3D video vision training method and system

Abstract

This application relates to the technical field of 3D video processing, and more particularly to a 3D video vision training method and system. The method includes: upon detecting that a user is wearing 3D glasses, acquiring the user's training information; determining whether the user is an initial user based on the training information; if so, collecting the user's basic vision information and a 3D video; testing and updating the basic vision information based on the 3D video to obtain real-time vision information; determining video output parameters that match the real-time vision information; and adjusting the 3D video output parameters based on the video output parameters to obtain a target 3D video suitable for the user's 3D viewing experience. This application improves the user's 3D video viewing experience.

Description

Technical Field

[0001] This application relates to the technical field of 3D video processing, and in particular to a 3D video vision training method and system. Background Technology

[0002] In recent years, with the popularization of 3D display technology, the application scenarios of 3D videos in film and television entertainment, visual rehabilitation, education and training, and other fields have been continuously expanding. However, traditional 3D display technologies generally suffer from poor visual comfort and insufficient individual adaptability, leading to discomfort symptoms such as visual fatigue, dizziness, double vision, and even nausea for some users (especially those with visual abnormalities or visual impairments) when watching 3D content. Studies have shown that the comfort of the 3D visual experience is closely related to the user's individual visual characteristics (such as refractive state, stereoscopic visual acuity, and eye accommodation ability), and existing technologies have failed to effectively solve the problem of dynamic adaptation between 3D content and the user's visual state, thus reducing the user's viewing experience of 3D videos. Summary of the Invention

[0003] To address at least one of the aforementioned technical problems, this application provides a 3D video vision training method and system.

[0004] Firstly, this application provides a 3D video vision training method, which adopts the following technical solution: Once it is detected that a user is wearing 3D glasses, the user's training information is obtained; Based on the user training information, determine whether the user is an initial user. If so, collect the user's basic vision information and 3D video, and test and update the basic vision information based on the 3D video to obtain real-time vision information. The video output parameters that match the real-time vision information are determined, and the output parameters of the 3D video are adjusted based on the video output parameters to obtain the target 3D video that matches the user's 3D viewing experience.

[0005] By employing the above technical solution, when the system detects that a user is wearing 3D glasses, it actively acquires the user's training information. Then, by determining whether the user is an initial user, the system can take different targeted strategies. For initial users, basic vision information is collected and tested using 3D video. In this process, the 3D video serves as dynamic test material, more realistically reflecting the user's vision during actual viewing, thus obtaining more accurate real-time vision information. This dynamic acquisition and updating of vision information ensures the timeliness and accuracy of the data, providing a reliable basis for subsequent adjustments to video output parameters. After obtaining accurate real-time vision information, the system can further determine video output parameters suitable for the user's viewing experience. This is directly related to the user's viewing comfort. By adjusting video output parameters based on real-time vision information, the system can dynamically adjust the display effect of the 3D video, such as contrast, brightness, and color saturation, according to the user's actual vision, thereby obtaining a target 3D video that meets the user's 3D viewing needs. This personalized video output adjustment enhances the user's viewing experience.

[0006] In one possible implementation, the step of testing and updating the basic vision information based on the 3D video to obtain real-time vision information includes: The visual acuity information for the left eye and the right eye is determined based on the aforementioned basic visual acuity information. The 3D video is subjected to first visual image segmentation processing to obtain right eye vision images with different vision levels that are adapted to the left eye vision information and similar to the right eye vision information; The 3D video is subjected to second visual image segmentation processing to obtain left eye vision images with different vision levels that are adapted to the right eye vision information and similar to the left eye vision information; The right eye vision image and the left eye vision image are mapped one by one onto the 3D glasses for visual testing to obtain the left eye feedback vision and the right eye feedback vision. Based on preset visual acuity standards, visual acuity is evaluated for the left-eye feedback visual and the right-eye feedback visual respectively to obtain the user's left-eye visual acuity and the user's right-eye visual acuity. The basic vision information is updated based on the user's left eye vision and right eye vision to obtain real-time vision information.

[0007] In one possible implementation, determining whether the user is an initial user based on the user training information includes: If the user training information is not the initial user, then historical vision information and 3D video are obtained, and the user's current vision is deduced based on the historical vision information to obtain the current vision information; The video output parameters that match the current vision information are determined, and the output parameters of the 3D video are adjusted based on the video output parameters to obtain a target 3D video that matches the user's 3D viewing experience.

[0008] In one possible implementation, the step of adjusting the output parameters of the 3D video based on the video output parameters to obtain a target 3D video suitable for the user's 3D viewing experience further includes: Collect the first video output parameters corresponding to different time points during the user's 3D movie viewing; Determine the second video output parameters corresponding to different time points based on the target 3D video; The first video output parameter and the second video output parameter are compared to determine whether there is at least one parameter in the first video output parameter that is not compatible with the second video output parameter. If so, an abnormal parameter output record is made based on the current time node, the first video output parameter, and the second video output parameter. Determine whether the total number of abnormal output records of the parameters is greater than the preset number of output records. If it is greater, then the second video output parameters are fine-tuned according to the parameter difference relationship of the same type between the first video output parameters and the second video output parameters to obtain multiple sets of fine-tuned second video output parameters and multiple sets of fine-tuned corresponding first video output parameters. Based on the multiple sets of fine-tuned second video output parameters and the multiple sets of corresponding fine-tuned first video output parameters, a correction analysis is performed to obtain the corrected second video output parameters. The target 3D video is updated with visual parameters based on the corrected second video output parameters to obtain the updated target 3D video.

