Pixel compensation method and device, electronic equipment and computer readable storage medium

Abstract

Embodiments of the present application provide a pixel compensation method and device, electronic equipment and computer readable storage medium, relating to the technical field of computer. The method comprises: determining a temperature prediction value of a pixel unit of a display screen, determining a target pixel compensation value of the pixel unit according to the temperature prediction value, and performing pixel compensation on the pixel unit based on the target pixel compensation value. The pixel compensation method provided by the embodiments of the present application can compensate the pixel points of the display area after the display area of the display screen displays a certain image for a long time, avoid the problem of residual image caused by different light-emitting efficiencies of the LED lamps in the display area due to long-time display of a certain image, and cause uneven display. The embodiments of the present application solve the problem of uneven display of the MiniLED display in the related art.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more specifically, to a pixel compensation method, apparatus, electronic device, and computer-readable storage medium. Background Technology

[0002] In the field of image display, the application of Mini LED (Mini light-emitting diode) displays is becoming increasingly widespread. Mini LED displays are smaller than LED displays, with chip sizes typically between 50 and 200 μm, but offer a more refined display effect and are more energy-efficient. Furthermore, Mini LED displays have a long lifespan and low cost, making them popular with users. With the rapid development of Mini LED display technology, Mini LED display products have begun to be applied to ultra-large-screen high-definition displays, such as in commercial fields like monitoring and command centers, high-definition broadcasting, high-end cinemas, medical diagnostics, advertising displays, conference and exhibition facilities, office displays, and virtual reality.

[0003] However, MiniLED displays are prone to uneven image display. For example, when displaying an image for a long time, the heat accumulation in different areas of the screen is different. When the screen switches to display an image of the same grayscale, uneven image display, or ghosting, may occur, affecting the display effect. Summary of the Invention

[0004] The purpose of this application is to at least solve one of the aforementioned technical defects, particularly the problem of uneven display in MiniLED displays in related technologies.

[0005] According to one aspect of this application, a pixel compensation method is provided, the method comprising: determining a temperature prediction value of a pixel unit of a display screen; wherein the temperature prediction value is determined based on pixel parameters of a target image displayed on the display screen and the display duration of the target image;

[0006] Based on the predicted temperature value, determine the target pixel compensation value for the pixel unit;

[0007] Pixel compensation is performed on the pixel unit based on the target pixel compensation value.

[0008] Optionally, determining the predicted temperature value of the pixel unit of the display screen includes:

[0009] The predicted temperature value is determined based on the target cumulative pixel value of the pixel unit; wherein the target cumulative pixel value is determined based on the pixel value of the pixel unit and the display duration.

[0010] Optionally, determining the target pixel compensation value of the pixel unit based on the predicted temperature value includes:

[0011] Obtain pixel features and weight features of the target image; wherein the pixel features are obtained by sampling the target cumulative pixel value of the pixel unit, and the weight features are obtained by sampling the preset weight value of the pixel unit;

[0012] Determine the temperature diffusion coefficient, and then determine the diffusion matrix based on the temperature diffusion coefficient;

[0013] The weighted features are determined based on the pixel features, the weight features, and the diffusion matrix;

[0014] The predicted temperature value is determined based on the weighted features.

[0015] Optionally, determining the temperature diffusion coefficient and determining the diffusion matrix based on the temperature diffusion coefficient includes:

[0016] The temperature diffusion coefficient is determined based on the maximum value among the pixel values;

[0017] Based on the numerical range of the temperature diffusion coefficient, determine the diffusion matrix corresponding to the numerical range.

[0018] Optionally, determining the weighted features based on the pixel features, the weight features, and the diffusion matrix includes:

[0019] The diffusion matrix and the weight feature are multiplied in pairs to obtain the diffusion weight feature;

[0020] The weighted feature is obtained by multiplying the diffusion weight feature with the pixel feature.

[0021] Optionally, before determining the temperature prediction value based on the target accumulated pixel value of the pixel unit, the method further includes:

[0022] The target cumulative pixel value is determined based on the pixel value of the pixel unit, the display duration, and the first data relationship;

[0023] The first data relationship includes:

[0024]

[0025] X ij This represents the target cumulative pixel value of the pixel unit in the i-th row and j-th column of the target image; i represents the row number; j represents the column number;

[0026] 'a' represents the preset adjustment coefficient;

[0027] Tmax-ij This represents the preset temperature empirical value;

[0028] I sumtij The actual cumulative pixel value within the display duration is represented by t; the display duration is represented by I. sumtij =I1+I2+…+I t-1 ;I1, I2, ..., I t-1 These represent the pixel values ​​of the pixel unit in the i-th row and j-th column at each time point.

[0029] Optionally, before determining the temperature prediction value based on the target accumulated pixel value of the pixel unit, the method further includes:

[0030] Obtain a training sample set; wherein the training sample set includes sample images and sample display duration;

[0031] For each of the sample images, the target cumulative pixel value and sample display duration of the pixel unit in the sample image are input into the initial training model to obtain the sample temperature prediction value of each pixel unit;

[0032] The training loss value is determined based on the predicted temperature value of the sample and the actual temperature value of the pixel unit.

[0033] Based on the training loss value, the initial training model is repeatedly trained until the temperature prediction network that meets the training termination condition is obtained.

[0034] Optionally, determining the target pixel compensation value of the pixel unit based on the temperature prediction value includes:

[0035] A pixel compensation model is used to determine the predicted pixel compensation value corresponding to the predicted temperature value; wherein, the predicted temperature value and the predicted pixel compensation value are inversely proportional.

[0036] The target pixel compensation value is determined based on the predicted pixel compensation value and the compensation time.

[0037] Optionally, determining the target pixel compensation value based on the predicted pixel compensation value and the compensation time includes:

[0038] The target pixel compensation value is determined based on the predicted pixel compensation value, the compensation time, and the second data relationship;

[0039] The second data relationship is:

[0040]

[0041] in; The target pixel compensation value is represented by t; the compensation time is represented by u; the predicted pixel compensation value is represented by v; the preset dissipation rate is represented by x; the horizontal component of the predicted pixel compensation value is represented by y; and the vertical component of the predicted pixel compensation value is represented by y.

