Self-adaptive incomplete deformation cavity three-dimensional point cloud volume accurate calculation method and system

Abstract

The invention discloses a self-adaptive incomplete deformation cavity three-dimensional point cloud volume accurate calculation method and system, and relates to the technical field of laser radar point cloud processing, and the method comprises the steps: obtaining a reference point cloud; the reference point cloud is a directly measured empty warehouse point cloud or a virtual empty warehouse point cloud generated by a historical cavity point cloud and a granary design drawing; dividing the reference point cloud into a material surface upper warehouse wall point cloud and a material surface lower warehouse wall point cloud through the material surface point cloud; fusing the bin wall point cloud below the material surface of the corresponding cavity point cloud in the segmented reference point cloud and the material surface point cloud of the real-time cavity point cloud to obtain a to-be-calculated material point cloud; calculating the volume of the to-be-calculated material point cloud; according to the method, the historical cavity point cloud and the granary design parameters are fused to obtain the reference point cloud, granary deformation and point cloud deficiency in actual measurement are effectively compensated through the virtual empty granary modeling technology, and the calculation precision of the granary material volume is remarkably improved by combining the material surface point cloud segmentation and hierarchical fusion algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of laser radar point cloud processing, and in particular to a method and system for accurately calculating the volume of a cavity three-dimensional point cloud with adaptive incomplete deformation. Background Art

[0002] Radar level meters are widely used in industry, especially in the measurement of solid materials. They determine the height of the material by emitting electromagnetic waves and measuring the time it takes for the reflected waves to be reflected. However, the disadvantage is that radar level meters usually have a low resolution, which can result in inaccurate measurements of inventory levels, especially when measuring small changes.

[0003] Structured light scanning technology acquires the 3D shape of an object by projecting a grating or stripe pattern, and is commonly used in industrial inspection and reverse engineering. This technology does not work well in environments with strong light or reflective surfaces, and is affected by the texture and color of the object's surface, which may result in incomplete or inaccurate data collection.

[0004] Image processing and computer vision use cameras and image processing algorithms, combined with deep learning technology, to extract three-dimensional information of objects from images. This method is sensitive to ambient lighting conditions and may have difficulty accurately identifying objects in complex backgrounds.

[0005] In the calculation of the granary point cloud volume, because the granary itself is closed and it is impossible to directly obtain the complete model of the granary raw materials, the granary inventory volume is generally obtained by subtracting the volume of the blank area model above the material surface from the volume of the empty granary model. Ideally, the empty granary model can be directly measured or obtained based on the granary drawings when the granary is initially installed. This is an ideal empty granary model, but in the subsequent practical process, the interior of the granary will deform and differ from the ideal empty granary model. This difference will lead to inaccurate final volume measurement. In addition, dust will be generated inside the granary, and most laser radars cannot effectively penetrate the dust. Directly using the point cloud measured by the laser radar in a dusty granary will result in a large volume error in calculating the blank area model above the material surface. Summary of the invention

[0006] The purpose of the present invention is to solve the problem of low accuracy of the existing granary point cloud volume calculation method. The present invention provides a cavity three-dimensional point cloud volume accurate calculation method with adaptive incomplete deformation. The technical solution includes the following steps: Obtain a reference point cloud; the reference point cloud is a directly measured empty warehouse point cloud or a virtual empty warehouse point cloud generated by combining historical cavity point clouds and grain warehouse design drawings; The real-time cavity point cloud is segmented to obtain the material surface point cloud, and the reference point cloud is segmented into the warehouse wall point cloud above the material surface and the warehouse wall point cloud below the material surface through the material surface point cloud; The warehouse wall point cloud below the material surface in the segmented reference point cloud and the material surface point cloud of the real-time cavity point cloud are merged to obtain the material point cloud to be calculated; The point cloud volume of the material to be calculated.

[0007] Specifically, obtaining the reference point cloud includes: If the empty warehouse point cloud can be directly measured, the measured empty warehouse point cloud is used as the reference point cloud, or the historical cavity point cloud that meets the requirements of the first volume confidence interval is directly selected as the reference point cloud; otherwise, a virtual empty warehouse point cloud is constructed as the reference point cloud through the historical cavity point cloud and the granary geometric parameters.

[0008] Specifically, the method of constructing a virtual empty warehouse point cloud as a reference point cloud using the historical cavity point cloud and the grain warehouse geometric parameters includes: Selecting the historical cavity point cloud that meets the second volume confidence interval requirement; Align the historical cavity point cloud axis with the central axis of the granary design drawing; The historical cavity point cloud after axial alignment and the design parameters of the granary are fused to obtain the virtual empty silo point cloud; Perform error compensation on the virtual empty warehouse point cloud to obtain the reference point cloud; Preferably, the first volume confidence interval is ; The second volume confidence interval is: , is the volume confidence, defined as: ; in, is the volume of a historical cavity point cloud, It is the theoretical volume in the empty warehouse state.

[0009] Specifically, the historical cavity point cloud after axial alignment and the design parameters of the granary are fused to obtain the virtual empty warehouse point cloud: Through axial translation transformation and parameterized stretching coefficient, the measured data is coupled with the design parameters to achieve rapid geometric reconstruction of the virtual empty warehouse. The virtual empty warehouse point cloud that needs to be reconstructed includes the measured section and the extended section. The measured section directly uses the warehouse wall points in the historical cavity point cloud; the extended section is divided into the side wall and the warehouse bottom. The side wall is based on the side wall height in the grain warehouse design drawing. By axial stretching: ; ; in, is the side wall height of the historical cavity point cloud, is the difference between the side wall height of the granary design drawing and the side wall height of the historical cavity point cloud. is the stretching coefficient, which is used to control the degree of stretching so that the extended section and the measured section are smoothly connected. is the virtual warehouse wall point coordinate of the side wall of the extension section, is the coordinate of the highest point of the measured segment, The measured section and the extended section are spliced ​​to obtain the virtual empty warehouse point cloud. The essence of the above method is the parametric deformation method in geometric modeling. While ensuring the calculation efficiency, it enhances the practicality by introducing adjustable parameters and using the height of the design drawing. The virtual granary was reconstructed to ensure that it met the design specifications and the historical height This ensures consistency with the measured data.

