Projector optical module optimization method, system and computer equipment

Abstract

The present invention relates to a projector optical-mechanical module optimization method, system and computer equipment, and the method includes: obtaining light source system parameters and projection environment data of the projector optical-mechanical module, performing adaptive adjustment, and obtaining initialization light source output parameters; obtaining real-time operation data of the projector optical-mechanical module, and performing correlation processing with the initialization light source output parameters to obtain corresponding real-time projection state information; obtaining projection picture data of the projector optical-mechanical module, performing quality assessment on the real-time projection state information, and obtaining corresponding picture optimization trends; performing solution analysis on the real-time projection state information and the picture optimization trends, and obtaining corresponding initial module adjustment solutions; performing effect prediction on the enhanced picture based on the picture optimization trends, and performing comprehensive analysis with the initial module adjustment solutions, and obtaining corresponding global optimization strategies. The present invention can adaptively adjust light source output parameters and effectively cope with challenges under different projection environments.

Description

Technical Field

[0001] The present invention relates to the technical field of projectors, and in particular to a method and system for optimizing an optical-mechanical module of a projector and computer equipment. Background Art

[0002] As an important visual display device, projectors are widely used in many fields such as business, education, and entertainment. With the continuous improvement of users' requirements for the quality of projected images, how to optimize the performance of projector optical modules to achieve high-quality and stable projection effects has become one of the research focuses. Existing optimization methods for projector optical modules often only focus on a single factor, such as light source brightness or color adjustment, while ignoring the comprehensive impact of multiple factors such as projection environment and operating status on the projection effect. This limitation makes it difficult for the optimization effect to meet the projection needs in different scenarios, and it is also unable to effectively deal with various abnormal situations that occur during the projection process. In addition, traditional optimization methods lack the ability to evaluate and dynamically adjust the quality of the projected image in real time, and are difficult to adapt to complex and changing projection environments and user needs. Therefore, developing a projector optical module optimization method that can comprehensively consider multiple factors and has adaptive adjustment capabilities is of great significance for improving projection quality and user experience. Summary of the invention

[0003] The main purpose of the present invention is to provide a projector optical-mechanical module optimization method, system and computer equipment, which can adaptively adjust the light source output parameters and effectively cope with the challenges in different projection environments.

[0004] To achieve the above object, the present invention provides a method for optimizing an optical-mechanical module of a projector, comprising: Obtain the light source system parameters and projection environment data of the projector optical module, perform adaptive adjustments, and obtain the initialization light source output parameters; Acquire the real-time operation data of the optical-mechanical module of the projector, and associate it with the output parameters of the initialized light source to obtain corresponding real-time projection status information; Acquire projection picture data of the projector optical-mechanical module, perform quality assessment on the real-time projection state information, and obtain corresponding picture optimization trends; Performing a solution analysis on the real-time projection status information and the picture optimization trend to obtain a corresponding initial module adjustment solution; Performing projection image distortion preprocessing and bipolar line constraint dedistortion on the projection picture data to obtain an enhanced picture; Based on the picture optimization trend, the effect of the enhanced picture is predicted to obtain a predicted picture quality index, and a comprehensive analysis is performed with the initial module adjustment plan to obtain a corresponding global optimization strategy.

[0005] Furthermore, the light source system parameters and projection environment data of the projector optical machine module are obtained, and adaptive adjustments are performed to obtain corresponding initialization light source output parameters, including: Collect the light source system parameters of the projector optical module, including light source brightness, color temperature, spectral distribution and power consumption data; Obtain projection environment data, including ambient light intensity, projection distance, and projection surface reflectivity; Performing nonlinear scaling processing on the light source system parameters and projection environment data to obtain a nonlinear scaling parameter set; Performing cluster analysis on the nonlinear scaling parameter set according to a preset mean clustering method to obtain an initial light source adjustment factor; Preliminarily adjusting the light source system parameters according to the initial light source adjustment factor to obtain adjusted light source parameters; Performing nonlinear fitting on the adjusted light source parameters according to an improved Levenberg-Marquardt algorithm to obtain fitting light source parameters; Optimizing the fitting light source parameters according to a preset multi-objective differential evolution algorithm to obtain an initialized light source parameter set; The light source output is adjusted according to the initialization light source parameter set to obtain the initialization light source output parameters.

[0006] Furthermore, the real-time operation data of the projector optical-mechanical module is acquired and associated with the initialization light source output parameters to obtain corresponding real-time projection status information, including: Performing real-time status monitoring on the projector optical and mechanical module to obtain corresponding real-time operating data; Constructing a correlation matrix according to the real-time operation data and the initialized light source output parameters to obtain a light source parameter correlation matrix; Adaptively adjusting the driving current and driving voltage of the projector optical-mechanical module based on the light source parameter association matrix to obtain adjusted light source parameters; Performing time series analysis on the adjusted light source parameters to obtain a change trend of the light source parameters; According to the changing trend of light source parameters, the light source state in the future is predicted to obtain the predicted light source state; The adjusted light source parameters and the predicted light source state are subjected to state analysis to obtain the real-time projection state information.

[0007] Furthermore, the acquisition of projection picture data of the projector optical-mechanical module, the quality assessment of the real-time projection state information, and the acquisition of the corresponding picture optimization trend include: Performing color space analysis and brightness distribution analysis on the projection picture of the projector optical module to obtain corresponding projection picture data; Performing frequency decomposition on the projection picture data to obtain a plurality of frequency sub-band images; Performing local contrast analysis on the plurality of frequency sub-band images respectively to obtain corresponding local contrast indicators; Adaptively allocating the plurality of frequency sub-band images according to the local contrast index to obtain a fusion coefficient; Reconstructing and fusing the plurality of frequency sub-band images according to the fusion coefficients to obtain enhanced picture data; Performing clarity analysis on the enhanced picture data to obtain a picture clarity evaluation index; Correlation analysis is performed on the picture clarity evaluation index and the real-time projection state information to obtain a picture quality evaluation result; Performing trend analysis on the picture quality evaluation result to obtain the picture optimization trend.

[0008] Furthermore, the real-time projection status information and the picture optimization trend are analyzed to obtain a corresponding initial module adjustment plan, including: Performing multi-dimensional feature extraction on the real-time projection state information to obtain a projection state feature vector; Calculating a corresponding correlation degree according to the projection state feature vector and the picture optimization trend to obtain a state optimization correlation degree; Perform parameter sensitivity analysis based on the state optimization correlation to obtain a key adjustment parameter set; Performing multi-objective constraint optimization on the key adjustment parameter set to obtain initial adjustment parameters; Performing ray tracing analysis on the projector optical-mechanical module according to the initial adjustment parameters to obtain an optical path optimization solution; According to the optical path optimization scheme, a simulation is performed on the drive circuit parameter adjustment of the projector optical-mechanical module to obtain a drive optimization scheme; The optical path optimization scheme and the drive optimization scheme are integrated to obtain the initial module adjustment scheme.