[0042] Optionally, the pixel unit includes one or at least two pixels.

[0043] According to another aspect of this application, a pixel compensation device is provided, the device comprising:

[0044] A temperature determination module is used to determine the predicted temperature value of a pixel unit of a display screen; wherein the predicted temperature value is determined based on the pixel parameters of the target image displayed on the display screen and the display duration of the target image;

[0045] A pixel determination module is used to determine the target pixel compensation value of the pixel unit based on the temperature prediction value.

[0046] The compensation module is used to perform pixel compensation on the pixel unit based on the target pixel compensation value.

[0047] According to another aspect of this application, an electronic device is provided, the electronic device comprising:

[0048] One or more processors;

[0049] Memory;

[0050] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to: perform the pixel compensation method according to any one of the first aspects of this application.

[0051] For example, in a third aspect of this application, a computing device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0052] The memory is used to store at least one executable instruction that causes the processor to perform the operation corresponding to the pixel compensation method shown in the first aspect of this application.

[0053] According to another aspect of this application, a computer-readable storage medium is provided, wherein a computer program, when executed by a processor, implements the pixel compensation method described in any of the first aspects of this application. For example, a fourth aspect of the embodiments of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the pixel compensation method shown in the first aspect of this application.

[0054] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in various alternative implementations of the first aspect described above.

[0055] The beneficial effects of the technical solution provided in this application are:

[0056] This application embodiment determines the predicted temperature value of a pixel unit on the display screen, determines the target pixel compensation value of the pixel unit based on the predicted temperature value, and performs pixel compensation on the pixel unit based on the target pixel compensation value. The pixel compensation method provided in this application embodiment compensates the pixels in the display area after displaying an image for a long time, avoiding image retention caused by different luminous efficiencies of the LEDs in the display area due to prolonged image display, thus preventing uneven display. This application embodiment solves the problem of uneven display in MiniLED displays in related technologies. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below.

[0058] Figure 1 A schematic diagram of the architecture of a pixel compensation method provided in an embodiment of this application;

[0059] Figure 2 A schematic flowchart illustrating a pixel compensation method provided in an embodiment of this application;

[0060] Figure 3 This is a schematic diagram of a function in a pixel compensation method provided in an embodiment of this application;

[0061] Figure 4 This is a schematic diagram of a pixel compensation method provided in an embodiment of this application;

[0062] Figure 5 This is a schematic diagram of a pixel compensation method provided in an embodiment of this application;

[0063] Figure 6 is a schematic diagram of an application scenario of a pixel compensation method provided in an embodiment of this application;

[0064] Figure 7 A schematic flowchart illustrating a pixel compensation method provided in an embodiment of this application;

[0065] Figure 8 This is a schematic diagram of sample data in a pixel compensation method provided in an embodiment of this application;

[0066] Figure 9 This is a schematic diagram illustrating an application scenario of a pixel compensation method provided in an embodiment of this application;

[0067] Figure 10 A schematic flowchart illustrating a pixel compensation method provided in an embodiment of this application;

[0068] Figure 11 This is a schematic diagram of the structure of a pixel compensation device provided in an embodiment of this application;

[0069] Figure 12 This is a schematic diagram of the structure of an electronic device for pixel compensation provided in an embodiment of this application. Detailed Implementation

[0070] The embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the embodiments described below with reference to the accompanying drawings are exemplary descriptions for explaining the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions of the embodiments of this application.

[0071] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the terms “comprising” and “including” as used in embodiments of this application mean that the corresponding feature can be implemented as the presented feature, information, data, step, operation, element, and / or component, but do not exclude implementation as other features, information, data, step, operation, element, component, and / or combinations thereof supported by the art. It should be understood that when we say that an element is “connected” or “coupled” to another element, the one element can be directly connected or coupled to the other element, or it can mean that the one element and the other element establish a connection relationship through an intermediate element. Furthermore, “connected” or “coupled” as used herein can include wireless connection or wireless coupling. The term “and / or” as used herein indicates at least one of the items defined by the term; for example, “A and / or B” can be implemented as “A,” or as “B,” or as “A and B.”

[0072] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0073] At least some of the pixel compensation methods provided in this application involve fields such as machine learning in the field of artificial intelligence, as well as various fields of cloud technology, such as cloud computing, cloud services, and related data computing and processing in the field of big data.

[0074] Artificial intelligence (AI) is the theory, methods, technology, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive technology within computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence. AI studies the design principles and implementation methods of various intelligent machines, enabling them to possess the functions of perception, reasoning, and decision-making.

[0075] Artificial intelligence (AI) is a comprehensive discipline encompassing a wide range of fields, including both hardware and software technologies. Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies primarily include computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0076] Machine learning (ML) is a multidisciplinary field involving probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory. It specifically studies how computers can simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to endow computers with intelligence; its applications span all areas of artificial intelligence. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and instructional learning.

[0077] To further illustrate the technical solutions provided in the embodiments of this application, a detailed description is provided below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiments of this application provide method operation steps as shown in the following embodiments or drawings, the method may include more or fewer operation steps based on conventional or non-inventive methods. In steps where there is no logically necessary causal relationship, the execution order of these steps is not limited to the execution order provided in the embodiments of this application.

[0078] First, combine Figure 1This is a system architecture diagram of the pixel compensation method provided in the embodiments of this application. The system may include a server 101 and a terminal cluster, wherein the server 101 can be considered as a backend server for performing pixel compensation.

[0079] The terminal cluster may include: terminal 102, terminal 103, terminal 104, ..., wherein each terminal has a client installed that supports image display. Communication connections may exist between the terminals; for example, there is a communication connection between terminal 102 and terminal 103, and a communication connection between terminal 103 and terminal 104.

