Intelligent illumination control method, device and system based on image recognition

Abstract

The invention relates to an intelligent lighting control method, device and system based on image recognition. The method comprises the following steps: acquiring a real-time environment image of a lighting lamp in a current environment; acquiring real-time scene information and real-time light color information in the current environment according to the obtained real-time environment image; and according to the obtained real-time scene information and the real-time light color information, controlling the illumination lamp to adjust the color temperature of the illumination lamp so as to be matched with the current environment. According to the invention, the environment change can be sensed in real time, and the color temperature of the lamp is dynamically adjusted based on the actual demand of a user so as to improve the automation, personalization and intelligence level of smart home illumination.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent lighting, in particular to an intelligent lighting control method, device and system based on image recognition. BACKGROUND

[0002] Traditional intelligent lighting systems mainly control the color temperature of lamps and lanterns through preset lighting modes (such as reading mode, sleep mode, leisure mode, etc.) or manual adjustment by users. However, these methods have obvious limitations. On the one hand, preset modes are difficult to accurately match diverse environmental scenarios. For example, the intensity and color of natural light indoors vary greatly at different times, and indoor furnishings, decoration styles, and real-time activities (such as dining, working, and parent-child interaction) also affect lighting needs. However, existing preset modes cannot perceive these complex environmental changes, resulting in a mismatch between lighting effects and actual needs, affecting user experience.

[0003] On the other hand, manual adjustment relies on user subjective judgment and operation, lacking real-time and intelligence. Users need to frequently adjust the color temperature of lamps and lanterns according to their own feelings, which is not only cumbersome, but also different users have different preferences for lighting color temperature, making it difficult to meet individual needs. At the same time, manual adjustment cannot respond to dynamic changes in environmental light, such as sudden weather changes, indoor personnel and object position changes, etc., making the lighting system unable to maintain the best working state at all times.

[0004] Therefore, there is an urgent need for an intelligent lighting solution that can perceive environmental changes in real time and dynamically adjust the color temperature of lamps and lanterns based on actual user needs to improve the automation, personalization, and intelligence level of smart home lighting. SUMMARY

[0005] The present application provides an intelligent lighting control method, device and system based on image recognition, which can perceive environmental changes in real time and dynamically adjust the color temperature of lamps and lanterns based on actual user needs to improve the automation, personalization, and intelligence level of smart home lighting.

[0006] To solve the above technical problems, the present application provides an intelligent lighting control method based on image recognition, which comprises:

[0007] Obtaining real-time environmental images of lighting lamps and lanterns in the current environment;

[0008] According to the obtained real-time environmental images, obtaining real-time scene information and real-time light color information in the current environment;

[0009] According to the obtained real-time scene information and real-time light color information, controlling the lighting lamps and lanterns to adjust their color temperature to match the current environment.

[0010] Optionally, the real-time scene information and real-time light color information in the current environment are obtained according to the obtained real-time environment image, and the obtaining comprises:

[0011] The AI model based on image recognition performs scene recognition on the real-time environment image to obtain real-time scene information of the lighting lamp in the current environment.

[0012] The AI model based on image recognition performs light color recognition on the real-time environment image to obtain real-time light color information of the lighting lamp in the current environment.

[0013] The AI model comprises a scene recognition model and a light color recognition model.

[0014] Optionally, the AI model based on image recognition performs scene recognition on the real-time environment image to obtain real-time scene information of the lighting lamp in the current environment, and the performing comprises:

[0015] The scene recognition model based on image recognition performs scene analysis on the real-time environment image to obtain a current use scene of the lighting lamp in the current environment from the real-time environment image.

[0016] The current use scene comprises a work office scene, a life leisure scene, a sleep scene, and a learning scene.

[0017] Optionally, the AI model based on image recognition performs light color recognition on the real-time environment image to obtain real-time light color information of the lighting lamp in the current environment, and the performing comprises:

[0018] The light color recognition model based on image recognition performs light color analysis on the real-time environment image to obtain point color information from the real-time environment image.

[0019] The current picture color of the lighting lamp in the current environment is obtained according to the point color information of the real-time environment image.

[0020] The current picture color is calculated and processed to obtain real-time light color information of the lighting lamp in the current environment.

[0021] Optionally, the light color recognition model based on image recognition performs light color analysis on the real-time environment image to obtain point color information from the real-time environment image, and the performing comprises:

[0022] In response to a specific point region selected by a user from the real-time environment image, the light color recognition model based on image recognition performs light color analysis on the specific point region of the real-time environment image.

[0023] According to the light color analysis of the specific point position area, point position color information of the specific point position area of the real-time environment image is obtained;

[0024] Alternatively, in response to user selection of at least one of the plurality of real-time environment images, a light color analysis of each point position area of the selected real-time environment image is performed based on an image recognition light color recognition model;

[0025] According to the light color analysis of all point position areas of the real-time environment image, point position color information of the real-time environment image is obtained;

[0026] Alternatively, a light color analysis of each point position area of the real-time environment image is performed based on an image recognition light color recognition model;

[0027] According to the light color analysis of all point position areas of the real-time environment image, point position color information of the real-time environment image is obtained.