[0009] Furthermore, the projected picture data is subjected to projection image distortion preprocessing and bipolar line constraint dedistortion to obtain an enhanced picture, including: Performing distortion analysis on the projection picture data to obtain corresponding distortion parameters; Establishing a distortion correction algorithm according to the projection image distortion preprocessing method in combination with the distortion parameters, wherein the distortion correction algorithm includes correction of radial distortion and tangential distortion; Calculating the mapping relationship between each pixel point in the projection picture data and the corresponding point in the standard distortion-free image according to the distortion correction algorithm; Mapping the projection picture data onto the standard distortion-free image according to the mapping relationship to obtain mapping coordinates, and performing interpolation processing to obtain reconstructed pixel values; Reconstructing the image according to the reconstructed pixel values ​​to obtain a pre-processed projection picture that has been corrected for distortion; Performing unidirectional fringe extraction on the preprocessed projection image to obtain corresponding fringe feature data; The preprocessed projection picture is enhanced according to the bipolar constraint dedistortion method in combination with the stripe feature data to obtain the enhanced picture.

[0010] Furthermore, the step of performing image enhancement processing on the preprocessed projection image according to the bipolar constraint dedistortion method in combination with the fringe feature data to obtain the enhanced image includes: Performing epipolar equation calculation on the fringe characteristic data to obtain corresponding initial epipolar parameters; Performing a first epipolar constraint process on the preprocessed projection image according to the initial epipolar parameters to obtain preliminary matching point pairs; Performing error analysis on the preliminary matching point pairs to obtain corresponding matching error data; Optimizing and adjusting the initial epipolar parameters according to the matching error data to obtain optimized epipolar parameters; Performing a second epipolar constraint process on the preprocessed projection image according to the optimized epipolar parameters to obtain an accurate matching point set; Interpolating and reconstructing the preprocessed projection picture according to the precise matching point set to obtain a reconstructed picture; The reconstructed picture is subjected to picture adjustment processing including edge enhancement, contrast adjustment and color correction to obtain the enhanced picture.

[0011] Furthermore, the effect of the enhanced image is predicted based on the image optimization trend to obtain a predicted image quality index, and a comprehensive analysis is performed with the initial module adjustment plan to obtain a corresponding global optimization strategy, including: Performing a scale transformation on the picture optimization trend to obtain a multi-scale trend coefficient; Adaptively correcting the enhanced picture according to the multi-scale trend coefficient to obtain a corrected image; Performing frequency domain analysis and spatial domain transformation on the corrected image to obtain an image quality feature matrix; Performing a convolution operation on the image quality feature matrix and a preset image quality evaluation parameter to obtain a predicted image quality index; Calculating the index of the initial module adjustment scheme according to the predicted picture quality index to obtain quality optimization parameters; The initial module adjustment scheme is optimized according to the quality optimization parameter in combination with the predicted picture quality index to obtain the global optimization strategy.

[0012] The present invention further provides a projector optical-mechanical module optimization system, which is applied to any one of the above projector optical-mechanical module optimization methods, comprising: An acquisition module, which is used to obtain light source system parameters and projection environment data of the projector optical machine module, perform adaptive adjustments, and obtain initialization light source output parameters; An analysis module, the analysis module is used to obtain the real-time operation data of the projector optical and mechanical module, and associate it with the initialization light source output parameters to obtain corresponding real-time projection status information; An association module, the association module is used to obtain projection picture data of the projector optical and mechanical module, perform quality evaluation on the real-time projection state information, and obtain a corresponding picture optimization trend; A processing module, the processing module is used to perform a solution analysis on the real-time projection state information and the picture optimization trend to obtain a corresponding initial module adjustment solution; A control module, the control module is used to perform projection image distortion preprocessing and bipolar line constraint dedistortion on the projection picture data to obtain an enhanced picture; An execution module is used to predict the effect of the enhanced image based on the image optimization trend, obtain a predicted image quality index, and perform a comprehensive analysis with the initial module adjustment plan to obtain a corresponding global optimization strategy.

[0013] The present invention also provides a computer device for optimizing a projector optical-mechanical module, comprising: Memory, used to store programs; The processor is used to execute the program to implement each step of the projector optical-mechanical module optimization method described in any one of the above items.

[0014] The present invention provides a projector optical-mechanical module optimization method, system and computer equipment, which have the following beneficial effects: By associating the real-time operation data with the output parameters of the initialized light source, the real-time monitoring and evaluation of the projection state is realized, providing a reliable basis for dynamic adjustment. The quality of the real-time projection state is evaluated based on the projection screen data, and the picture optimization trend is obtained, making the optimization process more targeted and forward-looking. The projection screen is enhanced by the preset image processing method, and the effect is predicted in combination with the picture optimization trend, which greatly improves the quality of the projection screen. Finally, by comprehensively analyzing the initial module adjustment plan and predicting the picture quality indicators, a global optimization strategy is formulated to achieve a comprehensive improvement in the performance of the projector optical module. This multi-dimensional and dynamic optimization method not only overcomes the limitation of traditional methods that only focus on a single factor, but also can effectively cope with complex and changing projection environments and user needs. Through real-time evaluation and dynamic adjustment, this method significantly improves the stability and adaptability of the projection quality, providing users with a better visual experience. At the same time, this intelligent optimization strategy also provides technical support for the flexible adjustment of projectors in different application scenarios, expanding the application scope of projection equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of a method for optimizing a projector optical-mechanical module provided by the present invention; Figure 2 This is a structural diagram of a projector optical-mechanical module optimization system provided by the present invention; Figure 3 It is a structural diagram of a computer device for optimizing a projector optical-mechanical module provided by the present invention.

[0016] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] The present invention is further described below in conjunction with the accompanying drawings and specific implementation methods.

[0019] Reference Figure 1 As shown, the present invention provides a method for optimizing an optical-mechanical module of a projector, comprising: Step S1: Obtaining the light source system parameters and projection environment data of the projector optical module, performing adaptive adjustment, and obtaining the initialization light source output parameters; Step S2: acquiring real-time operation data of the projector optical machine module, and performing correlation processing with the initialization light source output parameters to obtain corresponding real-time projection state information; Step S3: Acquire projection picture data of the projector optical module, perform quality assessment on the real-time projection status information, and obtain the corresponding picture optimization trend; Step S4: Analyze the real-time projection status information and the picture optimization trend to obtain the corresponding initial module adjustment plan; Step S5: performing projection image distortion preprocessing and bipolar constraint dedistortion on the projection picture data to obtain an enhanced picture; Step S6: Based on the picture optimization trend, the effect of the enhanced picture is predicted to obtain the predicted picture quality index, and a comprehensive analysis is performed with the initial module adjustment plan to obtain the corresponding global optimization strategy.

[0020] Based on the above steps, the detailed process is as follows: Step S1: Analyze and record the light source system of the projector optical module in detail. These parameters include the type of light source (such as LED, laser), brightness, color temperature, power consumption, etc. These parameters are the basis for subsequent adjustments.

[0021] Collect and analyze data about the environment in which the projector is located. This environmental data includes ambient light intensity, projection distance, projection surface characteristics (such as color, material), etc. Environmental data can affect the performance of the light source system, so it needs to be considered during the optimization process.

