Wall decoration detection method and system

Abstract

This invention provides a method and system for inspecting wall decoration, relating to the field of building inspection technology. The method includes acquiring wall decoration data using a laser level and camera equipment, the data including height, level, and image information; sending the data to a wall flatness model for flatness calculation to obtain flatness error data; performing edge calculation based on the flatness error data and decoration data to obtain crack data, including location and shape information; analyzing the data using a data analysis model to obtain smoothness and color data; and finally, sending the flatness error data, crack data, smoothness, and color data to a qualification analysis model for analysis to obtain the wall decoration inspection result. This invention achieves a comprehensive assessment of wall decoration quality through the analysis and detection of multiple data sources, accurately determining whether a wall is qualified, and is characterized by high efficiency, accuracy, and a high degree of automation.

Description

Technical Field

[0001] This invention relates to the field of building inspection technology, and more specifically, to a method and system for inspecting wall decoration. Background Technology

[0002] With the rapid development of the construction industry, the quality of wall decoration has become a key concern for both users and contractors. Existing wall decoration inspection methods mainly rely on visual inspection and simple tool measurements, which cannot comprehensively and accurately assess quality indicators such as wall flatness, cracks, and smoothness. This traditional method is not only inefficient but also easily affected by human factors, leading to inaccurate results. Furthermore, current technologies lack systematic data analysis and processing in wall decoration quality inspection, making it difficult to fully grasp the complex conditions of walls and thus failing to effectively identify potential quality problems, creating difficulties for subsequent decoration and maintenance.

[0003] Therefore, there is an urgent need for a new type of wall decoration inspection method that can comprehensively analyze indicators such as wall flatness, cracks, smoothness, and color through multiple data acquisition methods to provide comprehensive and accurate inspection results. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for detecting wall decoration defects, thereby improving the aforementioned problems. To achieve this objective, the technical solution adopted by this invention is as follows:

[0005] Firstly, this application provides a method for testing wall decoration, including:

[0006] Wall decoration data is acquired using a laser level and camera equipment. The wall decoration data includes height data, horizontal data, and image information of all walls.

[0007] The wall decoration data is sent to the wall flatness model for flatness calculation to obtain the wall flatness error data.

[0008] Edge calculation is performed based on the flatness error data of the wall surface and the wall surface decoration data to obtain the crack data of the wall surface. The crack data of the wall surface includes the location data and shape data of the cracks in the wall surface.

[0009] The wall decoration data is sent to a data analysis model for analysis to obtain the wall's smoothness and color data.

[0010] The flatness error data, crack data, smoothness data, and color data of the wall surface are sent to the qualified analysis model for data analysis to obtain the inspection results of the wall decoration.

[0011] Secondly, this application also provides a wall decoration inspection system, including:

[0012] The acquisition unit is used to acquire wall decoration data information based on a laser level and a camera device. The wall decoration data information includes height data, horizontal data, and image information of all walls.

[0013] The first processing unit is used to send the wall decoration data information to the wall flatness model for flatness calculation to obtain the wall flatness error data.

[0014] The second processing unit is used to perform edge calculation based on the flatness error data of the wall surface and the wall surface decoration data to obtain the crack data of the wall surface. The crack data of the wall surface includes the location data and shape data of the cracks in the wall surface.

[0015] The first analysis unit is used to send the wall decoration data information to the data analysis model for data analysis to obtain the smoothness data and color data of the wall.

[0016] The second analysis unit is used to send the flatness error data, crack data, smoothness data and color data of the wall surface to the qualified analysis model for data analysis, and obtain the test results of the wall decoration.

[0017] The beneficial effects of this invention are as follows:

[0018] This invention combines a laser level with a camera to comprehensively acquire wall surface decoration data, including height, level, and image information. By sending this data to a flatness model, a data analysis model, and a qualification analysis model, systematic flatness calculations, smoothness and color analysis, and crack data extraction are performed to obtain a comprehensive inspection result for the wall surface decoration. This method not only improves inspection efficiency and accuracy but also overcomes the shortcomings of existing technologies in data processing and analysis, achieving a comprehensive assessment of wall surface condition and providing important technical support for improving the quality of wall surface decoration.

[0019] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of the wall decoration testing method described in this embodiment of the invention;

[0022] Figure 2 This is a schematic diagram of the wall decoration detection system described in an embodiment of the present invention.

[0023] In the diagram: 701, Acquisition Unit; 702, First Processing Unit; 703, Second Processing Unit; 704, First Analysis Unit; 705, Second Analysis Unit; 7021, First Processing Subunit; 7022, Second Processing Subunit; 7023, Third Processing Subunit; 7024, Fourth Processing Subunit; 7025, First Calculation Subunit; 7031, Fifth Processing Subunit; 7032, Sixth Processing Subunit; 7033, Seventh Processing Subunit; 7034, Eighth Processing Subunit; 7035, ... Second calculation subunit; 7036, Third calculation subunit; 7041, Ninth processing subunit; 7042, Fourth calculation subunit; 7043, Fifth calculation subunit; 7044, First analysis subunit; 70441, Second analysis subunit; 70442, Sixth calculation subunit; 70443, Seventh calculation subunit; 7051, Third analysis subunit; 7052, Fourth analysis subunit; 7053, Fifth analysis subunit; 7054, Sixth analysis subunit; 7055, Seventh analysis subunit. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0025] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0026] Example 1:

[0027] This embodiment provides a method for inspecting wall decoration.

