Defect spatial positioning method, system, device, medium and product of power transmission line

Abstract

The application discloses a power transmission line defect space positioning method, system, device, medium and product, and is characterized in that the method comprises the following steps: acquiring measurement distance data of a camera assembly and a power transmission line, image data and pose data of the power transmission line; performing space registration on the image data and the pose data to obtain target image data, inputting the target image data into a preset defect detection model to obtain a plurality of defect detection boxes; extracting pixel coordinate information of each defect detection box, performing three-dimensional projection on each pixel coordinate information to obtain initial three-dimensional coordinates of a power transmission line defect in a camera coordinate system, correcting the initial three-dimensional coordinates to obtain target three-dimensional coordinates of the power transmission line defect, and performing coordinate transformation on the target three-dimensional coordinates by using a coordinate transformation matrix to obtain space positioning coordinates corresponding to the power transmission line defect. The application can improve the space positioning precision of the power transmission line defect in a complex inspection environment.

Description

Technical Field

[0001] This invention relates to the field of defect spatial location, and more particularly to methods, systems, equipment, media, and products for spatial location of defects in transmission lines. Background Technology

[0002] Transmission lines are a crucial component of the power system, serving as key infrastructure for long-distance power transmission and stable power supply. Their operational status directly impacts grid security and power supply reliability. Due to long-term exposure to the outdoor environment, transmission lines and their associated components are susceptible to erosion from wind and rain, aging from sunlight, lightning strikes, and external interference, leading to various structural defects such as corrosion, loosening, broken strands, deformation, and damage. Failure to promptly detect and accurately locate these defects can easily trigger major accidents such as line tripping, short circuits, or even tower collapse and line breakage, causing widespread power outages and severe economic losses.

[0003] Current power transmission line inspection technologies largely rely on UAVs equipped with visible light imaging devices for image acquisition, combined with deep learning algorithms for defect detection and identification. However, in complex inspection environments, such as cluttered backgrounds, large distance variations, unstable visual perspectives, and complex lighting conditions, simply relying on image information is insufficient to achieve high-precision mapping of defects in real space. This leads to uncontrollable positioning errors in the distance direction, thus failing to comprehensively improve the spatial positioning accuracy of power transmission line defects in complex inspection environments. Furthermore, existing technologies generally suffer from insufficient spatiotemporal alignment accuracy of multi-source sensor data, low reliability of depth information, and significant accumulation of coordinate transformation model errors. Consequently, the spatial positioning accuracy and stability of defects fail to meet engineering application requirements, affecting the accuracy and reliability of subsequent maintenance decisions. Summary of the Invention

[0004] This invention provides a method, system, equipment, medium, and product for spatial location of defects in transmission lines, which can improve the spatial location accuracy of transmission line defects in complex inspection environments.

[0005] In a first aspect, embodiments of the present invention provide a method for spatially locating defects in transmission lines, comprising: Acquire measurement distance data between the camera assembly and the power transmission line, image data of the power transmission line, and pose data; Spatial registration is performed on the image data and the pose data to obtain target image data. The target image data is then input into a preset defect detection model to obtain several defect detection boxes. The pixel coordinate information of each defect detection box is extracted. Based on the measured distance data and the camera intrinsic parameters of the camera component, the pixel coordinate information is 3D projected to obtain the initial 3D coordinates of the transmission line defect in the camera coordinate system. The initial 3D coordinates are corrected to obtain the target 3D coordinates of the transmission line defect. The target 3D coordinates are then transformed using a coordinate transformation matrix to obtain the spatial positioning coordinates corresponding to the transmission line defect. The coordinate transformation matrix is ​​determined based on the pose data.

[0006] This invention achieves simultaneous acquisition of visual, depth, and spatial attitude information required for defect detection by obtaining measurement distance data between the camera component and the transmission line, image data of the transmission line, and corresponding pose data. This ensures that the subsequent positioning process simultaneously has two-dimensional observation basis, distance constraints, and spatial attitude reference, reducing the uncertainty introduced by a single information source at the data source level and improving the basic accuracy and reliability of defect spatial positioning in complex inspection environments. By spatially registering the image data and the pose data, target image data is obtained. This target image data is then input into a preset defect detection model to obtain several defect detection boxes. This establishes a one-to-one correspondence between the defect detection results and the corresponding spatial attitude information under the same spatiotemporal reference, thereby avoiding target position deviations caused by changes in image acquisition time or attitude. This method improves the spatial consistency of defect detection results under complex flight attitudes and multi-view conditions, providing stable input for subsequent precise positioning. By extracting the pixel coordinate information of each defect detection box and performing three-dimensional projection on the pixel coordinate information based on the measured distance data and the camera intrinsic parameters of the camera component, the initial three-dimensional coordinates of the transmission line defect in the camera coordinate system are obtained. The initial three-dimensional coordinates are further corrected to obtain the target three-dimensional coordinates. The target three-dimensional coordinates are then transformed using a coordinate transformation matrix determined based on the pose data to obtain the spatial positioning coordinates corresponding to the transmission line defect. This accurately maps the defect detection results in the two-dimensional image to the real three-dimensional space, reducing positioning errors in the distance and spatial directions, and achieving high-precision and stable spatial positioning of transmission line defects in complex inspection environments.

[0007] Furthermore, the step of spatially registering the image data and the pose data to obtain the target image data includes: The image data and the pose data are synchronized in time to obtain the first registration data; Spatial coordinate alignment is performed on the first registration data to obtain the target image data.

[0008] This invention, through time synchronization and spatial coordinate alignment of image data and pose data, establishes an accurate correspondence between defect detection results and corresponding spatial pose information under a unified spatiotemporal reference, effectively reducing spatial mapping deviations caused by time and pose errors, thereby improving the spatial positioning accuracy and stability of transmission line defects in complex inspection environments.

[0009] Furthermore, the step of inputting the target image data into a preset defect detection model to obtain several defect detection boxes includes: The target image data is input into a preset defect detection model to extract features from the target image data, obtain several features, and fuse the features to obtain a first feature map. The first feature map is jointly weighted based on an attention mechanism to obtain the second feature map; Target detection is performed on the second feature map to obtain several defect detection boxes.