[0022] Combining the light source system parameters and projection environment data, adaptive adjustments are made through a certain algorithm to generate a set of initial light source output parameters. The initial light source output parameters will serve as the benchmark for subsequent steps.

[0023] Step S2: During the operation of the projector, the operating status of the optical machine module is monitored in real time. These operating status data include temperature, operating time, actual output brightness, input voltage and current, etc. These data can reflect the actual working status of the projector.

[0024] The collected real-time operation data is correlated with the initialization light source output parameters. Through comparative analysis, the deviation or change trend between the operation data and the initial parameters is identified.

[0025] Through the association processing, real-time projection status information is generated, which can reflect the working efficiency of the current projector, the use of light source, etc.

[0026] Step S3: Using a sensor or camera or other equipment, obtain the data of the current projection image of the projector, including the brightness, contrast, color accuracy, clarity, etc. of the image.

[0027] The acquired projection image data and real-time projection status information are comprehensively analyzed to evaluate the quality of the current image. This evaluation process can use image processing algorithms or artificial intelligence technology to identify defects or deficiencies in the image. Based on the results of the quality evaluation, the optimization trend of the image is analyzed. This trend includes the need to increase brightness, enhance contrast, correct color deviation, etc.

[0028] Step S4: Integrate the real-time projection status information with the picture optimization trend. This integration process aims to fully understand the relationship between the current performance of the projector and the picture effect.

[0029] Using the integrated information, detailed solution analysis can be performed, using decision trees, neural networks or other optimization algorithms to analyze which factors have the greatest impact on image quality and identify specific aspects that can be improved. Based on the results of the solution analysis, an initial module adjustment plan is generated, including specific measures such as adjusting light source brightness, modifying color settings, and adjusting projection angles to improve the quality of the projected image.

[0030] Step S5: Pre-process the projection image data for distortion. This process uses image processing technology to identify and correct the geometric distortion of the projection image to ensure the accuracy of the image shape.

[0031] The bipolar constraint algorithm is applied to further correct the distortion in the picture. This algorithm can eliminate complex distortion in the picture through the camera projection model and geometric constraints to obtain a more natural and realistic picture effect. After the above steps, the enhanced projection picture is obtained.

[0032] Step S6: Predict the effect of the obtained enhanced picture. A learning model or other prediction algorithm can be used to evaluate the potential changes in picture quality under different environments and settings. Specific picture quality indicators such as brightness, contrast, color accuracy, clarity, etc. are extracted from the effect prediction. These indicators provide a quantitative basis for evaluating the actual performance of the enhanced picture.

[0033] Analyze the predicted image quality indicators and the generated initial module adjustment plan. Evaluate the effectiveness of the current adjustment plan and identify areas that need further optimization.

[0034] Based on the results of the comprehensive analysis, a global optimization strategy is generated. This strategy will combine the information obtained in all steps to propose a comprehensive and coordinated adjustment plan to ensure that the projector can provide the best projection effect in various usage scenarios.

[0035] The present invention provides a method for optimizing the optical-mechanical module of a projector, which realizes real-time monitoring and evaluation of the projection state by associating the real-time operation data with the output parameters of the initial light source, and provides a reliable basis for dynamic adjustment. The quality of the real-time projection state is evaluated according to the projection picture data, and the picture optimization trend is obtained, so that the optimization process is more targeted and forward-looking. The projection picture is enhanced by a preset image processing method, and the effect is predicted in combination with the picture optimization trend, which greatly improves the quality of the projection picture. Finally, by comprehensively analyzing the initial module adjustment scheme and the predicted picture quality index, a global optimization strategy is formulated, and the overall performance of the projector optical-mechanical module is improved. This multi-dimensional and dynamic optimization method not only overcomes the limitation of the traditional method that only focuses on a single factor, but also can effectively cope with complex and changeable projection environments and user needs. Through real-time evaluation and dynamic adjustment, the method significantly improves the stability and adaptability of the projection quality, and provides users with a better visual experience. At the same time, this intelligent optimization strategy also provides technical support for the flexible adjustment of the projector in different application scenarios, and expands the application range of the projection equipment.

[0036] In one embodiment, the light source system parameters and projection environment data of the projector optical module are obtained, and adaptive adjustments are performed to obtain corresponding initialization light source output parameters, including: The light source system parameters of the projector optical module include light source brightness, color temperature, spectral distribution and power consumption data. These parameters are collected through built-in sensors or external measuring devices. For example, light source brightness can be measured by a light intensity sensor, color temperature can be measured by a color temperature sensor, spectral distribution can be measured by a spectrometer, and power consumption data can be measured by a power meter.

[0037] The projection environment data includes the ambient light intensity, projection distance and projection surface reflectivity. The ambient light intensity is measured by an ambient light sensor, the projection distance is measured by an ultrasonic sensor or a laser rangefinder, and the projection surface reflectivity is measured by a reflectivity sensor or estimated by a preset reflectivity table.

[0038] The collected light source system parameters and projection environment data need to be nonlinearly scaled to eliminate the dimension differences and nonlinear effects between different parameters. Nonlinear scaling can be achieved by applying a preset nonlinear function to each parameter. For example, the light source brightness is processed by a logarithmic function, the color temperature is processed by an exponential function, the spectral distribution can be normalized, and the power consumption data can be linearly normalized. The ambient light intensity and projection distance can also be processed by similar nonlinear functions, and the projection surface reflectivity can be linearly normalized.

[0039] The parameter set after nonlinear scaling is called a nonlinear scaling parameter set. In order to further analyze these parameters, the nonlinear scaling parameter set is clustered by a preset mean clustering method. The mean clustering method is an unsupervised learning method that divides data points into several clusters so that the similarity of data points in the same cluster is high and the similarity of data points between different clusters is low. The result of the cluster analysis is a set of initial light source adjustment factors, which reflect the degree of influence of different parameters on the light source output.

[0040] According to the initial light source adjustment factor, the light source system parameters are preliminarily adjusted to obtain the adjusted light source parameters. The preliminary adjustment process is achieved by multiplying the initial light source adjustment factor by the corresponding light source system parameters. For example, if the initial light source adjustment factor of a light source brightness is 1.2, then the adjusted light source brightness will be 1.2 times the original light source brightness.

[0041] Nonlinear fitting is performed by using the pre-improved Levenberg-Marquardt algorithm. The Levenberg-Marquardt algorithm is a commonly used nonlinear least squares optimization algorithm that iteratively adjusts parameters to minimize the objective function. The improved Levenberg-Marquardt algorithm adds an adaptive step adjustment mechanism on the basis of the standard algorithm, which improves the convergence speed and stability. The objective function of nonlinear fitting can be the quality index of the projected image, such as contrast, brightness uniformity and color reproduction. Through nonlinear fitting, a set of fitting light source parameters are obtained, which can better meet the quality requirements of the projected image.

[0042] The preset multi-objective differential evolution algorithm is used to perform multi-objective optimization on the fitting light source parameters. The multi-objective differential evolution algorithm is an evolutionary algorithm that simulates the process of natural selection and genetic variation to find a set of optimal solutions. The objective function of multi-objective optimization can include multiple quality indicators, such as contrast, brightness uniformity, and color reproduction. Through the multi-objective differential evolution algorithm, a set of initialized light source parameter sets are obtained, which can optimize multiple quality indicators at the same time.

