A Dynamic Monitoring Method and System for Deep Foundation Pit Construction Based on BIM

Abstract

The present invention relates to a dynamic monitoring method and system for deep foundation pit construction based on BIM. Specifically, according to the construction stages, the BIM design model is divided into multiple stages. The on-site point cloud data of the deep foundation pit and the current construction stage are obtained. Based on the attribution consistency probability and boundary compliance degree of the points in the point cloud in the BIM design model of the current construction stage, a point cloud map is constructed. The point cloud map is segmented using minimum segmentation with hierarchical constraints to obtain multiple point cloud clusters. The intrinsic geometric shape of the point cloud clusters is calculated based on the eigenvalues of the covariance matrix of the point cloud clusters. Using the geometric shape and the positional relationship of the point cloud clusters, the point cloud clusters are associated with the construction components in the BIM design model of the current construction stage. The point cloud clusters are three-dimensionally reconstructed using the construction components associated with the point cloud clusters, and the current construction progress status of each component is updated and visually displayed in the BIM design model.

Description

Technical Field

[0001] The present invention relates to the field of construction, and specifically to a dynamic monitoring method and system for deep foundation pit construction based on BIM. Background Technique

[0002] The deep foundation pit project is a basic link in construction. Its construction process is complex and risky, involving multiple key steps such as earth excavation, support structure construction, and dewatering. The states such as deformation, displacement, and stress during the construction process are directly related to the safety of the foundation pit itself and the surrounding environment. Conducting dynamic and accurate monitoring of deep foundation pit construction is crucial and is a necessary way to ensure project safety, control quality, and master the progress. Traditional deep foundation pit monitoring methods mainly rely on manually arranging monitoring points and using instruments such as total stations, levels, and inclinometers for regular or irregular measurements. Although these methods can reflect the changes of key points to a certain extent, there are problems such as sparse monitoring points, limited data coverage, low automation level, high labor intensity, and lagging response. BIM technology can establish a digital model containing rich geometric and non-geometric information during the design stage, providing a unified data basis for construction planning, simulation, and management. Point cloud technology can quickly and accurately obtain the three-dimensional spatial information of the construction site, form dense point cloud data, and objectively record the site. By combining BIM and point cloud technology, through comparing the design model with the measured point cloud on site, automatic analysis of construction progress, deviation, and quality can be achieved. However, how to automatically segment the point cloud and perform three-dimensional reconstruction of the point cloud is the key to the dynamic monitoring of deep foundation pit construction. Summary of the Invention

[0003] To solve the above problems, in the first aspect of the present invention, a dynamic monitoring method for deep foundation pit construction based on BIM is provided. The method includes the following steps:

[0004] Divide the BIM design model into multiple stages according to the construction stage, obtain the deep foundation pit on-site point cloud data and the current construction stage, construct a point cloud map based on the belonging consistency probability and boundary conformity of the points in the point cloud in the BIM design model of the current construction stage, and use the minimum segmentation with hierarchical constraints to segment the point cloud map to obtain multiple point cloud clusters;

[0005] Calculate the intrinsic geometric shape of the point cloud cluster based on the eigenvalues of the covariance matrix of the point cloud cluster, and use the geometric shape and the positional relationship of the point cloud cluster to associate the point cloud cluster with the construction components in the BIM design model of the current construction stage;

[0006] Perform three-dimensional reconstruction of the point cloud cluster using the construction components associated with the point cloud cluster, and update and visually display the current construction progress status of each component in the BIM design model.

[0007] Preferably, constructing a point cloud map based on the belonging consistency probability and boundary compliance degree of points in the point cloud in the BIM design model of the current construction stage, specifically:

[0008] Align the on-site point cloud data with the BIM design model of the current construction stage to the same coordinate system; calculate the nearest component in the BIM design model of the current construction stage to the point, and calculate the belonging probability of the point belonging to the nearest component based on the distance.

[0009] Find the k nearest neighbor points of each point in the on-site point cloud data in the point cloud. If the point and the nearest neighbor points belong to the same component, the belonging consistency probability is the product of their belonging probabilities; otherwise, the belonging consistency probability is 0.

