Power transmission line icing type identification method and device, equipment and storage medium

Abstract

The invention provides a power transmission line icing type identification method and device, equipment and a storage medium, and relates to the technical field of electric power safety. The method comprises the following steps: acquiring a power transmission line image, and determining whether the power transmission line is iced according to the power transmission line image; if the power transmission line is iced, acquiring a power transmission line area corresponding to the power transmission line based on the power transmission line image and the iced area corresponding to the power transmission line; if the power transmission line area meets the preset length-width relation, determining that the icing type of the power transmission line is glaze; if the power transmission line area does not meet the preset length-width relation, performing second-order curve fitting on pixel points in the power transmission line area to obtain a fitting result; and based on the fitting result, identifying that the icing type of the power transmission line is rime or mixed rime. The method can greatly reduce the calculation power requirement, and can effectively improve the recognition precision and reliability of the icing type of the power transmission line.

Description

Technical Field

[0001] The present application relates to the technical field of power safety, and particularly to a method, device, equipment and storage medium for identifying icing types of transmission lines. Background Art

[0002] Transmission lines play an important role in transmitting electric energy in the power grid. However, due to factors such as the complexity of their operating environment and the wide range of line crossings, they are vulnerable to the influence of macroclimate, microtopography and micro-meteorological factors, resulting in icing of transmission lines. Icing of transmission lines can trigger serious accidents such as line galloping, line breakage, tower inclination or even collapse. Different icing types have different densities and thus different hazards to transmission lines. Therefore, accurately identifying the icing type and providing a reliable basis for power personnel to judge the icing condition is of great significance for preventing icing accidents and improving the reliability of the power system.

[0003] Currently, a trained neural network model is usually used to identify the icing type of transmission lines. However, when identifying the icing type in the above manner, there is a problem of high computing power requirements. Summary of the Invention

[0004] The present application provides a method, device, equipment and medium for identifying icing types of transmission lines to solve the problem of high computing power requirements in identifying icing types by the current method.

[0005] In a first aspect, the present application provides a method for identifying icing types of transmission lines, including:

[0006] Obtain an image of a transmission line;

[0007] Determine whether the transmission line is iced according to the image of the transmission line;

[0008] If the transmission line is iced, obtain the transmission line area corresponding to the transmission line based on the image of the transmission line and the icing area corresponding to the transmission line;

[0009] If the transmission line area meets the preset length-width relationship, determine that the icing type of the transmission line is glaze ice;

[0010] If the transmission line area does not meet the preset length-width relationship, perform second-order curve fitting on the pixel points in the transmission line area to obtain a fitting result; based on the fitting result, identify the icing type of the transmission line as rime ice or mixed ice.

[0011] Optionally, based on the transmission line image and the icing area corresponding to the transmission line, obtaining the transmission line area corresponding to the transmission line includes: converting the transmission line image to the HSV color space to obtain a converted image; extracting the transmission line based on the hue component value, saturation component value, and brightness component value corresponding to the converted image to obtain an initial transmission line area; and performing background removal processing on the initial transmission line area through the icing area to obtain the transmission line area.

[0012] Optionally, extracting the transmission line based on the hue component value, saturation component value, and brightness component value corresponding to the converted image to obtain an initial transmission line area includes: extracting the transmission line in the converted image according to the first upper limit of the hue component value, the second upper limit of the saturation component value, and the third upper limit of the brightness component value corresponding to the color of the transmission line in the HSV color space, where the third upper limit is determined according to the mean value of the brightness component values of the pixel points included in the converted image and the background illumination of the converted image, to obtain the initial transmission line area.

[0013] Optionally, performing second-order curve fitting on the pixel points in the transmission line area to obtain a fitting result includes: performing second-order curve fitting on the pixel points in the transmission line area using the random sample consensus algorithm to obtain the fitting result.

[0014] Optionally, based on the fitting result, identifying the icing type of the transmission line as rime or mixed rime includes: according to the fitting result, if the ratio of the first quantity to the second quantity is less than or equal to a preset threshold, determining that the icing type of the transmission line is mixed rime, where the first quantity is the number of pixel points in the transmission line area on the second-order curve, and the second quantity is the number of pixel points in the transmission line area; if the ratio is greater than the preset threshold, determining whether the pixel points on the second-order curve are in a discrete state; if they are in a discrete state, determining that the icing type of the transmission line is rime, and if they are not in a discrete state, determining that the icing type of the transmission line is mixed rime.