[0080] Meanwhile, server 101 can provide services to the terminal cluster through communication connection function. Any terminal in the terminal cluster can have a communication connection with server 101. For example, terminal 102 has a communication connection with server 101, and terminal 103 has a communication connection with server 101. The above-mentioned communication connection is not limited to the connection method. It can be directly or indirectly connected through wired communication, or directly or indirectly connected through wireless communication, or through other methods.

[0081] The network for the aforementioned communication connection can be a wide area network (WAN), a local area network (LAN), or a combination of both. This application does not impose any restrictions on this.

[0082] The pixel compensation method of this application embodiment can be executed on the server side or the terminal side, and the execution subject is not limited in this application embodiment. The method provided in this application embodiment can be executed by a computer device, which includes, but is not limited to, a terminal (including the aforementioned user terminal) or a server (including the aforementioned server 101). The aforementioned server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The aforementioned terminal can be a smartphone, tablet computer, laptop computer, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. The terminal and the server can be directly or indirectly connected through wired or wireless communication, and this application does not impose any restrictions here.

[0083] Of course, the methods provided in the embodiments of this application are not limited to... Figure 1 The application scenarios shown can also be used in other possible scenarios, and this application does not impose any limitations. Figure 1 The functions that each device in the application scenario shown can achieve will be described in subsequent method embodiments, and will not be elaborated on here.

[0084] This application provides a possible implementation, which can be executed by any electronic device. Optionally, any electronic device can be a server device with pixel compensation capabilities, or a device or chip integrated into these devices. Figure 2 As shown, this is one of the flowcharts of a pixel compensation method provided in an embodiment of this application. The method includes the following steps:

[0085] Step S201: Determine the predicted temperature value of the pixel unit of the display screen.

[0086] The temperature prediction value is determined based on the pixel parameters of the target image displayed on the display screen and the display duration of the target image.

[0087] Optionally, the pixel compensation method of this application embodiment can be applied to application scenarios that perform pixel compensation on pixel units in a display screen.

[0088] The pixel unit may include one or at least two pixels on the display screen. Optionally, in some implementation scenarios, if a more accurate compensation effect is required, the pixel unit may be a single pixel; furthermore, in other implementation scenarios, since the granularity of a single pixel is small, if it is necessary to improve pixel compensation efficiency, the pixel unit may include at least two pixels.

[0089] The temperature prediction value is the temperature value of the pixel unit predicted based on the pixel parameters of the target image displayed on the display screen and the display duration of the target image.

[0090] The target image is the image displayed on the screen.

[0091] The pixel parameters of the target image can be pixel values. More specifically, the pixel parameters are the pixel values ​​of the pixel units when displaying the target image during the process of predicting the temperature value of the pixel units.

[0092] Display duration is the duration for which the target image is displayed on the display screen.

[0093] The above is an introduction to pixel units, temperature prediction values, and other related content. The following section explains how to determine the temperature prediction value.

[0094] Since the longer the display time of the target image, the higher the surface temperature of the display screen, the cumulative pixel value can be used in this embodiment to simulate the temperature rise of the display screen. That is, the larger the cumulative pixel value, the more heat accumulates over time, and the higher the display screen temperature. Therefore, for a pixel unit in the display screen, the predicted temperature value can be determined based on the target cumulative pixel value of the pixel unit.

[0095] The cumulative pixel value of the pixel unit is called the target cumulative pixel value.

[0096] The target cumulative pixel value is determined based on the pixel value of the pixel unit and the display duration. For example, within a certain time range, the target cumulative pixel value has a linear relationship with the display duration. For instance, if the pixel value of the pixel unit is 'a' and the display duration is 5 minutes, then the target cumulative pixel value can be 5a; if the display duration is 10 minutes, then the target cumulative pixel value can be 10a; if the display duration is 15 minutes, then the target cumulative pixel value can be 15a, and so on. Furthermore, since the display screen temperature does not rise indefinitely, after the display duration exceeds a certain range, the display screen temperature reaches its maximum value and tends to stabilize. Therefore, the trend of the target cumulative pixel value changing over time can be as follows: Figure 3 The sigmoid function is shown below.

[0097] Optionally, when determining the temperature prediction value, a pre-trained temperature prediction network can be used to determine the temperature prediction value based on the target accumulated pixel value of the pixel unit. For example, the temperature prediction network can be obtained by training a pixel2pixel network architecture.

[0098] In actual implementation, the target image and the display duration of the target image can be used as input data for the temperature prediction network. Then, the temperature prediction value of each pixel unit is determined based on the target cumulative pixel value of each pixel unit when the target image is displayed. Then, a temperature prediction map of the display screen is generated based on the temperature prediction value of each pixel unit. It can be understood that the temperature prediction map is used to characterize the temperature prediction value of each pixel unit.

[0099] Step S202: Determine the target pixel compensation value of the pixel unit based on the predicted temperature value.

[0100] After determining the predicted temperature value for each pixel unit, the target pixel compensation value for that pixel unit can be determined based on the predicted temperature value. The target pixel compensation value is the pixel value used to compensate for the pixel unit.

[0101] Because the driving current of the light-emitting diodes (LEDs) in a display screen is positively correlated with the pixel value of the pixel unit—that is, the larger the pixel value, the larger the driving current—and also positively correlated with the accumulated heat (temperature) of the pixel unit—that is, the larger the driving current, the higher the accumulated heat (temperature) of the pixel unit—it can be understood that the larger the pixel value of a pixel unit, the higher its temperature. Therefore, after displaying a target image on the screen for a period of time, different areas of the screen accumulate different amounts of heat, resulting in different temperatures. This leads to varying luminous efficiency of the LEDs in different areas of the screen, ultimately causing uneven display when the entire screen switches to display the same pixel value.

[0102] To achieve uniform display of pixel units in the display screen, in this embodiment of the application, pixel compensation can be performed by using a method where pixel units with low temperature have large pixel compensation values ​​and pixel units with high temperature have small pixel compensation values. That is, the temperature prediction value and the pixel compensation value are inversely proportional.

