Naked eye 3D imaging evaluation method and system based on feedback analysis

Abstract

The invention discloses a naked eye 3D imaging evaluation method and system based on feedback analysis, and relates to the technical field of 3D display. And a private network is established through the cloud and the 3D terminal, and the initial display data is stored in real time and converted into the naked eye 3D content. On the basis of feedback analysis, on one hand, an interaction matrix is generated through user interaction behaviors, and operation characteristic differences are analyzed; on the other hand, the binocular vision simulation technology is utilized, the color histogram distribution of left and right views is analyzed by adopting a moving pixel window, and the imaging weight is quantified. The system performs characteristic decomposition on an interaction matrix, establishes a content priority group in combination with an imaging weight, dynamically adjusts a cloud cache strategy, and improves 3D display efficiency. According to the method, the user experience is effectively improved, the imaging quality is effectively optimized, the picture interaction efficiency of the naked eye 3D display equipment is effectively improved, and the multi-user display efficiency of the 3D display end is improved.

Description

Technical Field

[0001] The present invention relates to the field of naked-eye 3D imaging, and more specifically, to a naked-eye 3D imaging evaluation method and system based on feedback analysis. Background Art

[0002] Glasses-free 3D technology typically uses a parallax barrier, lenticular lenses, or other optical elements to separate the images for the left and right eyes, creating separate displays to achieve the effect. Glasses-free 3D display technology has seen some development and application in advertising screens, televisions, digital photo frames, and game consoles.

[0003] However, for some exhibition hall-type naked-eye 3D display platforms, since multiple users are analyzing and displaying 3D videos at the same time, there is a lot of naked-eye 3D content, and the conversion is prone to excessive delays. Existing technologies make it difficult to achieve smooth and synchronous display of multi-terminal image imaging, and the experience for multi-point user applications is poor. At the same time, existing technologies lack user interactive display and feedback analysis, making it difficult to dynamically adjust and display 3D content transmission and conversion. Summary of the Invention

[0004] The present invention overcomes the defects of the prior art and proposes a naked-eye 3D imaging evaluation method and system based on feedback analysis.

[0005] A first aspect of the present invention provides a naked-eye 3D imaging evaluation method based on feedback analysis, comprising: S101: Establishing a dedicated network connection between the cloud and the 3D display terminal, and storing initial display data in the cloud; S102: The user interacts through the 3D display terminal. The cloud converts the initial display data into naked-eye 3D content and displays it through the 3D display terminal. During an interaction cycle, the user's interaction information for each initial display data is collected, and an interaction matrix is generated based on the interaction information. S103: Based on an initial display data, using a camera module, and according to the user's viewing distance, simulating binocular acquisition of left and right image data of a 3D display end, using a preset pixel matrix as a moving window, moving through the left and right image data, and calculating a color value histogram of the preset pixel matrix in the left and right image data based on each movement, analyzing binocular visual differences in the left and right image data through feedback from the color value histogram, and setting imaging weights based on the visual difference evaluation; S104: performing feature decomposition through the interaction matrix and evaluating the differences of the interaction matrix, and classifying the initial display data based on the differences, and setting priority groups for the initial display data based on the classification results and combined with imaging weights; S105: Cache settings are performed on the initial presentation data based on the cloud using the priority groups to generate a 3D presentation cache solution.

[0006] In this solution, the S101 is specifically: Establish a dedicated network connection between the cloud and multiple 3D display terminals, collect user interaction information in real time through the 3D display terminals and transmit it to the cloud for storage, and store initial display data based on the cloud.

[0007] In this solution, the S102 is specifically: Set an interaction cycle and divide it into multiple time nodes; During an interaction cycle, the 3D display terminal determines the initial display data corresponding to the user interaction process and collects the corresponding interaction information; An interaction information includes the interaction frequency, number of views and views, and browsing time at each time point in the initial display data. The interaction matrix is constructed with time nodes as the first dimension and interaction information as the second dimension.

[0008] In this solution, the S103 is specifically: Obtain the user's binocular distance and viewing distance, and set two camera devices through the camera module to collect image data from the 3D display end to obtain left and right image data; Set a 3×3 pixel matrix as a moving window and move the window across the left image data. In each move, calculate and count the corresponding color histogram based on the pixel matrix, and extract color features through the color histogram. After the move is completed, the entire left image data is covered and calculated. Based on the color features extracted for each movement, a left image feature set is formed; Perform color feature extraction on the right image to form a right image feature set; Selecting the color features extracted each time from the left image feature set and the right image feature set to perform feature difference calculation to obtain multiple difference values; The multiple difference values are averaged to obtain a visual difference value, and the imaging weight is set based on the visual difference value.

