Power transmission line wire diameter measuring method and system based on unmanned aerial vehicle image
By combining UAV imagery with stereoscopic measurement and reference object inference, the problem of incorrect conductor type identification in power transmission lines has been solved, enabling high-precision conductor diameter measurement in complex environments and providing an efficient and safe method for power transmission line inspection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- STATE GRID HUNAN ELECTRIC POWER COMPANY LIMITED
- Filing Date
- 2025-12-31
- Publication Date
- 2026-05-15
AI Technical Summary
In existing technologies, errors in identifying the conductor type of transmission lines lead to inaccurate operational analysis results. Manual measurement is costly and poses significant safety risks. Monocular scale inference and stereo measurement methods lack sufficient accuracy in complex environments, and there is a lack of a joint fusion scheme for reference scale inference and stereo measurement.
By acquiring multi-view images using a drone equipped with a camera and laser ranging module, and combining stereo measurement and reference object inference, the first and second estimates of the conductor diameter are calculated using a sub-pixel edge fitting algorithm and a minimum variance weighted fusion algorithm. Consistency checks and data fusion are then performed to output the final conductor diameter result.
It maintains high reliability and accuracy in complex environments, provides an efficient and safe transmission line inspection solution, and overcomes the limitations of a single method.
Smart Images
Figure CN122048811A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent inspection technology for power transmission lines, specifically to a method and system for measuring the conductor diameter of power transmission lines based on UAV imagery. Background Technology
[0002] As one of the most critical components in power transmission engineering, the conductor of a transmission line is fundamental for key operations such as line operation analysis, asset management, sag calculation, and current-carrying capacity assessment. In practical engineering, the conductor types mainly include steel-cored aluminum stranded wires such as LGJ-400 / 50, LGJ-630 / 45, and LGJ-630 / 50, each corresponding to a fixed nominal diameter. Incorrect model identification will affect the results of operation analysis and may lead to safety hazards.
[0003] Traditional methods of conductor type confirmation rely on design data, as-built archives, or manual tower climbing for measurement upon requesting a power outage. However, discrepancies between archived information and actual site conditions are common due to variations in line construction dates, incomplete modification records, and unregistered construction replacements. Manual tower climbing for measurement also suffers from drawbacks such as high power outage costs and significant safety risks, making it unsuitable for large-scale inspection needs.
[0004] The development of UAV inspection technology has made image-based guideline parameter identification possible. Existing methods mainly fall into two categories: monocular scale inference and multi-view stereo measurement. Among them, monocular scale inference is highly dependent on camera distance and strategic scale calibration, and its accuracy is insufficient due to factors such as shooting angle, lighting, and depth of field. Stereo measurement methods improve depth estimation accuracy by constructing a parallax model, but they are still affected by factors such as the attitude perturbation of the UAV platform, the limited baseline length, and the slender characteristics of the guideline, resulting in instability or excessive errors in actual inspection scenarios.
[0005] Insulators, fittings, and other components in power transmission lines are characterized by standardized structures, uniform models, and clearly defined physical dimensions. They are typically clearly visible in UAV imagery, possessing natural "reference points." However, current technology has not yet proposed a scheme to jointly integrate reference point scale inference with stereo measurement, enabling the measurement link to mutually verify each other. Summary of the Invention
[0006] The technical problem to be solved by the present invention is to provide a method and system for measuring the conductor diameter of power transmission lines based on UAV imagery, which overcomes the limitations of a single method by integrating stereo measurement and reference object inference, and enables conductor diameter measurement to maintain high reliability and accuracy in complex environments.
[0007] To solve the above-mentioned technical problems, the technical solution adopted by the present invention includes the following steps: Image acquisition steps: Using a drone equipped with a camera and laser rangefinder module, acquire multi-view images of the power transmission line, and record shooting pose and distance information through onboard sensors; Stereoscopic measurement steps: Distortion and geometric correction are performed on the multi-view images. The sub-pixel edge fitting algorithm is used to obtain the pixel coordinates of the conductor edge to calculate the conductor pixel width. Feature matching is performed on the multi-view images to obtain the disparity. The distance between the conductor and the camera is calculated based on the disparity. The first estimated value of the conductor diameter and its uncertainty are calculated in combination with the conductor pixel width. Reference object measurement steps: Use a drone to acquire a reference image that includes both conductors and insulators, identify the insulator model and obtain its actual size, and calculate a second estimate of the conductor diameter and its uncertainty based on the ratio of the pixel length of the insulator in the image to the pixel length of the conductor diameter, using the actual size of the insulator. Data fusion steps: Perform a consistency test on the first and second estimates. When the test passes, use the minimum variance weighted fusion algorithm to obtain the fused line diameter result.
