Power transmission line discharge detection method, device, equipment, storage medium and product

Abstract

The invention relates to the technical field of image processing, and discloses a power transmission line discharge detection method, device and equipment, a storage medium and a product, and the method comprises the steps: obtaining a multi-modal image of a power transmission line, segmenting the multi-modal image based on an active contour model, obtaining a segmentation result image, and extracting a discharge light spot in the segmentation result image, analyzing the discharge light spot according to a preset multi-dimensional characteristic quantity to obtain a discharge detection result of the power transmission line; according to the method, the multi-modal image of the power transmission line is acquired, the multi-modal image is segmented by using the active contour model, the discharge light spot is accurately extracted, and the preset multi-dimensional characteristic quantity is combined to analyze the discharge light spot, so that the discharge detection result of the power transmission line is obtained; the problem of information loss possibly existing in a single image source is effectively solved, the key area in the image can be automatically and accurately identified, and the efficiency and accuracy of power transmission line discharge detection are remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, device, equipment, storage medium and product for detecting discharge of a power transmission line. Background Art

[0002] At present, the combination of ultraviolet imaging equipment and drones has made the discharge detection of power facilities safer and more efficient. However, the existing detection module is single, the effect of ultraviolet imaging discharge area target segmentation and extraction is not ideal, and the feature quantity characterizing the discharge state of the equipment surface is slightly insufficient. Summary of the invention

[0003] The main purpose of this application is to provide a transmission line discharge detection method, device, equipment, readable storage medium and computer program product, aiming to solve the technical problems of low accuracy and efficiency of transmission line discharge detection due to the single detection module, inaccurate discharge area extraction and insufficient feature characterization in the prior art.

[0004] To achieve the above objectives, the present application proposes a method for detecting discharge of a transmission line, the method comprising:

[0005] Acquire multimodal images of transmission lines;

[0006] Segmenting the multimodal image based on an active contour model to obtain a segmentation result map, and extracting discharge spots in the segmentation result map;

[0007] The discharge light spot is analyzed according to a preset multi-dimensional feature quantity to obtain a discharge detection result of the transmission line.

[0008] In one embodiment, the active contour model includes: an initial curve and an energy function;

[0009] The step of segmenting the multimodal image based on the active contour model to obtain a segmentation result map, and extracting the discharge light spot in the segmentation result map includes:

[0010] Initializing the multimodal image based on the initial curve to obtain a processed multimodal image;

[0011] The processed multimodal image is segmented according to the energy function to obtain a segmentation result image, and the discharge light spot in the segmentation result image is extracted.

[0012] In one embodiment, the active contour model further includes: a level set function;

[0013] The step of segmenting the processed multimodal image according to the energy function to obtain a segmentation result map, and extracting the discharge light spot in the segmentation result map comprises:

[0014] Obtaining an initial segmentation contour of the processed multimodal image;

[0015] Evolving the initial segmentation contour based on the level set function to obtain an evolved contour;

[0016] Calculating the statistical characteristics of the inner and outer regions of the evolution profile, and evaluating the degree of approximation of the evolution profile to the real boundary according to the statistical characteristics of the inner and outer regions to obtain an approximation degree evaluation result;

[0017] Based on the approximation degree evaluation result and the energy function, dynamically adjusting the position and shape of the evolution contour of the processed multimodal image until a preset convergence condition is met, and outputting a segmentation result image;

[0018] A discharge area is extracted from the segmentation result image, and boundary recognition and boundary refinement processing are performed on the discharge area to obtain a discharge light spot.

[0019] In one embodiment, the step of extracting the discharge area from the segmentation result image, and performing boundary recognition and boundary refinement processing on the discharge area to obtain the discharge spot includes:

[0020] Extracting a discharge area from the segmentation result image;

[0021] Performing boundary smoothing and correction processing on each boundary of the discharge area to obtain a processed discharge area;

[0022] The boundaries of the treated discharge area are connected to obtain a discharge spot.

[0023] In one embodiment, the step of analyzing the discharge light spot according to the preset multi-dimensional feature quantity to obtain the discharge detection result of the transmission line includes:

[0024] Extracting target multi-dimensional feature quantities of the discharge light spot according to preset multi-dimensional feature quantities;

[0025] Training the preset multi-dimensional feature quantity to obtain a feature quantity model;

[0026] According to the feature quantity model, the target multi-dimensional feature quantity is analyzed to obtain the discharge detection result of the transmission line

[0027] In one embodiment, the step of acquiring a multimodal image of a power transmission line includes:

[0028] Collecting transmission line images on a preset path;

[0029] identifying a noise type of the power transmission line image, and assessing a noise level based on the noise type;

[0030] The power transmission line image is subjected to denoising preprocessing according to the noise level to obtain a multimodal image.