[0010] This invention improves the accuracy and stability of defect detection under complex backgrounds and small target conditions by performing multi-layer feature extraction and fusion on target image data and introducing an attention mechanism to adaptively enhance defect-related features, thus providing a reliable target basis for the accurate spatial positioning of subsequent transmission line defects.

[0011] Further, the step of extracting the pixel coordinate information of each defect detection box, and performing a three-dimensional projection of each pixel coordinate information based on the measured distance data and the camera intrinsic parameters of the camera component to obtain the initial three-dimensional coordinates of the transmission line defect in the camera coordinate system includes: The pixel coordinates of the transmission line defects in the image coordinate system are determined based on the center point coordinates of each defect detection box. The pixel coordinates are obtained by performing coordinate translation on the pixel coordinate information based on the camera intrinsic parameters of the camera component; Based on the measured distance data, the target pixel coordinates are subjected to three-dimensional back projection processing to obtain the initial three-dimensional coordinates of the transmission line defect in the camera coordinate system.

[0012] This invention extracts pixel coordinates based on the center point of the defect detection frame and combines the measured distance data with camera intrinsic parameters to complete three-dimensional back projection, thereby achieving accurate mapping of defects from the image plane to the camera coordinate system, effectively improving the three-dimensional positioning accuracy of transmission line defects in complex inspection environments.

[0013] Furthermore, the step of correcting the initial three-dimensional coordinates to obtain the target three-dimensional coordinates of the transmission line defect includes: Depth information is determined based on the image data and the measured distance data, and corresponding weight parameters are calculated based on the depth information; The depth information and the weight parameters are fused together to obtain the target depth value. The initial three-dimensional coordinates are corrected based on the target depth value to obtain the target three-dimensional coordinates.

[0014] This invention improves the spatial positioning accuracy and stability of transmission line defects in complex inspection environments by weighted fusion of multi-source depth information from image data and measurement distance data to correct the initial three-dimensional coordinates.

[0015] Furthermore, the step of using a coordinate transformation matrix to perform coordinate transformation on the three-dimensional coordinates of the target to obtain the spatial location coordinates corresponding to the transmission line defect includes: Based on the pose data, the rotation matrix and displacement vector of the transmission line relative to the camera coordinate system are determined, and a coordinate transformation matrix is ​​constructed based on the rotation matrix and the displacement vector. The coordinates of the target three-dimensional coordinates are transformed according to the coordinate transformation matrix to obtain the spatial location coordinates corresponding to the transmission line defect.

[0016] This invention constructs a coordinate transformation matrix based on pose data, which uniformly transforms the target three-dimensional coordinates of the defect to the transmission line reference coordinate system, thereby achieving accurate mapping of the defect location in real space and improving the spatial positioning accuracy and consistency of transmission line defects in complex inspection environments.

[0017] Secondly, embodiments of the present invention provide a spatial location system for defects in transmission lines, the system comprising: an acquisition module, a transformation module, and a location module; The acquisition module is used to acquire the measured distance data between the camera component and the transmission line, the image data of the transmission line, and the pose data of the transmission line; The transformation module is used to spatially register the image data and the pose data to obtain target image data, and input the target image data into a preset defect detection model to obtain a number of defect detection boxes; The positioning module is used to extract the pixel coordinate information of each defect detection box, perform three-dimensional projection on each pixel coordinate information based on the measured distance data and the camera intrinsic parameters of the camera component to obtain the initial three-dimensional coordinates of the transmission line defect in the camera coordinate system, correct the initial three-dimensional coordinates to obtain the target three-dimensional coordinates of the transmission line defect, and perform coordinate transformation on the target three-dimensional coordinates using a coordinate transformation matrix to obtain the spatial positioning coordinates corresponding to the transmission line defect, wherein the coordinate transformation matrix is ​​determined based on the pose data.

[0018] This invention achieves automatic mapping of transmission line defects from two-dimensional images to three-dimensional spatial coordinates by uniformly acquiring and collaboratively processing image information, measurement distance information, and pose information. This improves the accuracy and stability of defect spatial positioning and enhances the intelligence and reliability of transmission line defect inspection in engineering applications.

[0019] Thirdly, embodiments of the present invention provide a terminal device, including: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus; The memory is used to store at least one executable instruction that causes the processor to perform operations such as the defect spatial location method for transmission lines as described in this application.

[0020] Fourthly, embodiments of the present invention provide a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device or system where the computer-readable storage medium is located to perform the defect spatial location method for transmission lines as described in this application.

[0021] Based on the above-described method embodiments, another embodiment of the present invention provides a computer program product, including a computer program or instructions, which, when executed by a communication device, implements the method for spatial location of defects in transmission lines according to any embodiment of the present invention.

[0022] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0023] To more clearly illustrate the technical solution of this application, 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 from these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating one embodiment of the method for spatial location of defects in transmission lines provided in this application; Figure 2 This is a flowchart illustrating steps S201 to S203 provided in this application; Figure 3 This is a flowchart illustrating steps S301 to S303 provided in this application; Figure 4 This is a flowchart illustrating steps S401 to S402 provided in this application; Figure 5 This is a schematic diagram of an embodiment of the spatial location method for defects in transmission lines provided in this application. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, 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.

[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0027] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0028] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0029] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0030] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0031] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0032] Transmission lines, as crucial infrastructure in the power system responsible for long-distance power transmission and stable power supply, directly impact the safety and reliability of the power grid. Due to the long-term influence of complex outdoor environments, transmission lines and their components are susceptible to erosion from wind and rain, aging from sunlight, lightning strikes, and external interference, leading to various structural defects such as corrosion, loosening, broken strands, deformation, and damage. Failure to detect and accurately locate these defects in a timely manner can easily trigger major accidents such as line tripping and short circuits, causing widespread power outages and severe economic losses. Current transmission line inspection technologies often employ drones equipped with visible light imaging equipment to acquire image data, combined with deep learning algorithms for defect detection and identification. However, in practical application scenarios with complex backgrounds, varying inspection distances, unstable viewing angles, and variable lighting conditions, relying solely on image information is insufficient to achieve high-precision mapping of defects in real three-dimensional space, resulting in significant errors in distance and direction positioning. In addition, existing technologies still have shortcomings in terms of spatiotemporal alignment of multi-source sensor data, reliability of depth information, and accuracy of coordinate transformation models. Errors are prone to accumulate, which makes it difficult for the spatial positioning accuracy and stability of transmission line defects to meet the needs of engineering applications, affecting the accuracy and reliability of subsequent inspection and maintenance decisions.