[0043] The light source output is adjusted according to the initialization light source parameter set to obtain the initialization light source output parameter. The light source output adjustment process is achieved by setting the parameter value in the initialization light source parameter set as the control parameter of the light source system. For example, if the value of the brightness of a light source in the initialization light source parameter set is 1000 lumens, then the control parameter of the light source system will be set to 1000 lumens. In this way, the quality of the projected image can be ensured to reach the optimal level.

[0044] This embodiment eliminates the dimensional differences and nonlinear effects between different parameters by performing nonlinear scaling processing on the light source system parameters and projection environment data, thereby ensuring the accuracy and consistency of subsequent processing. Secondly, the mean clustering method is used to perform cluster analysis on the nonlinear scaling parameter set to obtain the initial light source adjustment factors, which can reflect the actual impact of different parameters on the light source output and provide a scientific basis for preliminary adjustment. The adjusted light source parameters are nonlinearly fitted by the improved Levenberg-Marquardt algorithm to further optimize the light source parameters, so that the contrast, brightness uniformity and color reproduction of the projection picture are significantly improved. In addition, the multi-objective differential evolution algorithm is used for multi-objective optimization, which can find the best balance point between multiple quality indicators and ensure the overall quality of the projection picture. The light source output is adjusted according to the initialization light source parameter set, so as to achieve precise control of the light source system and improve the stability and reliability of the projection picture. In summary, this method not only improves the quality of the projection picture, but also enhances the adaptability and flexibility of the system, providing users with a better visual experience.

[0045] In one embodiment, real-time operation data of the projector optical machine module is obtained, and associated with the initialization light source output parameters to obtain corresponding real-time projection state information, including: The real-time operation data of the projector optical module includes the real-time brightness, color temperature, spectral distribution, power consumption of the light source system, as well as the real-time light intensity, projection distance and projection surface reflectivity of the projection environment. These data can be collected in real time through built-in sensors. For example, the brightness of the light source can be monitored in real time through a light intensity sensor, the color temperature can be monitored in real time through a color temperature sensor, the spectral distribution can be monitored in real time through a spectrometer, and the power consumption data can be monitored in real time through a power meter. Projection environment data such as ambient light intensity can be monitored in real time through an ambient light sensor, the projection distance can be monitored in real time through an ultrasonic sensor or a laser rangefinder, and the projection surface reflectivity can be monitored in real time through a reflectivity sensor or estimated through a preset reflectivity table.

[0046] The real-time operation data and the initialized light source output parameters are associated and processed to construct a light source parameter association matrix. The light source parameter association matrix is ​​a multidimensional matrix, in which each element represents the degree of association between the real-time operation data and the initialized light source output parameters. In the process of constructing the light source parameter association matrix, linear regression or neural network methods can be used to train the model through historical data to obtain the association relationship between the various parameters. For example, a linear regression model can be established, with real-time brightness, color temperature and other parameters as input, and the initialized light source output parameters as output. The model is trained by minimizing the error to obtain the light source parameter association matrix.

[0047] Based on the light source parameter association matrix, the projector optical machine module is adaptively adjusted in terms of driving current and driving voltage to obtain the adjusted light source parameters. The adaptive adjustment process is achieved through a feedback control mechanism. Specifically, the driving current and driving voltage can be adjusted according to the degree of correlation in the light source parameter association matrix so that the actual light source output parameters are close to or reach the initialized light source output parameters. For example, if the real-time brightness is lower than the initialized brightness, the brightness can be increased by increasing the driving current; if the real-time color temperature deviates from the initialized color temperature, the color temperature can be corrected by adjusting the driving voltage.

[0048] Perform time series analysis on the adjusted light source parameters to obtain the changing trend of the light source parameters. Time series analysis is to analyze the changing rules of the adjusted light source parameters over time through statistical methods or machine learning algorithms. For example, the sliding window method can be used to divide the adjusted light source parameters within a period of time into several windows, and calculate the statistical characteristics such as the average value, maximum value, and minimum value in each window to obtain the changing trend of the light source parameters. The results of the time series analysis can be used to evaluate the stability and response speed of the light source system.

[0049] According to the change trend of light source parameters, the light source state in the future is predicted to obtain the predicted light source state. The process of predicting the light source state can be achieved through time series prediction. According to historical data and current change trends, the light source parameters in the future are predicted.

[0050] The state analysis of the adjusted light source parameters and predicted light source status is performed to obtain real-time projection status information. State analysis evaluates the working status of the current projector optical module by comprehensively considering the adjusted light source parameters and predicted light source status. By defining a series of thresholds, when the adjusted light source parameters or predicted light source status exceed these thresholds, an alarm is triggered or automatic adjustment is made. The results of the state analysis can be used to monitor the operating status of the projector, discover and solve problems in a timely manner, and ensure the quality and stability of the projected image.

[0051] This embodiment obtains real-time operation data by real-time status monitoring of the projector optical machine module, ensures the accuracy and timeliness of the data, and provides a reliable basis for subsequent optimization processing. Secondly, by constructing a light source parameter association matrix, the association relationship between real-time operation data and the initialization light source output parameters is established, making the adjustment of the light source system more scientific and accurate. Furthermore, based on the light source parameter association matrix, the adaptive adjustment of the driving current and driving voltage can dynamically adjust the light source output to ensure that the brightness, color temperature and spectral distribution of the projection picture are always maintained in the optimal state, thereby improving the quality and stability of the projection picture. By performing a timing analysis on the adjustment of the light source parameters, the change trend of the light source parameters can be monitored in real time, potential problems can be discovered and adjusted in time, and the fault diagnosis and prevention capabilities of the system can be enhanced. By predicting the light source state in the future, measures can be taken in advance to avoid projection quality problems caused by fluctuations in light source parameters, further improving the reliability of the system and user experience. Comprehensive analysis is performed on the adjustment of light source parameters and the prediction of light source state to obtain real-time projection state information, providing users with comprehensive monitoring and management means to ensure that the projector is always in the best working state.

[0052] In one embodiment, the projection picture data of the projector optical module is obtained, and the quality of the real-time projection state information is evaluated to obtain the corresponding picture optimization trend, including: The color space and brightness distribution of the projector optical module projection screen are analyzed to obtain the projection screen data. Color space analysis is to detect the color value of each pixel and identify the distribution of each color channel in the screen, while brightness distribution analysis is to evaluate the overall brightness uniformity and contrast of the screen by calculating the brightness value of each pixel. The results of these two analyses constitute the original data basis of the projection screen, that is, the projection screen data.

[0053] Perform frequency decomposition on the acquired projection image data. This process uses multi-resolution analysis methods, such as wavelet transform, to decompose the image data into several frequency sub-band images. Each sub-band image represents the information characteristics of the projection image in different frequency ranges. This decomposition method helps to identify the detailed features of different scales in the image, providing a basis for subsequent contrast analysis.

