective quality evaluation result is established, and the terminal can calculate the average opinion value of the video quality according to the deduction calculation model, so that the accuracy of the video quality evaluation result is improved.
Example two
Fig. 4 is a schematic structural diagram of a terminal according to an embodiment of the present invention. As shown in fig. 4, the terminal includes: a processor 401, a memory 402, and a communication bus 403;
the communication bus 403 is used for realizing connection communication between the processor 401 and the memory 402;
the processor 401 is configured to execute the evaluation program of the video quality stored in the memory 402 to implement the following steps:
acquiring a target deduction calculation model; the target deduction model is used for determining the mean opinion value of the video quality; acquiring a current transmission mode, a current code rate, an actual value of a preset calculation factor and a current target value of the preset calculation factor corresponding to the current transmission mode and the current code rate; and determining the current mean opinion value according to the current target value, the actual value and the target deduction calculation model.
Optionally, the processor 401 is specifically configured to execute the evaluation program of the video quality, so as to implement the following steps:
acquiring a sample transmission mode, a sample code rate, a sample value of the preset calculation factor, a sample target value of the preset calculation factor corresponding to the sample transmission mode and the sample code rate, and a first target mean opinion value; inputting the sample value and the sample target value into a preset first deduction calculation model to obtain a sample mean opinion value; adjusting coefficients corresponding to the preset calculation factors in the preset first deduction calculation model until the sample mean opinion value and the first target mean opinion value meet a preset error, and obtaining a second deduction calculation model; adjusting the second deduction calculation model to obtain the target deduction calculation model; acquiring a detection transmission mode, a detection code rate, a detection value of the preset calculation factor, a detection target value of the preset calculation factor corresponding to the detection transmission mode and the detection code rate, and a second target mean opinion value; and adjusting coefficients corresponding to the preset calculation factors in the second deduction calculation model according to the detection values, the detection target values and the second target mean opinion values to obtain the target deduction calculation model.
Optionally, the target deduction calculation model includes a first target model, a second target model and a third target model, and the processor 401 is specifically configured to execute the evaluation program of the video quality, so as to implement the following steps:
when the actual value is smaller than or equal to the current target value, inputting the actual value and the current target value into the first target model to obtain a first deduction value corresponding to the preset calculation factor; inputting the first deduction value into the third target model to obtain the current mean opinion value;
when the actual value is larger than the current target value, inputting the actual value and the current target value into the second target model to obtain a second deduction value corresponding to the preset calculation factor; and inputting the second deduction value into the third target model to obtain the current mean opinion value.
Optionally, the preset calculation factor at least includes one of the following: packet loss rate, jitter displacement, and delay time.
According to the terminal provided by the embodiment of the invention, the terminal acquires a target deduction calculation model; the target deduction model is used for determining the mean opinion value of the video quality; acquiring a current transmission mode, a current code rate, an actual value of a preset calculation factor and a current target value of the preset calculation factor corresponding to the current transmission mode and the current code rate; and determining the current mean opinion value according to the current target value, the actual value and the target deduction calculation model. In the technical scheme of the invention, the deduction calculation model close to the subjective quality evaluation result is established, and the terminal can calculate the average opinion value of the video quality according to the deduction calculation model, so that the accuracy of the video quality evaluation result is improved.
Embodiments of the present invention also provide a computer-readable storage medium storing one or more programs, where the one or more programs are executable by one or more network processors to implement the above-described method for evaluating video quality. The computer-readable storage medium may be a volatile Memory (volatile Memory), such as a Random-Access Memory (RAM); or a non-volatile Memory (non-volatile Memory), such as a Read-Only Memory (ROM), a flash Memory (flash Memory), a Hard Disk (Hard Disk Drive, HDD) or a Solid-State Drive (SSD); or may be a respective device, such as a mobile phone, computer, tablet device, personal digital assistant, etc., that includes one or any combination of the above-mentioned memories.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention.
Claims (10)
1. A method for evaluating video quality, the method comprising:
acquiring a target deduction calculation model; the target deduction calculation model is used for determining the mean opinion value of the video quality;
acquiring a current transmission mode, a current code rate, an actual value of a preset calculation factor and a current target value of the preset calculation factor corresponding to the current transmission mode and the current code rate; the preset calculation factor is a factor influencing the video quality;
determining a current mean opinion value according to the current target value, the actual value and the target deduction calculation model; obtaining a preset deduction calculation model, comprising:
acquiring a sample transmission mode, a sample code rate, a sample value of the preset calculation factor, a sample target value of the preset calculation factor corresponding to the sample transmission mode and the sample code rate, and a first target mean opinion value;
inputting the sample value and the sample target value into a preset first deduction calculation model to obtain a sample mean opinion value;
adjusting coefficients corresponding to the preset calculation factors in the preset first deduction calculation model until the sample mean opinion value and the first target mean opinion value meet a preset error, and obtaining a second deduction calculation model;
adjusting the second deduction calculation model to obtain the target deduction calculation model;
the first target mean opinion value is a subjective quality assessment of video quality by a viewer watching a video sample;
determining a current mean opinion value according to the current target value, the actual value and the target deduction calculation model comprises: after acquiring the current target value and the actual value of the preset calculation factor, the terminal inputs the current target value and the actual value of the preset calculation factor into the target deduction calculation model, so as to determine the current mean opinion value.
