Metasurface dynamic color holographic display method and system

Abstract

The invention discloses a metasurface dynamic color holographic display method and system, and relates to the technical field of photoelectric display, and the system obtains image and depth data, observation angle and attitude parameters, external illumination parameters and target display area structural feature data in a display device manufacturing process in real time; preprocessing the collected data, fusing illumination parameters to generate a multispectral phase response matrix, and forming a visual angle depth coding map through visual angle and depth joint coding; a dynamic model is trained in combination with an image sequence and environmental parameters, light field distribution prediction and coding instruction output are realized, and the reconstruction quality of a color dynamic holographic image is improved; the color fidelity, the dynamic response performance and the three-dimensional reconstruction accuracy coefficient are calculated and compared with the preset threshold values, real-time evaluation and strategy adjustment of color rendition, the dynamic performance and the three-dimensional effect in the display device manufacturing process are achieved, and the product quality and the display effect of display device manufacturing are effectively guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of photoelectric display, in particular to a metasurface dynamic color holographic display method and system. BACKGROUND

[0002] With the continuous development of information display technology, the manufacturing of metasurface holographic display devices has become an important research direction to realize high-resolution, low-power consumption, and high-integration three-dimensional visual systems. Traditional static holographic display technology is often limited by material response lag, image color distortion, poor dynamic refresh performance, and three-dimensional reconstruction distortion, making it difficult to meet the technical needs of high-quality dynamic color holographic image reconstruction in future meta-universe, naked-eye 3D display, augmented reality, and other scenarios.

[0003] Currently, in the manufacturing process of display devices, there is a lack of consideration of the fusion of multi-dimensional factors such as manufacturing process structure, display angle parameters, and environmental light, making it difficult to achieve dynamic regulation and control of holographic performance based on actual use environment. At the same time, traditional systems lack real-time monitoring capability of reconstructed image quality, and cannot intelligently optimize driving control and encoding strategy according to current reconstruction effect, resulting in energy waste and insufficient visual experience.

[0004] The development of artificial intelligence has introduced a new optimization method for holographic display. Deep learning models based on convolutional neural networks have the ability to extract multi-dimensional features and perform nonlinear fitting, enabling adaptive prediction and regulation during hologram reconstruction. However, existing AI-driven models are mostly limited to static images or simple environments, and lack the ability to handle complex manufacturing process data and multi-modal perception inputs. SUMMARY

[0005] In view of the deficiencies of the prior art, the present application provides a metasurface dynamic color holographic display method and system to solve the problems mentioned in the background art.

[0006] To achieve the above purpose, the present application realizes the following technical scheme: a metasurface dynamic color holographic display method and system, comprising: a data acquisition module, a data processing module, an AI dynamic adjustment model establishment module, a color fidelity monitoring module, a dynamic response performance monitoring module, and a three-dimensional reconstruction monitoring module; The data acquisition module is used for real-time monitoring and quality detection of the production process in the manufacturing of display devices, and the acquired data includes: image and depth data, observation angle and attitude parameters, external light parameters, and target display area structure feature data; The data processing module is used for registration, filtering, and normalization processing of the acquired RGB image and depth information, fusion of light parameters to generate a multi-spectral phase response matrix, and generation of a view angle and depth joint encoding atlas through view angle and depth joint encoding; The AI dynamic adjustment model establishing module is configured to construct an initial holographic display model based on a convolutional neural network, and train and optimize the initial model through image sequences and environmental parameters to generate a dynamic model for predicting light field distribution and encoding instructions, while extracting intermediate layer features to realize multi-dimensional optimization of spatial angle and improve the reconstruction quality of color dynamic holographic images. The color fidelity monitoring module is configured to monitor color output and structural features of a display surface in real time, calculate a color fidelity coefficient CSx based on color information of input image sequences and environmental lighting parameters, and compare the color fidelity coefficient CSx with a first threshold Q1 to determine whether the color restoration quality of the image is qualified. If the color restoration quality is not qualified, a strategy is provided. The dynamic response performance monitoring module is configured to calculate a dynamic response performance coefficient DTX based on material response data and refresh frame rate dynamic parameters, compare the dynamic response performance coefficient DTX with a second threshold Q2 to determine whether the full-dimensional dynamic performance is up to standard, and provide a strategy if the dynamic performance is not up to standard. The three-dimensional reconstruction monitoring module is configured to calculate a three-dimensional reconstruction accuracy coefficient SWZx based on multi-view depth encoding images and actual depth images, spatial structural continuity and multi-angle consistency data, compare the three-dimensional reconstruction accuracy coefficient SWZx with a third threshold Q3 to determine whether the three-dimensional reconstruction effect is up to standard, and provide a strategy if the three-dimensional reconstruction effect is not up to standard.

[0007] Preferably, the data acquisition module includes a first acquisition unit, a second acquisition unit, a third acquisition unit and a fourth acquisition unit. The first acquisition unit is configured to monitor and detect the production process in the manufacture of display devices in real time. Image and depth data are acquired by a multi-modal imaging device, including RGB image frame sequences, dense point cloud data of depth images and near-infrared structured light. The second acquisition unit is configured to acquire observation angle and attitude parameters by a visual fusion sensor array, including visual angle coordinate information, spatial vector information corresponding to observation points, visual angle step resolution and angle coverage range. The third acquisition unit is configured to acquire external lighting parameters by an environmental spectrum analysis module and a lighting sensor, including lighting incident angle, direction distribution, illumination intensity and color temperature information, and environmental spectrum distribution. The fourth acquisition unit is configured to acquire target display area structural feature data by display surface scanning, including display surface inclination angle and curvature distribution, spatial edge contour and occlusion information, and microstructure arrangement and boundary constraint parameters.

