Cinema environment parameter self-adaptive adjusting system and method

Abstract

The invention provides a self-adaptive adjustment system and method for cinema environment parameters, and relates to the technical field of self-adaptive adjustment of air conditioning systems. The processing module is used for carrying out gray processing on the cinema image to obtain a target image; the first construction module is used for constructing a people number identification model based on a support vector machine algorithm; the recognition module is used for inputting the target image into a people number recognition model for people number recognition and determining the current cinema people number; the determination module is used for determining the target indoor temperature and the target indoor humidity of the cinema according to the current number of people in the cinema; and the adjusting module is used for carrying out self-adaptive control on an air conditioner of the cinema through the PI lambda D mu controller according to the target indoor temperature and the target indoor humidity so as to carry out self-adaptive adjustment on the indoor temperature and the indoor humidity of the cinema. The air conditioner in the cinema can be accurately adjusted according to the real-time change of the number of people, and the efficiency and comfort of the system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of adaptive regulation of air conditioning systems, and particularly to a system and method for adaptively regulating cinema environmental parameters. Background Art

[0002] With the continuous development of technology and the widespread application of intelligent devices, cinemas, as a public entertainment venue, are facing increasingly severe environmental management challenges. The number of audiences in the cinema, the changes in the external climate, and the environmental differences in different areas all directly affect the indoor temperature and humidity, and thus affect the viewing experience of the audience. Therefore, in order to improve the comfort of the audience and the energy utilization efficiency of the cinema, it is particularly crucial to introduce an efficient and automated air conditioning regulation system.

[0003] In the prior art, the air conditioning systems of some cinemas have tried to automatically regulate the indoor environment through temperature sensors and humidity sensors. However, these systems usually only rely on the single data collected by the sensors to control the temperature and humidity, and cannot fully consider the dynamic changes of the environment.

[0004] In addition, the air conditioning systems of existing cinemas often lack accurate identification of the personnel distribution and activity levels in the cinema, resulting in the air conditioning being unable to accurately adjust according to the real-time change in the number of people, thus affecting the efficiency and comfort of the system. Summary of the Invention

[0005] In order to solve the technical problems that the air conditioning systems of traditional cinemas only rely on the single data collected by sensors to control the temperature and humidity, cannot fully consider the dynamic changes of the environment, and often lack accurate identification of the personnel distribution and activity levels in the cinema, resulting in the air conditioning being unable to accurately adjust according to the real-time change in the number of people, thus affecting the efficiency and comfort of the system, the present invention provides a system and method for adaptively regulating cinema environmental parameters.

[0006] The technical solutions provided by the embodiments of the present invention are as follows:

[0007] First aspect:

[0008] An adaptive regulation system for cinema environmental parameters provided by an embodiment of the present invention includes:

[0009] An acquisition module, configured to acquire cinema images;

[0010] A processing module, configured to perform grayscale processing on the cinema images to obtain target images;

[0011] A first construction module, configured to construct a number recognition model based on the support vector machine algorithm;

[0012] An identification module, configured to input the target image into the number-of-people recognition model based on the support vector machine algorithm for number-of-people recognition to determine the current number of people in the cinema;

[0013] A determination module, configured to determine the target indoor temperature and target indoor humidity of the cinema according to the current number of people in the cinema;

[0014] An adjustment module, configured to perform adaptive control on the air conditioner in the cinema according to the target indoor temperature and the target indoor humidity through a PI λ D μ controller to perform adaptive adjustment on the indoor temperature and indoor humidity in the cinema.

[0015] Second aspect:

[0016] A method for adaptive adjustment of cinema environment parameters provided by an embodiment of the present invention includes:

[0017] S1: Obtain a cinema image;

[0018] S2: Perform grayscale processing on the cinema image to obtain a target image;

[0019] S3: Construct a number-of-people recognition model based on the support vector machine algorithm;

[0020] S4: Input the target image into the number-of-people recognition model based on the support vector machine algorithm for number-of-people recognition to determine the current number of people in the cinema;

[0021] S5: Determine the target indoor temperature and target indoor humidity of the cinema according to the current number of people in the cinema;

[0022] S6: Perform adaptive adjustment on the indoor temperature and indoor humidity in the cinema according to the target indoor temperature and the target indoor humidity through a PI λ D μ controller.

[0023] The beneficial effects brought by the technical solution provided by the embodiment of the present invention at least include:

[0024] In the embodiment of the present invention, by performing grayscale processing on the cinema image to obtain a target image, and inputting the target image into the number-of-people recognition model based on the support vector machine algorithm for number-of-people recognition to determine the current number of people in the cinema, and determining the target indoor temperature and target indoor humidity of the cinema according to the current number of people in the cinema, it avoids the traditional air conditioning system in the cinema relying only on the single data collected by the sensor for temperature and humidity control, can fully consider the dynamic changes of the environment, such as the change in the number of people, has accurate recognition of the personnel distribution and activity level in the cinema, and according to the target indoor temperature and the target indoor humidity, through a PI λ D μThe controller adaptively adjusts the indoor temperature and humidity of the cinema, ensuring that the air conditioner inside the cinema can be accurately adjusted according to the change in the real-time number of people, improving the efficiency and comfort of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0026] Figure 1 FIG. is a schematic structural diagram of a system for adaptively adjusting cinema environment parameters provided by an embodiment of the present invention;

[0027] Figure 2 FIG. is a schematic flowchart of a method for adaptively adjusting cinema environment parameters provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The following will describe the technical solutions in the present invention with reference to the drawings.

