LED screen brightness balancing method based on dynamic toning algorithm

Abstract

The invention discloses an LED screen brightness balancing method based on a dynamic toning algorithm, and the method comprises the following steps: dividing the display content of an LED screen into a plurality of partitions according to a physical structure, and obtaining the display content data of the partitions; environment illumination intensity, temperature and actual brightness of each partition are collected in real time, and partition environment parameter data are obtained; performing feature fusion on the partition display content data and the partition environment parameter data to generate partition joint feature data; the partition joint feature data are input into a partition CycleGAN model, and partition enhanced content data are output; outputting overall enhanced display content data obtained by seamlessly splicing the partitioned enhanced content data to an LED screen driving system; and continuously collecting the actual display effect and environment change of each partition, obtaining partition feedback data, and inputting the partition feedback data to the partition CycleGAN model. According to the invention, the partition CycleGAN and the multi-objective loss optimization are adopted, so that the brightness balance of the LED screen is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of LED display and intelligent image processing technology, and particularly relates to an LED screen brightness equalization method based on a dynamic color adjustment algorithm. BACKGROUND

[0002] At present, LED display screens are widely used in the fields of advertising media, traffic indication, stage performance and monitoring command. With the continuous expansion of the area of LED screens and the continuous improvement of the requirements for display quality, the traditional overall brightness and color adjustment method has been difficult to meet the actual needs. In the prior art, LED screen brightness equalization usually relies on global brightness mapping, static color correction or a simple partitioned brightness adjustment scheme. These methods mainly adjust the whole screen or local area with fixed parameters or preset strategies, and cannot achieve fine response to different regional environmental changes and dynamic content. The existing partitioned adjustment method mainly uses a brightness or color sensor feedback based on hardware sampling, combined with a partitioned correction based on rules or linear algorithms, but the interaction between multiple partitions, seamless connection at the boundary, color consistency and dynamic adaptive ability are not considered, which easily leads to problems such as brightness discontinuity, color discontinuity and slow environmental adaptive response between partitions.

[0003] In addition, with the popularization of high-resolution large screens and outdoor complex environments, the demand for dynamic brightness equalization and color optimization of LED screens in strong light interference, temperature change and environmental diversity scenarios is more prominent. Although the existing deep learning-based image enhancement or style transfer methods have made progress in the field of image processing, they are mostly aimed at natural images or single content enhancement, and lack systematic solutions to the problems of multi-source data fusion, partition-level adaptive color adjustment and seamless splicing in the partitioned scenario of LED screens.

[0004] Therefore, how to provide an LED screen brightness equalization method based on a dynamic color adjustment algorithm is a problem that those skilled in the art need to solve. SUMMARY

[0005] One object of the present application is to provide an LED screen brightness equalization method based on a dynamic color adjustment algorithm. The present application combines partition feature extraction, partitioned CycleGAN neural network, partitioned environmental parameter fusion and multi-objective loss optimization, and describes in detail the overall process of realizing dynamic adaptive equalization of brightness and color, seamless splicing and online feedback optimization in a multi-partitioned LED screen. The method has the advantages of strong brightness equalization, high color consistency, excellent environmental adaptability and natural and continuous display effect, and can effectively improve the intelligent display quality and user experience of various LED display screens in complex scenarios.

[0006] A method for equalizing the brightness of an LED screen based on a dynamic color adjustment algorithm according to an embodiment of the present invention includes the following steps:

[0007] The LED screen's display content is divided into multiple zones based on its physical structure to obtain the zone display content data;

[0008] For each zone, the ambient light intensity, temperature and actual brightness of the corresponding area are collected in real time to obtain the zone's environmental parameter data;

[0009] Feature fusion is performed on the partition display content data and partition environment parameter data to generate partition joint feature data;

[0010] The joint feature data of the partitions is input into the partition CycleGAN model, and the partition-enhanced content data is output.

[0011] The enhanced content data of each zone is seamlessly spliced ​​to generate overall enhanced display content data, which is then output to the LED screen driver system.

[0012] The system continuously collects the actual display effects and environmental changes of each partition to obtain partition feedback data. This partition feedback data is then used as online feedback input to the partition CycleGAN model to dynamically optimize the parameters of the partition CycleGAN model.

[0013] Optionally, the partition display content data includes pixel data of the original image within the partition, spatial location information of the partition on the LED screen, resolution parameters of the partition, average brightness value, average color temperature value, color histogram, contrast value, and timestamp of partition content acquisition.

[0014] Optionally, the partitioned environmental parameter data includes the ambient light intensity value, ambient temperature value, actual brightness value, spatial location information of the partition in the LED screen, and the timestamp of the partitioned environmental parameter collection for the corresponding area.

[0015] Optionally, the step of fusing the partition display content data and partition environment parameter data to generate partition joint feature data specifically includes:

[0016] Extract the original image pixel data, spatial location information, resolution parameters, average brightness value, average color temperature value, color histogram, contrast value, and the timestamp of partition content collection from the partition display content data;

[0017] Extract the ambient light intensity value, ambient temperature value, actual brightness value, spatial location information, and the timestamp of the partition environmental parameter data from the partition environmental parameter data;

[0018] The partition display content data and partition environment parameter data are matched according to the partition spatial location information and timestamp to ensure that the data corresponds one-to-one;

[0019] The partition display content data and all parameters in the partition environment parameter data are concatenated to generate partition joint feature data, and all partition joint feature data are numbered and stored according to the partition index.