[0008] Preferably, the data processing module is used to perform spatial alignment, noise filtering and color normalization on the collected RGB images and depth information through image registration and filtering technology; to fuse the RGB images and illumination parameters through a multi-channel phase control algorithm to generate a multi-spectral phase response matrix; and to fuse multi-angle images, depth information and display structure constraints through perspective and depth joint coding technology to generate a perspective depth coding map.

[0009] Preferably, the AI ​​dynamic adjustment model establishment module is used to use a convolutional neural network to construct an initial model of the metasurface dynamic color holographic display, and train and test the model with input image sequences and environmental parameter data; the trained model is used as a dynamic prediction model, responsible for fitting and predicting the input image sequence, outputting the target light field distribution and encoding instructions, driving the dynamic holographic display, and realizing high-quality color dynamic holographic image reconstruction. At the same time, the intermediate layer feature vector of the input data is used to extract multi-dimensional information of spatial angles, further train and optimize, and run as an AI dynamic adjustment model after training to realize driving dynamic holography to achieve high-quality color dynamic holographic image reconstruction.

[0010] Preferably, the color fidelity monitoring module includes a first calculation unit and a first analysis unit; The first calculation unit is used to calculate and obtain the color fidelity coefficient CSx by real-time monitoring the color output and structural characteristics of the display surface, combining the color information of the input image sequence and the ambient lighting parameters after dimensionless processing. The formula is as follows:

[0011] Where, It represents the RGB structural similarity index, reflecting the overall similarity between the reconstructed image and the target image in the red, green, and blue channel structures. M represents the number of vertical pixels in the image, N represents the number of horizontal pixels in the image, x represents the horizontal coordinate index of the pixel, and y represents the vertical coordinate index of the pixel. Reconstructed image in The average brightness at Indicates that the target image is The average brightness at represents a constant that prevents the denominator from being zero, represents the average crosstalk, the cross interference degree of RGB signals between adjacent pixels, and w1, w2, and w3 represent weight coefficients.

[0012] Preferably, the first analysis unit is configured to preset a first threshold Q1 in advance, and compare and analyze the color fidelity coefficient CSx with the first threshold Q1, and obtaining the first evaluation result includes: When the color fidelity coefficient CSx ≥ the first threshold Q1, it means that the color reproduction quality of the image is qualified and continues to be monitored; When the color fidelity coefficient CSx is less than the first threshold Q1, it indicates that the color restoration quality of the image is unqualified, triggering the first warning instruction and generating the first strategy: optimizing the spectral reconstruction network parameters and its input features, improving the fitting ability of high-contrast color areas, combining the color reconstruction error distribution, dynamically adjusting the lighting angle and exposure parameters, reconstructing multi-angle high-fidelity sampling data, returning to the image processing module, regenerating the spectral reconstruction image based on the current input image, and updating the calculation until the color fidelity coefficient CSx is greater than or equal to the first threshold Q1.

[0013] Preferably, the dynamic response performance monitoring module includes a second calculation unit and a second analysis unit; The second calculation unit is used to calculate the dynamic response performance coefficient DTx by combining the material response data and the refresh frame rate dynamic parameters after dimensionless processing. The formula is as follows:

[0014] Where, Represents the image refresh rate, e represents the base of the natural constant, represents the thermal response adjustment factor, obtained by experiment, represents the excitation temperature difference, represents the reference temperature difference, represents the material response time, represents the voltage response coupling coefficient, obtained by experiment, represents the control voltage, represents the average power consumption, It represents the thermal stability of the material, and a1, a2 and a3 represent the weight coefficients.

[0015] Preferably, the second analysis unit is used to preset a second threshold Q2 in advance, and compare and analyze the dynamic response performance coefficient DTx with the second threshold Q2, and obtain the second evaluation result including: When the dynamic response performance coefficient DTx ≥ the second threshold Q2, it indicates that the full-dimensional dynamic performance meets the standard, there is no problem of control deviation and power consumption thermal control mismatch, and continuous monitoring is performed; When the dynamic response performance coefficient DTx is less than the second threshold Q2, it indicates that the full-dimensional dynamic performance does not meet the standard, and there are problems of control deviation and power consumption thermal control mismatch, which triggers the second warning instruction and generates the second strategy: when the dominant item response time is detected to be abnormal, switch to the local high-speed response material domain; divide the holographic image into sub-pixel control areas, and use parallel control and time interpolation reconstruction to improve the overall refresh frame rate; after applying a short-time high-frequency excitation pulse, switch to low-voltage maintenance mode to reduce control delay and thermal load; construct a map of thermally sensitive areas, automatically avoid thermal drift areas and reallocate control tasks; adjust the control drive sequence to stabilize and optimize the response performance.

[0016] Preferably, the three-dimensional reconstruction monitoring module includes a third calculation unit and a third analysis unit; The third calculation unit is used to calculate and obtain the three-dimensional reconstruction accuracy coefficient SWZx through the multi-view depth coding map and the actual depth map, combined with the spatial structure continuity and multi-angle consistency data after dimensionless processing. The formula is as follows:

[0017] Where M represents the number of vertical pixels in the image, N represents the number of horizontal pixels in the image, x represents the horizontal coordinate index of the pixel, and y represents the vertical coordinate index of the pixel. Represents the depth error, the difference between the predicted depth map and the true depth in pixels The error difference at Indicates the gradient change of the depth map in the z-axis direction, represents multi-angle consistency, s1, s2, and s3 represent weight coefficients; The third analysis unit is used to preset a third threshold Q3 in advance, and compare and analyze the three-dimensional reconstruction accuracy coefficient SWZx with the third threshold Q3 to obtain a third evaluation result including: When the 3D reconstruction accuracy coefficient SWZx ≥ the third threshold Q3, it indicates that the 3D reconstruction effect meets the standard and is continuously monitored; When the three-dimensional reconstruction accuracy coefficient SWZx is less than the third threshold Q3, it indicates that the three-dimensional reconstruction effect does not meet the standard and cannot satisfy the requirements of realistic stereoscopic expression. The third warning instruction is triggered, and the third strategy is generated: updating the multi-angle coding map, improving the joint consistency of spatial angles and stereoscopic coherence, and finally outputting the holographic image update instruction to enhance the depth level performance and improve the fidelity reconstruction capability of large parallax three-dimensional scenes.