[0028] See Figure 1 The figure shows that the method includes steps S1, S2, S3, S4 and S5.

[0029] Step S1: Obtain wall decoration data information based on laser level and camera equipment. The wall decoration data information includes height data, horizontal data and image information of all walls.

[0030] It's understandable that laser levels can accurately measure wall height, typically using the principle of beam emission and reception combined with high-precision measurement algorithms to ensure the capture of height differences across a wide area. Simultaneously, it avoids human error that may be introduced in traditional levelness testing, guaranteeing data reliability. Meanwhile, the camera equipment is responsible for collecting image information of the wall. Through high-resolution camera technology, it can meticulously capture features such as wall texture, color, and cracks, thus laying a solid foundation for subsequent image processing and analysis.

[0031] The data obtained in this step, including height, level, and image information, provides a multi-dimensional perspective, enabling subsequent analysis models to conduct comprehensive evaluations. Specifically, the wall's height and level data are used to establish a preliminary flatness model, while the image information provides raw data for crack detection and color analysis. This comprehensive acquisition of data not only improves the comprehensiveness and accuracy of the inspection but also effectively identifies potential quality hazards. Furthermore, technically, this step transforms wall inspection from traditional qualitative analysis to quantitative analysis, greatly enhancing the scientific rigor and objectivity of the inspection and providing data support for subsequent compliance analysis.

[0032] Step S2: Send the wall decoration data to the wall flatness model for flatness calculation to obtain the wall flatness error data;

[0033] It is understandable that this step, through precise numerical calculations and model optimization, makes the assessment of wall flatness more scientific and objective, greatly improving the ability to monitor the quality of wall decoration and laying the foundation for subsequent quality qualification analysis. In this step, step S2 includes steps S21, S22, S23, S24 and S25.

[0034] Step S21: Divide each wall surface into at least two grids based on the orthogonal grid method;

[0035] Understandably, the orthogonal mesh method first divides the wall surface into multiple rectangular or square grid areas based on its overall dimensions and shape. This division method is simple and easy to implement, allowing each grid to effectively represent a portion of the wall surface, thus more clearly reflecting the wall's height variations and horizontal information. In practical applications, the size and number of grids can be flexibly adjusted based on actual wall measurement data to adapt to the complexity of different wall structures and the sparsity of the data. During the division process, the starting and ending points of the grids are first determined, and then a coordinate system is established on the wall surface with uniform spacing. This coordinate system will help to accurately label subsequent height and horizontal data. The coordinate information of each grid will provide the basic data for flatness calculation, ensuring the accuracy of subsequent interpolation and error compensation processes. Through scientific grid division, subsequent analysis becomes more comprehensive, enhancing the reliability of the overall inspection.

[0036] Step S22: Mark each grid based on the height and horizontal data of all walls, and interpolate the height and horizontal data of each grid point to the adjacent grid points based on the piecewise linear interpolation method. In this process, the height and horizontal data of the intermediate interpolation point are generated based on the intermediate distance between two grid points, and an initial flatness model is constructed. The initial flatness model includes continuous height data distribution data and horizontal data distribution data.

[0037] It is understandable that the linearization process using piecewise linear interpolation solves the problem caused by the discreteness of the measurement data, resulting in a continuous height and horizontal distribution over a large area of ​​the wall surface. This process not only helps eliminate jumps and discontinuities between data points but also more accurately reflects the actual condition of the wall surface. The efficient interpolation method makes subsequent error compensation and model fitting more precise, while also accurately reflecting the overall condition of the wall surface, providing a reliable basis for subsequent flatness calculations. This not only improves the accuracy of the analysis but also provides more comprehensive data support for the inspection process, ensuring the reliability and validity of the final inspection results.

[0038] Step S23: Perform error compensation on the initial smoothness model based on the preset Gaussian process regression kernel function to obtain the error-compensated initial smoothness model;

[0039] Gaussian kernel functions are often used to capture the smoothness of data, and their properties allow them to adapt to variations in wall height and level. Furthermore, appropriate hyperparameters need to be set to optimize the model's fit. Subsequently, a pre-defined Gaussian process regression kernel function is used to process the initial flatness model, calculating the error and corresponding correction value for each point in the model. This process not only compensates for measurement errors but also smooths the data, eliminating fluctuations caused by local extrema or noise, making the model more stable. The error compensation method based on Gaussian process regression demonstrates its flexibility and advantages in handling complex datasets, making the results of the entire wall detection process more reliable and usable. The pre-defined Gaussian process regression kernel function in this step is shown below:

[0040]

[0041] Where, k(x) i x j ) represents the input point x i and x j Covariance between Let |x| represent the variance of the function values, l represent the length scale, and |x| represent the variance of the function values. i -x j || 2 Indicates input point x i and x j The square of the Euclidean distance between them.

