Cross-over recognition method based on aerial power channel image data

By taking aerial photography of the image data of the power channel, we can build a three-dimensional model and identify the arrangement method of transmission lines, solving the problem of difficult to determine the cross-span situation in power grid management, achieving automatic judgment of safety hazards, and promoting the digital transformation of power grid management.

CN113033445BActive Publication Date: 2024-11-08GUANGDONG POWER GRID CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202110354619.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-03-31
Publication Date
2024-11-08
Estimated Expiration
2041-03-31

AI Technical Summary

Technical Problem

During the digital transformation of power grid management, it is difficult for elevated tower line management to determine the cross-crossing of transmission lines through the management system, resulting in on-site inspections, which violates the principle of digital management.

Method used

A three-dimensional model is constructed by aerial photography of the image data of the power channel, and the arrangement of transmission lines is identified, so as to judge the cross-span distance between transmission lines and avoid on-site inspections.

Benefits of technology

It realizes the automatic judgment of safety hazards of power channels without on-site inspection, and promotes the digital transformation of the power grid management system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113033445B_ABST
    Figure CN113033445B_ABST
Patent Text Reader

Abstract

The present invention discloses a method for identifying crossovers based on aerial photography of electric power channel image data, wherein the method for identifying crossovers includes acquiring aerial photography image data; generating a three-dimensional model according to image files at different angles in the aerial photography image data; identifying the arrangement of transmission lines in the target electric power channel according to the three-dimensional model; and determining the crossover distance of the transmission lines according to the arrangement. The present invention generates a three-dimensional model of the target electric power channel in the management system through image files at different angles in the aerial photography image data. Since the three-dimensional model can reflect the positional relationship between the transmission lines in space, the arrangement of the transmission lines is used to identify the crossover distance between any two transmission lines, thereby automatically determining whether there are safety hazards in the target electric power channel, without the need for maintenance personnel to conduct on-site inspections, and promoting the digital transformation of the power grid management system.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a crossover recognition method based on aerial power channel image data. Background Art

[0002] In order to realize the digital transformation of power grid management, various equipment in the existing network are transformed into intelligent ones and entered into the management system. At the same time, the connection architecture of various equipment in the existing network is also registered to form a complete digital power grid in the management system.

[0003] During the digital transformation process, there are certain difficulties in the line management of elevated towers. Although the connection relationship between each device can be known in the management system, the actual crossing and spanning situation of the transmission lines in the local area cannot be obtained through the connection relationship between the devices in the management system. This brings certain difficulties to the digital management of the power grid and requires maintenance personnel to conduct on-site inspections, which is not in line with the principles of digital management. Summary of the invention

[0004] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0005] An embodiment of the present invention provides a method for identifying crossings and spans based on aerial power channel image data. A three-dimensional image is obtained through aerial power channel image data, so that the distance of crossings and spans between transmission lines can be judged based on the three-dimensional image. There is no need for maintenance personnel to conduct on-site inspections, thereby promoting the digital transformation of power grid management systems.

[0006] In a first aspect, an embodiment of the present invention provides a crossover identification method, comprising:

[0007] Acquire aerial image data, wherein the image data includes image files of at least three angles of the target power channel, and the angle difference between any two angles of the at least three angles is not less than 60 degrees;

[0008] Generate a three-dimensional model based on image files of different angles in the aerial image data;

[0009] Identifying the arrangement of power transmission lines in the target power channel according to the three-dimensional model;

[0010] The crossing distance of the transmission lines is determined according to the arrangement.

[0011] The crossing identification method provided in the first aspect of the embodiment of the present invention has at least the following beneficial effects: a three-dimensional model of the target power channel is generated in the management system through image files of different angles in the aerial image data. Since the three-dimensional model can reflect the positional relationship between the transmission lines in space, the arrangement of the transmission lines is used to identify the crossing distance between any two transmission lines, thereby automatically judging whether there are safety hazards in the target power channel, eliminating the need for maintenance personnel to conduct on-site inspections, and promoting the digital transformation of the power grid management system.

[0012] In some embodiments, the acquiring of aerial image data includes:

[0013] Get the transmission port information of the aerial photography drone;

[0014] Pulling the image file according to the transmission port information;

[0015] The image file belonging to the target power channel is determined according to the GPS information in the image file.

