Parameter control methods, systems, equipment and media for immersive naked-eye 3D imaging

Abstract

This application relates to a parameter control method, system, device, and medium for immersive naked-eye 3D imaging, belonging to the technical field of naked-eye 3D imaging devices. The method includes: generating an initial parameter set for 3D imaging based on the inherent parameters of the screen; collecting current ambient light, calculating the average distance and main viewing angle of the viewer from the screen, and combining the ambient light, average distance, and main viewing angle into an environmental data vector; searching a historical environmental data vector that matches the environmental data vector from a historical database; if found, retrieving the historical optimal parameter set associated with the found historical environmental data vector as the current optimal parameter set; if not found, comprehensively analyzing the initial parameter set and the environmental data vector to generate the current optimal parameter set; and sending the current optimal parameter set to the display driver circuit of the screen to update the screen output. This application has the beneficial effects of improving 3D display effects and increasing parameter adjustment efficiency.

Description

Technical Field

[0001] This application relates to the technical field of naked-eye 3D imaging devices, and in particular to a parameter control method, system, device and medium for immersive naked-eye 3D imaging. Background Technology

[0002] With the continuous advancement of technology, naked-eye 3D technology has been widely applied in various fields, such as museum exhibitions, advertising media, commercial displays, education and training, and medical imaging. In museum exhibitions, 3D holographic display cases and other equipment can vividly display precious or inconveniently displayed cultural relics to visitors.

[0003] Existing glasses-free 3D display devices are typically installed and debugged manually, adjusting each parameter one by one. This relies on the experience of technicians and multiple trials to achieve the desired display effect. However, manual debugging is time-consuming, inefficient, and due to human factors, the results are unstable, making it difficult to guarantee optimal 3D display performance on every attempt. Summary of the Invention

[0004] To improve the 3D display effect and increase the efficiency of parameter adjustment, this application provides a parameter control method, system, device and medium for immersive naked-eye 3D imaging.

[0005] In a first aspect, this application provides a parameter control method for immersive naked-eye 3D imaging, employing the following technical solution: A method for parameter control in immersive naked-eye 3D imaging includes: Based on the inherent parameters of the screen itself, an initial set of parameters for 3D imaging is generated; The system collects the current ambient light, calculates the current average distance of the audience from the screen and the current main viewing angle, and integrates the current ambient light, current average distance and current main viewing angle into an environmental data vector; Search the historical database for historical environmental data vectors that match the environmental data vector; If found, the set of historical optimal parameters associated with the found historical environmental data vector is retrieved as the current set of optimal parameters; If not found, the initial parameter set and the environmental data vector are comprehensively analyzed to generate the current optimal parameter set; The current optimal parameter set is sent to the display driver circuit of the screen to update the screen output.

[0006] By adopting the above technical solution, an initial parameter set for 3D imaging is first generated based on the inherent parameters of the screen itself, ensuring that the imaging parameters are compatible with the screen's characteristics and guaranteeing basic imaging quality. Next, by collecting current ambient light, calculating the average distance between the viewer and the screen, and the main viewing angle, an environmental data vector is formed, comprehensively considering environmental factors affecting the viewing experience. Since the intensity of ambient light, the distance between the viewer and the screen, and the viewing angle all significantly affect the naked-eye 3D imaging effect, this method can quantitatively analyze these factors. If a matching historical environmental data vector can be found in the historical database, the associated historical optimal parameter set is directly retrieved as the current optimal parameter set, avoiding repetitive and complex calculations, saving time and computing resources, and quickly providing the viewer with the best imaging parameters. When no matching historical environmental data vector is found, the initial parameter set and the environmental data vector are comprehensively analyzed to generate the current optimal parameter set, ensuring that suitable parameters are generated under various environmental conditions, achieving optimal imaging results. Finally, the current optimal parameter set is sent to the screen's display driver circuit to update the screen output, realizing real-time dynamic parameter adjustment. This means that the screen can adjust the imaging parameters in a timely manner according to changes in the environment and the viewer's position, providing the viewer with a consistently high-quality naked-eye 3D viewing experience, effectively improving the quality and stability of immersive naked-eye 3D imaging, and enhancing the viewer's visual enjoyment.

