A method and apparatus for adjusting light

Abstract

The application discloses a light adjusting method and device, and belongs to the technical field of light control. According to the overhead scene image of the current scene, the visual field direction of each human body in the scene is analyzed, the visual field area of each human body in the current scene is obtained by combining the human visual field angle range, the brightness weight of each light service area is obtained according to each visual field area, and the corresponding light equipment is adjusted to the adaptive brightness adjusting gear, so that the visual field attention demand of the personnel in the scene is ensured, the brightness of the non-visual field concentrated area in the scene is reduced, and the energy-saving effect is improved.

Description

Technical Field

[0001] This invention relates to the field of lighting control technology, and in particular to a lighting adjustment method and device. Background Technology

[0002] Current lighting systems generally suffer from core problems such as insufficient intelligence, poor user experience, and low energy efficiency. Traditional adjustment methods rely heavily on manual operation by users and lack the ability to perceive and process environmental information in real time. For example, they cannot adjust according to the lighting needs of people in the scene, resulting in many lighting systems operating at unnecessary full load for extended periods, causing significant energy waste. Summary of the Invention

[0003] To address the technical problems existing in the prior art, this invention provides a light adjustment method, comprising the following steps: Acquire a top-down view of the current scene and identify the position of each human body in the top-down view. Identify the field of vision orientation of the corresponding human body in each human body position; The visual field area of ​​each human in the current scene is obtained based on the orientation of the field of vision and the range of human visual field angles. Obtain the illumination service area of ​​each lighting device in the current scene; The brightness weights of each illumination service area are obtained based on each field of view area; Obtain the brightness adjustment level of each lighting device and the preset brightness weight threshold value of each brightness adjustment level. Adjust the brightness level of the corresponding lighting device according to the brightness weight and the preset brightness weight threshold value.

[0004] Furthermore, the step of identifying the human body position in the top-down scene image specifically involves identifying the human head in the top-down scene image using a preset first deep learning model, and using the pixel area occupied by the human head in the top-down scene image as the corresponding human body position.

[0005] Furthermore, the identification of the visual orientation of the corresponding human body at each position specifically involves: The two shoulders of the human body are identified in the top-down scene image using a pre-set second deep learning model; Extract the center point in the pixel area occupied by the two shoulders respectively, and connect the two center points to obtain the connecting line; Obtain the perpendicular bisector of the connecting line, and denote the two ends of the perpendicular bisector as the first direction and the second direction, respectively. The human feet are identified in the top-down scene image through a pre-defined third deep learning method, and the direction of the human feet is obtained. Obtain the angle between the first pointing direction and the corresponding foot pointing direction of the human body, and record it as the first angle; obtain the angle between the second pointing direction and the corresponding foot pointing direction of the human body, and record it as the second angle. If the first included angle is smaller than the second included angle, then the first direction is the direction of the human body's field of vision.

[0006] Furthermore, the step of obtaining the visual field area of ​​each human body in the current scene based on the field of vision orientation and the range of human visual field angles specifically involves: Obtain the center point of the pixel region occupied by the human head in the top-down scene image, and the endpoint of the human's field of vision, wherein the endpoint is the intersection of the field of vision and the image edge of the top-down scene image. Connect the center point with the corresponding endpoint to form the estimated line of sight for the corresponding human body; Based on the range of human field of vision, and using the estimated line of sight as the bisector of the range of human field of vision, two edge lines of the corresponding human field of vision are obtained in the top-down scene image. The pixel region enclosed by the two visual field angle edge lines and the image edge between the two visual field angle edge lines is taken as the visual field region of the corresponding human body.

[0007] Furthermore, the step of obtaining the brightness weight of each illumination service area based on each visual field region specifically involves: Convert all view areas to grayscale and set the grayscale value to 2; Overlay all the view areas, and increment the grayscale value of each pixel that is overlaid once; After the overlay is completed, the grayscale value of each pixel in the top-down scene image is counted, and the grayscale value of pixels that do not belong to any field of view is set to 1. The average gray value of each illumination service area is calculated as the brightness weight of the corresponding illumination service area.

