Immersion prediction method for display systems with different view fields based on electroencephalogram signals

Abstract

The invention discloses a method for predicting immersion of display systems with different view field sizes based on electroencephalogram signals. The accurate virtual scene immersion perception influence model is constructed by combining the size of the view field and the multi-dimensional features of the electroencephalogram signals, the model can quantify the influence of the size of the view field on the immersion of a user in a display system, and meanwhile the physiological mechanism of a human visual system is fully considered. Furthermore, a frequency domain analysis method is introduced, key features in the electroencephalogram signals are extracted, subjective immersion scoring is combined, and the model can generate an immersion prediction result highly consistent with human eye visual perception. According to the method and the device, the immersion prediction precision can be remarkably improved, and a scientific basis is provided for immersion optimization design of the virtual scene.

Description

Technical Field

[0001] The present invention relates to the fields of immersion perception, visual interaction, neurocognition and display field of view, and more specifically, to a method for predicting immersion of display systems with different field of view sizes based on electroencephalogram signals. Background Art

[0002] Field of View (FOV) is a key factor in the design of Virtual Reality (VR) systems. It determines the visible range of users in the virtual environment and directly affects the sense of immersion and realism. Reasonable setting of FOV can significantly enhance the user's immersive experience, but the size of FOV also has complex effects on the user's psychological and physiological state. Reducing FOV can reduce the consumption of system computing resources and reduce visual fatigue. It is suitable for application scenarios with limited hardware performance or focusing on comfort. Although this method reduces hardware pressure, it may weaken the sense of space. Expanding FOV can enhance immersion and presence. It is suitable for application scenarios with high immersion requirements, such as virtual teaching and remote collaboration, but it will increase hardware load and device heating. Therefore, how to balance user experience and hardware performance, and dynamically adjust FOV according to different scenario requirements, has become an important challenge in the development of VR equipment.

[0003] In recent years, researchers have conducted in-depth explorations on the impact of FOV on immersion, using a variety of methods to evaluate users' psychological and physiological responses. Among them, subjective questionnaires are one of the commonly used methods. By recording users' scores on immersion and comfort, the impact of FOV changes on user experience is revealed. The existing technology uses the concept of "functional threshold" to evaluate the minimum acceptable level of sensory experience in virtual environments, and determines the functional threshold of the field of view size in virtual scenes through questionnaires and individual subjective real-time feedback. However, due to individual differences, the results of subjective questionnaires may be uncertain. To overcome this limitation, physiological signal monitoring technology, such as electroencephalogram (EEG), electrocardiogram (ECG), and electrodermal activity (EDA), can be introduced to more objectively evaluate the user state. Existing studies have proposed two core indicators, "emotional arousal" and "cognitive absorption", based on EEG signals to evaluate the user's immersion state under different FOVs.

[0004] However, with the rapid development of virtual reality technology, users' requirements for immersion and interactive experience are constantly increasing. FOV dynamic control technology has gradually become mainstream. By integrating subjective feedback and physiological signals such as EEG to build a relationship model between FOV and immersion, it provides a scientific basis for FOV dynamic control. Personalized control methods further combine users' physiological characteristics and interaction preferences to provide users with customized immersive experience optimization solutions. These methods show broad application prospects in virtual teaching, cultural tourism, remote collaboration and other fields. In the future, FOV dynamic control technology based on multimodal data will promote VR devices to achieve efficient resource management and intelligent experience control, bringing users a more immersive virtual world. Although the current virtual reality technology can enhance users' immersion and sense of reality through field of view control, the existing FOV control methods often have several defects. First, traditional methods are mostly based on fixed or limited FOV configurations, and lack the ability to dynamically adapt to different user needs, and cannot fully meet the different immersive experience needs brought about by individual differences. Secondly, the existing FOV evaluation mostly relies on subjective questionnaires or single physiological signal indicators, which are greatly affected by personal subjective factors and are difficult to fully and objectively reflect the user's immersion state. Finally, existing research lacks the means to conduct comprehensive analysis and modeling of multimodal data (including subjective feedback and physiological signals), and cannot systematically reveal the relationship between FOV control and user immersion experience, thus limiting the scientificity and accuracy of FOV optimization. The above defects restrict the immersive experience of VR systems in different application scenarios to a certain extent, and make it difficult for existing VR systems to balance the immersive experience and hardware performance. Summary of the invention

[0005] The present invention overcomes the defects of the prior art and proposes an immersion prediction method for display systems with different field sizes based on electroencephalogram signals.

