Real-time image quality optimization method and system for intelligent display equipment

Abstract

The invention relates to a real-time image quality optimization method and system for intelligent display equipment, and the method comprises the following steps: carrying out the real-time sensing of the preset environment illumination intensity and watching distance of the display equipment, and obtaining a scene parameter data stream; performing dynamic brightness mapping on a target display image in the display device based on the scene parameter data stream to obtain a brightness compensation curve; performing pixel-level modulation on the target display image based on the brightness compensation curve to obtain image enhancement data; performing color space conversion on the image enhancement data to obtain a color enhancement matrix; gray scale voltage modulation is carried out on the display panel based on the color enhancement matrix, an optimized display image is obtained, and the technical problem that overexposure or color distortion of an image is prone to occurring in a strong light or weak light environment due to the fact that a traditional image enhancement technology is difficult to adapt to a complex and changeable viewing environment is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of display devices, in particular to a real-time image quality optimization method and system for intelligent display devices. BACKGROUND

[0002] With the rapid development of display technology, intelligent display devices have been widely used in various scenes of people's daily life, such as smart phones, tablet computers, televisions, and vehicle displays. Users' requirements for display quality are increasingly improving, and they are no longer limited to clarity and resolution, but also pursue visual comfort and image quality performance in different environments. Traditional image enhancement techniques rely on static image processing algorithms, which are difficult to adapt to complex and variable viewing environments, resulting in problems such as overexposure, loss of dark details, or color distortion in strong or weak light environments, affecting users' visual experience. SUMMARY

[0003] The main purpose of the present application is to provide a real-time image quality optimization method and system for intelligent display devices, which solves the technical problem that traditional image enhancement techniques are difficult to adapt to complex and variable viewing environments, resulting in overexposure or color distortion in strong or weak light environments.

[0004] To achieve the above purpose, the present application provides a real-time image quality optimization method for intelligent display devices, comprising the following steps: real-time sensing of the preset environmental light intensity and viewing distance of the display device to obtain scene parameter data stream; based on the scene parameter data stream, performing dynamic brightness mapping on the target display image in the display device to obtain a brightness compensation curve; wherein the display device is provided with a display panel; based on the brightness compensation curve, performing pixel-level modulation on the target display image to obtain image enhancement data; performing color space conversion on the image enhancement data to obtain a color enhancement matrix; based on the color enhancement matrix, performing gray scale voltage modulation on the display panel to obtain an optimized display image.

[0005] Further, the viewing distance is the spatial positional relationship between the viewer and the display panel, and the real-time sensing of the preset environmental light intensity and viewing distance of the display device to obtain the scene parameter data stream comprises: wavelength decomposition sampling of the preset environmental light intensity around the display device by a multi-band spectral sensing array to obtain a spectral distribution feature map, and performing frequency spectrum analysis on the environmental light intensity based on the spectral distribution feature map to obtain light spectrum features; The time-of-flight ranging system is used to locate the spatial position relationship between the viewer and the display panel in three-dimensional coordinates, to obtain position distribution point cloud data, and to extract geometric features of the position distribution point cloud data to obtain a viewing distance dynamic mapping curve. The light spectrum features and the viewing distance dynamic mapping curve are subjected to time sequence correlation analysis to obtain a scene feature correlation mode, and the scene feature correlation mode is used to calculate the weight distribution of the preset real-time collected environmental parameters to obtain scene parameter data flow.

[0006] Further, the target display image is subjected to pixel-level modulation based on the brightness compensation curve to obtain image enhancement data, including: The brightness compensation curve is subjected to spatial frequency decomposition to obtain a multi-band contrast component map; The multi-band contrast component map is subjected to regional contrast calculation to obtain contrast modulation parameters, and the low-contrast regions of the target display image are subjected to selective enhancement processing based on the contrast modulation parameters to obtain a detail recovery gain coefficient; The detail recovery gain coefficient is used to separate and enhance the texture details and edge structures in the target display image to obtain a structure and texture level matrix; The target display image is subjected to pixel-level modulation based on the structure and texture level matrix to obtain image enhancement data.

[0007] Further, the image enhancement data is subjected to color space conversion to obtain a color enhancement matrix, including: The image enhancement data is subjected to color channel decoupling analysis to obtain a color component feature vector, and the colorimetric characteristics of the target display image are quantified based on the color component feature vector to obtain a color saturation distribution; The color saturation distribution is subjected to visual cognitive scene matching calculation based on a color adaptability transformation kernel to obtain a colorimetric adaptability parameter, and the color performance of the image enhancement data is non-uniformly enhanced based on the colorimetric adaptability parameter to obtain a color enhancement gradient surface; The color enhancement gradient surface is subjected to visual color constancy analysis to obtain a color constancy compensation factor, and the color offset regions in the image enhancement data are selectively corrected based on the color constancy compensation factor to obtain a color gamut mapping control parameter; The color gamut mapping control parameter is subjected to color space coordinate transformation to obtain a target color space transformation matrix, and the color relationship in the image enhancement data is reconstructed based on the target color space transformation matrix to obtain a color enhancement matrix.

[0008] Further, the preset display panel is subjected to gray scale voltage modulation based on the color enhancement matrix to obtain an optimized display image, including: The color enhancement matrix is converted from a digital signal to a voltage signal by a gray scale voltage mapping processor to obtain an initial voltage modulation data set, and input signal calibration is performed on a pixel driving circuit in the display panel based on the initial voltage modulation data set to obtain a pixel driving voltage mapping table; Nonlinear response characteristics analysis is performed on the pixel driving voltage mapping table by a gamma curve optimization unit to obtain gamma compensation parameters, and panel physical characteristic matching processing is performed on the gamma compensation parameters by a display panel characteristic compensation engine to obtain a panel characteristic compensation vector, uniformity correction calculation is performed on different regions in the display panel based on the panel characteristic compensation vector to obtain a region uniformity compensation matrix, and content adaptive adjustment is performed on the display panel based on the region uniformity compensation matrix to obtain a frame rate optimization control signal; The frame rate optimization control signal and the color enhancement matrix are subjected to comprehensive evaluation processing to obtain a display quality evaluation index, and real-time voltage and timing fine tuning is performed on the driving circuit of the display panel based on the display quality evaluation index to obtain an optimized display image.

[0009] Further, the real-time voltage and timing fine tuning is performed on the driving circuit of the display panel based on the display quality evaluation index to obtain an optimized display image, including: Voltage-luminance response characteristic analysis is performed on the display quality evaluation index by a multi-dimensional voltage mapping system to obtain pixel driving voltage optimization parameters, and real-time voltage compensation processing is performed on the gate driving circuit and the source driving circuit of the display panel based on the pixel driving voltage optimization parameters to obtain a compensated driving voltage curve; In-frame synchronization characteristic optimization is performed on the compensated driving voltage curve to obtain timing modulation control parameters, and content-dependent dynamic adjustment is performed on the display panel based on the timing modulation control parameters to obtain adaptive timing control parameters; Comprehensive and synergistic optimization is performed on the adaptive timing control parameters and the compensated driving voltage curve to obtain a voltage-timing joint modulation coefficient table, and accurate fine tuning is performed on the driving circuit of the display panel based on the voltage-timing joint modulation coefficient table to obtain an optimized display image.

