A power transmission line external damage identification method, a storage medium and an electronic device

Abstract

This invention discloses a method, storage medium, and electronic device for identifying external damage to power transmission lines, comprising the following steps: determining a motion region in the current environmental image based on a current environmental image and a historical environmental image of the power transmission line, wherein the historical environmental image is an adjacent environmental image above the current environmental image; performing connected component analysis on the motion region to obtain connected component information for each moving target; for a moving target, obtaining the height information and ground coordinates of the corresponding connected component information; delineating a danger zone for the moving target based on the ground coordinates and the height information; and, in response to any moving target entering the danger zone of the moving target, using the moving target as the identification result and issuing a warning. Through the technical solution of this application, accurate identification results for external damage to power transmission lines can be obtained.

Description

Technical Field

[0001] This invention relates to the field of power system inspection technology, and in particular to a method for identifying external damage to transmission lines, a storage medium, and an electronic device. Background Technology

[0002] Currently, with the improvement of power facilities, transmission lines can deliver electricity to all parts of the country. However, while power facilities are constantly being improved, urban and rural infrastructure construction is also increasing, leading to frequent external damage to transmission lines caused by illegal tree planting, building construction, and other construction work. External object intrusion and damage have become one of the biggest threats and hidden dangers to the safe and stable operation of overhead transmission lines.

[0003] To ensure that completed power transmission lines are not damaged by vehicles, machinery, or other external forces, the identification of external damage to power transmission lines is crucial. Current methods primarily employ deep learning algorithms to detect and identify objects on construction machinery and issue warnings. However, in practice, due to significant background interference in image recognition and a large object detection range, the confidence interval must be expanded to ensure no missed detections. This results in lower accuracy of external damage detection and alarms, and ultimately requires maintenance personnel to inspect a large area of ​​abnormal images, significantly reducing the efficiency and accuracy of the identification process.

[0004] Given the complexity of images of power transmission line scenes, how to invent a method suitable for power transmission line scenes to obtain accurate identification results of external damage prevention of power transmission lines is a key problem that urgently needs to be solved in this field. Summary of the Invention

[0005] The purpose of this invention is to provide a method, storage medium, and electronic device for identifying external damage to power transmission lines, which can obtain accurate identification results for external damage to power transmission lines.

[0006] The technical solution adopted in this invention is as follows:

[0007] A method for identifying external damage to power transmission lines, specifically including the following steps:

[0008] S101: Determine the motion area in the current environmental image based on the current environmental image and the historical environmental image of the transmission line, wherein the historical environmental image is an adjacent environmental image above the current environmental image;

[0009] S102: Perform connected component analysis on the motion region to obtain connected component information for each moving target;

[0010] S103: For a moving target, obtain the height information and ground coordinates of the corresponding connected component information. The height information is the height value of the bounding rectangle of the connected component information, and the ground coordinates are the coordinates of the lowest pixel in the connected component information.

[0011] S104: Delineate the danger zone for the moving target based on the ground coordinates and the altitude information;

[0012] S105: In response to any moving target entering the danger zone of the moving target, the moving target is identified and an early warning is issued.

[0013] The confirmation of the motion area in step S101 specifically includes the following steps:

[0014] The frame difference map is obtained by subtracting the historical environment image from the current environment image, where the historical environment image is the environment image that is adjacent to the current environment image.

[0015] The segmentation threshold of the frame difference map is determined by the maximum inter-class variance method, and the frame difference map is segmented based on the segmentation threshold to obtain a binary map;

[0016] The region consisting of pixels with a value of 1 in the binary image corresponds to the motion region in the current environment image;

[0017] The frame difference map satisfies the following relationship:

[0018]

[0019] in, Image of the current environment. Historical environmental images, This is a frame difference map.

[0020] Step S102 specifically includes the following steps:

[0021] The motion region is expanded and then etched to obtain a pre-processing result.

[0022] Connectivity analysis is performed on the preprocessed results to obtain the connectivity information of each moving target.

[0023] Step S103 specifically includes the following steps:

[0024] Obtain the connected component information of the moving target, and obtain the bounding rectangle of the connected component information;

[0025] The height value of the circumscribed rectangle is used as the height information of the connected component information;

[0026] The center point of the bottom edge of the circumscribed rectangle is taken as the lowest pixel in the connected component information, and the coordinates of the center point of the bottom edge of the circumscribed rectangle correspond to the ground coordinates of the connected component information.

