LED light point data extraction method and device and computer equipment

Abstract

This application relates to a method, apparatus, computer device, storage medium, and computer program product for extracting LED light point data. It includes acquiring image information from an LED display device, performing grayscale processing on the image information, and analyzing it to obtain bright spot information. Based on the bright spot information, the image information is filtered to determine the region boundary of the LED display device, and valid bright spot information within the region boundary is obtained. Based on the valid bright spot information, the data of each LED light point within the region boundary is analyzed. The LED display device includes LED light points. This application, by filtering the bright spot information, can calculate the region boundary of the LED display device, reducing errors in valid bright spot information. Therefore, based on the parallelism between the LED display device and the image acquisition device, it is not necessary to strictly limit the parallelism between the LED display device and the image acquisition device in the image frame, which can improve the convenience of LED light point identification.

Description

Technical Field

[0001] This application relates to the field of LED display technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for extracting LED light spot data. Background Technology

[0002] With the development of industrial integration, the manufacturing process of LED display devices has become increasingly precise, leading to the emergence of various methods for calibrating these devices. Calibration technology is a core technology in the LED display field, primarily used to correct the brightness of LED points on LED display devices, directly affecting the display effect. Calibration technologies include LED point identification technology, LED point brightness extraction technology, and luminance / color correction technology, among others. These technologies complement each other to achieve the calibration of LED display devices.

[0003] Traditional LED light spot recognition technology employs a large-scale law approach. This method selects a threshold, binarizes the light spot image, and then performs light spot detection calculations on the binarized image to locate the light spot. However, this method requires the LED display device to be parallel to the camera's imaging plane, and the LED display device must be perfectly aligned within the camera's view (i.e., the edge of the LED display device's light emission is parallel to the edge of the camera's imaging plane). Otherwise, calculation errors are likely to occur, requiring re-shooting and recalculation. In practical use, this method is demanding and inconvenient. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for extracting LED light spot data that can improve the convenience of LED light spot identification, in order to address the above-mentioned technical problems.

[0005] In a first aspect, this application provides a method for extracting LED light spot data, the method comprising:

[0006] Acquire image information from an LED display device, wherein the LED display device includes LED light points;

[0007] The image information is processed in grayscale to obtain the highlight information.

[0008] The image information is filtered based on the bright spot information to determine the area boundary of the LED display device, and the effective bright spot information within the area boundary is obtained.

[0009] Based on the effective highlight information, the data of each LED light point within the boundary of the area are obtained through analysis.

[0010] In one embodiment, the step of filtering the image information based on each of the bright spot information to determine the area boundary of the LED display device, and filtering out the valid bright spot information within the area boundary, includes:

[0011] Based on the bright spot information and the image information, the maximum light spot area is filtered to obtain the denoised image information;

[0012] Boundary detection is performed on the denoised image information to determine the region boundary of the LED display device;

[0013] The bright spot information is filtered based on the region boundary to obtain the valid bright spot information within the region boundary.

[0014] In one embodiment, after filtering the maximum light spot area based on each of the bright spot information and the image information to obtain denoised image information, and before performing boundary detection on the denoised image information to determine the area boundary of the LED display device, the method further includes:

[0015] The bright spot information in the denoised image information is smoothed to obtain smoothed denoised bright spot information;

[0016] Based on the smoothed denoised bright spot information, an erosion threshold is obtained, and the smoothed denoised bright spot information is eroded according to the erosion threshold to obtain eroded denoised bright spot information.

[0017] Based on the denoised bright spot information after erosion, dilation processing is performed to obtain dilated denoised bright spot information, and the dilated denoised bright spot information is used to update the denoised image information.

[0018] In one embodiment, the step of analyzing and obtaining data for each LED light point within the area boundary based on the effective bright spot information includes:

[0019] Based on the aforementioned valid bright spot information, empty points within the boundary of the region are determined;

[0020] Based on the empty points within the boundary of the area and the information of the effective bright spots, the LED lights are sorted to obtain the serial number of each LED light.

[0021] By combining the effective highlight information and the serial number of each LED light point, the data of each LED light point within the boundary of the area are obtained through analysis.

[0022] In one embodiment, determining the empty points within the region boundary based on the valid bright spot information includes:

[0023] Based on the aforementioned effective highlight information, the spacing between the light points is calculated;

[0024] The effective bright spot information is analyzed based on the light spot spacing and preset deflection angle to determine the empty spots within the boundary of the area.

[0025] In one embodiment, the step of performing grayscale processing on the image information and analyzing it to obtain the highlight information of the image information includes:

[0026] The image information is processed in grayscale, and a histogram is obtained by statistical analysis.

[0027] The histogram is smoothed to obtain a smoothed histogram;

[0028] The light spot threshold is obtained by analyzing the smooth histogram, and the bright spot information of the image information is obtained by identifying the bright spot based on the light spot threshold.

[0029] Secondly, this application also provides an LED light spot data extraction device, the device comprising:

[0030] An image acquisition module is used to acquire image information from an LED display device, the LED display device including LED lights;

[0031] The highlight analysis module is used to perform grayscale processing on the image information and analyze it to obtain the highlight information of the image information;

[0032] The highlight filtering module is used to filter the image information according to the highlight information, determine the area boundary of the LED display device, and filter out the valid highlight information within the area boundary;

[0033] The data extraction module is used to analyze and obtain the data of each LED light point within the boundary of the area based on the effective bright spot information.

[0034] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0035] Acquire image information from an LED display device, wherein the LED display device includes LED light points;

[0036] The image information is processed in grayscale to obtain the highlight information.

[0037] The image information is filtered based on the bright spot information to determine the area boundary of the LED display device, and the effective bright spot information within the area boundary is obtained.

[0038] Based on the effective highlight information, the data of each LED light point within the boundary of the area are obtained through analysis.

[0039] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0040] Acquire image information from an LED display device, wherein the LED display device includes LED light points;

[0041] The image information is processed in grayscale to obtain the highlight information.

[0042] The image information is filtered based on the bright spot information to determine the area boundary of the LED display device, and the effective bright spot information within the area boundary is obtained.

[0043] Based on the effective highlight information, the data of each LED light point within the boundary of the area are obtained through analysis.

[0044] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0045] Acquire image information from an LED display device, wherein the LED display device includes LED light points;

[0046] The image information is processed in grayscale to obtain the highlight information.

[0047] The image information is filtered based on the bright spot information to determine the area boundary of the LED display device, and the effective bright spot information within the area boundary is obtained.

[0048] Based on the effective highlight information, the data of each LED light point within the boundary of the area are obtained through analysis.

