Method and device for determining distance between power transmission line and external hazard source, medium and product

Abstract

The invention discloses a method and device for determining the distance between a power transmission line and an external hazard source, a medium and a product, and relates to the field of distance calculation, and the method comprises the steps: obtaining a binocular image pair and millimeter wave radar data of a to-be-detected target; adopting a binocular stereo matching algorithm to extract parallax information of the binocular image pair; further determining depth information of the binocular image pair; further respectively determining three-dimensional point clouds of the to-be-detected target; fusing the three-dimensional point cloud with the transmission line radar data and the external hazard source radar data; carrying out target detection on any image in the binocular image pair by adopting a YOLOV5 algorithm to obtain a detection result of the power transmission line and a detection result of an external hazard source; determining the distance between the power transmission line and the external hazard source according to the detection result of the power transmission line, the detection result of the external hazard source and the fusion data; the distance between the power transmission line and the external hazard source can be accurately determined, the safety performance of electric power facilities is improved, and resource waste is reduced.

Description

Technical Field

[0001] This application relates to the field of distance measurement, and in particular to a method, device, medium and product for determining the distance between a power transmission line and an external hazard source. Background Technology

[0002] Currently, the scale and capacity of power grids are gradually expanding and increasing. Transmission lines bear the heavy responsibility of long-distance power transmission, and their condition is crucial to the safe and stable operation of the entire power system. In the field of power transmission, due to the complexity of equipment and the diversity of operating environments, ensuring the safe operation of equipment and the safety of personnel is particularly important. The vast majority of transmission lines are deployed in suburban areas, using overhead lines for power transmission. Transmission line cables are made of steel wire and multi-strand aluminum stranded wire. During long-distance transmission line condition monitoring and maintenance at power construction sites, it has been found that due to the long distance and large field of view, the cable coverage area is small, the pixel ratio is low, and the contained feature information is limited. This leads to poor results and low accuracy in long-distance cable detection, resulting in a high false alarm rate in safety monitoring.

[0003] Currently, power facility monitoring equipment generally uses single cameras for image acquisition. However, single-camera systems have some significant limitations: they collect limited information, suffer from scale uncertainty when calculating depth using translation, and cannot provide depth information for the captured images. This makes it impossible to accurately determine the distance between transmission lines and external hazards (such as cranes, aerial work platforms, and excavators). Depth information is crucial for determining the distance between external hazards and transmission lines. The lack of this information prevents transmission line monitoring products from accurately detecting the actual distance between potential safety hazards and the conductors and transmission lines, resulting in numerous invalid alarms. This not only wastes valuable monitoring resources but may also cause genuine safety hazards to be overlooked.

[0004] Therefore, based on the above problems, there is an urgent need to provide a new method for determining the distance between transmission lines and external hazards, which can accurately calculate the distance between transmission lines and external hazards, improve the safety performance of power facilities, and reduce resource waste. Summary of the Invention

[0005] The purpose of this application is to provide a method, device, medium, and product for determining the distance between a power transmission line and an external hazard source, which can accurately calculate the distance between the power transmission line and the external hazard source, improve the safety performance of power facilities, and reduce resource waste.

[0006] To achieve the above objectives, this application provides the following solution:

[0007] In a first aspect, this application provides a method for determining the distance between a transmission line and an external hazard source. The method for determining the distance between a transmission line and an external hazard source includes:

[0008] Acquire binocular image pairs and millimeter-wave radar data of the target to be detected; the target to be detected includes: power transmission lines and external hazard sources; the binocular image pairs include images of the target to be detected acquired from different locations; the millimeter-wave radar data includes: power transmission line radar data and external hazard source radar data;

[0009] A binocular stereo matching algorithm is used to extract the disparity information of the binocular image pair; and the depth information of the binocular image pair is determined based on the disparity information.

