Deep foundation pit construction dynamic monitoring method and system based on BIM

Abstract

The invention relates to a BIM-based deep foundation pit construction dynamic monitoring method and system, and specifically, the method comprises the steps: dividing a BIM design model into a plurality of stages according to a construction stage, and obtaining deep foundation pit site point cloud data and a current construction stage; constructing a point cloud picture based on the affiliation consistency probability and boundary conformity of the points in the point cloud in the BIM design model at the current construction stage, and segmenting the point cloud picture by adopting minimum segmentation with hierarchical constraint to obtain a plurality of point cloud clusters; calculating the internal geometrical morphology of the point cloud cluster based on the characteristic value of the covariance matrix of the point cloud cluster, and associating the point cloud cluster with the construction member in the BIM design model at the current construction stage by using the position relationship between the geometrical morphology and the point cloud cluster; and performing three-dimensional reconstruction on the point cloud cluster by using construction components associated with the point cloud cluster, and updating and visually displaying the current construction progress state of each component in the BIM design model.

Description

Technical Field

[0001] The present invention relates to the field of construction, and in particular to a BIM-based deep foundation pit construction dynamic monitoring method and system. Background Art

[0002] Deep foundation pit engineering is a basic link in construction. Its construction process is complex and high-risk, involving multiple key steps such as earth excavation, support structure construction, and precipitation. The deformation, displacement, stress and other states during the construction process are directly related to the safety of the foundation pit itself and the surrounding environment. Dynamic and accurate monitoring of deep foundation pit construction is crucial and is a necessary way to ensure project safety, control quality and master progress. Traditional deep foundation pit monitoring methods mainly rely on manual deployment of monitoring points and use 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 degree of automation, high labor intensity, and delayed response. BIM technology can establish a digital model containing rich geometric and non-geometric information in the design stage, providing a unified data basis for construction planning, simulation and management. Point cloud technology can quickly and accurately obtain three-dimensional spatial information of the construction site, form dense point cloud data, and objectively record the site. Combining BIM with point cloud technology, by comparing the design model with the on-site measured point cloud, it is possible to automatically analyze the construction progress, deviation and quality. However, how to automatically segment the point cloud and reconstruct the point cloud in 3D is the key to dynamic monitoring of deep foundation pit construction. Summary of the invention

[0003] In order to solve the above problems, in a first aspect of the present invention, a BIM-based deep foundation pit construction dynamic monitoring method is provided, the method comprising the following steps: The BIM design model is divided into multiple stages according to the construction stage. The deep foundation pit on-site point cloud data and the current construction stage are obtained. A point cloud map is constructed based on the probability of belonging consistency and boundary conformity of the midpoints of the point cloud in the BIM design model of the current construction stage. The point cloud map is segmented using the minimum segmentation with hierarchical constraints to obtain multiple point cloud clusters. Calculating the intrinsic geometric form of the point cloud cluster based on the eigenvalue of the covariance matrix of the point cloud cluster, and associating the point cloud cluster with the construction components in the BIM design model of the current construction stage by using the positional relationship between the geometric form and the point cloud cluster; The point cloud cluster is three-dimensionally reconstructed using construction components associated with the point cloud cluster, and the current construction progress status of each component is updated and visually displayed in the BIM design model.

[0004] Preferably, the point cloud map is constructed based on the probability of belonging consistency and boundary conformity of the midpoints of the point cloud in the BIM design model of the current construction stage, specifically: 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 probability of the point belonging to the nearest component based on the distance; 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 point belong to the same component, the probability of belonging consistency is the product of the two belonging probabilities. Otherwise, the probability of belonging consistency is 0. Obtain a line segment from a 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 conformity factor according to the number of the intersection points; The product of the boundary conformity factor and the attribution consistency probability is used as the weight of the point and the nearest neighbor point, and a point cloud map is constructed based on the weight.