[0049] The aforementioned LED light point data extraction method, apparatus, computer equipment, computer-readable storage medium, and computer program product include acquiring image information from an LED display device, performing grayscale processing on the image information, and analyzing to obtain bright spot information from the image information. Based on the bright spot information, the image information is filtered to determine the region boundary of the LED display device, and valid bright spot information within the region boundary is obtained. Based on the valid bright spot information, data for each LED light point within the region boundary is analyzed. The LED display device includes LED light points. This application, by filtering the bright spot information, can calculate the region boundary of the LED display device, reducing errors in valid bright spot information. Therefore, based on the parallelism between the LED display device and the image acquisition device, it is not necessary to strictly limit the parallelism between the LED display device and the image acquisition device in the image frame, which can improve the convenience of LED light point recognition. Attached Figure Description

[0050] Figure 1 This is an application environment diagram of the LED light spot data extraction method in one embodiment;

[0051] Figure 2 This is a flowchart illustrating an LED light spot data extraction method in one embodiment;

[0052] Figure 3 This is a flowchart illustrating the steps of filtering image information based on each highlight information, determining the area boundary of the LED display device, and filtering out the valid highlight information within the area boundary in one embodiment.

[0053] Figure 4 This is a flowchart illustrating the steps of filtering image information based on each highlight information, determining the area boundary of the LED display device, and filtering out valid highlight information within the area boundary in another embodiment.

[0054] Figure 5 This is a flowchart illustrating the steps of analyzing and obtaining data for each LED light point within a region boundary based on valid highlight information in one embodiment.

[0055] Figure 6 This is a schematic diagram of the smoothing process in one embodiment;

[0056] Figure 7 This is a schematic diagram comparing a histogram and a smoothed histogram in one embodiment;

[0057] Figure 8 This is a flowchart illustrating the bright spot detection process in one embodiment;

[0058] Figure 9 This is a structural block diagram of an LED light spot data extraction device in one embodiment;

[0059] Figure 10 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0061] It is understood that the terms "first," "second," etc., used herein may be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another. For example, without departing from the scope of this application, a first resistor may be referred to as a second resistor, and similarly, a second resistor may be referred to as a first resistor. Both the first resistor and the second resistor are resistors, but they are not the same resistor.

[0062] It is understood that the term "connection" in the following embodiments should be understood as "electrical connection," "communication connection," etc., if the connected circuits, modules, units, etc., have electrical signal or data transmission with each other.

[0063] When used herein, the singular forms of “a,” “an,” and “the” may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising,” “including,” or “having,” etc., specify the presence of the stated feature, whole, step, operation, component, part, or combination thereof, but do not preclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts, or combinations thereof.

[0064] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0065] The LED light spot data extraction method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, the LED display device 100 is connected to the control system 108, the control system 108 is connected to the calibration calculation module 106, and the calibration calculation module 106 is connected to the image acquisition device 102 via the processor 104. The LED display device 100 is the device under test, and it includes an LED light panel with multiple LED dots. The image acquisition device 102 is correspondingly configured with the LED display device 100, ensuring that the LED display device 100 is within the acquisition range of the image acquisition device 102, and that the plane of the LED light panel of the LED display device 100 is parallel to the plane of the acquisition lens of the image acquisition device 102.

[0066] The control system 108 controls the driver module in the LED display device 100 to start, controlling the LEDs on the LED display device 100 to be in working state, causing the LED panel to emit light. The image acquisition device 102's acquisition lens acquires an image of the LED display device 100, which includes an image of the aforementioned emitting LED panel. The processor 104 acquires the image acquired by the image acquisition device 102, obtains the data of each LED in the image by executing the LED data extraction method, and transmits it to the correction calculation module 106. The correction calculation module 106 can calculate correction coefficients based on the LED data and transmit the correction coefficients to the control system 108. When performing display correction on the LED display device 100, the control system 108 can complete the display correction function based on the correction coefficients.

[0067] The control system 108, calibration calculation module 106, and processor 104 can be, but are not limited to, various personal computers, laptops, smartphones, and tablets, including chips with certain computing functions. In some application environments, the control system 108 may include a calibration calculation module. In other application environments, the control system 108, calibration calculation module, and processor 104 may also be a personal computer, laptop, smartphone, or tablet that includes a computing chip, with different running software in the computing chip used to execute the calculations of the control system 108, calibration calculation module 106, and processor 104. The image acquisition device 102 can be a camera, imager, or photosensor array, etc.

[0068] In one embodiment, such as Figure 2 As shown, a method for extracting LED light spot data is provided, which can be applied to... Figure 1 Taking processor 104 as an example, the explanation includes the following steps:

[0069] Step 202: Obtain image information from the LED display device.

[0070] The LED display device includes LED light points. When there are two or more LED light points, they form an LED light panel. The LED light panel is parallel to the plane of the image acquisition lens of the image acquisition device. That is, during the image acquisition process, the plane of the LED light panel of the LED display device is parallel to the plane of the image acquisition device's captured image. Specifically, the image acquisition device takes a picture of the LED display device to acquire its image information. The processor is connected to the image acquisition device and acquires the image information of the LED display device through the image acquisition device.

[0071] Step 204: Perform grayscale processing on the image information and analyze to obtain the highlight information of the image information.

[0072] Grayscale is a method of displaying images using black as a base color and varying shades of black. Grayscale processing is the process of converting a color image into a grayscale image. In grayscale processing, pixels in the image represent different shades of black based on their grayscale values.

[0073] Specifically, image information is processed to obtain grayscale image information. Highlight information can be obtained from the grayscale values ​​of each pixel within the grayscale image. For example, when the grayscale value of a pixel is greater than a set grayscale threshold, that pixel is marked as a highlight area. The grayscale value and location information of this highlight area are recorded and integrated into a single highlight information. Alternatively, the center of each highlight area can be selected, and its grayscale value and location information, along with the previously obtained highlight areas, can be integrated into a single highlight information.

[0074] Step 206: Filter the image information based on the information of each highlight to determine the area boundary of the LED display device, and filter out the valid highlight information within the area boundary.

[0075] Specifically, the obtained highlight information and image information are analyzed. The image information includes basic image information, such as the resolution of the image acquisition device, which is used to analyze the data of each highlight. Based on the above calculation and analysis of the highlight information and basic image information, the area boundary of the LED display device in the image information can be determined. The processor filters the highlights by determining whether the highlight information corresponding to each highlight belongs to the area boundary of the LED display device, removing the highlight information outside the area boundary of the LED display device, and obtaining the valid highlight information within the area boundary.