[0010] The application also provides a real-time image quality optimization system of an intelligent display device, including: A perception module is configured to perceive the ambient light intensity and the viewing distance of the preset display device in real time to obtain scene parameter data streams; The mapping module is configured to perform dynamic brightness mapping on a target display image in the display device based on the scene parameter data stream, so as to obtain a brightness compensation curve; and the display device is provided with a display panel. The first modulation module is configured to perform pixel-level modulation on the target display image based on the brightness compensation curve, so as to obtain image enhancement data. The conversion module is configured to perform color space conversion on the image enhancement data, so as to obtain a color enhancement matrix. The second modulation module is configured to perform gray-scale voltage modulation on the display panel based on the color enhancement matrix, so as to obtain an optimized display image.

[0011] The present application also provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to realize the steps of the method.

[0012] The present application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the steps of the method.

[0013] The present application provides a real-time image quality optimization method of an intelligent display device, which comprises the following steps: real-time sensing of a preset environmental light intensity and a viewing distance of the display device to obtain a scene parameter data stream; performing dynamic brightness mapping on a target display image in the display device based on the scene parameter data stream to obtain a brightness compensation curve; performing pixel-level modulation on the target display image based on the brightness compensation curve to obtain image enhancement data; performing color space conversion on the image enhancement data to obtain a color enhancement matrix; and performing gray-scale voltage modulation on the display panel based on the color enhancement matrix to obtain an optimized display image. BRIEF DESCRIPTION OF DRAWINGS

[0014] Figure 1 is a step schematic diagram of the real-time image quality optimization method of the intelligent display device in an embodiment of the present application. Figure 2 is a structural block diagram of the real-time image quality optimization device of the intelligent display device in an embodiment of the present application. Figure 3 is a structural schematic block diagram of the computer device in an embodiment of the present application.

[0015] The purposes, technical solutions and advantages of the present application will be further described with reference to the accompanying drawings and embodiments. DETAILED DESCRIPTION

[0016] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application.

[0017] As shown in Figure 1 , Figure 1 is a schematic diagram of the steps of a real-time image quality optimization method of an intelligent display device in an embodiment of the present application; An embodiment of the present application provides a real-time image quality optimization method of an intelligent display device, which comprises the following steps: Step S1, real-time sensing of a preset ambient light intensity and a viewing distance of a display device to obtain a scene parameter data stream; Step S2, dynamic brightness mapping of a target display image in the display device based on the scene parameter data stream to obtain a brightness compensation curve; wherein the display device is provided with a display panel; Step S3, pixel-level modulation of the target display image based on the brightness compensation curve to obtain image enhancement data; Step S4, color space conversion of the image enhancement data to obtain a color enhancement matrix; Step S5, gray scale voltage modulation of the display panel based on the color enhancement matrix to obtain an optimized display image.

[0018] Specifically, in the real-time image quality optimization method of the intelligent display device, first, step S1 is performed, that is, the ambient light intensity and viewing distance of the preset display device are perceived in real time to obtain scene parameter data stream, this step is the basis and premise of the whole image optimization process, and the purpose is to obtain the key physical parameters of the external environment where the current device is located, so that the subsequent processing can respond based on the real and dynamic use scene; Specifically, the ambient light sensor built-in the display device is responsible for collecting surrounding light intensity information, for example, in bright outdoor sunlight, the light intensity may reach tens of thousands of lux, while in a dim indoor environment, it may be less than 100 lux, at the same time, the device can also estimate the viewing distance between the user and the display panel through infrared sensors, ToF (Time of Flight) sensors or front-facing cameras combined with deep learning algorithms, for example, when the user watches TV in the living room, the distance may be 3 meters, while when reading on a handheld phone, the distance is only about 30 centimeters; These continuously collected data are integrated into a scene parameter data stream that changes over time, which not only contains the current light and distance values, but also may contain their trend, thereby providing sufficient context information for subsequent processing. Then step S2 is entered, dynamic brightness mapping is performed on the target display image in the display device based on the scene parameter data stream to obtain a brightness compensation curve; Here, "dynamic brightness mapping" refers to establishing a non-linear brightness adjustment function according to the combination of the current ambient light intensity and viewing distance, for example, in strong light environment, the perception ability of human eye to screen brightness decreases, so the overall brightness of the image needs to be improved to ensure readability, while in weak light environment, the brightness needs to be reduced to avoid glare; At the same time, the viewing distance also affects the sensitivity of the human eye to contrast and details, near distance viewing requires higher local contrast to enhance clarity, and long distance relies more on overall brightness balance; Therefore, the system will generate a brightness compensation curve that adapts to the current scene by integrating these two parameters, this curve defines how each brightness level in the original image should be mapped to the new output value, thereby realizing personalized brightness adjustment strategy. Then step S3 is performed, pixel-level modulation is performed on the target display image based on the brightness compensation curve to obtain image enhancement data; The core of this step is to apply the aforementioned brightness compensation curve to each pixel point of the target display image pixel by pixel, to realize fine pixel-level brightness adjustment, for example, for a landscape image containing sky, buildings and shadow areas, in outdoor strong light environment, the system may enhance the brightness of the dark area to reveal details through the brightness compensation curve, while moderately suppressing the highlight area to prevent overexposure, this modulation process is not a simple global brightening or darkening, but a result of the synergistic effect of image content and environmental parameters, the finally output image enhancement data retains more visual information and improves the dynamic range performance.Next is step S4, color space conversion is performed on the image enhancement data to obtain a color enhancement matrix; in this process, the system converts the image data after brightness modulation from the original color space (such as RGB) to an intermediate space (such as YUV or LAB) that is more suitable for color optimization, wherein the luminance component (Y) has been optimized by the previous step, and the chrominance component (U / V or a / b) can be adjusted according to the color temperature characteristics of the ambient light, for example, in a warm light environment, the blue saturation is appropriately enhanced to offset the yellowing effect caused by the ambient light, and in a cold light, the red color is enhanced to improve the visual warmth; through this conversion, the system generates a color enhancement matrix that encapsulates the color correction and enhancement parameters for the current scene, ensuring that the color performance is both true and expressive. Finally, step S5 is performed, the gray scale voltage of the display panel is modulated based on the color enhancement matrix to obtain an optimized display image; this step marks the transition of image processing from the digital domain to the physical display domain, and the color enhancement matrix is sent to the display driving chip to adjust the gray scale voltage output level of each pixel on the display panel, for example, a certain pixel originally should display medium red (R = 128), but under the current environment and image content, the color enhancement matrix indicates that its saturation needs to be improved, then the driving circuit will correspondingly increase the gray scale voltage of the red sub-pixel of this pixel, so that it emits light more strongly, thus presenting a more vivid red color; this gray scale voltage modulation based on optimized data directly acts on the light emitting mechanism of the display panel, ensuring that the final optimized display image not only gets enhanced at the algorithm level, but also realizes accurate restoration in the physical display effect. For example, when a user uses a tablet computer to watch a video in the strong sunlight in the afternoon, the device perceives that the ambient light intensity is as high as 50,000 lux and the viewing distance is about 40 cm, and the system generates a compensation curve that significantly improves the mapping of the medium and low brightness interval in step S2, and the dark area of the video frame is locally brightened in step S3 to avoid loss of shadow details, then the color saturation and hue are adjusted according to the enhanced luminance data in step S4 to prevent the color from becoming pale due to the increase in brightness, and the display panel is driven with higher gray scale voltage in step S5 to finally present a bright and clear image with vivid colors and visual comfort; on the contrary, when the user uses the same device at night in bed, the ambient light is weak (about 50 lux) and the viewing distance is shortened to 25 cm, the system generates a compensation curve that reduces the overall brightness but enhances the local contrast to avoid strong light stimulating the eyes, while maintaining color accuracy through the color enhancement matrix, and finally realizes the display effect of eye protection and picture quality through fine adjustment of the gray scale voltage; as can be seen, through the close connection of the five steps, the system realizes full-link collaborative optimization from environment perception to physical display, significantly improving the image quality performance of intelligent display devices in diversified application scenarios.