[0029] Refer to the attached drawings of the specification Figure 1 , which shows a schematic structural diagram of a system for adaptively adjusting cinema environment parameters provided by an embodiment of the present invention.

[0030] An embodiment of the present invention provides a system 20 for adaptively adjusting cinema environment parameters, including:

[0031] An acquisition module 201, configured to acquire cinema images.

[0032] Specifically, the cinema images are captured in real time by a camera installed above the cinema.

[0033] A processing module 202, configured to perform grayscale processing on the cinema images to obtain target images.

[0034] In a possible implementation manner, the processing module 202 is specifically configured to:

[0035] Perform grayscale processing on the cinema images through gamma transformation to obtain target images.

[0036] It should be noted that gamma transformation is a non - linear image - processing technique used to adjust the brightness and contrast of images. It makes the image appear brighter or darker visually by adjusting the brightness value of each pixel in the image. The key to gamma transformation lies in selecting a gamma value. When the gamma value is greater than 1, the image becomes brighter, and when the gamma value is less than 1, the image becomes darker. This transformation helps to improve the visual effect of images under different lighting conditions, especially when the image contrast is not obvious or the lighting is uneven, and can better enhance details.

[0037] Specifically, according to the following formula, the theater image is grayscale - processed to obtain the target image:

[0038]

[0039] where, V out represents the grayscale value of the target image, A represents the proportionality coefficient used to adjust the intensity of gamma transformation, V in represents the grayscale value of the theater image, and r represents the gamma value.

[0040] In the present invention, through gamma transformation, details can be enhanced in low - contrast images, especially in the case of uneven lighting or low contrast, making the important features in the image clearer, which is convenient for subsequent number recognition and image analysis. The lighting conditions in the theater environment may vary. Gamma transformation can ensure the consistency of the image under different lighting conditions by adjusting the brightness of the image, thereby improving the stability and accuracy of image processing. After grayscale - processing and adjusting the brightness and contrast of the theater image, it can provide clearer and more standardized input data for subsequent image recognition, thereby improving the recognition accuracy.

[0041] The first construction module 203 is used to construct a number - recognition model based on the support vector machine algorithm.

[0042] It should be noted that the support vector machine (SVM) algorithm is a supervised learning algorithm commonly used in classification and regression analysis. It separates samples of different classes by finding an optimal decision boundary (i.e., a hyperplane) and maximizing the interval between classes, thereby achieving accurate classification. The core idea of SVM is to map the data into a high - dimensional space, find a hyperplane in this space such that the distance from the data points to the plane is maximized, thereby improving the generalization ability of the model. For non - linearly separable data, SVM can map the data into a higher - dimensional feature space through a kernel function, making the data linearly separable in this space. SVM is widely used in fields such as text classification, face recognition, and image classification.

[0043] In the present invention, the SVM algorithm separates samples of different classes by finding an optimal hyperplane and maximizes the margin between classes, thereby effectively improving the classification accuracy. During the process of human number recognition, SVM can accurately determine whether there are people or no people in the image, thus reducing the possibility of misrecognition. SVM has strong generalization ability. Even when the training data is limited, SVM can avoid overfitting and can accurately recognize in new images. Especially in the cinema environment, the change of the number of people is dynamic. Using SVM can effectively handle these changes and accurately recognize. In cinema images, there is a large amount of pixel information, which is usually high-dimensional. SVM can effectively process this high-dimensional data, extract key features and perform efficient classification.

[0044] The recognition module 204 is configured to input the target image into the human number recognition model based on the support vector machine algorithm for human number recognition to determine the current number of people in the cinema.

[0045] In the present invention, the SVM algorithm separates data of different classes by constructing an optimal hyperplane. When facing a complex cinema environment, it can efficiently and accurately distinguish whether there are people in the cinema, so as to obtain the accurate current number of people.

[0046] In a possible implementation manner, the recognition module 204 is specifically configured to:

[0047] Based on a preset pixel size, divide the target image into multiple cells.

[0048] It should be noted that those skilled in the art can set the preset pixel size according to actual needs. Optionally, divide the target image into multiple cells of 8×8 pixel size.

[0049] Calculate the horizontal gradient and vertical gradient of each pixel point in the cell through the Sobel filter.

[0050] It should be noted that the Sobel filter is a commonly used edge detection operator, mainly used in image processing to highlight the edges of objects in the image. It detects edges by calculating the horizontal and vertical gradients of each pixel point in the image. The Sobel filter uses two 3x3 convolution kernels (one for horizontal edge detection and the other for vertical edge detection) to calculate the changes in the image in the horizontal and vertical directions respectively. By performing a convolution operation on the image, the gradient magnitude and direction of each point in the image can be obtained, thereby identifying the edges of the image. The Sobel filter is commonly used in tasks such as edge detection, contour extraction, and image feature extraction.

[0051] In a possible implementation manner, the recognition module 204 is specifically further configured to:

[0052] According to the following formula, calculate the horizontal gradient and vertical gradient of each pixel in the cell through the Sobel filter:

[0053] I X = I * R x , R x = [-1, 0, 1]

[0054] I Y = I * R y , R y = [-1, 0, 1] T

[0055] Among them, I X represents the horizontal gradient of the pixel, I represents the pixel value of the pixel, and R x represents the Sobel filter matrix in the horizontal direction, and I Y represents the vertical gradient of the pixel, and R y represents the Sobel filter matrix in the vertical direction, T represents the transpose operation.