[0010] Independently reconstruct the warehouse bottom according to the design drawing parameters: The height of the flat bottom based on the design drawing The bottom boundary of the side wall is projected to generate a uniformly rasterized point cloud; The cone bottom is designed by the drawing parameters (the cone top of the drawing , Drawing half-width , Drawing radius ) is driven by the discretization of parametric analytical surfaces to generate point clouds, which are expressed as: ; in, It is a conical silo bottom. For the cone top of the drawing, For the half-width of the drawing, is the drawing radius, ] is the radial distance, is the azimuth, Perpendicular to the axis The plane orthogonal basis vectors of ; Finally, the topological closure fusion of the side wall and warehouse bottom point clouds is achieved through the normal vector consistency constraint and the nearest neighbor interpolation algorithm based on KD-Tree, eliminating the geometric seams and ensuring that the virtual empty warehouse point cloud inherits the local details of the measured data while the global morphology strictly complies with the design specifications and structural continuity.

[0011] The measured section and the extended section are spliced ​​together to obtain the virtual empty warehouse point cloud.

[0012] Specifically, the real-time cavity point cloud is segmented to obtain a material surface point cloud, and the reference point cloud is segmented into a warehouse wall point cloud above the material surface and a warehouse wall point cloud below the material surface through the material surface point cloud, including the following steps: Spatial registration of real-time cavity point cloud and reference point cloud; Perform difference distance field calculation and spatial mapping on real-time cavity point cloud; Adaptive threshold segmentation of material surface and warehouse wall of real-time cavity point cloud; Perform morphological optimization and topological verification on material surface point cloud; Based on the material surface point cloud of the cavity point cloud, the reference point cloud is divided into the warehouse wall point cloud above the material surface and the warehouse wall point cloud below the material surface.

[0013] Specifically, the material surface point cloud based on the cavity point cloud, dividing the reference point cloud into a warehouse wall point cloud above the material surface and a warehouse wall point cloud below the material surface includes: Material surface height field modeling; from the material surface point cloud, calculate its height distribution field : ; in, is the horizontal projection neighborhood of the material surface, Points on the material surface The vertical coordinate of .

[0014] Based on height distribution field , perform regional segmentation on the reference point cloud: (a) Point cloud of the warehouse wall below the material surface: ; (b) Point cloud of the warehouse wall above the material surface: ; in, is the reference point cloud, is a point on the reference point cloud The vertical coordinate of is the noise standard deviation; Specifically, the step of fusing the warehouse wall point cloud below the material surface of the cavity point cloud corresponding to the segmented reference point cloud with the material surface point cloud of the real-time cavity point cloud to obtain the material point cloud to be calculated includes the following steps: Extract the boundary of the material surface point cloud through the α-shape algorithm And the boundary of the warehouse wall point cloud below the material surface ,in, is a point on the boundary of the material surface point cloud. is the member function of α-shape; Construct KD-Tree acceleration structure to Perform a search with radius r, r=2 , is the radius search threshold, marker and boundary Overlapping Area , is a point on the boundary of the reference point cloud in the overlapping area, for For the kth point on the material surface whose distance in the neighborhood is less than r, the non-maximum suppression strategy is used to eliminate redundant points; At the border With border Create buffer zones at junctions , the transition surface is fitted by the moving least squares method to achieve continuous fusion of the material surface point cloud and the warehouse wall point cloud below the material surface. The formula is as follows: ; in, and are two independent variables used to parameterize the surface, is the distance weight function, defined as , p represents the point in the parameter space (u, v) mapped to the three-dimensional space, is the shortest Euclidean distance from point p to the material surface boundary, is the buffer width, which controls the transition range of the fusion area. and They represent the local fitting surfaces of the material surface point cloud and the warehouse wall point cloud respectively. The transition surface representing the fusion area; Adopt a multi-resolution strategy based on Poisson disk sampling to adaptively adjust the point spacing in the fusion area ,in, is the resampling point spacing, adaptively taking the minimum spacing between the material surface point cloud and the warehouse wall point cloud below the material surface. is the average point spacing of the material surface point cloud, is the average point spacing of the warehouse wall point cloud below the material surface; Apply anisotropic curvature diffusion filtering to remove local distortion caused by noise: ; in, For point and its neighboring points The Gaussian curvature of quantifies the local surface curvature, Neighborhood point The normal vector indicates the local direction of the surface. For point The neighborhood point set of (based on KD-Tree search), For the The three-dimensional coordinates of a point.

[0015] Furthermore, after the historical cavity point cloud and the real-time cavity point cloud are acquired, a preprocessing operation needs to be performed on them, including the following steps: The granary measurement point cloud is downsampled and outliers are removed; for the convenience of description, the historical point cloud and the real-time cavity point cloud are referred to as the granary measurement point cloud; Integrity assessment and repair of granary measurement point cloud.

[0016] At the same time, the present invention also provides a cavity three-dimensional point cloud volume accurate calculation system with adaptive incomplete deformation, the system is used to calculate the volume of the cavity three-dimensional point cloud, including: Data acquisition module, used for automatic acquisition or manual import of point cloud data; A data processing module, used for performing volume calculation based on the point cloud data in the data acquisition module; A data transmission module, used for transmitting the three-dimensional point cloud volume of the cavity calculated by the data processing module to the terminal; The volume calculation method used in the data processing module is the above-mentioned adaptive incomplete deformation cavity three-dimensional point cloud volume accurate calculation method.

[0017] After adopting the above scheme, the beneficial effects of the present invention are: the virtual empty warehouse modeling technology is used to effectively compensate for the warehouse deformation and point cloud missing in the actual measurement, and the material surface point cloud segmentation and layered fusion algorithm are combined to significantly improve the calculation accuracy of the grain warehouse material volume; it innovatively integrates historical point clouds and design parameters to reconstruct the reference point cloud, breaking through the dependence on actual empty warehouse scanning, and providing a highly robust solution for dynamic warehouse management. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is the main flow chart of the present invention; Figure 2 A schematic diagram of generating a virtual cavity point cloud through historical cavity point clouds and design drawings in a specific implementation of the present invention; Figure 3 It is a principle diagram of dividing the reference point cloud into a warehouse wall point cloud above the material surface and a warehouse wall point cloud below the material surface in a specific implementation of the present invention; Figure 4 It is a schematic diagram of the fusion of the material surface point cloud and the warehouse wall point cloud below the material surface in a specific implementation of the present invention; Figure 5 A diagram showing the use scenario of the method for accurately calculating the volume of a cavity three-dimensional point cloud with adaptive incomplete deformation provided by the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0020] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0021] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field 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 can 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 the present invention.

