CN113420809A - Video quality evaluation method and device and electronic equipment - Google Patents
Video quality evaluation method and device and electronic equipment Download PDFInfo
- Publication number
- CN113420809A CN113420809A CN202110695109.1A CN202110695109A CN113420809A CN 113420809 A CN113420809 A CN 113420809A CN 202110695109 A CN202110695109 A CN 202110695109A CN 113420809 A CN113420809 A CN 113420809A
- Authority
- CN
- China
- Prior art keywords
- video
- quality evaluation
- played
- equipment
- sample
- 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
- 238000013441 quality evaluation Methods 0.000 title claims abstract description 204
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000011156 evaluation Methods 0.000 claims abstract description 57
- 238000013507 mapping Methods 0.000 claims abstract description 42
- 238000012549 training Methods 0.000 claims abstract description 31
- 230000006870 function Effects 0.000 claims description 40
- 238000001303 quality assessment method Methods 0.000 claims description 18
- 238000010801 machine learning Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 5
- 239000003550 marker Substances 0.000 description 4
- 238000013136 deep learning model Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Tourism & Hospitality (AREA)
- Computational Linguistics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Evolutionary Biology (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medical Informatics (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The invention provides a video quality evaluation method, a video quality evaluation device and electronic equipment, wherein the method comprises the following steps: inputting the obtained video to be evaluated into a quality evaluation model trained in advance under first equipment to obtain a first evaluation result when the video to be evaluated is played on the first equipment; and determining a second evaluation result when the video to be evaluated is played on the second equipment based on the quality evaluation mapping relation between the second equipment and the first evaluation result. According to the method, the quality evaluation model obtained by training under the first device is used, the quality evaluation result of the video when the first device plays is obtained, and the quality evaluation result of the video on other devices can be obtained through the quality evaluation mapping relation between different devices.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a video quality evaluation method and device and electronic equipment.
Background
With the development of multimedia technology and display devices, videos are not only viewed on a PC (Personal Computer) after being collected, but also viewed on display devices such as ipads and mobile phones. Different devices have different resolutions, screen sizes and the like, so that the visual impressions of the same video on different devices are different, and the subjective quality evaluation of the video viewed on different viewing devices becomes an important way and way for knowing the subjective impressions of users.
In the related art, two modes of evaluating the quality of videos on different devices are provided, one mode is that an evaluator watches videos on different devices in a certain specific environment and scores the videos to obtain quality evaluation results under different devices, but the mode needs to consume a large amount of manpower and financial resources; the other method is to grade the video through a quality evaluation algorithm, develop and train corresponding models aiming at different devices, and use the models to predict the quality of the video with unknown quality on the corresponding devices, but the method develops and trains corresponding subjective quality evaluation models for different devices respectively, so that the cost is high, and the time consumption and the resource occupation are high when model prediction is performed on machines with weak processing performance, such as mobile phones and the like. Therefore, the technical solutions provided in the related art have problems of time consumption and limited processing resources.
Disclosure of Invention
The invention aims to provide a video quality evaluation method, a video quality evaluation device and electronic equipment, so as to improve the cost of cross-platform video quality evaluation and avoid the problem of limited processing resources.
In a first aspect, the present invention provides a video quality evaluation method, including: inputting the obtained video to be evaluated into a pre-trained quality evaluation model to obtain a first evaluation result when the video to be evaluated is played on first equipment; the quality evaluation model is obtained through training of a preset sample set, and each sample in the sample set comprises a sample video and a quality evaluation score of the sample video when the sample video is played on first equipment; and determining a second evaluation result when the video to be evaluated is played on the second equipment based on a preset quality evaluation mapping relation between the second equipment and the first evaluation result.
In an alternative embodiment, the quality evaluation mapping relationship between the second device and the first device is determined by: acquiring a plurality of label data; each annotation data comprises an annotation video, and a quality evaluation score when the annotation video is played on first equipment and a quality evaluation score when the annotation video is played on second equipment; and performing data fitting on the quality evaluation score of each marked video when the marked video is played on the first equipment and the quality evaluation score when the marked video is played on the second equipment to obtain a quality evaluation mapping relation between the second equipment and the first equipment.