[0009] In one possible implementation, the step of fine-tuning the second video output parameters according to a preset specification based on the parameter difference relationship of the same type between the first video output parameters and the second video output parameters to obtain multiple sets of fine-tuned second video output parameters and multiple sets of corresponding fine-tuned first video output parameters includes: Obtain fine-tuning specification standards, wherein the fine-tuning specification standards are the relationship between the differences of different parameters between the second video output parameters and the first video output parameters, the number of adjustments, and the corresponding standards of the adjustment parameter specifications; By matching the parameter difference relationship with the difference relationship in the fine-tuning specification standard, the target number of adjustments and the target adjustment specification are obtained. The second video output parameters are adjusted multiple times according to the target adjustment number and target adjustment specification, and the first video output parameters are recorded in real time after each adjustment of the second video output parameters is completed. The second video output parameters and the second video output parameters after each adjustment are integrated to obtain multiple sets of fine-tuned second video output parameters; The first video output parameters and the first video output parameters after each adjustment of the second video output parameters are integrated to obtain multiple sets of fine-tuned first video output parameters.

[0010] In one possible implementation, the step of performing correction analysis based on the multiple sets of fine-tuned second video output parameters and the multiple sets of corresponding fine-tuned first video output parameters to obtain the corrected second video output parameters includes: The multiple sets of finely tuned second video output parameters and the multiple sets of finely tuned corresponding first video output parameters are associated and grouped one-to-one according to time nodes to obtain multiple sets of video experimental parameters. The multiple sets of video experimental parameters are grouped in pairs according to the time node sequence to obtain multiple video experimental parameter groups, wherein each video experimental parameter group contains two sets of video experimental parameters with adjacent time nodes. The multiple video experiment parameter groups are respectively input into a preset correction algorithm for calculation to obtain the first video parameter coefficient and the second video parameter coefficient corresponding to each video experiment parameter group; The second video output parameters are corrected based on the first video parameter coefficient, the second video parameter coefficient, and the video experimental parameter set to obtain the corrected second video output parameters.

[0011] In one possible implementation, the step of correcting the second video output parameters based on the first video parameter coefficients, the second video parameter coefficients, and the video experimental parameter set to obtain the corrected second video output parameters includes: The first video output parameter and the second video output parameter in the video experiment parameter group are calculated according to the parameter type to obtain the first parameter difference and the second parameter difference corresponding to each group of video experiment parameters in the video experiment parameter group; Determine whether there is at least one difference between the first parameter difference and the second parameter difference that does not conform to the preset difference range. If so, remove the video experiment parameter group and the first video parameter coefficient and the second video parameter coefficient corresponding to the video experiment parameter group to obtain the filter experiment parameters. Calculate the mean value of the first video parameter coefficient and the mean value of the second video parameter coefficient in the filtering experiment parameters to obtain the first target coefficient and the second target coefficient; The second video output parameters, the first target coefficient, and the second target coefficient are input into a preset correction algorithm for calculation to obtain the corrected second video output parameters.

[0012] Secondly, this application provides a 3D video vision training system, which adopts the following technical solution: A 3D video vision training system, comprising: The information acquisition module is used to acquire the user's training information when it detects that the user is wearing 3D glasses; The test update module is used to determine whether the user is an initial user based on the user training information. If so, it collects the user's basic vision information and 3D video, and performs test update on the basic vision information based on the 3D video to obtain real-time vision information. The parameter adjustment module is used to determine the video output parameters that conform to the real-time vision information for viewing, and adjust the output parameters of the 3D video based on the video output parameters to obtain the target 3D video that conforms to the user's 3D viewing.

[0013] In one possible implementation, when the test update module performs a test update on the basic vision information based on the 3D video to obtain real-time vision information, it is specifically used for: The visual acuity information for the left eye and the right eye is determined based on the aforementioned basic visual acuity information. The 3D video is subjected to first visual image segmentation processing to obtain right eye vision images with different vision levels that are adapted to the left eye vision information and similar to the right eye vision information; The 3D video is subjected to second visual image segmentation processing to obtain left eye vision images with different vision levels that are adapted to the right eye vision information and similar to the left eye vision information; The right eye vision image and the left eye vision image are mapped one by one onto the 3D glasses for visual testing to obtain the left eye feedback vision and the right eye feedback vision. Based on preset visual acuity standards, visual acuity is evaluated for the left-eye feedback visual and the right-eye feedback visual respectively to obtain the user's left-eye visual acuity and the user's right-eye visual acuity. The basic vision information is updated based on the user's left eye vision and right eye vision to obtain real-time vision information.

[0014] In another possible implementation, when the test update module determines whether the user is an initial user based on the user training information, it is specifically used for: If the user training information is not the initial user, then historical vision information and 3D video are obtained, and the user's current vision is deduced based on the historical vision information to obtain the current vision information; The video output parameters that match the current vision information are determined, and the output parameters of the 3D video are adjusted based on the video output parameters to obtain a target 3D video that matches the user's 3D viewing experience.

[0015] In another possible implementation, the system further includes: a parameter acquisition module, a parameter determination module, a parameter comparison module, a parameter fine-tuning module, a parameter correction module, and a video update module, wherein, The parameter acquisition module is used to acquire the first video output parameters corresponding to different time points during the user's 3D movie viewing. The parameter determination module is used to determine the second video output parameters corresponding to different time points based on the target 3D video; The parameter comparison module is used to compare the first video output parameter and the second video output parameter to determine whether there is at least one parameter in the first video output parameter that is not compatible with the second video output parameter. If so, an abnormal parameter output record is made based on the current time node, the first video output parameter, and the second video output parameter. The parameter fine-tuning module is used to determine whether the total number of abnormal output records of the parameters is greater than the preset number of output records. If it is greater, the second video output parameters are fine-tuned according to the parameter difference relationship of the same type between the first video output parameters and the second video output parameters to obtain multiple sets of fine-tuned second video output parameters and multiple sets of fine-tuned corresponding first video output parameters. The parameter correction module is used to perform correction analysis based on the multiple sets of fine-tuned second video output parameters and the multiple sets of corresponding fine-tuned first video output parameters to obtain the corrected second video output parameters. The video update module allows the user to update the visual parameters of the target 3D video according to the corrected second video output parameters, thereby obtaining the updated target 3D video.

