Brightness self-adaptive adjusting method and system of intelligent blackboard

Abstract

The invention provides a brightness adaptive adjustment method and system for an intelligent blackboard, and the method comprises the steps: collecting and obtaining illumination intensity data in real time, and constructing an illumination intensity matrix; eye reaction information of students in different directions in a classroom is monitored and acquired in real time, and an eye reaction index matrix is constructed; constructing a brightness adjustment controller based on a fuzzy logic control theory, taking the comprehensive illumination intensity value and the comprehensive eye reaction index as input, and performing fuzzification, fuzzy reasoning and defuzzification operations through the brightness adjustment controller to output a brightness adjustment value; and adjusting the display screen brightness of the smart blackboard according to the brightness adjustment value. According to the invention, self-adaptive automatic adjustment of the brightness of the blackboard is realized, the teaching efficiency and the user experience are improved, and the brightness of the blackboard can be adjusted in real time according to the environment illumination change and the eye comfort requirements of students, so that a more comfortable and healthy teaching visual environment is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of smart blackboards, and in particular to a method and system for adaptively adjusting the brightness of a smart blackboard. Background Art

[0002] With the development of educational informatization, smart blackboards have become an important teaching tool in modern classrooms. In the actual use of smart blackboards, the brightness of the blackboard needs to be properly adjusted to ensure students' visual comfort.

[0003] Traditional blackboard brightness adjustment usually relies on manual settings, which is not only cumbersome to operate, but also difficult to adapt to changes in ambient lighting and students' visual needs in real time, making it difficult to scientifically and maximally ensure the visual comfort of most students in the classroom. Summary of the invention

[0004] Based on this, the purpose of the present invention is to propose a method and system for adaptively adjusting the brightness of a smart blackboard to solve the above-mentioned problems.

[0005] According to a method for adaptively adjusting brightness of a smart blackboard proposed by the present invention, the method comprises:

[0006] Optical sensors are evenly arranged in a matrix around the smart blackboard to collect light intensity data in real time and construct a light intensity matrix;

[0007] Real-time monitoring to obtain eye reaction information of students in different positions in the classroom, and construct an eye reaction index matrix, wherein the eye reaction information includes pupil changes and blinking frequency;

[0008] Performing fusion processing on the illumination intensity matrix to obtain a comprehensive illumination intensity value;

[0009] Performing fusion processing on the eye response index matrix to obtain a comprehensive eye response index;

[0010] Based on fuzzy logic control theory, a brightness adjustment controller is constructed, and the comprehensive light intensity value and the comprehensive eye reaction index are used as inputs, and fuzzification, fuzzy reasoning and defuzzification operations are performed by the brightness adjustment controller to output a brightness adjustment value;

[0011] According to the brightness adjustment value, the display screen brightness of the smart blackboard is adjusted to perform adaptive adjustment of the brightness of the smart blackboard.

[0012] Furthermore, the step of constructing a brightness adjustment controller based on fuzzy logic control theory, taking the comprehensive light intensity value and the comprehensive eye reaction index as input, and performing fuzzification, fuzzy reasoning and defuzzification operations through the brightness adjustment controller to output a brightness adjustment value includes:

[0013] The comprehensive light intensity value α and the comprehensive eye reaction index β are defined as input variables, and the brightness adjustment value γ is defined as an output variable;

[0014] The input variables α and β and the output variable γ are divided into a first input fuzzy set, a second input fuzzy set and an output fuzzy set respectively;

[0015] A series of fuzzy rules are established to describe the adjustment of γ according to different combinations of input variables α and β;

[0016] According to the values ​​of input variables α and β and the established fuzzy rules, fuzzy reasoning is performed to determine the membership of the output fuzzy set;

[0017] Based on the membership of the output fuzzy set, the output fuzzy set is converted into a specific brightness adjustment value γ through the defuzzification method.

[0018] Furthermore, the step of performing fuzzy reasoning according to the values ​​of the input variables α and β and the established fuzzy rules to determine the membership of the output fuzzy set includes:

[0019] Take the minimum value of the membership values ​​corresponding to the input variables α and β to calculate the activation of each fuzzy rule. The calculation formula is: Activation = min(μA(α), μB(β)), where μA(α) is the membership of the input variable α corresponding to the first input fuzzy set A, and μB(β) is the membership of the input variable β corresponding to the second input fuzzy set B. The min function means taking the smaller value of the two.