[0022] For ease of understanding, specific terms in the present invention are explained here: 1. Empty Silo Point Cloud (USC): The point cloud of the empty silo obtained by a single measurement at any time.

[0023] 2. Empty cavity point cloud (OSC): The point cloud above the material surface in the point cloud obtained by a single measurement of the granary at any time, including the complete point cloud of the material surface and the cavity wall above the material surface. When there is no material in the granary, it is an empty granary point cloud. Note that the granary wall here also includes the granary wall at the top of the granary. The granary top and the granary bottom can both be part of the granary wall, so they are collectively referred to as granary walls in the description of this invention.

[0024] 3. Material point cloud: The point cloud below the material surface in the point cloud obtained by a single measurement of the granary at any time, including the material surface point cloud and the silo wall point cloud below the material surface. Note that the silo wall here also includes the silo wall at the bottom of the material.

[0025] 4. Reference point cloud: The empty warehouse point cloud used as a template can be an empty warehouse point cloud obtained by direct measurement or a point cloud of a grain warehouse in an empty warehouse state reconstructed through virtual reconstruction.

[0026] The core idea of ​​the present invention is: to calculate the volume of a single granary point cloud, the reference point cloud and the material surface point cloud in the cavity point cloud measured this time are combined to obtain a material point cloud composed of a complete material surface and the silo wall below the material surface, and the material point cloud is three-dimensionally gridded to obtain the material point cloud volume. In the application scenario of the granary, the granary is basically in a state of feeding and discharging every day, and it is difficult to directly measure the empty granary model. Therefore, the present invention obtains a real empty silo point cloud that is closer to the current measurement moment based on the historical cavity point cloud and the granary drawing parameters during use, rather than directly using the initial ideal empty granary model (that is, the empty silo point cloud obtained only based on the drawing).

[0027] See also Figure 5 , Figure 5 This is a diagram of the use scenario of the method for accurately calculating the volume of a cavity three-dimensional point cloud with adaptive incomplete deformation provided by the present invention. Figure 5 As shown, the terminal and the server are connected via a network, such as a wired or wireless network connection. The terminal may include but is not limited to portable terminals such as mobile phones and tablets installed with various network platform applications, as well as fixed terminals such as computers, query machines, and advertising machines. The server provides users with various business services, including service push servers, user recommendation servers, etc.

[0028] It should be noted that Figure 5 The scene diagram of the method for accurately calculating the volume of a cavity three-dimensional point cloud with adaptive incomplete deformation shown is only an example. The terminal, server and application scenario described in the embodiment of the present invention are intended to more clearly illustrate the technical solution of the embodiment of the present invention, and do not generate any limitation on the technical solution provided by the embodiment of the present invention. A person skilled in the art can know that with the evolution of the system and the emergence of new business scenarios, the technical solution provided by the embodiment of the present invention is also applicable to similar technical problems.

[0029] The present invention specifically implements a method for calculating the volume of a grain silo point cloud with adaptive incomplete deformation, comprising the following steps: S1. Preprocessing of granary measurement point cloud: This step is the preprocessing of the granary point cloud. The subsequent historical cavity point cloud and real-time cavity point cloud must be preprocessed. For the convenience of description, they are collectively referred to as granary measurement point clouds here.

[0030] S1.1. Downsample the granary measurement point cloud and remove outliers; the specific steps are as follows: Considering the particularity of the granary scene with large dust and the complexity of data processing, the point cloud data needs to be preprocessed first. Among them, downsampling and outlier removal are key preprocessing steps, which aim to improve data quality and reduce the complexity of subsequent calculations.

[0031] S1.1.1. Introduce the voxel grid downsampling algorithm, establish a three-dimensional voxel rasterization model, and weightedly average the point cloud coordinates in each voxel unit into a single centroid point, thereby achieving spatial uniformity of point cloud density while maintaining the significance of geometric features, effectively reducing data redundancy and computational complexity.

[0032] S1.1.2. Based on the statistical outlier removal mechanism, a k-nearest neighbor search domain is constructed and the distance distribution between each point and the neighborhood point set is calculated. The outlier noise points that deviate from the main distribution are removed by presetting the standard deviation multiplier threshold. The specific steps are as follows: (1) Construct a k-nearest neighbor search domain. For each point in the point cloud , calculate the Euclidean distance between it and all other points in the point cloud , ),in , choose the one with the smallest distance Points, constitute of Neighbor search domain ),in , the neighborhood distance is With Euclidean distance between neighboring points; (2) Traverse the points outside the k nearest neighbor search domain in the cavity point cloud. If the point satisfy , then determine The noise points are removed, among which, , are the mean and standard deviation of neighborhood distances, is the empirical coefficient; (3) Identify the largest point cloud subset with topological continuity through Euclidean distance clustering and eliminate the discrete noise point set; Through the above steps, the signal-to-noise ratio and spatial consistency of the point cloud are significantly improved while maintaining the integrity of the main structure of the point cloud, laying a solid data foundation for subsequent three-dimensional reconstruction and morphological analysis.

