Light bead identification method, device, equipment and medium

CN122820830APending Publication Date: 2026-09-25JIANGMEN SIYU TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610963182.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-06-30
Publication Date
2026-09-25

AI Technical Summary

Technical Problem

传统的人工识别方法效率低下且容易出错

Benefits of technology

[0005]根据本申请第一方面实施例的灯珠识别方法,至少具有如下有益效果:通过低亮/高亮帧差分生成前景掩膜然后进行按位或处理,有效抑制背景干扰,在常规现场光照条件下检测成功率大幅提高。此外,通过使用标准格雷码,仅需少数帧即可完成识别动作,编码效率高,无需大量的数据,地址唯一性与准确率显著提升,相较于现有技术中的深度学习模型识别,在保证识别准确性的同时降低数据计算量,有效降低灯珠识别成本。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122820830A_ABST
    Figure CN122820830A_ABST
Patent Text Reader

Abstract

The application discloses a lamp bead recognition method, device, equipment and medium, which is applied to an LED lamp group. The lamp bead recognition method comprises the following steps: acquiring a first video image of the LED lamp group; dividing the first video image into a plurality of image frames, calculating the average brightness of all the image frames, and taking the frame with the maximum average brightness as an anchor point frame; calculating an inter-frame step length according to the video frame rate of the first video image and the flicker frequency of the LED lamp group; calculating a key frame sequence according to the inter-frame step length, the anchor point frame and the first video image; calculating a mask image between two frames according to the full-bright frame and the full-dark frame; calculating the key frame sequence based on the mask image to obtain a lamp point list corresponding to each key frame in the key frame sequence, and taking the lamp point list corresponding to the full-bright frame as a reference point set; and pairing and recognizing the reference point set and the lamp point list corresponding to all the gray code coding frames to determine the positions of the lamp beads in the LED lamp group.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of LED bead recognition technology, and in particular to an LED bead recognition method, device, equipment, and medium. Background Technology

[0002] LED light clusters consist of numerous LEDs connected by specific wiring. During production, quality inspection, or after-sales maintenance, it's necessary to quickly locate LEDs with specific numbers or verify the correct wiring of the entire light board. Traditional manual identification methods are inefficient and prone to errors. Related technologies use random binary encoding to drive the LED cluster to blink and acquire multiple blinking images. A deep learning model then performs multi-target detection on these images to obtain the LED's position and on / off state. This data is accumulated into a binary array, and the LED number is retrieved by looking up a table. However, training deep learning models requires massive amounts of precisely labeled training data, resulting in high setup and maintenance costs, large model size, and slow inference speed, making them unsuitable for direct deployment in lightweight embedded devices or production environments. Summary of the Invention

[0003] This application provides a method, apparatus, device, and medium for identifying LED beads. By using image processing, encoding, and automatic keyframe extraction, LED light points can be accurately located, effectively reducing the cost of LED bead identification.

[0004] In a first aspect, embodiments of this application provide a method for identifying LED beads, applied to LED light groups, including: Acquire the first video image of the LED light group; The first video image is divided into multiple image frames, the average brightness of all image frames is calculated, and the frame with the highest average brightness is taken as the anchor frame. The inter-frame step size is calculated based on the video frame rate of the first video image and the flashing frequency of the LED light group; Based on the inter-frame step size, the anchor frame, and the first video image, a key frame sequence is calculated, wherein the key frame sequence includes at least one fully bright frame, at least one fully dark frame, and multiple Gray code encoded frames. Calculate the mask image between the two frames based on the fully bright frame and the fully dark frame; The keyframe sequence is calculated based on the mask image to obtain a list of light points corresponding to each keyframe in the keyframe sequence, and the list of light points corresponding to the fully lit frame is used as a reference point set. The position of each LED bead in the LED group is determined by pairing and identifying the reference point set with the list of LED dots corresponding to all Gray code encoded frames.

[0005] The LED bead recognition method according to the first aspect of this application has at least the following advantages: by generating a foreground mask through low-brightness / high-brightness frame difference and then performing bitwise OR processing, background interference is effectively suppressed, and the detection success rate is significantly improved under normal ambient lighting conditions. Furthermore, by using standard Gray code, the recognition action can be completed with only a few frames, resulting in high encoding efficiency, requiring no large amount of data, and significantly improving address uniqueness and accuracy. Compared to deep learning model recognition in the prior art, this method reduces the amount of data computation while ensuring recognition accuracy, effectively reducing the cost of LED bead recognition.