[0016] In some embodiments, generating a three-dimensional model according to image files at different angles in the aerial image data includes:

[0017] Obtaining angle information of the image file;

[0018] Selecting first angle information for constructing a three-dimensional coordinate system according to the angle information;

[0019] A three-dimensional model of the target power channel is constructed according to a first image file corresponding to the first angle information.

[0020] In some embodiments, constructing the three-dimensional model of the target power channel according to the first image file corresponding to the first angle information includes:

[0021] Preprocessing the first image file to enhance the clarity of each frame of image;

[0022] Selecting at least three feature points in the first image file, at least one of the feature points being located on an image corresponding to a power transmission line of the target power channel;

[0023] A plurality of frames of images are extracted from the first image file according to the selected feature points, and a three-dimensional model is generated according to the extracted images.

[0024] In some embodiments, the preprocessing of the first image file to enhance the clarity of each frame of image includes:

[0025] Gray-scaling the first image file;

[0026] De-noising is performed on the grayscaled first image file.

[0027] In some embodiments, identifying the arrangement of power transmission lines in the target power channel according to the three-dimensional model includes:

[0028] Identifying first direction information of a first power transmission line in the target power channel in the three-dimensional model;

[0029] searching for an adjacent second transmission line according to the first direction information and determining second direction information of the second transmission line;

[0030] The arrangement of the power transmission lines in the target power channel is determined according to the first direction information and the second direction information.

[0031] In some embodiments, determining the crossing distance of the transmission lines according to the arrangement method includes:

[0032] Performing spatial sectioning on the arrangement to obtain a series of section views, wherein the section views contain at least one cross section of a power transmission line;

[0033] Obtain a first distance between any two transmission lines in the cross-sectional view;

[0034] If the first distance is greater than a threshold distance of the crossing, an alarm is issued.

[0035] In a second aspect, an embodiment of the present invention further provides a crossing identification system based on aerial power channel image data, comprising:

[0036] An acquisition unit, used to acquire aerial image data, wherein the image data includes image files of at least three angles of the target power channel, and the angle difference between any two angles of the at least three angles is not less than 60 degrees;

[0037] A generating unit, used for generating a three-dimensional model according to image files of different angles in the aerial image data;

[0038] an identification unit, configured to identify an arrangement of power transmission lines in the target power channel according to the three-dimensional model;

[0039] A judgment unit is used to determine the crossing distance of the transmission line according to the arrangement method.

[0040] In a third aspect, an embodiment of the present invention further provides a device for identifying cross-spanning based on aerial power channel image data, comprising at least one processor and a memory for communicating with the at least one processor; 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 so that the at least one processor can execute the method for identifying cross-spanning based on aerial power channel image data as described in the first aspect.

[0041] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the cross-span identification method based on aerial power channel image data described in the first aspect.

[0042] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the examples of the present invention, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0044] Figure 1 is an overall method flow chart of the cross-span identification method provided by an embodiment of the present invention;

[0045] Figure 2 is a flow chart of a method for obtaining aerial image data provided by an embodiment of the present invention;

[0046] Figure 3 is a flow chart of a method for constructing a three-dimensional model based on angle information provided by an embodiment of the present invention;

[0047] Figure 4 is a flow chart of a method for generating a three-dimensional model through feature points provided by an embodiment of the present invention;

[0048] Figure 5 is a flow chart of a method for preprocessing a first image file provided by an embodiment of the present invention;

[0049] Figure 6 is a flow chart of a method for determining a transmission line arrangement mode provided by an embodiment of the present invention;

[0050] Figure 7 It is a flow chart of a method for spatially sectioning an arrangement provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0052] In the description of the present invention, "several" means one or more, "more" means more than two, "greater than", "less than", "exceed" etc. are understood as not including the number itself, and "above", "below", "within" etc. are understood as including the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0053] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0054] During the digital transformation of the power grid management system, it is necessary to build connection relationships among the entire network's equipment. However, these connection relationships are virtual in the system and cannot reflect the layout of the transmission lines in actual scenarios. As a result, it is impossible to know the safety of crossings between transmission lines. Therefore, there are still unresolved pain points in the digital transformation of the management system, and manual on-site inspections are often required, which is time-consuming and labor-intensive.