[0033] See Figure 1 To improve the spatial positioning accuracy of transmission line defects in complex inspection environments, an embodiment of the present invention provides a spatial positioning method for transmission line defects, including steps S101 to S103. Step S101: Obtain the measured distance data between the camera component and the transmission line, the image data of the transmission line, and the pose data of the transmission line; In some embodiments, the camera assembly is mounted on an inspection platform, which can be a drone, an inspection robot, or a live-line working device. The camera assembly maintains a relatively stable spatial relationship with the transmission line. The image data is acquired by an optical camera in the camera assembly. During the inspection, the optical camera continuously images the transmission line at a preset sampling frequency, acquiring original image frames containing transmission conductors, insulators, and their associated components. Each image frame corresponds to a unique image timestamp, used to characterize the acquisition time of the image data. The measured distance data is acquired by a laser ranging unit mounted on the camera assembly. The laser ranging unit emits a laser beam towards the transmission line along a preset measurement direction and receives the reflected signal. It calculates the straight-line distance from the optical center of the camera assembly to the surface of the transmission line using a time-of-flight measurement method, thereby obtaining the measured distance data at the corresponding time. The measured distance data and the image data are associated through timestamps. The pose data is jointly acquired by an inertial measurement unit (IMU) and a satellite positioning unit rigidly connected to the camera component. The IMU collects the attitude angle information of the inspection platform in space, and the satellite positioning unit collects the position data of the inspection platform in the geographic coordinate system. By fusing the attitude angle information and the position data, the pose data corresponding to the camera component when acquiring the image data is obtained. The pose data includes the position information and attitude information of the camera component in space. In this embodiment, the image data, measurement distance data, and pose data all have a unified time stamp and are stored in the same data buffer to ensure a one-to-one correspondence between various types of data during subsequent spatial registration and fusion processing.

[0034] Through the above steps, the synchronous acquisition and unified management of image data, measurement distance data and pose data during the inspection of transmission lines are realized, providing a reliable data foundation for subsequent spatial registration of multi-source data, three-dimensional projection and precise spatial location of defects, thereby improving the temporal consistency and spatial accuracy of transmission line defect location.

[0035] Step S102: Spatial registration is performed on the image data and the pose data to obtain target image data. The target image data is then input into a preset defect detection model to obtain several defect detection boxes. In some embodiments, spatially registering the image data and the pose data to obtain target image data includes: temporally synchronizing the image data and the pose data to obtain first registration data; and aligning the first registration data with spatial coordinates to obtain the target image data.

[0036] In some embodiments, the image data and the pose data are time-synchronized to obtain first registration data. Specifically, the image data is acquired by an optical camera, and each frame of image data corresponds to an image acquisition timestamp. The pose data was acquired by an IMU / GNSS integrated navigation system, and each set of pose data corresponds to a pose acquisition timestamp. The pose data includes the current position coordinates and attitude angle information. To eliminate time reference differences between different sensors, the image data and the pose data are time-synchronized. Time synchronization employs a combination of hardware triggering and software compensation. By introducing inherent system time offset and clock drift compensation, the image acquisition timestamp is uniformly corrected. The time synchronization model is expressed as: ; in, The corrected unified timestamp; Image acquisition timestamp; This refers to the inherent time offset between the optical camera and the IMU / GNSS integrated navigation system. This is the clock drift compensation amount. Based on the unified timestamp. In the pose data, the pose acquisition data with the closest timestamp is selected as the pose data corresponding to the current image data, thereby establishing a one-to-one correspondence between the image data and the pose data in the time dimension, and obtaining the first registration data that completes time synchronization.

[0037] In some embodiments, spatial coordinate alignment is performed on the first registration data to obtain the target image data. Specifically, after time synchronization is completed, spatial coordinate alignment processing is performed on the first registration data to achieve a unified representation of image data and pose data in a spatial coordinate system. In this embodiment, by calibrating the spatial relationship between the optical camera and the IMU, the extrinsic parameter transformation matrix of the camera coordinate system relative to the body coordinate system is obtained, which is expressed as: ; in, It is a 3×3 rotation matrix used to describe the attitude relationship between the camera coordinate system and the body coordinate system; This is a 3×1 translation vector used to describe the positional relationship between the camera coordinate system origin and the body coordinate system. Based on the extrinsic transformation matrix, the spatial information in the camera coordinate system corresponding to the image data in the first registration data is transformed to the body coordinate system, completing the spatial coordinate alignment process. Specifically, for any spatial point in the image data, its homogeneous coordinates in the body coordinate system are represented as: ; Through the above spatial coordinate alignment process, the image data and the corresponding pose data are mapped in a unified spatial coordinate system, thereby obtaining target image data with unified spatiotemporal registration, providing an accurate spatial basis for subsequent defect spatial localization and coordinate transformation.

[0038] It should be noted that, in this embodiment, the camera coordinate system is used to describe the spatial position of the defect in the optical camera imaging reference frame; the body coordinate system is used to describe the pose information of the mounted platform, and the pose data is given by the IMU / GNSS integrated navigation system in the body coordinate system. Since the optical camera and the body have a fixed offset in installation position and orientation, the camera coordinate system and the body coordinate system are two different coordinate systems, and they are correlated through the extrinsic parameter transformation matrix obtained through calibration.

[0039] In some embodiments, inputting the target image data into a preset defect detection model to obtain a plurality of defect detection boxes includes: inputting the target image data into the preset defect detection model to extract features from the target image data to obtain a plurality of features, and fusing the features to obtain a first feature map; performing joint feature weighting on the first feature map based on an attention mechanism to obtain a second feature map; and performing target detection on the second feature map to obtain a plurality of defect detection boxes.

