A method and system for generating image matching evaluation for an XR shed

Abstract

The present invention provides a generation image matching evaluation method and system for an XR studio, and relates to the field of image processing technology; the system of the present invention includes an XR studio, a user information capturing unit, a virtual scene simulation unit, a display content generating unit, a playback module dividing unit, a perspective image processing unit, an image matching evaluation unit and a playback module management unit; and in conjunction with the method steps, according to the different positions and viewing angles of the users, the user information is located and the perspective image processing is performed in a targeted manner, so as to obtain a soft module processing image that satisfies the user's viewing experience, and then the image matching evaluation unit is used to determine whether the original soft module generation image is better or the soft module processing image has a better effect, and then the soft module processing image is controlled to be played and displayed, so as to meet the user's viewing needs from a specific viewing angle.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly to a method and system for generating map matching evaluation for an XR shed. Background Art

[0002] An XR shed is a new type of content display device, whose appearance resembles a box with one side opened, and a display wall / display screen for displaying content is arranged inside the box. Viewers can get an immersive viewing experience by standing at the opening.

[0003] Due to the special design of the XR shed, the content it displays is also different from traditional single-plane images. Image processing based on perspective relationships is required at some transition positions (such as corners and edges) to make the image transition between different planes natural, smooth and reasonable.

[0004] Existing image processing usually adopts manual frame-by-frame processing or batch processing using an image processing model. Among them, the manual frame-by-frame processing method can meet the visual needs of specific scenarios, making its adaptability better and the display effect better. However, the disadvantages are slow processing speed and high cost.

[0005] Using an image processing model can process images quickly and at low cost, and can continuously optimize the generated drawing quantity with the improvement of the algorithm, which is the future development trend. However, the disadvantage is that the fixed processing model has poor adaptability, and users often view the display content of the XR shed from different angles, positions and heights, resulting in the inability of the fixed-optimized content to adapt.

[0006] Therefore, a method and system for generating map matching evaluation for an XR shed are needed to solve the technical problem that the fixed-optimized content cannot adapt to the viewing needs of users from different angles, positions and heights. Summary of the Invention

[0007] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a method and system for generating map matching evaluation for an XR shed, aiming to solve the technical problem that the fixed-optimized content cannot adapt to the different viewing needs of users.

[0008] To achieve the above purpose, the present application proposes a system for generating map matching evaluation for an XR shed, including:

[0009] An XR shed, used to play and display content through a playback module; wherein, the playback module includes a hard module and a soft module;

[0010] A user information capture unit, used to capture user information in the viewing area in front of the XR shed;

[0011] A virtual scene simulation unit for performing virtual scene simulation on the XR shed and the viewing area;

[0012] A display content generation unit for generating a flat generation diagram that can be played by the XR shed according to the prepared display content;

[0013] A playback module division unit for dividing the flat generation diagram into a hard module generation diagram and a soft module generation diagram;

[0014] A perspective image processing unit for selecting and performing perspective image processing on the soft module generation diagram according to the target perspective to obtain a corresponding soft module processed diagram;

[0015] An image matching evaluation unit for performing image matching evaluation on the soft module processed diagram to obtain a matching evaluation score;

[0016] A playback module management unit for determining whether the XR shed plays and displays the soft module processed diagram according to the matching evaluation score.

[0017] As a further solution, the user information capture unit includes a personnel recognition module, a behavior recognition module, and a spatial positioning module; wherein, the personnel recognition module is used to recognize the personnel in the viewing area; the behavior recognition module is used to recognize the behavior of the personnel and mark the personnel with viewing behavior as users; the spatial positioning module is used to perform spatial positioning on the head position of the user to obtain user positioning information.

[0018] As a further solution, the user information capture unit further includes an eye movement capture module; wherein, the eye movement capture module is used to capture the eye view of the user to obtain user view information.

[0019] As a further solution, the virtual scene simulation unit includes a virtual space simulation module, a virtual XR shed simulation module, and a virtual view simulation module; wherein, the virtual space simulation module is used to provide a virtual simulation space, including a virtual viewing area and a virtual XR shed area; the virtual XR shed simulation module is used to perform XR shed simulation playback in the virtual simulation space, and the virtual view simulation module is used to perform virtual view simulation according to the user information.