[0031] In addition, to achieve the above-mentioned purpose, the present application also proposes a transmission line discharge detection device, the transmission line discharge detection device comprising:

[0032] An image acquisition module, used for acquiring multimodal images of the transmission line;

[0033] An image processing module, used for segmenting the multimodal image based on an active contour model, obtaining a segmentation result map, and extracting the discharge light spot in the segmentation result map;

[0034] The discharge detection module is used to analyze the discharge light spot according to a preset multi-dimensional feature quantity to obtain a discharge detection result of the transmission line.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a transmission line discharge detection device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the transmission line discharge detection method described above.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the transmission line discharge detection method described above are implemented.

[0037] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the power transmission line discharge detection method as described above are implemented.

[0038] The technical solution proposed in the present application obtains a multimodal image of a transmission line, segments the multimodal image based on an active contour model, obtains a segmentation result map, extracts the discharge spots in the segmentation result map, analyzes the discharge spots according to preset multidimensional feature quantities, and obtains a discharge detection result of the transmission line; since the present application obtains a multimodal image of a transmission line, segments the multimodal image using an active contour model, accurately extracts the discharge spots, and analyzes the discharge spots in combination with preset multidimensional feature quantities to obtain a discharge detection result of the transmission line, it effectively compensates for the information missing problem that may exist in a single image source, can automatically and accurately identify key areas in the image, and significantly improves the efficiency and accuracy of transmission line discharge detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0041] Figure 1 A schematic diagram of a flow chart provided for the first embodiment of the method for detecting discharge of a power transmission line of the present application;

[0042] Figure 2 This is the result of spot segmentation of corona discharge UV imaging;

[0043] Figure 3 A schematic diagram of a flow chart provided for Embodiment 2 of the method for detecting discharge of a power transmission line of the present application;

[0044] Figure 4 This is a schematic diagram of the power transmission line image processing process for this application;

[0045] Figure 5 A schematic diagram of a flow chart provided for Embodiment 3 of the method for detecting discharge of a power transmission line of the present application;

[0046] Figure 6 This is a schematic diagram of the structure of a drone equipped with a multispectral imager for this application;

[0047] Figure 7 This is a schematic diagram of the module structure of the power transmission line discharge detection device according to an embodiment of the present application;

[0048] Figure 8 Schematic diagram of the equipment structure of the hardware operating environment involved in the power transmission line discharge detection method in the embodiment of the present application.

[0049] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0050] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0051] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0052] The current discharge detection technology has a single detection module. The drone is only equipped with an ultraviolet imaging module, which is unable to measure the temperature of the fault point. The effect of target segmentation and extraction in the ultraviolet imaging discharge area is not ideal, and the feature quantity characterizing the discharge state on the surface of the equipment is slightly insufficient.

[0053] Therefore, in order to overcome the above-mentioned defects, the present application provides a solution by acquiring a multimodal image of the transmission line, segmenting the multimodal image using an active contour model, accurately extracting the discharge spot, and analyzing the discharge spot in combination with preset multi-dimensional feature quantities to obtain the discharge detection result of the transmission line, which effectively compensates for the information missing problem that may exist in a single image source, can automatically and accurately identify the key areas in the image, and significantly improves the efficiency and accuracy of transmission line discharge detection.

[0054] It should be noted that the execution subject of each embodiment of the present application may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a power transmission line discharge detection device, etc. The following embodiments are described below taking the power transmission line discharge detection device as an example.

[0055] Based on this, the present application embodiment provides a method for detecting discharge of a transmission line, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the power transmission line discharge detection method of the present application.

[0056] In this embodiment, the power transmission line discharge detection method includes steps S10 to S30:

[0057] Step S10, acquiring a multimodal image of the power transmission line.

[0058] It should be noted that power transmission facilities such as power lines are affected by various internal and external factors. After long-term operation, they will experience problems such as aging, broken strands, scattered strands, defects, dirtiness, and discharge. The emergence of these problems will endanger the stable operation of the entire transmission network. If not handled in time, it will aggravate the damage to power facilities and cause serious transmission accidents.

[0059] In recent years, with the rapid development of the drone industry, ultraviolet imaging equipment has been combined with drones to realize discharge detection of power facilities. Based on ultraviolet imaging equipment, drone power transmission line discharge detection can well detect the discharge point. However, this technology still has the following defects: (1) The detection module is single. The drone is only equipped with one ultraviolet imaging module and cannot measure the temperature of the fault point; (2) The effect of ultraviolet imaging discharge area target segmentation and extraction is not ideal, and the feature quantity that characterizes the discharge state of the equipment surface is slightly insufficient.

[0060] It can be understood that the acquired multimodal images are multi-type data from different sensors or imaging technologies, which can more comprehensively reflect the status and environmental information of the transmission line.

[0061] It should be understood that the acquired original image may be affected by various factors such as lighting, weather, shooting angle, etc., resulting in poor image quality. However, through pre-processing methods such as denoising, contrast enhancement, and distortion correction, the image quality can be improved, making subsequent analysis and recognition more accurate.

[0062] Step S20, segmenting the multimodal image based on an active contour model to obtain a segmentation result image, and extracting the discharge spot in the segmentation result image.