[0040] In some embodiments, the target image data is input into a preset defect detection model to extract features from the target image data, obtaining several features. These features are then fused to obtain a first feature map. Specifically, the spatiotemporally registered target image data is input into a defect detection model built on YOLOv5. First, the Backbone network performs layer-by-layer convolution and downsampling operations on the target image data to extract semantic and texture features at different scales, obtaining multi-scale feature maps corresponding to shallow, mid-level, and deep layers, respectively. The shallow feature map contains richer edge and texture information, while the deep feature map contains stronger semantic expression capabilities. Subsequently, the multi-scale feature maps are input into a feature fusion structure in the Neck network. Through upsampling, downsampling, and lateral connection operations, the feature maps at different scales are aligned and fused, allowing high-resolution features and high-semantic features to complement each other, forming a fused multi-scale feature representation. After completing the multi-scale feature fusion, the fused feature map is output as the first feature map for subsequent attention-weighted processing.

[0041] In some embodiments, the first feature map is jointly weighted based on an attention mechanism to obtain a second feature map. Specifically, the first feature map is input into the CBAM attention module embedded after the Neck network in YOLOv5, and channel attention weighting and spatial attention weighting are performed sequentially. In the channel attention weighting stage, let the first feature map be: ,in, For the number of channels, and These represent the height and width of the feature map, respectively. Global average pooling and global max pooling operations are performed on the first feature map in the spatial dimension to obtain the channel description vector: ; in, For the first feature map in the th Global average pooling results across all channels; For the first feature map in the th Global max pooling results on each channel; These are the height and width of the first feature map, respectively. The two channel description vectors are input into a multilayer perceptron (MLP) with shared parameters for non-linear mapping, and then a channel attention weight vector is generated using the sigmoid function. ; in, This is the channel attention weight vector, used to represent the importance of each channel; The channel description vector is obtained by global average pooling of each channel; The channel description vector is obtained by global max pooling of each channel; This is the weight matrix of the first fully connected layer, used for dimensionality reduction of the channel features; This is the weight matrix for the second fully connected layer, used to increase the dimensionality of the channel features; The sigmoid activation function is used to normalize the weight values ​​to 0. Interval 1. Multiply the channel attention weight vector with the first feature map channel by channel to obtain the channel-weighted feature map: ; in, The feature map is after channel attention weighting; This indicates a channel-by-channel multiplication operation; This is the channel attention weight vector; This is the first feature map. During the spatial attention weighting stage, the feature map is weighted by the channel. Average pooling and max pooling operations are performed along the channel dimension, and the pooling results are concatenated and input into a 7×7 convolutional layer. The spatial attention weight matrix is ​​generated by the sigmoid function. ; in, This is the spatial attention weight matrix; This indicates the feature map The feature map is obtained by average pooling along the channel dimension; This indicates the feature map The feature map obtained by max pooling along the channel dimension; This represents a convolution operation with a kernel size of 7×7; The sigmoid activation function is used. The spatial attention weight matrix is ​​multiplied pixel-by-pixel by the channel-weighted feature map to obtain the second attention-weighted feature map: ; in, The second feature map is obtained by weighting the combined channel attention and spatial attention. This is the spatial attention weight matrix; The feature map is after channel attention weighting; This indicates element-wise multiplication.

[0042] In some embodiments, target detection is performed on the second feature map to obtain several defect detection boxes. Specifically, the second feature map is input into the YOLOv5 detection head, and the feature maps at different resolutions are predicted using a multi-scale detection head. The corresponding bounding box position parameters, target confidence, and defect category probability are output. During model training, a joint loss function matching the attention mechanism is introduced to enhance the supervision of the localization accuracy of high-response regions. The total loss function is defined as follows: ; in, The total loss function of the defect detection model; The bounding box coordinate regression loss is used to constrain the deviation between the predicted box and the actual defect location; The target loss is used to characterize whether the detection box contains a defective target; The classification loss is used to characterize the accuracy of defect category prediction; This is an auxiliary loss related to the attention mechanism, used to enhance supervision of regions with high attention response; These are the weight coefficients corresponding to each loss term. Through the above detection head inference and loss function constraints, several defect detection boxes corresponding to transmission line defects are output. Each defect detection box includes the location range of the defect in the image and its category information, providing a basis for subsequent pixel coordinate extraction and three-dimensional spatial localization.

[0043] Through the above steps, high-consistency registration of multi-source heterogeneous data under a unified spatiotemporal reference system was achieved, eliminating the impact of inspection platform movement, asynchronous sensor sampling, and installation bias on image understanding. At the same time, based on the defect detection model with an attention mechanism, feature extraction and joint weighting of target image data were performed, enabling the model to pay more attention to key areas and effective features related to transmission line defects. This improved the accuracy and robustness of defect detection under complex backgrounds, lighting changes, and occlusion conditions, thus providing a reliable and stable detection foundation for subsequent pixel-level defect coordinate extraction and high-precision three-dimensional spatial positioning, and overall improving the spatial positioning accuracy of transmission line defects in complex inspection environments.

[0044] Step S103: Extract the pixel coordinate information of each defect detection box, perform three-dimensional projection on each pixel coordinate information based on the measured distance data and the camera intrinsic parameters of the camera component to obtain the initial three-dimensional coordinates of the transmission line defect in the camera coordinate system, correct the initial three-dimensional coordinates to obtain the target three-dimensional coordinates of the transmission line defect, and use a coordinate transformation matrix to perform coordinate transformation on the target three-dimensional coordinates to obtain the spatial positioning coordinates corresponding to the transmission line defect, wherein the coordinate transformation matrix is ​​determined based on the pose data.

