Power wire data processing method, device, equipment, medium and program product

Abstract

The invention provides a power wire data processing method, device and equipment, a medium and a program product. Relates to the technical field of data processing. The method comprises the following steps: acquiring incomplete point cloud data and two-dimensional conductor data of a power conductor group; wherein the power wire group comprises at least one power wire; according to the incomplete point cloud data, constructing three-dimensional space data of a space region where the power conductor group is located; and according to the three-dimensional space data, the two-dimensional wire data and the incomplete point cloud data, performing three-dimensional reconstruction processing on the power wire group to obtain three-dimensional fitting data of the power wire group. According to the method provided by the invention, the problem that the accuracy of three-dimensional reconstruction of the power wire is relatively low under the condition that the point cloud data on the wire with the missing partial length is concentrated in the prior art is solved.

Description

[0001] This application claims priority to Chinese Patent Application No. 202410516502.3, filed on April 25, 2024, entitled “Power Conductor Data Processing Method, Apparatus, Equipment, Medium and Program Product”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of data processing technology, and in particular to a method, apparatus, equipment, medium, and program product for processing data of power conductors. Background Technology

[0003] With the continuous increase in electricity consumption, higher challenges are posed to the stability of power grid operation, especially the safety and stability of transmission lines. LiDAR technology is a commonly used method for power grid stability detection. In power conductor scanning, LiDAR technology can achieve high-precision measurement and three-dimensional modeling of conductors, thereby providing more accurate and comprehensive conductor information.

[0004] In existing technologies, high-precision three-dimensional point cloud data of power line corridors are collected quickly and efficiently using airborne LiDAR (Light Laser Detection and Ranging) systems. Through fine processing of the three-dimensional point cloud data, including filtering and segmentation, point cloud sets representing power lines are extracted from massive amounts of data. Furthermore, the point cloud sets are fitted using a preset straight-parabolic hybrid model to achieve three-dimensional reconstruction of the power lines.

[0005] However, the above method requires data fitting based on most of the data on the span between power poles to achieve three-dimensional reconstruction of power conductors. When dealing with point cloud data on conductors with concentrated missing lengths, the accuracy of three-dimensional reconstruction of power conductors is low. Summary of the Invention

[0006] This application provides a method, apparatus, device, medium, and program product for processing power conductor data, which addresses the problem of low accuracy in the three-dimensional reconstruction of power conductors when dealing with point cloud data on conductors with concentrated missing lengths.

[0007] In a first aspect, this application provides a method for processing power conductor data, including:

[0008] Acquire residual defect cloud data and two-dimensional conductor data of a power conductor group; wherein the power conductor group includes at least one power conductor;

[0009] Based on the residual cloud data, construct three-dimensional spatial data of the spatial region where the power conductor group is located;

[0010] Based on the three-dimensional spatial data, the two-dimensional conductor data, and the residual defect cloud data, the power conductor group is subjected to three-dimensional reconstruction processing to obtain the three-dimensional fitting data of the power conductor group.

[0011] In one optional implementation, the power conductor group is subjected to three-dimensional reconstruction processing based on the three-dimensional spatial data, the two-dimensional conductor data, and the residual defect cloud data to obtain three-dimensional fitting data of the power conductor group, including:

[0012] For any power conductor, the equation of the straight line of the power conductor in the first plane is determined based on the conductor residual cloud data corresponding to the power conductor.

[0013] Based on the three-dimensional spatial data and the two-dimensional conductor data, determine the quadratic curve equation of the power conductor in the second plane;

[0014] At preset intervals, conductor fitting data for the power conductor is determined based on the straight line equation and the quadratic curve equation;

[0015] Based on the conductor fitting data of the multiple power conductors, the three-dimensional fitting data of the power conductor group is determined.

[0016] In one optional implementation, based on the residual fault cloud data, three-dimensional spatial data of the spatial region where the power conductor group is located is constructed, including:

[0017] Based on the span of the power conductor group, determine the first spatial data in the X-axis direction of the three-dimensional coordinate system in which the spatial region is located;

[0018] Based on the straight line equations of the multiple power conductors in the first plane, determine the second spatial data in the Y-axis direction of the three-dimensional coordinate system in which the spatial region is located;

[0019] Based on the height of the tower to which the power conductor group belongs, determine the third spatial data in the Z-axis direction of the three-dimensional coordinate system in which the spatial region is located; based on the first spatial data, the second spatial data, and the third spatial data, determine the three-dimensional spatial data of the spatial region.

[0020] In one optional implementation, determining the straight line equation of the power conductor in the first plane based on the conductor residual defect cloud data corresponding to the power conductor includes:

[0021] Based on the residual point cloud data of the conductor, a first spatial transformation matrix is ​​determined; the first spatial transformation matrix is ​​used to characterize the spatial transformation relationship between the three-dimensional point cloud data and the two-dimensional projection data on the preset plane.

[0022] Based on the first spatial transformation matrix, the projection coordinate transformation is performed on the wire residual cloud data in the first plane to obtain the first projection data;

[0023] Based on the first projection data, the straight line equation of the power conductor in the first plane is obtained by fitting.

[0024] In one optional implementation, determining the first spatial transformation matrix based on the conductor residual point cloud data includes:

[0025] Based on the residual cloud data of the conductor, the first straight line equation of the first plane is obtained by fitting, and the second straight line equation of the second plane is obtained by fitting.

[0026] Based on the preset function, the first straight line equation, and the second straight line equation, the rotation angle between the scanning device and the tower to which the power conductor group belongs is determined;

[0027] Based on the rotation angle, construct the first spatial transformation matrix.

[0028] In one optional implementation, determining the quadratic curve equation of the power conductor in the second plane based on the three-dimensional spatial data and the two-dimensional conductor data includes:

[0029] Based on the three-dimensional spatial data and the two-dimensional conductor data, determine the conductor fitting data of the power conductor in the spatial region;

[0030] Based on the conductor fitting data, the quadratic curve equation of the power conductor in the second plane is determined.

[0031] In one optional implementation, determining conductor fitting data for the power conductor in the spatial region based on the three-dimensional spatial data and the two-dimensional conductor data includes:

[0032] Obtain a predetermined second spatial transformation matrix; the second spatial transformation matrix is ​​used to characterize the spatial transformation relationship between three-dimensional point cloud data and two-dimensional image data.

[0033] Based on the second spatial transformation matrix, the three-dimensional spatial data is transformed by data projection coordinates in the two-dimensional image plane to obtain the second projection data;

[0034] Determine the traverse projection data in the second projection data that corresponds to the two-dimensional traverse data;

[0035] Based on the three-dimensional spatial data, determine the three-dimensional coordinate data corresponding to the conductor projection data, and use the three-dimensional coordinate data as the initial fitting data for the power conductor group;

[0036] The initial fitting data of the power conductor group is segmented to obtain the conductor fitting data for each power conductor.

[0037] In one optional implementation, there is a mapping relationship between each three-dimensional coordinate point in the three-dimensional spatial data and each two-dimensional coordinate point in the second projection data.

[0038] In one alternative implementation, the method further includes:

[0039] Based on the three-dimensional fitting data and the residual point cloud data, the supplementary point cloud data of the power conductor group is determined;

[0040] The supplementary point cloud data and the residual point cloud data are labeled and stored respectively.

[0041] In one alternative implementation, acquiring residual defect cloud data of a power conductor group includes:

[0042] Based on a preset spatial bounding box, the initial point cloud data obtained by scanning the power conductor group is processed to obtain point cloud data located within the spatial bounding box.

[0043] The point cloud data within the spatial bounding box is segmented to obtain at least one set of point cloud cluster data.

[0044] Based on the data characteristics of each point cloud cluster, the residual point cloud data of the power conductor group is obtained.

[0045] In one optional implementation, acquiring two-dimensional conductor data of a power conductor group includes:

[0046] The initial two-dimensional image of the power conductor group is preprocessed to obtain a two-dimensional conductor image containing the power conductor group.

[0047] The two-dimensional conductor image is subjected to image skeletonization processing to obtain the two-dimensional conductor data of the power conductor group.

[0048] Secondly, this application provides a power conductor data processing apparatus, comprising:

[0049] The data acquisition module is used to acquire residual defect cloud data and two-dimensional conductor data of the power conductor group; wherein, the power conductor group includes at least one power conductor;

[0050] The data construction module is used to construct three-dimensional spatial data of the spatial region where the power conductor group is located based on the residual cloud data.

[0051] The data fitting module is used to perform three-dimensional fitting processing on the power conductor group based on the three-dimensional spatial data, the two-dimensional conductor data, and the residual defect cloud data, to obtain the three-dimensional fitting data of the power conductor group.

[0052] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0053] The memory stores computer-executed instructions;

[0054] The processor executes computer execution instructions stored in the memory to implement the method as described in the first aspect.

[0055] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method described in the first aspect.

[0056] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect.