[0010] Obtain the line segment from the point to the nearest neighbor point, calculate the intersection points of the line segment with all components in the BIM design model of the current construction stage, and calculate the boundary compliance factor based on the number of the intersection points.

[0011] Take the product of the boundary compliance factor and the belonging consistency probability as the weight of the point and the nearest neighbor point, and construct a point cloud map based on the weight.

[0012] Preferably, using minimum segmentation with hierarchical constraints to segment the point cloud map to obtain multiple point cloud clusters, specifically:

[0013] For any two connected points in the point cloud map, obtain the hierarchical difference of the two connected points in the BIM component of the current construction stage.

[0014] Obtain an adjustment weight based on the hierarchical difference, and adjust the weight of the edge of the two connected points according to the adjustment weight.

[0015] Segment the adjusted point cloud map by the minimum segmentation method to obtain multiple point cloud clusters.

[0016] Preferably, calculating the intrinsic geometric shape of the point cloud cluster based on the eigenvalue of the point cloud cluster, specifically:

[0017] Calculate the 3x3 covariance matrix of all points in the point cloud cluster, obtain the first 3 largest eigenvalues corresponding to the covariance matrix, and obtain the intrinsic geometric shape based on the first 3 largest eigenvalues.

[0018] Preferably, performing three-dimensional reconstruction on the point cloud cluster by using the construction component associated with the point cloud cluster, specifically:

[0019] If the construction component associated with the point cloud cluster has a complex shape, use the construction component to guide the three-dimensional reconstruction of the point cloud cluster; otherwise, extract the geometric type from the attributes of the associated BIM component, fit the parameters of the geometric primitive of the corresponding type by the least squares method, and generate a three-dimensional model of the point cloud cluster according to the fitted parameters.

[0020] In the second aspect of the present invention, a dynamic monitoring system for deep foundation pit construction based on BIM is provided. The system includes the following modules:

[0021] A segmentation module, configured to divide the BIM design model into multiple stages according to the construction stage, obtain the on-site point cloud data of the deep foundation pit and the current construction stage, construct a point cloud map based on the belonging consistency probability and boundary compliance degree of the points in the point cloud in the BIM design model of the current construction stage, and segment the point cloud map by using the minimum segmentation with hierarchical constraints to obtain multiple point cloud clusters;

[0022] An association module, configured to calculate the intrinsic geometric shape of the point cloud cluster based on the eigenvalues of the covariance matrix of the point cloud cluster, and associate the point cloud cluster with the construction components in the BIM design model of the current construction stage by using the geometric shape and the positional relationship of the point cloud cluster;

[0023] A progress visualization module, configured to perform three-dimensional reconstruction on the point cloud cluster by using the construction components associated with the point cloud cluster, and update and visually display the current construction progress status of each component in the BIM design model.

[0024] Preferably, constructing the point cloud map based on the belonging consistency probability and boundary compliance degree of the points in the point cloud in the BIM design model of the current construction stage specifically includes:

[0025] Align the on-site point cloud data and the BIM design model of the current construction stage to the same coordinate system; calculate the distance from the point to the nearest component in the BIM design model of the current construction stage, and calculate the belonging probability of the point belonging to the nearest component based on the distance;

[0026] For each point in the on-site point cloud data, find its k nearest neighbor points in the point cloud. If the point and the nearest neighbor points belong to the same component, the belonging consistency probability is the product of their belonging probabilities; otherwise, the belonging consistency probability is 0;

[0027] Obtain the line segment from the point to the nearest neighbor point, calculate the intersection points of the line segment and all components in the BIM design model of the current construction stage, and calculate the boundary compliance factor according to the number of the intersection points;

[0028] Use the product of the boundary compliance factor and the belonging consistency probability as the weight of the point and the nearest neighbor point, and construct the point cloud map based on the weight.