[0063] It should be noted that the active contour model is an image processing model. Among its many types, this application chooses to use the CV model to segment the image. The CV model constructs an energy function that combines the regional information of the image (such as the average grayscale value of the internal and external areas) and the geometric properties of the contour curve (such as length and enclosed area). In the process of minimizing the energy function, the contour curve gradually approaches the edge of the target object, thereby segmenting the target area.

[0064] For example, a discharge region segmentation test is performed on multiple corona discharge UV images to verify the effectiveness of the CV model. Figure 2 To explain, Figure 2 The figure shows the result of corona discharge UV imaging spot segmentation. In order to observe the dependence of the segmentation effect of the CV model on the initial contour setting, two initial contours are set, namely circular and rectangular initial contours. The main parameters of the calculation model are set as: μ = 0.01 / 255 2,Δt=0.1,ε=1. By comparison, it can be seen that when segmenting a single light spot, the CV model has less dependence on the setting of the initial contour curve. From the first and second rows, it can be seen that when the initial contour is set to a circle or a rectangle, the model can accurately segment the discharge light spot; when segmenting a single light spot, no matter whether the initial contour is a circle or a rectangle, the CV model can also accurately segment two real discharge light spots.

[0065] It is understandable that since multimodal images usually contain multiple information from different imaging devices or technologies, all features of the target may not be fully revealed in a single modality. Through segmentation, useful information from different modalities can be integrated to form a more comprehensive understanding. In addition, through segmentation, the target area can be separated from the background or irrelevant areas, and the segmented image can be more easily quantitatively analyzed.

[0066] It should be noted that in the actual image segmentation step, it is not always possible to directly obtain a perfect segmentation result that only contains the discharge area. The goal of the segmentation algorithm is to distinguish different objects or regions in the image, but due to the complexity of the image itself (such as noise, illumination changes, background interference, etc.), the segmentation result often includes some non-discharge areas or fails to completely cover the discharge area.

[0067] It should be understood that in order to obtain a more accurate discharge area, the segmentation results need to be further processed and optimized, and more sophisticated techniques need to be used to accurately extract the white light spot area generated by the discharge. This step also takes into account the shape, brightness distribution and time series changes of the light spot.

[0068] For example, a rectangular box is manually or automatically defined in the UV image, and the area should contain all possible discharge points. In this area, the number of photons is calculated using image processing software, and based on the calculation result of the number of photons, the discharge spot is separated from the background using image segmentation technology.

[0069] Step S30: analyzing the discharge light spot according to a preset multi-dimensional feature quantity to obtain a discharge detection result of the transmission line.

[0070] It is understandable that the preset multi-dimensional feature quantities can comprehensively and accurately describe the various characteristics of the discharge spot, such as the spot area, boundary perimeter, discharge intensity, frequency, etc. By classifying and evaluating the multi-dimensional feature quantities of the discharge spot, the fault source can be quickly located, the fault type can be determined, and strong support can be provided for subsequent fault handling and maintenance.

[0071] Exemplarily, the preset multi-dimensional feature quantity may include:

[0072] 1. Spot area. That is, the size of the spot, expressed as the sum of the number of pixels that make up the spot, and the unit is pixel.

[0073] 2. Boundary perimeter: The sum of the distances between consecutive pixels on the boundary of the spot area, in pixels.

[0074] 3. Major axis and minor axis. The shape of the discharge spot is not necessarily circular, but may also be elongated. The area and perimeter alone cannot well characterize the discharge state, so the major axis and minor axis are extracted. Major axis: the distance between the farthest two points on the boundary through the centroid of the discharge spot. Minor axis: the distance between the closest two points on the boundary through the centroid of the discharge spot, in pixels.

[0075] It should be understood that the characteristic quantities of the discharge light spot can be analyzed in real time through preset monitoring algorithms and thresholds, and an alarm can be immediately issued once an abnormality is found, thereby improving monitoring efficiency and accuracy.

[0076] It should be understood that in order to accurately describe the characteristics of the discharge spot, assist in fault diagnosis, and improve monitoring efficiency, multi-dimensional feature quantities are used and classified and evaluated, and comprehensive consideration of information from multiple aspects can adapt to the needs of different application scenarios and achieve more flexible and personalized monitoring and evaluation.

[0077] The present embodiment provides a method for detecting discharge of a power transmission line, which obtains a multimodal image of the power transmission line, segments the multimodal image based on an active contour model, obtains a segmentation result image, extracts the discharge spot in the segmentation result image, analyzes the discharge spot according to a preset multidimensional feature quantity, and obtains a discharge detection result of the power transmission line; since the present application obtains a multimodal image of the power transmission line, segments the multimodal image using an active contour model, accurately extracts the discharge spot, and analyzes the discharge spot in combination with a preset multidimensional feature quantity to obtain a discharge detection result of the power transmission line, the present application effectively compensates for the information missing problem that may exist in a single image source, can automatically and accurately identify key areas in the image, and significantly improves the efficiency and accuracy of transmission line discharge detection.

[0078] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 3 , the active contour model includes: an initial curve and an energy function; the step S20 may include steps S201 to S202:

[0079] Step S201 : performing initialization processing on the multimodal image based on the initial curve to obtain a processed multimodal image.