[0019] In a specific scenario, the viewing distance is the spatial positional relationship between the viewer and the display panel, the preset ambient light intensity and viewing distance of the display device are perceived in real time to obtain a scene parameter data stream, including: The ambient light intensity around the preset display device is wavelength-decomposed and sampled by a multi-band spectral sensing array to obtain a spectral distribution feature map, and the ambient light intensity is spectrally analyzed based on the spectral distribution feature map to obtain a light spectrum feature; The spatial positional relationship between the viewer and the display panel is three-dimensionally positioned based on a time-of-flight ranging system to obtain position distribution point cloud data, and the position distribution point cloud data is geometrically characterized to obtain a viewing distance dynamic mapping curve; The light spectrum feature and the viewing distance dynamic mapping curve are time-series correlation analyzed to obtain a scene feature correlation mode, and the preset real-time collected environmental parameters are weight-allocated and calculated based on the scene feature correlation mode to obtain a scene parameter data stream.

[0020] Specifically, the ambient light intensity and viewing distance of the preset display device are perceived in real time to obtain scene parameter data stream, and this process not only depends on basic sensor input, but also constructs a dynamic parameter system that can truly reflect the user's use environment through multi-dimensional and high-precision data collection and fusion analysis. Specifically, the viewing distance is essentially the spatial positional relationship between the viewer and the display panel, and its change directly affects the subjective experience of human eye in image definition, contrast and color perception. Therefore, in the perception link, the system first performs wavelength decomposition sampling on the ambient light intensity around the preset display device through a multi-band spectral sensing array, which means that the sensor no longer measures only the intensity of the overall light, but collects the incident light according to different wavelength intervals (such as red, green, blue, near-infrared, etc.), thereby obtaining a spectral distribution feature map that records the energy distribution of each wavelength of light in the environment. For example, under sunlight, the visible spectrum is relatively balanced, while under incandescent lamp lighting, the red component is significantly enhanced. Based on the spectral distribution feature map, the system further performs spectral analysis on the ambient light intensity, identifies the dominant light source type (such as natural light, LED, fluorescent lamp, etc.), and extracts key light spectrum features. These features not only include brightness values, but also cover color temperature, color rendering index and other important parameters that affect visual perception. At the same time, in order to accurately obtain the spatial positional relationship between the viewer and the display panel, the system uses a time-of-flight (ToF) ranging system. This system realizes high-precision positioning of three-dimensional space coordinates by emitting modulated light pulses and measuring the time difference of the reflected pulses from the target (i.e. the viewer's face or eyes) back to the sensor, thereby obtaining position distribution point cloud data. These point cloud data contain real-time position information of the viewer on the X, Y and Z axes, especially in the Z-axis direction, which can accurately reflect the distance change. Subsequently, the system extracts geometric features from the position distribution point cloud data, identifies key structures such as face contour and eye position, and constructs a viewing distance dynamic mapping curve that changes over time through displacement analysis between consecutive frames. This curve can reflect the user's behavior patterns such as moving forward and backward and tilting the viewing angle during use. Next, instead of treating the light spectrum features and viewing distance dynamic mapping curve as isolated data, the system performs time sequence correlation analysis, i.e. synchronously compares the fluctuation trends of the two in the time dimension. For example, when the user enters a dim bedroom from a bright living room, the light spectrum features will gradually change from high brightness and cold color to low brightness and warm color, while the viewing distance dynamic mapping curve may show that the user sits closer. The system thereby identifies the typical scene feature correlation pattern of "nighttime close-range viewing". Based on this pattern, the system performs weight allocation calculation on the preset real-time collected environmental parameters, such as giving higher weight to light intensity in a bright and far distance scene, and increasing the influence proportion of viewing distance in a dim and close distance scene, and finally fusing to generate a scene parameter data stream with context awareness capability.For example, when a user uses a smart TV on a balcony in the afternoon when the sun is shining directly, the multi-band spectral sensing array detects a strong sunlight component, and the time-of-flight ranging system confirms that he is sitting on a sofa 3 meters away. The system accordingly determines that the screen brightness needs to be significantly increased and the color needs to be adjusted to counteract the environmental light interference; at night, the same user lies on the sofa 2 meters away to watch a movie, the light spectrum feature shows low-intensity warm light, and the viewing distance dynamic mapping curve presents a small fluctuation. The system automatically reduces the overall brightness, enhances the dark details, and fine-tunes the color saturation to achieve a comfortable eye-protecting viewing experience. As can be seen, through multi-modal sensing and deep data fusion, the scheme realizes accurate characterization of complex use scenarios and provides highly reliable basic input for subsequent image optimization.

[0021] In a specific scenario, the dynamic brightness mapping of the target display image in the display device based on the scene parameter data stream comprises: The scene parameter data stream is subjected to light perception vector decomposition to obtain light parameter feature components, and the pixel brightness distribution of the target display image is subjected to histogram analysis based on the light parameter feature components to obtain a brightness distribution probability density function; The brightness distribution probability density function is subjected to nonlinear stretching transformation by a light compensation processor to obtain a brightness dynamic range expansion coefficient, and the pixel level of the target display image is subjected to point-by-point brightness remapping based on the brightness dynamic range expansion coefficient to obtain a brightness modulation curve; The edge brightness transition of the brightness modulation curve is analyzed by an adaptive color gamut boundary detector to obtain an edge brightness gradient vector, and the transition zone between the high-brightness region and the low-brightness region in the target display image is subjected to smoothing processing based on the edge brightness gradient vector to obtain a transition zone width adjustment parameter; The transition zone width adjustment parameter is subjected to regional brightness balance calculation by a partitioned brightness equalization processing unit to obtain a local brightness equalization factor, and different brightness regions in the target display image are subjected to parameterized adjustment based on the local brightness equalization factor to obtain a regional brightness response curve; The regional brightness response curve is subjected to global optimization and integration by a multi-level curve fusion network to obtain a global brightness mapping function, and the overall brightness distribution of the target display image is subjected to adaptive modulation based on the global brightness mapping function to obtain a brightness compensation curve.