[0020] As a further solution, the virtual XR shed simulation module includes a virtual XR shed model and a virtual playback module; wherein, the virtual XR shed model is used to simulate the physical structure of the XR shed, and the virtual playback module includes a virtual hard module and a virtual soft module, and is arranged in the virtual XR shed model according to the actual installation position.

[0021] On the other hand, the present invention also provides a method for evaluating the matching of generated images for an XR shed, which is applied to an XR shed generated image matching evaluation system as described in any one of the above, and includes the following steps:

[0022] Step 1: Obtain the prepared display content to generate a planar generated image that can be played by the XR shed, and generate a planar generated image that can be played by the XR shed through the display content generation unit;

[0023] Step 2: The playback module division unit divides the planar generated image to obtain the corresponding hard module generated image and soft module generated image;

[0024] Step 3: The user information capture unit captures the user information at the viewing area in front of the XR shed;

[0025] Step 4: The perspective image processing unit selects the target field of view according to the preset selection logic and in combination with the user information;

[0026] Step 5: The perspective image processing unit performs perspective image processing on the soft module generated image according to the target perspective to obtain the corresponding soft module processed image;

[0027] Step 6: The virtual scene simulation unit performs virtual scene simulation on the XR shed and the viewing area;

[0028] Step 7: The image matching evaluation unit performs image matching evaluation on the soft module processed image in the virtual scene simulation to obtain the matching evaluation score;

[0029] Step 8: The playback module management unit determines whether the matching evaluation score is greater than the replacement threshold;

[0030] If so, control the XR shed to play and display the hard module generated image and the soft module processed image;

[0031] If not, control the XR shed to play and display the hard module generated image and the soft module generated image;

[0032] Step 9: Loop through Steps 1 to 8 until the XR shed completes the playback display.

[0033] As a further solution, the image matching evaluation unit performs image matching evaluation through the following steps:

[0034] Obtain the target perspective and the soft module generated image and soft module processed image that need to be evaluated;

[0035] Control the virtual perspective simulation module to perform virtual perspective simulation according to the target perspective;

[0036] The image generated by the soft module is simulated and played through the virtual XR studio simulation module, and the virtual perspective image at this time is obtained through the virtual perspective simulation module to obtain the original perspective image;

[0037] The soft module processing diagram is simulated and played through the virtual XR studio simulation module, and the virtual perspective image at this time is obtained through the virtual perspective simulation module to obtain the processing perspective diagram;

[0038] Evaluate the deformation degree of the original view image relative to the image generated by the soft module to obtain the deformation parameters of the original image;

[0039] Evaluate the deformation degree of the processed view graph relative to the graph generated by the soft module, and obtain the processed graph deformation parameters;

[0040] By changing the parameters of the original image and the processed image, the matching evaluation score of the corresponding soft module processed image under the target perspective is obtained.

[0041] As a further solution, when the user is a single user, preset the selection logic:

[0042] If there is a specified annotation perspective, the specified annotation perspective will be used as the target perspective;

[0043] Otherwise, the viewing angle position is determined by the user positioning information of a single user.

[0044] If an eye-movement capture module is provided, the user perspective information of a single user is used as the target perspective;

[0045] If the eye-tracking module is not set, the default horizontal viewing angle is used as the target viewing angle.

[0046] As a further solution, when the user is multiple users, preset the selection logic:

[0047] Obtain user location information and user perspective information of each user;

[0048] The spatial position is averaged through the user positioning information to obtain the public positioning information;

[0049] The spatial angle is averaged through the user's perspective information to obtain the public perspective information;

[0050] The viewpoint position is determined through the public positioning information, and the public viewpoint information is used as the target viewpoint.