[0057] The power conductor data processing method provided in this application acquires residual point cloud data of a power conductor group, using it as the basic data for power conductor group reconstruction, providing a reliable foundation for subsequent reconstruction work and improving the accuracy of the reconstruction results. Furthermore, it acquires two-dimensional conductor data of the power conductor group, using it as the basis for reconstruction, providing prior information for subsequent reconstruction and improving the accuracy and completeness of the reconstruction results. Based on this, it constructs three-dimensional spatial data of the spatial region where the power conductor group is located based on the residual point cloud data, and uses this three-dimensional spatial data as the basis for power conductor reconstruction, providing richer prior information including conductor morphology for subsequent reconstruction, further improving the accuracy and completeness of the reconstruction results. Thus, based on accurate reconstruction results, it achieves precise restoration and completion of conductor morphology, making the generated power conductor not only complete and accurate, but also capable of accurate three-dimensional reconstruction even for point cloud data on conductors with concentrated missing lengths. Moreover, the reconstructed power conductor can be directly used for distance measurement and other related business processing, greatly improving work efficiency. Attached Figure Description

[0058] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0059] Figure 1 An application scenario diagram of the power conductor data processing method provided in this application;

[0060] Figure 2 A flowchart illustrating a power conductor data processing method provided in an embodiment of this application;

[0061] Figure 3 A schematic diagram of a projection onto the XOY plane is provided as an embodiment of this application;

[0062] Figure 4 A schematic diagram of a projection onto the XOZ plane is provided as an embodiment of this application;

[0063] Figure 5 This is a schematic diagram of the structure of a power conductor data processing device provided in an embodiment of this application;

[0064] Figure 6 This is a block diagram illustrating an electronic device according to an embodiment of this application.

[0065] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0066] To facilitate a clear description of the technical solutions in the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with essentially the same function and purpose. For example, "first device" and "second device" are merely used to distinguish different devices and do not limit their order of execution. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that "first" and "second" do not necessarily imply that they are different.

[0067] It should be noted that, in this application, the terms "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0068] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0069] The application of lidar in power line scanning mainly benefits from its high-precision measurement and 3D modeling capabilities. LiDAR systems can accurately measure information such as the distance, velocity, and orientation of target objects by emitting laser beams and receiving the echoes reflected from obstacles.

[0070] Therefore, in the scanning of power lines, lidar technology can achieve rapid, high-precision measurement and 3D modeling of the lines. Specifically, by scanning the lines, information such as their position, height, direction, and bending radius can be obtained, enabling comprehensive monitoring and evaluation of the lines. Furthermore, lidar technology can be combined with other sensors and data processing technologies to achieve automated inspection and intelligent monitoring of power lines, further improving the operational efficiency and safety of power equipment.

[0071] One possible implementation is to use the three-dimensional point cloud data of power lines acquired by the LiDAR system for efficient modeling and fitting, so as to achieve accurate depiction and condition monitoring of power lines.

[0072] Specifically, the data quality is improved by preprocessing the 3D point cloud data, such as denoising and filtering. Furthermore, feature extraction technology is used to identify and segment the point cloud data related to power lines. Then, curve fitting or surface fitting algorithms (such as least squares method, spline interpolation, etc.) are applied to perform high-precision geometric modeling on the segmented point cloud data related to power lines. Combined with the physical characteristics of power lines, the model parameters are optimized to achieve 3D reconstruction of power conductors and further improve the accuracy of the model.

[0073] Another possible implementation involves using power line point cloud data acquired by an airborne LiDAR system to achieve accurate 3D reconstruction of a single power conductor between individual towers (i.e., a single span). This involves using an airborne LiDAR system to quickly and efficiently collect high-precision 3D point cloud data of the power line corridor. Furthermore, through fine processing of the point cloud data, including filtering and segmentation, a point cloud set representing the power conductor is extracted from the massive data. Finally, a pre-defined straight-parabolic hybrid model is used to fit the point cloud set to achieve 3D reconstruction of the power conductor.

[0074] Specifically, by preprocessing the 3D point cloud data, ground and other non-power line target points are removed, while power line feature points are retained. Furthermore, a clustering algorithm suitable for the characteristics of power lines is used to identify and separate point cloud data belonging to a single power conductor. Then, based on this point cloud data, a proposed straight-parabolic hybrid model is used for fitting to achieve 3D reconstruction of the power conductor. In addition, the model parameters can be iteratively adjusted to make the reconstruction model fit the shape and size of the actual power conductor to the greatest extent. This reconstruction model is a model that combines straight line segments and parabolic segments to describe the 3D shape of the power conductor, and can better adapt to the shape changes of the conductor under different conditions.

[0075] It should be noted that the above method can realize automated and high-precision three-dimensional reconstruction of power conductors, which helps to improve the safety and efficiency of power line operation and maintenance. In practical applications, comparative tests have verified the applicability and accuracy of the method in complex terrain and long-distance transmission line scenarios.

[0076] However, both of the above methods rely on a large portion of the span data between power poles when addressing the issue of power conductor point cloud data coverage. Their common feature is the use of algorithms to effectively fit and supplement a small number of missing point clouds. However, when faced with concentrated missing points cloud data on conductor lengths, such as when the power conductor point cloud data only covers less than 15% of the span between power poles, these two methods cannot be effectively implemented. They struggle to accurately and completely complete this severely deficient data, resulting in low accuracy in the 3D reconstruction of power conductors.

[0077] Understandably, traditional point cloud completion algorithms for power lines primarily focus on scenarios involving point cloud data from both ends of the power line. In these cases, the length of the missing portion in the required data is relatively low compared to the total length. However, the situation becomes more complex when dealing with LiDAR scan data mounted on a pan-tilt unit. This presents the challenge of dealing with scan data containing only point cloud information representing no more than 15% of the total power line length. This makes traditional completion algorithms unsuitable, significantly reducing accuracy in achieving automatic power line completion. Therefore, even if these scan data are used to accurately acquire key measurement data such as the sag point of the power line, the low accuracy of the fitted conductor makes it difficult to implement important business functions such as distance measurement based on this limited scan data.

[0078] To address the aforementioned issues, this application provides a method for processing power conductor data. When creating a 3D model of a power conductor, it uses 3D spatial data obtained by constructing data from the spatial region where the power conductor is located, along with 2D conductor data, as the basis for reconstruction. Furthermore, it uses residual defect cloud data obtained from scanning the power conductor as the foundation for reconstruction, generating a complete point cloud dataset to achieve 3D reconstruction of the power conductor. Specifically, based on the scanned residual defect cloud data, 3D spatial data of the spatial region where the power conductor is located is constructed. The constructed 3D spatial data and the captured 2D image data are used as the basis data for reconstruction, i.e., prior information, enabling rapid and accurate reconstruction processing and improving the accuracy of the reconstruction results. Furthermore, using the scanned residual defect cloud data as the foundation data for reconstruction ensures a high similarity between the reconstruction results and the actual scanning results, further enhancing the accuracy of the reconstruction results.

[0079] Figure 1 This is an application scenario diagram of the power conductor data processing method provided in this application. For ease of understanding, the following is combined with... Figure 1 The application scenarios applicable to the embodiments of this application are described below. See also... Figure 1 This application scenario can be applied to the reconstruction of power transmission lines in power transmission tunnels. This application scenario includes: LiDAR 101, imaging system 102 and data processing system 103.

[0080] Specifically, the lidar 101 collects point cloud data of a portion of the span between the two power poles, such as point cloud information representing 15% of the total length of the power conductor. Figure 1 The system scans the power lines in region A1 to obtain the defect cloud data of the power lines. Furthermore, the lidar 101 transmits the collected data to the data processing system 103 for three-dimensional reconstruction of the power lines.

[0081] At the same time, the imaging system 102 photographs the power conductors with a complete span between the two power poles, obtaining two-dimensional conductor data, such as... Figure 1 The complete power conductor in area A is photographed to obtain two-dimensional image data of the power conductor in the complete span between power poles. Furthermore, the photographing system 102 transmits the acquired data to the data system 103 for three-dimensional reconstruction processing of the power conductor.

[0082] Furthermore, the data processing system 103 performs a series of complex algorithmic operations on the residual cloud data and two-dimensional image data, such as data segmentation, data construction, and three-dimensional reconstruction. By processing this data, complete fitting data of the power conductors within the power transmission tunnel is obtained, such as... Figure 1 As shown in region B.

[0083] This allows for the generation of complete and accurate three-dimensional fitting data for power conductors, supporting subsequent operational processes such as ranging, monitoring, and evaluation. This completion fitting algorithm, based on three-dimensional spatial data of the airspace where the power conductors are located, not only improves the completeness of the power conductor data but also enhances the reliability and effectiveness of the data in operational applications.

