Full-automatic correction method and device for LED display screen

Abstract

The invention provides a full-automatic correction method and device for an LED display screen, and belongs to the technical field of display screen correction. The problems that an existing LED display screen correction method is low in efficiency, limited in precision, incapable of achieving dynamic adjustment and the like are solved. Comprising the following steps: starting correction: initializing a system; a user sets a target; connecting the correction equipment and verifying whether the equipment is successfully connected; initial data collection; carrying out AI pre-analysis; the main correction comprises the steps of parameter adjustment, wherein the display screen parameters are preliminarily adjusted according to the initial correction coefficient and whether the display screen parameters reach the standard or not is judged; carrying out multiple iterations on substandard objects; two-dimensional judgment: judging whether the correction coefficient after each iteration can reach the standard or not, and predicting whether the correction coefficient possibly exceeds the target parameter or not through an ultra-optimal solution prediction model; outputting an optimal parameter according to the multiple iterations, and generating two schemes; the invention is applied to the LED display screen.

Description

Technical Field

[0001] The present application relates to the technical field of display screen correction, and in particular to a fully automatic correction method and device for an LED display screen. Background Art

[0002] During the installation phase, LED display calibration is essential to ensure optimal display quality. However, current LED display calibration methods primarily rely on manual operation, which is inefficient and prone to errors. Furthermore, existing calibration methods cannot adjust the calibration effect in real time, making it difficult to adapt to changes in brightness and chromaticity under different usage environments. Regarding the light decay of LED lamp beads, existing methods only adjust the calibration coefficient based on usage time, which fails to accurately reflect actual light decay and results in suboptimal calibration results. Existing calibration methods cannot achieve differentiated adjustment of the R, G, and B single-color attenuation and compensation ratios, making it difficult to meet the needs of high-precision displays.

[0003] In summary, the existing LED display screen calibration method has the following disadvantages: The calibration process is complicated and requires professional operation, which increases labor costs; The calibration cycle is long and cannot quickly respond to changes in the brightness and color of the display; The correction accuracy is limited, making it difficult to achieve highly uniform and consistent display effects. Summary of the Invention

[0004] In order to solve the problems of low efficiency, limited accuracy, and inability to dynamically adjust existing LED display screen correction methods, this application proposes a fully automatic correction method and device for LED display screens that can meet high-precision display requirements.

[0005] The technical solution adopted in this application is: a fully automatic calibration method for an LED display screen, comprising the following steps: S1: Start calibration, including: S101: System initialization; S102: User setting: The user inputs target parameters and selects an optimization mode according to needs; S103: Connect the calibration device and verify whether the device is connected successfully; S104: Initial Data Collection: A multispectral camera and luminance meter are used to synchronously collect the full-screen color and luminance values ​​of the display screen from the initial power-off state, through the heating process after power-on, and to the maximum heating value. A temperature sensor is also used to collect the display screen temperature value in real time. An initial report is then generated, which includes a luminance uniformity distribution heat map, a chromaticity CIE1976 scatter plot, and a temperature curve. S105: AI pre-analysis: Use the AI ​​model to identify the brightness uniformity distribution diagram and the chromaticity CIE1976 scatter diagram, and generate initial correction coefficients; S2: Main calibration, including: S201: Parameter adjustment: Preliminary adjustment of display screen parameters based on initial calibration coefficients; then proceeding to step S203 to compare the adjusted display screen parameters with the user's target parameters to determine whether they meet the standards. If not, proceeding to step S202 for iterative optimization mode; S202: Data re-collection: After the parameter adjustment in step S201, if the parameters do not meet the standards, it is necessary to repeat step S104 to re-collect the data, and perform AI pre-analysis in step S105 to obtain the correction coefficients of the first iteration. The display parameters are re-adjusted based on the correction coefficients of the first iteration, and the adjusted display parameters are obtained and compared with the initial report to generate a difference report; S203: Two-dimensional judgment: Adjust the display screen parameters according to the correction coefficient after each iteration, compare the adjusted display screen parameters with the target parameters set by the user, and determine whether they reach the user's target parameters. If they reach the target parameters, record the parameters of the current iteration and enter the super-optimal solution detection step. Use the super-optimal solution prediction model to predict whether it is possible to exceed the target parameters. If it can be exceeded, start the genetic algorithm optimization and record the final optimized parameters. If it cannot be exceeded, record the parameters of the current iteration as the optimal parameters. If the target parameters set by the user are not reached, execute the gradient descent optimization algorithm to achieve rapid convergence; S3: Output decision: Output the optimal parameters after multiple iterations and generate two solutions.