[0008] As a further improvement of the present invention, the stereoscopic measurement step specifically includes: Lens distortion correction, high-pass enhancement, adaptive filtering and noise reduction, and automatic ROI localization are performed on the multi-view images; The sub-pixel edge fitting algorithm is used to obtain the pixel coordinates of the conductor edge to calculate the conductor pixel width. The specific formula is as follows:
[0009] in, The width is in pixels. , , , These are the pixel coordinates of the conductor edges in adjacent images; Calculate the disparity of the same guide point in adjacent images based on the difference in horizontal position of the same feature point in adjacent images. p ; The distance Z between the camera's optical center and the duct is calculated using the following formula:
[0010] in, The physical focal length of the camera. B The baseline for capturing adjacent images; Based on the principle of similar triangles, the first estimated value of the wire diameter is calculated using the following formula. :
[0011] in, mThe physical size of the pixels in the camera sensor; The uncertainty of the first estimate is calculated using the law of error propagation. The calculation formula is as follows:
[0012] in ， ， These are parallax error, guideline pixel edge error, and baseline error, with corresponding sensitivity coefficients as follows: Parallax p sensitivity : ; For pixel width sensitivity : ; For baseline B sensitivity : .
[0013] As a further improvement of the present invention, the reference measurement step specifically includes: The inspection process involves referring to the insulator image in the reference image, identifying its model based on the steel stamp on the shed, and retrieving the actual dimensions of the insulator model from the insulator database. ; Measuring the pixel length of an insulator in an image pixel width of the conductor diameter The second estimate of the conductor diameter is calculated according to the following formula. : ; Calculate the uncertainty of the second estimate : ; in ， ， The sensitivity coefficients for the actual error of the reference object, the pixel error of the reference object, and the edge error of the wire pixel are respectively: For wire pixels sensitivity : ; True value of insulator sensitivity : ; For insulator pixels sensitivity : .
[0014] As a further improvement of the present invention, the consistency check in the data fusion step adopts the z-score algorithm, and the calculation formula is as follows:
[0015] When |z|≤2, the two estimated values are considered to be consistent.
[0016] As a further improvement of the present invention, the weighted fusion algorithm in the data fusion step is as follows:
[0017] in, For fusion wire diameter.
[0018] As a further improvement to the present invention, it also includes: Model identification steps: Match the fused wire diameter results with the preset wire model database and output the best matching wire model.
[0019] As a further improvement of the present invention, the method of matching the fused wire diameter results with a preset conductor model database and calculating the degree of matching using the following formula is described. :
[0020] in, To find the wire diameter matched from the wire type database, when | Models with |≤2 are output.
[0021] This invention also provides a transmission line conductor diameter measurement system based on UAV imagery, for implementing the above-described transmission line conductor diameter measurement method based on UAV imagery, comprising: The image acquisition module is used to control the drone to acquire multi-view images and reference images; The preprocessing module is used to perform distortion correction and geometric correction on the multi-view image, and to use a sub-pixel edge fitting algorithm to obtain the pixel coordinates of the conductor edge in order to calculate the conductor pixel width. The stereo measurement module is used to perform feature matching on multi-view images to obtain disparity, calculate the distance between the conductor and the camera based on the disparity, and calculate the first estimate of the conductor diameter and its uncertainty by combining the conductor pixel width. The reference object recognition module is used to acquire reference images containing both conductors and insulators via a drone, identify the insulator model and obtain its true size, and calculate a second estimate of the conductor diameter and its uncertainty based on the ratio of the pixel length of the insulator in the image to the pixel length of the conductor diameter using the true size of the insulator. The data fusion module performs a consistency check on the first and second estimates. When the check passes, the minimum variance weighted fusion algorithm is used to obtain the fused line diameter result.
