CN118430465B - Backlight compensation method and system for intelligent display screen and display screen - Google Patents

Abstract

The present application relates to the technical field of display screen backlight compensation, and specifically to a backlight compensation method, system and display screen for smart display screens, the method comprising: determining the area and target area of the current frame, obtaining the background area and foreground area; obtaining the visual complexity index of all areas of the current frame; calculating the texture detail feature value and contrast significance of the target area, and then obtaining the relative compensation demand of the target area; determining the previous adjacent frame, obtaining the backlight adjustment degree between frames, obtaining the backlight brightness reference, and then obtaining the backlight intensity of the target area in the current frame, and obtaining the backlight compensation result of the smart display screen in the target area according to the backlight intensity of the target area in the current frame and the backlight brightness reference, and obtaining the backlight compensation result of the smart display screen. The present application solves the problem that the details of the highlight or dark area are lost due to excessive adjustment or too weak adjustment of the backlight system.

Description

Backlight compensation method, system and display screen for intelligent display screen

Technical Field

The present application relates to the technical field of display screen backlight compensation, and in particular to a backlight compensation method, system and display screen for a smart display screen.

Background Art

Display backlight compensation technology adjusts the backlight brightness to adapt to different ambient light conditions, while reducing viewer eye fatigue, enhancing image details and improving color accuracy, which can improve the visual experience and display effect. Display backlight compensation can also be fine-tuned according to the dynamic range of the displayed content and user preferences, further improving the user's viewing experience and enabling the display to provide high-quality display effects in various environments. Among them, the dynamic range limitation of the displayed content involves the display's ability to display content at different brightness levels.

In particular, in high-contrast and low-brightness scenes, backlight compensation may affect the dynamic range of the display. In high-contrast scenes, in order to adapt to the ambient light, backlight compensation will increase the screen brightness, but too bright a screen will result in loss of details in the highlight part; in low-brightness scenes, in order to reduce viewer eye fatigue, backlight compensation will reduce the screen brightness, but too dark a screen will result in unclear details in the dark part. Therefore, in order to ensure high-quality display of the display in various environments, it is necessary to solve the problem of excessive or weak adjustment of the backlight system causing loss of details in the highlight or dark area.

Summary of the invention

In order to solve the above technical problems, the purpose of this application is to provide a backlight compensation method, system and display screen for a smart display screen. The technical solutions adopted are as follows:

In a first aspect, an embodiment of the present application provides a backlight compensation method for a smart display screen, the method comprising the following steps:

Determine each local area of the current frame of the display screen, and take any local area as a target area;

Obtaining a visual complexity index of the target area according to the number, number difference and position distribution of pixels belonging to the foreground area and the background area in the target area;

According to the texture information of the pixel points in the neighborhood area of the edge pixel points of the current frame, the texture detail feature value of the target area is calculated, and the contrast significance of the target area is obtained according to the distance between the central pixel points of all local areas in the current frame and the visual complexity index of all local areas in the current frame. The relative compensation demand of the target area is obtained in combination with the texture detail feature value of the target area;

According to the difference in relative compensation requirements and contrast between the target area of the current frame and the previous frame adjacent to the current frame, the inter-frame backlight adjustment degree of the target area in the current frame is obtained, and the backlight brightness benchmark of the target area in the current frame is obtained according to the pixel values of all pixels contained in the previous adjacent frame of the target area. The backlight intensity of the target area in the current frame is obtained in combination with the inter-frame backlight adjustment degree. According to the backlight intensity of the target area in the current frame and the backlight brightness benchmark, the backlight compensation result of the target area of the smart display is obtained.

