Power system inspection registration method based on BIM model and 3D point cloud model

Abstract

The present invention relates to the technical field of power system maintenance, and in particular to a power system inspection registration method based on a BIM model and a three-dimensional point cloud model, comprising: obtaining and analyzing the BIM model file and the three-dimensional point cloud file of the power system to construct a first and a second registration descriptor; calculating a coarse transformation matrix through the first and the second registration descriptors; converting the BIM spatial coordinate system to the point cloud spatial coordinate system according to the coarse transformation matrix to obtain a coarsely registered BIM model file; triangulating the coarsely registered BIM model file to obtain three-dimensional point cloud models of different scales, and organizing them in a KD-tree hierarchy to iteratively calculate a fine transformation matrix; and finely registering the coarsely registered BIM model file according to the fine transformation matrix. Thus, the method solves the problems that the operation of drones in existing power line inspections is highly dependent on the pilot's experience, which poses a safety risk to the power system and has low inspection efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of power system maintenance, and in particular to a power system inspection registration method based on a BIM model and a three-dimensional point cloud model. Background Art

[0002] With the continuous development of power system maintenance, power system maintenance work has gradually shifted from manual operations to unattended operations. Currently, mainstream drone technology not only has the advantages of small size, controllable speed, and simple operation, but also enables remote photography, providing a new means for power line inspection. In the past few years, emerging unmanned aerial vehicles (UAVs) equipped with sensors (such as light detection and ranging / lidar, optical cameras, infrared cameras, and ultraviolet cameras) have provided a rich data source for comprehensive and accurate power line inspections. One challenge that still hinders the use of drones in power line inspections is that their operation is highly dependent on the pilot's experience, which may pose risks to power system safety and reduce inspection efficiency. Therefore, it is necessary to develop and design a system that utilizes rich data sources (3D point cloud models, BIM models) to guide power system component inspections. Summary of the Invention

[0003] The present invention provides a power system inspection registration method based on a BIM model and a three-dimensional point cloud model to solve the problems in existing power line inspections, such as the excessive reliance of drone operation on pilot experience, which poses a safety risk to the power system and low inspection efficiency.

[0004] In a first aspect, an embodiment of the present invention provides a power system inspection and registration method based on a BIM model and a 3D point cloud model, comprising the following steps: obtaining a BIM model, a BIM model file, a 3D point cloud model, and a 3D point cloud file of a target power system; extracting a geometric representation and a geometric coordinate system in the BIM model file, and generating a first registration descriptor of the BIM model according to the geometric representation and the geometric coordinate system; extracting an intersection direction feature and a normal vector feature of the 3D point cloud file, and generating a second registration descriptor of the 3D point cloud model according to the intersection direction feature and the normal vector feature; calculating a coarse transformation matrix between the BIM model and the 3D point cloud model through the first registration descriptor and the second registration descriptor; converting the BIM model and the 3D point cloud model into a coarse transformation matrix according to the coarse transformation matrix; and The first spatial coordinate system of the BIM model is converted to the second spatial coordinate system of the three-dimensional point cloud model to obtain a coarsely registered BIM model file; the coarsely registered BIM model file is triangulated to generate a plurality of triangular mesh facets; the triangular mesh facets are down-sampled to obtain three-dimensional point cloud models of different scales; the three-dimensional point cloud model and the three-dimensional point cloud models of different scales are organized in a KD-tree hierarchy to obtain KD-tree node units, and a fine transformation matrix is iteratively calculated based on the KD-tree node units; the coarsely registered BIM model file is converted into a finely registered BIM model file based on the fine transformation matrix; an inspection route is generated based on the finely registered BIM model file, and the inspection route is sent to a target UAV.

[0005] Optionally, extracting a geometric representation and a geometric coordinate system from the BIM model file, and generating a first registration descriptor of the BIM model according to the geometric representation and the geometric coordinate system includes:

[0006] Extracting the geometric coordinate system and shape definition of each element in the BIM model file;

[0007] Extracting a geometric representation under the shape definition and resolving the type of the geometric representation;

[0008] Calculating normal vector information, boundary information, and intersection line information of each face according to the type of the geometric representation;

[0009] Based on the geometric coordinate system, the normal vector information, boundary information and intersection line information of each face are combined to obtain a first quadruple representation or a first triplet representation of a series of non-parallel planes as the first registration descriptor.

[0010] Optionally, extracting the intersection direction features and the normal vector features of the three-dimensional point cloud file, and generating a second registration descriptor of the three-dimensional point cloud model according to the intersection direction features and the normal vector features, includes:

[0011] Randomly selecting three points in the three-dimensional point cloud file to construct a temporary plane, and calculating the distance between each point and the temporary plane;

[0012] Distinguishing the three points into inner points and outer points according to the distance, and extracting the inner points and the temporary plane from the three-dimensional point cloud file as the current plane boundary information;

[0013] Iteratively performing the process of extracting plane boundary information from the three-dimensional point cloud file until all points in the three-dimensional point cloud file are randomly selected to obtain plane boundary information of a plurality of surfaces;

[0014] Calculating the intersection direction feature and the normal vector feature according to the plane boundary information of the multiple faces;

[0015] The intersection direction feature and the normal vector feature are combined to obtain a second quadruple representation or a second triplet representation of a series of non-parallel planes as the second registration descriptor.