In an optional implementation manner, the step of performing data fitting on the quality evaluation score of each annotation video when played on the first device and the quality evaluation score when played on the second device to obtain a quality evaluation mapping relationship between the second device and the first device includes: substituting the quality evaluation score of each marked video when being played on the first equipment and the quality evaluation score when being played on the second equipment into a preset objective function, and determining the numerical value of a function parameter in the objective function; and determining the target function of the determined function parameter as a quality evaluation mapping relation between the second equipment and the first equipment.
In an alternative embodiment, the objective function includes:
Q2＝a/(b+exp(-c*Q1))；
wherein Q2 represents the quality assessment score of the annotation video as it is played on the second device; q1 represents the quality assessment score of the annotation video as it is played on the first device; a. b and c both represent function parameters.
In an alternative embodiment, the quality evaluation model is obtained by training in the following manner: obtaining a sample set; and performing machine learning training on the initial model of the quality evaluation model based on the sample set to obtain the quality evaluation model.
In an optional embodiment, the step of performing machine learning training on the initial model of the quality evaluation model based on the sample set to obtain the quality evaluation model includes: determining a target sample based on the sample set; inputting the target sample into the initial model to obtain an output result; determining a loss value based on the output result and the quality evaluation score carried by the target sample; and adjusting the weight parameters of the initial model according to the loss values, and continuing to execute the step of determining the target sample based on the sample set until the adjusted initial model converges or reaches the preset training times to obtain the quality evaluation model.
In an optional implementation manner, the step of determining, based on a preset quality evaluation mapping relationship between the second device and the first evaluation result, a second evaluation result when the video to be evaluated is played on the second device includes: and substituting the first evaluation result into a quality evaluation mapping relation between the second equipment and the first equipment to obtain a second evaluation result when the video to be evaluated is played on the second equipment.
In a second aspect, the present invention provides a video quality evaluation apparatus, including: the quality evaluation module is used for inputting the acquired video to be evaluated into a pre-trained quality evaluation model to obtain a first evaluation result when the video to be evaluated is played on the first equipment; the quality evaluation model is obtained through training of a preset sample set, and each sample in the sample set comprises a sample video and a quality evaluation score of the sample video when the sample video is played on first equipment; and the evaluation conversion module is used for determining a second evaluation result when the video to be evaluated is played on the second equipment based on a preset quality evaluation mapping relation between the second equipment and the first evaluation result.
In a third aspect, the present invention provides an electronic device comprising a processor and a memory, the memory storing machine executable instructions capable of being executed by the processor, the processor executing the machine executable instructions to implement the video quality assessment method described above.
In a fourth aspect, the present invention provides a machine-readable storage medium having stored thereon machine-executable instructions that, when invoked and executed by a processor, cause the processor to implement the video quality assessment method described above.
The embodiment of the invention has the following beneficial effects:
the invention provides a video quality evaluation method, a video quality evaluation device and electronic equipment.A video to be evaluated is input into a quality evaluation model trained in advance under first equipment to obtain a first evaluation result when the video to be evaluated is played on the first equipment; and then determining a second evaluation result when the video to be evaluated is played on the second equipment based on a preset quality evaluation mapping relation between the second equipment and the first evaluation result. According to the method, the quality evaluation model obtained by training under the first device is used to obtain the quality evaluation result of the video played on the first device, and then the quality evaluation result of the video on other devices can be obtained through the quality evaluation mapping relation between different devices.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention as set forth above.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a video quality evaluation method according to an embodiment of the present invention;
fig. 2 is a flowchart of another video quality evaluation method according to an embodiment of the present invention;
fig. 3 is a flowchart of a training method of a video quality evaluation apparatus according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a video quality evaluation apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the related art, two methods for performing quality evaluation on videos played on different devices are provided, one scheme is determined through a subjective evaluation test, namely, an evaluator watches videos on different devices in a certain specific environment and scores the videos to obtain quality evaluation results under different devices, but the method needs to consume a large amount of manpower and financial resources and needs to perform the subjective evaluation test on each video on devices of different models.