[0008] Furthermore, the acquisition of the brightness adjustment level of each lighting device and the preset brightness weight threshold value of each brightness adjustment level specifically involves: Obtain the maximum adjustable brightness of each lighting device and the preset minimum brightness of each lighting service area in the current scene, and use the corresponding preset minimum brightness and maximum adjustable brightness as the brightness adjustment range of the corresponding lighting device. Each brightness adjustment range is divided into average segments as the brightness adjustment levels of the lighting device, and each brightness adjustment level corresponds to a preset brightness weight threshold. The number of average segments and the preset brightness weight threshold are set by the user. The higher the brightness adjustment level, the greater the brightness of the lighting device and the corresponding preset brightness weight threshold.

[0009] Furthermore, the step of adjusting the brightness level of the corresponding lighting device according to the brightness weight and the preset brightness weight threshold specifically involves: Calculate the absolute value of the difference between the brightness weight and each preset brightness weight threshold value, and take the brightness adjustment level corresponding to the preset brightness weight threshold value corresponding to the minimum value as the brightness adjustment level of the corresponding lighting device. If there are two minimum values, then take the brightness adjustment level corresponding to the preset brightness weight threshold value that is greater than the corresponding brightness weight as the brightness adjustment level of the corresponding lighting device.

[0010] The present invention also provides a light adjustment device, comprising: The first recognition module is used to acquire a top-down view of the current scene and identify the position of each human body in the top-down view. The second recognition module is used to identify the field of vision orientation of the corresponding human body in each human body position; The first acquisition module is used to acquire the field of vision area of ​​each human body in the current scene based on the field of vision orientation and the range of human field of vision angle. The second acquisition module acquires the illumination service area of ​​each lighting device in the current scene; The calculation module is used to obtain the brightness weight of each illumination service area based on each field of view area; The adjustment module is used to obtain the brightness adjustment level of each lighting device and the preset brightness weight threshold value of each brightness adjustment level, and adjust the brightness level of the corresponding lighting device according to the brightness weight and the preset brightness weight threshold value.

[0011] Furthermore, the identification of the visual orientation of the corresponding human body at each position specifically involves: The two shoulders of the human body are identified in the top-down scene image using a pre-set second deep learning model; Extract the center point in the pixel area occupied by the two shoulders respectively, and connect the two center points to obtain the connecting line; Obtain the perpendicular bisector of the connecting line, and denote the two ends of the perpendicular bisector as the first direction and the second direction, respectively. The human feet are identified in the top-down scene image through a pre-defined third deep learning method, and the direction of the human feet is obtained. Obtain the angle between the first pointing direction and the corresponding foot pointing direction of the human body, and record it as the first angle; obtain the angle between the second pointing direction and the corresponding foot pointing direction of the human body, and record it as the second angle. If the first included angle is smaller than the second included angle, then the first direction is the direction of the human body's field of vision.

[0012] Furthermore, the step of obtaining the visual field area of ​​each human body in the current scene based on the field of vision orientation and the range of human visual field angles specifically involves: Obtain the center point of the pixel region occupied by the human head in the top-down scene image, and the endpoint of the human's field of vision, wherein the endpoint is the intersection of the field of vision and the image edge of the top-down scene image. Connect the center point with the corresponding endpoint to form the estimated line of sight for the corresponding human body; Based on the range of human field of vision, and using the estimated line of sight as the bisector of the range of human field of vision, two edge lines of the corresponding human field of vision are obtained in the top-down scene image. The pixel region enclosed by the two visual field angle edge lines and the image edge between the two visual field angle edge lines is taken as the visual field region corresponding to the human body. Compared with the prior art, the beneficial effects of the present invention are as follows: This invention analyzes the field of vision orientation of each person in the scene based on the top-down scene image of the current scene, and obtains the field of vision area of ​​each person in the current scene by combining the human field of vision angle range. Based on each field of vision area, the brightness weight of each lighting service area is obtained, and the corresponding lighting equipment is adjusted to the appropriate brightness adjustment level. This ensures the field of vision illumination needs of people in the scene, and reduces the brightness of non-field of vision areas in the scene, thereby improving energy saving effect. By analyzing the predicted line of sight of the human body and combining it with the range of human field of vision angles, the accuracy of the assessment of the field of vision range of personnel is improved, thereby ensuring the brightness requirements within the field of vision range of personnel. At the same time, by superimposing the field of vision area and the gray value, the brightness weight of each lighting service area is analyzed to reflect the concentrated areas of the field of vision in the scene. The brightness level is adjusted according to the brightness weight, which further ensures the brightness requirements within the field of vision range of personnel while saving energy for lighting equipment in non-concentrated areas of the field of vision. Attached Figure Description

