Method, system, medium and device for calculating ice thickness of power transmission line
By introducing perspective transformation of sensor physical parameters and feature point coordinates into the calculation of icing thickness on transmission lines, and combining geometric and physical constraints, the problems of low environmental adaptability and low detection accuracy in existing technologies are solved, and high-precision icing thickness identification is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- STATE GRID INTELLIGENCE TECHNOLOGY CO LTD
- Filing Date
- 2026-05-06
- Publication Date
- 2026-07-24
AI Technical Summary
Existing technologies have problems with poor environmental adaptability and low detection accuracy when identifying the thickness of ice on transmission lines. In particular, the accuracy of traditional methods cannot meet the requirements in rainy, snowy, foggy or backlit weather.
A perspective transformation method based on sensor physical parameters and feature point coordinates is adopted, combined with a hybrid constraint of geometric information and physical constraints, to optimize the image. The trained transmission line segmentation model is then used for image segmentation to extract icing feature points, calculate the icing thickness, and introduce a temperature correction coefficient to correct for errors caused by density variations.
It improves the environmental adaptability and detection accuracy of ice thickness identification, significantly reduces errors, and achieves high-precision ice thickness calculation under different weather conditions.
Smart Images
Figure CN122134787B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power transmission line safety monitoring technology, and in particular to a method, system, medium and equipment for calculating the icing thickness of power transmission lines. Background Technology
[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.
[0003] Icing on power transmission lines is a unique safety hazard in winter. Currently, the thickness of icing on transmission lines is primarily determined using the line tilt method and image recognition algorithms. However, the line tilt method, which relies on parameters such as span length and tension, suffers from calculation errors exceeding 20% when the icing thickness is uneven, rendering the results unsuitable for practical de-icing operations. Traditional image recognition algorithms often combine Canny edge detection with threshold segmentation, but their accuracy decreases in rain, snow, fog, or backlighting conditions, failing to meet usage requirements. Summary of the Invention
[0004] To address the aforementioned technical problems, this invention provides a method, system, medium, and equipment for calculating the icing thickness of transmission lines, which can balance environmental adaptability and detection accuracy.
[0005] To achieve the above objectives, the present invention adopts the following technical solution: The first aspect of the present invention provides a method for calculating the icing thickness of transmission lines.
[0006] In one or more embodiments, a method for calculating the icing thickness of a transmission line is provided, including: Acquire the original image of the transmission line and perform distortion correction; Under the hybrid constraints constructed by geometric information and physical constraints, the distortion-corrected transmission line image is optimized by using a perspective transformation method based on sensor physical parameters and feature point coordinates. The optimized transmission line image is processed using a trained transmission line segmentation model to obtain a transmission line region image. Ice-covered feature points are extracted from the image of the transmission line area, and the center offset of the transmission line is calculated based on feature point matching. The positional deviation of the transmission line before and after icing is corrected to obtain the diameter of the iced transmission line and the actual diameter of the uniced transmission line. Based on the diameter of the iced transmission line and the actual diameter of the uniced transmission line, the initial icing thickness is obtained, and a temperature correction coefficient is introduced to correct the error caused by the change in icing density, thus obtaining the final icing thickness.
[0007] In one implementation, the hybrid constraint is composed of a weighted sum of geometric errors, physical constraint errors, and consistency constraints. The expression for the hybrid constraint is: E = α·E_geometry + β·E_physics + γ·E_consistency; Where E is the hybrid constraint; E_geometry is the geometric error; E_physics is the physical constraint error; E_consistency is the consistency constraint; α, β and γ are the weights of the geometric error, physical constraint error and consistency constraint, respectively.
[0008] As one implementation method, the formula for calculating the weight of geometric error is: ; ; in, For variance estimation of geometric errors, measures the noise level of point coordinates or the degree of deviation of the initial matrix from the true transformation; The initial estimated homography matrix; The first image of the transmission line before optimization i Homogeneous coordinates of the feature points; For the optimized transmission line image, the first i Homogeneous coordinates of feature points.