[0020] Optionally, the step of inputting the joint feature data of the partitions into the partition CycleGAN model and outputting the partition-enhanced content data specifically includes:

[0021] The joint feature data of each partition is input into the partition CycleGAN model, which includes a partition generator and a partition discriminator.

[0022] The partition generator receives the partition joint feature data for each partition and generates partition-enhanced content data;

[0023] The partition discriminator receives partition enhancement content data and outputs true / false discrimination score, brightness consistency evaluation score, color consistency evaluation score, and style and structure consistency judgment result respectively.

[0024] Based on the true / false discrimination score, brightness consistency evaluation score, color consistency evaluation score, and style and structure consistency judgment results, a multi-objective loss optimization function is constructed, and the parameters of the partitioned CycleGAN model are jointly optimized to obtain the trained partitioned CycleGAN model.

[0025] Using the trained partition CycleGAN model, inference processing is performed on the joint feature data of the partitions to output partition-enhanced content data, which is then numbered and stored.

[0026] Optionally, the partition generator receives the joint partition feature data for each partition, and the generated partition-enhanced content data specifically includes:

[0027] The partition generator receives joint feature data for each partition, and the partition generator includes an input feature fusion layer, an encoding layer, a feature mapping layer, and a decoding layer;

[0028] The input feature fusion layer receives the joint feature data of each partition, performs feature-level concatenation and normalization of the partition display content data and the corresponding partition environment parameter data, and outputs the fused feature vector.

[0029] The coding layer receives the fused feature vector, performs deep feature extraction on the fused feature vector, and outputs the coded feature representation;

[0030] The feature mapping layer receives the encoded feature representation and, in response to the dynamic changes in the partition content and environmental features, adopts an adaptive adjustment mechanism to perform partition-level optimization of brightness and color features, and outputs the feature mapping results.

[0031] The decoding layer receives the feature mapping results, upsamples and restores the feature mapping results, outputs the partitioned enhanced content data, and numbers and stores all the partitioned enhanced content data.

[0032] Optionally, the partition discriminator receives partition-enhanced content data and outputs true / false discrimination scores, brightness consistency evaluation scores, color consistency evaluation scores, and style and structure consistency judgment results, specifically including:

[0033] The partition discriminator receives partition-enhanced content data, and the partition discriminator includes an input feature extraction layer, a local discriminant layer, and a consistency judgment layer;

[0034] The input feature extraction layer receives partitioned enhanced content data, performs multi-scale feature extraction on the partitioned enhanced content data, and outputs a multi-scale feature representation of the partition.

[0035] The local discriminant layer receives multi-scale feature representations of the partitions and calculates true / false scores based on the discriminant network.

[0036] The consistency judgment layer receives the multi-scale feature representation of the partition, calculates the brightness consistency evaluation score, the color consistency evaluation score, and the style and structure consistency judgment result;

[0037] Output the true / false discrimination score, brightness consistency evaluation score, color consistency evaluation score, and style and structure consistency judgment results.

[0038] Optionally, the construction of a multi-objective loss optimization function, jointly optimizing the parameters of the partitioned CycleGAN model, and obtaining the trained partitioned CycleGAN model specifically includes:

[0039] A multi-objective loss optimization function is defined for the partitioned CycleGAN model. The multi-objective loss optimization function is a weighted combination of the adversarial loss function, the partitioned cycle consistency loss function, the partitioned brightness equalization loss function, and the partitioned color consistency loss function.

[0040] An adversarial loss function is constructed based on the true / false discrimination scores output by the partition discriminator, specifically: the probability output of each partition discriminator for real content and generated content;

[0041] Based on the consistency of partition content, a partition-based cyclic consistency loss function is constructed, which is extended to be calculated independently at the partition level based on the CycleGAN cyclic consistency loss function.

[0042] A partition brightness equalization loss function is constructed based on the brightness consistency evaluation score of the partition-generated content to measure the error between the brightness of the partition-generated content and the target brightness.

[0043] A partition color consistency loss function is constructed based on the color consistency evaluation score of the partitioned generated content to measure the error between the color distribution of the partitioned generated content and the target color distribution.

[0044] Using a multi-objective loss optimization function, the parameters of the partitioned CycleGAN model are jointly optimized through backpropagation. The model is iteratively trained until the multi-objective loss optimization function converges or meets the preset conditions, and the trained partitioned CycleGAN model is output.

[0045] Optionally, the step of seamlessly stitching together the partitioned enhanced content data to generate overall enhanced display content data, and outputting the overall enhanced display content data to the LED screen driving system specifically includes:

[0046] Based on the physical structure partition index of the LED screen, sort all partition enhancement content data in sequence, determine the corresponding spatial position of each partition enhancement content data on the screen, and output the sorted partition enhancement content dataset.

[0047] Brightness and color smoothing are performed on the boundary pixels of each partition enhancement content data in the sorted partition enhancement content dataset and the boundary pixels of adjacent partition enhancement content data to generate a seamlessly fused partition enhancement content dataset.

[0048] The seamlessly integrated partitioned enhanced content datasets are combined according to their corresponding spatial locations to generate overall enhanced display content data;

[0049] The overall enhanced display content data is output to the LED screen driver system.