[0006] Furthermore, in the process of performing multiple data re-collection in step S202 and multiple iterative judgments in step S203, an anti-dead loop mechanism in step S204 is added.

[0007] Furthermore, the anti-dead loop mechanism includes a triple anti-dead loop mechanism of iteration counter, convergence detection and timeout forced exit. When any one of them is met, the iterative calculation can be forced to exit.

[0008] Furthermore, the AI ​​model used in AI pre-analysis is a convolutional neural network.

[0009] Furthermore, the super-optimal solution prediction model uses an LSTM neural network to predict the hardware limits of the display system in the display screen.

[0010] Furthermore, the two output solutions are Solution A that meets the user-set parameters and Solution B with super-optimal parameters recommended by AI. The two output solutions can be visualized and the optimal parameters can be stored.

[0011] Furthermore, the target parameters set by the user include brightness, chroma and optimization control parameters, the optimization modes include standard mode and aggressive mode, and the optimization control parameters include the maximum number of iterations and the convergence judgment threshold.

[0012] Furthermore, the user can individually adjust the R, G, and B single color values ​​and compensation ratios on the PC before or after calibration.

[0013] Furthermore, the parameter adjustment in step S201 is achieved by using the least squares method to calculate the compensation matrix of each pixel, inputting the correction coefficient obtained in each iteration into the lookup table of the display screen, and the driver IC adjusts the PWM duty cycle and RGB mixing ratio according to the region to achieve adjustment of the display screen parameters.

[0014] A computer device comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method.

[0015] The beneficial effects of this application compared to the prior art are: High efficiency: The fully automatic calibration process greatly shortens the calibration time and improves work efficiency; High precision: Through multiple rounds of optimization and dynamic adjustment, high uniformity and high consistency of display effects are achieved; Flexibility: supports user-defined correction effect levels to meet the needs of different application scenarios; Intelligent: Automatically determine the correction effect without manual intervention, reducing the difficulty of operation; Reduce labor costs: Reduce dependence on professional correction personnel and reduce labor costs; Improve equipment utilization: Rapid correction improves equipment availability and extends equipment life; Improve market competitiveness: High-precision calibration technology can increase product added value and enhance market competitiveness; Promote industry development: Provides an efficient and accurate calibration method for the LED display industry, promoting technological progress in the industry; Improve user experience: High-precision calibration can improve display effects and enhance user visual experience; Energy saving and environmental protection: By optimizing the calibration process, the energy consumption of the equipment is reduced, which complies with the concept of energy saving and environmental protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present application will be further described below with reference to the accompanying drawings: Figure 1 A flow chart of the method provided in the embodiment of the present application; Figure 2 This is a calibration flow chart provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] like Figure 1 and 2 As shown, the present application provides a fully automatic correction method for an LED display screen. By setting the correction effect level, the brightness and chromaticity of each pixel are self-adjusted, and the correction effect is gradually optimized through multiple uploads of correction coefficients and multiple rounds of repeated operations of camera acquisition and judgment, and finally the set target effect is achieved. Its main implementation steps are: setting the correction effect level, and the user can choose different correction accuracy and effects according to actual needs. After the connection of the correction equipment system is completed, the correction program is automatically started to achieve self-adjustment of brightness and chromaticity. By using multiple uploads of correction coefficients and multiple rounds of repeated operations of camera acquisition and judgment, the correction effect is gradually optimized until the set target effect is achieved. According to the corrected effect collected by the camera, the brightness and chromaticity attenuation and compensation ratio are dynamically adjusted to achieve different adjustments of R, G, and B monochrome attenuation and compensation ratios. When the improvement of the correction effect after multiple rounds is almost unchanged, the correction task is automatically ended and the final correction effect is output.

[0018] The following is based on the attached Figure 1 and 2 The method of this application is described in detail, and its specific steps are as follows: S1: Start calibration: including: S101: System initialization: Start the system calibration program, initialize system parameters, and prepare to enter the setting process.

[0019] S102: User settings: The user enters the target parameters and selects the optimization mode (calibration accuracy level) according to the requirements. Different optimization modes have different accuracy levels. The accuracy level will affect the number of subsequent adjustments, the parameter step size, and the allowable error range (e.g., high-precision requires chromaticity △E < 2, standard requires chromaticity △E < 5); The target parameters input in this embodiment include brightness, chromaticity ΔE and optimization control parameters, among which brightness mainly considers brightness uniformity and is expressed in percentage, such as 95%. Brightness-related parameters include target brightness value and allowable tolerance range; chromaticity-related parameters include target chromaticity coordinates and ΔE qualified threshold; optimization control parameters include the maximum number of iterations and convergence judgment threshold.