[0033] S1.2. Integrity assessment and repair of the granary measurement point cloud; After the granary measurement point cloud is preprocessed, the point cloud volume calculation method of the subsequent grid generation needs to ensure the integrity of the point cloud, so the denoised point cloud needs to be evaluated for integrity. Due to the non-uniform distribution of dust interference in the granary scene, the measured granary point cloud will have a certain degree of incompleteness and holes. Therefore, before subsequent processing, the granary point cloud needs to be repaired to obtain a valid granary point cloud to avoid the influence of the residual point cloud edge on the subsequent feature extraction and grid volume calculation. The specific steps are as follows: S1.2.1. Construct the topological relationship of the point cloud surface based on Delaunay triangulation, extract the boundary contour B through the α-shape algorithm, and identify the hole area The geometric parameters (perimeter , curvature etc.), providing geometric basis for subsequent repair; S1.2.2. Calculate the standard deviation of the point cloud density per unit volume , when the local area density is lower than the overall density mean by 3 When a point cloud is detected, it is judged as a potential defect area; the discontinuous edge segment is detected by the curvature change rate CVR, and abnormal fracture is determined by CVR>0.25; after constructing the Delaunay triangulation, the hole area that cannot form a closed surface is detected. When any of the above defect types (defects, fractures and holes) is detected, the point cloud repair process is started: (1) Local geometric feature modeling: For each identified hole, a local reference coordinate system is established along its boundary, and geometric modeling is performed in two steps: (a) Principal curvature analysis: Use the covariance matrix method to calculate the maximum / minimum curvature of the boundary points ( ), construct the curvature tensor field ,in is the characteristic value, is the main direction of curvature; (b) Feature propagation: in the boundary neighborhood ), local surfaces are fitted by moving least squares (MLS) , and its energy function is: ; in Neighborhood ), for The normal vector is used to constrain the direction of surface fitting. is the position of the current fitting point, is the radial basis function, which is used to calculate the and The distance between the fitting errors is weighted to ensure the smoothness and continuity of the local surface. The goal of this energy function is to minimize the geometric deviation between the fitting surface and the neighborhood point cloud while maintaining the smoothness of the surface. (2) Extraction of global structural constraints: To enhance the global consistency of the above restoration results, a geometric reasoning model based on graph neural network is introduced: (a) Symmetry detection: Use the non-rigid ICP algorithm to match the symmetry axis of the point cloud and establish a mirror transformation , generate a symmetric candidate point set ; (b) Topological consistency constraint: Construct a Markov random field model and define the energy term: ; in, and For matching point pairs, is the single-point geometric likelihood (such as curvature continuity), It is a topological smoothness constraint between adjacent points to ensure the geometric consistency of the repaired area; (3) Adaptive repair strategy: A divide-and-conquer strategy is used to handle holes of different scales according to the scale of the holes: (a) For holes whose perimeter is less than the threshold, : Based on radial basis function interpolation, solve the equation: ; Among them, p is the point to be estimated, is the kth point on the hole boundary, serving as the center point of interpolation. is a cubic kernel function that controls the local influence range of the interpolation function. is a low-order polynomial to compensate for the global deviation of the radial basis function. m is the order. Taking a low order can avoid overfitting. Through the boundary conditions Determine the weight , generate a smooth transition surface; (b) For holes whose perimeter is greater than or equal to the threshold, : Combining Generative Adversarial Networks with Physical Constraints to Train Conditional Generators , where the latent variable z follows a Gaussian distribution, condition Contains geometric descriptors such as boundary curvature and normal vector field, and generates point clouds by jointly optimizing adversarial loss and geometric regularization terms; Through the above steps, the curvature continuity and physical rationality of manufacturing constraints (such as flatness and roundness) are maintained, and the incomplete and hole parts of the granary point cloud are effectively repaired. Subsequent granary point clouds are processed based on the repaired ones in S1.2, which effectively avoids the problem of feature extraction and meshing anomalies caused by incomplete holes; S2. Obtain a reference point cloud; the reference point cloud is a directly measured empty warehouse point cloud or a virtual empty warehouse point cloud generated by combining historical cavity point clouds and grain warehouse design drawings; In the existing granary usage scenario, since the granary is in a state of adding materials for a long time, a single granary will have a period of 1-3 months when it is not empty. It is difficult to obtain the empty warehouse point cloud by direct measurement. In addition, due to the deformation of the granary itself and the error of the measuring equipment over time, the two empty warehouse point clouds measured 1-3 months apart will also have a small angle rotation and offset, so a standard empty warehouse point cloud is needed as a template. If the actual empty warehouse point cloud can be measured directly, it can be directly used as a template as the reference point cloud, but it is difficult to obtain in the actual usage scenario, so it is necessary to construct a virtual empty warehouse point cloud as the reference point cloud. It should be understood that the actual process error of the granary will increase with the passage of time, so the empty warehouse point cloud selects the empty warehouse point cloud measured most recently, and the historical cavity point cloud also uses the empty warehouse point cloud measured most recently, that is to say, the historical cavity point cloud and the empty warehouse point cloud are not used all the time after being measured once, but will be updated as needed, and each measurement will overwrite the historical cavity point cloud and the empty warehouse point cloud measured last time.

[0034] Generally, granary manufacturers will have granary design drawings. Taking a square granary as an example, by obtaining the geometric parameters of the length, width and height of the granary according to the drawings, a virtual empty granary point cloud in a custom coordinate system can be generated. However, because some granaries are not built strictly according to the design drawings, there will be large errors in directly generating virtual empty granary point clouds based on geometric parameters. Therefore, it is necessary to generate a virtual empty granary point cloud through the geometric parameters of the design drawings and the measured historical cavity point cloud as a reference point cloud.

[0035] S2.1. If the empty cavity point cloud can be directly measured, the measured empty cavity point cloud is used as the reference point cloud, or the historical cavity point cloud that meets the requirements of the first volume confidence interval is directly selected as the reference point cloud; specifically, define the volume confidence for: ; in, is the volume of a historical cavity point cloud, is the theoretical volume in the empty state; when the volume confidence When , it is determined that the historical cavity point cloud meets the requirements of the first volume confidence interval, that is, the cavity point cloud is close to the empty warehouse state, and the historical cavity point cloud is directly used as the reference point cloud; otherwise, it goes to S2.2; S2.2. Constructing a virtual empty warehouse point cloud as a reference point cloud using the historical cavity point cloud and the warehouse geometric parameters; including the following steps: Since a granary is rarely empty, and the cavity point cloud measured once is also part of the point cloud when the granary is empty, for example, when the volume of the material in the granary is 1 / 4, the volume of the 3 / 4 cavity above the material is the same as or similar to the empty point cloud (because the granary wall may contain a small amount of material). Therefore, the present invention can also generate a virtual empty point cloud through the cavity point cloud measured once and the geometric parameters of the granary, and use it as the reference point cloud. This principle is as follows: Figure 2 shown.