[0056] In the present invention, the Sobel filter is mainly used to detect edge information in an image. By calculating the horizontal and vertical gradients of the image, obvious edge features in the image can be extracted. Edges usually can reflect the contours and structures of objects, which are crucial for subsequent human number recognition and target detection. The Sobel filter strengthens the regions with large gradient changes in the image, and these regions usually correspond to the boundaries or significant features of objects. In human number recognition, these edge information helps to identify the shapes and contours of people, thereby improving the recognition accuracy.

[0057] According to the horizontal gradient and vertical gradient of each pixel in the cell, calculate the gradient magnitude and gradient direction of each pixel in the cell.

[0058] In a possible implementation manner, the recognition module 204 is specifically further configured to:

[0059] According to the following formula, calculate the gradient magnitude and gradient direction of each pixel in the cell:

[0060]

[0061] Among them, G represents the gradient magnitude of the pixel, || represents taking the absolute value, θ represents the gradient direction of the pixel, tan() represents the arctangent function, and mod represents the modulo operation.

[0062] In the present invention, by calculating the gradient magnitude (i.e., edge intensity) and gradient direction (i.e., the orientation of the edge) of each pixel, the edge information in the image can be accurately extracted. Edge information is particularly important for human number recognition because the contours of objects (such as human bodies) are usually manifested through edges, and the gradient magnitude and direction help to better capture this information. By calculating the gradient magnitude and direction, the image information can be transformed from pixel-level details into statistical features of local regions. This method can reduce the influence of redundant data, making subsequent image analysis and human number recognition more efficient while ensuring the retention of important features.

[0063] According to the gradient directions of each pixel point in the cell, multiple direction groups are divided within the cell.

[0064] Optionally, within the range of 0 to 180°, 9 direction groups are evenly divided (direction group 1 is from 0° to 20°, direction group 2 is from 20° to 40°, direction group 3 is from 40° to 60°, direction group 4 is from 60° to 80°, direction group 5 is from 80° to 100°, direction group 6 is from 100° to 120°, direction group 7 is from 120° to 140°, direction group 8 is from 140° to 160°, and direction group 9 is from 160° to 180°).

[0065] For example, when the gradient direction of the pixel point is 45°, the pixel point is classified into direction group 3, and when the gradient direction of the pixel point is 165°, the pixel point is classified into direction group 9.

[0066] According to the gradient magnitudes of each pixel point in the cell, calculate the sum of the gradient magnitudes of each direction group to obtain the histogram of oriented gradients.

[0067] It should be noted that the histogram of oriented gradients (HOG) is an image feature descriptor widely used in object detection, especially in the recognition of objects such as faces and pedestrians. It describes the shape and structure of objects in the image by calculating the gradient information in local regions of the image. Specifically, HOG first calculates the gradient magnitude and direction of each pixel in the image, then divides the image into several small cells, and divides each cell into multiple direction groups (usually 9 direction groups) according to the gradient direction within each cell. Then, the gradient magnitudes of each direction group are accumulated to generate the histogram of oriented gradients, and finally, these histogram features are concatenated into a descriptor for image classification or object detection. The HOG method has strong robustness to illumination changes and is therefore very commonly used in computer vision.

[0068] In a possible implementation manner, the recognition module 204 is further specifically configured to:

[0069] According to the following formula, calculate the sum of the gradient magnitudes of each direction group to obtain the histogram of oriented gradients:

[0070]

[0071] Among them, H j represents the sum of the gradient magnitudes of the j-th direction group, M represents the total number of pixel points in the direction group, and G i represents the gradient magnitude of the i-th pixel point in the direction group.

[0072] In the present invention, by grouping and summing the gradient information in the image according to directions, the main edge directions in each direction of the image can be extracted, thereby enhancing the directional characteristics of the image. This enables the system to more effectively distinguish different objects and backgrounds, improving the accuracy of recognition. By grouping and summing the gradient magnitudes of pixel points according to directions, redundant information in the image is reduced, and more discriminative features are retained. This data compression not only improves the computational efficiency but also preserves the key information of the image, facilitating subsequent classification and recognition tasks.

[0073] Group each cell to obtain multiple feature blocks.

[0074] Optionally, combine adjacent 2×2 cells into a feature block. That is, each feature block contains 4 cells (for example: cells of 8×8 pixels, and the size of each feature block is 16×16 pixels).

[0075] Stitch the histograms of oriented gradients in each cell of the feature block to obtain a block feature vector.

[0076] Through the L2-Norm algorithm, normalize the block feature vector to obtain a histogram of oriented gradients descriptor.

[0077] It should be noted that the L2-Norm algorithm is a commonly used vector normalization method for adjusting the magnitude of a vector to unit length, and is often used in feature processing and data preprocessing. The L2-Norm calculates the sum of the squares of all elements in the vector and then takes the square root to obtain the L2 norm (i.e., the Euclidean length) of the vector. Then, each element in the vector is divided by this L2 norm to obtain a normalized unit vector. This process helps to eliminate the dimensional differences between different features, enabling them to have the same weight when performing calculations. In many machine learning and computer vision tasks, the L2-Norm is used to improve the stability and performance of the model, especially when dealing with image features and large-scale data in the dataset.

[0078] Specifically, according to the following formula, normalize the block feature vector to obtain a histogram of oriented gradients descriptor:

[0079]

[0080] Among them, denotes the block feature vector after normalization processing, v denotes the block feature vector, || ||2 denotes the L2 norm, and ε denotes a constant (usually taking a value of 10 -6 ).

[0081] By means of a sliding window with a preset window size, the target image is gradually scanned, and the histogram of oriented gradients descriptor within the current window is extracted.