[0054] When performing local contrast analysis on frequency sub-band images, the preset contrast calculation method is used to evaluate the local contrast level of each sub-band image. The contrast index is used to reflect the clarity and detail expression of the image at different frequencies based on the brightness difference calculation within the pixel neighborhood. Sub-band images with high contrast indexes show higher detail expression capabilities.

[0055] According to the local contrast index, multiple frequency sub-band images are adaptively allocated, and the fusion coefficient of each sub-band image in the reconstruction process is calculated. The calculation principle of the fusion coefficient is to improve the contrast and clarity of the overall picture, and weighted allocation is performed according to the contrast contribution of each sub-band image. Sub-band images with high contrast will be given higher weights, that is, larger fusion coefficients.

[0056] The frequency sub-band images are reconstructed and fused using the fusion coefficients. The reconstruction process recombines the sub-band images according to the weighted ratio to generate enhanced picture data. The enhanced picture data has significantly improved contrast and detail performance compared to the original picture.

[0057] Perform clarity analysis on the enhanced image data and quantitatively evaluate the clarity level of the image using pre-set clarity evaluation indicators, such as edge strength, texture richness, etc. Compared with the original image, the clarity index of the enhanced image should be significantly improved.

[0058] The correlation analysis step combines the picture clarity evaluation index with the real-time projection status information to evaluate the quality of the current projection picture. The projection status information includes the ambient light intensity, projection distance, screen material, etc. These factors have different degrees of influence on the picture quality.

[0059] By analyzing the trend of the picture quality evaluation results, we can get the picture optimization trend and determine the direction of picture optimization. Trend analysis reveals the law of picture quality changes in long-term use, guides the subsequent optimization strategy adjustment and parameter setting, and ensures that the projector optical module continues to provide high-quality projection effects under different usage conditions.

[0060] This embodiment can accurately identify and adjust the color and brightness uniformity of the picture through color space and brightness distribution analysis, thereby improving the visual effect. At the same time, by using frequency decomposition and local contrast analysis, the detail performance of the picture can be deeply explored and enhanced to ensure that the details at different frequencies are fully displayed. By using adaptively allocated fusion coefficients, the optimal combination of contrast and clarity is achieved during the image reconstruction process, further improving the visual clarity of the picture. Through correlation analysis with real-time projection status information, this method fully considers the impact of external environmental factors on projection quality, thereby achieving dynamic optimization of the picture. Through trend analysis, the optimization method provides guidance for the maintenance of picture quality in long-term use, ensuring that the projector can provide high-quality projection effects under various conditions of use.

[0061] In one embodiment, a solution analysis is performed on the real-time projection status information and the picture optimization trend to obtain a corresponding initial module adjustment solution, including: The real-time projection status information is subjected to multi-dimensional feature extraction to obtain the projection status feature vector. By collecting parameters of multiple dimensions such as brightness, contrast, color, and clarity of the projector and normalizing these parameters, a multi-dimensional feature vector is finally formed to characterize the current projection status. The feature extraction adopts the principal component analysis method to retain the main feature information.

[0062] The corresponding correlation is calculated based on the projection state feature vector and the picture optimization trend to obtain the state optimization correlation. The correlation between the feature vector and the preset picture optimization target is calculated by using the grey correlation analysis method. The higher the correlation, the closer the current state is to the optimization target. The correlation calculation takes into account the weight of each feature, which is determined by expert experience.

[0063] Based on the state optimization correlation, parameter sensitivity analysis is performed to obtain the key adjustment parameter set. By adopting the orthogonal experimental design method, by changing different parameter combinations and observing the change of correlation, the key parameter set with a greater impact on the optimization effect is determined. The sensitivity analysis sets the parameter change range and step size to ensure the comprehensiveness of the analysis.

[0064] The key adjustment parameter set is optimized with multi-objective constraints to obtain the initial adjustment parameters. The genetic algorithm is used for multi-objective optimization. The objective function includes multiple indicators such as brightness, contrast, and color, while considering the adjustment range constraints of each parameter. During the optimization process, the population size is set to 100, the number of iterations is 1000, the crossover probability is 0.8, and the mutation probability is 0.1.

[0065] According to the initial adjustment parameters, the projector optical module is subjected to ray tracing analysis to obtain the optical path optimization scheme. By using optical simulation software, a three-dimensional model of the optical module can be constructed based on the initial adjustment parameters, ray tracing simulation can be performed, the optical path propagation characteristics can be analyzed, and the position and angle of the optical components can be fine-tuned according to the analysis results to form an optical path optimization scheme. Ray tracing uses the Monte Carlo method, and the number of rays is set to 1 million.

[0066] According to the optical path optimization scheme, the projector optical module is simulated to adjust the drive circuit parameters and obtain the drive optimization scheme. According to the optical path optimization scheme, the LED drive current, DMD drive timing and other parameters are adjusted, and the circuit simulation analysis is performed to optimize the drive circuit parameters and form a drive optimization scheme. The impact of temperature changes on circuit performance is considered during the simulation process.

[0067] The optical path optimization scheme and the drive optimization scheme are combined to obtain the initial module adjustment scheme. The optical optimization and circuit optimization results are combined to form a unified adjustment scheme. The weighted average method is used in the fusion process, and the weights of optical path optimization and drive optimization are 0.6 and 0.4 respectively. The final initial module adjustment scheme includes optimization suggestions for multiple aspects such as optical component position and drive parameters.

[0068] This embodiment realizes a comprehensive evaluation of the projection state and an accurate grasp of the optimization trend through multi-dimensional feature extraction and grey correlation analysis, providing a reliable data basis for subsequent optimization. By adopting parameter sensitivity analysis and multi-objective constraint optimization, the key adjustment parameters are effectively identified and the optimal initial adjustment scheme is obtained, which greatly improves the optimization efficiency. Combined with ray tracing analysis and drive circuit simulation, the coordinated optimization of optics and circuits is achieved, ensuring the comprehensiveness and feasibility of the optimization scheme. Through the weighted fusion of optical path and drive optimization scheme, a comprehensive adjustment scheme that takes into account multiple factors is obtained, effectively balancing various performance indicators. The entire optimization process takes into account a variety of influencing factors and constraints, can adapt to different types of projectors, and improves the versatility and practicality of the method. This method can realize the rapid optimization of projector performance, improve user experience, and reduce the complexity and time cost of manual debugging.

[0069] In one embodiment, projection image data is subjected to projection image distortion preprocessing and bipolar line constraint dedistortion to obtain an enhanced image, including: Perform distortion analysis on the projection image data to obtain the corresponding distortion parameters. Distortion analysis usually uses the calibration plate method, which extracts feature point coordinates by taking multiple calibration plate images at different positions and angles, establishes a distortion model, and solves the distortion parameters. Distortion parameters include radial distortion coefficient and tangential distortion coefficient.

[0070] After obtaining the distortion parameters, a distortion correction algorithm is established based on the projection image distortion preprocessing method combined with the distortion parameters. The algorithm mainly includes the correction of radial distortion and tangential distortion. Radial distortion correction can be achieved by using a polynomial model, while tangential distortion correction considers the distortion caused by the non-parallelism between the lens and the image plane. The establishment of the correction algorithm needs to consider the accuracy and computational efficiency of the distortion model.