[0028] Optionally, the calculation and processing of the current picture color to obtain real-time light color information of the lighting lamp in the current environment includes:

[0029] Mode conversion is performed on the current picture color obtained from the real-time environment image to convert the current picture color in RGB mode into a converted picture color in HSV mode;

[0030] According to the obtained converted picture color in HSV mode, a first real-time distance and a second real-time distance of the hue angle of the converted picture color in HSV mode to red and green are calculated;

[0031] According to the obtained first real-time distance and second real-time distance, a weight value of red and green in the converted picture color in HSV mode is calculated;

[0032] According to the obtained weight value of red and green in the converted picture color, DUV of the lighting lamp in the current environment is calculated.

[0033] Optionally, according to the obtained real-time scene information and real-time light color information, the lighting lamp adjusts its color temperature to match the current environment, including:

[0034] According to the obtained current use scene and real-time light color information of the lighting lamp in the current environment, preliminary color temperature information of the lighting lamp is obtained;

[0035] According to the obtained DUV of the lighting lamp in the current environment, the DUV is mapped to the preliminary color temperature information of the lighting lamp to obtain the required color temperature information of the lighting lamp.

[0036] According to the obtained demand color temperature information of the lighting lamp, the lighting lamp is controlled to adjust its current color temperature to meet the requirement of the demand color temperature information, so that the current color temperature of the lighting lamp matches the current environment.

[0037] Optionally, the obtaining of the real-time environment image of the lighting lamp in the current environment comprises:

[0038] In response to a color temperature matching instruction of the user on the lighting lamp, the camera is controlled to obtain the real-time environment image of the lighting lamp in the current environment.

[0039] Optionally, the camera comprises a camera head arranged on the intelligent terminal device, or a camera head arranged on the lighting lamp, or a camera arranged in the environment where the lighting lamp is located.

[0040] In addition, the present application further provides an intelligent lighting control device based on image recognition, which comprises:

[0041] An environment image obtaining module is configured to obtain a real-time environment image of a lighting lamp in a current environment;

[0042] A scene and color obtaining module is configured to obtain real-time scene information and real-time light color information in the current environment according to the obtained real-time environment image;

[0043] A color temperature adjusting module is configured to control the lighting lamp to adjust its color temperature to match the current environment according to the obtained real-time scene information and real-time light color information.

[0044] In addition, the present application further provides an intelligent lighting system, which comprises:

[0045] A lighting lamp;

[0046] A camera is configured to collect a real-time environment image of the lighting lamp in a current environment;

[0047] A lamp controller is connected with the lighting lamp and the camera;

[0048] The lamp controller is configured to implement the intelligent lighting control method based on image recognition as described above.

[0049] In addition, the present application further provides a computer readable storage medium, wherein computer execution instructions are stored in the computer readable storage medium, and the computer execution instructions are configured to implement all method steps or part of method steps of the intelligent lighting control method based on image recognition as described above when executed by a processor.

[0050] The technical scheme provided by the present application has the following beneficial effects:

[0051] The real-time environment image of the lighting lamp in the current environment can be acquired, and the current scene of the lighting lamp is analyzed according to the real-time environment image, the scene type (i.e. real-time scene information) where the lighting lamp is located is determined, and the color temperature setting range of the lighting lamp can be determined according to the scene type where the lighting lamp is located; at the same time, the light color of the scene where the lighting lamp is located can be analyzed according to the real-time environment image, the light intensity and light color characteristics of the lighting lamp in the current scene (i.e. real-time light color information) are determined, so that the specific color temperature information of the lighting lamp can be further determined on the basis of determining the color temperature setting range of the lighting lamp according to the scene type where the lighting lamp is located, so that the light color temperature of the lighting lamp matches the current environment.

[0052] In this way, through the intelligent lighting control method based on image recognition provided by the present application, through real-time acquisition of environment images, combined with intelligent image recognition technology, the environment scene type, light intensity and light color can be accurately analyzed, the lighting effect of the lighting lamp can be dynamically adjusted, the lighting effect is highly matched with the environment, and the user experience is significantly improved. BRIEF DESCRIPTION OF DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0054] Figure 1 The structure schematic diagram of the intelligent lighting system described in the embodiment of the present application is shown in the figure;

[0055] Figure 2 The structure schematic diagram of the intelligent lighting system (when multiple lighting lamps are set) described in the embodiment of the present application is shown in the figure;

[0056] Figure 3 The step flowchart of the intelligent lighting control method based on image recognition described in the embodiment of the present application is shown in the figure;

[0057] Figure 4 The structure schematic diagram of the intelligent lighting system (when the lamp controller is set as the lamp body controller) described in the embodiment of the present application is shown in the figure;

[0058] Figure 5 The structure schematic diagram of the intelligent lighting system (when the lamp controller is set as the intelligent terminal device) described in the embodiment of the present application is shown in the figure;

[0059] Figure 6 The structure schematic diagram of the intelligent lighting control system based on image recognition described in the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0060] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of embodiments of the present application, rather than all embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work belong to the scope of protection of the present application.

[0061] In the prior art, the traditional intelligent lighting system mainly controls the color temperature of the lamps and lanterns through a preset lighting mode (such as a reading mode, a sleep mode, a leisure mode, etc.) or a manual adjustment mode of a user. However, these modes have obvious limitations, cannot perceive environmental changes in real time, cannot dynamically adjust the color temperature of the lamps and lanterns based on actual needs of the user, cannot detect the brightness and basic color parameters of the ambient light, cannot obtain overall visual information of the environment, cannot comprehensively consider the needs of the color temperature of complex factors such as environmental conditions and personnel activities, and cannot improve the automation, personalization and intelligent level of the lighting lamps and lanterns. Therefore, in order to solve the problems in the prior art, the present application proposes an intelligent lighting control method, device and system based on image recognition.