[0082] It should be noted that those skilled in the art can set the preset window size according to actual needs, and the present invention does not make any limitations here.

[0083] Based on the histogram of oriented gradients descriptor within the current window, the number of people is recognized through the support vector machine algorithm to determine the number of people in the current cinema.

[0084] Specifically, according to the following formula, the number of people is recognized through the support vector machine algorithm to determine the number of people in the current cinema:

[0085] F(x0) = w T x0 + b0

[0086] where F() represents the output of the support vector machine algorithm, x0 represents the histogram of oriented gradients descriptor within the current window, w represents the weight coefficient of the support vector machine, and b0 represents the bias term. Among them, when F(x0) > 0, the current window is classified as a window with people, and when F(x0) < 0, the current window is classified as a window without people.

[0087] In the present invention, the horizontal and vertical gradients of each pixel are calculated through the Sobel filter to extract the image edge information, which helps to distinguish the object from the background, especially to identify the human body contour in a complex cinema environment and improve the accuracy of the number of people recognition. The histogram of oriented gradients (HOG) is generated, and the gradient information is grouped and accumulated according to the direction to obtain the local feature descriptor. The HOG method has strong robustness to illumination and perspective, can stably extract the shape features of the object, and performs well especially under uneven illumination or complex backgrounds. The feature vector is normalized through the L2-Norm algorithm to eliminate the dimension difference, ensure the consistent influence of the features on the classification model, improve the feature stability and the generalization ability of the classifier, and avoid misclassification. The image is scanned through a sliding window, and SVM classification is performed based on the HOG descriptor of each window to efficiently detect the area with people in the image, realize fast and accurate number of people recognition, and is applicable to real-time image processing.

[0088] The determination module 205 is used to determine the target indoor temperature and the target indoor humidity of the cinema according to the number of people in the current cinema.

[0089] In the present invention, the number of people in the cinema affects the heat and humidity in the air. Increasing the number of people may cause the temperature to rise or the humidity to increase. Dynamically adjusting the temperature and humidity according to the number of people to ensure that the indoor environment is always within a comfortable range helps to improve the viewing experience of the audience. Automatically adjusting the temperature and humidity according to the actual number of people in the cinema enables the air conditioning system to quickly respond to changes in the cinema environment. This dynamic adjustment can better adapt to the temperature and humidity fluctuations caused by changes in the number of people in the cinema, thus ensuring the continuous comfort of the environment.

[0090] In a possible implementation manner, the determining module 205 is specifically configured to:

[0091] Set the basic ideal indoor temperature and the basic ideal indoor humidity of the cinema.

[0092] It should be noted that the basic ideal indoor temperature refers to the indoor temperature remaining at a constant value in an ideal comfortable environment to ensure a temperature range that makes most people feel comfortable. This temperature usually refers to the local climate conditions and human comfort standards, which can meet the needs of most people and at the same time avoid excessive energy consumption.

[0093] It should be noted that the basic ideal indoor humidity refers to the relative humidity indoors remaining within a suitable range in an ideal comfortable environment to ensure that the air is moist but not damp or overly dry. This humidity value helps to maintain the comfort and health of the human body and at the same time avoids discomfort caused by too high or too low humidity.

[0094] Determine the target indoor temperature and the target indoor humidity of the cinema according to the current number of people in the cinema, the basic ideal indoor temperature, and the basic ideal indoor humidity:

[0095]

[0096] Wherein, T target represents the target indoor temperature, T0 represents the basic ideal indoor temperature, b T represents the temperature change coefficient, N0 represents the current number of people in the cinema, N max represents the maximum capacity of the cinema, H target represents the target indoor humidity, H0 represents the basic ideal indoor humidity, b H represents the humidity change coefficient.

[0097] It should be noted that as the number of people in the cinema increases, the heat and humidity in the air will also increase accordingly. Therefore, the system needs to adjust the temperature and humidity according to the change in the number of people to maintain a comfortable indoor environment. This adjustment will ensure that the air quality and comfort in the cinema are always maintained within the ideal range under different numbers of people, while avoiding excessive energy consumption.

[0098] In the present invention, as the number of people in the cinema increases, the heat and humidity also increase, directly affecting the comfort level. By automatically adjusting the temperature and humidity according to the change in the number of people, the comfort of the indoor environment in the cinema can be maintained, and the discomfort or air quality problems caused by the fluctuation in the number of people can be avoided. By dynamically adjusting the target temperature and humidity through the temperature and humidity change coefficients, the system can accurately adjust under different numbers of people and environmental conditions, avoiding the inability of simple fixed temperature and humidity settings to cope with complex actual situations, and improving the responsiveness and flexibility of the system. By accurately adjusting the temperature and humidity, the air conditioning system can operate within a more reasonable working range, avoiding equipment overload or low energy efficiency caused by excessive cooling or heating, thereby prolonging the service life of the air conditioning equipment and improving its working efficiency.

[0099] The adjustment module 206 is configured to adaptively control the air conditioner in the cinema according to the target indoor temperature and the target indoor humidity, so as to adaptively adjust the indoor temperature and the indoor humidity in the cinema through a PI λ D μ controller.

[0100] It should be noted that the PI λ D μ controller is an advanced controller based on proportional (P), integral (I), and derivative (D) control, and its characteristic is the introduction of fractional-order integral (λ) and fractional-order derivative (μ) operations. Different from the traditional PID controller, the PIλDμ controller uses fractional-order operations in the integral and derivative parts, and can adjust the system response more flexibly, especially when dealing with systems with complex dynamic characteristics, such as systems with long time delays or high-order dynamic characteristics. By adjusting the integral order (λ) and the derivative order (μ), the stability and response speed of the system can be improved, providing more precise control, and being suitable for application scenarios that require high-precision control.