[0080] It should be noted that before the algorithm is executed, some initial parameters or states need to be set, a process called initialization. Initialization may include selecting a segmentation method, setting an initial segmentation threshold, defining an initial segmentation area, etc.

[0081] It should be understood that the starting point of the evolution of the initial curve contour is to define an initial closed curve in the image according to prior knowledge of the image or user input, and the curve should be as close as possible to the boundary of the target object.

[0082] Further, initializing the multimodal image based on the initial curve may include parameter setting, fusion of multimodal information, setting of constraint conditions, etc. Due to the complexity and diversity of multimodal images, the setting of initialization processing needs to be adjusted and optimized according to specific circumstances.

[0083] It can be understood that the initialization process can preliminarily locate and describe the segmentation result (such as the discharge area) based on the feature information (such as brightness, color, texture, etc.) in the image.

[0084] By way of example, a preliminary description of the discharge region is given:

[0085] 1. Brightness and temperature distribution: The discharge area usually appears as a local high temperature area in infrared thermal imaging, and its temperature is significantly higher than the surrounding background. The initial description can include analyzing the brightness or temperature distribution in the image to identify areas that are significantly different from the surrounding environment.

[0086] 2. Shape and Boundary: The shape of the discharge region may vary depending on the discharge type, electrode configuration, and discharge conditions. It may appear irregular, but usually has a certain degree of connectivity and continuity. In the preliminary description, we can focus on the boundary features of the region, such as edge clarity, irregularity, etc., to assist in the subsequent segmentation process.

[0087] 3. Location and distribution: The discharge area often appears in key parts of high-voltage equipment, such as insulator surface, wire joints, switch contacts, etc. In the preliminary description, based on the known equipment structure and discharge mechanism, the possible location of the discharge area can be predicted and used as the search focus of the segmentation algorithm.

[0088] 4. Dynamic changes: In some cases, the discharge phenomenon may have the characteristics of dynamic changes. Therefore, the changes in the discharge area in the time series image, such as the fluctuation of the discharge intensity and the diffusion trend, can also be considered in the preliminary description.

[0089] Step S202 , performing segmentation processing on the processed multimodal image according to the energy function to obtain a segmentation result image, and extracting the discharge light spot in the segmentation result image.

[0090] It should be noted that the segmentation result image includes the discharge area, which is a broad concept covering all areas involved in the entire discharge process. The discharge spot usually refers to the area with specific brightness or color changes in the image due to corona discharge or other electrical faults.

[0091] It is understandable that although the segmentation result can roughly locate the area where the discharge occurs, it may contain some non-discharge noise or background information. As the most significant and characteristic part of the discharge phenomenon, the discharge spot usually has higher brightness and clearer boundaries, so extracting the discharge spot can further improve the precision and accuracy of discharge detection.

[0092] In order to improve the accuracy of discharge light plate extraction, the active contour model further includes: a level set function; the step S202 includes steps S2021 to S2025:

[0093] Step S2021, obtaining an initial segmentation contour of the processed multimodal image.

[0094] Step S2022: Evolving the initial segmentation contour based on the level set function to obtain an evolved contour.

[0095] It should be noted that the level set function expresses the low-dimensional evolution curve or surface through the high-dimensional function surface, that is, the evolving (changing) curve or surface (interface) is indirectly expressed by the zero level set of the high-dimensional level set function. This method transforms the evolution equation of the evolution curve or surface into the evolution partial differential equation of the high-dimensional level set function, and captures the moving boundary surface by solving these equations.

[0096] It should be understood that evolving the initial segmentation contour means iteratively adjusting the image contour so that it gradually approaches the real boundary.

[0097] Step S2023, calculating the statistical characteristics of the inner and outer regions of the evolution profile, and evaluating the degree of approximation of the evolution profile to the real boundary according to the statistical characteristics of the inner and outer regions, to obtain an approximation evaluation result.

[0098] It should be understood that in image processing, the need to find the exact boundaries of the discharge area in the image involves iterative adjustment of the contour until it most accurately reflects the true boundaries of the target. In order to evaluate the approximation of the contour, we can calculate certain statistical properties of the areas inside and outside the contour, such as the average gray value.

[0099] For example, suppose a discharge area has obtained a preliminary contour line through some initialization processing. This contour line roughly circles the position of the discharge area, but it is not accurate enough. Therefore, the average gray value of the area inside the contour line (discharge area) and the area outside the contour line (background) is calculated. By comparing the two average gray values, it can be determined whether the contour line is well approximated to the real boundary of the discharge area. If not, it is necessary to adjust the contour line and continuously optimize the position of the contour line until a satisfactory approximation is obtained.

[0100] Step S2024, based on the approximation degree evaluation result and the energy function, dynamically adjust the position and shape of the evolution contour of the processed multimodal image until a preset convergence condition is met, and output a segmentation result image.

[0101] It should be noted that the energy function can be defined as the probability of whether each pixel belongs to the foreground or the background, and accurate image segmentation can be achieved by minimizing the value of the energy function.

