A coal bunker bottom modeling method, device, equipment and storage medium

Abstract

This invention discloses a method, apparatus, device, and storage medium for modeling the bottom of a coal bunker. The method includes: acquiring bottom point cloud data of a target coal bunker; constructing a bottom geometric base based on the spatial distribution characteristics of the bottom point cloud data; mapping each point cloud coordinate point in the bottom point cloud data to the bottom geometric base to obtain a corresponding point cloud mapping point; for each point cloud mapping point, adjusting the height value of the point cloud mapping point based on the height value of its neighboring mapping points, and smoothing the adjusted point cloud mapping point to obtain a bottom mapping model; projecting and rendering the bottom mapping model in three-dimensional space to obtain a three-dimensional model of the bottom of the target coal bunker. The technical solution of this invention solves the problem in existing technologies where coal bunker bottom modeling cannot accurately reflect the actual shape, by performing point cloud smoothing based on the height value of neighboring point clouds, thus improving the accuracy of coal bunker bottom modeling.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of coal management technology, and in particular to a method, apparatus, equipment and storage medium for modeling the bottom of a coal bunker. Background Technology

[0002] Coal is a vital energy resource in my country, and its storage management is crucial for ensuring energy security and improving operational efficiency. As a key facility for coal storage, the accurate perception of the bottom morphology of coal bunkers is fundamental to achieving precise location measurement, automated emptying, and safe operations. Acquiring point cloud data of the coal bunker bottom using 3D laser scanning technology and performing high-fidelity 3D rendering is a core step in building a digital twin warehouse and realizing intelligent management.

[0003] Due to the unique and complex working environment at the bottom of coal bunkers, existing technologies have significant limitations in practical applications, mainly reflected in the following aspects: Poor point cloud data quality leads to model distortion: Coal bunkers are typically poorly lit and dusty, and the coal surface itself has low reflectivity, resulting in a large number of missing, sparse, and noisy raw point cloud data. Existing preprocessing algorithms often fail to address these severe data defects, struggling to achieve effective point cloud completion and depth smoothing. This leads to the final 3D model exhibiting holes, geometric distortions, or loss of detail, failing to accurately reflect the actual shape of the coal bunker bottom (especially funnel-shaped structures). Summary of the Invention

[0004] This invention provides a method, apparatus, device, and storage medium for modeling the bottom of a coal bunker. The technical solution of this invention can perform point cloud smoothing based on the height value of the neighboring point cloud, thereby improving the accuracy of coal bunker bottom modeling.

[0005] In a first aspect, embodiments of the present invention provide a method for modeling the bottom of a coal bunker, the method comprising: Obtain bottom point cloud data of the target coal bunker, construct a bottom geometric base based on the spatial distribution characteristics of the bottom point cloud data, and map each point cloud coordinate point in the bottom point cloud data to the bottom geometric base to obtain a corresponding point cloud mapping point; for each point cloud mapping point, adjust the height value of the point cloud mapping point based on the height value of the neighboring mapping points corresponding to the point cloud mapping point, and smooth the adjusted point cloud mapping point to obtain a bottom mapping model; project and render the bottom mapping model in three-dimensional space to obtain a three-dimensional model of the bottom of the coal bunker corresponding to the target coal bunker.

[0006] Secondly, embodiments of the present invention provide a coal bunker bottom modeling device, the device comprising: The point cloud mapping module is used to acquire bottom point cloud data of the target coal bunker, construct a bottom geometric base based on the spatial distribution characteristics of the bottom point cloud data, and map each point cloud coordinate point in the bottom point cloud data to the bottom geometric base to obtain the corresponding point cloud mapping point; the point cloud smoothing module is used to adjust the height value of each point cloud mapping point based on the height value of the neighboring mapping points corresponding to the point cloud mapping point, and smooth the adjusted point cloud mapping point to obtain the bottom mapping model; the three-dimensional model construction module is used to project and render the bottom mapping model in three-dimensional space to obtain the three-dimensional model of the bottom of the coal bunker corresponding to the target coal bunker.

[0007] Thirdly, embodiments of the present invention provide a computer device, the computer device comprising: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the coal bunker bottom modeling method described in any embodiment.

[0008] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the coal bunker bottom modeling method described in any embodiment.