The other scheme is that the video is scored through a quality evaluation algorithm, corresponding models need to be developed and trained aiming at different devices, and the models are used on the corresponding devices to predict the quality of the video. On one hand, the training data is obtained by carrying out subjective labeling on a large amount of video data on different equipment, so that the cost is high, on the other hand, the real-time performance can be ensured by predicting the trained model on a machine with higher processing performance such as a PC (personal computer), but the time consumption and the resource occupation are high when model prediction is carried out on machines with weaker processing performance such as a mobile phone.
Based on the above problems, embodiments of the present invention provide a video quality evaluation method, an apparatus, and an electronic device, where the method is applied in a scene where a video is subjected to quality evaluation on different devices. To facilitate understanding of the present embodiment, first, a video quality evaluation method disclosed in the present embodiment is described in detail, and as shown in fig. 1, the method includes the following specific steps:
step S102, inputting the obtained video to be evaluated into a quality evaluation model which is trained in advance to obtain a first evaluation result when the video to be evaluated is played on first equipment; the quality evaluation model is obtained through training of a preset sample set, and each sample in the sample set comprises a sample video and a quality evaluation score of the sample video when the sample video is played on the first device.
The video to be evaluated can be a video shot by a camera or a video recorder, can also be a certain video in a specified video file, and can also be a video segment captured from a live video or a recorded video. In specific implementation, the video to be evaluated may be taken by a device such as a camera connected to the communication device, or may be acquired from a storage device in which the taken video to be evaluated is stored, or may be acquired from a storage device of a designated video file.
The quality evaluation model can be a neural network model or a deep learning model. The quality evaluation model is usually obtained by training a sample set in a machine learning manner, the sample set comprises a large number of samples, each sample comprises a sample video and a quality evaluation score of the sample video when being played on first equipment, and the quality evaluation score is a result of a marker scoring the video playing quality by using a uniform marking standard when the sample video is played on the first equipment. To ensure the generalization of the model, the sample video in the sample set is usually several videos collected at different scenes and different resolutions.
In a specific implementation, the first device usually selects a device with higher resolution and better computational power, for example, a computer or a personal computer with a resolution of 1080p or above, and selects the computer or the personal computer with higher resolution as the first device, because the computational power of the computer or the personal computer is stronger, model training and quality evaluation result prediction can be better performed under sufficient computational power, so that the problems of higher time consumption and resource occupation when model prediction is performed on a machine with weaker processing performance, such as a mobile phone, can be avoided.
Inputting a video to be evaluated into a trained quality evaluation model, wherein the quality evaluation model can evaluate the quality of the video to be evaluated, so as to obtain a first evaluation result when the video to be evaluated is played on first equipment, and the first evaluation result is usually a quality evaluation score.
And step S104, determining a second evaluation result when the video to be evaluated is played on the second equipment based on a preset quality evaluation mapping relation between the second equipment and the first evaluation result.
The second device is usually other than the first device, and the second device may be various models of mobile phones, tablet computers, televisions, and the like. The quality evaluation mapping relation between the second device and the first device is obtained by a research and development staff according to the quality evaluation scores of the first device and the second device when the same video is played in advance, specifically, the quality evaluation score of a certain video played on the first device and the quality evaluation score of a certain video played on the second device are obtained by pre-marking by a marker, the accuracy is high, and therefore the accurate quality mapping relation between the first device and the second device can be obtained.
After a first evaluation result of the video to be evaluated when the video is played on the first device is obtained, the first evaluation result can be converted into a second evaluation result of the video to be evaluated when the video is played on the second device according to a quality evaluation mapping relationship between the second device and the first device.
