CN118411583A - Immersive video quality evaluation method and device based on multi-feature fusion - Google Patents

Abstract

The present invention discloses an immersive video quality evaluation method and device based on multi-feature fusion, which relate to the field of video processing, including: extracting features from a reference texture video sequence and a distorted texture video sequence using a 3D-LOG filter to obtain reference texture features and distorted texture features, calculating texture feature similarity, and obtaining a texture video quality score through a 3D-LOG pooling strategy based on the texture feature similarity; calculating reference depth features and distorted depth features according to a reference depth video sequence and a distorted depth video sequence; calculating depth feature similarity according to the reference depth features and the distorted depth features and determining gradient weights, and calculating a depth video quality score according to the depth feature similarity and the gradient weights; and calculating a quality score of an immersive video to be evaluated according to the texture video quality score and the depth video quality score, so as to solve the problem that the existing video evaluation algorithm does not conform to the visual characteristics of the human eye and the characteristics of the immersive video.

Description

Immersive video quality evaluation method and device based on multi-feature fusion

Technical Field

The present invention relates to the field of video processing, and in particular to an immersive video quality evaluation method and device based on multi-feature fusion.

Background technique

With the rapid development of high-speed network transmission, video acquisition, video processing and display technology, as well as the growing demand for immersive experience, immersive video has ushered in an explosive period and has become a hot spot in video technology research. It is widely used in remote office, intelligent transportation, commercial broadcasting and other fields. Compared with traditional video, immersive video has the characteristics of ultra-wide viewing angle, high degree of freedom, high resolution, etc., and has a very high sense of immersion and interactivity. The high degree of freedom is reflected in the fact that when people watch the video, it can provide translation on three main axes and rotation on three auxiliary axes, which can give users an immersive feeling.

Immersive video mainly adopts multi-viewpoint texture plus depth video format, which can be generated by computer or shot by camera. It will be interfered by various distortions during video processing, which weakens the visual expression effect of immersive scene, affects the user experience and reduces the subjective perception quality. Therefore, it is very important to propose an algorithm that conforms to the visual characteristics of human eyes and can accurately and quickly evaluate the quality of immersive video.

At present, most video quality assessment algorithms are mainly focused on the field of natural videos. However, since immersive videos have different temporal and spatial characteristics from natural videos in terms of content and video format, the effect of directly migrating quality assessment algorithms related to natural videos to immersive videos is relatively poor. Therefore, designing a video quality assessment algorithm that conforms to the characteristics of human vision and immersive videos has important theoretical research significance and practical application value.

Summary of the invention

The purpose of this application is to propose an immersive video quality evaluation method and device based on multi-feature fusion to address the above-mentioned technical problems.

In a first aspect, the present invention provides an immersive video quality evaluation method based on multi-feature fusion, comprising the following steps:

A reference immersive video and an immersive video to be evaluated are obtained, wherein the reference immersive video includes a reference texture video sequence and a reference depth video sequence, and the immersive video to be evaluated includes a distorted texture video sequence and a distorted depth video sequence. A 3D-LOG filter is used to extract features from the reference texture video sequence and the distorted texture video sequence to obtain reference texture features and distorted texture features. Texture feature similarity is calculated based on the reference texture features and the distorted texture features, and a texture video quality score is obtained based on the texture feature similarity through a 3D-LOG pooling strategy.

A reference depth feature and a distorted depth feature are calculated based on a reference depth video sequence and a distorted depth video sequence; a depth feature similarity is calculated based on the reference depth feature and the distorted depth feature and a gradient weight is determined, and a depth video quality score is calculated based on the depth feature similarity and the gradient weight;

The quality score of the immersive video to be evaluated is calculated according to the texture video quality score and the depth video quality score.

Preferably, a 3D-LOG filter is used to extract features from the reference texture video sequence and the distorted texture video sequence to obtain reference texture features and distorted texture features, which specifically include:

The calculation formula of 3D-LOG filter is:

;

in, Represents the horizontal, vertical and time coordinates in the space-time domain, is the standard deviation of the 3D Gaussian kernel function, , Represents the function corresponding to the 3D-LOG filter;

The reference texture video sequence and the distorted texture video sequence are respectively input into the 3D-LOG filter for convolution to obtain the reference texture features and the distorted texture features, as shown in the following formula:

;

;

in, and Respectively represent the brightness value corresponding to each pixel of the input reference texture video sequence and the distorted texture video sequence, and Respectively represent the reference texture features and distorted texture features extracted by the 3D-LOG filter, The symbol represents the convolution operation.