[0016] Optionally, the calculating a coarse transformation matrix between the BIM model and the three-dimensional point cloud model by using the first registration descriptor and the second registration descriptor includes:

[0017] Constructing a KD tree of the first registration descriptor and the second registration descriptor;

[0018] Calculating the Euclidean distance between each descriptor in the first registration descriptor and each descriptor in the second registration descriptor according to the KD tree;

[0019] The Euclidean distance is compared with a preset threshold. If the Euclidean distance is less than the preset threshold, the straight line segments of the two matching descriptors extracted from the BIM model and the three-dimensional point cloud model are used to calculate the coarse transformation matrix corresponding to each of the two matching descriptors.

[0020] Optionally, converting the first spatial coordinate system of the BIM model to the second spatial coordinate system of the three-dimensional point cloud model according to the coarse transformation matrix to obtain a coarsely registered BIM model file includes:

[0021] Calculating the probability that a point in the three-dimensional point cloud model falls into the first spatial coordinate system according to the coarse transformation matrix corresponding to each of the two matched descriptors;

[0022] The first spatial coordinate system is transformed into the second spatial coordinate system according to the coarse transformation matrix with the highest probability, so as to obtain the BIM model file after the coarse registration.

[0023] Optionally, organizing the three-dimensional point cloud model and the three-dimensional point cloud models of different scales in a KD-tree hierarchy to obtain KD-tree node units, and iteratively calculating a refined transformation matrix based on the KD-tree node units includes:

[0024] Organizing the three-dimensional point cloud model and the three-dimensional point cloud models of different scales in a KD-tree hierarchy to obtain the KD-tree node unit;

[0025] Solving the objective function of the KD-tree node unit based on the maximum likelihood method and Gaussian function;

[0026] The KD-tree node unit is iteratively transformed using the Newton method until the objective function converges to obtain the refined transformation matrix.

[0027] In a second aspect, an embodiment of the present invention provides an electric power system inspection and registration device based on a BIM model and a 3D point cloud model, comprising: an acquisition module for acquiring a BIM model, a BIM model file, a 3D point cloud model and a 3D point cloud file of a target electric power system; a first extraction module for extracting a geometric representation and a geometric coordinate system in the BIM model file, and generating a first registration descriptor of the BIM model according to the geometric representation and the geometric coordinate system; a second extraction module for extracting an intersection direction feature and a normal vector feature of the 3D point cloud file, and generating a second registration descriptor of the 3D point cloud model according to the intersection direction feature and the normal vector feature; a matrix calculation module for calculating a coarse transformation matrix between the BIM model and the 3D point cloud model through the first registration descriptor and the second registration descriptor; a coarse registration module for converting the BIM model and the 3D point cloud model into a coarse transformation matrix according to the coarse transformation matrix. The first spatial coordinate system of the BIM model is converted to the second spatial coordinate system of the three-dimensional point cloud model to obtain a BIM model file after coarse registration; a segmentation module is used to triangulate the BIM model file after coarse registration to generate a plurality of triangular mesh facets; a downsampling module is used to downsample the triangular mesh facets to obtain three-dimensional point cloud models of different scales; an iterative calculation module is used to organize the three-dimensional point cloud model and the three-dimensional point cloud models of different scales in a KD-tree hierarchy to obtain KD-tree node units, and iteratively calculate the fine transformation matrix according to the KD-tree node units; a fine registration module is used to convert the coarsely registered BIM model file into a finely registered BIM model file according to the fine transformation matrix; a generation module is used to generate an inspection route according to the finely registered BIM model file, and send the inspection route to the target drone.

[0028] An embodiment of the third aspect of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored on the memory and runnable on the processor, wherein the processor executes the program to implement the power system inspection and registration method based on the BIM model and the three-dimensional point cloud model as described in the above embodiment.

[0029] A fourth aspect of the present invention provides a computer program product, which, when executed by a processor, implements the above-mentioned power system inspection and registration method based on a BIM model and a three-dimensional point cloud model.

[0030] A fifth aspect of the present invention provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above-mentioned power system inspection and registration method based on the BIM model and the three-dimensional point cloud model.