[0103] Optionally, in actual implementation, in order to achieve the best human eye observation effect and to combine with the above-mentioned temperature prediction network to jointly form an end-to-end pixel compensation network architecture and reduce post-processing work, the embodiments of this application can determine the pixel compensation value through a pre-trained pixel compensation model. For ease of description, the pixel compensation value determined by the pixel compensation model can be called the predicted compensation pixel value.

[0104] Specifically, the temperature prediction map of the display screen generated by the temperature prediction network in the above steps can be input into the pixel compensation model, and the pixel compensation model can be used to make predictions to obtain the pixel compensation map, which is used to characterize the predicted pixel compensation value of each pixel unit.

[0105] Furthermore, since the heat of a pixel unit changes with the increase in display time, this embodiment of the application can dynamically determine the target pixel compensation value of the pixel unit based on the predicted pixel compensation value and the display time when performing pixel compensation. In other words, in this embodiment, the target pixel compensation value of the pixel unit changes dynamically with the display time. This allows for dynamic correction of the pixel unit, ensuring that the image observed by the human eye remains uniform throughout the changing time.

[0106] Step S203: Perform pixel compensation on the pixel unit based on the target pixel compensation value.

[0107] After determining the target pixel compensation value, pixel compensation can be performed on the pixel unit based on the target pixel compensation value.

[0108] This application embodiment determines the predicted temperature value of a pixel unit on the display screen, determines the target pixel compensation value of the pixel unit based on the predicted temperature value, and performs pixel compensation on the pixel unit based on the target pixel compensation value. The pixel compensation method provided in this application embodiment compensates the pixels in the display area after displaying an image for a long time, avoiding image retention caused by different luminous efficiencies of the LEDs in the display area due to prolonged image display, thus preventing uneven display. This application embodiment solves the problem of uneven display in MiniLED displays in related technologies.

[0109] In one embodiment of this application, determining the predicted temperature value of a pixel unit on the display screen includes:

[0110] The predicted temperature value is determined based on the target cumulative pixel value of the pixel unit; wherein the target cumulative pixel value is determined based on the pixel value of the pixel unit and the display duration.

[0111] Specifically, since the longer the display time when displaying the target image, the higher the surface temperature of the display screen, in this embodiment, the cumulative pixel value can be used to simulate the temperature rise process of the display screen. That is, the larger the cumulative pixel value, the more heat accumulates over time, and the higher the display screen temperature. Therefore, for a pixel unit in the display screen, the predicted temperature value can be determined based on the target cumulative pixel value of the pixel unit.

[0112] The cumulative pixel value of the pixel unit is called the target cumulative pixel value.

[0113] The target cumulative pixel value is determined based on the pixel value of the pixel unit and the display duration. For example, within a certain time range, the target cumulative pixel value has a linear relationship with the display duration. For instance, if the pixel value of the pixel unit is 'a' and the display duration is 5 minutes, then the target cumulative pixel value can be 5a; if the display duration is 10 minutes, then the target cumulative pixel value can be 10a; if the display duration is 15 minutes, then the target cumulative pixel value can be 15a, and so on. However, since the display screen temperature does not rise indefinitely, after the display duration exceeds a certain range, the display screen temperature reaches its maximum value and tends to stabilize. Therefore, the trend of the target cumulative pixel value changing over time can be seen in... Figure 3 The sigmoid function is shown below.

[0114] Therefore, this application embodiment can use the sigmoid function to simulate the target cumulative pixel value. That is, the target cumulative pixel value rises rapidly in the initial stage, and the rate of increase slows down over time until it reaches an upper limit. In actual implementation, the sigmoid function image is modified to pass through 0, obtaining the function representation of the target cumulative pixel value. That is, the target cumulative pixel value is determined based on the pixel value of the pixel unit, the display duration, and a first data relationship. The first data relationship includes:

[0115]

[0116] X ij This represents the target cumulative pixel value of the pixel unit in the i-th row and j-th column of the target image; i represents the row number; j represents the column number;

[0117] 'a' represents the preset adjustment coefficient;

[0118] T max-ij This represents the preset temperature empirical value;

[0119] I sumtij The actual cumulative pixel value within the display duration is represented by t; the display duration is represented by I. sumtij =I1+I2+…+I t-1 ;I1, I2, ..., I t-1 These represent the pixel values ​​of the pixel unit in the i-th row and j-th column at each time point.

[0120] After determining the target cumulative pixel value of the pixel unit, the temperature prediction value can be determined based on the target cumulative pixel value using a pre-trained temperature prediction network.

[0121] like Figure 4 As shown, in this embodiment, the temperature prediction network adopts the ResNet50 feature extraction network structure, and spatial attention and a diffusion matrix (the diffusion matrix is...) are added to this structure. Figure 4 The small, medium, and large kernels shown in the diagram are used to simulate the temperature diffusion process at different times through this network structure. The working principle of this temperature prediction network in determining the predicted temperature value is as follows:

[0122] Obtain pixel features and weight features of the target image; wherein the pixel features are obtained by sampling the target cumulative pixel value of the pixel unit, and the weight features are obtained by sampling the preset weight value of the pixel unit;

[0123] Determine the temperature diffusion coefficient, and then determine the diffusion matrix based on the temperature diffusion coefficient;

[0124] The weighted features are determined based on the pixel features, the weight features, and the diffusion matrix;

[0125] The predicted temperature value is determined based on the weighted features.

[0126] Combination Figure 4 In practical implementation, the target image and its display duration can be used as input data for the temperature prediction network. The target cumulative pixel value of each pixel unit in the target image can be determined through the aforementioned first data relationship. Downsampling the target cumulative pixel value of each pixel unit using a multi-layer convolutional neural network yields the pixel features of the target image, i.e., the feature map F shown in the figure. Downsampling the preset weight value of each pixel unit using a multi-layer convolutional neural network yields the weight features of the target image, i.e., the spatial attention map shown in the figure.

[0127] In addition, the temperature diffusion coefficient needs to be determined, and the diffusion matrix is ​​determined based on the temperature diffusion coefficient.