[0020] According to the activation degree of the fuzzy rule and the consequent of the fuzzy rule, the membership degree of the output fuzzy set is determined. The calculation formula is: μC(γ) = activation degree * μC rule (γ), where μC(γ) is the membership function of the output variable γ corresponding to the output fuzzy set C, C rule (γ) the membership degree of C in the consequent of the fuzzy rule;

[0021] If multiple fuzzy rules are activated, the output of each fuzzy rule is aggregated by taking the maximum value method to obtain the membership degree of each element point of the final output fuzzy set. The calculation formula is: μC final (γ)=max(μC1(γ),μC2(γ),...,μC n (γ)), ​​where μC final(γ) is the membership degree of the final output fuzzy set C at the element γ point, μC1(γ), μC2(γ), ..., μC n (γ) is the membership degree of each rule output.

[0022] Furthermore, the step of converting the output fuzzy set into a specific brightness adjustment value γ based on the membership of the output fuzzy set by a defuzzification method includes:

[0023] Determine each element γ in the output fuzzy set C i The membership degree μC(γ i );

[0024] Combine each element γ in the output fuzzy set C i The membership degree and its corresponding value are used to calculate the specific brightness adjustment value γCOG. The calculation formula is: γCOG=(Σ[μC(γ i )*γ i ]) / (ΣμC(γ i )), where Σ represents the summation, μC(γ i ) is the element γ in the output fuzzy set C i The membership degree, γ i are the values ​​of each element in the output fuzzy set C.

[0025] Furthermore, the step of fusing the illumination intensity matrix to obtain a comprehensive illumination intensity value includes:

[0026] All elements in the light intensity matrix are weighted averaged to obtain a comprehensive light intensity value.

[0027] Furthermore, the step of fusing the eye reaction index matrix to obtain a comprehensive eye reaction index includes:

[0028] All elements in the eye response index matrix are weighted averaged to obtain a comprehensive eye response index.

[0029] Furthermore, the step of adjusting the display brightness of the smart blackboard according to the brightness adjustment value to perform adaptive adjustment of the brightness of the smart blackboard also includes:

[0030] The content displayed on the smart blackboard is enhanced in real time through the GAN algorithm to present high-quality and clear images in real time.

[0031] Furthermore, the step of enhancing the content displayed on the smart blackboard in real time by using the GAN algorithm includes:

[0032] Collect blackboard images under different brightness conditions and annotate them to distinguish clear and blurred areas;

[0033] Preprocess the collected images, including cropping, scaling, and normalization operations;

[0034] Design a generator that takes in a low-quality blackboard image and outputs an enhanced high-quality, clear image.

[0035] Design a discriminator to distinguish the image output by the generator from the real clear blackboard image;

[0036] The generator and discriminator are trained through the adversarial loss function, where the goal of the generator is to generate realistic images to deceive the discriminator in order to maximize the probability that the discriminator makes mistakes, and the goal of the discriminator is to distinguish between real images and generated images;

[0037] Deploy the trained generator model to a real-time system;

[0038] The image of the smart blackboard is input into the trained generator, and the generator generates and outputs the enhanced image, which is displayed in real time on the smart blackboard interface.

[0039] The present invention also provides a brightness adaptive adjustment system for a smart blackboard, the system comprising:

[0040] Light intensity acquisition module: used to evenly arrange optical sensors in a matrix around the smart blackboard to collect light intensity data in real time and build a light intensity matrix;

[0041] Eye response acquisition module: used to monitor and acquire the eye response information of students in different positions in the classroom in real time, and construct an eye response index matrix. The eye response information includes pupil changes and blinking frequency.

[0042] A first fusion processing module: used for performing fusion processing on the illumination intensity matrix to obtain a comprehensive illumination intensity value;

[0043] A second fusion processing module: used for fusing the eye reaction index matrix to obtain a comprehensive eye reaction index;

[0044] Fuzzy logic control module: used to construct a brightness adjustment controller based on fuzzy logic control theory, and take the comprehensive light intensity value and the comprehensive eye reaction index as input, and perform fuzzification, fuzzy reasoning and defuzzification operations through the brightness adjustment controller to output a brightness adjustment value;

[0045] Brightness adjustment module: used to adjust the display brightness of the smart blackboard according to the brightness adjustment value to perform adaptive adjustment of the brightness of the smart blackboard.