[0009] In this solution, the S104 is specifically: Perform eigendecomposition on all interaction matrices to obtain eigenvalues and eigenvectors. Calculate the difference between interaction matrices based on the eigenvalues and eigenvectors of each interaction matrix to obtain the matrix difference value between every two interaction matrices. Based on the matrix difference value, all interaction matrices are grouped so that the maximum matrix difference value in the same group does not exceed the preset difference, thereby obtaining multiple groups of interaction matrices; By mapping multiple groups of interaction matrices to the classification of the initial display data, multiple groups of display data are obtained; The imaging weight mean corresponding to the initial display data in each group of display data is calculated, and the priority of each group of display data is set based on the weight mean to obtain a priority group.

[0010] In this solution, the S105 is specifically: By using the priority group, the initial display data is cached based on the cloud and a 3D display cache solution is generated. In the 3D display cache solution, the first-priority initial display data is converted in real time through the cloud and stored in a cache list; Preload the initial presentation data based on the second priority and set a real-time queue task.

[0011] A second aspect of the present invention further provides a naked-eye 3D imaging evaluation system based on feedback analysis, the system comprising: a memory and a processor, wherein the memory includes a naked-eye 3D imaging evaluation program based on feedback analysis, and when the naked-eye 3D imaging evaluation program based on feedback analysis is executed by the processor, the following steps are implemented: S101: Establishing a dedicated network connection between the cloud and the 3D display terminal, and storing initial display data in the cloud; S102: The user interacts through the 3D display terminal. The cloud converts the initial display data into naked-eye 3D content and displays it through the 3D display terminal. During an interaction cycle, the user's interaction information for each initial display data is collected, and an interaction matrix is generated based on the interaction information. S103: Based on an initial display data, using a camera module, and according to the user's viewing distance, simulating binocular acquisition of left and right image data of a 3D display end, using a preset pixel matrix as a moving window, moving through the left and right image data, and calculating a color value histogram of the preset pixel matrix in the left and right image data based on each movement, analyzing binocular visual differences in the left and right image data through feedback from the color value histogram, and setting imaging weights based on the visual difference evaluation; S104: performing feature decomposition through the interaction matrix and evaluating the differences of the interaction matrix, and classifying the initial display data based on the differences, and setting priority groups for the initial display data based on the classification results and combined with imaging weights; S105: Cache settings are performed on the initial presentation data based on the cloud using the priority groups to generate a 3D presentation cache solution.

[0012] The third aspect of the present invention also provides a computer-readable storage medium, which includes a naked-eye 3D imaging evaluation program based on feedback analysis. When the naked-eye 3D imaging evaluation program based on feedback analysis is executed by a processor, it implements the steps of the naked-eye 3D imaging evaluation method based on feedback analysis as described in any one of the above items.

[0013] The present invention discloses a naked-eye 3D imaging evaluation method and system based on feedback analysis, which relates to the field of 3D display technology. A dedicated network is established between the cloud and the 3D terminal, and the initial display data is stored and converted into naked-eye 3D content in real time. Based on feedback analysis, on the one hand, an interaction matrix is generated through user interaction behavior to analyze the differences in operation characteristics; on the other hand, binocular vision simulation technology is used to analyze the color histogram distribution of the left and right views using a moving pixel window to quantify the imaging weights. The system performs feature decomposition on the interaction matrix, establishes content priority groups in combination with imaging weights, dynamically adjusts the cloud cache strategy, and improves 3D display efficiency. The present invention effectively improves user experience and optimizes imaging quality, effectively improves the screen interaction efficiency of naked-eye 3D display devices, and improves the multi-user display efficiency of 3D display terminals. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A flow chart of a naked-eye 3D imaging evaluation method based on feedback analysis according to the present invention is shown; Figure 2 A block diagram of a naked-eye 3D imaging evaluation system based on feedback analysis of the present invention is shown. DETAILED DESCRIPTION

[0015] In order to more clearly understand the above-mentioned objects, 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, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0016] 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 scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0017] Figure 1 The flowchart of the naked-eye 3D imaging evaluation method based on feedback analysis of the present invention is shown.

[0018] like Figure 1 As shown, the first aspect of the present invention provides a naked-eye 3D imaging evaluation method based on feedback analysis, comprising: S101: Establishing a dedicated network connection between the cloud and the 3D display terminal, and storing initial display data in the cloud; S102: The user interacts through the 3D display terminal. The cloud converts the initial display data into naked-eye 3D content and displays it through the 3D display terminal. During an interaction cycle, the user's interaction information for each initial display data is collected, and an interaction matrix is generated based on the interaction information. S103: Based on an initial display data, using a camera module, and according to the user's viewing distance, simulating binocular acquisition of left and right image data of a 3D display end, using a preset pixel matrix as a moving window, moving through the left and right image data, and calculating a color value histogram of the preset pixel matrix in the left and right image data based on each movement, analyzing binocular visual differences in the left and right image data through feedback from the color value histogram, and setting imaging weights based on the visual difference evaluation; S104: performing feature decomposition through the interaction matrix and evaluating the differences of the interaction matrix, and classifying the initial display data based on the differences, and setting priority groups for the initial display data based on the classification results and combined with imaging weights; S105: Cache settings are performed on the initial presentation data based on the cloud using the priority groups to generate a 3D presentation cache solution.