[0022] Specifically, based on the scene parameter data stream, the target display image in the display device is subjected to dynamic brightness mapping to obtain a brightness compensation curve, which is a core link for realizing environment-adaptive image optimization. Through multi-level and refined brightness analysis and reconstruction mechanism, external perception information is converted into a mathematical function that can guide pixel-level dimming. Specifically, the system first performs illumination perception vector decomposition on the scene parameter data stream. This operation decomposes the multi-dimensional data stream containing the dynamic mapping curve of ambient light intensity and viewing distance into independent illumination parameter characteristic components according to their physical properties, for example, separates the total light intensity into the contribution weights of visible light, infrared and ultraviolet bands, and combines the viewing distance to reflect the change trend of the human eye sensitivity to brightness, to form a group of feature vectors that can fully represent the current visual environment. Subsequently, based on the illumination parameter characteristic components, the pixel brightness distribution of the target display image is subjected to histogram analysis, that is, the frequency of each brightness level (such as 0~255 gray scale) in the image is counted, and then a brightness distribution probability density function is constructed. This function not only reveals whether the overall image is dark, bright or has high contrast characteristics, but also identifies the brightness interval of key details, providing a basis for subsequent targeted enhancement. Next, the system introduces a light compensation processor to perform nonlinear scaling transformation on the brightness distribution probability density function. This transformation is not a simple linear stretching, but an adaptive mapping strategy according to the current ambient light conditions (such as lifting the response of the low brightness area under strong light, and compressing the high brightness area under weak light to protect the eyes), so as to obtain a brightness dynamic range expansion coefficient. This coefficient quantifies the brightness range that the image should be expanded or compressed under the current environment. Based on the brightness dynamic range expansion coefficient, the system performs point-by-point brightness remapping of the pixel level of the target display image, that is, the original brightness value of each pixel is revalued according to the new mapping relationship to generate a preliminary brightness modulation curve. This curve preliminarily realizes the global brightness optimization and adjustment, but may cause discontinuity or distortion at the junction of light and shade. In order to improve this problem, the system analyzes the edge brightness transition of the brightness modulation curve through an adaptive color gamut boundary detector to identify the boundary position between the high brightness area (such as sky, light) and the low brightness area (such as shadow, dark part) in the image, and extract the brightness change rate of these boundaries to form an edge brightness gradient vector. Based on the edge brightness gradient vector, the system performs smoothing processing on the transition zone between the high brightness area and the low brightness area in the target display image to avoid the "halo" or "edge break" phenomenon caused by large brightness jump, thereby obtaining a transition zone width adjustment parameter. This parameter determines whether the transition area should be widened or compressed to realize natural fusion in vision.Subsequently, the system performs regional luminance balance calculation on the transition band width adjustment parameter by using a partitioned luminance balance processing unit, that is, the image is divided into multiple logical regions (such as a central region and a corner region), and the required local luminance balance factor of each region is calculated in combination with the user gaze preference reflected by the viewing distance dynamic mapping curve (such as paying more attention to the central content when viewing at a close distance); these factors are used to further fine-tune the luminance response characteristics of each region, to ensure that the central region is clear and the edge region is not too dark, and finally a set of regional luminance response curves reflecting spatial differentiation is generated. Finally, the system performs global optimization and integration on the regional luminance response curves by using a multi-level curve fusion network. The network uses weighted fusion or a deep learning model to seamlessly splice multiple local optimization curves into a continuous, smooth, and globally consistent global luminance mapping function. Based on the global luminance mapping function, the system adaptively modulates the overall luminance distribution of the target display image, comprehensively considers multiple factors such as ambient light intensity, viewing distance, image content structure, and finally outputs a luminance compensation curve that can improve visual comfort and preserve the semantic information of the original image. For example, when a user uses a tablet computer to view a city street scene photo outdoors in the afternoon when the sunlight is strong, the scene parameter data stream shows that the ambient light intensity is as high as 50,000 lux and the viewing distance is about 40 cm. The system identifies that the ability of the human eye to identify dark details decreases in a strong light environment through light perception vector decomposition, and then finds that the image shadow region pixels are concentrated in the low gray stage and the luminance distribution probability density function presents a left bias feature in histogram analysis. The light compensation processor accordingly applies a nonlinear scaling transformation to significantly improve the mapping weight of the medium and low luminance region, generating a preliminary luminance modulation curve. The adaptive color gamut boundary detector then detects that there is a sharp luminance gradient at the junction of the building and the sky, and the edge luminance gradient vector indicates that the transition band needs to be widened. The system realizes gradual fusion through the transition band width adjustment parameter. The partitioned luminance balance processing unit further enhances the local contrast of the central road region, and the multi-level curve fusion network finally integrates all the regional response curves to generate a luminance compensation curve that can highlight dark details without overexposure of highlights, so that the user can still clearly identify the picture content in strong light. When reading an e-book at close range at night, the system detects that the ambient light is weak and the user is close to the screen, and accordingly generates a compensation curve that compresses the highlight region and improves the contrast of the medium gray scale, effectively reducing visual fatigue. As can be seen, through the complete chain from light perception to multi-level fusion, the scheme realizes a dynamic luminance mapping mechanism that cooperates situation perception, content adaptation, and visual optimization.

[0023] In specific scenarios, the pixel-level modulation of the target display image based on the luminance compensation curve to obtain image enhancement data includes: performing spatial frequency decomposition on the luminance compensation curve to obtain a multi-band contrast component map; The multi-band contrast component map is subjected to a regional contrast calculation to obtain a contrast modulation parameter, and a low-contrast region of the target display image is subjected to a selective enhancement processing based on the contrast modulation parameter to obtain a detail recovery gain coefficient; The detail recovery gain coefficient is subjected to a separate enhancement processing of texture details and edge structures in the target display image to obtain a structure and texture level matrix. The target display image is subjected to a pixel-level modulation based on the structure and texture level matrix to obtain image enhancement data.

