A color gamut boundary compensation method and system for an LED lamp pole screen advertising machine

Abstract

This invention relates to the field of display control technology, specifically to a method and system for color gamut boundary compensation of an LED light pole screen advertising machine. The method includes: acquiring an input HDR image and converting it to the XYZ color space to obtain an original layer image; performing bilateral filtering on the original layer image to obtain a base layer image, and obtaining a detail layer image by the difference between the original layer image and the base layer image; sequentially performing chroma adaptation processing and tone compression on the base layer image to obtain a tone-compressed base layer image; performing the same processing on the original layer image to obtain a tone-compressed original layer image and a chroma-adapted original layer image; and compositing the tone-compressed base layer image and the detail layer image after detail adjustment to obtain a detail composite image. The tonal compression base layer image, the tonal compression original layer image, and the chroma adaptation original layer image are converted to the IPT color space to obtain the I luminance component and P and T chroma components. The Euclidean amplitude of the P and T differences is calculated and normalized according to the maximum amplitude to generate a color difference map. At the same time, the ratio of chroma amplitudes is calculated to obtain the color scaling degree. Based on the color difference map, weighted fusion is performed and compensated according to the color scaling degree to obtain the standard chroma component. An enhanced stop mask and enhancement gain are generated, and a chroma difference direction vector is constructed. These are superimposed and scaled to obtain the enhanced chroma component. The luminance component of the detail composite image is extracted and the enhanced chroma component is synthesized to output an image. After inverse transformation, a low dynamic range display image is obtained and displayed on the target device. This invention solves the problem that LED light pole screen advertising machines easily produce color distortion and halos at color boundaries and saturation reduction in low brightness and low chroma areas after chroma adaptation and tonal compression of HDR images.

Description

Technical Field

[0001] This invention relates to the field of display control technology, and in particular to a method and system for color gamut boundary compensation of LED light pole screen advertising machines. Background Technology

[0002] LED light pole advertising displays often require high dynamic range images to be mapped to low dynamic range images after chromatic adaptation and hue compression in outdoor strong light, backlight and high contrast scenarios for display. However, in existing appearance models or hue mapping processing based on bilateral decomposition, hue compression is often performed separately on each CIEXYZ channel, which can easily disrupt the color balance between channels. When the hue compression result is recombined with the detail layer, color distortion is amplified in strong boundary areas and halo artifacts are induced. At the same time, there is also an overall desaturation problem in low brightness areas, which affects the color consistency and visual appeal of the advertising image at the edges. Summary of the Invention

[0003] In view of the above technical problems, the present invention provides a color gamut boundary compensation method and system for LED light pole screen advertising machines. It aims to solve the problems that LED light pole screen advertising machines easily produce color distortion and halos at color boundaries after HDR images are chromaticity adapted and hue compressed, and that saturation decreases in low brightness and low chromaticity areas. The invention provides a color gamut boundary compensation method that obtains color information for boundary distortion detection and compensation through multi-layer decomposition, and compensates and enhances the chromaticity components in a color space with better hue linearity, so as to improve the boundary color stability and overall color performance of the displayed image.

[0004] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0005] According to one aspect of the present invention, a method for color gamut boundary compensation of LED light pole screen advertising machines is proposed, the method comprising: The input HDR image is acquired and converted to the XYZ color space to obtain the original layer image; The original layer image is subjected to bilateral filtering to obtain the basal layer image, and the detail layer image is obtained by the difference between the original layer image and the basal layer image; The base layer image is sequentially subjected to chroma adaptation processing and hue compression to obtain a hue-compressed base layer image. The original layer image is subjected to the same processing to obtain a hue-compressed original layer image and a chroma-adapted original layer image. The hue-compressed base layer image is then combined with the detail layer image after detail adjustment to obtain a detail composite image. The hue-compressed base layer image, the hue-compressed original layer image, and the chroma-adapted original layer image are converted to the IPT color space to obtain the corresponding I luminance component and P and T chroma components. Calculate the difference between the tone-compressed base layer image and the tone-compressed original layer image in the P and T chromaticity components, obtain the Euclidean magnitude of the difference, and normalize it according to the maximum magnitude to generate a color difference map; calculate the ratio of the chromaticity magnitude of the tone-compressed original layer image to the chromaticity adaptation original layer image to obtain the color scaling degree. The chromaticity components of the original hue compression layer image and the original chromaticity adaptation layer image are weighted and fused according to the chromaticity difference diagram, and the fusion contribution of the original chromaticity adaptation layer image is compensated according to the color scaling degree to obtain the standard chromaticity components. An enhanced stop mask is generated based on the chroma amplitude of the original hue-compressed layer image. An enhanced gain is generated based on the relative relationship between the luminance components of the original hue-compressed layer image and the original chroma-adapted layer image. A chroma difference direction vector is obtained from the direction of the difference. The chroma difference direction vector is superimposed on the standard chroma component under the modulation of the enhanced stop mask and scaled by the enhanced gain to obtain the enhanced chroma component. The luminance component of the detailed composite image is extracted and combined with the enhanced chrominance component to synthesize an output image. The output image is then inversely transformed to obtain a low dynamic range display image, which is then displayed on the target device.

[0006] Furthermore, the bilateral filtering smooths the edges of the original layer image by simultaneously introducing spatial distance weights and pixel value difference weights, so that the base layer image contains low-frequency brightness and color variations and suppresses color mixing across edges; the detail layer image is a pixel-by-pixel difference between the original layer image and the base layer image; the detail adjustment includes applying one of local contrast redistribution, gain modulation, and noise suppression to the detail layer image to improve detail visibility and avoid amplifying boundary halos when synthesizing the detail composite image.

[0007] Furthermore, the chromaticity adaptation process includes: The base layer image is low-pass filtered to obtain an adapted image for characterizing scene lighting trends; The chromaticity features of the ambient lighting are determined based on the adapted image, and a chromaticity adaptation transformation is generated. The chromaticity adaptation transformation is applied to the XYZ components of the base layer image and the original layer image, respectively, to obtain the chromaticity-adapted base layer image and the chromaticity-adapted original layer image.

[0008] Furthermore, the tone compression includes: A monotonic dynamic range compression function is established based on the human visual response, and the compression function is applied to the XYZ components of the chroma adaptation base layer image and the chroma adaptation original layer image respectively to obtain the hue compression base layer image and the hue compression original layer image; wherein, the dynamic range compression function is any one of the following: a combination function of rod response and cone response, a piecewise continuous function, or a lookup table mapping.

