Tunnel modeling method and device, electronic equipment and computer storage medium

Abstract

The invention relates to a tunnel modeling method and device, electronic equipment and a computer storage medium, and belongs to the technical field of tunnel engineering.The tunnel modeling method comprises the steps that original three-dimensional point cloud data of a tunnel to be modeled are obtained, and the original three-dimensional point cloud data are thinned to obtain three-dimensional point cloud data to be modeled; calculating an axial inclination slope of the to-be-modeled three-dimensional point cloud data based on a preset initial coordinate system, determining an axial coordinate system of the to-be-modeled tunnel based on the axial inclination slope, and configuring the to-be-modeled three-dimensional point cloud data to the axial coordinate system; and constructing a three-dimensional grid model of the to-be-modeled tunnel based on the position of the to-be-modeled three-dimensional point cloud data in the axial coordinate system. According to the method, the three-dimensional grid model of the tunnel can be accurately constructed.

Description

Technical Field

[0001] This invention relates to the field of tunnel engineering technology, and in particular to a tunnel modeling method, apparatus, electronic device, and computer storage medium. Background Technology

[0002] With the increasing density of urban rail transit and the advancement of cross-regional highway projects, the technical difficulty and safety requirements of tunnel construction have significantly increased. Tunnel construction scenarios are enclosed and spatially confined, with intertwined equipment and pipelines. Conventional methods such as text and two-dimensional images are insufficient to intuitively represent the three-dimensional spatial relationships and dynamic states, easily leading to information discrepancies and hindering collaboration and risk management. Collapses, equipment interference, and other hidden dangers and quality problems occur frequently during construction, resulting in significant management pressure. Therefore, constructing a digital model that accurately maps the construction scenario has become crucial for improving management capabilities, and this need has driven the research and application of digital technologies in tunnel engineering.

[0003] Among digital technologies applicable to tunnel construction, 3D modeling technology has become the mainstream technology for solving the aforementioned construction management challenges due to its core advantages such as visualization, information sharing, and interactivity. However, existing 3D modeling technologies still face many bottlenecks in tunnel construction, restricting their large-scale promotion and effectiveness. The massive point cloud data generated by laser scanning is easily affected by various factors at the construction site, resulting in noise, occlusion, and missing data, which affects modeling accuracy. Currently, conventional equipment and algorithms cannot quickly complete the entire process from point cloud data preprocessing to 3D mesh model reconstruction, resulting in efficiency that does not match the construction schedule, or where some parts can be completed quickly but accuracy cannot be guaranteed.

[0004] This shows that existing technologies cannot efficiently complete high-precision modeling of tunnels. Summary of the Invention

[0005] In view of this, it is necessary to provide a tunnel modeling method, apparatus, electronic device and computer storage medium to solve the problem that existing technologies cannot efficiently complete high-precision tunnel modeling.

[0006] To address the aforementioned problems, in a first aspect, the present invention provides a tunnel modeling method, comprising: Obtain the original 3D point cloud data of the tunnel to be modeled, and thin the original 3D point cloud data to obtain the 3D point cloud data to be modeled. The axial tilt slope of the three-dimensional point cloud data to be modeled is calculated based on the preset initial coordinate system, and the axial coordinate system of the tunnel to be modeled is determined based on the axial tilt slope. The three-dimensional point cloud data to be modeled is then configured into the axial coordinate system. A 3D mesh model of the tunnel to be modeled is constructed based on the position of the 3D point cloud data to be modeled in the axial coordinate system.

[0007] In one possible implementation, the original 3D point cloud data is thinned to obtain the 3D point cloud data to be modeled, including: The original 3D point cloud data is divided into multiple spatial grids, and the side length of the spatial grid is determined by the preset target point cloud density. The original 3D point cloud data in each spatial grid is randomly sampled to determine the representative 3D point cloud of each spatial grid. The number of representative 3D point clouds in each spatial grid does not exceed the target point cloud density. By integrating the representative 3D point clouds from each spatial grid, the 3D point cloud data to be modeled is obtained.