Preferably, the texture feature similarity is calculated based on the reference texture feature and the distorted texture feature, and the texture video quality score is obtained through the 3D-LOG pooling strategy based on the texture feature similarity, specifically including:

The texture feature similarity is calculated using the following formula: :

;

in, and Respectively represent the reference texture features and distorted texture features extracted by 3D-LOG, is a constant that maintains numerical stability;

The maximum value of the reference texture feature and the distorted texture feature is used as the texture weight , as shown below:

;

Among them, max means taking the maximum value;

The texture weight and texture feature similarity are weighted to obtain the texture video quality score , as shown below:

.

Preferably, the reference depth feature and the distorted depth feature are calculated according to the reference depth video sequence and the distorted depth video sequence, and the reference depth feature and the distorted depth feature are obtained, specifically including:

The gradient amplitude is calculated for the reference texture video sequence and the distorted texture video sequence respectively to obtain the corresponding depth features:

;

;

;

in, represents a depth video frame, and denote the partial derivatives in the horizontal and vertical directions respectively, and Represent the gradient amplitude components in the horizontal and vertical directions respectively, Represents the depth feature. The depth features calculated from the depth video frames in the reference depth video sequence and the distorted depth video sequence correspond to the reference depth features. and distortion depth features , The symbol represents the convolution operation.

Preferably, the depth feature similarity is calculated based on the reference depth feature and the distorted depth feature and the gradient weight is determined, and the depth video quality score is calculated based on the depth feature similarity and the gradient weight, specifically including:

The following formula is used to calculate the deep feature similarity:

;

in, and represent the reference depth feature and the distorted depth feature respectively, represents the deep feature similarity, is another constant that maintains numerical stability;

The maximum value of the reference depth feature and the distorted depth feature is used as the gradient weight , as shown below:

;

Among them, max means taking the maximum value;

The gradient weight and the depth feature similarity are weighted to obtain the depth video quality score. , as shown below:

.

Preferably, the quality score of the immersive video to be evaluated is calculated according to the texture video quality score and the depth video quality score, specifically including:

Calculate the importance of texture video quality score and depth video quality score to get the importance score , as shown below:

;

in, It is a parameter used to adjust the relative importance between texture features and depth features;

The maximum value of the absolute value of the texture video quality score and the absolute value of the depth video quality score is used as the evaluation weight , as shown below:

;

Among them, max means taking the maximum value. is the absolute value symbol;

The evaluation weight and the importance score are weighted and calculated to obtain the quality score MMF of the immersive video to be evaluated, as shown in the following formula:

;

Where N represents the number of immersive video sequences to be evaluated, i=1,2,…,N.

In a second aspect, the present invention provides an immersive video quality assessment device based on multi-feature fusion, comprising:

The texture video quality score calculation module is configured to obtain a reference immersive video and an immersive video to be evaluated, wherein the reference immersive video includes a reference texture video sequence and a reference depth video sequence, and the immersive video to be evaluated includes a distorted texture video sequence and a distorted depth video sequence, and extract features from the reference texture video sequence and the distorted texture video sequence using a 3D-LOG filter to obtain reference texture features and distorted texture features; calculate texture feature similarity based on the reference texture features and the distorted texture features, and obtain a texture video quality score based on the texture feature similarity using a 3D-LOG pooling strategy;

The depth video quality score calculation module is configured to calculate reference depth features and distorted depth features according to the reference depth video sequence and the distorted depth video sequence; calculate the depth feature similarity according to the reference depth feature and the distorted depth feature and determine the gradient weight, and calculate the depth video quality score according to the depth feature similarity and the gradient weight;

The quality score calculation module is configured to calculate the quality score of the immersive video to be evaluated according to the texture video quality score and the depth video quality score.

In a third aspect, the present invention provides an electronic device comprising one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner in the first aspect.

In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any implementation manner in the first aspect.

In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements the method described in any implementation manner in the first aspect.