[0018] Preferably, a metasurface dynamic color holographic display method comprises the following steps: Step 1: Through real-time monitoring and quality inspection of the production process in display device manufacturing, data is collected and acquired, including: image and depth data, observation angle and posture parameters, external lighting parameters, and target display area structural feature data; Step 2: By registering, filtering and normalizing the collected RGB image and depth information, the illumination parameters are integrated to generate a multi-spectral phase response matrix, and the perspective depth coding map is generated by jointly encoding the perspective and depth; Step 3: By building an initial holographic display model based on a convolutional neural network and optimizing it through image sequence and environmental parameter training, a dynamic model is generated to predict light field distribution and encoding instructions. At the same time, the intermediate layer features are extracted to achieve multi-dimensional optimization of spatial angles and improve the quality of color dynamic holographic image reconstruction; Step 4: By real-time monitoring of the display surface color output and structural characteristics, combined with the color information of the input image sequence and the ambient lighting parameters, the color fidelity coefficient CSx is calculated and compared with the first threshold Q1 to determine whether the image color reproduction quality is qualified. If it is unqualified, a strategy is given; Step 5: Calculate the dynamic response performance coefficient DTx by combining the material response data and the refresh frame rate dynamic parameters, and compare and analyze it with the second threshold Q2 to determine whether the full-dimensional dynamic performance meets the standard. If not, a strategy is given; Step 6: Calculate the 3D reconstruction accuracy coefficient SWZx by combining the multi-view depth coding map and the actual depth map with the spatial structure continuity and multi-angle consistency data, and compare and analyze it with the third threshold Q3 to determine whether the 3D reconstruction effect meets the standard. If not, a strategy is given.

[0019] The present invention provides a metasurface dynamic color holographic display method and system thereof, which has the following beneficial effects: (1) This metasurface dynamic color holographic display method and system, through the data acquisition module, comprehensively acquires multi-dimensional information such as image, depth, posture, illumination and structure, realizes real-time monitoring and precise detection of the display device manufacturing process, provides high-quality input for subsequent processing and model optimization, and enhances the system's perception of real scenes.

[0020] (2) This metasurface dynamic color holographic display method and system, through image registration, filtering and normalization technology, combines multi-spectral phase control and perspective-depth joint coding in the processing module to achieve adaptive processing of complex environmental illumination and structural changes, and provide accurate coding map support for dynamic holographic display.

[0021] (3) A metasurface dynamic color holographic display method and system thereof, wherein the AI ​​dynamic adjustment model establishment module constructs a dynamic prediction model based on a deep neural network, and utilizes the intermediate layer features to perform multi-dimensional optimization of spatial angles. It can still stably output high-fidelity light field reconstruction instructions under multiple environmental conditions, effectively improving the restoration effect and realism of color dynamic holographic images.

[0022] (4) A metasurface dynamic color holographic display method and system thereof, wherein the color fidelity monitoring module, the dynamic response performance monitoring module and the three-dimensional reconstruction monitoring module respectively perform real-time evaluation and feedback control from the three aspects of color restoration, response performance and stereoscopic reconstruction, ensuring that the output quality of the holographic system is stable and reliable, and can maintain excellent display performance even in high dynamic, complex lighting or multi-angle observation scenes. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a block diagram and flow chart of a metasurface dynamic color holographic display system of the present invention; Figure 2 This is a schematic diagram of the steps of a metasurface dynamic color holographic display method of the present invention. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention. Example 1: Please refer to Figure 1 , the present invention provides a metasurface dynamic color holographic display system, comprising: a data acquisition module, a data processing module, an AI dynamic adjustment model establishment module, a color fidelity monitoring module, a dynamic response performance monitoring module and a three-dimensional reconstruction monitoring module;

[0025] The data acquisition module is used for real-time monitoring and quality inspection of the production process in the display device manufacturing, and the acquired data includes: image and depth data, observation angle and posture parameters, external lighting parameters and target display area structural feature data; The data processing module is used to align, filter and normalize the collected RGB image and depth information, fuse the illumination parameters to generate a multi-spectral phase response matrix, and generate a perspective depth coding map through the joint coding of perspective and depth; The AI ​​dynamic adjustment model building module is used to build an initial holographic display model based on a convolutional neural network, and generate a dynamic model for predicting light field distribution and encoding instructions through image sequence and environmental parameter training optimization. At the same time, it extracts intermediate layer features to achieve multi-dimensional optimization of spatial angles and improve the quality of color dynamic holographic image reconstruction; The color fidelity monitoring module is used to calculate the color fidelity coefficient CSx by monitoring the color output and structural characteristics of the display surface in real time, combining the color information of the input image sequence and the ambient light parameters, and compare and analyze it with the first threshold Q1 to determine whether the color reproduction quality of the image is qualified. If it is unqualified, a strategy is given; The dynamic response performance monitoring module is used to calculate the dynamic response performance coefficient DTx by combining the material response data and the refresh frame rate dynamic parameters, and compare and analyze it with the second threshold Q2 to determine whether the full-dimensional dynamic performance meets the standard. If not, a strategy is given; The three-dimensional reconstruction monitoring module is used to calculate the three-dimensional reconstruction accuracy coefficient SWZx through the multi-view depth coding map and the actual depth map, combined with the spatial structure continuity and multi-angle consistency data, and compare and analyze it with the third threshold Q3 to determine whether the three-dimensional reconstruction effect meets the standard. If it does not meet the standard, a strategy is given.

