Method and system for constructing single-tree point cloud model of power transmission line of power network

Abstract

The invention provides a construction method and system of a single-tree point cloud model of a power network transmission line, and relates to the technical field of electric power. According to the implementation scheme, vegetation point clouds corresponding to two adjacent and communicated power nodes in a power network are connected, and a point cloud connection graph is obtained; based on the length of the shortest path from each point cloud node to the point cloud root node, dividing each point cloud node into a plurality of hierarchies; determining mutually connected point clouds in the point cloud node set of each level to obtain a connected point cloud cluster of each level; and for a cross-layer connecting line crossing two adjacent levels, skeleton point connection is carried out on the point cloud centers of the connected point cloud clusters where two end points in the cross-layer connecting line are located, so that a first single-wood skeleton is obtained. In this way, the single-tree skeleton formed by the vegetation point clouds related to the power transmission line can be accurately extracted. Furthermore, based on the first individual tree skeleton, cylinder fitting is performed on the vegetation point cloud, and a target individual tree point cloud model can be accurately obtained.

Description

Technical Field

[0001] The present invention relates to the field of information security technology, and in particular to a method and system for constructing a single-tree point cloud model of a power network transmission line. Background Art

[0002] In recent years, with the development of LiDAR technology, its application in power transmission channel monitoring has gradually become a research hotspot. The maintenance and management of power transmission channels require accurate and efficient technical means to ensure the safe operation of power facilities. Due to its high precision and three-dimensional characteristics, LiDAR point cloud data provides technical support for the refined modeling of key targets in power transmission channels (such as single trees, poles, etc.).

[0003] In power transmission channels, the refined construction of single-tree point cloud models is of great significance. On the one hand, the single-tree model can accurately reflect the spatial relationship between vegetation and power transmission lines, and assist in assessing the potential risk of electric shock from trees; on the other hand, the refined single-tree model can also provide basic data for ecological environmental monitoring of power transmission channels. However, due to the large amount of data, complex point cloud distribution, and high difficulty in extracting detailed features of single-tree point cloud data, how to optimize the efficiency of point cloud data processing and model construction while maintaining model accuracy is still a technical challenge.

[0004] Existing single-tree point cloud modeling methods are usually based on global point cloud processing or traditional 3D reconstruction technology, which is easily affected by point cloud noise, branch overlap and missing local features, resulting in insufficient model accuracy or huge data volume. Summary of the invention

[0005] The present invention provides a method and system for constructing a single-tree point cloud model of a power network transmission line, which can solve at least one of the above technical problems.

[0006] According to one aspect of the present invention, a method for constructing a single-tree point cloud model of a power network transmission line is provided, comprising: Based on each transmission line in the power network, vegetation point clouds corresponding to any two adjacent and connected power nodes in the power network are connected to obtain a point cloud connection diagram; Based on the length of the shortest path from each point cloud node to a point cloud root node in the point cloud connection graph, each point cloud node in the point cloud connection graph is divided into multiple levels to obtain a point cloud node set of each level; Based on the point cloud connection graph, mutually connected point clouds are respectively determined in the point cloud node sets of each level to obtain connected point cloud clusters of each level; Based on the point cloud connection graph, determining a cross-layer connection line spanning two adjacent layers; For each of the cross-layer connection lines, the point cloud centers of the connected point cloud clusters where two endpoints of the cross-layer connection line are located are respectively connected by skeleton points to obtain a first single-wood skeleton; Based on the first single-tree skeleton, cylindrical fitting is performed on the vegetation point clouds corresponding to the two adjacent and connected power nodes to obtain a target single-tree point cloud model of the power network.

[0007] According to another aspect of the present invention, there is provided a device for constructing a single-tree point cloud model of a power network transmission line, comprising: A point cloud connection diagram construction module is used to connect vegetation point clouds corresponding to any two adjacent and connected power nodes in the power network based on each transmission line in the power network to obtain a point cloud connection diagram; A point cloud partitioning module, for partitioning each point cloud node in the point cloud connection graph into multiple levels based on the length of the shortest path from each point cloud node to a point cloud root node in the point cloud connection graph, so as to obtain a point cloud node set of each level; A point cloud cluster determination module, configured to determine mutually connected point clouds in the point cloud node sets of each level based on the point cloud connection graph, so as to obtain connected point cloud clusters of each level; A cross-layer line determination module, used for determining a cross-layer connection line spanning two adjacent layers based on the point cloud connection graph; A skeleton point connection module is used to connect the point cloud centers of the connected point cloud clusters where the two endpoints of each cross-layer connection line are located by skeleton points, so as to obtain a first single-wood skeleton; The point cloud model construction module is used to perform cylindrical fitting on the vegetation point clouds corresponding to the two adjacent and connected power nodes based on the first single-wood skeleton to obtain a target single-wood point cloud model of the power network.