[0076] Optionally, the basic image information also includes the resolution of the LED panel in the LED display device. The resolution of the LED panel represents the maximum area that each LED can occupy in the image information, which is the maximum number of pixels. By analyzing the information of each bright spot in conjunction with the basic image information, valid bright spot information within the area boundary can be filtered.

[0077] Step 208: Based on the valid highlight information, analyze and obtain the data of each LED light point within the area boundary.

[0078] Specifically, the effective highlight information is analyzed and organized into data for each LED light point. The LED light point data includes the position information and brightness information of the LED light points, which facilitates the subsequent correction processing by the control system.

[0079] The aforementioned LED light point data extraction method includes acquiring image information from an LED display device, performing grayscale processing on the image information, and analyzing the bright spot information. Based on the bright spot information, the image information is filtered to determine the region boundary of the LED display device, and valid bright spot information within the region boundary is obtained. Based on the valid bright spot information, the data of each LED light point within the region boundary is analyzed. Here, the LED display device includes LED light points. This application, by filtering the bright spot information, can calculate the region boundary of the LED display device, reducing errors in valid bright spot information. Therefore, based on the parallelism between the LED display device and the image acquisition device, it is not necessary to strictly limit the parallelism between the LED display device and the image acquisition device in the image frame, which can improve the convenience of LED light point recognition.

[0080] In one embodiment, such as Figure 3 As shown, step 206 includes steps 302, 304 and 306.

[0081] Step 302: Based on the information of each highlight and the image information, the maximum light spot area is filtered to obtain the denoised image information.

[0082] The maximum LED dot area refers to the maximum number of pixels each LED dot can occupy in the image information. This maximum dot area can be calculated based on the resolution of the image acquisition device and the resolution of the LED panel. For example, if the resolution of the image acquisition device is CW×CH and the resolution of the LED panel is DW×DH, then the maximum dot area can be TW×TH.

[0083] TW = MIN(CW / DW, CH / DH)(1)

[0084] TH = TW(2)

[0085] In the above formula, CW is the horizontal resolution of the image acquisition device, CH is the vertical resolution of the image acquisition device, DW is the horizontal resolution of the LED light panel, DH is the vertical resolution of the LED light panel, TW is the horizontal resolution of the maximum light spot area, and TH is the vertical resolution of the maximum light spot area. MIN() represents finding the minimum value.

[0086] Because the aspect ratio of the image acquisition device's resolution is not necessarily equal to that of the LED light board's resolution, during calibration, the image is usually filled in one of the length or width directions, leaving a gap in the other direction. The aspect ratio of the image acquisition device's resolution (i.e., horizontal and vertical resolution) divided by the LED light board's resolution indicates the length and width occupied by a pixel when an LED light point on the LED light board is imaged in the image acquisition device. Since the light point is usually circular, the minimum aspect ratio (Equation 1) is taken as the length and width of the light point area (Equation 2). The positive direction pixel area formed by this light point area is the maximum light point area. This improves the accuracy of the calculated maximum light point area and facilitates subsequent processing.

[0087] Specifically, the maximum light spot area is calculated based on the basic image information. Each bright spot is then filtered based on this maximum area, removing those that do not conform to it, resulting in a denoised image. The filtering rule for the maximum area is as follows: the length and width data of each bright spot are obtained and compared with the maximum area. If the length and width of a bright spot are greater than the maximum area, the processor determines that the bright spot is not an LED light spot and may be noise generated by factors such as noise, poor contact, or light reflection. The processor then removes this bright spot and proceeds to the next, continuing this process until all bright spot information has been traversed. The remaining bright spots are then considered the denoised image.

[0088] Step 304: Perform boundary detection on the denoised image information to determine the area boundary of the LED display device.

[0089] Specifically, before performing boundary detection on the denoised image information, the denoised image information needs to be processed. This involves statistically analyzing the distribution of bright spots in the denoised image information according to their horizontal and vertical directions, obtaining horizontal and vertical bright spot distribution statistics. The horizontal bright spot distribution statistics are used to determine the left and right boundaries of the LED display device, while the vertical bright spot distribution statistics are used to determine the top and bottom boundaries of the LED display device.

[0090] Convolution calculations are performed on the statistical results of horizontal and vertical bright spot distributions respectively, and the resulting left-right and top-bottom boundaries are integrated into the region boundaries. For example, the edge detection module is called to perform convolution operations to identify the boundaries. The region boundaries of the LED display device are determined through convolution calculations.

[0091] Step 306: Filter the highlight information based on the region boundary to obtain the valid highlight information within the region boundary.

[0092] Specifically, the bright spot information is filtered based on the obtained area boundaries. The processor compares the location information of each bright spot with the area boundaries of the LED display device. When the location information of a bright spot is outside the area boundary, the bright spot is filtered out; when the location information of a bright spot is inside the area boundary, the bright spot is valid.

[0093] In this embodiment, the largest light spot area is filtered based on each bright spot information and image information to obtain denoised image information. Then, boundary detection is performed on the denoised image information to determine the area boundary of the LED display device. Bright spot information is filtered based on the area boundary to obtain valid bright spot information within the area boundary. By removing excessive noise and noise outside the area boundary of the LED display device, the bright spot information is accurately filtered, resulting in accurate and minimally erroneous valid bright spot information. This method can identify the area boundary of the LED display device, and even without strictly limiting the parallelism between the LED display device and the image acquisition device in the image frame, it can accurately distinguish bright spot information, remove noise errors, and improve the convenience and accuracy of LED light spot identification.

[0094] To avoid noise in the highlight information located near the area boundary of the LED light panel, which could lead to incorrect area boundary recognition of the LED light panel, in one embodiment, such as... Figure 4 As shown, after step 302 and before step 304, steps 402, 404 and 406 are also included.

[0095] Before step 402, the denoised image information needs to be processed. Specifically, the distribution of bright spots in the denoised image information is statistically analyzed according to the horizontal and vertical directions, resulting in horizontal and vertical bright spot distribution statistics. The horizontal bright spot distribution statistics are used to determine the left and right boundaries of the LED display device, while the vertical bright spot distribution statistics are used to determine the top and bottom boundaries of the LED display device.

[0096] Step 402: Smooth the bright spot information in the denoised image information to obtain smoothed denoised bright spot information.

[0097] Specifically, the statistical results of the horizontal and vertical bright spot distributions are smoothed separately. A smoothing kernel with a set radius is used to smooth the statistical results of the horizontal and vertical bright spot distributions separately, so that the data of the statistical results of the horizontal and vertical bright spot distributions are smoothed, avoiding the error in judging the area boundary of the LED light board due to the discontinuous brightness distribution of the bright spots.