[0101] In the present invention, the PI λ D μ controller enables the controller to make more precise adjustments according to the dynamic characteristics of the actual system by introducing fractional-order integral (λ) and fractional-order derivative (μ). This flexibility is particularly suitable for dealing with the long time delays or complex dynamic characteristics that may exist in the cinema air conditioning system, and can provide a more stable and rapid response. The fractional-order operations enable the PI λ D μ controller to better adapt to non-linear and high-order systems, improving the stability of the control system. For a system such as the cinema air conditioning that requires precise control of temperature and humidity, the PI λ D μ controller can avoid instability caused by overly fast or slow responses, ensuring the stable performance of the system over a long period of time.

[0102] In a possible implementation, the adjustment module 206 is specifically configured to:

[0103] Obtain the actual indoor temperature and actual indoor humidity of the cinema through a temperature sensor and a humidity sensor.

[0104] Specifically, the actual indoor temperature of the cinema is collected in real time through a temperature sensor installed inside the cinema, and the actual indoor humidity of the cinema is collected in real time through a humidity sensor installed inside the cinema.

[0105] According to the target indoor temperature, target indoor humidity, actual indoor temperature, and actual indoor humidity, through a PI λ D μ controller, adaptively control the air conditioner of the cinema to adaptively adjust the indoor temperature and indoor humidity of the cinema:

[0106]

[0107] where, u T (h) represents the temperature control signal at time h, represents the temperature proportional gain coefficient, e T (h) represents the deviation between the target indoor temperature and the actual indoor temperature at time h, represents the temperature integral gain coefficient, represents the temperature differential gain coefficient, D -λ represents the fractional-order integral operation, λ represents the integral order, D μ represents the fractional-order differential operation, μ represents the differential order, T now (h) represents the actual indoor temperature at time h, u H (h) represents the humidity control signal at time h, represents the humidity proportional gain coefficient, e H (h) represents the deviation between the target indoor humidity and the actual indoor humidity at time h, represents the humidity integral gain coefficient, represents the humidity differential gain coefficient, H now (h) represents the actual indoor humidity at time h.

[0108] In the present invention, by monitoring the temperature and humidity changes in the cinema in real time through temperature and humidity sensors, the system can dynamically respond to environmental changes. Whether the number of moviegoers increases or the external environment changes, the system can adjust the air conditioner settings in real time to ensure that the indoor environment always remains within a comfortable range. PI λ D μThe controller adjusts according to the deviation between the actual temperature and humidity and the target values, which can control the temperature and humidity more precisely, avoid the over-operation of the air-conditioning system and energy waste. This precise adjustment helps to improve the energy efficiency of the air-conditioning system while maintaining a comfortable indoor environment. By obtaining the actual temperature and humidity in real time and comparing them with the target temperature and humidity, the system can adjust the working state of the air conditioner in a timely manner to ensure that the audience can enjoy the best temperature and humidity conditions under different numbers of people and environments. Avoid discomfort caused by environmental changes and improve the movie-watching experience.

[0109] In a possible implementation manner, the theater environment parameter adaptive adjustment system further includes:

[0110] A second construction module, which is used to construct an objective function with the goal of reducing the air-conditioning energy consumption during the operation of the air conditioner.

[0111] Specifically, the calculation method of the air-conditioning energy consumption specifically includes:

[0112] Calculate the power consumption of the air conditioner during operation:

[0113]

[0114] Among them, P represents the power consumption of the air conditioner, Q represents the cooling capacity or heating capacity of the air conditioner, and COP represents the energy efficiency ratio of the air conditioner (that is, the cooling capacity or heating capacity provided by a unit of energy input).

[0115] According to the power consumption of the air conditioner during operation, calculate the air-conditioning energy consumption during the operation of the air conditioner:

[0116] E = P·k

[0117] Among them, E represents the air-conditioning energy consumption during the operation of the air conditioner, and k represents the operation duration of the air conditioner.

[0118] Furthermore, the objective function is specifically:

[0119] minf(δ) = P·k

[0120] Among them, min represents taking the minimum value, f() represents the objective function, and δ represents the control parameter set of the PI λ D μ controller, and the control parameter set of the PI λ D μ controller includes a proportional gain coefficient, an integral gain coefficient, a derivative gain coefficient, an integral order, and a derivative order.

[0121] An optimization module, which is used to optimize the PI λ D μ controller according to the objective function through the particle swarm optimization algorithm.

[0122] It should be noted that the Particle Swarm Optimization (PSO) algorithm is a global optimization algorithm that simulates the foraging behavior of bird flocks in nature and belongs to the swarm intelligence algorithm. It searches for the optimal solution in the solution space by simulating the process of a group of "particles". Each particle represents a possible solution and continuously updates its position through the interaction of individual experience and group experience. Each particle adjusts according to its own historical best position and the best position in the entire group during the search process, thus gradually approaching the optimal solution. The Particle Swarm Optimization algorithm has the advantages of simplicity, easy implementation, fast convergence speed, etc., and is widely used in fields such as function optimization, machine learning, and parameter tuning.