[0128] The temperature diffusion coefficient is the diffusion factor α in the figure; the diffusion matrix refers to the small core, medium core, and large core in the figure.

[0129] The temperature diffusion coefficient is used to characterize the degree of temperature diffusion of a pixel unit. For example, the degree of temperature diffusion can be described as the extent to which the cumulative heat (or temperature) of a pixel unit can affect the temperature of surrounding pixel units after the display screen displays the target image for the specified display time.

[0130] In some embodiments, the temperature diffusion coefficient can be determined in the following manner, and the diffusion matrix can be determined based on the temperature diffusion coefficient:

[0131] The temperature diffusion coefficient is determined based on the maximum value among the pixel values;

[0132] Based on the numerical range of the temperature diffusion coefficient, determine the diffusion matrix corresponding to the numerical range.

[0133] In other words, the maximum value of each pixel unit in the target image can be determined, and the corresponding temperature diffusion coefficient can be determined based on the maximum value.

[0134] Then, the diffusion matrix is ​​selected based on the temperature diffusion coefficient.

[0135] The diffusion matrix is ​​divided into three types: small kernel, medium kernel, and large kernel. The small kernel has a relatively small diffusion range, the medium kernel has a relatively large diffusion range, and the large kernel has the largest diffusion range. Since the degree of temperature diffusion represented by the temperature diffusion coefficient is positively correlated with the cumulative heat (or temperature) of the pixel unit, and the cumulative heat is positively correlated with the display duration, the temperature diffusion coefficient α reflects the display duration of the input image.

[0136] When selecting the diffusion matrix, the value range of α can be divided into three intervals. When α is in the first interval (the interval with smaller values), it reflects that the display time of the target image is short and the temperature diffusion range is also small, so a small kernel can be selected. Similarly, when α is in the second interval (the interval with intermediate values), a medium kernel can be selected; when α is in the third interval (the interval with larger values), a large kernel can be selected.

[0137] The pixel features and weight features were obtained, and the diffusion matrix was determined.

[0138] Furthermore, the weighted features can be determined based on the pixel features, the weight features, and the diffusion matrix.

[0139] Optionally, in one embodiment of this application, determining the weighted features based on the pixel features, the weight features, and the diffusion matrix includes:

[0140] The diffusion matrix and the weight feature are multiplied in pairs to obtain the diffusion weight feature;

[0141] The weighted feature is obtained by multiplying the diffusion weight feature with the pixel feature.

[0142] Specifically, when performing a positional product operation between the diffusion matrix and the weight feature, the matrix element A with the largest weight value in the matrix of the weight feature can be determined first; and the matrix element B corresponding to the center point of the diffusion matrix can be determined; after aligning A and B, the diffusion matrix and the weight feature can be performed a positional product operation to obtain the diffusion weight feature.

[0143] Then, the diffusion weight feature is multiplied by the pixel feature to obtain the weighted feature.

[0144] Furthermore, the weighted features are upsampled using a multi-layer deconvolutional neural network to obtain a temperature prediction map. The temperature prediction map includes the predicted temperature value for each pixel unit.

[0145] In one embodiment of this application, determining the target pixel compensation value of the pixel unit based on the temperature prediction value includes:

[0146] A pixel compensation model is used to determine the predicted pixel compensation value corresponding to the predicted temperature value; wherein, the predicted temperature value and the predicted pixel compensation value are inversely proportional.

[0147] The target pixel compensation value is determined based on the predicted pixel compensation value and the compensation time.

[0148] After determining the predicted temperature value for each pixel unit, the target pixel compensation value for that pixel unit can be determined based on the predicted temperature value. The target pixel compensation value is the pixel value used to compensate for the pixel unit.

[0149] Because the LED driving current of a display screen is positively correlated with the pixel value of a pixel unit (i.e., the larger the pixel value, the larger the driving current), and also positively correlated with the accumulated heat (temperature) of a pixel unit (i.e., the larger the driving current, the higher the accumulated heat (temperature) of the pixel unit), it can be understood that the larger the pixel value, the higher its temperature. Therefore, after displaying a target image on the screen for a period of time, different areas of the screen accumulate different amounts of heat, resulting in different temperatures. This leads to varying luminous efficiency of the LEDs in different areas of the screen, ultimately causing uneven display when the entire screen switches to display the same pixel value.

[0150] To achieve uniform display of pixel units in the display screen, in this embodiment of the application, pixel compensation can be performed by using a method where pixel units with low temperature have large pixel compensation values ​​and pixel units with high temperature have small pixel compensation values. That is, the temperature prediction value and the pixel compensation value are inversely proportional.

[0151] Optionally, in actual implementation, in order to achieve the best human eye observation effect and to combine with the above-mentioned temperature prediction network to jointly form an end-to-end pixel compensation network architecture and reduce post-processing work, the embodiments of this application can determine the pixel compensation value through a pre-trained pixel compensation model. For ease of description, the pixel compensation value determined by the pixel compensation model can be called the predicted compensation pixel value.

[0152] Specifically, such as Figure 5 As shown, the temperature prediction map of the display screen generated by the temperature prediction network in the above steps can be input into the pixel compensation model. The pixel compensation model is used to make predictions and obtain the pixel compensation map, which is used to characterize the predicted pixel compensation value of each pixel unit.

[0153] Furthermore, since the heat of the pixel unit will gradually dissipate as the display duration increases, when performing pixel compensation on the pixel unit, the embodiments of this application can dynamically determine the target pixel compensation value of the pixel unit based on the above-mentioned predicted pixel compensation value and the display duration.

[0154] The process of dynamically determining the target pixel compensation value described above can be simulated by the afterimage fading model, which is a two-dimensional diffusion model. The pixel compensation map described above is applied to the afterimage fading model, and the predicted pixel compensation value of each pixel unit is dynamically corrected through the model to obtain the target pixel compensation value, so that the image observed by the human eye is always a uniform image as time changes.