[0006] According to some embodiments of the first aspect of this application, dividing the first video image into multiple image frames and calculating the average brightness of all image frames includes: The first video image is divided into multiple image frames, and the first color intensity, second color intensity, and third color intensity in the image frames are obtained. The average brightness of the image frame is obtained by weighting the first color intensity, the second color intensity, and the third color intensity.

[0007] According to some embodiments of the first aspect of this application, calculating the inter-frame step size based on the video frame rate of the first video image and the flicker frequency of the LED light group includes: The inter-frame step size is obtained by dividing the product of the video frame rate of the first video image and the flashing frequency of the LED group by a preset parameter.

[0008] According to some embodiments of the first aspect of this application, calculating the mask image between two frames based on the fully bright frame and the fully dark frame includes: Calculate the absolute difference image between the two frames based on the fully bright frame and the fully dark frame; The absolute difference image is converted into a grayscale image and the pixels are flipped to obtain a grayscale processed image; The grayscale image is binarized and flipped based on a fixed threshold to obtain a mask image, wherein the background and non-LED regions in the mask image are marked as 0.

[0009] According to some embodiments of the first aspect of this application, the step of calculating the keyframe sequence based on the mask image to obtain a list of light points corresponding to each keyframe in the keyframe sequence includes: The mask image is bitwise ORed with each keyframe in the keyframe sequence to obtain the processed image. The processed image is segmented by color thresholding to obtain a binary image; The binary image is subjected to morphological opening and area filtering to obtain a spot image; Connected component analysis and speckle algorithm are used to extract bright spot regions in the light spot image, and the centroid coordinates of each bright spot region are calculated to form the light spot list of the key frame.

[0010] According to some embodiments of the first aspect of this application, the step of pairing and identifying the reference point set with the list of light points corresponding to all Gray code encoded frames to determine the position of each LED bead in the LED light group includes: Assign a Gray code bit array of length equal to the number of Gray code encoded frames to each reference point in the reference point set; The list of lights corresponding to the Gray code encoded frame is matched with the set of reference points using a greedy nearest neighbor method. For each reference point that is successfully matched, the on / off state of the corresponding light in the Gray code encoded frame is marked in its corresponding Gray code bit array to obtain the Gray code sequence accumulated for each reference point. The position of each LED bead in the LED group is determined based on the Gray code sequence.

[0011] According to some embodiments of the first aspect of this application, determining the position of each LED bead in the LED group based on the Gray code sequence includes: The Gray code sequence is converted into a binary sequence and the decimal address value is calculated to determine the control address and physical location of each LED bead in the LED light group.

[0012] Secondly, embodiments of this application provide an operation control device for implementing the LED bead identification method as provided in the first aspect embodiment.

[0013] Thirdly, embodiments of this application provide an electronic device including the operation control device provided in the second aspect of the embodiments above.

[0014] Fourthly, embodiments of this application also provide a computer-readable storage medium storing computer-executable instructions for causing a computer to perform the LED identification method as described in the first aspect embodiment above.

[0015] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the description, claims and drawings. Attached Figure Description

[0016] The accompanying drawings are provided to further understand the technical solutions of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the technical solutions of the present invention, and do not constitute a limitation on the technical solutions of the present invention.

[0017] Figure 1 A detailed flowchart of a lamp bead identification method provided in an embodiment of this application; Figure 2 for Figure 1 The detailed flowchart of step S500; Figure 3 for Figure 1 The detailed flowchart of step S600; Figure 4 for Figure 1 The detailed flowchart of step S700; Figure 5 This is a schematic diagram of the structure of an operation control device provided in an embodiment of this application. Detailed Implementation

[0018] 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.

[0019] It is understandable that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, or the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0020] LED light clusters consist of numerous LEDs connected by specific wiring. During production, quality inspection, or after-sales maintenance, it's necessary to quickly locate LEDs with specific numbers or verify the correct wiring of the entire light board. Traditional manual identification methods are inefficient and prone to errors. Related technologies use random binary encoding to drive the LED cluster to blink and acquire multiple blinking images. A deep learning model then performs multi-target detection on these images to obtain the LED's position and on / off state. This data is accumulated into a binary array, and the LED number is retrieved by looking up a table. However, training deep learning models requires massive amounts of precisely labeled training data, resulting in high setup and maintenance costs, large model size, and slow inference speed, making them unsuitable for direct deployment in lightweight embedded devices or production environments.

