Amusement facility management and maintenance system based on big data

Abstract

The invention relates to the technical field of intelligent recreation facility management, and discloses a recreation facility management and maintenance system based on big data. According to the system, high-definition pictures of a large recreation facility and a small recreation facility are shot through a high-definition camera in a picture acquisition module, a picture processing module carries out brightness adjustment, contrast adjustment, denoising, zooming and normalization operation on the acquired pictures, and a feature extraction module carries out feature extraction on the processed picture data. The intelligent image recognition module takes the images subjected to image processing and feature extraction as a sample set and inputs the sample set into a convolutional neural network training image recognition model, and the big data prompt module applies the trained image recognition model to carry out image recognition. And the supervision requirement, the use management requirement, the maintenance requirement and the taking precautions of taking the large-scale recreation facility and the small-scale recreation facility are prompted and displayed through a visual interface.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent amusement facility management, and in particular to an amusement facility management and maintenance system based on big data. Background Art

[0002] Amusement facilities refer to a series of equipment and devices for people to entertain and play in places such as playgrounds, theme parks, and amusement parks. They are usually designed to be interesting and stimulating, aiming to provide tourists with a happy and relaxing experience. Common amusement facilities include roller coasters, Ferris wheels, bumper cars, carousels, water slides, mazes, etc. Effective management can ensure that amusement facilities undergo regular inspections and maintenance, and can promptly detect and repair potential safety hazards, thereby reducing the risk of accidents. The management system will formulate clear operating procedures and safety specifications to ensure that operators follow standards and enhance passengers' sense of security.

[0003] At present, the management method of amusement facilities is mainly through manual reminders and on-site inspections. This method requires a large number of inspectors to spread out to cover the entire amusement park. The management efficiency is very low, resulting in the failure of amusement park facilities to be discovered in time, thus causing safety hazards. Summary of the invention

[0004] 1. Technical issues to be solved

[0005] In view of the shortcomings of the prior art, the present invention provides an amusement facility management and maintenance system based on big data, which has the function of taking high-definition pictures of large amusement facilities such as Ferris wheels, pirate ships, bobbing chairs and roller coasters and small amusement facilities such as inflatable castles, climbing nets, swing machines and grass slides through a high-definition camera in an image acquisition module. The image processing module adjusts the brightness, contrast, denoises, scales and normalizes the collected pictures of large amusement facilities and small amusement facilities. The feature extraction module extracts edge features, texture features and shape features from the image data processed by the image processing module. The intelligent image The recognition module uses the images that have undergone image processing and feature extraction as sample sets, and inputs them into the convolutional neural network to train the image recognition model to identify large and small amusement facilities. The big data prompt module uses the trained image recognition model to prompt the regulatory requirements, usage management requirements, maintenance requirements and riding precautions for large and small amusement facilities, and displays them through a visual interface. The use of this system does not require a large amount of manpower to inspect the amusement facilities, and can promptly discover faults in the amusement park facilities, thereby improving management and maintenance efficiency, reducing safety hazards in the play of amusement facilities, and solving the above-mentioned problems.

[0006] (II) Technical solution

[0007] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a big data-based amusement facility management and maintenance system, comprising a picture acquisition module, a picture processing module, a feature extraction module, an intelligent image recognition module and a big data prompt module;

[0008] The image acquisition module uses a high-definition camera to capture high-definition images of large amusement facilities such as Ferris wheels, pirate ships, bobbing chairs, and roller coasters, and small amusement facilities such as inflatable castles, climbing nets, swing machines, and grass slides, and transmits the captured images to the image processing module;

[0009] The image processing module adjusts the brightness, adjusts the contrast, removes noise, scales, and normalizes the collected images of the large-scale amusement facilities and the small-scale amusement facilities, and sends the normalized images to the feature extraction module;

[0010] The feature extraction module extracts edge features, texture features and shape features from the image data processed by the image processing module, and transmits the image data after feature extraction to the intelligent image recognition module;

[0011] The intelligent image recognition module uses the images processed and feature extracted as sample sets, inputs them into the convolutional neural network to train the image recognition model, and identifies large amusement facilities and small amusement facilities;

[0012] The big data prompt module uses a trained image recognition model to prompt the regulatory requirements, usage management requirements, maintenance requirements and riding precautions for large and small amusement facilities, and displays them through a visual interface.