[0155] In one embodiment of this application, the predicted pixel compensation value of each pixel unit is dynamically corrected using this model to obtain the target pixel compensation value. This can be achieved in the following way:

[0156] The target pixel compensation value is determined based on the predicted pixel compensation value, the compensation time, and the second data relationship;

[0157] The second data relationship is:

[0158]

[0159] in; The target pixel compensation value is represented by t; the compensation time is represented by u; the predicted pixel compensation value is represented by v; the preset dissipation rate is represented by x; the horizontal component of the predicted pixel compensation value is represented by y; and the vertical component of the predicted pixel compensation value is represented by y.

[0160] As shown in Figure 6, this is a rectangular afterimage simulated according to the above afterimage fading model after 10 ( Figure 6a ), 100 Figure 6b ) and 500 Figure 6c The 3D effect after the time unit shows that the rectangular afterimage gradually decreases.

[0161] In this embodiment, the target pixel compensation value of the pixel unit changes dynamically with the display duration. This allows for dynamic correction of the pixel unit after ghosting occurs, ensuring that the image observed by the human eye remains uniform throughout the display process.

[0162] In summary, such as Figure 7 As shown in the embodiments of this application, the process of pixel compensation for the pixel unit is as follows: inputting the target image and display duration into the temperature prediction network to obtain the temperature prediction map; inputting the temperature prediction map into the compensation network (the compensation network may include a pixel compensation model and a ghosting fading model) to obtain the pixel compensation map.

[0163] In one embodiment of this application, before determining the temperature prediction value based on the target accumulated pixel value of the pixel unit, the method further includes:

[0164] Obtain a training sample set; wherein the training sample set includes sample images and sample display duration;

[0165] For each of the sample images, the target cumulative pixel value and sample display duration of the pixel unit in the sample image are input into the initial training model to obtain the sample temperature prediction value of each pixel unit;

[0166] The training loss value is determined based on the predicted temperature value of the sample and the actual temperature value of the pixel unit.

[0167] Based on the training loss value, the initial training model is repeatedly trained until the temperature prediction network that meets the training termination condition is obtained.

[0168] This application provides an embodiment of the training process for a temperature prediction network:

[0169] The sample images can be obtained from publicly available datasets or through self-built datasets. Since the afterimages formed by different images after being displayed on a screen for a period of time vary, to cover as many scenarios as possible, the sample images can include images of different shapes, sizes, and colors, thereby constructing different typical pattern data for training. As an example, sample images can be found in [reference needed]. Figure 8 As shown.

[0170] In practice, 100 sample images can be acquired, increasing in increments of 5 minutes for a display duration of 50 minutes. In this case, the 100 sample images correspond to 1000 sample images with accumulated pixel values. For example, for sample image m, 5 minutes corresponds to one sample image with accumulated pixel values, 10 minutes to one sample image with accumulated pixel values, 15 minutes to one sample image with accumulated pixel values, and so on.

[0171] When acquiring tag data (i.e., acquiring the actual temperature value of each pixel unit), 100 sample images are displayed one by one on the screen for 50 minutes. The actual temperature map of each sample image (which includes the actual temperature value of each pixel unit) is sampled every 5 minutes. This yields 1000 tag images (the tag images are the actual temperature maps). These 1000 actual temperature maps correspond to the actual temperature values ​​of the sample images at different display durations. As an example, the actual temperature maps can be as follows: Figure 9 As shown, Figure 9 Four actual temperature graphs are provided for different sample images under different display durations.

[0172] During training, the mean squared error loss function was used, the number of training epochs was set to 1000, the learning rate was set to 0.001, no additional data augmentation was performed, and the network with the smallest training loss was saved as the final temperature prediction network.

[0173] In addition, for the training of the compensation network (which may include pixel compensation model and afterimage fading model), the loss function is the mean squared error loss, the number of training epochs is set to 1000, the learning rate is set to 0.001, no additional data augmentation is performed, and the network with the smallest training loss is saved as the final compensation network.

[0174] In summary, combining Figure 10 As shown, the training process of this application involves displaying the training data (i.e., sample images) on a display screen to obtain the screen surface temperature (i.e., the actual temperature map); inputting the training data into a temperature prediction network to obtain a temperature prediction map of the screen surface; and inputting the temperature prediction map into a compensation network (the compensation network may include a pixel compensation model and a ghosting fading model) to finally generate a pixel compensation map.

[0175] This application embodiment determines the predicted temperature value of a pixel unit on the display screen, determines the target pixel compensation value of the pixel unit based on the predicted temperature value, and performs pixel compensation on the pixel unit based on the target pixel compensation value. The pixel compensation method of this application embodiment can avoid heat accumulation in areas of the display screen after displaying an image for a long time, thereby affecting the luminous efficiency of the LEDs in that area and preventing uneven display (i.e., ghosting) when the display screen switches to the same grayscale display, thus improving the display effect.

[0176] This application provides a pixel compensation device, such as... Figure 11 As shown, the pixel compensation device 110 may include: a temperature determination module 1101, a pixel determination module 1102, and a compensation module 1103, wherein,

[0177] Temperature determination module 1101 is used to determine the predicted temperature value of a pixel unit of a display screen; wherein the predicted temperature value is determined based on the pixel parameters of the target image displayed on the display screen and the display duration of the target image;

[0178] The pixel determination module 1102 is used to determine the target pixel compensation value of the pixel unit based on the temperature prediction value.

[0179] The compensation module 1103 is used to perform pixel compensation on the pixel unit based on the target pixel compensation value.

[0180] In one embodiment of this application, the temperature determination module is specifically used for:

[0181] The predicted temperature value is determined based on the target cumulative pixel value of the pixel unit; wherein the target cumulative pixel value is determined based on the pixel value of the pixel unit and the display duration.

[0182] In one embodiment of this application, the pixel determination module is specifically used for:

[0183] Obtain pixel features and weight features of the target image; wherein the pixel features are obtained by sampling the target cumulative pixel value of the pixel unit, and the weight features are obtained by sampling the preset weight value of the pixel unit;

[0184] Determine the temperature diffusion coefficient, and then determine the diffusion matrix based on the temperature diffusion coefficient;

[0185] The weighted features are determined based on the pixel features, the weight features, and the diffusion matrix;

[0186] The predicted temperature value is determined based on the weighted features.