[0021] Based on this, embodiments of this application provide a method, apparatus, device, and medium for LED bead identification. By generating a foreground mask through low-brightness / high-brightness frame differential analysis followed by OR processing, background interference is effectively suppressed, significantly improving the detection success rate under normal ambient lighting conditions. Furthermore, by using standard Gray code, the identification process can be completed with only a few frames, resulting in high encoding efficiency, eliminating the need for large amounts of data, and significantly improving address uniqueness and accuracy. Compared to deep learning model identification in existing technologies, this method reduces data computation while maintaining identification accuracy, effectively lowering the cost of LED bead identification.

[0022] Firstly, referring to Figure 1 , Figure 1 A flowchart illustrating a method for identifying LED beads provided in this application includes, but is not limited to, the following steps: Step S100: Acquire the first video image of the LED light group; Step S200: Divide the first video image into multiple image frames, calculate the average brightness of all image frames, and take the frame with the highest average brightness as the anchor frame. Step S300: Calculate the inter-frame step length based on the video frame rate of the first video image and the flicker frequency of the LED light group; Step S400: Calculate the keyframe sequence based on the inter-frame step size, anchor frame, and the first video image; Step S500: Calculate the mask image between two frames based on the fully bright frame and the fully dark frame; Step S600: Calculate the key frame sequence based on the mask image to obtain the list of light points corresponding to each key frame in the key frame sequence, and use the list of light points corresponding to the fully lit frame as the reference point set. Step S700: Match and identify the reference point set with the list of lamp points corresponding to all Gray code encoded frames to determine the position of each lamp bead in the LED group.

[0023] Understandably, if it is necessary to locate each LED bead on the LED light group, the LED light group can be controlled to light up randomly or in a preset lighting sequence. Then, an image acquisition device can be used to acquire the first video image of the LED light group during the lighting process. Since the first video image consists of multiple image frames, it can be divided into multiple image frames. Then, the average brightness of all image frames can be calculated, and the frame with the highest average brightness can be used as the anchor frame. The anchor frame can be used as the first image frame for subsequent processing to achieve anchor point positioning of the first video image. Since there is a frequency difference between the video frame rate and the flicker frequency of the LED light group, the inter-frame step size can be calculated based on the video frame rate of the first video image and the flicker frequency of the LED light group. Then, based on the inter-frame step size, the anchor frame, and the first video image, the key frames in the first video image can be calculated. The key frames are image frames in the first video image that have the same flicker frequency as the LED light group. The key frame sequence includes at least one fully lit frame, at least one fully extinguished frame, and multiple Gray code encoded frames. For example, with an inter-frame step size of 3, if the first frame in the keyframe sequence is the anchor frame, then the second frame in the keyframe sequence is the image frame obtained by adding 3 to the anchor frame in the first video image. Next, a mask image is calculated between the two frames based on the fully lit and fully dark frames. Then, based on the mask image, the keyframe sequence is calculated to obtain the list of light points corresponding to each keyframe. The list of light points corresponding to the fully lit frames is used as a reference point set. A mask image is generated by differentiating low-brightness / high-brightness frames and then processed on all keyframes. This effectively suppresses background interference and improves the detection success rate under normal ambient lighting conditions. Finally, the reference point set is paired with the list of light points corresponding to all Gray code encoded frames to determine the position of each LED in the LED group.

[0024] It should be noted that after dividing the first video image into multiple image frames, the first color intensity, second color intensity, and third color intensity of each image frame can be obtained. Then, the first color intensity, second color intensity, and third color intensity are weighted and calculated to obtain the average brightness of the image frame. For example, using... Calculate the average brightness, where, Average brightness The first color intensity, The second color intensity, The intensity of the third color.

[0025] It should be noted that the inter-frame step size can be obtained by dividing the product of the video frame rate of the first video image and the flicker frequency of the LED light group by a preset parameter. For example, using... Calculate the inter-frame step size. The inter-frame step size, The video frame rate of the first video image. The flashing frequency of the LED light group is 1000, which is a preset parameter. The preset parameter can be adjusted according to the actual use situation, and this application does not make specific limitations.

[0026] Reference Figure 2 , Figure 2 for Figure 1 The detailed flowchart of step S500 includes, but is not limited to, the following steps: Step S510: Calculate the absolute difference image between two frames based on the fully bright frames and the fully dark frames; Step S520: Convert the absolute difference image to a grayscale image and perform pixel flipping to obtain a grayscale processed image; Step S530: The grayscale image is binarized and flipped based on a fixed threshold to obtain a mask image.