[0009] Furthermore, the step of converting the tone-compressed base layer image, the tone-compressed original layer image, and the chroma-adapted original layer image to the IPT color space includes: For any image to be processed represented by the XYZ color space, obtain the XYZ components of the image to be processed; Perform a linear transformation on the XYZ components to obtain the L, M, and S channel components corresponding to the visual long-wave channel, mid-wave channel, and short-wave channel; Sign-preserving nonlinear exponentiation is performed on the L, M, and S channel components respectively to obtain nonlinear L, M, and S channel components; linear combination is performed on the nonlinear L, M, and S channel components to obtain the luminance component, chrominance component P, and chrominance component T. Performing an inverse transform on the output image includes: The output image is restored from the IPT color space to the XYZ color space by inverting the linear combination, inverting the nonlinear exponentiation, and inverting the linear transformation.

[0010] Furthermore, the generation of the color difference map includes: At the pixel location, calculate the chromaticity component P difference and the chromaticity component T difference between the chromaticity compression base layer image and the chromaticity compression original layer image; then perform Euclidean synthesis on the chromaticity component P difference and the chromaticity component T difference to obtain the chromaticity difference amplitude value. The maximum value of the chromaticity difference amplitude is determined within the entire map range, and the chromaticity difference amplitude is normalized using the maximum value to obtain the chromaticity difference map that indicates stronger boundary colors with larger values. Adaptive compensation intensity control is then implemented for the boundary regions based on the chromaticity difference map.

[0011] Furthermore, the generation of the color scaling factor includes: The chromaticity components P and T of the original hue compression layer image and the original chromaticity adaptation layer image are respectively synthesized using Euclidean algorithm to obtain their respective chromaticity amplitudes, and the ratio of the chromaticity amplitude of the original hue compression layer image to the chromaticity amplitude of the original chromaticity adaptation layer image is used as the color scaling degree. The weighted fusion includes: Increase the weight of the chromaticity component of the original image of the hue compression at the position where the chromaticity map value is low, and increase the weight of the chromaticity component of the original image of the chromaticity adaptation at the position where the chromaticity map value is high; The fusion contribution to the original layer image adapted to the chroma is compensated according to the color scaling, including: The chromaticity components of the original layer image are scaled according to the color scaling factor before being fused to obtain the standard chromaticity components that include standard P chromaticity components and standard T chromaticity components, thereby reducing hue shift at color boundaries and suppressing halo artifacts.

[0012] Furthermore, the enhanced stop mask is generated based on the Euclidean composite amplitude of the chromaticity component P and chromaticity component T of the original hue compression layer image, and takes a preset maximum weight when the Euclidean composite amplitude is higher than a preset threshold, and attenuates according to the proportion of the Euclidean composite amplitude when the Euclidean composite amplitude is lower than the preset threshold, so as to suppress white point drift or hue drift at low saturation or near-neutral color boundaries. The enhancement gain is obtained by using a preset monotonic mapping function based on the ratio of the luminance component of the original hue compression layer image to the luminance component of the original chroma adaptation layer image, and a lower limit is set for the enhancement gain to avoid desaturation. The chromatic difference direction vector is obtained by dividing the difference between the chromaticity component P and the difference between the chromaticity component T of the chromaticity compressed base layer image and the chromaticity compressed original layer image by the maximum value of the chromaticity difference amplitude, respectively. The enhanced chroma component is obtained by superimposing the chroma direction vector onto the standard chroma component under the enhanced stop mask modulation and scaling it by the enhancement gain, and the output image is composed of the enhanced chroma component and the luminance component of the detailed composite image in the IPT color space.

[0013] According to another aspect of the present invention, a color gamut boundary compensation system for LED light pole screen advertising machines is provided, comprising: The input conversion module is used to acquire the input HDR image and convert it to the XYZ color space to obtain the original layer image; The decomposition module is used to perform bilateral filtering on the original layer image to obtain the basal layer image, and to obtain the detail layer image by the difference between the original layer image and the basal layer image; The compression compositing module is used to sequentially perform chroma adaptation processing and hue compression on the base layer image to obtain a hue-compressed base layer image, perform the same processing on the original layer image to obtain a hue-compressed original layer image and a chroma adaptation original layer image, and then combine the hue-compressed base layer image with the detail layer image after detail adjustment to obtain a detail composite image. The IPT extraction module is used to convert the tone compression base layer image, the tone compression original layer image and the chromaticity adaptation original layer image to the IPT color space to obtain the corresponding I luminance component and P and T chromaticity components. The color difference direction module is used to calculate the difference between the tone compression base layer image and the tone compression original layer image in the P and T chromaticity components, obtain the Euclidean amplitude of the difference and normalize it according to the maximum amplitude to generate a color difference map; calculate the ratio of the chromaticity amplitude of the tone compression original layer image to the chromaticity adaptation original layer image to obtain the color scaling degree. The fusion compensation module is used to perform weighted fusion of the chromaticity components of the original hue compression layer image and the chromaticity adaptation layer image based on the chromaticity difference diagram, and to compensate the fusion contribution of the chromaticity adaptation layer image according to the color scaling degree to obtain the standard chromaticity components. An enhancement control module is used to generate an enhancement stop mask based on the chroma amplitude of the original hue compression layer image, generate an enhancement gain based on the relative relationship between the luminance components of the original hue compression layer image and the original chroma adaptation layer image, obtain a chroma difference direction vector from the direction of the difference, and superimpose the chroma difference direction vector onto the standard chroma component under the modulation of the enhancement stop mask and scale it by the enhancement gain to obtain the enhanced chroma component. The recombined output module is used to extract the luminance component of the detailed composite image and synthesize it with the enhanced chrominance component to form an output image, and to perform an inverse transformation on the output image to obtain a low dynamic range display image, and to display the low dynamic range display image on the target device.

[0014] The technical solution of the present invention has the following beneficial effects: Compared to existing methods that rely solely on single-path tone mapping or simple chroma scaling, this invention utilizes the chroma difference between the base layer and the original layer in a multi-layer decomposition to construct a chroma map. This map is used to locate and quantify color distortion areas at strong boundaries. It also compensates for chroma deviations between chroma adaptation and hue compression by combining chroma scaling. Simultaneously, it suppresses white point drift or hue drift at low-saturation or near-neutral boundaries by enhancing a stop mask, and generates enhancement gain based on brightness variation to directionally enhance the saturation decrease in boundary areas. Finally, the compensated and enhanced chroma and brightness components are recombined and output, thereby reducing boundary color distortion and halo artifacts, improving desaturation in low-brightness areas, and enhancing the image layering and color consistency of LED light pole advertising displays. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating a color gamut boundary compensation method for an LED light pole screen advertising machine as described in this specification. Figure 2This is a structural block diagram of a color gamut boundary compensation system for an LED light pole screen advertising machine, as described in one of the embodiments of this specification. Figure 3 This specification describes a terminal device for implementing a color gamut boundary compensation method for LED light pole screen advertising machines in its embodiments. Figure 4 This specification describes a computer-readable storage medium that stores a color gamut boundary compensation method for LED light pole screen advertising machines, as exemplified in this specification. Detailed Implementation

[0016] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of the specific details omitted, or other methods, components, systems, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0017] Furthermore, the accompanying drawings are merely illustrative of this disclosure. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor systems and / or microcontroller systems.