[0010] Based on the depth information of the binocular image pair, the three-dimensional point cloud of the target to be detected is determined respectively;

[0011] The 3D point cloud is fused with power transmission line radar data and external hazard source radar data respectively to obtain fused data; the fused data includes power transmission line fused data and external hazard source fused data;

[0012] The YOLOv5 algorithm is used to perform target detection on any image in the binocular image pair to obtain the detection results of the transmission line and the detection results of the external hazard source;

[0013] Based on the detection results of the transmission line, the detection results of the external hazard source, and the fused data, the distance between the transmission line and the external hazard source is determined.

[0014] Optionally, acquiring the binocular image pair and millimeter-wave radar data of the target to be detected specifically includes:

[0015] Use a binocular camera to acquire binocular image pairs of the target to be detected;

[0016] 4D millimeter-wave radar is used to acquire radar data of power transmission lines and radar data of external hazard sources.

[0017] Optionally, the step of extracting disparity information of the binocular image pair using a binocular stereo matching algorithm and determining the depth information of the binocular image pair based on the disparity information specifically includes:

[0018] Using the formula d=U L -U R Determine the disparity information of the binocular image pair;

[0019] Using formula Determine the depth information of the stereo image pair;

[0020] Where d represents the disparity information of the binocular image, U L U represents the x-coordinate of the left eye image.R Z represents the x-coordinate of the right eye image, Z represents the depth information of the binocular image, f represents the pixel focal length of the binocular camera, and b represents the distance between the two cameras of the binocular camera.

[0021] Optionally, the fusion of the 3D point cloud with transmission line radar data and external hazard source radar data to obtain fused data specifically includes:

[0022] Convert the coordinates of the 3D point cloud to world coordinates to obtain the coordinate-transformed 3D point cloud;

[0023] The coordinate-transformed 3D point cloud is fused with transmission line radar data and external hazard source radar data using the Kalman filter algorithm to obtain fused data.

[0024] Optionally, the process of converting the coordinates of the 3D point cloud to world coordinates to obtain the coordinate-transformed 3D point cloud specifically includes:

[0025] Using formula formula and formula Determine the 3D point cloud after coordinate transformation;

[0026] Where (X,Y,Z) are the coordinates of the 3D point cloud after coordinate transformation, (x,y) are the coordinates of the stereo image, (u,v) are the pixel coordinates, and (c) are the pixel coordinates. x ,c y ) are the coordinates of the principal point, f x f is the focal length of the camera on the x-axis. y Z represents the focal length of the camera on the y-axis, and Z represents the depth information of the binocular image.

[0027] Optionally, determining the distance between the transmission line and the external hazard source based on the detection results of the transmission line, the detection results of the external hazard source, and the fused data specifically includes:

[0028] Based on the detection results and fusion data of the transmission lines, the three-dimensional coordinates of the fusion data center points of the transmission lines are determined;

[0029] Based on the detection results of external hazard sources and the fused data of external hazard sources, determine the three-dimensional coordinates of the fused data center point of the external hazard sources;

[0030] The distance between the transmission line and the external hazard source is determined based on the three-dimensional coordinates of the fusion data center point of the transmission line and the three-dimensional coordinates of the fusion data center point of the external hazard source.

[0031] Optionally, determining the distance between the transmission line and the external hazard source based on the three-dimensional coordinates of the fusion data center point of the transmission line and the three-dimensional coordinates of the fusion data center point of the external hazard source specifically includes:

[0032] Using formula Determine the distance D between the transmission line and the external hazard source;

[0033] Where (x1,y1,z1) are the three-dimensional coordinates of the converged data center point of the transmission line, and (x2,y2,z2) are the three-dimensional coordinates of the converged data center point of the external hazard source.

[0034] In a second aspect, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for determining the distance between a transmission line and an external hazard source as described above.

[0035] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for determining the distance between a transmission line and an external hazard source as described above.

[0036] Fourthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method for determining the distance between a transmission line and an external hazard source as described above.