[0016] In another possible implementation, when the parameter fine-tuning module fine-tunes the second video output parameter according to a preset specification based on the parameter difference relationship of the same type between the first video output parameter and the second video output parameter, and obtains multiple sets of fine-tuned second video output parameters and multiple sets of fine-tuned corresponding first video output parameters, it is specifically used for: Obtain fine-tuning specification standards, wherein the fine-tuning specification standards are the relationship between the differences of different parameters between the second video output parameters and the first video output parameters, the number of adjustments, and the corresponding standards of the adjustment parameter specifications; By matching the parameter difference relationship with the difference relationship in the fine-tuning specification standard, the target number of adjustments and the target adjustment specification are obtained. The second video output parameters are adjusted multiple times according to the target adjustment number and target adjustment specification, and the first video output parameters are recorded in real time after each adjustment of the second video output parameters is completed. The second video output parameters and the second video output parameters after each adjustment are integrated to obtain multiple sets of fine-tuned second video output parameters; The first video output parameters and the first video output parameters after each adjustment of the second video output parameters are integrated to obtain multiple sets of fine-tuned first video output parameters.

[0017] In another possible implementation, when the parameter correction module performs correction analysis based on the multiple sets of fine-tuned second video output parameters and the corresponding multiple sets of fine-tuned first video output parameters to obtain the corrected second video output parameters, it is specifically used for: The multiple sets of finely tuned second video output parameters and the multiple sets of finely tuned corresponding first video output parameters are associated and grouped one-to-one according to time nodes to obtain multiple sets of video experimental parameters. The multiple sets of video experimental parameters are grouped in pairs according to the time node sequence to obtain multiple video experimental parameter groups, wherein each video experimental parameter group contains two sets of video experimental parameters with adjacent time nodes. The multiple video experiment parameter groups are respectively input into a preset correction algorithm for calculation to obtain the first video parameter coefficient and the second video parameter coefficient corresponding to each video experiment parameter group; The second video output parameters are corrected based on the first video parameter coefficient, the second video parameter coefficient, and the video experimental parameter set to obtain the corrected second video output parameters.

[0018] In another possible implementation, when the parameter correction module corrects the second video output parameters according to the first video parameter coefficients, the second video parameter coefficients, and the video experimental parameter set to obtain the corrected second video output parameters, it is specifically used for: The first video output parameter and the second video output parameter in the video experiment parameter group are calculated according to the parameter type to obtain the first parameter difference and the second parameter difference corresponding to each group of video experiment parameters in the video experiment parameter group; Determine whether there is at least one difference between the first parameter difference and the second parameter difference that does not conform to the preset difference range. If so, remove the video experiment parameter group and the first video parameter coefficient and the second video parameter coefficient corresponding to the video experiment parameter group to obtain the filter experiment parameters. Calculate the mean value of the first video parameter coefficient and the mean value of the second video parameter coefficient in the filtering experiment parameters to obtain the first target coefficient and the second target coefficient; The second video output parameters, the first target coefficient, and the second target coefficient are input into a preset correction algorithm for calculation to obtain the corrected second video output parameters.

[0019] Thirdly, this application provides an electronic device that adopts the following technical solution: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application being configured to: execute a 3D video vision training method as described in any of the first aspects.

[0020] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform a 3D video vision training method as described in any of the first aspects.

[0021] In summary, this application includes at least one of the following beneficial technical effects: Upon detecting that a user is wearing 3D glasses, the system proactively acquires the user's training information. Then, by determining whether the user is an initial user, the system can adopt different strategies accordingly. For initial users, basic vision information is collected and updated using 3D video for testing. During this process, the 3D video serves as dynamic testing material, more realistically reflecting the user's vision during actual viewing, thus obtaining more accurate real-time vision information. This dynamic acquisition and updating of vision information ensures the timeliness and accuracy of the data, providing a reliable basis for subsequent adjustments to video output parameters. After obtaining accurate real-time vision information, the system can further determine the video output parameters suitable for the user's viewing experience, directly impacting the user's viewing comfort. By adjusting video output parameters based on real-time vision information, the system can dynamically adjust the display effects of the 3D video, such as contrast, brightness, and color saturation, according to the user's actual vision, thereby obtaining a target 3D video that meets the user's 3D viewing needs. This personalized video output adjustment enhances the user's viewing experience. Attached Figure Description

[0022] Figure 1 This is a flowchart illustrating a 3D video vision training method provided in an embodiment of this application.

[0023] Figure 2This is a schematic diagram of the structure of a 3D video vision training system provided in an embodiment of this application.

[0024] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0025] The following is in conjunction with the appendix Figure 1-3 This application will be described in further detail.

[0026] This specific embodiment is merely an explanation of this application and is not intended to limit it. After reading this specification, those skilled in the art can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they are within the scope of this application.

[0027] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0028] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0029] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0030] This application provides a 3D video vision training method executed by an electronic device. This electronic device can be a standalone physical electronic device, a cluster of multiple physical electronic devices, a distributed system, or a cloud electronic device providing cloud computing services. This application does not impose limitations on this method. Figure 1 As shown, the method includes: Step S10: After detecting that the user is wearing 3D glasses, obtain the user's training information.

[0031] In this embodiment of the application, user training information is used to represent the information that a user needs to provide for authentication and recording when wearing 3D glasses. This refers to data that uniquely identifies the user and relates to the user's use of 3D glasses, typically including username, password (in some cases, other authentication methods are used instead of password), user ID, etc.

[0032] Specifically, the device first uses built-in sensors (such as infrared sensors and cameras) to monitor in real time whether the user is wearing 3D glasses. Once it detects that the user is wearing 3D glasses, the device will immediately initiate the process of acquiring the user's training information.

[0033] Step S11: Determine whether the user is an initial user based on the user training information. If so, collect the user's basic vision information and 3D video, and test and update the basic vision information based on the 3D video to obtain real-time vision information.

[0034] In the embodiments of this application, basic vision information refers to vision-related data obtained by the user through conventional vision testing methods when the user has not been exposed to 3D content, such as myopia, hyperopia, astigmatism, binocular disparity, etc., which are used to represent the user's initial visual ability status.