Compared with the prior art, the present invention has the following beneficial effects:

(1) The immersive video quality evaluation method based on multi-feature fusion proposed in the present invention takes into account that immersive videos not only contain complex edge information and spatiotemporal texture features of motion changes, but also have depth information that provides immersion and high degrees of freedom, and focuses on the characteristics of the human visual system and immersive videos. Therefore, a 3D-LOG filter is used to extract the edge and contour information of the texture video in the spatial domain and the motion information in the temporal domain, and the gradient amplitude in the depth video is calculated to perceive the quality degradation caused by flicker distortion. The texture features and depth features extracted are weighted to obtain the texture video quality score and the depth video score. Finally, a weighting strategy is designed in combination with the human visual characteristics to measure the contribution of texture and depth to the immersive video, and the quality score of the immersive video is obtained. The result is highly consistent with the perception result of the human visual system.

(2) The immersive video quality evaluation method based on multi-feature fusion proposed in the present invention considers the visual characteristics of the human eye and the characteristics of immersive video from many aspects, and has good video quality evaluation performance.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

FIG1 is a schematic flow chart of an immersive video quality assessment method based on multi-feature fusion according to an embodiment of the present application;

FIG2 is a flowchart of an immersive video quality assessment method based on multi-feature fusion according to an embodiment of the present application;

FIG3 is a schematic diagram of an immersive video quality assessment device based on multi-feature fusion according to an embodiment of the present application;

FIG. 4 is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention.

Detailed ways

In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

FIG1 shows an immersive video quality assessment method based on multi-feature fusion provided by an embodiment of the present application, comprising the following steps:

S1, obtain a reference immersive video and an immersive video to be evaluated, the reference immersive video includes a reference texture video sequence and a reference depth video sequence, the immersive video to be evaluated includes a distorted texture video sequence and a distorted depth video sequence, use a 3D-LOG filter to extract features from the reference texture video sequence and the distorted texture video sequence to obtain reference texture features and distorted texture features; calculate the texture feature similarity based on the reference texture features and the distorted texture features, and obtain the texture video quality score based on the texture feature similarity through the 3D-LOG pooling strategy.

In a specific embodiment, a 3D-LOG filter is used to extract features from a reference texture video sequence and a distorted texture video sequence to obtain reference texture features and distorted texture features, which specifically include:

The calculation formula of 3D-LOG filter is:

;

in, Represents the horizontal, vertical and time coordinates in the space-time domain, is the standard deviation of the 3D Gaussian kernel function, , Represents the function corresponding to the 3D-LOG filter;

The reference texture video sequence and the distorted texture video sequence are respectively input into the 3D-LOG filter for convolution to obtain the reference texture features and the distorted texture features, as shown in the following formula:

;

;

in, and Respectively represent the brightness value corresponding to each pixel of the input reference texture video sequence and the distorted texture video sequence, and Respectively represent the reference texture features and distorted texture features extracted by 3D-LOG, The symbol represents the convolution operation.

In a specific embodiment, the texture feature similarity is calculated based on the reference texture feature and the distorted texture feature, and the texture video quality score is obtained through the 3D-LOG pooling strategy based on the texture feature similarity, which specifically includes:

The texture feature similarity is calculated using the following formula: :

;

in, and Respectively represent the reference texture features and distorted texture features extracted by 3D-LOG, is a constant that maintains numerical stability;

The maximum value of the reference texture feature and the distorted texture feature is used as the texture weight , as shown below:

;

Among them, max means taking the maximum value;

The texture weight and texture feature similarity are weighted to obtain the texture video quality score , as shown below:

.

Specifically, referring to FIG2, the immersive video to be evaluated is directly extracted into a reference texture video sequence and a reference depth video sequence without processing. The reference texture video sequence and the reference depth video sequence are both in an undistorted state. The immersive video to be evaluated is processed and extracted to obtain a distorted texture video sequence and a distorted depth video sequence. First, the reference texture video sequence and the distorted texture video sequence are subjected to feature extraction using a 3D-LOG filter to obtain reference texture features. and distorted texture features . The 3D-LOG filter can well simulate the feedback process of human visual neurons for image processing, and more comprehensively measure and perceive the temporal and spatial quality feature degradation of the texture area in the immersive video. Furthermore, the texture feature similarity is calculated based on the reference texture feature and the distorted texture feature. In the calculation formula of the texture feature similarity, The texture video quality score is obtained based on the texture feature similarity through a 3D-LOG pooling strategy. .