[0026] In this embodiment, by integrating data acquisition, processing, intelligent modeling and multi-dimensional monitoring modules, closed-loop control and adaptive optimization of the entire holographic display process are achieved, which significantly improves the reconstruction quality and stability of color dynamic holographic images, ensuring high-fidelity, high-responsiveness and high-stereoscopic display effects in complex environments and multi-angle observation conditions. Example 2: This example is an explanation of Example 1. Specifically, the data acquisition module includes a first acquisition unit, a second acquisition unit, a third acquisition unit, and a fourth acquisition unit;

[0027] The first acquisition unit is used for real-time monitoring and quality inspection of the production process in the display device manufacturing; collecting image and depth data through a multimodal imaging device, including: RGB image frame sequence, depth map dense point cloud data and near-infrared structured light; The second acquisition unit is used to obtain observation angle and posture parameters through the visual fusion sensor array, including: viewing angle coordinate information, space vector information corresponding to the observation point, viewing angle step resolution and angle coverage; The third acquisition unit is used to collect external light parameters through the environmental spectrum analysis module and the light sensor, including: light incident angle, direction distribution; illumination intensity and color temperature information; environmental spectrum distribution; The fourth acquisition unit is used to acquire target display area structural feature data by scanning the display surface, including: display surface inclination and curvature distribution; spatial edge contour and occlusion information; microstructure arrangement and boundary constraint parameters.

[0028] In this embodiment, by setting up a multi-source collaborative data acquisition module, the system can comprehensively obtain multi-dimensional information such as image depth, viewing angle posture, lighting environment and display structure, providing a high-precision and high-completeness data foundation for subsequent holographic image processing and modeling, thereby significantly improving the accuracy and adaptability of dynamic color holographic display. Example 3: This example is an explanation of Example 1. Specifically, the data processing module is used to perform spatial alignment, noise filtering and color normalization on the collected RGB image and depth information through image registration and filtering technology; through a multi-channel phase control algorithm, the RGB image and illumination parameters are fused to generate a multi-spectral phase response matrix; through the perspective and depth joint coding technology, multi-angle images, depth information and display structure constraints are fused to generate a perspective depth coding map.

[0029] In this embodiment, the image and depth information are aligned, filtered and normalized through the data processing module, and the illumination and structural features are integrated to generate a multi-spectral phase response matrix and a viewing depth coding map, which effectively improves the spatial consistency and optical restoration accuracy of the holographic image, and provides reliable data support for subsequent high-quality holographic reconstruction. Example 4: This example is an explanation of Example 3. Specifically, the AI ​​dynamic adjustment model building module is used to use a convolutional neural network to construct an initial model of a metasurface dynamic color holographic display, and train and test the model with input image sequences and environmental parameter data; the trained model is used as a dynamic prediction model, responsible for fitting and predicting the input image sequence, outputting the target light field distribution and encoding instructions, driving the dynamic holographic display, and realizing high-quality color dynamic holographic image reconstruction. At the same time, the intermediate layer feature vector of the input data is used to extract multi-dimensional information of spatial angles, further train and optimize, and run as an AI dynamic adjustment model after training to realize driving dynamic holography to realize high-quality color dynamic holographic image reconstruction.

[0030] In this embodiment, the AI ​​dynamic adjustment model building module is used to build and optimize the dynamic prediction model based on the convolutional neural network, which can efficiently fit the input image sequence and environmental parameters, accurately predict the light field distribution and coding instructions, and realize real-time reconstruction of high-quality color dynamic holographic images. It also realizes multi-dimensional optimization of spatial angles through intermediate layer feature extraction, significantly improving the realism and adaptability of holographic display. Example 5: This example is an explanation of Example 4. Specifically, the color fidelity monitoring module includes a first calculation unit and a first analysis unit;

[0031] The first calculation unit is used to calculate and obtain the color fidelity coefficient CSx by real-time monitoring the color output and structural characteristics of the display surface, combining the color information of the input image sequence and the ambient lighting parameters after dimensionless processing. The formula is as follows:

[0032] Where, It represents the RGB structural similarity index, reflecting the overall similarity between the reconstructed image and the target image in the red, green, and blue channel structures. M represents the number of vertical pixels in the image, N represents the number of horizontal pixels in the image, x represents the horizontal coordinate index of the pixel, and y represents the vertical coordinate index of the pixel. Reconstructed image in The average brightness at Indicates that the target image is The average brightness at represents a constant that prevents the denominator from being zero, represents the average crosstalk, the cross interference of RGB signals between adjacent pixels, w1, w2 and w3 represent weight coefficients, , .

[0033] In this embodiment, the first calculation unit in the color fidelity monitoring module analyzes the display surface's color output and its structural characteristics in real time during dynamic display. It also combines the color information of the input image sequence with the current ambient lighting parameters to accurately calculate the color fidelity coefficient CSx after dimensionless processing. This coefficient comprehensively considers RGB structural similarity, inter-pixel crosstalk, and lighting factors, fully reflecting the accuracy of color reproduction during image reconstruction. This significantly improves color consistency and visual realism, provides optimization guidance for the color reconstruction network, enhances reconstruction accuracy in high-contrast areas, and achieves closed-loop control and automatic correction of color quality. Example 6: This example is an explanation of Example 5. Specifically, the first analysis unit is configured to preset a first threshold Q1 in advance and compare and analyze the color fidelity coefficient CSx with the first threshold Q1. Obtaining a first evaluation result includes:

[0034] When the color fidelity coefficient CSx ≥ the first threshold Q1, it means that the color reproduction quality of the image is qualified and continues to be monitored; When the color fidelity coefficient CSx is less than the first threshold Q1, it indicates that the color restoration quality of the image is unqualified, triggering the first warning instruction and generating the first strategy: optimizing the spectral reconstruction network parameters and its input features, improving the fitting ability of high-contrast color areas, combining the color reconstruction error distribution, dynamically adjusting the lighting angle and exposure parameters, reconstructing multi-angle high-fidelity sampling data, returning to the image processing module, regenerating the spectral reconstruction image based on the current input image, and updating the calculation until the color fidelity coefficient CSx is greater than or equal to the first threshold Q1.