[0019] It should be noted that the 3D display terminal of the present invention includes a naked-eye 3D 8K display screen, which can convert ordinary 2D videos or traditional 3D (glasses required) content into naked-eye 3D 8K content that does not require glasses. Naked-eye 3D content can be directly played through HDMI interface, media player, video camera and other devices. It can be widely used in commercial naked-eye 3D advertising screens, naked-eye 3D TVs, naked-eye 3D digital photo frames, naked-eye 3D game consoles, etc., and for home naked-eye 3D display screens, it can perform app conversion based on the multimedia content on the mobile phone, store it in the cloud, and further display it on the 3D display terminal.

[0020] According to an embodiment of the present invention, the S101 is specifically as follows: Establish a dedicated network connection between the cloud and multiple 3D display terminals, collect user interaction information in real time through the 3D display terminals and transmit it to the cloud for storage, and store initial display data based on the cloud.

[0021] It should be noted that the cloud is used for complex interactive data analysis, conversion of standard media content into glasses-free 3D content, and storage of initial presentation data. Initial presentation data refers to standard media content, such as 2D videos and images, that is converted into glasses-free 3D content. Large presentation data files can be split into multiple parts for presentation, generating and storing multiple initial presentation data files.

[0022] 3D display terminals are generally display terminals such as 3D exhibition halls, 3D advertising screens, naked-eye 3D TVs, naked-eye 3D digital photo frames, and naked-eye 3D game consoles. In exhibition halls and multimedia applications, there is a large amount of display data, which is generally ordinary 2D content. The present invention uses initial display data to represent it. For larger data display platforms, such as multi-user digital sandboxes and multimedia exhibition hall applications, the display data is large, and the 3D display content generally needs to be dynamically set. Therefore, a large amount of initial display data needs to be stored in the database and dynamically converted and presented at any time.

[0023] According to an embodiment of the present invention, the S102 is specifically: Set an interaction cycle and divide it into multiple time nodes; During an interaction cycle, the 3D display terminal determines the initial display data corresponding to the user interaction process and collects the corresponding interaction information; An interaction information includes the interaction frequency, number of views and views, and browsing time at each time point in the initial display data. The interaction matrix is constructed with time nodes as the first dimension and interaction information as the second dimension.

[0024] It should be noted that the initial display data includes multiple, each data corresponds to interactive information. Each interactive information corresponds to an interactive matrix. It is worth mentioning here that for different types of 3D naked-eye display content, when the exhibition hall display terminal, multimedia naked-eye display terminal, etc. perform interactive display, users usually need to browse, click and display multiple times. The corresponding behavioral feature data is relatively complex and involves different display data. Therefore, the present invention subdivides the display data, stores it as initial display data, and analyzes the user's interactive information based on each initial display data, and stores the information in the form of an interactive matrix. Subsequently, for each initial display data, a rapid comparison process of the interactive matrix can be used to realize the correlation between the display data and the user behavior, and to mine the user's interest display data. Subsequently, through the interactive matrix, accurate comparative analysis of the corresponding interactive characteristics can be achieved.

[0025] According to an embodiment of the present invention, the S103 is specifically as follows: Obtain the user's binocular distance and viewing distance, and set two camera devices through the camera module to collect image data from the 3D display end to obtain left and right image data; Set a 3×3 pixel matrix as a moving window and move the window across the left image data. In each move, calculate and count the corresponding color histogram based on the pixel matrix, and extract color features through the color histogram. After the move is completed, the entire left image data is covered and calculated. Based on the color features extracted for each movement, a left image feature set is formed; Perform color feature extraction on the right image to form a right image feature set; Selecting the color features extracted each time from the left image feature set and the right image feature set to perform feature difference calculation to obtain multiple difference values; The multiple difference values are averaged to obtain a visual difference value, and the imaging weight is set based on the visual difference value.

[0026] It should be noted that the binocular distance refers to the distance between the user's left and right eyes, and the viewing distance is the distance between the user's eyes and the 3D display screen. The left and right image data include left image data and right image data. The camera module includes two cameras that simulate the human eye to capture and analyze images. The distance between the cameras is set to the user's binocular distance. At the same time, the size of the captured image is adjusted to match the image size actually obtained at the viewing distance. Feature difference calculation can be based on feature conversion into feature vectors and calculation based on Euclidean distance. The imaging weight is proportional to the visual difference value.

[0027] The camera module simulates binocular capture of left and right image data from the 3D display based on the user's viewing distance. Specifically, the captured image captures the user viewing a specific initial display. This can be multi-image capture, encompassing both left and right views. Window movement can start from the upper left corner of the image, row by row, with the unit of movement being three pixels, i.e., the preset pixel matrix size. The feature set analysis process for the left and right images is identical.