The video quality evaluation method provided by the embodiment of the invention comprises the steps of firstly inputting an obtained video to be evaluated into a quality evaluation model trained in advance under first equipment to obtain a first evaluation result when the video to be evaluated is played on the first equipment; and then determining a second evaluation result when the video to be evaluated is played on the second equipment based on a preset quality evaluation mapping relation between the second equipment and the first evaluation result. According to the method, the quality evaluation model obtained by training under the first device is used to obtain the quality evaluation result of the video played on the first device, and then the quality evaluation result of the video on other devices can be obtained through the quality evaluation mapping relation between different devices.
The embodiment of the invention also provides another video quality evaluation method, which is realized on the basis of the method of the embodiment; the method mainly describes a specific process of determining a quality evaluation mapping relation between the second device and the first device before obtaining a first evaluation result (realized by steps S202-S204 described below), and a specific process of determining a second evaluation result when a video to be evaluated is played on the second device based on a preset quality evaluation mapping relation between the second device and the first evaluation result (realized by step S208 described below); as shown in fig. 2, the method comprises the following specific steps:
step S202, acquiring a plurality of marking data; each annotation data comprises an annotation video, and a quality evaluation score when the annotation video is played on a first device and a quality evaluation score when the annotation video is played on a second device.
The plurality of annotation data may be a plurality of samples extracted from the sample set, and then the sample video (equivalent to the annotation video) in each sample is played on the second device, so that the annotator performs quality evaluation annotation on the played sample video to obtain a quality evaluation score when the sample video is played on the second device, and each annotation data includes the quality evaluation score when the sample video is played on the first device and the quality evaluation score when the sample video is played on the second device. In a specific implementation, the number of samples extracted from the sample set may be set according to the development requirement, for example, may be set to be not less than 3.
In some embodiments, the annotation video in the annotation data may also be a video different from the sample video in the sample set, and after the annotation video is obtained, the annotator may play the annotation video on the first device and the second device respectively using a uniform annotation standard, and annotate the play quality of the annotation video to obtain a quality evaluation score when the annotation video is played on the first device and a quality evaluation score when the annotation video is played on the second device.
In a specific implementation, the range of the quality evaluation scores marked by the marker can be set between 0 and 100 or between 0 and 50, and the like, so as to unify the quality grade corresponding to each quality evaluation score.
Step S204, performing data fitting on the quality evaluation score of each annotation video when played on the first device and the quality evaluation score when played on the second device to obtain a quality evaluation mapping relation between the second device and the first device.
And performing data fitting by using the quality evaluation score of each video in the plurality of labeled data when the video is played on the first device and the quality evaluation score of each video when the video is played on the second device, so that a quality evaluation mapping relation from the first device to the second device can be obtained through fitting. Specifically, the step S204 can be implemented by the following steps 10 to 11:
and step 10, substituting the quality evaluation score of each marked video when being played on the first equipment and the quality evaluation score when being played on the second equipment into a preset objective function, and determining the numerical value of the function parameter in the objective function.
The objective function may be set according to research and development requirements, and the unknown function parameter in the objective function is usually a constant, and may be determined according to the quality evaluation scores of the multiple annotation videos when played on the first device and the quality evaluation scores of the multiple annotation videos when played on the second device.
In a specific implementation, the objective function may be selected from the following functions:
Q2＝a/(b+exp(-c*Q1))；
wherein Q2 represents the quality assessment score of the annotation video as it is played on the second device; q1 represents the quality assessment score of the annotation video as it is played on the first device; a. b and c both represent function parameters.
In some embodiments, to define the quality assessment score when the video is played on the second device, the range of values of the quality assessment score may be constrained by the equation Q2 ═ max (min (Q2,100),0) to define the range of values of the quality assessment score between 0-100. Specifically, the above equation may be adjusted to limit the range of the quality evaluation score to other numerical ranges.
And step 11, determining the target function of the determined function parameter as a quality evaluation mapping relation between the second equipment and the first equipment.
In a specific implementation, the quality evaluation mapping relationship between the second device and the first device may be represented by a function, so that the quality evaluation mapping relationship between different devices may be more intuitively indicated.