[0035] In this embodiment, the first analysis unit performs real-time comparative analysis on the color fidelity coefficient CSx and the preset threshold Q1, thereby enabling automatic evaluation and dynamic response of the image color reproduction quality. This mechanism not only enables precise monitoring of color fidelity but also instantly triggers a first warning command and generates an optimization strategy when color reproduction quality falls short of standards, proactively intervening in the display system's adjustment process. It offers the following specific advantages: It establishes an intelligent closed-loop feedback control mechanism: The system autonomously identifies issues and triggers adjustments when color reproduction falls short of standards. This feedback control process requires no human intervention, enhancing the overall system's intelligence and stability. It also improves color adaptability in complex scenarios: By dynamically adjusting spectral reconstruction network parameters, optimizing input features, and optimizing reconstruction error distribution, the system can adapt to color distortion in scenes with high contrast, complex lighting, or non-uniform illumination, enhancing the display system's adaptability to complex real-world environments. It also improves the consistency and visual coherence of multi-angle displays: By reconstructing high-fidelity multi-angle sampling data and regenerating spectral reconstruction images, image colors are consistently reproduced across different viewing angles, significantly enhancing the user's stereoscopic viewing experience and sense of realism. It also ensures color stability over the long term: This analysis mechanism continuously operates and regularly reviews CSx values. Even with long-term operation or device aging, it maintains high image color fidelity through parameter adaptation, ensuring high-quality output levels in display device manufacturing. Example 7: This example is an explanation of Example 4. Specifically, the dynamic response performance monitoring module includes a second calculation unit and a second analysis unit;

[0036] The second calculation unit is used to calculate the dynamic response performance coefficient DTx by combining the material response data and the refresh frame rate dynamic parameters after dimensionless processing. The formula is as follows:

[0037] Where, Represents the image refresh rate, e represents the base of the natural constant, represents the thermal response adjustment factor, obtained by experiment, represents the excitation temperature difference, represents the reference temperature difference, represents the material response time, represents the voltage response coupling coefficient, obtained by experiment, represents the control voltage, represents the average power consumption, Indicates the thermal stability of the material, a1, a2 and a3 are weight coefficients, .

[0038] In this embodiment, the second calculation unit comprehensively constructs a calculation model for the dynamic response performance coefficient DTx based on multiple source parameters such as image refresh rate, material thermal response, control voltage, and power consumption, thereby enabling quantitative evaluation of the response performance of the dynamic holographic display system. This has the following specific advantages: it implements a collaborative evaluation mechanism for multiple physical factors, improves the system's sensitivity to changes in material properties and its adaptive adjustment capabilities, enhances the display system's real-time control capabilities and environmental adaptability, and provides an accurate basis for subsequent performance optimization. Example 8: This example is an explanation of Example 7. Specifically, the second analysis unit is configured to preset a second threshold value Q2 in advance, and compare and analyze the dynamic response performance coefficient DTx with the second threshold value Q2. Obtaining the second evaluation result includes:

[0039] When the dynamic response performance coefficient DTx ≥ the second threshold Q2, it indicates that the full-dimensional dynamic performance meets the standard, there is no problem of control deviation and power consumption thermal control mismatch, and continuous monitoring is performed; When the dynamic response performance coefficient DTx is less than the second threshold Q2, it indicates that the full-dimensional dynamic performance does not meet the standard, and there are problems of control deviation and power consumption thermal control mismatch, which triggers the second warning instruction and generates the second strategy: when the dominant item response time is detected to be abnormal, switch to the local high-speed response material domain; divide the holographic image into sub-pixel control areas, and use parallel control and time interpolation reconstruction to improve the overall refresh frame rate; after applying a short-time high-frequency excitation pulse, switch to low-voltage maintenance mode to reduce control delay and thermal load; construct a map of thermally sensitive areas, automatically avoid thermal drift areas and reallocate control tasks; adjust the control drive sequence to stabilize and optimize the response performance.

[0040] In this embodiment, the dynamic response performance coefficient DTx is compared with the preset threshold Q2 in real time by the second analysis unit, which can effectively judge the dynamic response stability of the holographic display system under multi-parameter coupling, and timely trigger the optimization strategy when the performance does not meet the standard. It has the following specific advantages: accurate identification and hierarchical response of full-dimensional dynamic performance anomalies: the system can determine control deviation, power consumption mismatch and thermal control bottleneck according to the comparison results of DTx and Q2, accurately locate the leading failure link, and improve the system diagnosis capability and intelligent fault tolerance level; support the rapid deployment of multi-level dynamic compensation strategies: through strategy combination response, such as material domain switching, area division parallel control, time interpolation reconstruction and other methods, the refresh frame rate and response speed are improved. Significantly improve visual defects such as image update delay, motion blur and local distortion; enhance the system's thermal control adaptability in high-load scenarios: introduce a power consumption management mechanism of high-frequency excitation + low-voltage maintenance, combined with an automatic avoidance mechanism for heat-sensitive area maps, which can effectively reduce the risk of local heat accumulation, delay material performance degradation, and ensure the stability and reliability of the system under high-frequency operation; optimize the driving sequence to improve the overall coordinated response efficiency: after detecting an imbalance in response performance, through intelligent adjustment of the control driving sequence and task allocation plan, dynamic optimization of system performance from a global scheduling perspective is achieved, ensuring high-quality output levels in display device manufacturing. Example 9: This example is an explanation of Example 4. Specifically, the three-dimensional reconstruction monitoring module includes a third calculation unit and a third analysis unit;