[0006] The first aspect of the present invention provides a method for predicting immersion of display systems with different field sizes based on electroencephalogram signals, comprising:

[0007] S1: multiple immersion perception tasks are set based on different field of view sizes FOV, and the immersion state of the test subject is induced through multiple immersion perception tasks. The immersion perception data in the virtual scene is collected through the EEG portable head-mounted device and the IPQ subjective questionnaire; the immersion perception data includes the subjective immersion score Score of the test subject and its corresponding EEG signal, and the immersion perception data is cleaned;

[0008] S2: Process the EEG signal to obtain key features. Apply the Hamming window function to preprocess the collected EEG data to reduce the spectrum leakage problem and obtain the preprocessed time domain signal. Perform fast Fourier transform on the time domain signal to obtain the frequency domain signal. For the frequency domain signal data after fast Fourier transform, extract the corresponding frequency band data and calculate the power spectral density PSD. Sum and take the logarithm of the power spectral density in the frequency band to obtain the absolute frequency band power Absolute Brainwaves, which is used to represent the energy distribution in a specific frequency band. Map the absolute frequency band power from the original range to [0,100], and use the corresponding mapped value of the absolute frequency band power of the Beta wave as the objective score of immersion, marked as P β ;

[0009] S3: After completing the EEG data preprocessing and frequency domain analysis, the corresponding key feature data are recorded;

[0010] S4: According to the distribution of subjective immersion scores under different field of view sizes, outliers are removed from the data, and the FOV and P are combined. β , construct the field of view index I FOV , using the Arctan model to establish a nonlinear mapping relationship between the field of view index and the immersion of the display system, and constructing an immersion impact model through the nonlinear mapping relationship;

[0011] S5: A cross-validation method is used to verify the accuracy of the immersion impact model, using the mean square error (MSE) as the evaluation indicator and the determination coefficient (R) as the evaluation index. 2 Assess the goodness of fit of the model.

[0012] In this solution, in S1, the immersion perception data is cleaned to ensure the quality and validity of the data;

[0013] In this solution, in S2, the collected EEG data is preprocessed by applying the Hamming window function to reduce the spectrum leakage problem, and the preprocessed time domain signal is obtained. The time domain signal is fast Fourier transformed to obtain the frequency domain signal. For the frequency domain signal data after the fast Fourier transform, the corresponding frequency band data is extracted, and the power spectral density PSD is calculated, specifically:

[0014] The Hamming window function preprocessing is defined as follows:

[0015]

[0016] Where w(n) is the time domain signal processed by the Hamming window function. is the default value, n is the index of the window, L is the length of the window;

[0017] Perform fast Fourier transform on the preprocessed time domain signal to obtain the frequency domain signal. The corresponding formula is as follows:

[0018]

[0019] Where X(k) represents the frequency domain signal after Fourier transform, N is the total number of samples of the input signal, j is the imaginary unit, represents the rotation factor in the frequency domain, n is the index of the window, and k is the input sample;

[0020] For the frequency domain signal data after fast Fourier transform, extract the corresponding frequency band data and calculate the power spectrum density PSD. The PSD is expressed in logarithmic form as follows:

[0021] PSD = log 10 (|X(k)| 2 ), (3)

[0023] In this scheme, the power spectrum density in the frequency band is summed and the logarithm is taken to obtain the absolute frequency band power AbsoluteBrainwaves, which is used to represent the energy distribution in a specific frequency band. The absolute frequency band power is mapped from the original range to [0,100], and the absolute frequency band power of the Beta wave is used as the objective score of immersion, marked as P β , specifically:

[0024] The power spectrum density in the frequency band is summed and the logarithm is taken to obtain the absolute band power Absolute Brainwaves, which is used to represent the energy distribution in a specific frequency band. The specific calculation is as follows:

[0025]

[0026] where f 1 and f 2 are the upper and lower limits of the frequency band, and f represents the frequency point;

[0027] The absolute frequency band power is mapped from the original range to [0,100], and the absolute frequency band power of the Beta wave is used as the objective score of immersion, marked as P β .