[0031] The power system inspection alignment method based on BIM model and three-dimensional point cloud model proposed in the embodiment of the present invention can plan a more accurate inspection route for the drone by aligning the BIM model and the three-dimensional point cloud model. This method can effectively reduce the inspection accuracy problem caused by differences in pilot experience and improve the efficiency of power system inspection; the use of high-performance servers for route planning reduces the requirements of the drone end on hardware equipment and computing power, and users can conduct power system component inspections more conveniently and at a low cost without having to rely on high-performance drone end hardware; the three-dimensional point cloud model file and the BIM model file can be used in combination to ensure the multi-source fusion of inspection data and provide real-time feedback. It is an effective intelligent power system maintenance tool that improves the scientificity and accuracy of inspection decisions; the solution has strong adaptability and can be adjusted and optimized according to different power inspection scenarios, and can also handle power inspection tasks of different scales and complexities.

[0032] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0034] Figure 1 A flowchart of a power system inspection registration method based on a BIM model and a three-dimensional point cloud model provided by an embodiment of the present invention;

[0035] Figure 2 A schematic diagram of a specific implementation of a power system inspection registration method based on a BIM model and a three-dimensional point cloud model provided by an embodiment of the present invention;

[0036] Figure 3 A schematic diagram showing the geometric features of a BIM model provided in an embodiment of the present invention;

[0037] Figure 4 A block diagram of a power system inspection and registration device based on a BIM model and a three-dimensional point cloud model provided by an embodiment of the present invention;

[0038] Figure 5 This is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0040] The following describes a power system inspection registration method based on a BIM model and a three-dimensional point cloud model according to an embodiment of the present invention with reference to the accompanying drawings.

[0041] Specifically, Figure 1 A flowchart of a power system inspection registration method based on a BIM model and a three-dimensional point cloud model is provided in an embodiment of the present invention.

[0042] like Figure 1 As shown, the power system inspection registration method based on the BIM model and the three-dimensional point cloud model includes the following steps:

[0043] In step S101 , a BIM model, a BIM model file, a 3D point cloud model, and a 3D point cloud file of a target power system are obtained.

[0044] During the actual implementation process, a laser radar is installed on the target UAV to obtain the three-dimensional point cloud model and three-dimensional point cloud file of the target power system through the laser radar, and at the same time read the pre-set BIM model of the target power system and the BIM model file in the IFC file format.

[0045] In step S102 , a geometric representation and a geometric coordinate system are extracted from the BIM model file, and a first registration descriptor of the BIM model is generated according to the geometric representation and the geometric coordinate system.

[0046] In some embodiments, extracting a geometric representation and a geometric coordinate system from a BIM model file, and generating a first registration descriptor of the BIM model based on the geometric representation and the geometric coordinate system, includes:

[0047] Extract the geometric coordinate system and shape definition of each element in the BIM model file;

[0048] Extract the geometric representation under the shape definition and resolve the type of the geometric representation;

[0049] Calculate the normal vector information, boundary information and intersection line information of each face according to the type of geometric representation;

[0050] Based on the geometric coordinate system, the normal vector information, boundary information and intersection line information of each face are combined to obtain a first quadruple representation or a first triple representation of a series of non-parallel planes as a first registration descriptor.

[0051] like Figure 2 and 3 As shown, in the actual execution process, the geometric coordinate system IfcLocalPlacement and shape definition IfcProductDefinitionShape of each element IfcElement are extracted from the BIM model file, the geometric representation Representations are extracted under the shape definition, and the type Item of the geometric representation is parsed. If the type is a stretched body IfcExtrudedAreaSolid, the stretched length Depth, stretched direction ExtrusionDirection, coordinate position Position, and stretched area attribute SweptArea of the stretched body are parsed, and then the normal vector information and intersection line information of each face are calculated based on the attributes; if the type is a stretched body IfcFaseBasedSurfaceModel, a polyhedron IfcFaseTedBrep, etc., the boundary information and normal vector information of each face are extracted; then the above-extracted normal vector information, boundary information, and intersection line information are combined to obtain a series of quadruple representations of non-parallel planes. Or triples represent , the first registration descriptor is obtained based on the multi-tuple representation.

[0052] In step S103, the intersection direction features and normal vector features of the three-dimensional point cloud file are extracted, and a second registration descriptor of the three-dimensional point cloud model is generated according to the intersection direction features and the normal vector features.

[0053] In some embodiments, extracting intersection direction features and normal vector features of a 3D point cloud file and generating a second registration descriptor of the 3D point cloud model based on the intersection direction features and the normal vector features includes:

[0054] Randomly select three points in the 3D point cloud file to construct a temporary plane, and calculate the distance from each point to the temporary plane;

[0055] The three points are divided into inner points and outer points according to the distance, and the inner points and the temporary plane are extracted from the 3D point cloud file as the plane boundary information of the current front;

[0056] Iteratively execute the process of extracting plane boundary information from the 3D point cloud file until all points in the 3D point cloud file are randomly selected, and plane boundary information of multiple faces is obtained;

[0057] Calculate the intersection direction features and normal vector features based on the plane boundary information of multiple faces;

[0058] The intersection direction feature and the normal vector feature are combined to obtain a second quadruple representation or a second triple representation of a series of non-parallel planes as a second registration descriptor.