[0008] According to the technical solution of the present invention, based on each transmission line in the power network, the point clouds corresponding to any two adjacent and connected power nodes in the power network are connected to obtain a point cloud connection diagram; based on the length of the shortest path from each point cloud node to the point cloud root node in the point cloud connection diagram, each point cloud node in the point cloud connection diagram is divided into multiple levels to obtain a point cloud node set of each level; based on the point cloud connection diagram, mutually connected point clouds are respectively determined in the point cloud node set of each level to obtain a connected point cloud cluster of each level; based on the point cloud connection diagram, a cross-layer connection line spanning two adjacent levels is determined; for each cross-layer connection line, the point cloud centers of the connected point cloud clusters where the two endpoints in the cross-layer connection line are located are respectively connected by skeleton points to obtain the first single tree skeleton. In this way, the single tree skeleton composed of the vegetation point cloud related to the transmission line can be accurately extracted. Furthermore, based on the first single tree skeleton, the vegetation point cloud is cylindrically fitted to accurately obtain the target single tree point cloud model in the power network. Subsequently, when the target single-tree point cloud model is used for information processing or monitoring related to the transmission line, the processing accuracy can be improved.

[0009] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are used to better understand the present invention and do not constitute a limitation of the present invention. Figure 1 It is a flow chart of a method for constructing a single-tree point cloud model of a power network transmission line according to an embodiment of the present invention; Figure 2 is a schematic diagram of a first single wood frame according to an embodiment of the present invention; Figure 3 is a schematic diagram of a second single wood frame according to an embodiment of the present invention; Figure 4 is a schematic diagram of a target single tree point cloud model according to an embodiment of the present invention; Figure 5 It is a structural block diagram of a device for constructing a single-tree point cloud model of a power network transmission line according to an embodiment of the present invention; Figure 6 The block diagram is a block diagram of an electronic device for implementing the method according to the embodiment of the present invention. DETAILED DESCRIPTION

[0011] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be appreciated by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present invention. Similarly, for clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0012] Figure 1 It is a flow chart of a method for constructing a single-tree point cloud model of a power network transmission line according to an embodiment of the present invention.

[0013] like Figure 1 As shown, the method for constructing a single point cloud model of the power network transmission line may include: S110, based on each transmission line in the power network, connecting vegetation point clouds corresponding to any two adjacent and connected power nodes in the power network to obtain a point cloud connection diagram; S120, dividing each point cloud node in the point cloud connection graph into multiple levels based on the length of the shortest path from each point cloud node to the point cloud root node in the point cloud connection graph, so as to obtain a point cloud node set of each level; S130, based on the point cloud connection graph, respectively determining mutually connected point clouds in the point cloud node sets of each level to obtain connected point cloud clusters of each level; S140, determining a cross-layer connection line spanning two adjacent layers based on the point cloud connection graph; S150, for each cross-layer connection line, respectively connect the point cloud centers of the connected point cloud clusters where two endpoints of the cross-layer connection line are located by skeleton point connection to obtain a first single-wood skeleton; S160, based on the first single-tree skeleton, cylindrical fitting is performed on the vegetation point clouds corresponding to the two adjacent and connected power nodes to obtain a target single-tree point cloud model of the power network.

[0014] Exemplarily, the power network may be a regional network, such as the South China regional power grid or a power grid of a certain city.

[0015] Exemplarily, two adjacent and connected power nodes mean that there is no power transmission line between the two power nodes. If the two power nodes are adjacent but not connected, it means that there is no power transmission line between the two power nodes.

[0016] Exemplarily, the Delaunay triangulation algorithm can be used to sequentially connect vegetation point clouds corresponding to any two adjacent and connected power nodes in the power network based on each transmission line in the power network, so that a point cloud connection diagram can be obtained.

[0017] Exemplarily, the point cloud connection graph includes multiple point clouds, and there is a connection or disconnection relationship between two adjacent point clouds. The point cloud connection graph may include a path composed of multiple continuously connected point clouds.