[0009] The technical solution provided by this invention involves acquiring bottom point cloud data of a target coal bunker, constructing a bottom geometric base based on the spatial distribution characteristics of the bottom point cloud data, and mapping each point cloud coordinate point in the bottom point cloud data to the bottom geometric base to obtain a corresponding point cloud mapping point. For each point cloud mapping point, the height value of the point cloud mapping point is adjusted based on the height value of its neighboring mapping points, and the adjusted point cloud mapping point is smoothed to obtain a bottom mapping model. The bottom mapping model is then projected and rendered in three-dimensional space to obtain a three-dimensional model of the bottom of the coal bunker corresponding to the target coal bunker. This invention solves the problem in existing technologies where coal bunker bottom modeling cannot accurately reflect the actual shape, as it can perform point cloud smoothing based on the height value of neighboring point clouds, thus improving the accuracy of coal bunker bottom modeling. Attached Figure Description

[0010] Figure 1 This is a flowchart of a coal bunker bottom modeling method provided in an embodiment of the present invention; Figure 2 This is a flowchart of another coal bunker bottom modeling method provided in an embodiment of the present invention; Figure 3 This is a flowchart illustrating a process for modeling the bottom of a coal bunker, as provided in an embodiment of the present invention. Figure 4 This is a schematic diagram of the structure of a coal bunker bottom modeling device provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. The acquisition, storage, use, and processing of data in the technical solutions of the embodiments of the present invention all comply with the relevant provisions of national laws and regulations.

[0012] Figure 1 This is a flowchart of a coal bunker bottom modeling method provided by an embodiment of the present invention. The embodiment of the present invention can be applied to the three-dimensional modeling of the bottom of a coal bunker. The method can be executed by a coal bunker bottom modeling device, which can be implemented by software and / or hardware.

[0013] like Figure 1 As shown, the method for modeling the bottom of a coal bunker includes the following steps: S110. Obtain the bottom point cloud data of the target coal bunker, construct the bottom geometric base based on the spatial distribution characteristics of the bottom point cloud data, and map each point cloud coordinate point in the bottom point cloud data to the bottom geometric base to obtain the corresponding point cloud mapping point.

[0014] The bottom point cloud data can be obtained by scanning the bottom of the target coal bunker. Since the bottom point cloud data consists of multiple discrete coordinate points at the bottom of the target coal bunker, it cannot accurately reflect the true shape of the bottom. Therefore, interpolation and smoothing processing are required to restore the true shape of the bottom. The bottom geometric base can be the background base used to construct the bottom model of the target coal bunker. Specifically, the spatial distribution characteristics of the bottom point cloud data can be analyzed to determine the size requirements for constructing the base, and then a bottom geometric base with uniform point cloud density can be constructed based on these size requirements. The point cloud mapping point can be the coordinate point corresponding to the point cloud coordinate point in the bottom point cloud data on the bottom geometric base. Specifically, for each point cloud coordinate point in the bottom point cloud data, the point cloud coordinate point can be mapped onto the bottom geometric base to obtain the corresponding point cloud mapping point.

[0015] Because the bottom point cloud data is massive and the point cloud density is not unique in different areas, direct interpolation can easily lead to holes, geometric distortions, or loss of detail in the final 3D model. Therefore, by constructing a bottom geometric base with uniform density, the fitting distortion and structural blurring problems caused by forced interpolation on sparse point clouds with uneven heights caused by upsampling algorithms are avoided. It can not only achieve more complete and geometrically reasonable completion of large-scale holes, but also eliminate density jumps when dealing with areas with extremely large differences in point cloud density, generating smooth surfaces with extremely high topological consistency.

[0016] S120. For each point cloud mapping point, adjust the height value of the point cloud mapping point based on the height value of the neighboring mapping points corresponding to the point cloud mapping point, and smooth the adjusted point cloud mapping point to obtain the bottom mapping model.

[0017] In this context, "neighborhood mapping points" refers to the other mapping points ultimately determined and distributed within the neighborhood of the point cloud mapping point. Specifically, for each point cloud mapping point, other mapping points within a preset range around it can be considered as neighboring mapping points. Furthermore, to smooth the outer contour of the bottom model, the height value of the point cloud mapping point can be adaptively adjusted based on the height values ​​of its corresponding neighboring mapping points. Further, the bottom mapping model can be a model of the bottom of the target coal bunker built within a bottom geometric base. Specifically, the adjusted point cloud mapping points can be connected and smoothed to obtain the bottom mapping model.

[0018] S130. Project and render the bottom mapping model in three-dimensional space to obtain the three-dimensional model of the bottom of the target coal bunker.

