LED lighting intelligent control system and method

Abstract

The present invention relates to an LED lighting intelligent control system and method, and relates to the field of lighting control, including: receiving a real-time image of a preset area taken by an Internet of Things sensor; receiving a regional target image of the preset area; performing feature comparison between the target image and the real-time image to obtain brightness and color deviation distribution information; sorting areas where the brightness deviation or color deviation exceeds a threshold to obtain a lighting deviation area; performing control optimization on the lighting deviation area to obtain a three-color light brightness percentage; initializing a dimming drive power supply according to the three-color light brightness percentage to control an LED light strip. The present application solves the technical problem in the prior art that the LED lighting control response time is prolonged and cannot meet the needs of fast response scenes, and achieves the technical effect of quickly identifying abnormal lighting areas and performing real-time precise control through feature comparison.

Description

Technical Field

[0001] The present invention relates to the field of lighting control, and in particular to an intelligent control system and method for LED lighting. Background Art

[0002] With the continuous expansion of LED lighting application scenarios, higher requirements are placed on the real-time and accuracy of LED lighting control. At present, LED lighting control mainly relies on machine vision models for scene recognition and lighting parameter adjustment. However, machine vision models require a long computing time when performing image processing, resulting in a long response delay from detecting an abnormality to executing control. It usually takes several seconds or even longer to complete the entire control process. This response delay is difficult to meet application requirements in some scenarios with high real-time requirements, such as stage lighting and real-time live broadcasts. Therefore, the existing LED lighting control response time is extended and cannot meet the needs of fast response scenarios. Summary of the invention

[0003] The present invention aims to solve the technical problem in the prior art that the response time of LED light regulation is prolonged and cannot meet the requirements of rapid response scenes, and provides an LED light intelligent control system and method to solve the problem.

[0004] The technical solution of the present invention to solve the above technical problems is as follows:

[0005] In a first aspect, the present invention provides an LED lighting intelligent control system, comprising: an image acquisition module, for receiving a regional real-time image taken by an Internet of Things sensor of a preset area after the LED light strip is started, wherein the Internet of Things sensor is deployed at a fixed position in the preset area; a target image receiving module, for receiving a regional target image of the preset area, wherein the regional target image and the regional real-time image have coordinate consistency; an image feature comparison module, for performing feature comparison on the regional target image and the regional real-time image to obtain brightness deviation distribution information and color deviation distribution information; a deviation area sorting module, for performing feature comparison on the regional target image and the regional real-time image to obtain brightness deviation distribution information and color deviation distribution information; and a deviation area sorting module, for sorting the regional target image based on the brightness deviation distribution information and the color deviation distribution information. The color deviation distribution information sorts the areas where the brightness deviation is greater than or equal to the brightness deviation threshold, or the color deviation is greater than or equal to the color deviation threshold, to obtain the light deviation area, wherein the light deviation area has a target brightness identifier and / or a target color identifier; a light optimization control module is used to perform light control optimization on the light deviation area according to the target brightness identifier and / or the target color identifier to obtain the red light brightness percentage, the blue light brightness percentage and the green light brightness percentage; a drive power control module is used to initialize the dimming drive power according to the red light brightness percentage, the blue light brightness percentage and the green light brightness percentage to control the LED light strip in the light deviation area.

[0006] In a second aspect, the present invention provides an LED lighting intelligent control method, comprising: when the LED light strip is started, receiving a regional real-time image taken by an Internet of Things sensor of a preset area, wherein the Internet of Things sensor is deployed at a fixed position of the preset area; receiving a regional target image of the preset area, wherein the regional target image and the regional real-time image have coordinate consistency; performing feature comparison on the regional target image and the regional real-time image to obtain brightness deviation distribution information and color deviation distribution information; based on the brightness deviation distribution information and the color deviation distribution information, sorting areas where the brightness deviation is greater than or equal to the brightness deviation threshold, or the color deviation is greater than or equal to the color deviation threshold, to obtain a light deviation area, wherein the light deviation area has a target brightness identifier and / or a target color identifier; according to the target brightness identifier and / or the target color identifier, performing light control optimization on the light deviation area to obtain a red light brightness percentage, a blue light brightness percentage and a green light brightness percentage; initializing a dimming drive power supply according to the red light brightness percentage, the blue light brightness percentage and the green light brightness percentage to control the LED light strip in the light deviation area.

[0007] In a third aspect, the present application provides an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is used to execute an LED lighting intelligent control system provided by the present application.

[0008] The beneficial effects of the present invention are:

[0009] After the LED light strip is started, the image acquisition module receives the real-time image of the preset area taken by the IoT sensor. The IoT sensor is deployed at a fixed position in the preset area to realize real-time monitoring of the target area. The target image receiving module receives the regional target image of the preset area. The target image has coordinate consistency with the regional real-time image, providing a standard reference for the lighting effect. The image feature comparison module compares the regional target image with the regional real-time image to obtain brightness deviation distribution information and color deviation distribution information, and quickly identifies the difference between the actual lighting effect and the target effect. The deviation area sorting module is based on the above deviation distribution information. Select the area where the brightness deviation is greater than or equal to the brightness deviation threshold, or the color deviation is greater than or equal to the color deviation threshold, and obtain the light deviation area, which has the target brightness mark and / or the target color mark, and accurately locates the specific area that needs to be adjusted; the light optimization control module performs light control optimization on the light deviation area according to the target brightness mark and / or the target color mark, obtains the red light brightness percentage, the blue light brightness percentage and the green light brightness percentage, and calculates the optimal light parameters; the driving power control module initializes the dimming driving power according to the above RGB brightness percentage, controls the LED light strip in the light deviation area, and performs the actual light adjustment operation. By using feature comparison to replace the traditional machine vision model, the response time is shortened, and the rapid and precise control of LED lights is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of the structure of an LED lighting intelligent control system provided by the present invention;

[0011] Figure 2 A schematic diagram of a flow chart of an LED lighting intelligent control method provided by the present invention;

[0012] Figure 3 A schematic diagram of the structure of an electronic device provided by the present invention;

[0013] Figure 4 A schematic structural diagram of an LED lighting assembly provided by the present invention.

[0014] In the accompanying drawings, the components represented by the reference numerals are as follows:

[0015] Image acquisition module 11, target image receiving module 12, image feature comparison module 13, deviation area sorting module 14, lighting optimization control module 15, driving power control module 16, electronic device 200, memory 210, processor 220, first computer program 211. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0017] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0018] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0019] Embodiment 1:

[0020] like Figure 1 As shown, an embodiment of the present invention provides an LED lighting intelligent control system, which is communicatively connected with an LED lighting component and an Internet of Things sensor. The LED lighting component includes an LED light strip and a dimming drive power supply.

[0021] Specifically, the LED lighting intelligent control system establishes a communication connection with the LED lighting components and the IoT sensor through a communication interface. The LED lighting components include LED light strips and dimming drive power supplies, such as Figure 4 As shown, the LED light strip adopts a two-color light strip structure, and is connected to a dimming drive power supply through a dimming color adjustment drive and a live and neutral line. The dimming drive power supply is used to receive control instructions and adjust the light-emitting state of the LED light strip accordingly.

[0022] LED lighting intelligent control system includes:

[0023] The image acquisition module 11 is used to receive a real-time image of a preset area taken by an Internet of Things sensor after the LED light strip is started, wherein the Internet of Things sensor is deployed at a fixed position in the preset area.

[0024] Specifically, the image acquisition module 11 is used to collect real-time image data of a preset area. In specific implementation, the IoT sensor is installed in a fixed manner in the preset area, for example, it is installed in a position such as a ceiling, a wall or a column. When the LED light strip starts working, the IoT sensor continues to collect images of the preset area within its coverage. The image acquisition module 11 receives the collected image information in real time through the data interface, obtains a real-time image of the area, and provides basic data support for subsequent image processing and lighting control.

[0025] The target image receiving module 12 is used to receive the regional target image of the preset area, wherein the regional target image and the regional real-time image have coordinate consistency.