[0018] This invention provides a method for color gamut boundary compensation in LED light pole advertising displays. (Refer to...) Figure 1 The diagram shown is a flowchart illustrating a color gamut boundary compensation method for an LED light pole screen advertising machine according to an embodiment of the present invention. This method can be applied to electronic devices such as personal computers and servers. The method can be executed by a device, which can be implemented by software and / or hardware. Specifically, the method may include the following steps S101~S107: In step S101, the input HDR image is acquired and converted to the XYZ color space to obtain the original layer image.

[0019] As an explanation, the XYZ color space is used to establish a unified color reference for subsequent processing. The input HDR image can be high dynamic range image data containing scene radiance information, typically expressed as linear intensity, capable of covering a wide range of brightness variations from bright to dark areas. To ensure consistency in color representation across different acquisition devices or content sources, the input HDR image is converted from its source color representation to the CIEXYZ color space to obtain the original layer image. CIEXYZ is a device-independent color system, facilitating consistent modeling of luminance and chrominance in subsequent processing and maintaining the same working domain with subsequent chroma adaptation and tone compression processing. During the conversion process, the tristimulus components of the input image in the source color space are linearized to obtain linear components proportional to light intensity. Then, a color transformation relationship corresponding to the white point in the source color space is used to map this to the X, Y, and Z channels. The Y channel represents the luminance-related components, while the X and Z channels are related to the overall chromaticity representation. The resulting CIEXYZ three-channel image serves as the original layer image, used to preserve the complete color and boundary information of the input image without introducing spatial smoothing. This provides a data foundation for subsequent detail preservation through multi-layer decomposition and for locating color distortion regions through the chromaticity difference between the basal and original layers. Simultaneously, the original layer image undergoes no edge-preserving filtering or detail adjustment at this stage to avoid introducing additional color mixing or boundary shifts before boundary distortion detection, ensuring that subsequent difference calculations on the chromaticity channels reflect the true color changes caused by hue compression.

[0020] In step S102, the original layer image is subjected to bilateral filtering to obtain the base layer image, and the detail layer image is obtained by the difference between the original layer image and the base layer image.

[0021] The bilateral filtering process involves simultaneously introducing spatial distance weights and pixel value difference weights to smooth the edges of the original layer image, ensuring that the base layer image contains low-frequency brightness and color variations and suppressing color mixing across edges. The detail layer image is a pixel-by-pixel difference between the original layer image and the base layer image. The detail adjustment process includes applying one of local contrast redistribution, gain modulation, and noise suppression to the detail layer image to improve detail visibility and prevent boundary halos from being magnified when synthesizing the detail composite image.

[0022] As an explanation, the original layer image is subjected to bilateral filtering to obtain the basal layer image. Bilateral filtering, during the smoothing process, simultaneously considers the spatial proximity of pixels and the differences in pixel values, smoothing brightness variations while preserving edge positions. This reduces noise and excessive contrast while retaining structural contours without crossing boundaries during blending. The basal layer image primarily exhibits low-frequency brightness and color variation trends, serving as a layer for global contrast and dynamic range compression in subsequent processing. This filtering method can be implemented quickly to improve processing speed, reducing computational load through subsampling and piecewise linear bilateral filtering, thus adapting to the needs of high-resolution image processing. After the basal layer image is determined, the detail layer image is obtained by pixel-by-pixel difference between the original layer image and the basal layer image. The difference result preserves local contrast components and texture details, which are more visually sensitive and suitable for controlled enhancement during the detail adjustment stage.

[0023] Detail adjustments can be applied to the detail layer image using one of the following methods: local contrast redistribution, gain modulation, or noise suppression. Local contrast redistribution is used to re-stretch texture undulations at a small scale to improve visibility; gain modulation is used to control the magnitude of detail on a pixel or region basis to avoid over-enhancement near strong boundaries; and noise suppression is used to limit the synchronous amplification of high-frequency noise before and after enhancement. Since contrast compression is applied only to the base layer and the detail layer is superimposed during compositing, the risk of halo artifacts can be reduced while preserving details. Detail adjustments should be consistent with the decomposition results that maintain smooth edges, avoiding the amplification of errors or noise at boundaries as details. This improves detail visibility and suppresses halo expansion when compositing the detail layer image in subsequent steps.

[0024] In step S103, the base layer image is sequentially subjected to chroma adaptation processing and hue compression to obtain a hue-compressed base layer image. The original layer image is subjected to the same processing to obtain a hue-compressed original layer image and a chroma-adapted original layer image. The hue-compressed base layer image is then combined with the detail layer image after detail adjustment to obtain a detail composite image.

[0025] The chromaticity adaptation process includes: performing low-pass filtering on the base layer image to obtain an adapted image for characterizing scene lighting trends; determining the chromaticity features of ambient lighting based on the adapted image and generating a chromaticity adaptation transformation; and applying the chromaticity adaptation transformation to the XYZ components of the base layer image and the original layer image respectively to obtain the chromaticity-adapted base layer image and the chromaticity-adapted original layer image.

[0026] The tone compression includes: establishing a monotonic dynamic range compression function based on the human visual response, and applying the compression function to the XYZ components of the chroma adaptation base layer image and the chroma adaptation original layer image respectively to obtain the tone-compressed base layer image and the tone-compressed original layer image; wherein, the dynamic range compression function is any one of the following: a combination function of rod response and cone response, a piecewise continuous function, or a lookup table mapping.