[0036] S2.2.1. Select the historical cavity point cloud that meets the requirements of the second volume confidence interval. In order to ensure the accuracy and reliability of the virtual empty warehouse point cloud, the selection of the historical cavity point cloud must meet the geometric integrity. Therefore, the volume confidence of the historical cavity point cloud needs to be within the second volume confidence interval: , that is, the historical cavity point cloud should be able to cover the main structural features of the granary to ensure that the local geometric form of the granary can be accurately reflected; S2.2.2. Align the axis of the historical cavity point cloud with the central axis of the granary design drawing; based on the reference axis of the granary design drawing (the central axis of the granary), use the principal component analysis method to establish a design coordinate system with the central axis of the granary as the main axis; calculate the covariance matrix of the historical cavity point cloud: ,in, is the covariance matrix, which is used to describe the spatial distribution of data points. is the total number of points in the historical cavity point cloud, This is the first The three-dimensional coordinates of the points, is the geometric center of the historical cavity point cloud; for the covariance matrix Perform eigenvalue decomposition and extract the eigenvector corresponding to the maximum eigenvalue (reflecting the main direction of the granary) as the axis of the historical cavity point cloud , by rotating Achieve alignment; S2.2.3. The historical cavity point cloud after axial alignment and the design parameters of the granary are fused to obtain the virtual empty warehouse point cloud; since the historical cavity point cloud meets the second confidence level, the height of the historical cavity point cloud will be less than the design height of the granary drawing. Therefore, the virtual empty warehouse point cloud that needs to be reconstructed includes the measured section and the extended section. The measured section directly uses the warehouse wall points in the historical cavity point cloud; the extended section is divided into the side wall and the warehouse bottom. The side wall is based on the side wall height in the granary design drawing. By axial stretching: ; .

[0037] The above scheme utilizes the parametric deformation method in geometric modeling to generate new geometric shapes by stretching the point cloud along a specific direction. and They are the historical cavity point cloud height (the vertical distance between the highest and lowest points in the point cloud) and the height in the design drawing (the vertical distance between the highest and lowest points of the granary in the design drawing). is the stretching coefficient, which is used to control the degree of stretching so that the extended section and the measured section are smoothly connected. is the virtual warehouse wall point coordinate of the side wall of the extension section, is the coordinate of the highest point of the measured segment, The measured section and the extended section are spliced ​​to obtain the virtual empty warehouse point cloud. The essence of the above method is the parametric deformation method in geometric modeling. While ensuring the calculation efficiency, it enhances the practicality by introducing adjustable parameters and using the height of the design drawing. The virtual granary was reconstructed to ensure that it met the design specifications and the historical height This ensures consistency with the measured data.

[0038] Independently reconstruct the warehouse bottom according to the design drawing parameters: The height of the flat bottom based on the design drawing The bottom boundary of the side wall is projected to generate a uniformly rasterized point cloud; The cone bottom is designed by the drawing parameters (the cone top of the drawing , Drawing half-width , Drawing radius ) is driven by the discretization of parametric analytical surfaces to generate point clouds, which are expressed as: ; in, It is a conical silo bottom. For the cone top of the drawing, For the half-width of the drawing, is the drawing radius, ] is the radial distance, is the azimuth, Perpendicular to the axis The plane orthogonal basis vectors of ; Finally, the topological closure fusion of the side wall and warehouse bottom point clouds is achieved through the normal vector consistency constraint and the nearest neighbor interpolation algorithm based on KD-Tree, eliminating the geometric seams and ensuring that the virtual empty warehouse point cloud inherits the local details of the measured data while the global morphology strictly complies with the design specifications and structural continuity.

[0039] The measured section and the extended section are spliced ​​together to obtain the virtual empty warehouse point cloud.

[0040] S2.2.4. Perform error compensation on the virtual empty warehouse point cloud to obtain the reference point cloud; specifically, taking the cylindrical granary as an example, the cylinder is fitted by the random sampling consistency algorithm to extract the radius of the granary. , the objective function of the cylindrical fitting is: ,in, is the radius of the cylinder to be fitted, is the reference point on the cylinder axis (3D coordinates), The first points, iterative optimization to obtain the optimal , the confidence of the fitted cylinder radius is: , is the number of internal points extracted in the random sampling consensus algorithm, is the total number of points in the point cloud; when (Insufficient confidence), introduce the design cylinder radius in the design drawing Perform weighted fusion to obtain the radius of the fused cylinder : ; Through the above steps, when the granary is cylindrical, adding confidence and weighted fusion methods can effectively combine the measured cavity point cloud and design parameters to generate a more stable virtual empty warehouse point cloud, which is used as the reference point cloud. Granary point clouds of other shapes can be used to establish virtual empty warehouse point clouds with high confidence through the same data fusion scheme and error compensation mechanism; but in fact, most existing granaries are cylindrical.

[0041] S3. Segment the real-time cavity point cloud to obtain the material surface point cloud. The reference point cloud is segmented into the warehouse wall point cloud above the material surface and the warehouse wall point cloud below the material surface through the material surface point cloud. The principle is as follows Figure 3 As shown; After obtaining the reference point cloud through S2, the material surface of the granary to be measured at that moment can be extracted by measuring the real-time cavity point cloud (cavity point cloud at a certain moment), and the silo wall parts above and below the material surface in the real-time cavity point cloud can be extracted in the reference point cloud, providing a geometric basis for subsequent data fusion. Given that the silo wall structures of the reference point cloud and the real-time cavity point cloud are geometrically consistent, the silo walls of the reference point cloud and the real-time cavity point cloud are defined as consistent areas, and the material surface of the real-time cavity point cloud is defined as inconsistent areas.

[0042] The reference point cloud obtained by S2 is in the custom design coordinate system, while the real-time cavity point cloud is in the measured local coordinate system. Therefore, it is necessary to first unify the two coordinate systems and then use the difference distance field to segment the material surface and the warehouse wall.