[0059] In the actual implementation process, based on the random consistency sampling RANSAC method, three points are randomly selected in the 3D point cloud file. 、 、 , construct a temporary plane equation , and calculate each point The distance to the temporary plane is compared with a preset threshold value, and the three points are divided into inner points and outer points. If the ratio of the inner points meets the preset requirements, the inner points and the temporary plane are extracted from the 3D point cloud file as the current plane boundary information; the process of extracting plane boundary information from the 3D point cloud file is iteratively executed until all points in the 3D point cloud file are randomly selected to obtain plane boundary information of multiple faces; the intersection direction features and normal vector features are calculated based on the plane boundary information of multiple faces; the intersection direction features and normal vector features are combined to obtain a second quadruple representation or a second triple representation of a series of non-parallel planes as a second registration descriptor.

[0060] For example, in step S102 and step S103, the registration descriptor is obtained based on the multi-tuple representation of non-parallel planes, and the steps may be as follows:

[0061] Assuming a plane ,flat , Represents non-planar lines and The distance between Represents a straight line and The angle of yes and The angle of Represents a straight line With plane The angle between The registration descriptor of is described as follows, if ; Otherwise, change the plane order:

[0062]

[0063] In the unlikely case, it is possible to find fewer than two pairs of non-parallel planes. In this case, only two parallel horizontal planes and two parallel vertical planes are extracted, and there is no non-parallel plane quadruple that can uniquely define a rigid transformation. Similarly, the descriptor based on planes and intersection lines is a 6-dimensional vector defined as:

[0064]

[0065] For digital models (BIM models or 3D point cloud models) ,Model The registration descriptor is defined as .

[0066] In step S104 , a coarse transformation matrix between the BIM model and the three-dimensional point cloud model is calculated using the first registration descriptor and the second registration descriptor.

[0067] In some embodiments, calculating a coarse transformation matrix between the BIM model and the 3D point cloud model using the first registration descriptor and the second registration descriptor includes:

[0068] Construct a KD tree of the first registration descriptor and the second registration descriptor;

[0069] Calculate the Euclidean distance between each descriptor in the first registration descriptor and each descriptor in the second registration descriptor according to the KD tree;

[0070] The Euclidean distance is compared with a preset threshold. If the Euclidean distance is less than the preset threshold, the straight line segments of the two matching descriptors extracted from the BIM model and the 3D point cloud model are used to calculate the coarse transformation matrix corresponding to each of the two matching descriptors.

[0071] In the actual implementation process, build BIM model The corresponding first registration descriptor and 3D point cloud models The corresponding second registration descriptor KD tree is used to calculate the Euclidean distance between two descriptors. For eight-dimensional descriptors , excluding the extra two-dimensional descriptor vector, downsampled to To calculate;

[0072] If the Euclidean distance between the descriptors is less than the threshold, the two descriptors are called matched descriptors. After obtaining the matched descriptor vector, the BIM model is used to and 3D point cloud models The extracted straight line segments are used to calculate the coarse transformation matrix corresponding to each registration descriptor ,in represents the rotating part, Represents the translation part.

[0073] In step S105 , the first space coordinate system of the BIM model is converted to the second space coordinate system of the three-dimensional point cloud model according to the coarse transformation matrix to obtain a coarsely registered BIM model file.

[0074] In some embodiments, converting the first spatial coordinate system of the BIM model to the second spatial coordinate system of the three-dimensional point cloud model according to the coarse transformation matrix to obtain a coarsely registered BIM model file includes:

[0075] Calculating the probability that a point in the three-dimensional point cloud model falls into the first spatial coordinate system according to the coarse transformation matrix corresponding to each of the two matched descriptors;

[0076] The first spatial coordinate system is transformed into the second spatial coordinate system according to the coarse transformation matrix with the highest probability to obtain the BIM model file after coarse registration.

[0077] In the actual execution process, the three-dimensional point cloud model is calculated according to the coarse transformation matrix corresponding to the two matched descriptors. The points in the BIM model The probability of the first spatial coordinate system is obtained, and the transformation matrix with the highest probability is selected as the result of coarse registration, and the BIM model is output as the BIM model file after coarse registration. This process realizes the preliminary registration of BIM model and 3D point cloud with less calculation amount, and can also be used for the preliminary generation of UAV route.

[0078] In step S106 , the BIM model file after the rough registration is triangulated to generate a plurality of triangular mesh surfaces.

[0079] In step S107 , the triangular mesh facets are downsampled to obtain three-dimensional point cloud models of different scales.