[0022] As a further improvement to the system of the present invention, it also includes: The model matching module is used for conductor model database management and matching identification.
[0023] The present invention also proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for measuring the conductor diameter of a power transmission line based on UAV imagery.
[0024] Compared with the prior art, the advantages of the present invention are as follows: This invention overcomes the limitations of single methods by integrating three-dimensional measurement and reference object inference, enabling conductor diameter measurement to maintain high reliability and accuracy in complex environments, and providing an efficient and safe solution for transmission line inspection. Attached Figure Description
[0025] Figure 1 This is a schematic diagram of the method flow according to an embodiment of the present invention.
[0026] Figure 2 This is a schematic diagram illustrating the execution of the stereoscopic measurement steps in an embodiment of the present invention.
[0027] Figure 3 This is a schematic diagram illustrating the execution of the reference object measurement steps in an embodiment of the present invention. Detailed Implementation
[0028] The present invention will be further described below with reference to the accompanying drawings and specific preferred embodiments, but this does not limit the scope of protection of the present invention.
[0029] The method and technical solution adopted in this embodiment are as follows: Figure 1 As shown, it includes the following steps: Image acquisition steps: Using a drone equipped with a camera and laser rangefinder module, acquire multi-view images of the power transmission line, and record shooting pose and distance information through airborne sensors; typically, control the drone equipped with a telephoto camera and laser rangefinder module to fly within a safe distance of 1-3 meters from the power transmission line. Stereo measurement steps: Distortion and geometric correction are performed on the multi-view images. A sub-pixel edge fitting algorithm is used to obtain the pixel coordinates of the conductor edge to calculate the conductor pixel width. Feature matching is performed on the multi-view images to obtain disparity. The distance between the conductor and the camera is calculated based on the disparity. Finally, the first estimated value of the conductor diameter and its uncertainty are calculated in conjunction with the conductor pixel width. Typically, an airborne real-time dynamic differential positioner (RTK), inertial measurement unit (IMU), and camera intrinsic parameters are used to perform distortion correction on the images. Reference object measurement steps: Use a drone to acquire a reference image that includes both conductors and insulators, identify the insulator model and obtain its actual size, and calculate a second estimate of the conductor diameter and its uncertainty based on the ratio of the pixel length of the insulator in the image to the pixel length of the conductor diameter, using the actual size of the insulator. Data fusion steps: Perform a consistency test on the first and second estimates. When the test passes, use the minimum variance weighted fusion algorithm to obtain the fused line diameter result.
[0030] In specific application examples, the stereoscopic measurement steps specifically include: Lens distortion correction, high-pass enhancement, adaptive filtering and noise reduction, and automatic ROI localization are performed on the multi-view images; The sub-pixel edge fitting algorithm is used to obtain the pixel coordinates of the conductor edge to calculate the conductor pixel width. The specific formula is as follows:
[0031] in, The width is in pixels. , , , These are the pixel coordinates of the conductor edges in adjacent images; Calculate the disparity of the same guide point in adjacent images based on the difference in horizontal position of the same feature point in adjacent images. p ; The distance Z between the camera's optical center and the duct is calculated using the following formula:
[0032] in, The physical focal length of the camera. B The baseline for capturing adjacent images; Based on the principle of similar triangles, the first estimated value of the wire diameter is calculated using the following formula. :
[0033] in, m The physical size of the pixels in the camera sensor; The uncertainty of the first estimate is calculated using the law of error propagation. The calculation formula is as follows: ; in ， ， These are parallax error, guideline pixel edge error, and baseline error, with corresponding sensitivity coefficients as follows: Parallax p sensitivity : ; For pixel width sensitivity : ; For baseline B sensitivity : .
[0034] like Figure 2 The image shown is a schematic diagram of the guide wire taken by the drone when calculating the first estimate, demonstrating the drone flying to the side of the guide wire to take multi-view photos.