[0050] Optionally, the continuous collection of actual display effects and environmental changes in each partition, obtaining partition feedback data, and dynamically optimizing the partition CycleGAN model parameters specifically includes:

[0051] During the dynamic display process of the LED screen, the actual display effect data of each zone is collected in real time;

[0052] The actual display effect data includes the brightness value, color distribution, smoothness evaluation results of the transition area of ​​the display content boundary, and real-time physical environment parameters of the partition;

[0053] The actual display effect data is compared synchronously with the partition environment parameter data to generate partition feedback data.

[0054] The partition feedback data includes the deviation between the actual brightness and the target brightness of the partition, the difference between the actual color distribution and the target color distribution of the partition, and the change in the partition environmental parameters;

[0055] The partitioned feedback data is used as online feedback input to the trained partitioned CycleGAN model. The parameters of the partitioned CycleGAN model are adjusted in real time by combining the partitioned brightness equalization loss function and the partitioned color consistency loss function.

[0056] The beneficial effects of this invention are:

[0057] This invention proposes a brightness equalization method for LED screens based on a dynamic color adjustment algorithm, enabling fine-grained dynamic adaptive adjustment of brightness and color across multiple zones of an LED screen. This method fuses multimodal features based on zone environmental parameters, displayed content, and historical feedback data. It then utilizes a zone-specific CycleGAN neural network to adaptively enhance the content of each zone, improving the consistency of brightness and color across zones and enhancing the display's adaptability to environmental changes. Through a multi-objective loss optimization function, it effectively constrains zone-level brightness equalization and color consistency, ensuring the LED screen maintains stable and reliable display performance under various usage environments.

[0058] This invention introduces a pixel-level smoothing and seamless splicing mechanism in the processing of partition boundaries, improving the unnatural brightness and color transitions that may occur between partitions. After the enhanced content of each partition is blended at the boundary, continuous brightness and color distribution is achieved when the overall display content is spliced, thereby avoiding discontinuities, color bands, or splicing marks between partitions, which helps to improve the display uniformity and visual comfort of the overall LED screen.

[0059] Furthermore, an online feedback mechanism is employed to continuously collect and dynamically adjust the actual display effects and environmental parameters of each partition, supporting real-time optimization of the partition CycleGAN model. This effectively improves the system's response speed and intelligent adaptive level to changes in the external environment and dynamic display content. Overall, this invention can meet the comprehensive requirements of high-resolution, complex scenarios for LED displays in terms of brightness balance, color consistency, and adaptive capabilities, and has promising engineering application prospects. Attached Figure Description

[0060] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0061] Figure 1 This is a flowchart of an LED screen brightness equalization method based on a dynamic color adjustment algorithm proposed in this invention;

[0062] Figure 2 This is a schematic diagram of the partition generator structure in the LED screen brightness equalization method based on dynamic color adjustment algorithm proposed in this invention;

[0063] Figure 3 This is a schematic diagram of the partition discriminator structure in the LED screen brightness equalization method based on dynamic color adjustment algorithm proposed in this invention;

[0064] Figure 4 This is a flowchart of the training process of the partitioned CycleGAN model in the LED screen brightness equalization method based on dynamic color adjustment algorithm proposed in this invention. Detailed Implementation

[0065] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, illustrating only the basic structure of the invention, and therefore only show the components relevant to the invention.

[0066] refer to Figures 1-4 A method for equalizing the brightness of an LED screen based on a dynamic color adjustment algorithm includes the following steps:

[0067] The LED screen's display content is divided into multiple zones based on its physical structure to obtain the zone display content data;

[0068] For each zone, the ambient light intensity, temperature and actual brightness of the corresponding area are collected in real time to obtain the zone's environmental parameter data;

[0069] Feature fusion is performed on the partition display content data and partition environment parameter data to generate partition joint feature data;

[0070] The joint feature data of the partitions is input into the partition CycleGAN model, and the partition-enhanced content data is output.

[0071] The enhanced content data of each zone is seamlessly spliced ​​to generate overall enhanced display content data, which is then output to the LED screen driver system.

[0072] The system continuously collects the actual display effects and environmental changes of each partition to obtain partition feedback data. This partition feedback data is then used as online feedback input to the partition CycleGAN model to dynamically optimize the parameters of the partition CycleGAN model.

[0073] In this embodiment, the partition display content data includes pixel data of the original image within the partition, spatial location information of the partition in the LED screen (including row index and column index or pixel coordinate range), resolution parameters of the partition (including width and height), average brightness value, average color temperature value, color histogram, contrast value, and timestamp of partition content acquisition.

[0074] Acquire the overall content image of the LED screen display area to be processed, and record it as the raw display content data;

[0075] Based on the physical structure parameters of the LED screen, the original display content data is divided into several partitions according to the preset partitioning scheme, and each partition has a unique row index and column index.

[0076] For each partition, extract the corresponding sub-region from the original display content data to generate partition display content data, and number and store all partition display content data according to the partition index;

[0077] The partition display content data includes pixel data of the original image within the partition, spatial location information of the partition on the LED screen (including row and column indices or pixel coordinate range), resolution parameters of the partition (including width and height), average brightness value, average color temperature value, color histogram, contrast value, and timestamp of partition content acquisition.

[0078] In this embodiment, the partitioned environmental parameter data includes the ambient light intensity value, ambient temperature value, actual brightness value, spatial location information of the partition in the LED screen (including row index and column index or pixel coordinate range), and the timestamp of the partitioned environmental parameter collection.