[0018] For example, the Dijkstra greedy algorithm can be used to search for the shortest path from the point cloud root node to each point cloud node in the point cloud connection graph, taking the Euclidean distance between any two point clouds with a connection line in the point cloud connection graph as the weight. In this way, the point clouds in the point cloud connection graph can be adjusted from short to long according to the length of the shortest path from the point cloud root node to each point cloud node, and the adjusted point cloud connection graph can be obtained.

[0019] It can be understood that the point cloud root node is a point cloud in the point cloud connection graph, and is the point cloud with the lowest point.

[0020] Exemplarily, based on the length of the shortest path from each point cloud node to the point cloud root node in the point cloud connection graph, each point cloud node in the point cloud connection graph is divided into multiple levels to obtain a point cloud node set at each level. In this way, point cloud nodes with different interval lengths from the point cloud root node are divided into different levels, which is convenient for the subsequent construction of the initial single wooden skeleton. Different levels correspond to different length intervals. In other words, according to the shortest path length from each point cloud node to the point cloud root node in the adjusted point cloud connection graph, each point cloud node in the graph is divided into In the level, is a positive integer greater than 1.

[0021] Exemplarily, a connected point cloud cluster includes multiple interconnected point clouds. For example, although point cloud A and point cloud D have no direct connection line, point cloud A is connected to point cloud D through the connection with point cloud B, point cloud B and point cloud C, and point cloud C and point cloud D. Any point cloud in a connected point cloud cluster can be connected to other point clouds in the point cloud cluster.

[0022] It can be understood that each level may include one or more connected point cloud clusters.

[0023] It can be understood that the two endpoints of the cross-layer connection line are also point cloud nodes.

[0024] It can be understood that, when any two adjacent and connected point cloud nodes are found in the point cloud connection graph, and the levels to which the two point cloud nodes belong are different, the connection line between the two point cloud nodes is determined to be a cross-layer connection line that crosses two adjacent levels. The levels to which the two point cloud nodes belong are adjacent levels.

[0025] For example, the point cloud center can be the cluster center in the connected point cloud cluster or the arithmetic mean of all point cloud positions. The point cloud center is used as the skeleton point, and each skeleton point is connected through a cross-layer connection line to obtain the first single wood skeleton.

[0026] Exemplarily, when performing cylindrical fitting on the point clouds corresponding to each power node in the power network based on the first single-wood skeleton to obtain a target single-wood point cloud model of the power network, the skeleton lines and / or skeleton points in the first single-wood skeleton can be optimized first, and then the optimized second single-wood skeleton can be used to perform cylindrical fitting on the point clouds corresponding to each power node in the power network to obtain the target single-wood point cloud model of the power network.

[0027] For example, after obtaining the target single tree point cloud model, the target single tree point cloud model is used to evaluate the risk of electric shock between the transmission line and the surrounding vegetation. Alternatively, the target single tree point cloud model is used to monitor the surrounding ecological environment of each transmission line in the power network.

[0028] like Figure 2 As shown, it shows a schematic diagram of the first single wood frame of the embodiment of the present application. The first single wood frame obtained after processing the point cloud corresponding to each power node in the power network through the above steps S110 to S150 can be as follows Figure 2 shown.

[0029] According to the above implementation, based on each transmission line in the power network, the point clouds corresponding to any two adjacent and connected power nodes in the power network are connected to obtain a point cloud connection graph; based on the length of the shortest path from each point cloud node to the point cloud root node in the point cloud connection graph, each point cloud node in the point cloud connection graph is divided into multiple levels to obtain a point cloud node set of each level; based on the point cloud connection graph, the mutually connected point clouds are respectively determined in the point cloud node set of each level to obtain a connected point cloud cluster of each level; based on the point cloud connection graph, the cross-layer connection line spanning two adjacent levels is determined; for each cross-layer connection line, the point cloud centers of the connected point cloud clusters where the two endpoints in the cross-layer connection line are located are respectively connected by skeleton points to obtain the first single tree skeleton. In this way, the single tree skeleton composed of the vegetation point cloud related to the transmission line can be accurately extracted. Furthermore, based on the first single tree skeleton, the vegetation point cloud is cylindrically fitted to accurately obtain the target single tree point cloud model in the power network. Subsequently, when the target single-tree point cloud model is used for information processing or monitoring related to the transmission line, the processing accuracy can be improved.