[0013] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This is a flowchart of a lighting adjustment method according to the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0017] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0018] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" and "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0019] Example 1 See Figure 1 As shown, the present invention provides a light adjustment method, which specifically includes the following steps: S1. Obtain a top-down view of the current scene and identify the position of each human body in the top-down view. S2. Identify the field of vision orientation of the corresponding human body in each human body position; S3. Obtain the field of vision area of ​​each human in the current scene based on the field of vision orientation and the range of human field of vision angle; S4. Obtain the illumination service area of ​​each lighting device in the current scene; S5. Obtain the brightness weight of each illumination service area based on each field of view area; S6. Obtain the brightness adjustment level of each lighting device and the preset brightness weight threshold value of each brightness adjustment level. Adjust the brightness level of the corresponding lighting device according to the brightness weight and the preset brightness weight threshold value.

[0020] S1. Obtain a top-down view of the current scene, and identify the positions of each human body in the top-down view: In step S1, the overhead view of the current scene can be acquired using a high-definition camera.

[0021] In step S1, the human body position of each person is identified in the top-down scene image. Specifically, the human head in the top-down scene image is identified by a preset first deep learning model, and the pixel area occupied by the human head in the top-down scene image is used as the corresponding human body position.

[0022] The first deep learning model is trained in advance using multiple different human head feature data as training samples. When identifying the position of each human body in the top-down scene image, it identifies whether there are human head features in the top-down scene image and uses the position of the identified human head features as the position of the corresponding human body in the top-down scene image.

[0023] In step S2, identifying the visual orientation of the corresponding human body at each human body position specifically involves: S21. Identify the two shoulders of the human body in the top-view scene image using a preset second deep learning model; S22. Extract the center point in the pixel area occupied by the two shoulders respectively and connect the two center points to obtain the connecting line; S23. Obtain the perpendicular bisector of the connecting line, and the two ends of the perpendicular bisector are respectively denoted as the first direction and the second direction. S24. Identify the human feet in the top-down scene image through a preset third deep learning method, and obtain the direction of the human feet. S25. Obtain the angle between the first pointing direction and the corresponding foot pointing direction of the human body, and record it as the first angle. Obtain the angle between the second pointing direction and the corresponding foot pointing direction of the human body, and record it as the second angle. S26. If the first included angle is less than the second included angle, then the first direction is the direction of the human body's field of vision.

[0024] The second deep learning model is trained in advance using multiple different human shoulder feature data as training samples to identify the two shoulders of each human body in the top-down scene image. The top-down scene image is input into the second deep learning model, and the pixel position regions of the two shoulders of the corresponding human body are output.

[0025] The third deep learning model was trained in advance using multiple different human foot morphology data as training samples.

[0026] In step S3, obtaining the visual field area of ​​each human body in the current scene based on the field of vision orientation and the range of human visual field angles specifically involves: S31. Obtain the center point of the pixel area occupied by the human head in the top-view scene image, and the endpoint of the human's field of vision, wherein the endpoint is the intersection of the field of vision and the image edge of the top-view scene image. S32. Connect the center point with the corresponding endpoint to form the estimated line of sight for the corresponding human body; S33. Based on the range of human field of vision, and using the estimated line of sight as the bisector of the range of human field of vision, obtain two edge lines of the field of vision corresponding to the human body in the top-view scene image. S34. The pixel region formed by the two visual field angle edge lines and the image edge between the two visual field angle edge lines is taken as the visual field region of the corresponding human body.