Furthermore, the process of determining the visual complexity index of the target area is as follows:

For the target area of the current frame, the ratio between the number of pixels in the target area belonging to the foreground area and the number of pixels in the target area is recorded as the foreground area ratio; the ratio between the number of pixels in the background area and the number of pixels in the target area is recorded as the background area ratio; the absolute value of the difference between the foreground area ratio and the background area ratio is recorded as the segmentation difference degree of the target area;

The run matrix of the target area in the horizontal direction is recorded as the horizontal run matrix of the target area, half of the maximum run in the horizontal run matrix is recorded as a half run, a run whose length is less than a half run is recorded as a short run, the number of short runs with the same length as the short run in the horizontal run matrix is used as the weight of the short run, the run lengths of each short run are weighted and summed, and the ratio of the weighted sum value to the number of pixels contained in the target area is recorded as the segmentation clutter of the target area;

According to the segmentation difference and segmentation clutter of the target area, a visual complexity index of the target area is obtained, and the visual complexity index of the target area is positively correlated with the segmentation difference and segmentation clutter of the target area, respectively.

Furthermore, the texture detail feature value of the target area is calculated based on the texture information of the pixel points in the neighborhood area of the edge pixel points of the current frame, and the specific process of obtaining the texture detail feature value is as follows:

In the current frame, a window with the edge pixel as the center and the first preset threshold as the side length is recorded as the texture feature window of the edge pixel;

The average of the texture feature values of all pixels in the texture feature window of the edge pixel is taken as the texture feature value of the edge pixel;

The average of the texture feature values of all edge pixels in the target area is recorded as the texture detail feature value of the target area.

Furthermore, the contrast significance of the target area is obtained according to the distance between the central pixels of all local areas in the current frame and the visual complexity index of all local areas in the current frame. The specific process of obtaining is:

Obtain the central pixel points of all regions in the current frame, calculate the Euclidean distance between the central pixel point of the target region and the central pixel point of each other local region in the current frame, and record the Euclidean distance as the first distance between the corresponding two regions;

Calculate the ratio between the visual complexity index of the target area and the visual complexity index of each other local area in the current frame respectively, and record the ratio as the first ratio of the corresponding two areas;

The product of the first distance and the first ratio of the two regions is recorded as the first contrast of the two regions, and the cumulative sum of the first contrast of the target region and each other local region in the current frame is recorded as the contrast significance of the target region.

Furthermore, the process of determining the relative compensation requirement of the target area is as follows:

The ratio of the contrast saliency of the target area to the texture detail feature value of the target area is recorded as the relative compensation requirement of the target area.

Further, according to the difference in relative compensation requirements and contrast between the target area of the current frame and the target area of the previous frame adjacent to the current frame, the inter-frame backlight adjustment degree of the target area in the current frame is obtained, and the specific process of obtaining is:

Record the previous adjacent image frame of the current frame as the previous adjacent frame;

The difference between the relative compensation requirements of the target area of the current frame and the previous adjacent frame is recorded as the relative compensation difference of the target area in the current frame; the difference between the contrast of the target area of the current frame and the previous adjacent frame is recorded as the contrast difference of the target area in the current frame;

According to the relative compensation difference and contrast difference of the target area in the current frame, the inter-frame backlight adjustment degree of the target area in the current frame is obtained, and the inter-frame backlight adjustment degree of the target area in the current frame is positively correlated with the relative compensation difference and contrast difference of the target area in the current frame.

Furthermore, the backlight brightness reference of the target area in the current frame is obtained according to the pixel values of all pixels contained in the target area in the previous adjacent frame, and the backlight intensity of the target area in the current frame is obtained in combination with the backlight adjustment degree between frames. The specific process of obtaining is:

The normalized value of the inter-frame backlight adjustment degree of the target area in the current frame is recorded as the first adjustment degree of the target area in the current frame, and the product of the backlight brightness benchmark, the first adjustment degree and the preset error adjustment parameter of the target area in the current frame is recorded as the backlight intensity of the target area in the current frame.