[0008] In one possible implementation, the axial tilt slope of the 3D point cloud data to be modeled is calculated based on a preset initial coordinate system, including: The estimated initial axis of the tunnel to be modeled is determined based on the coverage of the 3D point cloud data to be modeled in the initial coordinate system. The point cloud data to be modeled is uniformly segmented based on the estimated initial axis, and the extreme point cloud of the point cloud data to be modeled in the initial coordinate system is determined in each segment. The fitting slope of the 3D point cloud data to be modeled in each initial coordinate system plane is calculated based on the extreme point cloud.

[0009] In one possible implementation, the axial coordinate system of the tunnel to be modeled is determined based on the axial tilt slope, and the 3D point cloud data to be modeled is configured into the axial coordinate system, including: The cross product of the axial vectors of the fitted slope in the corresponding coordinate plane is determined as the axial vector of the tunnel to be modeled. The rotation correction matrix of the 3D point cloud data to be modeled is determined based on the preset target axis and the axis vector of the tunnel to be modeled, and the 3D point cloud data to be modeled is registered to the axial coordinate system of the target axis based on the rotation correction matrix.

[0010] In one possible implementation, before constructing a 3D mesh model of the tunnel to be modeled based on the position of the 3D point cloud data to be modeled in the axial coordinate system, the following steps are included: The median of the point cloud in the transverse direction of the tunnel to be modeled is determined based on the target axis, and the 3D point cloud data to be modeled that are less than the median of the point cloud are extracted to obtain the central axis surface point set. The preset distance threshold is determined according to the width of the tunnel to be modeled. Calculate the maximum point cloud height difference in the vertical direction of each point cloud in the central axis surface point set. When the difference between the maximum point cloud height difference and the tunnel design height is greater than the preset height difference threshold, delete the point cloud within the preset height threshold at the bottom of the 3D point cloud data to be modeled, and obtain the target point cloud data to be modeled.

[0011] In one possible implementation, a three-dimensional mesh model of the tunnel to be modeled is constructed based on the position of the three-dimensional point cloud data to be modeled in the axial coordinate system, including: Determine the neighborhood space of each point in the 3D point cloud data to be modeled, and count the probability of occurrence of the normals of each plane direction formed by different combinations of points in the neighborhood space. The point normal vector of each point in the 3D point cloud to be modeled is determined based on the probability of occurrence of normals in different directions. A 3D mesh model of the tunnel to be modeled is constructed based on point normal vectors.

[0012] In one possible implementation, a three-dimensional mesh model of the tunnel to be modeled is constructed based on point normal vectors, including: When the difference between the grid coordinates in the 3D mesh model and the coordinates of the corresponding region in the original 3D point cloud data exceeds the maximum operating difference, the 3D mesh model is clipped.

[0013] Secondly, the present invention also provides a tunnel modeling apparatus, comprising: The point cloud data acquisition module is used to acquire the original 3D point cloud data of the tunnel to be modeled, and to thin out the original 3D point cloud data to obtain the 3D point cloud data to be modeled. The coordinate system determination module is used to calculate the axial tilt slope of the 3D point cloud data to be modeled based on the preset initial coordinate system, determine the axial coordinate system of the tunnel to be modeled based on the axial tilt slope, and configure the 3D point cloud data to be modeled to the axial coordinate system. The mesh building module is used to construct a 3D mesh model of the tunnel to be modeled based on the position of the 3D point cloud data to be modeled in the axial coordinate system.

[0014] Thirdly, the present invention also provides an electronic device, including a memory and a processor, wherein, Memory, used to store programs; The processor, coupled to the memory, is used to execute a program stored in the memory to implement the steps in the tunnel modeling method of any of the above embodiments.

[0015] Fourthly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instructions, which, when executed by a processor, can implement the steps in the tunnel modeling method of any of the above embodiments.