[0019] The 3D model of the coal bunker bottom can be the final generated 3D model of the bottom of the target coal bunker. Since the bottom mapping model is the initially generated bottom model, it cannot accurately reproduce the 3D information and color structure of the bottom of the target coal bunker. Therefore, the bottom mapping model can be projected and rendered in 3D space to obtain the final 3D model of the coal bunker bottom.

[0020] The technical solution provided by this invention involves acquiring bottom point cloud data of a target coal bunker, constructing a bottom geometric base based on the spatial distribution characteristics of the bottom point cloud data, and mapping each point cloud coordinate point in the bottom point cloud data to the bottom geometric base to obtain a corresponding point cloud mapping point. For each point cloud mapping point, the height value of the point cloud mapping point is adjusted based on the height value of its neighboring mapping points, and the adjusted point cloud mapping point is smoothed to obtain a bottom mapping model. The bottom mapping model is then projected and rendered in three-dimensional space to obtain a three-dimensional model of the bottom of the target coal bunker. This invention solves the problem in existing technologies where coal bunker bottom modeling fails to accurately reflect the actual shape, as it can perform point cloud smoothing based on the height value of neighboring point clouds, thus improving the accuracy of coal bunker bottom modeling.

[0021] Figure 2 This is a flowchart of another coal bunker bottom modeling method provided by an embodiment of the present invention. This embodiment of the present invention can be applied to the three-dimensional modeling of the bottom of a coal bunker. Based on the above embodiments, this embodiment further explains how to construct the bottom geometric base based on the spatial distribution characteristics of the bottom point cloud data; how to adjust the height value of the point cloud mapping point based on the height value of the neighboring mapping point corresponding to the point cloud mapping point, and smooth the adjusted point cloud mapping point to obtain the bottom mapping model; and how to project and render the bottom mapping model in three-dimensional space to obtain the three-dimensional model of the bottom of the coal bunker corresponding to the target coal bunker. This device can be implemented by software and / or hardware and integrated into a computer device with application development functions.

[0022] like Figure 2 As shown, the method for modeling the bottom of a coal bunker includes the following steps: S210. Obtain the bottom point cloud data of the target coal bunker, determine the reference diameter based on the spatial distribution characteristics of the bottom point cloud data, construct a circular point cloud network with the reference diameter, use the circular point cloud network as the bottom geometric base, and map each point cloud coordinate point in the bottom point cloud data to the bottom geometric base to obtain the corresponding point cloud mapping point.

[0023] The bottom point cloud data can be obtained by scanning the bottom of the target coal bunker. Since the bottom point cloud data consists of multiple discrete coordinate points at the bottom of the target coal bunker and cannot accurately reflect the true shape of the bottom, interpolation and smoothing processing are required to restore the true shape of the bottom. The reference diameter can be the diameter used to construct the base of the coal bunker's bottom. Specifically, the spatial distribution characteristics between point cloud coordinate points (including the three-dimensional coordinates of the point cloud coordinate points) can be analyzed based on the bottom point cloud data, and the corresponding reference diameter can be determined based on a standard that encompasses all point cloud coordinate points.

[0024] Furthermore, the circular point cloud network is a cylindrical base with uniform point cloud density constructed using a reference diameter. The point cloud mapping point can be the coordinate point on the bottom geometric base corresponding to a point cloud coordinate point in the bottom point cloud data. Specifically, for each point cloud coordinate point in the bottom point cloud data, the point cloud coordinate point can be mapped onto the bottom geometric base, thus obtaining the corresponding point cloud mapping point.

[0025] Because the bottom point cloud data is massive and the point cloud density is not unique in different areas, direct interpolation can easily lead to holes, geometric distortions, or loss of detail in the final 3D model. Therefore, by constructing a bottom geometric base with uniform density, the fitting distortion and structural blurring problems caused by forced interpolation on sparse point clouds with uneven heights caused by upsampling algorithms are avoided. It can not only achieve more complete and geometrically reasonable completion of large-scale holes, but also eliminate density jumps when dealing with areas with extremely large differences in point cloud density, generating smooth surfaces with extremely high topological consistency.

[0026] Optionally, the reference diameter is determined based on the spatial distribution characteristics of the bottom point cloud data, including: determining the horizontal coordinate data of each point cloud coordinate point based on the bottom point cloud data, determining the horizontal distance between every two point cloud coordinate points based on the horizontal coordinate data, and using the maximum value of the horizontal distance as the reference diameter. By selecting the maximum value of the horizontal distance as the reference diameter, the bottom geometric base subsequently generated based on the reference diameter can encompass all point cloud coordinate points in the bottom point cloud data, ensuring the integrity of the coal bunker bottom model.