[0035] Specifically, the system first analyzes the acquired user training information. If the user training information record is empty, or there is no historical data related to the user, the system will determine that the user is an initial user. Once the user is determined to be an initial user, the system will initiate the process of collecting the user's basic vision information. This can be achieved by connecting to external vision testing devices (such as eye charts, refractometers, etc.). The system will guide the user to perform a vision test according to the prompts to obtain basic vision information. At the same time, the system will select the 3D video chosen by the user from local storage or a cloud server. Subsequently, the system will start playing the 3D video and test and update the user's basic vision information based on the video content during playback. For example, while playing the 3D video, the system will record the user's visual response to different 3D scenes, such as the accuracy of judging the distance of objects and the ability to track fast-moving objects. Based on these responses, the system will adjust relevant parameters in the basic vision information, such as adjusting binocular disparity data and updating myopia or hyperopia degrees, ultimately obtaining real-time vision information.

[0036] Specifically, based on basic visual acuity information, left-eye and right-eye visual acuity information is determined. The 3D video undergoes first-vision image segmentation processing to obtain right-eye visual acuity images with different vision levels that match the left-eye visual acuity information and are similar to the right-eye visual acuity information. The 3D video also undergoes second-vision image segmentation processing to obtain left-eye visual acuity images with different vision levels that match the right-eye visual acuity information and are similar to the left-eye visual acuity information. These right-eye and left-eye visual acuity images are then mapped one by one onto 3D glasses for visual testing to obtain left-eye and right-eye feedback visuals. Based on preset visual acuity standards, visual acuity is evaluated for both left-eye and right-eye feedback visuals to obtain the user's left-eye and right-eye visual acuity. The basic visual acuity information is then updated based on the user's left-eye and right-eye visual acuity to obtain real-time visual acuity information.

[0037] In this embodiment, the system first extracts left-eye and right-eye vision information from basic vision information. For the first visual image segmentation of the 3D video, the system adjusts the 3D video image based on left-eye vision information, such as the degree of myopia and astigmatism in the left eye. For example, if the left-eye myopia is high, the system appropriately enlarges or enhances the image's clarity, while also considering right-eye vision information to ensure the generated right-eye vision image is visually similar to the right-eye vision, avoiding visual discomfort or inaccurate testing due to significant differences between the left and right eye images. Similarly, for the second visual image segmentation of the 3D video, the system processes the image based on right-eye vision information to generate a left-eye vision image suitable for right-eye vision and similar to the left-eye vision information. After image segmentation, the system maps the obtained right-eye and left-eye vision images one by one into the 3D glasses. When the user wears the 3D glasses to view these images, the left and right eyes receive the corresponding images, thus generating left-eye and right-eye feedback vision. The system records various user reactions during viewing, such as evaluations of image clarity and perception of stereoscopic effect. Next, based on preset visual acuity standards, the system assesses the visual feedback of the left and right eyes separately. For example, these standards specify the minimum font size that can be clearly distinguished at a certain distance, and the accuracy of recognizing objects of different colors and shapes. The system evaluates the user's left and right eye visual feedback according to these standards, thus obtaining the user's left and right eye visual acuity. Finally, the system updates the basic visual acuity information based on the assessed left and right eye visual acuity. For example, if the assessment results show that the user's left eye visual acuity has improved or worsened after watching 3D videos, the system records this change in the basic visual acuity information to obtain real-time visual acuity information, enabling the system to provide the user with a more suitable 3D visual experience or conduct related vision health monitoring.

[0038] Step S12: Determine the video output parameters that match the real-time vision information for viewing, and adjust the output parameters of the 3D video based on the video output parameters to obtain the target 3D video that matches the user's 3D viewing experience.

[0039] In this embodiment, the system first analyzes real-time vision information. For example, if the real-time vision information shows that the user's left eye has a higher degree of myopia and poorer perception of the clarity of near objects, the system will appropriately adjust the depth-of-field settings when determining the video output parameters, making the main objects in the picture appear further away to reduce visual fatigue in the left eye caused by focusing on near objects. Simultaneously, considering the user's overall visual adaptation ability, the system will reduce the frame rate to accommodate fast-moving 3D objects, ensuring sufficient time for the user to adapt to changes in the picture without affecting the smoothness of the image. When determining the video output parameters, the system also refers to some common 3D video playback standards and specifications, while also considering the user's previous viewing preferences and feedback on different types of 3D videos. For example, if the user was more interested in high-contrast images when watching action 3D movies, the system will appropriately increase the values ​​of color depth and contrast parameters to enhance the sense of depth and visual impact of the image. After determining the video output parameters, the system will adjust the output parameters of the original 3D video. This includes operations such as converting video encoding formats, rearranging image pixels, and adjusting color and brightness curves. For example, the resolution might be adjusted from 1080P to 720P, which is more suitable for the user's eyesight (if the user has poor eyesight, high resolution can lead to overly complex image details, increasing visual burden). Simultaneously, color depth is adjusted to make color transitions more natural, reducing visual discomfort caused by overly vibrant colors or excessive contrast. After a series of parameter adjustments, the final target 3D video will be played on a 3D display device. When the user wears 3D glasses, they will experience a 3D effect more suited to their visual condition, with improved image clarity, stereoscopic effect, and color to better meet their visual needs, thus enhancing their viewing experience.

[0040] In this embodiment, the system utilizes machine learning algorithms to analyze real-time vision information. First, the system collects a large amount of viewing feedback data from users with different vision conditions on 3D videos with different video output parameters, constructing a training dataset. Then, a deep learning model (such as a convolutional neural network) is trained on this dataset, allowing the model to learn the mapping relationship between real-time vision information and optimal video output parameters. Once the user's real-time vision information is obtained, the system inputs this information into the trained model, and the model outputs a set of video output parameters that match the user's real-time vision information. Next, the system adjusts the output parameters of the original 3D video using video processing software (such as FFmpeg). For example, based on the output depth parameters, the depth information of objects in the video is re-rendered; based on color depth and brightness parameters, the color space and brightness curve of the video are adjusted. The final target 3D video is played on a 3D display device, providing users with a personalized viewing experience.