[0013] Preferably, the image processing module adjusts the brightness of the collected images of large-scale amusement facilities and small-scale amusement facilities, and the image brightness adjustment formula is as follows:

[0014] Txt new =c*log(1+Txst old )

[0015] In the formula, Txst new Indicates the image pixel after brightness adjustment, c represents a constant with a value of 255, Txst old Represents the original image pixel value.

[0016] Preferably, the image processing module adjusts the contrast of the collected images of large-scale amusement facilities and small-scale amusement facilities, and the image contrast adjustment formula is as follows:

[0017] Duib new =α*((Txst old -Pjld)+Pjld

[0018] In the formula, Duib new Indicates the pixel value for adjusting contrast, α indicates the contrast factor, a value greater than 1 indicates enhanced contrast, a value less than 1 indicates reduced contrast, Txst old Represents the original image pixel value, Pjld represents the average brightness value of the image, which is automatically obtained by the system.

[0019] Preferably, the image processing module performs a denoising operation on the collected images of large-scale amusement facilities and small-scale amusement facilities, and the image denoising formula is as follows:

[0020] Tp new (x,y)=median{Txst old (x1,y1)|(x1,y1)∈N(x,y)}

[0021] In the formula, Tp new (x, y) represents the new pixel value of the denoised image, median represents the median filter denoising formula, Txst old (x1, y1) represents the original image pixel, and N(x, y) represents the neighborhood centered at (x, y).

[0022] Preferably, the image processing module performs a scaling operation on the collected images of large-scale amusement facilities and small-scale amusement facilities, and the image scaling formula is as follows:

[0023]

[0024] In the formula, Sf new (x, y) represents the pixel point after the image is scaled, Txst old Represents the original image pixel value, s x ,s y The scaling factors for the horizontal and vertical directions respectively.

[0025] Preferably, the image processing module performs a normalization operation on the collected images of large-scale amusement facilities and small-scale amusement facilities, and the image normalization formula is as follows:

[0026]

[0027] In the formula, Guiy(x,y) represents the normalized image pixel, Txst old (x, y) represents the original image pixel, Txst max With Txst min Represents the maximum and minimum pixel values ​​in the image.

[0028] Preferably, the feature extraction module extracts edge features from the image data processed by the image processing module, and the edge feature extraction formula is as follows:

[0029]

[0030] In the formula, G(x,y) represents the image pixels for edge detection, σ represents the standard deviation, which controls the width of the Gaussian distribution. The larger the standard deviation, the wider the distribution, resulting in more pixels being smoothed. The smaller the standard deviation, the narrower the distribution, and the less smoothing effect. 2πσ 2 represents the normalization constant of the Gaussian distribution, ensuring that the integral of the entire distribution is 1, The exponential term represents the Gaussian function and describes the shape of the distribution. It means that the farther the distance from the center to the (x, y) point is, the smaller the function value is, forming a radial attenuation.

[0031] Preferably, the feature extraction module extracts texture features from the image data processed by the image processing module, and the texture feature extraction formula is as follows:

[0032] Expl = δ(Txst old (x,y)-Txst old (x+d*cosθ,y+d*sinθ))

[0033] In the formula, Expl represents the image texture feature, δ represents the Kronecker delta function used for feature extraction, d represents the distance between image pixels, and θ represents the angle between image pixels.

[0034] Preferably, the feature extraction module extracts shape features from the image data processed by the image processing module, and the shape feature extraction formula is as follows:

[0035]

[0036] In the formula, Cpxe represents the flatness of the image shape, P represents the perimeter of the image, and A represents the area of ​​the image. The closer the flatness is to 1, the closer the shape is to a circle. The larger the value, the more complex the shape.

[0037] Preferably, the intelligent image recognition module uses the images processed and feature extracted as sample sets and inputs them into a convolutional neural network to train an image recognition model. The convolution algorithm formula is as follows:

[0038]

[0039] In the formula, Sc i,j Indicates the value of position (i, j) in the output feature image, Sr i+m,j+nRepresents the pixel value of the input image at position (i+m,j+n), (flteri) m,n Represents the value of the convolution kernel, K represents the size of the filter, and i, j represents the position index of the output feature image.