[0020] In this embodiment, there are two optimization modes: standard mode (safe mode) and aggressive mode. The aggressive mode has higher requirements for brightness uniformity and lower chromaticity ΔE than the standard mode, thereby achieving higher accuracy requirements and achieving the best correction effect within the hardware limits of the display control system. For example, in the standard mode, the final brightness and chromaticity must maintain an error of approximately ±3% from the target parameters, while in the aggressive mode, the final brightness and chromaticity must maintain an error of approximately ±0.5% from the target parameters.

[0021] S103: Connecting the calibration device and verifying: After the user sets the target parameters and optimization mode, the corresponding calibration device is connected and the device response time is tested by sending instructions to determine whether the device is connected successfully. If the device is connected successfully, the device parameters are initialized. If the device connection fails, an alarm is triggered to prompt the user to check the physical connection of the interface or install the driver. An automatic retry mechanism is also supported. The calibration equipment includes a calibrator (brightness meter), which is connected to the display control system via a USB / network port. The system automatically identifies the device driver and confirms that the communication protocol handshake is successful. After the calibrator initializes its parameters, it loads the pre-stored parameters for the display model (such as default brightness and color temperature) by default. It then begins capturing a full-screen uniformity test pattern (such as full white / full red / full green / full blue) of the display using the default connected multispectral camera. If the calibrator fails to initialize its parameters, it starts dynamic calibration. Dynamic calibration requires the use of the ambient light sensor to adjust the initial value in real time to compensate for ambient light effects. The ambient light sensor is primarily used to sense ambient light intensity, enabling optimized parameter compensation settings. The initial value is a parameter compensation value applied to the calibration effect based on the ambient light sensor's perception of the surrounding environment. This compensation value is the initial value.

[0022] The multispectral camera is connected to the display control system through the Camera Link interface. The system automatically identifies the device driver and confirms that the communication protocol handshake is successful. The multispectral camera can use a high-precision CCD camera. S104: Initial Data Collection: A multispectral camera and luminance meter are used to synchronously collect the full-screen color block (RGBW + 50% gray) and brightness values ​​of the display screen from the initial power-off state, through the heating process after power-on, and to the maximum heating value. The temperature value of the display screen is collected in real time through a temperature sensor, and an initial report is generated. The initial report includes a brightness uniformity distribution heat map, a chromaticity CIE1976 scatter plot, and a temperature curve. The brightness uniformity distribution heat map is generated by sequentially stacking multiple images of the display screen heating process captured by a camera over time. The chromaticity CIE1976 scatter plot is generated by sequentially stacking the brightness values ​​of the display screen heating process captured by a luminance meter over time. During this process, the display screen temperature values ​​captured by the temperature sensor are converted into a temperature curve.

[0023] S105: AI pre-analysis: A convolutional neural network is used to identify the brightness uniformity distribution map and the chromaticity CIE1976 scatter plot, identify hot spots and mosaic effects, and generate initial compensation suggestions. The initial compensation suggestions are initial correction coefficients (including RGB channel compensation parameters, pixel-level compensation parameters, and uniformity optimization parameters). The intervention value of the initial correction coefficient can be adjusted according to the temperature curve. The intervention value refers to a specific value used to adjust the initial correction coefficient.

[0024] S2: Main correction: including: S201: Parameter Adjustment: The least squares method is used to calculate the compensation matrix for each pixel. The initial correction coefficients are entered into the display's lookup table. The driver IC adjusts the PWM duty cycle and RGB mixing ratio by region to adjust the display parameters. The process then proceeds to step S203, where the adjusted display parameters are compared with the user's target parameters. The full-screen uniformity index (e.g., brightness standard deviation σ ≤ 5%) is calculated. If the target is met, a PDF report is generated, including before-and-after comparison images and the percentage of brightness uniformity improvement. If the target is not met, the process proceeds to step S202 for iterative optimization.

[0025] S202: Data re-collection: After the parameter adjustment in S201, if the standard is not met, it is necessary to repeat step S104 for data re-collection, and perform AI pre-analysis in step S105 to obtain the correction coefficient of the first iteration. The display parameters are readjusted according to the correction coefficient of the first iteration, and the adjusted display parameters are obtained and compared with the initial report to generate a difference report.

