In-building illumination optimization and energy-saving control system based on artificial intelligence

Abstract

The invention relates to the technical field of illumination energy-saving control, in particular to an in-building illumination optimization and energy-saving control system based on artificial intelligence, and the system comprises an image collection module which is used for obtaining an indoor image; the area screening module is used for obtaining a shadow connected domain and a non-dynamic area according to the number of pixel points in an overlapped area of the suspected shadow connected domain in the same position area in the indoor image at each moment and a plurality of previous moments; the illumination change analysis module is used for obtaining a light intensity adjustment factor according to the difference between the overall contrast ratios of the same non-dynamic region in the indoor image at all moments and the slope and direction of a gray fitting straight line of all pixel points in the same non-dynamic region; and the optimization adjustment module is used for adjusting the original lamplight illumination intensity through the lamplight intensity adjustment factor to obtain the adjusted lamplight illumination intensity. According to the invention, the influence of hysteresis during illumination adjustment is reduced, and the energy consumption is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of lighting energy-saving control, and particularly to an indoor lighting optimization and energy-saving control system based on artificial intelligence. Background Art

[0002] In a building, lighting adjustment has an important impact on aspects such as the comfort of users, eye health, energy consumption management, building function optimization, and sustainable development. Existing indoor lighting optimization systems usually rely on preset time and thresholds to control the on / off of the lighting system, but this method cannot dynamically adapt to the indoor lighting needs according to different weather or season conditions. Most existing indoor lighting optimization systems use preset time and thresholds to control the lighting system to turn on or off the lights, and cannot adapt to the lighting needs under different weather or seasons; although some systems can adjust the brightness of indoor lighting according to the intensity of outdoor natural light, these systems lack the analysis of the lighting change trend and cannot predict lighting changes in advance, resulting in a lag in the adjustment of indoor light brightness, which affects the activity comfort and work efficiency of indoor personnel.

[0003] After the existing lighting adjustment system detects the change in the intensity of outdoor natural light, it usually cannot immediately adjust the brightness of indoor lights when the brightness changes, resulting in unstable indoor lighting levels. This delayed response affects the comfort of the indoor environment. Especially in the case of rapid changes in lighting needs, it cannot provide appropriate indoor lighting in a timely manner, thereby reducing the system's usage efficiency and increasing energy consumption. Summary of the Invention

[0004] The present invention provides an indoor lighting optimization and energy-saving control system based on artificial intelligence to solve the problem of lag in lighting adjustment of the existing energy-saving control system.

[0005] The indoor lighting optimization and energy-saving control system based on artificial intelligence of the present invention adopts the following technical solutions: An embodiment of the present invention provides an indoor lighting optimization and energy-saving control system based on artificial intelligence, and the system includes the following modules: Image acquisition module: used to acquire indoor images at a continuous number of moments; Region screening module: used to evenly divide the indoor image at each moment to obtain a number of position regions; perform edge detection on each position region in the indoor image at each moment to obtain the suspected shadow connected regions of each position region in the indoor image at each moment; screen out the shadow connected regions from the suspected shadow connected regions according to the number of pixel points in the overlapping region of the suspected shadow connected regions of the same position region in the indoor images at each moment and several previous moments; screen out the non-dynamic regions from all the position regions of the indoor image according to the proportion of the number of edge pixel points in the suspected shadow connected region of each position region in the indoor image at each moment and the number of edge pixel points in the overlapping region of all the shadow connected regions in the indoor images at each moment and several previous moments in the total number of edge pixel points in each position region of the indoor image at each moment. Lighting change analysis module: used to obtain the overall contrast of each non-dynamic region in the indoor image at each moment according to the gray histogram of each non-dynamic region in the indoor image at each moment; obtain the gray fitting line of each pixel point; obtain the change degree of the natural light intensity in the building interior according to the difference between the overall contrasts of the same non-dynamic region in the indoor images at all moments, the slope and direction of the gray fitting lines of all pixel points in the same non-dynamic region; perform negative mapping on the change degree of the natural light intensity in the building interior to obtain the lighting intensity adjustment factor. Optimization and adjustment module: used to obtain the original lighting intensity, and adjust the original lighting intensity through the lighting intensity adjustment factor to obtain the adjusted lighting intensity.