[0071] After the distortion correction algorithm is established, the mapping relationship between each pixel in the projected image data and the corresponding point in the standard undistorted image is calculated. This step is achieved through reverse mapping, that is, for each pixel in the standard undistorted image, its corresponding position in the original distorted image is calculated. This reverse mapping can avoid holes in the target image.

[0072] According to the obtained mapping relationship, the projection screen data is mapped to the standard undistorted image to obtain the mapping coordinates. Since the mapping coordinates are usually not integers, interpolation processing is required to obtain the reconstructed pixel values. The interpolation methods of interpolation processing include nearest neighbor interpolation, bilinear interpolation and bicubic interpolation, among which bilinear interpolation achieves a better balance between accuracy and efficiency.

[0073] The reconstructed pixel values ​​are used to reconstruct the image to obtain a distortion-corrected preprocessed projection image. During the image reconstruction process, attention should be paid to boundary processing to avoid black edges or information loss.

[0074] Perform unidirectional stripe extraction on the preprocessed projection image to obtain the corresponding stripe feature data. Stripe extraction usually uses grayscale threshold method or edge detection algorithm to extract the stripe structure in the image. The extracted stripe feature data includes information such as the position, width, and direction of the stripes.

[0075] The pre-processed projection image is enhanced based on the bipolar constraint dedistortion method combined with the fringe feature data to obtain an enhanced image. The bipolar constraint dedistortion method uses the geometric relationship between the projector and the camera to establish a bipolar constraint model to further eliminate residual distortion. In the image enhancement process, the continuity and consistency of the fringe features need to be considered to ensure the quality of the enhanced image.

[0076] The embodiment realizes accurate correction of radial and tangential distortion by utilizing the distortion parameters obtained by distortion analysis, thereby reducing image distortion and enhancing the visual effect of the picture. Through mapping relationship and interpolation processing, accurate reconstruction of projection picture data on a standard distortion-free image is ensured, thereby ensuring the integrity of picture details. The combination of unidirectional stripe extraction and bipolar constraint dedistortion further improves the clarity and contrast of the picture, making the projection picture more realistic and natural. In addition, the method improves processing efficiency and reduces calculation time through systematic step design, providing an efficient solution for the optimization of the projector optical and mechanical module. This method can improve the projection quality without replacing hardware equipment, and has high economy and practicality.

[0077] In one embodiment, the pre-processed projection picture is enhanced according to the bipolar constraint dedistortion method combined with the fringe feature data to obtain an enhanced picture, including: The epipolar equation is calculated for the fringe feature data to obtain the corresponding initial epipolar parameters. The epipolar equation is calculated based on the known internal and external parameters of the camera and the coordinates of the fringe feature points, and the epipolar equation is derived using the epipolar geometry principle. The initial epipolar parameters include the slope and intercept of the epipolar line, which describe the geometric relationship between the corresponding points in the two images.

[0078] The preprocessed projection image is subjected to the first epipolar constraint processing according to the initial epipolar parameters to obtain preliminary matching point pairs. The first epipolar constraint processing is achieved by searching for potential matching points along the initial epipolar lines in the preprocessed projection image. The search process uses methods such as correlation matching or feature descriptor matching to find the best matching point within a certain range near the epipolar line. The preliminary matching point pairs are a set of point pairs that meet the epipolar constraints and have a high similarity.

[0079] Perform error analysis on the preliminary matching point pairs to obtain the corresponding matching error data. Error analysis includes calculating the Euclidean distance, similarity score and other indicators between the matching point pairs. The matching error data reflects the accuracy and reliability of the preliminary matching results and provides a basis for subsequent parameter optimization.

[0080] The initial epipolar parameters are optimized and adjusted according to the matching error data to obtain the optimized epipolar parameters. The optimization and adjustment process uses the least square method or other optimization algorithms to iteratively optimize the epipolar parameters with the goal of minimizing the matching error. The optimized epipolar parameters more accurately describe the geometric relationship between the two images, which helps to improve the accuracy of subsequent matching.

[0081] The pre-processed projection image is subjected to a second epipolar constraint process based on the optimized epipolar parameters to obtain an accurate matching point set. The second epipolar constraint process uses the optimized epipolar parameters to match within a more accurate search range. This step uses stricter matching conditions and more sophisticated search strategies to screen out high-confidence matching point pairs and form an accurate matching point set.

[0082] The pre-processed projection image is interpolated and reconstructed based on the exact matching point set to obtain the reconstructed image. The interpolation and reconstruction process uses the exact matching point set as the control point and uses bilinear interpolation, cubic spline interpolation and other methods to reconstruct the entire image. This step aims to eliminate the distortion in the image and restore the geometric correctness of the image.

[0083] The reconstructed image is processed by edge enhancement, contrast adjustment and color correction to obtain an enhanced image. Edge enhancement highlights image details through high-pass filtering or nonlinear sharpening algorithm; contrast adjustment uses histogram equalization or adaptive contrast enhancement technology to improve the dynamic range of the image; color correction optimizes the color performance of the image based on color space conversion and white balance algorithm. These processing steps comprehensively improve the visual quality and information expression ability of the image.

[0084] This embodiment achieves efficient enhancement of the pre-processed projection image by combining the double epipolar constraint dedistortion method with stripe feature data. Through the initial epipolar parameter calculation and the first epipolar constraint processing, the preliminary matching point pairs are quickly obtained, laying the foundation for subsequent optimization. The error analysis and parameter optimization links effectively improve the accuracy of the epipolar constraint, ensuring that the second processing can obtain a more accurate set of matching points. The interpolation reconstruction step not only eliminates the image distortion, but also ensures the geometric correctness of the image. The final image adjustment processing combines edge enhancement, contrast adjustment and color correction techniques to comprehensively improve the image quality.

[0085] In one embodiment, the effect of the enhanced image is predicted based on the image optimization trend to obtain the predicted image quality index, and a comprehensive analysis is performed with the initial module adjustment plan to obtain the corresponding global optimization strategy, including: By using a multi-resolution analysis method to decompose the image optimization trend curve at multiple scales, we can obtain trend coefficients at different scales. By using the Gaussian pyramid and Laplace pyramid to downsample and differentiate the trend curve step by step, we can obtain trend information at different scales. By analyzing the changing rules of coefficients at different scales, we can more comprehensively grasp the overall trend of image optimization.

[0086] According to the obtained multi-scale trend coefficients, the enhanced image is adaptively corrected to obtain a corrected image. During the correction process, the brightness, contrast, color saturation and other parameters of the enhanced image are adjusted according to the weights of different scale coefficients. A nonlinear mapping function is used during the adjustment to ensure that the corrected image is more in line with the optimization trend while maintaining the natural transition of the image.

[0087] The corrected image is subjected to frequency domain analysis and spatial domain transformation to obtain the image quality feature matrix. The frequency domain analysis uses discrete cosine transform (DCT) to extract the spectral features of the image; the spatial domain analysis uses the local binary pattern (LBP) method to extract the texture features of the image. The frequency domain and spatial domain features are combined to form an image quality feature matrix to fully characterize the image quality.

