Dual-light image monitoring method and device for icing monitoring of power transmission line

Abstract

The embodiment of the invention provides a dual-light image monitoring method and device for power transmission line icing monitoring and a storage medium. The method comprises the following steps: in an icing period, respectively acquiring a visible light image and an infrared image of an iced conductor at the same position at preset time intervals; performing size unification and gray level normalization processing on the visible light image and the infrared image; fusing the pre-processed visible light image and infrared image to obtain a fused image; extracting the edge contour of the iced conductor from the fused image by using a gradient-based edge detection algorithm; and determining the icing thickness of the ice-coated wire based on the comparison of the edge contour and the edge contour of the ice-coated wire when the ice-coated wire is not coated with the ice.

Description

Technical Field

[0001] This application relates to the field of transmission line monitoring, specifically to a dual-light image monitoring method, device, and storage medium for monitoring icing on transmission lines. Background Technology

[0002] Transmission lines in high-altitude, snow-covered mountainous areas are highly susceptible to icing. Severe icing can overload lines and towers, leading to accidents such as line galloping, wire breaks, and insulator flashover due to icing, seriously threatening the safe and stable operation of transmission lines. A line fault or damage can result in enormous economic losses.

[0003] For power grid anti-icing, timely understanding of the icing status of each power line is crucial for scientifically guiding subsequent de-icing technologies. Therefore, power grid icing monitoring plays a vital role in the anti-freezing and de-icing system. Currently, various online icing monitoring methods for transmission lines have some shortcomings: tension monitoring sensors have short lifespans, low data transmission stability, and are easily affected by environmental factors such as temperature and humidity, leading to performance degradation and data distortion. Microwave monitoring cannot directly measure the thickness of line ice, and the data is unstable during icing formation, with potential jumps in ice thickness. Image monitoring can provide intuitive feedback on icing and assist in channel monitoring. However, due to the short wavelength of visible light (400-700nm), small particles in the air such as fog and dust can block light, resulting in poor image capture performance in adverse weather conditions such as rain, snow, fog, and sandstorms, sometimes even leading to a complete loss of monitoring capability. Infrared imaging forms images by sensing the heat of objects and can function normally even in complete darkness. Furthermore, because infrared wavelengths (8-14µm) are longer than visible light, they are less affected by aerosols during propagation, resulting in better fog penetration. However, due to factors such as thermal imaging principles and atmospheric transmission characteristics, infrared lenses also suffer from problems such as low resolution, low contrast, low signal-to-noise ratio, and blurred edge details.

[0004] Therefore, there is an urgent need to provide a new method for monitoring icing on power transmission lines to solve the problem that visible light monitoring is ineffective in low-visibility weather conditions such as fog and haze. Summary of the Invention

[0005] The purpose of this application is to provide a dual-light image monitoring method, device, and storage medium for monitoring icing on power transmission lines.

[0006] To achieve the above objectives, the first aspect of this application provides a dual-light image monitoring method for monitoring icing on transmission lines, comprising:

[0007] During the freezing period, visible light and infrared images of the icy conductor are collected at the same location at preset intervals.

[0008] Visible light and infrared images are subjected to size unification and grayscale normalization.

[0009] The preprocessed visible light image and infrared image are fused to obtain a fused image;

[0010] A gradient-based edge detection algorithm was used to extract the edge contours of icy conductors from the fused image.

[0011] The icing thickness of the icing conductor is determined by comparing its edge profile with that of an icy conductor when it is not iced.

[0012] In this embodiment of the application, fusing the preprocessed visible light image and infrared image to obtain a fused image includes: decomposing the visible light image and infrared image into low-frequency components and high-frequency components respectively; performing fusion based on pixel value comparison on the low-frequency components; performing weighted fusion based on statistical features on the high-frequency components; and superimposing the fused low-frequency components and high-frequency components to obtain the fused image.

[0013] In this embodiment, the low-frequency components are fused based on pixel value comparison according to the following formula:

[0014]

[0015] Among them, L ir It refers to the low-frequency component of the infrared image separated by a Gaussian low-pass filter, L vis It refers to the low-frequency component of the visible light image separated by a Gaussian low-pass filter, L fuse It refers to the low-frequency fusion component of infrared and visible light images.