[0043] S3.1. Perform spatial registration on the real-time cavity point cloud and the reference point cloud; The improved ICP algorithm is used to perform rigid registration of the two sets of point clouds: the matching point pairs are screened through the RANSAC mechanism to solve the optimal rotation matrix of the real-time cavity point cloud and the reference point cloud. with translation vector , so that the objective function Minimize and eliminate the systematic deviation caused by the position error of the measuring device, establish a unified spatial reference system, and use the optimal rotation matrix of the real-time cavity point cloud and the reference point cloud respectively with translation vector Perform registration between the two; S3.2. Perform difference distance field calculation and spatial mapping on real-time cavity point cloud; Based on the KD-Tree data structure, the accelerated spatial index of the reference point cloud is constructed, and each point in the real-time cavity point cloud is implement Nearest neighbor search ( ), get the closest Euclidean distance to the reference point cloud , generating a scalar distance field of the surface of a real-time cavity point cloud ,in, Represents a point in the real-time cavity point cloud; the distance field quantifies the degree of local deformation caused by material accumulation in the cavity point cloud. The material surface area will show high distance value characteristics due to significant protrusions; S3.3. Adaptively segment the material surface and the warehouse wall of the real-time cavity point cloud by threshold; In order to distinguish the silo wall noise from the real material surface, a dynamic threshold function is designed ,in , are the mean and standard deviation of the scalar distance field D, β is the sensitivity coefficient (usually 2.5~3.5), and the real-time cavity point cloud is divided into material surface point cloud by binarization operation. With the Cangbi point cloud, is the distance threshold; this threshold strategy can effectively suppress the false signals caused by point cloud registration residuals and measurement equipment jitter; S3.4. Perform morphological optimization and topological verification on the material surface point cloud; In order to improve the topological rationality of the segmentation results, the following post-processing steps are used for optimization: (a) Material surface point cloud Perform Euclidean cluster analysis and remove clusters with an area smaller than a threshold. (a) Delaunay triangulation is used to construct the material surface mesh, and the region growing algorithm is used to fill the local holes caused by occlusion; (b) The maximum connected domain is extracted. As the final material surface point cloud, ensure its smooth transition with the warehouse wall boundary; S3.5. Material surface point cloud based on cavity point cloud , split the reference point cloud into the warehouse wall point cloud above the material surface Point cloud of the warehouse wall below the material surface ; The specific steps are as follows: S3.5.1. Material surface height field modeling; Material surface point cloud extracted from S3.4 Calculate its height distribution field : ; in, is the horizontal projection neighborhood of the material surface, Points on the material surface The vertical coordinate of .

[0044] S3.5.2. Based on the height distribution field , for the reference point cloud Cloud segmentation: (a) Point cloud of the warehouse wall below the material surface: ; (b) Point cloud of the warehouse wall above the material surface: ; in, is a point on the reference point cloud The vertical coordinate of is the noise standard deviation, which is estimated by statistical filtering residuals and is used to offset the impact of point cloud noise on segmentation; Through the above process, this scheme can effectively segment the warehouse wall area and material surface area in the cavity point cloud and the warehouse wall area above and below the material surface of the corresponding cavity point cloud in the empty warehouse point cloud. While retaining the fine-grained geometric features of the material surface, high-precision material surface extraction is achieved, providing a reliable three-dimensional data foundation for the subsequent combination of the material surface of the measurement point cloud and the warehouse wall of the reference point cloud and the volume calculation of the material point cloud.

[0045] S4. The warehouse wall point cloud corresponding to the cavity point cloud material surface in the segmented reference point cloud and the material surface point cloud of the real-time cavity point cloud are merged to obtain the material point cloud to be calculated. The principle is as follows Figure 4 As shown; After the point cloud segmentation in S3, the material surface part in the cavity point cloud is obtained , and the warehouse wall point cloud above the material surface in the reference point cloud relative to the material surface in the cavity point cloud And the point cloud of the warehouse wall below the material surface . For the material surface point cloud and the base point cloud, the warehouse wall point cloud below the material surface By combining them, we can get the material point cloud. The specific steps are as follows: S4.1. Extracting material surface point cloud using α-shape algorithm The border And the point cloud of the warehouse wall below the material surface The border ,in, is a point on the boundary of the material surface point cloud. is the member function of α-shape; S4.2. Construct KD-Tree acceleration structure to Perform a search with radius r, r=2 , is the radius search threshold, marker and boundary Overlapping Area , is a point on the boundary of the reference point cloud in the overlapping area, for For the kth point on the material surface whose distance in the neighborhood is less than r, the non-maximum suppression strategy is used to eliminate redundant points; S4.3. At the border With border Create buffer zones at junctions , the transition surface is fitted by the moving least squares method to achieve continuous fusion of the material surface point cloud and the warehouse wall point cloud below the material surface. The formula is as follows: ; in, and are two independent variables used to parameterize the surface, is the distance weight function, defined as , p represents the point in the parameter space (u, v) mapped to the three-dimensional space, is the shortest Euclidean distance from point p to the material surface boundary, is the buffer width, which controls the transition range of the fusion area. and They represent the local fitting surfaces of the material surface point cloud and the warehouse wall point cloud respectively. The transition surface representing the fusion area; S4.4. Adopt a multi-resolution strategy based on Poisson disk sampling to adaptively adjust the point spacing in the fusion area ,in, is the resampling point spacing, adaptively taking the minimum spacing between the material surface point cloud and the warehouse wall point cloud below the material surface. is the average point spacing of the material surface point cloud, The average point spacing of the silo wall point cloud below the material surface is used to maintain uniform point distribution and avoid point aggregation or sparseness; S4.5. Apply anisotropic curvature diffusion filtering to eliminate local distortion caused by noise: ; in, For point and its neighboring points The Gaussian curvature of quantifies the local surface curvature, Neighborhood point The normal vector indicates the local direction of the surface. For point The neighborhood point set of (based on KD-Tree search), For the The three-dimensional coordinates of a point; Through the above steps, the material surface part of the real-time cavity point cloud and the warehouse wall part in the reference point cloud are fused together, and the edge position of the fusion point is optimized through distance weighting and geometric consistency enhancement to maintain the geometric integrity of the edge.