[0079] An environmental data acquisition device is installed in each zone of the LED screen to collect the ambient light intensity, ambient temperature, and actual brightness of the zone.

[0080] When the LED screen is working, the environmental acquisition devices of each zone are periodically controlled to collect data, obtain the ambient light intensity value, ambient temperature value and actual brightness value of each zone, and assign corresponding zone row index and column index and timestamp information to each acquisition.

[0081] The ambient light intensity, ambient temperature, actual brightness, spatial location information, and collection timestamp of each partition are integrated to form corresponding partition environmental parameter data. All partition environmental parameter data are numbered and stored according to the partition index.

[0082] In this embodiment, the step of fusing the partition display content data and the partition environment parameter data to generate joint partition feature data specifically includes:

[0083] Extract the original image pixel data, spatial location information, resolution parameters, average brightness value, average color temperature value, color histogram, contrast value, and the timestamp of partition content collection from the partition display content data;

[0084] Extract the ambient light intensity value, ambient temperature value, actual brightness value, spatial location information, and the timestamp of the partition environmental parameter data from the partition environmental parameter data;

[0085] The partition display content data and partition environment parameter data are matched according to the partition spatial location information and timestamp to ensure that the data corresponds one-to-one;

[0086] The partition display content data and all parameters in the partition environment parameter data are concatenated to generate partition joint feature data. All partition joint feature data are numbered and stored according to the partition index. The partition joint feature data includes original image pixel data, spatial location information, resolution parameters, average brightness value, average color temperature value, color histogram, contrast value, content acquisition timestamp, ambient light intensity value, ambient temperature value, actual brightness value, and environmental parameter acquisition timestamp.

[0087] In this embodiment, the step of inputting the joint feature data of the partitions into the partition CycleGAN model and outputting the partition-enhanced content data specifically includes:

[0088] The joint feature data of each partition is input into the partition CycleGAN model, which includes a partition generator and a partition discriminator. The partition generator and the partition discriminator are set independently for each partition structure.

[0089] The partition generator receives the joint feature data of each partition and generates partition-enhanced content data. The partition-enhanced content data has brightness equalization and color optimization characteristics. The partition generator includes an input feature fusion layer, an encoding layer, a feature mapping layer and a decoding layer. The input feature fusion layer is used to receive and fuse the joint feature data of each partition. The encoding layer is used to extract the fused features. The feature mapping layer is used to perform brightness and color adaptive transformation. The decoding layer is used to output the partition-enhanced content data.

[0090] The partition discriminator receives partitioned enhanced content data and outputs true / false discrimination scores, brightness consistency evaluation scores, color consistency evaluation scores, and style and structure consistency judgment results. The partition discriminator includes an input feature extraction layer, a local discrimination layer, and a consistency judgment layer. The input feature extraction layer is used to extract multi-scale features of the partitioned enhanced content data. The local discrimination layer is used to perform fine-grained discrimination on the authenticity and style of the partitioned enhanced content data. The consistency judgment layer is used to judge the consistency between the partitioned enhanced content data and the target brightness and color distribution.

[0091] Based on the true / false discrimination score, brightness consistency evaluation score, color consistency evaluation score, and style and structure consistency judgment results, a multi-objective loss optimization function is constructed, including adversarial loss function, partition cycle consistency loss function, partition brightness equalization loss function, and partition color consistency loss function. The parameters of the partition CycleGAN model are jointly optimized to obtain the trained partition CycleGAN model.

[0092] Using the trained CycleGAN model, the joint feature data of the partitions is processed for inference, and the partition-enhanced content data is output. The partition-enhanced content data is then numbered and stored as input for subsequent seamless stitching and overall enhanced display content generation.

[0093] In this embodiment, the partition generator receives the partition joint feature data of each partition, and the generation of partition enhanced content data specifically includes:

[0094] The partition generator receives joint feature data for each partition, and the partition generator includes an input feature fusion layer, an encoding layer, a feature mapping layer, and a decoding layer;

[0095] The input feature fusion layer receives the joint feature data of each partition, performs feature-level concatenation and normalization of the partition display content data and the corresponding partition environment parameter data, and outputs the fused feature vector.

[0096] The coding layer receives the fused feature vector, performs deep feature extraction on the fused feature vector, and outputs a coded feature representation. The coded feature representation retains the correlation between the partition content and the environmental features, thereby realizing the information aggregation of multimodal features.

[0097] The feature mapping layer receives the encoded feature representation and, in response to the dynamic changes in the partition content and environmental features, adopts an adaptive adjustment mechanism to perform partition-level optimization of brightness and color features, outputting the feature mapping result to achieve local adaptive color adjustment and brightness balance.

[0098] The decoding layer receives the feature mapping result, upsamples and restores the feature mapping result, outputs the partition enhancement content data, numbers and stores all the partition enhancement content data, and the partition enhancement content data meets the target brightness balance and color optimization requirements and has the characteristic of seamless splicing with neighboring partitions.

[0099] In this embodiment, the partition discriminator receives partition enhancement content data and outputs true / false discrimination scores, brightness consistency evaluation scores, color consistency evaluation scores, and style and structure consistency judgment results, specifically including:

[0100] The partition discriminator receives partition-enhanced content data, and the partition discriminator includes an input feature extraction layer, a local discriminant layer, and a consistency judgment layer;

[0101] The input feature extraction layer receives partitioned enhanced content data, performs multi-scale feature extraction on the partitioned enhanced content data, and outputs a multi-scale feature representation of the partition.