[0024] Specifically, the target display image is pixel-level modulated based on the brightness compensation curve to obtain image enhancement data. This process is not a simple global brightness adjustment, but through in-depth analysis of the frequency domain characteristics and spatial structure distribution of the brightness compensation curve, the image content is finely and adaptively enhanced. Specifically, the system first performs spatial frequency decomposition on the brightness compensation curve. This operation disassembles the brightness compensation curve, which is originally a whole mapping function, according to different spatial frequency components, thereby obtaining multi-band contrast component maps. These component maps correspond to the contrast response characteristics of low frequency (such as large area color blocks), medium frequency (such as gradient areas), and high frequency (such as edges and textures) in the image, so that the system can identify which frequency range of contrast needs to be enhanced or suppressed under the current environmental light and viewing distance conditions. Then, the system performs regional contrast calculation on the multi-band contrast component maps, that is, multiple local regions (such as a nine-square grid or irregular blocks based on saliency detection) are divided in the spatial domain of the image, and the contrast levels of each frequency band in each region are counted respectively, thereby identifying low-contrast regions in the target display image, such as the "diluted" shadow part of the screen under strong light or the blurred distant details when viewed at a distance, and generating a set of contrast modulation parameters related to spatial position and frequency characteristics. These parameters not only reflect the overall brightness mapping trend, but also reflect the local visual perception needs, and based on the contrast modulation parameters, the low-contrast regions of the target display image are selectively enhanced to avoid over-processing of regions with sufficient contrast, which may cause noise amplification or distortion, thereby accurately improving the visual distinguishability, and finally obtaining a detail recovery gain coefficient reflecting the detail recovery capability. This coefficient is a spatially varying weight map indicating the gain intensity that each pixel or pixel block should obtain in the enhancement process. Subsequently, the system separates and enhances the texture details and edge structures in the target display image using the detail recovery gain coefficient. This step uses image decomposition techniques (such as guided filtering, Laplacian pyramid, or deep learning segmentation models) to separate the original image into a structure layer (representing object outlines and main shapes) and a texture layer (representing surface fine lines and high-frequency information), and then applies enhancement strategies based on the detail recovery gain coefficient to each layer. For the structure layer, the focus is on maintaining edge sharpness and geometric integrity to prevent jaggedness or blurring. For the texture layer, the focus is on improving the visibility of small features, such as clothing wrinkles, leaf veins, or text strokes. Through this differentiated processing, the system generates a structure and texture level matrix that can preserve both macroscopic structures and microscopic details. This matrix not only records the enhanced pixel values, but also encodes the relative relationships between different levels, ensuring that the enhanced image is naturally coordinated, without structure collapse or texture adhesion.Finally, the target display image is pixel-level modulated based on the structure and texture level matrix, that is, the matrix is pixel by pixel applied to each luminance channel (such as Y channel or RGB channel) of the original image, and the output value of each pixel is dynamically adjusted, so that the visual clarity and level of the image are significantly improved without destroying the semantic content of the image, and image enhancement data is obtained. For example, when a user uses a tablet computer to view a city street scene photo outdoors in strong sunlight, due to the high intensity of the environmental light, the screen reflection is serious, and the building shadow area in the original image appears dark and lacks details; at this time, the luminance compensation curve generated by the system through the foregoing steps is decomposed by spatial frequency to identify that the contrast of the low-frequency region is insufficient, the image lower part is found to be a typical low-contrast region through regional calculation, and a higher detail recovery gain coefficient is calculated, and the sidewalk texture and window edge are selectively enhanced according to the gain coefficient, so that the originally blurred ground brick texture and building outline become clear and distinguishable; when the same device plays a movie screen in the night at a close distance, the system detects that the viewing distance dynamic mapping curve shows that the user is close to the screen, and accordingly enhances the medium and high frequency details in the dark field scene, and enhances the facial expression of the person and the texture of the cloth through the structure and texture level matrix, so that the viewing experience is more immersive and realistic. As can be seen, through the multi-level and phased pixel-level modulation mechanism, the complete enhancement chain from global mapping to local optimization and from luminance compensation to detail restoration is realized, and the image performance and visual comfort of the intelligent display device in a complex environment are effectively improved.

[0025] In a specific scenario, the image enhancement data is color space converted to obtain a color enhancement matrix, including: The image enhancement data is color channel decoupling analyzed to obtain a color component feature vector, and a colorimetric characteristic quantity of a target display image is quantified based on the color component feature vector to obtain a color saturation distribution; The color saturation distribution is calculated based on a color adaptability transformation kernel to match a visual cognitive scene, to obtain a colorimetric adaptability parameter, and the color performance of the image enhancement data is non-uniformly enhanced based on the colorimetric adaptability parameter to obtain a color enhancement gradient surface; The color enhancement gradient surface is analyzed for visual color constancy to obtain a color constancy compensation factor, and a color offset region in the image enhancement data is selectively corrected based on the color constancy compensation factor to obtain a color gamut mapping control parameter; The color gamut mapping control parameter is color space coordinate transformed to obtain a target color space transformation matrix, and the color relationship in the image enhancement data is overall reconstructed based on the target color space transformation matrix to obtain a color enhancement matrix.

[0026] Specifically, the image enhancement data is color space converted to obtain a color enhancement matrix. This process is not a simple color format conversion, but a multi-level optimization mechanism that integrates colorimetric analysis, visual perception modeling, and color constancy correction, aiming to achieve environment-adaptive and human-eye-perception characteristic color reproduction. Specifically, the system first performs color channel decoupling analysis on the image enhancement data, i.e., separates the image data after pixel-level brightness modulation into three independent color channels of red, green, and blue in the original color space (such as RGB), and further extracts the statistical features and spatial distribution patterns of each channel, thereby obtaining color component feature vectors that can represent the local and global color characteristics of the image. These vectors not only contain the intensity values of each pixel point, but also contain information such as color transition smoothness, channel correlation, and regional color concentration trend. Based on the color component feature vectors, the system quantifies the colorimetric characteristics of the target display image by converting RGB values to CIE Lab or CIE XYZ, which are closer to human eye perception, to calculate the hue, saturation, and lightness parameters of each pixel point, and then generate a graph that reflects the color saturation spatial distribution of the entire image, i.e., color saturation distribution. This distribution map clearly identifies which regions in the image have rich colors and which regions tend to be dark, providing a basis for subsequent targeted enhancement. Next, the system introduces a visual cognitive scene matching mechanism based on a color adaptive transformation kernel. This transformation kernel simulates the physiological characteristics of human eye color perception adjustment under different lighting environments (such as dark adaptation and light adaptation), and combines the scene feature association pattern constructed by the lighting spectrum features and viewing distance dynamic mapping curve obtained in step S1 to determine whether the current viewing scene belongs to a high-light warm-toned environment (such as a dusk indoor environment) or a cold-light strong-illumination environment (such as a noon outdoor environment), thereby calculating a set of colorimetric adaptability parameters that reflect the non-linear characteristics of the visual system's color response. These parameters are used to guide the non-uniform enhancement processing of the color saturation distribution, i.e., applying higher enhancement weights to areas with weak color performance (such as the surfaces of objects in shadows), and avoiding excessive enhancement in saturated areas to prevent overflow. Finally, a color enhancement gradient surface that changes with spatial position is generated. This surface is like a three-dimensional topographic map, with high points representing color regions that need to be enhanced, and low points corresponding to regions that remain unchanged or are slightly adjusted.Subsequently, the system performs visual color constancy analysis on the color enhancement gradient surface, in order to prevent overall color cast of the image caused by changes in the color temperature of the ambient light. For example, a white wall photographed under an incandescent lamp may appear yellow on the screen, although the brightness has been optimized, but the color distortion still affects the sense of reality. Through color constancy analysis, the system identifies the areas in the image that should be neutral gray or white but are affected by the ambient light and accordingly derives a color constancy compensation factor, which is used to reverse correct the color cast of such areas, ensuring that the visual consistency principle that "white paper still looks white under any light" is maintained. Based on the color constancy compensation factor, the system performs selective correction processing on the color cast areas in the image enhancement data, avoiding the loss of details caused by global white balance adjustment, and finally generates a set of gamut mapping control parameters that accurately control the color mapping range and direction. Finally, the system performs color space coordinate transformation on the gamut mapping control parameters, i.e., converts them from the perceptual optimization space (such as Lab) to the physical color space supported by the display device (such as DCI-P3 or sRGB), forming a target color space transformation matrix that can guide pixel-level color remapping. This matrix not only defines the conversion relationship from input color to output color, but also integrates multiple optimization results such as brightness modulation, contrast enhancement, and visual adaptability. Based on the target color space transformation matrix, the system reconstructs the color relationship in the image enhancement data as a whole, adjusts the final color output value of each pixel on the display panel, and thus obtains a color enhancement matrix. This matrix serves as the input for subsequent gray-scale voltage modulation, ensuring that the color optimization results can accurately affect the physical display process. For example, when a user uses a tablet computer to view a photo containing blue sky, green land, and a portrait under strong sunlight in the afternoon, although the brightness compensation has improved the overall visibility, the blue component in the strong light may cause the skin color to be cold. The system identifies that the red component of the face area is low through color channel decoupling analysis, judges it as a cold white sunlight environment combined with the spectral characteristics of the light, generates adaptive chroma adaptability parameters using the color adaptability transformation kernel, and corrects the skin color blue problem through color constancy analysis. The final color enhancement matrix makes the skin color of the portrait natural and rosy, and the blue sky more transparent without distortion. When viewing the same home video played on the device in a weak light environment in the bedroom at night, the system detects that the warm light source causes the overall yellow cast, and accordingly suppresses the yellow channel gain through the color constancy compensation factor, while moderately increasing the blue saturation in the dark area to enhance the visual balance, so that the picture still maintains color accuracy and rich layers under low brightness. As can be seen, through the complete closed-loop process from color decoupling to constancy correction, the system realizes intelligent color optimization that is truly human-oriented and environment-coordinated.