[0062] The present application proposes an intelligent lighting control method based on image recognition, which is applied to an intelligent lighting system 10. As shown in the figure, the intelligent lighting system 10 includes lighting lamps and lanterns 12 and a camera 14, and a lamp controller 16 connected to the lighting lamps and lanterns 12 and the camera 14, and the camera 14 and the lighting lamps and lanterns 12 can work through the lamp controller 16. Moreover, in the intelligent lighting system 10, one or more lighting lamps and lanterns 12 (as shown in the figure) can be arranged, and one or more lamp controllers 16 can also be arranged correspondingly; in addition, one or more cameras 14 can also be arranged. Figure 1 Figure 2 Specifically, as shown in the figure, the intelligent lighting control method based on image recognition can include the following steps:

[0063] Specifically, as shown in the figure, the intelligent lighting control method based on image recognition can include the following steps: Figure 3 S100, obtaining a real-time environmental image of the lighting lamps and lanterns 12 in the current environment;

[0064] S200, obtaining real-time scene information and real-time light color information in the current environment according to the obtained real-time environmental image;

[0065] S300, controlling the lighting lamps and lanterns 12 to adjust the color temperature thereof to match the current environment according to the obtained real-time scene information and real-time light color information.

[0066]

[0067] ​​The real-time environment image of the lighting lamp 12 in the current environment can be acquired, and the current scene of the lighting lamp 12 is analyzed according to the real-time environment image, the scene type in which the lighting lamp 12 is located (i.e. real-time scene information) is determined, and the color temperature setting range of the lighting lamp 12 can be determined according to the scene type in which the lighting lamp 12 is located. At the same time, the light color of the scene in which the lighting lamp 12 is located can be analyzed according to the real-time environment image, and the light intensity and light color characteristics of the lighting lamp 12 in the current scene (i.e. real-time light color information) are determined, so that the specific color temperature information of the lighting lamp 12 can be further determined on the basis of the color temperature setting range of the lighting lamp 12 determined according to the scene type in which the lighting lamp 12 is located, so that the light color temperature of the lighting lamp 12 matches the current environment in which it is located.

[0068] In this way, through the intelligent lighting control method based on image recognition provided by the present application, by real-time acquisition of environment images, combined with intelligent image recognition technology, the environment scene type, light intensity and light color can be accurately analyzed, the lighting effect of the lighting lamp 12 can be dynamically adjusted, the lighting effect is highly matched with the environment, and the user experience is significantly improved.

[0069] Further, in step S100, acquiring the real-time environment image of the lighting lamp 12 in the current environment can further include the following steps:

[0070] S110, acquiring the color temperature matching instruction of the user for the lighting lamp 12.

[0071] When the user needs to use the lighting lamp 12 for lighting, and the color temperature of the lighting lamp 12 when lighting meets the use demand, the color temperature matching instruction can be sent to the lamp controller 16 of the lighting lamp 12, and the lamp controller 16 of the lighting lamp 12 can receive the color temperature matching instruction.

[0072] For example, as shown in Figure 4 The lamp controller 16 of the lighting lamp 12 can be a self-provided lamp body controller 162, the lamp body controller 162 has a control button or a liquid crystal control panel or a voice input module, the user can trigger the color temperature matching instruction through the control button or the liquid crystal control panel, and the lamp body controller 162 can receive the color temperature matching instruction. Specifically, the user can press the control button on the lamp body controller 162 to trigger the color temperature matching instruction configured in the lamp body controller 162; or the user can press or touch the color temperature matching virtual identifier (such as a virtual button) on the liquid crystal control panel of the lamp body controller 162 to trigger the color temperature matching instruction configured in the lamp body controller 162; or the user can send the color temperature matching instruction to the lamp body controller 162 through the voice input module in a voice manner.

[0073] Moreover, as shown in Figure 5 not only the dedicated lamp controller 16 can be arranged to intelligently control the lighting lamp 12, but also the smart terminal device 164 can be communicatively connected (such as Bluetooth connection, WIFI connection) with the lighting lamp 12, so as to control the lighting lamp 12 through the smart terminal device 164, that is, the smart terminal device 164 can be set as the lamp controller 16. Specifically, the smart terminal device 164 can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart Internet of Things device, etc. Moreover, a lamp control program (such as a lamp control APP (Application)) can be configured on the smart terminal device 164, and the color temperature matching instruction can be triggered through the lamp control program.

[0074] S120, in response to the color temperature matching instruction of the user about the lighting lamp 12, the camera 14 is controlled to acquire a real-time environment image of the lighting lamp 12 in the current environment.

[0075] After receiving the color temperature matching instruction, the lamp controller 16 of the lighting lamp 12 can respond to the color temperature matching instruction, that is, control the camera 14 to take a picture of the environment (i.e. the current environment) where the lighting lamp 12 is located, and collect a real-time environment image of the environment where the lighting lamp 12 is located. Moreover, the collected real-time environment image can include one, or multiple (such as taking pictures of the environment where the lighting lamp 12 is located from multiple angles).