[0005] Preferably, the point cloud image is segmented by using the minimum segmentation with hierarchical constraints to obtain a plurality of point cloud clusters, specifically: For any two connected points in the point cloud, obtain the hierarchical difference between the two connected points in the BIM component of the current construction stage; Obtaining an adjustment weight based on the level difference, and adjusting the weight of the edge of the two connected points according to the adjustment weight; The adjusted point cloud image is segmented using the minimum segmentation method to obtain multiple point cloud clusters.

[0006] Preferably, the intrinsic geometric form of the point cloud cluster is calculated based on the eigenvalue of the point cloud cluster, specifically: The 3x3 covariance matrix of all points in the point cloud cluster is calculated, and the first three largest eigenvalues ​​corresponding to the covariance matrix are obtained. The intrinsic geometric form is obtained according to the first three largest eigenvalues.

[0007] Preferably, the point cloud cluster is three-dimensionally reconstructed using the construction components associated with the point cloud cluster, specifically: If the construction component associated with the point cloud cluster is a complex shape, the construction component is used to guide the point cloud cluster for three-dimensional reconstruction; otherwise, the geometric type is extracted from the associated BIM component attributes, the parameters of the corresponding type of geometric primitives are fitted by the least squares method, and the three-dimensional model of the point cloud cluster is generated according to the fitted parameters.

[0008] In a second aspect of the present invention, a BIM-based deep foundation pit construction dynamic monitoring system is provided, the system comprising the following modules: A segmentation module is used to 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 point in the point cloud in the BIM design model of the current construction stage, and segment the point cloud map using the minimum segmentation with hierarchical constraints to obtain multiple point cloud clusters; An association module, for calculating the intrinsic geometric form of the point cloud cluster based on the eigenvalue of the covariance matrix of the point cloud cluster, and associating the point cloud cluster with the construction components in the BIM design model of the current construction stage by using the positional relationship between the geometric form and the point cloud cluster; The progress visualization module is used to perform three-dimensional reconstruction of the point cloud cluster using the construction components associated with the point cloud cluster, and to update and visualize the current construction progress status of each component in the BIM design model.

[0009] Preferably, the point cloud map is constructed based on the probability of belonging consistency and boundary conformity of the midpoints of the point cloud in the BIM design model of the current construction stage, specifically: 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 probability of the point belonging to the nearest component based on the distance; 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 point belong to the same component, the probability of belonging consistency is the product of the two belonging probabilities. Otherwise, the probability of belonging consistency is 0. Obtain a line segment from a 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 conformity factor according to the number of the intersection points; The product of the boundary conformity factor and the attribution consistency probability is used as the weight of the point and the nearest neighbor point, and a point cloud map is constructed based on the weight.

[0010] Preferably, the point cloud image is segmented by using the minimum segmentation with hierarchical constraints to obtain a plurality of point cloud clusters, specifically: For any two connected points in the point cloud, obtain the hierarchical difference between the two connected points in the BIM component of the current construction stage; Obtaining an adjustment weight based on the level difference, and adjusting the weight of the edge of the two connected points according to the adjustment weight; The adjusted point cloud image is segmented using the minimum segmentation method to obtain multiple point cloud clusters.

[0011] Preferably, the intrinsic geometric form of the point cloud cluster is calculated based on the eigenvalue of the point cloud cluster, specifically: The 3x3 covariance matrix of all points in the point cloud cluster is calculated, and the first three largest eigenvalues ​​corresponding to the covariance matrix are obtained. The intrinsic geometric form is obtained according to the first three largest eigenvalues.

[0012] Preferably, the point cloud cluster is three-dimensionally reconstructed using the construction components associated with the point cloud cluster, specifically: If the construction component associated with the point cloud cluster is a complex shape, the construction component is used to guide the point cloud cluster for three-dimensional reconstruction; otherwise, the geometric type is extracted from the associated BIM component attributes, the parameters of the corresponding type of geometric primitives are fitted by the least squares method, and the three-dimensional model of the point cloud cluster is generated according to the fitted parameters.