[0030] In one embodiment, based on the length of the shortest path from each point cloud node to the point cloud root node in the point cloud connection graph, each point cloud node in the point cloud connection graph is divided into multiple levels, including: based on the length of the shortest path from each point cloud node to the point cloud root node in the point cloud connection graph, the maximum value of the shortest path length is determined; for each point cloud node in the point cloud connection graph, the level to which the point cloud node belongs is determined based on the ratio between the length of the shortest path from the point cloud node to the point cloud root node and the maximum value of the shortest path length, and a preset total number of levels.

[0031] Exemplarily, the ratio is multiplied by the total number of levels, and the multiplication result is rounded to the integer, so as to obtain the level to which the point cloud node belongs.

[0032] For example, the following formula may be used to determine the level to which each point cloud node belongs: ; In the formula, For the The level to which the point cloud node belongs, is the total number of levels, For the The shortest path length from a point cloud node to the point cloud root node, It is the maximum value of the shortest path length of all point cloud nodes in the graph.

[0033] According to the above implementation, each point cloud can be accurately divided into different levels.

[0034] In one embodiment, for each cross-layer connection line, the point cloud centers of the connected point cloud clusters where the two endpoints of the cross-layer connection line are located are respectively connected by skeleton points to obtain a first single-wood skeleton, including: determining the corresponding index label for each connected point cloud cluster; connecting the index labels of the connected point cloud clusters where the two endpoints of each cross-layer connection line are located to obtain an index connection topology graph; based on the two index label endpoints of each index connection line in the index connection topology graph, connecting the point cloud centers of the corresponding connected point cloud clusters to obtain the first single-wood skeleton.

[0035] It can be understood that based on the two index label endpoints of each index connection line in the index connection topology graph, the point cloud centers of the connected point cloud clusters corresponding to the two index label endpoints are connected.

[0036] Exemplarily, the point cloud center may be a cluster center in a connected point cloud cluster or an arithmetic mean of the positions of all point clouds.

[0037] It can be understood that the first single wood frame is an initial single wood frame, which can be Figure 2 shown.

[0038] According to the above embodiment, an initial single-wood frame can be constructed quickly and accurately.

[0039] In one embodiment, based on the first single-tree skeleton, cylindrical fitting is performed on the vegetation point clouds corresponding to the above-mentioned two adjacent and connected power nodes to obtain a target single-tree point cloud model of the power network, including: optimizing the skeleton points and / or skeleton lines in the first single-tree skeleton to obtain a second single-tree skeleton; based on each skeleton line in the second single-tree skeleton, cylindrical fitting is performed on the vegetation point clouds corresponding to the above-mentioned two adjacent and connected power nodes to obtain a first single-tree point cloud model; leaf simulation and coloring are performed on the branch ends of the first single-tree point cloud model to obtain a target single-tree point cloud model of the power network.

[0040] Exemplarily, optimizing the skeleton points and / or skeleton lines in the first single-wood skeleton may include deleting skeleton lines with shorter lengths, deleting redundant skeleton points, or merging skeleton points with similar distances to merge skeleton lines.

[0041] For example, Figure 3 , which is a schematic diagram of a second single wood skeleton obtained by optimizing the skeleton points and / or skeleton lines in the first single wood skeleton. The second single wood skeleton is similar to the original point cloud of the power network and can successfully reflect its unique branch layout and morphological characteristics.

[0042] For example, Figure 4 As shown in FIG, the second single wood skeleton is subjected to leaf simulation and coloring processing to obtain the target single wood point cloud model of the power network. Figure 4 It can be seen that the final single tree model visually restores the shape of the real tree to a high degree, and the structure and extension of the branches are accurately reproduced.

[0043] According to the above implementation, the skeleton points and / or skeleton lines in the initial single-tree skeleton can be optimized, and then the corresponding vegetation point cloud of the optimized second single-tree skeleton can be cylindrically fitted to obtain the first single-tree point cloud model, and finally, the model can be leaf simulated and colorized to obtain the target single-tree point cloud model of the power network. In this way, the tree morphology can be truly restored to accurately evaluate the relationship between the tree and the transmission line.