[0037] According to the specific embodiments provided in this application, this application has the following technical effects:

[0038] This application provides a method, device, medium, and product for determining the distance between a power transmission line and an external hazard source. By combining a binocular stereo matching algorithm and the YOLOv5 algorithm to process binocular image pairs, it improves ranging accuracy while exhibiting higher adaptability and robustness. Since the binocular stereo matching algorithm is greatly affected by lighting conditions and target texture information, while 4D millimeter-wave radar is not affected by weather and obstructed areas, this application further integrates millimeter-wave radar data, making it applicable to complex or dynamically changing environments, further improving adaptability and robustness, and enhancing ranging accuracy. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a flowchart illustrating a method for determining the distance between a transmission line and an external hazard source in one embodiment of this application.

[0041] Figure 2 This is a flowchart illustrating the method for determining the distance between a transmission line and an external hazard source in one embodiment of this application.

[0042] Figure 3 This is a flowchart of time synchronization in one embodiment of this application;

[0043] Figure 4 This is a schematic diagram of spatial calibration in one embodiment of this application. Detailed Implementation

[0044] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0045] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0046] In one exemplary embodiment, such as Figure 1 and Figure 2 As shown, a method for determining the distance between a transmission line and an external hazard source is provided, including the following S1-S6. Wherein:

[0047] S1: Acquire binocular image pairs and millimeter-wave radar data of the target to be detected.

[0048] Existing visual ranging methods are mainly divided into monocular visual ranging and binocular visual ranging. Compared with binocular visual ranging, monocular visual ranging has less information and suffers from scale uncertainty when calculating depth using translation. Therefore, this application uses binocular visual ranging, that is, using a binocular camera to acquire binocular image pairs of the target to be detected, wherein the target to be detected includes: power transmission lines and external hazards. The binocular image pairs include images of the target to be detected acquired from different locations.

[0049] Since binocular visual ranging is significantly affected by lighting conditions and target texture information, and suffers from inaccurate parallax estimation in obstructed areas, this application introduces millimeter-wave radar data. 4D millimeter-wave radar is unaffected by weather and obstructed areas, effectively addressing these issues. This application utilizes 4D millimeter-wave radar to acquire millimeter-wave radar data, including power transmission line radar data and external hazard source radar data.

[0050] As a specific embodiment, this application performs joint calibration on the binocular camera and the 4D millimeter-wave radar before acquiring binocular image pairs and millimeter-wave radar data. The joint calibration includes temporal calibration and spatial calibration.

[0051] Time calibration uses a soft calibration method. The specific calibration process is as follows: The stereo camera's time is synchronized with Beijing time. Then, the 4D millimeter-wave radar is activated to acquire millimeter-wave radar data of the target. The stereo camera acquires stereo image pairs of the current frame and timestamps the image pairs. After acquisition, the stereo image pairs of the target and the millimeter-wave radar data are output. Then, the maximum time difference algorithm is used for synchronization again. The synchronization process is as follows: Figure 3 As shown, S Ti The maximum time difference is represented by Ti, which is the time interval between the stereo image pair to be matched and the millimeter-wave radar data.

[0052] Spatial calibration uses the homography transformation method. In the image domain, the homography transformation method represents the mapping relationship between the position of a target object in reality and its image pixel position; it can also be used to represent the mapping relationship between two planes. In this application, the coordinate system of the stereo camera is set as (X... C ,Y C Z C The radar coordinate system of the 4D millimeter-wave radar is (X... W ,Y W Z W If the coordinates of the millimeter-wave radar data determined by the 4D millimeter-wave radar are (x... r ,y r ,z r The target pixel coordinates acquired by the binocular camera are (u,v), and the spatial calibration process for both is as follows: Figure 4 As shown.

[0053] As can be seen from the principle of the homography transformation method, the conversion relationship between calibrating a 4D millimeter-wave radar and a stereo camera is the mapping relationship between target points on the calibrated 4D millimeter-wave radar plane and corresponding target points on the pixel plane. According to the principle of the homography transformation method, the relationship between the 4D millimeter-wave radar acquisition plane and the stereo image pixel plane can be obtained as follows:

[0054]

[0055] Where s is the scale factor, M is the intrinsic parameter matrix of the stereo camera, and T is the transformation matrix.