[0045] Please refer to Figure 2 In some embodiments, the step of extracting the pixel coordinate information of each defect detection box and performing three-dimensional projection on each pixel coordinate information based on the measurement distance data and the camera intrinsic parameters of the camera component to obtain the initial three-dimensional coordinates of the transmission line defect in the camera coordinate system includes: steps S201 to S203. Step S201: Determine the pixel coordinate information of the transmission line defect in the image coordinate system based on the center point coordinates of each defect detection box; In some embodiments, for each defect detection box output by the defect detection model, its bounding box parameters in the image coordinate system are extracted. These bounding box parameters include the pixel coordinates of the top-left corner. and bottom right pixel coordinates Based on the bounding box parameters, the center point coordinates of the defect detection box are calculated as the pixel coordinates of the defect in the image coordinate system. The calculation method is as follows: ; in, These are the pixel coordinates of the transmission line defects in the image coordinate system. The pixel coordinates of the top-left corner of the defect detection box in the image coordinate system; Here are the pixel coordinates of the lower right corner of the defect detection box in the image coordinate system. By using this method, the geometric center of the defect detection box can be used as the representative pixel position of the defect, thereby reducing the impact of edge noise and changes in the detection box scale on subsequent spatial positioning accuracy.

[0046] Step S202: Based on the camera intrinsic parameters of the camera component, perform coordinate translation on the pixel coordinate information to obtain the target pixel coordinates; In some embodiments, the camera intrinsic parameters of the camera component are obtained, including the coordinates of the camera principal point. and camera focal length parameters Using the camera principal point as the reference origin, the pixel coordinates are... The target pixel coordinates are obtained by performing coordinate translation, and the calculation method is as follows: ; in, These are the target pixel coordinates after coordinate translation; These are the original pixel coordinates of the defect in the image coordinate system; Here are the pixel coordinates of the camera principal point in the image coordinate system. Through the above coordinate translation process, the pixel coordinates are transformed from the image coordinate system with the top left corner of the image as the origin to the camera imaging plane coordinate system with the camera optical axis projection point as the origin, providing a unified geometric reference for subsequent 3D backprojection calculations.

[0047] Step S203: Perform three-dimensional back projection processing on the target pixel coordinates based on the measured distance data to obtain the initial three-dimensional coordinates of the transmission line defect in the camera coordinate system.

[0048] In some embodiments, the linear distance between the camera assembly and the power transmission line is obtained by a laser rangefinder. and the angle between the camera's optical axis and the measurement direction. Based on the pinhole camera imaging model, the target pixel coordinates are... Combined with the measured distance data, the initial three-dimensional coordinates of the defect in the camera coordinate system are calculated as follows: ; in, The initial three-dimensional coordinates of the transmission line defect in the camera coordinate system are given in meters. These are the target pixel coordinates after translation via the camera principal point; These are the focal length parameters of the camera in the horizontal and vertical directions, in pixels. The straight-line distance measured by a laser rangefinder; The angle between the camera's optical axis and the ranging direction is denoted as . Through the aforementioned three-dimensional back projection processing, the mapping from two-dimensional image pixel coordinates to three-dimensional spatial coordinates in the camera coordinate system is achieved, yielding the initial spatial location result of the transmission line defect in the camera coordinate system.

[0049] Please refer to Figure 3 In some embodiments, the step of correcting the initial three-dimensional coordinates to obtain the target three-dimensional coordinates of the transmission line defect includes: steps S301 to S303. Step S301: Determine depth information based on the image data and the measured distance data, and calculate the corresponding weight parameters based on the depth information; In some embodiments, firstly, the straight-line distance between the camera assembly and the power transmission line is obtained based on a laser rangefinder, and then the measured distance is directionally corrected by combining the angle between the camera optical axis and the ranging direction to obtain the laser ranging depth. Secondly, based on the synchronously acquired binocular image data, a binocular vision matching algorithm is used to calculate the disparity value between the left and right views, and the disparity value is converted into corresponding depth information according to the camera intrinsic parameters to obtain the binocular visual depth. Next, based on the monocular image data, the image data is input into a preset monocular depth estimation model to perform depth regression prediction on the scene structure in the image, thereby obtaining the monocular estimated depth. After obtaining the above three types of depth information, a corresponding standard deviation of measurement error is configured for each type of depth information. and confidence score The corresponding weight parameters are calculated based on the depth information and statistical characteristics, and the calculation method is as follows: ; in, The depth information source type can be represented by values ​​including laser ranging, binocular vision, and monocular estimation. For the first The depth value corresponding to this depth information; For the first Standard deviation of the measurement error for depth information; For the first The confidence score for this depth information ranges from 0. 1; Statistical mean of the three depth information types; The statistical standard deviations of the three depth information types. Through the above method, depth information with smaller measurement errors, higher confidence levels, and consistency with the overall depth distribution is given higher fusion weights.

[0050] Step S302: Perform depth fusion processing on each of the depth information and each of the weight parameters to obtain the target depth value; In some embodiments, based on the laser ranging depth Binocular visual depth and monocular depth estimation And combined with their respective weight parameters , and The target depth value of the transmission line defect is obtained by weighted fusion processing of multi-source depth information. The calculation method is as follows: ; in, The target depth value after fusion; For laser ranging depth; Depth calculated for binocular vision; Depth estimated by monocular depth; , , These are the weighting parameters corresponding to the depth information. Through the multi-source depth fusion method described above, the advantages of different depth acquisition methods under different working conditions can be fully utilized, reducing the impact of anomalies in single depth information on overall positioning accuracy.

[0051] Step S303: Correct the initial three-dimensional coordinates based on the target depth value to obtain the target three-dimensional coordinates.

[0052] In some embodiments, the initial three-dimensional coordinates of the transmission line defect in the camera coordinate system are obtained. and the target depth value obtained by fusion As a depth reference, the depth components in the initial three-dimensional coordinates are corrected while maintaining the proportional relationship between the horizontal and vertical coordinates, resulting in the corrected target three-dimensional coordinates. The processing method is as follows: ; in, Initial three-dimensional coordinates; The corrected three-dimensional coordinates of the target; The target depth value is obtained through fusion. By employing the above correction method, the 3D localization results of transmission line defects in the camera coordinate system maintain spatial orientation consistency while achieving higher depth accuracy, providing reliable 3D input for subsequent coordinate transformation and spatial positioning.