[0042] It is understandable that after determining the covariance through the Gaussian kernel function, a covariance matrix can be constructed using the covariance. Then, Bayes' theorem can be used to give a new input point and calculate the mean of its posterior distribution, thereby obtaining the error and achieving error compensation.

[0043] Step S24: Based on the spline surface fitting method, perform data transformation on each grid point in the initial flatness model after error compensation to obtain a continuous flatness fitting surface;

[0044] It is understandable that the flatness fitting surface generated in this step can provide a reliable basis for subsequent analysis. In particular, the smoothing properties of spline fitting, compared to simple interpolation methods, can more realistically reflect the actual condition of the wall surface.

[0045] The formula for spline surface fitting is shown below:

[0046]

[0047]

[0048] Where S(x, y) represents the height value of the generated spline surface at the point (x, y); N i，p(u) represents the B-spline basis function, M j，q (υ) represents the spline basis function in the y-direction, P ij Let z represent a known point on the spline surface, E represent the total error, m represent the number of spline segments, n represent the total number of sample points, and z represent the total number of sample points. i S(x) represents the actual height value of the sample point. i y i ) indicates the height predicted by the model.

[0049] Step S25: Calculate the second derivative of the continuous flatness fitting surface based on the Laplacian operator to obtain the flatness error data of each grid region of the surface.

[0050] Understandably, the Laplacian operator provides local information for each grid point, showing the rate of change of that point relative to its neighborhood. If the Laplacian value of a region is positive, it indicates that the point is a local minimum (concave), while a negative value means it is a local maximum (convex). This is crucial for detecting the flatness of wall surfaces, as excessive convexity or concavity can directly affect the quality and aesthetics of the finish.

[0051] By calculating the flatness error data for each grid area, subsequent analysis can more accurately identify specific problems on the wall, such as obvious unevenness or localized deformation, thus providing a basis for subsequent repair and renovation. This calculation step not only improves the accuracy of wall inspection but also lays the foundation for subsequent data visualization and intelligent analysis, ensuring a significant improvement in the efficiency and effectiveness of wall inspection in practical applications.

[0052] The formula for calculating the second derivative is shown below:

[0053]

[0054] Where Z represents the height value of the wall flatness fitting surface at any point, X represents any abscissa Y on the flatness fitting surface, and Y represents any ordinate on the flatness fitting surface. This represents the result of applying the Laplacian operator to the flatness-fitted surface.

[0055] Step S3: Based on the flatness error data of the wall surface and the wall surface decoration data, perform edge calculation to obtain the crack data of the wall surface. The crack data of the wall surface includes the location data and shape data of the cracks in the wall surface.

[0056] Understandably, this step improves the crack detection rate and makes the detection results more visual, facilitating subsequent analysis and processing, and providing a reliable foundation for the extraction of subsequent crack location and morphology data. In this way, the condition of wall cracks can be quickly located and assessed in real-time monitoring and analysis, thus providing data support for subsequent repair and maintenance. In this step, step S3 includes steps S31, S32, S33, S34, S35, and S36.

[0057] Step S31: Use the Canny edge detection algorithm to process the image information of the wall and calculate the gradient of each pixel in the image information of the wall;

[0058] Understandably, the Canny algorithm performs Gaussian smoothing on the original wall image to remove random noise. By selecting an appropriate Gaussian kernel, the algorithm effectively reduces the interference of noise on subsequent edge detection results. Next, the algorithm calculates the gradient for each pixel, typically using the Sobe L operator, a commonly used edge detection operator. This operator calculates the gradient strength and direction of each pixel by calculating the derivative of the image in the horizontal and vertical directions. The gradient strength reflects the brightness variation between that point and other points in its neighborhood, while the gradient direction indicates the orientation of the edge.

[0059] In this process, regions with higher intensity in the gradient image generated by the Canny algorithm are marked as edge candidates, while regions with lower intensity are considered potential noise. Based on this, subsequent steps apply thresholding and edge connection to determine which points constitute actual edges. Therefore, technically, by calculating the gradient of each pixel, not only can crack features in wall images be extracted efficiently, but reliable foundational data is also provided for subsequent edge tracking and morphological analysis. The successful implementation of this process will lay a solid foundation for obtaining subsequent crack location and morphological data, making the overall wall detection process more accurate and efficient.

[0060] Step S32: Based on a preset threshold, the gradient of each pixel is distinguished to obtain the strong edges and weak edges of the wall image information. The strong edges and weak edges of the wall image information are then connected by the hysteresis edge method to obtain continuous crack edge image information of the wall.

[0061] Understandably, this system sets high and low thresholds. The gradient intensity of each pixel is compared to these two thresholds. If the gradient intensity of a pixel is greater than the high threshold, it is considered a strong edge and marked as a possible location of the crack. Conversely, if the gradient intensity of a pixel is lower than the low threshold, it is considered noise and ignored. Pixels between these two thresholds are marked as weak edges, and these pixels require further analysis to determine whether to include them in the final edge result. The system then performs a local search starting from the strong edges, examining adjacent weak edge pixels. If the gradient intensity of an adjacent weak edge pixel is greater than the low threshold, it is considered part of the connection. This approach ensures that even relatively weak edges, as long as they are connected to strong edges, can be included in the final crack edge image information. This process not only improves the robustness of edge detection but also guarantees the continuity and integrity of the final result, significantly reducing the risk of edge loss due to noise or small intensity variations.