[0041] This application provides a 3D video vision training method. When a user is detected wearing 3D glasses, the system actively acquires the user's training information. Then, by determining whether the user is an initial user, the system can adopt different targeted strategies. For initial users, basic vision information is collected and updated in conjunction with 3D video for testing. In this process, the 3D video serves as dynamic test material, more realistically reflecting the user's vision during actual viewing, thus obtaining more accurate real-time vision information. The dynamic acquisition and updating of vision information ensures the timeliness and accuracy of the data, providing a reliable basis for subsequent adjustments to video output parameters. After obtaining accurate real-time vision information, the system can further determine video output parameters suitable for the user's viewing experience. This is directly related to the user's viewing comfort. By adjusting video output parameters based on real-time vision information, the system can dynamically adjust the display effect of the 3D video, such as contrast, brightness, and color saturation, according to the user's actual vision, thereby obtaining a target 3D video that meets the user's 3D viewing needs. This personalized video output adjustment enhances the user's viewing experience.

[0042] Furthermore, when the user's training information is not the initial user, historical vision information and 3D video are obtained, and the user's current vision is inferred based on the historical vision information to obtain the current vision information; the video output parameters that match the current vision information are determined, and the output parameters of the 3D video are adjusted based on the video output parameters to obtain the target 3D video that matches the user's 3D viewing experience.

[0043] Specifically, the system first retrieves the non-initial user's historical vision information from a database or storage device. This information is stored in a structured format, such as a table, recording the user's vision test data at different points in time. When extrapolating the user's current vision based on historical vision information, the system considers multiple factors. For example, it analyzes the trend of myopia changes in the user's historical vision information. If it finds that the user's myopia has increased at a certain rate each year over a period of time, the system will calculate the user's current myopia based on this growth trend and the interval between the current time and the most recent vision test. Simultaneously, the system also considers the impact of factors such as the user's age and eye habits (such as daily screen time and reading habits) on vision changes. If the user is older and has a history of excessive eye strain, the system will assume that their vision will decline to some extent. After determining the current vision information, the system will determine the video output parameters suitable for the user's current vision. For example, if the calculated current vision information indicates that the user has a high degree of myopia and poor perception of the clarity of near objects, the system will appropriately adjust the depth-of-field settings when determining video output parameters. This will make the main objects in the image appear further away, reducing visual fatigue caused by close-up focusing. Simultaneously, considering that the user's sensitivity to color and brightness may change due to changes in vision, the system will also adjust the color depth and brightness parameters accordingly.

[0044] In addition, a real-time vision monitoring mechanism is immediately activated when the user's actual vision does not match the predicted current vision information. Advanced vision monitoring sensors, such as miniature eye-tracking cameras and infrared vision detection modules, are integrated into 3D viewing devices (e.g., 3D glasses, 3D displays) to continuously acquire the user's actual vision data, including but not limited to key indicators such as myopia, astigmatism, binocular disparity, and clarity after vision correction. This real-time monitored vision data is compared and analyzed with the predicted current vision information. Using a preset algorithm model, the degree of difference between the two is calculated, and it is determined whether the difference exceeds an acceptable error range. If the difference exceeds the range, the system will re-determine the video output parameters to match the user's current actual vision based on the real-time vision data. For example, if the system detects that the user's myopia has increased compared to the predicted value, it will adjust the depth-of-field settings of the 3D video accordingly, making objects in the image appear farther away to reduce the user's pressure on close-up focusing; at the same time, it will adjust the color contrast and brightness to adapt to the user's visual experience after the change in vision. Based on the re-determined video output parameters, the target 3D video is dynamically adjusted in real time. During the adjustment process, the system will maintain the smoothness and stability of the video, avoiding issues such as screen stuttering and flickering, and ensuring that users can continuously enjoy a good 3D viewing experience.

[0045] In this embodiment, historical vision information of non-initial users is obtained through a database query interface. The database stores the user's historical vision test records, including the time of each test, myopia degree, hyperopia degree, astigmatism degree, and other data. Simultaneously, the system retrieves information about 3D videos previously watched by the user from video playback logs. When extrapolating current vision information, the system uses time-series analysis algorithms, such as the ARIMA model, to analyze and predict the user's historical myopia degree data. Based on the prediction results and the current time, the system derives the user's current myopia degree and other vision information. Next, the system utilizes machine learning algorithms, such as decision trees or support vector machines, to determine the optimal video output parameters based on the current vision information. These algorithms are trained based on a large amount of viewing feedback data from users with different vision conditions on 3D videos under different video output parameters. After determining the parameters, the system adjusts the output parameters of the original 3D video using video processing software (such as FFmpeg). For example, based on the output depth parameters, the depth information of objects in the video is re-rendered; based on color depth and brightness parameters, the color space and brightness curve of the video are adjusted to finally obtain the target 3D video.

[0046] Furthermore, the output parameters of the 3D video are adjusted based on the video output parameters to obtain a target 3D video suitable for the user's 3D viewing experience. This includes: collecting the first video output parameters corresponding to different time points during the user's 3D viewing; determining the second video output parameters corresponding to different time points based on the target 3D video; comparing the first and second video output parameters to determine if there is at least one parameter in the first video output parameters that is incompatible with the second video output parameters; if so, recording an abnormal parameter output based on the current time point, the first video output parameters, and the second video output parameters; determining if the total number of abnormal parameter output records exceeds the preset number of output records; if so, fine-tuning the second video output parameters according to the parameter difference relationship of the same type between the first and second video output parameters to obtain multiple sets of fine-tuned second video output parameters and multiple sets of corresponding fine-tuned first video output parameters; and performing correction analysis based on the multiple sets of fine-tuned second video output parameters and their corresponding first video output parameters to obtain corrected second video output parameters. The visual parameters of the target 3D video are updated based on the corrected second video output parameters to obtain the updated target 3D video.