[0007] Optionally, the step of generating an initial set of parameters for 3D imaging based on the inherent parameters of the screen itself includes: Calculate the pixel density based on the screen resolution and screen physical size; Calculate the initial parallax grating based on typical values ​​of screen viewing angle and viewing distance, and calculate the initial pixel offset based on the initial parallax grating and the pixel density; Calculate the preset brightness and preset contrast based on the screen's allowed brightness and contrast range. Integrate preset brightness, preset contrast, initial pixel offset, and initial parallax grating to generate an initial parameter set.

[0008] Optionally, the step of comprehensively analyzing the initial parameter set and the environmental data vector to generate the current optimal parameter set includes: The average value of the audience's physiological parameters is obtained, and the estimated retinal illuminance is calculated based on the average value and the environmental data vector. Determine the optimal retinal illumination based on the average age of the audience; The visual load index is calculated based on the estimated retinal illuminance and the optimal retinal illuminance. Based on the visual load index and the initial parameter set, the current optimal parameter set is generated.

[0009] By adopting the above technical solution, firstly, by acquiring the average physiological parameters of the audience and combining them with environmental data vectors to calculate the estimated retinal illuminance, the audience's physiological characteristics can be accurately combined with the actual environmental factors. The audience's physiological parameters, such as pupil size and eye sensitivity to light, affect the actual light intensity received by the retina, while the environmental data vector, containing information such as ambient light, the average distance between the audience and the screen, and the main viewing angle, also has a significant impact on retinal illuminance. Through this comprehensive consideration, the actual light exposure experienced by the audience's retina can be more accurately assessed. By comparing the estimated retinal illuminance with the optimal retinal illuminance, the eye load experienced by the audience when viewing 3D images in the current environment can be quantified. The visual load index can intuitively reflect the degree of eye fatigue and visual stress, providing a clear quantitative indicator for adjusting imaging parameters. Finally, by generating the current optimal parameter set based on the visual load index and the initial parameter set, precise adjustment of the naked-eye 3D imaging parameters can be achieved. Based on the visual load index, the initial parameter set is optimized and adjusted so that the 3D images output to the screen meet the audience's visual needs while minimizing eye strain. It can not only enhance the viewing experience and reduce visual fatigue and discomfort, but also protect the viewers' vision health to a certain extent, providing viewers with a higher quality, more comfortable and healthier immersive naked-eye 3D viewing experience.

[0010] Optionally, the step of generating the current optimal parameter set based on the visual load index and the initial parameter set includes: The visual load index, the initial parameter set, and the preset definition of game participants are used as the input basis for the iterative process. Initiate the virtual game iteration process, and guide each participant to propose parameter adjustment suggestions based on the visual load index; The iteration rounds are executed, in which player 1 proposes brightness and contrast values, player 2 proposes parallax pitch and offset values, and player 3 proposes refresh rate values; For each proposal, the payoff function for each player is calculated to evaluate the optimization effect of the parameters on visual load; Monitor changes in returns, iterate repeatedly until the parameters converge to the Nash equilibrium point, and output the set of optimized parameters.

[0011] By employing the above technical solution, different players are responsible for proposing different types of parameters, such as brightness and contrast values, parallax and offset values, and refresh rate values. This ensures that each key imaging parameter receives dedicated attention and optimization. During the iteration process, the benefit function for each player is calculated for each proposal to evaluate the optimization effect of the parameters on visual load. This allows for precise measurement of the impact of each parameter adjustment, avoiding the adverse consequences that may result from blindly adjusting parameters. Ultimately, this ensures that the final parameter set minimizes the viewer's visual load and enhances the viewing experience.

[0012] Optionally, the steps following the output of the optimized parameter set include: The degree of ghosting is calculated based on the number of ghosting pixels and the physical size of the screen; Based on the content played, obtain the average audio fright index and the average electromyographic signal of the audience; The audience comfort score is calculated based on the degree of ghosting, the average audio startle index, and the average electromyographic signal. Based on the audience comfort value, the set of optimized parameters is corrected to generate the current optimal set of parameters.