[0029] Preferably, the point cloud map is segmented into multiple point cloud clusters by using the minimum segmentation with hierarchical constraints, specifically as follows:

[0030] For any two connected points in the point cloud map, obtain the hierarchical difference between the two connected points in the BIM component at the current construction stage;

[0031] Based on the hierarchical difference, obtain an adjustment weight, and adjust the weight of the edge connecting the two points according to the adjustment weight;

[0032] Segment the adjusted point cloud map by using the minimum segmentation method to obtain multiple point cloud clusters.

[0033] Preferably, the intrinsic geometric shape of the point cloud cluster is calculated based on the eigenvalue of the point cloud cluster, specifically as follows:

[0034] Calculate the 3x3 covariance matrix of all points in the point cloud cluster, obtain the first 3 largest eigenvalues corresponding to the covariance matrix, and obtain the intrinsic geometric shape according to the first 3 largest eigenvalues.

[0035] Preferably, the point cloud cluster is three-dimensionally reconstructed by using the construction component associated with the point cloud cluster, specifically as follows:

[0036] If the construction component associated with the point cloud cluster has a complex shape, use the construction component to guide the three-dimensional reconstruction of the point cloud cluster; otherwise, extract the geometric type from the attributes of the associated BIM component, fit the parameters of the geometric primitive of the corresponding type by the least squares method, and generate a three-dimensional model of the point cloud cluster according to the fitted parameters.

[0037] In addition, the present invention also provides a computer-readable storage medium, on which a computer program is stored. The computer program is characterized in that when being executed by a processor, the computer program implements the method described in the first aspect.

[0038] The present invention constructs a point cloud map based on the belonging consistency probability and the boundary conformity, and uses the minimum segmentation algorithm with hierarchical constraints, thereby improving the semantic accuracy of the segmentation; moreover, by calculating the intrinsic geometric shape of the point cloud cluster and combining the position information, the association between the point cloud cluster and the BIM component is realized, and the three-dimensional reconstruction process of the point cloud cluster is guided by the BIM component, thereby improving the accuracy of the reconstructed model. Description of the Drawings

[0039] Figure 1 is a flowchart of the first embodiment;

[0040] Figure 2 is a partial schematic diagram of the point cloud map;

[0041] Figure 3 is a schematic diagram of the minimum segmentation of the point cloud map;

[0042] Figure 4 It is the structural diagram of the second embodiment. Specific implementation manners

[0043] In this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.

[0044] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0045] Figure 1 The flowchart of the first embodiment of the present invention is shown, as Figure 1 shown, including the following steps:

[0046] S1. Divide the BIM design model into multiple stages according to the construction stage, obtain the deep foundation pit on-site point cloud data and the current construction stage, construct a point cloud map based on the attribution consistency probability and boundary compliance of the points in the point cloud in the BIM design model of the current construction stage, and use minimum segmentation with hierarchical constraints to segment the point cloud map to obtain multiple point cloud clusters;

[0047] Divide the complete BIM (Building Information Modeling) design model according to different construction stages, and each stage has a corresponding BIM sub-model. Use a 3D laser scanner, etc. to obtain the point cloud data of the deep foundation pit construction site and the current construction stage, such as the earth excavation stage, the support structure installation stage, etc. Align the point cloud data obtained on-site and the BIM sub-model corresponding to the current construction stage to the same coordinate system to ensure consistent spatial positions. In one embodiment, set identification points in the BIM design model and set corresponding identification points at the construction site, and use the identification points to align the point cloud and the BIM design model of the current construction stage. In one embodiment, construct a point cloud map based on the belonging consistency probability and boundary compliance degree of the points in the point cloud in the BIM design model of the current construction stage. Specifically:

[0048] Align the on-site point cloud data and the BIM design model of the current construction stage to the same coordinate system; calculate the nearest component in the BIM design model of the current construction stage to the point, and calculate the belonging probability of the point belonging to the nearest component based on the distance;

[0049] Find the k nearest neighbor points of each point in the on-site point cloud data in the point cloud. If the point and the nearest neighbor points belong to the same component, the belonging consistency probability is the product of their belonging probabilities; otherwise, the belonging consistency probability is 0;

[0050] Obtain the line segment from the point to the nearest neighbor point, calculate the intersection points of the line segment and all components in the BIM design model of the current construction stage, and calculate the boundary compliance factor according to the number of the intersection points;

[0051] Take the product of the boundary compliance factor and the belonging consistency probability as the weight of the point and the nearest neighbor point, and construct a point cloud map based on the weight.