[0016] The beneficial effects of the present invention are: the tunnel modeling method provided by the present invention, by collecting the original three-dimensional point cloud data of the tunnel to be modeled and thinning the original three-dimensional point cloud data, can prevent the data from being affected by various factors at the construction site due to the large amount of point cloud data, resulting in noise, occlusion and missing data, thereby improving the modeling accuracy and modeling efficiency. The axial tilt slope of the 3D point cloud data to be modeled is calculated using a preset initial coordinate system. Based on the axial tilt slope, the axial coordinate system of the tunnel to be modeled is determined, and the 3D point cloud data to be modeled is configured into the axial coordinate system. Based on the position of the 3D point cloud data to be modeled in the axial coordinate system, a 3D mesh model of the tunnel to be modeled is constructed. Considering the geometric features of the tunnel, multi-dimensional fitting calculations are performed on the axial direction of the tunnel point cloud. Taking into full account data noise, fitting calculation errors, etc., the axial information of the tunnel point cloud acquired by the device can be obtained with high precision and robustness. This provides a high-quality data feature foundation for the registration of tunnel point cloud data and quickly generates a 3D tunnel real-scene mesh model. The entire process processing time meets the real-time requirements of construction, while restoring the real situation of the tunnel with high precision. A good balance is achieved between real-time performance and high precision, which can effectively reduce labor and time costs and promote the development of tunnel engineering towards digitalization and intelligence. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating a tunnel modeling method provided in an embodiment of the present invention. Figure 2 A schematic flowchart of a point cloud thinning method provided in an embodiment of the present invention; Figure 3 A schematic flowchart of a slope calculation method provided in an embodiment of the present invention; Figure 4 A schematic flowchart of a point cloud registration method provided in an embodiment of the present invention; Figure 5 A flowchart illustrating a point cloud denoising method provided in an embodiment of the present invention; Figure 6 A flowchart illustrating a mesh model construction method provided in an embodiment of the present invention; Figure 7 This is a schematic diagram of the structure of a tunnel modeling device provided in an embodiment of the present invention; Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0019] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0020] In the description of the embodiments of the present invention, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0021] The terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0022] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0023] A specific embodiment of the present invention, such as Figure 1 As shown, a tunnel modeling method is disclosed, including: S101, Obtain the original 3D point cloud data of the tunnel to be modeled, and thin the original 3D point cloud data to obtain the 3D point cloud data to be modeled.

[0024] In this embodiment of the invention, for tunnels under construction, the original three-dimensional point cloud data of the tunnel can be acquired by laser scanning. By emitting high-density laser point cloud data, the three-dimensional geometric information of the tunnel face, lining structure, and working space can be quickly captured, forming a high-density, high-fidelity point cloud data carrier, providing reliable data support for subsequent three-dimensional modeling. Specifically, a camera scans the actual tunnel construction site to acquire large-scale, high-precision three-dimensional point cloud data for each stage of excavation, initial support, and secondary lining.

[0025] Furthermore, to reduce the impact of external factors on point cloud data and decrease the amount of point cloud data, the collected raw 3D point cloud data can be thinned to obtain a more concise 3D point cloud data to be modeled. Specific methods for point cloud thinning will be described in detail later in this invention.

[0026] S102, calculate the axial tilt slope of the three-dimensional point cloud data to be modeled based on the preset initial coordinate system, determine the axial coordinate system of the tunnel to be modeled based on the axial tilt slope, and configure the three-dimensional point cloud data to be modeled to the axial coordinate system.

[0027] In this embodiment of the invention, when modeling the tunnel to be modeled, it is necessary to first determine the axial direction of the tunnel. This axial direction can be determined by the slope of the 3D point cloud data to be modeled. After determining the axial direction, an axial coordinate system is determined based on the axial slope, and all the 3D point cloud data to be modeled are registered to this axial coordinate system. The specific process of slope calculation and registration will be described in detail later in this invention.

[0028] S103, construct a three-dimensional mesh model of the tunnel to be modeled based on the position of the three-dimensional point cloud data to be modeled in the axial coordinate system.

[0029] In this embodiment of the invention, after determining the axial coordinate system of the tunnel to be modeled, the 3D mesh reconstruction of the tunnel can be achieved based on the positions of each 3D point cloud data to be modeled within this axial coordinate system, generating a real-world mesh model of the tunnel. Specifically, the final 3D real-world mesh model of the tunnel can be obtained through the Poisson reconstruction algorithm and scalar field optimization clipping. The specific process of model construction will be described in detail later in this invention.