[0028] It is worth mentioning here that naked-eye 3D technology uses parallax barriers, cylindrical lenses, etc. to separate the images of the left and right eyes, so that the left eye can only see the corresponding left-view image, and the right eye sees the right-view image, thereby simulating the stereoscopic vision of the human eye in the real world. Therefore, the difference between the left and right eye images can determine the imaging effect to a certain extent. In the present invention, the pixel matrix is used to compare and analyze the left and right images, and the difference is calculated by the color histogram within the pixel matrix. This method can quickly analyze the difference between the left and right eye pixels and perform real-time imaging evaluation. The traditional general comparison method often compares pixel by pixel, which has large redundant calculations and high computing power consumption. In addition, there are certain pixel errors in the camera analysis. Therefore, extraction and analysis through the pixel matrix can achieve effective and fast binocular difference analysis, and further realize the effective classification and cache setting of the display data in the subsequent process.

[0029] The imaging weight is used to reflect the imaging effect. The greater the visual difference, the better the effect.

[0030] According to an embodiment of the present invention, the S104 is specifically as follows: Perform eigendecomposition on all interaction matrices to obtain eigenvalues and eigenvectors. Calculate the difference between interaction matrices based on the eigenvalues and eigenvectors of each interaction matrix to obtain the matrix difference value between every two interaction matrices. Based on the matrix difference value, all interaction matrices are grouped so that the maximum matrix difference value in the same group does not exceed the preset difference, thereby obtaining multiple groups of interaction matrices; By mapping multiple groups of interaction matrices to the classification of the initial display data, multiple groups of display data are obtained; The imaging weight mean corresponding to the initial display data in each group of display data is calculated, and the priority of each group of display data is set based on the weight mean to obtain a priority group.

[0031] It should be noted that matrix difference (similarity) determines the difference between two interaction matrices by combining the eigenvalue difference and the Euclidean distance of the eigenvectors. Specifically, it is calculated as the weighted average of the eigenvalue difference and the Euclidean distance of the eigenvectors. Each initial display data corresponds to one interaction matrix. Priority groups are multiple sets of display data containing priority information. Each interaction matrix corresponds to independent eigenvalues and eigenvectors.

[0032] According to an embodiment of the present invention, the S105 is specifically as follows: By using the priority group, the initial display data is cached based on the cloud and a 3D display cache solution is generated. In the 3D display cache solution, the first-priority initial display data is converted in real time through the cloud and stored in a cache list; Preload the initial presentation data based on the second priority and set a real-time queue task.

[0033] It should be noted that based on the priority group, layered caching settings are set for display data groups of different priorities, and the caching mechanism and picture data transmission scheme are dynamically optimized, which can greatly improve the 3D naked-eye platform experience of multiple users. At the same time, it can reduce the pressure of data conversion, effectively improve the picture smoothness of multiple 3D naked-eye display terminals, and improve the real-time picture output capability of 3D display, thereby improving the overall user experience of the 3D naked-eye exhibition hall (or multimedia 3D display terminal).

[0034] According to an embodiment of the present invention, the further embodiment includes: Calculate the variance of the imaging weights corresponding to all initial display data to obtain the first variance; Calculate the variance of the eigenvalues corresponding to all interaction matrices to obtain the second variance; Based on the first variance and the second variance, the consistency between the user behavior characteristics and the data imaging effect is determined; If the consistency is lower than the expected state, the eigenvectors of all interaction matrices are obtained as cluster samples; The cluster samples are grouped based on the K-means algorithm, K cluster centers are set, the distance between feature vectors is measured by Euclidean distance, and the clustering is cyclically clustered to form K groups of data and the center points are cyclically updated until the center points no longer move and the clustering is completed; Based on the clustering results, the initial display data is grouped and mapped to obtain multiple groups of display data. The imaging weight mean of each group of display data is calculated to determine the priority and obtain the priority group.

[0035] It should be noted that in 3D naked-eye video conversion and display applications based on multi-user, big data video libraries, it is difficult to conduct a relatively accurate group analysis of the 3D content behavior characteristics of multiple users. For example, in a multi-user urban 3D naked-eye display platform or exhibition hall, different users usually have different display data characteristics and user interaction behavior characteristics. When the user group is large, it is difficult for existing technologies to perform accurate analysis.