[0009] As one implementation method, the formula for calculating the weight of physical constraint error is: ; ; in: For variance estimation of physical constraint error, it measures the difference between the homography matrix after transformation from the normalized coordinate system back to the pixel coordinate system and the directly calculated homography matrix; is the inverse of the camera intrinsic parameter matrix; K is the camera intrinsic parameter matrix; This is the representation of the initial homography matrix in the normalized camera coordinate system; The homography matrix is obtained directly from pixel coordinates using geometric methods; It is the Frobenius norm.
[0010] As one implementation method, the formula for calculating the weight of the consistency constraint is: ; ; in, The variance estimate of the regularization error measures the initial homography matrix. The degree of deviation from the identity matrix I; It is the Frobenius norm.
[0011] As one implementation method, the loss function of the transmission line segmentation model is a weighted sum of cross-entropy loss and Dice loss during the training process.
[0012] As one implementation method, the expression for the final icing thickness is: h_final = h × k; k = 1.02 - 0.001 × T; Where h_final is the final icing thickness; h is the initial icing thickness; k is the temperature correction factor; and T is the ambient temperature.
[0013] A second aspect of the present invention provides a system for calculating the icing thickness of power transmission lines.
[0014] In one or more embodiments, a power transmission line icing thickness calculation system includes: The distortion correction module is used to acquire the original image of the transmission line and perform distortion correction. The image optimization module is used to optimize the distortion-corrected transmission line image under the hybrid constraints constructed by geometric information and physical constraints, using a perspective transformation method based on sensor physical parameters and feature point coordinates. The image segmentation module is used to process the optimized transmission line image using a trained transmission line segmentation model to obtain the transmission line region image. The diameter calculation module is used to extract icing feature points in the image of the transmission line area, and calculate the center offset of the transmission line based on feature point matching and correct the positional deviation of the transmission line before and after icing, so as to obtain the diameter of the iced transmission line and the actual diameter of the uniced transmission line. The icing thickness determination module is used to obtain the initial icing thickness based on the diameter of the iced transmission line and the actual diameter of the uniced transmission line, and introduces a temperature correction coefficient to correct the error caused by the change in icing density, so as to obtain the final icing thickness.
[0015] A third aspect of the present invention provides a computer-readable storage medium.
[0016] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-described method for calculating the icing thickness of transmission lines.
[0017] A fourth aspect of the present invention provides an electronic device.
[0018] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps in the above-described method for calculating the icing thickness of transmission lines.
[0019] Compared with the prior art, the beneficial effects of the present invention are: This invention innovatively proposes a method for calculating the icing thickness of transmission lines. Under the hybrid constraints constructed by geometric information and physical constraints, it utilizes a perspective transformation method based on sensor physical parameters and feature point coordinates to optimize the distortion-corrected transmission line image. Then, combined with image segmentation and feature point matching techniques, it calculates the diameter of the iced transmission line and the actual diameter of the uniced transmission line, thereby obtaining the initial icing thickness. A temperature correction coefficient is then introduced to correct the error caused by changes in icing density, resulting in the final icing thickness. This method solves the problem that the accuracy of existing icing thickness recognition methods decreases and fails to meet usage requirements, achieving a balance between environmental adaptability and detection accuracy. Attached Figure Description
[0020] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.
[0021] Figure 1 This is a flowchart of the method for calculating the icing thickness of transmission lines according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the transmission line icing thickness calculation system according to an embodiment of the present invention; Figure 3 This is a schematic diagram of an electronic device according to an embodiment of the present invention; Figure 4 This is a comparison chart of the cumulative error curves of an embodiment of the present invention. Detailed Implementation
[0022] The present invention will be further described below with reference to the accompanying drawings and embodiments.
[0023] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, 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 invention pertains.
[0024] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.
[0025] Figure 1 A schematic diagram illustrating the principle of the method for calculating the icing thickness of transmission lines according to an embodiment of the present invention is provided. Figure 1 The method for calculating the icing thickness of transmission lines in this embodiment may include the following steps S101 to S105.
[0026] The specific implementation process of steps S101 to S105 is as follows: Step S101: Acquire the original image of the transmission line and perform distortion correction.