[0013] In addition, the present invention also provides a computer-readable storage medium, on which a computer program is stored, characterized in that when the computer program is executed by a processor, it implements the method described in the first aspect.

[0014] The present invention improves the semantic accuracy of segmentation by constructing a point cloud map based on the probability of belonging consistency and boundary conformity and adopting a minimum segmentation algorithm with hierarchical constraints; and realizes the association between point cloud clusters and BIM components by calculating the intrinsic geometric form of point cloud clusters and combining position information, and uses BIM components to guide the three-dimensional reconstruction process of point cloud clusters, thereby improving the accuracy of the reconstructed model. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of Embodiment 1; Figure 2 It is a local schematic diagram of the point cloud image; Figure 3 A schematic diagram for performing minimum segmentation on a point cloud image; Figure 4 This is a structural diagram of the second embodiment. DETAILED DESCRIPTION

[0016] In this article, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Figure 1 A flow chart of a first embodiment of the present invention is shown. Figure 1 As shown, the following steps are included: S1, dividing the BIM design model into multiple stages according to the construction stage, acquiring the deep foundation pit on-site point cloud data and the current construction stage, constructing a point cloud map based on the belonging consistency probability and boundary conformity of the point in the point cloud in the BIM design model of the current construction stage, and segmenting the point cloud map using the minimum segmentation with hierarchical constraints to obtain multiple point cloud clusters; The complete BIM (Building Information Model) design model is divided into different construction stages, and each stage has a corresponding BIM sub-model. Use a three-dimensional laser scanner 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 consistency in spatial position. In one embodiment, identification points are set in the BIM design model, and corresponding identification points are set at the construction site. The point cloud and the BIM design model of the current construction stage are aligned using the identification points. In one embodiment, the point cloud map is constructed based on the probability of consistency of belonging and boundary conformity of the midpoints of the point cloud in the BIM design model of the current construction stage, specifically: 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 probability of the point belonging to the nearest component based on the distance; 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 point belong to the same component, the probability of belonging consistency is the product of the two belonging probabilities. Otherwise, the probability of belonging consistency is 0. Obtain a line segment from a 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 conformity factor according to the number of the intersection points; The product of the boundary conformity factor and the attribution consistency probability is used as the weight of the point and the nearest neighbor point, and a point cloud map is constructed based on the weight.

[0019] For each point in the point cloud, calculate its distance to all components in the BIM sub-model at the current stage, find the component with the closest distance, and based on this shortest distance, calculate the probability that the point belongs to the nearest component. The closer the distance, the higher the probability. In one embodiment, if the distance is 0 or a negative value, the 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 attribution consistency between them is the product of the attribution probabilities of the two points; if they do not belong to the same BIM component, the probability of attribution consistency between them is 0. For each point in the point cloud and one of its nearest neighbors, obtain the line segment connecting the two points, and calculate the number of intersections between this line segment and the surface of all components in the BIM sub-model at the current stage. Calculate the boundary conformity factor based on the number of intersections. The fewer the intersections, the more likely the 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. There is an edge between the point and its k nearest neighboring points. The weight of the edge is the product or sum of the probability of belonging consistency between the point and its nearest neighboring points and the boundary conformity factor, thereby constructing a weighted point cloud graph. Figure 2 A portion of a point cloud image is shown.

[0020] In one embodiment, the point cloud image is segmented by using the minimum segmentation with hierarchical constraints to obtain multiple point cloud clusters, specifically: For any two connected points in the point cloud, obtain the hierarchical difference between the two connected points in the BIM component of the current construction stage; Obtaining an adjustment weight based on the level difference, and adjusting the weight of the edge of the two connected points according to the adjustment weight; The adjusted point cloud image is segmented using the minimum segmentation method to obtain multiple point cloud clusters.

