Intelligent management system and method for wallboard installation

Abstract

The invention aims to provide an intelligent management system and method for wallboard installation. The method comprises the following steps: acquiring a wall image; optimizing the wallboard installation management model; and inputting the wall image into the wallboard installation management model, and outputting a wallboard installation result by the wallboard installation management model. The method has the wall position detection capability and the wallboard layout prediction capability at the same time, the whole house wallboard installation is comprehensively covered, a plurality of detection results are combined, a wallboard installation management scheme is intelligently evaluated, the wallboard installation accuracy and reliability are improved, and the wallboard layout precision is improved through a genetic algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to an intelligent management system and method for wall panel installation. Background Art

[0002] Image recognition is an important area of ​​artificial intelligence that uses computers to process, analyze, and understand images to identify targets and objects in various different patterns. Image recognition technology automatically identifies and classifies objects, scenes, and other information in images by analyzing features and patterns in images. Image recognition, also known as computer vision, is a technology that uses computers and artificial intelligence technology to analyze and understand images. It can not only identify objects and scenes in two-dimensional images, but also process objects and environmental perception in the three-dimensional world. Image recognition technology has a wide range of applications in various industries, including manufacturing, healthcare, retail, agriculture, and security monitoring. In manufacturing, image recognition is used for automated quality control; in healthcare, it helps doctors detect diseases more accurately; in retail, image recognition can provide a personalized shopping experience; in agriculture, it helps identify crop problems and take action; in security monitoring, image recognition is used to monitor and detect abnormal situations.

[0003] Traditional image processing methods mainly rely on traditional computer vision and image processing technologies such as edge detection and color segmentation. Machine learning methods are based on statistical machine learning algorithms and are beginning to be applied to image recognition. The emergence of deep learning methods such as convolutional neural networks (CNNs) has greatly promoted the development of image recognition and achieved end-to-end image recognition tasks. Pre-trained models and transfer learning: Model efficiency is improved by pre-training models on large-scale data sets and then fine-tuning them on specific tasks. In recent years, image recognition has been combined with other technologies such as natural language processing (NLP) and augmented reality (AR) to promote innovative applications.

[0004] The traditional wall panel installation process requires the use of measuring tools (such as tape measures or levels) to measure the wall size and position, and mark the wall installation position. This method has low installation efficiency and low installation accuracy, so artificial intelligence can be used to intelligently assist the installation of wall panels. At present, when artificial intelligence identifies the installation position of wall panels, since most wall panels are white, but white itself has no obvious color contrast, it is difficult to determine the range and type of the installation position of the wall panels that is not very obvious during image detection, making it difficult to accurately install the wall panels. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent management system and method for wall panel installation, which has both wall position detection capabilities and wall panel layout prediction capabilities, comprehensively covers the installation of wall panels throughout the house, combines multiple detection results, intelligently evaluates wall panel installation management plans, improves the accuracy and reliability of wall panel installation, and improves the accuracy of wall panel layout through genetic algorithms.

[0006] An intelligent management method for wall panel installation, comprising:

[0007] Get the wall image;

[0008] Optimize the wall panel installation management model;

[0009] The wall surface image is input into the wall panel installation management model, and the wall panel installation management model outputs the wall panel installation result.

[0010] Preferably, after acquiring the wall image, the method further includes preprocessing the wall image, specifically:

[0011] Grayscale the wall image;

[0012] De-noising the grayscale wall image;

[0013] Perform enhancement processing on the denoised wall image;

[0014] The enhanced wall image is size-standardized.

[0015] Preferably, the optimized wall panel installation management model includes:

[0016] Replacing the architecture of the wall panel installation management model with ResNet50 feature extraction;

[0017] Add RPN and RoI pooling detection layers to the wall panel installation management model;

[0018] Optimizing the loss function of the wall panel installation management model;

[0019] A genetic algorithm is added to the wall panel installation management model.

[0020] Preferably, after the grayscale wall image is subjected to denoising, the method further includes judging whether the denoising effect meets the standard, specifically:

[0021] The denoising effect is expressed as:

[0022]

[0023] Among them, f is the original image, g is the denoised image, and u f is the average value of the original image, u gThe average value of the denoised image, σ (f，g) is the covariance of the original image and the denoised image, σ f is the variance of the original image, σ g Variance of the denoised image, A1 and A2 are constants.