[0084] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0085] Figure 2 This is a flowchart illustrating a power conductor data processing method provided in an embodiment of this application. The method can be executed by a power conductor data processing device, which can be a server or an electronic device. The following description uses an electronic device as an example. The method in this embodiment can be implemented through software, hardware, or a combination of both. Figure 2 As shown, the method includes the following steps.

[0086] S210. Obtain residual defect cloud data and two-dimensional conductor data of the power conductor group.

[0087] The power transmission tunnel contains multiple power conductors, or power conductor assemblies, used to transmit electrical energy generated by the power plant. To facilitate monitoring and maintenance of these power conductor assemblies by technicians, point cloud data of the conductor assemblies can be collected and analyzed. However, if the collected point cloud data is incomplete, it will affect the monitoring and maintenance results of the power conductor assemblies.

[0088] Therefore, to support subsequent inspection and maintenance processes, the power conductor group can be reconstructed in three dimensions when the collected point cloud data is incomplete, so as to obtain complete and accurate three-dimensional fitting data of the power conductor.

[0089] It should be understood that incomplete point cloud data refers to point cloud data of power lines that contains missing or incomplete portions. This can be caused by various reasons, including but not limited to limitations of data acquisition equipment, environmental factors, obstructions, and differences in reflectivity. For example, during data acquisition, some areas may be obstructed by other objects, preventing data from being collected in these areas; for instance, buildings, trees, or other obstacles may obscure parts of the power lines; furthermore, the resolution and accuracy of lidar, cameras, or other sensors are limited, and they may not be able to capture all details, especially at long distances or in complex environments; and environmental factors such as weather and lighting conditions can also affect the quality of data acquisition. For example, strong light, shadows, rain, and snow may lead to incomplete data acquisition.

[0090] Two-dimensional conductor data can be understood as two-dimensional data obtained by processing image data obtained from photographing groups of power conductors.

[0091] In this application, since the two-dimensional conductor data corresponds to the complete span of the power conductor between the two power towers, the processed two-dimensional conductor data can be used as one of the prior information for the three-dimensional reconstruction of the power conductor group to ensure that the reconstruction results are more accurate.

[0092] S220. Based on the residual cloud data, construct three-dimensional spatial data of the spatial region where the power conductor group is located.

[0093] In this application, the spatial region where the power conductor group is located can be understood as a spatial bounding box constructed with the power conductor group as the center of the region; correspondingly, the three-dimensional spatial data of the spatial region can be understood as multiple three-dimensional coordinate data constructed by detecting preset intervals within the aforementioned spatial bounding box.

[0094] In one optional implementation, since there is a large spatial interval between the multiple power conductors in the power conductor group, in order to reduce the amount of data constructed, in other words, to reduce the amount of data input during subsequent reconstruction, sub-3D spatial data of the subspace bounding box of each power conductor can be constructed separately, and the 3D spatial data corresponding to the power conductor group can be obtained based on the 3D spatial data of each bounding box.

[0095] To ensure the accuracy of the constructed 3D spatial data, it can be based on the residual defect cloud data obtained by scanning the power conductor group. For a detailed explanation of how to construct 3D spatial data using residual defect cloud data, please refer to the following implementation method.

[0096] Based on the obtained three-dimensional spatial data, since the three-dimensional spatial data also contains the data corresponding to the complete span of the power conductors between the two power towers, for example, based on the two-dimensional conductor data, the three-dimensional spatial data also contains the morphological data of the power conductor group; therefore, the obtained three-dimensional spatial data is also used as another prior information for the three-dimensional reconstruction of the power conductor group, to further ensure that the reconstruction results are more accurate.

[0097] It should be noted that in other scenarios, when performing 3D reconstruction of the object to be reconstructed based on images, a depth camera or remote sensing camera can be used to directly capture images of the object to be reconstructed, directly obtaining 3D image data containing the morphological data of the object to be reconstructed, and then performing reconstruction processing based on the 3D image data.

[0098] However, in this scenario, namely when performing 3D reconstruction of power conductor groups, the morphological data obtained by using depth cameras and remote sensing cameras to photograph power conductors is relatively inaccurate due to the slender structure of the power conductors and the generally large distance between them and the camera. This further affects the accuracy of the reconstruction results of the power conductor group. Therefore, in order to obtain more accurate 3D spatial data, this application uses point cloud data as prior information for conductor morphological data when constructing 3D spatial data, thereby automatically constructing 3D spatial data to ensure more accurate reconstruction results.

[0099] S230. Based on the three-dimensional spatial data, two-dimensional conductor data, and residual defect cloud data, perform three-dimensional reconstruction processing on the power conductor group to obtain the three-dimensional fitting data of the power conductor group.

[0100] In this application, the three-dimensional reconstruction can be either fitting and generating point cloud data corresponding to the power conductor or fitting and generating at least one power conductor equation. The embodiments of this application do not specifically limit the results of the three-dimensional reconstruction.

[0101] For example, when performing 3D reconstruction based on 3D spatial data, 2D conductor data, and residual defect cloud data, the reconstruction process can be performed on each power conductor first to obtain the power conductor equation corresponding to a single power conductor, and then the corresponding conductor fitting data can be obtained based on the power conductor equation. After the reconstruction of each power conductor is completed, the conductor fitting data of each power conductor are combined to determine a set of 3D fitting data that spans both sides of the power tower and includes the fitting data of multiple power conductors.

[0102] Optionally, three-dimensional spatial data, two-dimensional conductor data, and residual point cloud data can be input into the three-dimensional reconstruction model to obtain point cloud data generated by fitting the power conductor group, or conductor equations generated by fitting the power conductor group. The embodiments of this application do not specifically limit the three-dimensional reconstruction model, which can be a pre-trained deep learning model for three-dimensional reconstruction based on the above point cloud data and image data; or it can be a mathematical model constructed according to the target and corresponding constraints, which is not limited.

[0103] It is understandable that this application can complete the defect cloud data of power conductors by processing three-dimensional spatial data, two-dimensional conductor data and defect cloud data, thereby obtaining complete three-dimensional fitting data of the power conductor group.

[0104] Specifically, this application uses the aforementioned power conductor data processing method to obtain residual point cloud data of the power conductor group, which is used as the basic data for the reconstruction of the power conductor group, providing a reliable foundation for subsequent reconstruction work and improving the accuracy of the reconstruction results. Furthermore, it acquires two-dimensional conductor data of the power conductor group, using it as the basis for reconstruction, providing prior information for subsequent reconstruction and improving the accuracy and completeness of the reconstruction results. Based on this, it constructs three-dimensional spatial data of the spatial region where the power conductor group is located using the residual point cloud data, and also uses this three-dimensional spatial data as the basis for power conductor reconstruction, providing richer prior information including conductor morphology for subsequent reconstruction, further improving the accuracy and completeness of the reconstruction results. Thus, based on accurate reconstruction results, it achieves precise restoration and completion of conductor morphology, making the generated power conductor not only complete and accurate, but also capable of accurate three-dimensional reconstruction even for point cloud data on conductors with concentrated missing lengths. Moreover, the reconstructed power conductor can be directly used for distance measurement and other related business processing, greatly improving work efficiency.

[0105] Next, the process of generating residual cloud data for power conductor groups will be explained in detail.

[0106] Optionally, the process of obtaining residual point cloud data in this application may include: processing the initial point cloud data obtained by scanning the power conductor group based on a preset spatial bounding box to obtain point cloud data located within the spatial bounding box; segmenting the point cloud data within the spatial bounding box to obtain at least one set of point cloud cluster data; and obtaining the residual point cloud data of the power conductor group according to the data characteristics of each point cloud cluster data.

[0107] In this application, to reduce potential errors in power line data during the Simultaneous Localization and Mapping (SLAM) algorithm's calculation process, a special strategy is adopted in the data acquisition phase. Specifically, at the start of data acquisition, the gimbal housing the LiDAR is kept stationary, continuously collecting power line data for a period of time. This ensures more stable and accurate data in the initial stage. Furthermore, to distinguish this stationary data from subsequent data acquired during gimbal rotation, pre-defined tags are used when storing the power line data for this period; for example, stationary data is tagged with a "stationary data acquisition" tag.

[0108] Optionally, initial point cloud data of the power conductor group within the target range can be obtained; the target range can be a partial span between any two power poles, such as a span not exceeding 15% of the total length of the power conductor, or the target range can be the range that the pan-tilt device can scan. In this embodiment, the specific size of the target range is not limited.

[0109] Optionally, if the acquired initial point cloud data does not cover the complete power conductor between any two power poles, the initial point cloud data is determined to be incomplete initial point cloud data, and it is then completed to enable subsequent business processing such as distance measurement of the power conductor group.

[0110] In this application, in order to filter out the point cloud data of power conductors in a specific direction from the field of view and avoid mixing in interference data from other directions, and considering that the installation position and preset scanning angle position of a single pan-tilt device are preset, the range of point cloud data obtained each time is relatively fixed. Therefore, by pre-setting the size of a bounding box that only contains the point cloud data of each power conductor in the power conductor group, the point cloud data of the power conductor group is obtained by filtering the initial point cloud data obtained by scanning using the bounding box.