[0027] As an explanation, chroma adaptation and tone compression are sequentially performed on the base layer image to obtain a global brightness and color reference suitable for display devices. Simultaneously, the same processing path is performed on the original layer image to obtain the corresponding results required for subsequent boundary compensation. Chroma adaptation takes the base layer image as input and performs low-pass filtering to form an adapted image, which characterizes the overall trend of scene lighting and reduces the interference of local details on lighting estimation. Based on the adapted image, the chroma characteristics of ambient lighting are obtained, and a chroma adaptation transformation is constructed. This transformation is applied to the XYZ components of the base layer image and the original layer image, respectively, to obtain the chroma-adapted base layer image and the chroma-adapted original layer image. The significance of this processing is to suppress the overall desaturation and color cast caused by lighting prediction bias, allowing subsequent dynamic range compression to be performed on a color representation closer to the visual adaptation state, reducing the undesirable impact of brightness changes on chroma.

[0028] Tone compression is performed after chroma adaptation. A monotonic dynamic range compression function is constructed based on the human visual response. This function is applied to the XYZ components of both the chroma-adapted base layer image and the original chroma-adapted layer image, resulting in the tone-compressed base layer image and the tone-compressed original layer image, respectively. Simultaneously, the original chroma-adapted layer image is retained as a reference result before tone compression, used for subsequent compensation and enhancement on the chroma channels. The dynamic range compression function can adopt a combination of rod and cone responses, a piecewise continuous form, or a lookup table mapping form. It only needs to maintain overall monotonicity to preserve the brightness order relationship and avoid structural distortion caused by inversion or local abrupt changes. In implementation, applying tone compression channel by channel achieves contrast compression, but it can easily disrupt the color balance between the CIEXYZ channels, providing a necessary source of difference for subsequent boundary color difference detection and compensation.

[0029] To balance detail preservation and dynamic range compression, the tonal compression base layer image and the detail layer image after detail adjustment are composited to obtain a composited image. During the compositing process, pixel-by-pixel addition or equivalent overlay can be used, allowing the base layer image to carry global brightness and large-scale color changes, while the detail layer image carries local texture and micro-contrast. Detail adjustment before compositing controls the magnitude of detail and noise, preventing the amplification of decomposition residuals or high-frequency noise near strong boundaries, thus reducing the risk of halo expansion and laying a stable foundation of brightness and detail for subsequent boundary compensation and saturation restoration only in the chroma channel.

[0030] In step S104, the tone-compressed base layer image, the tone-compressed original layer image, and the chromaticity-adapted original layer image are converted to the IPT color space to obtain the corresponding I luminance component and P and T chromaticity components.

[0031] The step of converting the tone-compressed base layer image, the tone-compressed original layer image, and the chroma-adapted original layer image to the IPT color space includes: for any image to be processed represented by the XYZ color space, obtaining the XYZ components of the image to be processed; performing a linear transformation on the XYZ components to obtain L, M, and S channel components corresponding to the long-wavelength, mid-wavelength, and short-wavelength channels of vision; performing sign-preserving nonlinear exponentiation on the L, M, and S channel components respectively to obtain nonlinear L, M, and S channel components; and performing a linear combination on the nonlinear L, M, and S channel components to obtain the luminance component, chroma component P, and chroma component T.

[0032] As an explanation, step S104 maps the tone-compressed base layer image, the tone-compressed original layer image, and the chroma-adapted original layer image from the CIEXYZ color space to the IPT color space to obtain the I luminance component and P and T chroma components of each image in IPT. IPT belongs to the opposite color space, where I corresponds to the luminance channel, and P and T correspond to the chroma channels, and has good hue linearity, which facilitates boundary color difference measurement and subsequent compensation calculations in the chroma channels. The mapping process consists of two 3×3 matrix transformations and one nonlinear power function: a linear transformation is performed on the XYZ components of any image to be processed to obtain the L, M, and S channel components, satisfying: ; Subsequently, sign-preserving nonlinear exponentiation is performed on L, M, and S respectively to obtain nonlinear channel components L′, M′, and S′, where: ; ; ; Based on this, a linear combination of L′, M′, and S′ yields the I, P, and T components, satisfying: ; After the above transformation, the three images to be processed are respectively obtained as I luminance components and P and T chrominance components, providing a unified data representation for subsequent chrominance difference, direction vector extraction and weighted fusion in the P and T planes.

[0033] In step S105, the difference between the tone-compressed base layer image and the tone-compressed original layer image in the P and T chromaticity components is calculated, the Euclidean amplitude of the difference is obtained, and the difference is normalized according to the maximum amplitude to generate a color difference map; the ratio of the chromaticity amplitude of the tone-compressed original layer image to the chromaticity adaptation original layer image is calculated to obtain the color scaling degree.

[0034] The generation of the color difference map includes: calculating the chromaticity component P difference and chromaticity component T difference between the chromaticity compression base layer image and the chromaticity compression original layer image at pixel locations; performing Euclidean synthesis on the chromaticity component P difference and the chromaticity component T difference to obtain the chromaticity difference amplitude; determining the maximum value of the chromaticity difference amplitude across the entire image range and normalizing the chromaticity difference amplitude with the maximum value to obtain the color difference map that indicates stronger boundary colors with larger values, and implementing adaptive compensation intensity control for boundary regions based on the color difference map.

[0035] The generation of the color scaling factor includes: performing Euclidean synthesis on the chromaticity components P and T of the hue compression original layer image and the chromaticity adaptation original layer image respectively to obtain their respective chromaticity amplitudes, and using the ratio of the chromaticity amplitude of the hue compression original layer image to the chromaticity amplitude of the chromaticity adaptation original layer image as the color scaling factor.

[0036] As an explanation, color distortion measurement around the boundary region is performed using the chroma channels of the IPT space. The difference between the tone-compressed base layer image and the tone-compressed original layer image in the P and T channels is used to locate color distortion regions at strong boundaries, and the difference intensity is normalized to obtain a color difference map; where, let , Let the P and T components of the tone-compressed basal layer image at coordinates (i,j) be represented. , If the P and T components of the original image at the same location in the tone compression layer are represented, then the chromaticity difference between the two is divided into: ; ; The above differences are then Euclidean synthesized in the PT plane to obtain the chromaticity difference amplitude: ; Find it across the entire map. maximum value The color difference map is obtained by normalizing the amplitude of each pixel using this maximum value. ; The value of is used to characterize the intensity of boundary color distortion. A value closer to a smaller value indicates a region with a smaller boundary error, while a value closer to a larger value indicates a region with a larger boundary error. This enables the subsequent compensation process to implement adaptive compensation intensity control for the boundary region based on this image.

[0037] Color scaling measures the proportion of change in chroma amplitude between chroma adaptation and hue compression. This change is related to the brightness effect caused by the change in dynamic range, and is therefore calculated as a scalar ratio of the PT axis chroma response of the original layer image under the two processing results.