[0055] Based on this, an embodiment of the present invention provides a method for identifying crossings and spans based on aerial power channel image data, constructs a three-dimensional model based on aerial power channel image data, and determines the crossings and spans between transmission lines by identifying the arrangement of transmission lines in the three-dimensional model.

[0056] The embodiments of the present invention are further described below in conjunction with the accompanying drawings.

[0057] Reference Figure 1 The embodiment of the present invention provides a method for identifying cross-overs based on aerial power channel image data, including but not limited to the following steps S100, S200, S300 and S400.

[0058] Step S100, obtaining aerial image data, the image data including image files of at least three angles of the target power channel, and the angle difference between any two angles of the at least three angles is not less than 60 degrees;

[0059] By using drones and other equipment to take aerial photos of the target power channel in the air, aerial image data for generating a three-dimensional model can be obtained. Since each frame of the image file obtained by aerial photography is a two-dimensional plane, if the drone takes photos along the direction of the target power channel, it is obviously impossible to obtain multi-angle image files of the target power channel. Therefore, the drone is required to take photos of the target power channel at multiple angles, such as taking photos along the circumference of the target power channel, or taking photos back and forth on both sides of the target power channel. Since the aerial image files may be continuous, and even the image files of the target power channel at different angles are in the same image file, they can be divided according to different angles so that the divided image files represent different angles.

[0060] It is understandable that in order to obtain a more accurate three-dimensional model, the angle difference between any two angles of the aerial photography is required to be no less than 60 degrees. Based on the relationship between the three-dimensional space coordinates, such an angle value method can enclose a three-dimensional space, form a three-dimensional shooting of the target power channel, and then obtain an accurate three-dimensional model. It is worth noting that the angle of the embodiment of the present invention can be used as a reference for a certain frame of the image file, and the angle of other image files can be inferred based on the moving path of the drone and other equipment.

[0061] Step S200, generating a three-dimensional model according to image files of different angles in the aerial image data.

[0062] Based on the image file obtained above, a three-dimensional model of the target power channel is generated by automatic construction. For example, the power grid management system has built-in three-dimensional modeling software, etc., which analyzes and judges the acquired image file, thereby automatically generating a three-dimensional model. It can be understood that there are many three-dimensional modeling methods, and the embodiment of the present invention does not limit the three-dimensional modeling method. Those skilled in the art can choose different three-dimensional modeling methods according to the actual aerial image data, which will not be expanded here one by one.

[0063] Step S300, identifying the arrangement of power transmission lines in the target power channel according to the three-dimensional model;

[0064] Step S400, determining the crossing distance of the transmission lines according to the arrangement method.

[0065] The three-dimensional model can be used to obtain information such as the shape and position of each transmission line in the target power channel. Therefore, by identifying these transmission lines, the layout of the transmission lines can be organized. Since the layout of the transmission lines is known, the crossing and spanning conditions between the transmission lines can be determined when the safe distance for crossing and spanning is known.

[0066] Based on the above steps S100 to S400, a specific implementation scheme is described in detail below.

[0067] Reference Figure 2 In step S100, obtaining aerial image data can be achieved by following the steps below:

[0068] Step S110, obtaining the transmission port information of the aerial photography drone;

[0069] Step S120, pulling the image file according to the transmission port information;

[0070] Step S130, determining the image file belonging to the target power channel according to the GPS information in the image file.

[0071] If the aerial photography drone adopts the method of real-time data transmission, the image file can be pulled through the transmission port of the aerial photography drone by the power grid management system. The transmission port can be an IP port, so that the power grid management system can obtain the image file sent back by the aerial photography drone in real time, and promptly judge the shooting quality of the aerial photography drone, so as to adjust the working status of the aerial photography drone at any time during the aerial photography process. It can be understood that in order to determine which power channel the target power channel in the image file corresponds to, it is necessary to read the GPS information in the image file, match the corresponding power channel in the power grid management system based on the GPS information, and the image files corresponding to the GPS information within a certain range around the target power channel belong to the target power channel. Since aerial photography may be continuous, when the position represented by the GPS information of the image file offsets the position range of the target power channel, it is considered that this part of the image file does not belong to the target power channel.

[0072] Of course, aerial photography drones can also use non-real-time data transmission methods. In this case, the data captured by the aerial photography drone during operation will be stored locally, and then transferred from the local storage to the power grid management system. The power grid management system then determines the ownership of the image file based on the GPS information.