[0024] Preferably, replacing the architecture of the wallboard installation management model with ResNet50 feature extraction includes:

[0025] ResNet50 is used to extract features from wall images, expressed as:

[0026]

[0027] Among them, w ij is the weight of the i-th row and j-th column of the convolution kernel, x ij is the element in the i-th row and j-th column of the input feature map, b is the bias term, and the size of the convolution kernel is m×n.

[0028] Preferably, the loss function for optimizing the wall panel installation management model includes:

[0029]

[0030] Among them, p i is the probability that the i-th anchor box is predicted as a target, is the true value of the i-th anchor box. When it is a positive sample, the value is 1, otherwise it is 0. L1 is the classification loss function, L2 is the regression loss function, and L t is the total loss function, N1 is the number of training anchor boxes, N2 is the number of anchor boxes that need to be regressed, α is the balance coefficient, smooth is the smoothing function, and t i is the offset parameter between the predicted box and the corresponding anchor box, is the offset parameter between the real target box and the corresponding anchor box.

[0031] Preferably, adding a genetic algorithm to the wall panel installation management model comprises:

[0032] The wall data and wall panel dimensions are input into the genetic algorithm as a training set;

[0033] Training the genetic algorithm;

[0034] The trained genetic algorithm is used to calculate the installation layout and installation quantity of wall panels according to the wall surface data and wall panel dimensions.

[0035] An intelligent wallboard defect detection system based on image recognition, comprising:

[0036] An image acquisition module, used for acquiring wall images;

[0037] Model optimization module, used to optimize the wall panel installation management model;

[0038] The image processing module is used to input the wall surface image into the wall panel installation management model, and the wall panel installation management model outputs the wall panel installation result.

[0039] An electronic device comprises: a chip, a processor and a memory, wherein the memory is used to store computer program codes, the computer program codes include computer instructions, and when the chip executes the computer instructions, the electronic device executes an intelligent management method for wall panel installation.

[0040] A computer-readable storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes an intelligent management method for wall panel installation.

[0041] The beneficial effects of the present invention are: 1. The present invention preprocesses the wall image, and the installation position in the preprocessed wall image will be easier to detect, which can help machine vision better identify the wall panel installation position. 2. The present invention optimizes and improves the wall panel installation management model, making the model more sensitive to the wall installation position, replacing the feature extraction network to better extract features related to the wall panel installation position, and optimizing the loss function to make the model's detection accuracy higher. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0044] Figure 1 A flow chart of an intelligent management method for wall panel installation according to the present invention;

[0045] Figure 2 Optimizing the flow chart of the wall panel installation management model of the present invention;

[0046] Figure 3 The figure is a schematic diagram of the hardware structure of an electronic device of the present invention. DETAILED DESCRIPTION

[0047] 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.

[0048] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0049] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0050] The traditional wall panel installation process requires the use of measuring tools (such as tape measures or levels) to measure the wall size and position, and mark the wall installation position. This method has low installation efficiency and low installation accuracy, so artificial intelligence can be used to intelligently assist the installation of wall panels. At present, when artificial intelligence identifies the installation position of wall panels, since most wall panels are white, but white itself has no obvious color contrast, it is difficult to determine the range and type of the installation position of the wall panels that is not very obvious during image detection, making it difficult to accurately install the wall panels.

[0051] The present invention preprocesses the wall image, and the installation position in the preprocessed wall image will be easier to detect, which can help machine vision better identify the wall panel installation position. The present invention optimizes and improves the wall panel installation management model, making the model more sensitive to the wall installation position, replacing the feature extraction network to better extract features related to the wall panel installation position, and optimizing the loss function to make the model have higher detection accuracy.