[0006] Further, the steps of evenly dividing the indoor image at each moment to obtain a number of position regions; performing edge detection on each position region in the indoor image at each moment to obtain the suspected shadow connected regions of each position region in the indoor image at each moment include: Evenly divide the indoor image at each moment into parts, then the indoor image at each moment obtains position regions; where represents the preset region quantity parameter; Perform edge detection on each position region in the indoor image at each moment through the canny edge detection algorithm to obtain all the edge pixel points in each position region in the indoor image at each moment; record the closed region formed by the edge pixel points in each position region in the indoor image at each moment as the suspected shadow connected region of each position region in the indoor image at each moment.

[0007] Further, the step of screening out the shadow connected regions from the suspected shadow connected regions according to the number of pixel points in the overlapping region of the suspected shadow connected regions of the same position region in the indoor images at each moment and several previous moments includes:

[0008] In the formula, represents the number of pixel points in the suspected shadow connected domain of the th position area in the indoor image at the th moment, represents the number of pixel points in the overlapping area of the suspected shadow connected domains of the indoor images at the th moment and the th moment in the th position area, represents the possibility that the th position area in the indoor image at the th moment is a suspected non-dynamic area, represents the number of several moments before each moment; For each position area in the indoor image at each moment where the possibility of the suspected non-dynamic area is greater than or equal to a preset first threshold , it is recorded as a suspected non-dynamic area; the suspected shadow connected domain in the suspected non-dynamic area is recorded as a shadow connected domain.

[0009] Furthermore, screening out non-dynamic areas from all position areas of the indoor image according to the proportion of the number of edge pixel points in the suspected shadow connected domain of each position area in the indoor image at each moment, and the number of edge pixel points in the overlapping area of all shadow connected domains in the indoor images at each moment and several moments before, in the total number of all edge pixel points in each position area of the indoor image at each moment, includes:

[0010] In the formula, represents the number of edge pixel points in the suspected shadow connected domain of the th position area in the indoor image at the th moment, represents the number of edge pixel points in the overlapping area of all shadow connected domains of the th position area in the indoor images at the th moment and all reference moments, represents the total number of all edge pixel points in the th position area in the indoor image at the th moment; represents the total number of all indoor images taken in time sequence; represents the possibility that the th position area in the indoor image is a non-dynamic area; Among them, before each moment a moment, denoted as the reference moment for each moment; among them, represents a preset reference quantity; The position area in the indoor image of each moment where the possibility of the non-dynamic area is greater than or equal to a preset first threshold is denoted as the non-dynamic area.

[0011] Furthermore, obtaining the overall contrast of each non-dynamic area in the indoor image of each moment according to the gray histogram of each non-dynamic area in the indoor image of each moment; obtaining the gray fitting line of each pixel point includes: Obtaining the gray histogram of each non-dynamic area in the indoor image of each moment, calculating the standard deviation of the number of pixel points corresponding to all gray values of the gray histogram of each non-dynamic area in the indoor image of each moment, and denoting the reciprocal of the standard deviation as the overall contrast of each non-dynamic area in the indoor image of each moment; Obtaining the gray values of all pixel points at the same position in the indoor images of all moments, and performing linear fitting on the gray values of all pixel points at the same position by the least squares method to obtain the gray fitting line of each pixel point.

[0012] Furthermore, obtaining the degree of change in the natural light intensity in the building interior according to the differences between the overall contrasts of the same non-dynamic area in the indoor images of all moments, the slopes and directions of the gray fitting lines of all pixel points in the same non-dynamic area, includes: According to the differences between the overall contrasts of the same non-dynamic area in the indoor images of all moments, the slopes of the gray fitting lines of all pixel points in the same non-dynamic area, obtaining the degree of change in the illumination of each non-dynamic area in the indoor image; according to the degree of change in the illumination of each non-dynamic area in the indoor image, the slope directions of the gray fitting lines of all pixel points within the non-dynamic area, obtaining the degree of change in the natural light intensity in the building interior.

[0013] Furthermore, obtaining the degree of change in the illumination of each non-dynamic area in the indoor image according to the differences between the overall contrasts of the same non-dynamic area in the indoor images of all moments, the slopes of the gray fitting lines of all pixel points in the same non-dynamic area, includes:

[0014] In the formula, represents the overall contrast of the th non-dynamic area in the indoor image of the th moment, represents the overall contrast of the th non-dynamic area in the indoor image of the th moment, Represents the total number of all indoor images captured in time sequence, Represents the maximum value of the slope of the gray-scale fitting straight line of all pixel points in the nth non-dynamic region, Represents the linear normalization function, Represents the degree of illumination change in the

[0015] nth non-dynamic region in the indoor image.