[0036] It's worth noting that for some exhibition hall-type naked-eye 3D display platforms, due to the simultaneous analysis and display of 3D videos by multiple users, the large amount of naked-eye 3D content, and the tendency for large delays in simultaneous conversion, existing technologies have difficulty achieving smooth, synchronized display of multi-terminal image imaging, and the experience is poor for multi-user applications. Furthermore, existing technologies lack user interactive display feedback analysis, making it difficult to dynamically adjust and display 3D content transmission and conversion. In particular, for scenarios such as data sandboxes and multimedia exhibition halls, existing technologies have low display efficiency for naked-eye 3D displays that convert real-time video. The multi-user experience is poor, and it's difficult to perform user interactive matching displays, making it difficult to improve the viewing efficiency of naked-eye 3D exhibition halls in multiple scenarios.

[0037] Based on the above problems, on the one hand, the present invention adopts the matrix difference value of the interaction matrix for grouping setting, which is suitable for analysis when the number of user groups is small. On the other hand, when the user group is large, the consistency between the corresponding user interaction and the display characteristics is low, and accurate grouping analysis is required. Therefore, the present invention analyzes the discrete type of the imaging weight of the display data and the interaction characteristics, and judges the consistency of the display data and the interaction characteristics of the user group by calculating the variance. Based on the discrete situation (consistency situation), it is judged whether it is necessary to cluster the interaction data and refine the grouping of the user group, thereby screening out the priority group with higher accuracy and setting a caching solution suitable for multiple user groups.

[0038] In the embodiment, if the consistency is lower than the expected state, that is, both variance values are lower than the expected values.

[0039] According to an embodiment of the present invention, the further embodiment includes: In the second interaction cycle, the cloud and 3D display interact with each other based on the 3D display cache solution; Based on the second interaction cycle, analyze the user's interaction matrix, calculate the corresponding matrix difference value, and calculate the mean of the matrix difference value to obtain the second mean; Calculate the mean of the matrix difference values in the first interaction cycle to obtain the first mean; If the second mean is greater than the first mean and the absolute difference is greater than the threshold, the display transmission efficiency of the first interaction cycle and the second interaction cycle is calculated; The efficiency of the 3D display cache solution is evaluated by comparing the absolute difference and the display transmission efficiency in two interaction cycles.

[0040] It should be noted that the matrix difference value is an indicator of differences in user interaction characteristics. When the interaction characteristics of user groups vary significantly, the complexity of the corresponding display data content increases accordingly. Therefore, when the interaction differences between two cycles are large, the 3D display caching solution can be effectively evaluated. Based on this, the present invention periodically compares the matrix difference value to determine the changes in interaction differences, and further analyzes the cache efficiency by comparing the display transmission efficiency.

[0041] Display transmission efficiency refers to a comprehensive analysis of the conversion time of the user's initial display data, image latency, data transmission time, and other information between the cloud and the 3D display. Generally speaking, the larger the absolute difference and the higher the display transmission efficiency, the more efficient the cache solution is and the more suitable it is for the current 3D display platform.

[0042] The absolute difference is the absolute difference between the first mean and the second mean.

[0043] Figure 2 A block diagram of a naked-eye 3D imaging evaluation system based on feedback analysis of the present invention is shown.

[0044] A second aspect of the present invention further provides a naked-eye 3D imaging evaluation system 2 based on feedback analysis, the system comprising: a memory 21 and a processor 22, wherein the memory 21 includes a naked-eye 3D imaging evaluation program based on feedback analysis, and when the naked-eye 3D imaging evaluation program based on feedback analysis is executed by the processor 22, the following steps are implemented: S101: Establishing a dedicated network connection between the cloud and the 3D display terminal, and storing initial display data in the cloud; S102: The user interacts through the 3D display terminal. The cloud converts the initial display data into naked-eye 3D content and displays it through the 3D display terminal. During an interaction cycle, the user's interaction information for each initial display data is collected, and an interaction matrix is generated based on the interaction information. S103: Based on an initial display data, using a camera module, and according to the user's viewing distance, simulating binocular acquisition of left and right image data of a 3D display end, using a preset pixel matrix as a moving window, moving through the left and right image data, and calculating a color value histogram of the preset pixel matrix in the left and right image data based on each movement, analyzing binocular visual differences in the left and right image data through feedback from the color value histogram, and setting imaging weights based on the visual difference evaluation; S104: performing feature decomposition through the interaction matrix and evaluating the differences of the interaction matrix, and classifying the initial display data based on the differences, and setting priority groups for the initial display data based on the classification results and combined with imaging weights; S105: Cache settings are performed on the initial presentation data based on the cloud using the priority groups to generate a 3D presentation cache solution.

[0045] It should be noted that the 3D display terminal of the present invention includes a naked-eye 3D 8K display screen, which can convert ordinary 2D videos or traditional 3D (glasses required) content into naked-eye 3D 8K content that does not require glasses. Naked-eye 3D content can be directly played through HDMI interface, media player, video camera and other devices. It can be widely used in commercial naked-eye 3D advertising screens, naked-eye 3D TVs, naked-eye 3D digital photo frames, naked-eye 3D game consoles, etc., and for home naked-eye 3D display screens, it can perform app conversion based on the multimedia content on the mobile phone, store it in the cloud, and further display it on the 3D display terminal.