[0052] Example 1

[0053] An intelligent management method for wall panel installation, reference Figure 1 ,include:

[0054] S100, acquiring a wall image;

[0055] Laser radar scanning is combined with a camera to obtain wall images. Laser radar scanning the wall is to determine the distance and position of the target object by emitting a laser beam and measuring the time it takes for it to reflect back, thereby constructing a three-dimensional point cloud map of the surrounding environment. The working principle of laser radar can be summarized as three steps: "transmit-reflect-receive". It performs continuous scanning in a specified area through high-speed rotation or electronic scanning. When a target is detected entering the set warning area, it can quickly locate the target position and track it in real time. When identifying the side wall, the laser radar will scan the side of the wall, and then calculate the distance and position of the wall based on the reflected laser signal. Through the combination of multiple scanning points, the laser radar can construct the three-dimensional shape of the wall, thereby realizing accurate identification of the side wall.

[0056] Through laser radar scanning, point cloud data of the wall can be obtained, and the point cloud data can be used in the fields of 3D modeling, scene reconstruction, robot navigation, virtual reality and augmented reality. Through point cloud data, a realistic 3D scene model can be generated. In the embodiment of the present invention, the point cloud data is used to calculate the parameters of the wall, and the parameters of the wall include: the height of the wall, the width of the wall and the position of the wall.

[0057] S200, optimized wall panel installation management model;

[0058] The main function of the wall panel installation management model is to calculate the installation plan of the wall panel according to the obtained wall parameters. The content of the wall panel installation plan includes: at the specified position of the specified wall surface and at the specified angle, the wall panel installation management model first needs to process the wall image, capture the specified position of the wall image, and then start matching the corresponding wall panel to be installed, and then control the wall panel to install the wall panel according to the specified angle. Then the installation plan is output to the mechanical control module, and the mechanical control module installs the wall panel according to the installation plan. The robot system developed using artificial intelligence technology is used to automatically install the wall panel. The mechanical control module includes robots, sensors, control systems and related software, which can automatically complete operations such as picking, clamping, lifting, flipping and installing wall panels.

[0059] S300, inputting the wall surface image into the wall panel installation management model, and the wall panel installation management model outputs the wall panel installation result.

[0060] In an embodiment of the present invention, the wall panel installation management model can accurately identify the specific position on the wall where the wall panel needs to be installed, and can match the type of wall panel to be installed in the design plan. In the wall panel installation management plan, each wall where the wall panel needs to be installed is first labeled, and then the wall panel to be installed is labeled, and then the wall is identified. After the wall where the wall panel needs to be installed in the design plan is identified, the installation position of the wall is searched. After the installation position is determined, the control signal is output to the mechanical control module to control the wall panel to be intelligently installed. The present invention does not require manual control and can intelligently install wall panels according to the input design plan. It has high installation efficiency and accurate installation position, avoids installation defects caused by manual measurement errors, and can also install multiple wall panels at the same time, which can greatly improve the wall panel installation efficiency.

[0061] Preferably, after S100, obtaining the wall image, the method further includes S110, preprocessing the wall image, specifically:

[0062] S111, graying the wall image;

[0063] Because most walls are solid colors or have a small number of patterns, and the color and pattern of the wall have little effect on the installation position of the wallboard, it is necessary to grayscale the wall image to reduce the influence of unnecessary colors, simplify image processing, improve computational efficiency, reduce the amount of data, and enhance the recognizability of image features. Each pixel in a color image is determined by three components: red (R), green (G), and blue (B), which means that the amount of data in a color image is large and relatively complex to process. In contrast, each pixel in a grayscale image has only one grayscale value, which simplifies the image representation and makes the processing process more efficient. Each pixel in a color image can have 16777216 color changes (256 cubed), while each pixel in a grayscale image has only 256 color changes (0-255). Therefore, converting a color image to a grayscale image can significantly reduce the amount of computation and improve processing speed. In a grayscale image, the grayscale value of each pixel reflects the brightness information of the point, which helps to better analyze and identify wall image features in image processing and computer vision tasks.

[0064] S112, performing denoising on the grayscale wall image;

[0065] The main function of image denoising is to improve the quality of the image and make it more suitable for subsequent computer vision processing and analysis. Image denoising technology can significantly improve the clarity and details of wall images by removing noise from wall images, thereby improving the overall visual effect of wall images. By removing random noise from wall images, such as light interference and sensor noise, image denoising technology can make wall images clearer, reduce blur and distortion, and improve the overall quality of the image. In the wall panel installation management model, denoising can reduce the interference of noise on wall image recognition and classification, and improve the performance and accuracy of the system.