[0027] The delineation of the hazardous area in step S104 specifically includes the following steps:

[0028] A true height mapping model is constructed, wherein the input of the true height mapping model is the ground coordinates and height information of the connected component information, and the output is the true height of the moving target corresponding to the connected component information;

[0029] For a moving target, the height information of the connected component information corresponding to the moving target and the ground coordinates are input into the true height mapping model to obtain the true height of the moving target;

[0030] The safe distance of the moving target in the environmental image is obtained based on the actual height, and the danger zone of the moving target is delineated in the environmental image based on the safe distance. The distance from any point in the danger zone to the power line is less than or equal to the safe distance.

[0031] The true height mapping model is a trained backpropagation (BP) neural network, and the training method of the BP neural network includes:

[0032] The sample is placed in the environment of the power transmission line, and the height information of the connected component information and the ground coordinates of the sample in the environmental image are obtained as a set of training data, and the true height of the sample is used as the label of the training data.

[0033] The training data is input into the BP neural network to output the prediction result, and the mean squared error loss function is calculated based on the prediction result and the label.

[0034] The BP neural network is updated using gradient descent.

[0035] Multiple sets of training data are collected and the BP neural network is iteratively updated until the value of the mean squared error loss function is less than a set value, thus obtaining a trained BP neural network.

[0036] It also includes step S106, updating the danger zone of the moving target, which specifically includes the following steps:

[0037] Acquire a future environment image, which is the next adjacent environment image to the current environment image;

[0038] Obtain the connected component information of each moving target in the future environment image;

[0039] Calculate the true height of the moving target corresponding to the connected component information in the future environmental image based on the ground coordinates and height information of the connected component information;

[0040] For each moving target, the true height of the moving target in the current environment image and the future environment image is determined based on the intersection-union ratio of the connected component information, and the average value of the true height is calculated;

[0041] A safe distance is obtained based on the average value of the actual height, and a danger zone is delineated in the environmental image based on the safe distance to update the danger zone of the moving target.

[0042] The step S104, which involves obtaining the safe distance of the moving target in the environmental image based on its true height, specifically includes the following steps:

[0043] Compare the actual height with the height threshold;

[0044] In response to the actual height being greater than or equal to the height threshold, a preset distance is used as the safe distance;

[0045] In response to the actual height being less than the height threshold, the safe distance is 0.

[0046] A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the device containing the computer-readable storage medium performs the transmission line external damage identification method.

[0047] An electronic device includes a memory and a processor, wherein the memory stores a program that can run on the processor, and the processor executes the program to implement the transmission line external damage identification method.

[0048] The present invention, through the technical solution provided in this application, first obtains the motion region in the current environmental image, and then locates the connected component information of each moving target; calculates the true height of the moving target based on the height information of the connected component information and the ground coordinates, and accurately delineates the danger zone of the moving target based on the true height of the moving target; when any moving target enters the danger zone corresponding to the moving target, an early warning is issued, and the moving target entering the danger zone is used as the external damage prevention identification result, thereby obtaining an accurate external damage prevention identification result for power transmission lines. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a flowchart of the present invention;

[0051] Figure 2 This is a system block diagram of the present invention. Detailed Implementation

[0052] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] It should be understood that when the terms "first," "second," etc., are used in the claims, description, and drawings of this application, they are only used to distinguish different objects and not to describe a specific order. The terms "comprising" and "including" used in the description and claims of this application indicate the presence of the described features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or collections thereof.

[0054] According to a first aspect of this application, this application provides a method for identifying external damage to power transmission lines. Figure 1 This is a flowchart of a transmission line external damage identification method according to an embodiment of this application. Figure 1 As shown, the identification method 100 includes steps S101 to S105, which are described in detail below.

[0055] S101, determine the motion area in the current environmental image based on the current environmental image and the historical environmental image of the transmission line, wherein the historical environmental image is an adjacent environmental image above the current environmental image.

[0056] In one embodiment, a fixed-position image acquisition device is deployed on the power transmission line where external damage detection is required to monitor moving objects around the power transmission line. For example, the image acquisition device can be deployed on the tower of the power transmission line to collect environmental image sequences of the power transmission line.

[0057] Specifically, determining the motion region in the current environmental image based on the current environmental image and the historical environmental image of the transmission line includes: subtracting the historical environmental image from the current environmental image to obtain a frame difference map, wherein the historical environmental image is the environmental image adjacent to the current environmental image; determining the segmentation threshold of the frame difference map using the Otsu's method, and segmenting the frame difference map based on the segmentation threshold to obtain a binary image; the region composed of pixels with a value of 1 in the binary image corresponds to the motion region in the current environmental image.