2. The method of claim 1, wherein said adjusting said second scoring computation model to obtain said target scoring computation model comprises:
acquiring a detection transmission mode, a detection code rate, a detection value of the preset calculation factor, a detection target value of the preset calculation factor corresponding to the detection transmission mode and the detection code rate, and a second target mean opinion value;
adjusting a coefficient corresponding to the preset calculation factor in the second deduction calculation model according to the detection value, the detection target value and the second target mean opinion value to obtain the target deduction calculation model;
the second target mean opinion value is a rating by a viewer based on the test video.
3. The method of claim 1, wherein the target deduction calculation model comprises a first target model and a third target model, and wherein determining a current mean opinion value based on the current target value, the actual value and the target deduction calculation model comprises:
when the actual value is smaller than or equal to the current target value, inputting the actual value and the current target value into the first target model to obtain a first deduction value corresponding to the preset calculation factor;
and inputting the first deduction value into the third target model to obtain the current mean opinion value.
4. The method of claim 3, wherein the target scoring computation model further comprises a second target model, and wherein determining a current mean opinion value based on the current target value, the actual value, and the target scoring computation model comprises:
when the actual value is larger than the current target value, inputting the actual value and the current target value into the second target model to obtain a second deduction value corresponding to the preset calculation factor;
and inputting the second deduction value into the third target model to obtain the current mean opinion value.
5. The method of claim 1, wherein the predetermined calculation factor comprises at least one of: packet loss rate, jitter displacement, and delay time.
6. A terminal, characterized in that the terminal comprises: a processor, a memory, and a communication bus;
the communication bus is used for realizing connection communication between the processor and the memory;
the processor is used for executing the evaluation program of the video quality stored in the memory so as to realize the following steps:
acquiring a target deduction calculation model; the target deduction calculation model is used for determining the mean opinion value of the video quality; acquiring a current transmission mode, a current code rate, an actual value of a preset calculation factor and a current target value of the preset calculation factor corresponding to the current transmission mode and the current code rate; the preset calculation factor is a factor influencing the video quality;
determining a current mean opinion value according to the current target value, the actual value and the target deduction calculation model;
the processor is specifically configured to execute the video quality evaluation program to implement the following steps:
acquiring a sample transmission mode, a sample code rate, a sample value of the preset calculation factor, a sample target value of the preset calculation factor corresponding to the sample transmission mode and the sample code rate, and a first target mean opinion value; inputting the sample value and the sample target value into a preset first deduction calculation model to obtain a sample mean opinion value; adjusting coefficients corresponding to the preset calculation factors in the preset first deduction calculation model until the sample mean opinion value and the first target mean opinion value meet a preset error, and obtaining a second deduction calculation model; adjusting the second deduction calculation model to obtain the target deduction calculation model;
the first target mean opinion value is a subjective quality assessment of video quality by a viewer watching a video sample;
determining a current mean opinion value according to the current target value, the actual value and the target deduction calculation model comprises: after acquiring the current target value and the actual value of the preset calculation factor, the terminal inputs the current target value and the actual value of the preset calculation factor into the target deduction calculation model, so as to determine the current mean opinion value.
7. The terminal of claim 6, wherein the processor is further specifically configured to execute the video quality evaluation procedure to implement the following steps:
acquiring a detection transmission mode, a detection code rate, a detection value of the preset calculation factor, a detection target value of the preset calculation factor corresponding to the detection transmission mode and the detection code rate, and a second target mean opinion value; adjusting a coefficient corresponding to the preset calculation factor in the second deduction calculation model according to the detection value, the detection target value and the second target mean opinion value to obtain the target deduction calculation model;
the second target mean opinion value is a rating by a viewer based on the test video.
8. The terminal according to claim 6, wherein the target deduction calculation model comprises a first target model, a second target model and a third target model, and the processor is specifically configured to execute the evaluation procedure of the video quality to implement the following steps:
when the actual value is smaller than or equal to the current target value, inputting the actual value and the current target value into the first target model to obtain a first deduction value corresponding to the preset calculation factor; inputting the first deduction value into the third target model to obtain the current mean opinion value;
when the actual value is larger than the current target value, inputting the actual value and the current target value into the second target model to obtain a second deduction value corresponding to the preset calculation factor; and inputting the second deduction value into the third target model to obtain the current mean opinion value.