[0053] Please refer to Figure 4In some embodiments, the step of using a coordinate transformation matrix to transform the three-dimensional coordinates of the target to obtain the spatial location coordinates corresponding to the transmission line defect includes: steps S401 to S402. Step S401: Determine the rotation matrix and displacement vector of the transmission line relative to the camera coordinate system based on the pose data, and construct a coordinate transformation matrix based on the rotation matrix and the displacement vector; In some embodiments, pose data synchronized with image data is acquired, wherein the pose data is used to characterize the spatial pose relationship of the transmission line reference component in the camera coordinate system. Based on the pose data, three-dimensional pose parameters of the reference component relative to the camera coordinate system are determined, and a corresponding rotation matrix is ​​constructed from the pose parameters. and displacement vector Wherein, the rotation matrix The displacement vector is a three-dimensional orthogonal matrix used to describe the spatial orientation relationship between the coordinate axes of the reference component and the camera coordinate axes. Let be the position vector of the origin of the reference component's coordinate system in the camera's coordinate system. Based on this, the rotation matrix... With displacement vector The coordinate transformation matrix for coordinate system transformation is constructed by combining the following forms: ; in, The rotation matrix of the reference component relative to the camera coordinate system; The displacement vector of the reference component in the camera coordinate system; This is the coordinate transformation matrix composed of the rotation matrix and the displacement vector. Through this method, a spatial mapping relationship is established between the camera coordinate system and the local coordinate system of the reference component, providing a unified coordinate transformation basis for subsequent defect spatial localization.

[0054] Step S402: Perform coordinate transformation on the target three-dimensional coordinates according to the coordinate transformation matrix to obtain the spatial positioning coordinates corresponding to the transmission line defect.

[0055] In some embodiments, the target three-dimensional coordinates of the transmission line defect in the camera coordinate system are obtained. And represent it as a column vector: Based on the rotation matrix of the reference component and displacement vector The three-dimensional coordinates of the target are transformed to obtain the spatial location coordinates of the transmission line defect in the local coordinate system of the reference component. The calculation method is as follows: ; in, , representing the spatial location coordinates of the transmission line defect in the local coordinate system of the reference component; Rotation matrix The transpose matrix is ​​used to implement the orientation transformation from the camera coordinate system to the local coordinate system of the reference component; The target's three-dimensional coordinates in the camera coordinate system represent the defect. This refers to the position vector of the reference component in the camera coordinate system. Furthermore, while obtaining the spatial positioning coordinates, the spherical coordinate parameters of the defect relative to the camera can be calculated based on the target's three-dimensional coordinates to characterize the spatial orientation of the defect. The calculation method is as follows: ; in, The spatial distance from the defect to the camera; The azimuth angle of the defect relative to the camera; Let be the pitch angle of the defect relative to the camera. Through the above coordinate transformation and spatial relationship description method, a unified spatial location expression of transmission line defects in the camera coordinate system, spherical coordinate system, and local coordinate system of the reference component is realized.

[0056] It should be noted that, in this embodiment, the reference component is a structural fixing component on the transmission line, used as a coordinate reference for spatial positioning of defects. The reference component includes, but is not limited to, any one of insulator strings, hardware assemblies, or conductor fixing clamps. In this embodiment, the coordinate system of the reference component is a local three-dimensional Cartesian coordinate system attached to the reference component, and its origin and coordinate axis directions are defined as follows: the geometric center of the reference component or a preset structural feature point is used as the coordinate origin. The direction of the reference component along the transmission line is taken as... The positive direction of the axis; taking the opposite direction of the reference component pointing towards the ground in the vertical direction as... Positive direction of the axis; according to the right-hand coordinate system rule, from the... shaft and Axis determination The positive direction of the axis. Using the above definition, a reference component coordinate system is constructed, corresponding one-to-one with the transmission line structural entity, to characterize the spatial positional relationship of transmission line defects relative to the reference components. In this embodiment, the rotation matrix... This represents the attitude relationship between the reference component coordinate system and the camera coordinate system, and is used to map the direction vector in the camera coordinate system to the reference component coordinate system; the displacement vector Indicates the origin of the coordinate system of the reference component. The position coordinates in the camera coordinate system. Therefore, through the rotation matrix... With the displacement vector The combination of these elements enables the spatial mapping relationship between the camera coordinate system and the reference component coordinate system.

[0057] In some embodiments, the pixel coordinates of the defect in the image coordinate system Combined with the focal length parameter in the camera's intrinsic parameters and the depth value in the target's three-dimensional coordinates The positioning accuracy of the defect in the φ axis and φ axis of the camera coordinate system is calculated using the error propagation model, and its expression is as follows: ; in, These represent the defects in the camera coordinate system, respectively. Axial direction and Planar positioning accuracy in the axial direction (unit: meter); This indicates the depth of the defect in the camera coordinate system (unit: meters). This represents the pixel coordinates of the defect in the image coordinate system; These represent the detection errors of pixel coordinates in the horizontal and vertical directions, respectively (unit: pixels). These represent the camera's focal length parameters in the horizontal and vertical directions, respectively (unit: pixels). These represent the calibration errors for the corresponding focal length parameters. For depth measurement results from different depth acquisition methods, their corresponding measurement errors are obtained, and the overall measurement accuracy of the defect in the depth direction is calculated using an error synthesis model. The calculation formula is as follows: ; in, Indicates the measurement accuracy of the defect in the depth direction in the camera coordinate system (unit: meters); This represents the standard deviation of the error in the depth measurement value corresponding to the laser rangefinder. This represents the standard deviation of the depth measurement error calculated based on binocular vision. This represents the standard deviation of the depth measurement error obtained based on the monocular depth estimation model. The planar positioning accuracy parameter... and the depth measurement accuracy parameters The error covariance matrix is ​​uniformly incorporated into the three-dimensional error matrix to describe the overall positioning uncertainty of the defect in three-dimensional space. Its three-dimensional positioning accuracy evaluation model is expressed as: ; in, The three-dimensional localization error covariance matrix representing the defects in transmission lines; These represent the correlation coefficients between the positioning errors of defects in different coordinate axis directions, used to characterize the correlation between errors in each direction; These represent the defects in the camera coordinate system. Positioning accuracy parameters in the direction. Using the aforementioned three-dimensional positioning accuracy evaluation model, the reliability of spatial positioning results for transmission line defects can be quantitatively described, providing a basis for subsequent automated maintenance decisions.