[0030] The tunnel modeling method provided by this invention collects the original three-dimensional point cloud data of the tunnel to be modeled and thins the original three-dimensional point cloud data. This can prevent the data from being affected by various factors at the construction site due to the large amount of point cloud data, resulting in noise, occlusion and missing data, thereby improving the modeling accuracy and efficiency. The axial tilt slope of the 3D point cloud data to be modeled is calculated using a preset initial coordinate system. Based on the axial tilt slope, the axial coordinate system of the tunnel to be modeled is determined, and the 3D point cloud data to be modeled is configured into the axial coordinate system. Based on the position of the 3D point cloud data to be modeled in the axial coordinate system, a 3D mesh model of the tunnel to be modeled is constructed. Considering the geometric features of the tunnel, multi-dimensional fitting calculations are performed on the axial direction of the tunnel point cloud. Taking into full account data noise, fitting calculation errors, etc., the axial information of the tunnel point cloud acquired by the device can be obtained with high precision and robustness. This provides a high-quality data feature foundation for the registration of tunnel point cloud data and quickly generates a 3D tunnel real-scene mesh model. The entire process processing time meets the real-time requirements of construction, while restoring the real situation of the tunnel with high precision. A good balance is achieved between real-time performance and high precision, which can effectively reduce labor and time costs and promote the development of tunnel engineering towards digitalization and intelligence.

[0031] In some possible embodiments of the present invention, such as Figure 2As shown, the original 3D point cloud data is thinned to obtain the 3D point cloud data to be modeled, including: S201, The original 3D point cloud data is divided into grids to obtain multiple spatial grids. The side length of the spatial grid is determined by the preset target point cloud density. S202, randomly extract the original 3D point cloud data from each spatial grid to determine the representative 3D point cloud of each spatial grid, wherein the number of representative 3D point clouds in each spatial grid does not exceed the target point cloud density. S203 integrates representative 3D point clouds from various spatial grids to obtain the 3D point cloud data to be modeled.

[0032] In this embodiment of the invention, when thinning the original 3D point cloud data, it is necessary to first divide the space where the original 3D point cloud data is located into a grid. When dividing the grid, the side length of the grid can be determined according to the preset target point cloud density. The target point cloud density refers to the number of point cloud data in a single grid, and the specific calculation formula is as follows:

[0033] in, The side length of the grid. The target point cloud density is predetermined.

[0034] In this embodiment of the invention, after the mesh is divided into multiple meshes, the original 3D point cloud data in each mesh is randomly filtered to obtain representative 3D point clouds that represent the 3D point cloud data in that mesh. The number of representative 3D point clouds in each mesh cannot exceed a pre-set target point cloud density. By randomly filtering, the overall features of the tunnel point cloud to be modeled can be preserved as much as possible. The points retained after filtering all spatial meshes are integrated to form the final thinned 3D point cloud data to be modeled.

[0035] This invention reduces the number of points and minimizes external interference by thinning the original 3D point cloud data, while preserving the original features of the tunnel to be modeled.

[0036] In some possible embodiments of the present invention, such as Figure 3 As shown, the axial tilt slope of the 3D point cloud data to be modeled is calculated based on a preset initial coordinate system, including: S301, Determine the estimated initial axis of the tunnel to be modeled based on the coverage of the 3D point cloud data to be modeled in the initial coordinate system; S302, based on the estimated initial axis, uniformly segment the point cloud data to be modeled, and determine the extreme point cloud of the point cloud data to be modeled in the initial coordinate system in each segment; S303 is the fitting slope of the 3D point cloud data to be modeled in each initial coordinate system plane based on extreme point cloud computing.