[0098] Optionally, the smoothing kernel radius can be 3. The smoothing kernel radius can be adjusted when it is near the edge region to avoid the smoothing width exceeding the boundaries of the horizontal and vertical bright spot distribution statistics results.

[0099] For example, let the horizontal bright spot distribution statistics be HMY and the vertical bright spot distribution statistics be VMY, then the expression for smoothing is:

[0100]

[0101]

[0102] In the formula, n is the horizontal or vertical position of the reference point, and i is the radius of the smoothing kernel rounded down. Specifically, i is 0 at the boundary between SHY and SVY.

[0103] Step 404: Obtain the erosion threshold based on the smoothed denoised bright spot information, and perform erosion processing on the smoothed denoised bright spot information based on the erosion threshold to obtain the eroded denoised bright spot information.

[0104] Specifically, the average of the horizontal and vertical bright spot distribution statistics in the smoothed denoised bright spot information is calculated, and this average is used as the erosion threshold. The smoothed denoised bright spot information is then eroded using an erosion kernel with the same radius as the smoothing kernel. Let the erosion threshold be FTH, and the erosion result of the smoothed horizontal bright spot distribution statistics result SHY is denoted as FHY, and the erosion result of the smoothed vertical bright spot distribution statistics result SVY is denoted as FVY. The expression for the erosion process is then:

[0105]

[0106]

[0107] Step 406: Perform dilation processing on the denoised bright spot information after erosion to obtain dilated denoised bright spot information, and update the denoised image information with the dilated denoised bright spot information.

[0108] Specifically, based on the denoised bright spot information after erosion, dilation processing is performed. The dilated result of the statistical result of the horizontal bright spot distribution after erosion, FHY, is denoted as PHY, and the dilated result of the statistical result of the vertical bright spot distribution after erosion, FVY, is denoted as PVY. The dilation processing expression is:

[0109]

[0110]

[0111] In this embodiment, by performing smoothing, erosion, and dilation processing on the denoised image information before boundary detection, the bright spot information in the denoised image information is optimized. This is beneficial for accurately obtaining the region boundary of the LED display device during subsequent boundary detection. It reduces the error caused by noise in the bright spot information being located near the region boundary of the LED light board, which leads to incorrect identification of the region boundary of the LED light board. This is beneficial for accurately identifying the region boundary of the LED display device.

[0112] In one embodiment, such as Figure 5 As shown, step 208 includes steps 502, 504 and 506.

[0113] Step 502: Based on the valid bright spot information, determine the empty points within the region boundary.

[0114] A dead spot refers to a damaged LED in the LED light board. This damaged LED does not emit light when the LED display device is working, thus forming a dead spot.

[0115] Specifically, noise outside the area boundaries of the LED display device has been removed before obtaining valid bright spot information. However, there may also be empty spots within the area boundaries of the LED display device. In this case, the processor needs to exclude the empty spots within the area boundaries of the LED display device based on the valid bright spot information.

[0116] In one embodiment, step 502 includes steps 602 and 604.

[0117] Step 602: Calculate the spacing between light points based on the valid bright spot information.

[0118] Specifically, the initial point P is set as the effective bright spot information closest to the center point of the image captured by the image acquisition device. Then, the statistical results of the horizontal and vertical bright spot distributions are differentially processed according to requirements. Specifically, if the detection is in a horizontal state, the horizontal bright spot distribution statistical results are differentially processed; if the detection is in a vertical state, the vertical bright spot distribution statistical results are differentially processed. Taking the horizontal detection state as an example, the differential formula is as follows:

[0119] l=ABS(MY[n].px-MY[n-1].px) (9)

[0120] In the formula, l represents the horizontal distance between two adjacent valid bright spot information, ABS represents taking the absolute value, MY is the set of valid bright spot information, n is the selected valid bright spot information, and px is the horizontal coordinate of the valid bright spot information. At the same time, if it is in the vertical detection state, px in formula (9) can be replaced with py, where py represents the vertical coordinate of the valid bright spot information, and l represents the vertical distance between two adjacent valid bright spot information.

[0121] The values ​​of l obtained after differential processing are statistically analyzed, and the l with the most values ​​is selected as the lamp spacing L. If the lamp spacing obtained in the lateral detection state and the longitudinal detection state are different, the lateral lamp spacing LH and the longitudinal lamp spacing LV need to be recorded separately.

[0122] Step 604: Analyze the effective bright spot information based on the light spot spacing and preset deflection angle to determine the empty spots within the area boundary.

[0123] Specifically, the bright spots in the effective bright spot information are calculated and analyzed based on the light spot spacing and the preset deflection angle. The theoretical bright spot position is calculated based on the light spot spacing. The theoretical bright spot position is matched with the effective bright spot information. The theoretical bright spot position that does not match the effective bright spot information is determined as an empty point within the area boundary.

[0124] Optionally, when the matching rate between valid bright spot information and theoretical bright spot position is lower than a set matching threshold, the preset deflection angle is adjusted to a set precision. For example, if the set matching threshold is 90% and the set precision is 5°, when the matching rate between valid bright spot information and theoretical bright spot position is lower than 90%, the preset deflection angle of 0° is adjusted to 5° according to the set precision of 5°.

[0125] For example, taking the initial point P as the center, the position of each theoretical light point is found sequentially in all directions according to the light point spacing L (including the horizontal light point spacing LH and the vertical light point spacing LV). That is, taking the initial point P as the center, the search is performed to find whether there is a bright spot at the theoretical light point position. The search range is LH×LV. During the search, theoretical light points where there is no bright spot information at the theoretical light point position are marked as empty points.

[0126] Furthermore, since this application does not require strict limitation that the LED display device and the image acquisition device are parallel in the image frame, a preset deflection angle can be set to analyze the effective bright spot information when searching for the theoretical light spot position. Let the preset deflection angle be Φ, and the value of Φ can be 0°. If the current light spot position is CP, and the retrieved new theoretical light spot position is NP, the calculation expression is as follows:

[0127] NP.x=CP.x±LH×sinΦ (10)

[0128] NP.y=CP.y±LV×cosΦ (II)

[0129] In the formula, x represents the horizontal coordinate of the light point in the image information, and y represents the vertical coordinate of the light point in the image information. The deviation between the actual deflection angle and the preset deflection angle Φ cannot exceed atan(LV / LH) degrees.