[0052] For each point in the point cloud, calculate its distance to all components in the current-stage BIM sub-model, find the component with the shortest distance, and based on this shortest distance, calculate the probability that the point belongs to this nearest component. The closer the distance, the higher the probability. In one embodiment, if the distance is 0 or negative, then this point belongs to this component. For each point in the point cloud, find its k nearest neighbor points in the point cloud data. If a point and its nearest neighbor point belong to the same BIM component, then the probability of their belonging consistency is the product of the respective belonging probabilities of these two points; if they do not belong to the same BIM component, then the probability of their belonging consistency is 0. For each point in the point cloud and one of its nearest neighbor points, obtain the line segment connecting these two points, and calculate the number of intersection points of this line segment with the surfaces of all components in the current-stage BIM sub-model. Calculate the boundary conformity factor based on the number of intersection points. The fewer the intersection points, the more likely it is that these two points are inside or on the surface of the same component, and the higher the conformity. Each point in the point cloud is a node of the graph, and there is an edge between the point and its k nearest neighbor points. The weight of the edge is the product or sum of the probability of belonging consistency between the point and its nearest neighbor point and the boundary conformity factor, thereby constructing a weighted point cloud graph. Figure 2 Shows a partial view of a point cloud graph.

[0053] In one embodiment, the point cloud graph is segmented into multiple point cloud clusters by using minimum segmentation with hierarchical constraints, specifically as follows:

[0054] For any two connected points in the point cloud graph, obtain the hierarchical difference between the two connected points in the BIM components at the current construction stage;

[0055] Based on the hierarchical difference, obtain an adjusted weight, and adjust the weight of the edge between the two connected points according to the adjusted weight;

[0056] Segment the adjusted point cloud graph by using the minimum segmentation method to obtain multiple point cloud clusters.

[0057] For any two points connected by an edge in the point cloud map, find their corresponding components in the BIM model at the current stage. Determine the difference in the BIM structural levels of these two components. Calculate the adjustment weight according to the level difference. Here, the level difference is the difference in the BIM structural levels of the two points, that is, the difference in the BIM components represented by these two points at different levels of the building structure such as foundation, column, beam, slab, etc. If the BIM components corresponding to the two points have a large difference in the structural level, for example, one belongs to the foundation and the other belongs to the roof beam, then even if they may be close in space, they are unlikely to belong to the same actual construction component. In one embodiment, the greater the level difference, the smaller the adjustment weight, indicating that they should not be assigned to the same cluster. Use the adjustment weight to adjust the original edge weight calculated in the point cloud map, for example, by multiplication. Apply a minimum cut algorithm to the point cloud map with adjusted weights, such as Normalized Cuts, etc. The goal of the minimum cut algorithm is to find a segmentation method that minimizes the total weight of the edges between the separated clusters and maximizes the total weight of the edges within the clusters, thereby dividing the entire point cloud map into multiple point cloud clusters, and each point cloud cluster corresponds to a component at the construction site. Figure 3 Schematic diagram of segmentation after using the adjustment weight.

[0058] S2. Calculate the intrinsic geometric shape of the point cloud cluster based on the eigenvalues of the covariance matrix of the point cloud cluster, and use the geometric shape and the positional relationship of the point cloud cluster to associate the point cloud cluster with the construction components in the BIM design model at the current construction stage.

[0059] For a point cloud cluster, the covariance matrix can be used to calculate the distribution of these points in three dimensions and their correlation. Performing eigenvalue decomposition on the covariance matrix will obtain eigenvalues and eigenvectors. Among them, the eigenvalue represents the degree of dispersion or variance size of the point cloud data in the direction of the corresponding eigenvector. By comparing the magnitude relationship of these three eigenvalues, it is possible to determine which geometric shape this point cloud cluster macroscopically resembles more. The BIM model contains all design components, such as walls, columns, beams, slabs, pipes, etc. Match and correspond the point cloud cluster with the design components in the BIM model. Specifically, compare the characteristics of the point cloud cluster, such as shape classification, position, direction, etc., with the characteristics of each component in the BIM model at the current stage. For example, a point cloud cluster identified as having a planar feature and with a position and direction very close to a certain wall in the BIM model will be associated with this wall; a point cloud cluster identified as having a linear feature and with a position and direction consistent with the edge of a certain column in the BIM will be associated with this column.