[0016] in, I ir Refers to infrared images, I vis σ refers to the visible light image, which can be obtained based on empirical values, manual adjustment, or by using an image processing library. x and y refer to the coordinates of pixels in the image.

[0017] In this embodiment, high-frequency components are weighted and fused based on statistical features according to the following formula:

[0018]

[0019] Among them, H fuse This refers to the high-frequency fusion component of infrared and visible light images, H. vis H refers to the high-frequency components of a visible light image. ir λ1 and λ2 refer to the high-frequency components of the infrared image, while λ1 and λ2 refer to the eigenvalues ​​of the covariance matrix of the pixel matrix composed of the visible light image and the infrared image.

[0020] In this embodiment, the method of extracting the edge contour of the icy conductor from the fused image using a gradient-based edge detection algorithm includes: using the Sobel operator to determine the gradient values ​​of each pixel in the x and y directions of the fused image; determining the gradient magnitude of each pixel based on the gradient values; approximating the gradient direction of each pixel and comparing the gradient magnitudes of adjacent pixels along its gradient direction to perform non-maximum suppression; judging the gradient magnitude based on preset high and low thresholds to determine strong edge points, weak edge points, and non-edge points; and connecting strong edge points and weak edge points adjacent to the strong edge points to determine the edge contour of the icy conductor.

[0021] In this embodiment of the application, determining the gradient magnitude of each pixel in the fused image in the x and y directions includes: calculating its gradient G in the x direction using the Sobel operator. x and the gradient G in the y-direction y Based on gradient G x and gradient G y Determine the gradient magnitude G;

[0022] in, I refers to the fused image.

[0023] The gradient magnitude G is determined according to the following formula:

[0024]

[0025] In this embodiment, determining strong edge points, weak edge points, and non-edge points by judging the gradient magnitude based on preset high and low thresholds includes: determining a pixel as a strong edge point when the gradient magnitude of the pixel is greater than the high threshold; determining a pixel as a non-edge point when the gradient magnitude of the pixel is less than the low threshold; and determining a pixel as a weak edge point when the gradient magnitude of the pixel is greater than or equal to the low threshold and less than or equal to the high threshold. The high and low thresholds are determined based on image quality and the continuity requirements of the edge contour.

[0026] In this embodiment of the application, the ice thickness of the icing conductor is determined according to the following formula:

[0027]

[0028] Wherein, d4 refers to the icing thickness of the icing conductor, d1 refers to the diameter of the icing conductor when it is not iced, d2 refers to the outer contour pixel width of the icing conductor when it is not iced, and d3 refers to the outer contour pixel width of the icing conductor when it is iced.

[0029] A second aspect of this application provides a dual-light image monitoring device for monitoring icing on transmission lines, comprising:

[0030] The memory is configured to store instructions;

[0031] The processor is configured to retrieve instructions from memory and, when executing the instructions, to implement the aforementioned dual-light image monitoring method for monitoring icing on transmission lines.

[0032] A third aspect of this application provides a machine-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the aforementioned dual-light image monitoring method for monitoring icing on transmission lines.

[0033] This method monitors the icing condition of transmission lines using both infrared imaging and visible light dual-channel monitoring. By fusing infrared and visible light imaging, it combines the advantages of both methods. Compared to visible light monitoring alone, it can perform normal monitoring in rainy, snowy, and foggy weather. Furthermore, compared to infrared monitoring alone, this monitoring method offers higher resolution, contrast, and edge detail.

[0034] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0035] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings:

[0036] Figure 1 The schematic diagram illustrates a flow chart of a dual-light image monitoring method for monitoring icing on transmission lines according to an embodiment of this application;

[0037] Figure 2 The schematic diagram illustrates a flow chart of a dual-light image monitoring method for monitoring icing on transmission lines according to another embodiment of this application;

[0038] Figure 3 This illustration schematically shows an image monitoring process according to an embodiment of the present application;

[0039] Figure 4 The diagram illustrates the internal structure of a computer device according to an embodiment of this application. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0041] Figure 1 A schematic flowchart of a dual-light image monitoring method for monitoring icing on transmission lines according to an embodiment of this application is shown. Figure 1 As shown in one embodiment of this application, a dual-light image monitoring method for monitoring icing on transmission lines is provided, comprising the following steps:

[0042] Step 102: During the icing period, at preset intervals, collect visible light and infrared images of the icy conductor at the same location.