[0187] In one embodiment of this application, the pixel determination module is specifically used for:

[0188] The temperature diffusion coefficient is determined based on the maximum value among the pixel values;

[0189] Based on the numerical range of the temperature diffusion coefficient, determine the diffusion matrix corresponding to the numerical range.

[0190] In one embodiment of this application, the pixel determination module is specifically used for:

[0191] The diffusion matrix and the weight feature are multiplied in pairs to obtain the diffusion weight feature;

[0192] The weighted feature is obtained by multiplying the diffusion weight feature with the pixel feature.

[0193] In one embodiment of this application, the pixel determination module is specifically used for:

[0194] Before determining the predicted temperature value based on the target accumulated pixel value of the pixel unit.

[0195] The target cumulative pixel value is determined based on the pixel value of the pixel unit, the display duration, and the first data relationship;

[0196] The first data relationship includes:

[0197]

[0198] X ijThis represents the target cumulative pixel value of the pixel unit in the i-th row and j-th column of the target image; i represents the row number; j represents the column number;

[0199] 'a' represents the preset adjustment coefficient;

[0200] T max-ij This represents the preset temperature empirical value;

[0201] I sumtij The actual cumulative pixel value within the display duration is represented by t; the display duration is represented by I. sumiij =I1+I2+…+I t-1 ;I1, I2, ..., I t-1 These represent the pixel values ​​of the pixel unit in the i-th row and j-th column at each time point.

[0202] In one embodiment of this application, the apparatus further includes a training module, specifically used for:

[0203] Before determining the temperature prediction value based on the target accumulated pixel value of the pixel unit.

[0204] Obtain a training sample set; wherein the training sample set includes sample images and sample display duration;

[0205] For each of the sample images, the target cumulative pixel value and sample display duration of the pixel unit in the sample image are input into the initial training model to obtain the sample temperature prediction value of each pixel unit;

[0206] The training loss value is determined based on the predicted temperature value of the sample and the actual temperature value of the pixel unit.

[0207] Based on the training loss value, the initial training model is repeatedly trained until the temperature prediction network that meets the training termination condition is obtained.

[0208] In one embodiment of this application, the pixel determination module is specifically used for:

[0209] A pixel compensation model is used to determine the predicted pixel compensation value corresponding to the predicted temperature value; wherein, the predicted temperature value and the predicted pixel compensation value are inversely proportional.

[0210] The target pixel compensation value is determined based on the predicted pixel compensation value and the compensation time.

[0211] In one embodiment of this application, the pixel determination module is specifically used for:

[0212] The target pixel compensation value is determined based on the predicted pixel compensation value, the compensation time, and the second data relationship;

[0213] The second data relationship is:

[0214]

[0215] in; The target pixel compensation value is represented by t; the compensation time is represented by u; the predicted pixel compensation value is represented by v; the preset dissipation rate is represented by x; the horizontal component of the predicted pixel compensation value is represented by y; and the vertical component of the predicted pixel compensation value is represented by y.

[0216] In one embodiment of this application, the pixel unit includes one or at least two pixels.

[0217] The apparatus in this application embodiment can execute the method provided in this application embodiment, and the implementation principle is similar. The actions performed by each module in the apparatus of each embodiment of this application correspond to the steps in the method of each embodiment of this application. For detailed functional descriptions of each module of the apparatus, please refer to the descriptions in the corresponding methods shown above, which will not be repeated here.

[0218] This application embodiment determines the predicted temperature value of a pixel unit on the display screen, determines the target pixel compensation value of the pixel unit based on the predicted temperature value, and performs pixel compensation on the pixel unit based on the target pixel compensation value. The pixel compensation method of this application embodiment can avoid heat accumulation in areas of the display screen after displaying an image for a long time, thereby affecting the luminous efficiency of the LEDs in that area and preventing uneven display (i.e., ghosting) when the display screen switches to the same grayscale display, thus improving the display effect.

[0219] This application provides an electronic device, comprising: a memory and a processor; at least one program stored in the memory, which, when executed by the processor, can achieve the following compared to the prior art: This application determines a predicted temperature value for a pixel unit of a display screen, determines a target pixel compensation value for the pixel unit based on the predicted temperature value, and performs pixel compensation on the pixel unit based on the target pixel compensation value. The pixel compensation method of this application can avoid heat accumulation in an area of ​​the display screen after displaying an image for a long time, thereby affecting the luminous efficiency of the LEDs in that area and causing uneven display (i.e., ghosting) when the display screen switches to the same grayscale display, thus improving the display effect.

[0220] In one alternative embodiment, an electronic device is provided, such as Figure 12 As shown, Figure 12The illustrated electronic device 4000 includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of this application.

[0221] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0222] Bus 4002 may include a pathway for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 12 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0223] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0224] The memory 4003 stores application code (computer program) that executes the solution of this application, and its execution is controlled by the processor 4001. The processor 4001 executes the application code stored in the memory 4003 to implement the content shown in the foregoing method embodiments.

[0225] Electronic devices include, but are not limited to: mobile phones, laptops, multimedia players, desktop computers, etc.

[0226] This application provides a computer-readable storage medium storing a computer program that, when run on a computer, enables the computer to execute the corresponding content in the aforementioned method embodiments.

[0227] This application embodiment determines the predicted temperature value of a pixel unit on the display screen, determines the target pixel compensation value of the pixel unit based on the predicted temperature value, and performs pixel compensation on the pixel unit based on the target pixel compensation value. The pixel compensation method of this application embodiment can avoid heat accumulation in areas of the display screen after displaying an image for a long time, thereby affecting the luminous efficiency of the LEDs in that area and preventing uneven display (i.e., ghosting) when the display screen switches to the same grayscale display, thus improving the display effect.

[0228] The terms "first," "second," "third," "fourth," "1," "2," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in a sequence other than that shown in the figures or text.