[0047] The first video output parameter refers to the actual video output parameters that affect the user's viewing experience, collected in real-time at different time points during the user's 3D viewing process. These parameters include, but are not limited to, screen resolution, frame rate, color depth, depth of field setting, parallax adjustment, brightness, and contrast, reflecting the technical indicators related to the actual 3D video playback effect received by the user. The second video output parameter refers to the parameter values ​​corresponding to the video output parameters of the previously determined target 3D video at different time points, and its parameter type is consistent with the video output parameter type corresponding to the first video output parameter. The process of comparing the collected first video output parameters with the second video output parameters corresponding to the target 3D video item by item aims to check whether there are any differences between the two and to determine whether the actual playback parameters meet the expected settings. The preset output record number is a pre-set threshold used to measure whether the number of abnormal parameter output records reaches the level where parameter adjustment is required. When the total number of abnormal parameter output records exceeds this threshold, the system will trigger the parameter fine-tuning mechanism. The preset specification fine-tuning is to make minor adjustments to the second video output parameters according to certain rules and amplitudes. This adjustment is based on the difference between the same type of parameters between the first and second video output parameters, with the aim of exploring more suitable parameter combinations to improve the user's viewing experience.

[0048] Specifically, the fine-tuning specification standard is obtained. This standard comprises the relationship between the differences in parameters between the second and first video output parameters, the number of adjustments, and the corresponding standard for the adjustment parameter specifications. The parameter difference relationship is matched with the difference relationship in the fine-tuning specification standard to obtain the target number of adjustments and the target adjustment specification. Based on the target number of adjustments and the target adjustment specification, the second video output parameter is adjusted multiple times, and the first video output parameter is recorded in real time after each adjustment. The second video output parameter and the adjusted second video output parameter are integrated to obtain multiple sets of fine-tuned second video output parameters. The first video output parameter and the first video output parameter after each second video output parameter adjustment are also integrated to obtain multiple sets of fine-tuned first video output parameters.

[0049] Specifically, multiple sets of fine-tuned second video output parameters and their corresponding first video output parameters are grouped one-to-one according to time nodes to obtain multiple sets of video experimental parameters. These multiple sets of video experimental parameters are then grouped in pairs according to the time node sequence to obtain multiple video experimental parameter groups, where each video experimental parameter group contains two sets of video experimental parameters at adjacent time nodes. These multiple video experimental parameter groups are then input into a preset correction algorithm for calculation, obtaining the first video parameter coefficients and second video parameter coefficients corresponding to each video experimental parameter group. Based on the first video parameter coefficients, second video parameter coefficients, and the video experimental parameter groups, the second video output parameters are corrected to obtain the corrected second video output parameters.

[0050] In this embodiment of the application, the preset correction algorithm includes y=ax+b, where y is the first video output parameter, x is the second video output parameter, a is the coefficient of the first video parameter, and b is the coefficient of the second video parameter.

[0051] Specifically, the first and second video output parameters in the video experiment parameter group are calculated according to their parameter types to obtain the first and second parameter differences for each group of video experiment parameters in the video experiment parameter group. It is determined whether at least one of the first and second parameter differences does not conform to a preset difference range. If so, the video experiment parameter group and its corresponding first and second video parameter coefficients are removed to obtain the filtering experiment parameters. The mean of the first and second video parameter coefficients in the filtering experiment parameters are calculated to obtain the first and second target coefficients. The second video output parameters, the first target coefficient, and the second target coefficient are then input into a preset correction algorithm for calculation to obtain the corrected second video output parameters.

[0052] At this point, in the preset correction algorithm y=ax+b, y represents the corrected second video output parameter, x represents the second video output parameter, a represents the first target coefficient, and b represents the second target coefficient. The corrected second video output parameter is used to update the parameters of the target 3D video, resulting in first video output parameters that are consistent with the previous second video output parameters.

[0053] The following describes a 3D video vision training system provided in an embodiment of this application. The 3D video vision training system described below can be referred to in conjunction with the 3D video vision training method described above. Figure 2 , Figure 2 This is a schematic diagram of the structure of a 3D video vision training system 20 provided in an embodiment of this application, including: The information acquisition module 21 is used to acquire the user's training information when it detects that the user is wearing 3D glasses; The test update module 22 is used to determine whether the user is an initial user based on the user training information. If so, it collects the user's basic vision information and 3D video, and tests and updates the basic vision information based on the 3D video to obtain real-time vision information. The parameter adjustment module 23 is used to determine the video output parameters that are compatible with real-time vision information for viewing, and to adjust the output parameters of the 3D video based on the video output parameters to obtain the target 3D video that is compatible with the user's 3D viewing experience.

[0054] In one possible implementation of this application embodiment, when the test update module 22 performs test updates on basic vision information based on 3D video to obtain real-time vision information, it is specifically used for: Determine the visual acuity information for the left and right eyes based on the basic visual acuity information; The 3D video is processed by first-vision image segmentation to obtain right-eye vision images with different vision levels that are adapted to the left-eye vision information and similar to the right-eye vision information; The 3D video is processed by second visual image segmentation to obtain left eye vision images with different vision levels that are adapted to the right eye vision information and similar to the left eye vision information; The right eye vision image and the left eye vision image were mapped one by one onto the 3D glasses for visual testing to obtain the left eye feedback visual and the right eye feedback visual; Based on preset visual acuity standards, visual acuity is assessed for the left and right eye feedback visuals to obtain the user's left and right eye visual acuity. The basic vision information is updated based on the user's left and right eye vision to obtain real-time vision information.

[0055] Another possible implementation in this application embodiment is that, when the test update module 22 determines whether a user is an initial user based on user training information, it is specifically used for: If the user's training information is not that of an initial user, then historical vision information and 3D video are obtained, and the user's current vision is inferred based on the historical vision information to obtain the current vision information; The video output parameters that match the user's current visual information are determined, and the output parameters of the 3D video are adjusted based on the video output parameters to obtain the target 3D video that matches the user's 3D viewing experience.