[0043] Step 104: Perform size unification and grayscale normalization on the visible light image and the infrared image;

[0044] Step 106: Fuse the preprocessed visible light image and infrared image to obtain a fused image;

[0045] Step 108: Extract the edge contours of the icy conductor from the fused image using a gradient-based edge detection algorithm;

[0046] Step 110: Determine the icing thickness of the icing conductor based on a comparison of the edge profile with the edge profile of the icing conductor when it is not iced.

[0047] The icing period refers to the time when transmission lines are prone to icing, typically during winter or early spring, a seasonal period of low ambient temperature and high humidity, such as during periods of rain, snow, fog, and freezing rain. During the icing period, the processor can acquire visible light and infrared images of the iced conductor at the same location at preset time intervals. The preset time interval is a pre-set time difference that can be adjusted based on historical meteorological data, warning levels, or actual needs, such as shortening the interval during severe ice storm warnings. In a specific embodiment, the preset time interval can be set to 4 hours. Visible light images are images captured by a visible light camera module, with wavelengths ranging from 400 to 700 nanometers. These images are characterized by high resolution, high contrast, and clear edge details. Infrared images are images captured by an infrared camera module, formed by sensing the temperature distribution on the surface of an object, with wavelengths ranging from 8 to 14 μm, longer than visible light. In fog-free, lightly foggy, or well-lit daytime conditions, visible light images provide a very clear outline of the conductor, making them an ideal data source for measuring icing thickness. Infrared images can penetrate obstacles and ensure continuous monitoring under adverse visibility conditions such as rain, snow, fog, and haze, as well as at night. However, their drawbacks include low resolution and blurred edges. Therefore, in this embodiment, visible light and infrared images acquired at the same location can be combined to ultimately determine the ice thickness of the icing conductor. This method fundamentally solves the problem of single sensor failure under specific severe weather conditions.

[0048] Next, the processor can perform size unification and grayscale normalization on the visible light and infrared images. For example, the visible light and infrared images can be resized to the same pixel size. Since visible light cameras typically have higher resolution, the visible light image can be scaled to the same size as the infrared image. Grayscale normalization refers to mapping the grayscale values ​​of a grayscale image to a uniform standard range, typically [0,1] or [0,255]. Therefore, after resizing the visible light and infrared images to the same pixel size, the image color mode can be converted from RGB mode to grayscale mode. Here, let f(x,y) represent the infrared and visible light grayscale images, and the grayscale range of these images can be represented as f... min ≤f(x,y)≤f max , where f max f mim These represent the maximum and minimum grayscale values ​​of the infrared and visible light images, respectively. The grayscale ranges of the infrared and visible light images are then normalized.

[0049] r = [f(x,y) - f mim ] / (f max -f min )

[0050] In the formula, r represents the normalized grayscale value of the infrared and visible light images, and it satisfies 0≤r≤1.

[0051] This operation eliminates the differences in overall brightness and contrast between visible light and infrared images caused by different imaging mechanisms, allowing them to be fused on the same benchmark and improving the fusion effect. Furthermore, the processor can fuse the preprocessed visible light and infrared images to obtain a fused image. Then, a gradient-based edge detection algorithm can be used to extract the edge contour of the icy conductor from the fused image. The edge contour is the set of pixels representing the outer boundary of the conductor, extracted by the edge detection algorithm. The processor can determine the ice thickness of the icy conductor by comparing the edge contour with the edge contour of the icy conductor when it is not iced. When the ice thickness exceeds a first preset threshold, or when the ice thickness growth rate exceeds a second preset threshold, the processor can output an alarm message. The ice thickness growth rate refers to the increase in ice thickness per unit time. The calculation method for the ice thickness growth rate v is as follows:

[0052]

[0053] Where b1 is the current icing thickness, b2 is the previous icing thickness, and b0 is the designed icing thickness.

[0054] In one embodiment, both the first preset threshold and the second preset threshold are pre-set critical values. The first preset threshold relates to the absolute value of the icing thickness, and the second preset threshold relates to the rate of increase of the icing thickness.

[0055] In one specific embodiment, the threshold for the icing thickness growth rate v is 0.3 times the designed icing thickness of the conductor. The threshold for the icing thickness is 0.6 times the designed icing thickness of the conductor.