[0044] In one embodiment, skeleton points and / or skeleton lines in a first single-wood skeleton are optimized to obtain a second single-wood skeleton, including: for each skeleton point in the first single-wood skeleton, determining the weight of each skeleton point based on the sum of the shortest path lengths from the skeleton point to its corresponding sub-point cloud nodes; determining the standard skeleton length value of each skeleton line based on the ratio of the weights of two skeleton endpoints of each skeleton line in the first single-wood skeleton; based on the standard skeleton length value of each skeleton line, deleting the skeleton lines whose skeleton length standard values ​​meet preset conditions in the first single-wood skeleton to obtain the second single-wood skeleton.

[0045] Exemplarily, the ratio of the weights of the two skeleton endpoints of the skeleton line can be the ratio between the smaller value and the larger value of the weights of the two skeleton endpoints of the skeleton line. If the ratio is less than a preset threshold, the skeleton line is deleted from the first single-wood skeleton. If the ratio is greater than the preset threshold, the skeleton line is retained in the first single-wood skeleton. For example, the ratio is 0.19 or 0.20.

[0046] For example, after deleting the skeleton lines whose standard values ​​of skeleton length meet the preset conditions, some redundant points may be further removed and some similar points may be merged to obtain the final simplified second single-wood skeleton.

[0047] Exemplarily, the Douglas-Peucker algorithm with an adaptive threshold is used to remove redundant points inside the skeleton, and the original skeleton is represented by as few points as possible while maintaining the shape of the skeleton line.

[0048] Exemplarily, for a point cloud node with multiple branches, the two branch point cloud nodes with the closest distance among all branches of the point cloud node are merged into a new point cloud node, as shown in the following formula: ; In the formula, , are the coordinates of two adjacent points, , is the weight of two points.

[0049] The skeleton is smoothed as a whole by using the Hermite cubic spline interpolation method to obtain a lightweight and smooth simplified skeleton.

[0050] In one embodiment, based on each skeleton line in the second single-wood skeleton, a point cloud corresponding to each power node in the power network is cylindrically fitted to obtain a first single-wood point cloud model, including: determining an initial neighborhood radius based on the tree breast diameter in the point cloud connection diagram; performing heterometric growth on the initial neighborhood radius based on the weights of the two skeleton endpoints of each skeleton line in the second single-wood skeleton and the weights of the two skeleton endpoints of the first skeleton line connected to the point cloud root node to obtain a neighborhood radius of each skeleton line; for each skeleton line that is not a branch end in the second single-wood skeleton, determining the weight of the skeleton line based on the distance from the point cloud node to the skeleton line within the neighborhood radius of the skeleton line; based on the weight of the skeleton line, performing cylindrical fitting on the point cloud in the skeleton line to obtain a cylinder corresponding to the skeleton line; for the skeleton line that is a branch end in the second single-wood skeleton, using the neighborhood radius of the skeleton line as the radius of the cylinder corresponding to the skeleton line, fitting the point cloud in the skeleton line to obtain a cylinder corresponding to the overhead wire; determining the first single-wood point cloud model based on the cylinder corresponding to each skeleton line in the second single-wood skeleton.

[0051] For example, the tree diameter at breast height in the original point cloud is calculated as the initial neighborhood radius According to the physical characteristics of vegetation growth, the allometric growth equation of neighborhood radius and skeleton line weight is established, as shown in the following formula: ; In the formula, It is The neighborhood radius of the skeleton line, is the initial neighborhood radius, , is the weight of the starting point and the ending point of the first skeleton line connected to the root node, , It is The weights of the start and end points of the skeleton lines.

[0052] Taking the skeleton line as the center, the point cloud within the neighborhood radius of the skeleton line is divided into the corresponding skeleton line. On this basis, the point cloud is re-weighted according to the distance from the point cloud to the skeleton line.

[0053] The weighted least square method is used to fit the cylinder radius to the point cloud within the neighborhood radius of the skeleton line. For the end of the branch at the treetop, the above-mentioned allometric growth equation is used to estimate the cylinder radius to obtain the branch model.

[0054] According to the above implementation, the first single tree point cloud model can be accurately fitted.

[0055] In one embodiment, leaf simulation and coloring are performed on the branch ends of the first single tree point cloud model to obtain a target single tree point cloud model of the power network, including: randomly simulating multiple rectangular patches on the branch ends of the first single tree point cloud model to simulate the leaves in the first single tree point cloud model; based on the branch color and the leaf color, the branches and leaves in the first single tree point cloud model with simulated leaves are respectively colored to obtain the target single tree point cloud model.