[0056] t is the translation matrix, R is the rotation matrix, (x i ,y i ,z i Let t represent the coordinates of the 3D point cloud. [R t] is a 3×4 matrix with 6 degrees of freedom. R has 9 parameters, but due to the orthogonal constraint of the rotation matrix, it only has 3 degrees of freedom. Expanding the relationship between the 4D millimeter-wave radar acquisition plane and the binocular image pixel plane yields the following formula:

[0057]

[0058] Where (x,y,z) are the coordinates of the 3D point cloud, h pq Let p be the row number of [R t] and q be the column number of [R t].

[0059] After further processing, the following formula can be obtained:

[0060]

[0061] The spatial calibration results can be obtained by solving the above equations.

[0062] S2: Use a binocular stereo matching algorithm to extract the disparity information of the binocular image pair; and determine the depth information of the binocular image pair based on the disparity information.

[0063] As a specific embodiment, this application performs temporal and spatial calibration on the binocular camera, acquires binocular image pairs using the calibrated binocular camera, and performs stereo correction on the binocular image pairs. The stereo-corrected binocular image pairs must be processed by a binocular stereo matching algorithm to obtain disparity information. In the process of the binocular stereo matching algorithm, the primary task is to find corresponding points in the left and right eye images, and then process each matching point to finally determine the disparity information of the binocular image pairs.

[0064] The stereo matching algorithm proposed in this application employs the IGEV++ algorithm. The IGEV++ algorithm combines the complementary advantages of filtering and iterative optimization. It utilizes IGEV++ to construct a Multi-range Geometric Coding Structure (MGEV), thereby enabling the encoding of coarse-grained geometric information with large differences in ill-posed regions (such as occluded or textureless regions) and large differences, while also encoding fine-grained geometric information with small differences and minor details. This demonstrates that the IGEV++ algorithm can obtain high-quality and high-precision disparity information in complex scenes. Furthermore, the IGEV++ algorithm innovatively incorporates multi-range and multi-granular geometric features. After indexing, these features are input into Convolutional Gated Recurrent Units (ConvGRUs) to iteratively update the disparity information, resulting in more accurate disparity data.

[0065] Specifically, the formula for calculating the disparity information of a binocular image pair is as follows:

[0066] d=U L -U R .

[0067] Where d represents the disparity information of the binocular image, U L U represents the x-coordinate of the left eye image. R The x-coordinate of the right eye image.

[0068] The depth information of the binocular image pair is determined based on the disparity information. The formula for calculating the depth information is as follows:

[0069]

[0070] Where Z represents the depth information of the binocular image, f represents the pixel focal length of the binocular camera, and b represents the distance between the two cameras of the binocular camera.

[0071] S3: Based on the depth information of the binocular image pair, determine the three-dimensional point cloud of the target to be detected.

[0072] S4: The 3D point cloud is fused with the transmission line radar data and the external hazard source radar data respectively to obtain fused data; the fused data includes the transmission line fused data and the external hazard source fused data.

[0073] S4 specifically includes:

[0074] S41: Convert the coordinates of the 3D point cloud to world coordinates to obtain the 3D point cloud after coordinate transformation.

[0075] Specifically, the conversion of 3D point cloud coordinates to world coordinates is based on the joint calibration of the binocular cameras, and the conversion formula is as follows:

[0076]

[0077] Where (X,Y,Z) are the coordinates of the 3D point cloud after coordinate transformation, and (x,y) are the coordinates of the stereo image. (u,v) are pixel coordinates, f x f is the focal length of the camera on the x-axis. y Let be the focal length of the camera on the y-axis. (c x ,c y ) is the coordinate of the main point, and K is the intrinsic parameter matrix.