[0056] This method monitors the icing condition of transmission lines using both infrared imaging and visible light dual-channel monitoring. By fusing infrared and visible light imaging, it combines the advantages of both methods. Compared to visible light monitoring alone, it can perform normal monitoring in rainy, snowy, and foggy weather. Furthermore, compared to infrared monitoring alone, this monitoring method offers higher resolution, contrast, and edge detail.

[0057] In one embodiment, fusing a preprocessed visible light image and an infrared image to obtain a fused image includes: decomposing the visible light image and the infrared image into low-frequency components and high-frequency components, respectively; performing pixel value comparison-based fusion on the low-frequency components; performing statistical feature-based weighted fusion on the high-frequency components; and superimposing the fused low-frequency components and high-frequency components to obtain the fused image.

[0058] Low-frequency components refer to the smooth, gradual gray-level changes in an image, representing the image's basic outline and general structure. These low-frequency components can be separated from the source image using a Gaussian low-pass filter. High-frequency components refer to the sharp, drastic gray-level changes in an image, representing the image's edges, texture, and details. These high-frequency components can be calculated from the source image and the low-frequency image. After decomposing the visible light image and infrared image into low-frequency and high-frequency components respectively, the processor can perform pixel-value-based fusion on the low-frequency components. That is, it compares the gray-level values ​​of the two low-frequency images pixel by pixel, selecting the pixel with the larger gray-level value as the fused low-frequency pixel value. It can be seen that the "larger value" rule used in this embodiment tends to retain information with higher energy. In an image, this typically means retaining the more prominent thermal target outlines in the infrared image and the brighter background structure in the visible light image, ensuring a clear basic structure of the fused image. Furthermore, the processor can perform weighted fusion on the high-frequency components based on statistical features. Specifically, weighted principal component analysis can be used to perform weighted fusion on the high-frequency components based on statistical features. The weights are determined by the eigenvalues ​​of the covariance matrix. Then, the processor can superimpose the fused low-frequency components with the high-frequency components to obtain a fused image.

[0059] In one embodiment, weighted fusion of high-frequency components based on statistical features includes: constructing pixel matrices of high-frequency components from visible light and infrared images; determining the covariance matrix and eigenvalues ​​of the pixel matrices; and performing weighted average fusion of the high-frequency components based on the eigenvalues. For statistical analysis, in this embodiment, the pixel values ​​of the two high-frequency component images are reorganized into a mathematical matrix. Assuming the image size is M*N pixels, the size of this matrix X is (M*N)*2. The first column X1 is H... vis All pixel values, the second column X2 is H ir All pixel values. Each row represents the high-frequency intensity value of a pixel location in both images. Where H... vis H refers to the high-frequency components of a visible light image. ir This refers to the high-frequency components of the infrared image. Then, the covariance matrix of the pixel matrix and its eigenvalues ​​can be determined, and the high-frequency components are then weighted and averaged based on these eigenvalues. The eigenvalues ​​λ1 and λ2 are a set of scalar values ​​(λ1 ≥ λ2 ≥ 0) obtained by eigenvalue decomposition of the covariance matrix R.

[0060] Each eigenvalue corresponds to an eigenvector. The eigenvector indicates the main direction of data change, while the eigenvalue quantifies the magnitude of data change in that direction, i.e., the variance. In other words, the eigendirection corresponding to a larger eigenvalue λ1 is the direction with the most information and the most significant change in the data. The direction corresponding to a smaller eigenvalue λ2 has relatively less information. In the context of image fusion, eigenvalues ​​are interpreted as the "information" or "importance" contained in the corresponding image component. Since visible light images typically have richer high-frequency details, their corresponding eigenvalue λ1 will be greater than λ2 in most cases. Therefore, in the fusion result, the eigenvalue from H... vis The sharp edge details are enhanced and preserved. At the same time, infrared high-frequency information is not completely discarded, but rather incorporated with a small weight λ², which helps to supplement some edge cues under extremely harsh visible light conditions. Since the weights are not fixed but calculated based on the image data acquired each time, they can adapt to imaging variations under different weather conditions, achieving optimal fusion.