[0026] Specifically, the target image receiving module 12 is used to obtain an ideal lighting effect image of a preset area. In practical applications, the target image receiving module 12 receives regional target images pre-stored by the system or uploaded by the user through a data interface. These regional target images represent the lighting effects expected to be achieved in the preset area, including target brightness distribution and color distribution.

[0027] In order to ensure the accuracy of subsequent image comparison, the system has unified the coordinate systems of the regional target image and the real-time image. Specifically, whether it is the regional real-time image collected by the IoT sensor or the regional target image received by the system, the same coordinate mapping method is used to ensure that the position of each pixel in the image corresponds one to one. For example, if the field of view of the IoT sensor is 120 degrees and the shooting distance is 3 meters, the pixel coordinates of the regional target image are mapped to the actual space according to the same proportional relationship. This coordinate consistency design lays the foundation for subsequent feature comparison and lighting control.

[0028] The image feature comparison module 13 is used to perform feature comparison on the regional target image and the regional real-time image to obtain brightness deviation distribution information and color deviation distribution information.

[0029] Specifically, the image feature comparison module 13 is used to analyze the difference between the regional target image and the regional real-time image. The image feature comparison module 13 uses fast feature comparison, which can identify abnormal areas more quickly than traditional machine vision analysis methods.

[0030] In the specific implementation, the input data of the image feature comparison module 13 is the regional target image and the regional real-time image, and the two have the same size and pixel coordinates. The image feature comparison module 13 first normalizes the two images to ensure that the pixel values ​​fall within a unified range, which is convenient for subsequent comparison. Next, the image feature comparison module 13 adopts a pixel-by-pixel comparison strategy, extracts the brightness value and RGB color value of the corresponding pixel on the regional target image and the regional real-time image for each pixel position, and calculates the difference between the two to characterize the brightness deviation and color deviation at the pixel position. After completing the pixel-by-pixel comparison, the image feature comparison module 13 generates a brightness deviation map and a color deviation map with the same size as the original image. The value at each pixel position in the deviation map represents the brightness deviation value and color deviation value of the original two images at this position. The larger the deviation value, the larger the deviation of the image at this position. Afterwards, the image feature comparison module 13 performs binarization processing on the brightness deviation map and the color deviation map. The pixel position with a deviation value greater than the set threshold is marked as 1, indicating that the brightness or color at the position is abnormal; the pixel position with a deviation value less than or equal to the threshold is marked as 0, indicating that the brightness and color at the position are normal. After the binarization process, a binary image matrix representing the brightness deviation distribution and color deviation distribution is obtained as the brightness deviation distribution information and color deviation distribution information.

[0031] Through the image feature comparison module 13, the deviation comparison between the regional target image and the regional real-time image can be completed accurately and efficiently, so as to prepare for the subsequent deviation area positioning and lighting control.

[0032] The deviation area sorting module 14 is used to sort the areas where the brightness deviation is greater than or equal to the brightness deviation threshold, or the color deviation is greater than or equal to the color deviation threshold based on the brightness deviation distribution information and the color deviation distribution information, to obtain the light deviation area, wherein the light deviation area has a target brightness identification and / or a target color identification.

[0033] Specifically, the input data of the deviation area sorting module 14 is the brightness deviation distribution information and color deviation distribution information output by the image feature comparison module 13, which is used to sort out the areas where the brightness deviation is greater than or equal to the brightness deviation threshold, or the color deviation is greater than or equal to the color deviation threshold, and output them as light deviation areas.

[0034] First, the deviation area sorting module 14 traverses the input brightness deviation distribution information, finds out the pixel positions where the brightness deviation is greater than or equal to the brightness deviation threshold, and marks these positions as candidate brightness deviation areas. Similarly, the deviation area sorting module 14 traverses the color deviation distribution information, finds out the pixel positions where the color deviation is greater than or equal to the color deviation threshold, and marks them as candidate color deviation areas. Then, the deviation area sorting module 14 merges the candidate brightness deviation area and the candidate color deviation area to obtain a complete light deviation area. The light deviation area contains all pixel positions where the brightness deviation or color deviation exceeds the corresponding threshold. These pixel positions indicate the areas in the regional real-time image that are significantly different from the regional target image, and subsequent light adjustment is required. In addition, the deviation area sorting module 14 extracts the brightness value and color value of the corresponding position of the light deviation area from the regional target image as the target brightness mark and target color mark of the light deviation area. These target brightness marks and target color marks represent the ideal state of the light deviation area in terms of brightness and color, and provide optimization targets for subsequent light adjustment.

[0035] Through the deviation area sorting module 14, according to the comparison of the brightness deviation threshold and the color deviation threshold and the merging of the candidate areas, the light deviation areas with large brightness deviation or color deviation are accurately sorted out from the real-time image of the entire area, and the corresponding target brightness mark and target color mark are extracted, laying the foundation for realizing accurate local light adjustment.

[0036] The lighting optimization control module 15 is used to perform lighting control optimization on the lighting deviation area according to the target brightness identifier and / or the target color identifier to obtain the red light brightness percentage, the blue light brightness percentage and the green light brightness percentage.

[0037] Specifically, the lighting optimization control module 15 performs lighting control optimization on the lighting deviation area according to the target brightness identification and / or target color identification output by the deviation area sorting module 14, thereby obtaining the red light brightness percentage, blue light brightness percentage and green light brightness percentage of the corresponding area, and providing control parameters for subsequent lighting adjustment.

[0038] First, the lighting optimization control module 15 determines the optimization target of the lighting deviation area in terms of brightness according to the target brightness mark, that is, adjusts the overall brightness of the area to be consistent with the target brightness mark. At the same time, the lighting optimization control module refers to the target color mark to determine the optimization target of the lighting deviation area in terms of color, that is, adjusts the color of the area to be consistent with the target color mark. After clarifying the optimization targets of brightness and color, the lighting optimization control module 15 uses an intelligent algorithm to find the optimal red light, blue light, and green light ratio scheme, so that while meeting the brightness requirements, the color is as close to the target color mark as possible. Specifically, the lighting optimization control module 15 performs an optimization search in the value space of the percentage of red light, blue light, and green light brightness, and finds a set of percentage combinations so that the brightness and color after mixing are closest to the target mark. Among them, the search process can adopt an intelligent optimization algorithm, such as a genetic algorithm, a particle swarm algorithm, etc., to improve the optimization efficiency and result quality. The result of the optimization is a set of optimal red light brightness percentage, blue light brightness percentage, and green light brightness percentage values, which represent the specific control parameters for adjusting the brightness and color of the lighting deviation area. The lighting optimization control module 15 outputs these percentage parameters for the driving power control module 16 to perform subsequent lighting adjustments.

[0039] Through the lighting optimization control module 15, using the target brightness identifier and the target color identifier, the optimal RGB ratio scheme is found for each lighting deviation area, while ensuring that the brightness meets the standard, the regional color is optimized to the maximum extent, thereby achieving accurate local lighting control.

[0040] The driving power supply control module 16 is used to initialize the dimming driving power supply according to the red light brightness percentage, the blue light brightness percentage and the green light brightness percentage, and control the LED light strip in the light deviation area.

[0041] Specifically, the driving power control module 16 is responsible for receiving the red light brightness percentage, blue light brightness percentage and green light brightness percentage output by the lighting optimization control module 15, and initializing the dimming driving power supply according to these parameters, thereby achieving precise control of the LED light strip within the lighting deviation area.