[0026] S203: Two-dimensional judgment: adjust the display screen parameters according to the correction coefficient after each iteration, and compare the display screen parameters after each adjustment with the target parameters set by the user. If the target parameters set by the user are reached, the parameters of the current iteration are recorded, and the super-optimal solution detection step is entered. The super-optimal solution prediction model is used to predict whether it is possible to exceed the target parameters. If it can be exceeded, the genetic algorithm optimization is started and the final optimized parameters are recorded. If it cannot be exceeded, the parameters of the current iteration are recorded as the best parameters. If the target parameters set by the user are not reached, the gradient descent optimization algorithm is executed to achieve rapid convergence; the purpose of executing the gradient descent optimization algorithm is to quickly adjust the correction coefficient and other parameters by calculating the gradient direction of the loss function when the display screen parameter adjustment does not reach the target parameters set by the user, so that the algorithm is iteratively updated along the optimal path, thereby accelerating convergence to the optimal solution close to the target parameters.

[0027] In this embodiment, the super-optimal solution prediction model uses an LSTM neural network to predict hardware potential.

[0028] S204: Anti-dead loop mechanism: An anti-dead loop mechanism is added during the process of multiple data re-collection in step S202 and multiple iterative judgments in step S203. The anti-dead loop mechanism includes a set iteration counter, convergence detection, and timeout forced exit triple anti-dead loop mechanism. When any one of them is met, it can be forced to exit. The iteration counter is set to a maximum of 20 iterations in this embodiment, and forced exit is performed after more than 20 iterations; convergence detection is achieved by determining whether the chromaticity △E fluctuation in the last 5 rounds is less than 0.2 or whether the brightness standard deviation σ value fluctuation in the last 3 iterations is less than 0.5%. If the △E fluctuation is less than 0.2 or the σ fluctuation is less than 0.5%, it is determined that there is no improvement, indicating that there is no convergence. At this time, the genetic algorithm is enabled to optimize the compensation coefficient to avoid local optimal solutions; the timeout forced exit is set to 30 minutes in this embodiment, and forced exit is performed after more than 30 minutes.

[0029] S3: Output decision: Based on the above multiple iterations, the optimal parameters are output, two solutions are generated, and they are visualized and stored. The two solutions are: Solution A that meets the user's set parameters and Solution B with AI-recommended super-optimal parameters; the visualization includes a view that displays the color gamut coverage comparison side by side and a view that dynamically demonstrates the difference in gamma curves; the optimal parameters can be written to the non-volatile memory of the controller of the display control system and synchronized to the cloud backup (transmitted using the AES-256 encryption algorithm), supporting fast call.

[0030] Among them, Solution B, which uses AI to recommend super-optimal parameters, is a parameter solution generated by AI optimization methods such as genetic algorithms after the super-optimal solution prediction model determines that there is potential for surpassing.

[0031] After the automatic calibration is completed, the calibration device is disconnected to release system resources and the operation log (including timestamp, operator ID, and relationship parameter snapshot) is recorded.

[0032] The present application also supports different adjustments of R, G, and B single color attenuation and compensation ratios, and this process can be implemented separately before or after the automatic correction process.

[0033] The typical workflow example for this application is as follows: 1. User sets △E≤3.0 and selects "Standard Mode"; 2. After 8 rounds of iteration, the system reaches △E=2.9; 3. AI detected that it could be optimized to △E=2.3 (requires 3 additional iterations); 4. Generate: Solution A: ΔE=2.9 (power consumption reduced by 15%); Solution B: △E=2.3 (color gamut expanded by 8%); 5. The user selects the final solution based on actual needs.

[0034] The following is a partial program that uses Python coding to implement automatic correction of this application: 1. Target parameter settings: .

[0035] 2. Initial data collection and AI preprocessing: ; The above-mentioned simulated data refers to virtual data generated during the algorithm iteration or model training process to verify the optimization strategy, test the algorithm performance or pre-adjust the auxiliary parameters, rather than the actual measurement data directly collected by hardware devices such as luminance meters and colorimetry cameras.

[0036] 3. Generated adjustment results: ; Adjust the brightness and chroma pixel by pixel according to the brightness adjustment curve and chroma adjustment track generated above.

[0037] 4. Multiple rounds of iteration: .

[0038] This application can achieve: Automated calibration: It realizes fully automatic operation from calibration equipment connection to calibration completion, without manual intervention, thus improving calibration efficiency.

[0039] Dynamic optimization: Through multiple rounds of repeated operations and dynamic adjustments, the correction effect is gradually optimized to ensure correction accuracy.