[0130] The system traverses and searches the areas within the boundary of the LED display device where theoretical LED points might exist, identifying empty points within the boundary. This can be done by first searching horizontally and then vertically, or vice versa. The presence of bright spots within each theoretical LED point location determines whether it is an empty point.

[0131] Step 504: Sort each LED light point according to the information of empty points and valid bright points within the area boundary to obtain the serial number of each LED light point.

[0132] Specifically, based on the information of empty points and valid bright points within the area boundary, the empty points within the area boundary are excluded or marked, and the LED lights within the valid bright point information are sorted to obtain the serial number of each LED light.

[0133] For example, suppose the LEDS array includes light point position information and light point type information as: {y,x,row,col,flag}, where x and y represent the horizontal and vertical coordinates of the pixel position of the light point in the image, respectively, row represents the row number of the light point in the LED light board, col represents the column number of the light point in the LED light board, row and col are initialized to 0, and flag represents the current light point type, which can be either empty point (0) or light point (1).

[0134] Taking the initial point P as an example (Φ=0, LH=LV=L), first search for the light points horizontally, then search for the light points vertically, and record them in the light point array LEDS. Record the light point information of point P as col=0, row=0, flag=1. The x and y values ​​can be obtained from the effective light point information MY as px and py. In summary, the light point information of point P can be recorded as LEDS[0]={px,py,0,0,1}.

[0135] The search area for LED points cannot exceed the boundaries of the LED display device. Let the upper boundary of the LED display device be MU, the lower boundary be MD, the left boundary be ML, and the right boundary be MR. First, search in one direction, for example, searching for LED points to the right. The current LED point position CP = P, and the new LED point position NP is:

[0136] NP.x = CP.x + L

[0137] NP.y = CP.y

[0138] NP.col = CP.col + 1

[0139] NP.row = CP.row

[0140] Where the search range cannot exceed the right boundary of the LED display device, that is, NP.x < MR, otherwise end the search to the right. If searching to the left, the new light point NP is:

[0141] NP.x = CP.x - L

[0142] NP.y = CP.y

[0143] NP.col = CP.col - 1

[0144] NP.row = CP.row

[0145] Where the search range cannot exceed the left boundary of the LED display device, that is, NP.x > ML, otherwise end the search to the left.

[0146] In this order, traverse all the bright points in this row within the valid bright point information MY. If no bright point is found within the L×L range centered on the point NP, then this point is an empty point, and record it as LEDS[k] = {NP.x, NP.y, NP.row, NP.col, 0}, where k is a natural number. On the contrary, if a bright point is found, record LEDS[k] = {NP.x, NP.y, NP.row, NP.col, 1}. After completing the data recording of the new light point, assign the new light point to the old light point and continue to search for the next light point until the left or right boundary is retrieved and then end, obtaining all the points in the row where the initial point P is located recorded in the array LEDS, including light points and empty points.

[0147] Then search up and down. When searching up for sorting, the new light point NP is:

[0148] NP.x = CP.x

[0149] NP.y = CP.y - L

[0150] NP.col = CP.col

[0151] NP.row = CP.row - 1

[0152] Where the search range cannot exceed the upper boundary of the LED display device, that is, NP.y > MU, otherwise end the search up. If searching down, the new light point NP is:

[0153] NP.x = CP.x

[0154] NP.y = CP.y + 1

[0155] NP.col = CP.col

[0156] NP.row = CP.row + 1

[0157] The search range cannot exceed the lower boundary of the LED display device, that is, NP.x < MD, otherwise the downward search ends.

[0158] Furthermore, when any boundary in any direction of the found area boundary is an empty point, the area boundary of the LED display device is corrected again to further improve the accuracy of the area boundary of the LED display device.

[0159] Traverse the members of the LEDS array, find the minimum and maximum values of col and row and record them as MinCol (negative value), MaxCol (positive value), MinRow (negative value) and MaxRow (positive value), which are used to filter out the empty points at the boundary.

[0160] Left boundary filtering: Search for all points with col = MinCol in the LEDS. If these points are all empty points, then MinCol is incremented by 1, and the above steps are repeated until a non-empty point is found among the found points. At this time, MinCol is the left boundary of the light points.

[0161] Right boundary filtering: Search for all points with col = MaxCol in the LEDS. If these points are all empty points, then MaxCol is decremented by 1, and the above steps are repeated until a non-empty point is found among the found points. At this time, MaxCol is the right boundary of the light points.

[0162] Upper boundary filtering: Search for all points with row = MinRow in the LEDS. If these points are all empty points, then MinRow is incremented by 1, and the above steps are repeated until a non-empty point is found among the found points. At this time, MinRow is the upper boundary of the light points.

[0163] Lower boundary filtering: Search for all points with row = MaxRow in the LEDS. If these points are all empty points, then MaxRow is decremented by 1, and the above steps are repeated until a non-empty point is found among the found points. At this time, MaxRow is the lower boundary of the light points.

[0164] After correcting the area boundary of the LED display device, traverse the LED dot sorting array of all LED dots in the LEDS again. If the row and col in the LED dot sorting array exceed the area boundary of the LED display device, the LED dot sorting array is screened out and removed from the LEDS array. That is, when the condition row > MaxRow or row < MinRow or col > MaxCol or col < MinCol is satisfied, the LED dot sorting array is removed from the LEDS array. Finally, subtract MinCol from the col and subtract MinRow from the row of all the LED dot sorting arrays in the LEDS array. The obtained array set LEDS is the LED dot sorting result, including the serial numbers of each LED dot.

[0165] Step 506: Analyze and obtain the data of each LED dot within the area boundary by combining the valid bright dot information and the serial numbers of each LED dot.

[0166] Specifically, according to the serial numbers of each LED dot, associate the gray values in the valid bright dot information with the serial numbers of the LED dots and integrate them into the LED dot data.

[0167] The array set LEDS records the pixel positions of the image information of the dot and the empty dot and the dot positions on the lamp board. Calculate the brightness value of the dot according to the pixel position in the image information and the valid bright dot information in a specified manner. The specified manner can be to take the maximum gray value near the dot as the brightness value of the dot, or take the average gray value of the pixels above g% of the maximum gray value near the dot (g ranges from 0 to 100, and g = 75 is selected in this embodiment) as the brightness value of the dot. Traverse all members in the LEDS array according to the selected bright dot value calculation method, calculate the brightness value of each dot in turn, and integrate it into the dot data array LEDY in combination with the LEDS array, so that the LEDY array includes the dot positions (row, col) on the lamp board in the LEDS array and the brightness value LY. Each LED dot has a corresponding row and col position data and brightness value LY data.

[0168] In one embodiment, step 204 includes step 702, step 704, and step 706.