[0027] Specifically, icing detection equipment is installed on the power transmission line. Zhang's calibration method is used to correct camera distortion. For example, a 12*9 checkerboard calibration board (square size 20mm) is used, and eight calibration images are taken from different angles within the camera's field of view. The intrinsic parameter matrix (focal length, principal point coordinates) and distortion coefficients are calculated using the OpenCV library to establish a mapping relationship between image pixels and actual dimensions. Actual size = pixel size × calibration factor; Calibration factor = Actual checkerboard square size / Square pixel size in the image.
[0028] Step S102: Under the hybrid constraints constructed by geometric information and physical constraints, the distortion-corrected transmission line image is optimized using a perspective transformation method based on sensor physical parameters and feature point coordinates.
[0029] To address the perspective distortion of transmission lines in images, a perspective transformation method combining sensor physical parameters and feature point coordinates is proposed. This method utilizes both geometric information and physical constraints to improve the accuracy of the perspective transformation. The method employs both geometric correspondences and camera physical parameters (sensor size, focal length) to construct a hybrid constraint optimization problem, yielding the optimal homography matrix. The process is as follows: Step a: Calculate the sensor pixel size; ; ; in: The sensor size is for the X-axis; The sensor size along the Y-axis (in mm / pixel); the sensor's coordinate system is pre-built; Wsensor and Hsensor are the width and height dimensions of the sensor (in mm), respectively; Wimage and Himage are the width and height of the transmission line image (in pixels), respectively.
[0030] Step b: Construct the camera intrinsic parameter matrix K; ; ; ; Among them, focal length This represents the normalized focal length of the camera along the x and y axes of the power transmission line image, in pixels. This refers to the camera's physical focal length. The principal point coordinates are the intersection of the optical axis and the imaging plane.
[0031] Step c: Normalization process; For each feature point on the transmission line image The coordinates of the corresponding feature points after normalization are ; ; ; Step d: Construct the expression for the mixed constraint; E = α·E_geometry + β·E_physics + γ·E_consistency; Where E is the hybrid constraint; E_geometry is the geometric error; E_physics is the physical constraint error; E_consistency is the consistency constraint; α is the geometric error weight, which controls the strictness of the correspondence between points; β is the physical constraint weight, which controls the constraint strength of the camera physical model; and γ is the consistency weight, which is the regularization strength to prevent overfitting and singular solutions.
[0032] In this embodiment, the expression for geometric error is: E_geometry = Σ||H·src_norm_i - dst_norm_i||²; The expression for the physical constraint error is: E_physics = ||K·H·K -1 - H direct ||² ; The consistency constraint E_consistency is a regularization term; Where src_norm_i is the normalized camera coordinate of the i-th feature point in the transmission line image before optimization; H is the homography matrix in the normalized coordinate system to be solved; and dst_norm_i is the normalized camera coordinate of the i-th corresponding feature point in the transmission line image after optimization.
[0033] It should be noted here that the regularization term can be represented by L1 regularization or L2 regularization; where L1 regularization is the sum of the absolute values of the parameter weights; and L2 regularization is the sum of the squares of the parameter weights.
[0034] Specifically, the formula for calculating the weight of geometric error is: ; ; in, For variance estimation of geometric errors, measures the noise level of point coordinates or the degree of deviation of the initial matrix from the true transformation; The initial estimated homography matrix; The first image of the transmission line before optimization i Homogeneous coordinates of the feature points; For the optimized transmission line image, the first i Homogeneous coordinates of feature points.
[0035] The formula for calculating the weight of physical constraint error is: ; ; in: For variance estimation of physical constraint error, it measures the difference between the homography matrix after transformation from the normalized coordinate system back to the pixel coordinate system and the directly calculated homography matrix; is the inverse of the camera intrinsic parameter matrix; K is the camera intrinsic parameter matrix; This is the representation of the initial homography matrix in the normalized camera coordinate system; The homography matrix is obtained directly from pixel coordinates using geometric methods; It is the Frobenius norm, which is the square root of the sum of the squares of all elements of the matrix.
[0036] The formula for calculating the weights of consistency constraints is: ; ; in, The variance estimate of the regularization error measures the initial homography matrix. The degree of deviation from the identity matrix I; I is a 3x3 identity matrix, representing the identity transformation; It is the Frobenius norm, which is the square root of the sum of the squares of all elements of the matrix.
