Tower edge layout generation method, device and system for power unmanned aerial vehicle routing inspection distribution network project

Abstract

The invention provides a tower edge layout generation method, device and system for an electric power unmanned aerial vehicle routing inspection distribution network project, and the method comprises the steps: carrying out the routing inspection of the distribution network project through an unmanned aerial vehicle, and shooting a visible light image of each tower; the method comprises the following steps: performing data processing on tower visible light images acquired by an unmanned aerial vehicle, endowing towers in each image with independent numbers, extracting metadata information in the images corresponding to the towers, and establishing a tower multi-dimensional information table; extracting longitude and latitude information in the metadata information corresponding to each tower image, and marking the position of the tower on a map; identifying a line in each image, and calculating an azimuth angle of the line in combination with yaw angle information in the tower image metadata information; direction angles of adjacent towers are calculated, and the connection relation of lines is judged by combining the line azimuth angles; and generating a tower edge layout according to the tower connection relationship. According to the method, the labor cost of line patrol drawing of the tower edge layout is reduced, and the acceptance efficiency of a distribution network project is improved.

Description

Technical Field

[0001] The present invention relates to the field of pole tower layout generation, and in particular to a method, device and system for generating a pole tower layout for an electric power drone inspection distribution network project. Background Art

[0002] With the advancement of drone technology, the power industry is gradually shifting from traditional ground-based inspections to aerial inspections, and distribution network project acceptance methods are also gradually evolving towards automation and visualization. Traditionally, tower layout mapping in distribution network project acceptance relies primarily on manual field coordinate surveying and topological relationship verification. This method is time-consuming and labor-intensive, and is susceptible to geographical constraints and human resource limitations. Drone inspections, a new inspection model built using autonomous aircraft equipped with multiple sensors and data transmission technology, can rapidly traverse an entire area, overcoming various environmental constraints. The introduction of drone technology can improve data acquisition efficiency through image acquisition, but generating accurate tower layout maps using visible light images captured by drones presents process challenges. Therefore, designing a method for generating tower layout maps using visible light images captured by power drones is crucial for distribution network project acceptance.

[0003] The main problems in existing work are as follows: First, although drone images contain rich metadata information (such as latitude and longitude, attitude angle, etc.), it is impossible to obtain all information by directly reading the image attributes, resulting in the inability to fully utilize information such as attitude angle; Second, when drones shoot tower images, the aircraft yaw angle and the gimbal yaw angle are not always constant, resulting in the actual orientation of the towers in the captured images being inconsistent, and it is impossible to directly determine the actual direction of the line; Third, the current method of determining the connection relationship between towers mainly uses on-site manual judgment, ignoring the mathematical relationship between the line direction and the tower position, resulting in a waste of human resources; Finally, the current generation of tower layout relies heavily on manual annotation, which is difficult to achieve automation and efficiency.

[0004] The problem that needs to be solved urgently by existing technologies is how to use the tower images and metadata information collected by drones during distribution network inspections to determine the tower locations and connection relationships, and then generate a tower layout map to support the acceptance work of distribution network projects. Summary of the Invention

[0005] In response to the main defects of current methods in generating pole tower layout maps using drone images and their metadata information, the present invention designs a method, device and system for generating pole tower layout maps for power drone inspection of distribution network projects, which reduces the labor cost of determining pole tower positions and connection relationships and improves the efficiency of distribution network project acceptance.

[0006] A method for generating a tower layout for a power distribution network project inspected by a UAV includes the following steps:

[0007] Step (1): inspect the towers of the distribution network project by using a drone, and obtain an image of each tower from above;

[0008] Step (2) processing the images of the towers collected in step (1), assigning independent numbers to the towers in each image, extracting metadata information of the towers in the image, and establishing a multi-dimensional information table of the towers including the tower numbers, longitudes and latitudes, and various yaw angles;

[0009] Step (3), based on the longitude and latitude information of the towers extracted in step (2), marking the geographical locations of all towers on the map;

[0010] Step (4), identifying the line in the image of the tower in step (1), combining the yaw angle information extracted in step (2), calculating the azimuth of the line and storing it in the tower multidimensional information table;

[0011] Step (5), based on the tower longitude and latitude information in the tower multidimensional information table established in step (2), traverse all tower points according to the geographical locations of all towers marked in step (3), calculate the direction angle between the current tower point and the adjacent tower points, combine the azimuth matching connection relationship of the line in step (4), and generate a tower connection relationship table;

[0012] Step (6): Based on the tower connection relationship table in step (5), the tower layout of the distribution network project is automatically generated using an undirected graph structure.