S2, calculating reference depth features and distorted depth features based on the reference depth video sequence and the distorted depth video sequence; calculating depth feature similarity based on the reference depth features and the distorted depth features and determining gradient weights, and calculating a depth video quality score based on the depth feature similarity and the gradient weights.

In a specific embodiment, the gradient amplitudes are calculated for the reference texture video sequence and the distorted texture video sequence respectively to obtain the corresponding depth features:

;

;

;

in, represents a depth video frame, and denote the partial derivatives in the horizontal and vertical directions respectively, and Represent the gradient amplitude components in the horizontal and vertical directions respectively, Represents the depth feature. The depth features calculated from the depth video frames in the reference depth video sequence and the distorted depth video sequence correspond to the reference depth features. and distortion depth features , The symbol represents the convolution operation.

In a specific embodiment, the depth feature similarity is calculated based on the reference depth feature and the distorted depth feature, and the gradient weight is determined. The depth video quality score is calculated based on the depth feature similarity and the gradient weight, specifically including:

The following formula is used to calculate the deep feature similarity:

;

in, and represent the reference depth feature and the distorted depth feature respectively, represents the deep feature similarity, is another constant that maintains numerical stability;

The maximum value of the reference depth feature and the distorted depth feature is used as the gradient weight , as shown below:

;

Among them, max means taking the maximum value;

The gradient weight and the depth feature similarity are weighted to obtain the depth video quality score. , as shown below:

.

Specifically, the gradient amplitude of the reference depth video sequence and the distorted depth video sequence is calculated as the key feature for detecting the flicker distortion position, and the reference depth feature and the distorted depth feature are obtained. The depth feature similarity is further calculated based on the reference depth feature and the distorted depth feature. In the calculation formula of the depth feature similarity, after a large number of experiments, it is determined that The larger value between the reference and distortion gradient features is used to calculate the gradient weight, simulating the different attention paid to different pixels by human eyes when watching videos. Then, the similarity with the extracted deep features is weighted and calculated to obtain the deep video quality score. .

S3, calculating the quality score of the immersive video to be evaluated according to the texture video quality score and the depth video quality score.

In a specific embodiment, step S3 specifically includes:

Calculate the importance of texture video quality score and depth video quality score to get the importance score , as shown below:

;

in, It is a parameter used to adjust the relative importance between texture features and depth features;

The maximum value of the absolute value of the texture video quality score and the absolute value of the depth video quality score is used as the evaluation weight , as shown below:

;

Among them, max means taking the maximum value. is the absolute value symbol;

The evaluation weight and the importance score are weighted and calculated to obtain the quality score MMF of the immersive video to be evaluated, as shown in the following formula:

;

Where N represents the number of immersive video sequences to be evaluated, i=1,2,…,N.

Specifically, the texture features extracted by the 3D-LOG filter and the depth features obtained by calculating the gradient amplitude are used as evaluation indicators of immersive video quality. Combined with the visual characteristics of the human eye, the larger quality score of the texture video quality score and the depth video quality score is used as a weighting strategy to characterize the quality score of the immersive video. It is a parameter used to adjust the relative importance between texture features and depth features. After experimental analysis, it is set to .

The above steps S1-S3 do not necessarily represent the order between the steps, but are represented by step symbols, and the order between the steps can be adjusted.

The superiority of the method of the present invention is demonstrated below through specific examples and data.

Table 1 Comprehensive performance comparison results of the proposed method MMF and other algorithms on the SIMVD database:

Table 1 is a comparison of the experimental results of the immersive video quality evaluation method based on multi-feature fusion proposed in the present invention (expressed by MMF) and other advanced algorithms on the immersive video database SIMVD, where SSIM, MS-SSIM, GMSD, VSI, FSIM, SPSIM, GSS, ESIM, GFM, SpEED, ViS3, STMAD, VMAF, SGFTM, and IV-PSNR are the names of other advanced algorithms. PLCC (Pearson linear correlation coefficient), SROCC (Spearman rank correlation coefficient) and RMSE (root mean square error) are three common standards, which are three classic related parameters used to consider the quality of evaluation methods in the field of video quality evaluation. The closer the values of PLCC and SROCC are to 1, the smaller the RMSE value is, and the higher the correlation between the results of the objective algorithm and the results of the subjective evaluation is, the more superior the algorithm is. In Table 1, the top three algorithms with better performance are represented in bold. From the data, the PLCC and SROCC values obtained by the immersive video quality evaluation method based on multi-feature fusion proposed in the present invention are greater than those of other algorithms and closer to 1, and the RMSE is smaller than that of other algorithms. This shows that the higher the correlation between the immersive video quality evaluation method based on multi-feature fusion proposed in the present invention and the results of subjective evaluation, the more superior the algorithm is, and it is more superior in evaluating the quality of immersive video.