[0046] In summary, according to the above-mentioned method for adaptively adjusting the brightness of a smart blackboard, optical sensors are evenly arranged in a matrix form around the smart blackboard to collect real-time and comprehensive light intensity data around the blackboard, and construct a light intensity matrix to provide accurate and reliable ambient light information; the eye response information of students in different positions of the classroom is monitored in real time, including pupil changes and blinking frequency, and an eye response index matrix is ​​constructed. These data not only reflect the visual comfort of the entire classroom students, but also indirectly reflect the suitability of the current blackboard brightness. Therefore, based on these data, the blackboard brightness can be adjusted more humanely to take care of the visual needs of most students in the classroom as much as possible; by adjusting the light intensity The intensity matrix and the eye reaction index matrix are fused and processed to obtain a comprehensive light intensity value and a comprehensive eye reaction index; Brightness adjustment based on fuzzy logic: The present invention adopts fuzzy logic control theory to construct a brightness adjustment controller, which can handle the uncertainty and ambiguity in the input comprehensive light intensity value and the comprehensive eye reaction index. Through the operations of fuzzification, fuzzy reasoning and defuzzification, the system can output a brightness adjustment value that conforms to the current environment and satisfies the comfort of students. This adjustment method not only improves the flexibility and adaptability of brightness adjustment, but also ensures the rationality and comfort of the adjustment result; then according to the output value of the brightness adjustment controller, the brightness of the display screen of the smart blackboard is automatically adjusted. The brightness adaptive adjustment method of the smart blackboard of the present invention not only realizes the adaptive automatic adjustment of the blackboard brightness, improves the teaching efficiency and user experience, but also enables the blackboard to realize real-time adjustment of the brightness according to the changes in ambient light and the comfort requirements of students' eyes, thereby providing a more comfortable and healthy teaching visual environment.

[0047] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description or will be learned through embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0049] Figure 1 This is a flow chart of a method for adaptively adjusting brightness of a smart blackboard according to Embodiment 1 of the present invention;

[0050] Figure 2 This is a system block diagram of a brightness adaptive adjustment system for a smart blackboard according to Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0051] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0052] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0054] Embodiment 1

[0055] See also Figure 1 The present invention proposes a method for adaptively adjusting brightness of a smart blackboard, the method comprising steps S101 to S106:

[0056] S101, evenly arranging optical sensors in a matrix form around the smart blackboard to collect and obtain light intensity data in real time and construct a light intensity matrix;

[0057] It is understandable that arranging optical sensors in a matrix-like and uniform manner around the smart blackboard can ensure that the optical sensors can fully and accurately sense the lighting conditions around the blackboard. This layout not only covers all directions of the blackboard, but also effectively avoids blind spots in light perception, thereby more realistically reflecting the overall lighting conditions of the environment where the blackboard is located.

[0058] All sensor data is transmitted to the blackboard control system wirelessly or wiredly to obtain real-time light intensity data, so that changes in ambient light can be continuously tracked. This is crucial for subsequent brightness adjustment, because ambient light is an important factor affecting the blackboard display effect and students' visual comfort. Real-time data collection ensures that the system can respond promptly according to actual lighting conditions.

[0059] The system integrates the light intensity data collected by each sensor into a matrix, thus forming a comprehensive view of the ambient light intensity. This matrix not only contains the numerical information of the light intensity, but also implies the spatial characteristics of the light distribution.

[0060] S102, real-time monitoring and acquisition of eye reaction information of students at different positions in the classroom, and construction of an eye reaction index matrix, wherein the eye reaction information includes pupil changes and blinking frequency.

[0061] Understandably, infrared sensors or cameras can be used to capture the eye reactions of students at different locations in the classroom. Since students at the same location are in similar ambient lighting conditions, their eye reactions also have certain similarities. Therefore, by monitoring students at different locations, comprehensive and representative data about the visual status of students in the entire classroom can be obtained. At each location, the eye reaction information of several students can be collected and averaged, thereby reducing the impact of abnormal values ​​of individual students' eye reactions on the overall data, improving the stability and reliability of the data, and making the obtained data more representative and more able to reflect the general visual status of students at that location.

[0062] Real-time monitoring of students' eye response information, especially pupil changes and blinking frequency, is crucial to assessing the suitability of the current blackboard brightness. Pupil changes are a direct reflection of the eye's response to light intensity, while blinking frequency is closely related to visual fatigue and discomfort. By continuously tracking these indicators, the system can understand students' visual status in a timely manner and provide a strong basis for subsequent brightness adjustment.

[0063] In the process of constructing the eye response index matrix, the system integrates and standardizes the eye response information collected by each sensor or camera. This not only enables data from different sources to be compared and analyzed at the same scale, but also reflects the spatial characteristics of the data.

[0064] S103, performing fusion processing on the illumination intensity matrix to obtain a comprehensive illumination intensity value.

[0065] Understandably, all elements in the light intensity matrix can be weighted averaged to obtain a comprehensive light intensity value, which is a comprehensive indicator reflecting the overall ambient light conditions. Weighted average not only takes into account the light data collected by each sensor, but also needs to balance the influence of light intensity at different locations through the distribution of weights, thereby ensuring the comprehensiveness and accuracy of the data, making the comprehensive light intensity value closer to the actual ambient light conditions, so that the brightness of the smart blackboard can be adaptively adjusted according to the actual ambient light conditions.