[0062] Step S33: Based on morphological opening and closing operations, enhance the crack edge image information of the continuous wall surface to obtain enhanced crack edge image information.

[0063] Opening is a morphological operation that erodes an image using a structuring element before dilating it. In crack edge images, opening effectively removes small noise points and subtle interference while preserving larger crack features. Specifically, by sliding a structuring element (such as a circle or rectangle) across the image, opening first shrinks the edges of all objects, removing noise points smaller than the structuring element, and then dilates the image back to its original size, restoring larger crack edges. Thus, the main effect of opening is noise reduction, edge smoothing, and preservation of key crack information. Closing is the inverse operation of opening; it first dilates the image and then erodes it. Applying closing to crack edge images effectively fills gaps between cracks or small breaks.

[0064] After a combination of opening and closing operations, the enhanced crack edge image information is clear and coherent, providing strong support for subsequent crack data analysis. This enhancement process not only improves the visual effect of the image but also enhances the algorithm's ability to extract crack features, thereby ensuring high accuracy and reliability in wall decoration inspection.

[0065] Step S34: Based on the Hough transform, the pixels of the crack are mapped from the image space to the parameter space, and the accumulator is used to detect crack features with linear or arc-shaped morphology.

[0066] It is understandable that this step, which maps the crack pixels from the image space to the parameter space based on the Hough transform, can be represented by the following formula:

[0067]

[0068] Where P(r, θ) represents the accumulator value for a specific parameter combination, I(Q) represents the value of the current pixel, and H(x) represents the value of the current pixel. Q y Q (x, r, θ) represents the edge pixel point (x) Q y Q The mapping function is used to map the edge pixels to the parameter space (r, θ), where E represents the set of edge pixels and Q represents the index of the edge pixel being processed.

[0069] Step S35: Based on the watershed algorithm, segment the crack region containing crack features and calculate the width and length of each crack;

[0070] Understandably, this step involves constructing a height map, mapping the intensity value of each pixel in the image to its corresponding height. High-intensity areas form "peaks" on the height map, while low-intensity areas form "valleys." This is then simulated by depicting water flowing from the peaks to the valleys, with the region segmentation determined by the inflow rate. When the water flows meet, a watershed line forms at the point of intersection, thus separating the different fractured areas.

[0071] The formulas for calculating the width and length of each crack are shown below;

[0072]

[0073]

[0074] Among them, L f W represents the total length of the crack. f The average width of the crack is represented by M, and the total number of points on the crack boundary is represented by (u k v k ) represents the coordinates of the k-th crack boundary point, g l This represents the width measurement value of the l-th point.

[0075] Step S36: Determine the location data of the wall cracks based on the flatness error data of the wall surface and the width and length of each crack.

[0076] Understandably, this step maps the crack's morphological information onto the wall's three-dimensional coordinate system, thereby obtaining precise crack location data. This not only improves detection accuracy but also provides effective data support for subsequent repair plans. This method is particularly suitable for handling cracks that may occur in complex wall structures, laying the foundation for crack repair work.

[0077] Step S4: Send the wall decoration data to the data analysis model for data analysis to obtain the wall smoothness data and color data;

[0078] Understandably, this step provides specific data on the smoothness and color of the wall surface, offering detailed foundational information for subsequent quality inspection. This data analysis model-based processing method effectively quantifies the appearance characteristics of the wall surface, improving the accuracy of the analysis and making the results highly practical and instructive, facilitating the implementation of subsequent processing and rectification measures. In this step, step S4 includes steps S41, S42, S43, and S44.

[0079] Step S41: Send the height and horizontal data of the wall to a three-dimensional rectangular coordinate system for processing to obtain a three-dimensional model of the wall.

[0080] Understandably, this step, through processing in a three-dimensional Cartesian coordinate system, transforms two-dimensional wall data into a three-dimensional geometric model. This model provides a realistic geometric representation of the wall, offering accurate foundational data for subsequent wall characteristic analysis, such as smoothness and crack detection. Simultaneously, it enhances the system's ability to identify minute wall defects, making the detection results more reliable and accurate.

[0081] Step S42: Calculate the average value of adjacent grid points of each grid point in the three-dimensional rectangular coordinate system based on the local averaging method, and calculate the smoothness index of the grid point based on the preset smoothness index calculation formula.

[0082] It is understandable that the local averaging method in this step can smooth the three-dimensional spatial grid point data, eliminate noise interference, and thus improve the accuracy of smoothness calculation. Through the calculation of the smoothness index formula, the system can quantify the smoothness of the wall surface and identify minor local defects. This method not only improves the accuracy of smoothness detection but also provides a scientific basis for the subsequent determination of the overall pass / fail status of the wall surface. The preset smoothness index calculation formula is as follows:

[0083]

[0084] Where S represents the smoothness index of the current grid point, and P i Q represents the height value of the current grid point. jThe height of adjacent grid points is represented by |P. i -Q j | represents the absolute value of the height difference between the current grid point and its adjacent grid points.