[0076] Moreover, the camera 14 can include a camera 142 arranged on the smart terminal device 164, or a camera 142 arranged on the lighting lamp 12, or a camera 142 arranged in the environment where the lighting lamp 12 is located. That is, the camera 14 can include a camera 142 arranged on a smart phone, or a tablet computer, or a notebook computer, or a desktop computer, or a smart Internet of Things device, that is, the current environment where the lighting lamp 12 is located can be photographed through the camera 142 on the smart terminal device 164, and a real-time environment image of the current environment can be acquired.

[0077] In this embodiment, the camera 14 can include a camera 142 arranged on a smart phone, when the user triggers the color temperature matching instruction through the lamp control program (such as the lamp control APP) configured on the smart phone, the lamp controller 16 can send a picture shooting instruction to the camera 142, and control the camera 142 of the smart phone to shoot and collect the image of the environment where the lighting lamp 12 is located. Moreover, when shooting and collecting the image of the environment where the lighting lamp 12 is located, the camera 142 can be completely automatically controlled to shoot the image, or the camera 142 can be semi-automatically controlled to shoot the image (the camera 142 of the smart phone can be automatically called when shooting, and the camera 142 can be triggered to shoot by the user's click, or touch, or voice, or gesture when shooting).

[0078] In addition, when the camera 142 provided on the lighting lamp 12, i.e. the camera 142 provided integrally with the lighting lamp 12, photographs the environment where the lighting lamp 12 is located, the photographing can be automatically performed under the control of the lamp controller 16. In addition, when the camera 142 provided in the environment where the lighting lamp 12 is located, such as the independent camera 142 provided in conjunction with the lighting lamp 12, can be placed at a position capable of photographing the current environment in the largest range, and can be automatically photographed under the control of the lamp controller 16. Moreover, the independent camera 142 can also use other camera equipment, such as a monitoring camera 142 used for monitoring the current environment as the camera 142 of the lighting lamp 12.

[0079] In addition, in step S200, the real-time scene information and the real-time light color information of the current environment are obtained according to the obtained real-time environment image, which can further include the following steps:

[0080] S210, the AI model based on image recognition performs scene recognition on the real-time environment image to obtain the real-time scene information of the lighting lamp 12 in the current environment;

[0081] S220, the AI model based on image recognition performs light color recognition on the real-time environment image to obtain the real-time light color information of the lighting lamp 12 in the current environment;

[0082] The AI model includes a scene recognition model and a light color recognition model.

[0083] After the real-time environment image of the environment (i.e. the current environment) where the lighting lamp 12 is located is collected by the camera 142, the real-time environment image can be analyzed by the AI model based on image recognition, the current scene (i.e. the real-time scene information) where the lighting lamp 12 is located is determined according to the real-time environment image, and the light intensity and color characteristics (i.e. the real-time light color information) of the lighting lamp 12 in the current scene are detected.

[0084] Further, in step S210, the AI model based on image recognition performs scene recognition on the real-time environment image to obtain the real-time scene information of the lighting lamp 12 in the current environment, which can further include:

[0085] S212, the scene recognition model based on image recognition performs scene analysis on the real-time environment image to obtain the current use scene of the lighting lamp 12 in the current environment from the real-time environment image;

[0086] The current use scene includes a work office scene, a life leisure scene, a sleep scene, and a learning scene.

[0087] After obtaining the real-time environment image of the current environment where the lighting lamp 12 is located, the scene recognition model based on the AI model of image recognition can be used to determine the specific scene where the lighting lamp 12 is located from the real-time environment image. That is, the scene recognition model can be used to identify and determine which of the working office scene, the living and leisure scene, the sleep scene, and the learning scene the lighting lamp 12 is located in from the real-time environment image. Moreover, the above-mentioned various scenes can be further subdivided according to the needs and actual conditions. For example, the working office scene can include the office office scene and the factory workshop production scene, etc. In addition, the working scene of the lighting lamp 12 can also include more types of scenes according to the needs and actual conditions.

[0088] Moreover, the above-mentioned step S210 can further include the following steps:

[0089] S214, based on the current geographic location where the lighting lamp 12 is located, obtaining real-time location information and real-time time information of the lighting lamp 12 in the current use scene.

[0090] In actual conditions, not only the working scene of the lighting lamp 12 affects its color temperature demand, but also the geographic location (i.e. real-time location information) and the time (i.e. real-time time information) where the lighting lamp 12 is located also affect its color temperature demand. Because the sunlight illumination conditions of different geographic locations (such as high latitude locations, low latitude locations, etc.) are different, the corresponding lighting color temperature demands are also different; moreover, the sunlight illumination conditions of different time periods (such as morning period, noon period, night period, etc.) are also different, and the corresponding lighting color temperature demands are also different.

[0091] Moreover, the geographic location (i.e. real-time location information) and the time (i.e. real-time time information) where the lighting lamp 12 is located can be obtained according to the positioning device and the timing device (provided on the lamp controller 16) provided on the lighting lamp 12, or can be obtained from the Internet or the smart terminal device 164 through a communication connection mode.

[0092] Moreover, in step S220, the real-time light color information of the lighting lamp 12 in the current environment obtained by the light color recognition of the real-time environment image based on the AI model of image recognition can further include:

[0093] S222, the light color recognition model based on image recognition analyzes the light color of the real-time environment image to obtain the point color information from the real-time environment image.