[0061] Specifically, if the visible light source image and the infrared source image are both M×N in size, then they can form a pixel matrix X of size MN×2:

[0062]

[0063] The covariance matrix R is calculated as follows:

[0064]

[0065] in,

[0066]

[0067] Since the covariance matrix R is a positive semi-definite matrix, its eigenvalues ​​λ1 and λ2 are both non-negative. The high-frequency components H of the infrared image... ir and the high-frequency component H of visible light images vis Fusion:

[0068]

[0069] Final fused image I fuse for:

[0070] I fuse =L fuse +H fuse .

[0071] In one specific embodiment, the low-frequency components are fused based on pixel value comparison according to the following formula:

[0072]

[0073] Among them, L ir It refers to the low-frequency component of the infrared image separated by a Gaussian low-pass filter, L vis It refers to the low-frequency component of the visible light image separated by a Gaussian low-pass filter, L fuse It refers to the low-frequency fusion component of infrared and visible light images.

[0074] in, I ir Refers to infrared images, I vis σ refers to the visible light image, which can be obtained based on empirical values, manual adjustment, or by using an image processing library. x and y refer to the coordinates of pixels in the image.

[0075] In one embodiment, high-frequency components can be weighted and fused based on statistical features according to the following formula:

[0076]

[0077] Among them, H fuse This refers to the high-frequency fusion component of infrared and visible light images, H. vis H refers to the high-frequency components of a visible light image. ir λ1 and λ2 refer to the high-frequency components of the infrared image, while λ1 and λ2 refer to the eigenvalues ​​of the covariance matrix of the pixel matrix composed of the visible light image and the infrared image.

[0078] In one embodiment, extracting the edge contour of an icy conductor from a fused image using a gradient-based edge detection algorithm includes: using the Sobel operator to determine the gradient values ​​of each pixel in the fused image in the x and y directions; determining the gradient magnitude of each pixel based on the gradient values; approximating the gradient direction of each pixel and comparing the gradient magnitudes of adjacent pixels along its gradient direction to perform non-maximum suppression; judging the gradient magnitude based on preset high and low thresholds to determine strong edge points, weak edge points, and non-edge points; and connecting strong edge points and adjacent weak edge points to determine the edge contour of the icy conductor.

[0079] A gradient is a vector representing the direction and magnitude of the most dramatic change in brightness at a pixel in an image. The gradient magnitude refers to the rate of change of the gradient, i.e., the "intensity" or "distinctiveness" of the edge. In monitoring icy guideways, the edges of the guideways or ice layers exhibit significant brightness or temperature differences compared to their background (sky, mountains), resulting in large gradient magnitudes. Calculating the gradient magnitude is the first step in finding all potential edge points. Therefore, the processor can use the Sobel operator to determine the gradient values ​​of each pixel in the x and y directions of the fused image, and then determine the gradient magnitude of each pixel based on these gradient values. Here, the gradient values ​​in the x and y directions of each pixel represent the rate of change of brightness in the horizontal (x-axis) and vertical (y-axis) directions, respectively.

[0080] Specifically, in one embodiment, determining the gradient magnitude of each pixel in the fused image in the x and y directions includes: calculating its gradient G in the x direction using the Sobel operator. x and the gradient G in the y-direction y Based on gradient G x and gradient G y Determine the gradient magnitude G.

[0081] in, I refers to the fused image, where the gradient magnitude G is determined according to the following formula:

[0082]

[0083] like Figure 2 As shown, after determining the gradient magnitude of each pixel, the processor can approximate the gradient direction of each pixel and compare the gradient magnitudes of adjacent pixels along its gradient direction to perform non-maximum suppression. The gradient direction refers to the angle of the gradient vector, indicating the direction of the fastest increase in brightness at that point in the image; this direction is always perpendicular to the edge itself. Approximation involves approximating the calculated continuous gradient direction angle to a finite number of discrete directions. Specifically, these can be values ​​such as 0°, 45°, 90°, 135°, 180°, 225°, 270°, and 315°. After obtaining the gradient magnitude and direction, the processor compares the gradient magnitude of the current pixel with its two preceding and following adjacent pixels along the gradient direction, i.e., the direction perpendicular to the edge. If the gradient magnitude of the current pixel is a local maximum, it is retained as a candidate edge point; otherwise, its magnitude is set to zero. This process is non-maximum suppression. Understandably, this operation is a key step in the Canny algorithm to ensure that the edges are both "fine" and "accurate." This operation eliminates the width of the edges, ensuring that the final extracted edges are thin lines with a width of only one pixel, thereby greatly improving the accuracy of edge positioning, which is crucial for subsequent icing thickness measurement.