[0051] As a further solution, when there are multiple users, gaze selection logic is also set:

[0052] Obtain user location information and user perspective information of each user;

[0053] Determine the playback module that each user is looking at based on the user location information and the user viewing angle information;

[0054] Divide users who are looking at the same software module into the same group;

[0055] The spatial position is averaged through the positioning information of users in the same group to obtain the mass positioning information of the same group;

[0056] The spatial angle is averaged through the user perspective information of the same group to obtain the public perspective information of the same group;

[0057] Determine the viewpoint position through the mass positioning information of the same group, and use the mass viewpoint information of the same group as the target viewpoint of the same group;

[0058] Each soft module replaces the target perspective separately according to the corresponding target perspective of the same group, and loops through steps 1 to 8 respectively until the XR studio completes the playback display.

[0059] Compared with related technologies, the method and system for generating image matching evaluation for XR studios provided by the present invention have the following advantages:

[0060] The present invention locates user information and performs perspective image processing in a targeted manner according to the user's position and viewing angle, thereby obtaining a soft module processing image that satisfies the user's viewing experience, and then uses an image matching evaluation unit to determine whether the original soft module generated image or the soft module processed image has a better effect, and then controls the soft module processed image to be played and displayed, thereby meeting the user's viewing needs from a specific viewing angle. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0063] Figure 1 A schematic diagram of the structure of a generated graph matching evaluation system for an XR shed provided by the present invention;

[0064] Figure 2 A schematic diagram of the structure of the playback module provided by the present invention;

[0065] Figure 3 A scene schematic diagram of a virtual scene simulation unit provided by the present invention;

[0066] Figure 4 Schematic diagram of the scene in the viewing area in front of the XR shed provided by the present invention;

[0067] Figure 5 Schematic diagram of the steps of a method for generating map matching evaluation for an XR shed provided by the present invention.

[0068] The realization of the purpose, functional features and advantages of this application will be further described in conjunction with the embodiments with reference to the accompanying drawings. Specific embodiments

[0069] To make the purpose, 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 in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Usually, the components of the embodiments of the present invention described and shown in the accompanying drawings here can be arranged and designed in various different configurations.

[0070] Embodiment 1

[0071] Please refer to Figure 1 , the embodiments of this application provide a system for generating map matching evaluation for an XR shed, including:

[0072] An XR shed for playing and displaying content through a playback module; wherein, the playback module includes a hard module and a soft module;

[0073] A user information capture unit for capturing user information in the viewing area in front of the XR shed;

[0074] A virtual scene simulation unit for simulating the virtual scene of the XR shed and the viewing area;

[0075] A display content generation unit for generating a planar generated map that can be played by the XR shed according to the prepared display content;

[0076] A playback module division unit for dividing the planar generated map into a hard module generated map and a soft module generated map;

[0077] A perspective image processing unit for selecting and performing perspective image processing on the soft module generated map according to the target perspective to obtain a corresponding soft module processed map;

[0078] An image matching evaluation unit for performing image matching evaluation on the soft module processed map to obtain a matching evaluation score;

[0079] A playback module management unit for determining whether the XR shed plays and displays the soft module processed map according to the matching evaluation score.

[0080] It should be noted that: as Figure 2As shown in the figure, a hard module refers to a playback module that does not need to be bent or deformed. This module can directly play the desired material without considering the deformation problem. A soft module is a playback module that is bent or deformed at the edge or diagonal. Since the soft module has certain deformation and bending, etc., when the image content is directly displayed, there will be certain deformation, which will affect the user's viewing experience.

[0081] Existing XR studios often do not distinguish between soft modules and hard modules. Even if the deformation and bending of the soft modules are processed, perspective transformation is performed through a fixed perspective to offset the impact of the deformation and bending. This can only provide a better viewing experience at a fixed perspective and cannot meet the viewing needs of users with different perspectives.

[0082] To this end, this embodiment locates the user information and performs targeted perspective image processing according to the user's position and viewing angle, so as to obtain a soft module processing image that satisfies the user's viewing experience, and then uses the image matching evaluation unit to determine whether the original soft module generated image or the soft module processed image has a better effect, and then controls the soft module processed image to play and display, thereby meeting the user's viewing needs from a specific perspective.