[0016] In the formula, Represents the degree of illumination change in the nth non-dynamic region in the indoor image, Represents the maximum value of the slope of the gray-scale fitting straight line of all pixel points in the nth non-dynamic region, Represents the absolute value symbol, Represents the set of all non-dynamic regions, Represents taking the minimum value from the set of all non-dynamic regions,

[0017] Represents the degree of change in natural light intensity in the building interior.

[0018] In the formula, Represents the degree of change in natural light intensity in the building interior, Represents the lighting intensity adjustment factor.

[0019] Furthermore, the adjustment of the original lighting illumination intensity by the lighting intensity adjustment factor to obtain the adjusted lighting illumination intensity includes:

[0020] In the formula, Represents the original lighting illumination intensity, Represents the adjusted lighting illumination intensity, Represents the lighting intensity adjustment factor.

[0021] The beneficial effects of the technical solution of the present invention are as follows: The indoor images at each moment are evenly divided to obtain several position regions; edge detection is performed on each position region in the indoor images at each moment to obtain the suspected shadow connected regions of each position region in the indoor images at each moment, improving the accuracy of analyzing the interference of local area movement factors; according to the number of pixel points in the overlapping regions of the suspected shadow connected regions of the same position region in the indoor images at each moment and several previous moments, the shadow connected regions are screened out from the suspected shadow connected regions; according to the proportion of the number of edge pixel points in the suspected shadow connected regions of each position region in the indoor images at each moment and the number of edge pixel points in the overlapping regions of all shadow connected regions in the indoor images at each moment and several previous moments in the total number of all edge pixel points in each position region in the indoor images at each moment, the non-dynamic regions are screened out from all position regions of the indoor images, improving the accuracy of analyzing the non-dynamic regions; according to the gray histogram of each non-dynamic region in the indoor images at each moment, the overall contrast of each non-dynamic region in the indoor images at each moment is obtained, improving the accuracy of local contrast analysis; the gray fitting line of each pixel point is obtained; according to the differences between the overall contrasts of the same non-dynamic region in the indoor images at all moments, the slopes and directions of the gray fitting lines of all pixel points in the same non-dynamic region, the change degree of the natural light intensity in the building interior is obtained; the negative mapping of the change degree of the natural light intensity in the building interior is performed to obtain the light intensity adjustment factor, improving the direction and accuracy of optimizing the light illumination intensity through the light intensity adjustment factor; the original light illumination intensity is adjusted through the light intensity adjustment factor to obtain the adjusted light illumination intensity, reducing the influence of hysteresis during light illumination adjustment and reducing energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0023] Figure 1 It is a module flowchart of the building interior lighting optimization and energy-saving control system based on artificial intelligence of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following specifically describes, in conjunction with the accompanying drawings and preferred embodiments, the specific implementation manner, structure, features, and effects of the artificial intelligence-based indoor lighting optimization and energy-saving control system proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0026] The following specifically describes the specific solution of the artificial intelligence-based indoor lighting optimization and energy-saving control system provided by the present invention in conjunction with the accompanying drawings.

[0027] Please refer to Figure 1 , which shows the module flowchart of the artificial intelligence-based indoor lighting optimization and energy-saving control system provided by an embodiment of the present invention. The system includes the following modules: Image acquisition module 101.

[0028] It should be noted that by installing a camera near each lamp, sequential images of the interior of the room are collected at equal intervals to analyze the trend of light intensity changes. By comparing the light intensity in consecutive images and performing time series analysis, the trend of natural light changes is predicted, and based on this, the brightness of artificial lighting is adjusted. The system provides real-time feedback and optimizes the lighting adjustment strategy to ensure that the indoor lighting always remains within the optimal range, while improving energy efficiency and comfort.

[0029] Specifically, a camera is installed near the lamps in the room, and then images are collected at a preset time interval to obtain a set of sequential indoor lighting images. Among them, one indoor lighting image is collected at each moment. Among them, in this embodiment, the preset time interval is [specific time] minutes. In this embodiment, the preset time interval is not specifically limited, and the implementer can determine it according to the specific situation.