Further, the backlight compensation result of the smart display screen in the target area is obtained according to the backlight intensity and backlight brightness reference of the target area in the current frame. The specific process of obtaining is:

The difference between the backlight intensity of the target area in the current frame and the backlight brightness reference of the target area in the current frame is used as the value of the backlight compensation amount of the target area in the display screen in the current frame to obtain the backlight compensation result of the target area in the display screen in the current frame.

In a second aspect, an embodiment of the present application also provides a backlight compensation system for a smart display screen, the system comprising a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of any one of the above methods when executing the computer program.

In a third aspect, an embodiment of the present application provides a backlight compensation display screen for a smart display screen, and the display screen is manufactured by any of the methods described above.

It can be seen from the above embodiments that the backlight compensation method, system and display screen for a smart display screen provided in the embodiments of the present application have at least the following beneficial effects:

The present application adopts a partitioned backlight compensation method to perform backlight compensation on the current frame, divides the display screen into multiple areas and determines the target area, analyzes the degree of chaos and continuity of the distribution of the foreground area and the background area in the target area, and obtains the visual complexity index of the target area; then, the texture richness and the richness of the detail information inside the target area are measured to obtain the texture detail feature value of the target area. The texture detail feature value of the target area reflects the degree of change of the microscopic detail information and the structure in the target area. When the texture richness and the richness of the detail information inside the target area are greater, in order to avoid the problem of loss of detail information after backlight compensation, the target area has a smaller demand for backlight compensation. Furthermore, the visual importance of the target area relative to all areas in the current frame is evaluated to obtain the contrast significance of the target area. The contrast significance measures the target area relative to all areas in the current frame. The visual importance of a region is determined. When the contrast significance of the target region is greater, the target region is more prominent visually and has a higher contrast difference in light and dark. The target region has a greater demand for backlight compensation, and then the relative compensation demand of the target region is obtained. The relative compensation demand is the comprehensive demand for backlight compensation of the target region obtained after comprehensively considering the texture detail feature value and contrast significance. Finally, the previous adjacent frame is determined, and the backlight compensation result of the smart display in the target region is obtained according to the difference in the comprehensive demand for backlight compensation of the same region of the current frame and the previous adjacent frame. Then, the backlight compensation result of the smart display is obtained. The backlight compensation result can enable the display to automatically adjust the screen brightness and reduce the eye fatigue of the viewer when displaying high-contrast and low-contrast images. At the same time, it reduces the loss of details in the high-contrast part and solves the problem of excessive or weak adjustment of the backlight system causing loss of details in the highlight or dark area.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

FIG1 is a flowchart of a backlight compensation method for a smart display screen provided by an embodiment of the present application;

FIG2 is a flowchart of obtaining a visual complexity index according to an embodiment of the present application;

FIG3 is a flowchart of obtaining relative compensation requirements provided by an embodiment of the present application.

DETAILED DESCRIPTION

In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of the backlight compensation method, system and display screen for a smart display screen proposed in accordance with the present application, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

Unless otherwise specified and limited, terms such as "comprises", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such articles or devices. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the article or device including the element. In addition, the term "and\or" used herein includes any and all combinations of one or more related listed items. All technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application.

The following is a detailed description of a backlight compensation method, system and display screen solution for a smart display screen provided by the present application in conjunction with the accompanying drawings.

Please refer to FIG. 1 , which shows a flowchart of a backlight compensation method for a smart display screen provided by an embodiment of the present application. The method includes the following steps:

Step 1: Determine each local area of the current frame of the display screen, and take any local area as the target area.

This embodiment adopts a partitioned backlight compensation method to perform backlight compensation on the current frame, and divides the display screen into 24 local areas for the convenience of subsequent processing.

Each frame of the display screen is acquired, and each local area in each frame of the image is analyzed respectively, and the analyzed image frame is recorded as the current frame, and the analyzed local area in the current frame is recorded as the target area.

In this embodiment, the display screen is divided into 24 local areas. The number of local areas is set according to the experience of those skilled in the art, or determined according to experimental debugging by those skilled in the art. As other implementation methods, the implementer can determine the value of the number of local areas according to actual conditions.