[0060] In an alternative embodiment, calculating the intrinsic geometric shape of the point cloud cluster based on the eigenvalues of the point cloud cluster is specifically as follows:

[0061] Calculate the 3x3 covariance matrix for all points in the point cloud cluster, obtain the first three largest eigenvalues corresponding to the covariance matrix, and obtain the intrinsic geometric form based on the first three largest eigenvalues.

[0062] Obtain the three-dimensional coordinates of all points in the point cloud cluster and calculate the 3x3 covariance matrix of these point coordinates. The 3x3 covariance matrix describes the main directions and dispersion degrees of the point distribution in the point cloud cluster. Perform eigenvalue decomposition on the calculated 3x3 covariance matrix to obtain three eigenvalues, sort them by size. The three eigenvalues represent the variances of the point cloud data in three mutually perpendicular principal directions. The approximate geometric shape of the point cloud cluster can be judged according to the relative sizes of the three eigenvalues:

[0063] If the first eigenvalue is much larger than the second and third eigenvalues, and the second and third eigenvalues are close, it indicates that the point cloud is mainly distributed along one direction and the shape tends to be linear, such as steel bars, columns, etc. If the first eigenvalue and the second eigenvalue are close and much larger than the third eigenvalue, it indicates that the point cloud is mainly distributed on a plane and the shape tends to be planar, such as walls, floors, etc. If the three eigenvalues are approximately equal, it indicates that the point cloud is evenly distributed in three directions and the shape tends to be volumetric. Furthermore, a geometric shape label can be assigned to the point cloud cluster, and the label is line, plane, or volume.

[0064] For each point cloud cluster, combine the intrinsic geometric form and location information. In the BIM design model of the current construction stage, search for construction components that are geometrically similar and spatially close to the point cloud cluster. For example, if the point cloud cluster is linear and located at a position where a support column is expected, search for columnar components near that position in the BIM model. If the point cloud cluster is planar and located at a position where a wall is expected, search for wall components near that position in the BIM model. Establish an association relationship between the point cloud cluster and the most likely corresponding construction component in the BIM design model according to the geometric shape matching degree and spatial location proximity.

[0065] S3. Use the construction component associated with the point cloud cluster to perform three-dimensional reconstruction on the point cloud cluster, and update and visually display the current construction progress status of each component in the BIM design model.

[0066] The point cloud cluster itself may be sparse, noisy, or incomplete even after recognition. After obtaining the point cloud cluster and the corresponding construction component, a connection is established between them, and the construction component can guide the three-dimensional reconstruction of the point cloud cluster. In one embodiment, extract the standard geometric representation of the component from the BIM model. For example, obtain its 3D Mesh M_bim, and the transformation matrix T that transforms M_bim from its standard coordinate system to the world coordinate system where the point cloud P is located. Apply the transformation T to M_bim to obtain an initial BIM model aligned with the point cloud.

[0067] For more precise reconstruction, the Iterative Closest Point (ICP) algorithm is used to further refine the registration of the point cloud clusters and the aligned BIM model M_aligned. The normal vectors of each point in the point cloud cluster P are calculated. When calculating the normal vectors, the information provided by M_aligned is utilized. For example, for a point p, find its closest point q on the surface of M_aligned, and use the surface normal vector at q as the initial normal vector estimate for p, or use the average of the normal vectors of p and q as the normal vector of p. Run the Poisson surface reconstruction algorithm using the point cloud with normal vector information.

[0068] In another embodiment, 3D reconstruction of the point cloud cluster is performed using the construction components associated with the point cloud cluster, specifically:

[0069] If the construction component associated with the point cloud cluster has a complex shape, the construction component is used to guide the 3D reconstruction of the point cloud cluster; otherwise, the geometric type is extracted from the attributes of the associated BIM component, the parameters of the geometric primitive of the corresponding type are fitted by the least squares method, and a 3D model of the point cloud cluster is generated according to the fitted parameters.