[0021] For any two points in the point cloud connected by edges, find their corresponding components in the BIM model of the current stage. Determine the difference between the two components in the BIM structural hierarchy. According to the hierarchical difference, calculate the adjustment weight. Among them, the hierarchical difference is the difference between the two points in the BIM structural hierarchy, that is, the difference between the BIM components represented by the two points at different levels of the building structure such as foundation, column, beam, plate, etc. If the BIM components corresponding to the two points are very different in the structural hierarchy, 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 hierarchical difference, the smaller the adjustment weight, indicating that they should not be classified into the same cluster. Use the adjustment weight to adjust the original edge weight calculated in the point cloud, for example, by multiplication. Apply the minimum segmentation algorithm to the weight-adjusted point cloud, for example, Normalized Cuts, etc. The goal of the minimum segmentation algorithm is to find a segmentation method that makes the total weight of the edges between the segmented clusters as small as possible, while the total weight of the edges within the clusters is as large as possible, thereby segmenting the entire point cloud into multiple point cloud clusters, each of which corresponds to a component at the construction site. Figure 3 Schematic diagram of segmentation after adjusting weights.

[0022] S2, calculating the intrinsic geometric form of the point cloud cluster based on the eigenvalue of the covariance matrix of the point cloud cluster, and associating the point cloud cluster with the construction components in the BIM design model of the current construction stage by using the positional relationship between the geometric form and the point cloud cluster; For a point cloud cluster, the covariance matrix can be used to calculate the distribution of these points in three dimensions and the correlation between them. The covariance matrix is ​​decomposed to obtain eigenvalues ​​and eigenvectors, where the eigenvalue represents the degree of dispersion or variance of the point cloud data in the direction of the corresponding eigenvector. By comparing the size relationship of these three eigenvalues, it is possible to determine which geometric shape this point cloud cluster is more like in the macroscopic sense. The BIM model contains all design components, such as walls, columns, beams, plates, pipes, etc. The point cloud cluster is matched with the design components in the BIM model. Specifically, the features of the point cloud cluster, such as shape classification, position, and direction, are compared with the features of each component in the BIM model at the current stage. For example, a point cloud cluster identified as a plane feature and whose position and direction are very close to a wall in the BIM model will be associated with this wall; a point cloud cluster identified as a linear feature and whose position and direction are consistent with the edge of a column in the BIM will be associated with this column.

[0023] In an optional embodiment, the intrinsic geometric form of the point cloud cluster is calculated based on the eigenvalue of the point cloud cluster, specifically: The 3x3 covariance matrix of all points in the point cloud cluster is calculated, and the first three largest eigenvalues ​​corresponding to the covariance matrix are obtained. The intrinsic geometric form is obtained according to the first three largest eigenvalues.

[0024] Get 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 direction and discreteness of the point distribution in the point cloud cluster. Perform eigenvalue decomposition on the calculated 3x3 covariance matrix to obtain three eigenvalues, which are sorted by size. The three eigenvalues ​​represent the variance of the point cloud data in three mutually perpendicular main directions. The approximate geometric shape of the point cloud cluster can be determined based on the relative sizes of the three eigenvalues: If the first eigenvalue is much larger than the second and third eigenvalues, and the second and third eigenvalues ​​are similar, it means that the point cloud is mainly distributed in one direction and the shape tends to be linear, such as steel bars and columns. If the first eigenvalue is similar to the second eigenvalue and much larger than the third eigenvalue, it means that the point cloud is mainly distributed on a plane and the shape tends to be planar, such as walls and floors. If the three eigenvalues ​​are approximately equal, it means that the point cloud is relatively evenly distributed in three directions and the shape tends to be volume-like, and the point cloud cluster can be labeled with a geometric shape, which is a line, a surface, or a volume.

[0025] For each point cloud cluster, the intrinsic geometry and location information are combined. In the BIM design model of the current construction phase, construction components with similar geometry and close spatial positions to the point cloud cluster are searched. For example, if the point cloud cluster is linear and located at a position where a support column is expected, the columnar components near the position are searched in the BIM model. If the point cloud cluster is planar and located at a position where a wall is expected, the wall components near the position are searched in the BIM model. Based on the matching degree of the geometric shape and the proximity of the spatial position, the point cloud cluster is associated with the construction component in the most likely corresponding BIM design model.