[0037] In this embodiment of the invention, when calculating the axial tilt slope of the 3D point cloud data to be modeled, it is necessary to first determine the estimated initial axis of the tunnel to be modeled. Specifically, in the initial coordinate system, based on the coverage range of the 3D point cloud data to be modeled on the X and Y axes, the axis of the tunnel point cloud is initially estimated. If the coverage range on the X axis is longer, the estimated initial axis is the X axis; if the coverage range on the Y axis is longer, the estimated initial axis is the Y axis. The tunnel point cloud is evenly divided into segments along the estimated axis. Within each segment, points with maximum and minimum coordinates on the other two coordinate axes besides the estimated axis are extracted to form four point sets, which are then divided into the maximum point cloud set on the Y axis in the X-axis direction. Set of minimum points along the Y-axis in the X-axis direction Maximum point cluster in the Z-axis direction and the maximum point cloud in the Z-axis direction Using the random sample consensus algorithm, calculate and Slope of the fit in the XOY plane , ,calculate and Slope of the fit in the YOZ plane , Then, the final fitting slope of the tunnel point cloud in the XOY and YOZ planes is obtained by averaging. and The calculation formula is:

[0038]

[0039] In this embodiment of the invention, the axial tilt slope of the thinned and simplified tunnel point cloud is fitted and calculated using a segmented feature extraction method and a random sample consensus algorithm to obtain a more accurate fitted slope, which is convenient for subsequent calculations.

[0040] In some possible embodiments of the present invention, such as Figure 4 As shown, the axial coordinate system of the tunnel to be modeled is determined based on the axial tilt slope, and the 3D point cloud data to be modeled is configured into the axial coordinate system, including: S401, the cross product of the axial vectors of the fitted slope on the corresponding coordinate plane is determined as the axial vector of the tunnel to be modeled; S402, determine the rotation correction matrix of the three-dimensional point cloud data to be modeled based on the preset target axis and the axis vector of the tunnel to be modeled, and register the three-dimensional point cloud data to be modeled to the axial coordinate system of the target axis based on the rotation correction matrix.

[0041] In this embodiment of the invention, following the foregoing embodiments, according to , Construct the axial vectors of the tunnel point cloud in the XOY and YOZ planes. , ,right , The actual tunnel point cloud axis is obtained by performing a cross product. ,right Normalization yields Let the final target axis be If the coordinates of the midpoint in the point cloud before transformation are v, then according to the Rodriguez formula, the coordinates of the point after rotation correction and registration can be obtained. The specific calculation formula is as follows:

[0042] Where k is an intermediate variable. It is the rotation angle.

[0043] This invention achieves coordinate unification of the 3D point cloud data to be modeled through registration, which facilitates the subsequent model construction.

[0044] In some possible embodiments of the present invention, such as Figure 5 As shown, before constructing the 3D mesh model of the tunnel to be modeled based on the position of the 3D point cloud data in the axial coordinate system, the following steps are included: S501, determine the median of the point cloud in the transverse direction of the tunnel to be modeled based on the target axis, and extract the 3D point cloud data to be modeled that are less than the median of the point cloud by a preset distance threshold to obtain the central axis surface point set, wherein the preset distance threshold is determined according to the width of the tunnel to be modeled. S502, calculate the maximum point cloud height difference in the vertical direction of each point cloud in the central axis surface point set. When the difference between the maximum point cloud height difference and the tunnel design height is greater than the preset height difference threshold, delete the point cloud within the preset height threshold at the bottom of the 3D point cloud data to be modeled, and obtain the target point cloud data to be modeled.

[0045] In this embodiment of the invention, before constructing a 3D mesh model of the tunnel to be modeled based on the 3D point cloud, it is necessary to combine the tunnel design model and, according to the inherent characteristics of the tunnel's geometric structure, separate and remove non-interested regions such as the ground from the point cloud, and simultaneously perform denoising processing to eliminate interfering data. Specifically, the 3D point cloud data to be modeled after axial correction and registration is traversed. Assuming that the axial direction of the registered tunnel point cloud is towards the positive Y-axis, the maximum value of the X-axis coordinate is recorded. and minimum value The median value on the X-axis is obtained by averaging. Set the X-axis filtering threshold based on the tunnel width. Extract all X coordinates that satisfy Construct the central axis point set from the points. Traverse the set of points on the central axis Calculate the maximum Z-axis coordinate difference in the point set. ,Will The difference between the points and the tunnel design height is compared. If the difference is greater than the set height threshold, ground points below a certain height are removed. Based on the accuracy requirements of the scanning equipment, a distance threshold from the scanning equipment is set, and low-precision points at a distance obtained during the acquisition are deleted. Based on the tunnel design model, the distance from each point in the point cloud to the design tunnel wall is calculated, and noise points with a distance exceeding a certain distance threshold are removed.