[0013] Furthermore, the step (1) specifically includes:

[0014] Keep the drone stationary above the tower, and at the same time, use the camera to shoot an image of the tower from the top in a vertical direction. Use a central composition when shooting, and try to place the main body of the tower in the center of the image. At the same time, the image can clearly and completely observe the direction of the line on the tower.

[0015] Furthermore, the step (2) specifically includes:

[0016] Image metadata extraction: Use a Python script file to read the XMP information of the tower image. The XMP information includes the latitude (GPS Latitude) and longitude (GPS Longitude) at the time of taking the photo, the gimbal yaw angle (Gimbal Yaw Degree, Northeast Celestial Coordinate System, North is True North), and the aircraft yaw angle (Flight Yaw Degree, Northeast Celestial Coordinate System, North is True North) at the time of taking the photo.

[0017] Establishment of a tower information matching table: an independent number is set for each tower in the image, and a multi-dimensional information matching table is established with its corresponding XMP information. The multi-dimensional information table of the tower includes the number, longitude and latitude, and yaw angle.

[0018] Furthermore, the step (3) specifically includes:

[0019] Map platform access: call the GIS map API, create a base map and set the display range to cover the area where the distribution network project is located;

[0020] Batch generation of markers: Read the multi-dimensional information table of towers, traverse each row of data in order of tower numbers, and extract the longitude and latitude coordinates. If the map annotation platform uses a coordinate system other than WGS-84, convert the original longitude and latitude into coordinate values ​​in the target coordinate system through a public coordinate conversion algorithm. Use the standardized longitude and latitude as anchor points to mark the geographic locations of all towers on the map.

[0021] Furthermore, the step (4) specifically includes:

[0022] Image preprocessing: Perform adaptive histogram equalization on the tower image to enhance image contrast and improve the texture clarity of the conductor;

[0023] Line azimuth calculation: Use the target detection algorithm to locate the line in the image, eliminate interference from towers and vegetation, and detect the line azimuth in each tower image:

[0024]

[0025] in,( ) is the coordinate of the center point of the rectangular frame, ( ) is the length and width of the rectangular frame, is the angle between the long side and the positive direction of the x-axis, counterclockwise is a negative angle, clockwise is a positive angle; the line azimuth Converted to the angle based on the positive direction of the y-axis, clockwise is a positive angle, the conversion formula is:

[0026]

[0027] Image spatial orientation alignment: Based on the yaw angle data in the tower multi-dimensional information table, the line azimuth is converted to the true north direction; the shooting direction angle based on the true north of each image is calculated based on the gimbal yaw angle and aircraft yaw angle in the tower multi-dimensional information table :

[0028]

[0029] Based on the true north direction, adjust the line azimuths in all images to the line azimuths based on the true north direction in the same reference system. The conversion formula is:

[0030]

[0031] Line azimuth clustering: Using a clustering algorithm and setting a minimum error of 10°, all line azimuths in each image are automatically divided into azimuth groups with obvious differences, which are regarded as lines with different directions. The median of the azimuths in each group is taken as the line azimuth of that direction and saved in the tower multidimensional information table.

[0032] Furthermore, the step (5) specifically includes:

[0033] Calculation of the direction angle of adjacent towers: traverse all tower points, based on the tower latitude and longitude information in the tower multidimensional information table, retrieve all tower points within a certain distance of the tower point, and solve the direction angle between the two towers based on their spatial position relationship. The coordinates of the two tower points are ( )and( ), its direction angle The calculation formula is:

[0034]

[0035] Determination of pole tower connection relationship: Compare the direction angle between two adjacent pole towers with the corresponding line azimuth angles of the two pole towers in the pole tower multidimensional information table. If the absolute value of the error between the direction angle and the azimuth angle is less than 10°, it is determined that the two pole towers are connected to each other, record the connection relationship of the pole towers, and generate a pole tower connection relationship table.