[0028] In this solution, the key feature data includes I FOV , P β , Score.

[0029] In this solution, in S4, the immersion impact model specifically includes:

[0030] The field of view index IFOV , the specific formula is as follows:

[0031]

[0032] Among them, θ is the field of view, P β is the objective immersion score of the corresponding test subject; further, the Arctan model is used to establish a nonlinear mapping relationship between the field of view index and the immersion of the display system:

[0033] S = μ·arctan(ω·I FOV )-τ, (6)

[0034] Where S is the quantified value of immersion, constants μ=98.8132, σ=0.0470, τ=12.4533, and the immersion influence model is constructed through the nonlinear mapping relationship.

[0035] In this solution, in S5, the specific evaluation formula is as follows:

[0036]

[0037] Among them, I i is the actual value of the i-th sample point, is the predicted value of the i-th sample point, and Y is the total number of sample points;

[0038] Further, through R 2 Values ​​are used to assess the goodness of fit of the model:

[0039]

[0040] Among them, R 2 is the coefficient of determination, used to assess goodness of fit, is the average value of the sample points, and Y is the total number of sample points.

[0041] The second aspect of the present invention further provides an immersion prediction system for display systems with different field sizes based on electroencephalogram signals, the system comprising: a memory, a processor, the memory comprising an immersion prediction program for display systems with different field sizes based on electroencephalogram signals, and the immersion prediction program for display systems with different field sizes based on electroencephalogram signals, when executed by the processor, implements the following steps:

[0042] S1: multiple immersion perception tasks are set based on different field of view sizes FOV, and the immersion state of the test subject is induced through multiple immersion perception tasks. The immersion perception data in the virtual scene is collected through the EEG portable head-mounted device and the IPQ subjective questionnaire; the immersion perception data includes the subjective immersion score Score of the test subject and its corresponding EEG signal, and the immersion perception data is cleaned;

[0043] S2: Process the EEG signal to obtain key features. Apply the Hamming window function to preprocess the collected EEG data to reduce the spectrum leakage problem and obtain the preprocessed time domain signal. Perform fast Fourier transform on the time domain signal to obtain the frequency domain signal. For the frequency domain signal data after fast Fourier transform, extract the corresponding frequency band data and calculate the power spectral density PSD. Sum and take the logarithm of the power spectral density in the frequency band to obtain the absolute frequency band power Absolute Brainwaves, which is used to represent the energy distribution in a specific frequency band. Map the absolute frequency band power from the original range to [0,100], and use the corresponding mapped value of the absolute frequency band power of the Beta wave as the objective score of immersion, marked as P β ;

[0044] S3: After completing the EEG data preprocessing and frequency domain analysis, the corresponding key feature data are recorded;

[0045] S4: According to the distribution of subjective immersion scores under different field of view sizes, outliers are removed from the data, and the FOV and P are combined. β , construct the field of view index I FOV , using the Arctan model to establish a nonlinear mapping relationship between the field of view index and the immersion of the display system, and constructing an immersion impact model through the nonlinear mapping relationship;

[0046] S5: A cross-validation method is used to verify the accuracy of the immersion impact model, using the mean square error (MSE) as the evaluation indicator and the determination coefficient (R) as the evaluation index. 2 Assess the goodness of fit of the model.

[0047] The third aspect of the present invention also provides a computer-readable storage medium, which includes an immersion prediction program for a display system with different field of view sizes based on electroencephalogram signals. When the immersion prediction program for a display system with different field of view sizes based on electroencephalogram signals is executed by a processor, the steps of the immersion prediction method for a display system with different field of view sizes based on electroencephalogram signals as described in any of the above items are implemented.