[0046] This invention reduces external interference by removing non-interested region data such as the ground from the point cloud.

[0047] In some possible embodiments of the present invention, such as Figure 6 As shown, a 3D mesh model of the tunnel to be modeled is constructed based on the position of the 3D point cloud data in the axial coordinate system, including: S601, determine the neighborhood space of each point in the 3D point cloud data to be modeled, and count the probability of occurrence of the normals of each plane direction formed by different combinations of points in the neighborhood space. S602, determine the point normal vector of each point in the 3D point cloud to be modeled based on the occurrence probability of normals in different directions; S603, constructing a 3D mesh model of the tunnel to be modeled based on point normal vectors.

[0048] In this embodiment of the invention, to construct a 3D mesh model of the tunnel to be modeled, the point normals of the tunnel point cloud can be calculated first. The traditional Hough transform is extended to a 3D point cloud scene, mapping the normal directions in the point cloud space to the parameter space. The possible normal directions of a single point in the point cloud are transformed into corresponding elements in the parameter space. Simultaneously, an accumulator is constructed to statistically analyze the probability of different normal directions. By randomly sampling point combinations in a local region of the point cloud, possible local planes are inferred, and the normal directions corresponding to these planes are obtained. The corresponding directions are then counted in the accumulator in the parameter space. The value in the accumulator represents the reliability of the corresponding normal direction, and the direction corresponding to the local maximum value in the accumulator is determined as the normal direction of the target point. Specifically, the parameters are dynamically adjusted according to the point cloud scale and accuracy requirements. This parameter represents the number of points contained in the local region of the point cloud during the calculation of the normal vector of a point. If it is too small, it may be affected by local noise points; if it is too large, it may violate the local neighborhood concept. Since a clean tunnel wall point cloud is a non-closed surface, the calculated point normal vectors may be inverted. In this case, all point normal vectors can be reversed.

[0049] Furthermore, the Poisson surface reconstruction algorithm treats the point cloud as a sample of the gradient information of a smooth implicit scalar function. By fitting the implicit function, isosurfaces are extracted to generate a smooth mesh model. However, when reconstructing meshes on non-closed surfaces, the Poisson surface reconstruction algorithm often fits redundant extensions that were not originally present at the original surface boundaries. To address this characteristic, the algorithm parameters can be dynamically adjusted according to the required reconstruction accuracy. An additional scalar field can be generated during the reconstruction process to represent the degree of correlation between the reconstructed mesh vertices and the original input point cloud, facilitating subsequent optimization of the reconstructed mesh. Specifically, point cloud processing software can be used, leveraging its various functions to construct the 3D mesh model.

[0050] In this embodiment of the invention, the normal vectors of points in the processed tunnel point cloud data are calculated. Based on the point normal vector characteristics of the tunnel point cloud, a three-dimensional mesh reconstruction of the tunnel point cloud is performed based on the Poisson reconstruction algorithm, thereby realizing the construction of a three-dimensional mesh model of the tunnel to be modeled.

[0051] In some possible embodiments of the present invention, constructing a three-dimensional mesh model of the tunnel to be modeled based on point normal vectors includes: When the difference between the grid coordinates in the 3D mesh model and the coordinates of the corresponding region in the original 3D point cloud data exceeds the maximum operating difference, the 3D mesh model is clipped.

[0052] In this embodiment of the invention, based on the density features generated during the reconstruction process, the scalar filtering function in point cloud processing software can also be used to remove redundancy and optimize the tunnel 3D mesh model. Specifically, based on the scalar field of the correlation between the mesh vertices generated during the reconstruction process and the original input point cloud, the minimum threshold allowed by the scalar field is adjusted to trim the mesh, remove the redundant extended regions generated by Poisson reconstruction, and obtain the final 3D tunnel real-scene mesh.