[0042] First, the driving power control module 16 calculates the corresponding red, blue and green driving current values ​​according to the percentage of red light brightness, blue light brightness and green light brightness. Since the brightness of the LED light strip is proportional to the driving current, the color and brightness of the LED light strip can be accurately controlled by adjusting the driving current of each color channel. Then, the driving power control module 16 sends the calculated red, blue and green driving current values ​​to the dimming driving power supply to initialize the configuration. The dimming driving power supply usually adopts a constant current driving circuit, and accurately controls the current flowing through each color channel of the LED light strip according to the input current value, thereby adjusting the brightness and color of the LED light strip. After completing the initialization of the dimming driving power supply, the driving power control module 16 sends a start instruction to it, so that it starts to drive the LED light strip according to the set current value. Due to the deviation area sorting and light optimization control in the early stage, the current combination output by the dimming driving power supply can accurately match the brightness and color requirements of each light deviation area, so as to achieve highly customized local light control. After the LED light strip receives the driving current from the dimming driver, the red, blue and green LEDs inside it will emit light according to the corresponding brightness ratio, together forming a light output that meets the expected brightness and color requirements, completing the precise correction of the lighting deviation area.

[0043] By driving the power control module 16, the dimming driving power is initialized and controlled to achieve precise adjustment of the LED light strip in the light deviation area, so that its brightness and color are consistent with or close to the target mark, completing the entire intelligent control process, realizing rapid identification of abnormal lighting areas and real-time precise regulation.

[0044] Furthermore, the image feature comparison module includes the following execution steps:

[0045] Performing image multi-value processing on the regional target image to obtain a first multi-value matrix;

[0046] Performing image multi-value processing on the real-time image of the region to obtain a second multi-value matrix;

[0047] The first multi-valued matrix and the second multi-valued matrix are compared to obtain the brightness deviation distribution information and the color deviation distribution information.

[0048] In a feasible implementation manner, the image feature comparison module 13 uses a comparison method based on image multi-value processing when performing feature comparison on the regional target image and the regional real-time image to obtain brightness deviation distribution information and color deviation distribution information.

[0049] Specifically, the image feature comparison module 13 first performs image multi-value processing on the regional target image and converts it into a first multi-value matrix. The so-called image multi-value processing refers to quantizing the pixel values ​​of the image according to a preset threshold interval, discretizing the continuous pixel values ​​into a limited number of intervals, and using different values ​​to represent different intervals. Through the image multi-value processing, the complexity of the image data is effectively reduced and the key features of the image are highlighted. Similarly, the image feature comparison module 13 performs image multi-value processing on the regional real-time image to obtain a second multi-value matrix. The first multi-value matrix and the second multi-value matrix respectively characterize the multi-value features of the regional target image and the regional real-time image.

[0050] After obtaining two multi-valued matrices, the image feature comparison module 13 compares the two multi-valued matrices element by element. By analyzing the difference distribution of the two multi-valued matrices in brightness and color values, the deviation distribution information of the regional real-time image and the regional target image in brightness and color is obtained. By using image multi-valued processing for feature comparison, areas with abnormal brightness or color deviations can be quickly screened out. Since the pixel values ​​are simplified to a limited number after the image is multi-valued, the difference comparison between images can be completed in a shorter time. Compared with the traditional pixel-by-pixel comparison method, the comparison method based on the multi-valued matrix has a significant improvement in speed, meeting the high real-time requirements of the LED lighting intelligent control scene.

[0051] By introducing image multi-valued processing, the image feature comparison module 13 converts the regional target image and the regional real-time image into corresponding multi-valued matrices, and obtains the brightness deviation distribution information and the color deviation distribution information by matrix comparison. While ensuring the accuracy of deviation recognition, it significantly improves the screening speed of the deviation area and improves the efficiency of lighting adjustment.

[0052] Furthermore, the image feature comparison module also includes the following execution steps:

[0053] Performing image brightness multi-value processing on the regional target image to obtain an image brightness multi-value result, wherein the image brightness multi-value result includes a first position pixel brightness multi-value result, a second position pixel brightness multi-value result, and so on until an N-th position pixel brightness multi-value result;

[0054] Performing image color multi-value processing on the regional target image to obtain an image color multi-value result, wherein the image color multi-value result includes a color multi-value result of a pixel at a first position, a color multi-value result of a pixel at a second position, and so on until a color multi-value result of a pixel at an Nth position;

[0055] According to the first position pixel brightness multi-valued result and the first position pixel color multi-valued result, a binary identifier of the first element of the matrix is ​​constructed; according to the second position pixel brightness multi-valued result and the second position pixel color multi-valued result, a binary identifier of the second element of the matrix is ​​constructed, until according to the N position pixel brightness multi-valued result and the N position pixel color multi-valued result, a binary identifier of the Nth element of the matrix is ​​constructed;

[0056] The first multi-valued matrix is ​​constructed according to the binary identifier of the first element of the matrix, the binary identifier of the second element of the matrix, and so on to the binary identifier of the Nth element of the matrix.

[0057] In a preferred embodiment, when the image feature comparison module 13 performs image multi-value processing on the regional target image to obtain a first multi-value matrix, it adopts a processing method based on independent multi-value processing of pixel brightness and pixel color, and generates the final multi-value matrix through a binary identification construction method.

[0058] First, the image feature comparison module 13 performs image brightness multi-valued processing on the regional target image, maps the brightness value of each pixel position of the image to a preset brightness interval, and represents it with a corresponding brightness multi-valued result. For example, the brightness value range of 0-255 is divided into 4 intervals, represented by 1, 2, 3, and 4 respectively. After the image brightness multi-valued processing, a group of image brightness multi-valued results are obtained, including the first position pixel brightness multi-valued result, the second position pixel brightness multi-valued result, and the Nth position pixel brightness multi-valued result, which corresponds to the brightness multi-valued results of all pixel positions in the regional target image. Next, the image feature comparison module 13 performs image color multi-valued processing on the regional target image. Similar to brightness multi-valued, the color value of each pixel position is mapped to a preset color interval, and represented by a corresponding color multi-valued result. For example, the color space is divided into several representative color intervals, and represented by different numerical values. After the image color multi-valued processing, a set of image color multi-valued results is obtained, including the color multi-valued result of the pixel at the first position, the color multi-valued result of the pixel at the second position, and so on to the color multi-valued result of the pixel at the Nth position, corresponding to the color multi-valued results of all pixel positions in the regional target image.

[0059] After obtaining the image brightness multi-valued result and the image color multi-valued result, the image feature comparison module 13 combines the two multi-valued results to construct a first multi-valued matrix. Specifically, for each pixel position, the image feature comparison module 13 generates a binary identification of a matrix element according to its brightness multi-valued result and color multi-valued result. For example, the brightness multi-valued result is used as the first position of the binary identification, and the color multi-valued result is used as the second position. In this way, the brightness multi-valued result and the color multi-valued result of the first position pixel constitute the binary identification of the first element of the matrix, and the two multi-valued results of the second position pixel constitute the binary identification of the second element of the matrix, and so on, until the two multi-valued results of the Nth position pixel constitute the binary identification of the Nth element of the matrix. Afterwards, the image feature comparison module 13 assembles the binary identifications of all pixel positions into a matrix of the same size as the regional target image according to their positional relationship in the image, i.e., the first multi-valued matrix. Each element in the matrix is ​​a binary identifier, which contains the brightness multi-valued result and color multi-valued result of the corresponding pixel position, which is used for subsequent image feature comparison.

[0060] The image feature comparison module 13 uses independent brightness multi-valued and color multi-valued processing, combined with the construction method of binary identification, to efficiently convert the regional target image into a first multi-valued matrix, which contains both the brightness feature information of the image and the color feature information of the image, laying the foundation for the subsequent deviation distribution information extraction. At the same time, discretizing the continuous brightness value and color value into a limited interval can reduce the complexity of the image data and improve the speed and efficiency of the subsequent comparison.