[0066] S104, performing fusion processing on the eye reaction index matrix to obtain a comprehensive eye reaction index.

[0067] Understandably, all elements in the eye response index matrix can be weighted averaged to obtain a comprehensive eye response index. This processing method can comprehensively consider the eye response data of students in different directions to ensure that the visual state of each student is effectively paid attention to. Through weighted averaging, a more representative index can be obtained, which accurately reflects the overall eye response of students in the classroom, including key information such as pupil changes and blinking frequency. This comprehensive eye response index enables the smart blackboard to adaptively adjust the brightness according to the real-time visual needs of students, thereby providing a more comfortable and healthy learning environment.

[0068] S105, constructing a brightness adjustment controller based on fuzzy logic control theory, and taking the comprehensive light intensity value and the comprehensive eye reaction index as input, performing fuzzification, fuzzy reasoning and defuzzification operations through the brightness adjustment controller to output a brightness adjustment value.

[0069] It can be understood that a brightness adjustment controller is constructed based on fuzzy logic control theory, and the brightness adjustment value is output through fuzzification, fuzzy reasoning and defuzzification operations, so that the smart blackboard of the present invention can adaptively adjust the brightness according to the ambient lighting and students' eye reactions. This adjustment method not only improves the usability and comfort of the blackboard, but also helps to protect students' eyesight health and improves the overall quality of the teaching environment.

[0070] This embodiment adopts fuzzy logic control theory to enable the system to handle the uncertainty and ambiguity in the brightness adjustment process well, which is more in line with the complexity and variability of the actual environment. In the process of generating the brightness adjustment value, this embodiment can convert the comprehensive light intensity value and the comprehensive eye reaction index into the membership value in the fuzzy set through fuzzification, so that the nonlinear relationship between these inputs and the brightness adjustment can be described more flexibly, so that the system can better understand and respond to various lighting conditions and changes in students' eye reactions. Fuzzy reasoning, that is, reasoning operations are performed according to a preset fuzzy rule base. These rules are set based on expert knowledge or experience, and fully consider the inherent connection between lighting and students' visual comfort. Fuzzy reasoning can simulate the human decision-making process, so that brightness adjustment is more in line with people's intuitive feelings and needs. The fuzzy output obtained by fuzzy reasoning can also be converted into a specific brightness adjustment value through a defuzzification operation to achieve precise control.

[0071] S106, adjusting the display screen brightness of the smart blackboard according to the brightness adjustment value to perform adaptive adjustment of the brightness of the smart blackboard.

[0072] Understandably, the system adjusts the brightness output of the smart blackboard display screen in real time through the corresponding control instructions or interfaces according to the calculated brightness adjustment value. This ensures that the brightness of the display screen always remains in the best viewing state. By adjusting the display screen brightness of the smart blackboard in real time, the present invention not only improves the comfort of the teaching environment, allowing students to view the blackboard content under more suitable lighting conditions, but also effectively reduces the visual fatigue that may be caused by watching the blackboard for a long time. At the same time, this adaptive adjustment mechanism also enhances the intelligence of the smart blackboard, enabling it to better adapt to the usage requirements in different scenarios and environments.

[0073] Based on step S101 to step S106, optical sensors are evenly arranged in a matrix around the smart blackboard to collect the light intensity data around the blackboard in real time and comprehensively, and a light intensity matrix is ​​constructed to provide accurate and reliable ambient light information; the eye response information of students in different positions in the classroom is monitored in real time, including pupil changes and blinking frequency, and an eye response index matrix is ​​constructed. These data not only reflect the visual comfort of the entire students in the classroom, but also indirectly reflect the suitability of the current blackboard brightness. Therefore, based on these data, the blackboard brightness can be adjusted in a more humane way to take care of the visual needs of most students in the classroom as much as possible; by adjusting the light intensity matrix and The eye reaction index matrix is ​​fused and processed to obtain a comprehensive light intensity value and a comprehensive eye reaction index; Brightness adjustment based on fuzzy logic: The present invention adopts fuzzy logic control theory to construct a brightness adjustment controller, which can handle the uncertainty and ambiguity in the input comprehensive light intensity value and the comprehensive eye reaction index. Through the operations of fuzzification, fuzzy reasoning and defuzzification, the system can output a brightness adjustment value that conforms to the current environment and satisfies the comfort of students. This adjustment method not only improves the flexibility and adaptability of brightness adjustment, but also ensures the rationality and comfort of the adjustment result; then according to the output value of the brightness adjustment controller, the brightness of the display screen of the smart blackboard is automatically adjusted. The brightness adaptive adjustment method of the smart blackboard of the present invention not only realizes the adaptive automatic adjustment of the blackboard brightness, improves the teaching efficiency and user experience, but also enables the blackboard to realize real-time adjustment of the brightness according to the changes in ambient light and the students' eye comfort requirements, thereby providing a more comfortable and healthy teaching visual environment.