[0027] In specific scenarios, the gray-scale voltage modulation on the preset display panel based on the color enhancement matrix to obtain an optimized display image includes: The color enhancement matrix is converted from a digital signal to a voltage signal by a grayscale voltage mapping processor to obtain a voltage modulation initial data set, and input signal calibration is performed on a pixel driving circuit in the display panel based on the voltage modulation initial data set to obtain a pixel driving voltage mapping table; Nonlinear response characteristic analysis is performed on the pixel driving voltage mapping table by a gamma curve optimization unit to obtain gamma compensation parameters, and panel physical characteristic matching processing is performed on the gamma compensation parameters by a display panel characteristic compensation engine to obtain a panel characteristic compensation vector, uniformity correction calculation is performed on different regions in the display panel based on the panel characteristic compensation vector to obtain a region uniformity compensation matrix, and content adaptive adjustment is performed on the display panel based on the region uniformity compensation matrix to obtain a frame rate optimization control signal; Comprehensive evaluation processing is performed on the frame rate optimization control signal and the color enhancement matrix to obtain a display quality evaluation index, and real-time voltage and timing fine tuning is performed on the driving circuit of the display panel based on the display quality evaluation index to obtain an optimized display image.

[0028] Specifically, the process of obtaining the optimized display image by modulating the gray voltage of the preset display panel based on the color enhancement matrix is realized through a series of complex signal processing and compensation mechanisms. First, the color enhancement matrix is converted from a digital signal to a voltage signal by a gray voltage mapping processor. In this process, the color enhancement matrix serves as input and contains color information optimized for each pixel point. The gray voltage mapping processor converts these digital color values into voltage signals that can drive the panel light-emitting unit according to the specific specifications and characteristics of the display panel, generating an initial voltage modulation data set. These data sets not only reflect the color intensity of each pixel, but also consider the nonlinear response characteristics of human visual perception. Then, the input signal of the pixel driving circuit in the display panel is calibrated based on the above initial voltage modulation data set, with the goal of ensuring that each pixel accurately presents the expected brightness and color after receiving the corresponding voltage signal. The pixel driving voltage mapping table generated in this way records the precise correspondence between different color values and the required driving voltage, ensuring the consistency and accuracy of color reproduction. Next, the pixel driving voltage mapping table is analyzed for nonlinear response characteristics based on a gamma curve optimization unit. Since the perception of brightness changes by the human eye is not linear, appropriate gamma correction needs to be applied to the voltage signal to match this nonlinear visual perception rule. By analyzing the nonlinear relationship between the voltage signal and the actual brightness output, a set of gamma compensation parameters is calculated. Subsequently, the display panel characteristic compensation engine uses these parameters and combines the panel's own physical characteristics (such as light-emitting efficiency, attenuation characteristics, etc.) to perform panel physical characteristic matching processing, thereby obtaining a panel characteristic compensation vector. These compensation vectors specifically describe how to adjust the voltage signal of each pixel point to overcome the inherent non-uniformity and non-ideal response of the panel. Then, based on the panel characteristic compensation vector, different regions in the display panel are calculated for uniformity correction, and a regional uniformity compensation matrix is finally obtained. This matrix precisely depicts the compensation measures required by each local region on the panel to achieve consistent color performance, and is used as the basis for adaptive adjustment of the display content to generate a frame rate optimization control signal, ensuring good picture quality stability and smoothness even in dynamic scenes.Finally, the frame rate optimization control signal and the color enhancement matrix are comprehensively evaluated. The comprehensive evaluation is not limited to the accuracy of color and brightness, but also includes contrast, clarity, and overall visual perception. Through quantifying these factors, a comprehensive display quality evaluation index is obtained. Based on this index, the system can implement real-time voltage and timing fine-tuning of the driving circuit of the display panel. This step is crucial because it allows the system to adjust the working state of the hardware in real time according to the characteristics of the current display content, maximizing the performance potential of the panel and avoiding potential distortion or delay problems caused by fixed settings. For example, when watching a high-speed sports event, if the rapid movement of the players on the screen causes a trailing phenomenon, the system will automatically detect this problem and reduce the picture retention time by fine-tuning the driving circuit, while enhancing the contrast between the characters and the background according to the color enhancement matrix, making the entire game scene more clear and realistic. When playing a night scene video in low light environment, the system will appropriately reduce the overall brightness while enhancing the visibility of the shadow part according to the enhancement information about dark details in the color enhancement matrix, and maintain stable frame rate output with the frame rate optimization control signal to avoid flicker. In this way, whether it is a static picture or a dynamic image, the best visual experience can be achieved. In summary, the entire process fine-tunes each link from digital signal to physical display, achieving high-quality image reproduction.