When the contrast between adjacent frames changes too much, it is easy to cause the backlight compensation to be too strong, causing the display screen to flicker and causing visual discomfort to the viewer. At this time, the degree of backlight compensation needs to be adjusted.

The current frame is grayed to obtain a gray image, and the gray image is binarized using the OTSU maximum inter-class variance method to obtain a partition threshold. The area composed of pixels in the gray image whose gray values are greater than or equal to the partition threshold is recorded as the foreground area, and the area composed of pixels in the gray image whose gray values are less than the partition threshold is recorded as the background area to obtain a binary image.

Among them, this embodiment adopts the average grayscale method to grayscale the current frame, and adopts the maximum inter-class variance method to binarize the grayscale image. The average grayscale method and the maximum inter-class variance method are both well-known technologies and will not be described in detail. On the basis of achieving the purpose of grayscale and binarization of the current frame, the implementer can adopt other methods of other existing technologies to grayscale and binarize the current frame, and this application does not make special restrictions.

At this point, the target area, background area, and foreground area of the current frame are obtained.

Step 2: Obtain the visual complexity index of the target area according to the number, number difference and position distribution of pixels in the foreground area and the background area of the target area.

According to the difference in the number of pixels in the foreground area and the background area of the target area, the segmentation difference of the target area is obtained. The segmentation difference of the target area is positively correlated with the difference in the number of pixels in the foreground area and the background area of the target area.

It can be understood that the positive correlation in this application refers to the relationship between the independent variable and the dependent variable. The positive correlation means that the independent variable increases (decreases) as the dependent variable increases (decreases), which can be an additive relationship, a multiplicative relationship, etc.

Preferably, as an embodiment of the present application, for the target area of the current frame, the ratio between the number of pixels in the target area in the foreground area and the number of pixels contained in the target area is recorded as the foreground area ratio; the ratio between the number of pixels in the background area of the target area and the number of pixels contained in the target area is recorded as the background area ratio; the absolute value of the difference between the foreground area ratio and the background area ratio is recorded as the segmentation difference degree of the target area.

The segmentation difference of the target area reflects the degree of confusion of the distribution of the foreground area and the background area in the target area. When the difference in the number of pixels in the foreground area and the background area in the target area is greater, the segmentation difference of the target area is greater.

Preferably, as another embodiment of the present application, the absolute value of the ratio of the foreground area ratio to the background area ratio is recorded as the segmentation difference of the target area.

The segmentation clutter of the target area is obtained according to the position distribution of the pixel points in the foreground area and the background area in the target area and the number of pixel points contained in the target area.

The grayscale run matrix algorithm is used for the binary image of the current frame contained in the target area to obtain the run matrix of the target area in the horizontal direction, and the run matrix of the target area in the horizontal direction is recorded as the horizontal run matrix of the target area. Half of the maximum run in the horizontal run matrix is recorded as a half run, and the run length less than the half run is recorded as a short run. The number of short runs with the same length as the short run in the horizontal run matrix is used as the weight of the short run, and the run length of each short run is weighted and summed. The ratio of the weighted sum value to the number of pixels contained in the target area is recorded as the segmentation clutter of the target area.

The visual complexity index of the target area reflects the continuity of the foreground area and the background area in the target area. When the irregularity of the distribution of the foreground area and the background area in the target area is greater, the number of short runs contained in the target area is greater, and the continuity of the foreground area and the background area in the target area is worse and the irregularity is stronger.

According to the segmentation difference and segmentation clutter of the target area, the visual complexity index of the target area is obtained, and the visual complexity index acquisition flow chart is shown in Figure 2. The visual complexity index of the target area is positively correlated with the segmentation difference and segmentation clutter of the target area.