[0038] make , If the chromaticity is adapted to the P and T components of the original layer image at (i,j), then the color scaling factor is defined as: ; This ratio serves as a weight to characterize the relative scaling relationship of chroma amplitudes under the two processing paths, providing scale consistency for chroma compensation in the boundary region. This enables the contribution of chroma adaptation results to be improved in areas with large boundary errors during subsequent fusion. At the same time, this scaling factor compensates for the amplitude differences between the two, avoiding the introduction of new hue shifts or saturation anomalies due to inconsistent chroma amplitudes.

[0039] In step S106, the chromaticity components of the original hue compression layer image and the chromaticity adaptation layer image are weighted and fused according to the chromaticity difference diagram, and the fusion contribution of the chromaticity adaptation layer image is compensated according to the color scaling degree to obtain the standard chromaticity components.

[0040] The weighted fusion includes: increasing the weight of the chromaticity component of the hue compression original layer image at positions where the chromaticity difference map value is low, and increasing the weight of the chromaticity component of the chromaticity adaptation original layer image at positions where the chromaticity difference map value is high.

[0041] The fusion contribution of the chroma-adapted original layer image is compensated according to the color scaling factor, including: scaling the chroma components of the chroma-adapted original layer image according to the color scaling factor before participating in the fusion, thereby obtaining the standard chroma component containing the standard P chroma component and the standard T chroma component, so as to reduce the hue shift at the color boundary and suppress halo artifacts.

[0042] As an explanation, the values ​​are compensated to ensure that the fused chroma maintains the appearance consistency of the hue compression result in most areas, while introducing a more stable chroma reference in areas with significant boundary distortion to mitigate hue shift and halo artifacts. For any pixel position (i,j), using... To represent the values ​​of the color difference image, use Indicates color scaling, using , The P and T components of the original layer image are represented by the tonal compression method. The P and T components represent the chroma adaptation of the original layer image. The standard chroma components are obtained by weighted fusion and scaling compensation for the chroma adaptation contribution. ; ; The above expression reflects the adaptive allocation of two chromaticity information paths by the color difference diagram: when At a low level, Dominant, the fusion result is closer to the original image after tone compression, thus maintaining the overall style and color consistency after tone compression; when At a high level, Dominantly, the blended result incorporates more compensated chroma adaptation components, suppressing color discontinuities and halo tendencies at the boundaries caused by independent channel compression and detail overlay. Color scaling This is used to match the amplitude of the chroma adaptation component, ensuring it is on a comparable scale to the hue compression result when participating in fusion, thus avoiding the introduction of new saturation anomalies or hue shifts due to excessive differences in the amplitudes of the two chroma components; the resulting... and These constitute the standard P-color component and the standard T-color component, providing a stable colorimetric reference for subsequent boundary color enhancement based on direction vectors.

[0043] In step S107, an enhanced stop mask is generated based on the chroma amplitude of the original hue compression layer image, an enhancement gain is generated based on the relative relationship between the luminance components of the original hue compression layer image and the original chroma adaptation layer image, and a chroma difference direction vector is obtained from the direction of the difference. Under the modulation of the enhanced stop mask, the chroma difference direction vector is superimposed on the standard chroma component and scaled by the enhancement gain to obtain the enhanced chroma component.

[0044] The enhanced stop mask is generated based on the Euclidean composite amplitude of the chromaticity component P and chromaticity component T of the original hue compression layer image. When the Euclidean composite amplitude is higher than a preset threshold, it takes a preset maximum weight, and when the Euclidean composite amplitude is lower than the preset threshold, it is attenuated according to the proportion of the Euclidean composite amplitude, so as to suppress white point drift or hue drift at low saturation or near-neutral color boundaries.

[0045] The enhancement gain is obtained by using a preset monotonic mapping function based on the ratio of the luminance component of the original hue compression layer image to the luminance component of the original chroma adaptation layer image, and a lower limit is set on the enhancement gain to avoid desaturation.

[0046] The chromatic difference direction vector is obtained by dividing the difference between the chromaticity component P and the difference between the chromaticity component T of the chromaticity compressed base layer image and the chromaticity compressed original layer image by the maximum value of the chromaticity difference amplitude.

[0047] The enhanced chroma component is obtained by superimposing the chroma direction vector onto the standard chroma component under the enhanced stop mask modulation and scaling it by the enhancement gain, and the output image is composed of the enhanced chroma component and the luminance component of the detailed composite image in the IPT color space.

[0048] As an explanation, step S107 focuses on chroma enhancement around the saturation decrease in low-brightness and low-chroma regions. The enhancement process is constrained by an enhancement stop mask, enhancement gain, and chroma difference direction vector. The enhancement stop mask is used to suppress white point drift or hue drift at monochromatic or low-saturation boundaries. The enhancement gain is used to correct the chroma compensation amplitude based on the brightness changes before and after tone compression. The chroma difference direction vector is used to indicate the direction of change in the P and T channels and to enhance the saturation in boundary regions. The enhancement stop mask, in IPT space, uses the Euclidean composite amplitude of the P and T channels of the original tone-compressed layer image as a saturation measure, defined as: ; And based on this, the enhanced stopping mask is obtained: ; Where 'c' is the threshold used to define the low-saturation region, ensuring that the high-saturation region maintains full-amplitude enhancement, while the enhancement intensity in the low-saturation region is reduced according to the saturation amplitude, thereby reducing the probability of white point shift or hue shift at the boundary. The enhancement gain is based on the brightness ratio in the I channel of the original tonal compression layer image and the original chroma adaptation layer image. It is assumed that brightness changes affect the chroma component, requiring compensation for the saturation corresponding to the brightness change. The enhancement gain is calculated as follows: ; The enhancement gain is ensured to be no less than 1 to prevent further attenuation of chroma. The chroma difference direction vector is obtained by normalizing the P and T differential channels according to the maximum chroma difference amplitude, and is used to express the direction of change in the P and T channels. It is calculated as follows: ; ; in , The difference between the tone-compressed basal layer image and the tone-compressed original layer image in the P and T channels. This represents the maximum value of the chromaticity difference amplitude.

[0049] After obtaining the standard color channel , Based on this, the chromaticity direction vector is superimposed onto the standard chromaticity channel under enhanced stop mask modulation, and then scaled by the overall enhancement gain to obtain the enhanced chromaticity component. , Its expression is: ; ; This processing method enables controlled chromaticity enhancement in the boundary region along the differential direction in the PT plane, enhances the stop mask to limit the low-saturation boundary, and enhances the gain to compensate for the enhancement amplitude according to the brightness change, thereby improving boundary desaturation while suppressing unstable drift of hue and white point.