[0013] By employing the aforementioned technical solutions, ghosting can severely interfere with the viewer's visual experience, reducing image clarity and realism. The audio scare index reflects the psychological impact of the audio content on the viewer, while the average electromyographic signal objectively reflects the viewer's level of tension or excitement. Calculating a viewer comfort score by combining ghosting intensity, audio scare index, and average electromyographic signal provides a comprehensive and accurate measure of the viewer's overall experience when watching glasses-free 3D content. By calculating the viewer comfort score in real time and adjusting parameters accordingly, the system can respond promptly to these changes, ensuring optimal imaging throughout the viewing process and significantly improving viewer satisfaction.

[0014] Optionally, the parameter adjustment method further includes: Identify the current playback scene type and playback time point, and obtain recommended parameter adjustment values ​​for the next scene type by querying the template library; Calculate the predicted brightness based on the current brightness value and the brightness adjustment value; calculate the predicted pixel offset based on the current pixel offset value and the offset adjustment value. Integrate the predicted pixel offset, the predicted brightness, the current pixel offset, and the current disparity grating distance to output a set of prediction parameters; The pre-adaptive adjustment is applied to gradually transition the parameters to the predicted parameter set n milliseconds in advance.

[0015] By adopting the above technical solution, and by identifying the current playback scene type and time point and querying the template library to obtain recommended parameter adjustment values ​​for the next scene, the naked-eye 3D imaging system can accurately adapt to different playback scenes. The system anticipates the parameter adjustment direction for the next scene, avoiding sudden changes in imaging effects during scene transitions. By gradually transitioning parameters to the predicted parameter set n milliseconds in advance, the imaging parameters smoothly transition during scene changes, effectively avoiding abrupt changes in the image and providing viewers with a smooth and natural viewing experience, reducing visual impact and discomfort.

[0016] Optionally, the parameter adjustment method further includes: Collect audience satisfaction feedback data, and perform correlation analysis between the feedback data and the corresponding environmental data vector and the current optimal parameter set to construct a feedback-parameter influence model and identify the sensitive weights of key parameters on audience satisfaction. Based on the aforementioned sensitive weights, the association rules between the historical environmental data vectors and the historical optimal parameter sets stored in the historical database are dynamically updated to optimize parameter matching accuracy, and the initial parameter sets generated subsequently are adjusted according to the aforementioned sensitive weights. The feedback-parameter influence model is periodically trained using newly collected feedback data and updated association rules.

[0017] By adopting the above technical solutions, the system can gain a deeper understanding of viewers' preferences and needs for different imaging parameters, and identify which parameter adjustments have the greatest impact on viewer satisfaction. As viewer needs and the environment change, the original association rules may no longer be applicable. By updating the association rules in real time, the system can more accurately retrieve the historically optimal parameter set associated with matching historical environmental data vectors, improving parameter matching accuracy. The system adjusts the subsequently generated initial parameter set based on sensitive weights, making the initial parameters closer to the optimal solution. The choice of initial parameters during parameter adjustment affects the efficiency and effectiveness of the entire adjustment process. If the initial parameters better meet viewer satisfaction needs, then subsequent parameter adjustments can converge to the optimal parameter set more quickly, reducing the number of iterations and improving the efficiency of parameter adjustment. Viewer needs and preferences change with time, environment, and content. Through continuous iterative training, the model can continuously learn and adapt to these changes, adjusting the sensitive weights of key parameters in a timely manner to provide viewers with a long-term, stable, and high-quality viewing experience.

[0018] Secondly, this application provides a parameter control system for immersive naked-eye 3D imaging, which adopts the following technical solution: A parameter control system for immersive naked-eye 3D imaging, comprising: The parameter generation module is used to generate an initial set of parameters for 3D imaging based on the inherent parameters of the screen itself. The parameter acquisition module is used to acquire the current ambient light, calculate the current average distance between the audience and the screen and the current main viewing angle, and integrate the current ambient light, current average distance and current main viewing angle into an environmental data vector; The parameter matching module is used to search for historical environmental data vectors that match the environmental data vectors in the historical database. If a match is found, the historical optimal parameter set associated with the found historical environmental data vector is retrieved as the current optimal parameter set. The parameter analysis module is used to perform a comprehensive analysis of the initial parameter set and the environmental data vector when no parameter is found, and to generate the current optimal parameter set. The screen adjustment module is used to send the current optimal parameter set to the display driver circuit of the screen to update the screen output.