[0073] Reference Figure 3 In order to select the required information from multiple image files to build a three-dimensional model, the image files need to be processed in some way. Therefore, the method for generating a three-dimensional model in step S200 may specifically include the following steps:

[0074] Step S210, obtaining angle information of the image file;

[0075] Step S220, selecting first angle information for constructing a three-dimensional coordinate system according to the angle information;

[0076] Step S230: constructing a three-dimensional model of the target power channel according to the first image file corresponding to the first angle information.

[0077] For image files, different angle information can be obtained for different shooting angles of the target power channel. This angle information can be obtained in a variety of ways. For example, by referring to the gyroscope and motion trajectory in the aerial photography drone, the orientation of the current shooting position relative to the photographed object can be obtained. Since not every image file with angle information is suitable for building a three-dimensional model, some screening is required in step S220. For example, repeated shooting angles or shooting angles with little difference can be discarded to reduce the amount of calculation for three-dimensional modeling. According to step S100, it can be seen that at least multiple shooting angles with an angle difference of not less than 60 degrees are required. After screening, the first angle information is obtained, and the three-dimensional model can be constructed according to the first image file corresponding to the first angle information.

[0078] Reference Figure 4 In step S230, after the first image file is screened, how to construct a three-dimensional model according to the image content in the first image file can refer to the following steps:

[0079] Step S231, pre-processing the first image file to enhance the clarity of each frame of image;

[0080] Step S232, selecting at least three feature points in the first image file, at least one of the feature points being located on an image corresponding to a power transmission line of a target power channel;

[0081] Step S233: extracting a plurality of frames of images from the first image file according to the selected feature points, and generating a three-dimensional model according to the extracted images.

[0082] First, the first image file is preprocessed to obtain an image with high definition that is easy for the system to recognize; then, since the first image file already has a suitable shooting angle, the same feature points must exist in the first image file. By selecting the feature points in the first image file, three-dimensional coordinates can be constructed according to the images taken around the feature points; finally, several representative frames of images are extracted from the multiple frames of images in the first image file, and a three-dimensional model is automatically generated based on the feature points on these several frames of images.

[0083] Reference Figure 5 In the above step S231, the preprocessing of the first image file can be achieved by the following steps:

[0084] Step S2311, graying the first image file;

[0085] Step S2312, performing denoising on the grayscaled first image file.

[0086] There are many ways of preprocessing, and the embodiments of the present invention select some of the preprocessing methods for illustration. For the image files shot in color, grayscale is performed to represent the color information of the points on the image with a uniform grayscale value. Then the grayscale image is processed by denoising technology, such as median filtering, which is essentially a nonlinear filtering method based on statistical sorting theory. Its basic principle is to sort the grayscale values ​​of all pixels in the window range centered on a certain pixel in the image, and then assign the middle value of the grayscale sequence to the central pixel. It has a good denoising effect and also has a good effect in overcoming the blur effect caused by filtering out noise.

[0087] Among them, the three-dimensional model construction method of the transmission line in the aerial image can be implemented by referring to the following algorithm. The first step is to detect the straight line based on LSD. LSD is based on local analysis and uses the straight line detection algorithm to achieve a faster computing speed. For the model of the transmission cable, which is a local straight line, it is more appropriate to use the LSD straight line detection algorithm based on the high-resolution image. Specifically, the aerial image is convoluted and downsampled by Gaussian template to smooth and reduce the noise of the image. The gradient amplitude and direction of the pixel points are calculated for the smoothed and denoised image, and the gradient of the aerial image is calculated using the Sobel operator. The pixel points with large gradient changes in the aerial image are judged according to the threshold method. Then, these pixels with large gradient changes are sorted according to the gradient size and the straight line region growth analysis is performed, and then the point density is calculated based on the NFA value and the straight line enhancement processing of the rectangular area is performed; the second step is to use an unsupervised clustering algorithm to find a combination of straight line segments that can form a straight line in the aerial image according to the slope; the third step is to filter out unnecessary targets in the image, such as trees, roads, etc., so that the final three-dimensional model is comprehensive and accurate.