[0070] Check the BIM component associated with the current point cloud cluster to determine whether its geometric shape is a complex shape or a simple shape. In one embodiment, the simple shapes are planes, cylinders, and cuboids, and other shapes are complex shapes. If the associated component has a complex shape, use the precise geometric shape of the BIM component as prior knowledge or a template, and fit the data points of the point cloud cluster to the surface of this BIM component. Reconstruction algorithms such as Poisson surface reconstruction use the shape information of the BIM component to generate a more regular and design-intent-compliant 3D model that reflects the actual point cloud data. If the associated component has a simple shape, extract its basic geometric type from the attribute information of the associated BIM component, and use the least squares method to fit the parameters of the corresponding geometric primitive for all points in the point cloud cluster. For example, if the geometric type is a plane, fit the best plane equation; if the geometric type is a cylinder, fit the best cylinder axis, radius, and height. Generate a geometric primitive as the 3D model of the point cloud cluster according to the optimized parameters obtained by the least squares method. In one embodiment, the guiding methods include, but are not limited to, using the BIM component as a shape template or as a reconstruction constraint space. For example, according to the spatial range limit of the BIM component, 3D reconstruction is performed within the spatial range limit to prevent interference from other points.

[0071] For each BIM component associated with a point cloud cluster that has successfully undergone 3D reconstruction, in the attribute set of the BIM model, mark the status of the component as constructed, partially constructed, etc. Associate the reconstructed 3D model or its key parameters, such as the fitted dimensions, with the BIM component and store them as the current situation information.

[0072] In the visualization interface of the BIM software, change the display mode of these components in the updated state. For example, change the color of the components, display those not yet constructed as gray or transparent, and display those that have been detected as green or other colors.

[0073] Figure 4 The structural diagram of the second embodiment of the present invention is shown, as Figure 4 The BIM-based dynamic monitoring system for deep foundation pit construction shown, includes the following modules:

[0074] The segmentation module is used to divide the BIM design model into multiple stages according to the construction stage, obtain the on-site point cloud data of the deep foundation pit and the current construction stage, construct a point cloud map based on the belonging consistency probability and boundary compliance degree of the points in the point cloud in the BIM design model of the current construction stage, and use the minimum segmentation with hierarchical constraints to segment the point cloud map to obtain multiple point cloud clusters;

[0075] The association module is used to calculate the intrinsic geometric shape of the point cloud cluster based on the eigenvalues of the covariance matrix of the point cloud cluster, and use the geometric shape and the positional relationship of the point cloud cluster to associate the point cloud cluster with the construction components in the BIM design model of the current construction stage;

[0076] The progress visualization module is used to perform three-dimensional reconstruction on the point cloud cluster by using the construction components associated with the point cloud cluster, and update and visually display the current construction progress status of each component in the BIM design model.

[0077] Preferably, constructing the point cloud map based on the belonging consistency probability and boundary compliance degree of the points in the point cloud in the BIM design model of the current construction stage is specifically:

[0078] Align the on-site point cloud data and the BIM design model of the current construction stage to the same coordinate system; calculate the distance from the point to the nearest component in the BIM design model of the current construction stage, and calculate the belonging probability of the point belonging to the nearest component based on the distance;

[0079] For each point in the on-site point cloud data, find its k nearest neighbor points in the point cloud. If the point and the nearest neighbor points belong to the same component, the belonging consistency probability is the product of their belonging probabilities, otherwise, the belonging consistency probability is 0;

[0080] Obtain the line segment from the point to the nearest neighbor point, calculate the intersection points of the line segment with all components in the BIM design model of the current construction stage, and calculate the boundary compliance factor based on the number of the intersection points;

[0081] Take the product of the boundary compliance factor and the belonging consistency probability as the weight of the point and the nearest neighbor point, and construct the point cloud map based on the weight.