[0041] The third calculation unit is used to calculate and obtain the three-dimensional reconstruction accuracy coefficient SWZx through the multi-view depth coding map and the actual depth map, combined with the spatial structure continuity and multi-angle consistency data after dimensionless processing. The formula is as follows:

[0042] Where M represents the number of vertical pixels in the image, N represents the number of horizontal pixels in the image, x represents the horizontal coordinate index of the pixel, and y represents the vertical coordinate index of the pixel. Represents the depth error, the difference between the predicted depth map and the true depth in pixels The error difference at Indicates the gradient change of the depth map in the z-axis direction, represents multi-angle consistency, s1, s2 and s3 represent weight coefficients, The third analysis unit is used to preset a third threshold Q3 in advance, and compare and analyze the three-dimensional reconstruction accuracy coefficient SWZx with the third threshold Q3 to obtain a third evaluation result including: When the 3D reconstruction accuracy coefficient SWZx ≥ the third threshold Q3, it indicates that the 3D reconstruction effect meets the standard and is continuously monitored; When the three-dimensional reconstruction accuracy coefficient SWZx is less than the third threshold Q3, it indicates that the three-dimensional reconstruction effect is not up to standard and cannot meet the demand of real stereoscopic expression, triggering the third early warning instruction, generating the third strategy: updating the multi-angle encoding atlas, improving the spatial angle joint consistency and stereoscopic continuity, and finally outputting the holographic image update instruction, enhancing the depth level performance and improving the fidelity reconstruction ability of large parallax three-dimensional scene.

[0043] In this embodiment, the three-dimensional reconstruction monitoring module can effectively evaluate the three-dimensional reconstruction accuracy of the display device under multi-view and complex spatial structure conditions by calculating the three-dimensional reconstruction accuracy coefficient SWZx and comparing it with the preset third threshold Q3. The following specific advantages are possessed: improving the stereoscopic reconstruction realism and spatial continuity of the three-dimensional display device: by introducing the depth error, z-axis gradient change and multi-angle consistency index, the three-dimensional structure restoration quality of the holographic image generated by the display device under different viewing angles is comprehensively evaluated, and the spatial consistency and visual immersion of the display picture are improved from the source; enhancing the stereoscopic fidelity reconstruction ability of large parallax complex scene: when the SWZx index is lower than the threshold Q3, the system can automatically trigger the optimization mechanism, update the multi-angle encoding atlas, enhance the depth level performance, and make the holographic image more accurately present the occlusion relationship and stereoscopic details in the complex scene, especially suitable for dynamic, simulation or interactive high-end display device manufacturing scene; realizing the process-level quality monitoring of the three-dimensional reconstruction ability of the display device: this module can perform real-time quality evaluation and feedback on the depth map construction process in the display device manufacturing process, ensure that the output image has consistency and spatial structure accuracy under multi-view conditions, and reduce the occurrence of stereoscopic misplacement and reconstruction distortion problems; providing data-driven instruction basis for holographic image update: by automatically generating optimization strategy and holographic image update instruction, driving the image rendering module to continuously iterate and adjust, realizing dynamic optimization of three-dimensional reconstruction effect in the manufacturing process, and improving the overall imaging quality and user experience of the terminal display product. Embodiment 10: A metasurface dynamic color holographic display method, please refer to Figure 2 , comprising the following steps:

[0044] Step one, through real-time monitoring and quality detection of the production process in the display device manufacturing, data including image and depth data, observation angle and attitude parameter, external illumination parameter and target display area structure feature data are collected and acquired; Step two, through registration, filtering and normalization processing of the collected RGB image and depth information, multi-spectral phase response matrix is generated by fusing illumination parameters, and view depth encoding atlas is generated by joint encoding of view and depth; Step 3: By building an initial holographic display model based on a convolutional neural network and optimizing it through image sequence and environmental parameter training, a dynamic model is generated to predict light field distribution and encoding instructions. At the same time, the intermediate layer features are extracted to achieve multi-dimensional optimization of spatial angles and improve the quality of color dynamic holographic image reconstruction; Step 4: By real-time monitoring of the display surface color output and structural characteristics, combined with the color information of the input image sequence and the ambient lighting parameters, the color fidelity coefficient CSx is calculated and compared with the first threshold Q1 to determine whether the image color reproduction quality is qualified. If it is unqualified, a strategy is given; Step 5: Calculate the dynamic response performance coefficient DTx by combining the material response data and the refresh frame rate dynamic parameters, and compare and analyze it with the second threshold Q2 to determine whether the full-dimensional dynamic performance meets the standard. If not, a strategy is given; Step 6: Calculate the 3D reconstruction accuracy coefficient SWZx by combining the multi-view depth coding map and the actual depth map with the spatial structure continuity and multi-angle consistency data, and compare and analyze it with the third threshold Q3 to determine whether the 3D reconstruction effect meets the standard. If not, a strategy is given.

[0045] In this embodiment, this method achieves multi-dimensional precision quality control and dynamic optimization of the manufacturing process by systematically integrating a complete closed loop from real-time production process monitoring data acquisition, image and depth information preprocessing, dynamic holographic model construction based on convolutional neural networks, color fidelity and dynamic response performance monitoring, to 3D reconstruction effect evaluation and feedback during the display device manufacturing process. This method can effectively improve the color dynamic holographic image reconstruction quality, dynamic response speed, and 3D stereoscopic restoration effect of the display device, ensuring that the final product has high-fidelity color performance, excellent response performance, and a realistic 3D spatial sense in multiple viewing angles and lighting environments. This significantly enhances the stability of display device manufacturing and the consistency of the finished product, improving the terminal display effect and user visual experience.

