A Threshold Zoning Detection Method for Building Formwork Flatness Based on Normal Vector Constraint RANSAC

Abstract

This invention relates to the technical field of building formwork, and in particular provides a method for threshold-based detection of flatness of building formwork based on RANSAC (Random Access Scale) constrained by normal vectors. The method includes: performing 3D laser scanning on the building formwork to acquire high-density point cloud data; performing preprocessing operations such as denoising and downsampling on the acquired point cloud data to improve data quality; using an improved RANSAC algorithm, fitting a reference plane of the formwork based on the preprocessed point cloud data, and introducing a unit normal vector to ensure the correct orientation of the reference plane; calculating the vertical distance from each point cloud point to the reference plane to obtain the deviation value; autonomously setting a deviation threshold according to building codes, classifying the deviation values ​​into different levels, and displaying them on the 3D point cloud model using color differentiation; and outputting a visualization result containing the 3D point cloud model and color indicators, intuitively displaying the flatness of the formwork. This method features automatic measurement and offers high efficiency and accuracy.

Description

Technical Field

[0001] This invention relates to the technical field of building construction, and in particular to a method for detecting threshold partitioning of building formwork flatness based on normal vector constraint RANSAC. Background Technology

[0002] Construction formwork is the outer shell mold for pouring and shaping concrete. It is often made of film-coated plywood. After installing the horizontal floor slab formwork, workers on site use methods such as string lines and rulers to check the flatness of the formwork. The above construction method is a single-point manual measurement method, which cannot reflect the deviation of each individual formwork piece, thus creating potential safety hazards for construction quality. This invention utilizes a 3D laser scanning point cloud model, improves the RANSAC algorithm, sets a unit normal vector to determine the correct direction of the reference plane, and autonomously sets thresholds and color-coded displays according to acceptance specifications. The final output is a visualized result of a 3D point cloud with color-coded zones.

[0003] The information disclosed in the background section is only for enhancing the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art.

[0004] Prior art 1, Chinese patent application number CN202410113884.5, discloses a method for detecting the flatness of bus side wall panels based on 3D point cloud and contour matching, including: acquiring a frame of 3D point cloud data for different types of bus side wall panels; preprocessing the 3D point cloud data to generate point cloud slice data; fitting the point cloud slice data to line segments, and storing the fitted line segment function, the number of collected points, and the region division into a template library; performing point cloud preprocessing operations when collecting each frame of point cloud data of the test component, matching it with the point cloud slice data in the template library, setting relevant defect thresholds, and determining whether a point is a defect point; expanding it into complete bus side wall panel point cloud data and segmenting the defect area; using an outlier removal algorithm to remove misjudged points and obtain the defect area. This invention solves the problem of excessively long detection time caused by the large size of bus side wall panels, and solves the problem of difficulty in detecting defects that are too small by using contour matching, thus enabling real-time and accurate defect detection on complex curved surfaces such as bus side wall panels.

[0005] Prior art 2, Chinese patent application number CN202210588295.3, discloses a method for detecting defects in sheet metal based on three-dimensional point clouds, relating to the field of industrial defect detection. By filtering, coordinate transformation, and plane fitting operations on the three-dimensional point cloud data of sheet metal collected on the production site, relevant parameters are measured and compared with set standard values ​​and thresholds to determine whether there are defects in size and flatness. Compared with the prior art, it does not require standard data samples as templates and does not require training a pre-set neural network model. It can achieve defect detection in size and flatness based solely on the three-dimensional point cloud data collected on site, and has the advantages of high efficiency, high precision, and low labor intensity.

[0006] Current existing technologies 1 and 2 rely primarily on manual measurement, resulting in low efficiency and poor accuracy, which fails to meet the quality requirements of modern construction. Therefore, this invention provides a threshold-based detection method for building formwork flatness based on normal vector constraint RANSAC. Summary of the Invention

[0007] To achieve the above objectives, the present invention adopts the following technical solution:

[0008] One aspect of the present invention provides a method for detecting the threshold partitioning of building formwork flatness based on normal vector constraint RANSAC, comprising the following steps:

[0009] Three-dimensional laser scanning is performed on the building template to obtain high-density point cloud data;

[0010] The collected point cloud data is preprocessed by denoising and downsampling to improve data quality;

[0011] Using the improved RANSAC algorithm, a reference plane for the template is fitted based on the preprocessed point cloud data, and a unit normal vector is introduced to ensure the correct orientation of the reference plane.

[0012] Calculate the vertical distance from each point in the point cloud to the reference plane to obtain the deviation value;

[0013] Based on building codes, deviation thresholds are set independently, and deviation values ​​are divided into different levels and displayed on the 3D point cloud model by color differentiation.

[0014] The output includes a 3D point cloud model and color indicators, visually demonstrating the flatness of the template.

[0015] In one optional implementation, the step of performing 3D laser scanning on the building template to obtain high-density point cloud data includes: selecting a device with appropriate resolution and scanning range based on the size and complexity of the building template; ensuring that the scanner has sufficient power, the storage medium is available, and the device is in good working order; determining the specific location and coverage area of ​​the building template to be scanned; identifying multiple scanning locations based on the shape and structure of the template to ensure comprehensive coverage of all surfaces of the template; setting the scanning resolution as needed (higher resolution obtains more detailed data, but increases the data volume); adjusting the scanning frequency according to the dynamics of the template; fixing the scanner on a tripod or other stable support device to ensure that the device does not shake during the scanning process; calibrating the device to ensure the accuracy of the scanned data; monitoring the scanning progress and data quality in real time through the device display screen or a connected computer; and storing the raw point cloud data obtained from the scan in the device or directly transferring it to the computer.

[0016] In one optional implementation, the step of using the improved RANSAC algorithm to fit a reference plane of the template based on preprocessed point cloud data and introducing a unit normal vector to ensure the correct orientation of the reference plane includes: setting the number of iterations of the RANSAC algorithm according to the data scale and complexity to ensure that the optimal plane is found; defining a distance threshold from a point to the plane to determine whether a point belongs to the fitted plane; randomly selecting three points from the point cloud data as initial samples for the fitted plane; calculating the normal vector and equation of the plane based on these three points; calculating the normal vector according to the fitted plane equation; and normalizing the normal vector to make it a unit normal vector to ensure the consistency of orientation.