[0046] S5. Calculate the volume of the material point cloud to be calculated; the volume calculation uses the point cloud meshing method to convert the point cloud into a three-dimensional mesh model to obtain the model volume of the granary. The specific steps are as follows: S5.1. Surface reconstruction of the material point cloud to be calculated and construction of tetrahedral mesh ; Using the Delaunay triangulation method, all points in the point cloud meet the empty ball criterion, that is, the circumscribed ball of any tetrahedron does not contain other vertices. By constructing a tetrahedral mesh (From the tetrahedron point set The surface manifold is extracted by convex hull cutting and α-shape algorithm (geometric constraints, used to screen the surface manifold and remove the internal tetrahedron): ; in, is a single triangular patch in the surface manifold, consisting of the points constitute, is a surface manifold; S5.2. For tetrahedral meshes Perform optimization and repair; detect non-manifold edges (shared by more than two faces) and isolated vertices between boundary patches, apply edge collapse and vertex splitting operations, and the optimization goal is to minimize mesh geometry errors and topological complexity: ; in, is the regularization coefficient, balancing geometric error and topological complexity, is the original mesh, For the optimized mesh, is the topological complexity of the mesh (e.g. number of holes); S5.3. Using Tetrahedral Meshes Calculate material volume; select internal base point , each surface triangle and Tetrahedron ,pass ,in, is the number of tetrahedrons, is the edge vector of the nth tetrahedron.

[0047] Through the above steps, a surface topology structure close to the real material surface can be generated when the material surface is complex, and the problems of surface mesh repetitiveness and incompleteness can be avoided.

[0048] The slicing method can also be used to calculate the volume of the material point cloud to be calculated. The slicing method slices the material point cloud to be calculated along a certain direction, calculates the area of ​​each slice, and then adds the areas of all slices and multiplies them by the thickness of the slice to get the total volume. This is the existing technology and will not be explained in detail here.

[0049] It should be understood that the present invention can be used not only for measuring the volume of granaries, but also for measuring the volume of other materials; not only for cylindrical granaries, but also for granaries of other shapes; currently, almost all granaries are cylindrical.

[0050] The embodiment of the present invention provides an adaptive incomplete deformation cavity three-dimensional point cloud volume accurate calculation system, which is used to calculate the volume of the cavity three-dimensional point cloud, and includes: Data acquisition module, used for automatic acquisition or manual import of point cloud data; A data processing module, used for performing volume calculation based on the point cloud data in the data acquisition module; A data transmission module, used for transmitting the three-dimensional point cloud volume of the cavity calculated by the data processing module to the terminal; The volume calculation method used in the data processing module is the above-mentioned adaptive incomplete deformation cavity three-dimensional point cloud volume accurate calculation method.

[0051] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: Obtain a reference point cloud; the reference point cloud is a directly measured empty warehouse point cloud or a virtual empty warehouse point cloud generated by combining historical cavity point clouds and grain warehouse design drawings; The real-time cavity point cloud is segmented to obtain the material surface point cloud, and the reference point cloud is segmented into the warehouse wall point cloud above the material surface and the warehouse wall point cloud below the material surface through the material surface point cloud; The warehouse wall point cloud below the material surface in the segmented reference point cloud and the material surface point cloud of the real-time cavity point cloud are merged to obtain the material point cloud to be calculated; The point cloud volume of the material to be calculated.

[0052] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0053] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. 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 disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0054] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. 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.

[0055] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate 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 A function specified in one or more boxes.

[0056] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0057] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other 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.

[0058] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for accurately calculating the volume of a cavity three-dimensional point cloud with adaptive incomplete deformation, characterized in that: The steps include: Obtain a reference point cloud; the reference point cloud is a directly measured empty warehouse point cloud or a virtual empty warehouse point cloud generated by combining historical cavity point clouds and grain warehouse design drawings; The real-time cavity point cloud is segmented to obtain the material surface point cloud, and the reference point cloud is segmented into the warehouse wall point cloud above the material surface and the warehouse wall point cloud below the material surface through the material surface point cloud; The warehouse wall point cloud below the material surface in the segmented reference point cloud and the material surface point cloud of the real-time cavity point cloud are merged to obtain the material point cloud to be calculated; The point cloud volume of the material to be calculated.

2. The method for accurately calculating the volume of a cavity three-dimensional point cloud with adaptive incomplete deformation according to claim 1 is characterized in that: The obtaining of the reference point cloud comprises: If the empty warehouse point cloud can be directly measured, the measured empty warehouse point cloud is used as the reference point cloud, or the historical cavity point cloud that meets the requirements of the first volume confidence interval is directly selected as the reference point cloud; otherwise, a virtual empty warehouse point cloud is constructed as the reference point cloud through the historical cavity point cloud and the granary geometric parameters.

3. The method for accurately calculating the volume of a cavity three-dimensional point cloud with adaptive incomplete deformation according to claim 2 is characterized in that: The construction of a virtual empty warehouse point cloud as a reference point cloud using the historical cavity point cloud and the warehouse geometric parameters includes: Selecting the historical cavity point cloud that meets the second volume confidence interval requirement; Align the historical cavity point cloud axis with the central axis of the granary design drawing; The historical cavity point cloud after axial alignment and the design parameters of the granary are fused to obtain the virtual empty silo point cloud; The virtual empty warehouse point cloud is compensated for errors to obtain the reference point cloud.

4. The method for accurately calculating the volume of a cavity three-dimensional point cloud with adaptive incomplete deformation according to claim 3 is characterized in that: The first volume confidence interval is ; The second volume confidence interval is , is the volume confidence, defined as: ； in, is the volume of a historical cavity point cloud, It is the theoretical volume in the empty warehouse state.