Preferably, as an embodiment of the present application, the visual complexity index of the target area is the product of the segmentation difference and the segmentation clutter of the target area.

Preferably, as another embodiment of the present application, the visual complexity index of the target area is the sum of the segmentation difference and the segmentation clutter of the target area.

When the segmentation difference and segmentation clutter of the target area are greater, the visual complexity index of the target area is greater, the continuity of the distribution of the foreground area and the background area in the target area is worse, and the distribution is more chaotic.

According to the method for obtaining the visual complexity index of the target area, the visual complexity index of all areas of the current frame is obtained.

At this point, the visual complexity index of all regions of the current frame is obtained.

Step 3: Calculate the texture detail feature value of the target area based on the texture information of the pixel points in the neighborhood area of the edge pixel points of the current frame, obtain the contrast significance of the target area based on the distance between the central pixel points of all local areas in the current frame and the visual complexity index of all local areas in the current frame, and obtain the relative compensation requirement of the target area in combination with the texture detail feature value of the target area.

Use the Sobel operator on the grayscale image to obtain the edge pixels of the current frame. In the grayscale image of the current frame, calculate the texture feature value of each pixel. In the current frame, take the edge pixel as the center pixel, and record the window with the first preset threshold as the side length as the texture feature window of the center pixel. The average of the texture feature values of all pixels in the texture feature window of the edge pixel is taken as the texture feature value of the edge pixel. The average of the texture feature values of all edge pixels in the target area is recorded as the texture detail feature value of the target area.

Among them, this embodiment uses LBP eigenvalues as texture eigenvalues. As other implementation methods, on the basis of achieving the purpose of obtaining the texture eigenvalues of pixel points, the implementer can adopt other methods of the prior art to obtain the texture eigenvalues of pixel points, and this application does not make any special restrictions. Using the Sobel operator to obtain edge pixels is a well-known technology and will not be repeated here.

The texture detail eigenvalue of the target area measures the richness of the texture and the richness of the detail information inside the target area. When the texture detail eigenvalue of the target area is larger, the more microscopic detail information and structural changes there are in the target area, the richer the texture and the richer the detail information inside the target area, and in order to avoid the problem of detail information loss after backlight compensation, the target area has less demand for backlight compensation.

The contrast saliency of the target area is obtained according to the distance between the central pixels of all local areas in the current frame and the visual complexity index of all local areas in the current frame.

Get the central pixel points of all local areas in the current frame, calculate the Euclidean distance between the central pixel point of the target area and the central pixel point of each other local area in the current frame, and record the Euclidean distance as the first distance of the corresponding two areas. Calculate the ratio between the visual complexity index of the target area and the visual complexity index of each other local area in the current frame, and record the ratio as the first ratio of the corresponding two areas. The product of the first distance of the two areas and the first ratio is recorded as the first contrast of the two areas. The cumulative sum of the first contrast of the target area and each other local area in the current frame is recorded as the contrast significance of the target area.

The contrast saliency of the target region measures the visual importance of the target region relative to all regions in the current frame. When the contrast saliency of the target region is greater, the target region is more prominent visually, there is a higher contrast difference in light and dark, and the target region has a greater need for backlight compensation.

According to the texture detail feature value and contrast significance of the target area, the relative compensation requirement of the target area is obtained, and the relative compensation requirement acquisition flow chart is shown in Figure 3. The relative compensation requirement of the target area is positively correlated with the contrast significance of the target area, and negatively correlated with the texture detail feature value of the target area.

It can be understood that the positive correlation and negative correlation in this application refer to the relationship between the independent variable and the dependent variable. The positive correlation is that the independent variable increases (decreases) as the dependent variable increases (decreases), which can be an additive relationship, a multiplicative relationship, etc.; the negative correlation is that the independent variable decreases (increases) as the dependent variable increases (decreases), which can be an inverse relationship, a subtractive relationship, etc.