[0083] Specifically, the user information capture unit includes a person identification module, a behavior identification module and a space positioning module; Figure 4 As shown in the figure, we will use the personnel recognition module to identify the people in the viewing area, and then use the behavior recognition module to identify the people's behavior, and mark the people with viewing behavior as users (because some people are not watching, such as passers-by, security personnel, etc.). Finally, the spatial positioning module will spatially locate the user's head position to obtain the user positioning information.

[0084] In addition, in some demanding scenarios, we also set up an eye-tracking module, through which we can not only accurately obtain the user's perspective, but also further locate the playback module they are watching ( Figure 4 The red box part is the soft module that is positioned according to the user's perspective), and then performs more targeted perspective transformation processing.

[0085] Among them, the prepared display content can be 3D scene materials and 2D static materials prepared in advance, or it can be materials generated based on AI, such as Wensheng pictures, etc. The display content is not limited here.

[0086] The virtual scene simulation unit is mainly set up to simulate the real scene, so as to extract the relevant information we want in the simulation scene, mainly including the virtual space simulation module, the virtual XR studio simulation module and the virtual perspective simulation module; among them, the virtual space simulation module is used to provide a virtual simulation space, including a virtual viewing area and a virtual XR studio area; the virtual XR studio simulation module is used to perform XR studio simulation playback in the virtual simulation space, and the virtual perspective simulation module is used to perform virtual perspective simulation according to user information.

[0087] As Figure 3 shown, the virtual XR studio simulation module includes a virtual XR studio model and a virtual playback module; among them, the virtual XR studio model is used to simulate the physical structure of the XR studio, and the virtual playback module includes a virtual hard module and a virtual soft module, and is arranged in the virtual XR studio model according to the actual installation position.

[0088] Through the cooperation of the virtual XR studio model and the virtual playback module, we can accurately obtain the display effect of the image in the virtual scene, and further provide a data basis for subsequent judgment.

[0089] Embodiment 2

[0090] Please refer to Figure 5 , on the basis of Embodiment 1, this embodiment provides a method for generating map matching evaluation for an XR studio, including the following steps:

[0091] Step 1: Obtain the prepared display content to generate a planar generated map that can be played by the XR studio, and generate a planar generated map that can be played by the XR studio through the display content generation unit;

[0092] Step 2: The playback module division unit divides the planar generated map to obtain the corresponding hard module generated map and soft module generated map;

[0093] Step 3: The user information capture unit captures the user information at the viewing area in front of the XR studio;

[0094] Step 4: The perspective image processing unit selects the target field of view according to the preset selection logic and combines the user information;

[0095] Step 5: The perspective image processing unit performs perspective image processing on the soft module generated map according to the target perspective to obtain the corresponding soft module processed map;

[0096] Step 6: The virtual scene simulation unit performs virtual scene simulation on the XR studio and the viewing area;

[0097] Step 7: The image matching evaluation unit performs image matching evaluation on the soft module processed map in the virtual scene simulation to obtain the matching evaluation score;

[0098] Step 8: The playback module management unit determines whether the matching evaluation score is greater than the replacement threshold;

[0099] If so, it controls the XR shed to play and display the hard module generated image and the soft module processed image;

[0100] If not, it controls the XR shed to play and display the hard module generated image and the soft module generated image;

[0101] Step 9: Loop through Steps 1 to 8 until the XR shed completes the playback display.

[0102] Furthermore, the image matching evaluation unit needs to evaluate the soft module generated image and the soft module processed image to determine which one is more in line with the user's viewing needs, that is, which image looks more similar to the original viewing content from the user's perspective. The specific implementation is as follows:

[0103] Obtain the target perspective and the soft module generated image and the soft module processed image that need to be evaluated;

[0104] Control the virtual perspective simulation module to perform virtual perspective simulation according to the target perspective;

[0105] Here, we simulate and play the soft module generated image through the virtual XR shed simulation module, and obtain the virtual perspective image at this time through the virtual perspective simulation module to obtain the original perspective image. This original perspective image is the image seen from the user's perspective without processing;