[0102] For ease of understanding, the following references Figure 4 This invention is provided for illustration, but is not intended to limit the present application. Figure 4 This is a schematic diagram of the power transmission line image processing process. The specific steps for outputting the segmentation result map are as follows:

[0103] 1. Assume that the image I(x,y) with a domain of Ω is divided into the inner area and the outer area of ​​the curve by the closed contour curve C. The choice of weight coefficient has an impact on the expression of the energy function F in equation (1). Different weight coefficients need to be selected according to different images. Since the corona discharge images taken by the UV imager are all standardized, λ1=λ2=1 is set; in addition, it can be seen from the isoperimetric inequality that in the algorithm, the perimeter of the contour curve will limit and control the area of ​​the region. Here, the area coefficient η=0, and only the length term coefficient μ is retained. In general, μ takes a value of 0.01 / 255 2 .

[0104]

[0105] Where F(C,c1,c2) ​​is the energy function of curve C; Length(C) is the perimeter of curve C; inside(C) is the internal area of ​​curve C; Area(inside(C)) is the area of ​​inside(C); μ, η, λ1, λ2 are all weight coefficients, and η≥0, λ1, λ2>0; c1 and c2 are the average grayscale values ​​of and respectively. The first two terms are "smoothing terms" and the last two terms are "fitting terms".

[0106] 2. Select the initial curve and construct the initial level set For example, if the initial curve is selected as a circle, then The expression is Where r is the radius of the circle, (x0,y0) is the center of the circle, and (x,y) is any point on the image.

[0107] Introducing the level set function, the curve C can be expressed as follows through formula (2):

[0108]

[0109] Where, inside(C) is the inner area of ​​curve C; outside(C) is the outer area of ​​curve C; Indicates that every point (x, y) inside (C) satisfies the function The value of is greater than zero; is represented as a set of boundaries, where The value of is exactly zero; Indicates that every point (x, y) inside outside(C) satisfies the function The value of is less than zero.

[0110] At the same time, the Heaviside function H and the Dirac function δ are introduced, which are defined as:

[0111]

[0112] Where H(z) determines its output based on the value of the input variable z (greater than, equal to, or less than 0); δ(z) represents the step change of H(z) from 0 to 1 when z crosses 0.

[0113] 3. Calculate c1, c2, The value of is calculated by the finite difference method

[0114] Combining equation (2) and equation (3), and substituting them into equation (1), we can get:

[0115]

[0116] In the formula, is the gradient operator.

[0117]

[0118] Because it involves the problem of curve evolution, Keep evolving, remember It is time t The value of . The Euler-Lagrange method is used to derive the partial differential equation that satisfies equation (4) and is expressed in the form of a level set function:

[0119]

[0120] In the formula, represents the unit curvature of the level set function.

[0121] In the calculation process, the regularization function (Equation (8)) is used to replace H(z) and δ(z), so that the gradient descent flow equation (7) can act on all level sets, thereby detecting the holes inside the target area and making the energy function reach the global optimal solution.

[0122]

[0123] In the formula, ε is generally in the interval (0, 1].

[0124] 4. Calculate using explicit iteration method Where n is the number of iterations, Δt is the time step, It is the right side of the equal sign in formula (7).

[0125] 5. Check whether the evolution converges or the number of iterations reaches the set maximum value. If it converges or the number of iterations reaches the set value, stop the iteration and output the segmentation result.

[0126] Step S2025 , extracting a discharge area from the segmentation result image, and performing boundary recognition and boundary refinement processing on the discharge area to obtain a discharge light spot.

[0127] It should be understood that boundary recognition further determines the clear boundary between the discharge area and the surrounding background through image processing technology (such as edge detection algorithm), and usually identifies the pixels on the boundary based on the differences in grayscale, color, texture, etc. between pixels. The boundary obtained after boundary recognition may still contain some noise, burrs or unnecessary details, so image processing technology (such as morphological operation, contour smoothing, hole filling, etc.) is used to further optimize the boundary to make it smoother, continuous and close to the real boundary of the discharge area.

[0128] In order to make the extraction result more accurate, the step S2025 may include the following steps:

[0129] Extracting a discharge area from the segmentation result image;

[0130] Performing boundary smoothing and correction processing on each boundary of the discharge area to obtain a processed discharge area;

[0131] The boundaries of the treated discharge area are connected to obtain a discharge spot.

[0132] It is understandable that the purpose of boundary smoothing is to eliminate noise, burrs and irregular shapes on the boundary, making the boundary look smoother and more natural. Boundary correction is to further adjust the shape and position of the boundary based on smoothing, which may include filling small holes, removing small isolated areas, adjusting the curvature of the boundary, etc.

[0133] It should be understood that after smoothing and correction processing, a series of discrete boundary segments or point sets may be obtained. By using a corresponding algorithm to find and connect the points on the boundary to form a continuous contour line, a clear and accurate discharge spot is obtained.