[0074] The following is a further introduction to a method for adaptively adjusting brightness of a smart blackboard according to an embodiment of the present invention:

[0075] Further optionally, in step S105, the step of constructing a brightness adjustment controller based on fuzzy logic control theory, taking the comprehensive light intensity value and the comprehensive eye reaction index as input, and performing fuzzification, fuzzy reasoning and defuzzification operations by the brightness adjustment controller to output a brightness adjustment value includes:

[0076] The comprehensive light intensity value α and the comprehensive eye reaction index β are defined as input variables, and the brightness adjustment value γ is defined as an output variable;

[0077] The input variables α and β and the output variable γ are divided into a first input fuzzy set, a second input fuzzy set and an output fuzzy set respectively;

[0078] A series of fuzzy rules are established to describe the adjustment of γ according to different combinations of input variables α and β;

[0079] According to the values ​​of input variables α and β and the established fuzzy rules, fuzzy reasoning is performed to determine the membership of the output fuzzy set;

[0080] Based on the membership of the output fuzzy set, the output fuzzy set is converted into a specific brightness adjustment value γ through the defuzzification method.

[0081] Based on this step, by dividing each input variable and output variable into the corresponding first input fuzzy set, second input fuzzy set and output fuzzy set, the system can more flexibly handle the uncertainty and ambiguity existing in the actual environment. A series of fuzzy rules are established to accurately describe the impact of different input variable combinations on the brightness adjustment value, thereby simulating the decision-making logic of human experts. According to the real-time value of the input variable and the preset fuzzy rules, the system can determine the membership of the output fuzzy set, which reflects the possibility of different brightness adjustment values. Through the defuzzification method, the system converts these fuzzy possibilities into specific brightness adjustment values ​​γ, realizing the conversion from fuzzy logic to actual control. This series of steps together constitute the core logic of adaptive brightness adjustment, enabling the smart blackboard to perform intelligent and accurate brightness adjustment according to the real-time ambient lighting and student eye response.

[0082] Further optionally, the step of performing fuzzy reasoning according to the values ​​of the input variables α and β and the established fuzzy rules to determine the membership degree of the output fuzzy set includes:

[0083] Take the minimum value of the membership values ​​corresponding to the input variables α and β to calculate the activation of each fuzzy rule. The calculation formula is: Activation = min(μA(α), μB(β)), where μA(α) is the membership of the input variable α corresponding to the first input fuzzy set A, and μB(β) is the membership of the input variable β corresponding to the second input fuzzy set B. The min function means taking the smaller value of the two.

[0084] According to the activation degree of the fuzzy rule and the consequent of the fuzzy rule, the membership degree of the output fuzzy set is determined. The calculation formula is: μC(γ) = activation degree * μC rule(γ), where μC(γ) is the membership function of the output variable γ corresponding to the output fuzzy set C, C rule (γ) the membership degree of C in the consequent of the fuzzy rule;

[0085] If multiple fuzzy rules are activated, the output of each fuzzy rule is aggregated by taking the maximum value method to obtain the membership degree of each element point of the final output fuzzy set. The calculation formula is: μC final (γ)=max(μC1(γ),μC2(γ),...,μC n (γ)), ​​where μC final (γ) is the membership degree of the final output fuzzy set C at the element γ point, μC1(γ), μC2(γ), ..., μC n (γ) is the membership degree of each rule output.

[0086] Further optionally, the step of converting the output fuzzy set into a specific brightness adjustment value γ based on the membership of the output fuzzy set by a defuzzification method includes:

[0087] Determine each element γ in the output fuzzy set C i The membership degree μC(γ i );

[0088] Combine each element γ in the output fuzzy set C i The membership degree and its corresponding value are used to calculate the specific brightness adjustment value γCOG. The calculation formula is: γCOG=(Σ[μC(γ i )*γ i ]) / (ΣμC(γ i )), where Σ represents the summation, μC(γ i ) is the element γ in the output fuzzy set C i The membership degree, γ i are the values ​​of each element in the output fuzzy set C.

[0089] Further optionally, after step S106, the step of adjusting the display brightness of the smart blackboard according to the brightness adjustment value to perform adaptive adjustment of the brightness of the smart blackboard also includes:

[0090] The content displayed on the smart blackboard is enhanced in real time through the GAN algorithm to present high-quality and clear images in real time.