[0015] Optionally, determining whether the pixel points on the second-order curve are in a discrete state includes: sorting the pixel points on the second-order curve according to the x coordinate of the pixel points to obtain the sorted pixel points; if the distance between the x coordinates of two adjacent pixel points among the sorted pixel points is less than a distance threshold, determining that the two adjacent pixel points are a continuous block; if the number of continuous blocks is less than a quantity threshold, determining that the pixel points on the second-order curve are in a discrete state; if the number of continuous blocks is greater than or equal to the quantity threshold, determining that the pixel points on the second-order curve are not in a discrete state.

[0016] Optionally, determining whether the transmission line is ice-covered based on the transmission line image includes: inputting the transmission line image into an ice-coverage detection model for ice-coverage detection of the transmission line to obtain a detection result output by the ice-coverage detection model, where the ice-coverage detection model is constructed based on the U-net++ architecture; if the detection result includes an ice-covered area, determining that the transmission line is ice-covered; if the detection result does not include an ice-covered area, determining that the transmission line is not ice-covered.

[0017] Optionally, the ice-coverage detection model is obtained through training in the following manner: obtaining training samples, where the training samples include transmission line ice-covered sample images, transmission line non-ice-covered sample images, and reference ice-covered areas corresponding to the transmission line ice-covered sample images; based on the training samples, iteratively training the ice-coverage detection model until the calculated loss function value meets a preset evaluation condition or the number of iterations reaches a preset number of iterations to obtain a trained ice-coverage detection model, where the ice-coverage detection model is constructed based on the U-net++ architecture.

[0018] In a second aspect, the present application provides a device for identifying the ice-coverage type of a transmission line, including:

[0019] A first acquisition module for acquiring a transmission line image;

[0020] A first determination module for determining whether the transmission line is ice-covered according to the transmission line image;

[0021] A second acquisition module for, if the transmission line is ice-covered, acquiring a transmission line area corresponding to the transmission line based on the transmission line image and the ice-covered area corresponding to the transmission line;

[0022] A second determination module for, if the transmission line area meets a preset length-width relationship, determining that the ice-coverage type of the transmission line is glaze;

[0023] A processing module for, if the transmission line area does not meet the preset length-width relationship, performing second-order curve fitting on the pixel points within the transmission line area to obtain a fitting result; based on the fitting result, identifying the ice-coverage type of the transmission line as rime or mixed rime.

[0024] Optionally, the second acquisition module is specifically configured to: convert the transmission line image to the HSV color space to obtain a converted image; extract the transmission line based on the hue component value, saturation component value, and brightness component value corresponding to the converted image to obtain an initial transmission line area; perform background removal processing on the initial transmission line area through the ice-covered area to obtain the transmission line area.

[0025] Optionally, when the second acquisition module is used to extract the transmission line based on the hue component value, saturation component value, and brightness component value corresponding to the converted image to obtain the initial transmission line area, it is specifically used to: extract the transmission line in the converted image according to the first upper limit of the hue component value, the second upper limit of the saturation component value, and the third upper limit of the brightness component value corresponding to the color of the transmission line in the HSV color space to obtain the initial transmission line area, and the third upper limit is determined according to the average value of the brightness component values of the pixel points included in the converted image and the background illumination of the converted image.

[0026] Optionally, when the processing module is used to perform a second-order curve fitting on the pixel points in the transmission line area to obtain a fitting result, it is specifically used to: use the random sample consensus algorithm to perform a second-order curve fitting on the pixel points in the transmission line area to obtain a fitting result.

[0027] Optionally, when the processing module is used to identify the icing type of the transmission line as rime or mixed rime based on the fitting result, it is specifically used to: according to the fitting result, if the ratio of the first quantity to the second quantity is less than or equal to a preset threshold, it is determined that the icing type of the transmission line is mixed rime, where the first quantity is the number of pixel points in the transmission line area on the second-order curve, and the second quantity is the number of pixel points in the transmission line area; if the ratio is greater than the preset threshold, it is determined whether the pixel points on the second-order curve are in a discrete state; if they are in a discrete state, it is determined that the icing type of the transmission line is rime, and if they are not in a discrete state, it is determined that the icing type of the transmission line is mixed rime.