[0037] Based on the above expression for hybrid constraints, the optimal homography matrix is solved. The optimal homography matrix is then applied to the original transmission line image for optimization, resulting in a distortion-corrected transmission line image.
[0038] Step S103: Use the trained transmission line segmentation model to process the optimized transmission line image to obtain the transmission line region image.
[0039] In this embodiment of the invention, the structure of the transmission line segmentation model includes the following structure: Backbone: A pre-trained ResNet50 is used as the encoder to extract rich hierarchical features.
[0040] Neck: An ASPP (Atrous Spatial Pyramid Pooling) module is introduced after the top layer (C4 and C5 convolutional layers) of ResNet50 to expand the receptive field and capture icing context information at different scales.
[0041] Skip connections: Spatial and channel attention modules are introduced along the encoder-to-decoder path to weight the shallow detail features extracted by the C2 and C3 convolutional layers and suppress background noise.
[0042] Decoder: During upsampling, attention-weighted multi-scale features are gradually fused. Simultaneously, an edge prediction branch is added to the deeper side of the decoder, forcing the main network to learn sharper icing boundaries through deep supervised learning.
[0043] Post-processing: The pixel width of the segmented power transmission line mask is accurately calculated using a rotating caliper algorithm, and the icing thickness is calculated by combining the actual power transmission line diameter.
[0044] Decoder: After each upsampling stage, a spatial attention module (SA) and a channel attention module (CA) are added. SA calculates pixel weights through 3×3 convolution, and CA filters key channels through global average pooling and fully connected layers, which improves the model's attention to icy areas by 40%.
[0045] In this embodiment, during the training of the transmission line segmentation model, the loss function adopts cross-entropy loss (weight set to 0.4) + Dice loss (weight set to 0.6) to solve the sample imbalance problem of low pixel proportion of icing area in the dataset (about 5%~15%).
[0046] In this embodiment, the training process for the transmission line segmentation model includes: Dataset: 15,000 transmission line image samples were collected (including light icing <5mm, moderate icing 5~15mm, and heavy icing >15mm, accounting for 30%, 50%, and 20% respectively). LabelStudio was used as the annotation tool, with an annotation accuracy of 1 pixel. Training strategy: Cosine annealing learning rate (initial 0.001, minimum 0.00001), batch size 32, 120 training epochs, and MixUp data augmentation to improve generalization ability. Model deployment: Convert the trained model to ONNX format and deploy it to the edge computing development board (inference speed ≥20fps).
[0047] Step S104: Extract icing feature points from the transmission line area image, and calculate the center offset of the transmission line based on feature point matching, and correct the positional deviation of the transmission line before and after icing, so as to obtain the diameter of the iced transmission line and the actual diameter of the uniced transmission line.
[0048] Feature extraction: Within the transmission line area mask, the existing SIFT algorithm is used to extract 100-200 feature points (key point diameter 16 pixels) of the transmission line before icing, while the ORB algorithm (open source alternative) is used to extract feature points of the transmission line after icing. Feature matching: Feature points are matched using the existing FLANN matcher (fast nearest neighbor search library), valid pairs with a matching distance <20 are retained, the center offset of the transmission line is calculated (≤2 pixels), and the positional deviation of the transmission line before and after icing is corrected; Diameter measurement: Within the masked area of the icing region, take 10 measurement lines along the vertical direction of the transmission line, calculate the diameter (number of pixels) of each line after icing, remove the maximum and minimum values and take the average, and combine it with the calibration coefficient to obtain the actual diameter d1; similarly calculate the actual diameter d0 of the uniced transmission line.
[0049] Step S105: Based on the diameter of the iced transmission line and the actual diameter of the uniced transmission line, the initial icing thickness is obtained, and a temperature correction coefficient is introduced to correct the error caused by the change in icing density, so as to obtain the final icing thickness.
[0050] Basic calculation: Initial icing thickness h = (d1 - d0) / 2, thus obtaining the initial icing thickness; Error correction: A temperature correction coefficient k is introduced, where k = 1.02 - 0.001 × T, T is the ambient temperature in °C. When T < -20 °C, k = 1.04 to correct the error caused by the change in icing density; final thickness h_final = h × k.