[0030] The indoor lighting images are grayscaled to obtain indoor images; among them, the process of grayscaling the indoor lighting images is a well-known technology and will not be specifically described here.

[0031] Thus, a series of consecutive indoor images at different moments are obtained.

[0032] Region screening module 102.

[0033] It should be noted that when collecting images, if there is no interference from any moving objects indoors in a building, the trend of light illumination can be analyzed through indoor images in time series to make an adaptive adjustment of the indoor lighting in advance. However, in practice, there may be the movement of people or objects. At this time, there will be deviations in directly analyzing the light illumination trend through time series images. Therefore, first, the non-dynamic areas in the indoor images are screened, and the trend of light illumination is analyzed through the non-dynamic areas, which can improve the accuracy of analyzing the change trend of light illumination.

[0034] Furthermore, it should be noted that since the activities of people indoors are usually concentrated in certain positions, while other positions change relatively less. For example, in an office building, the activities at the desk positions are relatively frequent, while there are usually no significant changes in the positions of some large equipment and instruments. Therefore, it is first necessary to divide the indoor image into blocks, and screen out the non-dynamic areas in the indoor image according to the frequency of people's activities in each block area. That is, the more frequent the people's activities in a region, the greater the difference in gray-scale changes of the region in time series; while when the people's activities in a region are not frequent or even there is little activity, it means that the difference in gray-scale changes of the region in time series is smaller.

[0035] Specifically, the indoor image at each moment is evenly divided into position areas; where represents the parameter of the preset number of areas; where, in this embodiment, the parameter of the preset number of areas , and in this embodiment, the parameter of the preset number of areas is not specifically limited, and the implementer can determine it according to the specific situation.

[0036] It should be noted that since the change of natural light illumination usually does not change significantly in a short period of time, the non-dynamic areas in the indoor image can be judged and analyzed through the difference in gray-scale distribution or the edge overlap situation of the same position area in indoor images at multiple consecutive moments in time series. In order to determine the edge overlap situation of the same position area in adjacent indoor images in time series, the indoor image is first subjected to edge detection to obtain the edge pixel points of the indoor image at each moment, and the edge overlap situation is determined and analyzed according to the distribution of the edge pixel points.

[0037] Specifically, the canny edge detection algorithm is used to perform edge detection on each position area in the indoor image at each moment, and all the edge pixel points in each position area in the indoor image at each moment are obtained; the closed area formed by the edge pixel points in each position area in the indoor image at each moment is recorded as the suspected shadow connected domain of each position area in the indoor image at each moment. Thus, the suspected shadow connected domain of each position area in the indoor image at each moment is obtained through the above method.

[0038] Among them, the Canny edge detection algorithm is a well-known technology and will not be specifically described here.

[0039] It should be noted that by analyzing the overlapping degree of the suspected shadow connected regions corresponding to the same position area in the indoor images at several consecutive moments in time series, it is determined whether the position area is a suspected non-dynamic area; that is, the greater the overlapping degree of the suspected shadow connected regions corresponding to the same position area, the greater the possibility that the position area is a suspected non-dynamic area; the smaller the overlapping degree of the suspected shadow connected regions corresponding to the same position area, the smaller the possibility that the position area is a suspected non-dynamic area.

[0040] Specifically, according to the number of pixel points in the overlapping region of the suspected shadow connected regions of the same position area in the indoor images at each moment and several previous moments, the possibility that each position area in the indoor image at each moment is a suspected non-dynamic area is obtained; the possibility of the suspected non-dynamic area is specifically expressed by the formula:

[0041] In the formula, represents the number of pixel points in the suspected shadow connected region of the th position area in the indoor image at the th moment, represents the number of pixel points in the overlapping region of the suspected shadow connected regions of the th moment and the th moment in the indoor image of the th position area, represents the possibility that the th position area in the indoor image at the th moment is a suspected non-dynamic area; represents the number of several moments before each moment, where in this embodiment, the number of several moments before each moment is taken as 10. In this embodiment, the number of several moments before each moment is not specifically limited, and the implementer can determine it according to the specific situation.

[0042] Among them, represents the proportion of the number of pixel points in the overlapping region of the suspected shadow connected regions of the same position area in the indoor images at each moment and the previous moment in the total number of pixel points in the suspected shadow connected region of the same position area in the indoor image at each moment. When the proportion is larger, the overlapping degree is larger; when the proportion is smaller, the overlapping degree is smaller, that is, it indicates that there is a situation of people walking in this position area.