5. The method for accurately calculating the volume of a cavity three-dimensional point cloud with adaptive incomplete deformation according to claim 3 is characterized in that: The virtual empty warehouse point cloud is obtained by fusing the historical cavity point cloud after axial alignment with the design parameters of the granary: The virtual empty warehouse point cloud to be reconstructed includes the measured segment and the extended segment. The measured segment directly adopts the warehouse in the historical cavity point cloud. wall point; the extended section is divided into side walls and silo bottom, and the side walls are based on the side wall height in the silo design drawing By axial stretching: ； ； in, is the side wall height of the historical cavity point cloud, is the difference between the side wall height of the granary design drawing and the side wall height of the historical cavity point cloud. is the stretch coefficient, is the virtual warehouse wall point coordinate of the side wall of the extension section, is the coordinate of the highest point of the measured segment, It is the axial direction of the granary; The silo bottom is a flat silo bottom or a conical silo bottom. The flat silo bottom is based on the height of the design drawing. The bottom boundary of the projected side wall generates a uniformly rasterized point cloud; the bottom of the conical silo is driven by the design drawing parameters and generates a point cloud based on the discretization of the parametric analytical surface, which is expressed as: ； in, It is a conical silo bottom. For the cone top of the drawing, For the half-width of the drawing, is the drawing radius, ] is the radial distance, is the azimuth, Perpendicular to the axis The plane orthogonal basis vectors of ; The topological closure fusion of the side wall and warehouse bottom point cloud is achieved through the normal vector consistency constraint and the nearest neighbor interpolation algorithm based on KD-Tree; The measured section and the extended section are spliced ​​together to obtain the virtual empty warehouse point cloud.

6. The method for accurately calculating the volume of a cavity three-dimensional point cloud with adaptive incomplete deformation according to claim 1 is characterized in that: The method of segmenting the real-time cavity point cloud to obtain the material surface point cloud, and segmenting the reference point cloud into the warehouse wall point cloud above the material surface and the warehouse wall point cloud below the material surface through the material surface point cloud comprises the following steps: Spatial registration of real-time cavity point cloud and reference point cloud; Perform difference distance field calculation and spatial mapping on real-time cavity point cloud; Adaptive threshold segmentation of material surface and warehouse wall of real-time cavity point cloud; Perform morphological optimization and topological verification on material surface point cloud; Based on the material surface point cloud of the cavity point cloud, the reference point cloud is divided into the warehouse wall point cloud above the material surface and the warehouse wall point cloud below the material surface.

7. The method for accurately calculating the volume of a cavity three-dimensional point cloud with adaptive incomplete deformation according to claim 6 is characterized in that: The material surface point cloud based on the cavity point cloud, dividing the reference point cloud into a warehouse wall point cloud above the material surface and a warehouse wall point cloud below the material surface includes: Material surface height field modeling; from the material surface point cloud, calculate its height distribution field : ； in, is the horizontal projection neighborhood of the material surface, Points on the material surface The vertical coordinate of Based on height distribution field , perform regional segmentation on the reference point cloud: (a) Point cloud of the warehouse wall below the material surface: ; (b) Point cloud of the warehouse wall above the material surface: ; in, is the reference point cloud, is a point on the reference point cloud The vertical coordinate of is the noise standard deviation.

8. The method for accurately calculating the volume of a cavity three-dimensional point cloud with adaptive incomplete deformation according to claim 7 is characterized in that: The step of fusing the warehouse wall point cloud below the material surface in the segmented reference point cloud and the material surface point cloud in the real-time cavity point cloud to obtain the material point cloud to be calculated comprises the following steps: Extract the boundary of the material surface point cloud through the α-shape algorithm And the boundary of the warehouse wall point cloud below the material surface ,in is a point on the boundary of the material surface point cloud. is the member function of α-shape; Construct KD-Tree acceleration structure to accelerate the boundary Perform a search with radius r, r=2 , is the radius search threshold, marker and boundary Overlapping Area , is a point on the boundary of the reference point cloud in the overlapping area, for For the Kth point on the material surface whose distance in the neighborhood is less than r, the non-maximum suppression strategy is used to eliminate redundant points; At the border With border Create buffer zones at junctions , the transition surface is fitted by the moving least squares method to achieve continuous fusion of the material surface point cloud and the warehouse wall point cloud below the material surface. The formula is as follows: ； in, and are two independent variables used to parameterize the surface, is the distance weight function, defined as , p represents the point in the parameter space (u, v) mapped to the three-dimensional space, is the shortest Euclidean distance from point p to the material surface boundary, is the buffer width, which controls the transition range of the fusion area. and They represent the local fitting surfaces of the material surface point cloud and the warehouse wall point cloud respectively. The transition surface representing the fusion area; Adopt a multi-resolution strategy based on Poisson disk sampling to adaptively adjust the point spacing in the fusion area ,in, is the resampling point spacing, and the minimum spacing between the material surface point cloud and the warehouse wall point cloud below the material surface is adaptively taken. is the average point spacing of the material surface point cloud, is the average point spacing of the warehouse wall point cloud below the material surface; Apply anisotropic curvature diffusion filtering to remove local distortion caused by noise: ； in, For point and its neighboring points The Gaussian curvature of quantifies the local surface curvature, Neighborhood points The normal vector indicates the local direction of the surface, For point The set of neighboring points of For the The three-dimensional coordinates of a point.

9. The method for accurately calculating the volume of a cavity three-dimensional point cloud with adaptive incomplete deformation according to claim 1 is characterized in that: After the historical cavity point cloud and the real-time cavity point cloud are acquired, they need to be preprocessed, including the following steps: The granary measurement point cloud is downsampled and outliers are removed; for the convenience of description, the historical point cloud and the real-time cavity point cloud are referred to as the granary measurement point cloud; Integrity assessment and repair of granary measurement point cloud.

10. The cavity three-dimensional point cloud volume accurate calculation system with adaptive incomplete deformation is characterized by: The system is used to calculate the volume of a three-dimensional point cloud of a cavity, and includes: Data acquisition module, used for automatic acquisition or manual import of point cloud data; A data processing module, used for performing volume calculation based on the point cloud data in the data acquisition module; A data transmission module, used for transmitting the three-dimensional point cloud volume of the cavity calculated by the data processing module to the terminal; The volume calculation method used in the data processing module is the precise calculation method for the three-dimensional point cloud volume of the cavity with adaptive incomplete deformation as described in any one of claims 1 to 9.

Images