[0040] Compared with the prior art, the present invention provides an amusement facility management and maintenance system based on big data, which has the following beneficial effects:

[0041] The present invention uses a high-definition camera in a picture acquisition module to shoot high-definition pictures of large amusement facilities such as a Ferris wheel, a pirate ship, a bobbing chair, and a roller coaster, and small amusement facilities such as an inflatable castle, a climbing net, a swing machine, and a grass slide. The picture processing module adjusts the brightness, adjusts the contrast, removes noise, scales, and normalizes the collected pictures of the large amusement facilities and the small amusement facilities. The feature extraction module extracts edge features, texture features, and shape features from the picture data processed by the picture processing module. The intelligent image recognition module uses the pictures that have been processed and feature extracted as sample sets, inputs them into a convolutional neural network to train a picture recognition model, and identifies large amusement facilities and small amusement facilities. The big data prompt module uses the trained picture recognition model to prompt the supervision requirements, use management requirements, maintenance requirements, and riding precautions for riding large amusement facilities and small amusement facilities, and displays them through a visual interface. The use of the system does not require a large amount of manpower to inspect the amusement facilities, and faults in the amusement park facilities can be discovered in time, thereby improving the management and maintenance efficiency and reducing the safety hazards of the amusement facilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] The current way to manage amusement facilities is mainly through manual reminders and on-site inspections. This method requires a large number of inspectors to spread to cover the entire amusement park. The management efficiency is very low, resulting in the failure of amusement park facilities to be discovered in time, thus causing safety hazards. For this reason, a big data-based amusement facility management and maintenance system is proposed. Please refer to Figure 1 The system includes an image acquisition module, an image processing module, a feature extraction module, an intelligent image recognition module and a big data prompt module, wherein:

[0045] The picture acquisition module uses a high-resolution HD camera, which can accurately capture high-definition pictures of large amusement facilities such as Ferris wheels, pirate ships, swing chairs, roller coasters, and small amusement facilities such as inflatable castles, climbing nets, swing machines, and grass slides. The system is equipped with autofocus and image stabilization technology to ensure image clarity and detail even in fast-moving environments. The camera is selected with consideration of lighting conditions and is equipped with high-quality photosensitive elements for low-light environments, so that it can still capture high-quality pictures in low-light environments. At the same time, the system supports multi-angle shooting and can obtain comprehensive visual effects of amusement facilities from different perspectives. In addition, the real-time image preview function enables the operator to instantly adjust the shooting angle and parameters during the shooting process to obtain the best effect;

[0046] The collected high-definition images are transmitted to the image processing module in real time through high-speed data transmission interfaces such as USB 3.0 or Ethernet. During the transmission process, the data will be encrypted to ensure the security and integrity of the image content. The image processing module has a built-in powerful image processing algorithm, which can perform various processing on the collected images, such as denoising, contrast enhancement, color adjustment, and edge detection, to improve the visual effect of the image and the accuracy of information extraction;

[0047] The image processing module adjusts the brightness, contrast, denoises, scales, and normalizes the collected images of large-scale amusement facilities and small-scale amusement facilities, and sends the normalized images to the feature extraction module;

[0048] The formula for adjusting the image brightness is as follows:

[0049] Txt new =c*log(1+Txst old )

[0050] By adjusting the brightness, the details in the image can be made more obvious. In the monitoring image, adjusting the brightness can help technicians more easily identify potential safety problems or damage to the equipment, which helps to promptly discover and deal with potential hazards that may pose a threat to customer safety. In the formula, Txst new Indicates the image pixel after brightness adjustment, c represents a constant with a value of 255, Txst old Indicates the original image pixel value. During maintenance and inspection, standardized historical records can be made through unified brightness adjustment, making subsequent comparison and analysis more intuitive.