[0066] S113, performing enhancement processing on the denoised wall image;

[0067] The main function of image enhancement is to improve the visual effect and quality of the image, making it more suitable for specific application requirements. By enhancing the overall or local characteristics of the image, image enhancement technology can make the originally unclear image clear, enhance certain features of interest, expand the difference between the features of different objects in the image, and suppress features of no interest, thereby improving the quality of the image and enriching the amount of information. In an embodiment of the present invention, information such as the texture of the wall can be enhanced to strengthen the recognition of the installation location by the wall installation management model.

[0068] S114, standardizing the size of the enhanced wall image.

[0069] By standardizing the image size, the size differences caused by factors such as image acquisition equipment and environment can be eliminated, making the wall image more consistent and reliable during the recognition process, thereby improving the accuracy of recognition. The standardized image size can reduce the computational complexity and make the image processing algorithm more efficient. For example, when processing a large number of wall images, a unified size can simplify the processing flow and reduce the consumption of computing resources. Standardization can eliminate errors caused by different sizes and enhance the robustness of the wall panel installation management model, so that it can maintain a high recognition rate when facing wall image inputs of different sizes.

[0070] Preferably, S200, optimizing the wall panel installation management model includes:

[0071] S210, replace the architecture of the wall panel installation management model with ResNet50 feature extraction;

[0072] ResNet-50 is a deep convolutional neural network. The network structure of ResNet-50 includes the following parts: Input layer: usually a 224x224 pixel RGB image with 3 channels. Initialization convolution layer: 7x7 convolution kernel, 64 filters, stride 2. Batch normalization layer: normalization to improve the stability of training. ReLU activation layer: introduce nonlinearity. Maximum pooling layer: 3x3 pooling kernel, stride 2. Residual block: There are 16 residual blocks in total, divided into four stages, and the number of residual blocks and filters in each stage is different. Global average pooling layer: average pooling is used to compress the spatial dimension of each channel of the feature map into a single value to generate a global feature vector. Fully connected layer: used for the final classification task, followed by a Softmax layer for classification decision.

[0073] S220, adds RPN and RoI pooling detection layers to the wall panel installation management model;

[0074] The RPN (Region Proposal Network) detection layer is a key component in the target detection algorithm, which is mainly used to generate candidate target regions. RPN generates multiple candidate boxes (or candidate regions) by sliding a window on the feature map, and scores and regresses the coordinates of each candidate box to screen out the candidate boxes that may contain the target.

[0075] The RoI pooling detection layer is a technique used in target detection algorithms to process target regions of different sizes. The main function of RoI pooling (Region of Interest pooling) is to normalize candidate regions (RoI) of different sizes into fixed-size outputs for subsequent processing. The RoI pooling layer divides the input candidate region into multiple sub-regions and performs a maximum pooling operation on each sub-region to obtain a fixed-size output. The specific process is as follows: Input: The input of the RoI pooling layer includes a feature map and a series of candidate regions. The feature map is the feature extracted by the convolutional neural network (CNN), and RoIs are the mapping of the candidate box generated by RPN on the feature map. Divide sub-regions: Divide each RoI into multiple sub-regions, and the size of each sub-region is determined according to the output size. Pooling operation: Perform a maximum pooling operation on each sub-region to obtain a fixed-size output.

[0076] S230, optimizing the loss function of the wall panel installation management model;

[0077] The role of loss function in machine learning is mainly to quantify the difference between the model's predicted value and the actual value, and to optimize the model parameters by minimizing this difference, thereby improving the model's prediction accuracy. During the training process, the loss function serves as the objective function to guide the adjustment of the model parameters to minimize the prediction error. The loss function calculates a numerical value to represent the accuracy or error size of the model's prediction. The goal of the model is to minimize the value of the loss function by adjusting its parameters, thereby improving the accuracy of the prediction.

[0078] S240, add genetic algorithm to the wall panel installation management model.

[0079] In the embodiment of the present invention, a genetic algorithm is used to find the optimal layout and quantity of wall panels, and the most suitable installation scheme is found among reasonable wall panel installation schemes through continuous iteration of the genetic algorithm.