[0094] In the scene recognition model based on the AI model of image recognition, when the working scene of the lighting lamp 12 is acquired from the real-time environment image, the light color of the lighting lamp 12 can also be analyzed and acquired from the real-time environment image by the light color recognition model based on the AI model of image recognition. At this time, the point color information on the real-time environment image can be acquired by the light color recognition model, so as to acquire the real-time light color information of the lighting lamp 12 in the current environment according to the point color information on the real-time environment image.

[0095] Moreover, the point color information can be the color information at one point or multiple points on the real-time environment image, and the acquisition of the point color information can be triggered by the selection of the user or automatically acquired by the light color recognition model. Because the real-time environment image can have multiple colors, the acquired point color information needs to be the most representative color of the real-time environment image. For example, if the real-time environment image is yellow as a whole, the acquired point color information is the yellow color; if the real-time environment image is green as a whole, the acquired point color information is the green color.

[0096] S224, acquiring the current picture color of the lighting lamp 12 in the current environment according to the obtained point color information of the real-time environment image.

[0097] According to the representative point color information selected from the real-time environment image, the overall color information of the real-time environment image can be acquired, so that the current picture color of the lighting lamp 12 in the current environment can be obtained. For example, if it is detected that the selected point color is yellow, it is proved that the overall color of the real-time environment image presents yellow, that is, it can be judged that the current picture color of the lighting lamp 12 in the current environment is yellow; if it is detected that the selected point color is green, it is proved that the overall color of the real-time environment image presents green, that is, it can be judged that the current picture color of the lighting lamp 12 in the current environment is green.

[0098] S226, calculating and processing the current picture color to acquire the real-time light color information of the lighting lamp 12 in the current environment.

[0099] After obtaining the overall color (i.e. the current picture color) of the real-time environment image, the current picture color can be analyzed to detect the real-time light color information such as the intensity of the light, the color of the light, and the like. According to the real-time light color information, the overall color tone (such as cool tone, warm tone, and the like) presented by the real-time environment image and the environment where the lighting lamp 12 is located can be obtained.

[0100] Further, in step S222, the light color recognition model based on image recognition performs light color analysis on the real-time environment image to obtain point color information from the real-time environment image, which can further include:

[0101] S2221, in response to the user selecting a specific point region on the real-time environment image, the light color recognition model based on image recognition performs light color analysis on the specific point region of the real-time environment image.

[0102] At this time, the user can actively select a specific point region on the displayed real-time environment image when the device displays the acquired real-time environment image through the display interface, so as to trigger the analysis and processing of the selected specific point region on the real-time environment image by the lamp controller 16.

[0103] S2222, according to the light color analysis of the specific point region, the point color information of the specific point region of the real-time environment image is obtained.

[0104] In this embodiment, the user can select a local region (i.e. a specific point region) on the real-time environment image, and analyze the specific point region selected by the user through the light color recognition model based on image recognition to determine the overall color presented by the real-time environment image. At this time, the overall color of the real-time environment image can be determined according to the user, and the overall color of the real-time environment image can be represented by the user selecting a local region on the real-time environment image that can represent the overall color, or by the user selecting a color of a local region on the real-time environment image that can represent the user's preference.

[0105] In addition, in other embodiments, step S222 can further include the following steps:

[0106] S2223, in response to the user selecting at least one real-time environment image from a plurality of real-time environment images, the light color recognition model based on image recognition performs light color analysis on each point region of the selected real-time environment image;

[0107] S2224, according to the light color analysis of all point regions of the real-time environment image, the point color information of the real-time environment image is obtained.

[0108] In the embodiment, the user can select one or more real-time environment images as a whole, or select a local region (i.e., a specific point region) on one or more real-time environment images, and analyze the one or more real-time environment images or the specific point region on the one or more real-time environment images selected by the user through the light color recognition model based on image recognition, to determine the overall color presented by the one or more real-time environment images. At this time, the overall color of the one or more real-time environment images can be determined according to the user, and the one or more real-time environment images or the local region thereon representing the overall color can be selected by the user, or the one or more real-time environment images or the local region thereon representing the color preferred by the user can be selected by the user.

[0109] In addition, in other embodiments, step S222 can further include the following steps:

[0110] S2225, the light color recognition model based on image recognition analyzes the light color of each point region of the real-time environment image;

[0111] S2226, according to the light color analysis of all point regions of the real-time environment image, the point color information of the real-time environment image is obtained.

[0112] In the embodiment, the color information of each point region of the real-time environment image can be automatically obtained, so as to analyze the overall color feature of the entire real-time environment image. For example, if it is detected that the color of part of the point regions on the real-time environment image is yellow, the color of part of the point regions is green, and the color of part of the point regions is blue, and the proportion of the green point regions is large (such as more than half of the overall color proportion, which can be pre-set according to actual conditions).

[0113] In step S226, the current picture color is calculated and processed to obtain the real-time light color information of the lighting lamp 12 in the current environment, which can further include:

[0114] S22262, the current picture color in the RGB (Red, Green, Blue) mode is converted into a converted picture color in the HSV (Hue, Saturation, Value) mode through mode conversion.