[0043] The possibility of the suspected non-dynamic area being greater than or equal to the preset first threshold Each position area in the indoor image at each moment is denoted as a suspected non-dynamic area; the suspected shadow connected domain in the suspected non-dynamic area is denoted as the shadow connected domain. Among them, a first threshold is preset in this embodiment , where the preset first threshold in this embodiment is not specifically limited, and the implementer can determine it according to the specific situation.

[0044] It should be noted that the greater the degree of overlap of the shadow areas of static objects at different moments in the same position area, the greater the possibility that the position area is a non-dynamic area; conversely, the smaller the possibility that the position area is a non-dynamic area.

[0045] Specifically, according to the number of edge pixel points in the suspected shadow connected domain of each position area in the indoor image at each moment, and the number of edge pixel points in the overlapping area of all shadow connected domains in the indoor images at each moment and all reference moments, the proportion in the total number of all edge pixel points in each position area in the indoor image at each moment, the possibility that each position area in the indoor image is a non-dynamic area is obtained; the possibility of the non-dynamic area is specifically expressed by the formula as follows:

[0046] In the formula, represents the number of edge pixel points in the suspected shadow connected domain of the th position area in the indoor image at the th moment, represents the number of edge pixel points in the overlapping area of all shadow connected domains of the th moment and all reference moments in the th position area in the indoor image, represents the total number of all edge pixel points in the th position area in the indoor image at the th moment; represents the total number of all indoor images taken in time sequence; represents the possibility that the th position area in the indoor image is a non-dynamic area. Among them, the moments before each moment are denoted as the reference moments of each moment; among them, represents the preset reference quantity; among them, the preset reference quantity in this embodiment , where the preset reference quantity in this embodiment is not specifically limited, and the implementer can determine it according to the specific situation.

[0047] Among them, It represents the proportion of the edge pixel points in the suspected shadow connected region among all the edge pixel points in the same position area. The larger the proportion, the greater the possibility that the position area is a non-dynamic area; conversely, the smaller the possibility that the position area is a non-dynamic area. It represents the proportion of the edge pixel points corresponding to the static object among all the edge pixel points in the same position area. The larger the proportion, the greater the possibility that the position area is a non-dynamic area; conversely, the smaller the possibility that the position area is a non-dynamic area.

[0048] The position areas in the indoor images at each moment where the possibility of the non-dynamic area is greater than or equal to a preset first threshold are recorded as non-dynamic areas.

[0049] Thus, the non-dynamic areas in the indoor images are obtained through the above method.

[0050] The illumination change analysis module 103.

[0051] It should be noted that since the change in natural light intensity usually changes gradually and will not suddenly change greatly, the change trend of natural light intensity in the current period can be obtained according to the change in light intensity in multiple continuously captured indoor images, so as to predict the degree of change in natural light intensity.

[0052] Furthermore, it should be noted that when the indoor brightness is strong, the colors of the captured images will be more vivid, that is, the image contrast is higher. Therefore, the change in light intensity in this area can be obtained according to the change in the gray distribution in the consecutive images. Since the colors in the captured images may be relatively single, such as floor tiles, white walls, etc., when the light intensity changes, the gray values of the pixel points in the image change uniformly. Analyzing only based on the gray distribution will misidentify such situations as no change in illumination. Therefore, it is also necessary to combine the gray change of individual pixel points to calculate the accurate change in light intensity. Since when the light is dim, some objects that were originally lighter in color will also become darker, that is, the gray values are lower. When the light intensity increases, these objects will gradually show their original colors, that is, the gray values will also gradually increase. Therefore, based on the image contrast intensity, combined with the gray change of individual pixel points in the image, the change trend of light intensity is calculated.

[0053] Specifically, obtain the gray histogram of each non-dynamic area in the indoor image at each moment, calculate the standard deviation of the number of pixel points corresponding to all gray values in the gray histogram of each non-dynamic area in the indoor image at each moment, and record the reciprocal of the standard deviation as the overall contrast of each non-dynamic area in the indoor image at each moment. Among them, the process of obtaining the gray histogram is a well-known technology and will not be specifically described here.