[0056] In another possible implementation of this application embodiment, system 20 further includes: a parameter acquisition module, a parameter determination module, a parameter comparison module, a parameter fine-tuning module, a parameter correction module, and a video update module, wherein, The parameter acquisition module is used to collect the first video output parameters corresponding to different time points during the user's 3D movie viewing. The parameter determination module is used to determine the second video output parameters corresponding to different time points based on the target 3D video; The parameter comparison module is used to compare the first video output parameters and the second video output parameters to determine whether there is at least one parameter in the first video output parameters that is not compatible with the second video output parameters. If so, an abnormal parameter output record is made based on the current time node, the first video output parameters, and the second video output parameters. The parameter fine-tuning module is used to determine whether the total number of abnormal output records is greater than the preset number of output records. If it is greater, the second video output parameters are fine-tuned according to the parameter difference relationship of the same type between the first video output parameters and the second video output parameters, so as to obtain multiple sets of fine-tuned second video output parameters and multiple sets of fine-tuned corresponding first video output parameters. The parameter correction module is used to perform correction analysis based on multiple sets of fine-tuned second video output parameters and multiple sets of corresponding fine-tuned first video output parameters to obtain the corrected second video output parameters. The video update module allows the user to update the visual parameters of the target 3D video based on the corrected second video output parameters, resulting in an updated target 3D video.

[0057] Another possible implementation in this application embodiment is that when the parameter fine-tuning module fine-tunes the second video output parameters according to a preset specification based on the parameter difference relationship of the same type between the first video output parameters and the second video output parameters, and obtains multiple sets of fine-tuned second video output parameters and multiple sets of fine-tuned corresponding first video output parameters, it is specifically used for: Obtain the fine-tuning specification standard, which is the relationship between the differences of different parameters between the second video output parameters and the first video output parameters, the number of adjustments, and the corresponding standard of the adjustment parameter specifications; By matching the parameter difference relationship with the difference relationship in the fine-tuning specification standard, the target number of adjustments and the target adjustment specification are obtained. The second video output parameters are adjusted multiple times according to the target adjustment number and target adjustment specifications, and the first video output parameters are recorded in real time after each adjustment of the second video output parameters is completed. By integrating the second video output parameters and the second video output parameters after each adjustment, multiple sets of fine-tuned second video output parameters are obtained. The first video output parameters and the first video output parameters after each adjustment of the second video output parameters are integrated to obtain multiple sets of fine-tuned first video output parameters.

[0058] In another possible implementation of this application, when the parameter correction module performs correction analysis based on multiple sets of fine-tuned second video output parameters and multiple sets of corresponding fine-tuned first video output parameters to obtain the corrected second video output parameters, it is specifically used for: Multiple sets of finely tuned second video output parameters and multiple sets of finely tuned corresponding first video output parameters are grouped and associated one-to-one according to time nodes to obtain multiple sets of video experimental parameters. Multiple sets of video experimental parameters are grouped in pairs according to the time node sequence to obtain multiple video experimental parameter groups. Each video experimental parameter group contains two sets of video experimental parameters with adjacent time nodes. Multiple sets of video experimental parameters are input into a preset correction algorithm for calculation to obtain the first video parameter coefficient and the second video parameter coefficient corresponding to each set of video experimental parameters. The second video output parameters are corrected based on the first video parameter coefficient, the second video parameter coefficient, and the video experiment parameter set to obtain the corrected second video output parameters.

[0059] In another possible implementation of this application, when the parameter correction module corrects the second video output parameters according to the first video parameter coefficients, the second video parameter coefficients, and the video experimental parameter set to obtain the corrected second video output parameters, it is specifically used for: The first and second video output parameters in the video experiment parameter group are calculated according to their parameter types to obtain the first parameter difference and the second parameter difference corresponding to each group of video experiment parameters in the video experiment parameter group. Determine whether there is at least one difference between the first parameter difference and the second parameter difference that does not conform to the preset difference range. If so, remove the video experiment parameter group and the first video parameter coefficient and the second video parameter coefficient corresponding to the video experiment parameter group to obtain the filtered experiment parameters. Calculate the mean value of the first video parameter coefficient and the mean value of the second video parameter coefficient in the filtering experiment parameters to obtain the first target coefficient and the second target coefficient; The second video output parameters, the first target coefficient, and the second target coefficient are input into a preset correction algorithm for calculation to obtain the corrected second video output parameters.

[0060] This application provides an electronic device, such as... Figure 3 As shown, Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 3The illustrated electronic device 300 includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this electronic device 300 does not constitute a limitation on the embodiments of this application.

[0061] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in connection with the embodiments of this application. Processor 301 may also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0062] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0063] The memory 303 may be a ROM (Read-Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or it may be an EEPROM (Electrically Erasable Programmable Read-Only Memory), a CD-ROM (Compact Disc Read-Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0064] The memory 303 is used to store application code that executes the scheme of the embodiments of this application, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0065] Among them, electronic devices include, but are not limited to: mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0066] The following describes a computer-readable storage medium provided by an embodiment of this application. The computer-readable storage medium described below can be referred to in correspondence with the method described above.

[0067] This application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the 3D video vision training system described above.

[0068] Since the embodiments of the computer-readable storage medium portion correspond to the embodiments of the method portion, please refer to the description of the embodiments of the method portion for the embodiments of the computer-readable storage medium portion.