[0169] Step 702: Perform gray processing on the image information and statistically obtain a histogram.

[0170] Specifically, perform gray processing on the image information to obtain gray image information, and statistically process the gray values of each pixel point in the gray image information to obtain a histogram.

[0171] Optionally, if the light points in the grayscale image are too dense, causing them to merge and form patchy bright spots, an image opening operation needs to be performed on the grayscale image. Image opening involves sequentially performing erosion and dilation on the image information, which can eliminate small areas of high brightness without significantly changing the area of ​​other objects. After the image opening operation, the grayscale values ​​of each pixel in the grayscale image are statistically analyzed to obtain a histogram. The image opening operation can be repeated until the light points are no longer densely packed.

[0172] Step 704: Smooth the histogram to obtain a smoothed histogram.

[0173] Specifically, a smoothing kernel with a set radius is used to smooth the histogram, eliminating the influence of spikes and resulting in a smoothed histogram. Normally, the histogram curve obtained from image information should have two peaks and one trough. The two peaks represent the background area and the LED light point area of ​​the LED display device, respectively, while the trough between the two peaks is the distinction threshold between the background area and the LED light point area. However, due to the precision of the image acquisition equipment and the influence of the external environment, the histogram curve may exhibit abnormal fluctuations and lack smoothness, resulting in multiple troughs and affecting subsequent LED light point data extraction. Therefore, it is necessary to smooth the histogram curve to remove the influence of spikes and improve the accuracy of LED light point data extraction.

[0174] For example, suppose the statistical result in the obtained histogram is Y[n], where n is the gray value, and Y[n] represents the number of times a pixel with gray value n appears is Y. Taking a gray-level statistical length of 10 (i.e., ten different n's) and a smoothing kernel radius of 2 as an example, such as... Figure 6 As shown, the gray values ​​in the histogram statistics include ten values ​​from 0 to 9, and the smoothing kernel is represented by s. The statistical result of the gray values ​​in the smoothed histogram is then SY[n], and the calculation formula is:

[0175]

[0176] In the formula, SY[n] represents the statistical result of grayscale value n in the smoothing histogram, and m is the radius of the smoothing kernel. The radius of the smoothing kernel is adjusted at the edges of the histogram to ensure it does not exceed the statistical range of the histogram, i.e., the range of grayscale values ​​counted in the histogram. Therefore, special edge processing is performed on grayscale n in the regions [0, m-1] and [Max-m+1, Max]: m is temporarily assigned the value m = i (i ∈ [0, m-1]) or m = Max-i (i ∈ [Max-m+1, Max]). This means that the radius of the smoothing kernel decreases near the edge, ensuring the smoothed area does not exceed the upper and lower boundaries of the grayscale value, with a minimum value of 0 for m.

[0177] like Figure 6 As shown, when smoothing grayscale values ​​at the edges, the radius of the smoothing kernel decreases. For example, when smoothing the grayscale values ​​of 0 and 9, the radius of the smoothing kernel is 0, while when smoothing the grayscale values ​​of 1 and 8, the radius of the smoothing kernel is 1. A comparison of histograms and smoothed histograms is provided. Figure 7 As shown, where Figure 7 The left side shows the histogram without smoothing. Figure 7 The right side shows the smoothed histogram after smoothing. Smoothing removes the influence of spurious points and improves the accuracy of LED light point data extraction.

[0178] Step 706: Analyze the smooth histogram to obtain the light spot threshold, and perform bright spot recognition based on the light spot threshold to obtain the bright spot information of the image information.

[0179] The LED spot threshold is obtained by analyzing the smoothed histogram, and this threshold is used to distinguish between LED spot areas and background areas. Specifically, LED spot areas are identified and marked as bright spots. In particular, the statistical curves in the smoothed histogram are analyzed, and the gray values ​​corresponding to the peaks and troughs of the peak components in the background area and LED spot areas are used as the LED spot thresholds. Pixels with gray values ​​greater than the LED spot threshold are identified as bright spot areas, and the bright spot center is selected from these areas. The bright spot information includes both the bright spot area and the bright spot center.

[0180] For example, the trough is selected based on the following criteria:

[0181] SY[nk]≥SY[n] and SY[n+k]≥SY[n] and SY[n-k+1]≥SY[n] and SY[n+k-1]≥SY[n] and…SY[n-1]≥SY[n] and SY[n+1]≥SY[n].

[0182] Where SY[nk] represents the number of times the gray level appears at the k-th position to the left of the gray level n. The above determination is: the gray level n appears the least frequently within the range of ±k centered on gray level n, and is used to determine whether gray level n is a trough within its ±k range.

[0183] The processing flow for trough detection is similar to that of the smoothing process described above, except that the smoothing process is replaced by trough detection judgment. Here, k is the radius of the trough detection kernel. The boundary is specially handled by temporarily assigning k to k = i (i ∈ [0, k-1]) or k = Max-i (i ∈ [Max-k+1, Max]). That is, the smoothing width becomes smaller when it is close to the edge, so that the smoothing area does not exceed the upper and lower boundaries of gray level. The minimum value of k is 0. When k = 0, the detection result is invalid, that is, the detection results of minimum gray level and maximum gray level are invalid.

[0184] To prevent interference, the gray values ​​corresponding to all valleys are statistically analyzed and used as a pre-selected threshold PTH. The light spot threshold TH will be selected from the pre-selected thresholds. Specifically, when a gray value satisfies the valley condition, PTH[j] = n, and this is recorded as the pre-selected threshold. Here, j∈[0,Max], the initial value of j is 0, and the value of j is incremented by 1 each time a valley value is found, and n is the gray value corresponding to the detected valley. Subsequently, TH is selected from PTH, which can be based on the magnitude of the gray value, that is, the gray value closest to the average gray value in PTH is selected as the light spot threshold TH.

[0185] After determining the light spot threshold, bright spot identification is performed on the image information acquired by the image acquisition device. Bright spot identification is performed based on the gray value of the pixels in the image information, including: taking the pixels with gray values ​​greater than the light spot threshold as bright spot areas, and selecting the location of the largest gray value within the set bright spot area as the bright spot center.

[0186] A schematic diagram of the bright spot detection process is shown below. Figure 8 As shown, each square represents a bright spot area, with one square representing one pixel. The bright spot range is set to h=1. Pixels within this range are considered the detection area; edge points are invalid and not detected. For the detection points ( Figure 8 (a rectangle containing cross markers) and points within the detection area ( Figure 8 The grayscale value of the detection point (a rectangle containing a slash) is compared with the grayscale value of the detection point. If the grayscale value of the detection point is the largest value within the detection area and is greater than the light spot threshold TH, then the detection point is defined as the center of the bright spot. Figure 8 As shown, you can choose to traverse the bright area from left to right and from top to bottom to determine the center of the bright area, or you can choose other traversal methods to determine the center of the bright area.