[0054] It should be noted that the change in the gray value of each pixel in the image is not only related to the light intensity, but also affected by the color of the object. For objects with darker colors, the change range of their gray values is smaller when the light changes; while for objects with lighter colors, their true colors may not be accurately represented when the light is weak, showing darker gray values, and as the light increases, the change range of the gray values is larger. Therefore, by analyzing the gray value changes of each pixel in the images taken multiple times, the change of regional illumination can be judged more accurately, especially for objects with lighter colors, which are more sensitive to light changes.

[0055] Furthermore, it should be noted that the gray value changes of light-colored objects can better reflect the trend changes of natural light because their brightness is more sensitive to light changes. Dark-colored objects have less reflected light, so their gray value changes have a weaker response to light. Therefore, if the purpose is to infer the change of light intensity through the gray value changes of objects in the image, light-colored objects will be more representative.

[0056] Specifically, obtain the gray values of all pixel points at the same position in the indoor images at all times, and perform linear fitting on the gray values of all pixel points at the same position by the least squares method to obtain the gray fitting line of each pixel point; among them, the least squares method is a well-known technology and will not be specifically described here.

[0057] According to the difference between the overall contrasts of the same non-dynamic region in the indoor images at all times and the slopes of the gray fitting lines of all pixel points in the same non-dynamic region, obtain the degree of illumination change of each non-dynamic region in the indoor image; the degree of illumination change is specifically expressed by the formula:

[0058] In the formula, represents the overall contrast of the th non-dynamic region in the indoor image at the th moment, represents the overall contrast of the th non-dynamic region in the indoor image at the th moment, represents the total number of all indoor images taken in time sequence, represents the maximum value of the slopes of the gray fitting lines of all pixel points in the th non-dynamic region, represents the linear normalization function, represents the degree of illumination change of the th non-dynamic region in the indoor image.

[0059] Among them, It represents the difference in the overall contrast of the same non-dynamic area in indoor images at all adjacent times in terms of time sequence. When this difference is larger, it indicates that the degree of illumination change in each non-dynamic area is greater; conversely, it indicates that the degree of illumination change in each non-dynamic area is smaller. When the maximum value of the slope of the gray-level fitting straight line of all pixel points in each non-dynamic area is larger, it indicates that the degree of illumination change in each non-dynamic area is greater; conversely, it indicates that the degree of illumination change in each non-dynamic area is smaller.

[0060] It should be noted that because the distances between different non-dynamic areas in the captured image and the window are different, in order to ensure that each non-dynamic area has sufficient illumination, the adjustment of the lights should be based on the illumination intensity of the area with the lowest natural light intensity at the current time period. Because only by analyzing the illumination changes in all other non-dynamic areas according to the illumination changes in the non-dynamic area with the lowest natural light intensity can all non-dynamic areas be adaptively adjusted when the natural light changes.

[0061] Furthermore, it should be noted that since the change in illumination has two directions, namely enhancement and reduction, in order to ensure that there is no wrong adjustment during the process of adjusting the lights, the change direction of the natural light is specified by the change direction of the slope of the gray-level fitting straight line of all pixel points in the non-dynamic area.

[0062] Specifically, according to the degree of illumination change in each non-dynamic area in the indoor image and the slope direction of the gray-level fitting straight line of all pixel points in the non-dynamic area, the degree of change in the natural light intensity in the building interior is obtained. The degree of change in the natural light intensity in the building interior is specifically expressed by the formula:

[0063] In the formula, represents the degree of illumination change in the th non-dynamic area in the indoor image, represents the th non-dynamic area, and the maximum value of the slope of the gray-level fitting straight line of all pixel points in it, represents the absolute value symbol, represents the set of all non-dynamic areas, represents taking the minimum value from the set of all non-dynamic areas, represents the degree of change in the natural light intensity in the building interior.

[0064] Among them, is used to specify the change direction of the natural light. It means that when the natural light is enhanced, this degree of change is a positive value, and when the natural light is reduced, this degree of change is a negative value.

[0065] It should be noted that when the natural light decreases gradually in time sequence, the indoor lighting should be enhanced at this time; when the natural light increases gradually in time sequence, the indoor lighting should be decreased at this time. Therefore, the adjustment is carried out through the negative mapping of the slope of the gray fitting line of the pixel points in the non-dynamic area.

[0066] Specifically, the degree of change in the intensity of natural light in the building interior is negatively mapped to obtain a lighting intensity adjustment factor; the lighting intensity adjustment factor is specifically expressed by the formula:

[0067] In the formula, represents the degree of change in the intensity of natural light in the building interior, represents the lighting intensity adjustment factor.