Step S206, inputting the acquired video to be evaluated into a pre-trained quality evaluation model to obtain a first evaluation result when the video to be evaluated is played on the first device.
And step S208, substituting the first evaluation result into the quality evaluation mapping relation between the second equipment and the first equipment to obtain a second evaluation result when the video to be evaluated is played on the second equipment.
According to the video quality evaluation method, when the cross-device video quality evaluation result is calculated, the quality evaluation result of the video on the first device is obtained only by using the quality evaluation model on the first device in a prediction mode, and then the quality evaluation score of the video on other devices can be obtained through a simple function mapping relation.
The embodiment of the invention also provides a training method of the quality evaluation model, wherein the quality evaluation model is a model used for realizing the method of the embodiment; as shown in fig. 3, the training method includes the following specific steps:
step S302, a sample set is obtained; each sample in the sample set includes a sample video and a quality assessment score for the sample video as it is played on the first device.
The sample set comprises a large number of samples, each sample comprises a sample video and a quality evaluation score of the sample video when the sample video is played on the first device, and the quality evaluation score is a result of a marker scoring the video playing quality by using a uniform marking standard when the sample video is played on the first device.
And step S304, performing machine learning training on the initial model of the quality evaluation model based on the sample set to obtain the quality evaluation model.
In a specific implementation, the step S304 can be implemented by the following steps 20 to 23:
a target sample is determined based on the sample set, step 20.
Randomly selecting a sample from the sample set as a target sample when the target sample is determined from the sample set for the first time; and then, determining the target sample pair, wherein one sample can be randomly selected as a new target sample from the samples which are not determined as the target sample in the sample set.
And 21, inputting the target sample into an initial model to obtain an output result.
The initial model may be a neural network or a deep learning model, etc. The output result may be a result obtained after the initial model performs quality evaluation on the sample video in the target sample.
And step 22, determining a loss value based on the output result and the quality evaluation score carried by the target sample.
And during specific implementation, determining the difference between the output result and the quality evaluation score carried by the target sample as a loss value. Specifically, the loss value may be a difference between the output result and the quality evaluation score carried by the target sample, or may be a difference between the output result calculated by a preset loss function and the quality evaluation score carried by the target sample, where the loss function may be a cross entropy loss function, an absolute value loss function, a square loss function, or the like.
And step 23, adjusting the weight parameters of the initial model according to the loss values, and continuing to execute the step of determining the target sample based on the sample set until the adjusted initial model converges or reaches the preset training times, so as to obtain the quality evaluation model.
In specific implementation, the derivative of the loss value L to all the weight parameters W in the initial model can be obtained through a back propagation algorithm
The weight parameters W' of the initial model are then updated by a stochastic gradient descent algorithm:
and continuously and iteratively updating the weight parameters of the initial model until the initial model converges to obtain the quality evaluation model. Wherein, α is a learning rate, and is a super parameter preset manually, and the value of α is usually 0.01, 0.001, etc.
According to the quality evaluation model training method, the quality evaluation model obtained through training in the mode can accurately evaluate the quality evaluation result when the video is played on the first equipment, so that the accuracy of obtaining the quality evaluation score on the second equipment according to the quality evaluation mapping relation between the first equipment and the second equipment can be improved.
For the embodiment of the quality evaluation method, an embodiment of the present invention further provides a video quality evaluation apparatus, as shown in fig. 4, the apparatus includes:
the quality evaluation module 40 is configured to input the acquired video to be evaluated into a quality evaluation model which is trained in advance, so as to obtain a first evaluation result when the video to be evaluated is played on the first device; the quality evaluation model is obtained through training of a preset sample set, and each sample in the sample set comprises a sample video and a quality evaluation score of the sample video when the sample video is played on the first device.
And the evaluation conversion module 41 is configured to determine a second evaluation result when the video to be evaluated is played on the second device based on a preset quality evaluation mapping relationship between the second device and the first evaluation result.