[0056] In the step of realism enhancement, leaves and corresponding color information are added to the generated branch model to construct a realistic single tree model.

[0057] Specifically, leaf nodes in a single wood skeleton are found as branch ends, and 10 to 15 rectangular patches in different directions are randomly simulated at the ends of all branches in the trunk model using a spherical structure to simulate the shape of leaves, and the branches and leaves are colored according to their real colors.

[0058] According to the above implementation, leaf simulation and coloring processing can be performed on the branch ends of the first single tree point cloud model to obtain a target single tree point cloud model of the power network.

[0059] Figure 5 It is a structural block diagram of a device for constructing a single-tree point cloud model of a power network transmission line according to an embodiment of the present disclosure.

[0060] like Figure 5 As shown, the construction device of the single point cloud model of the power network transmission line may include: A point cloud connection diagram construction module 510 is used to connect point clouds corresponding to any two adjacent and connected power nodes in the power network based on each transmission line in the power network to obtain a point cloud connection diagram; A point cloud partitioning module 520, configured to partition each point cloud node in the point cloud connection graph into multiple levels based on the length of the shortest path from each point cloud node to a point cloud root node in the point cloud connection graph, so as to obtain a point cloud node set of each level; A point cloud cluster determination module 530 is used to determine mutually connected point clouds in the point cloud node sets of each level based on the point cloud connection graph, so as to obtain connected point cloud clusters of each level; A cross-layer line determination module 540, configured to determine a cross-layer connection line spanning two adjacent layers based on the point cloud connection graph; The skeleton point connection module 550 is used to connect the point cloud centers of the connected point cloud clusters where the two endpoints of each cross-layer connection line are located by skeleton points, so as to obtain a first single-wood skeleton; The point cloud model building module 560 is used to perform cylindrical fitting on the point clouds corresponding to each power node in the power network based on the first single-wood skeleton to obtain a target single-wood point cloud model of the power network.

[0061] In one implementation, the point cloud segmentation module 520 is specifically used to: Determine the maximum value of the shortest path length based on the length of the shortest path from each point cloud node to the point cloud root node in the point cloud connection graph; For each point cloud node in the point cloud connection graph, the level to which the point cloud node belongs is determined based on the ratio of the length of the shortest path from the point cloud node to the point cloud root node to the maximum value of the shortest path length, and the preset total number of levels.

[0062] In one implementation, the skeleton point connection module 550 is specifically used to: Determine a corresponding index label for each of the connected point cloud clusters; Connecting the index labels of the connected point cloud clusters where the two endpoints in each of the cross-layer connection lines are located to obtain an index connection topology graph; Based on the two index label endpoints of each index connection line in the index connection topology graph, the point cloud centers of the corresponding connected point cloud clusters are connected to obtain the first single wood skeleton.

[0063] In one implementation, the point cloud model building module 560 is specifically used to: Optimizing the skeleton points and / or skeleton lines in the first single-wood skeleton to obtain a second single-wood skeleton; Based on each skeleton line in the second single-wood skeleton, a first single-wood point cloud model is obtained for the vegetation point clouds corresponding to the two adjacent and connected power nodes; The branch ends of the first single tree point cloud model are subjected to leaf simulation and coloring processing to obtain a target single tree point cloud model of the power network.

[0064] In one embodiment, the optimizing of the skeleton points and / or skeleton lines in the first single wood skeleton to obtain the second single wood skeleton comprises: For each skeleton point in the first single wooden skeleton, determine the weight of each skeleton point based on the sum of the shortest path lengths from the skeleton point to each corresponding sub-point cloud node; Based on the ratio of the weights of the two skeleton endpoints of each skeleton line in the first single wood skeleton, respectively determine the skeleton length standard value of each skeleton line; Based on the standard values ​​of the skeleton lengths of the skeleton lines, the skeleton lines whose standard values ​​of the skeleton lengths meet preset conditions are deleted from the first single-wood skeleton to obtain the second single-wood skeleton.