[0068] Thus, the lighting intensity adjustment factor is obtained through the above method.

[0069] Optimization adjustment module 104.

[0070] Obtain the original lighting intensity, and adjust the original lighting intensity through the lighting intensity adjustment factor to obtain the adjusted lighting intensity; the adjusted lighting intensity is specifically expressed by the formula:

[0071] In the formula, represents the original lighting intensity, represents the adjusted lighting intensity, represents the lighting intensity adjustment factor.

[0072] Thus, this embodiment is completed.

[0073] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. An artificial intelligence-based indoor lighting optimization and energy-saving control system, characterized in that, The system includes the following modules: Image acquisition module: used to acquire indoor images at a continuous number of moments; Region screening module: used to evenly divide the indoor image at each moment to obtain a number of position regions; perform edge detection on each position region in the indoor image at each moment to obtain suspected shadow connected regions for each position region in the indoor image at each moment; screen out the shadow connected regions from the suspected shadow connected regions according to the number of pixel points in the overlapping region of the suspected shadow connected regions of the same position region in the indoor images at each moment and several previous moments; screen out the non-dynamic regions from all the position regions of the indoor image according to the proportion of the number of edge pixel points in the suspected shadow connected region of each position region in the indoor image at each moment and the number of edge pixel points in the overlapping region of all the shadow connected regions in the indoor images at each moment and several previous moments in the total number of all edge pixel points in each position region of the indoor image at each moment; Lighting change analysis module: used to obtain the overall contrast of each non-dynamic region in the indoor image at each moment according to the gray histogram of each non-dynamic region in the indoor image at each moment; obtain the gray fitting line of each pixel point; obtain the change degree of the natural light intensity in the building interior according to the difference between the overall contrasts of the same non-dynamic region in the indoor images at all moments, the slope and direction of the gray fitting lines of all pixel points in the same non-dynamic region; Perform negative mapping on the change degree of the natural light intensity in the building interior to obtain the lighting intensity adjustment factor; Optimization adjustment module: used to obtain the original lighting intensity, and adjust the original lighting intensity through the lighting intensity adjustment factor to obtain the adjusted lighting intensity.

2. The lighting optimization and energy-saving control system in a building based on artificial intelligence according to claim 1, characterized in that, The step of evenly dividing the indoor image at each moment to obtain a number of position regions; The step of performing edge detection on each position region in the indoor image at each moment to obtain the suspected shadow connected region for each position region in the indoor image at each moment, including: Divide the indoor image at each moment equally into parts, then the indoor image at each moment obtains position areas; among them, represents the preset area quantity parameter; Perform edge detection on each position region in the indoor image at each moment through the canny edge detection algorithm to obtain all the edge pixel points in each position region in the indoor image at each moment; record the closed region formed by the edge pixel points in each position region in the indoor image at each moment as the suspected shadow connected region for each position region in the indoor image at each moment.

3. The artificial intelligence-based building interior lighting optimization and energy-saving control system according to claim 1, characterized in that, The step of screening out the shadow connected regions from the suspected shadow connected regions according to the number of pixel points in the overlapping region of the suspected shadow connected regions of the same position region in the indoor images at each moment and several previous moments, including: In the formula, represents the number of pixel points in the suspected shadow connected domain of the th position area in the indoor image at the th moment, represents the number of pixel points in the overlapping area of the suspected shadow connected domains of the th moment and the th moment in the th position area of the indoor image, represents the possibility that the th position area in the indoor image at the th moment is a suspected non-dynamic area, represents the number of several moments before each moment; For each position area in the indoor image at each moment where the probability of the suspected non-dynamic area is greater than or equal to a preset first threshold it is denoted as a suspected non-dynamic area; the suspected shadow connected domain in the suspected non-dynamic area is denoted as a shadow connected domain.