[0019] Thirdly, this application provides a computer device that adopts the following technical solution: A computer device includes a memory, a processor, and a computer program stored in the memory, the processor executing the computer program to implement the parameter control method for immersive naked-eye 3D imaging as described in the first aspect.

[0020] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium storing a computer program capable of being loaded by a processor and executing a parameter control method for immersive naked-eye 3D imaging as described in the first aspect.

[0021] In summary, this application includes at least one of the following beneficial technical effects: First, an initial parameter set for 3D imaging is generated based on the inherent parameters of the screen itself, ensuring that the imaging parameters are compatible with the screen's characteristics and guaranteeing basic imaging quality. Next, by collecting current ambient light, calculating the average distance between the viewer and the screen, and the main viewing angle, an environmental data vector is constructed, comprehensively considering environmental factors affecting the viewing experience. Since the intensity of ambient light, the distance between the viewer and the screen, and the viewing angle all significantly affect the naked-eye 3D imaging effect, this method can quantitatively analyze these factors. If a matching historical environmental data vector can be found in the historical database, the associated historical optimal parameter set is directly retrieved as the current optimal parameter set, avoiding repetitive and complex calculations, saving time and computing resources, and quickly providing the viewer with the best imaging parameters. When no matching historical environmental data vector is found, the initial parameter set and the environmental data vector are comprehensively analyzed to generate the current optimal parameter set, ensuring that suitable parameters are generated under various environmental conditions, achieving optimal imaging results. Finally, the current optimal parameter set is sent to the screen's display driver circuit to update the screen output, realizing real-time dynamic parameter adjustment. This means the screen can adjust imaging parameters in real time according to changes in the environment and the viewer's position, providing a consistently high-quality naked-eye 3D viewing experience. This effectively improves the quality and stability of immersive naked-eye 3D imaging, enhancing the viewer's visual enjoyment. Attached Figure Description

[0022] Figure 1 This is a first flowchart of an embodiment of the method of this application; Figure 2 This is a second flowchart of an embodiment of the method of this application; Figure 3 This is a third flowchart of an embodiment of the method of this application; Figure 4 This is the fourth flowchart of an embodiment of the method of this application; Figure 5 This is the fifth flowchart of an embodiment of the method of this application; Figure 6 This is the sixth flowchart of an embodiment of the method of this application; Figure 7 This is the seventh flowchart of an embodiment of the method of this application. Detailed Implementation

[0023] To make the purpose, technical solution, and advantages of this application clearer, the following description is provided in conjunction with the appendix. Figure 1-7 The present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the application.

[0024] The first embodiment of this application discloses a parameter control method for immersive naked-eye 3D imaging. (Refer to...) Figure 1 The parameter control method includes S110-S160: S110 generates an initial set of parameters for 3D imaging based on the inherent parameters of the screen itself; S120 collects the current ambient light, calculates the current average distance of the audience from the screen and the current main viewpoint, and integrates the current ambient light, current average distance and current main viewpoint into an environmental data vector; S130, Search the historical database for historical environmental data vectors that match the environmental data vectors; S140, If found, retrieve the historical optimal parameter set associated with the found historical environment data vector as the current optimal parameter set; S150, if not found, perform a comprehensive analysis of the initial parameter set and the environmental data vector to generate the current optimal parameter set; S160 sends the current optimal parameter set to the display driver circuit of the screen to update the screen output.

[0025] Reference Figure 2 S110, the step of generating an initial set of parameters for 3D imaging based on the inherent parameters of the screen itself includes S210-S240: S210 calculates pixel density based on screen resolution and screen physical size; S220 calculates the initial parallax grating based on the typical values ​​of the screen's viewing angle and viewing distance, and calculates the initial pixel offset based on the initial parallax grating and pixel density; S230 calculates the preset brightness and preset contrast based on the screen's allowed brightness and contrast range, respectively. S240 integrates preset brightness, preset contrast, initial pixel offset, and initial parallax grating to generate an initial parameter set.