[0085] Step S43: Calculate the weighted average value based on the smoothness index of all grid points, and calculate the standard deviation based on the calculated global smoothness value. Use the calculated standard deviation as the smoothness error data of the wall surface.

[0086] Understandably, this step assesses the wall's smoothness error by weighted averaging of the smoothness indices of all grid points and further calculating the standard deviation. This process not only comprehensively reflects the overall smoothness of the entire wall surface but also quantifies the degree of deviation of local areas from the overall smoothness, thus more accurately reflecting the uniformity of the wall's smoothness.

[0087] Step S44: Perform color analysis based on the image information of the wall to obtain the color data information of the wall.

[0088] It is understandable that this step, through this color analysis method, can effectively identify the color quality of the wall and discover possible color differences or unevenness. For example, if the main color of a certain area differs significantly from the overall wall color, it may indicate uneven painting or material problems in that area. Step S44 in this step includes steps S441, S442, and S443.

[0089] Step S441: Perform edge detection on the image information of the wall to obtain the wall image information and the wall edge, and convert the wall image outside the wall edge into black;

[0090] Understandably, this step, through edge detection, can clearly identify the edge features of the wall, making subsequent crack analysis and wall quality assessment more accurate. This process effectively removes irrelevant background information, focusing on the main features of the wall structure, thereby providing high-quality basic data for subsequent analysis.

[0091] Step S442: Cluster the R, G, and B components of all pixels within the edge of the wall image, calculate the average value of the center points of all clusters, and use the average value as the color data of the wall image information.

[0092] Understandably, this step, by clustering pixels within the edges, effectively extracts the color features of the wall surface, simplifying its color representation. The clustering results will help to more accurately describe the color characteristics of the wall surface in practical applications, making color analysis and subsequent decoration quality assessment more scientific and systematic. This process not only reduces data dimensionality but also eliminates color interference caused by changes in lighting or image noise, enhancing the stability and repeatability of color data.

[0093] Step S443: Divide the color data of the image information of the wall into regions according to the grid points in the three-dimensional rectangular coordinate system, and calculate the mean of the color data corresponding to the divided regions to obtain the color data information of each grid point.

[0094] Understandably, this step, by dividing the color data of the wall image into regions and calculating the mean, effectively combines the wall's color characteristics with the spatial structure. This method not only reduces data complexity but also enhances the understanding of the overall visual effect of the wall. In practical applications, the color data information of each grid point can provide important references for subsequent decoration design, quality control, and aesthetic evaluation.

[0095] Step S5: Send the flatness error data, crack data, smoothness data, and color data of the wall surface to the qualified analysis model for data analysis to obtain the test results of the wall decoration.

[0096] Understandably, this step, by integrating and analyzing data from multiple dimensions, can comprehensively assess the quality of wall decoration. This comprehensive analysis not only improves the accuracy of the inspection but also makes the analysis process more transparent. In practical applications, the inspection results can provide a scientific basis for construction management, guide subsequent rectification measures, and ensure that the decoration quality meets the required standards. In this process, step S5 includes steps S51, S52, S53, S54, and S55.

[0097] Step S51: Perform hierarchical analysis on the flatness error data, crack data, smoothness data and color data of the wall surface based on the analytic hierarchy process (AHP) to determine the weight of each type of data.

[0098] Understandably, this step uses the analytic hierarchy process (AHP) to assign weights to different data types, effectively quantifying the relative importance of each factor in the quality assessment of wall decoration. The advantage of this method lies in its systematic approach and flexibility, making the assessment process more objective and scientific. In practical applications, this weighting analysis helps optimize the qualification analysis model, enabling it to more accurately reflect the actual condition of wall decoration when processing complex data, thereby improving the overall reliability and effectiveness of the inspection.

[0099] Step S52: Based on the correlation analysis of all types of data with the preset qualified threshold, obtain the correlation value of each type of data;

[0100] It is understandable that by performing correlation analysis between various data types and preset acceptable thresholds, the quality level of wall decoration can be quantitatively assessed. The advantage of this method lies in its ability to systematically integrate multiple data dimensions to form a comprehensive assessment of the wall decoration's condition. Simultaneously, correlation analysis can identify which indicators fail to meet the acceptable standards, thus providing a concrete basis for subsequent improvement and remedial measures. In practical applications, this process helps to promptly identify potential problems in wall decoration, ensure construction quality, and reduce later maintenance costs.

[0101] Step S53: Based on the preset minimum discrimination principle, summarize the weight of each type of data and its corresponding correlation value to obtain the summary weight value corresponding to each type of data.

[0102] It is understandable that the summary formula in this step is as follows:

[0103]

[0104] Among them, Q a U represents the redistribution of weights for the a-th data type. a T represents the initial weight of the a-th data type. a This represents the correlation value of the a-th data type. This represents the weighted sum of the weights and correlation values ​​for all data types.