[0029] In specific scenarios, the real-time voltage and timing fine-tuning of the driving circuit of the display panel based on the display quality evaluation index to obtain the optimized display image includes: The display quality evaluation index is analyzed for voltage-brightness response characteristics by a multi-dimensional voltage mapping system, and pixel driving voltage optimization parameters are obtained. Based on the pixel driving voltage optimization parameters, real-time voltage compensation processing is performed on the gate driving circuit and the source driving circuit of the display panel, and a compensated driving voltage curve is obtained. The compensated driving voltage curve is optimized for intra-frame synchronization characteristics, and timing modulation control parameters are obtained. Based on the timing modulation control parameters, content-dependent dynamic adjustment is performed on the display panel, and adaptive timing control parameters are obtained. The adaptive timing control parameters and the compensated driving voltage curve are comprehensively and cooperatively optimized to obtain a voltage-timing joint modulation coefficient table, and the driving circuit of the display panel is accurately fine-tuned based on the voltage-timing joint modulation coefficient table to obtain the optimized display image.

[0030] Specifically, based on the display quality evaluation index, the driving circuit of the display panel is real-time voltage and timing fine-tuned to obtain an optimized display image. This process is the key link in the whole real-time image quality optimization method of the intelligent display device to realize the precise control of the physical layer. It converts the color enhancement matrix generated in the previous step and the comprehensive judgment of the system on the overall display performance into fine control instructions executable by the driving circuit. Specifically, the system first analyzes the voltage-luminance response characteristics of the display quality evaluation index through the multi-dimensional voltage mapping system. This analysis not only focuses on whether the luminance output of the pixel at different gray scales meets the preset gamma curve, but also deeply investigates its multi-dimensional performance such as response speed, crosstalk suppression ability, and power efficiency under dynamic content, thereby comprehensively evaluating the pros and cons of the current driving strategy. On this basis, the system extracts the core factors affecting the image quality, such as dark field detail loss, bright area overshoot, or response delay, and accordingly deduces a set of pixel driving voltage optimization parameters that can improve these problems. These parameters define the optimal driving voltage value that should be applied to each pixel under specific image content and environmental conditions, ensuring accurate luminance and avoiding overheating or lifespan degradation caused by excessive voltage. Subsequently, based on the pixel driving voltage optimization parameters, the gate driving circuit and the source driving circuit of the display panel are subjected to real-time voltage compensation processing. The gate driving is responsible for controlling the on and off timing of the pixel switch, while the source driving determines the voltage amplitude input to the pixel unit. The two work together to determine the definition and color restoration of the image. Through real-time compensation, the system dynamically adjusts the output voltage of these two types of driving circuits, forming a compensated driving voltage curve that can adaptively adjust with changes in content and environment. This curve ensures the stability and consistency of pixel response in various complex scenarios. Next, the system optimizes the intra-frame synchronization characteristics of the compensated driving voltage curve to address issues such as inter-frame flicker, trailing, or local response lag that may occur during high-speed image switching or local high-contrast changes. By analyzing the timing deviation between voltage changes and actual pixel emission, the system calculates a set of timing modulation control parameters that accurately control the gate scanning frequency, source data writing timing, and pixel charging retention period, thereby improving the synchronization of each region within the frame. Based on the timing modulation control parameters, the system further performs content-dependent dynamic adjustment on the display panel. For example, when playing fast-moving sports event images, the system identifies a large number of motion vectors in the image and shortens the pixel charging time to speed up the response. When displaying static text or charts, it prolongs the writing period to improve the gray scale accuracy, thereby generating a set of adaptive timing control parameters that dynamically change with the image content.Subsequently, the system performs comprehensive and coordinated optimization of the adaptive timing control parameters and the compensated driving voltage curve. This step breaks the limitation of independent voltage and timing control in traditional driving. By establishing a coupling relationship model between the two, a voltage-timing joint modulation coefficient table covering the joint configuration of voltage amplitude and time sequence is generated. This table records the optimal voltage and timing combination strategy that the driving circuit should adopt under different image features (such as motion intensity, contrast distribution, brightness level) and environmental conditions (such as light intensity, viewing distance), achieving true coordinated optimization. Finally, based on the voltage-timing joint modulation coefficient table, the driving circuit of the display panel is precisely fine-tuned. The system loads these coefficients into the driving chip in real time, dynamically adjusting the voltage input and switching timing of each pixel. This ensures that the final output light signal not only highly reproduces the original intent in terms of color, brightness, and contrast, but also achieves an optimal balance in dynamic performance, uniformity, and response speed, thereby obtaining an optimized display image. For example, when a user watches an action movie on a tablet in strong afternoon sunlight, with frequent high-speed chase scenes, the system detects slight ghosting in local areas through display quality evaluation indicators. It then uses a multi-dimensional voltage mapping system to analyze the situation and determine that the source drive voltage needs to be increased to accelerate pixel charging. Combined with intra-frame synchronization optimization, the system adjusts the gate scan rhythm to generate a new compensated drive voltage curve and timing control parameters. Simultaneously, due to strong ambient light, the system collaboratively increases the overall drive voltage and fine-tunes the refresh timing based on the voltage-timing joint modulation coefficient table, ensuring that bright areas are not overexposed, dark details are not lost, and motion is smooth without ghosting. When reading an e-book at close range at night, the system assesses the current scene as a static, low-brightness environment. Therefore, it reduces the drive voltage to decrease blue light radiation and extends pixel stabilization time through adaptive timing control, improving text edge sharpness, ultimately achieving a reading experience that is both eye-friendly and clear. Thus, this solution, through deep collaborative regulation of voltage and timing, extends image optimization from the algorithm level to the hardware driver layer, significantly improving the overall visual quality and user experience of smart display devices in diverse application scenarios.

[0031] The above describes the real-time image quality optimization method for the intelligent display device in the embodiments of the present invention. The following describes the real-time image quality optimization system for the intelligent display device in the embodiments of the present invention. Please refer to [link / reference]. Figure 2 One embodiment of the real-time image quality optimization system for intelligent display devices in this invention includes: The sensing module 21 is used to sense the ambient light intensity and viewing distance of the preset display device in real time and obtain scene parameter data stream; The mapping module 22 is configured to perform dynamic brightness mapping on the target display image in the display device based on the scene parameter data stream to obtain a brightness compensation curve, wherein the display device is provided with a display panel. The first modulation module 23 is configured to perform pixel-level modulation on the target display image based on the brightness compensation curve to obtain image enhancement data. The conversion module 24 is configured to perform color space conversion on the image enhancement data to obtain a color enhancement matrix. The second modulation module 25 is configured to perform gray-scale voltage modulation on the display panel based on the color enhancement matrix to obtain an optimized display image.

[0032] In the embodiment, the specific implementation of each unit in the system embodiment is described above in the method embodiment, and will not be repeated here.

[0033] Reference Figure 3 In the embodiment, a computer device is also provided, and the internal structure of the computer device can be as shown in the figure. Figure 3 The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store corresponding data in the embodiment. The network interface of the computer device is configured to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement the above method.

[0034] Those skilled in the art can understand that Figure 3 The structure shown in the figure is only a block diagram of part of the structure related to the scheme, and does not constitute a limitation on the computer device to which the scheme is applied.