[0091] Based on this step, the present invention further enhances the content displayed on the smart blackboard in real time through the GAN algorithm to ensure that the content presented on the blackboard can maintain high quality and clarity under different brightness conditions, thereby providing a better visual experience. The application of the GAN algorithm enables the system to analyze and optimize the displayed content in real time, effectively eliminating problems such as image blur or loss of details that may be caused by brightness changes. This content enhancement technology not only improves the effect of adaptive brightness adjustment, but also significantly improves the overall visibility and recognition of the smart blackboard, providing clearer and more professional visual effects for scenes such as teaching or meetings.

[0092] Further optionally, the step of enhancing the content displayed on the smart blackboard in real time by using the GAN algorithm includes:

[0093] Collect blackboard images under different brightness conditions, including low-light, normal-light, and high-light conditions, and annotate them to distinguish clear and blurred areas;

[0094] Preprocess the collected images, including cropping, scaling, and normalization operations;

[0095] Design a generator that takes in a low-quality blackboard image and outputs an enhanced high-quality, clear image.

[0096] Design a discriminator to distinguish the image output by the generator from the real clear blackboard image;

[0097] The generator and discriminator are trained through the adversarial loss function, where the goal of the generator is to generate realistic images to deceive the discriminator in order to maximize the probability of the discriminator making mistakes, and the goal of the discriminator is to distinguish between real images and generated images as accurately as possible;

[0098] Deploy the trained generator model to a real-time system;

[0099] The image of the smart blackboard is input into the trained generator, and the generator generates and outputs the enhanced image, which is displayed in real time on the smart blackboard interface.

[0100] Embodiment 2

[0101] See also Figure 2 The present invention proposes a brightness adaptive adjustment system for a smart blackboard, the system comprising:

[0102] Light intensity acquisition module: used to evenly arrange optical sensors in a matrix around the smart blackboard to collect light intensity data in real time and build a light intensity matrix;

[0103] Eye response acquisition module: used to monitor and acquire the eye response information of students in different positions in the classroom in real time, and construct an eye response index matrix. The eye response information includes pupil changes and blinking frequency.

[0104] A first fusion processing module: used for performing fusion processing on the illumination intensity matrix to obtain a comprehensive illumination intensity value;

[0105] A second fusion processing module: used for fusing the eye reaction index matrix to obtain a comprehensive eye reaction index;

[0106] Fuzzy logic control module: used to construct a brightness adjustment controller based on fuzzy logic control theory, and take the comprehensive light intensity value and the comprehensive eye reaction index as input, and perform fuzzification, fuzzy reasoning and defuzzification operations through the brightness adjustment controller to output a brightness adjustment value;

[0107] Brightness adjustment module: used to adjust the display brightness of the smart blackboard according to the brightness adjustment value to perform adaptive adjustment of the brightness of the smart blackboard.

[0108] Further optionally, the fuzzy logic control module is also used for:

[0109] The comprehensive light intensity value α and the comprehensive eye reaction index β are defined as input variables, and the brightness adjustment value γ is defined as an output variable;

[0110] The input variables α and β and the output variable γ are divided into a first input fuzzy set, a second input fuzzy set and an output fuzzy set respectively;

[0111] A series of fuzzy rules are established to describe the adjustment of γ according to different combinations of input variables α and β;

[0112] According to the values ​​of input variables α and β and the established fuzzy rules, fuzzy reasoning is performed to determine the membership of the output fuzzy set;

[0113] Based on the membership of the output fuzzy set, the output fuzzy set is converted into a specific brightness adjustment value γ through the defuzzification method.

[0114] Further optionally, the fuzzy logic control module is also used for:

[0115] Take the minimum value of the membership values ​​corresponding to the input variables α and β to calculate the activation of each fuzzy rule. The calculation formula is: Activation = min(μA(α), μB(β)), where μA(α) is the membership of the input variable α corresponding to the first input fuzzy set A, and μB(β) is the membership of the input variable β corresponding to the second input fuzzy set B. The min function means taking the smaller value of the two.

[0116] According to the activation degree of the fuzzy rule and the consequent of the fuzzy rule, the membership degree of the output fuzzy set is determined. The calculation formula is: μC(γ) = activation degree * μC rule (γ), where μC(γ) is the membership function of the output variable γ corresponding to the output fuzzy set C, C rule (γ) the membership degree of C in the consequent of the fuzzy rule;

[0117] If multiple fuzzy rules are activated, the output of each fuzzy rule is aggregated by taking the maximum value method to obtain the membership degree of each element point of the final output fuzzy set. The calculation formula is: μC final (γ)=max(μC1(γ),μC2(γ),...,μC n (γ)), ​​where μC final (γ) is the membership degree of the final output fuzzy set C at the element γ point, μC1(γ), μC2(γ), ..., μC n (γ) is the membership degree of each rule output.