[0105] Step S54: Score each type of data according to the preset level threshold, and multiply the score obtained by the corresponding summary weight value to obtain the weighted score of each type of data;

[0106] Understandably, this step uses weighted calculations to combine the performance of each data type with its relative importance, ensuring that the final weighted score accurately reflects the overall quality of the wall decoration. This method effectively reduces the undue influence of any particular data type on the final result during the evaluation process, ensuring the comprehensiveness and objectivity of the test results.

[0107] Step S55: Determine whether the data of that type on the wall is qualified based on the weighted score of each type of data, and obtain the judgment result.

[0108] Understandably, this step, by comparing the weighted scores with preset thresholds, allows us to clearly determine whether the wall's performance on each quality indicator is up to standard. This method ensures the objectivity and reliability of the quality assessment, enabling the weighted scores of various data to effectively reflect the overall quality status of the wall. The output of this step will provide direct evidence for subsequent compliance analysis and necessary corrective measures, further improving the quality control and management level of wall decoration.

[0109] Example 2:

[0110] like Figure 2 As shown, this embodiment provides a wall decoration inspection system. (See attached image) Figure 2 The system includes an acquisition unit 701, a first processing unit 702, a second processing unit 703, a first analysis unit 704, and a second analysis unit 705.

[0111] The acquisition unit 701 is used to acquire wall decoration data information based on a laser level and a camera device. The wall decoration data information includes height data information, horizontal data information and image information of all walls.

[0112] The first processing unit 702 is used to send the wall decoration data information to the wall flatness model for flatness calculation to obtain the flatness error data of the wall.

[0113] The first processing unit 702 includes a first processing subunit 7021, a second processing subunit 7022, a third processing subunit 7023, a fourth processing subunit 7024, and a first calculation subunit 7025.

[0114] The first processing subunit 7021 is used to divide each wall surface into at least two grids based on the orthogonal grid method;

[0115] The second processing subunit 7022 is used to mark each grid based on the height and horizontal data information of all walls, and to interpolate the height and horizontal data information of each grid point to adjacent grid points based on the piecewise linear interpolation method. The height and horizontal data of the intermediate interpolation point are generated according to the intermediate distance between two grid points to construct an initial flatness model. The initial flatness model includes continuous height data distribution data and horizontal data distribution data.

[0116] The third processing subunit 7023 is used to perform error compensation on the initial smoothness model based on a preset Gaussian process regression kernel function to obtain the error-compensated initial smoothness model.

[0117] The fourth processing subunit 7024 is used to perform data transformation on each grid point in the initial flatness model after error compensation based on the spline surface fitting method to obtain a continuous flatness fitting surface.

[0118] The first calculation subunit 7025 is used to calculate the second derivative of the continuous flatness fitting surface based on the Laplacian operator to obtain the flatness error data of each grid region of the surface.

[0119] The second processing unit 703 is used to perform edge calculation based on the flatness error data of the wall surface and the wall surface decoration data to obtain the crack data of the wall surface. The crack data of the wall surface includes the location data and shape data of the cracks in the wall surface.

[0120] The second processing unit 703 includes a fifth processing subunit 7031, a sixth processing subunit 7032, a seventh processing subunit 7033, an eighth processing subunit 7034, a second calculation subunit 7035, and a third calculation subunit 7036.

[0121] The fifth processing subunit 7031 is used to process the image information of the wall using the Canny edge detection algorithm and calculate the gradient of each pixel in the image information of the wall.

[0122] The sixth processing subunit 7032 is used to distinguish the gradient of each pixel based on a preset threshold, obtain the strong edges and weak edges of the wall image information, and connect the strong edges and weak edges of the wall image information through the hysteresis edge method to obtain continuous crack edge image information of the wall.

[0123] The seventh processing subunit 7033 is used to enhance the crack edge image information of the continuous wall surface based on morphological opening and closing operations to obtain enhanced crack edge image information.

[0124] The eighth processing subunit 7034 is used to map the pixels of the crack from the image space to the parameter space based on the Hough transform, and to use an accumulator to detect crack features with linear or arc-shaped morphology.

[0125] The second computational subunit 7035 is used to segment the crack region containing crack features based on the watershed algorithm and calculate the width and length of each crack.

[0126] The third calculation subunit 7036 is used to determine the location data of the wall cracks based on the flatness error data of the wall surface and the width and length of each crack.

[0127] The first analysis unit 704 is used to send the wall decoration data information to the data analysis model for data analysis to obtain the smoothness data and color data of the wall.

[0128] The first analysis unit 704 includes a ninth processing subunit 7041, a fourth calculation subunit 7042, a fifth calculation subunit 7043, and a first analysis subunit 7044.

[0129] The ninth processing subunit 7041 is used to send the height and horizontal data of the wall to a three-dimensional rectangular coordinate system for processing to obtain a three-dimensional model of the wall.

[0130] The fourth calculation subunit 7042 is used to calculate the average value of the adjacent grid points of each grid point in the three-dimensional rectangular coordinate system based on the local averaging method, and to calculate the smoothness index of the grid point based on the preset smoothness index calculation formula.

[0131] The fifth calculation subunit 7043 is used to calculate the weighted average of the smoothness index of all grid points, and to calculate the standard deviation based on the calculated global smoothness value. The calculated standard deviation is used as the smoothness error data of the wall surface.