[0058] The maximum inter-class variance method mentioned above is a well-known technique to those skilled in the art and will not be described in detail here. The frame difference map satisfies the following relationship:

[0059]

[0060] in, Image of the current environment. Historical environmental images, This is a frame difference map.

[0061] S102, perform connected component analysis on the motion region to obtain connected component information for each moving target.

[0062] In one embodiment, multiple moving targets may appear at the same time, so the moving region includes the region information of multiple moving targets, and the region information of each moving target can be extracted using connected component analysis.

[0063] Specifically, performing connected component analysis on the moving region to obtain connected component information for each moving target includes: performing an expansion operation on the moving region followed by an erosion operation to obtain a preprocessing result; and performing connected component analysis on the preprocessing result to obtain connected component information for each moving target.

[0064] In this way, the connectivity information of all moving targets in the current environmental image of the power transmission line is obtained.

[0065] S103, for a moving target, obtain the height information and ground coordinates of the corresponding connected component information. The height information is the height value of the bounding rectangle of the connected component information, and the ground coordinates are the coordinates of the lowest pixel in the connected component information.

[0066] In one embodiment, since the pose of the image acquisition device is fixed, the size and position of the connected component information of a moving target can reflect the height information of the moving target. According to the imaging characteristics of the image acquisition device, which makes objects appear larger when closer and smaller when farther away, in order to accurately calculate the height information of the moving target, it is necessary to obtain the size and position of the connected component information corresponding to the moving target.

[0067] Specifically, for a moving target, obtaining the height information and ground coordinates of the corresponding connected component information includes: obtaining the connected component information of the moving target; obtaining the circumscribed rectangle of the connected component information; using the height value of the circumscribed rectangle as the height information of the connected component information; using the center point of the bottom edge of the circumscribed rectangle as the lowest pixel point in the connected component information; and the coordinates of the center point of the bottom edge of the circumscribed rectangle corresponding to the ground coordinates of the connected component information.

[0068] S104, Delineate the danger zone of the moving target based on the ground coordinates and the altitude information.

[0069] In one embodiment, since the pose of the image acquisition device is fixed, for a moving target, the ground coordinates of its connected component information can reflect the position information of the moving target in the current environmental image, and can be used to characterize the relative positional relationship between the moving target and the image acquisition device; furthermore, the height information of the connected component information corresponds to the height information of the moving target under this positional relationship, and the true height of the corresponding moving target can be calculated by combining the ground coordinates and the height information.

[0070] The moving target can be a pedestrian, a vehicle, or a large machine.

[0071] Specifically, delineating the danger zone of a moving target based on the ground coordinates and the height information includes: constructing a true height mapping model, wherein the input of the true height mapping model is the ground coordinates and height information of the connected component information, and the output is the true height of the moving target corresponding to the connected component information; for a moving target, inputting the height information of the connected component information corresponding to the moving target and the ground coordinates into the true height mapping model to obtain the true height of the moving target; obtaining the safe distance of the moving target in the environmental image based on the true height, and delineating the danger zone of the moving target in the environmental image based on the safe distance, wherein the distance from any point in the danger zone to the power line is less than or equal to the safe distance.

[0072] The true height mapping model is a trained backpropagation (BP) neural network. The training method for the BP neural network includes: placing samples in the environment of a power transmission line; obtaining the height information of the connected components and ground coordinates of the samples in the environmental image as a set of training data; and using the true height of the samples as the label of the training data; inputting the training data into the BP neural network to output a prediction result; calculating the mean squared error loss function based on the prediction result and the label; updating the BP neural network using gradient descent; collecting multiple sets of training data and iteratively updating the BP neural network until the value of the mean squared error loss function is less than a set value, thus obtaining a trained BP neural network. The set value is 0.001.

[0073] In one embodiment, obtaining the safe distance of the moving target in the environmental image based on the actual height includes: comparing the actual height with a height threshold; in response to the actual height being greater than or equal to the height threshold, using a preset distance as the safe distance; and in response to the actual height being less than the height threshold, setting the safe distance to 0. The preset distance is 3.5 meters.

[0074] The height threshold is the height of the power line from the ground. When the actual height is greater than or equal to the height threshold, it indicates that the power line will be touched. Therefore, only moving targets with an actual height greater than or equal to the height threshold will be in danger zones.

[0075] In this way, the danger zone of each moving target is obtained.

[0076] S105, in response to any moving target entering the dangerous area of ​​the moving target, the moving target is identified as the result and an early warning is issued.