[0058] In some embodiments, after completing the spatial location calculation and three-dimensional location accuracy assessment of the transmission line defect, the location results are standardized and encapsulated to form complete visual spatial location output data that can be used by subsequent equipment. Specifically, this involves: mapping the three-dimensional coordinates of the defect in the camera coordinate system... Defects relative to the spatial distance of the camera and direction and angle And combined with the location results of the defect in the local coordinate system of the reference component A unified encapsulation of the basic positioning information data structure VisualPosition is used to describe the spatial location information of defects in different coordinate systems; simultaneously, the accuracy parameters calculated from the planar positioning accuracy are... Depth accuracy parameters obtained from depth error synthesis calculation and the constructed three-dimensional positioning error covariance matrix The accuracy metadata structure AccuracyInfo is uniformly encapsulated and the positioning confidence is calculated based on the three-dimensional positioning error covariance matrix. The calculation method is as follows: ; in, This indicates the confidence level of the current defect spatial localization result; Represents the trace operation of a matrix; The covariance matrix represents the maximum allowable positioning error of the system and is used to normalize the positioning accuracy. Through the above standardized data encapsulation method, complete visual spatial positioning output data containing spatial position, orientation information, and positioning accuracy evaluation results is formed. This allows the positioning results output by the system to be directly called by the robotic arm control system, automated inspection system, or intelligent maintenance decision module, thereby improving the automation level and engineering applicability of the power transmission line defect handling process.

[0059] Through the above steps, a precise mapping of two-dimensional image information to initial three-dimensional coordinates in the camera coordinate system is achieved. By fusing multi-source depth information and weighting correction, the error of a single measurement method is effectively corrected, achieving high-precision correction of the target's three-dimensional coordinates in the camera coordinate system. Furthermore, using a coordinate transformation matrix constructed based on pose data, the three-dimensional coordinates of the defect are transformed to the local coordinate system of the reference component. At the same time, a three-dimensional error covariance matrix is ​​constructed to quantitatively evaluate the spatial positioning accuracy of the defect. Finally, through standardized data encapsulation, a complete visual output containing spatial position, orientation, and positioning accuracy is formed, providing highly reliable spatial positioning information that can be directly accessed for automated inspection, robotic arm grasping, and intelligent maintenance decision-making of transmission line defects, thereby improving the accuracy, robustness, and engineering applicability of defect spatial positioning.

[0060] like Figure 5 As shown, based on the above method embodiments, corresponding apparatus embodiments are provided; An embodiment of the present invention provides a schematic diagram of the structure of a defect spatial location system for transmission lines, including: an acquisition module 100, a transformation module 200, and a location module 300; The acquisition module 100 is used to acquire the measurement distance data between the camera component and the transmission line, the image data of the transmission line, and the pose data of the transmission line; The transformation module 200 is used to spatially register the image data and the pose data to obtain target image data, and input the target image data into a preset defect detection model to obtain a number of defect detection boxes; The positioning module 300 is used to extract the pixel coordinate information of each defect detection box, perform three-dimensional projection on each pixel coordinate information based on the measured distance data and the camera intrinsic parameters of the camera component to obtain the initial three-dimensional coordinates of the transmission line defect in the camera coordinate system, correct the initial three-dimensional coordinates to obtain the target three-dimensional coordinates of the transmission line defect, and perform coordinate transformation on the target three-dimensional coordinates using a coordinate transformation matrix to obtain the spatial positioning coordinates corresponding to the transmission line defect, wherein the coordinate transformation matrix is ​​determined based on the pose data.

[0061] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention, and can implement the method for spatial location of defects in transmission lines provided by any of the above-described method embodiments of the present invention. More detailed workflows and principles of this system can be found, but are not limited to, the relevant descriptions of the above methods.

[0062] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0063] Based on the above embodiments of the method for spatial location of defects in transmission lines, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the method for spatial location of defects in transmission lines according to any embodiment of the present invention.

[0064] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0065] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0066] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0067] Based on the above-described method embodiments, another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the defect spatial location method for transmission lines as described in any of the above-described method embodiments of the present invention.

[0068] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0069] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A method for spatially locating defects in transmission lines, characterized in that, include: Acquire measurement distance data between the camera assembly and the power transmission line, image data of the power transmission line, and pose data; Spatial registration is performed on the image data and the pose data to obtain target image data. The target image data is then input into a preset defect detection model to obtain several defect detection boxes. The pixel coordinate information of each defect detection box is extracted. Based on the measurement distance data and the camera intrinsic parameters of the camera component, the pixel coordinate information is 3D projected to obtain the initial 3D coordinates of the transmission line defect in the camera coordinate system. The initial 3D coordinates are corrected to obtain the target 3D coordinates of the transmission line defect. The target 3D coordinates are then transformed using a coordinate transformation matrix to obtain the spatial positioning coordinates of the transmission line defect. The coordinate transformation matrix is ​​determined based on the pose data. The measured distance data is obtained by a laser ranging unit installed on the camera assembly. The laser ranging unit emits a laser beam toward the transmission line along a preset measurement direction and receives the reflected signal. The straight-line distance from the optical center of the camera assembly to the surface of the transmission line is calculated by time-of-flight measurement, thereby obtaining the measured distance data at the corresponding time. The pose data is jointly acquired by an inertial measurement unit and a satellite positioning unit rigidly connected to the camera component. The inertial measurement unit is used to collect the attitude angle information of the inspection platform in space, and the satellite positioning unit is used to collect the position data of the inspection platform in the geographic coordinate system. By fusing and solving the attitude angle information and the position data, the pose data corresponding to the camera component when collecting the image data is obtained, wherein the pose data includes the position information and attitude information of the camera component in space. The step of correcting the initial three-dimensional coordinates to obtain the target three-dimensional coordinates of the transmission line defect includes: Depth information is determined based on the image data and the measured distance data, and corresponding weight parameters are calculated based on the depth information; The depth information and the weight parameters are fused together to obtain the target depth value. The initial three-dimensional coordinates are corrected based on the target depth value to obtain the target three-dimensional coordinates; The step of determining depth information based on the image data and the measured distance data, and calculating corresponding weight parameters based on the depth information, includes: The laser rangefinder is used to obtain the straight-line distance between the camera assembly and the power transmission line. The measured distance is then corrected for direction based on the angle between the camera's optical axis and the ranging direction to obtain the laser ranging depth. Simultaneously acquired binocular image data is used to calculate the disparity between the left and right views using a binocular vision matching algorithm. This disparity is then converted into corresponding depth information based on camera intrinsic parameters to obtain the binocular visual depth. Monocular image data is input into a preset monocular depth estimation model to perform depth regression prediction on the scene structure in the image, resulting in a monocular estimated depth. After obtaining these three types of depth information, corresponding measurement error standard deviations and confidence scores are configured for each depth information, and corresponding weight parameters are calculated based on each depth information and statistical characteristics.