[0027] It should be noted that pixels crossed by the edge line of the field of view also belong to the corresponding human visual field area.

[0028] The human field of vision refers to the angle that the human eye can see in degrees, which is usually 124 degrees.

[0029] In step S4, the lighting service area of ​​the lighting equipment in the current scene is the area illuminated by the lighting equipment in the current scene. When the scene is large, the area that the lighting equipment provides lighting for the scene is limited. Therefore, in such scenes, lighting equipment is usually installed in different places, and each lighting equipment is responsible for the lighting of a certain area.

[0030] In step S5, obtaining the brightness weight of each illumination service area based on each visual field region specifically involves: S51. Convert all visual areas to grayscale and set the grayscale value to 2; S52. Overlay all the visual areas, and increment the gray value of each pixel that is overlaid once. For example, in a top-down view of a scene image, there are human body A and human body B. The pixels in the field of view of each body are pixel a and pixel b. Then the gray value of pixel a and pixel b is 3, and the gray value of the remaining pixels is 2.

[0031] S53. After the overlay is completed, the gray values ​​of each pixel in the top view scene image are counted, and the gray values ​​of pixels that do not belong to any field of view area are set to 1. S54. Calculate the average gray value of each illumination service area as the brightness weight of the corresponding illumination service area.

[0032] The average gray value of the illumination service area is the average gray value of the pixels contained in the illumination service area in the top-view scene image.

[0033] In step S6, obtaining the brightness adjustment level of each lighting device and the preset brightness weight threshold value of each brightness adjustment level specifically involves: S61. Obtain the maximum adjustable brightness of each lighting device and the preset minimum brightness of each lighting service area in the current scene, and use the corresponding preset minimum brightness and maximum adjustable brightness as the brightness adjustment range of the corresponding lighting device. S62. Divide each brightness adjustment range into average segments as the brightness adjustment levels of the lighting device, and each brightness adjustment level corresponds to a preset brightness weight threshold value. The number of average segments and the preset brightness weight threshold values ​​are set by the user. The higher the brightness adjustment level, the greater the brightness of the lighting device and the corresponding preset brightness weight threshold value.

[0034] In step S6, adjusting the brightness level of the corresponding lighting device according to the brightness weight and the preset brightness weight threshold specifically involves: Calculate the absolute value of the difference between the brightness weight and each preset brightness weight threshold value, and take the brightness adjustment level corresponding to the preset brightness weight threshold value corresponding to the minimum value as the brightness adjustment level of the corresponding lighting device. If there are two minimum values, then take the brightness adjustment level corresponding to the preset brightness weight threshold value that is greater than the corresponding brightness weight as the brightness adjustment level of the corresponding lighting device.

[0035] For example, a certain lighting device has three brightness levels, 1, 2, and 3, with preset brightness weight thresholds of 2, 6, and 10 respectively. If the brightness weight of the corresponding lighting service area is 3, the absolute values ​​of the differences between these values ​​and the preset brightness weight thresholds are calculated to be 1, 3, and 7 respectively. The minimum value is 1, so the lighting device is adjusted to level 1. If the brightness weight of the corresponding lighting service area is 4, the absolute values ​​of the differences between these values ​​and the preset brightness weight thresholds are calculated to be 2, 2, and 6 respectively. There are two minimum values, namely 2. Among these two minimum values, the brightness adjustment level corresponding to the preset brightness weight threshold value that is greater than the corresponding brightness weight is taken as the brightness adjustment level of the corresponding lighting device, that is, the lighting device is adjusted to level 2.