[0078] S42: The coordinate-transformed 3D point cloud is fused with the transmission line radar data and the external hazard source radar data using the Kalman filter algorithm to obtain fused data.

[0079] When extracting disparity information of binocular image pairs using a binocular stereo matching algorithm, it is affected by weather and texture information of the target to be detected. By fusing millimeter-wave radar data obtained from 4D millimeter-wave radar, the 3D point cloud can be corrected to make it more accurate.

[0080] S5: Use the YOLOv5 algorithm to perform target detection on any image in the binocular image pair to obtain the detection results of the transmission line and the detection results of external hazards.

[0081] The YOLOv5 algorithm performs target detection on any image in a stereo image pair, obtaining the bounding box of the target to be detected. The bounding box of the power transmission line is the detection result of the power transmission line, and the bounding box of the external hazard is the detection result of the external hazard.

[0082] S6: Determine the distance between the transmission line and the external hazard source based on the detection results of the transmission line, the detection results of the external hazard source, and the fused data.

[0083] S6 specifically includes:

[0084] S61: Based on the detection results of the transmission lines and the fusion data of the transmission lines, determine the three-dimensional coordinates of the fusion data center point of the transmission lines.

[0085] Specifically, the three-dimensional coordinates of the fusion data center point of the transmission line are determined based on the two-dimensional coordinates of the center point of the boundary frame of the transmission line.

[0086] S62: Based on the detection results of external hazards and the fused data of external hazards, determine the three-dimensional coordinates of the fused data center point of the external hazards.

[0087] Specifically, the three-dimensional coordinates of the fusion data center point of the external hazard source are determined based on the two-dimensional coordinates of the center point of the boundary box of the external hazard source.

[0088] S63: Determine the distance between the transmission line and the external hazard source based on the three-dimensional coordinates of the integrated data center point of the transmission line and the three-dimensional coordinates of the integrated data center point of the external hazard source.

[0089] Specifically, the formula for calculating the distance D between the transmission line and the external hazard source is as follows:

[0090]

[0091] Where (x1,y1,z1) are the three-dimensional coordinates of the converged data center point of the transmission line, and (x2,y2,z2) are the three-dimensional coordinates of the converged data center point of the external hazard source.

[0092] This application significantly improves ranging efficiency by combining the data stability of 4D millimeter-wave radar with the high precision of binocular imaging, particularly excelling in complex environmental conditions. Secondly, because 4D millimeter-wave radar is unaffected by weather or obstructed areas, it effectively compensates for the shortcomings of binocular imaging in these aspects, thus ensuring the stability and reliability of the technical solution in various complex environments. While lidar performs well in certain applications, its high price and complex maintenance requirements pose significant cost pressures for large-scale deployments. In contrast, 4D millimeter-wave radar is not only more affordable but also has a relatively simple hardware structure, making it easy to integrate and maintain. This significantly reduces the cost of this application and improves the overall system's economics.

[0093] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device stores distance determination data between transmission lines and external hazards. The I / O interfaces of the computer device are used for exchanging information between the processor and external hazards. The communication interface of the computer device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for determining the distance between a transmission line and an external hazard.

[0094] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0095] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0096] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0097] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0098] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0099] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0100] 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.

[0101] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for determining the distance between a power transmission line and an external hazard source, characterized in that, The method for determining the distance between the transmission line and the external hazard source includes: Acquire binocular image pairs and millimeter-wave radar data of the target to be detected; the target to be detected includes: power transmission lines and external hazard sources; the binocular image pairs include images of the target to be detected acquired from different locations; the millimeter-wave radar data includes: power transmission line radar data and external hazard source radar data; A binocular stereo matching algorithm is used to extract the disparity information of the binocular image pair; and the depth information of the binocular image pair is determined based on the disparity information. Based on the depth information of the binocular image pair, the three-dimensional point cloud of the target to be detected is determined respectively; The 3D point cloud is fused with power transmission line radar data and external hazard source radar data respectively to obtain fused data; the fused data includes power transmission line fused data and external hazard source fused data; The YOLOv5 algorithm is used to perform target detection on any image in the binocular image pair to obtain the detection results of the transmission line and the detection results of the external hazard source; Based on the detection results of the transmission line, the detection results of the external hazard source, and the fused data, the distance between the transmission line and the external hazard source is determined.