[0017] Based on the structural characteristics of the building template, a reference normal vector is set as the correct direction of the reference plane. The angle between the unit normal vector of the current fitting plane and the reference direction is calculated, and it is determined whether the directions are consistent. If the directions are inconsistent, the direction of the normal vector is adjusted to make it closer to the reference direction. For each point cloud point, its vertical distance to the fitting plane is calculated. According to the set threshold, the points are divided into inner points and outer points. During the iteration process, sample points are randomly selected continuously to fit the plane, and the direction of the normal vector is adjusted. After each iteration, the number of inner points and the overall deviation of the current fitting plane are evaluated, and the optimal fitting result is recorded. When the set number of iterations is reached or the fitting result no longer improves significantly, the iteration is terminated.

[0018] Based on the iteration results, the plane with the most interior points and the smallest deviation is selected as the reference plane.

[0019] Output plane parameters: Output the plane equation, normal vector, and point cloud data of the reference plane for subsequent deviation calculation and visualization. The fitted reference plane is superimposed with the original point cloud data for visual inspection of the fitting effect, ensuring that the normal vector direction of the reference plane conforms to the preset reference direction and the deviation is within an acceptable range. Based on the verification results, the algorithm parameters are adjusted, and the fitting results are further optimized by iterating and setting thresholds. Based on the fitted reference plane, the deviation value of each point cloud point is calculated for the evaluation of template flatness. According to the deviation value, the template area is divided into different levels and displayed by color to visually show the flatness status. The improved RANSAC algorithm is integrated into the building formwork inspection system to achieve automated and high-precision flatness detection.

[0020] In one optional implementation, the step of autonomously setting deviation thresholds according to building codes, classifying deviation values ​​into different levels, and displaying them on the 3D point cloud model using color differentiation includes: setting a threshold range for each deviation level according to the codes; recording the set threshold ranges for subsequent data processing and adjustment; importing the preprocessed 3D point cloud data into selected software to ensure that the deviation value of each point cloud point has been calculated and associated with the point cloud data; classifying the deviation value of each point cloud point according to the set threshold range; updating the classification results to the point cloud data to ensure the accuracy of the classification information for each point cloud point; and selecting appropriate software based on the deviation level. A color scheme is selected, and color mapping rules are applied to the point cloud data to display color distinctions at different deviation levels in real time. The viewpoint and lighting settings of the 3D point cloud model are optimized to ensure clear and visible color distinctions. A portion of point cloud points are randomly selected, and their deviation values ​​are manually checked to ensure consistency with the classification results, thus ensuring classification accuracy. Based on the actual inspection results, the deviation threshold and color scheme are adjusted to improve classification accuracy and visualization effects. The visualization results of the 3D point cloud model and color labels are saved as images or videos for subsequent reporting and presentation. Based on the classification results, a detailed deviation analysis report is generated, summarizing the flatness of the template and proposing construction adjustment suggestions.

[0021] In one optional implementation, the plane fitting model is based on the Cartesian equation of the plane, also known as the general form equation, whose standard form is: ax + by + cz + d = 0, where (a, b, c) are the unit normal vectors of the plane, satisfying... =1, d is the plane offset;

[0022] Establish an optimization model for the objective function RANSAC:

[0023]

[0024] In the formula, N is the total number of point clouds. δ is the threshold for the distance between interior points, and δ is an indicator function that is 1 when the condition is met and 2 when the condition is not met.

[0025] In one optional implementation, a plane is established, the mathematical expression of which is ax + by + cz + d = 0, such that this plane can contain as many given points M as possible. , This refers to all the points of the template model in the point cloud model, and the distance of these points to the plane does not exceed a set threshold. The threshold is set according to the quality acceptance specifications;

[0026] The normal vector constraint conditions are satisfied as follows:

[0027]

[0028] Establish a deviation quantification model and symbolize vertical deviation:

[0029]

[0030] In the formula, >0 indicates a point Located on the positive side of the plane, <0 indicates a point Located on the negative side of the plane. The final absolute deviation smoothness index dataset is as follows:

[0031] = .

[0032] In one optional implementation, the threshold setting enables the results to display a dynamic two-color scheme, with blue indicating that the condition is met and red indicating that the condition is not met. The specific color assignment function of the mapping model is as follows:

[0033] Color )=

[0034] In the formula, τ is a preset threshold, which is set to 10mm according to the quality acceptance specifications;

[0035] Design a quality evaluation index calculation model to calculate the proportion of qualified point clouds and the maximum deviation value statistics, wherein the qualification rate is calculated as follows:

[0036]

[0037] δ is an indicator function, where 1 represents the condition that is met and 2 represents the condition that is not met. The above formula is used to calculate the proportion of points that meet the condition to the total number of points in the point cloud.

[0038] Maximum deviation statistics:

[0039] =max( ), =min( ).

[0040] Another aspect of the present invention provides a building formwork flatness threshold zoning detection system based on normal vector constraint RANSAC, including a three-dimensional laser scanning device for scanning building formwork to obtain high-density point cloud data;

[0041] A data processing device is used to preprocess the point cloud data and fit the reference surface of the template using an improved RANSAC algorithm, wherein the improved RANSAC algorithm ensures the correct orientation of the reference surface based on unit normal vector constraints.

[0042] The display device is used to set deviation thresholds independently according to building codes, divide deviation values ​​into different levels, and display them on the 3D point cloud model by color differentiation.

[0043] In another aspect, the present invention provides an electronic device comprising:

[0044] At least one memory stores computer-executable instructions non-transiently;

[0045] At least one processor, configured to run the computer-executable instructions,

[0046] The computer-executable instructions, when executed by the processor, implement the aforementioned method for detecting the flatness threshold partitioning of building templates based on normal vector constraint RANSAC.

[0047] In another aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions that, when executed by at least one processor, implement the above-described method for detecting the flatness threshold of building templates based on normal vector constraint RANSAC.