[0046] According to an embodiment of the present invention, the S101 is specifically as follows: Establish a dedicated network connection between the cloud and multiple 3D display terminals, collect user interaction information in real time through the 3D display terminals and transmit it to the cloud for storage, and store initial display data based on the cloud.

[0047] It should be noted that the cloud is used for complex interactive data analysis, conversion of standard media content into glasses-free 3D content, and storage of initial presentation data. Initial presentation data refers to standard media content, such as 2D videos and images, that is converted into glasses-free 3D content. Large presentation data files can be split into multiple parts for presentation, generating and storing multiple initial presentation data files.

[0048] 3D display terminals are generally display terminals such as 3D exhibition halls, 3D advertising screens, naked-eye 3D TVs, naked-eye 3D digital photo frames, and naked-eye 3D game consoles. In exhibition halls and multimedia applications, there is a large amount of display data, which is generally ordinary 2D content. The present invention uses initial display data to represent it. For larger data display platforms, such as multi-user digital sandboxes and multimedia exhibition hall applications, the display data is large, and the 3D display content generally needs to be dynamically set. Therefore, a large amount of initial display data needs to be stored in the database and dynamically converted and presented at any time.

[0049] According to an embodiment of the present invention, the S102 is specifically: Set an interaction cycle and divide it into multiple time nodes; During an interaction cycle, the 3D display terminal determines the initial display data corresponding to the user interaction process and collects the corresponding interaction information; An interaction information includes the interaction frequency, number of views and views, and browsing time at each time point in the initial display data. The interaction matrix is constructed with time nodes as the first dimension and interaction information as the second dimension.

[0050] It should be noted that the initial display data includes multiple, each data corresponds to interactive information. Each interactive information corresponds to an interactive matrix. It is worth mentioning here that for different types of 3D naked-eye display content, when the exhibition hall display terminal, multimedia naked-eye display terminal, etc. perform interactive display, users usually need to browse, click and display multiple times. The corresponding behavioral feature data is relatively complex and involves different display data. Therefore, the present invention subdivides the display data, stores it as initial display data, and analyzes the user's interactive information based on each initial display data, and stores the information in the form of an interactive matrix. Subsequently, for each initial display data, a rapid comparison process of the interactive matrix can be used to realize the correlation between the display data and the user behavior, and to mine the user's interest display data. Subsequently, through the interactive matrix, accurate comparative analysis of the corresponding interactive characteristics can be achieved.

[0051] According to an embodiment of the present invention, the S103 is specifically as follows: Obtain the user's binocular distance and viewing distance, and set two camera devices through the camera module to collect image data from the 3D display end to obtain left and right image data; Set a 3×3 pixel matrix as a moving window and move the window across the left image data. In each move, calculate and count the corresponding color histogram based on the pixel matrix, and extract color features through the color histogram. After the move is completed, the entire left image data is covered and calculated. Based on the color features extracted for each movement, a left image feature set is formed; Perform color feature extraction on the right image to form a right image feature set; Selecting the color features extracted each time from the left image feature set and the right image feature set to perform feature difference calculation to obtain multiple difference values; The multiple difference values are averaged to obtain a visual difference value, and the imaging weight is set based on the visual difference value.

[0052] It should be noted that the binocular distance refers to the distance between the user's left and right eyes, and the viewing distance is the distance between the user's eyes and the 3D display screen. The left and right image data include left image data and right image data. The camera module includes two cameras that simulate the human eye to capture and analyze images. The distance between the cameras is set to the user's binocular distance. At the same time, the size of the captured image is adjusted to match the image size actually obtained at the viewing distance. Feature difference calculation can be based on feature conversion into feature vectors and calculation based on Euclidean distance. The imaging weight is proportional to the visual difference value.

[0053] The camera module simulates binocular capture of left and right image data from the 3D display based on the user's viewing distance. Specifically, the captured image captures the user viewing a specific initial display. This can be multi-image capture, encompassing both left and right views. Window movement can start from the upper left corner of the image, row by row, with the unit of movement being three pixels, i.e., the preset pixel matrix size. The feature set analysis process for the left and right images is identical.

[0054] It is worth mentioning here that naked-eye 3D technology uses parallax barriers, cylindrical lenses, etc. to separate the images of the left and right eyes, so that the left eye can only see the corresponding left-view image, and the right eye sees the right-view image, thereby simulating the stereoscopic vision of the human eye in the real world. Therefore, the difference between the left and right eye images can determine the imaging effect to a certain extent. In the present invention, the pixel matrix is used to compare and analyze the left and right images, and the difference is calculated by the color histogram within the pixel matrix. This method can quickly analyze the difference between the left and right eye pixels and perform real-time imaging evaluation. The traditional general comparison method often compares pixel by pixel, which has large redundant calculations and high computing power consumption. In addition, there are certain pixel errors in the camera analysis. Therefore, extraction and analysis through the pixel matrix can achieve effective and fast binocular difference analysis, and further realize the effective classification and cache setting of the display data in the subsequent process.