[0027] Understandably, in an absolute difference image, the pixel differences in the background region are very small, while the LED light spot region, due to the drastic brightness change from "off" to "on," has a large difference value. Therefore, the absolute difference image between two frames can be calculated to identify the background region. This absolute difference image is then converted to a grayscale image and pixel inversion is performed, making the originally bright LED light spot region black and the background region brighter. Next, a fixed threshold is used to binarize the grayscale image, setting regions below the threshold (i.e., LED light spot regions) to 0 and regions above the threshold (i.e., background regions) to 255. Finally, inversion is performed again to obtain the mask image. In the mask image, all possible bright areas of the LED light spot are marked as foreground, while background and non-LED regions are marked as background. For example, in the mask image, the background and non-LED regions are marked as 0.

[0028] Reference Figure 3 , Figure 3 for Figure 1 The detailed flowchart of step S600 includes, but is not limited to, the following steps: Step S610: Perform a bitwise OR operation between the mask image and each keyframe in the keyframe sequence to obtain the processed image. Step S620: Perform color thresholding on the processed image to obtain a binary image; Step S630: Perform morphological opening operation and area filtering on the binary image to obtain the spot image; Step S640: Connected component analysis and speckle algorithm are used to extract bright spot regions in the light spot image, and the centroid coordinates of each bright spot region are calculated to form a list of light spots for key frames.

[0029] Understandably, by performing a bitwise OR operation between the mask image and each keyframe in the keyframe sequence, background interference can be suppressed, making the LED beads in the processed image stand out for easier subsequent processing. Then, color thresholding is performed on the processed image to obtain a binary image retaining the LED bead regions. Morphological opening and area filtering are then performed on the binary image to remove connected regions with excessively large or small pixel areas, resulting in a spot image. Finally, connected component analysis and spot detection algorithms are performed on the bright spot regions (LED bead regions) in the spot image. For each identified bright spot region, its centroid coordinates are calculated and used as a candidate light point on that frame image. The centroid coordinates of all bright spot regions in the spot image are used to form the light point list for the keyframe.

[0030] It should be noted that for very close bright spot areas in the spot image (e.g., less than 3 pixels apart), they can be merged and their average coordinates can be taken as the final centroid coordinates.

[0031] Reference Figure 4 , Figure 4 for Figure 1 The detailed flowchart of step S700 includes, but is not limited to, the following steps: Step S710: Assign a Gray code bit array with a length equal to the number of Gray code encoded frames to each reference point in the reference point set. Step S720: Perform greedy nearest neighbor matching between the list of lights corresponding to the Gray code encoded frame and the set of reference points. For reference points that are successfully matched, mark the on / off state of the corresponding light in the Gray code encoded frame in the Gray code bit array to obtain the Gray code sequence accumulated for each reference point. Step S730: Determine the position of each LED bead in the LED group according to the Gray code sequence.

[0032] Understandably, we can first assign a Gray code bit array of length equal to the number of Gray code encoded frames to each reference point in the reference point set. In this step, all bits of the Gray code bit array are 0. The number of Gray code encoded frames is determined by the number of LEDs. For example, if there are 8 LEDs, the number of Gray code encoded frames is 3 (8 logarithm to base 2 is 3), meaning that three Gray code encodings are sufficient to identify all LEDs. Then, we perform a greedy nearest neighbor matching between the list of LEDs corresponding to the Gray code encoded frames and the reference point set. For reference points that successfully match, we mark the on / off state of the corresponding LED in the Gray code encoded frame in its corresponding Gray code bit array, thus obtaining the accumulated Gray code sequence for each reference point (LED). A successfully matched reference point indicates that it is "on" in the current m-th frame. Then, the m-th position of the Gray code bit array corresponding to that reference point is set to 1. For example, with a total of 8 LEDs, according to the above calculation, it takes 3 Gray code encoding frames to complete the encoding. Assume the corresponding 3 frame patterns are as follows: Frame 1 (highest bit): Lights 1-4 are off (0), lights 5-8 are on (1); Frame 2 (middle position): Lights 1-2: off, Lights 3-4: on, Lights 5-6: off, Lights 7-8: on; Frame 3 (lowest bit): Lights 1, 4, 5, 8: off; Lights 2, 3, 6, 7: on.