[0187] The detection point is determined as the brightest point among pixels within a range of ±kx above and below the center (i.e., the defined bright spot range h). Pixels within the bright spot region are labeled IMG[px][py]. Pixels with values ​​greater than the light spot threshold are statistically analyzed, and the result is defined as MY[j]. The MY[j] array includes the pixel position and the pixel's grayscale value. The recognition condition expression is:

[0188] IMG[py][px]≥IMG[py-ky][px-kx] AND IMG[py][px]≥IMG[py-ky][px+kx] AND IMG[py][px]≥IMG[py-ky][px-kx+1] AND IMG[py][px]≥IMG[py-ky][px+kx-1] and IMG[py][px]≥IMG[py+ky][px+kx-1] and IMG[py][px]≥IMG[py+ky][px+kx]

[0189] Where py and px represent the x and y coordinates of the current detection point in the image information, and ky and kx represent half the width and half the height of the detection area, rounded down, corresponding to the defined bright spot range. When the bright spot detection condition is met, MY[j] = {py, px, IMG[py][px]} is calculated and recorded as bright spot information. Where j ∈ [0, Max], the initial value of j is 0, and the value of j is incremented by 1 each time a bright spot is found.

[0190] In this embodiment, a histogram is obtained by grayscale processing of the image information, followed by smoothing to obtain a smoothed histogram. A threshold for light spots is selected from the smoothed histogram, and bright spot identification is performed based on the threshold to obtain bright spot information. This accurate identification of bright spot information from the LED display device in the image information ensures accurate extraction of subsequent LED light spot data.

[0191] To better understand the above scheme, combined with Figure 1 The application scenario shown will be explained in detail below with reference to a specific embodiment. In one embodiment, the processor completes the LED light point data extraction method in 7 steps, including: histogram statistics, histogram smoothing, light point threshold calculation, bright spot identification, noise removal, light point sorting, and brightness extraction.

[0192] The processor acquires image information from the LED display device, performs grayscale processing on the image information, calculates a histogram, smooths the histogram to obtain a smoothed histogram, analyzes the smoothed histogram to obtain the lamp point threshold, and identifies bright spots based on the lamp point threshold to obtain the bright spot information of the image information. The processor completes the steps of histogram statistics, histogram smoothing, lamp point threshold calculation, and bright spot identification. The specific execution steps are described in detail above and will not be repeated here.

[0193] The noise removal step is used to remove noise outside the area boundaries of the LED display device. The processor filters the largest light spot area based on the bright spot information and image information to obtain denoised image information. The bright spot information in the denoised image information is then subjected to smoothing, erosion, and dilation processing in sequence, followed by boundary detection to determine the area boundaries of the LED display device. Based on the area boundaries, the bright spot information is filtered to obtain the effective bright spot information within the area boundaries.

[0194] The LED spot sorting and brightness extraction steps integrate the information of the LED spots, facilitating subsequent calibration of the LED display device. The processor calculates the spot spacing based on the effective bright spot information. It analyzes the effective bright spot information according to the spot spacing and preset deflection angle to identify empty spots within the area boundary. Based on the empty spots and effective bright spot information within the area boundary, each LED spot is sorted to obtain its serial number. Combining the effective bright spot information and the serial numbers of each LED spot, the data of each LED spot within the area boundary is analyzed.

[0195] In this embodiment, it is not necessary to strictly limit the parallelism between the LED display device and the image acquisition device in the image frame. Precise positioning of the LED dots can be achieved by determining the area boundaries of the LED display device. This eliminates large noise points and noise outside the area boundaries, ensuring accurate LED dot data and facilitating subsequent display calibration of the LED display device.

[0196] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0197] Based on the same inventive concept, this application also provides an LED light spot data extraction device for implementing the LED light spot data extraction method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the LED light spot data extraction device provided below can be found in the limitations of the LED light spot data extraction method described above, and will not be repeated here.

[0198] In one embodiment, such as Figure 9 As shown, an LED light spot data extraction device is provided, including: an image acquisition module 902, a bright spot analysis module 904, a bright spot filtering module 906, and a data extraction module 908, wherein:

[0199] Image acquisition module 902 is used to acquire image information of LED display device, which includes LED lights.

[0200] The highlight analysis module 904 is used to perform grayscale processing on image information and analyze the highlight information of the image information.

[0201] The highlight filtering module 906 is used to filter image information based on the highlight information, determine the area boundary of the LED display device, and filter out the valid highlight information within the area boundary.

[0202] The data extraction module 908 is used to analyze and obtain the data of each LED light point within the area boundary based on the effective bright spot information.

[0203] In one embodiment, the bright spot filtering module 906 is further configured to filter the largest light spot area based on the bright spot information and image information to obtain denoised image information. Boundary detection is performed on the denoised image information to determine the area boundary of the LED display device. Bright spot information is then filtered based on the area boundary to obtain valid bright spot information within the area boundary.

[0204] In one embodiment, the bright spot filtering module 906 is further configured to, after filtering the maximum light spot area based on each bright spot information and image information to obtain denoised image information, and before performing boundary detection on the denoised image information to determine the area boundary of the LED display device, smooth the bright spot information within the denoised image information to obtain smoothed denoised bright spot information. An erosion threshold is obtained based on the smoothed denoised bright spot information, and erosion processing is performed on the smoothed denoised bright spot information based on the erosion threshold to obtain eroded denoised bright spot information. Dilation processing is then performed based on the eroded denoised bright spot information to obtain dilated denoised bright spot information, and the dilated denoised bright spot information is used to update the denoised image information.

[0205] In one embodiment, the data extraction module 908 is further configured to determine empty points within the region boundary based on valid bright spot information. Based on the empty points and valid bright spot information within the region boundary, each LED light point is sorted to obtain its serial number. Combining the valid bright spot information and the serial numbers of each LED light point, the data for each LED light point within the region boundary is analyzed.

[0206] In one embodiment, the data extraction module 908 is further configured to calculate the light spot spacing based on the effective bright spot information. The effective bright spot information is analyzed based on the light spot spacing and a preset deflection angle to determine empty spots within the area boundary.