[0051] The following is a comparison of the statistical results of the perspective transformation of the transmission line icing thickness calculation method provided in this embodiment of the invention with the reprojection error of the existing method, the cumulative error curve, and the comparison results of the segmentation task.
[0052] Table 1. Statistical results of reprojection error;
[0053] As shown in Table 1, the hybrid constraint in the transmission line icing thickness calculation method of this embodiment significantly outperforms the traditional DLT (Direct Linear Transform) method in all statistical indicators. The average reprojection error is reduced from 3.24 pixels to 1.15 pixels, a reduction of approximately 65%. Table 1 demonstrates that introducing physical constraints effectively suppresses the influence of point coordinate noise and mismatch, significantly improving geometric accuracy. Furthermore, according to... Figure 4 It can be seen that the cumulative error curve of the transmission line icing thickness calculation method in this embodiment of the invention is better than that of the traditional DLT method.
[0054] Table 2. Comparison of segmentation accuracy;
[0055] The average IoU (Intersection over Union) refers to the average overlap of all categories. In image segmentation, the predicted label of each pixel is usually compared with the ground truth label, and then the IoU between them is calculated.
[0056] Average Dice (mDice) is a core metric used to evaluate model performance in image segmentation tasks, especially suitable for multi-class segmentation scenarios. It measures the degree of overlap between the predicted results and the ground truth in each class, and takes the average value over all classes.
[0057] The F1 score is a weighted average of precision and recall, used to simultaneously consider the number of predicted positives and actual positives; the boundary F1 score is used to characterize the accuracy of the transmission line profile.
[0058] As shown in Table 2, the average IoU of the transmission line icing thickness calculation method of this embodiment is improved by 7.7 percentage points compared with that after DLT correction, and by 12.1 percentage points compared with the original image. The average Dice of the corrected method is also better than that of the DLT correction method. The improvement in the boundary F1-score after the correction method is more significant (+9.2%). Therefore, accurate perspective transformation enables the segmentation model to capture the icing edge more accurately, which is crucial for subsequent icing thickness measurement.
[0059] like Figure 2As shown, the transmission line icing thickness calculation system provided in this embodiment of the invention can be implemented in software. The transmission line icing thickness calculation system includes the following software modules: distortion correction module 201, image optimization module 202, image segmentation module 203, diameter calculation module 204, and icing thickness determination module 205.
[0060] The functions of each software module in the power transmission line icing thickness calculation system are described below: The distortion correction module 201 is used to acquire the original image of the transmission line and perform distortion correction. Image optimization module 202 is used to optimize the distortion-corrected transmission line image under the hybrid constraints constructed by geometric information and physical constraints, using a perspective transformation method based on sensor physical parameters and feature point coordinates. Image segmentation module 203 is used to process the optimized transmission line image using a trained transmission line segmentation model to obtain a transmission line region image. The diameter calculation module 204 is used to extract icing feature points in the image of the transmission line area, and calculate the center offset of the transmission line based on feature point matching and correct the position deviation of the transmission line before and after icing, so as to obtain the diameter of the iced transmission line and the actual diameter of the uniced transmission line. The icing thickness determination module 205 is used to obtain the initial icing thickness based on the diameter of the iced transmission line and the actual diameter of the uniced transmission line, and introduce a temperature correction coefficient to correct the error caused by the change in icing density, so as to obtain the final icing thickness.
[0061] It should be noted that each module in the transmission line icing thickness calculation system of this embodiment corresponds one-to-one with each step in the transmission line icing thickness calculation method in the above embodiment, and their specific implementation processes are the same, so they will not be repeated here.
[0062] The structure of the electronic device according to an embodiment of the present invention will be described in detail below. Figure 3 This is a schematic diagram of the composition structure of an electronic device provided in an embodiment of the present invention. It can be understood that... Figure 3 The diagram shows only an exemplary structure of the electronic device, not the entire structure. Some or all of the structures shown may be implemented as needed.