[0080] In the actual implementation process, the BIM model file after rough registration is triangulated and downsampled into several Mesh triangles, and then downsampled at different spatial resolutions to obtain three-dimensional point cloud models of different scales. For example, the BIM model file after rough registration is triangulated and downsampled into several Mesh triangles. Downsampling with different voxel units to obtain 3D point cloud models with different resolutions , the spatial resolution satisfies .

[0081] In step S108 , the three-dimensional point cloud model and the three-dimensional point cloud models of different scales are organized in a KD-tree hierarchy to obtain KD-tree node units, and a refined transformation matrix is iteratively calculated based on the KD-tree node units.

[0082] In some embodiments, the 3D point cloud model and the 3D point cloud models of different scales are organized in a KD-tree hierarchy to obtain KD-tree node units, and a refined transformation matrix is iteratively calculated based on the KD-tree node units, including:

[0083] The three-dimensional point cloud model and the three-dimensional point cloud models of different scales are organized in a KD-tree hierarchy to obtain a KD-tree node unit;

[0084] Solve the objective function of KD-tree node unit based on maximum likelihood method and Gaussian function;

[0085] The Newton method is used to iteratively solve the transformation of KD-tree node units until the objective function converges and the refined transformation matrix is obtained.

[0086] In the actual implementation process, the three-dimensional point cloud models of different scales are subjected to the rough transformation matrix to obtain the three-dimensional point cloud models of different scales after the rough transformation. The three-dimensional point cloud models of different scales after the coarse transformation are organized in the KD-tree hierarchy, where each point in the point cloud model is located in a unique KD-tree node unit, each node of the KD-tree represents a voxel, and the feature of the node is mainly the mean of the points in it. and the covariance matrix Description, calculated as follows:

[0087]

[0088]

[0089] Where, is the number of points, are the coordinates of the voxel midpoint;

[0090] The coordinate distribution of points within a voxel follows the noise level The modified Gaussian distribution has a density function of:

[0091]

[0092] in, 、 are the coordinates of any two points within a voxel.

[0093] The objective function obtained based on the maximum likelihood method is:

[0094]

[0095] in, Representatives will Apply Transformation The coordinates after the calculation are approximated by Gaussian function to accelerate the processing, and the objective function is obtained. :

[0096]

[0097]

[0098]

[0099] in, It is the point cloud transformed after downsampling The node features of the KD-tree, 、 、 They are the coordinate values of the two points in the voxel in the first dimension, the second dimension, and the third dimension respectively.

[0100] Optimize the objective function using Newton method Perform iterative solution transformation : ,remember The resulting transformation matrix is , then the current solution transformation .

[0101] Repeat for point clouds of different resolutions , execute the above steps until the objective function converges and obtain the refined transformation matrix.

[0102] In step S109 , the coarsely registered BIM model file is converted into a finely registered BIM model file according to the fine transformation matrix.

[0103] In step S110 , an inspection route is generated according to the precisely registered BIM model file, and the inspection route is sent to the target UAV.

[0104] In the actual implementation process, the coarsely registered BIM model file is converted into the finely registered BIM model file according to the fine transformation matrix. After the preliminary registration of the BIM model and the 3D point cloud, the details of the 3D point cloud are combined with the details of the BIM downsampled point cloud to make the alignment of the BIM model and the 3D point cloud more accurate.

[0105] Furthermore, the A* algorithm (i.e., A-star search algorithm) can be used to process the precisely aligned BIM model file to generate an inspection route, and the inspection route is sent to the target UAV, so that the target UAV can inspect the target power system according to the inspection route.

[0106] In summary, the power system inspection registration method based on the BIM model and the three-dimensional point cloud model proposed in an embodiment of the present invention includes the following steps:

[0107] (1) By aligning the BIM model with the 3D point cloud model, a more accurate inspection route can be planned for the UAV. This method can effectively reduce the inspection accuracy problem caused by differences in pilot experience and improve the efficiency of power system inspection;

[0108] (2) Using high-performance servers for route planning reduces the requirements for hardware equipment and computing power on the drone side. Users can inspect power system components more conveniently and at a lower cost without having to rely on high-performance drone hardware.

[0109] (3) It can comprehensively use 3D point cloud model files and BIM model files to ensure the multi-source integration of inspection data and provide real-time feedback. It is an effective intelligent power system maintenance tool and improves the scientificity and accuracy of inspection decisions.

[0110] (4) The solution has strong adaptability and can be adjusted and optimized according to different power inspection scenarios. It can also handle power inspection tasks of different scales and complexities.

[0111] Next, a power system inspection and registration device based on a BIM model and a three-dimensional point cloud model proposed in an embodiment of the present invention will be described with reference to the accompanying drawings.

[0112] Figure 4 A block diagram of a power system inspection and registration device based on a BIM model and a three-dimensional point cloud model provided by an embodiment of the present invention.