[0046] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0047] The above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The coefficients in the formula are set by those skilled in the art according to actual conditions. The above is only a preferred specific implementation method of the present invention, but the protection scope of the present invention is not limited to this. Any technician familiar with this technical field, within the technical scope disclosed by the present invention, can make equivalent replacements or changes based on the technical solution and inventive concept of the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A metasurface dynamic color holographic display system, characterized in that: include: Data acquisition module, data processing module, AI dynamic adjustment model building module, color fidelity monitoring module, dynamic response performance monitoring module and 3D reconstruction monitoring module; The data acquisition module is used for real-time monitoring and quality inspection of the production process in the display device manufacturing, and the acquired data includes: image and depth data, observation angle and posture parameters, external lighting parameters and target display area structural feature data; The data processing module is used to align, filter and normalize the collected RGB image and depth information, fuse the illumination parameters to generate a multi-spectral phase response matrix, and generate a perspective depth coding map through the joint coding of perspective and depth; The AI ​​dynamic adjustment model building module is used to build an initial holographic display model based on a convolutional neural network, and generate a dynamic model for predicting light field distribution and encoding instructions through image sequence and environmental parameter training optimization. At the same time, it extracts intermediate layer features to achieve multi-dimensional optimization of spatial angles and improve the quality of color dynamic holographic image reconstruction; The color fidelity monitoring module is used to calculate the color fidelity coefficient CSx by monitoring the color output and structural characteristics of the display surface in real time, combining the color information of the input image sequence and the ambient light parameters, and compare and analyze it with the first threshold Q1 to determine whether the color reproduction quality of the image is qualified. If it is unqualified, a strategy is given; The dynamic response performance monitoring module is used to calculate the dynamic response performance coefficient DTx by combining the material response data and the refresh frame rate dynamic parameters, and compare and analyze it with the second threshold Q2 to determine whether the full-dimensional dynamic performance meets the standard. If not, a strategy is given; The three-dimensional reconstruction monitoring module is used to calculate the three-dimensional reconstruction accuracy coefficient SWZx through the multi-view depth coding map and the actual depth map, combined with the spatial structure continuity and multi-angle consistency data, and compare and analyze it with the third threshold Q3 to determine whether the three-dimensional reconstruction effect meets the standard. If it does not meet the standard, a strategy is given.

2. The metasurface dynamic color holographic display system according to claim 1, characterized in that: The data acquisition module includes a first acquisition unit, a second acquisition unit, a third acquisition unit and a fourth acquisition unit; The first acquisition unit is used for real-time monitoring and quality inspection of the production process in the manufacture of display devices; Capture image and depth data through a multimodal imaging device, including: RGB image frame sequences, depth map dense point cloud data, and near-infrared structured light; The second acquisition unit is used to obtain observation angle and posture parameters through the visual fusion sensor array, including: viewing angle coordinate information, space vector information corresponding to the observation point, viewing angle step resolution and angle coverage; The third acquisition unit is used to collect external light parameters through the environmental spectrum analysis module and the light sensor, including: light incident angle, direction distribution; illumination intensity and color temperature information; environmental spectrum distribution; The fourth acquisition unit is used to acquire target display area structural feature data by scanning the display surface, including: display surface inclination and curvature distribution; spatial edge contour and occlusion information; microstructure arrangement and boundary constraint parameters.

3. The metasurface dynamic color holographic display system according to claim 2, characterized in that: The data processing module is used to perform spatial alignment, noise filtering and color normalization on the collected RGB image and depth information through image registration and filtering technology; and to generate a multi-spectral phase response matrix by fusing the RGB image and illumination parameters through a multi-channel phase control algorithm; Through the perspective and depth joint coding technology, multi-angle images, depth information and display structure constraints are integrated to generate a perspective depth coding map.

4. The metasurface dynamic color holographic display system according to claim 3, characterized in that: The AI ​​dynamic adjustment model establishment module is used to use a convolutional neural network to construct an initial model for the metasurface dynamic color holographic display, and to train and test the model using an input image sequence and environmental parameter data; the trained model is used as a dynamic prediction model to fit and predict the input image sequence, output the target light field distribution and coding instructions, drive the dynamic holographic display, and achieve high-quality color dynamic holographic image reconstruction; at the same time, the intermediate layer feature vectors of the input data are used to extract multi-dimensional information of spatial angles, further train and optimize, and run as an AI dynamic adjustment model after training to achieve high-quality color dynamic holographic image reconstruction by driving the dynamic holography.

5. The metasurface dynamic color holographic display system according to claim 4, characterized in that: The color fidelity monitoring module includes a first calculation unit and a first analysis unit; The first calculation unit is used to calculate and obtain the color fidelity coefficient CSx by real-time monitoring the color output and structural characteristics of the display surface, combining the color information of the input image sequence and the ambient lighting parameters after dimensionless processing. The formula is as follows: Where, It represents the RGB structural similarity index, reflecting the overall similarity between the reconstructed image and the target image in the red, green, and blue channel structures. M represents the number of vertical pixels in the image, N represents the number of horizontal pixels in the image, x represents the horizontal coordinate index of the pixel, and y represents the vertical coordinate index of the pixel. Reconstructed image in The average brightness at Indicates that the target image is The average brightness at represents a constant that prevents the denominator from being zero, represents the average crosstalk, the cross interference degree of RGB signals between adjacent pixels, and w1, w2, and w3 represent weight coefficients.