[0033] First, initialize 8 arrays of length 3 for the 8 lights, and fill them with 0, such as [0,0,0]. In frame 1: lights 1-4 are dark (0), lights 5-8 are bright (1). Compare this with the fully lit frame to see if any of the points in frame 1 exist in the fully lit frame. For example, lights 1-4 are not present, so the first element of the array for lights 1-4 remains 0. Lights 5-8 are bright, so they can be found in the fully lit frame, and the first element of the array for lights 5-8 is filled with 1. The same applies to subsequent frames. After processing the first frame, the Gray code sequence changes as follows: Light 1: [0, , ]; Light 5: [1, , ]; after processing the second frame, the Gray code sequence changes as follows: Light 1: [0,0, ]; Light 3: [0,1, ]; Light 5: [1,0, ]; Light 7: [1,1, ]; after processing the second frame, the Gray code sequence changes as follows: Light 1: [0,0,0]; Light 2: [0,0,1]; Light 3: [0,1,1]; Light 4: [0,1,0]; Light 5: [1,0,0]; Light 6: [1,0,1]; Light 7: [1,1,1]; Light 8: [1,1,0]. Finally, we can get: Lamp 1:000, Lamp 2:001, Lamp 3:011, Lamp 4:010, Lamp 5:100, Lamp 6:101, Lamp 7:110, Lamp 8:111.

[0034] It should be noted that by converting the Gray code sequence corresponding to each LED bead into a binary sequence and calculating the decimal address value, the control address and physical location of each LED bead in the LED group are determined. The controller can then control the working state of the corresponding LED bead based on the control address.

[0035] It should be noted that due to factors such as shooting environment (obstruction, overexposure, slight motion blur, etc.), some points may be missed in the final identification. Therefore, all control addresses can be grouped according to the physical location of the LED beads, and the physical distance between consecutively numbered beads can be calculated. Then, the number of control addresses in each group can be used for completion or deduplication. For deduplication, the control addresses of LED beads whose physical distance between adjacent LED beads is less than a preset distance can be merged. For completion, if some LED beads are already in a group, the physical coordinates and control addresses of the missing LED beads are generated around these existing LED beads by random offset or based on an average step size model. If there are no detected LED beads in the group, but there are LED beads in the groups before and after it, the physical coordinates of the LED beads before and after it are used to calculate the physical coordinates and control addresses of the missing LED beads in the group by linear interpolation. If the group is missing and only the preceding group has data, the physical coordinates and control addresses of the missing LED beads are completed by inertial prediction from the physical coordinates of the LED beads in the previous group using an average step size.

[0036] Secondly, referring to Figure 5 This application provides an operation control device 500, including a memory 510, a processor 520, and a computer program stored in the memory 510 and executable on the processor 520. The processor 520 executes the program to implement the LED bead identification method of the first aspect embodiment above, for example, executing... Figure 1 Method steps S100 to S700 in the text Figure 2 Method steps S510 to S530, Figure 3 Method steps S610 to S640 and Figure 4 Method steps S710 to S730.

[0037] The memory 510, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs, such as the LED identification method in the above embodiments of this application. The processor 520 implements the LED identification method in the above embodiments of this application by running the non-transitory software program and instructions stored in the memory 510.

[0038] The memory 510 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data required for executing the LED identification method in the above embodiments. Furthermore, the memory 510 may include high-speed random access memory 510, and may also include non-transitory memory 510, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. It should be noted that the memory 510 may include remotely located memories 510 relative to the processor 520, and these remote memories 510 can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0039] Thirdly, embodiments of this application provide a diagnostic electronic device, which includes an operation control device 500 as described in the second aspect embodiment. This device generates a foreground mask through low-brightness / high-brightness frame differential analysis and then performs OR processing, effectively suppressing background interference and significantly improving the detection success rate under normal ambient lighting conditions. Furthermore, by using standard Gray code, the recognition action can be completed with only a few frames, resulting in high encoding efficiency, eliminating the need for large amounts of data, and significantly improving address uniqueness and accuracy. Compared to deep learning model recognition in existing technologies, this approach reduces data computation while ensuring recognition accuracy, effectively lowering the cost of LED bead recognition.