[0102] The local discriminant layer receives the multi-scale feature representation of the partition, calculates the true / false discrimination score based on the discriminant network, and uses it to determine whether the partitioned enhanced content data is real content data or generated content data, and outputs the true / false discrimination score.

[0103] The consistency judgment layer receives the multi-scale feature representation of the partition, calculates the brightness consistency evaluation score, the color consistency evaluation score, and the style and structure consistency judgment result. The brightness consistency evaluation score is calculated based on the mean square error formula between the partition enhanced content data and the target brightness distribution. The color consistency evaluation score is calculated based on the correlation coefficient between the color distribution of the partition enhanced content data and the target color distribution. The style and structure consistency judgment result is calculated based on the distance or similarity score between the partition enhanced content data and the reference style sample in the high-dimensional feature space.

[0104] Output the true / false discrimination score, brightness consistency evaluation score, color consistency evaluation score, and style and structure consistency judgment results.

[0105] In this embodiment, the construction of a multi-objective loss optimization function and the joint optimization of the partitioned CycleGAN model parameters to obtain the trained partitioned CycleGAN model specifically include:

[0106] A multi-objective loss optimization function is defined for the partitioned CycleGAN model. This multi-objective loss optimization function is a weighted combination of the adversarial loss function, the partitioned cycle consistency loss function, the partitioned brightness equalization loss function, and the partitioned color consistency loss function.

[0107] L total =λ1L adv +λ2L cyc +λ3L lum +λ4L col ;

[0108] Among them, L total For the multi-objective loss optimization function, L adv To counteract the loss function, L cyc Let L be the partitioned circular consistency loss function. lum L is the partition brightness equalization loss function. col Let λ1, λ2, λ3, and λ4 be the weighting coefficients for each loss term, representing the partition color consistency loss function.

[0109] An adversarial loss function is constructed based on the real / fake scores output by the partition discriminator. Specifically, each partition discriminator outputs the probability of real content versus generated content:

[0110]

[0111] Where N is the number of partitions the LED screen is divided into, k is the partition index, and x is the number of partitions. k Display the actual partition content data for the k-th partition. To enhance the content data of the k-th partition, p data (x k ) represents the probability distribution of the actual content data displayed in the k-th partition. For the probability distribution of augmented content data in the k-th partition, D k This is the k-th partition discriminator;

[0112] The adversarial loss function formula is derived based on the loss function of Generative Adversarial Networks (GANs). The global discriminator and generator in the original formula are extended to partition discriminators and partition generators for each LED screen partition. The original GAN ​​adversarial loss function is refined into partition-level losses and averaged over each partition. All components are probabilities or log probabilities, and are dimensionless. The formula maintains consistent physical dimensions, which is consistent with common sense.

[0113] Based on the consistency of partition content, a partition-based circular consistency loss function is constructed. This function is then extended from the CycleGAN circular consistency loss function to be computed independently at the partition level.

[0114]

[0115] Among them, C k To display content data for the k-th partition, G k For the k-th partition generator, F k For the k-th partition reverse generator, it is used to inversely transform the partition enhancement content data into a mapping of partition display content data. ||·||1 is the L1 norm, which represents the sum of the absolute distances of the corresponding partition data at each pixel point (i.e., the sum of the absolute errors of all pixels).

[0116] The formula for the partitioned cycle consistency loss function is based on the CycleGAN cycle consistency loss formula and is derived in combination with the LED screen partitioning scenario. The input and output are refined into partitioned display content data and partitioned enhanced content data. For each partition, forward and reverse generators are set independently, and finally aggregated into the global partition average loss. All components are pixel values ​​or normalized pixels, which are dimensionless. The dimensions on both sides of the formula are consistent, which is in line with common sense.

[0117] A partition brightness equalization loss function is constructed based on the brightness consistency evaluation score of the partitioned generated content to measure the error between the brightness of the partitioned generated content and the target brightness.

[0118]

[0119] in, Enhance the average brightness of the content data in the k-th partition. The target brightness value for the k-th partition;

[0120] The formula for the partitioned brightness equalization loss function originates from the mean squared error (MSE) formula in mathematics. It expands the predicted and target values ​​to the mean brightness value of the partitioned enhanced content data and the target brightness value of the partition, respectively, and then averages these values ​​across all partitions. and Both are brightness values, and the square of the difference between them is the square of the brightness value. After averaging by region, the dimensions remain unchanged, and the dimensions of the left and right sides are completely consistent.

[0121] A partition color consistency loss function is constructed based on the color consistency evaluation score of the partitioned generated content to measure the error between the color distribution of the partitioned generated content and the target color distribution.

[0122]

[0123] in, Enhance the red channel mean of the content data for the k-th partition. Let the target red channel mean be the value of the k-th partition. Enhance the green channel mean of the content data for the k-th partition. Let the target green channel mean be the value of the k-th partition. Enhance the blue channel mean of the content data for the k-th partition. The target blue channel mean for the k-th partition;

[0124] The formula for the partition color consistency loss function originates from the mean squared error (MSE) formula in mathematics. It expands the predicted and target values ​​to the mean RGB channels of the partition-enhanced content data and the mean target color channels of the partition, respectively, and then averages these values ​​across all partitions and channels. and All values ​​are the average of the color components, and the unit is the normalized color value, which is dimensionless. After squaring the difference, the dimension is the square of the color component. Finally, the summation and averaging do not affect the dimension, and the left and right sides are consistent.