[0080] Preferably, after the grayscale wall image is subjected to denoising, it is further included to determine whether the denoising effect meets the standard, specifically:

[0081] The denoising effect is expressed as:

[0082]

[0083] Among them, f is the original image, g is the denoised image, uf is the average value of the original image, and u g The average value of the denoised image, σ (f，g) is the covariance of the original image and the denoised image, σ f is the variance of the original image, σ g Variance of the denoised image, A1 and A2 are constants.

[0084] Because the wall surface is relatively smooth, there are few feature points that can be extracted. If there is noise, it will have a great impact on the wall recognition results. Since the noise of the wall image has a great impact on the subsequent wall panel installation plan, the denoising effect of the wall image must be evaluated. Only wall images that have passed the denoising effect evaluation can enter the wall panel installation management model for processing.

[0085] Denoising technology can reduce granular spots and discolored spots in the image, improving the clarity and realism of the image. The denoised wall image retains important features in the image, such as edges and textures, making subsequent image processing and analysis more accurate and effective, and can accurately extract the characteristic information of the wall, improving the prediction accuracy.

[0086] Preferably, S210, replacing the architecture of the wallboard installation management model with ResNet50 feature extraction includes:

[0087] ResNet50 is used to extract features from wall images, expressed as:

[0088]

[0089] Among them, w ij is the weight of the i-th row and j-th column of the convolution kernel, x ij is the element in the i-th row and j-th column of the input feature map, b is the bias term, and the size of the convolution kernel is m×n.

[0090] Feature extraction can reduce the dimensionality of raw data, remove redundant and irrelevant information, and retain only features that are useful for learning, thereby improving the learning efficiency and accuracy of the model. Feature extraction can help the model learn the inherent laws in the data and improve the generalization ability of the model.

[0091] In the embodiment of the present invention, the wall image feature extraction can reduce the dimension of the data, simplify the subsequent modeling and analysis process, and thus improve the processing speed and efficiency. By extracting relevant features, the accuracy and performance of the machine learning model can be improved, and the overfitting phenomenon can be reduced. The data after feature extraction is smaller and easier to process, which can accelerate the processing speed of the machine learning algorithm.

[0092] Preferably, S230, the loss function of optimizing the wall panel installation management model includes:

[0093]

[0094] Among them, pi is the probability that the i-th anchor box is predicted as the target, is the true value of the i-th anchor box. When it is a positive sample, the value is 1, otherwise it is 0. L1 is the classification loss function, L2 is the regression loss function, and L t is the total loss function, N1 is the number of training anchor boxes, N2 is the number of anchor boxes that need to be regressed, α is the balance coefficient, smooth is the smoothing function, and t i is the offset parameter between the predicted box and the corresponding anchor box, is the offset parameter between the real target box and the corresponding anchor box.

[0095] In an embodiment of the present invention, the total loss function is composed of two loss functions. The regression loss function refers to a function used to measure the difference between the model prediction value and the actual observation value in the regression problem. The regression problem aims to predict a continuous value output through a set of input features, so the design of the loss function needs to be able to reflect the error between the predicted value and the true value. The classification loss function is used to evaluate the performance of the classification model. The cross entropy loss function is usually used to measure the difference between the predicted value and the true value of the classification model. In machine learning and deep learning, the loss function is used as the optimization target. The model parameters are adjusted by minimizing the value of the loss function, thereby improving the prediction accuracy of the model. Commonly used optimization algorithms such as gradient descent update the model parameters by calculating the gradient of the loss function. The loss function can help monitor the overfitting of the model during the training process. By observing the losses on the training set and the validation set, it is possible to detect whether the model is overfitting early, so as to take corresponding measures, such as regularization. The loss function can introduce weights to balance the importance between different samples or targets, so as to more accurately measure the performance of the model. The present invention adopts a combination of multiple loss functions to evaluate the wall panel installation management model. The loss function has the advantages of fast convergence and strong robustness, and can cope with various scenarios, with a wide range of applications and strong adaptability.