[0113] like Figure 4 As shown, the power system inspection and registration device 40 based on the BIM model and the three-dimensional point cloud model includes: an acquisition module 401, a first extraction module 402, a second extraction module 403, a matrix calculation module 404, a coarse registration module 405, a segmentation module 406, a downsampling module 407, an iterative calculation module 408, a fine registration module 409 and a generation module 410.

[0114] Among them, the acquisition module 401 is used to obtain the BIM model, BIM model file, 3D point cloud model and 3D point cloud file of the target power system. The first extraction module 402 is used to extract the geometric representation and geometric coordinate system in the BIM model file, and generate the first registration descriptor of the BIM model based on the geometric representation and geometric coordinate system. The second extraction module 403 is used to extract the intersection direction features and normal vector features of the 3D point cloud file, and generate the second registration descriptor of the 3D point cloud model based on the intersection direction features and normal vector features. The matrix calculation module 404 is used to calculate the coarse transformation matrix between the BIM model and the 3D point cloud model using the first registration descriptor and the second registration descriptor. The coarse registration module 405 is used to convert the first spatial coordinate system of the BIM model to the second spatial coordinate system of the 3D point cloud model based on the coarse transformation matrix to obtain the coarsely registered BIM model file. The segmentation module 406 is used to triangulate the coarsely registered BIM model file to generate a number of triangular mesh facets. Downsampling module 407 is used to downsample triangular mesh facets to obtain 3D point cloud models of different scales. Iterative calculation module 408 is used to organize the 3D point cloud model and 3D point cloud models of different scales into a KD-tree hierarchy to obtain KD-tree node units, and iteratively calculate the fine transformation matrix based on the KD-tree node units. Fine registration module 409 is used to convert the coarsely registered BIM model file into a finely registered BIM model file based on the fine transformation matrix. Generation module 410 is used to generate an inspection route based on the finely registered BIM model file and send the inspection route to the target drone.

[0115] In some embodiments, the first extraction module 402 includes:

[0116] The first extraction unit is used to extract the geometric coordinate system and shape definition of each element in the BIM model file;

[0117] a second extraction unit, configured to extract a geometric representation under the shape definition and parse a type of the geometric representation;

[0118] A first calculation unit is used to calculate normal vector information, boundary information and intersection line information of each face according to the type of geometric representation;

[0119] The first combining unit is used to combine the normal vector information, boundary information and intersection line information of each face based on the geometric coordinate system to obtain a first quadruple representation or a first triple representation of a series of non-parallel planes as a first registration descriptor.

[0120] In some embodiments, the second extraction module 403 includes:

[0121] A random selection unit is used to randomly select three points in the 3D point cloud file to construct a temporary plane and calculate the distance between each point and the temporary plane;

[0122] A third extraction unit is used to distinguish the three points into inner points and outer points according to the distance, and extract the inner points and the temporary plane from the three-dimensional point cloud file as the current plane boundary information;

[0123] an iterative extraction unit, configured to iteratively execute a process of extracting plane boundary information from the three-dimensional point cloud file until all points in the three-dimensional point cloud file are randomly selected, thereby obtaining plane boundary information of a plurality of surfaces;

[0124] A second calculation unit is used to calculate the intersection direction feature and the normal vector feature according to the plane boundary information of the multiple faces;

[0125] The second organization unit is used to combine the intersection direction feature and the normal vector feature to obtain a second quadruple representation or a second triple representation of a series of non-parallel planes as a second registration descriptor.

[0126] In some embodiments, the coarse registration module 405 includes:

[0127] A construction unit, configured to construct a KD tree of the first registration descriptor and the second registration descriptor;

[0128] a third calculation unit, configured to calculate the Euclidean distance between each descriptor in the first registration descriptor and each descriptor in the second registration descriptor according to the KD tree;

[0129] A comparison unit is used to compare the Euclidean distance with a preset threshold. If the Euclidean distance is less than the preset threshold, the straight line segments of the two matching descriptors extracted from the BIM model and the three-dimensional point cloud model are used to calculate the coarse transformation matrix corresponding to each of the two matching descriptors.

[0130] In some embodiments, the iterative calculation module 408 includes:

[0131] A structural organization unit is used to organize the three-dimensional point cloud model and the three-dimensional point cloud models of different scales in a KD-tree hierarchy to obtain a KD-tree node unit;

[0132] A solving unit, used for solving the objective function of the KD-tree node unit based on the maximum likelihood method and the Gaussian function;

[0133] The iterative transformation unit is used to iteratively transform the KD-tree node unit using the Newton method until the objective function converges to obtain a refined transformation matrix.

[0134] It should be noted that the above explanation of the embodiment of the power system inspection and registration method based on BIM model and three-dimensional point cloud model is also applicable to the power system inspection and registration device based on BIM model and three-dimensional point cloud model in this embodiment, and will not be repeated here.