[0061] Furthermore, the image feature comparison module also includes the following execution steps:

[0062] Construct a brightness multi-value function:

[0063]

[0064] in, represents the brightness of the pixel at position i, Characterizes the multi-valued brightness result of the pixel at the i-th position, , , …, , , Characterize the brightness of the endpoints of the multi-valued interval;

[0065] According to the regional target image, extracting the brightness of the pixel at the first position, the brightness of the pixel at the second position, and the brightness of the pixel at the Nth position;

[0066] According to the brightness multi-valued function, traverse the brightness of the first position pixel, the brightness of the second position pixel, and finally the brightness of the N-th position pixel to perform pixel brightness processing, and obtain the brightness multi-valued result of the first position pixel, the brightness multi-valued result of the second position pixel, and finally the brightness multi-valued result of the N-th position pixel;

[0067] The first position pixel brightness multi-valued result, the second position pixel brightness multi-valued result, and so on until the N-th position pixel brightness multi-valued result are added to the image brightness multi-valued result.

[0068] In a preferred embodiment, when the image feature comparison module 13 performs image brightness multi-valued processing on the regional target image to obtain the image brightness multi-valued result, it adopts a mapping method based on the brightness multi-valued function to map the continuous pixel brightness value to a discrete brightness interval, thereby obtaining the brightness multi-valued result of each pixel position.

[0069] Specifically, the image feature comparison module 13 first constructs a brightness multi-value function for:

[0070] ,

[0071] The brightness multi-value function is used to map the pixel brightness value to the corresponding brightness multi-value result. Represents the brightness value of the i-th pixel position, the function value represents the brightness multi-valued result of the i-th pixel position. The domain of the brightness multi-valued function is divided into n+1 continuous intervals, each of which corresponds to a discrete function value. , , …, , Indicates the endpoint brightness value of each interval, and 255 indicates the upper limit of the brightness value. When it falls within a certain interval, it is mapped to the corresponding function value. For example, when Belong to the interval hour, ;when Belong to the interval hour, , and so on.

[0072] After obtaining the brightness multi-value function, the image feature comparison module 13 extracts the brightness value of each pixel position from the regional target image, including the brightness of the first position pixel, the brightness of the second position pixel, and so on to the brightness of the Nth position pixel, where N represents the total number of pixels in the regional target image. Then, the image feature comparison module 13 traverses all pixel positions of the regional target image according to the brightness multi-value function and performs brightness multi-value processing on each pixel brightness value. Specifically, for the brightness value of the i-th pixel position , substitute it into the brightness multi-value function, and get the corresponding pixel brightness multi-value result . In this way, the image feature comparison module 13 obtains the brightness multi-valued result of the first position pixel, the brightness multi-valued result of the second position pixel, and so on to the brightness multi-valued result of the Nth position pixel in sequence, covering all pixel positions of the regional target image. Afterwards, the image feature comparison module 13 adds the brightness multi-valued results of all pixel positions obtained into the image brightness multi-valued result in sequence, forming a brightness multi-valued result corresponding to the pixel position of the regional target image one by one, including the brightness multi-valued information of each pixel position in the regional target image, which is used for subsequent feature comparison and deviation analysis.

[0073] The image feature comparison module 13 maps continuous pixel brightness values ​​to discrete intervals by constructing a brightness multi-valued function, and traverses all pixel positions of the regional target image to perform brightness multi-valued processing to obtain a complete image brightness multi-valued result. This result characterizes the brightness distribution characteristics of the regional target image in a discrete form, reduces the complexity of the brightness data, and facilitates subsequent feature comparison. At the same time, by adjusting the interval division in the brightness multi-valued function, the granularity of the brightness multi-valued can be flexibly controlled, and a balance can be made between the fidelity of the brightness information and the degree of data simplification to meet the needs of different application scenarios.

[0074] Furthermore, the image feature comparison module also includes the following execution steps:

[0075] Construct a color multi-value matrix:

[0076]

[0077] in, Characterize the color feature value of the pixel at the jth position, , , , …, , 255, and , , , …, , 255, and , , , …, , 255 are all multi-valued interval endpoint characteristic values;

[0078] According to the regional target image, extracting the color RGB value of the first position, the color RGB value of the second position, and the color RGB value of the Nth position;

[0079] According to the color multi-valued matrix, traverse the color RGB value of the first position, the color RGB value of the second position, and finally the color RGB value of the Nth position to perform pixel color processing, and obtain the color multi-valued result of the pixel at the first position, the color multi-valued result of the pixel at the second position, and finally the color multi-valued result of the pixel at the Nth position;

[0080] The color multi-valued result of the pixel at the first position, the color multi-valued result of the pixel at the second position, and so on to the color multi-valued result of the pixel at the Nth position are added to the color multi-valued result of the image.

[0081] In a preferred embodiment, when the image feature comparison module 13 performs image color multi-valued processing on the regional target image to obtain the image color multi-valued result, a mapping method based on the color multi-valued matrix is ​​adopted to map the RGB color feature value of the pixel to a discrete color interval, thereby obtaining the color multi-valued result of each pixel position.

[0082] First, the image feature comparison module 13 constructs a color multi-value matrix as follows:

[0083] ,

[0084] The color multi-value matrix is ​​used to map the RGB color feature value of the pixel to the corresponding color multi-value result. , , Respectively represent the red, green, and blue component values ​​of the j-th pixel position, and the matrix value Represents the color multi-valued result of the j-th pixel position. The domain of the color multi-valued matrix is ​​a three-dimensional space, which consists of the value ranges of the three components of red, green, and blue. The three-dimensional space is divided into m+1 continuous sub-intervals, each of which corresponds to a discrete matrix value. Among them, , , …, represents the interval endpoint value of the red component, , , …, represents the interval endpoint value of the green component, , , …, Indicates the interval endpoint value of the blue component, 0 and 255 represent the lower and upper limits of the RGB color component value respectively. When it falls within a certain three-dimensional subinterval, it is mapped to the corresponding matrix value. For example, when Belong to the interval , Belong to the interval , Belong to the interval hour, ;when Belong to the interval , Belong to the interval , Belong to the interval hour, , and so on.

[0085] After constructing the color multi-valued matrix, the image feature comparison module 13 extracts the RGB color value of each pixel position from the regional target image, including the color RGB value of the first position, the color RGB value of the second position, and so on to the color RGB value of the Nth position, where N represents the total number of pixels in the regional target image. Then, the image feature comparison module 13 traverses all pixel positions of the regional target image according to the color multi-valued matrix and performs color multi-valued processing on the RGB color value of each pixel. Specifically, for the RGB color value of the jth pixel position , substitute it into the color multi-value matrix , and obtain the corresponding pixel color multi-valued result. In this way, the image feature comparison module 13 obtains the color multi-valued result of the first position pixel, the color multi-valued result of the second position pixel, and so on to the color multi-valued result of the Nth position pixel in sequence, covering all pixel positions of the regional target image. Afterwards, the image feature comparison module 13 adds the color multi-valued results of all pixel positions obtained into the image color multi-valued result in sequence, forming a color multi-valued result corresponding to the pixel position of the regional target image, including the color multi-valued information of each pixel position in the regional target image, for subsequent feature comparison and deviation analysis.

[0086] The image feature comparison module 13 maps the RGB color feature value of the pixel to a discrete color interval by constructing a color multi-value matrix, and traverses all pixel positions of the regional target image to perform color multi-value processing, thereby obtaining a complete image color multi-value result, characterizing the color distribution characteristics of the regional target image in a discrete form, reducing the complexity of the color data, and providing convenience for subsequent feature comparison. At the same time, by adjusting the interval division in the color multi-value matrix, the granularity of the color multi-value can be flexibly controlled, and a balance can be struck between the fidelity of color information and the degree of data simplification to meet the needs of different application scenarios.

[0087] Furthermore, the image feature comparison module also includes the following execution steps:

[0088] Extracting a first matrix color identifier and a first matrix brightness identifier according to the first multi-valued matrix;

[0089] Extracting a second matrix color identifier and a second matrix brightness identifier according to the second multi-valued matrix;

[0090] For the positions where the color identifiers in the first matrix color identifier and the second matrix color identifier are the same, the color deviation identifier is 0, and for the positions where the color identifiers in the first matrix color identifier and the second matrix color identifier are different, the color deviation identifier is 1, and the brightness deviation distribution information is generated;

[0091] For the positions where the brightness identifiers in the first matrix brightness identifier and the second matrix brightness identifier are the same, the brightness deviation identifier is 0, and for the positions where the brightness identifiers in the first matrix brightness identifier and the second matrix brightness identifier are different, the brightness deviation identifier is 1, and the color deviation distribution information is generated.