[0035] The embodiment also provides a computer readable storage medium having a computer program stored thereon, and the computer program is executed by the processor to implement the above method. It can be understood that the computer readable storage medium in the embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0036] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, storage, database or other medium provided by the present application and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM, etc.

[0037] It should be noted that in this document, the terms "comprising", "including", or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, device, article or method that comprises a list of elements does not only include those elements, but can also include other elements not expressly listed or inherent to such process, device, article or method. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, device, article or method that includes the element.

[0038] The above description is only the preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, based on the content of the present application specification and drawings, are also included in the patent protection scope of the present application.

Claims

1. A real-time image quality optimization method of an intelligent display device, characterized by, The method comprises the following steps: Real-time sensing of the ambient light intensity and viewing distance of a preset display device to obtain a scene parameter data stream; Dynamic brightness mapping of a target display image in the display device based on the scene parameter data stream to obtain a brightness compensation curve, wherein a display panel is arranged in the display device; Pixel-level modulation of the target display image based on the brightness compensation curve to obtain image enhancement data; Color space conversion of the image enhancement data to obtain a color enhancement matrix; Gray scale voltage modulation of the display panel based on the color enhancement matrix to obtain an optimized display image. 2.The real-time image quality optimization method of a smart display device according to claim 1, characterized in that, The viewing distance is the spatial positional relationship between the viewer and the display panel, and the real-time sensing of the ambient light intensity and viewing distance of a preset display device to obtain a scene parameter data stream comprises: Wavelength decomposition sampling of the ambient light intensity around the preset display device by a multi-band spectral sensing array to obtain a spectral distribution feature map, and frequency spectrum analysis of the ambient light intensity based on the spectral distribution feature map to obtain light spectrum features; Three-dimensional coordinate positioning of the spatial positional relationship between the viewer and the display panel based on a time-of-flight ranging system to obtain position distribution point cloud data, and geometric feature extraction of the position distribution point cloud data to obtain a viewing distance dynamic mapping curve; Time sequence correlation analysis of the light spectrum features and the viewing distance dynamic mapping curve to obtain a scene feature correlation mode, and weight distribution calculation of the preset real-time collected environmental parameters based on the scene feature correlation mode to obtain a scene parameter data stream. 3.The real-time image quality optimization method of a smart display device according to claim 1, characterized in that, The pixel-level modulation of the target display image based on the brightness compensation curve to obtain image enhancement data comprises: Spatial frequency decomposition of the brightness compensation curve to obtain a multi-band contrast component map; Regional contrast calculation of the multi-band contrast component map to obtain contrast modulation parameters, and selective enhancement processing of a low-contrast region of the target display image based on the contrast modulation parameters to obtain a detail recovery gain coefficient; Separate enhancement processing of texture details and edge structures in the target display image based on the detail recovery gain coefficient to obtain a structure and texture level matrix; Pixel-level modulation of the target display image based on the structure and texture level matrix to obtain image enhancement data. 4.The real-time image quality optimization method of the intelligent display device of claim 1, wherein, The color space conversion of the image enhancement data to obtain a color enhancement matrix comprises: Color channel decoupling analysis of the image enhancement data to obtain a color component feature vector, and colorimetric characteristic quantization of the target display image based on the color component feature vector to obtain a color saturation distribution; Visual cognitive scene matching calculation of the color saturation distribution based on a color adaptability transformation kernel to obtain a colorimetric adaptability parameter, and non-uniform enhancement of the color expressiveness of the image enhancement data based on the colorimetric adaptability parameter to obtain a color enhancement gradient surface; The visual color constancy analysis is performed on the color enhancement gradient surface to obtain a color constancy compensation factor, and a color offset region in the image enhancement data is selectively corrected based on the color constancy compensation factor to obtain a gamut mapping control parameter; The gamut mapping control parameter is subjected to color space coordinate transformation to obtain a target color space transformation matrix, and the color relationship in the image enhancement data is overall reconstructed based on the target color space transformation matrix to obtain a color enhancement matrix. 5.The real-time image quality optimization method of the intelligent display device of claim 1, wherein, The display panel is subjected to gray-scale voltage modulation based on the color enhancement matrix to obtain an optimized display image, including: The color enhancement matrix is converted from a digital signal to a voltage signal by a gray-scale voltage mapping processor to obtain an initial voltage modulation data set, and the input signal of a pixel driving circuit in the display panel is calibrated based on the initial voltage modulation data set to obtain a pixel driving voltage mapping table; The pixel driving voltage mapping table is subjected to nonlinear response characteristic analysis by a gamma curve optimization unit to obtain a gamma compensation parameter, the gamma compensation parameter is subjected to panel physical characteristic matching processing by a display panel characteristic compensation engine to obtain a panel characteristic compensation vector, different regions in the display panel are subjected to uniformity correction calculation based on the panel characteristic compensation vector to obtain a region uniformity compensation matrix, and the display panel is subjected to content adaptive adjustment based on the region uniformity compensation matrix to obtain a frame rate optimization control signal; The frame rate optimization control signal and the color enhancement matrix are subjected to comprehensive evaluation processing to obtain a display quality evaluation index, and the driving circuit of the display panel is subjected to real-time voltage and timing fine-tuning based on the display quality evaluation index to obtain an optimized display image. 6.The real-time image quality optimization method of the intelligent display device according to claim 5, wherein, The display panel is subjected to gray-scale voltage modulation based on the color enhancement matrix to obtain an optimized display image, including: The display quality evaluation index is subjected to voltage-luminance response characteristic analysis by a multi-dimensional voltage mapping system to obtain a pixel driving voltage optimization parameter, and the gate driving circuit and the source driving circuit of the display panel are subjected to real-time voltage compensation processing based on the pixel driving voltage optimization parameter to obtain a compensated driving voltage curve; The compensated driving voltage curve is subjected to intra-frame synchronization characteristic optimization to obtain a timing modulation control parameter, and the display panel is subjected to content-dependent dynamic adjustment based on the timing modulation control parameter to obtain an adaptive timing control parameter; The adaptive timing control parameter and the compensated driving voltage curve are subjected to comprehensive and cooperative optimization to obtain a voltage-timing joint modulation coefficient table, and the driving circuit of the display panel is subjected to accurate fine-tuning based on the voltage-timing joint modulation coefficient table to obtain an optimized display image.

7. A real-time image quality optimization system of a smart display device, characterized by, including: The perception module is configured to perceive the ambient light intensity and the viewing distance of the display device in real time to obtain scene parameter data streams; The mapping module is configured to perform dynamic luminance mapping on a target display image in the display device based on the scene parameter data streams to obtain a luminance compensation curve; wherein the display device is provided with a display panel. The first modulation module is configured to perform pixel-level modulation on the target display image based on the luminance compensation curve to obtain image enhancement data. The conversion module is configured to perform color space conversion on the image enhancement data to obtain a color enhancement matrix. The second modulation module is configured to perform gray-scale voltage modulation on the display panel based on the color enhancement matrix to obtain an optimized display image. 8.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-7. The processor executes the computer program to implement the steps of the method in any one of claims 1 to 6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

Images