[0051] The formula for adjusting the contrast of an image is as follows:

[0052] Duib new =α*(Txst old-Pjld)+Pjld

[0053] High-contrast images can extract features more effectively, making subsequent data analysis and machine learning model training more accurate, which helps to evaluate and predict facility performance. In the formula, Duib new Indicates the pixel value for adjusting contrast, α indicates the contrast factor, a value greater than 1 indicates enhanced contrast, a value less than 1 indicates reduced contrast, Txst old represents the pixel value of the original image, and Pjld represents the average brightness value of the image, which is automatically obtained by the system;

[0054] The image denoising formula is as follows:

[0055] Tp new (x, y) = median{Txst old (x1,y1)|(x1,y1)∈N(x,y)}

[0056] Denoising can eliminate interference and unnecessary details in the image, making important information more prominent and improving the clarity and readability of the overall image. In the formula, Tp new (x, y) represents the new pixel value of the denoised image, median represents the median filter denoising formula, Txst old (x1, y1) represents the original image pixel, and N(x, y) represents the neighborhood centered at (x, y). By removing noise points, the status of equipment and personnel can be more clearly identified, potential safety hazards can be discovered in time, and the safety of amusement facilities can be ensured;

[0057] The image scaling formula is as follows:

[0058]

[0059] The zoom function enables users to make intuitive comparisons between different images, improve the accuracy of data analysis, and help discover changes and trends. In the formula, Sf new (x, y) represents the pixel point after the image is scaled, Txst old Represents the original image pixel value, s x ,s y Horizontal and vertical zoom factors, respectively. When showing customers rides or safety checks, the zoom function can provide a more detailed perspective, enhancing customer trust and satisfaction;

[0060] The picture normalization formula is as follows:

[0061]

[0062] Normalization adjusts images from different sources and times to a consistent standard, making the data more visually uniform and easier to analyze and compare later. In the formula, Guiy(x,y) represents the normalized image pixel, and Txst old (x, y) represents the original image pixel, Txst max With Txst min Represents the maximum and minimum values ​​of the pixel values ​​in the image. When training machine learning models, normalization helps accelerate convergence and improve the accuracy of the model, especially in applications involving image classification, target detection, etc.

[0063] The feature extraction module extracts edge features, texture features and shape features from the image data processed by the image processing module, and transmits the extracted image data to the intelligent image recognition module, wherein:

[0064] The edge feature extraction formula is as follows:

[0065]

[0066] Edge feature extraction can clearly identify and locate the contours of amusement facilities, improve the target detection effect in dynamic images, and facilitate timely detection of problems. In the formula, G(x, y) represents the image pixels for edge detection, σ represents the standard deviation, and controls the width of the Gaussian distribution. The larger the standard deviation, the wider the distribution, resulting in more pixels being smoothed. The smaller the standard deviation, the narrower the distribution, and the less smoothing effect. 2πσ 2 represents the normalization constant of the Gaussian distribution, ensuring that the integral of the entire distribution is 1, The exponential term of the Gaussian function describes the shape of the distribution. It means that the farther the distance from the center to the (x, y) point is, the smaller the function value is, forming a radial attenuation. By extracting edge features, the amount of data to be processed can be reduced, the computational complexity can be reduced, and the speed of subsequent analysis and processing can be accelerated.

[0067] The texture feature extraction formula is as follows:

[0068] Expl = δ(Txst old (x,y)-Txst old (x+d*cosθ,y+d*sinθ))

[0069] By extracting texture features, we can better capture the details of the surface of amusement facilities, which helps to distinguish different types of equipment or components. In the formula, Expl represents the image texture features, δ represents the Kronecker delta function for feature extraction, d represents the distance between image pixels, and θ represents the angle between image pixels. Texture features can provide rich information, help form a comprehensive equipment status profile, and support more in-depth fault analysis and maintenance decisions;

[0070] The shape feature extraction formula is as follows:

[0071]

[0072] By monitoring the shape of the equipment, deformation, damage and other faults can be discovered in time, so as to issue early warnings and avoid safety accidents. In the formula, Cpxe represents the flatness of the shape of the image, P represents the perimeter of the image, and A represents the area of ​​the image. The closer the flatness is to 1, the closer the shape is to a circle. The larger the value, the more complex the shape. The regularity and stability of the shape can directly reflect the safety of the equipment and help identify whether there are potential safety hazards.