[0092] In a preferred embodiment, when the image feature comparison module 13 compares the first multi-valued matrix and the second multi-valued matrix to obtain brightness deviation distribution information and color deviation distribution information, it adopts a method based on matrix element identification comparison, and generates a binary matrix representing the deviation distribution by comparing the similarities and differences between the color identification and brightness identification at corresponding positions of the two multi-valued matrices.

[0093] First, the image feature comparison module 13 extracts the color identification and brightness identification information contained therein according to the first multi-valued matrix. Since each element of the first multi-valued matrix is ​​a binary identification, the first bit thereof represents the brightness identification and the second bit represents the color identification, so the first matrix brightness identification can be obtained by reading the first bit of each element, and the first matrix color identification can be obtained by reading the second bit of each element. The first matrix brightness identification and the first matrix color identification are matrices of the same size as the first multi-valued matrix, and respectively represent the brightness multi-valued results and color multi-valued results of each pixel position of the regional target image. Similarly, the image feature comparison module 13 extracts the second matrix color identification and the second matrix brightness identification contained therein according to the second multi-valued matrix. The second matrix brightness identification and the second matrix color identification represent the brightness multi-valued results and color multi-valued results of each pixel position of the regional real-time image.

[0094] Next, the image feature comparison module 13 compares the two groups of matrix identifiers to generate brightness deviation distribution information and color deviation distribution information. For the color deviation distribution information, the image feature comparison module 13 compares the color identifier values ​​of the first matrix color identifier and the second matrix color identifier at each pixel position one by one. If the color identifier values ​​of the two matrices are the same at a certain position, the color deviation identifier of the position is set to 0, indicating that the color of the position is consistent and there is no deviation; if the color identifier values ​​of the two matrices are different at a certain position, the color deviation identifier of the position is set to 1, indicating that the color of the position is inconsistent and there is a deviation. By comparing bit by bit, the image feature comparison module 13 obtains a binary matrix representing the color deviation distribution with the same size as the input matrix as the color deviation distribution information, wherein the position with a value of 0 indicates that the color is consistent, and the position with a value of 1 indicates that the color has a deviation. For the brightness deviation distribution information, the image feature comparison module 13 adopts a method similar to that of generating the color deviation distribution information, and compares the brightness identifier values ​​of the first matrix brightness identifier and the second matrix brightness identifier at each pixel position one by one, and sets the brightness deviation identifiers of the positions with the same value to 0, and sets the brightness deviation identifiers of the positions with different values ​​to 1, thereby obtaining a binary matrix representing the brightness deviation distribution as the brightness deviation distribution information.

[0095] The image feature comparison module 13 generates brightness deviation distribution information and color deviation distribution information by extracting the color identification and brightness identification of the first multi-valued matrix and the second multi-valued matrix and performing bit-by-bit comparison. Both deviation distribution information are binary matrices, which use 0 and 1 to indicate whether there is a deviation in brightness or color at the corresponding position, and intuitively describe the difference distribution between the image to be tested and the reference image. After obtaining the deviation distribution information, the light area that needs to be adjusted can be further analyzed and located, and corresponding control measures can be taken to reduce image deviation and improve the accuracy and effect of LED light control.

[0096] Furthermore, the deviation area sorting module includes the following execution steps:

[0097] The brightness deviation threshold and the color deviation threshold are equal to 1,

[0098] Based on the brightness deviation distribution information, select areas where the brightness deviation is greater than or equal to the brightness deviation threshold and set them as brightness deviation areas;

[0099] Extracting the target brightness mark of the brightness deviation area from the regional target image;

[0100] Based on the color deviation distribution information, sorting areas where the color deviation is greater than or equal to the color deviation threshold and setting them as color deviation areas;

[0101] Extracting the target color identification of the color deviation area from the regional target image;

[0102] The union area of ​​the brightness deviation area and the color deviation area is taken as the light deviation area.

[0103] In a preferred embodiment, the deviation area sorting module 14 adopts a threshold comparison and area merging method when sorting deviation areas based on brightness deviation distribution information and color deviation distribution information. By comparing the deviation value with a preset threshold, the area where the brightness deviation or color deviation exceeds the threshold is found, and these areas are merged to obtain a complete lighting deviation area, and the target brightness identification and target color identification of the area are extracted at the same time.

[0104] First, the deviation area sorting module 14 sets a brightness deviation threshold and a color deviation threshold to determine whether the brightness deviation or color deviation of the pixel position is significant. Among them, the brightness deviation threshold and the color deviation threshold are both set to 1, indicating that as long as the value of the brightness deviation mark or the color deviation mark of the pixel position is 1, it is considered that there is a significant brightness deviation or color deviation at the position. Next, the deviation area sorting module 14 compares the brightness deviation mark of each pixel position with the brightness deviation threshold one by one based on the brightness deviation distribution information. For those pixel positions whose brightness deviation marks are greater than or equal to the brightness deviation threshold (i.e., the value is 1), they are marked as brightness deviation areas. The brightness deviation area covers all pixel positions whose brightness deviation exceeds the threshold, and represents the part of the regional real-time image that has a significant difference in brightness from the regional target image. In order to obtain the brightness adjustment target of the brightness deviation area, the deviation area sorting module 14 extracts the pixel brightness value of the position corresponding to the brightness deviation area from the regional target image as the target brightness mark of the area. The target brightness mark represents the normal brightness level of the brightness deviation area in the reference image, and provides a quantitative reference basis for subsequent lighting adjustment. Similarly, the deviation area sorting module 14 will also sort out the area where the color deviation is greater than or equal to the threshold (i.e., the value is 1) based on the color deviation distribution information by comparing the color deviation mark of the pixel position with the color deviation threshold, and mark it as the color deviation area. The color deviation area covers all pixel positions where the color deviation exceeds the threshold, and represents the part of the regional real-time image that has a significant difference in color from the regional target image. At the same time, the pixel color value of the corresponding position of the color deviation area is extracted from the regional target image as the target color mark of the area, which is used to guide the subsequent light color adjustment.

[0105] In order to obtain a complete light deviation area, the deviation area sorting module 14 merges the brightness deviation area and the color deviation area, and takes the union of the two areas as the final light deviation area. The light deviation area includes all pixel positions where the brightness deviation or color deviation exceeds the threshold, taking into account both the brightness deviation and the color deviation, and fully reflects the difference distribution between the regional real-time image and the regional target image. The light deviation area and its corresponding target brightness mark and target color mark provide regional positioning and quantitative reference for subsequent precise light control, which helps to improve the pertinence and effectiveness of LED light control.

[0106] The deviation region sorting module 14 obtains a complete light deviation region by threshold comparison and region merging methods, which covers all pixel positions in the regional real-time image where the brightness deviation or color deviation exceeds the threshold. At the same time, the target brightness mark and target color mark corresponding to the light deviation region are extracted from the regional target image, providing a basis for subsequent quantitative light adjustment. This deviation region sorting method can quickly and accurately locate the area with significant deviation in the image and give the adjustment target, laying the foundation for realizing refined LED light intelligent control.

[0107] Furthermore, the lighting optimization control module includes the following execution steps:

[0108] Based on the target brightness identifier, constructing a sum constraint condition of red light brightness, blue light brightness and green light brightness, wherein the sum constraint condition ensures that the deviation of the sum of the red light brightness, the blue light brightness and the green light brightness from the target brightness identifier is less than or equal to a brightness deviation threshold;

[0109] Randomly assigning values ​​to the red light brightness, the blue light brightness, and the green light brightness according to the sum constraint condition to obtain a first red light brightness percentage, a first blue light brightness percentage, and a first green light brightness percentage;

[0110] Analyzing the first red light brightness percentage, the first blue light brightness percentage, and the first green light brightness percentage through an RGB color model to obtain a predicted color feature value;

[0111] When the predicted color feature value is the same as the target color identifier, the first red light brightness percentage, the first blue light brightness percentage, and the first green light brightness percentage are set to the red light brightness percentage, the blue light brightness percentage, and the green light brightness percentage;

[0112] Otherwise, the first red light brightness percentage, the first blue light brightness percentage, and the first green light brightness percentage are updated according to the addition constraint condition.