[0125] Using a multi-objective loss optimization function, the parameters of the partition CycleGAN model are jointly optimized through backpropagation, so that the partition generator and partition discriminator converge in terms of realism, consistency, brightness balance and color optimization. Iterative training continues until the multi-objective loss optimization function converges or meets the preset conditions, and the trained partition CycleGAN model is output.

[0126] The preset conditions include, but are not limited to, one or more of the following situations: the change of the multi-objective loss optimization function in several consecutive iterations is less than a preset threshold, the partitioned CycleGAN model training reaches the preset maximum number of training rounds, or the performance index of the partitioned CycleGAN model on the validation set does not improve in several consecutive iterations.

[0127] In this embodiment, the step of seamlessly splicing the partitioned enhanced content data to generate overall enhanced display content data and outputting the overall enhanced display content data to the LED screen driving system specifically includes:

[0128] Based on the physical structure partition index of the LED screen, sort all partition enhancement content data in sequence, determine the corresponding spatial position of each partition enhancement content data on the screen, and output the sorted partition enhancement content dataset.

[0129] For the boundary pixels of each partition enhancement content data in the sorted partition enhancement content dataset and the boundary pixels of adjacent partition enhancement content data, brightness and color smoothing processing is performed. Pixel-level weighted averaging, boundary fusion or other seamless stitching algorithms are used to generate a seamlessly fused partition enhancement content dataset. The fusion processing ensures that there are no obvious abrupt changes in the boundaries between partitions, and achieves natural transitions in brightness and color between partitions.

[0130] The partitioned enhanced content datasets that have undergone seamless fusion processing are combined according to their corresponding spatial locations to generate overall enhanced display content data. The overall enhanced display content data has brightness balance and color consistency across the entire screen.

[0131] The overall enhanced display content data is output to the LED screen driving system to achieve dynamic brightness balance display of the LED screen.

[0132] In this embodiment, the continuous collection of actual display effects and environmental changes in each partition, obtaining partition feedback data, and dynamically optimizing the partition CycleGAN model parameters specifically includes:

[0133] During the dynamic display process of the LED screen, the actual display effect data of each zone is collected in real time. The actual display effect data includes the brightness value, color distribution, smoothness evaluation results of the transition area of ​​the display content boundary, and real-time physical environment parameters of the zone.

[0134] The actual display effect data and the partition environment parameter data are synchronously compared to generate partition feedback data. The partition feedback data includes: the deviation between the actual brightness of the partition and the target brightness, the difference between the actual color distribution of the partition and the target color distribution, and the change in partition environment parameters.

[0135] The partition feedback data is used as online feedback input to the trained partition CycleGAN model. The partition brightness equalization loss function and the partition color consistency loss function are combined to correct the parameters of the partition CycleGAN model in real time.

[0136] By iteratively updating the parameters of the partition CycleGAN model, the partition enhancement content data output by the partition generator continuously matches the actual display requirements, improving the brightness balance and color consistency of the LED screen under different environmental changes.

[0137] Example 1:

[0138] To verify the feasibility of this invention in practice, it was applied to the daily operation of a large outdoor high-resolution LED advertising screen. This scenario involves commercial advertising in an outdoor plaza. The LED screen covers an area of ​​over 100 square meters and is divided into 96 physical zones (12×8). Each zone is equipped with ambient light, temperature, and brightness sensors to collect real-time environmental parameters. Daily advertising content includes high-definition video, dynamic graphics, and real-time weather data. The screen has extremely high requirements for brightness uniformity and color consistency, especially under changing light conditions (morning and evening) and in rainy weather, necessitating adaptive dynamic adjustment.

[0139] In this application scenario, the system first performs partitioned modeling of the LED screen's physical structure and then fuses the real-time environmental parameters of each partition with the displayed content into the partition CycleGAN model. The partition generator dynamically enhances the brightness and color features of different areas and time periods, while the discriminator outputs real-time true / false discrimination scores, brightness consistency evaluation scores, and color consistency evaluation scores. The model is optimized through a multi-objective loss function. All partition enhanced content data undergoes pixel-level seamless stitching, and the overall display content is uniformly output to the drive system. The display effect is monitored in real time through a feedback channel, and the partition CycleGAN parameters are fine-tuned online based on the monitoring data to ensure the system's adaptability to changes in the external environment.

[0140] Comparative testing over a period of actual operation clearly demonstrates the advantages of this invention's solution in terms of brightness balance, color consistency, and seamless splicing. Using the standard deviation of screen partition brightness as a metric, the standard deviation of brightness across different partitions is reduced to 2.1 cd / m² after adopting this invention's method. 2The standard deviation of traditional global brightness equalization schemes is 5.8 cd / m². 2 Regarding color consistency, the average difference in color space across zones is controlled within ΔE = 1.9, significantly better than the traditional method's ΔE = 4.5. For special weather and strong light environments, the system's dynamic brightness response time has decreased from an average of 7.2 seconds to 2.8 seconds. In the seam area of ​​actual playback content, user visual rating consistency has improved from 73.5% to 95.2%. Furthermore, this invention demonstrates good stability in dynamic scenes and high-frequency content switching, with no noticeable stuttering or delays during extended operation. The table below shows some key performance comparison data.