[0106] Then we simulate and play the soft module processed image through the virtual XR shed simulation module, and obtain the virtual perspective image at this time through the virtual perspective simulation module to obtain the processed perspective image. This processed perspective image is the image seen from the user's perspective during processing;

[0107] Evaluate the deformation degree of the original perspective image relative to the soft module generated image to obtain the original image deformation parameter;

[0108] Evaluate the deformation degree of the processed perspective image relative to the soft module generated image to obtain the processed image deformation parameter;

[0109] The deformation degree here can be selectively set according to different focuses,

[0110] For example, when focusing on content similarity, a pixel-based metric is used to directly compare the pixel value differences between the deformed and undeformed images. The following parameters can be used:

[0111] Mean Squared Error (MSE)

[0112] Calculate the mean square error of the pixel values of the two images. The smaller the value, the smaller the difference after deformation.

[0113] Mean Absolute Error (MAE)

[0114] Calculate the absolute average value of pixel value differences, which is more robust to outliers than MSE.

[0115] Peak Signal-to-Noise Ratio (PSNR)

[0116] A logarithmic metric based on MSE, commonly used to evaluate image compression or reconstruction quality.

[0117] In some scenarios where more attention is paid to structural relevance (such as building displays), it is necessary to measure the degree of preservation of the structural information of the image content. The following parameters can be used:

[0118] Structural Similarity Index (SSIM)

[0119] Combining luminance, contrast, and structural information, it is more in line with human visual perception.

[0120] Multi-Scale SSIM (MS-SSIM)

[0121] Calculate SSIM at multiple scales to enhance robustness to complex deformations.

[0122] In some scenarios where geometric relationships are concerned (such as vehicle mechanics simulation diagram displays, etc.), it is applicable to analyze the geometric deformations of images (such as affine transformation, elastic deformation), such as:

[0123] Displacement Field

[0124] Describe the displacement vector of each pixel point, commonly used in non-rigid registration (such as medical images).

[0125] Jacobian Determinant

[0126] Analyze the volume change of a local area (determinant > 1 indicates expansion, < 1 indicates contraction).

[0127] Strain Tensor

[0128] Describe the degree of stretching or shearing of local deformations (such as Green-Lagrange strain in engineering mechanics).

[0129] Curvature

[0130] For analyzing the change in the degree of curvature of a surface or contour.

[0131] After selecting appropriate parameters for measurement, we obtain the matching evaluation score of the processed soft module image corresponding to the target perspective by varying the parameters of the original image - processing the varying parameters of the image. If the score (positive) exceeds the replacement threshold, it indicates that the processed soft module image better meets the viewing requirements of the current perspective, and then it is replaced.

[0132] Furthermore, when there is a single user, the preset selection logic is as follows:

[0133] If there is a specified annotation perspective, then the specified annotation perspective is taken as the target perspective;

[0134] Otherwise, the perspective position is determined through the user positioning information of the single user.

[0135] If an eye movement capture module is set, then the user's perspective information of the single user is used as the target perspective;

[0136] If the eye movement capture module is not set, then the default frontal view perspective is taken as the target perspective.

[0137] Still further, when there are multiple users, the preset selection logic is as follows:

[0138] Obtain the user positioning information and user perspective information of each user;

[0139] Calculate the mean of the spatial positions through the user positioning information to obtain the general public positioning information;

[0140] Calculate the mean of the spatial angles through the user perspective information to obtain the general public perspective information;

[0141] Determine the perspective position through the general public positioning information and use the general public perspective information as the target perspective.