[0035] In specific application examples, the reference object measurement step specifically includes: The inspection process involves referring to the insulator image in the reference image, identifying its model based on the steel stamp on the shed, and retrieving the actual dimensions of the insulator model from the insulator database. ; Measuring the pixel length of an insulator in an image pixel width of the conductor diameter The second estimate of the conductor diameter is calculated according to the following formula. : ; Calculate the uncertainty of the second estimate : ; in ， ， The sensitivity coefficients for the actual error of the reference object, the pixel error of the reference object, and the edge error of the wire pixel are respectively: For wire pixels sensitivity : ; True value of insulator sensitivity : ; For insulator pixels sensitivity : .
[0036] like Figure 3 The image shown is a schematic diagram of the reference object and the conductor when the drone is taking pictures of the conductor and the insulator while adjusting the angle of the drone.
[0037] In specific application examples, the consistency check in the data fusion step uses the z-score algorithm, and the calculation formula is as follows:
[0038] When |z|≤2, the two estimated values are considered to be consistent.
[0039] In a specific application example, the weighted fusion algorithm in the data fusion step is as follows:
[0040] in, For fusion wire diameter.
[0041] In specific application examples, it also includes: Model identification steps: Match the fused wire diameter results with the preset wire model database and output the best matching wire model.
[0042] In specific application examples, the fused wire diameter results are matched with a preset conductor model database, and the degree of matching is calculated using the following formula. :
[0043] in, To find the wire diameter matched from the wire type database, when | Models with |≤2 are output.
[0044] This embodiment overcomes the limitations of a single method by integrating three-dimensional measurement and reference object inference, enabling conductor diameter measurement to maintain high reliability and accuracy even in complex environments, and providing an efficient and safe solution for transmission line inspection.
[0045] This embodiment also includes a transmission line conductor diameter measurement system based on UAV imagery, used to implement the above-described transmission line conductor diameter measurement method based on UAV imagery, including: The image acquisition module is used to control the drone to acquire multi-view images and reference images; The preprocessing module is used to perform distortion correction and geometric correction on the multi-view image, and to use a sub-pixel edge fitting algorithm to obtain the pixel coordinates of the conductor edge in order to calculate the conductor pixel width. The stereo measurement module is used to perform feature matching on multi-view images to obtain disparity, calculate the distance between the conductor and the camera based on the disparity, and calculate the first estimate of the conductor diameter and its uncertainty by combining the conductor pixel width. The reference object recognition module is used to acquire reference images containing both conductors and insulators via a drone, identify the insulator model and obtain its true size, and calculate a second estimate of the conductor diameter and its uncertainty based on the ratio of the pixel length of the insulator in the image to the pixel length of the conductor diameter using the true size of the insulator. The data fusion module performs a consistency check on the first and second estimates. When the check passes, the minimum variance weighted fusion algorithm is used to obtain the fused line diameter result.
[0046] In specific application examples, it also includes: The model matching module is used for conductor model database management and matching identification.
[0047] This embodiment also includes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method for measuring the conductor diameter of a power transmission line based on UAV imagery.
[0048] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the process. Figure 1 One or more processes and / or boxes Figure 1The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0049] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of the present invention.
Claims
1. A method for measuring the conductor diameter of a power transmission line based on UAV imagery, characterized in that, include: Image acquisition steps: Using a drone equipped with a camera and laser rangefinder module, acquire multi-view images of the power transmission line, and record shooting pose and distance information through onboard sensors; Stereoscopic measurement steps: Distortion and geometric correction are performed on the multi-view images. The sub-pixel edge fitting algorithm is used to obtain the pixel coordinates of the conductor edge to calculate the conductor pixel width. Feature matching is performed on the multi-view images to obtain the disparity. The distance between the conductor and the camera is calculated based on the disparity. The first estimated value of the conductor diameter and its uncertainty are calculated in combination with the conductor pixel width. Reference object measurement steps: Use a drone to acquire a reference image that includes both conductors and insulators, identify the insulator model and obtain its actual size, and calculate a second estimate of the conductor diameter and its uncertainty based on the ratio of the pixel length of the insulator in the image to the pixel length of the conductor diameter, using the actual size of the insulator. Data fusion steps: Perform a consistency test on the first and second estimates. When the test passes, use the minimum variance weighted fusion algorithm to obtain the fused line diameter result.