[0088] Reference Figure 6 The identification of the arrangement of the power transmission lines in step S300 can be achieved by the following steps:

[0089] Step S310, identifying first direction information of a first transmission line in a target power channel in the three-dimensional model;

[0090] Step S320, searching for an adjacent second transmission line according to the first direction information and determining second direction information of the second transmission line;

[0091] Step S330: determining the arrangement of the power transmission lines in the target power channel according to the first direction information and the second direction information.

[0092] A transmission line (first transmission line) is randomly selected in the target power channel and its direction is determined. Since there are generally other transmission lines near the first transmission line, the second transmission line adjacent to the first transmission line is searched from the first transmission line. There may be multiple second transmission lines, and the arrangement method representing the relationship between the first transmission line and the second transmission line is obtained by combination. Of course, after finding the second transmission line, other adjacent transmission lines can also be searched from the second transmission line in the above manner, and then combined to form a larger arrangement method.

[0093] Reference Figure 7 Step S400 can be specifically implemented by the following steps:

[0094] Step S410, spatially sectioning the arrangement to obtain a series of section views, wherein the section views contain at least one cross section of a power transmission line;

[0095] Step S420, obtaining a first distance between any two transmission lines in the cross-sectional view;

[0096] Step S430: If the first distance is greater than the crossing threshold distance, an alarm is issued.

[0097] The arrangement is spatially sectioned to obtain a series of section diagrams containing multiple transmission lines in the arrangement. In order to ensure the correct sectioning method, the section diagram must contain at least one cross section of the transmission line, so that the distance of the crossing can be determined from the cross section. Select any two transmission lines in the section diagram to obtain the first distance between the two on the same plane. Based on the size of this distance, it can be determined whether there is an unreasonable crossing between the two transmission lines.

[0098] Through the above steps of the embodiment of the present invention, a three-dimensional model of the target power channel is generated in the management system through image files of different angles in the aerial image data. Since the three-dimensional model can reflect the positional relationship between the transmission lines in space, the arrangement of the transmission lines is used to identify the crossing distance between any two transmission lines, thereby automatically judging whether there are safety hazards in the target power channel, eliminating the need for maintenance personnel to conduct on-site inspections, and promoting the digital transformation of the power grid management system.

[0099] The embodiment of the present invention further provides a crossing identification system based on aerial power channel image data, comprising:

[0100] An acquisition unit, used to acquire aerial image data, the image data including image files of at least three angles of the target power channel, and the angle difference between any two angles of the at least three angles is not less than 60 degrees;

[0101] A generating unit, used for generating a three-dimensional model according to image files of different angles in the aerial image data;

[0102] An identification unit, used to identify the arrangement of power transmission lines in the target power channel according to the three-dimensional model;

[0103] The judgment unit is used to determine the crossing distance of the transmission line according to the arrangement mode.

[0104] An embodiment of the present invention also provides a cross-span identification device based on aerial power channel image data, including at least one processor and a memory for communicating with the at least one processor; 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 so that the at least one processor can execute the aforementioned cross-span identification method.

[0105] Take the example that the control processor and memory in the cross-span identification device can be connected by a bus. The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk memory, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the control processor, and these remote memories may be connected to the cross-span identification device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0106] The embodiment of the present invention further provides a computer-readable storage medium, which stores computer-executable instructions. The computer-executable instructions are executed by one or more control processors. For example, the computer-executable instructions are executed by the control processors to enable the one or more control processors to execute the crossover identification method in the above method embodiment. For example, the above described Figure 1 Steps S100 to S400 of the method, Figure 2 Steps S110 to S130 of the method, Figure 3 Steps S210 to S230 of the method, Figure 4 Steps S231 to S233 of the method, Figure 5 Steps S2311 to S2312 of the method, Figure 6 Steps S310 to S330 of the method and Figure 7 Method steps S410 to S430.