[0036] Example 2 The present invention also provides a light adjustment device, specifically comprising: The first recognition module is used to acquire a top-down view of the current scene and identify the position of each human body in the top-down view. The second recognition module is used to identify the field of vision orientation of the corresponding human body in each human body position; The first acquisition module is used to acquire the field of vision area of ​​each human body in the current scene based on the field of vision orientation and the range of human field of vision angle. The second acquisition module acquires the illumination service area of ​​each lighting device in the current scene; The calculation module is used to obtain the brightness weight of each illumination service area based on each field of view area; The adjustment module is used to obtain the brightness adjustment level of each lighting device and the preset brightness weight threshold value of each brightness adjustment level, and adjust the brightness level of the corresponding lighting device according to the brightness weight and the preset brightness weight threshold value.

[0037] The identification of the visual orientation of the corresponding human body at each position specifically involves: The two shoulders of the human body are identified in the top-down scene image using a pre-set second deep learning model; Extract the center point in the pixel area occupied by the two shoulders respectively, and connect the two center points to obtain the connecting line; Obtain the perpendicular bisector of the connecting line, and denote the two ends of the perpendicular bisector as the first direction and the second direction, respectively. The human feet are identified in the top-down scene image through a pre-defined third deep learning method, and the direction of the human feet is obtained. Obtain the angle between the first pointing direction and the corresponding foot pointing direction of the human body, and record it as the first angle; obtain the angle between the second pointing direction and the corresponding foot pointing direction of the human body, and record it as the second angle. If the first included angle is smaller than the second included angle, then the first direction is the direction of the human body's field of vision.

[0038] The process of obtaining the visual field area of ​​each human in the current scene based on the orientation of the field of vision and the range of human visual field angles is as follows: Obtain the center point of the pixel region occupied by the human head in the top-down scene image, and the endpoint of the human's field of vision, wherein the endpoint is the intersection of the field of vision and the image edge of the top-down scene image. Connect the center point with the corresponding endpoint to form the estimated line of sight for the corresponding human body; Based on the range of human field of vision, and using the estimated line of sight as the bisector of the range of human field of vision, two edge lines of the corresponding human field of vision are obtained in the top-down scene image. The pixel region enclosed by the two visual field angle edge lines and the image edge between the two visual field angle edge lines is taken as the visual field region of the corresponding human body.

[0039] The process of obtaining the brightness weights of each illumination service area based on each field of view is specifically as follows: Convert all view areas to grayscale and set the grayscale value to 2; Overlay all the view areas, and increment the grayscale value of each pixel that is overlaid once; After the overlay is completed, the grayscale value of each pixel in the top-down scene image is counted, and the grayscale value of pixels that do not belong to any field of view is set to 1. The average gray value of each illumination service area is calculated as the brightness weight of the corresponding illumination service area.

[0040] The specific steps for obtaining the brightness adjustment levels of each lighting device and the preset brightness weight threshold values ​​for each brightness adjustment level are as follows: Obtain the maximum adjustable brightness of each lighting device and the preset minimum brightness of each lighting service area in the current scene, and use the corresponding preset minimum brightness and maximum adjustable brightness as the brightness adjustment range of the corresponding lighting device. Each brightness adjustment range is divided into average segments as the brightness adjustment levels of the lighting device, and each brightness adjustment level corresponds to a preset brightness weight threshold. The number of average segments and the preset brightness weight threshold are set by the user. The higher the brightness adjustment level, the greater the brightness of the lighting device and the corresponding preset brightness weight threshold.

[0041] The process of adjusting the brightness level of the corresponding lighting device based on the brightness weight and a preset brightness weight threshold is as follows: Calculate the absolute value of the difference between the brightness weight and each preset brightness weight threshold value, and take the brightness adjustment level corresponding to the preset brightness weight threshold value corresponding to the minimum value as the brightness adjustment level of the corresponding lighting device. If there are two minimum values, then take the brightness adjustment level corresponding to the preset brightness weight threshold value that is greater than the corresponding brightness weight as the brightness adjustment level of the corresponding lighting device.

[0042] Example 3 The present invention also provides an electronic device, including: a processor, a transmitting device, an input device, an output device, and a memory. The processor may be implemented using a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit, or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory may be implemented using a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), and is used to store computer program code. The computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes a method as described in any of the above possible implementation methods.