[0141] Table 1. Comparison Test Data of Brightness Uniformity and Color Consistency of LED Screens

[0142]

[0143] As can be seen from the table above, the present invention achieves a certain improvement over the traditional global equalization scheme in key performance indicators of LED screen brightness balance and color consistency. Firstly, regarding the standard deviation of zone brightness, the present invention achieves 2.1 cd / m². 2 Its superior performance is far lower than the traditional solution's 5.8 cd / m³. 2 This fully demonstrates that the zone-based dynamic color adjustment algorithm can effectively suppress uneven brightness across different zones, improving the overall balance of the screen display. In the test of the color space mean difference ΔE, the method of this invention has a value of only 1.9, while the traditional method has a value of 4.5, showcasing the highly efficient constraint of color consistency in multi-zone, dynamic scenarios, and reducing color differences perceptible to the naked eye. Regarding the response capability to dynamic environments and strong light interference in actual use, the system dynamic brightness response time using this invention is shortened to 2.8 seconds, better than the 7.2 seconds of the traditional solution, enhancing the LED screen's adaptability to changes in the external environment.

[0144] This invention also excels in seamless display and user experience in the seam area. Through pixel-level seamless splicing and boundary smoothing algorithms, the visual score consistency of the seam area reaches 95.2%, significantly better than the 73.5% of the traditional global equalization scheme, greatly improving the user's visual comfort and overall screen feel during actual viewing. Furthermore, in terms of long-term average stability and adaptability to extreme environments, this invention achieved high scores of 97.4 and 93.6% respectively, higher than the traditional scheme's 85.9 and 68.2%. The average color saturation under rainy weather also improved to 91.8%, demonstrating stronger robustness of the display system to complex environmental changes. In addition, the convergence period of zone adaptive adjustment is shortened to 5.1 seconds, far lower than the 13.6 seconds of the traditional scheme, indicating that the model of this invention can complete adaptive adjustment and parameter optimization faster, effectively supporting the real-time display needs of high-frequency content switching and complex application scenarios.

[0145] The above data analysis shows that the LED screen brightness equalization method based on dynamic color adjustment algorithm proposed in this invention has achieved technical progress in improving zonal balance, color consistency, environmental adaptability, and user experience. It can meet the high standards and requirements of LED display engineering applications and provides strong technical support for the intelligent and refined upgrading of the industry.

[0146] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for equalizing the brightness of an LED screen based on a dynamic color adjustment algorithm, characterized in that, Includes the following steps: The LED screen's display content is divided into multiple zones based on its physical structure to obtain the zone display content data; For each zone, the ambient light intensity, temperature and actual brightness of the corresponding area are collected in real time to obtain the zone's environmental parameter data; Feature fusion is performed on the partition display content data and partition environment parameter data to generate partition joint feature data; The joint feature data of the partitions is input into the partition CycleGAN model, and the partition-enhanced content data is output. The enhanced content data of each zone is seamlessly spliced ​​to generate overall enhanced display content data, which is then output to the LED screen driver system. The system continuously collects the actual display effects and environmental changes of each partition to obtain partition feedback data. This partition feedback data is then used as online feedback input to the partition CycleGAN model to dynamically optimize the parameters of the partition CycleGAN model.

2. The LED screen brightness equalization method based on dynamic color adjustment algorithm according to claim 1, characterized in that, The partition display content data includes pixel data of the original image within the partition, spatial location information of the partition on the LED screen, resolution parameters of the partition, average brightness value, average color temperature value, color histogram, contrast value, and timestamp of partition content acquisition.

3. The LED screen brightness equalization method based on dynamic color adjustment algorithm according to claim 1, characterized in that, The partitioned environmental parameter data includes the ambient light intensity value, ambient temperature value, actual brightness value, spatial location information of the partition in the LED screen, and the timestamp of the partitioned environmental parameter collection.

4. The LED screen brightness equalization method based on dynamic color adjustment algorithm according to claim 1, characterized in that, The step of fusing the partition display content data and partition environment parameter data to generate joint partition feature data specifically includes: Extract the original image pixel data, spatial location information, resolution parameters, average brightness value, average color temperature value, color histogram, contrast value, and the timestamp of partition content collection from the partition display content data; Extract the ambient light intensity value, ambient temperature value, actual brightness value, spatial location information, and the timestamp of the partition environmental parameter data from the partition environmental parameter data; The partition display content data and partition environment parameter data are matched according to the partition spatial location information and timestamp to ensure that the data corresponds one-to-one; The partition display content data and all parameters in the partition environment parameter data are concatenated to generate partition joint feature data, and all partition joint feature data are numbered and stored according to the partition index.

5. The LED screen brightness equalization method based on dynamic color adjustment algorithm according to claim 1, characterized in that, The step of inputting the joint feature data of the partitions into the partition CycleGAN model and outputting the partitioned enhanced content data specifically includes: The joint feature data of each partition is input into the partition CycleGAN model, which includes a partition generator and a partition discriminator. The partition generator receives the partition joint feature data for each partition and generates partition-enhanced content data; The partition discriminator receives partition enhancement content data and outputs true / false discrimination score, brightness consistency evaluation score, color consistency evaluation score, and style and structure consistency judgment result respectively. Based on the true / false discrimination score, brightness consistency evaluation score, color consistency evaluation score, and style and structure consistency judgment results, a multi-objective loss optimization function is constructed, and the parameters of the partitioned CycleGAN model are jointly optimized to obtain the trained partitioned CycleGAN model. Using the trained partition CycleGAN model, inference processing is performed on the joint feature data of the partitions to output partition-enhanced content data, which is then numbered and stored.