[0111] Specifically, based on the static data acquisition labels set in the initial point cloud data and the spatial bounding box size (box1) of the power conductors, key information is extracted from the complete LAS format initial point cloud data acquired by the lidar, such as the three-dimensional spatial coordinates (X, Y, Z) of each point, the acquisition timestamp, and radar reflectivity information. Furthermore, the Cloud Compare tool is used to perform visualization analysis of the three-dimensional spatial coordinates (X, Y, Z) to obtain the point cloud data of the power conductors within the spatial bounding box. The spatial bounding box not only limits the spatial range of the power conductor point cloud data but also provides the maximum and minimum values ​​of the three-dimensional spatial coordinates, providing an important basis for subsequent data processing and analysis.

[0112] In this application, in order to reduce the impact of noise values ​​and outlier point cloud coordinate data on subsequent processing results during the acquisition process, a statistical filtering algorithm can be used to remove outliers in the point cloud data. This statistical filtering algorithm is based on the principle of statistical analysis. By performing detailed statistical analysis on each point cloud data point, it calculates the statistical characteristics in its neighborhood, such as the mean and standard deviation. Based on these statistical characteristics, it accurately determines which points are noise or outliers and effectively filters them out.

[0113] In this way, by filtering the point cloud data within the bounding box, the resulting processed point cloud data is a relatively clean set of point cloud data, containing only point cloud data of power lines. Through filtering, not only is the accuracy and reliability of the data improved, but also the efficiency and precision of data processing are enhanced.

[0114] In some alternative implementations, in addition to the power conductors, there are also power spacers erected on each power conductor in the power conductor group within the complete span of the two power poles. To ensure the accuracy of the three-dimensional reconstruction results of the power conductor group, the filtered point cloud data includes point cloud data of the power spacers in addition to the point cloud data of the power conductor group. However, when performing three-dimensional reconstruction of the power conductors in this application, the point cloud data of the spacers is not necessary data. To reduce the amount of data calculation and improve the accuracy of data processing, the point cloud data of the power spacers included in the point cloud data can be removed.

[0115] Specifically, segmentation algorithms can be used to segment point cloud data, and the segmented gap bar point cloud data can be removed. For example, the Euclidean Cluster Extraction clustering algorithm can be used to perform in-depth analysis of point cloud data to identify and separate multiple point cloud clusters.

[0116] The Euclidean Cluster Extraction algorithm is a clustering method for point cloud data processing, especially when processing data from LiDAR or depth cameras. It can identify and extract clusters or groups of points in the point cloud based on Euclidean distance. Its basic idea is to group points that are close to each other in space into one class, assuming that they belong to the same object or surface.

[0117] Specifically, the workflow of the Euclidean Cluster Extraction algorithm includes the following steps:

[0118] Step 1) Before starting clustering, define two key parameters: the search radius (or neighborhood radius) and the minimum number of points. The search radius determines which points are considered to be close to each other, while the minimum number of points is used to ensure that a cluster contains at least that many points.

[0119] Step 2) Traverse each point in the point cloud data, and use each point as the center to find other points within the search radius.

[0120] Step 3) If a point has enough points around it within the search radius (at least the minimum number of points), these points are considered a cluster, the point is marked as part of the cluster, and is removed from the list of unprocessed points.

[0121] Step 4) For a point that has already been marked as part of a cluster, it is necessary to check whether other points in its neighborhood have also been marked. If not, these points are added to the cluster and removed from the list of unprocessed points. The above process is repeated iteratively until no more points can be added to the cluster.

[0122] Step 5) Continue processing the remaining unmarked points, repeating steps 2) to 4) until all points have been processed.

[0123] Step 6) Output a set of clusters, each containing a set of spatially close points.

[0124] Based on this, the clustering characteristics of each point cloud cluster are analyzed, such as the location and orientation of the point cloud cluster, to distinguish which point cloud clusters correspond to the power spacer bars and remove them, thus obtaining the residual point cloud data of the power conductor.

[0125] Thus, by employing the simple yet effective point cloud data clustering method EuclideanClusterExtraction and setting appropriate parameters, it is possible to separate specific structures from a complex environment. In this application, the location and shape of power lines can be effectively segmented to obtain point cloud data containing only power lines, thereby improving the efficiency and accuracy of subsequent data processing.

[0126] The above steps effectively eliminate irrelevant data, ensuring the accuracy and completeness of the acquired point cloud data of power lines, and laying a solid foundation for subsequent data analysis and processing.

[0127] Next, we will describe in detail the process of obtaining the two-dimensional conductor data corresponding to the power conductor group.

[0128] Optionally, the data acquisition process provided in this application may include: performing image preprocessing on the initial two-dimensional image obtained by photographing the power conductor group to obtain a two-dimensional conductor image containing the power conductor group; and performing image skeletonization processing on the two-dimensional conductor image to obtain two-dimensional conductor data of the power conductor group.

[0129] Since the field of view is relatively fixed when the camera is shooting, image data of a specific area can be directly captured and cropped for processing, effectively reducing the amount and difficulty of data processing. It should be noted that the specific area is an image containing the complete span of the power conductor between the two power poles. Next, a series of image processing operations can be used to extract the skeleton of the power conductor group, obtaining the two-dimensional conductor data of the power conductor group.

[0130] First, the initial 2D image is converted to grayscale. Specifically, the captured color image can be converted into a grayscale image, simplifying the image data, reducing computational complexity, and preserving the image's basic structure and features to ensure data accuracy in subsequent processing. For example, image grayscale conversion is typically achieved by weighted averaging of the RGB color channel values ​​to obtain a grayscale image represented by grayscale values.

[0131] In some alternative implementations, the grayscale image obtained above can also be normalized. Specifically, the contrast of the processed grayscale image can be increased by adjusting the grayscale value range; or, the grayscale values ​​of the grayscale image can be mapped to a preset range, such as 0 to 255, where 0 represents black and 255 represents white.

[0132] The grayscale processing described above improves the visual effect of the image and facilitates subsequent image processing, thereby increasing image processing efficiency.

[0133] Secondly, Gaussian blur can be used for noise reduction on grayscale images. It should be understood that Gaussian blur is a smoothing filter used to reduce noise and detail in an image. It is achieved by convolving a Gaussian kernel on the image, assigning different weights to pixels based on their distance from the center point; pixels near the center point have higher weights, while pixels further away have lower weights. In this application, using Gaussian blur to process the image can effectively remove high-frequency noise while preserving image edges and details as much as possible, improving image processing efficiency and accuracy.

[0134] Optionally, adaptive thresholding can also be used to reduce image noise. Specifically, adaptive thresholding can be explained as a local thresholding method that automatically adjusts the threshold according to different regions of the image, rather than using the same global threshold across the entire image, to reveal the edges and details of the image. This is particularly effective for images with uneven lighting or complex backgrounds, as it can better separate the foreground and background.

[0135] Based on this, this application also performs morphological operations on the denoised image, such as erosion and collision processing.

[0136] Optionally, small spots in the image can be removed by performing an erosion operation. Specifically, the image is scanned using a structuring element (usually a 3x3 or larger rectangle or circle). If all pixels covered by the structuring element are foreground pixels, then the corresponding pixel in the output image is also a foreground pixel; otherwise, the output pixel is a background pixel. This erosion operation can make the boundaries of power lines in the image clearer, improving image quality.

[0137] Optionally, a dilation operation can also be performed on the image. This is done by scanning the image using the same structuring element. If any pixel covered by the structuring element is a foreground pixel, then the corresponding pixel in the output image is also a foreground pixel. Based on the dilation operation's ability to fill gaps between objects, power lines in the image can appear more complete, further improving image quality.

[0138] Through the image preprocessing operations described above, we can obtain two-dimensional guideline images with better image quality, laying a solid foundation for subsequent data analysis and processing.

[0139] In this application, skeletonization can also be called image thinning, which is an image processing method used to thin out objects in an image into thin lines or skeletons, thereby extracting the center line or main line of the object.

[0140] Specifically, taking any power conductor in the power conductor group as an example, the operation stops when the center line or skeleton of the power conductor is obtained by gradually removing the edge pixels of the power conductor. This yields the two-dimensional conductor data of the power conductor.

[0141] Next, we will provide a detailed introduction to the three-dimensional spatial data of the area where the power conductor group is located.

[0142] Optionally, the construction process includes: determining the first spatial data in the X-axis direction of the three-dimensional coordinate system where the spatial region is located, based on the span to which the power conductor group belongs; determining the second spatial data in the Y-axis direction of the three-dimensional coordinate system where the spatial region is located, based on the straight line equations of multiple power conductors in the first plane; determining the third spatial data in the Z-axis direction of the three-dimensional coordinate system where the spatial region is located, based on the height of the tower to which the power conductor group belongs; and determining the three-dimensional spatial data of the spatial region based on the first, second, and third spatial data.