[0036] Furthermore, the step (6) specifically includes:

[0037] Layout generation: Based on the tower connection relationship table, traverse all tower points and generate lines connecting each tower point with other tower points using an undirected graph structure;

[0038] Output along the layout: Check whether there are any abnormal situations such as crossing of lines between different towers or no connection between towers and other towers in the generated layout, and output the generated tower layout.

[0039] A device for generating a tower layout for a power distribution network project inspected by a UAV, comprising:

[0040] The tower image acquisition module is used to inspect the towers of the distribution network project using drones and obtain images of each tower from above;

[0041] The tower multi-dimensional information table establishment module is used to process the collected tower images, assign independent numbers to the towers in each image, extract the metadata information of the towers in the image, and establish a tower multi-dimensional information table containing the number, tower latitude and longitude, and yaw angle;

[0042] The tower location marking module is used to mark the geographical locations of all towers on the map based on the extracted tower latitude and longitude information;

[0043] A line azimuth acquisition module is used to identify the line in the image of the tower, calculate the azimuth of the line based on the extracted yaw angle information, and store it in the tower multi-dimensional information table;

[0044] The tower connection relationship table generation module is used to traverse all tower points based on the tower longitude and latitude information in the established tower multidimensional information table, calculate the direction angle between the current tower point and the adjacent tower points, match the connection relationship in combination with the azimuth angle of the line, and generate the tower connection relationship table;

[0045] The tower layout generation module is used to automatically generate the tower layout of the distribution network project based on the tower connection relationship table with an undirected graph structure.

[0046] A system for generating a tower layout for an electric power UAV inspection distribution network project, comprising: a computer-readable storage medium and a processor;

[0047] The computer-readable storage medium is used to store executable instructions;

[0048] The processor is used to read the executable instructions stored in the computer-readable storage medium and execute the method for generating a tower layout for an electric power drone inspection distribution network project.

[0049] The present invention aims to generate a layout map of distribution network towers, and realizes metadata analysis of drone images, line topology relationship detection and reasoning, and automated mapping, thus reducing the operating cost of manual line inspection and layout drawing. It can be widely used in the acceptance of digital and automated distribution network projects using power drones. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a flow chart of a method for generating a tower layout for a power distribution network project inspected by a UAV according to an embodiment of the present invention;

[0051] Figure 2 Schematic diagram of the line azimuth of an embodiment of the present invention;

[0052] Figure 3 Schematic diagram of the tower direction angle according to an embodiment of the present invention;

[0053] Figure 4 It is a schematic diagram of the layout of the towers according to an embodiment of the present invention. DETAILED DESCRIPTION

[0054] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0055] See also Figure 1 The embodiment of the present invention provides a method for generating a tower layout for a power distribution network project inspected by a UAV, comprising the following steps:

[0056] Step (1), tower image acquisition: Use a drone to take a tower image, keep the drone stationary above the tower, and at the same time, shoot the top of the tower vertically from above. Use a central composition when shooting, so that the main body of the tower is located in the center of the image. The image can clearly and completely observe the direction of the line on the tower.

[0057] Step (2), obtaining latitude and longitude information and yaw angle information: read the XMP information of the tower image, including latitude (GPSLatitude), longitude (GPSLongitude), gimbal yaw angle (GimbalYawDegree), aircraft yaw angle (FlightYawDegree), etc., set an independent number for each tower in the image, and establish a multi-dimensional information matching table containing the tower number, longitude and latitude and each yaw angle with its corresponding XMP information.

[0058] Step (3), tower coordinate positioning: call the GIS map API, create a base map and set the display range to cover the area where the distribution network project is located, read the tower multidimensional information table, traverse each row of data in the order of the tower identification number, extract the longitude and latitude coordinates (GPS Latitude, GPS Longitude), and use the standardized longitude and latitude as anchor points to generate batch tower position marks on the map.