[0026] Specifically, the screen resolution and physical dimensions are obtained by calling the device API, and then calculated according to the formula. (Unit: pixels / meter) Calculate pixel density and resolution. This refers to the number of pixels in the horizontal and vertical directions of the screen. The screen's physical dimensions (width x height). Initial parallax pitch. (Unit: meters) This indicates a typical viewing distance, specified according to the screen model. Indicates the screen's viewing angle. Initializes pixel offset. (Unit: pixels), where k is an empirical coefficient (usually 0.1~0.3). Preset brightness. (Unit: cd / m²), Contrast Ratio The allowed brightness range of the screen device Contrast range Initial parameter set .

[0027] The system utilizes built-in sensors to collect environmental data: a light sensor acquires the current ambient light level (in lux), a ToF (Time of Flight) camera measures the average distance between the viewer and the screen (in meters), and the front-facing camera uses a facial recognition algorithm to determine the primary viewing angle (such as the horizontal offset angle). This data is then combined into an environmental data vector. The ambient light level is represented by d, and the average distance is represented by d. Indicates the main perspective.

[0028] By querying historical records from SQLite or MongoDB databases, and using a cosine similarity algorithm to match the environmental data vectors, the closest historical entries are found. If a match is found, the associated historical best parameter set is directly read as the current best parameter set.

[0029] Reference Figure 3 In S150, the steps of comprehensively analyzing the initial parameter set and environmental data vector to generate the current optimal parameter set include S310-S340: S310: Obtain the average value of the audience's physiological parameters, and calculate the estimated retinal illuminance based on the average value and the environmental data vector; S320 determines the optimal retinal illumination based on the average age of the audience; S330 calculates the visual load index based on the estimated retinal illuminance and the optimal retinal illuminance; S340 generates the current optimal parameter set based on the visual load index and the initial parameter set.

[0030] Specifically, if a match is not found, average values ​​of the audience's physiological parameters are collected using microphones or wearable devices distributed to the audience in advance. These values ​​include average electromyographic signals (in microvolts) and the capture audio startle index (an average calculated based on decibel fluctuations). Retinal illuminance estimation. This represents the average focal length of the human eye, estimated through pupil tracking.

[0031] Based on the registered ages of the audience, the average age is calculated, and then a predefined table (age-illuminance mapping) is consulted to determine the optimal retinal illuminance. Visual load index. For binocular parallax angle, For optimal retinal illumination, and These are the weighting coefficients.

[0032] Reference Figure 4 The steps for generating the current optimal parameter set based on the visual load index and the initial parameter set include S410-S450: S410 uses the visual load index, the initial parameter set, and the predefined game participants as the input basis for the iterative process. S420, initiate the virtual game iteration process, and guide each participant to propose parameter adjustment suggestions based on the visual load index; S430, executes iteration rounds, in which player 1 proposes brightness and contrast values, player 2 proposes parallax pitch and offset values, and player 3 proposes refresh rate values; S440 calculates the payoff function for each player for each proposal to evaluate the optimization effect of the parameters on visual load; S450 monitors changes in returns, iterates repeatedly until the parameters converge to the Nash equilibrium point, and outputs the set of optimized parameters.

[0033] Specifically, the visual load index, initial parameter set, and predefined game participant definitions (Player 1 as the brightness / contrast agent, Player 2 as the parallax pitch / offset agent, and Player 3 as the refresh rate agent) are input into the iterative process. A virtual game iteration is initiated, using multi-threading to simulate each participant: Player 1 proposes brightness values ​​(±10%) and contrast values ​​(±5%) based on random perturbations; Player 2 proposes parallax pitch values ​​(±5mm) and offset values ​​(±2 pixels); and Player 3 proposes refresh rate values ​​(e.g., 60Hz or 120Hz). Iteration rounds are executed, and the optimization effect of each proposal is evaluated using a payoff function (e.g., payoff = 1 / (change in visual load index + proposal cost)). Payoff changes are monitored, and convergence to the Nash equilibrium point is determined when the standard deviation of payoffs is less than a threshold (e.g., 0.01) for three consecutive rounds, and the optimized parameter set is output.