[0142] When there are multiple users and an eye movement capture module is set, we can obtain the soft modules gazed at by each user. Different soft modules use different target perspectives to simultaneously meet the viewing needs of different users. For example, Figure 4 As shown, the user wearing the No. 1 sweatshirt is watching the zenith; therefore, the soft module corresponding to the zenith is adapted to the perspective of this user; similarly, another user is gazing at the soft module on the right, and this soft module is also adapted to the perspective of the other user; the specific gaze selection logic is as follows:

[0143] Obtain the user positioning information and user perspective information of each user;

[0144] Determine the playback modules gazed at by each user through the user positioning information and user perspective information;

[0145] Group the users who are looking at the same soft module into the same group;

[0146] Calculate the mean value of the spatial positions based on the location information of the users in the same group to obtain the general location information of the group;

[0147] Calculate the mean value of the spatial angles based on the perspective information of the users in the same group to obtain the general perspective information of the group;

[0148] Determine the perspective position based on the general location information of the group, and use the general perspective information of the group as the target perspective of the group;

[0149] Each soft module separately replaces the target perspective according to the corresponding target perspective of the group, and separately and repeatedly executes steps 1 to 8 until the XR shed completes the playback and display.

[0150] This solution can further subdivide different soft modules to further meet the different viewing needs of different users, different perspectives, and different viewing areas.

[0151] The above are only partial embodiments of this application, and do not limit the patent scope of this application. Any equivalent structural transformation made under the technical concept of this application by using the content of the specification and drawings of this application, or any direct / indirect application in other related technical fields is included in the patent protection scope of this application.

Claims

1. A generation map matching evaluation system for an XR shed, characterized in that, Comprising: An XR booth for playing display content through a playing module; wherein, the playing module includes a hard module and a soft module; the hard module is a playing module that does not need to be bent or deformed, and the soft module is a playing module that is bent or deformed at the edge or diagonal; A user information capture unit for capturing user information in the viewing area in front of the XR booth; A virtual scene simulation unit for simulating a virtual scene of the XR booth and the viewing area; A display content generation unit for generating a planar generation diagram that can be played by the XR booth according to the prepared display content; A playing module division unit for dividing the planar generation diagram into a hard module generation diagram and a soft module generation diagram; A perspective image processing unit for selecting and performing perspective image processing on the soft module generation diagram according to the target perspective to obtain a corresponding soft module processed diagram; An image matching evaluation unit for performing image matching evaluation on the soft module processed diagram to obtain a matching evaluation score; A playing module management unit for determining whether the XR booth plays and displays the soft module processed diagram according to the matching evaluation score; The image matching evaluation unit performs image matching evaluation through the following steps: Obtain the target perspective and the soft module generation diagram and soft module processed diagram that need to be evaluated; Control the virtual perspective simulation module to perform virtual perspective simulation according to the target perspective; Simulate and play the soft module generation diagram through the virtual XR booth simulation module, and obtain the virtual perspective image at this time through the virtual perspective simulation module to obtain the original perspective diagram; Simulate and play the soft module processed diagram through the virtual XR booth simulation module, and obtain the virtual perspective image at this time through the virtual perspective simulation module to obtain the processed perspective diagram; Evaluate the deformation degree of the original perspective diagram relative to the soft module generation diagram to obtain the original graphic deformation parameter; Evaluate the deformation degree of the processed perspective diagram relative to the soft module generation diagram to obtain the processed graphic deformation parameter; Obtain the matching evaluation score of the corresponding soft module processed diagram under the target perspective through the original graphic deformation parameter - processed graphic deformation parameter; Wherein, the deformation degree is selectively set according to different emphases; When focusing on content similarity, use pixel-based metrics to directly compare the pixel value differences between the deformed and undeformed images, including mean squared error, mean absolute error, or peak signal-to-noise ratio; In scenarios where the structural relevance is concerned, measure the degree of retention of the structural information of the image content, including structural similarity index or multi-scale SSIM; In scenarios where the geometric relationship is concerned, analyze the geometric deformation of the image, including displacement field, determinant of the Jacobian matrix, strain tensor, or curvature.

2. The generation map matching evaluation system for an XR shed according to claim 1, wherein The user information capture unit includes a personnel recognition module, a behavior recognition module, and a spatial positioning module; wherein, the personnel recognition module is used to recognize the personnel in the viewing area; the behavior recognition module is used to recognize the behavior of the personnel and mark the personnel with viewing behavior as users; the spatial positioning module is used to perform spatial positioning on the head position of the user to obtain user positioning information.