4. The artificial intelligence-based building interior lighting optimization and energy-saving control system according to claim 1, characterized in that, The step of screening out the non-dynamic regions from all the position regions of the indoor image according to the proportion of the number of edge pixel points in the suspected shadow connected region of each position region in the indoor image at each moment and the number of edge pixel points in the overlapping region of all the shadow connected regions in the indoor images at each moment and several previous moments in the total number of all edge pixel points in each position region of the indoor image at each moment, including: In the formula, represents the number of edge pixel points in the suspected shadow connected region of the -th position area in the indoor image at the -th moment, represents the number of edge pixel points in the overlapping region of all shadow connected regions of the -th moment and the indoor images at all reference moments in the -th position area, represents the total number of all edge pixel points in the -th position area in the indoor image at the -th moment; represents the total number of all indoor images taken in time series; represents the possibility that the -th position area in the indoor image is a non-dynamic area; Among them, the moments before each moment are denoted as the reference moments of each moment; among them, represents a preset reference quantity. The position area in the indoor image at each moment where the possibility of the non-dynamic area is greater than or equal to a preset first threshold is denoted as the non-dynamic area.

5. The artificial intelligence-based building interior lighting optimization and energy-saving control system according to claim 1, wherein, Obtain the overall contrast of each non-dynamic region in the indoor image at each moment according to the grayscale histogram of each non-dynamic region in the indoor image at each moment; Obtain the grayscale fitting line of each pixel point, including: Obtain the grayscale histogram of each non-dynamic region in the indoor image at each moment, calculate the standard deviation of the number of pixel points corresponding to all grayscale values of the grayscale histogram of each non-dynamic region in the indoor image at each moment, and denote the reciprocal of the standard deviation as the overall contrast of each non-dynamic region in the indoor image at each moment; Obtain the grayscale values of all pixel points at the same position in the indoor images at all moments, and perform linear fitting on the grayscale values of all pixel points at the same position by the least squares method to obtain the grayscale fitting line of each pixel point.

6. The artificial intelligence-based in-building lighting optimization and energy-saving control system according to claim 1, wherein Obtain the degree of change in the natural light intensity in the building interior according to the differences between the overall contrasts of the same non-dynamic region in the indoor images at all moments, the slopes and directions of the grayscale fitting lines of all pixel points in the same non-dynamic region, including: Obtain the degree of change in the illumination of each non-dynamic region in the indoor image according to the differences between the overall contrasts of the same non-dynamic region in the indoor images at all moments and the slopes of the grayscale fitting lines of all pixel points in the same non-dynamic region; obtain the degree of change in the natural light intensity in the building interior according to the degree of change in the illumination of each non-dynamic region in the indoor image and the slope directions of the grayscale fitting lines of all pixel points in the non-dynamic region.

7. The artificial intelligence-based in-building lighting optimization and energy-saving control system according to claim 6, characterized in that, Obtain the degree of change in the illumination of each non-dynamic region in the indoor image according to the differences between the overall contrasts of the same non-dynamic region in the indoor images at all moments and the slopes of the grayscale fitting lines of all pixel points in the same non-dynamic region, including: In the formula, represents the overall contrast of the th non-dynamic region in the indoor image at the th moment, represents the overall contrast of the th non-dynamic region in the indoor image at the th moment, represents the total number of all indoor images captured in time sequence, represents the maximum value of the slope of the gray-scale fitting line of all pixel points in the th non-dynamic region, represents the linear normalization function, represents the degree of illumination change of the th non-dynamic region in the indoor image.

8. The artificial intelligence-based indoor lighting optimization and energy-saving control system according to claim 6, characterized in that, Obtain the degree of change in the natural light intensity in the building interior according to the degree of change in the illumination of each non-dynamic region in the indoor image and the slope directions of the grayscale fitting lines of all pixel points in the non-dynamic region, including: In the formula, represents the degree of illumination change of the th non-dynamic area in the indoor image, represents the maximum value of the slopes of the gray-scale fitting lines of all pixel points in the th non-dynamic area, represents the absolute value symbol, represents the set of all non-dynamic areas, represents taking the minimum value from the set of all non-dynamic areas, represents the degree of change in the natural light intensity in the building interior.

9. The artificial intelligence-based building interior lighting optimization and energy-saving control system according to claim 1, characterized in that Perform negative mapping on the degree of change in the natural light intensity in the building interior to obtain a lighting intensity adjustment factor, including: In the formula, represents the change degree of natural light intensity in the building interior, represents the light intensity adjustment factor.

10. The artificial intelligence-based building interior lighting optimization and energy-saving control system according to claim 1, wherein Adjust the original lighting illumination intensity by the lighting intensity adjustment factor to obtain the adjusted lighting illumination intensity, including: In the formula, represents the original light illumination intensity, represents the adjusted light illumination intensity, represents the light intensity adjustment factor.

Images