The video quality evaluation device firstly inputs an acquired video to be evaluated into a quality evaluation model trained in advance under first equipment to obtain a first evaluation result when the video to be evaluated is played on the first equipment; and then determining a second evaluation result when the video to be evaluated is played on the second equipment based on a preset quality evaluation mapping relation between the second equipment and the first evaluation result. According to the method, the quality evaluation model obtained by training under the first device is used to obtain the quality evaluation result of the video played on the first device, and then the quality evaluation result of the video on other devices can be obtained through the quality evaluation mapping relation between different devices.
Specifically, the apparatus further includes a relationship determining module, configured to: acquiring a plurality of label data; each annotation data comprises an annotation video, and a quality evaluation score when the annotation video is played on first equipment and a quality evaluation score when the annotation video is played on second equipment; and performing data fitting on the quality evaluation score of each marked video when the marked video is played on the first equipment and the quality evaluation score when the marked video is played on the second equipment to obtain a quality evaluation mapping relation between the second equipment and the first equipment.
Further, the relationship determination module is further configured to: substituting the quality evaluation score of each marked video when being played on the first equipment and the quality evaluation score when being played on the second equipment into a preset objective function, and determining the numerical value of a function parameter in the objective function; and determining the target function of the determined function parameter as a quality evaluation mapping relation between the second equipment and the first equipment.
In a specific implementation, the objective function includes:
Q2＝a/(b+exp(-c*Q1))；
wherein Q2 represents the quality assessment score of the annotation video as it is played on the second device; q1 represents the quality assessment score of the annotation video as it is played on the first device; a. b and c both represent function parameters.
Specifically, the apparatus further includes a model training module configured to: obtaining a sample set; and performing machine learning training on the initial model of the quality evaluation model based on the sample set to obtain the quality evaluation model.
Further, the model training module is further configured to: determining a target sample based on the sample set; inputting the target sample into the initial model to obtain an output result; determining a loss value based on the output result and the quality evaluation score carried by the target sample; and adjusting the weight parameters of the initial model according to the loss values, and continuing to execute the step of determining the target sample based on the sample set until the adjusted initial model converges or reaches the preset training times to obtain the quality evaluation model.
Specifically, the evaluation conversion module 41 is further configured to: and substituting the first evaluation result into a quality evaluation mapping relation between the second equipment and the first equipment to obtain a second evaluation result when the video to be evaluated is played on the second equipment.
The video quality evaluation device provided by the embodiment of the invention has the same implementation principle and technical effect as the method embodiment, and for brief description, the corresponding content in the method embodiment can be referred to where the device embodiment is not mentioned.
An embodiment of the present invention further provides an electronic device, as shown in fig. 5, where the electronic device includes a processor 101 and a memory 100, where the memory 100 stores machine executable instructions that can be executed by the processor 101, and the processor 101 executes the machine executable instructions to implement the video quality evaluation method.
Further, the terminal device shown in fig. 5 further includes a bus 102 and a communication interface 103, and the processor 101, the communication interface 103, and the memory 100 are connected through the bus 102.
The memory 100 may include a high-speed Random Access Memory (RAM) and may further include a non-volatile memory (non-volatile memory), such as at least one disk memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 103 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, and the like can be used. The bus 102 may be an ISA bus, PCI bus, EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 5, but this does not indicate only one bus or one type of bus.
The processor 101 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 101. The processor 101 may be a general-purpose processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 100, and the processor 101 reads the information in the memory 100, and completes the steps of the method of the foregoing embodiment in combination with the hardware thereof.
The embodiment of the present invention further provides a machine-readable storage medium, where the machine-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are called and executed by a processor, the machine-executable instructions cause the processor to implement the video quality evaluation method.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A video quality evaluation method, the method comprising:
inputting the obtained video to be evaluated into a pre-trained quality evaluation model to obtain a first evaluation result when the video to be evaluated is played on first equipment; the quality evaluation model is obtained through training of a preset sample set, and each sample in the sample set comprises a sample video and a quality evaluation score of the sample video when the sample video is played on the first equipment;
and determining a second evaluation result when the video to be evaluated is played on the second equipment based on a preset quality evaluation mapping relation between the second equipment and the first evaluation result.