[0135] According to an embodiment of the present invention, a power system inspection registration device based on a BIM model and a three-dimensional point cloud model includes the following steps:

[0136] (1) By aligning the BIM model with the 3D point cloud model, a more accurate inspection route can be planned for the UAV. This method can effectively reduce the inspection accuracy problem caused by differences in pilot experience and improve the efficiency of power system inspection;

[0137] (2) Using high-performance servers for route planning reduces the requirements for hardware equipment and computing power on the drone side. Users can inspect power system components more conveniently and at a lower cost without having to rely on high-performance drone hardware.

[0138] (3) It can comprehensively use 3D point cloud model files and BIM model files to ensure the multi-source integration of inspection data and provide real-time feedback. It is an effective intelligent power system maintenance tool and improves the scientificity and accuracy of inspection decisions.

[0139] (4) The solution has strong adaptability and can be adjusted and optimized according to different power inspection scenarios. It can also handle power inspection tasks of different scales and complexities.

[0140] Figure 5 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device may include:

[0141] Memory 501 , processor 502 , and computer programs stored in the memory 501 and executable on the processor 502 .

[0142] When the processor 502 executes the program, the power system inspection registration method based on the BIM model and the three-dimensional point cloud model provided in the above embodiment is implemented.

[0143] Furthermore, the electronic device further includes:

[0144] The communication interface 503 is used for communication between the memory 501 and the processor 502 .

[0145] The memory 501 is used to store computer programs that can be run on the processor 502 .

[0146] The memory 501 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0147] If the memory 501, processor 502, and communication interface 503 are implemented independently, the communication interface 503, memory 501, and processor 502 can be interconnected via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be divided into address buses, data buses, control buses, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0148] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.

[0149] The processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0150] An embodiment of the present invention further provides a computer program product, which, when executed by a processor, implements the above-mentioned power system inspection registration method based on a BIM model and a three-dimensional point cloud model.

[0151] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned power system inspection and registration method based on a BIM model and a three-dimensional point cloud model.

[0152] In the description of this specification, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0153] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "N" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0154] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or N executable instructions for implementing a custom logical function or step of a process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0155] The logic and / or steps represented in a flowchart or otherwise described herein, for example, can be considered a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" is any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (not exhaustive) of computer-readable media include: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program can be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing it in other suitable ways as necessary, and then storing it in a computer memory.

[0156] It should be understood that various components of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented using hardware, as in another embodiment, any of the following technologies known in the art or a combination thereof can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0157] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0158] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing module, or each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

[0159] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and are not to be construed as limiting the present invention. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A power system inspection registration method based on BIM model and 3D point cloud model, characterized in that: The following steps are involved: Obtain the BIM model, BIM model file, 3D point cloud model, and 3D point cloud file of the target power system; Extracting a geometric representation and a geometric coordinate system from the BIM model file, and generating a first registration descriptor of the BIM model according to the geometric representation and the geometric coordinate system; Extracting the intersection direction features and the normal vector features of the three-dimensional point cloud file, and generating a second registration descriptor of the three-dimensional point cloud model according to the intersection direction features and the normal vector features; Calculate a coarse transformation matrix between the BIM model and the three-dimensional point cloud model using the first registration descriptor and the second registration descriptor; Converting the first spatial coordinate system of the BIM model to the second spatial coordinate system of the three-dimensional point cloud model according to the coarse transformation matrix to obtain a coarsely registered BIM model file; Triangulate the coarsely registered BIM model file to generate a plurality of triangular mesh surfaces; Downsampling the triangular mesh facets to obtain three-dimensional point cloud models of different scales; Organizing the three-dimensional point cloud model and the three-dimensional point cloud models of different scales in a KD-tree hierarchy to obtain KD-tree node units, and iteratively calculating a refined transformation matrix based on the KD-tree node units; Converting the coarsely registered BIM model file into a finely registered BIM model file according to the fine transformation matrix; An inspection route is generated according to the precisely registered BIM model file, and the inspection route is sent to the target UAV.

2. The power system inspection registration method based on BIM model and 3D point cloud model according to claim 1 is characterized in that: The extracting the geometric representation and the geometric coordinate system from the BIM model file, and generating a first registration descriptor of the BIM model according to the geometric representation and the geometric coordinate system, includes: Extracting the geometric coordinate system and shape definition of each element in the BIM model file; Extracting a geometric representation under the shape definition and resolving the type of the geometric representation; Calculating normal vector information, boundary information, and intersection line information of each face according to the type of the geometric representation; Based on the geometric coordinate system, the normal vector information, boundary information and intersection line information of each face are combined to obtain a first quadruple representation or a first triplet representation of a series of non-parallel planes as the first registration descriptor.