[0063] The electronic device provided in this embodiment of the invention includes: at least one processor 301, a memory 302, a user interface 303, and at least one network interface 304. The various components in the transmission line icing thickness calculation system are coupled together via a bus system 305. It can be understood that the bus system 305 is used to realize the connection and communication between these components. In addition to a data bus, the bus system 305 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 3 The general designated all buses as Bus System 305.
[0064] The user interface 303 may include a monitor, keyboard, mouse, trackball, click wheel, buttons, touchpad, or touch screen.
[0065] It is understood that memory 302 can be volatile memory or non-volatile memory, or both. In this embodiment of the invention, memory 302 is capable of storing data to support the operation of the terminal. Examples of this data include any computer programs used to operate on the terminal, such as operating systems and applications. The operating system includes various system programs, such as framework layers, core library layers, driver layers, etc., used to implement various basic services and handle hardware-based tasks. Applications can include various applications.
[0066] In some embodiments, the transmission line icing thickness calculation system provided in this invention can be implemented using a combination of hardware and software. For example, the transmission line icing thickness calculation system provided in this invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the transmission line icing thickness calculation method provided in this invention. For instance, the hardware decoding processor can employ one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.
[0067] As an example, processor 301 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., wherein the general-purpose processor can be a microprocessor or any conventional processor, etc.
[0068] As an example of the hardware implementation of the transmission line icing thickness calculation system provided in this embodiment of the invention, the device provided in this embodiment of the invention can be directly executed by a processor 301 in the form of a hardware decoding processor. For example, it can be executed by one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components to implement the transmission line icing thickness calculation method provided in this embodiment of the invention.
[0069] The memory 302 in this embodiment of the invention is used to store various types of data to support the operation of the transmission line icing thickness calculation system, or to store data for execution. Figure 1 The program code for the method shown. Examples of this data include: any executable instructions for operating on the transmission line icing thickness calculation system, such as executable instructions that can be included in the executable instructions to implement the transmission line icing thickness calculation method of the embodiments of the present invention.
[0070] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including functions for executing... Figure 1 The program code for the method shown. In such an embodiment, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by the central processing unit, it performs the various functions defined in the apparatus of this application.
[0071] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0072] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. 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.
Claims
1. A method for calculating the icing thickness of transmission lines, characterized in that, include: Acquire the original image of the transmission line and perform distortion correction; Under the hybrid constraints constructed by geometric information and physical constraints, the distortion-corrected transmission line image is optimized by using a perspective transformation method based on sensor physical parameters and feature point coordinates. The optimization of the distortion-corrected transmission line image under the hybrid constraints constructed by geometric information and physical constraints, using a perspective transformation method based on sensor physical parameters and feature point coordinates, specifically includes: Step a: Calculate the sensor pixel size; ； ； in: The sensor size is for the X-axis; The sensor size is defined by the Y-axis; the sensor's coordinate system is pre-built; Wsensor and Hsensor are the width and height dimensions of the sensor, respectively; Wimage and Himage are the width and height of the transmission line image, respectively. Step b: Construct the camera intrinsic parameter matrix K; ； ； ； Among them, focal length This represents the normalized focal length of the camera along the x and y axes of the power transmission line image, in pixels. This refers to the camera's physical focal length. Principal point coordinates, i.e., the intersection of the optical axis and the imaging plane; Step c: Normalization process; For each feature point on the transmission line image The coordinates of the corresponding feature points after normalization are ; ； ； Step d: Construct the expression for the mixed constraint; E = α·E_geometry + β·E_physics + γ·E_consistency; Where E is the hybrid constraint; E_geometry is the geometric error; E_physics is the physical constraint error; E_consistency is the consistency constraint; α is the geometric error weight, which controls the strictness of the correspondence between points; β is the physical constraint weight, which controls the constraint strength of the camera physical model; and γ is the consistency weight, which is the regularization strength to prevent overfitting and singular solutions. The expression for geometric error is: E_geometry = Σ||H·src_norm_i - dst_norm_i||²; The expression for the physical constraint error is: E_physics = ||K·H·K -1 - H direct ||² ; The consistency constraint E_consistency is a regularization term; Where src_norm_i is the normalized camera coordinate of the i-th feature point in the transmission line image before optimization; H is the homography matrix in the normalized coordinate system to be solved; dst_norm_i is the normalized camera coordinate of the i-th corresponding feature point in the transmission line image after optimization. The homography matrix is obtained directly from pixel coordinates using geometric methods; By utilizing geometric correspondences and camera physical parameters, the optimal homography matrix is obtained by constructing a hybrid constraint optimization problem; The optimized transmission line image is processed using a trained transmission line segmentation model to obtain a transmission line region image. Within the transmission line area mask, feature points of the transmission line before icing and feature points of the transmission line after icing are extracted; feature point matching is performed on the feature points of the transmission line before icing and feature points of the transmission line after icing, the center offset of the transmission line is calculated, and the positional deviation of the transmission line before and after icing is corrected to obtain the diameter of the iced transmission line and the actual diameter of the uniced transmission line. Based on the diameter of the iced transmission line and the actual diameter of the uniced transmission line, the initial icing thickness is obtained, and a temperature correction coefficient is introduced to correct the error caused by the change in icing density, thus obtaining the final icing thickness.