[0115] Generally, the image acquired by the camera 14 is an RGB mode picture, and it is more convenient to perceive and adjust the color by converting the current picture color in RGB mode into HSV mode (HSV is a color model commonly used in digital images, design and color processing, which describes color through three dimensions of hue (Hue, reflecting the "category" of color (such as red, green, blue)), saturation (Saturation, reflecting the brightness of color), and value (Value, reflecting the light and dark degree of color), which is more in line with the intuitive perception of human eyes to color than the RGB model). The current picture color in HSV mode can be decomposed into three independent dimensions of "hue (H), saturation (S), and value (V)", and the color can be adjusted more intuitively and efficiently, which is suitable for visual interaction scenarios.

[0116] S22264, according to the obtained converted picture color in HSV mode, calculating the first real-time distance and the second real-time distance of the hue angle (i.e. hue H) of the converted picture color in HSV mode to red and green, or the third real-time distance and the fourth real-time distance of the hue angle (i.e. hue H) to blue and yellow.

[0117] In the HSV color model, the value range of the hue angle (H) is 0°-360°, forming a closed loop color wheel. When calculating the distance of a certain hue angle to red (0°) and green (120°) (or the distance to blue and yellow), the closed loop characteristic needs to be considered, that is, the distance of the hue angle is not a simple numerical difference, but an angle difference of the "shortest path". As known from the above, the converted picture color is the current picture color obtained from the point color information of the real-time environment image, that is, the overall color of the real-time environment image. According to the hue angle (i.e. hue H) of the converted picture color, the corresponding distance (i.e. the first real-time distance and the second real-time distance) can be obtained according to the calculation formula of a certain hue angle and red (0°) and green (120°) in the prior art, or the corresponding distance (i.e. the third real-time distance and the fourth real-time distance) can be obtained according to the calculation formula of a certain hue angle and blue (240°) and yellow (60°).

[0118] S22266, according to the obtained first real-time distance and second real-time distance, or third real-time distance and fourth real-time distance, calculating the weight value of red and green, or the weight value of blue and yellow in the converted picture color in HSV mode.

[0119] In the HSV color model, when calculating the weight value according to the distance of hue angle to red (0°) and green (120°), or the distance of blue (240°) and yellow (60°), the closer the distance, the greater the weight, that is, the closer the hue to a certain color (red / green), the higher the weight of that color, and generally the total weight sum needs to be controlled (such as normalized to the range of 0-1, or the total sum is 1). The specific weight value calculation method can be set and calculated according to the prior art and actual needs. Among them, the sum of the red weight value (w red) and the green weight value (w green) is 1, and the sum of the blue weight value (w blue) and the yellow weight value (w yellow) is 1.

[0120] S22268, according to the obtained weight values of red and green in the color of the converted picture, calculating the DUV of the lighting lamp 12 in the current environment.

[0121] In the context of color science and visual perception, DUV (Deviation from Unity, color deviation coefficient) is usually used to describe the balance deviation between two complementary colors (such as red and green, blue and yellow), and to quantify the degree of color deviation to one pole. When calculating DUV in combination with red weight value (w red) and green weight (w green), or blue weight value (w blue) and yellow weight value (w yellow), the specific method is to measure the degree of color deviation on the red-green axis or the blue-yellow axis through the difference or ratio of the two, and the value range is usually [-1, 1] (-1 represents pure green deviation or pure yellow deviation, 1 represents pure red deviation or pure blue deviation, and 0 represents balance).

[0122] Moreover, in step S300, according to the obtained real-time scene information and real-time light color information, the lighting lamp 12 is controlled to adjust its color temperature to match the current environment, which can further include:

[0123] S310, according to the obtained current use scene of the lighting lamp 12 in the current environment and the real-time light color information, obtaining the preliminary color temperature information of the lighting lamp 12.

[0124] In the working office scene, the life leisure scene, the sleep scene, and the learning scene, different scenes can correspond to different illumination color temperatures of the lighting lamp 12, so that the illumination color temperature of the lighting lamp 12 matches the scene in which it is located. For example, when the lighting lamp 12 is in the working office scene, the illumination color temperature of the lighting lamp 12 can correspond to a first preliminary preset color temperature range; when the lighting lamp 12 is in the life leisure scene, the illumination color temperature of the lighting lamp 12 can correspond to a second preliminary preset color temperature range; when the lighting lamp 12 is in the sleep scene, the illumination color temperature of the lighting lamp 12 can correspond to a third preliminary preset color temperature range; and when the lighting lamp 12 is in the learning scene, the illumination color temperature of the lighting lamp 12 can correspond to a fourth preliminary preset color temperature range. Moreover, the first preliminary preset color temperature range, the second preliminary preset color temperature range, the third preliminary preset color temperature range, and the fourth preliminary preset color temperature range can be pre-set and adjusted according to actual conditions. Moreover, according to the subdivision scenes of each large type of scene, the corresponding preliminary preset color temperature range can be correspondingly subdivided and matched.

[0125] Moreover, in combination with the preliminary preset color temperature range corresponding to different working scenes, the preliminary preset color temperature range can be further adjusted according to different geographical positions and different time periods to obtain preliminary color temperature information (including the first preliminary color temperature range, the second preliminary color temperature range, the third preliminary color temperature range, the fourth preliminary color temperature range, and the like).