[0082] Preferably, the point cloud map is segmented into multiple point cloud clusters by using the minimum segmentation with hierarchical constraints, specifically as follows:

[0083] For any two connected points in the point cloud map, obtain the hierarchical difference between the two connected points in the BIM component at the current construction stage;

[0084] Based on the hierarchical difference, obtain an adjustment weight, and adjust the weight of the edge between the two connected points according to the adjustment weight;

[0085] Segment the adjusted point cloud map by using the minimum segmentation method to obtain multiple point cloud clusters.

[0086] Preferably, the intrinsic geometric shape of the point cloud cluster is calculated based on the eigenvalue of the point cloud cluster, specifically as follows:

[0087] Calculate the 3x3 covariance matrix of all points in the point cloud cluster, obtain the first 3 largest eigenvalues corresponding to the covariance matrix, and obtain the intrinsic geometric shape according to the first 3 largest eigenvalues.

[0088] Preferably, the point cloud cluster is three-dimensionally reconstructed by using the construction component associated with the point cloud cluster, specifically as follows:

[0089] If the construction component associated with the point cloud cluster has a complex shape, use the construction component to guide the three-dimensional reconstruction of the point cloud cluster; otherwise, extract the geometric type from the attributes of the associated BIM component, fit the parameters of the geometric primitive of the corresponding type by the least squares method, and generate a three-dimensional model of the point cloud cluster according to the fitted parameters.

[0090] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the method as described in Embodiment 1.

[0091] In addition, the present invention also provides a computer device, which at least includes a memory and a processor, and a computer program is stored on the memory, and the computer program, when executed by the processor, implements the method as described in Embodiment 1.

[0092] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of adding a necessary general hardware platform, and of course, it can also be implemented by a combination of hardware and software. Based on such an understanding, the above technical solution, in essence, or the part that makes contributions to the prior art can be embodied in the form of a computer product. The present invention can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) that contain computer-usable program codes.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Other embodiments can also be adopted. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A dynamic monitoring method for deep foundation pit construction based on BIM, characterized in that, The method includes the following steps: Divide the BIM design model into multiple stages according to the construction stage, obtain the in-situ point cloud data of the deep foundation pit and the current construction stage, construct a point cloud map based on the belonging consistency probability and boundary compliance degree of the points in the point cloud in the BIM design model of the current construction stage, and use minimum segmentation with hierarchical constraints to segment the point cloud map to obtain multiple point cloud clusters; Calculate the intrinsic geometric shape of the point cloud cluster based on the eigenvalues of the covariance matrix of the point cloud cluster, and use the geometric shape and the positional relationship of the point cloud cluster to associate the point cloud cluster with the construction components in the BIM design model of the current construction stage; Use the construction components associated with the point cloud cluster to perform 3D reconstruction on the point cloud cluster, and update and visually display the current construction progress status of each component in the BIM design model.

2. The method according to claim 1, wherein The construction of the point cloud map based on the belonging consistency probability and boundary compliance degree of the points in the point cloud in the BIM design model of the current construction stage is specifically as follows: Align the in-situ point cloud data and the BIM design model of the current construction stage to the same coordinate system; calculate the nearest component in the BIM design model of the current construction stage to the point, and calculate the belonging probability of the point belonging to the nearest component based on the distance; Find the k nearest neighbor points of each point in the in-situ point cloud data in the point cloud. If the point and the nearest neighbor points belong to the same component, the belonging consistency probability is the product of their belonging probabilities; otherwise, the belonging consistency probability is 0; Obtain the line segment from the point to the nearest neighbor point, calculate the intersection points of the line segment and all components in the BIM design model of the current construction stage, and calculate the boundary compliance factor based on the number of the intersection points; Take the product of the boundary compliance factor and the belonging consistency probability as the weight of the point and the nearest neighbor point, and construct a point cloud map based on the weight.

3. The method according to claim 1, wherein The segmentation of the point cloud map using minimum segmentation with hierarchical constraints to obtain multiple point cloud clusters is specifically as follows: For any two connected points in the point cloud map, obtain the hierarchical difference of the two connected points in the BIM components of the current construction stage; Obtain the adjustment weight based on the hierarchical difference, and adjust the weight of the edge of the two connected points according to the adjustment weight; Segment the adjusted point cloud map using the minimum segmentation method to obtain multiple point cloud clusters.