[0048] This invention acquires high-density point cloud data by performing 3D laser scanning on building templates. Preprocessing operations such as denoising and downsampling are performed on the acquired point cloud data to improve data quality. An improved RANSAC algorithm is used to fit a reference plane of the template based on the preprocessed point cloud data, introducing a unit normal vector to ensure the correct orientation of the reference plane. The vertical distance from each point cloud point to the reference plane is calculated to obtain the deviation value. A deviation threshold is set autonomously according to building codes, and the deviation values ​​are divided into different levels and displayed on the 3D point cloud model using color differentiation. The output is a visualization containing the 3D point cloud model and color indicators, intuitively showing the flatness of the template. This invention features automatic measurement and offers high efficiency and accuracy. Attached Figure Description

[0049] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0050] Figure 1 This is a flowchart provided in Embodiment 1 of the present invention;

[0051] Figure 2 This is a system framework diagram provided in Embodiment 4 of the present invention;

[0052] Figure 3 This is a block diagram of the electronic device provided in Embodiment 5 of the present invention;

[0053] Figure 4 This is a block diagram of a computer-readable storage medium provided in Embodiment 6 of the present invention. Detailed Implementation

[0054] The technical solutions of the present invention will now be described with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0055] Hereinafter, the terms "first," "second," etc., are used for descriptive convenience only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0056] In this invention, unless otherwise explicitly specified and limited, the term "connection" should be interpreted broadly. For example, "connection" can be a fixed mechanical connection, a detachable mechanical connection, or an integral part; or, "connection" can be a direct connection or an indirect connection through an intermediate medium. Furthermore, unless otherwise explicitly specified and limited, the term "coupling" should be interpreted broadly. For example, "coupling" can be a direct electrical connection, such as physical contact and electrical conduction between two components; it can also be understood as an electrical connection between different components in a circuit structure through physical lines capable of transmitting electrical signals, such as copper foil or wires on a printed circuit board (PCB), to transmit electrical signals; or, "coupling" can be an indirect electrical connection between two components through an intermediate medium; or, "coupling" can be an electrical connection between two components in a non-contact manner, such as an electrical connection between two components using capacitive coupling to transmit electrical signals.

[0057] In this embodiment of the invention, directional terms such as "up," "down," "left," and "right" may be defined relative to the orientation of the components shown in the accompanying drawings. It should be understood that these directional terms can be relative concepts, used for relative description and clarification, and can change accordingly depending on the orientation of the components in the accompanying drawings.

[0058] Example 1:

[0059] like Figure 1 As shown, this embodiment of the invention provides a method for detecting the threshold partitioning of building formwork flatness based on normal vector constraint RANSAC, comprising the following steps:

[0060] Step S100: Perform 3D laser scanning on the building template to obtain high-density point cloud data;

[0061] Step S200: Perform noise reduction and downsampling preprocessing on the collected point cloud data to improve data quality;

[0062] Step S300: Using the improved RANSAC algorithm, based on the preprocessed point cloud data, fit the reference plane of the template, introduce the unit normal vector, and ensure the correct orientation of the reference plane.

[0063] Step S400: Calculate the vertical distance from each point cloud point to the reference plane to obtain the deviation value;

[0064] Step S500: Set deviation thresholds independently according to building codes, divide deviation values ​​into different levels, and display them on the 3D point cloud model by color differentiation;

[0065] Step S600: Output a visualization containing a 3D point cloud model and color markers, visually demonstrating the flatness of the template.

[0066] In the above embodiments, a 3D laser scanning device is used to scan the building template to obtain high-density point cloud data. Noise denoising: Noise points are removed through statistical filtering or curvature-based methods. Downsampling: The point cloud data is downsampled to reduce the data volume and improve processing efficiency. Three points are randomly selected as initial samples, and the normal vector of the fitting plane is calculated. The normal vector is normalized to ensure directional consistency. Normal vector constraints are introduced to adjust the orientation of the fitting plane to conform to the correct orientation of the template. Iterative optimization is performed, and the plane with the most interior points and the smallest deviation is selected as the reference plane.

[0067] Deviation Calculation and Classification: Calculate deviation values: For each point cloud point, calculate its vertical distance to the reference plane. Set deviation thresholds: Based on building codes, set threshold ranges for different deviation levels, such as slight deviation (≤2mm), moderate deviation (2mm-5mm), and severe deviation (>5mm). Classify point cloud points: Classify point cloud points into different levels according to their deviation values.

[0068] Color Mapping and Visualization: Select a color scheme: Choose a corresponding color for each deviation level, such as green for slight deviation, orange for moderate deviation, and red for severe deviation. Color Mapping: Map the classification results to point cloud data, using different colors to distinguish and display them on the 3D model. Add Legends and Labels: Add legends and labels to the visualization interface to explain the deviation levels represented by different colors.

[0069] Results Output and Reporting: Saving Visualization Results: Saving the visualization results of the 3D point cloud model and color labels as images or videos. Generating Deviation Analysis Reports: Summarizing the flatness of the template and proposing construction adjustment suggestions. Data Preprocessing Optimization: Resolution Adjustment: Adjusting the resolution of the point cloud data as needed to ensure a balance between data quality and processing efficiency. Data Alignment: Aligning the coordinates of the point cloud data obtained from multi-angle scanning to ensure data consistency. Improved RANSAC Algorithm Optimization: Adaptive Threshold: Dynamically adjusting the threshold of the RANSAC algorithm based on data characteristics to improve fitting accuracy. Parallel Computing: Utilizing multi-core processors or GPUs to accelerate the iteration process of the RANSAC algorithm and improve processing speed. Deviation Classification and Color Mapping Optimization: Dynamic Color Scheme: Dynamically adjusting the color scheme based on the actual deviation range to ensure color differentiation. Color Contrast Optimization: Adjusting color contrast to ensure that colors of different deviation levels are clearly distinguishable. Visualization Optimization: Interactive Interface: Developing an interactive visualization interface that allows users to adjust thresholds and color schemes in real time. Multi-View Display: Supporting multi-view display for easy observation of the template's flatness from different angles. Automated Report Generation: Intelligent Analysis: Based on classification results, the system intelligently analyzes template flatness issues and generates targeted adjustment suggestions. Report Templates: A variety of report templates are provided, allowing users to easily select and customize report formats according to their needs.