[0048] The fourth aspect of the present invention also provides a VR platform device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps of the method for predicting immersion in a display system with different field of view sizes based on electroencephalogram signals as described in any one of the above items are implemented.

[0049] In view of the problem that the existing virtual scene immersion perception evaluation methods do not fully consider the regulatory effect of field of view size on immersion and the multi-dimensional characteristics of electroencephalogram signals, the present invention proposes an immersion prediction method for display systems with different field of view sizes based on electroencephalogram signals.

[0050] First, the present invention proposes a virtual scene immersion perception impact model for field of view size regulation, and includes the interaction between field of view size and EEG signals in the display system into the research scope. Combined with subjective immersion scoring, a multi-dimensional immersion evaluation framework is constructed to achieve quantitative modeling of virtual scene immersion.

[0051] Then, the frequency domain feature extraction method was introduced into the EEG signal analysis, using the Hamming window function and fast Fourier transform for signal processing, and extracting the power spectrum density of each frequency band to reflect the relationship between EEG activity and immersion. This process fully considers the physiological mechanism of the human visual system (HVS) for immersive perception of virtual scenes, and can maintain a high consistency with human subjective evaluation results.

[0052] Finally, it is proposed to combine the frequency domain characteristics of EEG signals with the field of view size control parameters to construct an immersion quantification model. This model improves the accuracy of immersion prediction, can provide evaluation results consistent with human visual perception, and effectively supports the immersion optimization design of virtual scenes. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 A flow chart of a method for predicting immersion in display systems with different field sizes based on EEG signals of the present invention is shown;

[0054] Figure 2 The schematic diagram of the EEG signal feature extraction process of the present invention is shown;

[0055] Figure 3 A schematic diagram showing the training structure of the immersion impact model of the present invention;

[0056] Figure 4 A diagram showing the immersion prediction result of the display system of the present invention is shown;

[0057] Figure 5 A block diagram of an immersion prediction system for display systems with different field sizes based on EEG signals of the present invention is shown. DETAILED DESCRIPTION

[0058] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0059] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0060] The present invention aims to solve the shortcomings of the current FOV control technology, and proposes an immersion prediction method for display systems with different field of view sizes based on EEG signals, which is used for display systems with different field of view sizes to optimize the immersive experience effect of the VR system. By combining subjective feedback with EEG physiological signals, a relationship model between FOV control and immersion is constructed, and a nonlinear mapping relationship of user immersion is established using a machine learning algorithm. Based on this model, dynamic adjustment of FOV can be achieved to meet the personalized needs of different users. The present invention can not only significantly enhance the user's immersive experience in various VR application scenarios, but also find a balance between enhancing immersion and reducing system computing resource consumption through an intelligent FOV control mechanism, and has broad application value and promotion potential.

[0061] Figure 1 The present invention shows a flow chart of a method for predicting immersion of display systems with different field sizes based on electroencephalogram signals.

[0062] like Figure 1 As shown, the first aspect of the present invention provides a method for predicting immersion of display systems with different field sizes based on electroencephalogram signals, comprising:

[0063] S1: Multiple immersion perception tasks are set based on different field of view sizes FOV, and the immersion state of the test subject is induced through multiple immersion perception tasks. The immersion perception data in the virtual scene is collected through EEG portable head-mounted devices and IPQ subjective questionnaires;

[0064] The immersion perception data includes the subjective immersion score Score of the test subject and its corresponding electroencephalogram signal, and the immersion perception data is cleaned;

[0065] It should be noted that the subjective immersion score is expressed as Score.

[0066] During the data cleaning phase, ensure the quality and validity of the data;

[0067] Figure 2 The schematic diagram of the EEG signal feature extraction process of the present invention is shown;

[0068] like Figure 2As shown, on the left is the corresponding data collected based on the EEG portable head-mounted device and pre-processed using the Hamming window function, in the middle is the fast Fourier transform (FFT), and on the right is the calculation of the power spectral density PSD and the drawing of the spectrum diagram.