Further referring to Figure 3, as an implementation of the methods shown in the above figures, the present application provides an embodiment of an immersive video quality evaluation device based on multi-feature fusion. The device embodiment corresponds to the method embodiment shown in Figure 1, and the device can be specifically applied to various electronic devices.

The embodiment of the present application provides an immersive video quality assessment device based on multi-feature fusion, comprising:

The texture video quality score calculation module 1 is configured to obtain a reference immersive video and an immersive video to be evaluated, wherein the reference immersive video includes a reference texture video sequence and a reference depth video sequence, and the immersive video to be evaluated includes a distorted texture video sequence and a distorted depth video sequence, and extract features from the reference texture video sequence and the distorted texture video sequence using a 3D-LOG filter to obtain reference texture features and distorted texture features; calculate texture feature similarity based on the reference texture features and the distorted texture features, and obtain a texture video quality score based on the texture feature similarity using a 3D-LOG pooling strategy;

The depth video quality score calculation module 2 is configured to calculate reference depth features and distorted depth features according to the reference depth video sequence and the distorted depth video sequence; calculate the depth feature similarity according to the reference depth feature and the distorted depth feature and determine the gradient weight, and calculate the depth video quality score according to the depth feature similarity and the gradient weight;

The quality score calculation module 3 is configured to calculate the quality score of the immersive video to be evaluated according to the texture video quality score and the depth video quality score.

FIG4 is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. As shown in FIG4, the electronic device of this embodiment includes: a processor 401 and a memory 402; wherein the memory 402 is used to store computer-executable instructions; the processor 401 is used to execute the computer-executable instructions stored in the memory to implement the various steps performed by the electronic device in the above embodiment. For details, please refer to the relevant description in the above method embodiment.

Optionally, the memory 402 may be independent or integrated with the processor 401 .

When the memory 402 is independently provided, the electronic device further includes a bus 403 for connecting the memory 402 and the processor 401 .

An embodiment of the present invention further provides a computer storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the above method is implemented.

An embodiment of the present invention further provides a computer program product, including a computer program. When the computer program is executed by a processor, the above method is implemented.

In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to implement the solution of this embodiment.

In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, or each module may exist physically separately, or two or more modules may be integrated into one unit. The above-mentioned module-composed unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the methods of various embodiments of the present application.

It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.

The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device or a main control device.

Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk, etc., various media that can store program codes.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims (10)