[0113] Specifically, when the lighting optimization control module 15 performs lighting control optimization for the lighting deviation area according to the target brightness identifier and the target color identifier, it adopts a constraint-based random search method, constructs brightness constraints and color constraints, and performs iterative optimization in combination with the RGB color model, and finally obtains the red light brightness percentage, blue light brightness percentage and green light brightness percentage that meet the brightness requirements and color requirements as the optimal control parameters for LED lighting adjustment.

[0114] First, the lighting optimization control module 15 constructs the sum constraint of red light brightness, blue light brightness and green light brightness based on the target brightness mark. This constraint requires that the deviation between the sum of the red light brightness, blue light brightness and green light brightness and the target brightness mark is less than or equal to the preset brightness deviation threshold. Through this constraint, it can be ensured that the total brightness of the optimized brightness ratio of the three colors of red, blue and green is very close to the target brightness mark after mixing, ensuring the brightness adjustment accuracy of the lighting deviation area. Then, the lighting optimization control module 15 randomly assigns red light brightness, blue light brightness and green light brightness on the premise of satisfying the sum constraint, and obtains a set of initial brightness percentage combinations, namely the first red light brightness percentage, the first blue light brightness percentage and the first green light brightness percentage. Although this set of initial percentages meets the sum constraint of brightness, it does not necessarily meet the color requirements, so it needs to be further optimized.

[0115] In order to evaluate the color performance of the current red, blue and green brightness percentage combination, the lighting optimization control module 15 converts the first red light brightness percentage, the first blue light brightness percentage and the first green light brightness percentage into corresponding color feature values ​​through the RGB color model as predicted color feature values. The RGB color model is an additive color model based on the three primary colors of red, green and blue. By adjusting the brightness ratio of the three colors, various different colors can be synthesized. The lighting optimization control module 15 uses the RGB color model, takes the brightness percentage of the three colors of red, blue and green as input, calculates the red, green and blue component values ​​of the synthesized color by weighted summation, and uses it as the predicted color feature value. In this way, a mapping relationship between the brightness percentage combination and the color feature value is established. Then, the lighting optimization control module 15 compares the difference between the predicted color feature value and the target color identifier. If the two are exactly the same, it means that the first red light brightness percentage, the first blue light brightness percentage and the first green light brightness percentage not only meet the brightness addition constraint, but also can synthesize a color consistent with the target color identification, which is an optimal control parameter combination, and can be directly used as the final red light brightness percentage, blue light brightness percentage and green light brightness percentage output. However, if there is a difference between the predicted color feature value and the target color identification, it means that although the first red light brightness percentage, the first blue light brightness percentage and the first green light brightness percentage meet the brightness addition constraint, there is still room for optimization in terms of color. At this time, the lighting optimization control module 15 adjusts and updates the first red light brightness percentage, the first blue light brightness percentage and the first green light brightness percentage based on the sum constraint and the size and direction of the difference between the predicted color feature value and the target color identification, obtains a new brightness percentage combination, and recalculates its predicted color feature value through the RGB color model, and re-evaluates its closeness to the target color identification. This iterative optimization process is continued until a set of red light brightness percentages, blue light brightness percentages, and green light brightness percentages are found that satisfy the additive constraint and can synthesize a color that is very close to the target color identity.

[0116] The lighting optimization control module 15 takes the target brightness identifier as a constraint condition and the target color identifier as an optimization target. Through random search and iterative optimization methods, it uses the RGB color model to establish a mapping relationship between brightness percentage combinations and color feature values, and continuously adjusts and improves the brightness ratio of the three colors of red, blue, and green. It obtains the optimal control parameter combination that meets the brightness requirements and color requirements. While ensuring the brightness accuracy, it maximizes the optimization of the color performance effect, providing strong parameter support for realizing high-fidelity, high-reduction intelligent adjustment of LED lights.

[0117] An LED lighting intelligent control system provided by an embodiment of the present invention has at least the following technical effects:

[0118] The image acquisition module is used to receive the real-time image of the area taken by the IoT sensor of the preset area after the LED light strip is started, wherein the IoT sensor is deployed at a fixed position in the preset area to establish the real-time monitoring basis of the system and provide real-time data input for subsequent lighting control. The target image receiving module is used to receive the regional target image of the preset area, wherein the regional target image and the regional real-time image have coordinate consistency, provide a standard reference image for subsequent effect comparison, and ensure the accuracy of the comparison. The image feature comparison module is used to perform feature comparison on the regional target image and the regional real-time image to obtain brightness deviation distribution information and color deviation distribution information, and replace the traditional machine vision model with fast feature comparison to improve the processing speed. The deviation area sorting module is used to sort the area with brightness deviation greater than or equal to the brightness deviation threshold, or the color deviation greater than or equal to the color deviation threshold based on the brightness deviation distribution information and the color deviation distribution information, and obtain the light deviation area, wherein the light deviation area has a target brightness mark and / or a target color mark, and the area to be adjusted is screened out according to the set threshold, and the target brightness and color requirements are marked, the problem area is accurately located, and the pertinence of the control is improved. The lighting optimization control module is used to optimize the lighting control in the lighting deviation area according to the target brightness mark and / or target color mark, obtain the red light brightness percentage, blue light brightness percentage and green light brightness percentage, and convert the qualitative difference into quantitative control parameters to provide specific indicators for subsequent execution. The driving power control module is used to initialize the dimming driving power according to the red light brightness percentage, blue light brightness percentage and green light brightness percentage, control the LED light strip in the lighting deviation area, and realize accurate dimming of the target area.

[0119] Embodiment 2:

[0120] like Figure 2 As shown, based on the same inventive concept of an LED light intelligent control system provided in Embodiment 1, an embodiment of the present invention further provides an LED light intelligent control method, comprising:

[0121] When the LED light strip is started, a real-time image of a preset area captured by an IoT sensor is received, wherein the IoT sensor is deployed at a fixed position in the preset area;

[0122] Receiving a regional target image of the preset area, wherein the regional target image and the regional real-time image have coordinate consistency;

[0123] Performing feature comparison on the target image of the region and the real-time image of the region to obtain brightness deviation distribution information and color deviation distribution information;

[0124] Based on the brightness deviation distribution information and the color deviation distribution information, select the area where the brightness deviation is greater than or equal to the brightness deviation threshold, or the color deviation is greater than or equal to the color deviation threshold, to obtain a light deviation area, wherein the light deviation area has a target brightness identifier and / or a target color identifier;

[0125] According to the target brightness identifier and / or the target color identifier, optimizing the lighting control of the lighting deviation area to obtain the red light brightness percentage, the blue light brightness percentage and the green light brightness percentage;

[0126] The dimming driving power supply is initialized according to the red light brightness percentage, the blue light brightness percentage and the green light brightness percentage to control the LED light strip in the light deviation area.

[0127] Further, feature comparison is performed on the regional target image and the regional real-time image to obtain brightness deviation distribution information and color deviation distribution information, including:

[0128] Performing image multi-value processing on the regional target image to obtain a first multi-value matrix;

[0129] Performing image multi-value processing on the real-time image of the region to obtain a second multi-value matrix;

[0130] The first multi-valued matrix and the second multi-valued matrix are compared to obtain the brightness deviation distribution information and the color deviation distribution information.