[0043] Example 4 The present invention also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a processor of an electronic device, cause the processor to perform a method as described in any of the above possible implementations.

[0044] The beneficial effects of this invention are as follows: This invention analyzes the field of vision orientation of each person in the scene based on the top-down scene image of the current scene, and obtains the field of vision area of ​​each person in the current scene by combining the human field of vision angle range. Based on each field of vision area, the brightness weight of each lighting service area is obtained, and the corresponding lighting equipment is adjusted to the appropriate brightness adjustment level. This ensures the field of vision illumination needs of people in the scene, and reduces the brightness of non-field of vision areas in the scene, thereby improving energy saving effect. By analyzing the predicted line of sight of the human body and combining it with the range of human field of vision angles, the accuracy of the assessment of the field of vision range of personnel is improved, thereby ensuring the brightness requirements within the field of vision range of personnel. At the same time, by superimposing the field of vision area and the gray value, the brightness weight of each lighting service area is analyzed to reflect the concentrated areas of the field of vision in the scene. The brightness level is adjusted according to the brightness weight, which further ensures the brightness requirements within the field of vision range of personnel while saving energy for lighting equipment in non-concentrated areas of the field of vision.

[0045] In the description of this specification, the references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0046] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0047] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for adjusting lighting, characterized in that, Includes the following steps: Acquire a top-down view of the current scene and identify the position of each human body in the top-down view. Identify the field of vision orientation of the corresponding human body in each human body position; The visual field area of ​​each human in the current scene is obtained based on the orientation of the field of vision and the range of human visual field angles. Obtain the illumination service area of ​​each lighting device in the current scene; The brightness weights of each illumination service area are obtained based on each field of view area; Obtain the brightness adjustment level of each lighting device and the preset brightness weight threshold value of each brightness adjustment level. Adjust the brightness level of the corresponding lighting device according to the brightness weight and the preset brightness weight threshold value. Specifically, obtaining the brightness weight of each illumination service area based on each visual field region involves: Convert all view areas to grayscale and set the grayscale value to 2; Overlay all the view areas, and increment the grayscale value of each pixel that is overlaid once; After the overlay is completed, the grayscale value of each pixel in the top-down scene image is counted, and the grayscale value of pixels that do not belong to any field of view is set to 1. The average gray value of each illumination service area is calculated as the brightness weight of the corresponding illumination service area.

2. The light adjustment method according to claim 1, characterized in that, The step of identifying the human body position in the top-down scene image specifically involves identifying the human head in the top-down scene image using a preset first deep learning model, and using the pixel area occupied by the human head in the top-down scene image as the corresponding human body position.

3. The light adjustment method according to claim 1, characterized in that, The identification of the visual orientation of the corresponding human body at each position specifically involves: The two shoulders of the human body are identified in the top-down scene image using a pre-set second deep learning model; Extract the center point in the pixel area occupied by the two shoulders respectively, and connect the two center points to obtain the connecting line; Obtain the perpendicular bisector of the connecting line, and denote the two ends of the perpendicular bisector as the first direction and the second direction, respectively. The human feet are identified in the top-down scene image through a pre-defined third deep learning method, and the direction of the human feet is obtained. Obtain the angle between the first pointing direction and the corresponding foot pointing direction of the human body, and record it as the first angle; obtain the angle between the second pointing direction and the corresponding foot pointing direction of the human body, and record it as the second angle. If the first included angle is smaller than the second included angle, then the first direction is the direction of the human body's field of vision.

4. The light adjustment method according to claim 3, characterized in that, The process of obtaining the visual field area of ​​each human in the current scene based on the orientation of the field of vision and the range of human visual field angles is as follows: Obtain the center point of the pixel region occupied by the human head in the top-down scene image, and the endpoint of the human's field of vision, wherein the endpoint is the intersection of the field of vision and the image edge of the top-down scene image. Connect the center point with the corresponding endpoint to form the estimated line of sight for the corresponding human body; Based on the range of human field of vision, and using the estimated line of sight as the bisector of the range of human field of vision, two edge lines of the corresponding human field of vision are obtained in the top-down scene image. The pixel region enclosed by the two visual field angle edge lines and the image edge between the two visual field angle edge lines is taken as the visual field region of the corresponding human body.