[0050] In step S108, the luminance component of the detailed composite image is extracted and synthesized with the enhanced chrominance component to form an output image, and the output image is inversely transformed to obtain a low dynamic range display image, which is then displayed on the target device.

[0051] The inverse transformation of the output image includes: inverting the linear combination, inverting the nonlinear exponentiation, and inverting the linear transformation to restore the output image from the IPT color space to the XYZ color space.

[0052] As an explanation, step S108 recombines the luminance information provided by the detail-synthesized image with the enhanced chrominance information to form the output image. The detail-synthesized image is derived from the superposition of the base layer and detail layer after tone compression, containing the compressed global luminance trend and preserved local texture. Therefore, the luminance component is extracted from the detail-synthesized image as the output luminance component. In CIEXYZ representation, the luminance component can be obtained from the Y channel; in IPT representation, the luminance component corresponds to the I channel. The detail-synthesized image can be mapped to IPT and its I component can be taken as the output luminance component. The output image is obtained in the IPT color space by combining the luminance component and the enhanced chrominance component obtained in step S107, that is, forming at pixel position (i,j). ,in and These are the enhanced P and T chromaticity components, respectively. After combination, an inverse transform from IPT to CIEXYZ is performed on the output image to obtain a low dynamic range display image. The inverse transform includes the inverse of linear combination, the inverse of sign-preserving exponentiation, and the inverse of linear transform: Let Indicates will Linear combination to Given the matrix, we have: ; Performing inverse exponentiation on the nonlinear channel while maintaining sign consistency satisfies: ; ; ; make Indicates will Linear transformation to The matrix is ​​such that the CIEXYZ components can be recovered from its inverse matrix, satisfying: ; The resulting CIEXYZ three-channel image constitutes a low dynamic range display image. It can be further mapped according to the color space and electro-optical conversion characteristics of the target display device and then output to the LED light pole screen advertising machine for display, so that the image retains the detail level while presenting the color effect after boundary compensation and enhancement.

[0053] Based on the same line of thought, such as Figure 2 As shown, a color gamut boundary compensation system for LED light pole screen advertising machines is provided, comprising: The input conversion module 201 is used to acquire the input HDR image and convert it to the XYZ color space to obtain the original layer image; The decomposition module 202 is used to perform bilateral filtering on the original layer image to obtain the basal layer image, and to obtain the detail layer image by the difference between the original layer image and the basal layer image; The compression compositing module 203 is used to sequentially perform chroma adaptation processing and hue compression on the base layer image to obtain a hue-compressed base layer image, perform the same processing on the original layer image to obtain a hue-compressed original layer image and a chroma adaptation original layer image, and composite the hue-compressed base layer image with the detail layer image after detail adjustment to obtain a detail composite image; IPT extraction module 204 is used to convert the tone compression base layer image, the tone compression original layer image and the chromaticity adaptation original layer image to the IPT color space to obtain the corresponding I luminance component and P and T chromaticity components. The color difference direction module 205 is used to calculate the difference between the tone compression base layer image and the tone compression original layer image in the P and T chromaticity components, obtain the Euclidean amplitude of the difference and normalize it according to the maximum amplitude to generate a color difference map; calculate the ratio of the chromaticity amplitude of the tone compression original layer image to the chromaticity adaptation original layer image to obtain the color scaling degree. The fusion compensation module 206 is used to perform weighted fusion of the chromaticity components of the original hue compression layer image and the chromaticity adaptation layer image based on the chromaticity difference diagram, and to compensate the fusion contribution of the chromaticity adaptation layer image according to the color scaling degree to obtain the standard chromaticity components. The enhancement control module 207 is used to generate an enhancement stop mask based on the chroma amplitude of the hue compression original layer image, generate an enhancement gain based on the relative relationship between the luminance components of the hue compression original layer image and the chroma adaptation original layer image, obtain a chroma difference direction vector from the direction of the difference, and superimpose the chroma difference direction vector on the standard chroma component under the modulation of the enhancement stop mask and scale it by the enhancement gain to obtain the enhanced chroma component; The recombined output module 208 is used to extract the luminance component of the detailed composite image and synthesize it with the enhanced chrominance component to form an output image, and to perform an inverse transformation on the output image to obtain a low dynamic range display image, and to display the low dynamic range display image on the target device.

[0054] Compared to existing technologies that rely solely on single-path tone mapping or simple chroma scaling, this system utilizes the chroma difference between the base layer and the original layer in a multi-layer decomposition to construct a chroma map. This map is used to locate and quantify color distortion areas at strong boundaries. It also compensates for chroma deviations between chroma adaptation and tone compression by combining chroma scaling. Simultaneously, it suppresses white point drift or hue drift at low-saturation or near-neutral boundaries through an enhanced stop mask, and generates enhancement gain based on brightness variation to directionally enhance the saturation drop in boundary areas. Finally, the compensated and enhanced chroma and brightness components are recombined and output, thereby reducing boundary color distortion and halo artifacts, improving desaturation in low-brightness areas, and enhancing the image layering and color consistency of LED light pole advertising displays.

[0055] The specific details of each module / unit in the above system have been described in detail in the implementation method section. For any undisclosed details, please refer to the implementation method section, and therefore will not be repeated here.

[0056] Based on the same idea, this specification also provides an LED light pole screen advertising machine color gamut boundary compensation device, such as... Figure 3 As shown.

[0057] The color gamut boundary compensation device for LED light pole screen advertising machines can be the terminal device or server provided in the above embodiments.

[0058] The color gamut boundary compensation device for LED light pole advertising displays can vary significantly depending on configuration and performance. It may include one or more processors 301, a memory 302, and a bus. The memory 302 may store one or more application programs or data. The memory 302 may include readable media in the form of volatile storage units, such as random access memory (RAM) and / or cache memory units, i.e., plug-in external hard drives, smart media cards (SMC), secure digital cards (SD), flash cards, etc., and may further include read-only memory units. The application programs stored in the memory 302 may include one or more program modules (not shown in the figures). Such program modules include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Furthermore, the processor 301 may be configured to communicate with the memory 302 and execute a series of computer-executable instructions stored in the memory 302 on the LED light pole advertising display color gamut boundary compensation device. The LED light pole screen advertising machine color gamut boundary compensation device may also include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more I / O interfaces (input / output interfaces) 305, and one or more external devices 306 (e.g., keyboards). It may also communicate with one or more devices that enable user interaction with the device, and / or with any device that enables the device to communicate with one or more other computing devices (e.g., routers, network switches, etc.). This communication can be performed through I / O interfaces 305. Furthermore, the device can also communicate with one or more networks (e.g., local area networks (LANs)) through wired or wireless interfaces 304.