[0131] Further, performing image multi-value processing on the regional target image to obtain a first multi-value matrix includes:

[0132] Performing image brightness multi-value processing on the regional target image to obtain an image brightness multi-value result, wherein the image brightness multi-value result includes a first position pixel brightness multi-value result, a second position pixel brightness multi-value result, and so on until an N-th position pixel brightness multi-value result;

[0133] Performing image color multi-value processing on the regional target image to obtain an image color multi-value result, wherein the image color multi-value result includes a color multi-value result of a pixel at a first position, a color multi-value result of a pixel at a second position, and so on until a color multi-value result of a pixel at an Nth position;

[0134] According to the first position pixel brightness multi-valued result and the first position pixel color multi-valued result, a binary identifier of the first element of the matrix is ​​constructed; according to the second position pixel brightness multi-valued result and the second position pixel color multi-valued result, a binary identifier of the second element of the matrix is ​​constructed, until according to the N position pixel brightness multi-valued result and the N position pixel color multi-valued result, a binary identifier of the Nth element of the matrix is ​​constructed;

[0135] The first multi-valued matrix is ​​constructed according to the binary identifier of the first element of the matrix, the binary identifier of the second element of the matrix, and so on to the binary identifier of the Nth element of the matrix.

[0136] Further, the regional target image is subjected to image brightness multi-value processing to obtain an image brightness multi-value result, wherein the image brightness multi-value result includes a first position pixel brightness multi-value result, a second position pixel brightness multi-value result, and so on until an N-th position pixel brightness multi-value result, including:

[0137] Construct a brightness multi-value function:

[0138]

[0139] in, represents the brightness of the pixel at position i, Characterizes the multi-valued brightness result of the pixel at the i-th position, , , …, , , Characterize the brightness of the endpoints of the multi-valued interval;

[0140] According to the regional target image, extracting the brightness of the pixel at the first position, the brightness of the pixel at the second position, and the brightness of the pixel at the Nth position;

[0141] According to the brightness multi-valued function, traverse the brightness of the first position pixel, the brightness of the second position pixel, and finally the brightness of the N-th position pixel to perform pixel brightness processing, and obtain the brightness multi-valued result of the first position pixel, the brightness multi-valued result of the second position pixel, and finally the brightness multi-valued result of the N-th position pixel;

[0142] The first position pixel brightness multi-valued result, the second position pixel brightness multi-valued result, and so on until the N-th position pixel brightness multi-valued result are added to the image brightness multi-valued result.

[0143] Further, the regional target image is subjected to image color multi-value processing to obtain an image color multi-value result, wherein the image color multi-value result includes a first position pixel color multi-value result, a second position pixel color multi-value result, and so on until an N-th position pixel color multi-value result, including:

[0144] Construct a color multi-value matrix:

[0145]

[0146] in, Characterize the color feature value of the pixel at the jth position, , , , …, , 255, and , , , …, , 255, and , , , …, , 255 are all multi-valued interval endpoint characteristic values;

[0147] According to the regional target image, extracting the color RGB value of the first position, the color RGB value of the second position, and the color RGB value of the Nth position;

[0148] According to the color multi-valued matrix, traverse the color RGB value of the first position, the color RGB value of the second position, and finally the color RGB value of the Nth position to perform pixel color processing, and obtain the color multi-valued result of the pixel at the first position, the color multi-valued result of the pixel at the second position, and finally the color multi-valued result of the pixel at the Nth position;

[0149] The color multi-valued result of the pixel at the first position, the color multi-valued result of the pixel at the second position, and so on to the color multi-valued result of the pixel at the Nth position are added to the color multi-valued result of the image.

[0150] Further, comparing the first multi-valued matrix and the second multi-valued matrix to obtain the brightness deviation distribution information and the color deviation distribution information includes:

[0151] Extracting a first matrix color identifier and a first matrix brightness identifier according to the first multi-valued matrix;

[0152] Extracting a second matrix color identifier and a second matrix brightness identifier according to the second multi-valued matrix;

[0153] For the positions where the color identifiers in the first matrix color identifier and the second matrix color identifier are the same, the color deviation identifier is 0, and for the positions where the color identifiers in the first matrix color identifier and the second matrix color identifier are different, the color deviation identifier is 1, and the brightness deviation distribution information is generated;

[0154] For the positions where the brightness identifiers in the first matrix brightness identifier and the second matrix brightness identifier are the same, the brightness deviation identifier is 0, and for the positions where the brightness identifiers in the first matrix brightness identifier and the second matrix brightness identifier are different, the brightness deviation identifier is 1, and the color deviation distribution information is generated.

[0155] Further, based on the brightness deviation distribution information and the color deviation distribution information, a region where the brightness deviation is greater than or equal to the brightness deviation threshold, or a region where the color deviation is greater than or equal to the color deviation threshold is selected to obtain a light deviation region, wherein the light deviation region has a target brightness identifier and / or a target color identifier, including:

[0156] The brightness deviation threshold and the color deviation threshold are equal to 1,

[0157] Based on the brightness deviation distribution information, select areas where the brightness deviation is greater than or equal to the brightness deviation threshold and set them as brightness deviation areas;

[0158] Extracting the target brightness mark of the brightness deviation area from the regional target image;

[0159] Based on the color deviation distribution information, sorting areas where the color deviation is greater than or equal to the color deviation threshold and setting them as color deviation areas;

[0160] Extracting the target color identification of the color deviation area from the regional target image;

[0161] The union area of ​​the brightness deviation area and the color deviation area is taken as the light deviation area.

[0162] Further, according to the target brightness identifier and / or the target color identifier, the lighting control optimization is performed on the lighting deviation area to obtain the red light brightness percentage, the blue light brightness percentage and the green light brightness percentage, including:

[0163] Based on the target brightness identifier, constructing a sum constraint condition of red light brightness, blue light brightness and green light brightness, wherein the sum constraint condition ensures that the deviation of the sum of the red light brightness, the blue light brightness and the green light brightness from the target brightness identifier is less than or equal to a brightness deviation threshold;

[0164] Randomly assigning values ​​to the red light brightness, the blue light brightness, and the green light brightness according to the sum constraint condition to obtain a first red light brightness percentage, a first blue light brightness percentage, and a first green light brightness percentage;

[0165] Analyzing the first red light brightness percentage, the first blue light brightness percentage, and the first green light brightness percentage through an RGB color model to obtain a predicted color feature value;

[0166] When the predicted color feature value is the same as the target color identifier, the first red light brightness percentage, the first blue light brightness percentage, and the first green light brightness percentage are set to the red light brightness percentage, the blue light brightness percentage, and the green light brightness percentage;

[0167] Otherwise, the first red light brightness percentage, the first blue light brightness percentage, and the first green light brightness percentage are updated according to the addition constraint condition.

[0168] Embodiment three:

[0169] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an electronic device 200 provided by an embodiment of the present invention includes a memory 210, a processor 220, and a first computer program 211 stored in the memory 210 and executable on the processor 220. When the processor 220 executes the first computer program 211, an LED light intelligent control system is implemented.

[0170] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0171] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0172] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0173] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0174] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0175] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0176] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technology, the present invention is also intended to include these changes and variations.

Claims

1. An LED lighting intelligent control system, characterized in that: The system is connected to the LED lighting assembly and the IoT sensor in communication, and the LED lighting assembly includes an LED light strip and a dimming drive power supply, including: An image acquisition module, wherein the image acquisition module is used to receive a real-time image of a preset area captured by an IoT sensor after the LED light strip is started, wherein the IoT sensor is deployed at a fixed position in the preset area; A target image receiving module, the target image receiving module is used to receive a regional target image of the preset area, wherein the regional target image and the regional real-time image have coordinate consistency; An image feature comparison module, the image feature comparison module is used to perform feature comparison on the regional target image and the regional real-time image to obtain brightness deviation distribution information and color deviation distribution information; a deviation region sorting module, the deviation region sorting module being used to sort regions where the brightness deviation is greater than or equal to the brightness deviation threshold, or the color deviation is greater than or equal to the color deviation threshold, based on the brightness deviation distribution information and the color deviation distribution information, to obtain a light deviation region, wherein the light deviation region has a target brightness identifier and / or a target color identifier; A lighting optimization control module, the lighting optimization control module is used to perform lighting control optimization on the lighting deviation area according to the target brightness identifier and / or the target color identifier to obtain the red light brightness percentage, the blue light brightness percentage and the green light brightness percentage; A driving power supply control module is used to initialize the dimming driving power supply according to the red light brightness percentage, the blue light brightness percentage and the green light brightness percentage, and control the LED light strip in the light deviation area.