[0069] S2: Process the EEG signal to obtain key features. Apply the Hamming window function to preprocess the collected EEG data to reduce the spectrum leakage problem. The preprocessing definition is as follows:

[0070]

[0071] Where w(n) is the time domain signal processed by the Hamming window function. is the default value, n is the index of the window, L is the length of the window;

[0072] Perform fast Fourier transform on the preprocessed time domain signal to obtain the frequency domain signal. The corresponding formula is as follows:

[0073]

[0074] Where X(k) represents the frequency domain signal after Fourier transform, N is the total number of samples of the input signal, j is the imaginary unit, represents the rotation factor in the frequency domain, n is the index of the window, and k is the input sample.

[0075] For the frequency domain signal data after fast Fourier transform, extract the corresponding frequency band data and calculate the power spectrum density PSD. The PSD is expressed in logarithmic form as follows:

[0076] PSD = log 10 (|X(k)| 2 ), (3)

[0077] The power spectrum density in the frequency band is summed and the logarithm is taken to obtain the absolute band power Absolute Brainwaves, which is used to represent the energy distribution in a specific frequency band. The specific calculation is as follows:

[0078]

[0079] where f 1 and f 2 are the upper and lower limits of the frequency band, and f represents the frequency point.

[0080] For the convenience of analysis, the absolute frequency band power is mapped from the original range to [0,100], and the absolute frequency band power corresponding to the Beta wave is used as the objective score of immersion, marked as P β ;

[0081] S3: After the EEG data preprocessing and frequency domain analysis are completed, the corresponding key feature data are recorded. The key feature data includes I FOV , P β , Score, etc. It can also include intermediate process calculation data such as absolute frequency band power and PSD for subsequent modeling analysis. The recording function is used to completely store the data generated by the calculation process.

[0082] It should be noted that Fast Fourier Transform (FFT) and Power Spectral Density (PSD) are the key features that will provide a basis for subsequent modeling and analysis.

[0083] Figure 3 A schematic diagram showing the training structure of the immersion impact model of the present invention;

[0084] like Figure 3 As shown in Figure 3, Raw EEG Data is the EEG signal data, FOV Size is the field of view size, and Score is the subjective immersion score. The corresponding three are used as input data. Raw EEG Data is spectrally analyzed and processed to obtain the objective immersion score P β , FOV Size and P β The FOV index (i.e., field of view index) is formed and imported into the model together with the subjective immersion score. The model training is achieved through the Arctan model and cross validation (Fold cross Validation). The figure is a simplified schematic diagram.

[0085] Figure 4 is a graph showing the immersion prediction result of the display system of the present invention;

[0086] like Figure 4 As shown in the figure, Fitted curve is the fitting curve, Sample points are the sample points, Subjective IPQscore is the subjective immersion score, and 95%Confidence interval is the selected 95% confidence interval. It can be seen that the fitting curve coincides with the confidence interval. The determination coefficient at this time is R 2 =0.8488.

[0087] S4: According to the distribution of subjective immersion scores under different field of view sizes, the data is processed by removing outliers. The P obtained in formula (4) β Based on this, combined with FOV, the field of view index I is constructed FOV , the specific formula is as follows:

[0088]

[0089] Among them, θ is the field of view, P β is the objective immersion score of the corresponding test subject; further, the Arctan model is used to establish a nonlinear mapping relationship between the field of view index and the immersion of the display system:

[0090] S = μ·arctan(ω·I FOV )-τ, (6)

[0091] Where S is the quantified value of immersion, constants μ=98.8132, ω=0.0470, τ=12.4533, and the immersion influence model is constructed through the nonlinear mapping relationship.

[0092] It should be noted that the core of the immersion impact model is to obtain the output result by analyzing the nonlinear mapping relationship between the field of view angle index and the immersion of the display system. The model includes the storage of key feature data, the corresponding data processing flow and model parameters, etc.