[0126] S320, according to the obtained DUV of the lighting lamp 12 in the current environment, mapping the DUV to the preliminary color temperature information of the lighting lamp 12 to obtain the required color temperature information of the lighting lamp 12.

[0127] From the above content, it can be known that the DUV of the lighting lamp 12 in the current environment can be obtained according to the real-time light color information of the lighting lamp 12 in the current environment. Moreover, in the field of color science and illumination, color temperature and DUV are two core indicators for describing the color characteristics of a light source, and both of them jointly determine the visual coldness and color accuracy of the light source, but have different divisions, in which the color temperature defines the macroscopic coldness and warmth, and the DUV corrects the microscopic color deviation. Therefore, after determining the preliminary color temperature information through the current use scene of the lighting lamp 12 in the current environment, the preliminary color temperature information can be corrected to obtain accurate required color temperature information according to the DUV obtained from the real-time light color information.

[0128] S330, according to the obtained required color temperature information of the lighting lamp 12, controlling the lighting lamp 12 to adjust the current color temperature to meet the requirements of the required color temperature information, so that the current color temperature of the lighting lamp 12 matches the current environment.

[0129] The intelligent lighting control method based on image recognition provided in the present application can be applied to the field of intelligent lighting, and can realize accurate adjustment of the color temperature of intelligent lighting by performing deep analysis on the environment image based on the visual recognition technology of the camera 142 and the artificial intelligence technology.

[0130] In addition, the present application also provides an intelligent lighting control device 100 based on image recognition, which is applied to the intelligent lighting system 10. Figure 1 As shown in the figure, the intelligent lighting system 10 comprises the lighting lamp 12 and the camera 14, and the lamp controller 16 connected with the lighting lamp 12 and the camera 14, and the camera 14 and the lighting lamp 12 can be controlled to work through the lamp controller 16.

[0131] Specifically, as shown in the figure, the intelligent lighting control device 100 based on image recognition can comprise: Figure 5

[0132] The environment image acquisition module 102 is configured to acquire the real-time environment image of the lighting lamp 12 in the current environment;

[0133] The scene and color acquisition module 104 is configured to acquire the real-time scene information and the real-time light color information in the current environment according to the obtained real-time environment image;

[0134] The color temperature adjustment module 106 is configured to control the lighting lamp 12 to adjust its color temperature to match the current environment according to the obtained real-time scene information and real-time light color information.

[0135] The intelligent lighting control device 100 based on image recognition described in the present embodiment corresponds to the intelligent lighting control method based on image recognition described above, and the functions of each module in the intelligent lighting control device 100 based on image recognition in the present embodiment are described in detail in the corresponding method embodiment, which will not be described here.

[0136] In addition, as shown in the figure, the present application also provides an intelligent lighting system 10, which comprises the lighting lamp 12 and the camera 14 for acquiring the real-time environment image of the lighting lamp 12 in the current environment, and the lamp controller 16 connected with the lighting lamp 12 and the camera 14. The lamp controller 16 is configured to control the lighting lamp 12 and the camera 14 to work, that is, to control the camera 14 to acquire the real-time environment image of the lighting lamp 12 in the current environment, and to analyze the real-time environment image to acquire the real-time scene information and the real-time light color information in the current environment, and then to control the lighting lamp 12 to adjust its color temperature to match the current environment according to the real-time scene information and the real-time light color information. Figure 1 In addition, as shown in the figure, the present application also provides an intelligent lighting system 10, which comprises the lighting lamp 12 and the camera 14 for acquiring the real-time environment image of the lighting lamp 12 in the current environment, and the lamp controller 16 connected with the lighting lamp 12 and the camera 14. The lamp controller 16 is configured to control the lighting lamp 12 and the camera 14 to work, that is, to control the camera 14 to acquire the real-time environment image of the lighting lamp 12 in the current environment, and to analyze the real-time environment image to acquire the real-time scene information and the real-time light color information in the current environment, and then to control the lighting lamp 12 to adjust its color temperature to match the current environment according to the real-time scene information and the real-time light color information.​

[0137] Specifically, the lamp controller 16 is configured to implement the image recognition based intelligent lighting control method as described above. The specific implementation can refer to the specific content of the image recognition based intelligent lighting control method as described above, and will not be repeated here.

[0138] In addition, the present application also provides a computer readable storage medium, the computer readable storage medium stores computer execution instructions, the computer execution instructions are executed by the processor to implement all method steps or part of method steps of the image recognition based intelligent lighting control method as described above.

[0139] In addition, the present application also provides a computer program product, the computer program product is used for running on the computer to implement the image recognition based intelligent lighting control method as described above.

[0140] The present application can implement all or part of the above method, and can also be completed by a computer program to instruct the related hardware. The computer program can be stored in a computer readable storage medium. When the processor executes the computer program, the steps of the above method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium can include any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content of the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to the legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0141] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The processor is the control center of the computer device, and connects all parts of the computer device through various interfaces and lines.

[0142] The memory can be used to store computer programs and / or models. The processor realizes various functions of the computer device by running or executing the computer programs and / or models stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area. The program storage area can store an operating system and at least one application program required by a function (such as a sound playing function, an image playing function, etc.). The data storage area can store data created according to the use of the mobile phone (such as audio data, video data, etc.). In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0143] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, a server or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage, etc.) containing computer-usable program code.