[0073] The intelligent image recognition module uses the processed and feature-extracted images as sample sets and inputs them into the convolutional neural network to train the image recognition model;

[0074] The convolution algorithm formula is as follows:

[0075]

[0076] By building a multi-layer convolution structure, we can effectively extract features at different levels, from basic edges to complex shapes, and improve the model's ability to understand complex objects. In the formula, Sc i,j Indicates the value of position (i, j) in the output feature image, Sr i+m,j+n Represents the pixel value of the input image at position (i+m,j+n), (flteri) m,n represents the value of the convolution kernel, K represents the size of the filter, and i,j represents the position index of the output feature image. Through the convolutional neural network, image features such as facility damage and wear can be effectively identified and classified to improve the accuracy of fault detection;

[0077] The big data prompt module uses the trained image recognition model to prompt the supervision requirements, use management requirements, maintenance requirements and riding precautions of large and small amusement facilities, and displays them through a visual interface;

[0078] Once the scene of riding an amusement facility is identified, the system will automatically generate prompt information according to the pre-set regulatory requirements. For example, for large amusement facilities, the system may recommend strengthening the supervision of seat belt use and remind supervisors to check the safety and operational compliance of the facilities. For small amusement facilities, it may focus on the age limit and weight requirements for children to ensure passenger safety.

[0079] The module can also analyze passenger flow based on real-time data and adjust management strategies. For example, when the system detects that a facility is used too frequently, it will recommend adding more staff on duty to conduct more on-site inspections and management to ensure passenger safety and satisfaction.

[0080] Maintenance is another important aspect to ensure the safe operation of amusement facilities. Through image recognition, the system can detect potential faults of facilities, such as wear and tear of equipment, oil leakage or structural damage. After identifying abnormal conditions, the system will automatically generate a maintenance log and intelligently recommend maintenance cycles and emergency repair priorities based on parameters such as the frequency of use of the facilities and the type of faults.

[0081] In order to enhance passengers' sense of security and riding experience, the module is not limited to background data processing, but also displays riding precautions on a visual interface. For example, before passengers board the vehicle, the system can prompt them through the screen or mobile device whether they need to fasten their seat belts, confirm age and height requirements, etc. In addition, during the ride, passengers can be reminded in time to pay attention to specific safety instructions, such as the safety regulations to be followed when riding during peak hours.

[0082] The application of this system eliminates the need for a large amount of manpower to inspect amusement facilities, and enables timely detection of malfunctions in amusement park facilities, thereby improving management and maintenance efficiency and reducing safety hazards in amusement facility rides.

[0083] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An amusement facility management and maintenance system based on big data, characterized by: It includes picture acquisition module, picture processing module, feature extraction module, intelligent image recognition module and big data prompt module; The image acquisition module uses a high-definition camera to capture high-definition images of large amusement facilities such as Ferris wheels, pirate ships, bobbing chairs, and roller coasters, and small amusement facilities such as inflatable castles, climbing nets, swing machines, and grass slides, and transmits the captured images to the image processing module; The image processing module adjusts the brightness, adjusts the contrast, removes noise, scales, and normalizes the collected images of the large-scale amusement facilities and the small-scale amusement facilities, and sends the normalized images to the feature extraction module; The feature extraction module extracts edge features, texture features and shape features from the image data processed by the image processing module, and transmits the image data after feature extraction to the intelligent image recognition module; The intelligent image recognition module uses the images processed and feature extracted as sample sets, inputs them into the convolutional neural network to train the image recognition model, and identifies large amusement facilities and small amusement facilities; The big data prompt module uses a trained image recognition model to prompt the regulatory requirements, usage management requirements, maintenance requirements and riding precautions for large and small amusement facilities, and displays them through a visual interface.

2. The amusement facility management and maintenance system based on big data according to claim 1, characterized in that: The image processing module adjusts the brightness of the collected images of large-scale amusement facilities and small-scale amusement facilities. The image brightness adjustment formula is as follows: Txst new =c*log(1+Txst old ) In the formula, Txst new Indicates the image pixel after brightness adjustment, c represents a constant with a value of 255, Txst old Represents the original image pixel value.