[0040] Differentiated adjustment: supports different adjustments of R, G, and B monochrome attenuation and compensation ratios to meet high-precision display requirements.

[0041] Intelligent judgment: Through camera acquisition and judgment, the correction effect is monitored in real time to ensure the accuracy and reliability of the correction process.

[0042] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A fully automatic calibration method for an LED display, characterized by: The following steps are involved: S1: Start calibration, including: S101: System initialization; S102: User setting: The user inputs target parameters and selects an optimization mode according to needs; S103: Connect the calibration device and verify whether the device is connected successfully; S104: Initial Data Collection: A multispectral camera and luminance meter are used to synchronously collect the full-screen color and luminance values ​​of the display screen from the initial power-off state, through the heating process after power-on, and to the maximum heating value. A temperature sensor is also used to collect the display screen temperature value in real time. An initial report is then generated, which includes a luminance uniformity distribution heat map, a chromaticity CIE1976 scatter plot, and a temperature curve. S105: AI pre-analysis: Use the AI ​​model to identify the brightness uniformity distribution diagram and the chromaticity CIE1976 scatter diagram, and generate initial correction coefficients; S2: Main calibration, including: S201: Parameter adjustment: Preliminary adjustment of display screen parameters based on initial calibration coefficients; then proceeding to step S203 to compare the adjusted display screen parameters with the user's target parameters to determine whether they meet the standards. If not, proceeding to step S202 for iterative optimization mode; S202: Data re-collection: After the parameter adjustment in step S201, if the parameters do not meet the standards, it is necessary to repeat step S104 to re-collect the data, and perform AI pre-analysis in step S105 to obtain the correction coefficients of the first iteration. The display parameters are re-adjusted based on the correction coefficients of the first iteration, and the adjusted display parameters are obtained and compared with the initial report to generate a difference report; S203: Two-dimensional judgment: Adjust the display screen parameters according to the correction coefficient after each iteration, compare the adjusted display screen parameters with the target parameters set by the user, and determine whether they reach the user's target parameters. If they reach the target parameters, record the parameters of the current iteration and enter the super-optimal solution detection step. Use the super-optimal solution prediction model to predict whether it is possible to exceed the target parameters. If it can be exceeded, start the genetic algorithm optimization and record the final optimized parameters. If it cannot be exceeded, record the parameters of the current iteration as the optimal parameters. If the target parameters set by the user are not reached, execute the gradient descent optimization algorithm to achieve rapid convergence; S3: Output decision: Output the optimal parameters after multiple iterations and generate two solutions.

2. The fully automatic calibration method for an LED display according to claim 1, characterized in that: During the process of multiple data re-collection in step S202 and multiple iterative judgments in step S203, an anti-dead loop mechanism in step S204 is added.

3. The fully automatic calibration method for an LED display according to claim 2, characterized in that: The anti-dead loop mechanism includes a triple anti-dead loop mechanism of iteration counter, convergence detection and timeout forced exit. When any one of these conditions is met, the iterative calculation can be forced to exit.

4. The fully automatic calibration method for an LED display screen according to claim 3, characterized in that: The AI ​​model used in AI pre-analysis is convolutional neural network.

5. The fully automatic calibration method for an LED display screen according to claim 3, characterized in that: The super-optimal solution prediction model uses an LSTM neural network to predict the hardware limits of the display system in the display.

6. The fully automatic calibration method for an LED display screen according to claim 3, characterized in that: The two output solutions are Solution A that meets the user's set parameters and Solution B with super-optimal parameters recommended by AI. The two output solutions can be visualized and the optimal parameters can be stored.

7. A fully automatic calibration method for an LED display according to any one of claims 1 to 6, characterized in that: The target parameters set by the user include brightness, chromaticity and optimization control parameters. The optimization modes include standard mode and aggressive mode. The optimization control parameters include the maximum number of iterations and the convergence judgment threshold.

8. The fully automatic calibration method for an LED display screen according to claim 7, characterized in that: Before or after calibration, users can adjust the R, G, and B single color dithering and compensation ratios individually on the PC.

9. The fully automatic calibration method for an LED display screen according to claim 7, characterized in that: The parameter adjustment in step S201 is achieved by using the least squares method to calculate the compensation matrix of each pixel, inputting the correction coefficient obtained in each iteration into the lookup table of the display screen, and the driver IC adjusts the PWM duty cycle and RGB mixing ratio according to the area to achieve adjustment of the display screen parameters.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory, wherein: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 9.

Images