[0118] Further optionally, the fuzzy logic control module is also used for:

[0119] Determine each element γ in the output fuzzy set C i The membership degree μC(γ i );

[0120] Combine each element γ in the output fuzzy set C i The membership degree and its corresponding value are used to calculate the specific brightness adjustment value γCOG. The calculation formula is: γCOG=(Σ[μC(γ i )*γ i ]) / (ΣμC(γ i )), where Σ represents the summation, μC(γ i ) is the element γ in the output fuzzy set C i The membership degree, γ i are the values ​​of each element in the output fuzzy set C.

[0121] Further optionally, the first fusion processing module is further used for:

[0122] All elements in the light intensity matrix are weighted averaged to obtain a comprehensive light intensity value.

[0123] Further optionally, the second fusion processing module is further used for:

[0124] All elements in the eye response index matrix are weighted averaged to obtain a comprehensive eye response index.

[0125] Further optionally, the brightness adjustment module is also used for:

[0126] The content displayed on the smart blackboard is enhanced in real time through the GAN algorithm to present high-quality and clear images in real time.

[0127] Further optionally, the brightness adjustment module is also used for:

[0128] Collect blackboard images under different brightness conditions and annotate them to distinguish clear and blurred areas;

[0129] Preprocess the collected images, including cropping, scaling, and normalization operations;

[0130] Design a generator that takes in a low-quality blackboard image and outputs an enhanced high-quality, clear image.

[0131] Design a discriminator to distinguish the image output by the generator from the real clear blackboard image;

[0132] The generator and discriminator are trained through the adversarial loss function, where the goal of the generator is to generate realistic images to deceive the discriminator in order to maximize the probability that the discriminator makes mistakes, and the goal of the discriminator is to distinguish between real images and generated images;

[0133] Deploy the trained generator model to a real-time system;

[0134] The image of the smart blackboard is input into the trained generator, and the generator generates and outputs the enhanced image, which is displayed in real time on the smart blackboard interface.

[0135] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for adaptively adjusting brightness of a smart blackboard, characterized in that: The method comprises: Optical sensors are evenly arranged in a matrix around the smart blackboard to collect light intensity data in real time and construct a light intensity matrix; Real-time monitoring to obtain eye reaction information of students in different positions in the classroom, and construct an eye reaction index matrix, wherein the eye reaction information includes pupil changes and blinking frequency; Performing fusion processing on the illumination intensity matrix to obtain a comprehensive illumination intensity value; Performing fusion processing on the eye response index matrix to obtain a comprehensive eye response index; Based on fuzzy logic control theory, a brightness adjustment controller is constructed, and the comprehensive light intensity value and the comprehensive eye reaction index are used as inputs, and fuzzification, fuzzy reasoning and defuzzification operations are performed by the brightness adjustment controller to output a brightness adjustment value; According to the brightness adjustment value, the display screen brightness of the smart blackboard is adjusted to perform adaptive adjustment of the brightness of the smart blackboard.

2. The brightness adaptive adjustment method of the smart blackboard according to claim 1 is characterized in that: The step of constructing a brightness adjustment controller based on fuzzy logic control theory, taking the comprehensive light intensity value and the comprehensive eye reaction index as input, and performing fuzzification, fuzzy reasoning and defuzzification operations through the brightness adjustment controller to output a brightness adjustment value includes: The comprehensive light intensity value α and the comprehensive eye reaction index β are defined as input variables, and the brightness adjustment value γ is defined as an output variable; The input variables α and β and the output variable γ are divided into a first input fuzzy set, a second input fuzzy set and an output fuzzy set respectively; A series of fuzzy rules are established to describe the adjustment of γ according to different combinations of input variables α and β; According to the values ​​of input variables α and β and the established fuzzy rules, fuzzy reasoning is performed to determine the membership of the output fuzzy set; Based on the membership of the output fuzzy set, the output fuzzy set is converted into a specific brightness adjustment value γ through the defuzzification method.