2. The method for measuring the conductor diameter of a power transmission line based on UAV imagery according to claim 1, characterized in that, The stereoscopic measurement steps specifically include: Lens distortion correction, high-pass enhancement, adaptive filtering and noise reduction, and automatic ROI localization are performed on the multi-view images; The sub-pixel edge fitting algorithm is used to obtain the pixel coordinates of the conductor edge to calculate the conductor pixel width. The specific formula is as follows: ； in, The width is in pixels. , , , These are the pixel coordinates of the conductor edge in adjacent images; Calculate the disparity of the same guide point in adjacent images based on the difference in horizontal position of the same feature point in adjacent images. p ; The distance Z between the camera's optical center and the duct is calculated using the following formula: ； in, The physical focal length of the camera. B The baseline for capturing adjacent images; Based on the principle of similar triangles, the first estimated value of the wire diameter is calculated using the following formula. : ； in, m The physical size of the pixels in the camera sensor; The uncertainty of the first estimate is calculated using the law of error propagation. The calculation formula is as follows: ； in ， ， These are parallax error, guideline pixel edge error, and baseline error, with corresponding sensitivity coefficients as follows: Parallax p sensitivity : ； For pixel width sensitivity : ； For baseline B sensitivity : 。 3. The method for measuring the conductor diameter of a power transmission line based on UAV imagery according to claim 2, characterized in that, The reference object measurement steps specifically include: The inspection process involves referring to the insulator image in the reference image, identifying its model based on the steel stamp on the shed, and retrieving the actual dimensions of the insulator model from the insulator database. ; Measuring the pixel length of an insulator in an image pixel width of the conductor diameter The second estimate of the conductor diameter is calculated according to the following formula. : ； Calculate the uncertainty of the second estimate : ； in ， ， The sensitivity coefficients for the actual error of the reference object, the pixel error of the reference object, and the edge error of the wire pixel are respectively: For wire pixels sensitivity : ； True value of insulator sensitivity : ； For insulator pixels sensitivity : 。 4. The method for measuring the conductor diameter of a power transmission line based on UAV imagery according to claim 3, characterized in that, The consistency check in the data fusion step uses the z-score algorithm, and the calculation formula is as follows: ； When |z|≤2, the two estimated values are considered to be consistent.
5. The method for measuring the conductor diameter of a power transmission line based on UAV imagery according to claim 3, characterized in that, The weighted fusion algorithm in the data fusion step is: ； in, For fusion wire diameter.
6. The method for measuring the conductor diameter of a power transmission line based on UAV imagery according to claim 5, characterized in that, Also includes: Model identification steps: Match the fused wire diameter results with the preset wire model database and output the best matching wire model.
7. The method for measuring the conductor diameter of a power transmission line based on UAV imagery according to claim 6, characterized in that, The process involves matching the fused wire diameter results with a preset conductor model database, and calculating the degree of matching using the following formula. : ； in, To find the wire diameter matched from the wire type database, when | Models with |≤2 are output.
8. A transmission line conductor diameter measurement system based on UAV imagery, used to implement the transmission line conductor diameter measurement method based on UAV imagery as described in any one of claims 1 to 7, characterized in that, include: The image acquisition module is used to control the drone to acquire multi-view images and reference images; The preprocessing module is used to perform distortion correction and geometric correction on the multi-view image, and to use a sub-pixel edge fitting algorithm to obtain the pixel coordinates of the conductor edge in order to calculate the conductor pixel width. The stereo measurement module is used to perform feature matching on multi-view images to obtain disparity, calculate the distance between the conductor and the camera based on the disparity, and calculate the first estimate of the conductor diameter and its uncertainty by combining the conductor pixel width. The reference object recognition module is used to acquire reference images containing both conductors and insulators via a drone, identify the insulator model and obtain its true size, and calculate a second estimate of the conductor diameter and its uncertainty based on the ratio of the pixel length of the insulator in the image to the pixel length of the conductor diameter using the true size of the insulator. The data fusion module performs a consistency check on the first and second estimates. When the check passes, the minimum variance weighted fusion algorithm is used to obtain the fused line diameter result.
9. A transmission line conductor diameter measurement system based on UAV imagery according to claim 8, characterized in that, Also includes: The model matching module is used for conductor model database management and matching identification.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method for measuring the conductor diameter of a power transmission line based on UAV imagery, as described in any one of claims 1 to 7.