[0093] S5: A cross-validation method is used to verify the accuracy of the immersion impact model, and the mean square error (MSE) is used as an evaluation indicator. The specific evaluation formula is as follows:

[0094]

[0095] Among them, I i is the actual value of the i-th sample point, is the predicted value of the i-th sample point, and Y is the total number of sample points;

[0096] Further, through R 2 Values ​​are used to assess the goodness of fit of the model:

[0097]

[0098] Among them, R 2 is the coefficient of determination, used to assess goodness of fit, is the average value of the sample points, and Y is the total number of sample points.

[0099] It should be noted that, in the embodiment of the present invention, R 2 =0.8488, which ensures the accuracy and reliability of the model. FOV is the field of view.

[0100] Figure 5 A block diagram of an immersion prediction system for display systems with different field sizes based on EEG signals of the present invention is shown.

[0101] The second aspect of the present invention further provides an immersion prediction system 5 for display systems with different field sizes based on electroencephalogram signals, the system comprising: a memory 51, a processor 52, the memory comprising an immersion prediction program for display systems with different field sizes based on electroencephalogram signals, and the immersion prediction program for display systems with different field sizes based on electroencephalogram signals, when executed by the processor, implements the following steps:

[0102] S1: multiple immersion perception tasks are set based on different field of view sizes FOV, and the immersion state of the test subject is induced through multiple immersion perception tasks. The immersion perception data in the virtual scene is collected through the EEG portable head-mounted device and the IPQ subjective questionnaire; the immersion perception data includes the subjective immersion score Score of the test subject and its corresponding EEG signal, and the immersion perception data is cleaned;

[0103] S2: Process the EEG signal to obtain key features. Apply the Hamming window function to preprocess the collected EEG data to reduce the spectrum leakage problem and obtain the preprocessed time domain signal. Perform fast Fourier transform on the time domain signal to obtain the frequency domain signal. For the frequency domain signal data after fast Fourier transform, extract the corresponding frequency band data and calculate the power spectral density PSD. Sum and take the logarithm of the power spectral density in the frequency band to obtain the absolute frequency band power Absolute Brainwaves, which is used to represent the energy distribution in a specific frequency band. Map the absolute frequency band power from the original range to [0,100], and use the corresponding mapped value of the absolute frequency band power of the Beta wave as the objective score of immersion, marked as P β ;

[0104] S3: After completing the EEG data preprocessing and frequency domain analysis, the corresponding key feature data are recorded;

[0105] S4: According to the distribution of subjective immersion scores under different field of view sizes, outliers are removed from the data, and the FOV and P are combined. β , construct the field of view index I FOV , using the Arctan model to establish a nonlinear mapping relationship between the field of view index and the immersion of the display system, and constructing an immersion impact model through the nonlinear mapping relationship;

[0106] S5: A cross-validation method is used to verify the accuracy of the immersion impact model, using the mean square error (MSE) as the evaluation indicator and the determination coefficient (R) as the evaluation index. 2 Assess the goodness of fit of the model.

[0107] The third aspect of the present invention also provides a computer-readable storage medium, which includes an immersion prediction program for a display system with different field of view sizes based on electroencephalogram signals. When the immersion prediction program for a display system with different field of view sizes based on electroencephalogram signals is executed by a processor, the steps of the immersion prediction method for a display system with different field of view sizes based on electroencephalogram signals as described in any of the above items are implemented.

[0108] The fourth aspect of the present invention also provides a VR platform device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps of the method for predicting immersion in a display system with different field of view sizes based on electroencephalogram signals as described in any one of the above items are implemented.

[0109] The present invention discloses a method for predicting immersion in display systems with different field of view sizes based on electroencephalogram signals. By combining the field of view size with the multi-dimensional characteristics of electroencephalogram signals, an accurate virtual scene immersion perception impact model is constructed. The model can quantify the impact of the field of view size on the user's immersion in the display system while fully considering the physiological mechanism of the human visual system. Furthermore, by introducing the frequency domain analysis method, extracting the key features in the electroencephalogram signals, and combining the subjective immersion score, the model can generate immersion prediction results that are highly consistent with the visual perception of the human eye. Through the present invention, the accuracy of immersion prediction can be significantly improved, providing a scientific basis for the immersion optimization design of virtual scenes.