[0027] S220. For each point cloud mapping point, a spherical neighborhood is constructed with the point cloud mapping point as the center and a preset neighborhood radius, and other mapping points within the spherical neighborhood are used as the neighborhood mapping points corresponding to the point cloud mapping point.

[0028] The preset neighborhood radius can be a pre-defined radius used to determine the coordinates of neighboring points. Specifically, the preset neighborhood radius can be set manually or determined based on the spatial distribution characteristics of the bottom point cloud data; this is not limited here. Furthermore, the spherical neighborhood can be a spherical region used to determine whether something belongs to the neighborhood of a point cloud mapping point. Specifically, a spherical region centered on the point cloud mapping point and with a preset neighborhood radius as its radius can be considered the spherical neighborhood. Other mapping points refer to point cloud mapping points other than the currently analyzed point cloud mapping point. Neighborhood mapping points are the other mapping points ultimately determined to be distributed within the neighborhood of the point cloud mapping point.

[0029] S230. Calculate the local average height value by weighted averaging of the height values ​​of all neighborhood mapping points, and adjust the height values ​​of the point cloud mapping points based on the local average height value.

[0030] The local average height value can be the average height of other mapped points within the neighborhood of the point cloud mapping point. After determining the local average height value, it can replace the height value of the point cloud mapping point.

[0031] Optionally, adjusting the height value of the point cloud mapping point based on the local average height value includes: counting the number of neighboring mapping points corresponding to the point cloud mapping point, and determining the height adjustment weight corresponding to the point cloud mapping point based on the number of neighboring mapping points; and using the product of the local average height value and the height adjustment weight as the height value of the point cloud mapping point.

[0032] The height adjustment weight can be a weighting coefficient used to adjust the local average height value. Specifically, a pre-defined correspondence between the number of neighboring mapping points and the height adjustment weight can be established, and then the height adjustment weight for each cloud mapping point can be determined based on this correspondence. For example, the number of neighboring mapping points and the height adjustment weight can be positively correlated; the more neighboring mapping points there are, the larger the height adjustment weight, indicating a higher reliability of the local average height value; conversely, the fewer neighboring mapping points there are, the smaller the height adjustment weight, indicating a lower reliability of the local average height value. During the smoothing process, through reasonable control of the neighborhood range and weight allocation, it can be ensured that the filtering operation eliminates microscopic noise without excessively smoothing out the macroscopic geometric features that should exist at the bottom of the coal bunker (such as the slope of the coal chute and the outline of the unloading port), thus achieving the best balance between noise reduction and shape preservation.

[0033] S240. Based on the geometric distribution relationship between the point cloud mapping points, determine the transition coordinate points from the base coordinate points in the bottom geometric base. Based on the transition coordinate points as intermediate points, connect and smooth the point cloud mapping points to obtain the bottom mapping model.

[0034] The base coordinate points can be point cloud coordinate points inherent in the bottom geometric base, serving as the background. Transition coordinate points can be base coordinate points traversed between point cloud mapping points. Specifically, based on the geometric distribution relationship between point cloud mapping points, the base coordinate points traversed to connect the point cloud mapping points can be used as transition coordinate points. Since the density of point cloud coordinate points in the bottom geometric base is uniform, using base coordinate points as transition points for smoothing avoids the fitting distortion and structural ambiguity problems caused by forced interpolation on highly uneven sparse point clouds in existing technologies. This not only enables more complete and geometrically reasonable completion of large-scale voids but also eliminates density jumps and generates smooth surfaces with extremely high topological consistency when dealing with areas of extreme point cloud density differences. The bottom mapping model can be a model of the bottom of the target coal bunker established in the bottom geometric base. Specifically, the bottom mapping model can be obtained by connecting and smoothing point cloud mapping points based on transition coordinate points as intermediate points.

[0035] S250. Project and render the bottom mapping model in three-dimensional space to obtain the three-dimensional model of the bottom of the target coal bunker.

[0036] The 3D model of the coal bunker bottom can be the final generated 3D model of the bottom of the target coal bunker. Since the bottom mapping model is the initially generated bottom model, it cannot accurately reproduce the 3D information and color structure of the bottom of the target coal bunker. Therefore, the bottom mapping model can be projected and rendered in 3D space to obtain the final 3D model of the coal bunker bottom.