[0123] In the present invention, by constructing an objective function and optimizing the PI λ D μ controller parameters, the air-conditioning system can minimize power consumption and energy consumption on the premise of meeting the comfortable environment. The Particle Swarm Optimization algorithm can automatically adjust the control parameters according to actual needs to ensure the maximization of the operating efficiency of the air-conditioning system, thereby reducing energy waste. The PSO algorithm simulates the process of a particle swarm searching for the optimal solution in the solution space. By combining global search and local search, it can accurately optimize the PI λ D μ controller parameters, making the energy efficiency adjustment of the air-conditioning system more intelligent and refined. This optimization helps to dynamically adjust the operating mode of the air conditioner under complex environmental conditions, further improving the comprehensive performance of the air-conditioning system.

[0124] Specifically, initialize the parameters and set the maximum number of iterations of the Particle Swarm Optimization algorithm.

[0125] Generate an initial particle swarm. The initial particle swarm includes multiple particles, and each particle represents a set of feasible PI λ D μ controller control parameters.

[0126] Calculate the non-linear inertia weight of each particle:

[0127]

[0128] where ω(t) represents the inertia weight at the t-th iteration, ω max represents the initial maximum value of the inertia weight, ω min represents the initial minimum value of the inertia weight, T max represents the maximum number of iterations, and e represents the exponential function.

[0129] Using the objective function as the fitness function, calculate the fitness value of each particle, and take the particle with the maximum fitness value as the current particle.

[0130] Update the velocity and position of the current particle according to the non - linear inertia weight:

[0131] v b (t + 1)=ω(t)·v b (t)+c1r1(P b -X b )+c2r2(B - X b )

[0132] X b (t + 1)=X b (t)+X b (t + 1)

[0133] Wherein, v b (t + 1) represents the velocity of the b - th particle at the (t + 1)-th iteration, v b (t) represents the velocity of the b - th particle at the t - th iteration, c1 represents the individual learning factor, r1 represents the first random number, r2 represents the second random number, P b represents the historical optimal position of the b - th particle, X b represents the position of the b - th particle at the t - th iteration, c2 represents the swarm learning factor, B represents the global optimal position, X b (t + 1) represents the position of the b - th particle at the (t + 1)-th iteration.

[0134] Judge whether the maximum number of iterations is reached. If so, output the optimal control parameter set PI λ D μ of the controller. Otherwise, increment the iteration count by 1.

[0135] In the present invention, in the PSO algorithm, the calculation of the non - linear inertia weight enables the particles to explore a wider solution space in the initial stage and gradually converge in the later stage. This dynamic adjustment helps to balance global search and local search, enabling the particle swarm to avoid being trapped in local optimal solutions during the process of finding the optimal solution and improving the global optimization ability of the algorithm. The particle swarm of PSO has strong exploration and exploitation capabilities and can effectively search in the solution space to find the optimal solution. Through the mutual cooperation and competition of multiple particles, the algorithm can quickly find the optimal control parameter set, greatly shortening the optimization time. Through the automated particle swarm optimization process, there is no need to manually adjust the parameters of the PIλDμ controller, making the system more intelligent, reducing the need for human intervention, and improving the control accuracy and system reliability.

[0136] The beneficial effects brought by the technical solutions provided in the embodiments of the present invention at least include:

[0137] In an embodiment of the present invention, by performing grayscale processing on the cinema image, a target image is obtained, and the target image is input into a number recognition model based on the support vector machine algorithm for number recognition to determine the current number of people in the cinema. According to the current number of people in the cinema, the target indoor temperature and target indoor humidity of the cinema are determined, avoiding the traditional cinema air conditioning system relying only on single data collected by sensors for temperature and humidity control, being able to fully consider the dynamic changes of the environment, such as the change in the number of people, having accurate recognition of the personnel distribution and activity level in the cinema, and according to the target indoor temperature and target indoor humidity, through a PI λ D μ controller, adaptively adjust the indoor temperature and indoor humidity of the cinema, which can ensure that the air conditioner inside the cinema is accurately adjusted according to the real-time change in the number of people, improving the efficiency and comfort of the system.

[0138] Refer to the attached Figure 2 description, which shows a schematic flow chart of a method for adaptively adjusting cinema environment parameters provided by the present invention.

[0139] An embodiment of the present invention also provides a method for adaptively adjusting cinema environment parameters. This method can be implemented by a device for adaptively adjusting cinema environment parameters, and this device for adaptively adjusting cinema environment parameters can be a terminal or a server. The processing flow of the method for adaptively adjusting cinema environment parameters can include the following steps:

[0140] S1: Obtain a cinema image.

[0141] S2: Perform grayscale processing on the cinema image to obtain a target image.

[0142] In a possible implementation manner, S2 is specifically:

[0143] Perform grayscale processing on the cinema image through gamma transformation to obtain a target image.

[0144] S3: Construct a number recognition model based on the support vector machine algorithm.

[0145] S4: Input the target image into the number recognition model based on the support vector machine algorithm for number recognition to determine the current number of people in the cinema.

[0146] In a possible implementation manner, S4 specifically includes sub-steps S401 to S410:

[0147] S401: Divide the target image into multiple cells based on a preset pixel size.

[0148] S402: Calculate the horizontal gradient and vertical gradient of each pixel point in the cell through a Sobel filter.

[0149] In a possible implementation, S402 specifically is as follows:

[0150] According to the following formula, through the Sobel filter, calculate the horizontal gradient and vertical gradient of each pixel point in the cell:

[0151] I X =I*R x ,R x =[-1,0,1]

[0152] I Y =I*R y ,R y =[-1,0,1] T

[0153] Wherein, I X represents the horizontal gradient of the pixel point, I represents the pixel value of the pixel point, R x represents the Sobel filter matrix in the horizontal direction, I Y represents the vertical gradient of the pixel point, R y represents the Sobel filter matrix in the vertical direction, T represents the transpose operation.