9. The terminal of claim 6, wherein the predetermined calculation factor comprises at least one of: packet loss rate, jitter displacement, and delay time.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores one or more programs which are executable by one or more processors to implement the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711181351.7A CN109831663B (en) | 2017-11-23 | 2017-11-23 | Video quality evaluation method, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711181351.7A CN109831663B (en) | 2017-11-23 | 2017-11-23 | Video quality evaluation method, terminal and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109831663A CN109831663A (en) | 2019-05-31 |
| CN109831663B true CN109831663B (en) | 2022-03-04 |
Family
ID=66858929
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711181351.7A Active CN109831663B (en) | 2017-11-23 | 2017-11-23 | Video quality evaluation method, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109831663B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101594552A (en) * | 2009-06-29 | 2009-12-02 | 华东师范大学 | The method of testing of IPTV service quality damage by network transmission |
| CN102654539A (en) * | 2012-04-01 | 2012-09-05 | 广东省电力调度中心 | Method for evaluating operation state of electronic instrument transformer |
| CN103686218A (en) * | 2012-09-18 | 2014-03-26 | 中国科学院声学研究所 | QoE-based cross-layer optimal video transmission method and system under MIMO-OFDM (Multi-Input Multi-Output-Orthogonal Frequency Division Multiplexing) system |
| CN106303703A (en) * | 2016-08-01 | 2017-01-04 | 广州视源电子科技股份有限公司 | Method and device for selecting program source |
| CN106911925A (en) * | 2015-12-22 | 2017-06-30 | 中兴通讯股份有限公司 | The processing method and processing device of video quality |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090309977A1 (en) * | 2008-06-12 | 2009-12-17 | Microsoft Corporation | Benchmarking and calibrating video quality assessment tools |
-
2017
- 2017-11-23 CN CN201711181351.7A patent/CN109831663B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101594552A (en) * | 2009-06-29 | 2009-12-02 | 华东师范大学 | The method of testing of IPTV service quality damage by network transmission |
| CN102654539A (en) * | 2012-04-01 | 2012-09-05 | 广东省电力调度中心 | Method for evaluating operation state of electronic instrument transformer |
| CN103686218A (en) * | 2012-09-18 | 2014-03-26 | 中国科学院声学研究所 | QoE-based cross-layer optimal video transmission method and system under MIMO-OFDM (Multi-Input Multi-Output-Orthogonal Frequency Division Multiplexing) system |
| CN106911925A (en) * | 2015-12-22 | 2017-06-30 | 中兴通讯股份有限公司 | The processing method and processing device of video quality |
| CN106303703A (en) * | 2016-08-01 | 2017-01-04 | 广州视源电子科技股份有限公司 | Method and device for selecting program source |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109831663A (en) | 2019-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3170311B1 (en) | Automatic detection of preferences for subtitles and dubbing | |
| US8422699B2 (en) | Loudness consistency at program boundaries | |
| US20070260634A1 (en) | Apparatus, system, method, and computer program product for synchronizing the presentation of media content | |
| CN106604050A (en) | Direct broadcast video assessment method and device | |
| WO2019134293A1 (en) | Live streaming method, device, server and medium | |
| JP2017017687A (en) | Method of generating dynamic temporal versions of content | |
| CN106658226B (en) | Playing method and device | |
| CN109996110A (en) | A kind of video broadcasting method, terminal, server and storage medium | |
| WO2017161744A1 (en) | Video recommendation method and apparatus | |
| TW201416888A (en) | Scene clip playback system, method and recording medium thereof | |
| KR101693567B1 (en) | Streaming media segment preparation method and apparatus | |
| WO2017185584A1 (en) | Method and device for playback optimization | |
| CN104869430A (en) | Video speed multiplication playing method and apparatus | |
| CN104320670A (en) | Summary information extracting method and system for network video | |
| US20190394253A1 (en) | System and method for video encoding optimization and broadcasting | |
| WO2015144243A1 (en) | Image display device with automatic sound enhancement function | |
| US11095699B1 (en) | Streaming media file management | |
| CN109831663B (en) | Video quality evaluation method, terminal and storage medium | |
| US20230362425A1 (en) | Evolutionary parameter optimization for selecting optimal personalized screen carousels | |
| CN104837061B (en) | A kind of video broadcasts single modification management method and device | |
| WO2018196596A1 (en) | Identification code application method and device | |
| Song et al. | Initial perceived quality analysis for dash video streaming | |
| US10255947B2 (en) | Mitigating drift in audiovisual assets | |
| US12003564B1 (en) | Predicted presented quality metrics | |
| WO2021103983A1 (en) | Epg ui frame processing method and device, server and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |