A 3D point cloud data intelligent processing method and processing device

Abstract

The present invention relates to the field of data processing, and in particular to a method and device for intelligent processing of 3D point cloud data. The method comprises the following steps: obtaining initial image data to be processed; the initial image data includes a target object to be analyzed in an industrial monitoring scene; performing three-dimensional splicing on the initial image data to obtain a spliced image corresponding to the target object; performing virtual modeling based on the spliced image to obtain an initial virtual model of the target object; optimizing the spatial morphology of the initial virtual model through an adaptive optimization model to obtain an optimized virtual model; extracting the three-dimensional point cloud data of the target object from the optimized virtual model to complete the intelligent extraction of the three-dimensional point cloud data. The method can realize automated three-dimensional image analysis and extraction of target objects in industrial monitoring scenes, improve the image processing accuracy and efficiency of industrial monitoring, and provide users with more comprehensive and timely automated image processing services.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a method and device for intelligently processing 3D point cloud data. Background Art

[0002] In today's digital age, 3D point cloud data processing technology plays a key role in many fields. However, the amount of 3D point cloud data is too large, making it difficult for companies to access and use it after collection, especially when the point cloud data of a workshop is retrieved online and then manually evaluated.

[0003] Furthermore, during the manual evaluation process, differences in evaluators' experience, knowledge, and subjective judgment can lead to inaccurate feature extraction. This can result in different results when evaluating the same company's workshop data. Furthermore, even when the same evaluator evaluates the same company's workshop data at different times, inconsistent results can occur due to factors such as personal state and mood. This makes the evaluation process lack repeatability and cannot guarantee the reliability and stability of the results. For example, in analyzing cloud data of main welds in an automotive company's workshop, manual evaluation makes it difficult to determine the quality of the main welds in a timely and accurate manner based on the data.

[0004] Furthermore, manual assessments often focus on extracting and evaluating a company's current data, lacking effective early warning mechanisms for future risks. Evaluators primarily analyze and judge based on historical data and current information, making it difficult to predict potential risks within a company's shop floor. Furthermore, manual assessments lack real-time monitoring and dynamic analysis of risk factors, making it impossible to detect and respond to changes in risks promptly.

[0005] Therefore, there is an urgent need for a new solution to improve the quality of credit assessment, assist in improving the efficiency of credit assessment, and reduce the risk of credit assessment. Summary of the Invention

[0006] In response to the technical problems existing in the prior art, the present invention provides a 3D point cloud data intelligent processing method and processing device for realizing automated three-dimensional image analysis and extraction of target objects in industrial monitoring scenarios, improving the image processing accuracy and processing efficiency of industrial monitoring, and providing users with more comprehensive and timely automated three-dimensional image processing services.

[0007] In a first aspect, an embodiment of the present application provides a method for intelligently processing 3D point cloud data, comprising:

[0008] Acquire initial image data to be processed; the initial image data includes a target object to be analyzed in an industrial monitoring scene;

[0009] Performing three-dimensional stitching on the initial image data to obtain a stitched image corresponding to the target object;

[0010] Perform virtual modeling based on the stitched image to obtain an initial virtual model of the target object; the initial virtual model is a virtual three-dimensional model of the target object in the stitched image space;

[0011] The initial virtual model is optimized in spatial form by an adaptive optimization model to obtain an optimized virtual model; the optimized virtual model is a virtual three-dimensional model of the target object in the image optimization space;

[0012] The three-dimensional point cloud data of the target object is extracted from the optimized virtual model to complete the intelligent extraction of the three-dimensional point cloud data.

[0013] In a second aspect, an embodiment of the present application provides a 3D point cloud data intelligent processing system, which includes the following units:

[0014] An acquisition unit, configured to acquire initial image data to be processed; the initial image data includes a target object to be analyzed in an industrial monitoring scene;

[0015] a stitching unit, configured to perform three-dimensional stitching on the initial image data to obtain a stitched image corresponding to the target object;

[0016] A modeling unit, configured to perform virtual modeling based on the stitched image to obtain an initial virtual model of the target object; the initial virtual model is a virtual three-dimensional model of the target object in the stitched image space;

[0017] an optimization unit, configured to optimize the spatial form of the initial virtual model using an adaptive optimization model to obtain an optimized virtual model; the optimized virtual model is a virtual three-dimensional model of the target object in the image optimization space;

[0018] The extraction unit is used to extract the three-dimensional point cloud data of the target object from the optimized virtual model to complete the intelligent extraction of the three-dimensional point cloud data.

[0019] In a third aspect, an embodiment of the present application provides an electronic device, comprising:

[0020] at least one processor, memory, and input-output unit;

[0021] The memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the 3D point cloud data intelligent processing method of the first aspect.

[0022] In a fourth aspect, a computer-readable storage medium is provided, which includes instructions. When the instructions are executed on a computer, the computer executes the 3D point cloud data intelligent processing method of the first aspect.

[0023] The beneficial effects of the present invention are: providing a 3D point cloud data intelligent processing method and processing device. In this technical solution, the initial image data to be processed is obtained; the initial image data contains the target object to be analyzed in the industrial monitoring scene; the initial image data is three-dimensionally spliced to obtain a spliced image corresponding to the target object; virtual modeling is performed based on the spliced image to obtain an initial virtual model of the target object; the initial virtual model is a virtual three-dimensional model of the target object in the spliced image space; the initial virtual model is spatially optimized by an adaptive optimization model to obtain an optimized virtual model; the optimized virtual model is a virtual three-dimensional model of the target object in the image optimization space; the three-dimensional point cloud data of the target object is extracted from the optimized virtual model to complete the intelligent extraction of the three-dimensional point cloud data. This technical solution can realize the automated three-dimensional image analysis and extraction of target objects in industrial monitoring scenes, improve the image processing accuracy and processing efficiency of industrial monitoring, and provide users with more comprehensive and timely automated image processing services. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a flow chart of a method for intelligently processing 3D point cloud data according to an embodiment of the present application;

[0025] Figure 2 This is a structural diagram of a 3D point cloud data intelligent processing system according to an embodiment of the present application;

[0026] Figure 3 This is a schematic structural diagram of an electronic device according to an embodiment of the present application;

[0027] Figure 4 It is a structural diagram of a medium device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0029] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the described features. In the description of this application, "plurality" means two or more, unless otherwise specifically specified.

[0030] In the description of this application, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art will recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in this application.

[0031] The embodiments of the present application provide a method and a device for intelligently processing 3D point cloud data.

[0032] In an embodiment of the present application, initial image data to be processed is obtained; the initial image data includes a target object to be analyzed in an industrial monitoring scene; the initial image data is three-dimensionally spliced to obtain a spliced image corresponding to the target object; virtual modeling is performed based on the spliced image to obtain an initial virtual model of the target object; the initial virtual model is a virtual three-dimensional model of the target object in the spliced image space; the initial virtual model is spatially optimized through an adaptive optimization model to obtain an optimized virtual model; the optimized virtual model is a virtual three-dimensional model of the target object in the image optimization space; and three-dimensional point cloud data of the target object is extracted from the optimized virtual model to complete the intelligent extraction of three-dimensional point cloud data.

[0033] The embodiments of the present application can realize automated three-dimensional image analysis and extraction of target objects in industrial monitoring scenarios, improve the image processing accuracy and efficiency of industrial monitoring, and provide users with more comprehensive and timely automated image processing services.

[0034] The 3D point cloud data intelligent processing solutions provided in the embodiments of this application can also be executed by electronic devices, which can be servers, server clusters, or cloud servers. These electronic devices can also be terminal devices such as mobile phones, computers, tablets, wearable devices, or dedicated devices (such as dedicated terminal devices equipped with 3D point cloud data intelligent processing systems). These electronic devices can also be equipped with the chips described in the above embodiments. Alternatively, these electronic devices can also be installed with service programs for executing the 3D point cloud data intelligent processing solutions.

[0035] Figure 1 A schematic diagram of a 3D point cloud data intelligent processing method provided in an embodiment of the present application is shown as follows: Figure 1 As shown, the method includes the following steps:

[0036] 101. Obtaining initial image data to be processed;

[0037] 102. Perform three-dimensional stitching on the initial image data to obtain a stitched image corresponding to the target object;

[0038] 103. Perform virtual modeling based on the spliced image to obtain an initial virtual model of the target object;

[0039] 104. Optimizing the spatial form of the initial virtual model using an adaptive optimization model to obtain an optimized virtual model;

[0040] 105. Extract three-dimensional point cloud data of the target object from the optimized virtual model to complete intelligent extraction of three-dimensional point cloud data.

[0041] In an embodiment of the present application, the initial image data includes a target object to be analyzed in an industrial monitoring scene.

[0042] Take mechanical equipment, for example. In industrial production, various types of machinery are common monitoring targets. For example, components such as the spindle, tool holder, and guide rails of machine tools. Power equipment such as engines, turbines, and compressors, with their complex internal structures and moving parts, require monitoring to ensure proper operation and optimized performance. Initial image data from these devices can be used to detect defects such as wear, deformation, and cracks, as well as monitor equipment operating status and conduct fault diagnosis.

[0043] The target objects can be industrial parts, including various standard and custom parts such as bolts, nuts, gears, bearings, and molds. By processing and analyzing the initial image data of these parts, their dimensional accuracy, surface quality, and internal defects can be detected to ensure that the quality of the parts meets production requirements and avoid equipment failures and production accidents caused by component problems.

[0044] Target objects can be pipelines and containers. For example, pipelines and containers widely used in industries such as chemical, petroleum, and power generation are also important monitoring targets. Pipeline corrosion, blockages, and leaks, as well as container deformation, cracks, and weld quality issues can all be detected through analysis of the initial image data. For example, by processing the 3D point cloud data of the pipeline interior, it is possible to detect corrosion and sediment distribution on the pipeline's inner wall.

[0045] The target object can be an industrial building structure, such as a factory building's frame, walls, and roof. Monitoring industrial building structures can ensure their safety and stability, and promptly detect cracks, deformations, and other problems. The initial image data can be used to create a 3D model of the building structure, enabling more intuitive observation and analysis of its condition.

[0046] Furthermore, using visual sensors such as industrial cameras and webcams is a common method for collecting initial image data. These sensors can be installed in fixed locations or on mobile devices to capture the target object from multiple angles and directions. On automated production lines, multiple industrial cameras can be installed for real-time product monitoring. For monitoring large-scale equipment, drones equipped with cameras can be used to capture all-around images of the equipment.

[0047] Laser scanning devices such as LiDAR can quickly acquire 3D point cloud data of target objects and also generate corresponding image data. Laser scanning offers advantages such as high precision, high speed, and non-contact performance, making it suitable for monitoring complex and large objects. In industrial pipeline monitoring, laser scanning can accurately capture the pipeline's 3D shape and dimensions.

[0048] Structured light scanners project a specific structured light pattern onto an object and capture three-dimensional information based on changes in the reflected light. This method is suitable for monitoring parts requiring high precision, enabling detailed texture and shape information to be obtained from the object's surface.

[0049] Due to the diverse acquisition methods used, initial image data may come from different sensor types with varying formats and characteristics. Image data acquired by vision sensors is typically 2D color images, while data from laser scanning and structured light scanning includes 3D point cloud information and intensity data. This multi-source data requires effective fusion and processing to fully leverage the strengths of each.

[0050] In industrial monitoring scenarios, to fully and accurately reflect the status of target objects, it is often necessary to collect large amounts of image data. For large industrial facilities or long-term monitoring tasks, the amount of data can be enormous. This requires efficient data processing and storage technologies to ensure smooth data management and analysis.

[0051] In some industrial monitoring applications, such as real-time monitoring of production processes, it is necessary to acquire and process initial image data in a timely manner to detect problems and take appropriate measures. Therefore, the acquisition and processing of initial image data must be real-time to meet the needs of industrial production.

[0052] Specifically, for industrial monitoring scenarios, initial image data containing the target object is obtained and three-dimensional stitching is performed, and a complete stitched image can be constructed from images collected from multiple angles and different positions. Compared with data collection from a single perspective, this can avoid the loss of some information about the monitored object, comprehensively cover all parts of the target object, and provide a rich and complete data foundation for subsequent analysis, ensuring that details such as key components and complex structures of industrial equipment can be fully captured. In the three-dimensional stitching process, image matching, alignment and other technologies can be used to accurately integrate the image information of each part. When monitoring industrial pipelines, the images of interfaces, welds and other parts of the pipeline from different shooting angles can be accurately connected, reducing errors in information such as position and size due to perspective deviation, improving data accuracy, and providing a reliable basis for subsequent virtual modeling and analysis.

[0053] In the embodiments of this application, the initial virtual model is a virtual 3D model of the target object in the stitched image space. This virtual 3D model is constructed based on a spliced image obtained by three-dimensionally stitching initial image data containing the target object in the industrial monitoring scene. This is equivalent to initially presenting the target object in a 3D form in virtual space using the stitched image as the base material, providing an initial morphological framework for subsequent processing and analysis.

[0054] It provides a preliminary virtual three-dimensional form for the target object, so that the target object originally in the two-dimensional image can be observed and understood in three-dimensional form, making it convenient for operators to view the overall structure and general outline of the target object from different angles, and helping to have a comprehensive preliminary understanding of the target object.

[0055] As the basic data model for further processing and optimization, it provides input for the adaptive optimization model. Subsequent operations such as spatial morphology optimization are performed on the basis of this model. Its quality and accuracy will affect the effect and quality of the final 3D point cloud data extraction.

[0056] In industrial monitoring scenarios, the actual situation can be very complex, with various interference factors and complex backgrounds. The initial virtual model, through preliminary modeling of the target object, can separate the target object from the complex scene and present it in a relatively concise and clear 3D model, facilitating subsequent targeted analysis and processing.

[0057] In the embodiments of the present application, the optimized virtual model is a virtual three-dimensional model of the target object in the image optimization space. The optimized virtual model is obtained by optimizing the spatial morphology of the initial virtual model using an adaptive optimization model. During the construction process, the adaptive optimization model adjusts the positions of various points in the initial virtual model based on the geometric characteristics of the target object and pre-set geometric constraints. It then uses a surface fitting algorithm to smooth the surface and further adjusts the target object based on its proportional changes and dimensional relationships in various dimensions to ultimately obtain the optimized virtual model.

[0058] Thus, through a series of optimization operations, the model more accurately reflects the true morphology and characteristics of the target object. For example, adjustments to position points and surface smoothing make the model's surface smoother and more natural, more consistent with the target object's actual physical form, improving the model's visual and geometric accuracy. Factors such as the target object's proportional variations and dimensional relationships across various dimensions are taken into account, making the optimized model more adaptable to different observation angles and practical application scenarios. In industrial monitoring, different monitoring tasks may require observing the target object from different angles and scales. The optimized virtual model maintains good performance in all situations, supporting accurate analysis and decision-making. The optimized model provides a better foundation for extracting 3D point cloud data. Due to its more accurate and stable morphology, the extracted 3D point cloud data is of higher quality, with less noise and error, facilitating subsequent analysis and applications based on 3D point cloud data, such as object recognition, defect detection, and dimensional measurement.

[0059] Specifically, an initial virtual model constructed from the stitched images reflects the target object's three-dimensional form within the stitched image space. After optimizing geometric features, surface smoothness, and scale using an adaptive optimization model, the optimized virtual model more closely resembles the actual physical form of the industrial target object. When modeling industrial parts, the optimized model accurately captures subtle surface textures and complex surface transitions, enhancing model fidelity and facilitating a more realistic simulation of the object's actual state during industrial production.

[0060] Spatial morphology optimization makes the model more suitable for industrial monitoring data analysis. When analyzing the operating status of industrial equipment, optimizing the virtual model's proper shape allows the analysis algorithm to better extract characteristics such as deformation and displacement of key equipment parts, providing a more suitable model for fault diagnosis and performance evaluation, and improving the effectiveness and reliability of the analysis results.

[0061] Furthermore, 3D point cloud data is extracted from the optimized virtual model, completing the intelligent extraction process without extensive manual intervention, significantly saving time and costs. In large-scale industrial facility monitoring projects, point cloud data can be quickly extracted from numerous equipment models, improving data processing efficiency and enabling monitoring to keep pace with industrial production and identify potential problems promptly.

[0062] Finally, the 3D point cloud data extracted after these multiple processing steps is based on a high-quality, optimized virtual model, resulting in improved data integrity, accuracy, and consistency. In industrial equipment quality inspection, high-quality point cloud data can accurately reflect surface defects, dimensional deviations, and other issues, reducing the probability of misjudgments and missed detections, improving the quality and accuracy of industrial monitoring, and ensuring safe and stable industrial production.

[0063] For example, in step 101, initial image data to be processed is acquired. Appropriate image acquisition equipment should be selected based on the characteristics of the industrial monitoring scenario and target object. For close-range, high-precision monitoring of small components, a high-resolution industrial camera can be used. For large-scale scenes or objects with complex shapes, lidar can obtain more comprehensive three-dimensional information. For monitoring dynamic targets, a high-speed camera is more suitable. Plan the acquisition location, angle, and quantity. To fully capture information about the target object, capture images from multiple locations and angles to ensure that no part is missed. For example, when monitoring a large piece of industrial equipment, multiple acquisition points should be set up around the equipment, capturing images from different angles, such as the top, side, and bottom. Consider the impact of the acquisition environment, such as lighting conditions and background interference. During the acquisition process, factors that affect image quality, such as direct sunlight and shadows, should be avoided as much as possible. Fill-in lighting can be used to improve lighting conditions. Operate the acquisition equipment to acquire images according to the predetermined acquisition plan. During the acquisition process, ensure the stability and accuracy of the equipment to avoid image blur or positional deviation caused by jitter or movement.

[0064] For example, in step 102, the initial image data is three-dimensionally stitched to obtain a stitched image corresponding to the target object. Feature extraction is performed on each initial image. Common features include corners, edges, textures, etc. These features can assist in the subsequent image matching and stitching process. For example, the SIFT (Scale-Invariant Feature Transform) or SURF (Speeded Up Robust Features) algorithm is used to extract feature points in the image. Matching feature points are searched between different images. By comparing the descriptors of the feature points, it is determined which feature points represent the same physical point in different images. The nearest neighbor matching algorithm or the RANSAC (Random Sample Consensus) algorithm can be used to improve the accuracy and reliability of the matching.

[0065] Next, based on the matched feature points, the relative position and pose relationship between the different images is calculated. These images are then spatially transformed to align them in three-dimensional space. Finally, the aligned images are fused to produce a stitched image of the target object. During the fusion process, overlapping areas between the images must be carefully processed to avoid stitching artifacts and brightness differences.

[0066] For example, in step 103, virtual modeling is performed based on the stitched images to obtain an initial virtual model of the target object. Three-dimensional point cloud data of the target object is extracted from the stitched images. Depth information for each pixel in the image can be calculated using methods such as stereo vision and structured light to obtain the corresponding three-dimensional point coordinates. Based on the generated point cloud data, surface reconstruction is performed to construct a three-dimensional surface model of the target object. Commonly used surface reconstruction algorithms include Poisson reconstruction and moving least squares. These algorithms can fit a smooth surface based on the distribution of the point cloud, making the model more similar to the true shape of the target object.

[0067] Optimize the reconstructed model to remove noise points, fill holes, smooth the surface, etc. You can use filtering algorithms to remove noise, interpolation algorithms to fill holes, and surface fitting algorithms to smooth the surface.

[0068] In the above or following embodiments, in step 104, the initial virtual model is optimized for spatial form by using the adaptive optimization model to obtain the optimized virtual model, which can be implemented as follows:

[0069] Through the adaptive optimization model, the positions of the various position points in the initial virtual model are adjusted according to the geometric features of the target object and the pre-set geometric constraints to obtain a first optimization model; the first optimization model is smoothed using a surface fitting algorithm to obtain a second optimization model; and the second optimization model is adjusted according to the proportional changes and size relationships of the target object in various dimensions to obtain the optimized virtual model.

[0070] Step 1: Adjust the position points according to the geometric features and constraints to obtain the first optimization model.

[0071] Specifically, the initial virtual model of the target object is analyzed to extract its key geometric features, such as point density, curvature, and normal vectors in the point cloud data. These features can reflect information such as the surface shape and structure of the target object. A series of geometric constraints are pre-set based on the needs of the industrial monitoring scenario and the actual situation of the target object. For example, for a mechanical part, it may be stipulated that certain planes should remain parallel or perpendicular, and the diameters of certain holes should be within a specific range. Based on the extracted geometric features and the preset geometric constraints, the positions of the various points in the initial virtual model are adjusted. This can be achieved by solving an optimization problem, such as minimizing a certain objective function, which usually takes into account factors such as the distance between points and the distance from points to the constraint plane. Through iterative calculations, the positions of the points are continuously adjusted so that the model meets the geometric constraints.

[0072] Therefore, by adjusting the position points, any positional deviations in the initial virtual model can be corrected, making the model more consistent with the actual geometry of the target object. For example, in the modeling of industrial parts, ensuring the accuracy of the relative positions and dimensional relationships of each part improves the model's fidelity to the real object. Models that meet geometric constraints are more stable in subsequent processing and analysis. For example, when conducting mechanical analysis or motion simulation, an accurate geometric model provides a more reliable foundation, reducing deviations in analytical results caused by model errors.

[0073] Step 2: Use the surface fitting algorithm to smooth the surface and obtain the second optimization model.

[0074] Specifically, based on the characteristics of the first optimization model and application requirements, an appropriate surface fitting algorithm, such as least squares surface fitting or spline surface fitting, is selected. These algorithms can fit a smooth surface based on the point cloud data in the model to approximate the surface of the target object. The point cloud data in the first optimization model is input into the selected surface fitting algorithm, and the parameters of the fitted surface are calculated. During this process, some parameter adjustments and optimizations may be required to ensure the quality of the fitted surface. Based on the parameters of the fitted surface, the points in the first optimization model are adjusted to make the model surface smoother. This can be achieved by projecting the points onto the fitted surface or interpolating it.

[0075] Surface smoothing eliminates jagged edges and discontinuities on the model's surface, resulting in a smoother, more natural appearance. This is crucial for industrial products with demanding appearance quality, such as automotive parts and aircraft engine blades. Smooth surface models can reduce the impact of noise and errors during subsequent analysis and processing, improving data quality. For example, in 3D measurement or reverse engineering, smooth surface models can more accurately reflect the actual size and shape of the target object.

[0076] Step 3: Adjust the position according to the proportion change and size relationship to obtain the optimized virtual model.

[0077] Specifically, the target object's proportional changes and dimensional relationships in various dimensions are analyzed. This can be done by comparing with known standard models or design drawings, or by determining the relationship based on actual measurement data. Based on the analyzed proportional changes and dimensional relationships, the target object's contour change trends in the second optimized model are predicted. This prediction can be achieved by establishing a mathematical model or using a machine learning algorithm. Based on the predicted contour change trends, the spatial position points in various dimensions of the second optimized model are adjusted. This can be achieved by scaling, translating, and other operations on the coordinates of each point, so that the model's proportions and dimensions conform to the actual conditions of the target object.

[0078] By adjusting the position, the optimized virtual model's proportions and dimensions are ensured to be consistent with the actual target object. This is crucial for applications such as dimensional measurement and quality control in industrial monitoring, enabling accurate judgment of whether the target object meets design requirements. Models that conform to realistic proportions and dimensional relationships are more practical in real-world applications. For example, when conducting virtual assembly or simulating production processes, accurate models can better reflect actual conditions and provide a more reliable basis for decision-making.

[0079] It is understandable that in the above steps, we first need to have a deep understanding and analysis of the geometric structure of the target object. For a three-dimensional target object, we need to consider its 、 、 Observe how the proportional relationship between the length, width, height and other dimensions of the target object changes under different conditions (such as different working conditions, different environmental factors, etc.). For example, in some industrial production processes, due to thermal expansion and contraction, the target object The length of the dimension may change according to a certain proportional coefficient, and 、 The proportion of changes in dimensions may be different. Clarify the relationship between the sizes of various parts of the target object in different dimensions. For example, a mechanical part may have specific holes and protrusion structures. The sizes of these structures in different dimensions are mutually constrained. It is necessary to analyze the specific numerical relationship between them and the changing rules of this relationship under different circumstances. Then, for all position points in the second optimization model, their positions in various dimensions are adjusted in turn according to the adjustment strategies and methods determined based on the above-mentioned proportional changes and dimensional relationships. After adjusting all position points, the original second optimization model is transformed into an optimized virtual model. This optimized virtual model can more accurately reflect the spatial form of the target object under the current actual situation, and better conform to the actual characteristics of the target object such as proportional changes and dimensional relationships in various dimensions, thereby providing a more accurate model basis for subsequent analysis, monitoring and other work.

[0080] Further optionally, in the above steps, the position of the second optimized model is adjusted according to the proportional changes and size relationships of the target object in various dimensions to obtain the optimized virtual model, which can be implemented as follows:

[0081] According to the proportional changes and size relationships of the target object in various dimensions, the outer contour change trend coefficient of the target object in the second optimization model is predicted; based on the predicted outer contour change trend coefficient, the spatial position points in various dimensions in the second optimization model are anomaly identified; the identified abnormal spatial points are adjusted to obtain the optimized virtual model.

[0082] First, various data on the target object under different conditions must be collected, including but not limited to historical monitoring data, dimensional specifications in design drawings, and relevant process parameters. For example, for an industrial equipment component, its actual dimensional measurement data under different operating environments such as temperature and pressure should be collected, as well as the standard dimensions and tolerance ranges specified during the design.

[0083] Based on the collected data, analyze the target object in various dimensions ( 、 、 The relationship between proportional changes and related factors (such as temperature and time) can be determined through mathematical modeling. For example, a linear regression model can be established to describe the functional relationship between the proportional change in a component's length along a certain dimension and temperature as the temperature changes.

[0084] Clarify the dimensional relationships between the various parts of the target object, such as the mating dimensions and relative positional dimensions between components. These dimensional relationships may remain stable or change under different operating conditions. Analyze the changing patterns of dimensional relationships and determine the constraints between the dimensions under different conditions.

[0085] Taking into account the proportional change model and the dimensional relationship, the change trend coefficient of the target object's outline in the second optimization model is predicted. This coefficient can be a vector containing the change trend information in each dimension. For example, for a three-dimensional target object, the change trend coefficients are mapped to 、 、 The coefficient of trend of shape profile change in dimension.

[0086] Then, based on the predicted contour change trend coefficient, combined with the design standards of the target object and the experience in actual application, a normal range is set for the spatial position points in each dimension in the second optimization model. This normal range can be expressed by a mathematical formula, for example, In terms of dimension, for a certain point , its normal coordinate range can be expressed as ,in and It is calculated based on the change trend coefficient and other related factors.

[0087] For each spatial position point in the second optimization model = , calculate the deviation between its actual coordinate value in each dimension and the expected coordinate value predicted based on the change trend coefficient. The deviation value in the dimension is the point predicted based on the change trend coefficient exist The expected coordinate value along the dimension.

[0088] Compare the calculated deviation value with the set normal range. If the deviation value exceeds the normal range, the location point is judged as an abnormal point. For example, if Greater than and The difference between the two is considered to be exist By comprehensively judging the deviations in each dimension, we can determine whether each location point is an outlier.

[0089] Then, for the identified abnormal spatial points, an adjustment strategy is determined based on their deviation and the actual needs of the target object. If the anomaly is caused by a change in proportion, adjustments can be made based on the predicted proportional change trend; if the anomaly is caused by a dimensional relationship that does not meet the requirements, adjustments are made based on the correct dimensional relationship.

[0090] Adjust the coordinates of the abnormal space points in each dimension. Abnormal points in dimension , if its actual coordinate value Greater than the expected maximum , then adjust its coordinate value to ; If its actual coordinate value Less than the expected minimum , then adjust to By adjusting all abnormal spatial points, the outer contour of the second optimized model is made more consistent with the actual situation of the target object, thereby obtaining an optimized virtual model.

[0091] After completing the adjustment of the abnormal spatial points, the optimized virtual model is verified to check whether it meets the design requirements and actual application needs of the target object. If there are still some non-compliance issues, further adjustments and optimizations can be made until a satisfactory optimized virtual model is obtained.

[0092] For example, in the above steps, based on the predicted contour change trend coefficient, abnormality identification of spatial position points in each dimension in the second optimization model can be implemented as follows:

[0093] For the spatial position points in the second optimization model , determine the spatial location point The average distance between the adjacent spatial position points; the product between the contour change trend coefficient and the average distance and the spatial position point In the Add the coordinate reference values in each dimension to get the spatial position point In the dimensions; after solving the expected coordinate values of each spatial position point in the second optimization model in the corresponding dimension, calculate the abnormal parameters corresponding to each spatial position point according to the expected coordinate values of each spatial position point and the real-time coordinate values of each spatial position point in the second optimization model; compare the abnormal parameters of each spatial position point with the dynamic threshold to screen out the abnormal spatial points.

[0094] Through the above steps, the spatial position points in the second optimization model can be effectively identified as abnormal based on the predicted contour change trend coefficient, providing a basis for subsequent adjustment of abnormal points and further optimization of the model.

[0095] In the above steps, the spatial position point in the second optimization model The calculation process of the corresponding abnormal parameters is expressed as the following formula:

[0096] ;

[0097] in, Represents a spatial location point Corresponding abnormal parameters, weight factors To adjust the The contribution of dimensions in abnormal judgment, Represents a spatial location point In the The actual coordinate value in the dimension, Represents a spatial location point In the Expected coordinate values in dimension, 、 、 express In the The projected coordinate value on the dimension, Indicates that all spatial position points in the second optimization model are The average coordinate value in the dimension, is the number of spatial position points in the second optimization model, For indicating that each spatial position point in the second optimization model is The average fluctuation range in the dimension.

[0098] First, the spatial position point in the formula exist 、 、 By comprehensively calculating and summing the deviations across three dimensions, we can fully reflect the overall degree of anomaly at a point in three-dimensional space. In industrial monitoring scenarios, the spatial morphology of target objects often varies across multiple dimensions. This comprehensive calculation method avoids considering only a single dimension while ignoring the impact of changes in other dimensions on anomaly judgment, making anomaly identification more accurate and reliable. For example, for a complex mechanical part, dimensional changes in different dimensions can affect its function and performance. Integrating multi-dimensional information can more comprehensively capture anomalies caused by these changes.

[0099] Second, the expected coordinates are predicted based on factors such as the contour change trend coefficient, reflecting the target object's normal position. The greater the deviation between the actual and expected coordinates, the more likely the point is an outlier. This calculation method effectively captures unusual changes in spatial locations, providing an important basis for anomaly identification.

[0100] Third, by comparing the actual coordinates with the average coordinates and combining them with the average fluctuation range, we can determine whether the coordinate variation of the point in the dimension exceeds the normal fluctuation range. In industrial production, due to various factors, the coordinates of spatial locations will fluctuate to a certain extent. However, if the coordinate variation of a point exceeds the average fluctuation range, it is likely an outlier. This approach of considering the average fluctuation range can reduce misjudgments caused by normal fluctuations and improve the accuracy of anomaly identification.

[0101] This anomaly parameter calculation method is adaptable to diverse data distributions and industrial monitoring scenarios. Whether data points are relatively evenly distributed or locally dense or sparse, it effectively identifies anomalies by comprehensively considering factors such as multi-dimensional information, weighting factors, deviations between actual and expected coordinates, and average fluctuation range. Furthermore, by rationally adjusting weighting factors and other parameters for different types of target objects and monitoring tasks, the anomaly parameter calculation method can be better adapted to specific needs, demonstrating its versatility and flexibility.

[0102] In summary, the above abnormal parameter calculation process can more accurately and effectively identify abnormal spatial points in the second optimization model by integrating multiple factors, providing a reliable basis for subsequent model optimization and industrial monitoring analysis.

[0103] For example, based on the above formula, in the above steps, comparing the abnormal parameters of each spatial position point with the dynamic threshold to screen out the abnormal spatial point can be implemented as follows:

[0104] Based on the preset adjustment strategy, the dynamic threshold corresponding to each spatial position point is obtained in real time; if the abnormal parameter is greater than the corresponding dynamic threshold, the spatial position point corresponding to the current abnormal parameter is determined to be an abnormal spatial point; if the abnormal parameter is not greater than the corresponding dynamic threshold, the spatial position point corresponding to the current abnormal parameter is determined to be a normal spatial point.

[0105] The following is a description of the specific implementation of the preset adjustment strategy and the technical effects of the above steps:

[0106] For example, we can collect a large amount of historical data on abnormal parameters at spatial locations and analyze their distribution, such as calculating statistics like the mean and standard deviation. Based on this statistical information, we can determine a dynamic threshold. For example, we can set the dynamic threshold to be the mean plus a multiple of the standard deviation, ensuring that most normal data falls within the threshold and that abnormal data can be effectively identified. As new data is added, these statistics are continuously updated, enabling real-time adjustment of the dynamic threshold.

[0107] For example, if the monitoring environment changes, such as changes in the operating conditions of production equipment or adjustments to the material or process of the monitored object, the dynamic threshold can be adjusted accordingly. For example, when the operating speed of production equipment increases, the fluctuation of spatial position points may increase. In this case, the dynamic threshold can be appropriately raised to avoid misinterpreting normal fluctuations as abnormalities. By establishing a mapping relationship between environmental parameters and dynamic thresholds, the threshold can be adjusted based on the real-time monitored environmental parameters.

[0108] Alternatively, machine learning classification algorithms, such as support vector machines and decision trees, can be used to train known data on normal and abnormal spatial locations to build a classification model. The threshold can then be dynamically adjusted based on the model's output. For example, when the model's prediction accuracy is high, the current threshold setting is reasonable and can be maintained or fine-tuned. When the model makes a high number of false positives, the threshold can be adjusted accordingly to continuously optimize model performance. Clustering algorithms can also be used to cluster the abnormal parameters of spatial locations and determine thresholds for different categories based on the clustering results.

[0109] Furthermore, the system integrates the expertise and practical experience of domain experts to provide recommendations for dynamic threshold settings in different situations. For example, based on previous experience with similar projects, experts understand the range of abnormal parameters at spatial locations considered normal under certain conditions, and the range beyond which they are considered abnormal. By combining this experience with the results of data statistics and algorithmic analysis, more reasonable preset adjustment strategies can be developed, enabling real-time adjustments to dynamic thresholds.

[0110] Therefore, by comparing anomaly parameters with dynamic thresholds, it is possible to clearly determine whether a spatial location is abnormal and accurately screen out abnormal spatial points, providing precise information for subsequent model optimization and problem solving, avoiding misjudgment that could lead to incorrect operations or overlooking true anomalies. The dynamic threshold settings and preset adjustment strategies enable the system to adapt to various dynamic changes, whether to the monitored object itself or to changes in the monitored environment, ensuring the effectiveness and accuracy of anomaly identification and improving system stability and reliability. Preset adjustment strategies enable the system to automatically adjust the dynamic thresholds based on different situations, eliminating the need for frequent manual intervention. This improves the system's adaptability and intelligence, reduces labor costs, and mitigates potential errors and mistakes caused by human factors. After accurately screening out abnormal spatial points, targeted processing can be performed to further optimize the virtual model, ensuring that the model more accurately reflects the actual conditions of the target object, improving the model's accuracy and credibility, and providing more reliable support for subsequent analysis and decision-making.

[0111] In practical applications, timely detection of abnormal spatial points helps to discover potential problems and risks in advance and take corresponding measures to deal with them, thereby ensuring the safe and stable operation of the entire system and avoiding adverse consequences such as equipment failure and production accidents caused by failure to detect abnormalities in time. It has important practical significance and economic value.

[0112] Further optionally, in the above steps, using a surface fitting algorithm to perform surface smoothing processing on the first optimization model to obtain a second optimization model can be implemented as follows:

[0113] The first optimization model is processed by minimizing the curvature change; the first optimization model is processed by surface fitting through an energy function; the curvature minimization optimization result and the surface fitting result are fused to obtain the second optimization model.

[0114] Specifically, first, analyze each part of the surface of the first optimized model. For each small area of the model surface, calculate its curvature. The curvature reflects the degree of bending of the surface in that area. Then, determine a goal, which is to make the curvature change of the entire model surface as small as possible. To achieve this goal, adjust those areas where the curvature changes greatly. For example, if it is found that the curvature of a certain part of the model surface suddenly increases or decreases, the position of the point in that area is fine-tuned to make it closer to the curvature of the surrounding area, so that the curvature change of the entire model surface is smoother. During the adjustment process, make sure that the overall shape and key features of the model are not destroyed, and only optimize the slight degree of local curvature.

[0115] Furthermore, an energy function is introduced, which can measure the degree of difference between the model surface and the ideal surface. The ideal surface is a relatively smooth and regular surface shape that is pre-set according to the characteristics and requirements of the target object. The surface of the first optimized model is analyzed, and the points on the model surface are associated with the energy function. By adjusting the position of the points on the model surface, the value of the energy function is minimized. When the value of the energy function is minimum, it means that the difference between the model surface and the ideal surface is minimum, and a better surface fitting is achieved. When adjusting the position of the points, the relationship between the points and their position information in three-dimensional space are considered to ensure that the adjusted surface meets the requirements of the energy function while maintaining the rationality of the model.

[0116] Next, the model state after minimizing curvature changes and the model state after surface fitting are obtained. Taking these two results into consideration, the model is further adjusted and optimized. For example, the adjustment results of the model point positions from the two processing methods can be combined according to a certain weight ratio. If minimizing curvature changes is considered more important, its weight can be appropriately increased; if the effect of surface fitting is more critical, its weight can be increased accordingly. Through this fusion process, the model can maintain the smoothness of surface curvature changes while being as close to the ideal surface as possible, ultimately obtaining a smoother and more accurate second optimized model.

[0117] By minimizing curvature variations and performing surface fitting, the model's surface irregularities and sudden changes are significantly reduced, resulting in a smoother surface. This is crucial for applications requiring high surface quality, such as industrial product design and fluid dynamics simulation, as it improves simulation and analysis accuracy. The resulting second optimized model more closely resembles the true form of the target object. Because it comprehensively considers curvature variations and ideal surface fitting, it reduces model errors and deviations, enabling a more accurate representation of the target object's geometric characteristics. In industrial monitoring, such a model can be used more reliably to detect and analyze the target object's condition, improving monitoring accuracy and reliability. A smooth and accurate second optimized model is highly effective in a variety of applications. Whether used in 3D reconstruction, virtual reality, or computer-aided design, it provides a higher-quality data foundation, enabling smoother and more efficient operations and analysis. The high quality of the second optimized model facilitates subsequent processing and analysis. For example, when extracting three-dimensional point cloud data, a smooth model can reduce noise and interference and improve the quality of the point cloud data; when performing further optimization and deformation operations on the model, it is also easier to implement and control, saving processing time and computing resources.

[0118] For example, in step 105, the three-dimensional point cloud data of the target object is extracted from the optimized virtual model to complete the intelligent extraction of the three-dimensional point cloud data. The three-dimensional point cloud data of the target object is extracted from the optimized virtual model. The coordinates of the points on the model surface can be directly obtained, or a certain number of points can be uniformly selected on the model surface through sampling to generate point cloud data. The extracted point cloud data is cleaned and processed to remove noise points, outliers, etc. Statistical filtering, radius filtering, and other algorithms can be used to remove noise, and clustering algorithms can be used to separate different objects. The processed three-dimensional point cloud data is output as the final result, providing data support for subsequent industrial monitoring, analysis, and decision-making.

[0119] The embodiments of the present application can realize automated three-dimensional image analysis and extraction of target objects in industrial monitoring scenarios, improve the image processing accuracy and efficiency of industrial monitoring, and provide users with more comprehensive and timely automated image processing services.

[0120] Figure 2 A schematic diagram of the structure of a 3D point cloud data intelligent processing system provided in an embodiment of the present application is shown as follows: Figure 2 As shown, the system includes the following steps:

[0121] An acquisition unit, configured to acquire initial image data to be processed; the initial image data includes a target object to be analyzed in an industrial monitoring scene;

[0122] a stitching unit, configured to perform three-dimensional stitching on the initial image data to obtain a stitched image corresponding to the target object;

[0123] A modeling unit, configured to perform virtual modeling based on the stitched image to obtain an initial virtual model of the target object; the initial virtual model is a virtual three-dimensional model of the target object in the stitched image space;

[0124] an optimization unit, configured to optimize the spatial form of the initial virtual model using an adaptive optimization model to obtain an optimized virtual model; the optimized virtual model is a virtual three-dimensional model of the target object in the image optimization space;

[0125] The extraction unit is used to extract the three-dimensional point cloud data of the target object from the optimized virtual model to complete the intelligent extraction of the three-dimensional point cloud data.

[0126] Further optionally, the optimization unit optimizes the spatial form of the initial virtual model using an adaptive optimization model to obtain an optimized virtual model, specifically for:

[0127] By using the adaptive optimization model, adjusting the positions of the various points in the initial virtual model according to the geometric features of the target object and the pre-set geometric constraints, to obtain a first optimized model;

[0128] Using a surface fitting algorithm, the first optimization model is subjected to surface smoothing processing to obtain a second optimization model;

[0129] According to the proportion changes and size relationships of the target object in various dimensions, the position of the second optimized model is adjusted to obtain the optimized virtual model.

[0130] Further optionally, the optimization unit adjusts the position of the second optimization model according to the proportion change and size relationship of the target object in various dimensions to obtain the optimized virtual model, specifically for:

[0131] Predicting a contour change trend coefficient of the target object in the second optimization model based on the target object's proportional changes and size relationships in various dimensions;

[0132] Based on the predicted contour change trend coefficient, anomaly identification is performed on the spatial position points in each dimension in the second optimization model;

[0133] The identified abnormal spatial points are adjusted to obtain the optimized virtual model.

[0134] Further optionally, the optimization unit performs abnormality identification on spatial position points in each dimension in the second optimization model based on the predicted contour change trend coefficient, specifically for:

[0135] For the spatial position points in the second optimization model , determine the spatial location point The average distance between adjacent spatial locations;

[0136] The product of the contour change trend coefficient and the average distance is multiplied by the spatial position point In the Add the coordinate reference values in each dimension to get the spatial position point In the Expected coordinate values in dimensions;

[0137] After obtaining the expected coordinate value of each spatial position point in the corresponding dimension in the second optimization model, calculate the abnormality parameter corresponding to each spatial position point according to the expected coordinate value of each spatial position point and the real-time coordinate value of each spatial position point in the second optimization model;

[0138] The abnormal parameters of each spatial position point are compared with the dynamic threshold to screen out the abnormal spatial points.

[0139] Further optionally, the spatial position point in the second optimization model The calculation process of the corresponding abnormal parameters is expressed as the following formula:

[0140] ;

[0141] in, Represents a spatial location point Corresponding abnormal parameters, weight factors To adjust the The contribution of dimensions in abnormal judgment, Represents a spatial location point In the The actual coordinate value in the dimension, Represents a spatial location point In the Expected coordinate values in dimension, 、 、 express In the The projected coordinate value on the dimension, Indicates that all spatial position points in the second optimization model are The average coordinate value in the dimension, is the number of spatial position points in the second optimization model, For indicating that each spatial position point in the second optimization model is The average fluctuation range in the dimension.

[0142] Further optionally, the optimization unit compares the abnormal parameters of each spatial position point with a dynamic threshold to screen out the abnormal spatial points, specifically for:

[0143] Based on the preset adjustment strategy, the dynamic threshold corresponding to each spatial position point is obtained in real time;

[0144] If the abnormal parameter is greater than the corresponding dynamic threshold, the spatial position point corresponding to the current abnormal parameter is determined to be an abnormal spatial point;

[0145] If the abnormal parameter is not greater than the corresponding dynamic threshold, the spatial position point corresponding to the current abnormal parameter is determined to be a normal spatial point.

[0146] Further optionally, the optimization unit uses a surface fitting algorithm to perform surface smoothing on the first optimization model to obtain a second optimization model, which is specifically used to:

[0147] performing curvature change minimization processing on the first optimization model;

[0148] Performing surface fitting processing on the first optimization model through an energy function;

[0149] The curvature minimization optimization result and the surface fitting result are fused to obtain the second optimization model.

[0150] See also Figure 3 , Figure 3 This is a schematic diagram of an embodiment of an electronic device provided in an embodiment of the present application. Figure 3 As shown, an embodiment of the present application provides an electronic device 500, including a memory 510, a processor 520, and a computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 511, the aforementioned embodiment is implemented.

[0151] See also Figure 4 , Figure 4 This is a schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present application. Figure 4 As shown, this embodiment provides a computer-readable storage medium 600 on which a computer program 611 is stored. When the computer program 611 is executed by a processor, the aforementioned embodiment is implemented.

[0152] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0153] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0154] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0155] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0156] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0157] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0158] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A 3D point cloud data intelligent processing method, characterized in that: The method at least comprises: Acquire initial image data to be processed; the initial image data includes a target object to be analyzed in an industrial monitoring scene; Performing three-dimensional stitching on the initial image data to obtain a stitched image corresponding to the target object; Perform virtual modeling based on the stitched image to obtain an initial virtual model of the target object; the initial virtual model is a virtual three-dimensional model of the target object in the stitched image space; The initial virtual model is optimized in spatial form by an adaptive optimization model to obtain an optimized virtual model; the optimized virtual model is a virtual three-dimensional model of the target object in the image optimization space; Extracting three-dimensional point cloud data of the target object from the optimized virtual model to complete intelligent extraction of the three-dimensional point cloud data; The method of performing spatial morphological optimization on the initial virtual model by using an adaptive optimization model to obtain an optimized virtual model includes: adjusting the positions of various position points in the initial virtual model according to the geometric features of the target object and pre-set geometric constraints by using the adaptive optimization model to obtain a first optimized model; performing surface smoothing processing on the first optimized model by using a surface fitting algorithm to obtain a second optimized model; and adjusting the positions of the second optimized model according to the proportional changes and size relationships of the target object in various dimensions to obtain the optimized virtual model. wherein, the position adjustment of the second optimization model is performed according to the proportional change and size relationship of the target object in each dimension to obtain the optimized virtual model, including: based on the predicted shape contour change trend coefficient, the abnormality identification of the spatial position points in each dimension in the second optimization model; wherein, for the spatial position point Pi in the second optimization model, the average distance between the spatial position point Pi and the adjacent spatial position points is determined; the product of the shape contour change trend coefficient and the average distance is added to the coordinate reference value of the spatial position point Pi in the jth dimension to obtain the expected coordinate value of the spatial position point Pi in the jth dimension; after solving and obtaining the expected coordinate value of each spatial position point in the corresponding dimension in the second optimization model, the abnormal parameters corresponding to each spatial position point are calculated according to the expected coordinate value of each spatial position point and the real-time coordinate value of each spatial position point in the second optimization model; the abnormal parameters of each spatial position point are compared with the dynamic threshold to screen out the abnormal spatial points; The calculation process of the abnormal parameter corresponding to the spatial position point Pi in the second optimization model is expressed as the following formula: Among them, Di represents the abnormal parameter corresponding to the spatial position point Pi, and the weight factor w j Used to adjust the contribution of the jth dimension in abnormal judgment, x ij Represents the actual coordinate value of the spatial position point Pi in the jth dimension, Represents the expected coordinate value of the spatial position point Pi in the jth dimension, x, y, z represent x ij The projection coordinate value in the j-th dimension, represents the average coordinate value of all spatial position points in the second optimization model in the jth dimension, n is the number of spatial position points in the second optimization model, Used to represent the average fluctuation range of each spatial position point in the jth dimension in the second optimization model.

2. The 3D point cloud data intelligent processing method according to claim 1, characterized in that: The step of adjusting the position of the second optimized model according to the proportional changes and size relationships of the target object in various dimensions to obtain the optimized virtual model includes: Predicting a contour change trend coefficient of the target object in the second optimization model based on the target object's proportional changes and size relationships in various dimensions; Based on the predicted contour change trend coefficient, anomaly identification is performed on the spatial position points in each dimension in the second optimization model; The identified abnormal spatial points are adjusted to obtain the optimized virtual model.

3. The 3D point cloud data intelligent processing method according to claim 2, characterized in that: The comparing the abnormal parameters of each spatial position point with the dynamic threshold to screen out the abnormal spatial point includes: Based on the preset adjustment strategy, the dynamic threshold corresponding to each spatial position point is obtained in real time; If the abnormal parameter is greater than the corresponding dynamic threshold, the spatial position point corresponding to the current abnormal parameter is determined to be an abnormal spatial point; If the abnormal parameter is not greater than the corresponding dynamic threshold, the spatial position point corresponding to the current abnormal parameter is determined to be a normal spatial point.

4. The 3D point cloud data intelligent processing method according to claim 1, characterized in that: The method of using a surface fitting algorithm to perform surface smoothing processing on the first optimization model to obtain a second optimization model includes: performing curvature change minimization processing on the first optimization model; Performing surface fitting processing on the first optimization model through an energy function; The curvature minimization optimization result and the surface fitting result are fused to obtain the second optimization model.

5. A 3D point cloud data intelligent processing system, characterized in that: The system comprises at least the following units: An acquisition unit, configured to acquire initial image data to be processed; the initial image data includes a target object to be analyzed in an industrial monitoring scene; a stitching unit, configured to perform three-dimensional stitching on the initial image data to obtain a stitched image corresponding to the target object; a modeling unit, configured to perform virtual modeling based on the stitched image to obtain an initial virtual model of the target object; The initial virtual model is a virtual three-dimensional model of the target object in the spliced image space; an optimization unit, configured to optimize the spatial form of the initial virtual model using an adaptive optimization model to obtain an optimized virtual model; the optimized virtual model is a virtual three-dimensional model of the target object in the image optimization space; an extraction unit, configured to extract three-dimensional point cloud data of a target object from the optimized virtual model, so as to complete intelligent extraction of the three-dimensional point cloud data; The optimization unit, when performing spatial morphology optimization on the initial virtual model through the adaptive optimization model to obtain the optimized virtual model, is specifically configured to: adjust the positions of various position points in the initial virtual model according to the geometric features of the target object and pre-set geometric constraints through the adaptive optimization model to obtain a first optimized model; perform surface smoothing processing on the first optimized model using a surface fitting algorithm to obtain a second optimized model; and adjust the position of the second optimized model according to the proportional changes and size relationships of the target object in various dimensions to obtain the optimized virtual model; Wherein, the optimization unit adjusts the position of the second optimization model according to the proportional changes and size relationships of the target object in various dimensions, and when obtaining the optimized virtual model, is specifically used to: identify abnormalities of spatial position points in various dimensions in the second optimization model based on the predicted contour change trend coefficient; wherein, for the spatial position point Pi in the second optimization model, determine the average distance between the spatial position point Pi and the adjacent spatial position points; add the product of the contour change trend coefficient and the average distance to the coordinate reference value of the spatial position point Pi in the jth dimension to obtain the expected coordinate value of the spatial position point Pi in the jth dimension; after solving and obtaining the expected coordinate value of each spatial position point in the corresponding dimension in the second optimization model, calculate the abnormal parameters corresponding to each spatial position point according to the expected coordinate value of each spatial position point and the real-time coordinate value of each spatial position point in the second optimization model; compare the abnormal parameters of each spatial position point with the dynamic threshold to screen out the abnormal spatial points; The calculation process of the abnormal parameter corresponding to the spatial position point Pi in the second optimization model is expressed as the following formula: Among them, Di represents the abnormal parameter corresponding to the spatial position point Pi, and the weight factor w j Used to adjust the contribution of the jth dimension in abnormal judgment, x ij Represents the actual coordinate value of the spatial position point Pi in the jth dimension, Represents the expected coordinate value of the spatial position point Pi in the jth dimension, x, y, z represent x ij The projection coordinate value in the j-th dimension, represents the average coordinate value of all spatial position points in the second optimization model in the jth dimension, n is the number of spatial position points in the second optimization model, Used to represent the average fluctuation range of each spatial position point in the jth dimension in the second optimization model.

6. An electronic device, characterized in that: including a memory for storing a computer software program; A processor is used to read and execute the computer software program, thereby implementing the 3D point cloud data intelligent processing method described in any one of claims 1-4.

7. A non-transitory computer-readable storage medium, characterized in that The storage medium stores a computer software program, which, when executed by a processor, implements the 3D point cloud data intelligent processing method according to any one of claims 1 to 4.

Images