[0154] S403: According to the horizontal gradient and vertical gradient of each pixel point in the cell, calculate the gradient magnitude and gradient direction of each pixel point in the cell.

[0155] In a possible implementation, S403 specifically is as follows:

[0156] According to the following formula, calculate the gradient magnitude and gradient direction of each pixel point in the cell:

[0157]

[0158] Wherein, G represents the gradient magnitude of the pixel point, | | represents taking the absolute value, θ represents the gradient direction of the pixel point, tan( ) represents the arctangent function, and mod represents the modulo operation.

[0159] S404: According to the gradient direction of each pixel point in the cell, divide multiple direction groups in the cell.

[0160] S405: According to the gradient magnitude of each pixel point in the cell, calculate the sum of the gradient magnitudes of each direction group to obtain the direction gradient histogram.

[0161] In a possible implementation, S405 specifically is as follows:

[0162] According to the following formula, calculate the sum of the gradient magnitudes of each direction group to obtain the direction gradient histogram:

[0163]

[0164] Among them, H j represents the total gradient magnitude of the j-th direction group, M represents the total number of pixel points in the direction group, and G i represents the gradient magnitude of the i-th pixel point in the direction group.

[0165] S406: Group each cell to obtain multiple feature blocks.

[0166] S407: Concatenate the histograms of oriented gradients in each cell of the feature block to obtain a block feature vector.

[0167] S408: Standardize the block feature vector through the L2-Norm algorithm to obtain a histogram of oriented gradients descriptor.

[0168] S409: Gradually scan the target image through a sliding window with a preset window size, and extract the histogram of oriented gradients descriptor within the current window.

[0169] S410: According to the histogram of oriented gradients descriptor within the current window, perform the number of people recognition through the support vector machine algorithm to determine the number of people in the current cinema.

[0170] S5: Determine the target indoor temperature and target indoor humidity of the cinema according to the number of people in the current cinema.

[0171] In a possible implementation manner, S5 specifically includes sub-steps S501 and S502:

[0172] S501: Set the basic ideal indoor temperature and basic ideal indoor humidity of the cinema.

[0173] S502: Determine the target indoor temperature and target indoor humidity of the cinema according to the number of people in the current cinema, the basic ideal indoor temperature, and the basic ideal indoor humidity:

[0174]

[0175] Among them, T target represents the target indoor temperature, T0 represents the basic ideal indoor temperature, b T represents the temperature change coefficient, N0 represents the number of people in the current cinema, N max represents the maximum capacity of the cinema, H target represents the target indoor humidity, H0 represents the basic ideal indoor humidity, b H represents the humidity change coefficient.

[0176] S6: According to the target indoor temperature and target indoor humidity, through PI λ Dμ A controller adaptively controls the air conditioner in the cinema to adaptively adjust the indoor temperature and indoor humidity of the cinema.

[0177] In a possible implementation, S6 specifically includes sub-steps S601 and S602:

[0178] S601: Obtain the actual indoor temperature and actual indoor humidity of the cinema through a temperature sensor and a humidity sensor.

[0179] S602: According to the target indoor temperature, target indoor humidity, actual indoor temperature, and actual indoor humidity, through a PI λ D μ controller, adaptively control the air conditioner in the cinema to adaptively adjust the indoor temperature and indoor humidity of the cinema:

[0180]

[0181] where u T (h) represents the temperature control signal at time h, represents the temperature proportional gain coefficient, e T (h) represents the deviation between the target indoor temperature and the actual indoor temperature at time h, represents the temperature integral gain coefficient, represents the temperature differential gain coefficient, D -λ represents the fractional-order integral operation, λ represents the integral order, D μ represents the fractional-order differential operation, μ represents the differential order, T now (h) represents the actual indoor temperature at time h, u H (h) represents the humidity control signal at time h, represents the humidity proportional gain coefficient, e H (h) represents the deviation between the target indoor humidity and the actual indoor humidity at time h, represents the humidity integral gain coefficient, represents the humidity differential gain coefficient, H now (h) represents the actual indoor humidity at time h.

[0182] In a possible implementation, the method for adaptively adjusting the cinema environment parameters further includes:

[0183] S7: Construct an objective function with the goal of reducing the air conditioner energy consumption during the operation of the air conditioner.

[0184] S8: According to the objective function, optimize the PI λ D μ controller through a particle swarm optimization algorithm.

[0185] It should be noted that the adaptive adjustment method of theater environment parameters can be implemented by the above-mentioned adaptive adjustment system of theater environment parameters, and can achieve the same or similar technical effects. To avoid repetition, the present invention will not elaborate herein.

[0186] The beneficial effects brought by the technical solutions provided in the embodiments of the present invention at least include:

[0187] In the embodiments of the present invention, by performing grayscale processing on the theater image to obtain a target image, and inputting the target image into a number recognition model based on the support vector machine algorithm for number recognition to determine the current number of people in the theater, and according to the current number of people in the theater, determining the target indoor temperature and target indoor humidity of the theater, it avoids the traditional theater air conditioning system relying only on a single data collected by sensors for temperature and humidity control, can fully consider the dynamic changes of the environment, such as the change in the number of people, has an accurate recognition of the personnel distribution and activity level in the theater, and according to the target indoor temperature and target indoor humidity, through PI λ D μ controller, adaptively adjusts the indoor temperature and indoor humidity of the theater, which can ensure that the air conditioner inside the theater is accurately adjusted according to the real-time change in the number of people, and improves the efficiency and comfort of the system.