[0143] For ease of explanation, this application will now take any one of the power conductors in the power conductor group as an example to describe in detail the process of constructing three-dimensional spatial data.

[0144] Since the data of the power conductor in the X-axis direction can represent the length of the power conductor, the first spatial data can be determined based on the span between the power towers on both sides of the power conductor. For example, if the span between the two power towers is one kilometer, then to balance the amount of data to be processed and the data accuracy, one first spatial data point can be generated every 0.01 meters, that is, a total of 10,000 data points can be generated in the X-axis direction. Of course, the number of first spatial data points and the second and third spatial data points described above are merely illustrative examples and are not intended to limit this solution.

[0145] Since the second spatial data represents the location and state of power lines, it is difficult to construct such data directly based on the scene data where the power lines are located. Therefore, in this application, the construction of the second spatial data is based on the collected residual cloud data and the constructed first spatial data.

[0146] Specifically, the residual cloud data of the conductor can be projected and mapped to obtain its first straight line equation in the XOY plane (the first plane). For example, this straight line equation can be represented as y = ax + b. Based on this, the first spatial data, i.e., the data constructed in the X-axis direction, and the straight line equation in the XOY plane, can be used to obtain the data of the power conductor in the Y-axis direction, i.e., the second spatial data.

[0147] Since third-space data represents the morphological data of power conductors, and real power conductors are curves with curvature, when constructing morphological data representing the shape of the conductor, the approximate spatial height range of the power conductor can be predicted based on the approximate erection position of the power conductor in the tower and the tower height data. Multiple point cloud data can then be constructed at preset distances within this height range to obtain data in multiple Z-axis directions, i.e., third-space data.

[0148] By arranging and combining the first, second, and third spatial data respectively, multiple three-dimensional coordinate data are obtained, which are the three-dimensional spatial data of the spatial region where the power conductor is located.

[0149] The above-mentioned method of constructing three-dimensional coordinate data of the power lines within their spatial range based on actual scene data and collected point cloud data can help determine the accurate location and layout of the power lines, thereby ensuring the accuracy of subsequent three-dimensional reconstruction.

[0150] Based on the reconstruction basis data and reconstruction foundation data of the power conductor group obtained according to the above implementation method, the power conductor group is subjected to three-dimensional reconstruction processing to obtain the corresponding reconstruction results.

[0151] Optionally, the process of performing three-dimensional reconstruction based on the above data in this application may include: for any power conductor, determining the straight line equation of the power conductor in the first plane based on the conductor defect cloud data corresponding to the power conductor; determining the quadratic curve equation of the power conductor in the second plane based on the three-dimensional spatial data and the two-dimensional conductor data; determining the conductor fitting data of the power conductor at preset intervals based on the straight line equation and the quadratic curve equation; and determining the three-dimensional fitting data of the power conductor group based on the conductor fitting data of multiple power conductors.

[0152] Next, we will continue to use any one of the power conductors in the power conductor group as an example to introduce the three-dimensional reconstruction.

[0153] The process of reconstructing power lines can be the process of generating at least one power line equation. In this application, the first plane can be understood as a two-dimensional plane with coordinate data of 0 on the Z-axis, also referred to as the XOY plane. The second plane can be understood as a two-dimensional plane with coordinate data of 0 on the Y-axis, also referred to as the XOZ plane.

[0154] In this application, the preset distance is a pre-set distance value used to obtain point cloud data on a single power conductor, such as every 0.05 meters. Based on this, a fitting algorithm can be used to calculate the above point cloud data, image data, and three-dimensional spatial data to obtain the straight line equation of the power conductor in the first plane and the curve equation of the power conductor in the second plane.

[0155] Furthermore, by taking a value from the equation of the straight line in the first plane and the equation of the quadratic curve in the second plane, the point coordinates of the point cloud data on the Y-axis and the Z-axis are obtained. In this embodiment, the size of the preset distance is not specifically limited, and it can be determined based on the actual application scenario.

[0156] For example, the equations of the projected cross-section lines in the XOY plane (the equation of the line in the first plane) and the equations of the quadratic curves in the projected cross-sections in the XOZ plane (the equation of the quadratic curve in the second plane) are obtained using the least squares method. Further, point coordinate data for the X-axis are generated every 0.05 meters, and then the point coordinate data for the Y-axis and Z-axis are determined based on this X-axis point coordinate data. In this way, the fifth point cloud data (X, Y, Z) of the single-strand power conductor can be determined.

[0157] Next, the linear equation of the first plane obtained by fitting in this application will be described by way of example.

[0158] Optionally, determining the straight line equation of the power conductor in the first plane based on the conductor residual point cloud data can include: determining a first spatial transformation matrix based on the conductor residual point cloud data; the first spatial transformation matrix is ​​used to characterize the spatial transformation relationship between the three-dimensional point cloud data and the two-dimensional projection data on the preset plane; based on the first spatial transformation matrix, performing projection coordinate transformation on the conductor residual point cloud data in the first plane to obtain first projection data; and fitting the straight line equation of the power conductor in the first plane based on the first projection data.

[0159] In this application, the wire defect cloud data corresponding to any power wire in the defect cloud data can be used to construct the first spatial transformation matrix.

[0160] Optionally, the process of constructing the first spatial matrix includes: fitting a first straight line equation for a first plane and fitting a second straight line equation for a second plane based on the residual cloud data of the conductor; determining the rotation angle between the scanning device and the tower to which the power conductor group belongs based on a preset function, the first straight line equation and the second straight line equation; and constructing a first spatial transformation matrix based on the rotation angle.

[0161] Specifically, the least squares method can be used to solve for the linear equations of the projected cross-sections on the XOY plane (the first linear equation on the first plane) and the linear equations of the projected cross-sections on the XOZ plane (the second linear equation on the second plane), respectively, and obtain the precise geometric parameters of the two linear equations of the projected cross-sections. Furthermore, using the geometric parameters, the required horizontal (yaw) and tilt (pitch) rotation angles parallel to the ground when the pan-tilt unit faces the power pole can be calculated using the arctangent function. Further, based on these two key rotation angle values, a spatial transformation matrix can be constructed to achieve orthographic projection of point cloud data, thereby guiding the pan-tilt unit to perform precise spatial positioning and orientation adjustment.

[0162] The Least Squares Method (LSM) is a mathematical optimization technique used to find the best function fit for data by minimizing the sum of squared errors. Least Squares is widely used in regression analysis, especially linear regression. The core idea of ​​Least Squares is to find a function (usually a linear function) that minimizes the sum of squared differences between the function and the given data points.

[0163] Specifically, if there are n data points (x1, y1), (x2, y2), ..., (xn, yn), then we can find a function y = f(x, a) (where a is the parameter of the function) such that the sum of the squares of the differences between all data points and the function is minimized.

[0164] Optionally, the OBB (Oriented Bounding Box) algorithm can be used in this application to obtain the spatial transformation matrix of the minimum bounding box, and then the projection coordinate transformation can be realized based on the spatial transformation matrix. Alternatively, other algorithms can be used to obtain the spatial transformation matrix and realize the projection coordinate transformation.

[0165] Among them, the OBB algorithm is a method for calculating the oriented bounding box of an object in three-dimensional space. OBB is a minimum rectangular box that can tightly enclose an object and has an arbitrary orientation. Compared with AABB (Axis-Aligned Bounding Box), OBB can more accurately describe the shape and orientation of an object and has wide applications in collision detection, rendering optimization and other fields. Therefore, this application can use the OBB algorithm to obtain the spatial transformation matrix of the minimum bounding box, and then realize the projection coordinate transformation based on the spatial transformation matrix, thereby improving the accuracy of the projection coordinate transformation.

[0166] Understandably, the core of the OBB algorithm is to determine the orientation and size of the bounding box by calculating the principal components of the object. Furthermore, it uses Principal Component Analysis (PCA) to obtain the main directions and magnitudes of data variation. PCA is a commonly used data analysis method that uses eigenvalue decomposition of the covariance matrix of the data to determine these main directions and magnitudes. In the OBB algorithm, PCA is used to calculate the three principal directions of the object—the three axes of the bounding box—and the size of the object in each direction.

[0167] Specifically, the implementation of the OBB algorithm includes the following steps:

[0168] Step 1: Calculate the mean value of the vertex coordinates (point cloud data) of the power conductors, and translate the vertex coordinates of the power conductors to the vicinity of the coordinate origin in order to perform PCA calculation.

[0169] Step 2: Calculate the covariance matrix of the translated vertex coordinates. This covariance matrix is ​​used to describe the changes and correlations of the vertex coordinates of the power conductor in various directions.

[0170] Step 3: Perform eigenvalue decomposition on the covariance matrix to obtain three eigenvectors and their corresponding eigenvalues. The eigenvectors represent the three principal directions of the object, and the eigenvalues ​​represent the variation of the power conductor in each direction.