3. The generation map matching evaluation system for XR shed according to claim 2, characterized in that, The user information capture unit further includes an eye movement capture module; wherein, the eye movement capture module is used to capture the eye view of the user to obtain user view information.

4. A generation map matching evaluation system for an XR shed according to claim 1, characterized in that, The virtual scene simulation unit includes a virtual space simulation module, a virtual XR studio simulation module and a virtual perspective simulation module; wherein the virtual space simulation module is used to provide a virtual simulation space, including a virtual viewing area and a virtual XR studio area; the virtual XR studio simulation module is used to perform XR studio simulation playback in the virtual simulation space, and the virtual perspective simulation module is used to perform virtual perspective simulation according to user information.

5. The generation diagram matching evaluation system for an XR shed according to claim 4, characterized in that The virtual XR studio simulation module includes a virtual XR studio model and a virtual playback module; wherein the virtual XR studio model is used to simulate the physical structure of the XR studio, and the virtual playback module includes a virtual hard module and a virtual soft module, and is placed in the virtual XR studio model according to the actual installation position.

6. A method for evaluating the matching of generated graphs for an XR shed, which is applied to a system for evaluating the matching of generated graphs for an XR shed according to any one of claims 1 to 5, characterized in that, The steps include: Step 1: Obtain the prepared display content to generate a plane generation map that can be played in the XR studio, and generate a plane generation map that can be played in the XR studio through a display content generation unit; Step 2: The playback module division unit divides the plane generation graph into playback modules to obtain corresponding hard module generation graphs and soft module generation graphs; Step 3: Capture user information in the viewing area in front of the XR studio through a user information capture unit; Step 4: The perspective image processing unit selects the target field of view according to the preset selection logic and in combination with the user information; Step 5: The perspective image processing unit performs perspective image processing on the soft module generated image according to the target viewing angle to obtain a corresponding soft module processed image; Step 6: Perform virtual scene simulation on the XR studio and viewing area through the virtual scene simulation unit; Step 7: The image matching evaluation unit performs image matching evaluation on the soft module processing image in the virtual scene simulation to obtain a matching evaluation score; Step 8: The playback module management unit determines whether the matching evaluation score is greater than the replacement threshold; If yes, the XR studio is controlled to play and display the hard module generation diagram and the soft module processing diagram; If not, the XR studio is controlled to play and display the hard module generation image and the soft module generation image; Step 9: Repeat steps 1 to 8 until the XR studio completes the playback display.

7. A method for evaluating the matching of generated diagrams for an XR shed according to claim 6, characterized in that, When the user is a single user, the default selection logic is: If there is a specified annotation perspective, the specified annotation perspective will be used as the target perspective; Otherwise, the viewing angle position is determined by the user positioning information of a single user. If an eye-movement capture module is provided, the user perspective information of a single user is used as the target perspective; If the eye-tracking module is not set, the default horizontal viewing angle is used as the target viewing angle.

8. A method for evaluating the matching of generated diagrams for an XR shed according to claim 6, characterized in that When the user is multiple users, the default selection logic is: Obtain user location information and user perspective information of each user; The spatial position is averaged through the user positioning information to obtain the public positioning information; The spatial angle is averaged through the user's perspective information to obtain the public perspective information; The viewpoint position is determined through the public positioning information, and the public viewpoint information is used as the target viewpoint.

9. The method for generating map matching evaluation for an XR shed according to claim 8, wherein When there are multiple users, gaze selection logic is also set: Obtain user location information and user perspective information of each user; Determine the playback module that each user is looking at based on the user location information and the user viewing angle information; Divide users who are looking at the same software module into the same group; Calculate the mean of the spatial positions based on the location information of users in the same group to obtain the general location information of the group. Calculate the mean of the spatial angles based on the perspective information of users in the same group to obtain the general perspective information of the group. Determine the perspective position based on the general location information of the group, and use the general perspective information of the group as the target perspective of the group. Each software module separately replaces the target perspective according to the corresponding target perspective of the group, and separately loops through steps 1 to 8 until the XR booth completes the playback and display.

Images