[0028] Optionally, when the processing module is used to determine whether the pixel points on the second-order curve are in a discrete state, it is specifically used to: sort the pixel points on the second-order curve according to the x coordinate of the pixel points to obtain the sorted pixel points; if the distance between the x coordinates of two adjacent pixel points in the sorted pixel points is less than a distance threshold, it is determined that the two adjacent pixel points are a continuous block; if the number of continuous blocks is less than a quantity threshold, it is determined that the pixel points on the second-order curve are in a discrete state; if the number of continuous blocks is greater than or equal to the quantity threshold, it is determined that the pixel points on the second-order curve are not in a discrete state.

[0029] Optionally, the first determination module is specifically used to: input the transmission line image into an icing detection model for transmission line icing detection to obtain the detection result output by the icing detection model, and the icing detection model is constructed based on the U-net++ architecture; if the detection result includes an icing area, it is determined that the transmission line is iced; if the detection result does not include an icing area, it is determined that the transmission line is not iced.

[0030] Optionally, the transmission line icing type identification device further includes a training module for training an icing detection model in the following manner: obtaining training samples, where the training samples include transmission line icing sample images, transmission line non-icing sample images, and reference icing regions corresponding to the transmission line icing sample images; based on the training samples, iteratively training the icing detection model until the calculated loss function value meets a preset evaluation condition or the number of iterations reaches a preset number of iterations, to obtain a trained icing detection model, and the icing detection model is constructed based on the U-net++ architecture.

[0031] In a third aspect, the present application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0032] The memory stores computer-executable instructions;

[0033] The processor executes the computer-executable instructions stored in the memory to implement the transmission line icing type identification method as described in the first aspect of the present application.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium storing computer program instructions, which when executed, implement the transmission line icing type identification method as described in the first aspect of the present application.

[0035] In a fifth aspect, the present application provides a computer program product including a computer program, which when executed, implements the transmission line icing type identification method as described in the first aspect of the present application.

[0036] A method, device, equipment and storage medium for identifying icing types of transmission lines provided by this application. By acquiring an image of a transmission line, it is determined whether the transmission line is iced based on the image of the transmission line. If the transmission line is iced, based on the image of the transmission line and the icing area corresponding to the transmission line, the transmission line area corresponding to the transmission line is acquired. If the transmission line area meets the preset length-width relationship, it is determined that the icing type of the transmission line is glaze. If the transmission line area does not meet the preset length-width relationship, the pixel points in the transmission line area are subjected to second-order curve fitting to obtain a fitting result. Based on the fitting result, the icing type of the transmission line is identified as rime or mixed rime. This application adopts the following strategy to identify the icing type. Among them, in the first step, it is judged whether the transmission line in the transmission line image is iced, and the multi-icing type identification problem is transformed into a binary classification problem of "yes or no". In the second step, computer vision is used to extract the transmission line under the icing state to obtain the transmission line area corresponding to the transmission line, and then the icing type is identified by judging the integrity and continuity of the transmission line, that is, the icing type is identified based on the characteristics of different icing types, without the need to identify the icing type through a neural network model, which can greatly reduce the computing power requirements. And the above strategy can effectively improve the identification accuracy and reliability of the icing type of the transmission line, and can reduce the dependence on computing resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.

[0038] Figure 1 It is a flowchart of a method for identifying icing types of transmission lines provided by an embodiment of this application;

[0039] Figure 2 It is a flowchart of a method for identifying icing types of transmission lines provided by another embodiment of this application;

[0040] Figure 3 It is a schematic diagram of a detection result including an icing area provided by an embodiment of this application Figure 1 ;

[0041] Figure 4 It is a schematic diagram of a detection result including an icing area provided by an embodiment of this application Figure 2 ;

[0042] Figure 5 It is a schematic diagram of a detection result including an icing area provided by an embodiment of this application Figure 3 ;

[0043] Figure 6 It is a schematic diagram of a transmission line area provided by an embodiment of this application Figure 1 ;

[0044] Figure 7 Schematic diagram of the transmission line area provided by the embodiment of the present application Figure 2 ;

[0045] Figure 8 Schematic diagram of the transmission line area provided by the embodiment of the present application Figure 3 ;

[0046] Figure 9 Flowchart of the training method of the icing detection model provided by an embodiment of the present application;

[0047] Figure 10 Schematic diagram of the labeled transmission line icing sample image provided by an embodiment of the present application;

[0048] Figure 11 Schematic diagram of the structure of the transmission line icing type identification device provided by an embodiment of the present application;

[0049] Figure 12 Schematic diagram of the structure of the electronic device provided by an embodiment of the present application.