[0069] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0070] The above are only some embodiments of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A 3D video vision training method, characterized in that, include: Once it is detected that a user is wearing 3D glasses, the user's training information is obtained; Based on the user training information, determine whether the user is an initial user. If so, collect the user's basic vision information and 3D video, and test and update the basic vision information based on the 3D video to obtain real-time vision information. The step of testing and updating the basic vision information based on the 3D video to obtain real-time vision information includes: The visual acuity information for the left eye and the right eye is determined based on the aforementioned basic visual acuity information. The 3D video is subjected to first visual image segmentation processing to obtain right eye vision images with different vision levels that are adapted to the left eye vision information and similar to the right eye vision information; The 3D video is subjected to second visual image segmentation processing to obtain left eye vision images with different vision levels that are adapted to the right eye vision information and similar to the left eye vision information; The right eye vision image and the left eye vision image are mapped one by one onto the 3D glasses for visual testing; Determine the video output parameters that match the real-time vision information for viewing, and adjust the output parameters of the 3D video based on the video output parameters to obtain the target 3D video that matches the user's 3D viewing experience; This also includes: collecting the first video output parameters corresponding to different time points during the user's 3D movie viewing; Determine the second video output parameters corresponding to different time points based on the target 3D video; The first video output parameter and the second video output parameter are compared to determine whether there is at least one parameter in the first video output parameter that is incompatible with the second video output parameter. If so, an abnormal parameter output record is made. Determine whether the total number of abnormal output records of the parameters is greater than the preset number of output records. If it is greater, then the second video output parameters are fine-tuned according to the parameter difference relationship of the same type between the first video output parameters and the second video output parameters to obtain multiple sets of fine-tuned second video output parameters and multiple sets of fine-tuned corresponding first video output parameters. Based on the multiple sets of fine-tuned second video output parameters and the corresponding multiple sets of fine-tuned first video output parameters, a correction analysis is performed to obtain the corrected second video output parameters. This correction analysis includes: The multiple sets of finely tuned second video output parameters and the multiple sets of finely tuned corresponding first video output parameters are associated and grouped one-to-one according to time nodes to obtain multiple sets of video experimental parameters. The multiple sets of video experimental parameters are grouped in pairs according to the time node sequence to obtain multiple video experimental parameter groups; The multiple video experiment parameter groups are respectively input into a preset correction algorithm for calculation to obtain the first video parameter coefficient and the second video parameter coefficient corresponding to each video experiment parameter group. The preset correction algorithm includes y=ax+b, where y is the first video output parameter, x is the second video output parameter, a is the first video parameter coefficient, and b is the second video parameter coefficient. The target 3D video is updated with visual parameters based on the corrected second video output parameters to obtain the updated target 3D video.

2. The 3D video vision training method according to claim 1, characterized in that, The step of testing and updating the basic vision information based on the 3D video to obtain real-time vision information further includes: The visual feedback from the left eye and the visual feedback from the right eye were obtained based on the visual test. Based on preset visual acuity standards, visual acuity is evaluated for the left-eye feedback visual and the right-eye feedback visual respectively to obtain the user's left-eye visual acuity and the user's right-eye visual acuity. The basic vision information is updated based on the user's left eye vision and right eye vision to obtain real-time vision information.

3. The 3D video vision training method according to claim 1, characterized in that, The step of determining whether the user is an initial user based on the user training information includes: If the user training information is not the initial user, then historical vision information and 3D video are obtained, and the user's current vision is deduced based on the historical vision information to obtain the current vision information; The video output parameters that match the current vision information are determined, and the output parameters of the 3D video are adjusted based on the video output parameters to obtain a target 3D video that matches the user's 3D viewing experience.

4. A 3D video vision training method according to any one of claims 1-3, characterized in that, The step of fine-tuning the second video output parameters according to a preset specification based on the parameter difference relationship of the same type between the first video output parameters and the second video output parameters, to obtain multiple sets of fine-tuned second video output parameters and multiple sets of corresponding fine-tuned first video output parameters, includes: Obtain fine-tuning specification standards, wherein the fine-tuning specification standards are the relationship between the differences of different parameters between the second video output parameters and the first video output parameters, the number of adjustments, and the corresponding standards of the adjustment parameter specifications; By matching the parameter difference relationship with the difference relationship in the fine-tuning specification standard, the target number of adjustments and the target adjustment specification are obtained. The second video output parameters are adjusted multiple times according to the target adjustment number and target adjustment specification, and the first video output parameters are recorded in real time after each adjustment of the second video output parameters is completed. The second video output parameters and the second video output parameters after each adjustment are integrated to obtain multiple sets of fine-tuned second video output parameters; The first video output parameters and the first video output parameters after each adjustment of the second video output parameters are integrated to obtain multiple sets of fine-tuned first video output parameters.

5. A 3D video vision training method according to any one of claims 1-3, characterized in that, The multiple sets of video experimental parameters are grouped in pairs according to the time node sequence to obtain multiple video experimental parameter groups; Each video experiment parameter group contains two sets of video experiment parameters with adjacent time nodes; the second video output parameters are corrected based on the first video parameter coefficient, the second video parameter coefficient, and the video experiment parameter group to obtain the corrected second video output parameters.

6. The 3D video vision training method according to claim 5, characterized in that, The step of correcting the second video output parameters based on the first video parameter coefficients, the second video parameter coefficients, and the video experimental parameter set to obtain the corrected second video output parameters includes: The first video output parameter and the second video output parameter in the video experiment parameter group are calculated according to the parameter type to obtain the first parameter difference and the second parameter difference corresponding to each group of video experiment parameters in the video experiment parameter group; Determine whether there is at least one difference between the first parameter difference and the second parameter difference that does not conform to the preset difference range. If so, remove the video experiment parameter group and the first video parameter coefficient and the second video parameter coefficient corresponding to the video experiment parameter group to obtain the filter experiment parameters. Calculate the mean value of the first video parameter coefficient and the mean value of the second video parameter coefficient in the filtering experiment parameters to obtain the first target coefficient and the second target coefficient; The second video output parameters, the first target coefficient, and the second target coefficient are input into a preset correction algorithm for calculation to obtain the corrected second video output parameters.

7. A 3D video vision training system, characterized in that, Based on the method of any one of claims 1-6, comprising: The information acquisition module is used to acquire the user's training information when it detects that the user is wearing 3D glasses; The test update module is used to determine whether the user is an initial user based on the user training information. If so, it collects the user's basic vision information and 3D video, and performs test update on the basic vision information based on the 3D video to obtain real-time vision information. The parameter optimization module is used to perform the steps of parameter anomaly recording, fine-tuning, correction analysis and visual parameter updating in claim 1. The parameter adjustment module is used to determine the video output parameters that conform to the real-time vision information for viewing, and adjust the output parameters of the 3D video based on the video output parameters to obtain the target 3D video that conforms to the user's 3D viewing.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application being configured to: perform a 3D video vision training method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, include: The computer program is stored and can be loaded by a processor and executed as described in any one of claims 1-6.

Images