[0059] Step (4), calculation of the azimuth of the tower line: Adaptive histogram equalization is performed on the tower image to enhance the image contrast and improve the texture clarity of the conductor. The target detection algorithm is used to locate the line in the image, eliminating interference from towers, vegetation, etc., and detecting the azimuth of the line in each tower image. The algorithm output is a rotating box, and the output format is:

[0060]

[0061] in,( ) is the coordinate of the center point of the rectangular frame, ( ) is the length and width of the rectangular frame, The angle between the long side and the positive direction of the x-axis is negative in counterclockwise direction and positive in clockwise direction. Converted to the angle based on the positive direction of the y-axis, clockwise is a positive angle, the conversion formula is:

[0062]

[0063] Based on the yaw angle data in the tower multi-dimensional information table, the line azimuth is converted to the true north direction. The shooting direction angle based on the true north of each image is calculated based on the gimbal yaw angle and aircraft yaw angle in the tower multi-dimensional information table. :

[0064]

[0065] Adjust the line orientations in all images to the same reference frame to ensure comparability and consistency between images. Images should be rotated counterclockwise based on true north. At this time, the true north direction is the reference line azimuth The conversion formula is:

[0066]

[0067] Using the clustering algorithm, with a minimum error of 10°, all line azimuths in each image are automatically divided into groups with significantly different azimuths, which are considered to be lines with different directions. The median of the azimuths in each group is taken as the line azimuth of that direction and saved in the tower multidimensional information table as the line azimuth (e.g. Figure 2 As shown, are the azimuths of the two different lines).

[0068] Step (5): Calculation of the direction angle of adjacent towers and determination of tower connection relationships

[0069] Calculation of the direction angle of adjacent towers: traverse all tower points, based on the spatial position data in the tower multidimensional information table, retrieve all tower points within a certain distance of the tower point, and solve the direction angle between the two towers based on their spatial position relationship (such as Figure 3 As shown), assuming that the coordinates of the two tower points are ( )and( ), its direction angle The calculation formula is:

[0070]

[0071] Determination of the connection relationship between towers: Compare the direction angle between the two towers obtained with the corresponding line azimuth angles of the two towers in the tower multidimensional information table in step (4). If the absolute value of the error between the direction angle and the azimuth angle is less than 10°, it is determined that the two towers are connected to each other, record the connection relationship of the towers, and generate a tower connection relationship table.

[0072] Step (6), generating a tower layout: Based on the tower connection relationship table generated in step (5), traverse all tower points, generate lines connecting each tower point with other tower points in an undirected graph structure, check whether there are abnormal conditions such as crossover of lines between different towers, no connection between towers and other towers in the generated layout, and output the generated tower layout (such as Figure 4 shown).

[0073] In the task of generating along-line maps for distribution network project acceptance, the use of drones to conduct regional inspections and obtain relevant data to assist in the output of results is gradually being promoted and applied. However, the rich data contained in drone images cannot be directly obtained through image attributes, and the yaw angle of drone images is not always constant. The image content lacks comparability and consistency, making it difficult to directly determine the actual direction of the line. As a result, the current method of generating along-line maps relies primarily on manual judgment and annotation. Once the area of ​​the acceptance area increases to a certain extent, it will lead to a significant waste of human resources. Furthermore, along-line map generation is a repetitive process of matching undirected connections between points, which is consistent with the working characteristics of computers. Therefore, designing a method for automatically generating along-line maps of towers is a good choice.

[0074] The present invention first uses drones to take aerial photos of visible light images of towers in distribution network projects, and constructs a multi-dimensional information table of towers containing metadata such as independent numbers, longitude and latitude, and yaw angles, providing a data basis for subsequent topological analysis. Then, we design a logical judgment method for the connection relationship between towers based on tower images and metadata. We use target detection to identify the line azimuth of the image, use geographic coordinates to calculate the direction angle of adjacent towers, traverse through the matching of line azimuth and tower direction angle, and dynamically generate a tower connection relationship table to achieve a dual association between spatial position and electrical connection. Finally, an undirected graph structure is used to abstractly express the tower connection relationship and automatically generate a tower layout map for distribution network projects. This method significantly improves the efficiency of tower layout generation through multi-source data fusion and spatial topology analysis, and has strong applicability to distribution network project acceptance in various terrain scenarios.