[0132] The first analysis subunit 7044 is used to perform color analysis based on the image information of the wall to obtain the color data information of the wall.

[0133] The first analysis subunit 7044 includes a second analysis subunit 70441, a sixth calculation subunit 70442, and a seventh calculation subunit 70443.

[0134] The second analysis subunit 70441 is used to perform edge detection on the image information of the wall to obtain the image information of the wall edge, and convert the wall image outside the wall edge into black.

[0135] The sixth calculation subunit 70442 is used to cluster the R, G, and B components of all pixels within the edge of the wall image, calculate the average value of the center points of all the clusters, and use the average value as the color data of the wall image information.

[0136] The seventh calculation subunit 70443 is used to divide the color data of the image information of the wall into regions according to the grid points in the three-dimensional rectangular coordinate system, and to calculate the mean of the color data corresponding to the divided regions to obtain the color data information of each grid point.

[0137] The second analysis unit 705 is used to send the flatness error data, crack data, smoothness data and color data of the wall surface to the qualified analysis model for data analysis, and obtain the test results of the wall decoration.

[0138] The second analysis unit 705 includes a third analysis subunit 7051, a fourth analysis subunit 7052, a fifth analysis subunit 7053, a sixth analysis subunit 7054, and a seventh analysis subunit 7055.

[0139] The third analysis subunit 7051 is used to perform hierarchical analysis on the flatness error data, crack data, smoothness data and color data of the wall surface based on the analytic hierarchy process, and to determine the weight of each type of data.

[0140] The fourth analysis subunit 7052 is used to perform correlation analysis on all types of data with preset qualified thresholds to obtain the correlation value of each type of data.

[0141] The fifth analysis subunit 7053 is used to summarize the weight of each type of data and its corresponding correlation value based on the preset minimum discrimination principle, so as to obtain the summary weight value corresponding to each type of data.

[0142] The sixth analysis subunit 7054 is used to score each type of data according to a preset level threshold, and multiply the score obtained by the corresponding summary weight value to calculate the weighted score of each type of data.

[0143] The seventh analysis subunit 7055 is used to determine whether the data of that type on the wall is qualified based on the weighted score of each type of data, and obtain the judgment result.

[0144] It should be noted that the specific methods by which each module performs operations in the system described in the above embodiments have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0145] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0146] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for testing wall decoration, characterized in that, include: Wall decoration data is acquired using a laser level and camera equipment. The wall decoration data includes height data, horizontal data, and image information of all walls. The wall decoration data is sent to the wall flatness model for flatness calculation to obtain the wall flatness error data. Edge calculation is performed based on the flatness error data of the wall surface and the wall surface decoration data to obtain the crack data of the wall surface. The crack data of the wall surface includes the location data and shape data of the cracks in the wall surface. The wall decoration data is sent to a data analysis model for analysis to obtain the wall's smoothness and color data. The flatness error data, crack data, smoothness data, and color data of the wall surface are sent to the qualified analysis model for data analysis to obtain the test results of the wall decoration. Specifically, the wall surface decoration data is sent to a wall surface flatness model for flatness calculation to obtain wall surface flatness error data, including: Each wall surface is divided into at least two grids based on the orthogonal grid method; Each grid is marked based on the height and horizontal data of all walls. Then, based on the piecewise linear interpolation method, the height and horizontal data of each grid point are interpolated to the adjacent grid points. The height and horizontal data of the intermediate interpolation point are generated according to the intermediate distance between two grid points to construct an initial flatness model. The initial flatness model includes continuous height data distribution data and horizontal data distribution data. The initial smoothness model is subjected to error compensation based on a preset Gaussian process regression kernel function to obtain an error-compensated initial smoothness model. The spline surface fitting method is used to transform the data of each grid point in the initial flatness model after error compensation to obtain a continuous flatness fitting surface. The second derivative of the continuous flatness fitting surface is calculated based on the Laplacian operator to obtain the flatness error data of each grid region of the surface. The edge calculation based on the flatness error data of the wall surface and the wall decoration data includes: The Canny edge detection algorithm is used to process the image information of the wall and calculate the gradient of each pixel in the image information of the wall. The gradient of each pixel is distinguished based on a preset threshold to obtain the strong and weak edges of the wall image information. The strong and weak edges of the wall image information are then connected by the hysteresis edge method to obtain continuous crack edge image information of the wall. The image information of the crack edge of the continuous wall surface is enhanced by morphological opening and closing operations to obtain enhanced crack edge image information. The Hough transform is used to map the pixels of the crack from the image space to the parameter space, and the accumulator is used to detect crack features with linear or arc-shaped morphology. The watershed algorithm is used to segment the crack region containing crack features and calculate the width and length of each crack. The location data of the wall cracks are determined based on the flatness error data of the wall surface and the width and length of each crack.

2. The wall decoration testing method according to claim 1, characterized in that... The wall decoration data is sent to a data analysis model for analysis to obtain wall smoothness and color data, including: The height and horizontal data of the wall are sent to a three-dimensional rectangular coordinate system for processing to obtain a three-dimensional model of the wall. The average value of each grid point in a three-dimensional rectangular coordinate system is calculated based on the local averaging method, and the smoothness index of the grid point is calculated based on the preset smoothness index calculation formula. The weighted average of the smoothness index of all grid points is calculated, and the standard deviation is calculated based on the global smoothness value. The calculated standard deviation is used as the smoothness error data of the wall surface. Color analysis is performed based on the image information of the wall to obtain the color data information of the wall.