[0084] After approximating the gradient direction of each pixel and comparing the gradient magnitudes of adjacent pixels along its gradient direction for non-maximum suppression, two threshold values ​​can be introduced to filter for true edges: a preset high threshold and a preset low threshold. Then, the gradient magnitude is judged based on the preset high and low thresholds to determine strong edge points, weak edge points, and non-edge points. In one embodiment, judging the gradient magnitude based on the preset high and low thresholds to determine strong edge points, weak edge points, and non-edge points includes: if the gradient magnitude of a pixel is greater than the high threshold, the pixel is determined to be a strong edge point; if the gradient magnitude of a pixel is less than the low threshold, the pixel is determined to be a non-edge point; if the gradient magnitude of a pixel is greater than or equal to the low threshold and less than or equal to the high threshold, the pixel is determined to be a weak edge point. The high and low thresholds are determined based on image quality and edge contour continuity requirements.

[0085] As can be seen, this embodiment introduces a preset high threshold T. max and the preset low threshold T min To determine the contour edges. For any pixel, if the gradient magnitude G of the pixel is greater than T... max If T min <G<T max If G < T, then the pixel is a weak edge point. min If the threshold T is not an edge point, then the pixel is not an edge point. max and T min The shape is determined based on image quality and actual outline requirements. Finally, connecting strong edge pixels with their adjacent weak edge pixels forms a complete conductor edge outline.

[0086] In one specific embodiment, a dual-light image monitoring method for monitoring icing on transmission lines is provided. The method includes: during the icing period, acquiring visible light and infrared images of an iced conductor at the same location at preset time intervals; performing size unification and grayscale normalization processing on the visible light and infrared images; fusing the preprocessed visible light and infrared images to obtain a fused image; extracting the edge contour of the iced conductor from the fused image using a gradient-based edge detection algorithm; determining the icing thickness of the iced conductor based on a comparison of the edge contour with the edge contour of the iced conductor when it is not iced; and outputting an alarm message when the icing thickness exceeds a first preset threshold or the icing thickness growth rate exceeds a second preset threshold.

[0087] like Figure 3 As shown, before acquiring visible light and infrared images of the icy conductor at the same location at preset time intervals, the following steps are also included:

[0088] Step 1: The monitoring device is powered on, activates the wireless communication network, and interacts with the server to obtain various parameters from the server-side equipment. These parameters include configuration parameters such as timed image capture time, heating conditions, and image size. Timed image capture and transmission are performed according to the preset operating mode.

[0089] In this step, the scheduled photo-taking time is the time of day during which automatic photo taking occurs; at other times, it enters a scheduled sleep mode unless remotely woken up. For example, it can be set to take photos at 0:00, 8:00, and 16:00 every day.

[0090] In this step, the heating conditions include temperature threshold, humidity threshold, heating duration, and heating channel. When the micro-meteorological monitoring module detects that the ambient temperature and humidity have reached the set thresholds, it automatically activates the heating function for the designated heating channel within the set heating duration.

[0091] Step 2: After configuration, the device enters a timed sleep mode to save energy to the maximum extent.

[0092] Step 3: The device is woken up when it receives a wake-up command from the server or on-site debugging tool.

[0093] Step 4: Take a picture after waking up: When the set photo-taking time is reached, a timed photo is triggered; when a photo-taking command is received from the server or on-site debugging tool, a manual photo is triggered; otherwise, return to step 2 to enter timed sleep mode.

[0094] Step 5: When the micro-meteorological monitoring module detects that the ambient temperature and humidity have reached the set threshold, it triggers automatic heating; when it receives a heating command from the server or on-site debugging tools, it triggers manual heating. Otherwise, skip step 5.

[0095] Step 6: Activate the camera to take a picture. You can choose to use either an infrared camera module or a visible light camera module to take a picture.

[0096] Step 7: Transmit the acquired transmission line images wirelessly to the monitoring center server via the APN private network and determine whether the transmission is complete. If not, continue the transmission; if yes, return to step 2 and enter the timed sleep mode.