[0070] Integration with Building Management System: Integrate the flatness detection system into the building management software to achieve real-time data upload and analysis. Provide remote monitoring capabilities, allowing construction managers to view the flatness of the formwork anytime, anywhere. Integration with BIM Technology: Link point cloud data with the BIM model to achieve comparative analysis of formwork flatness against the design model. Generate deviation reports to guide construction adjustments and ensure construction quality meets design requirements. Mobile Application Development: Develop a mobile application to facilitate formwork inspection by construction personnel on-site using mobile phones or tablets. Provide real-time feedback, allowing construction personnel to make immediate adjustments based on inspection results. Training and Knowledge Sharing: Develop a training module providing system operation guides and case studies to help construction personnel quickly master the inspection methods. Establish a knowledge sharing platform where construction teams can upload and share inspection results and experiences, promoting team collaboration and knowledge accumulation.

[0071] Performance Testing and Verification, Test Environment Setup: Select building templates of different scales and complexities as test objects. Ensure the diversity and representativeness of the test environment, covering different construction conditions and template types. Algorithm Performance Testing: Fitting Accuracy: Test the fitting accuracy of the improved RANSAC algorithm under different noise and outlier conditions. Processing Speed: Evaluate the algorithm's processing speed under different data volumes, verifying its efficiency and scalability. Classification Accuracy Verification: Classification Accuracy: Verify the accuracy of biased classification through manual inspection and comparative analysis. Color Mapping Consistency: Ensure that the color mapping is consistent with the classification results, and that color distinctions are clear. User Feedback Collection: User Experience Testing: Invite users from different backgrounds to participate in system testing and collect their feedback. Functional Requirements Analysis: Analyze the completeness and improvement directions of the system functions based on user feedback. Continuous Optimization and Upgrades: Regular Updates: Optimize and upgrade the system regularly based on test results and user feedback. Technical Support: Provide technical support and consulting services to help users solve problems encountered during use.

[0072] Technical Comparison and Advantages Analysis: Compared with the Traditional RANSAC Algorithm: Fitting Accuracy: The improved RANSAC algorithm enhances fitting accuracy by introducing normal vector constraints, ensuring the correct orientation of the reference plane. Processing Speed: The optimized RANSAC algorithm is comparable to, and in some cases even faster than, the traditional algorithm in processing speed. Adaptability: The improved algorithm performs better on complex and noisy point cloud data, exhibiting greater adaptability. Compared with Manual Inspection Methods: Efficiency: Automated inspection systems significantly improve inspection efficiency and reduce labor costs. Accuracy: Algorithm-based inspection methods offer higher accuracy and consistency, reducing human error. Visualization: Color-coded display makes inspection results more intuitive, facilitating understanding and adjustments by the construction team.

[0073] Compared with existing detection systems: Functional comprehensiveness: This system integrates multiple functions such as data acquisition, processing, fitting, classification, and visualization, making it more comprehensive. User-friendliness: The system provides an interactive interface and intelligent analysis functions, making user operation more convenient. Scalability: The system supports integration with BIM technology, building management systems, etc., offering better scalability and application prospects.

[0074] Example 2:

[0075] like Figure 2 As shown in Example 1, the step S100 of this embodiment of the invention, which involves performing a three-dimensional laser scan on a building template to obtain high-density point cloud data, includes: selecting a device with appropriate resolution and scanning range based on the size and complexity of the building template; ensuring that the scanner has sufficient power, the storage medium is available, and the device is in good working order; determining the specific location and coverage area of ​​the building template to be scanned; determining multiple scanning positions based on the shape and structure of the template to ensure comprehensive coverage of all surfaces of the template; setting the scanning resolution as needed (higher resolution obtains more detailed data, but increases the data volume); adjusting the scanning frequency according to the dynamics of the template; fixing the scanner on a tripod or other stable support device to ensure that the device does not shake during the scanning process; calibrating the device to ensure the accuracy of the scanned data; monitoring the scanning progress and data quality in real time through the device display screen or a connected computer; and storing the original point cloud data obtained from the scan in the device or directly transferring it to the computer.

[0076] The steps of using the improved RANSAC algorithm to fit a reference plane of the template based on preprocessed point cloud data and introducing a unit normal vector to ensure the correct orientation of the reference plane include: setting the number of iterations of the RANSAC algorithm according to the data scale and complexity to ensure that the optimal plane is found; defining a distance threshold from a point to the plane to determine whether a point belongs to the fitted plane; randomly selecting three points from the point cloud data as initial samples for the fitted plane; calculating the normal vector and equation of the plane based on these three points; calculating the normal vector according to the fitted plane equation; and normalizing the normal vector to make it a unit normal vector to ensure the consistency of orientation.

[0077] Based on the structural characteristics of the building template, a reference normal vector is set as the correct direction of the reference plane. The angle between the unit normal vector of the current fitting plane and the reference direction is calculated, and it is determined whether the directions are consistent. If the directions are inconsistent, the direction of the normal vector is adjusted to make it as close as possible to the reference direction. For each point cloud point, its vertical distance to the fitting plane is calculated. According to the set threshold, the points are divided into inner points and outer points. During the iteration process, sample points are randomly selected continuously to fit the plane, and the direction of the normal vector is adjusted. After each iteration, the number of inner points and the overall deviation of the current fitting plane are evaluated, and the optimal fitting result is recorded. When the set number of iterations is reached or the fitting result no longer improves significantly, the iteration is terminated.

[0078] Based on the iteration results, the plane with the most interior points and the smallest deviation is selected as the reference plane.

[0079] Output plane parameters: Output the plane equation, normal vector, and point cloud data of the reference plane for subsequent deviation calculation and visualization. The fitted reference plane is superimposed with the original point cloud data for visual inspection of the fitting effect, ensuring that the normal vector direction of the reference plane conforms to the preset reference direction and the deviation is within an acceptable range. Based on the verification results, the algorithm parameters, such as the number of iterations and the threshold, are adjusted to further optimize the fitting results. Based on the fitted reference plane, the deviation value of each point cloud point is calculated for the evaluation of template flatness. According to the deviation value, the template area is divided into different levels and displayed by color to visually show the flatness status. The improved RANSAC algorithm is integrated into the building formwork inspection system to achieve automated and high-precision flatness detection.