[0077] In one embodiment, responding to any moving target entering the danger zone of the moving target includes: for any moving target, obtaining the ground coordinates of the connected component information corresponding to the moving target; and in response to the ground coordinates being any pixel point within the danger zone, determining that the moving target has entered the danger zone of the moving target. When any moving target enters the danger zone of the moving target, it indicates that the moving target poses a risk of touching the power transmission line, and the moving target is used as the identification result to issue a timely warning.

[0078] In other optional embodiments, to improve the accuracy of external damage prevention identification, the method further includes: acquiring a future environmental image, wherein the future environmental image is the next adjacent environmental image to the current environmental image; obtaining connected component information for each moving target in the future environmental image; calculating the true height of the moving target corresponding to the connected component information in the future environmental image based on the ground coordinates and height information of the connected component information; for each moving target, confirming the true height of the moving target in the current environmental image and the future environmental image based on the intersection-union ratio of the connected component information, and calculating the average value of the true height; obtaining a safety distance based on the average value of the true height, and delineating a danger zone in the environmental image based on the safety distance, thereby updating the danger zone of the moving target. This avoids calculation errors of the true height caused by relying solely on the current environmental image, ensuring the accuracy of external damage prevention identification.

[0079] The step of determining the true height of the moving target in the current and future environmental images based on the intersection-union ratio (IUR) of connected component information includes: for the connected component information of a moving target in the current environmental image, calculating the IUR of the connected component information with all connected component information in the future environmental image; taking the connected component information corresponding to the maximum IUR in the future environmental image as the target connected component information, and the true height corresponding to the target connected component information is the true height of the moving target in the future environmental image.

[0080] The technical principles and implementation details of the transmission line external damage prevention identification method of this application have been described above through specific embodiments. The technical solution provided by this application first acquires the moving regions in the current environmental image, and then locates the connected component information of each moving target; based on the height information of the connected component information and the ground coordinates, the true height of the moving target is calculated, and the danger zone of the moving target is accurately delineated based on the true height of the moving target; when any moving target enters the danger zone corresponding to the moving target, an early warning is issued, and the moving target entering the danger zone is taken as the external damage prevention identification result, thus obtaining an accurate external damage prevention identification result for the transmission line.

[0081] Furthermore, to avoid calculation errors in the true height caused by relying solely on the current environmental image, the danger zone of each moving target is updated based on environmental images acquired at future times, thereby improving the accuracy of external damage prevention identification.

[0082] This application also provides a computer-readable storage medium and an electronic device (not shown). The computer-readable storage medium stores computer-readable instructions, which are executed by a processor in the electronic device to implement the transmission line external damage identification method described in any of the above embodiments.

[0083] The integrated unit implemented as a software functional module can be stored in a computer-readable storage medium. This software functional module, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, computer equipment, or network device, etc.) or processor to execute portions of the transmission line icing monitoring method described in the various embodiments of this application.

[0084] When modules / units integrated into an electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware devices. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above.

[0085] The computer program includes computer program code, which may be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory, and other memory.

[0086] Furthermore, the computer-readable storage medium may primarily include a stored program area and a stored data area, wherein the stored program area may store the operating system, an application program required for at least one function, etc.; and the stored data area may store data created based on the use of blockchain nodes, etc.

[0087] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, only one arrow is used, but this does not indicate that there is only one bus or one type of bus. The bus is configured to implement communication between the memory and at least one processor, etc.

[0088] According to a second aspect of this application, this application also provides a transmission line external damage identification system. Figure 2 This is a block diagram of a power transmission line external damage prevention identification system according to an embodiment of this application. Figure 2 As shown, the device 50 includes a processor and a memory. The memory stores computer program instructions, which, when executed by the processor, implement the transmission line external damage identification method according to the first aspect of this application. The device also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. Their configuration and functions are known in the art and will not be described further here.

[0089] In this application, the aforementioned memory can be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store desired information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device. Any application or module described in this application can be implemented using computer-readable / executable instructions that can be stored or otherwise retained by such a computer-readable medium.

[0090] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0091] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

[0092] In the description of this invention, it should be noted that directional terms such as "center", "lateral", "longitudinal", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", and "counterclockwise" indicate the orientation and positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. They should not be construed as limiting the specific protection scope of this invention.

[0093] It should be noted that the terms "comprising" and "having" and any variations thereof in the specification and claims of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or device.