[0229] It should be understood that although arrows indicate various operation steps in the flowcharts of this application's embodiments, the order in which these steps are implemented is not limited to the order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of this application's embodiments, the implementation steps in each flowchart can be executed in other orders as required. Furthermore, some or all steps in each flowchart, based on the actual implementation scenario, may include multiple sub-steps or multiple stages. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage can also be executed at different times. In scenarios where execution times differ, the execution order of these sub-steps or stages can be flexibly configured according to requirements, and this application's embodiments do not limit this.

[0230] The above description is only an optional implementation method for some implementation scenarios of this application. It should be noted that for those skilled in the art, other similar implementation methods based on the technical concept of this application without departing from the technical concept of this application also fall within the protection scope of the embodiments of this application.

Claims

1. A pixel compensation method, characterized in that, include: Determine the predicted temperature value of a pixel unit on the display screen; wherein the predicted temperature value is determined based on the pixel parameters of the target image displayed on the display screen and the display duration of the target image; Based on the predicted temperature value, determine the target pixel compensation value for the pixel unit; Pixel compensation is performed on the pixel unit based on the target pixel compensation value; Determining the predicted temperature value of the pixel unit of the display screen includes: The predicted temperature value is determined based on the target cumulative pixel value of the pixel unit; wherein the target cumulative pixel value is determined based on the pixel value of the pixel unit and the display duration; Determining the target pixel compensation value for the pixel unit based on the predicted temperature value includes: Obtain pixel features and weight features of the target image; wherein the pixel features are obtained by sampling the target cumulative pixel value of the pixel unit, and the weight features are obtained by sampling the preset weight value of the pixel unit; Determine the temperature diffusion coefficient, and then determine the diffusion matrix based on the temperature diffusion coefficient; The weighted features are determined based on the pixel features, the weight features, and the diffusion matrix; The predicted temperature value is determined based on the weighted features.

2. The pixel compensation method according to claim 1, characterized in that, The determination of the temperature diffusion coefficient, and the determination of the diffusion matrix based on the temperature diffusion coefficient, include: The temperature diffusion coefficient is determined based on the maximum value among the pixel values; Based on the numerical range of the temperature diffusion coefficient, determine the diffusion matrix corresponding to the numerical range.

3. The pixel compensation method according to claim 1, characterized in that, The step of determining the weighted features based on the pixel features, the weight features, and the diffusion matrix includes: The diffusion matrix and the weight feature are multiplied in pairs to obtain the diffusion weight feature; The weighted feature is obtained by multiplying the diffusion weight feature with the pixel feature.

4. The pixel compensation method according to claim 1, characterized in that, Before determining the temperature prediction value based on the target accumulated pixel value of the pixel unit, the method further includes: The target cumulative pixel value is determined based on the pixel value of the pixel unit, the display duration, and the first data relationship; The first data relationship includes: ； Indicates the first in the target image Line 1 The target cumulative pixel value of the pixel unit in the column; Indicates the row number; Indicates the column number; Indicates the preset adjustment coefficient; This represents the preset temperature empirical value; This represents the actual cumulative pixel value within the display duration; This indicates the display duration; ; Each time point represents the first... Line 1 The pixel value of the pixel unit in the column.

5. The pixel compensation method according to claim 1, characterized in that, Before determining the temperature prediction value based on the target accumulated pixel value of the pixel unit, the method further includes: Obtain a training sample set; wherein the training sample set includes sample images and sample display duration; For each of the sample images, the target cumulative pixel value and sample display duration of the pixel unit in the sample image are input into the initial training model to obtain the sample temperature prediction value of each pixel unit; The training loss value is determined based on the predicted temperature value of the sample and the actual temperature value of the pixel unit. Based on the training loss value, the initial training model is repeatedly trained until a temperature prediction network that meets the training termination condition is obtained.

6. The pixel compensation method according to claim 1, characterized in that, Determining the target pixel compensation value of the pixel unit based on the predicted temperature includes: A pixel compensation model is used to determine the predicted pixel compensation value corresponding to the predicted temperature value; wherein, the predicted temperature value and the predicted pixel compensation value are inversely proportional. The target pixel compensation value is determined based on the predicted pixel compensation value and the compensation time.

7. The pixel compensation method according to claim 6, characterized in that, Determining the target pixel compensation value based on the predicted pixel compensation value and the compensation time includes: The target pixel compensation value is determined based on the predicted pixel compensation value, the compensation time, and the second data relationship; The second data relationship is: ； in; The target pixel compensation value is represented by t; the compensation time is represented by u; the predicted pixel compensation value is represented by v; the preset dissipation rate is represented by x; the horizontal component of the predicted pixel compensation value is represented by y; and the vertical component of the predicted pixel compensation value is represented by y.

8. The pixel compensation method according to any one of claims 1 to 7, characterized in that, The pixel unit includes one or at least two pixels.

9. A pixel compensation device, characterized in that, include: A temperature determination module is used to determine the predicted temperature value of a pixel unit of a display screen; wherein the predicted temperature value is determined based on the pixel parameters of the target image displayed on the display screen and the display duration of the target image; A pixel determination module is used to determine the target pixel compensation value of the pixel unit based on the temperature prediction value. The compensation module is used to perform pixel compensation on the pixel unit based on the target pixel compensation value; The temperature determination module is specifically used to determine the temperature prediction value based on the target cumulative pixel value of the pixel unit; wherein the target cumulative pixel value is determined based on the pixel value of the pixel unit and the display duration; The temperature determination module is further configured to acquire pixel features and weight features of the target image; wherein the pixel features are obtained by sampling the target cumulative pixel value of the pixel unit, and the weight features are obtained by sampling the preset weight value of the pixel unit; determine the temperature diffusion coefficient, determine the diffusion matrix based on the temperature diffusion coefficient; determine the weighted features based on the pixel features, the weighted features, and the diffusion matrix; and determine the temperature prediction value based on the weighted features.

10. An electronic device, characterized in that, The electronic device includes: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to: perform the pixel compensation method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the pixel compensation method according to any one of claims 1 to 8.

Images