[0059] Figure 3 Only the color gamut boundary compensation device for LED light pole screen advertising machines with components is shown; those skilled in the art will understand that... Figure 3 The structure shown does not constitute a limitation on the color gamut boundary compensation device for LED light pole screen advertising machines. It may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0060] Specifically, in this embodiment, the LED light pole screen advertising machine color gamut boundary compensation device includes a memory and one or more programs, wherein one or more programs are stored in the memory, and one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the LED light pole screen advertising machine color gamut boundary compensation device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following: The input HDR image is acquired and converted to the XYZ color space to obtain the original layer image; The original layer image is subjected to bilateral filtering to obtain the basal layer image, and the detail layer image is obtained by the difference between the original layer image and the basal layer image; The base layer image is sequentially subjected to chroma adaptation processing and hue compression to obtain a hue-compressed base layer image. The original layer image is subjected to the same processing to obtain a hue-compressed original layer image and a chroma-adapted original layer image. The hue-compressed base layer image is then combined with the detail layer image after detail adjustment to obtain a detail composite image. The hue-compressed base layer image, the hue-compressed original layer image, and the chroma-adapted original layer image are converted to the IPT color space to obtain the corresponding I luminance component and P and T chroma components. Calculate the difference between the tone-compressed base layer image and the tone-compressed original layer image in the P and T chromaticity components, obtain the Euclidean magnitude of the difference, and normalize it according to the maximum magnitude to generate a color difference map; calculate the ratio of the chromaticity magnitude of the tone-compressed original layer image to the chromaticity adaptation original layer image to obtain the color scaling degree. The chromaticity components of the original hue compression layer image and the original chromaticity adaptation layer image are weighted and fused according to the chromaticity difference diagram, and the fusion contribution of the original chromaticity adaptation layer image is compensated according to the color scaling degree to obtain the standard chromaticity components. An enhanced stop mask is generated based on the chroma amplitude of the original hue-compressed layer image. An enhanced gain is generated based on the relative relationship between the luminance components of the original hue-compressed layer image and the original chroma-adapted layer image. A chroma difference direction vector is obtained from the direction of the difference. The chroma difference direction vector is superimposed on the standard chroma component under the modulation of the enhanced stop mask and scaled by the enhanced gain to obtain the enhanced chroma component. The luminance component of the detailed composite image is extracted and combined with the enhanced chrominance component to synthesize an output image. The output image is then inversely transformed to obtain a low dynamic range display image, which is then displayed on the target device.

[0061] Based on the same idea, exemplary embodiments of the present invention also provide a computer-readable storage medium having a program product stored thereon capable of implementing the methods described above in this specification. In some possible embodiments, various aspects of this disclosure can also be implemented as a program product including program code, which, when the program product is run on a terminal device, causes the terminal device to perform the steps according to the various exemplary embodiments of this disclosure described in the "Exemplary Methods" section above.

[0062] refer to Figure 4 As shown, a program 400 for implementing the above-described method according to an exemplary embodiment of the present disclosure is described. This program may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, system, or device.

[0063] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0064] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, system, or device.

[0065] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, CSS, and HTML, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0066] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal system, or network device, etc.) to execute the method according to the exemplary embodiments of this disclosure.

[0067] Furthermore, the above figures are merely illustrative representations of the processes included in the methods according to exemplary embodiments of this disclosure, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0068] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to exemplary embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0069] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0070] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A color gamut boundary compensation method for LED lamp pole screen advertising machines, characterized in that, The method includes: The input HDR image is acquired and converted to the XYZ color space to obtain the original layer image; The original layer image is subjected to bilateral filtering to obtain the basal layer image, and the detail layer image is obtained by the difference between the original layer image and the basal layer image; The base layer image is sequentially subjected to chroma adaptation processing and hue compression to obtain a hue-compressed base layer image. The original layer image is subjected to the same processing to obtain a hue-compressed original layer image and a chroma-adapted original layer image. The hue-compressed base layer image is then combined with the detail layer image after detail adjustment to obtain a detail composite image. The hue-compressed base layer image, the hue-compressed original layer image, and the chroma-adapted original layer image are converted to the IPT color space to obtain the corresponding I luminance component and P and T chroma components. Calculate the difference between the tone-compressed base layer image and the tone-compressed original layer image in the P and T chromaticity components, obtain the Euclidean magnitude of the difference, and normalize it according to the maximum magnitude to generate a color difference map; calculate the ratio of the chromaticity magnitude of the tone-compressed original layer image to the chromaticity adaptation original layer image to obtain the color scaling degree. The chromaticity components of the original hue compression layer image and the original chromaticity adaptation layer image are weighted and fused according to the chromaticity difference diagram, and the fusion contribution of the original chromaticity adaptation layer image is compensated according to the color scaling degree to obtain the standard chromaticity components. An enhanced stop mask is generated based on the chroma amplitude of the original hue-compressed layer image. An enhanced gain is generated based on the relative relationship between the luminance components of the original hue-compressed layer image and the original chroma-adapted layer image. A chroma difference direction vector is obtained from the direction of the difference. The chroma difference direction vector is superimposed on the standard chroma component under the modulation of the enhanced stop mask and scaled by the enhanced gain to obtain the enhanced chroma component. The luminance component of the detailed composite image is extracted and combined with the enhanced chrominance component to synthesize an output image. The output image is then inversely transformed to obtain a low dynamic range display image, which is then displayed on the target device.

2. The LED lamp pole screen advertising machine color gamut boundary compensation method according to claim 1, characterized in that, The bilateral filtering smooths the edges of the original layer image by simultaneously introducing spatial distance weights and pixel value difference weights, so that the base layer image contains low-frequency brightness and color variations and suppresses color mixing across edges; the detail layer image is a pixel-by-pixel difference between the original layer image and the base layer image; the detail adjustment includes applying one of local contrast redistribution, gain modulation and noise suppression to the detail layer image to improve detail visibility and avoid amplifying boundary halos when synthesizing the detail composite image.

3. The LED lamp pole screen advertising machine color gamut boundary compensation method according to claim 1, characterized in that, The colorimetric adaptation process includes: The base layer image is low-pass filtered to obtain an adapted image for characterizing scene lighting trends; The chromaticity features of the ambient lighting are determined based on the adapted image, and a chromaticity adaptation transformation is generated. The chromaticity adaptation transformation is applied to the XYZ components of the base layer image and the original layer image, respectively, to obtain the chromaticity-adapted base layer image and the chromaticity-adapted original layer image.