[0065] In one embodiment, the first single-wood point cloud model is obtained based on the vegetation point clouds corresponding to the two adjacent and connected power nodes based on the skeleton lines in the second single-wood skeleton, including: Determine an initial neighborhood radius based on the tree diameters at breast height in the point cloud connection graph; Based on the weights of the two skeleton endpoints of each skeleton line in the second single wood skeleton and the weights of the two skeleton endpoints of the first skeleton line connected to the point cloud root node, the initial neighborhood radius is subjected to allometric growth to obtain the neighborhood radius of each skeleton line; For each skeleton line that is not a branch end in the second single tree skeleton, determine the weight of the skeleton line based on the distance from the point cloud node within the neighborhood radius of the skeleton line to the skeleton line; based on the weight of the skeleton line, perform cylindrical fitting on the vegetation point cloud within the skeleton line to obtain a cylinder corresponding to the skeleton line; For the skeleton line belonging to the end of the branch in the second single wood skeleton, the neighborhood radius of the skeleton line is used as the radius of the cylinder corresponding to the skeleton line, and the vegetation point cloud within the skeleton line is fitted to obtain the cylinder corresponding to the stringing line; The first single wood point cloud model is determined based on the cylinders corresponding to the skeleton lines in the second single wood skeleton.

[0066] In one embodiment, the performing leaf simulation and coloring processing on the branch ends of the first single tree point cloud model to obtain the target single tree point cloud model of the power network includes: Randomly simulating a plurality of rectangular patches at the branch ends of the first single tree point cloud model to simulate leaves in the first single tree point cloud model; Based on the branch color and the leaf color, the branches and leaves in the first single tree point cloud model that has simulated leaves are colored respectively, and then added to the target single tree point cloud model.

[0067] For the description of specific functions and examples of each module and submodule of the system in the embodiment of the present invention, reference can be made to the relevant description of the corresponding steps in the above method embodiment, which will not be repeated here.

[0068] In the technical solution of the present invention, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0069] According to an embodiment of the present invention, the present invention also provides a system and a readable storage medium.

[0070] Figure 6 A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0071] like Figure 6 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 to a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0072] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0073] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as a method for constructing a single-wood point cloud model of a power network transmission line. For example, in some embodiments, the method for constructing a single-wood point cloud model of a power network transmission line may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the method for constructing a single-wood point cloud model of a power network transmission line described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute the method for constructing a single-tree point cloud model of a power network transmission line in any other appropriate manner (for example, by means of firmware).

[0074] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0075] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0076] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0077] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0078] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0079] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0080] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present invention can be achieved, and this document does not limit this.

[0081] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for constructing a single-tree point cloud model of a power network transmission line, characterized in that: include: Based on each transmission line in the power network, vegetation point clouds corresponding to any two adjacent and connected power nodes in the power network are connected to obtain a point cloud connection diagram; Based on the length of the shortest path from each point cloud node to a point cloud root node in the point cloud connection graph, each point cloud node in the point cloud connection graph is divided into multiple levels to obtain a point cloud node set of each level; Based on the point cloud connection graph, mutually connected point clouds are respectively determined in the point cloud node sets of each level to obtain connected point cloud clusters of each level; Based on the point cloud connection graph, determining a cross-layer connection line spanning two adjacent layers; For each of the cross-layer connection lines, the point cloud centers of the connected point cloud clusters where two endpoints of the cross-layer connection line are located are respectively connected by skeleton points to obtain a first single-wood skeleton; Based on the first single-tree skeleton, cylindrical fitting is performed on the vegetation point clouds corresponding to the two adjacent and connected power nodes to obtain a target single-tree point cloud model of the power network.

2. The method according to claim 1, characterized in that The dividing each point cloud node in the point cloud connection graph into multiple levels based on the length of the shortest path from each point cloud node to the point cloud root node in the point cloud connection graph includes: Determine the maximum value of the shortest path length based on the length of the shortest path from each point cloud node to the point cloud root node in the point cloud connection graph; For each point cloud node in the point cloud connection graph, the level to which the point cloud node belongs is determined based on the ratio of the length of the shortest path from the point cloud node to the point cloud root node to the maximum value of the shortest path length, and the preset total number of levels.

3. The method according to claim 1, characterized in that: For each of the cross-layer connection lines, the point cloud centers of the connected point cloud clusters where two endpoints of the cross-layer connection line are located are connected by skeleton points to obtain a first single-wood skeleton, including: Determine a corresponding index label for each of the connected point cloud clusters; Connecting the index labels of the connected point cloud clusters where the two endpoints in each of the cross-layer connection lines are located to obtain an index connection topology graph; Based on the two index label endpoints of each index connection line in the index connection topology graph, the point cloud centers of the corresponding connected point cloud clusters are connected to obtain the first single wood skeleton.