[0034] Reference Figure 5 The steps following the output of the optimized parameter set include S510-S540: The S510 calculates the degree of ghosting based on the number of ghosting pixels and the physical size of the screen. S520, based on the content played, obtains the average audio fright index and the average electromyographic signal of the audience; S530 calculates the audience comfort score based on the degree of ghosting, the average value of the audio fright index, and the average value of electromyographic signals. S540 adjusts the set of optimized parameters based on the audience comfort value to generate the current optimal set of parameters.

[0035] Specifically, the number of ghosting pixels captured by the camera is used to calculate the degree of ghosting. (Dimensionless, 0~1); The audience comfort score is calculated using the weighted formula: audience comfort score = w1 × ghosting intensity + w2 × fright index + w3 × electromyographic signal (weights are set based on experience), with a score of 0-100. Based on the comfort score (e.g., below 60), the optimized parameter set is fine-tuned (e.g., brightness increased by 5%, offset decreased proportionally), generating the current optimal parameter set. This parameter set is then sent to the screen display driver circuit via I2C or SPI interface to update the output.

[0036] Reference Figure 6 The parameter control methods also include S610-S640: S610 identifies the current playback scene type and playback time point, and obtains the recommended parameter adjustment values ​​for the next scene type by querying the template library; S620 calculates the predicted brightness based on the current brightness value and the brightness adjustment value, and calculates the predicted pixel offset based on the current pixel offset value and the offset adjustment value; S630 integrates predicted pixel offset, predicted brightness, current pixel offset, and current disparity grating, and outputs a set of prediction parameters; S640 applies pre-adaptive adjustment, transitioning parameters to the prediction parameter set in advance by n milliseconds through a gradual approach.

[0037] Specifically, a pre-trained CNN model (such as ResNet) is used to analyze video frames, identify the current playback scene type (such as action or static) and time point, and then query a template library (storing scene-parameter mappings) to obtain recommended adjustment values ​​(such as brightness +10% for action scenes). Based on the current brightness value (such as 300 nits) and the recommended adjustment value (+10%), the predicted brightness is calculated as: predicted brightness = current value × (1 + adjustment ratio); similarly, based on the current pixel offset and the adjustment value, the predicted pixel offset is calculated as: predicted pixel offset = (1 + adjustment ratio). These values, along with the current disparity raster distance and the current pixel offset, are integrated to output a set of predicted parameters. Pre-adaptive adjustment is applied, using a linear interpolation algorithm to gradually change the parameters to the predicted values ​​within n milliseconds (such as 50 ms) to avoid abrupt changes in the image.

[0038] Reference Figure 7 The parameter control methods also include S710-S730: S710 collects feedback data on audience satisfaction and performs correlation analysis with the corresponding environmental data vector and the current optimal parameter set to construct a feedback-parameter influence model and identify the sensitive weights of key parameters on audience satisfaction. S720, based on sensitive weights, dynamically updates the association rules between historical environmental data vectors and historical optimal parameter sets stored in the historical database, optimizes parameter matching accuracy, and adjusts the initial parameter set generated subsequently according to sensitive weights; S730 periodically uses newly collected feedback data and updated association rules to iteratively train the feedback-parameter influence model.

[0039] Specifically, audience satisfaction feedback (e.g., 1-5 star ratings) can be collected via an app. This feedback data, along with corresponding environmental data vectors and the current optimal parameter set, is stored synchronously. Next, a random forest regression model is built using Python's scikit-learn library to perform association analysis on the data. During training, the model takes the environmental vector and parameter set as features and outputs the satisfaction rating as the target variable. Key parameters are identified through feature importance analysis (e.g., ambient light has a high sensitivity weight of 0.8 on satisfaction), thus constructing a feedback-parameter influence model. Based on these sensitivity weights (e.g., brightness weight of 0.6), historical database association rules are updated (e.g., similarity thresholds are adjusted), and the initial parameter set calculation is optimized (e.g., parameters with high weights are weighted in S110). The system triggers a batch processing task weekly or monthly, using newly collected audience satisfaction feedback data and updated association rules in S720 as input to incrementally train the feedback-parameter influence model (using online learning techniques such as the partial_fit method of random forests). This continuously corrects model biases and improves prediction robustness. The entire process is monitored through logs and alerts to ensure data freshness and continuous improvement in model performance.