[0080] The steps of independently setting deviation thresholds according to building codes, classifying deviation values ​​into different levels, and displaying them on the 3D point cloud model using color differentiation include: setting a threshold range for each deviation level according to the codes; recording the set threshold ranges for subsequent data processing and adjustment; importing the preprocessed 3D point cloud data into the selected software to ensure that the deviation value of each point cloud point has been calculated and associated with the point cloud data; classifying the deviation value of each point cloud point according to the set threshold ranges; updating the classification results to the point cloud data to ensure the accuracy of the classification information for each point cloud point; and selecting a color scheme according to the deviation level. Color mapping rules are applied to point cloud data to display color distinctions at different deviation levels in real time. The viewpoint and lighting settings of the 3D point cloud model are optimized to ensure clear and visible color distinctions. A portion of point cloud points are randomly selected, and their deviation values ​​are manually checked to ensure consistency with the classification results, thus ensuring classification accuracy. Based on the actual inspection results, the deviation threshold and color scheme are adjusted to improve classification accuracy and visualization effects. The visualization results of the 3D point cloud model and color labels are saved as images or videos for subsequent reporting and presentation. Based on the classification results, a detailed deviation analysis report is generated, summarizing the flatness of the template and proposing construction adjustment suggestions.

[0081] In the above embodiments, the following steps are taken: Selecting a suitable 3D laser scanner: Based on the size and complexity of the building template, select a device with appropriate resolution and scanning range. Checking device status: Ensure the scanner has sufficient power, the storage medium is available, and the device is in good working order. Determining the scanning range: Clearly define the specific location and coverage area of ​​the building template to be scanned. Selecting scanning positions: Based on the shape and structure of the template, determine multiple scanning positions to ensure complete coverage of all surfaces of the template. Adjusting the resolution: Set the scanning resolution as needed; higher resolution acquires more detailed data but increases the data volume. Setting the scanning frequency: Adjust the scanning frequency based on the dynamics of the template (e.g., whether there are moving parts). Setting the scanning angle: Ensure the scanning angle covers the entire template, avoiding blind spots. Using a stable support: Fix the scanner on a tripod or other stable support device to ensure the device does not shake during scanning. Calibrating the device: Perform device calibration to ensure the accuracy of the scanned data.

[0082] Start the scanning program: Follow the device operation guide to start the scanning program. Perform multi-angle scanning: Scan the template from different angles to ensure data comprehensiveness. Record scanning parameters: Record the position, angle, and parameter settings for each scan for subsequent data processing. Monitor the scanning process in real time: Monitor the scanning progress and data quality in real time via the device display or a connected computer. Store raw data: Store the raw point cloud data obtained from the scan in the device or transfer it directly to a computer.

[0083] Noise Reduction: Specialized software is used to denoise the point cloud data, removing outliers caused by environmental interference or equipment errors. Downsampling: The point cloud data is downsampled to reduce the data volume and improve subsequent processing efficiency. Coordinate Alignment: The coordinates of the point cloud data obtained from multi-angle scans are aligned to ensure data consistency and integrity.

[0084] Data visualization and inspection: Visualizing point cloud data: Use point cloud processing software (such as CloudCompare, MeshLab, etc.) to visualize the point cloud data and check whether the scan results meet expectations. Checking coverage: Ensure all template areas are scanned, with no omissions or blind spots. Evaluating data quality: Check the density, uniformity, and completeness of the point cloud data to ensure the data quality meets the requirements of subsequent analysis. Format conversion: Convert the point cloud data to common formats (such as LAS, PLY, etc.) for easier subsequent processing and analysis. Data backup: Back up the processed point cloud data and store it on a secure and reliable storage medium to prevent data loss. Establishing data management archives: Record information such as the time, location, and equipment parameters of data acquisition for easy traceability and management.

[0085] Quality control and optimization, data quality assessment: Through statistical analysis and visualization inspection, the quality of point cloud data is assessed to ensure it meets the requirements of subsequent flatness inspection. Optimized scanning strategy: Based on actual scanning results, scanning parameters and strategies are optimized to improve data acquisition efficiency and quality. Through these steps, a systematic and efficient 3D laser scanning of building formwork can be completed, acquiring high-density, high-quality point cloud data, providing a solid data foundation for subsequent formwork flatness inspection.

[0086] Preprocessed point cloud data: Ensure the point cloud data has undergone preprocessing steps such as denoising and downsampling, resulting in good data quality suitable for plane fitting. Setting the number of iterations: Based on the data size and complexity, set the number of iterations for the RANSAC algorithm to ensure the optimal plane is found. Setting a threshold: Define a distance threshold from a point to the plane to determine if a point belongs to the fitted plane. Randomly selecting sample points: Randomly select three points from the point cloud data as initial samples for the fitted plane. Fitting the plane equation: Calculate the plane's normal vector and equation based on these three points. Calculating the initial normal vector: Calculate the normal vector based on the fitted plane equation. Normalizing the normal vector: Normalize the normal vector to make it a unit normal vector, ensuring consistency in direction.

[0087] Determine the reference plane orientation and set the reference direction: Based on the structural characteristics of the building template, set a reference normal vector as the correct orientation of the reference plane. Compare the normal vector directions: Calculate the angle between the unit normal vector of the current fitted plane and the reference direction to determine if the directions are consistent. Adjust the normal vector direction: If the directions are inconsistent, adjust the direction of the normal vector to make it as close as possible to the reference direction. Calculate the distance from the point to the plane: For each point in the point cloud, calculate its perpendicular distance to the fitted plane. Classify the point cloud points: Based on the set threshold, classify the points into inliers (belonging to the fitted plane) and outliers (not belonging to the fitted plane).

[0088] Repeated random sampling and fitting: During the iteration process, sample points are continuously randomly selected, a fitting plane is formed, and the direction of the normal vector is adjusted. Evaluation of fitting results: After each iteration, the number of interior points and the overall deviation of the current fitting plane are evaluated, and the optimal fitting result is recorded. Termination condition: The iteration terminates when the set number of iterations is reached or the fitting result no longer significantly improves.