[0097] In one embodiment, determining the icing thickness of the icing conductor according to the following formula includes:

[0098]

[0099] Wherein, d4 refers to the icing thickness of the icing conductor, d1 refers to the diameter of the icing conductor when it is not iced, d2 refers to the outer contour pixel width of the icing conductor when it is not iced, and d3 refers to the outer contour pixel width of the icing conductor when it is iced.

[0100] This method monitors the icing condition of transmission lines using both infrared imaging and visible light dual-channel monitoring. By fusing infrared and visible light imaging, it combines the advantages of both methods, allowing for normal monitoring even in rain, snow, and foggy weather compared to visible light monitoring alone. Furthermore, it offers higher resolution, contrast, and edge detail compared to infrared monitoring alone.

[0101] In one embodiment, a dual-light image monitoring device for monitoring icing on transmission lines is provided. This device is deployed at high points on transmission line towers of various voltage levels for monitoring icing on transmission lines. The device includes an infrared camera module, a visible light camera module, a lens heating module, a micro-meteorological monitoring module, a communication module, a lithium battery module, and a solar panel. Specifically:

[0102] The infrared camera module uses an infrared imaging lens with fog-penetrating capabilities, used to capture infrared images of the line in dense fog.

[0103] The visible light camera module can automatically activate the fill light function at night or in low light conditions to capture visible light images of the line in fog-free or light fog weather.

[0104] The lens heating module is used to remove fog or ice from the lens by heating it.

[0105] The micro-meteorological monitoring module is used to measure ambient temperature, humidity, wind speed and direction, and rainfall.

[0106] Communication module: transmits monitoring data to the monitoring center server and transmits control commands from the monitoring center server to the monitoring device.

[0107] Lithium battery module: A high-capacity, low-temperature battery used to power the monitoring device.

[0108] Solar panel: Connected to the lithium battery module, used to charge the lithium battery module.

[0109] The lens heating module includes a visible light imaging heating module and an infrared imaging heating module. The former uses a silver-plated film for heating, covering the entire visible light lens; the latter uses a heating element that surrounds the infrared imaging lens. The lens heating module has an automatic heating function; when the micro-meteorological monitoring module detects that the ambient temperature and humidity have reached the set thresholds, it automatically activates the heating. The lithium battery module can monitor the lithium battery's charge and voltage in real time and manage the lithium battery's external power supply. Outside of rain, snow, and freezing periods, priority is given to ensuring the lithium battery's endurance; when the remaining charge or voltage of the lithium battery falls below the set threshold, the device enters a sleep state. During rain, snow, and freezing periods, priority is given to ensuring the normal operation of the monitoring device, allowing the remaining charge or voltage of the lithium battery to fall below the set threshold.

[0110] The following is a specific example. In this example, the infrared camera module of the dual-light image monitoring device used for monitoring icing on transmission lines has a 15mm lens, a response band of 8–14μm, a resolution of 256×192, and uses a vanadium oxide uncooled detector. The visible light camera module has a 12mm lens and a maximum image resolution of 2688×1520. The lithium battery module has a capacity of 100Ah and an operating voltage of 12V. The solar panel has a power output of 100W.

[0111] Figure 1 This is a flowchart illustrating a dual-light image monitoring method for monitoring icing on transmission lines in one embodiment. It should be understood that, although... Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise explicitly stated herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Furthermore, Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0112] This application provides a storage medium storing a program that, when executed by a processor, implements the aforementioned dual-light image monitoring method for monitoring icing on transmission lines.

[0113] This application provides a processor for running a program, wherein the program executes the above-described dual-light image monitoring method for monitoring icing on power transmission lines.

[0114] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown), and a database (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02, and a database (not shown). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A04. The network interface A02 is used for communication with external terminals via a network connection. When the computer program B02 is executed by the processor A01, it implements a dual-light image monitoring method for monitoring icing on power transmission lines.

[0115] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0116] This application provides a computer (electronic) device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of any of the above dual-light image monitoring methods for monitoring icing on transmission lines.

[0117] This application also provides a computer program product that, when executed on a data processing device, is adapted to execute a program having steps for initializing a dual-light image monitoring method for monitoring icing on transmission lines.