3. The amusement facility management and maintenance system based on big data according to claim 2, characterized in that: The image processing module adjusts the contrast of the collected images of large-scale amusement facilities and small-scale amusement facilities. The image contrast adjustment formula is as follows: Duib new =α*(Txst old -Pjld)+Pjld In the formula, Duib new Indicates the pixel value for adjusting contrast, α indicates the contrast factor, a value greater than 1 indicates enhanced contrast, a value less than 1 indicates reduced contrast, Txst old Represents the original image pixel value, Pjld represents the average brightness value of the image, which is automatically obtained by the system.

4. The amusement facility management and maintenance system based on big data according to claim 3 is characterized by: The image processing module performs denoising operation on the collected images of large-scale amusement facilities and small-scale amusement facilities. The image denoising formula is as follows: Tp new (x,y)=median{Txst old (x1,y1)|(x1,y1)∈N(x,y)} In the formula, Tp new (x, y) represents the new pixel value of the denoised image, median represents the median filter denoising formula, Txst old (x1, y1) represents the original image pixel, and N(x, y) represents the neighborhood centered at (x, y).

5. The amusement facility management and maintenance system based on big data according to claim 4 is characterized in that: The image processing module performs scaling operations on the collected images of large-scale amusement facilities and small-scale amusement facilities. The image scaling formula is as follows: In the formula, Sf new (x, y) represents the pixel point after the image is scaled, Txst old Represents the original image pixel value, s x ,s y The scaling factors for the horizontal and vertical directions respectively.

6. The amusement facility management and maintenance system based on big data according to claim 5, characterized in that: The image processing module performs normalization operation on the collected images of large-scale amusement facilities and small-scale amusement facilities. The image normalization formula is as follows: In the formula, Guiy(x, y) represents the normalized image pixel, Txst old (x, y) represents the original image pixel, Txst max With Txst min Represents the maximum and minimum pixel values ​​in the image.

7. The amusement facility management and maintenance system based on big data according to claim 6 is characterized by: The feature extraction module extracts edge features from the image data processed by the image processing module. The edge feature extraction formula is as follows: In the formula, G(x, y) represents the image pixels for edge detection, σ represents the standard deviation, which controls the width of the Gaussian distribution. The larger the standard deviation, the wider the distribution, resulting in more pixels being smoothed. The smaller the standard deviation, the narrower the distribution, and the less smoothing effect. 2πσ 2 represents the normalization constant of the Gaussian distribution, ensuring that the integral of the entire distribution is 1, The exponential term represents the Gaussian function and describes the shape of the distribution. It means that the farther the distance from the center to the (x, y) point is, the smaller the function value is, forming a radial attenuation.

8. The amusement facility management and maintenance system based on big data according to claim 7, characterized in that: The feature extraction module extracts texture features from the image data processed by the image processing module. The texture feature extraction formula is as follows: Expl=δ(Txst old (x,y)-Txst old (x+d*cosθ,y+d*sinθ)) In the formula, Expl represents the image texture feature, δ represents the Kronecker delta function used for feature extraction, d represents the distance between image pixels, and θ represents the angle between image pixels.

9. The amusement facility management and maintenance system based on big data according to claim 8, characterized in that: The feature extraction module extracts shape features from the image data processed by the image processing module. The shape feature extraction formula is as follows: In the formula, Cpxe represents the flatness of the image shape, P represents the perimeter of the image, and A represents the area of ​​the image. The closer the flatness is to 1, the closer the shape is to a circle. The larger the value, the more complex the shape.

10. The amusement facility management and maintenance system based on big data according to claim 9, characterized in that: The intelligent image recognition module uses the images processed and feature extracted as sample sets and inputs them into the convolutional neural network to train the image recognition model. The convolution algorithm formula is as follows: In the formula, Sc i，j Indicates the value of position (i, j) in the output feature image, Sr i+m，j+n Represents the pixel value of the input image at position (i+m, j+n), (flteri) m，n Represents the value of the convolution kernel, K represents the size of the filter, and i, j represent the position index of the output feature image.

Images