[0207] In one embodiment, the bright spot analysis module 904 is further configured to perform grayscale processing on the image information and obtain a histogram. The histogram is then smoothed to obtain a smoothed histogram. The smoothed histogram is analyzed to obtain a light spot threshold, and bright spot identification is performed based on the light spot threshold to obtain bright spot information from the image information.

[0208] Each module in the aforementioned LED light point data extraction device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0209] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 10 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for extracting LED light point data. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0210] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0211] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0212] Acquire image information from an LED display device, which includes LED lights;

[0213] The image information is processed in grayscale to obtain the highlight information.

[0214] The image information is filtered based on the information of each highlight to determine the area boundary of the LED display device, and the effective highlight information within the area boundary is obtained.

[0215] Based on the effective highlight information, the data of each LED light point within the area boundary is obtained through analysis.

[0216] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0217] Based on the bright spot information and image information, the largest light spot area is filtered to obtain denoised image information. Boundary detection is performed on the denoised image information to determine the area boundaries of the LED display device. Based on the area boundaries, bright spot information is filtered to obtain the effective bright spot information within the area boundaries.

[0218] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0219] The bright spots in the denoised image are smoothed to obtain smoothed denoised bright spots. An erosion threshold is then calculated based on the smoothed bright spots, and erosion is applied to the smoothed bright spots to obtain eroded bright spots. Finally, dilation is performed on the eroded bright spots to obtain dilated bright spots, which are then used to update the denoised image.

[0220] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0221] Based on the valid bright spot information, empty points within the area boundary are identified. According to the empty points and valid bright spot information within the area boundary, each LED light point is sorted to obtain its serial number. Combining the valid bright spot information and the serial numbers of each LED light point, the data for each LED light point within the area boundary is analyzed.

[0222] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0223] Based on the effective bright spot information, the spacing between light spots is calculated. The effective bright spot information is then analyzed based on the light spot spacing and the preset deflection angle to determine empty spots within the area boundary.

[0224] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0225] The image information is processed into grayscale, and a histogram is obtained. The histogram is then smoothed to obtain a smoothed histogram. The smoothed histogram is analyzed to obtain the light spot threshold, and bright spot identification is performed based on this threshold to obtain the bright spot information from the image.

[0226] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0227] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0228] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0229] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0230] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for extracting LED light spot data, characterized in that, The method includes: Acquire image information from an LED display device, wherein the LED display device includes LED light points; The image information is processed in grayscale to obtain the highlight information. The image information is filtered based on the bright spot information to determine the area boundary of the LED display device, and the effective bright spot information within the area boundary is obtained. Based on the aforementioned effective highlight information, the data of each LED light point within the boundary of the region are analyzed and obtained; The step of analyzing and obtaining data for each LED light point within the boundary of the region based on the effective bright spot information includes: Based on the effective bright spot information, empty points within the boundary of the region are determined; Based on the empty points within the boundary of the area and the information of the effective bright spots, the LED lights are sorted to obtain the serial number of each LED light. By combining the effective highlight information and the serial number of each LED light point, the data of each LED light point within the boundary of the area is obtained through analysis. The step of determining empty points within the region boundary based on the valid bright spot information includes: Based on the aforementioned effective highlight information, the spacing between the light spots is calculated; The effective bright spot information is analyzed based on the light spot spacing and preset deflection angle to determine the empty spots within the boundary of the area; The step of analyzing the effective bright spot information based on the light spot spacing and preset deflection angle to determine the empty spots within the region boundary includes: The theoretical bright spot position is calculated based on the light spot spacing. The theoretical bright spot position is matched with the effective bright spot information. The theoretical bright spot position that does not match the effective bright spot information is determined as an empty point within the area boundary. When the matching rate between the effective bright spot information and the theoretical bright spot position is lower than a set matching threshold, the preset deflection angle is adjusted with a set precision.

2. The method according to claim 1, characterized in that, The step of filtering the image information based on each of the bright spot information to determine the area boundary of the LED display device and filtering out the valid bright spot information within the area boundary includes: Based on the bright spot information and the image information, the maximum light spot area is filtered to obtain the denoised image information; Boundary detection is performed on the denoised image information to determine the region boundary of the LED display device; The bright spot information is filtered based on the region boundary to obtain the valid bright spot information within the region boundary.

3. The method according to claim 2, characterized in that, After filtering the maximum light spot area based on the bright spot information and the image information to obtain denoised image information, and before performing boundary detection on the denoised image information to determine the area boundary of the LED display device, the method further includes: The bright spot information in the denoised image information is smoothed to obtain smoothed denoised bright spot information; Based on the smoothed denoised bright spot information, an erosion threshold is obtained, and the smoothed denoised bright spot information is eroded according to the erosion threshold to obtain eroded denoised bright spot information. Based on the denoised bright spot information after erosion, dilation processing is performed to obtain dilated denoised bright spot information, and the dilated denoised bright spot information is used to update the denoised image information.

4. The method according to claim 1, characterized in that, The grayscale processing of the image information and the analysis to obtain the highlight information of the image information include: The image information is processed in grayscale, and a histogram is obtained by statistical analysis. The histogram is smoothed to obtain a smoothed histogram; The light spot threshold is obtained by analyzing the smooth histogram, and the bright spot information of the image information is obtained by identifying the bright spot based on the light spot threshold.

5. An LED light spot data extraction device, characterized in that, The device includes: An image acquisition module is used to acquire image information from an LED display device, the LED display device including LED lights; The highlight analysis module is used to perform grayscale processing on the image information and analyze it to obtain the highlight information of the image information; The highlight filtering module is used to filter the image information according to the highlight information, determine the area boundary of the LED display device, and filter out the valid highlight information within the area boundary; The data extraction module is used to analyze and obtain the data of each LED light point within the boundary of the area based on the effective bright spot information; The data extraction module is also used to determine empty points within the boundary of the region based on the effective bright spot information; Based on the empty points within the boundary of the area and the information of the effective bright spots, the LED lights are sorted to obtain the serial number of each LED light. By combining the effective highlight information and the serial number of each LED light point, the data of each LED light point within the boundary of the area is obtained through analysis. The data extraction module is also used to calculate the spacing between light points based on the effective bright spot information; The effective bright spot information is analyzed based on the light spot spacing and preset deflection angle to determine the empty spots within the boundary of the area; The data extraction module is further configured to calculate the theoretical bright spot position based on the light spot spacing, match the theoretical bright spot position with the effective bright spot information, and determine the theoretical bright spot position that does not match the effective bright spot information as an empty point within the region boundary; wherein, when the matching rate between the effective bright spot information and the theoretical bright spot position is lower than a set matching threshold, the preset deflection angle is adjusted with a set precision.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images