[0118] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0119] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0120] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0121] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0122] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0123] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0124] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0125] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0126] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A dual-light image monitoring method for monitoring icing on transmission lines, characterized in that, The method includes: During the freezing period, visible light and infrared images of the icy conductor are collected at the same location at preset intervals. The visible light image and infrared image are subjected to size unification and grayscale normalization processing; The preprocessed visible light image and infrared image are fused to obtain a fused image; The edge contours of the icy conductor are extracted from the fused image using a gradient-based edge detection algorithm. The icing thickness of the icing conductor is determined by comparing the edge profile with the edge profile of the icing conductor when it is not iced.

2. The method according to claim 1, characterized in that, The process of fusing the preprocessed visible light image and infrared image to obtain the fused image includes: The visible light image and infrared image are respectively decomposed into low-frequency components and high-frequency components; The low-frequency components are fused based on pixel value comparison; The high-frequency components are then subjected to weighted fusion based on statistical features. The fused low-frequency components are superimposed with the high-frequency components to obtain the fused image.

3. The method according to claim 2, characterized in that, The low-frequency components are fused based on pixel value comparison according to the following formula: Among them, L ir It refers to the low-frequency component of the infrared image separated by a Gaussian low-pass filter, L vis It refers to the low-frequency component of the visible light image separated by a Gaussian low-pass filter, L fuse It refers to the low-frequency fusion component of infrared and visible light images; in, I ir Refers to infrared images, I vis σ refers to the visible light image, which can be obtained based on empirical values, manual adjustment, or by using an image processing library. x and y refer to the coordinates of pixels in the image.

4. The method according to claim 2, characterized in that, The high-frequency components are weighted and fused based on statistical features according to the following formula: Among them, H fuse This refers to the high-frequency fusion component of infrared and visible light images, H. vis H refers to the high-frequency components of a visible light image. ir λ1 and λ2 refer to the high-frequency components of the infrared image, while λ1 and λ2 refer to the eigenvalues ​​of the covariance matrix of the pixel matrix composed of the visible light image and the infrared image.

5. The method according to claim 1, characterized in that, Extracting the edge contour of the icy conductor from the fused image using a gradient-based edge detection algorithm includes: The Sobel operator is used to determine the gradient values ​​of each pixel in the fused image in the x and y directions; The gradient magnitude of each pixel is determined based on the gradient value. The gradient direction of each pixel is approximated, and the gradient magnitudes of adjacent pixels are compared along the gradient direction to perform non-maximum suppression. The gradient magnitude is judged based on preset high and low thresholds to determine strong edge points, weak edge points and non-edge points; Connect the strong edge points and the weak edge points adjacent to the strong edge points to determine the edge profile of the icing conductor.

6. The method according to claim 5, characterized in that, Determining the gradient magnitude of each pixel in the fused image in the x and y directions includes: Calculate its gradient G in the x-direction using the Sobel operator. x and the gradient G in the y-direction y ; Based on gradient G x and gradient G y Determine the gradient magnitude G; in, I refers to the fused image. The gradient magnitude G is determined according to the following formula:

7. The method according to claim 5, characterized in that, Based on preset high and low thresholds, the gradient magnitude is judged to determine strong edge points, weak edge points, and non-edge points, including: If the gradient magnitude of a pixel is greater than the high threshold, the pixel is determined to be a strong edge point. If the gradient magnitude of a pixel is less than the low threshold, the pixel is determined to be a non-edge point. If the gradient magnitude of a pixel is greater than or equal to the low threshold and less than or equal to the high threshold, the pixel is determined to be a weak edge point. The high threshold and the low threshold are determined based on the requirements of image quality and the continuity of edge contours.

8. The method according to claim 1, characterized in that, The icing thickness of the icing conductor is determined according to the following formula: Wherein, d4 refers to the icing thickness of the icing conductor, d1 refers to the diameter of the icing conductor when it is not iced, d2 refers to the outer contour pixel width of the icing conductor when it is not iced, and d3 refers to the outer contour pixel width of the icing conductor when it is iced.

9. A dual-light image monitoring device for monitoring icing on transmission lines, characterized in that, include: The memory is configured to store instructions; The processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the dual-light image monitoring method for monitoring icing on transmission lines according to any one of claims 1 to 8.

10. A machine-readable storage medium storing instructions thereon, characterized in that, When executed by a processor, the instruction causes the processor to be configured to perform the dual-light image monitoring method for monitoring icing of transmission lines according to any one of claims 1 to 8.

Images