[0089] Output the reference plane and determine the optimal plane: Based on the iteration results, select the plane with the most interior points and the smallest deviation as the reference plane. Output plane parameters: Output the plane equation, normal vector, and point cloud data of the reference plane for subsequent deviation calculation and visualization.

[0090] Visualization and Verification: Visualize the fitting results: Overlay the fitted reference surface with the original point cloud data for a visual check of the fitting effect. Verify the correctness of the orientation: Ensure that the normal vector direction of the reference surface conforms to the preset reference direction, and the deviation is within an acceptable range. Adjustment and Optimization: Based on the verification results, adjust algorithm parameters, such as the number of iterations and thresholds, to further optimize the fitting results.

[0091] Applications and Extensions: Deviation Calculation: Based on the fitted reference surface, the deviation value of each point cloud point is calculated for evaluating the flatness of the template. Differentiated Color Display: Based on the deviation values, the template area is divided into different levels and displayed using color differentiation, providing a clear visual representation of the flatness status. Automated Detection: The improved RANSAC algorithm is integrated into the building template detection system to achieve automated, high-precision flatness detection. Through the above steps, the improved RANSAC algorithm can be effectively utilized to fit the reference surface of the template based on preprocessed point cloud data, ensuring the correctness of the reference surface orientation and providing a reliable foundation for subsequent template flatness detection.

[0092] Referring to the building construction quality acceptance specifications, the allowable deviation range and classification standards for formwork flatness are clearly defined. Deviation levels are determined: according to the specifications, deviation values ​​are divided into different levels such as slight deviation, moderate deviation, and severe deviation.

[0093] Determine the threshold range: Based on the specifications, set the threshold range for each deviation level. For example:

[0094] Slight deviation: 0 < deviation value ≤ 2mm;

[0095] Medium deviation: 2mm < deviation value ≤ 5mm;

[0096] Severe deviation: Deviation value > 5mm;

[0097] Record threshold parameters: Record the set threshold range for easy data processing and adjustment later.

[0098] Choose professional software that supports 3D point cloud data processing and visualization, such as CloudCompare, MeshLab, and PointCloudsLibrary (PCL). Understand the software's color mapping, data classification, and visualization capabilities to ensure that color differentiation of deviation levels can be achieved. Import point cloud data: Import the preprocessed 3D point cloud data into the selected software. Load deviation value data: Ensure that the deviation value for each point cloud point has been calculated and associated with the point cloud data.

[0099] Threshold classification: Based on a set threshold range, the deviation value of each point cloud point is classified. For example:

[0100] Deviation ≤ 2mm: classified as minor deviation;

[0101] 2mm < Deviation value ≤ 5mm: Classified as medium deviation;

[0102] Deviation > 5 mm: classified as serious deviation;

[0103] Update point cloud attributes: Update the classification results to the point cloud data to ensure that the classification information of each point cloud point is accurate.

[0104] Choose a color scheme: Select an appropriate color scheme based on the deviation level. For example:

[0105] Slight deviation: Green;

[0106] Moderate deviation: Orange;

[0107] Serious deviation: Red;

[0108] Configure color mapping rules: Set color mapping rules in the software to map each deviation level to the corresponding color.

[0109] Apply color mapping: Apply color mapping rules to point cloud data to display color distinctions for different deviation levels in real time. Adjust viewpoint and lighting: Optimize the viewpoint and lighting settings of the 3D point cloud model to ensure clear and visible color distinctions. Add legends and annotations: Add legends and annotations to the visualization interface to explain the deviation levels represented by different colors, facilitating understanding and analysis. Check classification accuracy: Randomly select a portion of point cloud points and manually check whether their deviation values ​​are consistent with the classification results to ensure classification accuracy. Adjust thresholds and color schemes: Adjust the deviation thresholds and color schemes based on actual inspection results to improve classification accuracy and visualization effects. Optimize processing speed: If the data volume is large, consider downsampling or optimizing the point cloud data to improve data processing and visualization efficiency. Save visualization results: Save the visualization results of the 3D point cloud model and color labels as images or videos for subsequent reporting and presentation. Generate deviation analysis report: Generate a detailed deviation analysis report based on the classification results, summarize the flatness of the template, and propose construction adjustment suggestions. Sharing and Feedback: Share the visualization results and reports with the construction team and relevant personnel, collect feedback, and further optimize the testing methods and visualization effects.

[0110] Record Improvement Measures: Based on feedback, record areas requiring improvement, such as adjusting thresholds or optimizing color schemes. Update Inspection Process: Incorporate improvement measures into the inspection process, continuously optimizing the entire deviation detection and visualization process. Training and Knowledge Sharing: Train the construction team to ensure they understand and utilize the visualization results, improving overall construction quality management. Through the above steps, deviation thresholds can be independently set according to building codes, deviation values ​​can be categorized into different levels, and displayed on a 3D point cloud model using color differentiation, intuitively showing the flatness of the template and providing a reliable basis for construction quality assessment and adjustment.

[0111] Example 3:

[0112] like Figure 3 As shown, based on the embodiments, the plane fitting model described in the steps provided by the embodiments of the present invention is based on the Cartesian equation of the plane, also known as the general form equation, whose standard form is: ax + by + cz + d = 0, where (a, b, c) are the unit normal vectors of the plane, satisfying... =1, d is the plane offset;

[0113] Establish an optimization model for the objective function RANSAC:

[0114]

[0115] In the formula, N is the total number of point clouds. δ is the threshold for the distance between interior points, and δ is an indicator function that is 1 when the condition is met and 2 when the condition is not met.

[0116] In one optional implementation, a plane is established, the mathematical expression of which is ax + by + cz + d = 0, such that this plane can contain as many given points M as possible. , This refers to all the points of the template model in the point cloud model, and the distance of these points to the plane does not exceed a set threshold. The threshold is set according to the quality acceptance specifications;

[0117] The normal vector constraint conditions are satisfied as follows:

[0118]

[0119] Establish a deviation quantification model and symbolize vertical deviation:

[0120]

[0121] In the formula, >0 indicates a point Located on the positive side of the plane, <0 indicates a point Located on the negative side of the plane. The final absolute deviation smoothness index dataset is as follows:

[0122] = .