[0171] Step 4: Sort the feature vectors according to the magnitude of their corresponding feature values, and select the three feature vectors with the largest changes as the directions of the three axes of the bounding box.

[0172] Step 5: Calculate the size of the bounding box in each direction based on the direction of the selected axis and the vertex coordinates of the power conductor. This size can be obtained by calculating the maximum and minimum values ​​of the power conductor in each direction.

[0173] Step 6: Construct an OBB bounding box based on the calculated orientation and size of the bounding box, and then determine the spatial transformation matrix of the minimum bounding box based on the OBB bounding box.

[0174] It should be noted that the method for obtaining the spatial transformation matrix is ​​not specifically limited in the embodiments of this application; the above is merely an example.

[0175] This application embodiment obtains the linear equation of the first plane and the quadratic curve equation of the second plane through fitting, and then determines the fifth point cloud data of the single-strand power conductor based on these two equations, which improves the efficiency of data fitting and can help find the optimal solution or the point cloud data of the single-strand power conductor that is close to the optimal solution.

[0176] Furthermore, the first spatial transformation matrix can be obtained according to the above implementation method, and the residual cloud data can be accurately projected to obtain two-dimensional projection data, thereby making the projection of the two-dimensional projection data on the three axes of XYZ clearer and more regular, which is convenient for subsequent reconstruction processing.

[0177] Figure 3 This application provides a schematic diagram of a projection onto the XOY plane, which, after projection transformation, is as follows: Figure 3 As shown, the data of a line segment pointing to the power poles on both sides of the power conductor can be obtained on the XOY plane, which is the first projection data.

[0178] A linear equation containing unknown parameters is constructed. This linear equation is used to characterize the linear equation of the projected cross section of the XOY plane. The unknown parameters in the linear equation are solved using the least squares method and the first projection data obtained from the above projection. The linear equation with known parameters is obtained, which is the linear equation of the first plane.

[0179] In this way, the height data of the power conductors, i.e., the Y-axis data, can be obtained, and then the power conductors can be reconstructed in three dimensions based on the Y-axis data.

[0180] At the same time, this application also determines the quadratic curve equation of the power conductor in the second plane based on three-dimensional spatial data and two-dimensional conductor data.

[0181] Optionally, the process of determining the quadratic curve equation of the power conductor in the second plane includes: determining conductor fitting data of the power conductor in the spatial region based on three-dimensional spatial data and two-dimensional conductor data; and determining the quadratic curve equation of the power conductor in the second plane based on the conductor fitting data.

[0182] Since the three-dimensional spatial data contains not only the three-dimensional coordinate data corresponding to the power conductors, but also the three-dimensional coordinate data corresponding to other points, the two-dimensional conductor data of the power conductors can be used as prior information to segment the three-dimensional spatial data and obtain the three-dimensional coordinate data corresponding to the power conductors, i.e., the initial fitting data.

[0183] Optionally, the process of obtaining initial fitting data in this application may include: acquiring a predetermined second spatial transformation matrix; the second spatial transformation matrix being used to characterize the spatial transformation relationship between the three-dimensional point cloud data and the two-dimensional image data; based on the second spatial transformation matrix, performing a data projection coordinate transformation on the three-dimensional spatial data in the two-dimensional image plane to obtain second projection data; determining the conductor projection data corresponding to the two-dimensional conductor data in the second projection data; determining the three-dimensional coordinate data corresponding to the conductor projection data based on the three-dimensional spatial data, and using the three-dimensional coordinate data as the initial fitting data for the power conductor group; and segmenting the initial fitting data of the power conductor group to obtain the conductor fitting data for each power conductor.

[0184] Specifically, the projectPoints method in OpenCV can be used to project the three-dimensional spatial data of the power conductor group onto a two-dimensional image plane sequentially.

[0185] `projectPoints` is a function in the OpenCV library primarily used to project points in 3D space onto a 2D image plane. This is a very fundamental and important operation in computer vision and 3D reconstruction. This function belongs to the camera calibration and 3D reconstruction module and can be used to calculate the 2D projection positions of these points on the image from known camera parameters (intrinsic and extrinsic parameters) and 3D point coordinates.

[0186] For example, the expression for the projectPoints function can be: void cv::projectPoints(InputArray objectPoints,InputArray rvec,InputArray tvec,InputArray cameraMatrix,InputArray distCoeffs,OutputArray imagePoints,OutputArray jacobian = noArray(),double aspectRatio = 0).

[0187] Among them, objectPoints: InputArray type, a set of points in three-dimensional space, usually an N×3 or 3×N matrix, where N is the number of points.

[0188] rvec: InputArray type, rotation vector, representing the camera's rotation relative to the world coordinate system, with a size of (3,1).

[0189] tvec: InputArray type, translation vector, representing the camera's translation relative to the world coordinate system, with a size of (3,1).

[0190] cameraMatrix: InputArray type, the camera intrinsic parameter matrix, that is, a 3×3 matrix composed of focal length and principal point coordinates.

[0191] distCoeffs: InputArray type, distortion coefficients, i.e., coefficients of radial and tangential distortion, the size can be (1,4), (1,5), (1,8), (1,12) or vector.

[0192] imagePoints: OutputArray type, output two-dimensional projection points, with a size of N×2 or 2×N, depending on the shape of objectPoints.

[0193] `jacobian`: OutputArray type, optional output, Jacobian matrix, used for numerical solutions. `aspectRatio`: double type, defaults to 0, used to correct the aspect ratio; usually does not need to be set.

[0194] In short, the projectPoints function uses the camera's intrinsic and extrinsic parameters to convert a set of 3D spatial points into their corresponding 2D coordinates on the camera's image plane. It is one of the core functions in scenarios such as 3D reconstruction, visual positioning and tracking, and AR / VR applications.

[0195] It should be noted that there is a mapping relationship between each three-dimensional coordinate point in the three-dimensional spatial data in this application and each two-dimensional coordinate point in the second projection data obtained after projection.

[0196] Specifically, this can be explained as follows: any three-dimensional coordinate point in three-dimensional spatial data and its corresponding two-dimensional coordinate point in the second projection data can have the same and unique coding index. That is, based on this unique coding index, the coordinate point can be found and mapped between different spatial coordinate systems.

[0197] For example, while mapping three-dimensional spatial data onto a two-dimensional image plane, the mapped two-dimensional projection data is also drawn onto the two-dimensional image. During the drawing process, each two-dimensional projection data is marked with a different index code; each index code can be displayed in different colors in the image. In this way, the relationship between the two-dimensional projection data can be intuitively displayed, and its coordinate position information in the original dataset (three-dimensional spatial data) can also be indicated.

[0198] Furthermore, the two-dimensional conductor data of the power conductor group obtained based on the above embodiments can be used to perform a masking operation on the second projection data to obtain the conductor projection data after masking.

[0199] It should be understood that mask calculation for two-dimensional image data typically refers to using a mask in image processing to extract or modify specific regions in an image. A mask is a binary image in which pixel values ​​are typically 0 or 1 (or other values, but usually binary), used to indicate which regions need to be preserved or processed, and which regions need to be ignored.

[0200] The masking process will now be described exemplarily.

[0201] Step 1: Create a binary image of the same size as the original image, where the areas that need to be preserved or processed are marked as 1 (white) and the areas that do not need to be processed are marked as 0 (black).

[0202] Step 2: Combine the mask with the original image using point-to-point multiplication. This is typically achieved using logical AND operations or element-wise multiplication.

[0203] Step 3: Based on the masking results, the Region of Interest (ROI) can be extracted, or these regions can be further processed, such as enhancement, blurring, edge detection, etc.

[0204] Next, based on the index code and color of each coordinate point in the conductor projection data, a three-dimensional coordinate query is performed in the three-dimensional space data to obtain the initial fitting data corresponding to the power conductor group.

[0205] Since the initial fitted data may be sparse and not smooth enough, it cannot be used as the final reconstruction result. However, since it contains morphological data that is crucial for the three-dimensional reconstruction of power lines, the initial fitted data can be projected onto the second plane, namely the XOZ plane, using the first spatial transformation matrix to obtain the third projection data.

[0206] Figure 4 A schematic diagram of a projection onto the XOZ plane is provided as an embodiment of this application, such as... Figure 4 As shown, multiple catenary-like power conductor data are presented on the XOZ plane.

[0207] To obtain conductor fitting data for a single power conductor, the initial fitting data can be segmented. Optionally, the Euclidean Cluster Extraction clustering algorithm described in the above embodiments can be used for processing; of course, other segmentation methods can also be used, and this application does not specifically limit this.

[0208] Since the third projection data corresponding to each power conductor is curve data, a quadratic curve equation containing unknown parameters is constructed. This equation is used to characterize the projection cross-section curve equation of the XOZ plane. Using the least squares method and the projection data of any power conductor in the third projection data, the unknown parameters in the curve equation are solved to obtain the curve equation with known parameters, that is, the curve equation of the second plane.