[0188] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

[0189] The following points need to be noted:

[0190] (1) The drawings of the embodiments of the present invention only relate to the structures involved in the embodiments of the present invention, and other structures can refer to the usual designs.

[0191] (2) For clarity, in the drawings used to describe the embodiments of the present invention, the thickness of layers or regions is enlarged or reduced, that is, these drawings are not drawn according to the actual scale. It can be understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element can be "directly" on or under the other element or there can be intermediate elements.

[0192] (3) Without conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other to obtain new embodiments.

[0193] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A cinema environment parameter adaptive adjustment system, characterized in that: include: An acquisition module, used for acquiring cinema images; A processing module, used for performing grayscale processing on the cinema image to obtain a target image; The first building module is used to build a people recognition model based on a support vector machine algorithm; A recognition module, used for inputting the target image into the crowd recognition model based on the support vector machine algorithm to perform crowd recognition and determine the number of people in the current theater; A determination module, configured to determine a target indoor temperature and a target indoor humidity of the cinema according to the current number of people in the cinema; The adjustment module is used to adjust the target indoor temperature and the target indoor humidity through PI λ D μ The controller performs adaptive control on the air conditioning of the theater to adaptively adjust the indoor temperature and indoor humidity of the theater.

2. The theater environment parameter adaptive adjustment system according to claim 1, characterized in that: The processing module is specifically used for: The cinema image is gray-scaled by gamma transformation to obtain a target image.

3. The theater environment parameter adaptive adjustment system according to claim 1, characterized in that: The identification module is specifically used for: Based on a preset pixel size, dividing the target image into a plurality of cells; Calculate the horizontal gradient and vertical gradient of each pixel in the cell through a Sobel filter; Calculating the gradient magnitude and gradient direction of each pixel point in the cell according to the horizontal gradient and the vertical gradient of each pixel point in the cell; Dividing the cell into a plurality of direction groups according to the gradient directions of the pixels in the cell; According to the gradient amplitude of each pixel point in the cell, the sum of the gradient amplitudes of each direction group is calculated to obtain a directional gradient histogram; Grouping each of the cells to obtain a plurality of feature blocks; splicing the directional gradient histograms in each cell in the feature block to obtain a block feature vector; The block feature vector is normalized by an L2-Norm algorithm to obtain a histogram of oriented gradients descriptor; Scanning the target image step by step through a sliding window of a preset window size, and extracting a histogram of oriented gradients descriptor in the current window; According to the directional gradient histogram descriptor in the current window, the number of people is recognized by using a support vector machine algorithm to determine the current number of people in the theater.

4. The cinema environment parameter adaptive adjustment system according to claim 3, characterized in that: The identification module is also specifically used for: According to the following formula, the horizontal gradient and vertical gradient of each pixel in the cell are calculated through the Sobel filter.

5. The theater environment parameter adaptive adjustment system according to claim 3, characterized in that: The identification module is also specifically used for: According to the following formula, the gradient amplitude and gradient direction of each pixel in the cell are calculated.

6. The theater environment parameter adaptive adjustment system according to claim 3, characterized in that: The identification module is also specifically used for: According to the following formula, the sum of the gradient amplitudes of each direction group is calculated to obtain a directional gradient histogram.

7. The theater environment parameter adaptive adjustment system according to claim 1, characterized in that: The determination module is specifically used for: Set the basic ideal indoor temperature and basic ideal indoor humidity of the theater; The target indoor temperature and target indoor humidity of the theater are determined according to the current number of people in the theater, the basic ideal indoor temperature, and the basic ideal indoor humidity.

8. The theater environment parameter adaptive adjustment system according to claim 1, characterized in that: The adjustment module is specifically used for: The actual indoor temperature and humidity of the cinema are obtained through the temperature sensor and the humidity sensor; According to the target indoor temperature, the target indoor humidity, the actual indoor temperature and the actual indoor humidity, the target indoor temperature, the target indoor humidity, the actual indoor temperature and the actual indoor humidity, the target indoor humidity, the actual indoor humidity, the target indoor temperature, the target indoor humidity, the actual indoor humidity, the actual indoor temperature, the actual indoor humidity ... λ D μ The controller performs adaptive control on the air conditioning of the theater to adaptively adjust the indoor temperature and indoor humidity of the theater.

9. The theater environment parameter adaptive adjustment system according to claim 1, characterized in that: Also includes: The second building module is used to build an objective function with the goal of reducing the air conditioning energy consumption during the operation of the air conditioner; The optimization module is used to optimize the PI according to the objective function through a particle swarm optimization algorithm. λ D μ Optimize the controller.

10. A method for adaptively adjusting theater environment parameters, characterized in that: include: S1: Get cinema images; S2: grayscale processing is performed on the cinema image to obtain a target image; S3: Build a people recognition model based on support vector machine algorithm; S4: inputting the target image into the crowd recognition model based on the support vector machine algorithm to perform crowd recognition and determine the number of people in the current theater; S5: Determine a target indoor temperature and a target indoor humidity of the cinema according to the current number of people in the cinema; S6: According to the target indoor temperature and the target indoor humidity, the target indoor temperature and the target indoor humidity are calculated by PI λ D μ The controller performs adaptive control on the air conditioning of the theater to adaptively adjust the indoor temperature and indoor humidity of the theater.

Images