6. The metasurface dynamic color holographic display system according to claim 5, characterized in that: The first analysis unit is configured to preset a first threshold Q1 in advance, and compare and analyze the color fidelity coefficient CSx with the first threshold Q1 to obtain a first evaluation result, including: When the color fidelity coefficient CSx ≥ the first threshold Q1, it means that the color reproduction quality of the image is qualified and continues to be monitored; When the color fidelity coefficient CSx is less than the first threshold Q1, it indicates that the color restoration quality of the image is unqualified, triggering the first warning instruction and generating the first strategy: optimizing the spectral reconstruction network parameters and its input features, improving the fitting ability of high-contrast color areas, combining the color reconstruction error distribution, dynamically adjusting the lighting angle and exposure parameters, reconstructing multi-angle high-fidelity sampling data, returning to the image processing module, regenerating the spectral reconstruction image based on the current input image, and updating the calculation until the color fidelity coefficient CSx is greater than or equal to the first threshold Q1.

7. The metasurface dynamic color holographic display system according to claim 4, characterized in that: The dynamic response performance monitoring module includes a second calculation unit and a second analysis unit; The second calculation unit is used to calculate the dynamic response performance coefficient DTx by combining the material response data and the refresh frame rate dynamic parameters after dimensionless processing. The formula is as follows: Where, Represents the image refresh rate, e represents the base of the natural constant, represents the thermal response adjustment factor, obtained by experiment, represents the excitation temperature difference, T0 represents the reference temperature difference, represents the material response time, represents the voltage response coupling coefficient, obtained by experiment, represents the control voltage, represents the average power consumption, It represents the thermal stability of the material, and a1, a2 and a3 represent the weight coefficients.

8. The metasurface dynamic color holographic display system according to claim 7, characterized in that: The second analysis unit is configured to preset a second threshold Q2 in advance and compare and analyze the dynamic response performance coefficient DTx with the second threshold Q2 to obtain a second evaluation result, including: When the dynamic response performance coefficient DTx ≥ the second threshold Q2, it indicates that the full-dimensional dynamic performance meets the standard, there is no problem of control deviation and power consumption thermal control mismatch, and continuous monitoring is performed; When the dynamic response performance coefficient DTx is less than the second threshold Q2, it indicates that the full-dimensional dynamic performance does not meet the standard, and there are problems of control deviation and power consumption thermal control mismatch, which triggers the second warning instruction and generates the second strategy: when the dominant item response time is detected to be abnormal, switch to the local high-speed response material domain; divide the holographic image into sub-pixel control areas, and use parallel control and time interpolation reconstruction to improve the overall refresh frame rate; after applying a short-time high-frequency excitation pulse, switch to low-voltage maintenance mode to reduce control delay and thermal load; construct a map of thermally sensitive areas, automatically avoid thermal drift areas and reallocate control tasks; adjust the control drive sequence to stabilize and optimize the response performance.

9. The metasurface dynamic color holographic display system according to claim 4, characterized in that: The three-dimensional reconstruction monitoring module includes a third calculation unit and a third analysis unit; The third calculation unit is used to calculate and obtain the three-dimensional reconstruction accuracy coefficient SWZx through the multi-view depth coding map and the actual depth map, combined with the spatial structure continuity and multi-angle consistency data after dimensionless processing. The formula is as follows: Where M represents the number of vertical pixels in the image, N represents the number of horizontal pixels in the image, x represents the horizontal coordinate index of the pixel, and y represents the vertical coordinate index of the pixel. Represents the depth error, the difference between the predicted depth map and the true depth in pixels The error difference at Indicates the gradient change of the depth map in the z-axis direction, represents multi-angle consistency, s1, s2, and s3 represent weight coefficients; The third analysis unit is used to preset a third threshold Q3 in advance, and compare and analyze the three-dimensional reconstruction accuracy coefficient SWZx with the third threshold Q3 to obtain a third evaluation result including: When the 3D reconstruction accuracy coefficient SWZx ≥ the third threshold Q3, it indicates that the 3D reconstruction effect meets the standard and is continuously monitored; When the three-dimensional reconstruction accuracy coefficient SWZx is less than the third threshold Q3, it indicates that the three-dimensional reconstruction effect does not meet the standard and cannot satisfy the requirements of realistic stereoscopic expression. The third warning instruction is triggered, and the third strategy is generated: updating the multi-angle coding map, improving the joint consistency of spatial angles and stereoscopic coherence, and finally outputting the holographic image update instruction to enhance the depth level performance and improve the fidelity reconstruction capability of large parallax three-dimensional scenes.

10. A metasurface dynamic color holographic display method, comprising a metasurface dynamic color holographic display system according to any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Through real-time monitoring and quality inspection of the production process in display device manufacturing, data is collected and acquired, including: image and depth data, observation angle and posture parameters, external lighting parameters, and target display area structural feature data; Step 2: By registering, filtering and normalizing the collected RGB image and depth information, the illumination parameters are integrated to generate a multi-spectral phase response matrix, and the perspective depth coding map is generated by jointly encoding the perspective and depth; Step 3: By building an initial holographic display model based on a convolutional neural network and optimizing it through image sequence and environmental parameter training, a dynamic model is generated to predict light field distribution and encoding instructions. At the same time, the intermediate layer features are extracted to achieve multi-dimensional optimization of spatial angles and improve the quality of color dynamic holographic image reconstruction; Step 4: By real-time monitoring of the display surface color output and structural characteristics, combined with the color information of the input image sequence and the ambient lighting parameters, the color fidelity coefficient CSx is calculated and compared with the first threshold Q1 to determine whether the image color reproduction quality is qualified. If it is unqualified, a strategy is given; Step 5: Calculate the dynamic response performance coefficient DTx by combining the material response data and the refresh frame rate dynamic parameters, and compare and analyze it with the second threshold Q2 to determine whether the full-dimensional dynamic performance meets the standard. If not, a strategy is given; Step 6: Calculate the 3D reconstruction accuracy coefficient SWZx by combining the multi-view depth coding map and the actual depth map with the spatial structure continuity and multi-angle consistency data, and compare and analyze it with the third threshold Q3 to determine whether the 3D reconstruction effect meets the standard. If not, a strategy is given.

Images