[0055] The imaging weight is used to reflect the imaging effect. The greater the visual difference, the better the effect.

[0056] According to an embodiment of the present invention, the S104 is specifically as follows: Perform eigendecomposition on all interaction matrices to obtain eigenvalues and eigenvectors. Calculate the difference between interaction matrices based on the eigenvalues and eigenvectors of each interaction matrix to obtain the matrix difference value between every two interaction matrices. Based on the matrix difference value, all interaction matrices are grouped so that the maximum matrix difference value in the same group does not exceed the preset difference, thereby obtaining multiple groups of interaction matrices; By mapping multiple groups of interaction matrices to the classification of the initial display data, multiple groups of display data are obtained; The imaging weight mean corresponding to the initial display data in each group of display data is calculated, and the priority of each group of display data is set based on the weight mean to obtain a priority group.

[0057] It should be noted that matrix difference (similarity) determines the difference between two interaction matrices by combining the eigenvalue difference and the Euclidean distance of the eigenvectors. Specifically, it is calculated as the weighted average of the eigenvalue difference and the Euclidean distance of the eigenvectors. Each initial display data corresponds to one interaction matrix. Priority groups are multiple sets of display data containing priority information. Each interaction matrix corresponds to independent eigenvalues and eigenvectors.

[0058] According to an embodiment of the present invention, the S105 is specifically as follows: By using the priority group, the initial display data is cached based on the cloud and a 3D display cache solution is generated. In the 3D display cache solution, the first-priority initial display data is converted in real time through the cloud and stored in a cache list; Preload the initial presentation data based on the second priority and set a real-time queue task.

[0059] It should be noted that based on the priority group, layered caching settings are set for display data groups of different priorities, and the caching mechanism and picture data transmission scheme are dynamically optimized, which can greatly improve the 3D naked-eye platform experience of multiple users. At the same time, it can reduce the pressure of data conversion, effectively improve the picture smoothness of multiple 3D naked-eye display terminals, and improve the real-time picture output capability of 3D display, thereby improving the overall user experience of the 3D naked-eye exhibition hall (or multimedia 3D display terminal).

[0060] The third aspect of the present invention also provides a computer-readable storage medium, which includes a naked-eye 3D imaging evaluation program based on feedback analysis. When the naked-eye 3D imaging evaluation program based on feedback analysis is executed by a processor, it implements the steps of the naked-eye 3D imaging evaluation method based on feedback analysis as described in any one of the above items.

[0061] The present invention discloses a naked-eye 3D imaging evaluation method and system based on feedback analysis, which relates to the field of 3D display technology. A dedicated network is established between the cloud and the 3D terminal, and the initial display data is stored and converted into naked-eye 3D content in real time. Based on feedback analysis, on the one hand, an interaction matrix is generated through user interaction behavior to analyze the differences in operation characteristics; on the other hand, binocular vision simulation technology is used to analyze the color histogram distribution of the left and right views using a moving pixel window to quantify the imaging weights. The system performs feature decomposition on the interaction matrix, establishes content priority groups in combination with imaging weights, dynamically adjusts the cloud cache strategy, and improves 3D display efficiency. The present invention effectively improves user experience and optimizes imaging quality, effectively improves the screen interaction efficiency of naked-eye 3D display devices, and improves the multi-user display efficiency of 3D display terminals.

[0062] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, 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.

[0063] 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 across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0064] 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.

[0065] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned method embodiments may be implemented by hardware associated with program instructions, and the aforementioned program may be stored in a computer-readable storage medium. When the program is executed, the program executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0066] Alternatively, if the integrated units described above are implemented as software modules and sold or used as standalone products, they can also be stored on a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product, stored on a storage medium, includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute all or part of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as removable storage devices, ROM, RAM, magnetic disks, or optical disks.

[0067] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the scope of protection of the present invention.

Claims

1. A naked-eye 3D imaging evaluation method based on feedback analysis, characterized in that: include: S101: Establishing a dedicated network connection between the cloud and the 3D display terminal, and storing initial display data in the cloud; S102: The user interacts through the 3D display terminal. The cloud converts the initial display data into naked-eye 3D content and displays it through the 3D display terminal. During an interaction cycle, the user's interaction information for each initial display data is collected, and an interaction matrix is generated based on the interaction information. S103: Based on an initial display data, using a camera module, and according to the user's viewing distance, simulating binocular acquisition of left and right image data of a 3D display end, using a preset pixel matrix as a moving window, moving through the left and right image data, and calculating a color value histogram of the preset pixel matrix in the left and right image data based on each movement, analyzing binocular visual differences in the left and right image data through feedback from the color value histogram, and setting imaging weights based on the visual difference evaluation; S104: performing feature decomposition through the interaction matrix and evaluating the differences of the interaction matrix, and classifying the initial display data based on the differences, and setting priority groups for the initial display data based on the classification results and combined with imaging weights; S105: Cache settings are performed on the initial presentation data based on the cloud using the priority groups to generate a 3D presentation cache solution.