[0088] The image quality feature matrix is ​​convolved with the preset image quality evaluation parameters to obtain the predicted image quality index. The image quality evaluation parameters include weight coefficients such as clarity, contrast, and color reproduction. Through the convolution operation, the predicted image quality index that comprehensively considers multiple factors is obtained. The convolution process uses the sliding window method to ensure full utilization of the global features of the image.

[0089] The initial module adjustment plan is calculated based on the predicted picture quality index to obtain the quality optimization parameters. During the calculation process, the predicted picture quality index is compared and analyzed with the various parameters of the initial plan, and the gradient descent method is used to optimize the various parameters to obtain the specific parameters that need to be optimized and the optimization range, forming the quality optimization parameters.

[0090] The initial module adjustment plan is optimized based on the quality optimization parameters combined with the predicted picture quality index to obtain a global optimization strategy. The optimization process uses a genetic algorithm, with the quality optimization parameters as the gene and the predicted picture quality index as the fitness function. The optical parameters and image processing algorithms of the initial plan are comprehensively adjusted. Through multiple generations of iterative optimization, a global optimization strategy that can maximize the picture quality is formed.

[0091] This embodiment can fully capture the trend characteristics at different scales by performing multi-scale analysis on the picture optimization trend, provide a more comprehensive basis for subsequent optimization, and improve the accuracy and adaptability of optimization. The Gaussian pyramid and Laplace pyramid are used for multi-scale decomposition, which avoids the complex calculation of traditional wavelet transform and improves processing efficiency. The image quality features are extracted by combining frequency domain and spatial domain analysis to fully characterize the image quality and overcome the limitations of single domain analysis. The DCT and LBP methods are used to capture the spectral characteristics of the image and extract texture information, providing a more comprehensive basis for image quality evaluation. By combining convolution operations with multiple image quality evaluation parameters, a predicted image quality index that comprehensively considers multiple factors is obtained, which improves the accuracy and comprehensiveness of the evaluation. The sliding window method is used for convolution to ensure that the global features of the image are fully utilized.

[0092] Reference Figure 2 As shown, the present invention also provides a projector optical-mechanical module optimization system, which is applied to any one of the above-mentioned projector optical-mechanical module optimization methods, including: The acquisition module is used to obtain the light source system parameters and projection environment data of the projector optical module, perform adaptive adjustments, and obtain the initialization light source output parameters; An analysis module is used to obtain real-time operation data of the projector optical and mechanical module, associate it with the initialization light source output parameters, and obtain corresponding real-time projection status information; The association module is used to obtain the projection picture data of the projector optical module, perform quality evaluation on the real-time projection status information, and obtain the corresponding picture optimization trend; A processing module is used to analyze the real-time projection status information and the picture optimization trend to obtain the corresponding initial module adjustment plan; A control module, the control module is used to perform projection image distortion preprocessing and bipolar line constraint dedistortion on the projection picture data to obtain an enhanced picture; The execution module is used to predict the effect of the enhanced image based on the image optimization trend, obtain the predicted image quality index, and conduct a comprehensive analysis with the initial module adjustment plan to obtain the corresponding global optimization strategy.

[0093] The present invention provides a projector optical-mechanical module optimization system, which realizes real-time monitoring and evaluation of the projection state by associating the real-time operation data and the initialization light source output parameters, and provides a reliable basis for dynamic adjustment. The quality of the real-time projection state is evaluated according to the projection picture data, and the picture optimization trend is obtained, so that the optimization process is more targeted and forward-looking. The projection picture is enhanced by a preset image processing method, and the effect is predicted in combination with the picture optimization trend, which greatly improves the quality of the projection picture. Finally, by comprehensively analyzing the initial module adjustment plan and the predicted picture quality index, a global optimization strategy is formulated, and the overall performance of the projector optical-mechanical module is improved. This multi-dimensional and dynamic optimization method not only overcomes the limitation of the traditional method that only focuses on a single factor, but also can effectively cope with complex and changeable projection environments and user needs. Through real-time evaluation and dynamic adjustment, the method significantly improves the stability and adaptability of the projection quality, and provides users with a better visual experience. At the same time, this intelligent optimization strategy also provides technical support for the flexible adjustment of the projector in different application scenarios, and expands the application scope of the projection equipment.

[0094] Reference Figure 3 As shown, the present invention also provides a computer device for optimizing a projector optical-mechanical module, comprising: Memory, used to store programs; The processor is used to execute the program to implement each step of any one of the above-mentioned projector optical-mechanical module optimization methods.

[0095] In this embodiment, the processor and the memory may be connected via a bus or other means. The memory may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a read-only memory, a flash memory, a hard disk, or a solid-state drive. The processor may be a general-purpose processor, such as a central processing unit, a digital signal processor, an application-specific integrated circuit, or one or more integrated circuits configured to implement the embodiments of the present invention.

[0096] It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and conciseness of description, the specific working process of the system and each module described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0097] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for optimizing a projector optical-mechanical module, characterized in that: include: Obtain the light source system parameters and projection environment data of the projector optical module, perform adaptive adjustments, and obtain the initialization light source output parameters; Acquire the real-time operation data of the optical-mechanical module of the projector, and associate it with the output parameters of the initialized light source to obtain corresponding real-time projection status information; Acquire projection picture data of the projector optical-mechanical module, perform quality assessment on the real-time projection state information, and obtain corresponding picture optimization trends; Performing a solution analysis on the real-time projection status information and the picture optimization trend to obtain a corresponding initial module adjustment solution; Performing projection image distortion preprocessing and bipolar line constraint dedistortion on the projection picture data to obtain an enhanced picture; Based on the picture optimization trend, the effect of the enhanced picture is predicted to obtain a predicted picture quality index, and a comprehensive analysis is performed with the initial module adjustment plan to obtain a corresponding global optimization strategy.

2. The projector optical-mechanical module optimization method according to claim 1, characterized in that: The step of obtaining the light source system parameters and projection environment data of the projector optical machine module and performing adaptive adjustment to obtain the corresponding initialization light source output parameters includes: Collect the light source system parameters of the projector optical module, including light source brightness, color temperature, spectral distribution and power consumption data; Obtain projection environment data, including ambient light intensity, projection distance, and projection surface reflectivity; Performing nonlinear scaling processing on the light source system parameters and projection environment data to obtain a nonlinear scaling parameter set; Performing cluster analysis on the nonlinear scaling parameter set according to a preset mean clustering method to obtain an initial light source adjustment factor; Preliminarily adjusting the light source system parameters according to the initial light source adjustment factor to obtain adjusted light source parameters; Performing nonlinear fitting on the adjusted light source parameters according to an improved Levenberg-Marquardt algorithm to obtain fitting light source parameters; Optimizing the fitting light source parameters according to a preset multi-objective differential evolution algorithm to obtain an initialized light source parameter set; The light source output is adjusted according to the initialization light source parameter set to obtain the initialization light source output parameters.