[0037] Specifically, the bottom mapping model can be projected along the normal vector direction of the point cloud to determine the corresponding 3D network topology, and an initial bottom 3D model can be constructed based on the 3D network topology; the initial bottom 3D model can be rendered based on a preset 3D rendering engine to obtain the bottom 3D model of the coal bunker.

[0038] For example, in order to better understand the technical solution provided by the present invention, specific embodiments are described below: Figure 3 This is a flowchart illustrating a process for modeling the bottom of a coal bunker, as provided in an embodiment of the present invention. Figure 3 As shown, the workflow for modeling the bottom of a coal bunker includes the following steps: Phase 1: Construction of a Regularized Data Base and Data Completion. This phase aims to fundamentally address the issues of sparsity, missing data, and uneven density in point clouds, thereby constructing an ideal and regular data base for subsequent processing.

[0039] Step 1.1: Spatial Feature Analysis and Reference Radius Calculation Spatial distribution feature diagnosis was performed on the collected point cloud of the original coal bunker bottom. Based on the spatial distribution features of the original coal bunker point cloud, an optimal baseline radius was calculated and defined. This radius serves as the geometric basis for subsequently constructing a regularized base.

[0040] Step 1.2: Generation of density-fixed regular point cloud basis Using the aforementioned baseline radius as the core parameter, an ideal circular point cloud mesh with uniform and fixed density is generated on a two-dimensional horizontal plane, covering the entire bottom projection area of ​​the coal bunker. This step is equivalent to preparing a regular "digital canvas" for subsequent reconstruction, eliminating the inherent defect of uneven density in the original point cloud from the root.

[0041] Step 1.3: Mapping Elevation Information Based on Surface Fitting The real terrain undulation information represented by the original sparse point cloud is completely mapped onto the regular point cloud base generated in step 1.2 using a precise elevation surface fitting algorithm. This algorithm ensures that the height values ​​of the completed area smoothly transition and seamlessly connect with the surrounding original data, thereby achieving simultaneous completion of data completion and density normalization.

[0042] The second stage: noise suppression and surface smoothing. In this stage, based on the completed, high-quality point cloud with fixed density, noise reduction and smoothing are performed to improve the visual quality and geometric realism of the model.

[0043] Step 2.1: Adaptive sliding window traversal of local neighborhood Design a dynamic sliding window centered on each point to systematically traverse the entire completed point cloud dataset. This window should be able to adapt to the point cloud density, ensuring consistency in the computational scope.

[0044] Step 2.2: Calculation of local elevation weighted average For each point within the sliding window (i.e., for each point cloud mapping point), the algorithm obtains the height values ​​of all points in its specific neighborhood (neighborhood mapping points) and performs a precise local elevation-weighted average calculation. This process is essentially a convolutional smoothing filter, which can effectively suppress small, abnormal fluctuations caused by scanning instrument noise or environmental interference.

[0045] Step 2.3: Preservation of macroscopic geometric features During the smoothing process, reasonable neighborhood range control and weight allocation ensure that the filtering operation eliminates micro-noise without excessively smoothing out the macro-geometric features that should exist at the bottom of the coal bunker (such as the slope of the coal chute and the outline of the unloading port), thereby achieving the best balance between noise reduction and shape preservation.

[0046] Phase 3: 3D Mesh Model Reconstruction. This phase transforms the processed point cloud into a 3D mesh model that can be used for rendering and interaction.

[0047] Step 3.1: Execute the greedy projection triangulation algorithm The point cloud, after the first two stages of deep optimization, is input into a greedy projection triangulation algorithm. This algorithm projects along the normal vector direction of the point cloud to quickly and efficiently construct the optimal triangular mesh topology in the two-dimensional parameter domain, and then maps it back to three-dimensional space.

[0048] Step 3.2: Visualization Rendering and Output The generated triangular mesh model is imported into a 3D rendering engine, and the final output is a high-precision, highly realistic 3D visualization model of the bottom of the coal bunker, which can be directly used for advanced applications such as bunker location calculation, safety monitoring and operation simulation.

[0049] The technical solution provided by this invention has the following beneficial effects: 1. Density-Fixed Point Cloud Completion Based on Reference Radius and Regularized Basis: Compared to traditional upsampling point cloud completion algorithms, the density-fixed completion algorithm adopted in this invention exhibits significant advantages in processing point clouds at the bottom of coal bunkers. This algorithm fundamentally avoids the fitting distortion and structural ambiguity problems caused by forced interpolation on sparse point clouds with uneven heights, by constructing a reference geometric basis with uniform density. It can not only achieve more complete and geometrically reasonable completion of large-scale voids, but also eliminate density jumps and generate smooth surfaces with extremely high topological consistency when processing areas with significant point cloud density differences. Furthermore, because this algorithm avoids the complex iterative calculations and global optimizations of upsampling, its computational efficiency is significantly improved, making it more suitable for real-time or near-real-time processing needs in industrial settings.