[0209] Understandably, this application utilizes the least squares method to derive the equations of the straight line in the first plane and the quadratic curve in the second plane. A major advantage is its ease of computation, and it yields good results in most cases. However, the least squares method also has some limitations. For example, it assumes that the errors are independent and identically distributed, and follow a normal distribution. If these assumptions do not hold, then the least squares method may not be the optimal choice. Therefore, the embodiments of this application are not limited to deriving the equations of the straight line in the first plane and the quadratic curve in the second plane based on the least squares method. Other fitting algorithms can also be used to derive the equations of the straight line in the first plane and the quadratic curve in the second plane. This application does not specifically limit the embodiments in this regard.

[0210] In summary, the least squares method is a powerful and commonly used mathematical tool that can be used to find the best-fitting model from data.

[0211] Based on the three-dimensional reconstruction results of the power conductor group, the technical solution of this application also includes: determining the supplementary point cloud data of the power conductor group according to the three-dimensional fitting data and the residual defect cloud data; adding labels to the supplementary point cloud data and the residual defect cloud data respectively, and storing them.

[0212] For example, taking the result of 3D reconstruction as at least one power conductor equation as an example, for the reconstruction of power conductors between any two power poles, after generating supplementary point cloud data using at least one power conductor equation, this supplementary point cloud data can be stored in a LAS format file for subsequent processing and application. To clearly distinguish the fitted supplementary point cloud data from the original collected data, a special tag can be added when saving this data. This tag, as a unique identifier, can clearly identify which data was generated by fitting the power conductor equation and which data was originally collected.

[0213] In this way, the labeling method not only ensures the accuracy and integrity of the data, but also facilitates subsequent data processing and analysis, ensuring that all types of data are correctly applied and processed.

[0214] It should be noted that if only one set of data is obtained during the processing of the above embodiments, such as a set of third point cloud clusters, the execution process of the above embodiments can also be executed. The embodiments of this application do not specifically limit the amount of data required for the specific execution process.

[0215] In the foregoing embodiments, the power conductor data processing method provided by the embodiments of this application has been described. To implement the functions of the methods provided by the embodiments of this application, the electronic device serving as the execution subject may include hardware structures and / or software modules, implementing the above functions in the form of hardware structures, software modules, or a combination of hardware structures and software modules. Whether a particular function is executed in the form of hardware structures, software modules, or a combination of hardware structures and software modules depends on the specific application and design constraints of the technical solution.

[0216] Figure 5 This is a schematic diagram of a power line data processing device provided in an embodiment of this application. See also... Figure 5 The power conductor data processing device 50 includes:

[0217] The data acquisition module 501 is used to acquire residual defect cloud data and two-dimensional conductor data of the power conductor group; wherein the power conductor group includes at least one power conductor;

[0218] Data construction module 502 is used to construct three-dimensional spatial data of the spatial region where the power conductor group is located based on the residual cloud data;

[0219] The data fitting module 503 is used to perform three-dimensional fitting processing on the power conductor group based on three-dimensional spatial data, two-dimensional conductor data and residual defect cloud data, to obtain three-dimensional fitting data of the power conductor group.

[0220] In one alternative implementation, the data fitting module 503 includes:

[0221] The first equation construction submodule is used to determine the straight line equation of any power conductor in the first plane based on the conductor defect cloud data corresponding to the power conductor.

[0222] The second equation construction submodule is used to determine the quadratic curve equation of the power conductor in the second plane based on the three-dimensional spatial data and the two-dimensional conductor data.

[0223] The first data fitting module is used to determine the conductor fitting data of the power conductor at preset intervals based on the equations of straight lines and quadratic curves.

[0224] The second data fitting module is used to determine the three-dimensional fitting data of the power conductor group based on the conductor fitting data of multiple power conductors.

[0225] In one alternative implementation, the data construction module 502 includes:

[0226] The first spatial data construction submodule is used to determine the first spatial data in the X-axis direction of the three-dimensional coordinate system of the spatial region based on the span to which the power conductor group belongs;

[0227] The second spatial data construction submodule is used to determine the second spatial data in the Y-axis direction of the three-dimensional coordinate system in which the spatial region is located, based on the straight line equations of multiple power conductors in the first plane.

[0228] The third spatial data construction submodule is used to determine the third spatial data in the Z-axis direction of the three-dimensional coordinate system of the spatial region based on the height of the tower to which the power conductor group belongs.

[0229] The three-dimensional spatial data construction submodule is used to determine the three-dimensional spatial data of a spatial region based on the first spatial data, the second spatial data, and the third spatial data.

[0230] In one alternative implementation, the first equation constructs a submodule, including:

[0231] The first spatial transformation matrix determination unit is used to determine the first spatial transformation matrix based on the point cloud data of the conductor residual points; the first spatial transformation matrix is ​​used to characterize the spatial transformation relationship between the three-dimensional point cloud data and the two-dimensional projection data on the preset plane.

[0232] The first projection data acquisition unit is used to perform projection coordinate transformation on the wire residual cloud data in the first plane according to the first spatial transformation matrix to obtain the first projection data.

[0233] The first equation generation unit is used to fit the straight line equation of the power conductor in the first plane based on the first projection data.

[0234] In one optional implementation, the first spatial transformation matrix determining unit includes:

[0235] A linear equation fitting sub-unit is used to fit the first linear equation of the first plane and the second linear equation of the second plane based on the residual cloud data of the conductor.

[0236] The rotation angle determination subunit is used to determine the rotation angle between the scanning device and the tower to which the power conductor group belongs, based on a preset function, a first straight line equation, and a second straight line equation.

[0237] The first spatial transformation matrix determines the sub-units, which are used to construct the first spatial transformation matrix based on the rotation angle.

[0238] In one alternative implementation, the second equation construction submodule includes:

[0239] The fitting data determination unit is used to determine the conductor fitting data of the power conductor in the spatial region based on the three-dimensional spatial data and the two-dimensional conductor data.

[0240] The second equation generation unit is used to determine the quadratic curve equation of the power conductor in the second plane based on the conductor fitting data.

[0241] In one optional implementation, the fitting data determination unit includes:

[0242] The second spatial transformation matrix determines the sub-unit, and a predetermined second spatial transformation matrix is ​​obtained; the second spatial transformation matrix is ​​used to characterize the spatial transformation relationship between three-dimensional point cloud data and two-dimensional image data.

[0243] The second projection data determination subunit is used to perform data projection coordinate transformation on the three-dimensional spatial data in the two-dimensional image plane according to the second spatial transformation matrix to obtain the second projection data.

[0244] The traverse projection data determination subunit is used to determine the traverse projection data corresponding to the two-dimensional traverse data in the second projection data;

[0245] The initial fitting data determination sub-unit is used to determine the three-dimensional coordinate data corresponding to the conductor projection data based on the three-dimensional spatial data, and the three-dimensional coordinate data is used as the initial fitting data for the power conductor group.

[0246] The conductor fitting data determination sub-unit is used to segment the initial fitting data of the power conductor group to obtain the conductor fitting data for each power conductor.

[0247] In one alternative implementation, there is a mapping relationship between each three-dimensional coordinate point in the three-dimensional spatial data and each two-dimensional coordinate point in the second projection data.

[0248] In one alternative embodiment, the device further includes:

[0249] The supplementary point cloud data determination module is used to determine the supplementary point cloud data of the power conductor group based on the 3D fitting data and the residual point cloud data.

[0250] The data storage module is used to add tags to the supplementary point cloud data and the residual point cloud data respectively, and then store them.

[0251] In one optional implementation, the data acquisition module 501 includes:

[0252] The point cloud data acquisition submodule is used to process the initial point cloud data obtained from scanning the power conductor group based on a preset spatial bounding box, and obtain the point cloud data located within the spatial bounding box.

[0253] The point cloud cluster data acquisition submodule is used to segment the point cloud data within the spatial bounding box to obtain at least one set of point cloud cluster data.

[0254] The residual defect cloud data acquisition submodule is used to obtain residual defect cloud data of the power conductor group based on the data characteristics of each point cloud cluster data.

[0255] In one optional implementation, the data acquisition module 501 includes:

[0256] The two-dimensional conductor image acquisition submodule is used to perform image preprocessing on the initial two-dimensional image obtained by capturing the electric conductor group to obtain a two-dimensional conductor image containing the electric conductor group.

[0257] The two-dimensional conductor data acquisition submodule is used to perform image skeletonization processing on the two-dimensional conductor image to obtain the two-dimensional conductor data of the power conductor group.

[0258] Figure 6 This is a block diagram illustrating an electronic device according to an embodiment of this application. The device may be a computer, a digital broadcasting terminal, etc.