[0050] Through the above-mentioned drawings, the clear embodiments of the present application have been shown, and there will be more detailed descriptions hereinafter. These drawings and text descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. Detailed implementation manners

[0051] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0052] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant laws, regulations, and standards, and corresponding operation entrances are provided for the user to select authorization or rejection.

[0053] First, some technical terms involved in the present application are explained:

[0054] HSV (Hue, Saturation, Value) is a color space created based on the intuitive characteristics of colors and is also known as the hexagonal pyramid model. Each color is represented by hue (H), saturation (S), and value (V). The parameters of colors in the HSV color space are hue (H), saturation (S), and brightness (V). The HSV color space is closer to the way humans perceive colors and is therefore widely used in image processing and computer vision.

[0055] U-Net++ is a deep learning architecture for medical image segmentation and is an improvement on the classic U-Net (a convolutional neural network architecture). U-Net++ aims to improve segmentation accuracy and model robustness by introducing dense skip connections and a deep supervision mechanism.

[0056] Transmission lines play an important role in transmitting electric energy in the power grid. However, due to factors such as the complexity of their operating environment and the wide span of transmission lines across regions, they are vulnerable to the influence of macroclimate, microtopography, and micro-meteorological factors, resulting in icing on the transmission lines. Icing disasters seriously affect the stable operation of the power grid. Minor ones may cause accidents such as violent dancing of transmission lines, ice flashover tripping of insulator strings, and phase-to-phase flashover tripping. Severe ones may cause accidents such as pole tilt or even collapse, line breakage, and damage to metal components of the line. Since transmission lines are usually erected in remote areas with poor transportation, once a serious icing accident occurs and the repair is not timely, it often causes long-term and large-area paralysis of the transmission lines, bringing many inconveniences to production and life.

[0057] With the rapid construction of the power grid, the coverage area of transmission line erection is gradually increasing. Especially for ultra-high voltage and extra-high voltage transmission lines, the erection area has a wide span, passes through complex climates and terrains, and is vulnerable to the impact of harsh meteorological environments. The reliable operation of transmission lines is seriously affected by line icing. Transmission line icing is mainly related to factors such as air temperature and humidity. Icing disasters mainly depend on the icing load and thickness changes. When the icing on the transmission line exceeds the load-bearing capacity of the transmission line, de-icing and melting ice operations need to be carried out. Determining parameters such as melting ice time and melting current for the operation is affected by the icing thickness. According to the survey specification of overhead transmission lines, when glaze, wet snow, and mixed glaze reach 31 mm and rime reaches 38 mm, the icing weight needs to be measured. Different icing types have different densities and pose different hazards to transmission lines. Therefore, accurately identifying the icing type and providing a reliable basis for power personnel to judge the icing condition is of great significance for preventing icing accidents and improving the reliability of the power system.

[0058] Currently, a trained neural network model is usually used to identify the icing types of transmission lines. However, when identifying the icing types in the above manner, the complexity of the neural network model is relatively high. Therefore, there is a problem of high computing power requirements.

[0059] Based on the above problems, the present application provides a method, device, equipment and storage medium for identifying the icing types of transmission lines. By acquiring transmission line images, it is determined whether the transmission lines are iced according to the transmission line images. If the transmission lines are iced, based on computer vision and the characteristics of different icing types (glaze ice, rime ice and mixed ice), the icing types of the transmission lines are identified. It is not necessary to identify the icing types through a neural network model, which can greatly reduce the computing power requirements, effectively improve the recognition accuracy and reliability of the icing types of transmission lines, and reduce the dependence on computing resources.

[0060] The following uses specific embodiments to elaborate in detail on the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems. These several specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below with reference to the drawings.

[0061] Figure 1 It is a flowchart of a method for identifying the icing types of transmission lines provided by an embodiment of the present application. This method for identifying the icing types of transmission lines can be executed by software and / or a hardware device. For example, the hardware device can be a device for identifying the icing types of transmission lines, and this device for identifying the icing types of transmission lines can be an electronic device or a processing chip in the electronic device. As Figure 1 shown, the method for identifying the icing types of transmission lines in the embodiment of the present application includes:

[0062] S101. Acquire transmission line images.

[0063] In the embodiment of the present application, for example, a monocular Red Green Blue (RGB) camera installed on the transmission line can be used to acquire transmission line images.

[0064] S102. Determine whether the transmission lines are iced according to the transmission line images.