[0094] Note that the above description is merely a preferred embodiment and application of the technical principles of the present invention. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the specific embodiments described herein, and may include many other effective embodiments without departing from the concept of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for identifying external damage to transmission lines, characterized in that, include: S101: Determine the motion area in the current environmental image based on the current environmental image and the historical environmental image of the transmission line, wherein the historical environmental image is an adjacent environmental image above the current environmental image; S102: Perform connected component analysis on the motion region to obtain connected component information for each moving target; S103: For a moving target, obtain the height information and ground coordinates of the corresponding connected component information. The height information is the height value of the bounding rectangle of the connected component information, and the ground coordinates are the coordinates of the lowest pixel in the connected component information. S104: Delineate the danger zone of the moving target based on the ground coordinates and the altitude information; the danger zone delineation in step S104 specifically includes the following steps: Construct a true height mapping model, wherein the input of the true height mapping model is the ground coordinates and height information of the connected component information, and the output is the true height of the moving target corresponding to the connected component information; For a moving target, the height information of the connected component information corresponding to the moving target and the ground coordinates are input into the true height mapping model to obtain the true height of the moving target; The safe distance of the moving target in the environmental image is obtained based on the actual height, and the danger zone of the moving target is delineated in the environmental image based on the safe distance. The distance from any point in the danger zone to the power line is less than or equal to the safe distance. The true height mapping model is a trained backpropagation (BP) neural network, and the training method of the BP neural network includes: The sample is placed in the environment of the power transmission line, and the height information and ground coordinates of the sample in the connected component information in the environment image are obtained. These are used as a set of training data, and the actual height of the sample is used as the label of the training data. The training data is input into the BP neural network to output the prediction result, and the mean squared error loss function is calculated based on the prediction result and the label. The BP neural network is updated using gradient descent. Multiple sets of training data are collected and the BP neural network is iteratively updated until the value of the mean squared error loss function is less than a set value, thus obtaining a trained BP neural network. S105: In response to any moving target entering the danger zone of the moving target, the moving target is identified as the result and an early warning is issued; S106: Update the danger zone for moving targets, specifically including the following steps: Acquire a future environment image, which is the next adjacent environment image to the current environment image; Obtain the connected component information of each moving target in the future environment image; Calculate the true height of the moving target corresponding to the connected component information in the future environmental image based on the ground coordinates and height information of the connected component information; For each moving target, the true height of the moving target in the current environment image and the future environment image is determined based on the intersection-union ratio of the connected component information, and the average value of the true height is calculated; A safe distance is obtained based on the average value of the actual height, and a danger zone is delineated in the environmental image based on the safe distance to update the danger zone of the moving target.

2. The external damage identification method for a power transmission line according to claim 1, characterized by, The confirmation of the motion area in step S101 specifically includes the following steps: The frame difference map is obtained by subtracting the historical environment image from the current environment image, where the historical environment image is the environment image that is adjacent to the current environment image. The segmentation threshold of the frame difference map is determined by the maximum inter-class variance method, and the frame difference map is segmented based on the segmentation threshold to obtain a binary map; The region consisting of pixels with a value of 1 in the binary image corresponds to the motion region in the current environment image; The frame difference map satisfies the following relationship: ； wherein, is a current environment image, is a historical environment image, is a frame difference map.

3. The external damage identification method for a power transmission line according to claim 1, characterized by, Step S102 specifically includes the following steps: The motion region is expanded and then etched to obtain a pre-processing result. Connectivity analysis is performed on the preprocessed results to obtain the connectivity information of each moving target.

4. The external damage identification method for a power transmission line according to claim 1, characterized by, Step S103 specifically includes the following steps: First, obtain the connected component information of the moving target, and then obtain the bounding rectangle of the connected component information; The height value of the circumscribed rectangle is used as the height information of the connected component information; The center point of the bottom edge of the circumscribed rectangle is taken as the lowest pixel in the connected component information, and the coordinates of the center point of the bottom edge of the circumscribed rectangle correspond to the ground coordinates of the connected component information.

5. The external damage identification method for power transmission lines according to claim 1, characterized in that, The step S104, which involves obtaining the safe distance of the moving target in the environmental image based on its true height, specifically includes the following steps: Compare the actual height with the height threshold; In response to the actual height being greater than or equal to the height threshold, a preset distance is used as the safe distance; In response to the actual height being less than the height threshold, the safe distance is 0.

6. A computer-readable storage medium having stored thereon a computer program, characterized in that, When the computer program is executed by the processor, it causes the device containing the computer-readable storage medium to perform the transmission line external damage identification method according to any one of claims 1-5.

7. An electronic device, characterized in that, include: A memory and a processor, wherein the memory stores a program that can run on the processor, and the processor executes the program to implement the transmission line external damage identification method as described in any one of claims 1-5.

Images