3. The power system inspection registration method based on BIM model and 3D point cloud model according to claim 1, characterized in that: The extracting the intersection direction feature and the normal vector feature of the three-dimensional point cloud file, and generating a second registration descriptor of the three-dimensional point cloud model according to the intersection direction feature and the normal vector feature, includes: Randomly selecting three points in the three-dimensional point cloud file to construct a temporary plane, and calculating the distance between each point and the temporary plane; Distinguishing the three points into inner points and outer points according to the distance, and extracting the inner points and the temporary plane from the three-dimensional point cloud file as the current plane boundary information; Iteratively performing the process of extracting plane boundary information from the three-dimensional point cloud file until all points in the three-dimensional point cloud file are randomly selected to obtain plane boundary information of a plurality of surfaces; Calculating the intersection direction feature and the normal vector feature according to the plane boundary information of the multiple faces; The intersection direction feature and the normal vector feature are combined to obtain a second quadruple representation or a second triplet representation of a series of non-parallel planes as the second registration descriptor.

4. The power system inspection registration method based on BIM model and 3D point cloud model according to claim 1, characterized in that: The calculating of a coarse transformation matrix between the BIM model and the three-dimensional point cloud model by using the first registration descriptor and the second registration descriptor includes: Constructing a KD tree of the first registration descriptor and the second registration descriptor; Calculating the Euclidean distance between each descriptor in the first registration descriptor and each descriptor in the second registration descriptor according to the KD tree; The Euclidean distance is compared with a preset threshold. If the Euclidean distance is less than the preset threshold, the straight line segments of the two matching descriptors extracted from the BIM model and the three-dimensional point cloud model are used to calculate the coarse transformation matrix corresponding to each of the two matching descriptors.

5. The power system inspection registration method based on BIM model and 3D point cloud model according to claim 4 is characterized in that: The step of converting the first spatial coordinate system of the BIM model into the second spatial coordinate system of the three-dimensional point cloud model according to the coarse transformation matrix to obtain a coarsely registered BIM model file includes: Calculating the probability that a point in the three-dimensional point cloud model falls into the first spatial coordinate system according to the coarse transformation matrix corresponding to each of the two matched descriptors; The first spatial coordinate system is transformed into the second spatial coordinate system according to the coarse transformation matrix with the highest probability, so as to obtain the BIM model file after the coarse registration.

6. The power system inspection registration method based on BIM model and 3D point cloud model according to claim 1, characterized in that: The three-dimensional point cloud model and the three-dimensional point cloud models of different scales are organized in a KD-tree hierarchy to obtain KD-tree node units, and a refined transformation matrix is iteratively calculated based on the KD-tree node units, including: Organizing the three-dimensional point cloud model and the three-dimensional point cloud models of different scales in a KD-tree hierarchy to obtain the KD-tree node unit; Solving the objective function of the KD-tree node unit based on the maximum likelihood method and Gaussian function; The KD-tree node unit is iteratively transformed using the Newton method until the objective function converges to obtain the refined transformation matrix.

7. A power system inspection registration device based on BIM model and 3D point cloud model, characterized in that: include: An acquisition module is used to acquire the BIM model, BIM model file, 3D point cloud model and 3D point cloud file of the target power system; a first extraction module, configured to extract a geometric representation and a geometric coordinate system from the BIM model file, and generate a first registration descriptor of the BIM model according to the geometric representation and the geometric coordinate system; a second extraction module, configured to extract intersection direction features and normal vector features of the three-dimensional point cloud file, and generate a second registration descriptor of the three-dimensional point cloud model according to the intersection direction features and the normal vector features; a matrix calculation module, configured to calculate a coarse transformation matrix between the BIM model and the three-dimensional point cloud model using the first registration descriptor and the second registration descriptor; a coarse registration module, configured to transform the first spatial coordinate system of the BIM model into the second spatial coordinate system of the three-dimensional point cloud model according to the coarse transformation matrix, so as to obtain a coarsely registered BIM model file; A triangulation module is used to triangulate the BIM model file after the rough registration to generate a plurality of triangular mesh surfaces; A downsampling module is used to downsample the triangular mesh facets to obtain three-dimensional point cloud models of different scales; an iterative calculation module, configured to organize the three-dimensional point cloud model and the three-dimensional point cloud models of different scales in a KD-tree hierarchy to obtain KD-tree node units, and iteratively calculate a refined transformation matrix based on the KD-tree node units; A fine registration module, configured to convert the coarsely registered BIM model file into a finely registered BIM model file according to the fine transformation matrix; A generation module is used to generate an inspection route according to the BIM model file after the precise registration, and send the inspection route to the target UAV.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the power system inspection and registration method based on the BIM model and the three-dimensional point cloud model as described in any one of claims 1 to 6.

9. A computer program product, characterized in that When the computer program / instruction is executed by a processor, the power system inspection and registration method based on the BIM model and the three-dimensional point cloud model as described in any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the power system inspection registration method based on a BIM model and a three-dimensional point cloud model as described in any one of claims 1 to 6.

Images