[0075] The embodiment of the present invention further provides a device for generating a tower layout for a power distribution network project inspected by a power drone, based on the same inventive concept, comprising the following steps:

[0076] The tower image acquisition module is used to inspect the towers of the distribution network project using drones and obtain images of each tower from above;

[0077] The tower multi-dimensional information table establishment module is used to process the collected tower images, assign independent numbers to the towers in each image, extract the metadata information of the towers in the image, and establish a tower multi-dimensional information table containing the number, tower latitude and longitude, and yaw angle;

[0078] The tower location marking module is used to mark the geographical locations of all towers on the map based on the extracted tower latitude and longitude information;

[0079] A line azimuth acquisition module is used to identify the line in the image of the tower, calculate the azimuth of the line based on the extracted yaw angle information, and store it in the tower multi-dimensional information table;

[0080] The tower connection relationship table generation module is used to traverse all tower points based on the tower longitude and latitude information in the established tower multidimensional information table, calculate the direction angle between the current tower point and the adjacent tower points, match the connection relationship in combination with the azimuth angle of the line, and generate the tower connection relationship table;

[0081] The tower layout generation module is used to automatically generate the tower layout of the distribution network project in an undirected graph structure based on the tower connection relationship table.

[0082] Another embodiment of the present invention provides a system for generating a tower layout for a power UAV inspection distribution network project, comprising: a computer-readable storage medium and a processor;

[0083] The computer-readable storage medium is used to store executable instructions;

[0084] The processor is used to read the executable instructions stored in the computer-readable storage medium and execute the method for generating a tower layout for an electric power drone inspection distribution network project.

[0085] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware.

[0086] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0088] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for generating a tower layout for a power distribution network project using a drone, characterized in that: The following steps are involved: Step (1): inspect the towers of the distribution network project by using a drone, and obtain an image of each tower from above; Step (2) processing the images of the towers collected in step (1), assigning independent numbers to the towers in each image, extracting metadata information of the towers in the image, and establishing a multi-dimensional information table of the towers including the tower numbers, longitudes and latitudes, and various yaw angles; Step (3), based on the longitude and latitude information of the towers extracted in step (2), marking the geographical locations of all towers on the map; Step (4), identifying the line in the image of the tower in step (1), combining the yaw angle information extracted in step (2), calculating the azimuth of the line and storing it in the tower multidimensional information table; Step (5), based on the tower longitude and latitude information in the tower multidimensional information table established in step (2), traverse all tower points according to the geographical locations of all towers marked in step (3), calculate the direction angle between the current tower point and the adjacent tower points, combine the azimuth matching connection relationship of the line in step (4), and generate a tower connection relationship table; Step (6): Based on the tower connection relationship table in step (5), the tower layout of the distribution network project is automatically generated using an undirected graph structure.

2. The method for generating a tower layout for an electric power UAV inspection distribution network project according to claim 1, characterized in that: The step (1) specifically includes: Keep the drone stationary above the tower, and at the same time, use the camera to shoot an image of the tower from the top in a vertical direction. Use a central composition when shooting, and try to place the main body of the tower in the center of the image. At the same time, the image can clearly and completely observe the direction of the line on the tower.

3. The method for generating a tower layout for an electric power UAV inspection distribution network project according to claim 1, characterized in that: The step (2) specifically includes: Image metadata extraction: Use a Python script file to read the XMP information of the tower image. The XMP information includes the latitude (GPS Latitude), longitude (GPS Longitude), gimbal yaw angle (Gimbal Yaw Degree), and aircraft yaw angle (Flight Yaw Degree) at the time of taking the photo. Establishment of a tower information matching table: an independent number is set for each tower in the image, and a multi-dimensional information matching table is established with its corresponding XMP information. The multi-dimensional information table of the tower includes the number, longitude and latitude, and yaw angle.

4. The method for generating a tower layout for an electric power UAV inspection distribution network project according to claim 1, characterized in that: The step (3) specifically includes: Map platform access: call the GIS map API, create a base map and set the display range to cover the area where the distribution network project is located; Batch generation of markers: Read the multi-dimensional information table of the towers, traverse each row of data in the order of the tower identification number, and extract the longitude and latitude coordinates. If the map annotation platform uses a non-WGS-84 coordinate system, use the public coordinate conversion algorithm to convert the original longitude and latitude into the coordinate values ​​in the target coordinate system. Use the standardized longitude and latitude as the anchor point to mark the geographic location of all towers on the map.