3. The wall decoration testing method according to claim 2, characterized in that... Color analysis is performed based on the image information of the wall to obtain the color data information of the wall, including: Edge detection is performed on the image information of the wall to obtain the wall edge, and the wall image outside the wall edge is converted into black; The R, G, and B components of all pixels within the edge of the wall image are clustered separately, and the average value of the center points of all the resulting clusters is calculated to obtain the average value of the center points of all clusters. This average value is then used as the color data of the wall image information. The color data of the image information on the wall is divided into regions according to grid points in a three-dimensional rectangular coordinate system, and the average value of the color data corresponding to the divided regions is calculated to obtain the color data information of each grid point.

4. A wall decoration inspection system, characterized in that, include: The acquisition unit is used to acquire wall decoration data information based on a laser level and a camera device. The wall decoration data information includes height data, horizontal data, and image information of all walls. The first processing unit is used to send the wall decoration data information to the wall flatness model for flatness calculation to obtain the wall flatness error data. The second processing unit is used to perform edge calculation based on the flatness error data of the wall surface and the wall surface decoration data to obtain the crack data of the wall surface. The crack data of the wall surface includes the location data and shape data of the cracks in the wall surface. The first analysis unit is used to send the wall decoration data information to the data analysis model for data analysis to obtain the smoothness data and color data of the wall. The second analysis unit is used to send the flatness error data, crack data, smoothness data and color data of the wall surface to the qualified analysis model for data analysis, and obtain the test results of the wall decoration. The first processing unit includes: The first processing sub-unit is used to divide each wall surface into at least two grids based on the orthogonal grid method; The second processing subunit is used to mark each grid based on the height and horizontal data of all walls, and to interpolate the height and horizontal data of each grid point to adjacent grid points based on the piecewise linear interpolation method. The height and horizontal data of the intermediate interpolation point are generated according to the intermediate distance between two grid points to construct an initial flatness model. The initial flatness model includes continuous height data distribution data and horizontal data distribution data. The third processing subunit is used to perform error compensation on the initial smoothness model based on a preset Gaussian process regression kernel function to obtain the error-compensated initial smoothness model. The fourth processing subunit is used to perform data transformation on each grid point in the initial flatness model after error compensation based on the spline surface fitting method to obtain a continuous flatness fitting surface. The first calculation subunit is used to calculate the second derivative of the continuous flatness fitting surface based on the Laplacian operator to obtain the flatness error data of each grid region of the surface. The second processing unit includes: The fifth processing subunit is used to process the image information of the wall using the Canny edge detection algorithm and calculate the gradient of each pixel in the image information of the wall. The sixth processing subunit is used to distinguish the gradient of each pixel based on a preset threshold, obtain the strong edges and weak edges of the wall image information, and connect the strong edges and weak edges of the wall image information through the hysteresis edge method to obtain continuous crack edge image information of the wall. The seventh processing subunit is used to enhance the crack edge image information of the continuous wall surface based on morphological opening and closing operations to obtain enhanced crack edge image information. The eighth processing subunit is used to map the crack pixels from the image space to the parameter space based on the Hough transform, and to detect crack features with linear or arc-shaped morphology using an accumulator. The second computational subunit is used to segment the crack region containing crack features based on the watershed algorithm and calculate the width and length of each crack. The third calculation subunit is used to determine the location data of the wall cracks based on the flatness error data of the wall surface and the width and length of each crack.

5. The wall decoration inspection system according to claim 4, characterized in that, The first analysis unit includes: The ninth processing subunit is used to send the height and horizontal data of the wall to a three-dimensional rectangular coordinate system for processing to obtain a three-dimensional model of the wall. The fourth calculation subunit is used to calculate the average value of the adjacent grid points of each grid point in the three-dimensional rectangular coordinate system based on the local averaging method, and to calculate the smoothness index of the grid point based on the preset smoothness index calculation formula. The fifth calculation subunit is used to calculate the weighted average of the smoothness index of all grid points, and to calculate the standard deviation based on the calculated global smoothness value. The calculated standard deviation is used as the smoothness error data of the wall surface. The first analysis subunit is used to perform color analysis based on the image information of the wall to obtain the color data information of the wall.

6. The wall decoration inspection system according to claim 5, characterized in that, The first analysis subunit includes: The second analysis subunit is used to perform edge detection on the image information of the wall to obtain the wall image information and the wall edge, and to convert the wall image outside the wall edge into black. The sixth calculation subunit is used to cluster the R, G, and B components of all pixels within the image edge of the wall, calculate the average value of the center points of all the clusters, and use the average value as the color data of the image information of the wall. The seventh calculation subunit is used to divide the color data of the image information on the wall into regions according to the grid points in the three-dimensional rectangular coordinate system, and to calculate the mean of the color data corresponding to the divided regions to obtain the color data information of each grid point.

Images