2. The method of claim 1, wherein the quality assessment mapping relationship between the second device and the first device is determined by:
acquiring a plurality of label data; each piece of annotation data comprises an annotation video, and a quality evaluation score of the annotation video when played on the first device and a quality evaluation score of the annotation video when played on the second device;
and performing data fitting on the quality evaluation score of each marked video when the marked video is played on the first equipment and the quality evaluation score when the marked video is played on the second equipment to obtain a quality evaluation mapping relation between the second equipment and the first equipment.
3. The method of claim 2, wherein the step of performing data fitting on the quality evaluation score of each of the annotated videos when played on the first device and the quality evaluation score when played on the second device to obtain a quality evaluation mapping relationship between the second device and the first device comprises:
substituting the quality evaluation score of each marked video when being played on the first equipment and the quality evaluation score when being played on the second equipment into a preset objective function, and determining the numerical value of a function parameter in the objective function;
and determining the target function for determining the function parameter as a quality evaluation mapping relation between the second equipment and the first equipment.
4. The method of claim 3, wherein the objective function comprises:
Q2＝a/(b+exp(-c*Q1))；
wherein Q2 represents a quality assessment score for the annotated video as played on the second device; q1 represents a quality assessment score for the annotated video as played on the first device; a. b and c both represent the function parameters.
5. The method of claim 1, wherein the quality assessment model is trained by:
obtaining the sample set;
and performing machine learning training on the initial model of the quality evaluation model based on the sample set to obtain the quality evaluation model.
6. The method of claim 5, wherein the step of performing machine learning training on the initial model of the quality evaluation model based on the sample set to obtain the quality evaluation model comprises:
determining a target sample based on the sample set;
inputting the target sample into the initial model to obtain an output result;
determining a loss value based on the output result and the quality evaluation score carried by the target sample;
and adjusting the weight parameters of the initial model according to the loss values, and continuing to execute the step of determining the target sample based on the sample set until the adjusted initial model converges or reaches a preset training time, so as to obtain the quality evaluation model.
7. The method according to claim 1, wherein the step of determining a second evaluation result when the video to be evaluated is played on the second device based on a preset quality evaluation mapping relationship between the second device and the first evaluation result comprises:
and substituting the first evaluation result into a quality evaluation mapping relation between the second equipment and the first equipment to obtain a second evaluation result when the video to be evaluated is played on the second equipment.
8. A video quality evaluation apparatus, characterized in that the apparatus comprises:
the quality evaluation module is used for inputting the acquired video to be evaluated into a pre-trained quality evaluation model to obtain a first evaluation result when the video to be evaluated is played on first equipment; the quality evaluation model is obtained through training of a preset sample set, and each sample in the sample set comprises a sample video and a quality evaluation score of the sample video when the sample video is played on the first equipment;
and the evaluation conversion module is used for determining a second evaluation result when the video to be evaluated is played on the second equipment based on a preset quality evaluation mapping relation between the second equipment and the first evaluation result.
9. An electronic device comprising a processor and a memory, the memory storing machine executable instructions executable by the processor, the processor executing the machine executable instructions to implement the video quality assessment method of any one of claims 1 to 7.