Preferably, as an embodiment of the present application, the relative compensation requirement of the target area is a ratio of the contrast significance of the target area to the texture detail feature value of the target area.

Preferably, as another embodiment of the present application, the relative compensation requirement of the target area is the difference between the contrast significance of the target area and the texture detail feature value of the target area.

When the contrast significance of the target area is smaller and the texture detail feature value of the target area is larger, the relative compensation requirement of the target area is smaller and the requirement of the target area for backlight compensation is smaller.

According to the method for obtaining the texture detail feature value of the target area, the texture detail feature values of all areas of the current frame are obtained.

At this point, the texture detail feature values of all regions of the current frame are obtained.

Step 4: Based on the difference in relative compensation requirements and contrast between the target area of the current frame and the previous frame adjacent to the current frame, obtain the inter-frame backlight adjustment degree of the target area in the current frame; based on the pixel values of all pixels of the target area in the previous adjacent frame, obtain the backlight brightness benchmark of the target area in the current frame; and based on the inter-frame backlight adjustment degree, obtain the backlight intensity of the target area in the current frame; based on the backlight intensity and backlight brightness benchmark of the target area in the current frame, obtain the backlight compensation result of the smart display in the target area.

The image frame immediately before the current frame is recorded as the previous adjacent frame. When the current frame is the first frame, there is no previous adjacent frame, and the following analysis cannot be performed, so the first frame of the display screen is not analyzed, that is, the first frame of the display screen is not backlight compensated.

The difference between the relative compensation requirements of the target area in the current frame and the previous adjacent frame is recorded as the relative compensation difference of the target area in the current frame.

When the relative compensation difference of the target area in the current frame is greater, the change in the backlight compensation demand of the target area between the current frame and the previous adjacent frame is greater, that is, the more significant the change in the backlight compensation demand of the target area between the current frame and the previous adjacent frame, the more it is necessary to adjust the degree of backlight compensation to help the human eye adapt to this change.

The difference between the contrast of the target area in the current frame and the previous adjacent frame is recorded as the contrast difference of the target area in the current frame.

This embodiment uses the extreme difference of the grayscale value contained in the target area as the contrast of the target area. On the basis of achieving the purpose of calculating the contrast of the target area, the implementer can use, for example, the LC significance algorithm to obtain the contrast of the target area, and this application does not impose any special restrictions.

When the contrast difference of the target area in the current frame is greater, the contrast change of the target area in the current frame and the previous adjacent frame is greater, and the degree of backlight compensation needs to be adjusted more to help the human eye adapt to this change.

According to the relative compensation difference and contrast difference of the target area in the current frame, the inter-frame backlight adjustment degree of the target area in the current frame is obtained. The inter-frame backlight adjustment degree of the target area in the current frame is positively correlated with the relative compensation difference and contrast difference of the target area in the current frame.

Preferably, as an embodiment of the present application, the inter-frame backlight adjustment degree of the target area in the current frame is the product of the relative compensation difference and the contrast difference of the target area in the current frame.

Preferably, as another embodiment of the present application, the inter-frame backlight adjustment degree of the target area in the current frame is the sum of the relative compensation difference and the contrast difference of the target area in the current frame.

When the relative compensation difference and contrast difference of the target area in the current frame are greater, the inter-frame backlight adjustment degree of the target area in the current frame is greater, and the degree of backlight compensation needs to be adjusted more to help the human eye adapt to this change.

At this point, the inter-frame backlight adjustment degree of the target area in the current frame is obtained.

The sum of the average and standard deviation of the pixel values of all pixels in the target area in the previous adjacent frame is recorded as the backlight brightness reference of the target area in the current frame. The backlight brightness reference of the target area in the current frame reflects the degree of backlight brightness that needs to be adjusted in the target area in the current frame.

The backlight intensity of the target area in the current frame is obtained according to the inter-frame backlight adjustment degree of the target area in the current frame and the backlight brightness reference.