[0053] To better implement the tunnel modeling method in this embodiment of the invention, based on the tunnel modeling method, correspondingly, as follows: Figure 7 As shown, this embodiment of the invention also provides a tunnel modeling device, the tunnel modeling device 700 comprising: The point cloud data acquisition module 701 is used to acquire the original three-dimensional point cloud data of the tunnel to be modeled, and to thin out the original three-dimensional point cloud data to obtain the three-dimensional point cloud data to be modeled. The coordinate system determination module 702 is used to calculate the axial tilt slope of the three-dimensional point cloud data to be modeled based on the preset initial coordinate system, determine the axial coordinate system of the tunnel to be modeled based on the axial tilt slope, and configure the three-dimensional point cloud data to be modeled to the axial coordinate system. Mesh building module 703 is used to build a 3D mesh model of the tunnel to be modeled based on the position of the 3D point cloud data to be modeled in the axial coordinate system.

[0054] The tunnel modeling device 700 provided in the above embodiments can realize the technical solutions described in the above tunnel modeling method embodiments. The specific implementation principles of each module or unit can be found in the corresponding content in the above tunnel modeling method embodiments, and will not be repeated here.

[0055] like Figure 8 As shown, the present invention also provides an electronic device 800. The electronic device 800 includes a processor 801, a memory 802, and a display 803. Figure 8 Only some components of the electronic device 800 are shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0056] In some embodiments, processor 801 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in memory 802 or process data, such as the tunnel modeling method of the present invention.

[0057] In some embodiments, processor 801 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 801 may be local or remote. In some embodiments, processor 801 may be implemented on a cloud platform. In some embodiments, the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-cloud, etc., or any combination thereof.

[0058] In some embodiments, memory 802 may be an internal storage unit of electronic device 800, such as a hard disk or memory of electronic device 800. In other embodiments, memory 802 may also be an external storage device of electronic device 800, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 800.

[0059] Furthermore, the memory 802 may include both internal storage units of the electronic device 800 and external storage devices. The memory 802 is used to store application software and various types of data installed on the electronic device 800.

[0060] In some embodiments, display 803 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 803 is used to display information from electronic device 800 and to display a visual user interface. Components 801-803 of electronic device 800 communicate with each other via a system bus.

[0061] In some embodiments, when processor 801 executes the tunnel modeling program in memory 802, the following steps may be performed: Obtain the original 3D point cloud data of the tunnel to be modeled, and thin the original 3D point cloud data to obtain the 3D point cloud data to be modeled. The axial tilt slope of the three-dimensional point cloud data to be modeled is calculated based on the preset initial coordinate system, and the axial coordinate system of the tunnel to be modeled is determined based on the axial tilt slope. The three-dimensional point cloud data to be modeled is then configured into the axial coordinate system. A 3D mesh model of the tunnel to be modeled is constructed based on the position of the 3D point cloud data to be modeled in the axial coordinate system.

[0062] It should be understood that when the processor 801 executes the tunnel modeling program in the memory 802, in addition to the functions mentioned above, it can also perform other functions, as detailed in the description of the corresponding method embodiments above.

[0063] Furthermore, this embodiment of the invention does not specifically limit the type of electronic device 800 mentioned. Electronic device 800 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the invention, electronic device 800 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0064] Accordingly, this application also provides a computer-readable storage medium for storing a computer-readable program or instruction. When the program or instruction is executed by a processor, it can implement the steps or functions of the tunnel modeling method provided in the above-described method embodiments.

[0065] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0066] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A tunnel modeling method, characterized in that, include: Obtain the original 3D point cloud data of the tunnel to be modeled, and thin the original 3D point cloud data to obtain the 3D point cloud data to be modeled. The axial tilt slope of the three-dimensional point cloud data to be modeled is calculated based on the preset initial coordinate system, and the axial coordinate system of the tunnel to be modeled is determined based on the axial tilt slope, and the three-dimensional point cloud data to be modeled is configured into the axial coordinate system. A three-dimensional mesh model of the tunnel to be modeled is constructed based on the position of the three-dimensional point cloud data to be modeled in the axial coordinate system.