10. A machine-readable storage medium having stored thereon machine-executable instructions which, when invoked and executed by a processor, cause the processor to carry out the video quality assessment method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110695109.1A CN113420809A (en) | 2021-06-22 | 2021-06-22 | Video quality evaluation method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110695109.1A CN113420809A (en) | 2021-06-22 | 2021-06-22 | Video quality evaluation method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113420809A true CN113420809A (en) | 2021-09-21 |
Family
ID=77716189
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110695109.1A Pending CN113420809A (en) | 2021-06-22 | 2021-06-22 | Video quality evaluation method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113420809A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114071233A (en) * | 2021-11-04 | 2022-02-18 | 广州华多网络科技有限公司 | Audio and video quality evaluation method and device, equipment, medium and product thereof |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105898294A (en) * | 2016-05-27 | 2016-08-24 | 乐视控股（北京）有限公司 | Video quality evaluation method and device |
| CN110674925A (en) * | 2019-08-29 | 2020-01-10 | 厦门大学 | No-reference VR video quality evaluation method based on 3D convolutional neural network |
| WO2020080698A1 (en) * | 2018-10-19 | 2020-04-23 | 삼성전자 주식회사 | Method and device for evaluating subjective quality of video |
| CN111711816A (en) * | 2020-07-08 | 2020-09-25 | 福州大学 | Video objective quality evaluation method based on observable coding effect intensity |
-
2021
- 2021-06-22 CN CN202110695109.1A patent/CN113420809A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105898294A (en) * | 2016-05-27 | 2016-08-24 | 乐视控股（北京）有限公司 | Video quality evaluation method and device |
| WO2020080698A1 (en) * | 2018-10-19 | 2020-04-23 | 삼성전자 주식회사 | Method and device for evaluating subjective quality of video |
| CN110674925A (en) * | 2019-08-29 | 2020-01-10 | 厦门大学 | No-reference VR video quality evaluation method based on 3D convolutional neural network |
| CN111711816A (en) * | 2020-07-08 | 2020-09-25 | 福州大学 | Video objective quality evaluation method based on observable coding effect intensity |
Non-Patent Citations (1)
| Title |
|---|
| 卓力;张美娜;王贯瑶;李嘉锋;: "基于支持向量回归的无参考MS-SSIM视频质量评价模型", 北京工业大学学报, no. 12, 10 December 2018 (2018-12-10), pages 20 - 27 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114071233A (en) * | 2021-11-04 | 2022-02-18 | 广州华多网络科技有限公司 | Audio and video quality evaluation method and device, equipment, medium and product thereof |
| CN114071233B (en) * | 2021-11-04 | 2023-04-25 | 广州华多网络科技有限公司 | Audio and video quality evaluation method and device, equipment, medium and product thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111314733B (en) | Method and apparatus for evaluating video sharpness | |
| CN112950581B (en) | Quality evaluation method and device and electronic equipment | |
| CN110213573B (en) | Video quality evaluation method and device and electronic equipment | |
| CN112818737B (en) | Video identification method, device, storage medium and terminal | |
| CN107545301B (en) | Page display method and device | |
| CN110211121B (en) | Method and device for pushing model | |
| CN112037223B (en) | Image defect detection method and device and electronic equipment | |
| CN113962965A (en) | Image quality evaluation method, device, equipment and storage medium | |
| WO2022062968A1 (en) | Self-training method, system, apparatus, electronic device, and storage medium | |
| CN112950579B (en) | Image quality evaluation method and device and electronic equipment | |
| CN112767313B (en) | Video quality evaluation method and device and electronic equipment | |
| CN108875931A (en) | Neural metwork training and image processing method, device, system | |
| CN112995690B (en) | Live content category identification method, device, electronic equipment and readable storage medium | |
| US20180048860A1 (en) | Method and system for measuring quality of video call | |
| CN109271929B (en) | Detection method and device | |
| CN111753729A (en) | False face detection method and device, electronic equipment and storage medium | |
| CN113420809A (en) | Video quality evaluation method and device and electronic equipment | |
| CN112434717A (en) | Model training method and device | |
| CN112672146B (en) | Frame rate testing method and computing device for video player playing video | |
| US11527091B2 (en) | Analyzing apparatus, control method, and program | |
| CN117557538A (en) | PCB surface defect detection method, device, computer equipment and storage medium | |
| CN109685015B (en) | Image processing method and device, electronic equipment and computer storage medium | |
| CN112614124A (en) | Video definition evaluation model training method, device and storage medium | |
| CN117314863A (en) | Defect output method, device, equipment and storage medium | |
| CN111832354A (en) | Target object age identification method and device and electronic equipment |
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 |