1. An immersive video quality evaluation method based on multi-feature fusion, characterized in that it comprises the following steps: A reference immersive video and an immersive video to be evaluated are obtained, wherein the reference immersive video includes a reference texture video sequence and a reference depth video sequence, and the immersive video to be evaluated includes a distorted texture video sequence and a distorted depth video sequence, and a 3D-LOG filter is used to extract features from the reference texture video sequence and the distorted texture video sequence to obtain reference texture features and distorted texture features; texture feature similarity is calculated based on the reference texture features and the distorted texture features, and a texture video quality score is obtained based on the texture feature similarity through a 3D-LOG pooling strategy; A reference depth feature and a distorted depth feature are calculated based on the reference depth video sequence and the distorted depth video sequence; a depth feature similarity is calculated based on the reference depth feature and the distorted depth feature and a gradient weight is determined, and a depth video quality score is calculated based on the depth feature similarity and the gradient weight; The quality score of the immersive video to be evaluated is calculated according to the texture video quality score and the depth video quality score. 2. The immersive video quality assessment method based on multi-feature fusion according to claim 1 is characterized in that the feature extraction of the reference texture video sequence and the distorted texture video sequence using a 3D-LOG filter to obtain reference texture features and distorted texture features specifically includes: The calculation formula of the 3D-LOG filter is: ; in, Represents the horizontal, vertical and time coordinates in the space-time domain, is the standard deviation of the 3D Gaussian kernel function, , represents the function corresponding to the 3D-LOG filter; The reference texture video sequence and the distorted texture video sequence are respectively input into the 3D-LOG filter for convolution to obtain reference texture features and distorted texture features, as shown in the following formula: ; ; in, and Respectively represent the brightness value corresponding to each pixel of the input reference texture video sequence and the distorted texture video sequence, and Respectively represent the reference texture features and the distorted texture features extracted by the 3D-LOG filter, The symbol represents the convolution operation. 3. The immersive video quality evaluation method based on multi-feature fusion according to claim 1 is characterized in that the texture feature similarity is calculated based on the reference texture feature and the distorted texture feature, and the texture video quality score is obtained based on the texture feature similarity through a 3D-LOG pooling strategy, specifically comprising: The texture feature similarity is calculated using the following formula: : ; in, and Respectively represent the reference texture features and distorted texture features extracted by 3D-LOG, is a constant that maintains numerical stability; The maximum value of the reference texture feature and the distorted texture feature is used as the texture weight , as shown below: ; Among them, max means taking the maximum value; The texture weight and texture feature similarity are weighted to obtain a texture video quality score , as shown below: . 4. The immersive video quality assessment method based on multi-feature fusion according to claim 1 is characterized in that the step of calculating the reference depth feature and the distortion depth feature according to the reference depth video sequence and the distorted depth video sequence to obtain the reference depth feature and the distortion depth feature specifically includes: The gradient amplitudes of the reference texture video sequence and the distorted texture video sequence are calculated respectively to obtain the corresponding depth features: ; ; ; in, represents a depth video frame, and denote the partial derivatives in the horizontal and vertical directions respectively, and Represent the gradient amplitude components in the horizontal and vertical directions respectively, represents a depth feature, and the depth features calculated from the depth video frames in the reference depth video sequence and the distorted depth video sequence correspond to the reference depth features and distortion depth features , The symbol represents the convolution operation. 5. The immersive video quality assessment method based on multi-feature fusion according to claim 1 is characterized in that the depth feature similarity is calculated based on the reference depth feature and the distorted depth feature and the gradient weight is determined, and the depth video quality score is calculated based on the depth feature similarity and the gradient weight, specifically comprising: The following formula is used to calculate the deep feature similarity: ; in, and represent the reference depth feature and the distorted depth feature respectively, represents the deep feature similarity, is another constant that maintains numerical stability; The maximum value of the reference depth feature and the distorted depth feature is used as the gradient weight , as shown below: ; Among them, max means taking the maximum value; The gradient weight and the depth feature similarity are weighted to obtain a depth video quality score. , as shown below: . 6. The immersive video quality evaluation method based on multi-feature fusion according to claim 1 is characterized in that the quality score of the immersive video to be evaluated is calculated according to the texture video quality score and the depth video quality score, specifically comprising: The importance of the texture video quality score and the depth video quality score is calculated to obtain an importance score. , as shown below: ; in, It is a parameter used to adjust the relative importance between texture features and depth features; The maximum value of the absolute value of the texture video quality score and the absolute value of the depth video quality score is used as the evaluation weight , as shown below: ; Among them, max means taking the maximum value. is the absolute value symbol; The evaluation weight and the importance score are weightedly calculated to obtain the quality score MMF of the immersive video to be evaluated, as shown in the following formula: ; Wherein, N represents the number of the immersive video sequences to be evaluated, i=1,2,…,N. 7. An immersive video quality assessment device based on multi-feature fusion, characterized in that it includes: The texture video quality score calculation module is configured to obtain a reference immersive video and an immersive video to be evaluated, wherein the reference immersive video includes a reference texture video sequence and a reference depth video sequence, and the immersive video to be evaluated includes a distorted texture video sequence and a distorted depth video sequence, and extract features from the reference texture video sequence and the distorted texture video sequence using a 3D-LOG filter to obtain reference texture features and distorted texture features; calculate texture feature similarity based on the reference texture features and the distorted texture features, and obtain a texture video quality score based on the texture feature similarity using a 3D-LOG pooling strategy; A depth video quality score calculation module is configured to calculate reference depth features and distorted depth features according to the reference depth video sequence and the distorted depth video sequence; calculate depth feature similarity according to the reference depth features and the distorted depth features and determine gradient weights, and calculate a depth video quality score according to the depth feature similarity and the gradient weights; The quality score calculation module is configured to calculate the quality score of the immersive video to be evaluated according to the texture video quality score and the depth video quality score. 8. An electronic device, comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6. 9. A computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented. 10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.