[0259] See Figure 6 The device 800 may include one or more of the following components: processing component 802, memory 804, power supply component 806, multimedia component 808, audio component 810, input / output interface 812, sensor component 814, and communication component 816.

[0260] Processing component 802 typically controls the overall operation of device 800, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the methods described above. Furthermore, processing component 802 may include one or more modules to facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.

[0261] Memory 804 is configured to store various types of data to support the operation of device 800. Examples of such data include instructions for any application or method operating on device 800, contact data, phonebook data, messages, pictures, videos, etc. Memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0262] Power supply component 806 provides power to various components of device 800. Power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to device 800.

[0263] Multimedia component 808 includes a screen that provides an output interface between device 800 and the user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a Touch Panel, the screen may be implemented as a touchscreen to receive input signals from the user. The Touch Panel includes one or more touch sensors to sense touches, swipes, and gestures on the Touch Panel. The touch sensors may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 808 includes a front-facing camera and / or a rear-facing camera. When device 800 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0264] Audio component 810 is configured to output and / or input audio signals. For example, audio component 810 includes a microphone (MIC) configured to receive external audio signals when device 800 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 804 or transmitted via communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

[0265] Input / output interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0266] Sensor assembly 814 includes one or more sensors for providing state assessments of various aspects of device 800. For example, sensor assembly 814 may detect the on / off state of device 800, the relative positioning of components such as the display and keypad of device 800, changes in the position of device 800 or a component of device 800, the presence or absence of user contact with device 800, the orientation or acceleration / deceleration of device 800, and temperature changes of device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 814 may also include an optical sensor, such as a complementary metal-oxide-semiconductor (CMOS) sensor or a charge-coupled device (CCD) sensor, for use in imaging applications. In some embodiments, sensor assembly 814 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0267] Communication component 816 is configured to facilitate wired or wireless communication between device 800 and other devices. Device 800 can access wireless networks based on communication standards, such as WiFi, 4G, or 5G, or combinations thereof. In one exemplary embodiment, communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 816 also includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wide Band (UWB), Bluetooth (BT), and other technologies.

[0268] In an exemplary embodiment, device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processors (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0269] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, which can be executed by a processor 820 of the device 800 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0270] A non-transitory computer-readable storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the aforementioned aircraft collision prediction method.

[0271] This application also provides a chip for executing commands, which is used to execute the technical solution of the aircraft collision prediction method in the above embodiments.

[0272] This application also provides a computer-readable storage medium storing computer-executable instructions. When the computer-executable instructions are executed on a computer, the computer executes the technical solution of the aircraft collision prediction method described in the above embodiments.

[0273] This application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When the at least one processor executes the computer program, it can implement the technical solution of the aircraft collision prediction method in the above embodiments.

[0274] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0275] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

[0276] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0277] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A power conductor data processing method, characterized by, The method comprises: Obtaining incomplete point cloud data and two-dimensional conductor data of a power conductor group; wherein the power conductor group comprises at least one power conductor; According to the incomplete point cloud data, constructing three-dimensional space data of a space region where the power conductor group is located; According to the three-dimensional space data, the two-dimensional conductor data and the incomplete point cloud data, performing three-dimensional reconstruction processing on the power conductor group to obtain three-dimensional fitting data of the power conductor group.

2. The method of claim 1, wherein, According to the three-dimensional space data, the two-dimensional conductor data and the incomplete point cloud data, performing three-dimensional reconstruction processing on the power conductor group to obtain three-dimensional fitting data of the power conductor group, comprising: For any power conductor, according to the conductor incomplete point cloud data corresponding to the power conductor, determining a straight line equation of the power conductor in a first plane; According to the three-dimensional space data and the two-dimensional conductor data, determining a quadratic curve equation of the power conductor in a second plane; Every other preset distance, according to the straight line equation and the quadratic curve equation, determining conductor fitting data of the power conductor; According to the conductor fitting data of each power conductor, determining three-dimensional fitting data of the power conductor group.

3. The method of claim 1, wherein, According to the incomplete point cloud data, constructing three-dimensional space data of a space region where the power conductor group is located, comprising: According to the span to which the power conductor group belongs, determining first space data of the space region in the X-axis direction of a three-dimensional coordinate system; According to the straight line equation of each power conductor in the first plane, determining second space data of the space region in the Y-axis direction of the three-dimensional coordinate system; According to the height of the tower to which the power conductor group belongs, determining third space data of the space region in the Z-axis direction of the three-dimensional coordinate system; According to the first space data, the second space data and the third space data, determining three-dimensional space data of the space region.

4. The method of claim 2, wherein, According to the conductor incomplete point cloud data corresponding to the power conductor, determining a straight line equation of the power conductor in a first plane, comprising: According to the conductor incomplete point cloud data, determining a first space transformation matrix; the first space transformation matrix is used to represent the space transformation relationship between three-dimensional point cloud data and two-dimensional projection data on a preset plane; According to the first space transformation matrix, performing projection coordinate conversion on the conductor incomplete point cloud data in the first plane to obtain first projection data; According to the first projection data, fitting to obtain the straight line equation of the power conductor in the first plane.

5. The method of claim 4, wherein, According to the conductor incomplete point cloud data, determining a first space transformation matrix, comprising: According to the conductor incomplete point cloud data, fitting to obtain a first straight line equation of the first plane, and fitting to obtain a second straight line equation of the second plane; According to a preset function, the first straight line equation and the second straight line equation, determining a rotation angle between a scanning device and the tower to which the power conductor group belongs; According to the rotation angle, constructing the first space transformation matrix.

6. The method of claim 2, wherein, According to the three-dimensional space data and the two-dimensional conductor data, determining a quadratic curve equation of the power conductor in a second plane, comprising: determining line fitting data of the power conductor in the spatial region according to the three-dimensional spatial data and the two-dimensional line data; determining a quadratic curve equation of the power conductor in a second plane according to the line fitting data.

7. The method of claim 6, wherein, determining line fitting data of the power conductor in the spatial region according to the three-dimensional spatial data and the two-dimensional line data, comprising: obtaining a predetermined second spatial transformation matrix; the second spatial transformation matrix is used to represent a spatial transformation relationship between three-dimensional point cloud data and two-dimensional image data; performing data projection coordinate transformation on the three-dimensional spatial data in a two-dimensional image plane to obtain second projection data according to the second spatial transformation matrix; determining line projection data corresponding to the two-dimensional line data in the second projection data; determining three-dimensional coordinate data corresponding to the line projection data according to the three-dimensional spatial data, and taking the three-dimensional coordinate data as initial fitting data of the power conductor group; performing segmentation processing on the initial fitting data of the power conductor group to obtain line fitting data of each power conductor.

8. The method of claim 7, wherein, There is a mapping relationship between each three-dimensional coordinate point in the three-dimensional spatial data and each two-dimensional coordinate point in the second projection data.

9. The method according to any one of claims 1-8, characterized in that, The method further comprises: determining supplementary point cloud data of the power conductor group according to the three-dimensional fitting data and the incomplete point cloud data; adding labels to the supplementary point cloud data and the incomplete point cloud data respectively and storing them.

10. The method according to any one of claims 1-8, characterized in that, Obtaining incomplete point cloud data of a power conductor group comprises: processing initial point cloud data obtained by scanning the power conductor group to obtain point cloud data located in a spatial bounding box based on a preset spatial bounding box; performing segmentation processing on the point cloud data in the spatial bounding box to obtain at least one group of point cloud cluster data; obtaining incomplete point cloud data of the power conductor group according to data characteristics of each point cloud cluster data.

11. The method according to any one of claims 1-8, characterized in that, Obtaining two-dimensional line data of a power conductor group comprises: performing image preprocessing on initial two-dimensional images obtained by photographing the power conductor group to obtain two-dimensional line images containing the power conductor group; performing image skeletonization processing on the two-dimensional line images to obtain two-dimensional line data of the power conductor group.

12. An electric power conductor data processing apparatus, characterized by The device comprises: a data acquisition module configured to obtain incomplete point cloud data and two-dimensional line data of a power conductor group; wherein the power conductor group comprises at least one power conductor; a data construction module configured to construct three-dimensional spatial data of a spatial region where the power conductor group is located according to the incomplete point cloud data; a data fitting module configured to perform three-dimensional fitting processing on the power conductor group according to the three-dimensional spatial data, the two-dimensional line data and the incomplete point cloud data to obtain three-dimensional fitting data of the power conductor group.

13. An electronic device, comprising: comprise: a processor and a memory connected in communication with the processor; the memory stores computer execution instructions; the processor is configured to implement the power conductor data processing method according to any one of claims 1 to 11 when executing the computer execution instructions.

14. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer execution instructions, and the computer execution instructions are used for realizing the power conductor data processing method in any one of claims 1 to 11 when executed by the processor.

15. A computer program product, characterised in that, Comprise: A computer program, which realizes the power conductor data processing method in any one of claims 1 to 11 when executed by the processor.

Images