2. The method for determining the distance between a transmission line and an external hazard source according to claim 1, characterized in that, The acquisition of the binocular image pairs and millimeter-wave radar data of the target to be detected specifically includes: Use a binocular camera to acquire binocular image pairs of the target to be detected; 4D millimeter-wave radar is used to acquire radar data of power transmission lines and radar data of external hazard sources.

3. The method for determining the distance between a transmission line and an external hazard source according to claim 1, characterized in that, The binocular stereo matching algorithm is used to extract the disparity information of the binocular image pair; And determine the depth information of the binocular image pair based on the disparity information, specifically including: Using the formula d=U L -U R Determine the disparity information of the binocular image pair; Using formula Determine the depth information of the stereo image pair; Where d represents the disparity information of the binocular image, U L U represents the x-coordinate of the left eye image. R Z represents the x-coordinate of the right eye image, Z represents the depth information of the binocular image, f represents the pixel focal length of the binocular camera, and b represents the distance between the two cameras of the binocular camera.

4. The method for determining the distance between a transmission line and an external hazard source according to claim 1, characterized in that, The process of fusing the 3D point cloud with transmission line radar data and external hazard source radar data to obtain fused data specifically includes: Convert the coordinates of the 3D point cloud to world coordinates to obtain the coordinate-transformed 3D point cloud; The coordinate-transformed 3D point cloud is fused with transmission line radar data and external hazard source radar data using the Kalman filter algorithm to obtain fused data.

5. The method for determining the distance between a transmission line and an external hazard source according to claim 4, characterized in that, The process of converting the coordinates of a 3D point cloud to world coordinates to obtain a coordinate-transformed 3D point cloud specifically includes: Using formula formula and formula Determine the 3D point cloud after coordinate transformation; Where (X,Y,Z) are the coordinates of the 3D point cloud after coordinate transformation, (x,y) are the coordinates of the stereo image, (u,v) are the pixel coordinates, and (c) are the pixel coordinates. x ,c y ) are the coordinates of the principal point, f x f is the focal length of the camera on the x-axis. y Z represents the focal length of the camera on the y-axis, and Z represents the depth information of the binocular image.

6. The method for determining the distance between a transmission line and an external hazard source according to claim 1, characterized in that, The determination of the distance between the transmission line and the external hazard source based on the detection results of the transmission line, the detection results of the external hazard source, and the fused data specifically includes: Based on the detection results and fusion data of the transmission lines, the three-dimensional coordinates of the fusion data center points of the transmission lines are determined; Based on the detection results of external hazard sources and the fused data of external hazard sources, determine the three-dimensional coordinates of the fused data center point of the external hazard sources; The distance between the transmission line and the external hazard source is determined based on the three-dimensional coordinates of the fusion data center point of the transmission line and the three-dimensional coordinates of the fusion data center point of the external hazard source.

7. The method for determining the distance between a transmission line and an external hazard source according to claim 6, characterized in that, The step of determining the distance between the transmission line and the external hazard source based on the three-dimensional coordinates of the fusion data center point of the transmission line and the three-dimensional coordinates of the fusion data center point of the external hazard source specifically includes: Using formula Determine the distance D between the transmission line and the external hazard source; Where (x1,y1,z1) are the three-dimensional coordinates of the converged data center point of the transmission line, and (x2,y2,z2) are the three-dimensional coordinates of the converged data center point of the external hazard source.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the method for determining the distance between a transmission line and an external hazard source as described in any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the method for determining the distance between a transmission line and an external hazard source as described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the method for determining the distance between a transmission line and an external hazard source as described in any one of claims 1-7.

Images