4. The color gamut boundary compensation method for LED light pole screen advertising machines according to claim 1, characterized in that, The tone compression includes: A monotonic dynamic range compression function is established based on the human visual response, and the compression function is applied to the XYZ components of the chroma adaptation base layer image and the chroma adaptation original layer image respectively to obtain the hue compression base layer image and the hue compression original layer image; wherein, the dynamic range compression function is any one of the following: a combination function of rod response and cone response, a piecewise continuous function, or a lookup table mapping.

5. The color gamut boundary compensation method for LED light pole screen advertising machines according to claim 1, characterized in that, The step of converting the tone-compressed base layer image, the tone-compressed original layer image, and the chroma-adapted original layer image to the IPT color space includes: For any image to be processed represented by the XYZ color space, obtain the XYZ components of the image to be processed; Perform a linear transformation on the XYZ components to obtain the L, M, and S channel components corresponding to the visual long-wave channel, mid-wave channel, and short-wave channel; Sign-preserving nonlinear exponentiation is performed on the L, M, and S channel components respectively to obtain nonlinear L, M, and S channel components; linear combination is performed on the nonlinear L, M, and S channel components to obtain the luminance component, chrominance component P, and chrominance component T. Performing an inverse transform on the output image includes: The output image is restored from the IPT color space to the XYZ color space by inverting the linear combination, inverting the nonlinear exponentiation, and inverting the linear transformation.

6. The color gamut boundary compensation method for LED light pole screen advertising machines according to claim 1, characterized in that, The generation of the color difference image includes: At the pixel location, calculate the chromaticity component P difference and the chromaticity component T difference between the chromaticity compression base layer image and the chromaticity compression original layer image; then perform Euclidean synthesis on the chromaticity component P difference and the chromaticity component T difference to obtain the chromaticity difference amplitude value. The maximum value of the chromaticity difference amplitude is determined within the entire map range, and the chromaticity difference amplitude is normalized using the maximum value to obtain the chromaticity difference map that indicates stronger boundary colors with larger values. Adaptive compensation intensity control is then implemented for the boundary regions based on the chromaticity difference map.

7. The color gamut boundary compensation method for LED light pole screen advertising machines according to claim 1, characterized in that, The generation of the color scaling factor includes: The chromaticity components P and T of the original hue compression layer image and the original chromaticity adaptation layer image are respectively synthesized using Euclidean algorithm to obtain their respective chromaticity amplitudes, and the ratio of the chromaticity amplitude of the original hue compression layer image to the chromaticity amplitude of the original chromaticity adaptation layer image is used as the color scaling degree. The weighted fusion includes: Increase the weight of the chromaticity component of the original image of the hue compression at the position where the chromaticity map value is low, and increase the weight of the chromaticity component of the original image of the chromaticity adaptation at the position where the chromaticity map value is high; The fusion contribution to the original layer image adapted to the chroma is compensated according to the color scaling, including: The chromaticity components of the original layer image are scaled according to the color scaling factor before being fused to obtain the standard chromaticity components that include standard P chromaticity components and standard T chromaticity components, thereby reducing hue shift at color boundaries and suppressing halo artifacts.

8. The color gamut boundary compensation method for LED light pole screen advertising machines according to claim 1, characterized in that, The enhanced stop mask is generated based on the Euclidean composite amplitude of the chromaticity component P and chromaticity component T of the original hue compression layer image. When the Euclidean composite amplitude is higher than a preset threshold, it takes a preset maximum weight, and when the Euclidean composite amplitude is lower than the preset threshold, it is attenuated according to the proportion of the Euclidean composite amplitude, so as to suppress white point drift or hue drift at low saturation or near-neutral color boundaries. The enhancement gain is obtained by using a preset monotonic mapping function based on the ratio of the luminance component of the original hue compression layer image to the luminance component of the original chroma adaptation layer image, and a lower limit is set for the enhancement gain to avoid desaturation. The chromatic difference direction vector is obtained by dividing the difference between the chromaticity component P and the difference between the chromaticity component T of the chromaticity compressed base layer image and the chromaticity compressed original layer image by the maximum value of the chromaticity difference amplitude, respectively. The enhanced chroma component is obtained by superimposing the chroma direction vector onto the standard chroma component under the enhanced stop mask modulation and scaling it by the enhancement gain, and the output image is composed of the enhanced chroma component and the luminance component of the detailed composite image in the IPT color space.

9. A color gamut boundary compensation system for LED light pole screen advertising machines, characterized in that, include: The input conversion module is used to acquire the input HDR image and convert it to the XYZ color space to obtain the original layer image; The decomposition module is used to perform bilateral filtering on the original layer image to obtain the basal layer image, and to obtain the detail layer image by the difference between the original layer image and the basal layer image; The compression compositing module is used to sequentially perform chroma adaptation processing and hue compression on the base layer image to obtain a hue-compressed base layer image, perform the same processing on the original layer image to obtain a hue-compressed original layer image and a chroma adaptation original layer image, and then combine the hue-compressed base layer image with the detail layer image after detail adjustment to obtain a detail composite image. The IPT extraction module is used to convert the tone compression base layer image, the tone compression original layer image and the chromaticity adaptation original layer image to the IPT color space to obtain the corresponding I luminance component and P and T chromaticity components. The color difference direction module is used to calculate the difference between the tone compression base layer image and the tone compression original layer image in the P and T chromaticity components, obtain the Euclidean amplitude of the difference and normalize it according to the maximum amplitude to generate a color difference map. The color scaling factor is obtained by calculating the ratio of the chroma magnitude of the original image of the hue compression layer to that of the original image of the chroma adaptation layer. The fusion compensation module is used to perform weighted fusion of the chromaticity components of the original hue compression layer image and the chromaticity adaptation layer image based on the chromaticity difference diagram, and to compensate the fusion contribution of the chromaticity adaptation layer image according to the color scaling degree to obtain the standard chromaticity components. An enhancement control module is used to generate an enhancement stop mask based on the chroma amplitude of the original hue compression layer image, generate an enhancement gain based on the relative relationship between the luminance components of the original hue compression layer image and the original chroma adaptation layer image, obtain a chroma difference direction vector from the direction of the difference, and superimpose the chroma difference direction vector onto the standard chroma component under the modulation of the enhancement stop mask and scale it by the enhancement gain to obtain the enhanced chroma component. The recombined output module is used to extract the luminance component of the detailed composite image and synthesize it with the enhanced chrominance component to form an output image, and to perform an inverse transformation on the output image to obtain a low dynamic range display image, and to display the low dynamic range display image on the target device.

Images