The normalized value of the inter-frame backlight adjustment degree of the target area in the current frame is recorded as the first adjustment degree of the target area in the current frame, and the product of the backlight brightness benchmark, the first adjustment degree and the preset error adjustment parameter of the target area in the current frame is recorded as the backlight intensity of the target area in the current frame.

In this embodiment, the value of the preset error adjustment parameter is 1.5. As other implementation modes, the implementer can determine the value of the preset error adjustment parameter according to actual conditions.

The difference between the backlight intensity of the target area in the current frame and the backlight brightness reference of the target area in the current frame is used as the value of the backlight compensation amount of the target area in the display screen in the current frame to obtain the backlight compensation result of the target area in the display screen in the current frame.

According to the method for obtaining the backlight compensation amount of the target area in the current frame, the backlight compensation amount of each area in the display screen in the current frame is obtained, the backlight compensation of the display screen in the current frame is realized, and the backlight compensation result of the smart display screen is obtained.

The value of the backlight compensation amount of each area in the display screen in the current frame is the adjustment amount of the backlight compensation of the display screen in the current frame. The backlight compensation amount can enable the display screen to automatically adjust the screen brightness when displaying high-contrast and low-contrast images, reduce the viewer's eye fatigue, and at the same time, reduce the loss of details in the high-contrast part.

At this point, the backlight compensation result of the smart display is obtained.

Based on the same inventive concept as the above method, an embodiment of the present invention also provides a backlight compensation system for a smart display screen, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the steps of any one of the above-mentioned backlight compensation methods for a smart display screen are implemented.

Based on the same inventive concept as the above method, an embodiment of the present application also provides a backlight compensation display screen for a smart display screen, and the display screen is made by any of the above-mentioned backlight compensation methods for a smart display screen.

It is to be understood that the sequence of the embodiments of the present application described above is for description only and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of the present specification. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

The above content is only an implementation method of the present application and is not intended to limit the scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the protection scope of the present application.

Claims (9)