4. The method according to claim 1, characterized in that The calculation of the intrinsic geometric shape of the point cloud cluster based on the eigenvalues of the point cloud cluster is specifically as follows: Calculate the 3x3 covariance matrix of all points in the point cloud cluster, obtain the first 3 largest eigenvalues corresponding to the covariance matrix, and obtain the intrinsic geometric shape based on the first 3 largest eigenvalues.

5. The method according to claim 1, characterized in that, The 3D reconstruction of the point cloud cluster using the construction components associated with the point cloud cluster is specifically as follows: If the construction component associated with the point cloud cluster has a complex shape, use the construction component to guide the 3D reconstruction of the point cloud cluster; otherwise, extract the geometric type from the attributes of the associated BIM component, fit the parameters of the geometric primitive of the corresponding type by the least squares method, and generate the 3D model of the point cloud cluster according to the fitted parameters.

6. A dynamic monitoring system for deep foundation pit construction based on BIM, characterized in that, The system includes the following modules: A segmentation module, which is used to divide the BIM design model into multiple stages according to the construction stage, obtain the in-situ point cloud data of the deep foundation pit and the current construction stage, and construct a point cloud map based on the belonging consistency probability and boundary compliance of the points in the point cloud in the BIM design model of the current construction stage. The point cloud map is segmented using minimum segmentation with hierarchical constraints to obtain multiple point cloud clusters; An association module, which is used to calculate the intrinsic geometric shape of the point cloud cluster based on the eigenvalues of the covariance matrix of the point cloud cluster, and use the geometric shape and the positional relationship of the point cloud cluster to associate the point cloud cluster with the construction components in the BIM design model of the current construction stage; A progress visualization module, which is used to perform three-dimensional reconstruction on the point cloud cluster using the construction components associated with the point cloud cluster, and update and visually display the current construction progress status of each component in the BIM design model.

7. The system according to claim 6, wherein The construction of the point cloud map based on the belonging consistency probability and boundary compliance of the points in the point cloud in the BIM design model of the current construction stage is specifically as follows: Align the in-situ point cloud data and the BIM design model of the current construction stage to the same coordinate system; calculate the distance from the point to the nearest component in the BIM design model of the current construction stage, and calculate the belonging probability of the point belonging to the nearest component based on the distance; For each point in the in-situ point cloud data, find its k nearest neighbor points in the point cloud. If the point and the nearest neighbor points belong to the same component, the belonging consistency probability is the product of their belonging probabilities; otherwise, the belonging consistency probability is 0; Obtain the line segment from the point to the nearest neighbor point, calculate the intersection points of the line segment with all components in the BIM design model of the current construction stage, and calculate the boundary compliance factor based on the number of the intersection points; Use the product of the boundary compliance factor and the belonging consistency probability as the weight of the point and the nearest neighbor point, and construct a point cloud map based on the weight.

8. The system according to claim 6, wherein The segmentation of the point cloud map using minimum segmentation with hierarchical constraints to obtain multiple point cloud clusters is specifically as follows: For any two connected points in the point cloud map, obtain the hierarchical difference between the two connected points in the BIM components of the current construction stage; Obtain the adjustment weight based on the hierarchical difference, and adjust the weight of the edge between the two connected points according to the adjustment weight; Segment the adjusted point cloud map using the minimum segmentation method to obtain multiple point cloud clusters.

9. The system according to claim 6, wherein The calculation of the intrinsic geometric shape of the point cloud cluster based on the eigenvalues of the point cloud cluster is specifically as follows: Calculate the 3x3 covariance matrix of all points in the point cloud cluster, obtain the first 3 largest eigenvalues corresponding to the covariance matrix, and obtain the intrinsic geometric shape based on the first 3 largest eigenvalues.

10. A computer-readable storage medium, on which a computer program is stored, characterized in that, The computer program, when executed by a processor, implements the method according to any one of claims 1-5.

Images