[0026] S3, using the construction components associated with the point cloud cluster to perform three-dimensional reconstruction on the point cloud cluster, and updating and visually displaying the current construction progress status of each component in the BIM design model.

[0027] The point cloud cluster itself, even after identification, may be sparse, noisy or incomplete. After obtaining the point cloud cluster and the construction component corresponding to the point cloud cluster, the two are connected, and the construction component can guide the three-dimensional reconstruction of the point cloud cluster. In one embodiment, the standard geometric representation of the component is extracted from the BIM model, for example, its 3D Mesh M_bim is obtained, and the transformation matrix T of M_bim is transformed from its standard coordinate system to the world coordinate system where the point cloud P is located. The transformation T is applied to M_bim to obtain the initial BIM model aligned with the point cloud.

[0028] For more accurate reconstruction, the iterative closest point algorithm is used to further fine-tune the registration of the point cloud cluster and the aligned BIM model M_aligned. The normal vector of each point in the point cloud cluster P is calculated. When calculating the normal vector, the information provided by M_aligned is used. For example, for point p, its nearest point q on the M_aligned surface is found, and the surface normal vector at q is used as the initial normal vector estimate of p, or the average of the normal vectors of p and q is used as the normal vector of p. The point cloud with normal vector information is used to run the Poisson surface reconstruction algorithm.

[0029] In yet another embodiment, the point cloud cluster is three-dimensionally reconstructed using the construction components associated with the point cloud cluster, specifically: If the construction component associated with the point cloud cluster is a complex shape, the construction component is used to guide the point cloud cluster for three-dimensional reconstruction; otherwise, the geometric type is extracted from the associated BIM component attributes, the parameters of the corresponding type of geometric primitives are fitted by the least squares method, and the three-dimensional model of the point cloud cluster is generated according to the fitted parameters.

[0030] 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 shape is a plane, a cylinder, a cuboid, and other shapes are complex shapes. If the associated component is a complex shape, the precise geometric shape of the BIM component is used as a priori knowledge or template to fit the data points of the point cloud cluster to the surface of the BIM component. Reconstruction algorithms such as Poisson surface reconstruction use the shape information of the BIM component to generate a more regular, more in line with the design intent, but also reflects the actual point cloud data. Three-dimensional model. If the associated component is 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 primitives for all points in the point cloud cluster. For example, if the geometric type is a plane, fit the best plane equation, and if the geometric type is a cylinder, fit the best cylinder axis, radius and height. According to the optimized parameters obtained by the least squares fitting, a geometric primitive is generated as the three-dimensional model of the point cloud cluster. In one embodiment, the guiding method includes but is 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, three-dimensional reconstruction is performed within the spatial range limit, which can prevent interference from other points.

[0031] For each BIM component associated with a successfully 3D reconstructed point cloud cluster, the status of the component is marked as constructed, partially constructed, etc. in the attribute set of the BIM model. The reconstructed 3D model or its key parameters such as the fitted size are associated with the BIM component and stored as status information.

[0032] In the visualization interface of the BIM software, change the display mode of these updated status components, for example, change the color of the components, display the unconstructed ones in gray or transparent, and display the detected ones in green or other colors.

[0033] Figure 4 1 shows a structural diagram of a second embodiment of the present invention, as shown in FIG. Figure 4 The BIM-based deep foundation pit construction dynamic monitoring system shown in the figure includes the following modules: A segmentation module is used to 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 point in the point cloud in the BIM design model of the current construction stage, and segment the point cloud map using the minimum segmentation with hierarchical constraints to obtain multiple point cloud clusters; An association module, for calculating the intrinsic geometric form of the point cloud cluster based on the eigenvalue of the covariance matrix of the point cloud cluster, and associating the point cloud cluster with the construction components in the BIM design model of the current construction stage by using the positional relationship between the geometric form and the point cloud cluster; The progress visualization module is used to perform three-dimensional reconstruction of the point cloud cluster using the construction components associated with the point cloud cluster, and to update and visualize the current construction progress status of each component in the BIM design model.