2. The tunnel modeling method according to claim 1, characterized in that, The process of thinning the original 3D point cloud data to obtain the 3D point cloud data to be modeled includes: The original 3D point cloud data is divided into multiple spatial grids, and the side length of the spatial grids is determined by the preset target point cloud density. The original three-dimensional point cloud data in each of the spatial grids are randomly extracted to determine the representative three-dimensional point cloud of each spatial grid, wherein the number of representative three-dimensional point clouds in each spatial grid does not exceed the target point cloud density. By integrating the representative 3D point clouds of each of the aforementioned spatial grids, the 3D point cloud data to be modeled is obtained.

3. The tunnel modeling method according to claim 1, characterized in that, The calculation of the axial tilt slope of the 3D point cloud data to be modeled based on a preset initial coordinate system includes: The estimated initial axis of the tunnel to be modeled is determined based on the coverage of the three-dimensional point cloud data to be modeled in the initial coordinate system. The point cloud data to be modeled is uniformly segmented based on the estimated initial axis, and the extreme point cloud of the point cloud data to be modeled in each segment in the initial coordinate system is determined. The extreme point computing algorithm calculates the fitting slope of the three-dimensional point cloud data to be modeled in each initial coordinate system plane.

4. The tunnel modeling method according to claim 3, characterized in that, The step of determining the axial coordinate system of the tunnel to be modeled based on the axial tilt slope, and configuring the 3D point cloud data to be modeled into the axial coordinate system, includes: The cross product of the axial vectors of the fitted slope in the corresponding coordinate system plane is determined as the axial vector of the tunnel to be modeled. Based on the preset target axis and the axial vector of the tunnel to be modeled, the rotation correction matrix of the three-dimensional point cloud data to be modeled is determined, and the three-dimensional point cloud data to be modeled is registered to the axial coordinate system of the target axis based on the rotation correction matrix.

5. The tunnel modeling method according to claim 4, characterized in that, Before constructing the 3D mesh model of the tunnel to be modeled based on the position of the 3D point cloud data to be modeled in the axial coordinate system, the following steps are included: Based on the target axis, the median of the point cloud in the lateral direction of the tunnel to be modeled is determined, and the 3D point cloud data to be modeled that are less than the median of the point cloud are extracted to obtain the central axis surface point set, wherein the preset distance threshold is determined according to the width of the tunnel to be modeled. Calculate the maximum point cloud height difference in the vertical direction of each point cloud in the central axis surface point set. When the difference between the maximum point cloud height difference and the tunnel design height is greater than a preset height difference threshold, delete the point cloud within the preset height threshold at the bottom of the three-dimensional point cloud data to be modeled, and obtain the target point cloud data to be modeled.

6. The tunnel modeling method according to claim 1, characterized in that, The construction of a 3D mesh model of the tunnel to be modeled based on the position of the 3D point cloud data to be modeled in the axial coordinate system includes: Determine the neighborhood space of each point in the 3D point cloud data to be modeled, and count the probability of occurrence of the normals of each plane direction formed by different combinations of points in the neighborhood space; The point normal vector of each point in the 3D point cloud to be modeled is determined based on the occurrence probability of the different directional normals. A three-dimensional mesh model of the tunnel to be modeled is constructed based on the point normal vectors.

7. The tunnel modeling method according to claim 6, characterized in that, The construction of the 3D mesh model of the tunnel to be modeled based on the point normal vectors includes: When the difference between the grid coordinates in the 3D mesh model and the coordinates of the corresponding region in the original 3D point cloud data exceeds the maximum operating difference, the 3D mesh model is clipped.

8. A tunnel modeling device, characterized in that, include: The point cloud data acquisition module is used to acquire the original three-dimensional point cloud data of the tunnel to be modeled, and to thin out the original three-dimensional point cloud data to obtain the three-dimensional point cloud data to be modeled. The coordinate system determination module is used to calculate the axial tilt slope of the three-dimensional point cloud data to be modeled based on a preset initial coordinate system, determine the axial coordinate system of the tunnel to be modeled based on the axial tilt slope, and configure the three-dimensional point cloud data to be modeled to the axial coordinate system. The mesh construction module is used to construct a three-dimensional mesh model of the tunnel to be modeled based on the position of the three-dimensional point cloud data to be modeled in the axial coordinate system.

9. An electronic device, characterized in that, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the tunnel modeling method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the tunnel modeling method according to any one of claims 1 to 7.

Images