2. The LED lighting intelligent control system according to claim 1, characterized in that: The image feature comparison module includes the following execution steps: Performing image multi-value processing on the regional target image to obtain a first multi-value matrix; Performing image multi-value processing on the real-time image of the region to obtain a second multi-value matrix; The first multi-valued matrix and the second multi-valued matrix are compared to obtain the brightness deviation distribution information and the color deviation distribution information.

3. The LED lighting intelligent control system according to claim 2, characterized in that: The image feature comparison module also includes the following execution steps: Performing image brightness multi-value processing on the regional target image to obtain an image brightness multi-value result, wherein the image brightness multi-value result includes a first position pixel brightness multi-value result, a second position pixel brightness multi-value result, and so on until an N-th position pixel brightness multi-value result; Performing image color multi-value processing on the regional target image to obtain an image color multi-value result, wherein the image color multi-value result includes a color multi-value result of a pixel at a first position, a color multi-value result of a pixel at a second position, and so on until a color multi-value result of a pixel at an Nth position; According to the first position pixel brightness multi-valued result and the first position pixel color multi-valued result, a binary identifier of the first element of the matrix is ​​constructed; according to the second position pixel brightness multi-valued result and the second position pixel color multi-valued result, a binary identifier of the second element of the matrix is ​​constructed, until according to the N position pixel brightness multi-valued result and the N position pixel color multi-valued result, a binary identifier of the Nth element of the matrix is ​​constructed; The first multi-valued matrix is ​​constructed according to the binary identifier of the first element of the matrix, the binary identifier of the second element of the matrix, and so on to the binary identifier of the Nth element of the matrix.

4. The LED lighting intelligent control system according to claim 3, characterized in that: The image feature comparison module also includes the following execution steps: Construct a brightness multi-value function: in, represents the brightness of the pixel at position i, Characterizes the multi-valued brightness result of the pixel at the i-th position, , , …, , , Characterize the brightness of the endpoints of the multi-valued interval; According to the regional target image, extracting the brightness of the pixel at the first position, the brightness of the pixel at the second position, and the brightness of the pixel at the Nth position; According to the brightness multi-valued function, traverse the brightness of the first position pixel, the brightness of the second position pixel, and finally the brightness of the N-th position pixel to perform pixel brightness processing, and obtain the brightness multi-valued result of the first position pixel, the brightness multi-valued result of the second position pixel, and finally the brightness multi-valued result of the N-th position pixel; The first position pixel brightness multi-valued result, the second position pixel brightness multi-valued result, and so on until the N-th position pixel brightness multi-valued result are added to the image brightness multi-valued result.

5. The LED lighting intelligent control system according to claim 3, characterized in that: The image feature comparison module also includes the following execution steps: Construct a color multi-value matrix: in, Characterize the color feature value of the pixel at the jth position, , , , …, , 255, and , , , …, , 255, and , , , …, , 255 are all multi-valued interval endpoint characteristic values; According to the regional target image, extracting the color RGB value of the first position, the color RGB value of the second position, and the color RGB value of the Nth position; According to the color multi-valued matrix, traverse the color RGB value of the first position, the color RGB value of the second position, and finally the color RGB value of the Nth position to perform pixel color processing, and obtain the color multi-valued result of the pixel at the first position, the color multi-valued result of the pixel at the second position, and finally the color multi-valued result of the pixel at the Nth position; The color multi-valued result of the pixel at the first position, the color multi-valued result of the pixel at the second position, and so on to the color multi-valued result of the pixel at the Nth position are added to the color multi-valued result of the image.

6. The LED lighting intelligent control system according to claim 2, characterized in that: The image feature comparison module also includes the following execution steps: Extracting a first matrix color identifier and a first matrix brightness identifier according to the first multi-valued matrix; Extracting a second matrix color identifier and a second matrix brightness identifier according to the second multi-valued matrix; For the positions where the color identifiers in the first matrix color identifier and the second matrix color identifier are the same, the color deviation identifier is 0, and for the positions where the color identifiers in the first matrix color identifier and the second matrix color identifier are different, the color deviation identifier is 1, and the brightness deviation distribution information is generated; For the positions where the brightness identifiers in the first matrix brightness identifier and the second matrix brightness identifier are the same, the brightness deviation identifier is 0, and for the positions where the brightness identifiers in the first matrix brightness identifier and the second matrix brightness identifier are different, the brightness deviation identifier is 1, and the color deviation distribution information is generated.

7. The LED lighting intelligent control system according to claim 1, characterized in that: The deviation area sorting module includes the following execution steps: The brightness deviation threshold and the color deviation threshold are equal to 1, Based on the brightness deviation distribution information, select areas where the brightness deviation is greater than or equal to the brightness deviation threshold and set them as brightness deviation areas; Extracting the target brightness mark of the brightness deviation area from the regional target image; Based on the color deviation distribution information, sorting areas where the color deviation is greater than or equal to the color deviation threshold and setting them as color deviation areas; Extracting the target color identification of the color deviation area from the regional target image; The union area of ​​the brightness deviation area and the color deviation area is taken as the light deviation area.

8. The LED lighting intelligent control system according to claim 1, characterized in that: The lighting optimization control module includes the following execution steps: Based on the target brightness identifier, constructing a sum constraint condition of red light brightness, blue light brightness and green light brightness, wherein the sum constraint condition ensures that the deviation of the sum of the red light brightness, the blue light brightness and the green light brightness from the target brightness identifier is less than or equal to a brightness deviation threshold; Randomly assigning values ​​to the red light brightness, the blue light brightness, and the green light brightness according to the sum constraint condition to obtain a first red light brightness percentage, a first blue light brightness percentage, and a first green light brightness percentage; Analyzing the first red light brightness percentage, the first blue light brightness percentage, and the first green light brightness percentage through an RGB color model to obtain a predicted color feature value; When the predicted color feature value is the same as the target color identifier, setting the first red light brightness percentage, the first blue light brightness percentage, and the first green light brightness percentage to the red light brightness percentage, the blue light brightness percentage, and the green light brightness percentage; Otherwise, the first red light brightness percentage, the first blue light brightness percentage, and the first green light brightness percentage are updated according to the addition constraint condition.

9. A LED lighting intelligent control method, characterized in that: Applied to the LED lighting intelligent control system, the system is connected to the LED lighting component and the IoT sensor, the LED lighting component includes an LED light strip and a dimming drive power supply, including: When the LED light strip is started, a real-time image of a preset area captured by an IoT sensor is received, wherein the IoT sensor is deployed at a fixed position in the preset area; Receiving a regional target image of the preset area, wherein the regional target image and the regional real-time image have coordinate consistency; Performing feature comparison on the target image of the region and the real-time image of the region to obtain brightness deviation distribution information and color deviation distribution information; Based on the brightness deviation distribution information and the color deviation distribution information, select the area where the brightness deviation is greater than or equal to the brightness deviation threshold, or the color deviation is greater than or equal to the color deviation threshold, to obtain a light deviation area, wherein the light deviation area has a target brightness identifier and / or a target color identifier; According to the target brightness identifier and / or the target color identifier, optimizing the lighting control of the lighting deviation area to obtain the red light brightness percentage, the blue light brightness percentage and the green light brightness percentage; The dimming driving power supply is initialized according to the red light brightness percentage, the blue light brightness percentage and the green light brightness percentage to control the LED light strip in the light deviation area.

10. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing an LED lighting intelligent control system as described in any one of claims 1-8.

Images