1. A backlight compensation method for a smart display screen, characterized in that the method comprises the following steps: Determine each local area of the current frame of the display screen, and take any local area as a target area; Obtaining a visual complexity index of the target area according to the number, number difference and position distribution of pixels belonging to the foreground area and the background area in the target area; In the current frame, a window with an edge pixel as the center and a first preset threshold as the side length is recorded as a texture feature window of the edge pixel; the average of the texture feature values of all pixels in the texture feature window of the edge pixel is taken as the texture feature value of the edge pixel; the average of the texture feature values of all edge pixels in the target area is recorded as the texture detail feature value of the target area; the contrast significance of the target area is obtained according to the distance between the central pixels of all local areas in the current frame and the visual complexity index of all local areas in the current frame, and the relative compensation demand of the target area is obtained in combination with the texture detail feature value of the target area; According to the difference in relative compensation requirements and contrast between the target area of the current frame and the previous frame adjacent to the current frame, the inter-frame backlight adjustment degree of the target area in the current frame is obtained, and the backlight brightness benchmark of the target area in the current frame is obtained according to the pixel values of all pixels contained in the previous adjacent frame of the target area. The backlight intensity of the target area in the current frame is obtained in combination with the inter-frame backlight adjustment degree. According to the backlight intensity of the target area in the current frame and the backlight brightness benchmark, the backlight compensation result of the target area of the smart display is obtained. 2. The backlight compensation method for a smart display screen according to claim 1, wherein the process of determining the visual complexity index of the target area is: For the target area of the current frame, the ratio between the number of pixels in the target area belonging to the foreground area and the number of pixels in the target area is recorded as the foreground area ratio; the ratio between the number of pixels in the background area and the number of pixels in the target area is recorded as the background area ratio; the absolute value of the difference between the foreground area ratio and the background area ratio is recorded as the segmentation difference degree of the target area; The run matrix of the target area in the horizontal direction is recorded as the horizontal run matrix of the target area, half of the maximum run in the horizontal run matrix is recorded as a half run, a run whose length is less than a half run is recorded as a short run, the number of short runs with the same length as the short run in the horizontal run matrix is used as the weight of the short run, the run lengths of each short run are weighted and summed, and the ratio of the weighted sum value to the number of pixels contained in the target area is recorded as the segmentation clutter of the target area; According to the segmentation difference and segmentation clutter of the target area, a visual complexity index of the target area is obtained, and the visual complexity index of the target area is positively correlated with the segmentation difference and segmentation clutter of the target area, respectively. 3. A backlight compensation method for a smart display screen according to claim 1, characterized in that the contrast significance of the target area is obtained according to the distance between the central pixels of all local areas in the current frame and the visual complexity index of all local areas in the current frame, and the specific process of obtaining is: Obtain the central pixel points of all regions in the current frame, calculate the Euclidean distance between the central pixel point of the target region and the central pixel point of each other local region in the current frame, and record the Euclidean distance as the first distance between the corresponding two regions; Calculate the ratio between the visual complexity index of the target area and the visual complexity index of each other local area in the current frame respectively, and record the ratio as the first ratio of the corresponding two areas; The product of the first distance and the first ratio of the two regions is recorded as the first contrast of the two regions, and the cumulative sum of the first contrast of the target region and each other local region in the current frame is recorded as the contrast significance of the target region. 4. The backlight compensation method for a smart display screen according to claim 1, wherein the relative compensation requirement of the target area is determined by: The ratio of the contrast saliency of the target area to the texture detail feature value of the target area is recorded as the relative compensation requirement of the target area. 5. A backlight compensation method for a smart display screen as claimed in claim 1, characterized in that the inter-frame backlight adjustment degree of the target area in the current frame is obtained according to the difference in relative compensation requirements and contrast between the target area in the current frame and the previous frame adjacent to the current frame, and the specific process of obtaining is: Record the previous adjacent image frame of the current frame as the previous adjacent frame; The difference between the relative compensation requirements of the target area of the current frame and the previous adjacent frame is recorded as the relative compensation difference of the target area in the current frame; the difference between the contrast of the target area of the current frame and the previous adjacent frame is recorded as the contrast difference of the target area in the current frame; According to the relative compensation difference and contrast difference of the target area in the current frame, the inter-frame backlight adjustment degree of the target area in the current frame is obtained, and the inter-frame backlight adjustment degree of the target area in the current frame is positively correlated with the relative compensation difference and contrast difference of the target area in the current frame. 6. A backlight compensation method for a smart display screen as claimed in claim 1, characterized in that the backlight brightness reference of the target area in the current frame is obtained according to the pixel values of all pixels contained in the target area in the previous adjacent frame, and the backlight intensity of the target area in the current frame is obtained in combination with the backlight adjustment degree between frames, and the specific process of obtaining is: The normalized value of the inter-frame backlight adjustment degree of the target area in the current frame is recorded as the first adjustment degree of the target area in the current frame, and the product of the backlight brightness benchmark, the first adjustment degree and the preset error adjustment parameter of the target area in the current frame is recorded as the backlight intensity of the target area in the current frame. 7. A backlight compensation method for a smart display screen as claimed in claim 1, characterized in that the backlight compensation result of the smart display screen in the target area is obtained according to the backlight intensity and backlight brightness reference of the target area in the current frame, and the specific process of obtaining is: The difference between the backlight intensity of the target area in the current frame and the backlight brightness reference of the target area in the current frame is used as the value of the backlight compensation amount of the target area in the display screen in the current frame to obtain the backlight compensation result of the target area in the display screen in the current frame. 8. A backlight compensation system for a smart display screen, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the method as described in any one of claims 1 to 7 when executing the computer program. 9. A backlight compensation display screen, characterized in that the backlight compensation of the display screen adopts the method described in any one of claims 1-7.