[0134] This embodiment uses an active contour model to segment the multimodal image, and after preliminary segmentation, performs boundary recognition, boundary smoothing and correction, and final boundary connection. The boundary between the discharge area and the background is clearly defined, ensuring the continuity and smoothness of the boundary, and significantly improving the segmentation accuracy and boundary quality of the discharge area.

[0135] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 5 , the step S30 may include steps S301 to S303:

[0136] Step S301 : extracting target multi-dimensional feature quantities of the discharge spot according to preset multi-dimensional feature quantities.

[0137] It should be noted that the preset multi-dimensional feature quantities refer to multiple parameters or indicators used to describe the characteristics of the discharge spot, including but not limited to: shape characteristics (such as the area, circumference, aspect ratio, and roundness of the spot), color characteristics (such as the brightness, color temperature, and color saturation of the spot), dynamic characteristics (movement speed, trajectory, duration), etc.

[0138] Step S302: training the preset multi-dimensional feature quantity to obtain a feature quantity model.

[0139] It should be understood that after collecting the data set containing the required multi-dimensional features, it is processed, and then the model is trained using the prepared data set, and the trained model is evaluated using the test set to check whether its performance meets expectations. The best feature quantity model is obtained through optimization processes such as adjusting model parameters, improving feature engineering, and replacing models.

[0140] Step S303: analyzing the target multi-dimensional feature quantity according to the feature quantity model to obtain a discharge detection result of the transmission line.

[0141] It can be understood that the trained feature quantity model is used as a classifier or identifier to analyze and interpret the multi-dimensional feature quantities extracted from the multimodal images of the discharge area.

[0142] It should be understood that, in order to identify and classify the multi-dimensional feature quantities of the discharge light spot according to the feature quantity model, first, the multi-modal image of the discharge area to be analyzed is input into the preprocessing process to extract the multi-dimensional feature quantities related to the discharge light spot. Then, these feature quantities are input into the trained feature quantity model to identify and analyze these feature quantities. Based on the analysis and comparison of the feature quantities, the model will make a classification decision and classify the discharge light spot into one of the predefined categories.

[0143] It should be noted that the classification category can represent different types of discharge phenomena, the severity of the discharge, or other relevant classification criteria. The output evaluation results can include the category label of the discharge spot, the confidence score (indicating the degree of confidence of the model in the classification result), and any additional diagnosis or suggestion information.

[0144] This embodiment presets multi-dimensional feature quantities according to the characteristics of the discharge light spot, extracts the multi-dimensional feature quantities from the discharge light spot, trains the multi-dimensional feature quantities, obtains a feature quantity model, identifies and classifies the multi-dimensional feature quantities of the discharge light spot according to the feature quantity model, and outputs the discharge detection result of the discharge light spot. By comprehensively considering the feature quantity information of different dimensions, the model can more accurately understand the nature of the discharge phenomenon and make more accurate decisions.

[0145] In the third embodiment, the step S10 may include steps S101 to S103:

[0146] Step S101, collecting a transmission line image on a preset path.

[0147] It should be noted that the present application adopts a power transmission line discharge detection platform for image acquisition, which may include multiple detection modules, thereby improving the comprehensiveness of detection.

[0148] For ease of understanding, refer to Figure 6 This invention is provided for illustration, but is not intended to limit the present application. Figure 6This is a schematic diagram of the structure of the drone equipped with a multi-spectral imager for this application, which includes: 1 is an infrared thermal imaging module, which is used to capture the temperature distribution information of the transmission line and its surrounding environment, and can perform fault judgment and early warning on hardware, insulators, lines, etc., so that many tasks can be completed quickly in a fully energized environment, ensuring the safety of electricity use; 2 is a rangefinder, which is used to accurately measure the distance to the transmission line, ensuring that the drone flies within a safe distance range to avoid collision; 3 is a thermometer and hygrometer, which is used to record the ambient temperature and humidity information during inspections; 4 is a visible light module, which is used to take ordinary color images of the transmission line and its surrounding environment, which can Mark the defect location; 5 is a day-blind ultraviolet module, which is used to capture images of transmission lines in the day-blind ultraviolet band, can detect local discharge, wildfires and other ultraviolet sources, and can achieve high-precision (error within 15%) local discharge quantitative detection, and output consistent photon counting values, which is convenient for defect level determination and standardized execution; 6 is a landing gear, which is used to support the UAV during takeoff and landing; 7 is an elevator wing, which is used to control the flight attitude and altitude of the UAV; 8 is a UAV casing, which is used to protect the internal equipment and sensors of the UAV, and provides the necessary mechanical support and protection to ensure that the UAV can work normally in harsh environments.

[0149] The process of collecting transmission line image information may include:

[0150] 1. Transmission line image acquisition

[0151] Using geographic information systems and drone autonomous flight technology, a preset inspection route covering the entire transmission line is planned.