2. The method for spatial location of defects in transmission lines as described in claim 1, characterized in that, The step of spatially registering the image data and the pose data to obtain the target image data includes: The image data and the pose data are synchronized in time to obtain the first registration data; Spatial coordinate alignment is performed on the first registration data to obtain the target image data.

3. The method for spatial location of defects in transmission lines as described in claim 1, characterized in that, The step of inputting the target image data into a preset defect detection model to obtain several defect detection boxes includes: The target image data is input into a preset defect detection model to extract features from the target image data, obtain several features, and fuse the features to obtain a first feature map. The first feature map is jointly weighted based on an attention mechanism to obtain the second feature map; Target detection is performed on the second feature map to obtain several defect detection boxes.

4. The method for spatial location of defects in transmission lines as described in claim 1, characterized in that, The step of extracting the pixel coordinate information of each defect detection box, and performing a three-dimensional projection of each pixel coordinate information based on the measured distance data and the camera intrinsic parameters of the camera component to obtain the initial three-dimensional coordinates of the transmission line defect in the camera coordinate system includes: The pixel coordinates of the transmission line defects in the image coordinate system are determined based on the center point coordinates of each defect detection box. The pixel coordinates are obtained by performing coordinate translation on the pixel coordinate information based on the camera intrinsic parameters of the camera component; Based on the measured distance data, the target pixel coordinates are subjected to three-dimensional back projection processing to obtain the initial three-dimensional coordinates of the transmission line defect in the camera coordinate system.

5. The method for spatial location of defects in transmission lines as described in claim 1, characterized in that, The step of transforming the three-dimensional coordinates of the target using a coordinate transformation matrix to obtain the spatial location coordinates corresponding to the transmission line defect includes: Based on the pose data, the rotation matrix and displacement vector of the transmission line relative to the camera coordinate system are determined, and a coordinate transformation matrix is ​​constructed based on the rotation matrix and the displacement vector. The coordinates of the target three-dimensional coordinates are transformed according to the coordinate transformation matrix to obtain the spatial location coordinates corresponding to the transmission line defect.

6. A spatial location system for defects in transmission lines, characterized in that, The system includes: an acquisition module, a transformation module, and a positioning module; The acquisition module is used to acquire the measured distance data between the camera component and the transmission line, the image data of the transmission line, and the pose data of the transmission line; The transformation module is used to spatially register the image data and the pose data to obtain target image data, and input the target image data into a preset defect detection model to obtain a number of defect detection boxes; The positioning module is used to extract the pixel coordinate information of each defect detection box, perform three-dimensional projection on each pixel coordinate information based on the measured distance data and the camera intrinsic parameters of the camera component to obtain the initial three-dimensional coordinates of the transmission line defect in the camera coordinate system, correct the initial three-dimensional coordinates to obtain the target three-dimensional coordinates of the transmission line defect, and perform coordinate transformation on the target three-dimensional coordinates using a coordinate transformation matrix to obtain the spatial positioning coordinates corresponding to the transmission line defect, wherein the coordinate transformation matrix is ​​determined based on the pose data; The measured distance data is obtained by a laser ranging unit installed on the camera assembly. The laser ranging unit emits a laser beam toward the transmission line along a preset measurement direction and receives the reflected signal. The straight-line distance from the optical center of the camera assembly to the surface of the transmission line is calculated by time-of-flight measurement, thereby obtaining the measured distance data at the corresponding time. The pose data is jointly acquired by an inertial measurement unit and a satellite positioning unit rigidly connected to the camera component. The inertial measurement unit is used to collect the attitude angle information of the inspection platform in space, and the satellite positioning unit is used to collect the position data of the inspection platform in the geographic coordinate system. By fusing and solving the attitude angle information and the position data, the pose data corresponding to the camera component when collecting the image data is obtained, wherein the pose data includes the position information and attitude information of the camera component in space. The step of correcting the initial three-dimensional coordinates to obtain the target three-dimensional coordinates of the transmission line defect includes: Depth information is determined based on the image data and the measured distance data, and corresponding weight parameters are calculated based on the depth information; The depth information and the weight parameters are fused together to obtain the target depth value. The initial three-dimensional coordinates are corrected based on the target depth value to obtain the target three-dimensional coordinates; The step of determining depth information based on the image data and the measured distance data, and calculating corresponding weight parameters based on the depth information, includes: The laser rangefinder is used to obtain the straight-line distance between the camera assembly and the power transmission line. The measured distance is then corrected for direction based on the angle between the camera's optical axis and the ranging direction to obtain the laser ranging depth. Simultaneously acquired binocular image data is used to calculate the disparity between the left and right views using a binocular vision matching algorithm. This disparity is then converted into corresponding depth information based on camera intrinsic parameters to obtain the binocular visual depth. Monocular image data is input into a preset monocular depth estimation model to perform depth regression prediction on the scene structure in the image, resulting in a monocular estimated depth. After obtaining these three types of depth information, corresponding measurement error standard deviations and confidence scores are configured for each depth information, and corresponding weight parameters are calculated based on each depth information and statistical characteristics.

7. A terminal device, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the method for spatial location of defects in transmission lines as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, include: A stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform the defect spatial location method for transmission lines as described in any one of claims 1-5.

9. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by the communication device, the defect spatial location method for transmission lines as described in any one of claims 1 to 5 is implemented.

Images