[0096] Preferably, S240, adding a genetic algorithm to the wall panel installation management model includes:

[0097] S241, inputting the wall surface data and the wall panel size into the genetic algorithm as a training set;

[0098] Genetic algorithm is an optimization search method based on the principles of natural selection and genetics. Genetic algorithm iteratively updates the solution of the problem by simulating Darwin's natural selection and genetic inheritance in the process of biological evolution in nature, thereby searching for the optimal solution or approximate optimal solution. The basic idea of ​​genetic algorithm is as follows: map the problem into a mathematical problem, that is, establish a mathematical model. Initialize a population, which contains multiple individuals, each of which represents a solution. Perform selection operation, evaluate individuals according to the fitness function, and select excellent individuals for reproduction. Perform crossover operation, randomly select two individuals for chromosome crossover, and produce new offspring. Perform mutation operation, and randomly mutate the chromosomes of offspring. Update the optimal solution, add excellent offspring to the population, and eliminate some poor individuals.

[0099] S242, training the genetic algorithm;

[0100] The main purpose of genetic algorithm training is to solve complex optimization problems. Genetic algorithms gradually optimize the solution to the problem by simulating the principles of natural selection and genetics through operations such as selection, crossover and mutation. Through an iterative process, genetic algorithms select individuals with high fitness from the total number of potential solutions, generate new individuals through crossover and mutation, and continuously optimize until a satisfactory solution is found.

[0101] S243, using the trained genetic algorithm to calculate the installation layout and installation quantity of the wall panels according to the wall surface data and the wall panel size.

[0102] The principle of genetic algorithm to find the most suitable installation plan is to gradually optimize the solution of the problem by simulating the genetic and natural selection mechanisms in the process of biological evolution. Genetic algorithm simulates the evolution process of organisms in nature and finds the optimal solution of the installation plan through operations such as selection, crossover and mutation. The specific process includes: Initialization of population: First, randomly generate an initial population. Each individual (or chromosome) in the population represents a possible solution. These individuals are composed of a string of numbers or symbol sequences. Fitness evaluation: Define a fitness function to evaluate the performance of each individual. The fitness function is designed according to the objective function of the problem and is used to measure the degree of individual adaptation to the problem. Individuals with high fitness have a higher chance of survival and reproduction. Selection operation: Select a part of individuals from the population as the parents of the next generation according to the fitness function. There are many ways to select, such as roulette selection, competition selection, tournament selection, etc. Crossover operation: Perform crossover operation on the selected parent individuals to generate new offspring individuals. The crossover methods include single-point crossover, multi-point crossover, uniform crossover, etc. Mutation operation: In the offspring individuals generated after crossover, certain genes are mutated with a certain probability to introduce new genetic information. Mutation is generally performed in a random manner, such as single-point mutation, multi-point mutation, bit mutation, etc. New population generation: A new population is generated through selection, crossover and mutation operations, and the above process is repeated until the termination condition is met, such as reaching the maximum number of iterations or the fitness of the solution reaches a preset threshold.

[0103] Example 2

[0104] An intelligent wallboard defect detection system based on image recognition, comprising:

[0105] An image acquisition module, used for acquiring wall images;

[0106] Model optimization module, used to optimize the wall panel installation management model;

[0107] The image processing module is used to input the wall surface image into the wall panel installation management model, and the wall panel installation management model outputs the wall panel installation result.

[0108] Example 3

[0109] An electronic device includes: a chip, a processor and a memory, the memory is used to store computer program codes, the computer program codes include computer instructions, and when the chip executes the computer instructions, the electronic device executes an intelligent management method for wall panel installation.

[0110] refer to Figure 3 , the electronic device 2 includes a processor 21, a memory 22, an input device 23, and an output device 24. The processor 21, the memory 22, the input device 23, and the output device 24 are coupled via a connector, and the connector includes various interfaces, transmission lines, or buses, etc., which are not limited in the embodiments of the present invention. It should be understood that in various embodiments of the present invention, coupling refers to mutual connection in a specific manner, including direct connection or indirect connection through other devices, for example, through various interfaces, transmission lines, buses, etc.

[0111] The processor 21 may be one or more graphics processing units (GPUs). When the processor 21 is a GPU, the GPU may be a single-core GPU or a multi-core GPU. Optionally, the processor 21 may be a processor group consisting of multiple GPUs, and the multiple processors are coupled to each other via one or more buses. Optionally, the processor may also be other types of processors, etc., which are not limited in the embodiments of the present invention.