[0040] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions for causing a computer to perform the LED identification method of the first aspect embodiment above, for example, executing... Figure 1 Method steps S100 to S700 in the text Figure 2 Method steps S510 to S530, Figure 3 Method steps S610 to S640 and Figure 4The method steps S710 to S730 are described above. Those skilled in the art will understand that all or some of the steps and systems disclosed in the above methods can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all physical components can be implemented as processors, such as central processing units, digital signal processors, or microprocessors executing software, or as hardware, or as integrated circuits, such as application-specific integrated circuits. Such software can be distributed on a computer-readable medium, which can include computer storage media or non-transitory media and communication media or transient media. As is known to those skilled in the art, computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc DVD or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information transmission medium.

[0041] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0042] The above is a detailed description of the preferred embodiments of this application. However, this application is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A method for identifying LED beads, characterized in that, Applications in LED lighting systems include: Acquire the first video image of the LED light group; The first video image is divided into multiple image frames, the average brightness of all image frames is calculated, and the frame with the highest average brightness is taken as the anchor frame. The inter-frame step size is calculated based on the video frame rate of the first video image and the flashing frequency of the LED light group; Based on the inter-frame step size, the anchor frame, and the first video image, a key frame sequence is calculated, wherein the key frame sequence includes at least one fully bright frame, at least one fully dark frame, and multiple Gray code encoded frames. Calculate the mask image between the two frames based on the fully bright frame and the fully dark frame; The keyframe sequence is calculated based on the mask image to obtain a list of light points corresponding to each keyframe in the keyframe sequence, and the list of light points corresponding to the fully lit frame is used as a reference point set. The position of each LED bead in the LED group is determined by pairing and identifying the reference point set with the list of LED dots corresponding to all Gray code encoded frames.

2. The LED bead identification method according to claim 1, characterized in that, The step of dividing the first video image into multiple image frames and calculating the average brightness of all image frames includes: The first video image is divided into multiple image frames, and the first color intensity, second color intensity, and third color intensity in the image frames are obtained. The average brightness of the image frame is obtained by weighting the first color intensity, the second color intensity, and the third color intensity.

3. The LED bead identification method according to claim 1, characterized in that, The step of calculating the inter-frame step size based on the video frame rate of the first video image and the flicker frequency of the LED light group includes: The inter-frame step size is obtained by dividing the product of the video frame rate of the first video image and the flashing frequency of the LED group by a preset parameter.

4. The LED bead identification method according to claim 1, characterized in that, The step of calculating the mask image between two frames based on the fully bright frame and the fully dark frame includes: Calculate the absolute difference image between the two frames based on the fully bright frame and the fully dark frame; The absolute difference image is converted into a grayscale image and the pixels are flipped to obtain a grayscale processed image; The grayscale image is binarized and flipped based on a fixed threshold to obtain a mask image, wherein the background and non-LED regions in the mask image are marked as 0.

5. The LED bead identification method according to claim 1, characterized in that, The step of calculating the keyframe sequence based on the mask image to obtain a list of light points corresponding to each keyframe in the keyframe sequence includes: The mask image is bitwise ORed with each keyframe in the keyframe sequence to obtain the processed image. The processed image is segmented by color thresholding to obtain a binary image; The binary image is subjected to morphological opening and area filtering to obtain a spot image; Connected component analysis and speckle algorithm are used to extract bright spot regions in the light spot image, and the centroid coordinates of each bright spot region are calculated to form the light spot list of the key frame.

6. The LED bead identification method according to claim 1, characterized in that, The step of matching and identifying the reference point set with the list of light points corresponding to all Gray code encoded frames to determine the position of each LED in the LED group includes: Assign a Gray code bit array of length equal to the number of Gray code encoded frames to each reference point in the reference point set; The list of lights corresponding to the Gray code encoded frame is matched with the set of reference points using a greedy nearest neighbor method. For each reference point that is successfully matched, the on / off state of the corresponding light in the Gray code encoded frame is marked in its corresponding Gray code bit array to obtain the Gray code sequence accumulated for each reference point. The position of each LED bead in the LED group is determined based on the Gray code sequence.

7. The LED bead identification method according to claim 6, characterized in that, Determining the position of each LED bead in the LED group based on the Gray code sequence includes: The Gray code sequence is converted into a binary sequence and the decimal address value is calculated to determine the control address and physical location of each LED bead in the LED light group.

8. An operation control device, characterized in that, The device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the LED identification method as described in any one of claims 1 to 7.

9. An electronic device, characterized in that, Includes the operation control device as described in claim 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions for causing a computer to perform the LED identification method as described in any one of claims 1 to 7.