2. The method for evaluating naked-eye 3D imaging based on feedback analysis according to claim 1, wherein: The S101 is specifically as follows: Establish a dedicated network connection between the cloud and multiple 3D display terminals, collect user interaction information in real time through the 3D display terminals and transmit it to the cloud for storage, and store initial display data based on the cloud.

3. The method for evaluating naked-eye 3D imaging based on feedback analysis according to claim 1, wherein: The S102 is specifically as follows: Set an interaction cycle and divide it into multiple time nodes; During an interaction cycle, the 3D display terminal determines the initial display data corresponding to the user interaction process and collects the corresponding interaction information; An interaction information includes the interaction frequency, number of views and views, and browsing time at each time point in the initial display data. The interaction matrix is constructed with time nodes as the first dimension and interaction information as the second dimension.

4. The method for evaluating naked-eye 3D imaging based on feedback analysis according to claim 1, wherein: The S103 is specifically as follows: Obtain the user's binocular distance and viewing distance, and set two camera devices through the camera module to collect image data from the 3D display end to obtain left and right image data; Set a 3×3 pixel matrix as a moving window and move the window across the left image data. In each move, calculate and count the corresponding color histogram based on the pixel matrix, and extract color features through the color histogram. After the move is completed, the entire left image data is covered and calculated. Based on the color features extracted for each movement, a left image feature set is formed; Perform color feature extraction on the right image to form a right image feature set; Selecting the color features extracted each time from the left image feature set and the right image feature set to perform feature difference calculation to obtain multiple difference values; The multiple difference values are averaged to obtain a visual difference value, and the imaging weight is set based on the visual difference value.

5. The method for evaluating naked-eye 3D imaging based on feedback analysis according to claim 1, wherein: The S104 is specifically as follows: Perform eigendecomposition on all interaction matrices to obtain eigenvalues and eigenvectors. Calculate the difference between interaction matrices based on the eigenvalues and eigenvectors of each interaction matrix to obtain the matrix difference value between every two interaction matrices. Based on the matrix difference value, all interaction matrices are grouped so that the maximum matrix difference value in the same group does not exceed the preset difference, thereby obtaining multiple groups of interaction matrices; By mapping multiple groups of interaction matrices to the classification of the initial display data, multiple groups of display data are obtained; The imaging weight mean corresponding to the initial display data in each group of display data is calculated, and the priority of each group of display data is set based on the weight mean to obtain a priority group.

6. The method for evaluating naked-eye 3D imaging based on feedback analysis according to claim 1, wherein: The S105 is specifically as follows: By using the priority group, the initial display data is cached based on the cloud and a 3D display cache solution is generated. In the 3D display cache solution, the first-priority initial display data is converted in real time through the cloud and stored in a cache list; Preload the initial presentation data based on the second priority and set a real-time queue task.

7. A naked-eye 3D imaging evaluation system based on feedback analysis, characterized in that: The system includes: a memory and a processor. The memory includes a naked-eye 3D imaging evaluation program based on feedback analysis. When the naked-eye 3D imaging evaluation program based on feedback analysis is executed by the processor, the following steps are implemented: S101: Establishing a dedicated network connection between the cloud and the 3D display terminal, and storing initial display data in the cloud; S102: The user interacts through the 3D display terminal. The cloud converts the initial display data into naked-eye 3D content and displays it through the 3D display terminal. During an interaction cycle, the user's interaction information for each initial display data is collected, and an interaction matrix is generated based on the interaction information. S103: Based on an initial display data, using a camera module, and according to the user's viewing distance, simulating binocular acquisition of left and right image data of a 3D display end, using a preset pixel matrix as a moving window, moving through the left and right image data, and calculating a color value histogram of the preset pixel matrix in the left and right image data based on each movement, analyzing binocular visual differences in the left and right image data through feedback from the color value histogram, and setting imaging weights based on the visual difference evaluation; S104: performing feature decomposition through the interaction matrix and evaluating the differences of the interaction matrix, and classifying the initial display data based on the differences, and setting priority groups for the initial display data based on the classification results and combined with imaging weights; S105: Cache settings are performed on the initial presentation data based on the cloud using the priority groups to generate a 3D presentation cache solution.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a naked-eye 3D imaging evaluation program based on feedback analysis. When the naked-eye 3D imaging evaluation program based on feedback analysis is executed by a processor, the steps of the naked-eye 3D imaging evaluation method based on feedback analysis according to any one of claims 1 to 6 are implemented.

Images