[0050] 2. Adaptive Smoothing Based on Local Neighborhood Averaging: Compared to point cloud smoothing algorithms based on least squares, the adaptive smoothing method based on local neighborhood averaging adopted in this invention demonstrates superior engineering applicability when processing massive coal bunker point cloud data. Least squares uses complex matrix operations to find the global optimum, causing its computational complexity to increase quadratically or even exponentially with the amount of data, making it difficult to meet real-time processing requirements. This method, however, reduces the complexity to a linear level through local, discrete sliding window averaging, achieving an order-of-magnitude efficiency improvement. More importantly, through carefully designed neighborhood range control, this method efficiently suppresses noise while adaptively preserving key geometric features such as the macroscopic slope and boundaries at the bottom of the coal bunker, avoiding the feature smoothing problem that may occur with least squares due to overfitting.

[0051] The technical solution provided in this invention involves acquiring bottom point cloud data of a target coal bunker, determining a reference diameter based on the spatial distribution characteristics of the bottom point cloud data, constructing a circular point cloud network using the reference diameter, and using the circular point cloud network as the bottom geometric base. Each point cloud coordinate point in the bottom point cloud data is mapped to the bottom geometric base to obtain a corresponding point cloud mapping point. For each point cloud mapping point, a spherical neighborhood is constructed with the point cloud mapping point as the center and a preset neighborhood radius. Other mapping points within the spherical neighborhood are used as the corresponding neighborhood mapping points. The height values ​​of all neighborhood mapping points are weighted and averaged to obtain a local average height value, and the height value of the point cloud mapping point is adjusted based on the local average height value. Based on the geometric distribution relationship between the point cloud mapping points, transition coordinate points are determined from the base coordinate points in the bottom geometric base. These transition coordinate points are used as intermediate points to connect and smooth the point cloud mapping points, resulting in a bottom mapping model. The bottom mapping model is then projected and rendered in three-dimensional space to obtain a three-dimensional model of the bottom of the target coal bunker. The technical solution of this invention solves the problem that the actual shape cannot be accurately reflected when modeling the bottom of a coal bunker in the prior art. It can perform point cloud smoothing based on the height value of the neighboring point cloud, thereby improving the accuracy of coal bunker bottom modeling.

[0052] Figure 4 This is a schematic diagram of a coal bunker bottom modeling device provided in an embodiment of the present invention. The embodiment of the present invention can be applied to the three-dimensional modeling of the bottom of a coal bunker. The device can be implemented by software and / or hardware and integrated into a computer device with application development capabilities.

[0053] like Figure 4 As shown, the coal bunker bottom modeling device includes: a point cloud mapping module 310, a point cloud smoothing module 320, and a three-dimensional model construction module 330.

[0054] The point cloud mapping module 310 is used to acquire bottom point cloud data of the target coal bunker, construct a bottom geometric base based on the spatial distribution characteristics of the bottom point cloud data, and map each point cloud coordinate point in the bottom point cloud data to the bottom geometric base to obtain a corresponding point cloud mapping point; the point cloud smoothing module 320 is used to adjust the height value of each point cloud mapping point based on the height value of the neighboring mapping points corresponding to the point cloud mapping point, and smooth the adjusted point cloud mapping point to obtain a bottom mapping model; the three-dimensional model construction module 330 is used to project and render the bottom mapping model in three-dimensional space to obtain a three-dimensional model of the bottom of the coal bunker corresponding to the target coal bunker.

[0055] The technical solution provided by this invention involves acquiring bottom point cloud data of a target coal bunker, constructing a bottom geometric base based on the spatial distribution characteristics of the bottom point cloud data, and mapping each point cloud coordinate point in the bottom point cloud data to the bottom geometric base to obtain a corresponding point cloud mapping point. For each point cloud mapping point, the height value of the point cloud mapping point is adjusted based on the height value of its neighboring mapping points, and the adjusted point cloud mapping point is smoothed to obtain a bottom mapping model. The bottom mapping model is then projected and rendered in three-dimensional space to obtain a three-dimensional model of the bottom of the coal bunker corresponding to the target coal bunker. This invention solves the problem in existing technologies where coal bunker bottom modeling cannot accurately reflect the actual shape, as it can perform point cloud smoothing based on the height value of neighboring point clouds, thus improving the accuracy of coal bunker bottom modeling.