[0152] When the drone flies along the preset path, the infrared thermal imaging module continuously captures the temperature distribution information of the transmission line and its surrounding environment, and intuitively identifies abnormal temperature rise areas caused by partial discharge, poor contact or overload, such as overheating of insulators and heating of fittings, so as to make preliminary fault judgment and early warning. When the temperature rise range is 10-20℃, it indicates general defects; when the temperature rise range is 20-40℃, it indicates major defects; when the temperature rise range is above 40℃, it indicates critical defects. The rangefinder measures the distance between the drone and the transmission line in real time with an accuracy of ±1mm, ensuring that the drone flies within a safe distance to avoid collision accidents. The thermometer and hygrometer record the ambient temperature and humidity information during the inspection. In the day-blind ultraviolet band, the day-blind ultraviolet module captures the ultraviolet radiation generated by partial discharge of the transmission line.

[0153] 2. Data Processing and Analysis

[0154] The collected transmission line image data will be transmitted to the ground station or cloud server for further processing and analysis. Through the comprehensive application of image recognition, temperature analysis, ultraviolet radiation quantification and other technical means, the health status of the transmission line can be comprehensively evaluated, and potential safety hazards can be discovered and warned in a timely manner.

[0155] Step S102: identifying the noise type of the power transmission line image, and evaluating the noise level based on the noise type.

[0156] It is understandable that in order to improve image quality and enhance the accuracy and reliability of subsequent image analysis (such as fault detection, defect identification, etc.), the multimodal images are preprocessed.

[0157] It should be noted that noise type recognition refers to analyzing the noise characteristics existing in an image and classifying it into a specific noise type. Common noise types include Gaussian noise, quantization noise, stripe noise or fixed pattern noise.

[0158] It should be understood that the level of noise will directly affect the selection and effect of subsequent denoising methods.

[0159] Step S103: performing denoising preprocessing on the power transmission line image according to the noise level to obtain a multimodal image.

[0160] It can be understood that the level set ultraviolet image segmentation method based on the CV model selects the corresponding algorithm or technology for denoising preprocessing according to the noise level, so it can accurately segment the discharge area in the ultraviolet image under the influence of noise, and has strong anti-noise ability and globality.

[0161] This embodiment uses the multimodal images acquired by the power transmission line discharge detection platform on the preset path to provide comprehensive information on the status of the power transmission line. The noise type is identified and the noise level is evaluated for denoising preprocessing, which effectively reduces the noise level in the image and improves the image clarity and signal-to-noise ratio. In addition, the accurate identification and effective removal of noise further enhances the detection capability of the detection platform, enabling it to more accurately identify discharge phenomena and other faults in the power transmission line.

[0162] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the power transmission line discharge detection method of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0163] This application also provides a transmission line discharge detection device, please refer to Figure 7 , the transmission line discharge detection device comprises:

[0164] An image acquisition module 10, used to acquire a multimodal image of a power transmission line;

[0165] An image processing module 20, configured to segment the multimodal image based on an active contour model, obtain a segmentation result map, and extract discharge spots in the segmentation result map;

[0166] The discharge detection module 30 is used to analyze the discharge light spot according to a preset multi-dimensional feature quantity to obtain a discharge detection result of the transmission line.

[0167] The power transmission line discharge detection device provided by the present application adopts the power transmission line discharge detection method in the above-mentioned embodiment, which can solve the technical problems of low accuracy and efficiency of power transmission line discharge detection due to the single detection module, inaccurate extraction of discharge area and insufficient feature characterization in the prior art. Compared with the prior art, the beneficial effects of the power transmission line discharge detection device provided by the present application are the same as the beneficial effects of the power transmission line discharge detection method provided by the above-mentioned embodiment, and the other technical features in the power transmission line discharge detection device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0168] The present application provides a transmission line discharge detection device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the transmission line discharge detection method in the above-mentioned embodiment 1.

[0169] Reference below Figure 8 , which shows a schematic diagram of the structure of a power transmission line discharge detection device suitable for implementing the embodiment of the present application. The power transmission line discharge detection device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions: tablet computers), PMPs (Portable Media Players: portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8 The power transmission line discharge detection device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0170] like Figure 8As shown, the power transmission line discharge detection device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. Various programs and data required for the operation of the power transmission line discharge detection device are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow the power transmission line discharge detection device to communicate with other devices wirelessly or by wire to exchange data. Although the power transmission line discharge detection device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0171] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0172] The power transmission line discharge detection device provided by the present application adopts the power transmission line discharge detection method in the above embodiment, which can solve the technical problems of low accuracy and efficiency of power transmission line discharge detection due to the single detection module, inaccurate extraction of discharge area and insufficient feature characterization in the prior art. Compared with the prior art, the beneficial effects of the power transmission line discharge detection device provided by the present application are the same as the beneficial effects of the power transmission line discharge detection method provided by the above embodiment, and the other technical features in the power transmission line discharge detection device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0173] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0174] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0175] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the power transmission line discharge detection method in the above-mentioned embodiment.

[0176] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0177] The computer-readable storage medium may be included in the power transmission line discharge detection device; or may exist independently without being assembled into the power transmission line discharge detection device.

[0178] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the transmission line discharge detection device, the transmission line discharge detection device: obtains a multimodal image of the transmission line, segments the multimodal image based on the active contour model, obtains a segmentation result image, and extracts the discharge spot in the segmentation result image, analyzes the discharge spot according to a preset multi-dimensional feature quantity, and obtains a discharge detection result of the transmission line.