[0123] In one optional implementation, the threshold setting enables the results to display a dynamic two-color scheme, with blue indicating that the condition is met and red indicating that the condition is not met. The specific color assignment function of the mapping model is as follows:

[0124] Color )=

[0125] In the formula, τ is a preset threshold value, which is set according to the quality acceptance specifications, such as 10mm.

[0126] Design a quality evaluation index calculation model to calculate the proportion of qualified point clouds and the maximum deviation value statistics, wherein the qualification rate is calculated as follows:

[0127]

[0128] δ is an indicator function, where 1 represents the condition that is met and 2 represents the condition that is not met. The above formula is used to calculate the proportion of points that meet the condition to the total number of points in the point cloud.

[0129] Maximum deviation statistics:

[0130] =max( ), =min( ).

[0131] The algorithm described above is implemented using the MATLAB software environment.

[0132] First, point cloud data is acquired. Then, using equipment such as 3D laser scanning, the completed template model is scanned and cropped until only the template model remains. Finally, it is exported as a LAS format.

[0133] Furthermore, input conversion code in MATLAB to convert the LAS format into PLY format data for subsequent processing.

[0134] Further input the code for the above formula, set the number of iterations and threshold data, and in this experiment, set the number of iterations to 2000 times, and finally output the image.

[0135] Example 4:

[0136] like Figure 2 As shown in Example 3, this embodiment of the invention provides a building template flatness threshold zoning detection system based on normal vector constraint RANSAC, including a three-dimensional laser scanning device for scanning the building template to obtain high-density point cloud data;

[0137] A data processing device is used to preprocess the point cloud data and fit the reference surface of the template using an improved RANSAC algorithm, wherein the improved RANSAC algorithm ensures the correct orientation of the reference surface based on unit normal vector constraints.

[0138] The display device is used to set deviation thresholds independently according to building codes, divide deviation values ​​into different levels, and display them on the 3D point cloud model by color differentiation.

[0139] Example 5

[0140] Figure 3 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present invention is shown.

[0141] The electronic device may include a central processing unit / microprocessor / main control chip, etc. 4; and a storage medium 5, coupled to the central processing unit / microprocessor / main control chip, etc. 4, and storing computer-executable instructions therein for performing the steps of various methods of embodiments of the present invention when executed by the processor.

[0142] The central processing unit / microprocessor / main control chip, etc., can include, but are not limited to, one or more processors or microprocessors.

[0143] Storage medium 5 may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (e.g., hard disk, floppy disk, solid-state drive, removable disk, CD-ROM, DVD-ROM, Blu-ray disc, etc.).

[0144] In addition, the electronic device may also include (but is not limited to) a data bus 6, an input / output bus / external bus / device bus 7, a display 8, and input / output devices 9 (e.g., keyboard, mouse, speaker, etc.).

[0145] The central processing unit / microprocessor / main control chip, etc. 4 can communicate with external devices (8, 9, etc.) via I / O bus 7 through wired or wireless network (not shown).

[0146] The storage medium 5 may also store at least one computer-executable instruction for performing the steps of various functions and / or methods in the embodiments described herein when the central processing unit / microprocessor / main control chip, etc., 4 is running.

[0147] In one embodiment, the at least one computer-executable instruction may also be compiled into or comprise a software product, wherein one or more computer-executable instructions are executed by a processor to perform the steps of the various functions and / or methods in the embodiments described herein.

[0148] Example 6

[0149] Figure 4 A schematic diagram of a computer-readable storage medium according to an embodiment of the present invention is shown.

[0150] like Figure 4 As shown, the non-transitory computer-readable storage medium 11 stores instructions, such as computer-readable instructions 10. When the computer-readable instructions 10 are executed by a processor, the various methods described above can be performed. The non-transitory computer-readable storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-transitory non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. For example, the non-transitory computer-readable storage medium 11 can be connected to a computing device such as a computer, and then, when the computing device executes the computer-readable instructions 10 stored on the computer-readable storage medium 11, the various methods described above can be performed.

[0151] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0152] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0153] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0154] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for executing all or part of the steps of the methods of the various embodiments of this invention through a computer device (which may be a personal computer, server, or network device, etc.). The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0155] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting the threshold partitioning of building formwork flatness based on normal vector constraint RANSAC, characterized in that, Includes the following steps: Three-dimensional laser scanning is performed on the building template to obtain high-density point cloud data; The collected point cloud data is preprocessed by denoising and downsampling to improve data quality; Using the improved RANSAC algorithm, a reference plane for the template is fitted based on the preprocessed point cloud data, and a unit normal vector is introduced to ensure the correct orientation of the reference plane. Calculate the vertical distance from each point in the point cloud to the reference plane to obtain the deviation value; Based on building codes, deviation thresholds are set independently, and deviation values ​​are divided into different levels and displayed on the 3D point cloud model by color differentiation. The output includes a visualization of a 3D point cloud model and color markers, visually demonstrating the flatness of the template. A plane fitting model is performed based on the Cartesian equation of the plane, also known as the general equation, whose standard form is: ax + by + cz + d = 0, where (a, b, c) are the unit normal vectors of the plane, satisfying... =1, d is the plane offset; Establish an optimization model for the objective function RANSAC: In the formula, N is the total number of point clouds. δ is the threshold for the distance between interior points, and δ is an indicator function that is 1 when the condition is met and 2 when the condition is not met. Construct a plane whose mathematical expression is ax + by + cz + d = 0, such that this plane contains as many given points M as possible. , This refers to all the points of the template model in the point cloud model, and the distance of these points to the plane does not exceed a set threshold. The threshold is set according to the quality acceptance specifications; The normal vector constraint conditions are satisfied as follows: Establish a deviation quantification model and symbolize vertical deviation: In the formula, >0 indicates a point Located on the positive side of the plane, <0 indicates a point The flatness index dataset for the final absolute deviation, located on the negative side of the plane, is as follows: = ； A threshold is set to display the results in a dynamic two-color scheme: blue is used when the condition is met, and red is used when the condition is not met. The specific color assignment function of the mapping model is shown below: Color( )= In the formula, τ is a preset threshold, which is set to 10mm according to the quality acceptance specifications; Design a quality evaluation index calculation model to calculate the proportion of qualified point clouds and the maximum deviation value statistics, wherein the qualification rate is calculated as follows: δ is an indicator function, where 1 represents the condition that is met and 2 represents the condition that is not met. The above formula is used to calculate the proportion of points that meet the condition to the total number of points in the point cloud. Maximum deviation statistics: =max( ) =min( ().