[0040] Based on the above method embodiments, the second embodiment of this application discloses a parameter control system for immersive naked-eye 3D imaging. The parameter control system for immersive naked-eye 3D imaging of this embodiment can implement any of the above-described parameter control methods for immersive naked-eye 3D imaging, and the specific working process of each module in the parameter control system for immersive naked-eye 3D imaging can be referred to the corresponding process in the above method embodiments.

[0041] For ease of understanding, an example is given below: A parameter control system for immersive naked-eye 3D imaging includes: The parameter generation module is used to generate an initial set of parameters for 3D imaging based on the inherent parameters of the screen itself. The parameter acquisition module is used to collect the current ambient light, calculate the current average distance of the audience from the screen and the current main viewing angle, and integrate the current ambient light, current average distance and current main viewing angle into an environmental data vector; The parameter matching module is used to search for historical environmental data vectors that match the environmental data vectors in the historical database. If a match is found, the module retrieves the historical optimal parameter set associated with the found historical environmental data vector as the current optimal parameter set. The parameter analysis module is used to perform a comprehensive analysis of the initial parameter set and environmental data vector when no parameter is found, and to generate the current optimal parameter set. The screen adjustment module is used to send the current optimal parameter set to the display driver circuit of the screen to update the screen output.

[0042] The third embodiment of this application provides a computer device, which may include a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement a parameter control method for immersive naked-eye 3D imaging.

[0043] The memory can communicate with the processor via a communication bus, which can be an address bus, a data bus, a control bus, etc.

[0044] Additionally, the memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device.

[0045] Furthermore, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0046] The fourth embodiment of this application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as a parameter control method for immersive naked-eye 3D imaging.

[0047] The computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device; the program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0048] It should be noted that the computer device and storage medium in the embodiments of this application are respectively electronic devices and storage media that apply the above-described parameter control method for immersive naked-eye 3D imaging. Therefore, all embodiments of the above-described parameter control method for immersive naked-eye 3D imaging are applicable to the computer device and storage medium, and can achieve the same or similar beneficial effects. For the computer device / storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple; relevant details can be found in the descriptions of the method embodiments.

[0049] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce a good effect.

[0050] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is only one example of a series of equivalent or similar features.

Claims

1. A method for parameter control in immersive naked-eye 3D imaging, characterized in that, include: Based on the inherent parameters of the screen itself, an initial set of parameters for 3D imaging is generated; The system collects the current ambient light, calculates the current average distance of the audience from the screen and the current main viewing angle, and integrates the current ambient light, current average distance and current main viewing angle into an environmental data vector; Search the historical database for historical environmental data vectors that match the environmental data vector; If found, the set of historical optimal parameters associated with the found historical environmental data vector is retrieved as the current set of optimal parameters; If not found, the initial parameter set and the environmental data vector are comprehensively analyzed to generate the current optimal parameter set; The current optimal parameter set is sent to the display driver circuit of the screen to update the screen output.

2. The parameter control method for immersive naked-eye 3D imaging according to claim 1, characterized in that, The steps for generating an initial set of parameters for 3D imaging based on the inherent parameters of the screen itself include: Calculate the pixel density based on the screen resolution and screen physical size; Calculate the initial parallax grating based on typical values ​​of screen viewing angle and viewing distance, and calculate the initial pixel offset based on the initial parallax grating and the pixel density; Calculate the preset brightness and preset contrast based on the screen's allowed brightness and contrast range. Integrate preset brightness, preset contrast, initial pixel offset, and initial parallax grating to generate an initial parameter set.