6. The LED screen brightness equalization method based on dynamic color adjustment algorithm according to claim 5, characterized in that, The partition generator receives the joint partition feature data for each partition and generates partition-enhanced content data, specifically including: The partition generator receives joint feature data for each partition, and the partition generator includes an input feature fusion layer, an encoding layer, a feature mapping layer, and a decoding layer; The input feature fusion layer receives the joint feature data of each partition, performs feature-level concatenation and normalization of the partition display content data and the corresponding partition environment parameter data, and outputs the fused feature vector. The coding layer receives the fused feature vector, performs deep feature extraction on the fused feature vector, and outputs the coded feature representation; The feature mapping layer receives the encoded feature representation and, in response to the dynamic changes in the partition content and environmental features, adopts an adaptive adjustment mechanism to perform partition-level optimization of brightness and color features, and outputs the feature mapping result. The decoding layer receives the feature mapping results, upsamples and restores the feature mapping results, outputs the partitioned enhanced content data, and numbers and stores all the partitioned enhanced content data.

7. The LED screen brightness equalization method based on dynamic color adjustment algorithm according to claim 5, characterized in that, The partition discriminator receives partition-enhanced content data and outputs true / false discrimination scores, brightness consistency evaluation scores, color consistency scores, and style and structure consistency judgment results, specifically including: The partition discriminator receives partition-enhanced content data, and the partition discriminator includes an input feature extraction layer, a local discriminant layer, and a consistency judgment layer; The input feature extraction layer receives partitioned enhanced content data, performs multi-scale feature extraction on the partitioned enhanced content data, and outputs a multi-scale feature representation of the partition. The local discriminant layer receives multi-scale feature representations of the partitions and calculates true / false scores based on the discriminant network. The consistency judgment layer receives the multi-scale feature representation of the partition, calculates the brightness consistency evaluation score, the color consistency evaluation score, and the style and structure consistency judgment result; Output the true / false discrimination score, brightness consistency evaluation score, color consistency evaluation score, and style and structure consistency judgment results.

8. The LED screen brightness equalization method based on dynamic color adjustment algorithm according to claim 5, characterized in that, The specific steps of constructing a multi-objective loss optimization function and jointly optimizing the parameters of the partitioned CycleGAN model to obtain the trained partitioned CycleGAN model include: A multi-objective loss optimization function is defined for the partitioned CycleGAN model. The multi-objective loss optimization function is a weighted combination of the adversarial loss function, the partitioned cycle consistency loss function, the partitioned brightness equalization loss function, and the partitioned color consistency loss function. An adversarial loss function is constructed based on the true / false discrimination scores output by the partition discriminator, specifically: the probability output of each partition discriminator for real content and generated content; Based on the consistency of partition content, a partition-based cyclic consistency loss function is constructed, which is extended to be calculated independently at the partition level based on the CycleGAN cyclic consistency loss function. A partition brightness equalization loss function is constructed based on the brightness consistency evaluation score of the partition-generated content to measure the error between the brightness of the partition-generated content and the target brightness. A partition color consistency loss function is constructed based on the color consistency evaluation score of the partitioned generated content to measure the error between the color distribution of the partitioned generated content and the target color distribution. Using a multi-objective loss optimization function, the parameters of the partitioned CycleGAN model are jointly optimized through backpropagation. The model is iteratively trained until the multi-objective loss optimization function converges or meets the preset conditions, and the trained partitioned CycleGAN model is output.

9. The LED screen brightness equalization method based on dynamic color adjustment algorithm according to claim 1, characterized in that, The process of seamlessly stitching together the partitioned enhanced content data to generate overall enhanced display content data, and then outputting the overall enhanced display content data to the LED screen driving system, specifically includes: Based on the physical structure partition index of the LED screen, sort all partition enhancement content data in sequence, determine the corresponding spatial position of each partition enhancement content data on the screen, and output the sorted partition enhancement content dataset. Brightness and color smoothing are performed on the boundary pixels of each partition enhancement content data in the sorted partition enhancement content dataset and the boundary pixels of adjacent partition enhancement content data to generate a seamlessly fused partition enhancement content dataset. The seamlessly integrated partitioned enhanced content datasets are combined according to their corresponding spatial locations to generate overall enhanced display content data; The overall enhanced display content data is output to the LED screen driver system.

10. The LED screen brightness equalization method based on dynamic color adjustment algorithm according to claim 1, characterized in that, The process of continuously collecting the actual display effects and environmental changes of each partition, obtaining partition feedback data, and dynamically optimizing the partition CycleGAN model parameters specifically includes: During the dynamic display process of the LED screen, the actual display effect data of each zone is collected in real time; The actual display effect data includes the brightness value, color distribution, smoothness evaluation results of the transition area of ​​the display content boundary, and real-time physical environment parameters of the partition; The actual display effect data is compared synchronously with the partition environment parameter data to generate partition feedback data. The partition feedback data includes the deviation between the actual brightness and the target brightness of the partition, the difference between the actual color distribution and the target color distribution of the partition, and the change in the partition environmental parameters; The partitioned feedback data is used as online feedback input to the trained partitioned CycleGAN model. The parameters of the partitioned CycleGAN model are adjusted in real time by combining the partitioned brightness equalization loss function and the partitioned color consistency loss function.

Images