[0112] The memory 22 can be used to store computer program instructions and various computer program codes including program codes for executing the scheme of the present invention. Optionally, the memory includes but is not limited to random access memory (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM), or portable read only memory (CD-ROM), which is used for related instructions and data.

[0113] The input device 23 is used to input data and / or signals, and the output device 24 is used to output data and / or signals. The output device 24 and the input device 23 may be independent devices or an integrated device.

[0114] Example 4

[0115] A computer-readable storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes an intelligent management method for wall panel installation.

[0116] The present invention preprocesses the wall image, and the installation position in the preprocessed wall image will be easier to detect, which can help machine vision better identify the wall panel installation position. The present invention optimizes and improves the wall panel installation management model, making the model more sensitive to the wall installation position, replacing the feature extraction network to better extract features related to the wall panel installation position, and optimizing the loss function to make the model have higher detection accuracy.

[0117] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. An intelligent management method for wall panel installation, characterized in that: include: Get the wall image; Optimize the wall panel installation management model; The wall surface image is input into the wall panel installation management model, and the wall panel installation management model outputs the wall panel installation result.

2. The intelligent management method for wall panel installation according to claim 1, characterized in that: After the wall image is acquired, the wall image is preprocessed, specifically: Grayscale the wall image; De-noising the grayscale wall image; Perform enhancement processing on the denoised wall image; The enhanced wall image is size-standardized.

3. The intelligent management method for wall panel installation according to claim 1, characterized in that: The optimized wall panel installation management model includes: Replacing the architecture of the wall panel installation management model with ResNet50 feature extraction; Add RPN and RoI pooling detection layers to the wall panel installation management model; Optimizing the loss function of the wall panel installation management model; A genetic algorithm is added to the wall panel installation management model.

4. The intelligent management method for wall panel installation according to claim 2, characterized in that: After the grayscale wall image is subjected to denoising, the process further includes determining whether the denoising effect meets the standard, specifically: The denoising effect is expressed as: Among them, f is the original image, g is the denoised image, and u f is the average value of the original image, u g The average value of the denoised image, σ (f，g) is the covariance of the original image and the denoised image, σ f is the variance of the original image, σ g Variance of the denoised image, A1 and A2 are constants.

5. The intelligent management method for wall panel installation according to claim 3, characterized in that: Replacing the architecture of the wall panel installation management model with ResNet50 feature extraction includes: ResNet50 is used to extract features from wall images, expressed as: Among them, w ij is the weight of the i-th row and j-th column of the convolution kernel, x ij is the element in the i-th row and j-th column of the input feature map, b is the bias term, and the size of the convolution kernel is m×n.

6. The intelligent management method for wall panel installation according to claim 3, characterized in that: The loss function for optimizing the wall panel installation management model includes: Among them, p i is the probability that the i-th anchor box is predicted as a target, is the true value of the i-th anchor box. When it is a positive sample, the value is 1, otherwise it is 0. L1 is the classification loss function, L2 is the regression loss function, and L t is the total loss function, N1 is the number of training anchor boxes, N2 is the number of anchor boxes that need to be regressed, α is the balance coefficient, smooth is the smoothing function, and t i is the offset parameter between the predicted box and the corresponding anchor box, is the offset parameter between the real target box and the corresponding anchor box.

7. The intelligent management method for wall panel installation according to claim 3, characterized in that: Adding a genetic algorithm to the wall panel installation management model includes: The wall data and wall panel dimensions are input into the genetic algorithm as a training set; Training the genetic algorithm; The trained genetic algorithm is used to calculate the installation layout and installation quantity of wall panels according to the wall surface data and wall panel dimensions.

8. An intelligent wallboard defect detection system based on image recognition, characterized in that: include: An image acquisition module, used for acquiring wall images; Model optimization module, used to optimize the wall panel installation management model; The image processing module is used to input the wall surface image into the wall panel installation management model, and the wall panel installation management model outputs the wall panel installation result.

9. An electronic device, characterized in that: include: A chip, a processor and a memory, wherein the memory is used to store computer program code, the computer program code includes computer instructions, and when the chip executes the computer instructions, the electronic device executes an intelligent management method for wall panel installation as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes an intelligent management method for wall panel installation as described in any one of claims 1 to 7.

Images