4. The method according to claim 1, characterized in that: The method of performing cylindrical fitting on the vegetation point clouds corresponding to the two adjacent and connected power nodes based on the first single-tree skeleton to obtain a target single-tree point cloud model of the power network includes: Optimizing the skeleton points and / or skeleton lines in the first single-wood skeleton to obtain a second single-wood skeleton; Based on each skeleton line in the second single-wood skeleton, a first single-wood point cloud model is obtained for the vegetation point clouds corresponding to the two adjacent and connected power nodes; The branch ends of the first single tree point cloud model are subjected to leaf simulation and coloring processing to obtain a target single tree point cloud model of the power network.

5. The method according to claim 4, characterized in that The step of optimizing the skeleton points and / or skeleton lines in the first single wood skeleton to obtain the second single wood skeleton comprises: For each skeleton point in the first single wooden skeleton, determine the weight of each skeleton point based on the sum of the shortest path lengths from the skeleton point to each corresponding sub-point cloud node; Based on the ratio of the weights of the two skeleton endpoints of each skeleton line in the first single wood skeleton, respectively determine the skeleton length standard value of each skeleton line; Based on the standard values ​​of the skeleton lengths of the skeleton lines, the skeleton lines whose standard values ​​of the skeleton lengths meet preset conditions are deleted from the first single-wood skeleton to obtain the second single-wood skeleton.

6. The method according to claim 4, characterized in that The first single-wood point cloud model is obtained based on the vegetation point clouds corresponding to the two adjacent and connected power nodes based on the skeleton lines in the second single-wood skeleton, including: Determine an initial neighborhood radius based on the tree diameters at breast height in the point cloud connection graph; Based on the weights of the two skeleton endpoints of each skeleton line in the second single wood skeleton and the weights of the two skeleton endpoints of the first skeleton line connected to the point cloud root node, the initial neighborhood radius is subjected to allometric growth to obtain the neighborhood radius of each skeleton line; For each skeleton line that is not a branch end in the second single tree skeleton, determine the weight of the skeleton line based on the distance from the point cloud node within the neighborhood radius of the skeleton line to the skeleton line; based on the weight of the skeleton line, perform cylindrical fitting on the vegetation point cloud within the skeleton line to obtain a cylinder corresponding to the skeleton line; For the skeleton line belonging to the end of the branch in the second single wood skeleton, the neighborhood radius of the skeleton line is used as the radius of the cylinder corresponding to the skeleton line, and the vegetation point cloud within the skeleton line is fitted to obtain the cylinder corresponding to the stringing line; The first single wood point cloud model is determined based on the cylinders corresponding to the skeleton lines in the second single wood skeleton.

7. The method according to claim 4, characterized in that The performing leaf simulation and coloring processing on the branch ends of the first single tree point cloud model to obtain the target single tree point cloud model of the power network includes: Randomly simulating a plurality of rectangular patches at the branch ends of the first single tree point cloud model to simulate leaves in the first single tree point cloud model; Based on the branch color and the leaf color, the branches and leaves in the first single tree point cloud model that has simulated leaves are colored respectively, and then added to the target single tree point cloud model.

8. A device for constructing a single-tree point cloud model of a power network transmission line, characterized in that: include: A point cloud connection diagram construction module is used to connect vegetation point clouds corresponding to any two adjacent and connected power nodes in the power network based on each transmission line in the power network to obtain a point cloud connection diagram; A point cloud partitioning module, for partitioning each point cloud node in the point cloud connection graph into multiple levels based on the length of the shortest path from each point cloud node to a point cloud root node in the point cloud connection graph, so as to obtain a point cloud node set of each level; A point cloud cluster determination module, configured to determine mutually connected point clouds in the point cloud node sets of each level based on the point cloud connection graph, so as to obtain connected point cloud clusters of each level; A cross-layer line determination module, used for determining a cross-layer connection line spanning two adjacent layers based on the point cloud connection graph; A skeleton point connection module is used to connect the point cloud centers of the connected point cloud clusters where the two endpoints of each cross-layer connection line are located by skeleton points, so as to obtain a first single-wood skeleton; The point cloud model construction module is used to perform cylindrical fitting on the vegetation point clouds corresponding to the two adjacent and connected power nodes based on the first single-wood skeleton to obtain a target single-wood point cloud model of the power network.

9. A system for constructing a single-tree point cloud model of a power network transmission line, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.

Images