[0110] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0111] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0112] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0113] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0114] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0115] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for predicting immersion of display systems with different field sizes based on EEG signals, characterized in that: include: S1: multiple immersion perception tasks are set based on different field of view sizes FOV, and the immersion state of the test subject is induced through multiple immersion perception tasks. The immersion perception data in the virtual scene is collected through the EEG portable head-mounted device and the IPQ subjective questionnaire; the immersion perception data includes the subjective immersion score Score of the test subject and its corresponding EEG signal, and the immersion perception data is cleaned; S2: Process the EEG signal to obtain key features. Apply the Hamming window function to preprocess the collected EEG data to reduce the spectrum leakage problem and obtain the preprocessed time domain signal. Perform fast Fourier transform on the time domain signal to obtain the frequency domain signal. For the frequency domain signal data after fast Fourier transform, extract the corresponding frequency band data and calculate the power spectral density PSD. Sum and take the logarithm of the power spectral density in the frequency band to obtain the absolute frequency band power AbsoluteBrainwaves, which is used to represent the energy distribution in a specific frequency band. Map the absolute frequency band power from the original range to [0,100], and use the corresponding mapped value of the absolute frequency band power of the Beta wave as the objective score of immersion, marked as P β ; S3: After completing the EEG data preprocessing and frequency domain analysis, the corresponding key feature data are recorded; S4: According to the distribution of subjective immersion scores under different field of view sizes, outliers are removed from the data, and the FOV and P are combined. β , construct the field of view index I FOV , using the Arctan model to establish a nonlinear mapping relationship between the field of view index and the immersion of the display system, and constructing an immersion impact model through the nonlinear mapping relationship; S5: A cross-validation method is used to verify the accuracy of the immersion impact model, using the mean square error (MSE) as the evaluation indicator and the determination coefficient (R) as the evaluation index. 2 Assess the goodness of fit of the model.

2. The method for predicting immersion of display systems with different field sizes based on EEG signals according to claim 1, characterized in that: In S1, the immersion perception data is cleaned to ensure the quality and validity of the data.

3. The method for predicting immersion of display systems with different field sizes based on EEG signals according to claim 2, characterized in that: In S2, the collected EEG data is preprocessed by applying a Hamming window function to reduce the spectrum leakage problem, and the preprocessed time domain signal is obtained. The time domain signal is fast Fourier transformed to obtain a frequency domain signal. For the frequency domain signal data after the fast Fourier transform, the corresponding frequency band data is extracted, and the power spectral density PSD is calculated, which is specifically: The Hamming window function preprocessing is defined as follows: Where w(n) is the time domain signal processed by the Hamming window function. is the default value, n is the index of the window, L is the length of the window; Perform fast Fourier transform on the preprocessed time domain signal to obtain the frequency domain signal. The corresponding formula is as follows: Where X(k) represents the frequency domain signal after Fourier transform, N is the total number of samples of the input signal, j is the imaginary unit, represents the rotation factor in the frequency domain, n is the index of the window, and k is the input sample; For the frequency domain signal data after fast Fourier transform, extract the corresponding frequency band data and calculate the power spectrum density PSD. The PSD is expressed in logarithmic form as follows: PSD=log 10 (|X(k)| 2 ), (3)。 4. The method for predicting immersion of display systems with different field sizes based on EEG signals according to claim 3, characterized in that: The power spectrum density in the frequency band is summed and logarithm is taken to obtain the absolute frequency band power AbsoluteBrainwaves, which is used to represent the energy distribution in a specific frequency band. The absolute frequency band power is mapped from the original range to [0,100], and the absolute frequency band power of the Beta wave is used as the objective score of immersion, marked as P β , specifically: The power spectrum density in the frequency band is summed and the logarithm is taken to obtain the absolute band power Absolute Brainwaves, which is used to represent the energy distribution in a specific frequency band. The specific calculation is as follows: Among them, f1 and f2 are the upper and lower limits of the frequency band, and f represents the frequency point; The absolute frequency band power is mapped from the original range to [0,100], and the absolute frequency band power of the Beta wave is used as the objective score of immersion, marked as P β .