[0179] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0180] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0181] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0182] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned power transmission line discharge detection method, and can solve the technical problems of low accuracy and efficiency of power transmission line discharge detection due to the single detection module, inaccurate discharge area extraction, and insufficient feature characterization in the prior art. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the power transmission line discharge detection method provided in the above-mentioned embodiment, and will not be repeated here.

[0183] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned power transmission line discharge detection method when executed by a processor.

[0184] The computer program product provided by the present application can solve the technical problem that the accuracy and efficiency of power transmission line discharge detection are low due to the single detection module, inaccurate extraction of discharge area and insufficient feature characterization in the prior art. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the power transmission line discharge detection method provided by the above embodiment, which will not be elaborated here.

[0185] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for detecting discharge of a transmission line, characterized in that: The method comprises the following steps: Acquire multimodal images of transmission lines; Segmenting the multimodal image based on an active contour model to obtain a segmentation result map, and extracting discharge spots in the segmentation result map; The discharge light spot is analyzed according to a preset multi-dimensional feature quantity to obtain a discharge detection result of the transmission line.

2. The method for detecting discharge of a power transmission line according to claim 1, characterized in that: The active contour model includes: an initial curve and an energy function; The step of segmenting the multimodal image based on the active contour model to obtain a segmentation result map, and extracting the discharge light spot in the segmentation result map includes: Initializing the multimodal image based on the initial curve to obtain a processed multimodal image; The processed multimodal image is segmented according to the energy function to obtain a segmentation result image, and the discharge light spot in the segmentation result image is extracted.

3. The method for detecting discharge of a power transmission line according to claim 2, characterized in that: The active contour model also includes: a level set function; The step of segmenting the processed multimodal image according to the energy function to obtain a segmentation result map, and extracting the discharge light spot in the segmentation result map comprises: Obtaining an initial segmentation contour of the processed multimodal image; Evolving the initial segmentation contour based on the level set function to obtain an evolved contour; Calculating the statistical characteristics of the inner and outer regions of the evolution profile, and evaluating the degree of approximation of the evolution profile to the real boundary according to the statistical characteristics of the inner and outer regions to obtain an approximation degree evaluation result; Based on the approximation degree evaluation result and the energy function, dynamically adjusting the position and shape of the evolution contour of the processed multimodal image until a preset convergence condition is met, and outputting a segmentation result image; A discharge area is extracted from the segmentation result image, and boundary recognition and boundary refinement processing are performed on the discharge area to obtain a discharge light spot.

4. The method for detecting discharge of a power transmission line according to claim 3, characterized in that: The step of extracting the discharge area from the segmentation result image, and performing boundary recognition and boundary refinement processing on the discharge area to obtain the discharge spot includes: Extracting a discharge area from the segmentation result image; Performing boundary smoothing and correction processing on each boundary of the discharge area to obtain a processed discharge area; The boundaries of the treated discharge area are connected to obtain a discharge spot.

5. The method for detecting discharge of a power transmission line according to any one of claims 1 to 4, characterized in that: The step of analyzing the discharge light spot according to the preset multi-dimensional feature quantity to obtain the discharge detection result of the transmission line includes: Extracting target multi-dimensional feature quantities of the discharge light spot according to preset multi-dimensional feature quantities; Training the preset multi-dimensional feature quantity to obtain a feature quantity model; The target multi-dimensional feature quantity is analyzed according to the feature quantity model to obtain a discharge detection result of the power transmission line.

6. The method for detecting discharge of a power transmission line according to any one of claims 1 to 5, characterized in that: The step of acquiring a multimodal image of a power transmission line comprises: Collecting transmission line images on a preset path; identifying a noise type of the power transmission line image, and assessing a noise level based on the noise type; The power transmission line image is subjected to denoising preprocessing according to the noise level to obtain a multimodal image.

7. A transmission line discharge detection device, characterized in that: The transmission line discharge detection device comprises: An image acquisition module, used for acquiring multimodal images of the transmission line; An image processing module, used for segmenting the multimodal image based on an active contour model, obtaining a segmentation result map, and extracting the discharge light spot in the segmentation result map; The discharge detection module is used to analyze the discharge light spot according to a preset multi-dimensional feature quantity to obtain a discharge detection result of the transmission line.

8. A transmission line discharge detection device, characterized in that: The power transmission line discharge detection device comprises: a memory, a processor, and a power transmission line discharge detection program stored in the memory and executable on the processor. When the power transmission line discharge detection program is executed by the processor, the power transmission line discharge detection method according to any one of claims 1 to 6 is implemented.

9. A storage medium, characterized in that: The storage medium stores a power transmission line discharge detection program, and when the power transmission line discharge detection program is executed by the processor, the power transmission line discharge detection method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product comprises a power transmission line discharge detection program, and when the power transmission line discharge detection program is executed by a processor, the power transmission line discharge detection method according to any one of claims 1 to 6 is implemented.

Images