2. The method for calculating the icing thickness of transmission lines as described in claim 1, characterized in that, The formula for calculating the weight of geometric error is: ； ； in, For variance estimation of geometric errors, measures the noise level of point coordinates or the degree of deviation of the initial matrix from the true transformation; This is the initial estimated homography matrix; The first image of the transmission line before optimization i Homogeneous coordinates of the feature points; For the optimized transmission line image, the first i Homogeneous coordinates of feature points.
3. The method for calculating the icing thickness of transmission lines as described in claim 1, characterized in that, The formula for calculating the weight of physical constraint error is: ； ； in: For variance estimation of physical constraint error, it measures the difference between the homography matrix after transformation from the normalized coordinate system back to the pixel coordinate system and the directly calculated homography matrix; is the inverse of the camera intrinsic parameter matrix; K is the camera intrinsic parameter matrix; This is the representation of the initial homography matrix in the normalized camera coordinate system; The homography matrix is obtained directly from pixel coordinates using geometric methods; It is the Frobenius norm.
4. The method for calculating the icing thickness of transmission lines as described in claim 1, characterized in that, The formula for calculating the weights of consistency constraints is: ； ； in, The variance estimate of the regularization error measures the initial homography matrix. The degree of deviation from the identity matrix I; It is the Frobenius norm.
5. The method for calculating the icing thickness of transmission lines as described in claim 1, characterized in that, In the process of training the transmission line segmentation model, its loss function is composed of a weighted sum of cross-entropy loss and Dice loss.
6. The method for calculating the icing thickness of transmission lines as described in claim 1, characterized in that, The expression for the final icing thickness is: h_final = h × k; k = 1.02 - 0.001 × T; Where h_final is the final icing thickness; h is the initial icing thickness; k is the temperature correction factor; and T is the ambient temperature.
7. A system for calculating the icing thickness of transmission lines, characterized in that, The method for calculating the icing thickness of transmission lines based on any one of claims 1-6 includes: The distortion correction module is used to acquire the original image of the transmission line and perform distortion correction. The image optimization module is used to optimize the distortion-corrected transmission line image under the hybrid constraints constructed by geometric information and physical constraints, using a perspective transformation method based on sensor physical parameters and feature point coordinates. The image segmentation module is used to process the optimized transmission line image using a trained transmission line segmentation model to obtain the transmission line region image. The diameter calculation module is used to extract icing feature points in the image of the transmission line area, and calculate the center offset of the transmission line based on feature point matching and correct the positional deviation of the transmission line before and after icing, so as to obtain the diameter of the iced transmission line and the actual diameter of the uniced transmission line. The icing thickness determination module is used to obtain the initial icing thickness based on the diameter of the iced transmission line and the actual diameter of the uniced transmission line, and introduces a temperature correction coefficient to correct the error caused by the change in icing density, so as to obtain the final icing thickness.
8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the method for calculating the ice thickness of transmission lines as described in any one of claims 1-6.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the method for calculating the icing thickness of transmission lines as described in any one of claims 1-6.