[0056] In one optional implementation, the point cloud mapping module 310 includes: a base construction unit, configured to: determine a reference diameter based on the spatial distribution characteristics of the bottom point cloud data, construct a circular point cloud network with the reference diameter, and use the circular point cloud network as the bottom geometric base; wherein the circular point cloud network is a cylinder with uniform point cloud density constructed with the reference diameter as its diameter.

[0057] In one optional implementation, the base construction unit includes a reference diameter determination subunit, configured to: determine the horizontal coordinate data of each point cloud coordinate point based on the bottom point cloud data, determine the horizontal distance between every two point cloud coordinate points based on the horizontal coordinate data, and use the maximum value of the horizontal distance as the reference diameter.

[0058] In one optional implementation, the point cloud smoothing module 320 includes: a point cloud height adjustment unit, configured to: construct a spherical neighborhood with the point cloud mapping point as the center and a preset neighborhood radius, and use other mapping points within the spherical neighborhood as the neighborhood mapping points corresponding to the point cloud mapping point; calculate a local average height value by weighted averaging the height values ​​of all neighborhood mapping points, and adjust the height value of the point cloud mapping point based on the local average height value.

[0059] In one optional implementation, the point cloud height adjustment unit includes: a local height analysis subunit, configured to: count the number of neighboring mapping points corresponding to the point cloud mapping point, and determine the height adjustment weight corresponding to the point cloud mapping point based on the number of neighboring mapping points; and use the product of the local average height value and the height adjustment weight as the height value of the point cloud mapping point.

[0060] In one optional implementation, the point cloud smoothing module 320 includes a smoothing processing unit, configured to: determine transition coordinate points from the base coordinate points in the bottom geometric base based on the geometric distribution relationship between the point cloud mapping points, and connect and smooth the point cloud mapping points based on the transition coordinate points as intermediate points to obtain the bottom mapping model.

[0061] In one optional implementation, the 3D model construction module 330 is specifically used to: project the bottom mapping model along the normal vector direction of the point cloud, determine the 3D network topology corresponding to the bottom mapping model, and construct an initial bottom 3D model based on the 3D network topology; and render the initial bottom 3D model based on a preset 3D rendering engine to obtain the bottom 3D model of the coal bunker.

[0062] The coal bunker bottom modeling device provided in this embodiment of the invention can execute the coal bunker bottom modeling method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0063] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Figure 5 A block diagram of an exemplary computer device 12 suitable for implementing embodiments of the present invention is shown. Figure 5 The computer device 12 shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of the present invention. The computer device 12 can be any terminal device with computing capabilities and can be configured in the coal bunker bottom modeling device.

[0064] like Figure 5 As shown, the computer device 12 is represented in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0065] Bus 18 can be one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0066] Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0067] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 5 Not shown; usually referred to as a "hard drive"). Although Figure 5 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0068] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0069] Computer device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with the computer device 12, and / or with any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 22. Furthermore, computer device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. Figure 5 As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18. It should be understood that, although... Figure 5As not shown, it can be used in conjunction with computer device 12 with other hardware and / or software modules, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0070] Processing unit 16 executes various functional applications and data processing by running programs stored in system memory 28, such as implementing the coal bunker bottom modeling method provided in this embodiment of the invention, which includes: Obtain bottom point cloud data of the target coal bunker, construct a bottom geometric base based on the spatial distribution characteristics of the bottom point cloud data, and map each point cloud coordinate point in the bottom point cloud data to the bottom geometric base to obtain a corresponding point cloud mapping point; for each point cloud mapping point, adjust the height value of the point cloud mapping point based on the height value of the neighboring mapping points corresponding to the point cloud mapping point, and smooth the adjusted point cloud mapping point to obtain a bottom mapping model; project and render the bottom mapping model in three-dimensional space to obtain a three-dimensional model of the bottom of the coal bunker corresponding to the target coal bunker.

[0071] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the coal bunker bottom modeling method as provided in any embodiment of the present invention, including: Obtain bottom point cloud data of the target coal bunker, construct a bottom geometric base based on the spatial distribution characteristics of the bottom point cloud data, and map each point cloud coordinate point in the bottom point cloud data to the bottom geometric base to obtain a corresponding point cloud mapping point; for each point cloud mapping point, adjust the height value of the point cloud mapping point based on the height value of the neighboring mapping points corresponding to the point cloud mapping point, and smooth the adjusted point cloud mapping point to obtain a bottom mapping model; project and render the bottom mapping model in three-dimensional space to obtain a three-dimensional model of the bottom of the coal bunker corresponding to the target coal bunker.