[0144] The present application is described in reference to the appended drawings figures and / or block diagrams of methods, apparatus (systems), servers, and computer program products according to embodiments of the application. It will be understood that each block of the flowchart and / or block diagrams, and combinations of blocks in the flowchart and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 one or more flowcharts and / or blocks

[0145] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flowchart and / or block diagram block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 one or more flowcharts and / or blocks

[0146] The computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flowchart and / or block diagram block or blocks. Figure 1 one or more flowcharts and / or blocks ​ one or more flowcharts and / or blocks

[0147] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. An image recognition-based intelligent lighting control method, characterized by, The method comprises: acquiring a real-time environment image of the lighting lamp in the current environment; acquiring real-time scene information and real-time light color information of the current environment according to the obtained real-time environment image; controlling the lighting lamp to adjust its color temperature to match the current environment according to the obtained real-time scene information and real-time light color information. 2.The image recognition based intelligent lighting control method according to claim 1, characterized in that, The method comprises: performing scene recognition on the real-time environment image based on an AI model of image recognition to acquire real-time scene information of the lighting lamp in the current environment; performing light color recognition on the real-time environment image based on an AI model of image recognition to acquire real-time light color information of the lighting lamp in the current environment; The AI model comprises a scene recognition model and a light color recognition model. 3.The image recognition based intelligent lighting control method according to claim 2, characterized in that, The method comprises: performing scene analysis on the real-time environment image based on a scene recognition model of image recognition to acquire a current use scene of the lighting lamp in the current environment from the real-time environment image; The current use scene comprises a work office scene, a life leisure scene, a sleep scene, and a learning scene.

4. The image recognition based intelligent lighting control method according to claim 3, wherein, The method comprises: performing light color analysis on the real-time environment image based on a light color recognition model of image recognition to acquire point color information from the real-time environment image; acquiring a current picture color of the lighting lamp in the current environment according to the point color information of the real-time environment image; performing calculation and processing on the current picture color to acquire real-time light color information of the lighting lamp in the current environment.

5. The image recognition based intelligent lighting control method according to claim 4, wherein, The method comprises: performing light color analysis on a specific point area selected by a user on the real-time environment image based on a light color recognition model of image recognition; acquiring point color information of the specific point area of the real-time environment image according to the light color analysis on the specific point area; or, performing light color analysis on each point area of the real-time environment image selected by a user from a plurality of real-time environment images based on a light color recognition model of image recognition; acquiring point color information of the real-time environment image according to the light color analysis on all point areas of the real-time environment image; or, performing light color analysis on each point area of the real-time environment image based on a light color recognition model of image recognition; According to the light color analysis of all point areas of the real-time environment image, the point color information of the real-time environment image is obtained. 6.The image recognition based intelligent lighting control method according to claim 4, characterized in that, The calculation and processing of the current picture color to obtain the real-time light color information of the lighting lamp in the current environment includes: Mode conversion is performed on the current picture color obtained from the real-time environment image, and the current picture color in RGB mode is converted into a converted picture color in HSV mode. According to the converted picture color in HSV mode, the first real-time distance and the second real-time distance of the hue angle of the converted picture color in HSV mode to red and green are calculated. According to the first real-time distance and the second real-time distance obtained, the weight values of red and green in the converted picture color in HSV mode are calculated. According to the weight values of red and green in the converted picture color obtained, the DUV of the lighting lamp in the current environment is calculated. 7.The image recognition based intelligent lighting control method according to claim 6, wherein, According to the real-time scene information and the real-time light color information obtained, the lighting lamp adjusts its color temperature to match the current environment, including: According to the current use scene and the real-time light color information of the lighting lamp in the current environment obtained, the preliminary color temperature information of the lighting lamp is obtained. According to the DUV of the lighting lamp in the current environment obtained, the DUV is mapped into the preliminary color temperature information of the lighting lamp to obtain the required color temperature information of the lighting lamp. According to the required color temperature information of the lighting lamp obtained, the lighting lamp adjusts its current color temperature to meet the requirements of the required color temperature information, so that the current color temperature of the lighting lamp matches the current environment. 8.The image recognition based intelligent lighting control method according to claim 1, wherein, The real-time environment image of the lighting lamp in the current environment is obtained, including: In response to the color temperature matching instruction of the user on the lighting lamp, the camera is controlled to obtain the real-time environment image of the lighting lamp in the current environment. 9.The image recognition based intelligent lighting control method according to claim 8, wherein, The camera includes a camera on the intelligent terminal device, or a camera on the lighting lamp, or a camera in the environment where the lighting lamp is located.

10. An image recognition based intelligent lighting control device, characterized in that, The device includes: An environment image acquisition module for obtaining a real-time environment image of a lighting lamp in a current environment; A scene and color acquisition module for obtaining real-time scene information and real-time light color information in the current environment according to the real-time environment image obtained; A color temperature adjustment module for controlling the lighting lamp to adjust its color temperature to match the current environment according to the real-time scene information and the real-time light color information obtained.

11. An intelligent lighting system characterized by It includes: A lighting lamp; A camera for capturing a real-time environment image of a lighting lamp in a current environment; A lamp controller connected to the lighting lamp and the camera; The lamp controller is used to implement the intelligent lighting control method based on image recognition as claimed in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to implement all method steps or part of the method steps of the intelligent lighting control method based on image recognition as claimed in any one of claims 1-9.

Images