[0034] Preferably, the point cloud map is constructed based on the probability of belonging consistency and boundary conformity of the midpoints of the point cloud in the BIM design model of the current construction stage, specifically: 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 probability of the point belonging to the nearest component based on the distance; 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 point belong to the same component, the probability of belonging consistency is the product of the two belonging probabilities. Otherwise, the probability of belonging consistency is 0. Obtain a line segment from a 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 conformity factor according to the number of the intersection points; The product of the boundary conformity factor and the attribution consistency probability is used as the weight of the point and the nearest neighbor point, and a point cloud map is constructed based on the weight.

[0035] Preferably, the point cloud image is segmented by using the minimum segmentation with hierarchical constraints to obtain a plurality of point cloud clusters, specifically: For any two connected points in the point cloud, obtain the hierarchical difference between the two connected points in the BIM component of the current construction stage; Obtaining an adjustment weight based on the level difference, and adjusting the weight of the edge of the two connected points according to the adjustment weight; The adjusted point cloud image is segmented using the minimum segmentation method to obtain multiple point cloud clusters.

[0036] Preferably, the intrinsic geometric form of the point cloud cluster is calculated based on the eigenvalue of the point cloud cluster, specifically: The 3x3 covariance matrix of all points in the point cloud cluster is calculated, and the first three largest eigenvalues ​​corresponding to the covariance matrix are obtained. The intrinsic geometric form is obtained according to the first three largest eigenvalues.

[0037] Preferably, the point cloud cluster is three-dimensionally reconstructed using the construction components associated with the point cloud cluster, specifically: If the construction component associated with the point cloud cluster is a complex shape, the construction component is used to guide the point cloud cluster for three-dimensional reconstruction; otherwise, the geometric type is extracted from the associated BIM component attributes, the parameters of the corresponding type of geometric primitives are fitted by the least squares method, and the three-dimensional model of the point cloud cluster is generated according to the fitted parameters.

[0038] The present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in the first embodiment is implemented.

[0039] In addition, the present invention also provides a computer device, which includes at least a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the method described in the first embodiment is implemented.

[0040] Through the description of the above implementation methods, technicians in this field can clearly understand that each implementation method can be implemented by adding a necessary general hardware platform, and of course can also be implemented by combining hardware and software. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a computer product, and the present invention can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0041] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it, and other embodiments may also be used. Although the present invention has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that they can still modify the technical solutions recorded in the aforementioned embodiments, or replace some of the technical features therein with equivalents. However, 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 BIM-based deep foundation pit construction dynamic monitoring method, characterized in that: The method comprises the following steps: The BIM design model is divided into multiple stages according to the construction stage. The deep foundation pit on-site point cloud data and the current construction stage are obtained. A point cloud map is constructed based on the probability of belonging consistency and boundary conformity of the midpoints of the point cloud in the BIM design model of the current construction stage. The point cloud map is segmented using the minimum segmentation with hierarchical constraints to obtain multiple point cloud clusters. Calculating the intrinsic geometric form of the point cloud cluster based on the eigenvalue of the covariance matrix of the point cloud cluster, and associating the point cloud cluster with the construction components in the BIM design model of the current construction stage by using the positional relationship between the geometric form and the point cloud cluster; The point cloud cluster is three-dimensionally reconstructed using construction components associated with the point cloud cluster, and the current construction progress status of each component is updated and visually displayed in the BIM design model.

2. The method according to claim 1, characterized in that The point cloud map is constructed based on the probability of belonging consistency and boundary conformity of the midpoints of the point cloud in the BIM design model of the current construction stage, specifically: 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 probability of the point belonging to the nearest component based on the distance; 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 point belong to the same component, the probability of belonging consistency is the product of the two belonging probabilities. Otherwise, the probability of belonging consistency is 0. Obtain a line segment from a 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 conformity factor according to the number of the intersection points; The product of the boundary conformity factor and the attribution consistency probability is used as the weight of the point and the nearest neighbor point, and a point cloud map is constructed based on the weight.