5. The method for predicting immersion of display systems with different field sizes based on EEG signals according to claim 4, characterized in that: The key feature data includes I FOV , P β , Score.

6. The method for predicting immersion of display systems with different field sizes based on EEG signals according to claim 5, characterized in that: In S4, the immersion impact model specifically includes: The field of view index I FOV , the specific formula is as follows: Among them, θ is the field of view, P β is the objective immersion score of the corresponding test subject; further, the Arctan model is used to establish a nonlinear mapping relationship between the field of view index and the immersion of the display system: S=μ·close(ω·I FOV )-τ, (6) Where S is the quantitative value of immersion, constant μ = 98.8132, ω = 0.0470, τ=12.4533, and an immersion influence model is constructed through the nonlinear mapping relationship.

7. The method for predicting immersion of display systems with different field sizes based on EEG signals according to claim 6, characterized in that: In S5, the specific evaluation formula is as follows: Among them, I i is the actual value of the i-th sample point, is the predicted value of the i-th sample point, and Y is the total number of sample points; Further, through R 2 Values ​​are used to assess the goodness of fit of the model: Among them, R 2 is the coefficient of determination, used to assess goodness of fit, is the average value of the sample points, and Y is the total number of sample points.

8. An immersion prediction system for display systems with different field sizes based on EEG signals, characterized in that: The system includes: a memory and a processor. The memory includes an immersion prediction program for displaying systems with different field sizes based on electroencephalogram signals. When the immersion prediction program for displaying systems with different field sizes based on electroencephalogram signals is executed by the processor, the following steps are implemented: S1: multiple immersion perception tasks are set based on different field of view sizes FOV, and the immersion state of the test subject is induced through multiple immersion perception tasks. The immersion perception data in the virtual scene is collected through the EEG portable head-mounted device and the IPQ subjective questionnaire; the immersion perception data includes the subjective immersion score Score of the test subject and its corresponding EEG signal, and the immersion perception data is cleaned; S2: Process the EEG signal to obtain key features. Apply the Hamming window function to preprocess the collected EEG data to reduce the spectrum leakage problem and obtain the preprocessed time domain signal. Perform fast Fourier transform on the time domain signal to obtain the frequency domain signal. For the frequency domain signal data after fast Fourier transform, extract the corresponding frequency band data and calculate the power spectral density PSD. Sum and take the logarithm of the power spectral density in the frequency band to obtain the absolute frequency band power AbsoluteBrainwaves, which is used to represent the energy distribution in a specific frequency band. Map the absolute frequency band power from the original range to [0,100], and use the corresponding mapped value of the absolute frequency band power of the Beta wave as the objective score of immersion, marked as P β ; S3: After completing the EEG data preprocessing and frequency domain analysis, the corresponding key feature data are recorded; S4: According to the distribution of subjective immersion scores under different field of view sizes, outliers are removed from the data, and the FOV and P are combined. β , construct the field of view index I FOV , using the Arctan model to establish a nonlinear mapping relationship between the field of view index and the immersion of the display system, and constructing an immersion impact model through the nonlinear mapping relationship; S5: A cross-validation method is used to verify the accuracy of the immersion impact model, using the mean square error (MSE) as the evaluation indicator and the determination coefficient (R) as the evaluation index. 2 Assess the goodness of fit of the model.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes an immersion prediction program for a display system with different field of view sizes based on electroencephalogram signals. When the immersion prediction program for a display system with different field of view sizes based on electroencephalogram signals is executed by a processor, the steps of the immersion prediction method for a display system with different field of view sizes based on electroencephalogram signals as described in any one of claims 1 to 7 are implemented.

10. A VR platform device, characterized in that: The VR platform device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the immersion prediction method for display systems with different field of view sizes based on EEG signals as described in any one of claims 1 to 7 when executing the computer program.

Images