3. The brightness adaptive adjustment method of the smart blackboard according to claim 2 is characterized in that: The step of performing fuzzy reasoning according to the values ​​of input variables α and β and the established fuzzy rules to determine the membership degree of the output fuzzy set includes: Take the minimum value of the membership values ​​corresponding to the input variables α and β to calculate the activation of each fuzzy rule. The calculation formula is: Activation = min(μA(α), μB(β)), where μA(α) is the membership of the input variable α corresponding to the first input fuzzy set A, and μB(β) is the membership of the input variable β corresponding to the second input fuzzy set B. The min function means taking the smaller value of the two. According to the activation degree of the fuzzy rule and the consequent of the fuzzy rule, the membership degree of the output fuzzy set is determined. The calculation formula is: μC(γ) = activation degree * μC rule (γ), where μC(γ) is the membership function of the output variable γ corresponding to the output fuzzy set C, C rule (γ) the membership degree of C in the consequent of the fuzzy rule; If multiple fuzzy rules are activated, the output of each fuzzy rule is aggregated by taking the maximum value method to obtain the membership degree of each element point of the final output fuzzy set. The calculation formula is: μC final (γ)=max(μC1(γ),μC2(γ),...,μC n (γ)), ​​where μC final (γ) is the membership degree of the final output fuzzy set C at the element γ point, μC1(γ), μC2(γ), ..., μC n (γ) is the membership degree of each rule output.

4. The method for adaptively adjusting brightness of a smart blackboard according to claim 2, characterized in that: The step of converting the output fuzzy set into a specific brightness adjustment value γ based on the membership of the output fuzzy set by a defuzzification method comprises: Determine each element γ in the output fuzzy set C i The membership degree μC(γ i ); Combine each element γ in the output fuzzy set C i The membership degree and its corresponding value are used to calculate the specific brightness adjustment value γCOG. The calculation formula is: γCOG=(Σ[μC(γ i )*γ i ]) / (ΣμC(γ i )), where Σ represents the summation, μC(γ i ) is the element γ in the output fuzzy set C i The membership degree, γ i are the values ​​of each element in the output fuzzy set C.

5. The method for adaptively adjusting brightness of a smart blackboard according to claim 1 is characterized in that: The step of fusing the illumination intensity matrix to obtain a comprehensive illumination intensity value comprises: All elements in the light intensity matrix are weighted averaged to obtain a comprehensive light intensity value.

6. The method for adaptively adjusting brightness of a smart blackboard according to claim 1, characterized in that: The step of fusing the eye reaction index matrix to obtain a comprehensive eye reaction index comprises: All elements in the eye response index matrix are weighted averaged to obtain a comprehensive eye response index.

7. The method for adaptively adjusting brightness of a smart blackboard according to claim 1, characterized in that: The step of adjusting the display brightness of the smart blackboard according to the brightness adjustment value to perform adaptive adjustment of the brightness of the smart blackboard also includes: The content displayed on the smart blackboard is enhanced in real time through the GAN algorithm to present high-quality and clear images in real time.

8. The method for adaptively adjusting brightness of a smart blackboard according to claim 7, characterized in that: The step of enhancing the content displayed on the smart blackboard in real time by using the GAN algorithm includes: Collect blackboard images under different brightness conditions and annotate them to distinguish clear and blurred areas; Preprocess the collected images, including cropping, scaling, and normalization operations; Design a generator that takes in a low-quality blackboard image and outputs an enhanced high-quality, clear image. Design a discriminator to distinguish the image output by the generator from the real clear blackboard image; The generator and discriminator are trained through the adversarial loss function, where the goal of the generator is to generate realistic images to deceive the discriminator in order to maximize the probability that the discriminator makes mistakes, and the goal of the discriminator is to distinguish between real images and generated images; Deploy the trained generator model to a real-time system; The image of the smart blackboard is input into the trained generator, and the generator generates and outputs the enhanced image, which is displayed in real time on the smart blackboard interface.

9. A brightness adaptive adjustment system for a smart blackboard, characterized in that: The system comprises: Light intensity acquisition module: used to evenly arrange optical sensors in a matrix around the smart blackboard to collect light intensity data in real time and build a light intensity matrix; Eye response acquisition module: used to monitor and acquire the eye response information of students in different positions in the classroom in real time, and construct an eye response index matrix. The eye response information includes pupil changes and blinking frequency. A first fusion processing module: used for performing fusion processing on the illumination intensity matrix to obtain a comprehensive illumination intensity value; A second fusion processing module: used for fusing the eye reaction index matrix to obtain a comprehensive eye reaction index; Fuzzy logic control module: used to construct a brightness adjustment controller based on fuzzy logic control theory, and take the comprehensive light intensity value and the comprehensive eye reaction index as input, and perform fuzzification, fuzzy reasoning and defuzzification operations through the brightness adjustment controller to output a brightness adjustment value; Brightness adjustment module: used to adjust the display brightness of the smart blackboard according to the brightness adjustment value to perform adaptive adjustment of the brightness of the smart blackboard.

Images