5. The light adjustment method according to claim 1, characterized in that, The specific steps for obtaining the brightness adjustment levels of each lighting device and the preset brightness weight threshold values ​​for each brightness adjustment level are as follows: Obtain the maximum adjustable brightness of each lighting device and the preset minimum brightness of each lighting service area in the current scene, and use the corresponding preset minimum brightness and maximum adjustable brightness as the brightness adjustment range of the corresponding lighting device. Each brightness adjustment range is divided into average segments as the brightness adjustment levels of the lighting device, and each brightness adjustment level corresponds to a preset brightness weight threshold. The number of average segments and the preset brightness weight threshold are set by the user. The higher the brightness adjustment level, the greater the brightness of the lighting device and the corresponding preset brightness weight threshold.

6. The light adjustment method according to claim 5, characterized in that, The process of adjusting the brightness level of the corresponding lighting device based on the brightness weight and a preset brightness weight threshold is as follows: Calculate the absolute value of the difference between the brightness weight and each preset brightness weight threshold value, and take the brightness adjustment level corresponding to the preset brightness weight threshold value corresponding to the minimum value as the brightness adjustment level of the corresponding lighting device. If there are two minimum values, then take the brightness adjustment level corresponding to the preset brightness weight threshold value that is greater than the corresponding brightness weight as the brightness adjustment level of the corresponding lighting device.

7. A lighting adjustment device, employing the lighting adjustment method according to any one of claims 1 to 6, characterized in that, include: The first recognition module is used to acquire a top-down view of the current scene and identify the position of each human body in the top-down view. The second recognition module is used to identify the field of vision orientation of the corresponding human body in each human body position; The first acquisition module is used to acquire the field of vision area of ​​each human body in the current scene based on the field of vision orientation and the range of human field of vision angle. The second acquisition module acquires the illumination service area of ​​each lighting device in the current scene; The calculation module is used to obtain the brightness weight of each illumination service area based on each field of view area; The adjustment module is used to obtain the brightness adjustment level of each lighting device and the preset brightness weight threshold value of each brightness adjustment level, and adjust the brightness level of the corresponding lighting device according to the brightness weight and the preset brightness weight threshold value.

8. The lighting adjustment device according to claim 7, characterized in that, The identification of the visual orientation of the corresponding human body at each position specifically involves: The two shoulders of the human body are identified in the top-down scene image using a pre-set second deep learning model; Extract the center point in the pixel area occupied by the two shoulders respectively, and connect the two center points to obtain the connecting line; Obtain the perpendicular bisector of the connecting line, and denote the two ends of the perpendicular bisector as the first direction and the second direction, respectively. The human feet are identified in the top-down scene image through a pre-defined third deep learning method, and the direction of the human feet is obtained. Obtain the angle between the first pointing direction and the corresponding foot pointing direction of the human body, and record it as the first angle; obtain the angle between the second pointing direction and the corresponding foot pointing direction of the human body, and record it as the second angle. If the first included angle is smaller than the second included angle, then the first direction is the direction of the human body's field of vision.

9. The lighting adjustment device according to claim 8, characterized in that, The process of obtaining the visual field area of ​​each human in the current scene based on the orientation of the field of vision and the range of human visual field angles is as follows: Obtain the center point of the pixel region occupied by the human head in the top-down scene image, and the endpoint of the human's field of vision, wherein the endpoint is the intersection of the field of vision and the image edge of the top-down scene image. Connect the center point with the corresponding endpoint to form the estimated line of sight for the corresponding human body; Based on the range of human field of vision, and using the estimated line of sight as the bisector of the range of human field of vision, two edge lines of the corresponding human field of vision are obtained in the top-down scene image. The pixel region enclosed by the two visual field angle edge lines and the image edge between the two visual field angle edge lines is taken as the visual field region of the corresponding human body.

Images