3. The parameter control method for immersive naked-eye 3D imaging according to claim 1, characterized in that, The steps for generating the current optimal parameter set by comprehensively analyzing the initial parameter set and the environmental data vector include: The average value of the audience's physiological parameters is obtained, and the estimated retinal illuminance is calculated based on the average value and the environmental data vector. Determine the optimal retinal illumination based on the average age of the audience; The visual load index is calculated based on the estimated retinal illuminance and the optimal retinal illuminance. Based on the visual load index and the initial parameter set, the current optimal parameter set is generated.

4. The parameter control method for immersive naked-eye 3D imaging according to claim 3, characterized in that, The steps for generating the current optimal parameter set based on the visual load index and the initial parameter set include: The visual load index, the initial parameter set, and the preset definition of game participants are used as the input basis for the iterative process. Initiate the virtual game iteration process, and guide each participant to propose parameter adjustment suggestions based on the visual load index; The iteration rounds are executed, in which player 1 proposes brightness and contrast values, player 2 proposes parallax pitch and offset values, and player 3 proposes refresh rate values; For each proposal, the payoff function for each player is calculated to evaluate the optimization effect of the parameters on visual load; Monitor changes in returns, iterate repeatedly until the parameters converge to the Nash equilibrium point, and output the set of optimized parameters.

5. The parameter control method for immersive naked-eye 3D imaging according to claim 4, characterized in that, The steps following outputting the optimized parameter set include: The degree of ghosting is calculated based on the number of ghosting pixels and the physical size of the screen; Based on the content played, obtain the average audio fright index and the average electromyographic signal of the audience; The audience comfort score is calculated based on the degree of ghosting, the average audio startle index, and the average electromyographic signal. Based on the audience comfort value, the set of optimized parameters is corrected to generate the current optimal set of parameters.

6. The parameter control method for immersive naked-eye 3D imaging according to claim 1, characterized in that, The parameter control method further includes: Identify the current playback scene type and playback time point, and obtain recommended parameter adjustment values ​​for the next scene type by querying the template library; Calculate the predicted brightness based on the current brightness value and the brightness adjustment value; calculate the predicted pixel offset based on the current pixel offset value and the offset adjustment value. Integrate the predicted pixel offset, the predicted brightness, the current pixel offset, and the current disparity grating distance to output a set of prediction parameters; The pre-adaptive adjustment is applied to gradually transition the parameters to the predicted parameter set n milliseconds in advance.

7. The parameter control method for immersive naked-eye 3D imaging according to claim 1, characterized in that, The parameter control method further includes: Collect audience satisfaction feedback data, and perform correlation analysis between the feedback data and the corresponding environmental data vector and the current optimal parameter set to construct a feedback-parameter influence model and identify the sensitive weights of key parameters on audience satisfaction. Based on the aforementioned sensitive weights, the association rules between the historical environmental data vectors and the historical optimal parameter sets stored in the historical database are dynamically updated to optimize parameter matching accuracy, and the initial parameter sets generated subsequently are adjusted according to the aforementioned sensitive weights. The feedback-parameter influence model is periodically trained using newly collected feedback data and updated association rules.

8. A parameter control system for immersive naked-eye 3D imaging, characterized in that, Performing the parameter control method for immersive naked-eye 3D imaging as described in any one of claims 1 to 7, comprising: The parameter generation module is used to generate an initial set of parameters for 3D imaging based on the inherent parameters of the screen itself. The parameter acquisition module is used to acquire the current ambient light, calculate the current average distance between the audience and the screen and the current main viewing angle, and integrate the current ambient light, current average distance and current main viewing angle into an environmental data vector; The parameter matching module is used to search for historical environmental data vectors that match the environmental data vectors in the historical database. If a match is found, the historical optimal parameter set associated with the found historical environmental data vector is retrieved as the current optimal parameter set. The parameter analysis module is used to perform a comprehensive analysis of the initial parameter set and the environmental data vector when no parameter is found, and to generate the current optimal parameter set. The screen adjustment module is used to send the current optimal parameter set to the display driver circuit of the screen to update the screen output.

9. A computer device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the parameter control method for immersive naked-eye 3D imaging as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer program stores a parameter control method for immersive naked-eye 3D imaging as described in any one of claims 1 to 7, which can be loaded by a processor and executed.

Images