3. The projector optical-mechanical module optimization method according to claim 1, characterized in that: The acquiring of the real-time operation data of the projector optical machine module and the associating processing with the initialization light source output parameter to obtain the corresponding real-time projection state information includes: Performing real-time status monitoring on the projector optical and mechanical module to obtain corresponding real-time operating data; Constructing a correlation matrix according to the real-time operation data and the initialized light source output parameters to obtain a light source parameter correlation matrix; Adaptively adjusting the driving current and driving voltage of the projector optical-mechanical module based on the light source parameter association matrix to obtain adjusted light source parameters; Performing time series analysis on the adjusted light source parameters to obtain a change trend of the light source parameters; According to the changing trend of light source parameters, the light source state in the future is predicted to obtain the predicted light source state; The adjusted light source parameters and the predicted light source state are subjected to state analysis to obtain the real-time projection state information.

4. The projector optical-mechanical module optimization method according to claim 1, characterized in that: The acquiring of the projection picture data of the optical-mechanical module of the projector, performing quality evaluation on the real-time projection state information, and obtaining a corresponding picture optimization trend includes: Performing color space analysis and brightness distribution analysis on the projection picture of the projector optical module to obtain corresponding projection picture data; Performing frequency decomposition on the projection picture data to obtain a plurality of frequency sub-band images; Performing local contrast analysis on the plurality of frequency sub-band images respectively to obtain corresponding local contrast indicators; Adaptively allocating the plurality of frequency sub-band images according to the local contrast index to obtain a fusion coefficient; Reconstructing and fusing the plurality of frequency sub-band images according to the fusion coefficients to obtain enhanced picture data; Performing clarity analysis on the enhanced picture data to obtain a picture clarity evaluation index; Correlation analysis is performed on the picture clarity evaluation index and the real-time projection state information to obtain a picture quality evaluation result; Performing trend analysis on the picture quality evaluation result to obtain the picture optimization trend.

5. The projector optical-mechanical module optimization method according to claim 1, characterized in that: The performing of solution analysis on the real-time projection status information and the picture optimization trend to obtain a corresponding initial module adjustment solution includes: Performing multi-dimensional feature extraction on the real-time projection state information to obtain a projection state feature vector; Calculating a corresponding correlation degree according to the projection state feature vector and the picture optimization trend to obtain a state optimization correlation degree; Perform parameter sensitivity analysis based on the state optimization correlation to obtain a key adjustment parameter set; Performing multi-objective constraint optimization on the key adjustment parameter set to obtain initial adjustment parameters; Performing ray tracing analysis on the projector optical-mechanical module according to the initial adjustment parameters to obtain an optical path optimization solution; According to the optical path optimization scheme, a simulation is performed on the drive circuit parameter adjustment of the projector optical-mechanical module to obtain a drive optimization scheme; The optical path optimization scheme and the drive optimization scheme are integrated to obtain the initial module adjustment scheme.

6. The projector optical-mechanical module optimization method according to claim 1, characterized in that: The performing projection image distortion preprocessing and bipolar constraint dedistortion on the projection picture data to obtain an enhanced picture includes: Performing distortion analysis on the projection picture data to obtain corresponding distortion parameters; Establishing a distortion correction algorithm according to the projection image distortion preprocessing method in combination with the distortion parameters, wherein the distortion correction algorithm includes correction of radial distortion and tangential distortion; Calculating the mapping relationship between each pixel point in the projection picture data and the corresponding point in the standard distortion-free image according to the distortion correction algorithm; Mapping the projection picture data onto the standard distortion-free image according to the mapping relationship to obtain mapping coordinates, and performing interpolation processing to obtain reconstructed pixel values; Reconstructing the image according to the reconstructed pixel values ​​to obtain a pre-processed projection picture that has been corrected for distortion; Performing unidirectional fringe extraction on the preprocessed projection image to obtain corresponding fringe feature data; The preprocessed projection picture is enhanced according to the bipolar constraint dedistortion method in combination with the stripe feature data to obtain the enhanced picture.

7. The projector optical-mechanical module optimization method according to claim 6, characterized in that: The step of performing image enhancement processing on the preprocessed projection image according to the bipolar constraint dedistortion method in combination with the fringe feature data to obtain the enhanced image includes: Performing epipolar equation calculation on the fringe characteristic data to obtain corresponding initial epipolar parameters; Performing a first epipolar constraint process on the preprocessed projection image according to the initial epipolar parameters to obtain preliminary matching point pairs; Performing error analysis on the preliminary matching point pairs to obtain corresponding matching error data; Optimizing and adjusting the initial epipolar parameters according to the matching error data to obtain optimized epipolar parameters; Performing a second epipolar constraint process on the preprocessed projection image according to the optimized epipolar parameters to obtain an accurate matching point set; Interpolating and reconstructing the preprocessed projection picture according to the precise matching point set to obtain a reconstructed picture; The reconstructed picture is subjected to picture adjustment processing including edge enhancement, contrast adjustment and color correction to obtain the enhanced picture.

8. The projector optical-mechanical module optimization method according to claim 1, characterized in that: The effect of the enhanced image is predicted based on the image optimization trend to obtain a predicted image quality index, and a comprehensive analysis is performed with the initial module adjustment plan to obtain a corresponding global optimization strategy, including: Performing a scale transformation on the picture optimization trend to obtain a multi-scale trend coefficient; Adaptively correcting the enhanced picture according to the multi-scale trend coefficient to obtain a corrected image; Performing frequency domain analysis and spatial domain transformation on the corrected image to obtain an image quality feature matrix; Performing a convolution operation on the image quality feature matrix and a preset image quality evaluation parameter to obtain a predicted image quality index; Calculating the index of the initial module adjustment scheme according to the predicted picture quality index to obtain quality optimization parameters; The initial module adjustment scheme is optimized according to the quality optimization parameter in combination with the predicted picture quality index to obtain the global optimization strategy.

9. A projector optical-mechanical module optimization system, characterized in that: The projector optical-mechanical module optimization method applied to any one of claims 1 to 8 above comprises: An acquisition module, which is used to obtain light source system parameters and projection environment data of the projector optical machine module, perform adaptive adjustments, and obtain initialization light source output parameters; An analysis module, the analysis module is used to obtain the real-time operation data of the projector optical and mechanical module, and associate it with the initialization light source output parameters to obtain corresponding real-time projection status information; An association module, the association module is used to obtain projection picture data of the projector optical and mechanical module, perform quality evaluation on the real-time projection state information, and obtain a corresponding picture optimization trend; A processing module, the processing module is used to perform a solution analysis on the real-time projection state information and the picture optimization trend to obtain a corresponding initial module adjustment solution; A control module, the control module is used to perform projection image distortion preprocessing and bipolar line constraint dedistortion on the projection picture data to obtain an enhanced picture; An execution module is used to predict the effect of the enhanced image based on the image optimization trend, obtain a predicted image quality index, and perform a comprehensive analysis with the initial module adjustment plan to obtain a corresponding global optimization strategy.

10. A computer device for optimizing a projector optical-mechanical module, characterized in that: include: Memory, used to store programs; A processor is used to execute the program to implement each step of a projector optical-mechanical module optimization method as described in any one of claims 1-8.

Images