2. The method for detecting the threshold partitioning of building formwork flatness based on normal vector constraint RANSAC as described in claim 1, characterized in that, The steps for performing 3D laser scanning on building templates to obtain high-density point cloud data include: selecting a device with appropriate resolution and scanning range based on the size and complexity of the building template; ensuring the scanner has sufficient power, the storage medium is available, and the device is in good working order; clearly defining the specific location and coverage area of ​​the building template to be scanned; determining multiple scanning positions based on the shape and structure of the template to ensure comprehensive coverage of all surfaces of the template; setting the scanning resolution as needed (higher resolution acquires more detailed data, but increases the data volume); adjusting the scanning frequency according to the dynamics of the template; fixing the scanner on a tripod or other stable support device to ensure the device does not shake during the scanning process; calibrating the device to ensure the accuracy of the scanned data; monitoring the scanning progress and data quality in real time through the device's display screen or a connected computer; and storing the raw point cloud data obtained from the scan in the device or directly transferring it to the computer.

3. The method for detecting the threshold partitioning of building formwork flatness based on normal vector constraint RANSAC as described in claim 1, characterized in that, The steps of using the improved RANSAC algorithm to fit a reference plane of the template based on preprocessed point cloud data and introducing a unit normal vector to ensure the correct orientation of the reference plane include: setting the number of iterations of the RANSAC algorithm according to the data scale and complexity to ensure that the optimal plane is found; defining a distance threshold from a point to the plane to determine whether a point belongs to the fitted plane; randomly selecting three points from the point cloud data as initial samples for the fitted plane; calculating the normal vector and equation of the plane based on these three points; calculating the normal vector according to the fitted plane equation; and normalizing the normal vector to make it a unit normal vector to ensure the consistency of orientation. Based on the structural characteristics of the building template, a reference normal vector is set as the correct direction of the reference plane. The angle between the unit normal vector of the current fitting plane and the reference direction is calculated, and it is determined whether the directions are consistent. If the directions are inconsistent, the direction of the normal vector is adjusted to make it as close as possible to the reference direction. For each point cloud point, its vertical distance to the fitting plane is calculated. According to the set threshold, the points are divided into inner points and outer points. During the iteration process, sample points are randomly selected continuously to fit the plane, and the direction of the normal vector is adjusted. After each iteration, the number of inner points and the overall deviation of the current fitting plane are evaluated, and the optimal fitting result is recorded. When the set number of iterations is reached or the fitting result no longer improves significantly, the iteration is terminated. Based on the iteration results, the plane with the most interior points and the smallest deviation is selected as the reference plane. Output plane parameters: Output the plane equation, normal vector, and point cloud data of the reference plane for subsequent deviation calculation and visualization. The fitted reference plane is superimposed with the original point cloud data for visual inspection of the fitting effect, ensuring that the normal vector direction of the reference plane conforms to the preset reference direction and the deviation is within an acceptable range. Based on the verification results, the algorithm parameters are adjusted, and the fitting results are further optimized by iterating and setting thresholds. Based on the fitted reference plane, the deviation value of each point cloud point is calculated for the evaluation of template flatness. According to the deviation value, the template area is divided into different levels and displayed by color to visually show the flatness status. The improved RANSAC algorithm is integrated into the building formwork inspection system to achieve automated and high-precision flatness detection.

4. The method for detecting the threshold partitioning of building formwork flatness based on normal vector constraint RANSAC as described in claim 1, characterized in that, The steps of independently setting deviation thresholds according to building codes, classifying deviation values ​​into different levels, and displaying them on the 3D point cloud model using color differentiation include: setting a threshold range for each deviation level according to the codes; recording the set threshold ranges for subsequent data processing and adjustment; importing the preprocessed 3D point cloud data into the selected software to ensure that the deviation value of each point cloud point has been calculated and associated with the point cloud data; classifying the deviation value of each point cloud point according to the set threshold ranges; updating the classification results to the point cloud data to ensure the accuracy of the classification information for each point cloud point; and selecting a color scheme according to the deviation level. Color mapping rules are applied to point cloud data to display color distinctions at different deviation levels in real time. The viewpoint and lighting settings of the 3D point cloud model are optimized to ensure clear and visible color distinctions. A portion of point cloud points are randomly selected, and their deviation values ​​are manually checked to ensure consistency with the classification results, thus ensuring classification accuracy. Based on the actual inspection results, the deviation threshold and color scheme are adjusted to improve classification accuracy and visualization effects. The visualization results of the 3D point cloud model and color labels are saved as images or videos for subsequent reporting and presentation. Based on the classification results, a detailed deviation analysis report is generated, summarizing the flatness of the template and proposing construction adjustment suggestions.

5. A RANSAC-based threshold zoning detection system for building formwork flatness based on normal vector constraint, as described in any one of claims 1 to 4, characterized in that, include: A 3D laser scanning device is used to scan building templates to obtain high-density point cloud data; A data processing device is used to preprocess the point cloud data and fit the reference surface of the template using an improved RANSAC algorithm, wherein the improved RANSAC algorithm ensures the correct orientation of the reference surface based on unit normal vector constraints. The display device is used to set deviation thresholds independently according to building codes, divide deviation values ​​into different levels, and display them on the 3D point cloud model by color differentiation.

6. An electronic device, comprising: At least one memory stores computer-executable instructions non-transiently; At least one processor, configured to run the computer-executable instructions, The computer-executable instructions are implemented by the processor at runtime according to any one of claims 1-4, which describes the building template flatness threshold partitioning detection method based on normal vector constraint RANSAC.

7. A computer-readable storage medium, wherein, The computer-readable storage medium stores computer-executable instructions, which, when executed by at least one processor, implement the building template flatness threshold partitioning detection method based on normal vector constraint RANSAC according to any one of claims 1-4.

Images