[0072] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0073] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0074] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0075] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as C, Java, Smalltalk, C++, C#, and Python, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0076] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0077] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for modeling the bottom of a coal bunker, characterized in that, include: Obtain bottom point cloud data of the target coal bunker, construct a bottom geometric base based on the spatial distribution characteristics of the bottom point cloud data, and map each point cloud coordinate point in the bottom point cloud data to the bottom geometric base to obtain the corresponding point cloud mapping point; For each point cloud mapping point, the height value of the point cloud mapping point is adjusted based on the height value of the neighboring mapping points corresponding to the point cloud mapping point, and the adjusted point cloud mapping point is smoothed to obtain the bottom mapping model. The bottom mapping model is projected and rendered in three-dimensional space to obtain the three-dimensional model of the bottom of the target coal bunker.

2. The method according to claim 1, characterized in that, The construction of the bottom geometric base based on the spatial distribution features of the bottom point cloud data includes: A reference diameter is determined based on the spatial distribution characteristics of the bottom point cloud data, a circular point cloud network is constructed using the reference diameter, and the circular point cloud network is used as the bottom geometric base. The circular point cloud network is a cylinder with uniform point cloud density constructed with the reference diameter as its diameter.

3. The method according to claim 2, characterized in that, The determination of the reference diameter based on the spatial distribution characteristics of the bottom point cloud data includes: Based on the bottom point cloud data, the horizontal coordinate data of each point cloud coordinate point is determined, and the horizontal distance between every two point cloud coordinate points is determined based on the horizontal coordinate data. The maximum value of the horizontal distance is used as the reference diameter.

4. The method according to claim 1, characterized in that, Adjusting the height value of the point cloud mapping point based on the height value of the neighboring mapping points corresponding to the point cloud mapping point includes: A spherical neighborhood is constructed with the point cloud mapping point as the center and a preset neighborhood radius, and other mapping points within the spherical neighborhood are used as the neighborhood mapping points corresponding to the point cloud mapping point. The local average height value is obtained by weighted averaging of the height values ​​of all neighborhood mapping points, and the height value of the point cloud mapping points is adjusted based on the local average height value.

5. The method according to claim 4, characterized in that, Adjusting the height value of the point cloud mapping points based on the local average height value includes: The number of neighboring mapping points corresponding to the point cloud mapping point is counted, and the height adjustment weight corresponding to the point cloud mapping point is determined based on the number of neighboring mapping points. The product of the local average height value and the height adjustment weight is used as the height value of the point cloud mapping point.

6. The method according to claim 1, characterized in that, The process of smoothing the adjusted point cloud mapping points to obtain the bottom mapping model includes: Based on the geometric distribution relationship between the point cloud mapping points, transition coordinate points are determined from the base coordinate points in the bottom geometric base. The point cloud mapping points are then connected and smoothed using the transition coordinate points as intermediate points to obtain the bottom mapping model.

7. The method according to claim 1, characterized in that, The step of projecting and rendering the bottom mapping model in three-dimensional space to obtain the three-dimensional model of the bottom of the target coal bunker includes: The bottom mapping model is projected along the normal vector direction of the point cloud to determine the three-dimensional network topology corresponding to the bottom mapping model, and an initial bottom three-dimensional model is constructed based on the three-dimensional network topology. The initial bottom 3D model is rendered using a preset 3D rendering engine to obtain the bottom 3D model of the coal bunker.

8. A coal bunker bottom modeling device, characterized in that, The device includes: The point cloud mapping module is used to acquire the bottom point cloud data of the target coal bunker, construct a bottom geometric base based on the spatial distribution characteristics of the bottom point cloud data, and map each point cloud coordinate point in the bottom point cloud data to the bottom geometric base to obtain the corresponding point cloud mapping point. The point cloud smoothing module is used to adjust the height value of each point cloud mapping point based on the height value of the neighboring mapping points corresponding to the point cloud mapping point, and to smooth the adjusted point cloud mapping point to obtain the bottom mapping model. The 3D model construction module is used to project and render the bottom mapping model in 3D space to obtain the 3D model of the bottom of the target coal bunker.

9. A computer device, characterized in that, The computer device includes: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the coal bunker bottom modeling method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the coal bunker bottom modeling method as described in any one of claims 1-7.

Images