3. The method according to claim 1, characterized in that The point cloud image is segmented by using the minimum segmentation with hierarchical constraints to obtain multiple point cloud clusters, specifically: For any two connected points in the point cloud, obtain the hierarchical difference between the two connected points in the BIM component of the current construction stage; Obtaining an adjustment weight based on the level difference, and adjusting the weight of the edge of the two connected points according to the adjustment weight; The adjusted point cloud image is segmented using the minimum segmentation method to obtain multiple point cloud clusters.

4. The method according to claim 1, characterized in that The intrinsic geometric form of the point cloud cluster is calculated based on the eigenvalue of the point cloud cluster, specifically: The 3x3 covariance matrix of all points in the point cloud cluster is calculated, and the first three largest eigenvalues ​​corresponding to the covariance matrix are obtained. The intrinsic geometric form is obtained according to the first three largest eigenvalues.

5. The method according to claim 1, characterized in that The point cloud cluster is reconstructed in three dimensions using the construction components associated with the point cloud cluster, specifically: If the construction component associated with the point cloud cluster is a complex shape, the construction component is used to guide the point cloud cluster for three-dimensional reconstruction; otherwise, the geometric type is extracted from the associated BIM component attributes, the parameters of the corresponding type of geometric primitives are fitted by the least squares method, and the three-dimensional model of the point cloud cluster is generated according to the fitted parameters.

6. A BIM-based deep foundation pit construction dynamic monitoring system, characterized in that: The system includes the following modules: A segmentation module is used to 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 point in the point cloud in the BIM design model of the current construction stage, and segment the point cloud map using the minimum segmentation with hierarchical constraints to obtain multiple point cloud clusters; An association module, for calculating the intrinsic geometric form of the point cloud cluster based on the eigenvalue of the covariance matrix of the point cloud cluster, and associating the point cloud cluster with the construction components in the BIM design model of the current construction stage by using the positional relationship between the geometric form and the point cloud cluster; The progress visualization module is used to perform three-dimensional reconstruction of the point cloud cluster using the construction components associated with the point cloud cluster, and to update and visualize the current construction progress status of each component in the BIM design model.

7. The system according to claim 6, characterized in that The point cloud map is constructed based on the probability of belonging consistency and boundary conformity of the midpoints of the point cloud in the BIM design model of the current construction stage, specifically: 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 probability of the point belonging to the nearest component based on the distance; 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 point belong to the same component, the probability of belonging consistency is the product of the two belonging probabilities. Otherwise, the probability of belonging consistency is 0. Obtain a line segment from a 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 conformity factor according to the number of the intersection points; The product of the boundary conformity factor and the attribution consistency probability is used as the weight of the point and the nearest neighbor point, and a point cloud map is constructed based on the weight.

8. The system according to claim 6, characterized in that The point cloud image is segmented by using the minimum segmentation with hierarchical constraints to obtain multiple point cloud clusters, specifically: For any two connected points in the point cloud, obtain the hierarchical difference between the two connected points in the BIM component of the current construction stage; Obtaining an adjustment weight based on the level difference, and adjusting the weight of the edge of the two connected points according to the adjustment weight; The adjusted point cloud image is segmented using the minimum segmentation method to obtain multiple point cloud clusters.

9. The system according to claim 6, characterized in that The intrinsic geometric form of the point cloud cluster is calculated based on the eigenvalue of the point cloud cluster, specifically: The 3x3 covariance matrix of all points in the point cloud cluster is calculated, and the first three largest eigenvalues ​​corresponding to the covariance matrix are obtained. The intrinsic geometric form is obtained according to the first three largest eigenvalues.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the computer program implements the method according to any one of claims 1 to 5.

Images