5. The method for generating a tower layout for an electric power UAV inspection distribution network project according to claim 1, characterized in that: The step (4) specifically includes: Image preprocessing: Perform adaptive histogram equalization on the tower image to enhance image contrast and improve the texture clarity of the conductor; Line azimuth calculation: Use the target detection algorithm to locate the line in the image, eliminate interference such as towers and vegetation, and detect the line azimuth in each tower image: ； in,( ) is the coordinate of the center point of the rectangular frame, ( ) is the length and width of the rectangular frame, is the angle between the long side and the positive direction of the x-axis, counterclockwise is a negative angle, clockwise is a positive angle; the line azimuth Converted to the angle based on the positive direction of the y-axis, clockwise is a positive angle, the conversion formula is: ； Image spatial orientation alignment: Based on the yaw angle data in the tower multi-dimensional information table, the line azimuth is converted to the true north direction; the shooting direction angle based on the true north of each image is calculated based on the gimbal yaw angle and aircraft yaw angle in the tower multi-dimensional information table : ； Based on the true north direction, adjust the line azimuths in all images to the line azimuths based on the true north direction in the same reference system. The conversion formula is: ； Line azimuth clustering: Using a clustering algorithm and setting a minimum error of 10°, all line azimuths in each image are automatically divided into azimuth groups with obvious differences, which are regarded as lines with different directions. The median of the azimuths in each group is taken as the line azimuth of that direction and saved in the tower multidimensional information table.

6. The method for generating a tower layout for an electric power UAV inspection distribution network project according to claim 1, characterized in that: Said step (5) specifically comprises: Calculation of the direction angle of adjacent towers: traverse all tower points, based on the tower latitude and longitude information in the tower multidimensional information table, retrieve all tower points within a certain distance of the tower point, and solve the direction angle between the two towers based on their spatial position relationship. The coordinates of the two tower points are ( )and( ), its direction angle The calculation formula is: ； Determination of pole tower connection relationship: Compare the direction angle between two adjacent pole towers with the corresponding line azimuth angles of the two pole towers in the pole tower multidimensional information table. If the absolute value of the error between the direction angle and the azimuth angle is less than 10°, it is determined that the two pole towers are connected to each other, record the connection relationship of the pole towers, and generate a pole tower connection relationship table.

7. The method for generating a tower layout for an electric power UAV inspection distribution network project according to claim 1, characterized in that: Said step (6) specifically comprises: Layout generation: Based on the tower connection relationship table, traverse all tower points and generate lines connecting each tower point with other tower points using an undirected graph structure; Output along the layout: Check whether there are any abnormal situations such as crossing of lines between different towers or no connection between towers and other towers in the generated layout, and output the generated tower layout.

8. A tower layout generation device for power UAV inspection of distribution network engineering, characterized in that: include: The tower image acquisition module is used to inspect the towers of the distribution network project using drones and obtain images of each tower from above; The tower multi-dimensional information table establishment module is used to process the collected tower images, assign independent numbers to the towers in each image, extract the metadata information of the towers in the image, and establish a tower multi-dimensional information table containing the number, tower latitude and longitude, and yaw angle; The tower location marking module is used to mark the geographical locations of all towers on the map based on the extracted tower latitude and longitude information; A line azimuth acquisition module is used to identify the line in the image of the tower, calculate the azimuth of the line based on the extracted yaw angle information, and store it in the tower multi-dimensional information table; The tower connection relationship table generation module is used to traverse all tower points based on the tower longitude and latitude information in the established tower multidimensional information table, calculate the direction angle between the current tower point and the adjacent tower points, match the connection relationship in combination with the azimuth angle of the line, and generate the tower connection relationship table; The tower layout generation module is used to automatically generate the tower layout of the distribution network project in an undirected graph structure based on the tower connection relationship table.

9. A system for generating a tower layout for a power distribution network project using a drone, comprising: Computer-readable storage medium and processor; The computer-readable storage medium is used to store executable instructions; The processor is used to read the executable instructions stored in the computer-readable storage medium and execute the method for generating a tower layout for an electric power drone inspection distribution network project according to any one of claims 1 to 7.

Images