[0107] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0108] It will be appreciated by those skilled in the art that all or some of the steps and systems in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or transient medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0109] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the above-mentioned implementation mode. Technical personnel familiar with the field can also make various equivalent deformations or substitutions without violating the spirit of the present application. These equivalent deformations or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. A method for identifying crossovers based on aerial power channel image data, comprising: Acquire aerial image data, wherein the image data includes image files of at least three angles of the target power channel, and the angle difference between any two angles of the at least three angles is not less than 60 degrees; Generate a three-dimensional model based on image files of different angles in the aerial image data; Identifying the arrangement of power transmission lines in the target power channel according to the three-dimensional model; Determine the crossing distance of the transmission line according to the arrangement mode; The generating of the three-dimensional model according to the image files at different angles in the aerial image data comprises: Acquire angle information of the image file; select first angle information for constructing a three-dimensional coordinate system according to the angle information; construct a three-dimensional model of the target power channel according to a first image file corresponding to the first angle information; The constructing the three-dimensional model of the target power channel according to the first image file corresponding to the first angle information includes: Preprocessing the first image file to enhance the clarity of each frame of the image; selecting at least three feature points in the first image file, at least one of the feature points being located on an image corresponding to a power transmission line of the target power channel; extracting a plurality of frames of images from the first image file according to the selected feature points, and generating a three-dimensional model according to the extracted images; The determining the crossing distance of the transmission lines according to the arrangement method includes: The arrangement is spatially sectioned to obtain a series of section diagrams, wherein the section diagrams contain at least a cross section of a transmission line; based on the cross sections, a first distance between any two transmission lines in the section diagrams is obtained; if the first distance is greater than a threshold distance of a crossing, an alarm is issued.

2. The crossover identification method according to claim 1, characterized in that: The obtaining of aerial image data includes: Get the transmission port information of the aerial photography drone; Pulling the image file according to the transmission port information; The image file belonging to the target power channel is determined according to the GPS information in the image file.

3. The crossover identification method according to claim 1, characterized in that: The preprocessing of the first image file to enhance the clarity of each frame of image includes: Gray-scaling the first image file; De-noising is performed on the grayscaled first image file.

4. The crossover identification method according to claim 1, characterized in that: The identifying, according to the three-dimensional model, an arrangement of power transmission lines in the target power channel includes: Identifying first direction information of a first power transmission line in the target power channel in the three-dimensional model; searching for an adjacent second transmission line according to the first direction information and determining second direction information of the second transmission line; The arrangement of the power transmission lines in the target power channel is determined according to the first direction information and the second direction information.

5. A crossing identification system based on aerial power channel image data, characterized in that: include: An acquisition unit, used to acquire aerial image data, wherein the image data includes image files of at least three angles of the target power channel, and the angle difference between any two angles of the at least three angles is not less than 60 degrees; A generating unit, used for generating a three-dimensional model according to image files of different angles in the aerial image data; an identification unit, configured to identify an arrangement of power transmission lines in the target power channel according to the three-dimensional model; A determination unit, used to determine the crossing distance of the transmission line according to the arrangement mode; The generating unit is specifically used for: Acquire angle information of the image file; select first angle information for constructing a three-dimensional coordinate system according to the angle information; construct a three-dimensional model of the target power channel according to a first image file corresponding to the first angle information; The constructing the three-dimensional model of the target power channel according to the first image file corresponding to the first angle information includes: Preprocessing the first image file to enhance the clarity of each frame of image; Selecting at least three feature points in the first image file, at least one of the feature points being located on an image corresponding to a power transmission line of the target power channel; extracting a plurality of frames of images from the first image file according to the selected feature points, and generating a three-dimensional model according to the extracted images; The judging unit is specifically used for: The arrangement is spatially sectioned to obtain a series of section diagrams, wherein the section diagrams contain at least one cross section of a transmission line; a first distance between any two transmission lines in the section diagrams is obtained; and an alarm is issued if the first distance is greater than a threshold distance of a crossover.

6. A crossing identification device based on aerial power channel image data, characterized in that: comprising at least one processor and a memory for communicatively connecting to the at least one processor; 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 so that the at least one processor can execute the crossing and spanning identification method based on aerial power channel image data as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the crossing and spanning identification method based on aerial power channel image data as described in any one of claims 1 to 4.

Citation Information

Patent Citations

  • Method for wirelessly monitoring cross spanning of electric transmission line and device

    CN104266686A

  • Three-dimensional virtual technology-based power grid facility layout planning result visualization method

    CN105808662A

  • Association expansion method and device for keyword

    CN107862015A

  • Ice coverage detection method and device for electric transmission circuit

    CN109870108A

  • Line patrol method, system and device for fixed-wing unmanned aerial vehicle in complex geographical environment

    CN111244822A