[0065] Exemplarily, the transmission lines in the acquired transmission line images may be in an iced state or an un-iced state. It can be determined whether the transmission lines are iced based on deep learning. For example, the transmission line images can be input into a pre-trained icing detection model for icing detection of the transmission lines to determine whether the transmission lines are iced. For how to determine whether the transmission lines are iced according to the transmission line images specifically, reference can be made to the subsequent embodiments.

[0066] S103. If the transmission line is ice-covered, based on the transmission line image and the ice-covered area corresponding to the transmission line, obtain the transmission line area corresponding to the transmission line.

[0067] It can be understood that the ice-covered types to be identified in the embodiments of the present application may include glaze ice, rime ice, and mixed ice. Among them, the characteristics of glaze ice are more obvious compared with rime ice and mixed ice. The color feature of glaze ice is usually semi-transparent. When the temperature is lower than minus five degrees Celsius, glaze ice will present a shiny transparent structure, resulting in the exposure of the transmission line and its color being clearly visible. While rime ice and mixed ice are mostly white or milky white. Under the ice-covered state, the transmission line is not completely wrapped or is completely wrapped, and the transmission line is faintly visible or completely invisible. Therefore, glaze ice can be identified based on the characteristics of the above different ice-covered types. In this step, the ice-covered area corresponding to the transmission line is obtained, for example, through an ice-covered detection model. After determining that the transmission line is ice-covered, the transmission line can be extracted based on the transmission line image, and combined with the ice-covered area corresponding to the transmission line, to accurately obtain the transmission line area corresponding to the transmission line. For how to specifically obtain the transmission line area corresponding to the transmission line based on the transmission line image and the ice-covered area corresponding to the transmission line, reference can be made to the subsequent embodiments.

[0068] S104. If the transmission line area meets the preset length-width relationship, determine that the ice-covered type of the transmission line is glaze ice.

[0069] Exemplarily, after obtaining the transmission line area corresponding to the transmission line, a morphological closing operation (an image processing technique) can be performed on the transmission line area to remove noise points. If the length and width of the circumscribed rectangle of the transmission line area meet the preset length-width relationship, it can be determined that the ice-covered type of the transmission line is glaze ice. The specific preset length-width relationship satisfies the following formula (1):

[0070] width < 0.75 * cols or height < 0.75 * rows Formula (1)

[0071] Wherein, width represents the length of the circumscribed rectangle of the transmission line area; height represents the width of the circumscribed rectangle of the transmission line area; cols represents the length of the transmission line image; rows represents the height (width) of the transmission line image.

[0072] S105. If the transmission line area does not meet the preset length-width relationship, perform a second-order curve fitting on the pixel points in the transmission line area to obtain a fitting result; based on the fitting result, identify the ice-covered type of the transmission line as rime ice or mixed ice.

[0073] It can be understood that the rime is granularly distributed on the transmission line, being discrete rather than continuous on the transmission line, with gaps between each other, looking relatively rough and unable to completely wrap the transmission line; the mixed rime is formed by rain continuously dripping on the rime, which results in two different types of ice coatings inside and outside, with a milky white color and an irregular shape, and can completely wrap the transmission line. Therefore, when the preset length-width relationship is not satisfied in the transmission line area, the ice coating type can be identified as rime or mixed rime based on the above characteristics.

[0074] Exemplarily, second-order curve fitting can be performed on the pixel points in the transmission line area to obtain a fitting result, that is, to determine the second-order curve expression f(x). For how to specifically perform second-order curve fitting on the pixel points in the transmission line area to obtain the fitting result, reference can be made to the subsequent embodiments. Furthermore, based on the second-order curve expression f(x), the first quantity of the pixel points in the transmission line area on the second-order curve can be determined, and based on the first quantity, it can be identified whether the ice coating type of the transmission line is mixed rime. If it is impossible to determine whether the ice coating type of the transmission line is mixed rime based on the first quantity, then it can also be determined whether the ice coating type is rime or mixed rime according to whether the pixel points on the second-order curve are in a discrete state. For how to specifically identify the ice coating type of the transmission line as rime or mixed rime based on the fitting result, reference can be made to the subsequent embodiments, and details will not be elaborated here.

[0075] The method for identifying the ice coating type of a transmission line provided by the embodiments of the present application includes obtaining a transmission line image, and determining whether the transmission line is ice-coated according to the transmission line image; if the transmission line is ice-coated, then based on the transmission line image and the ice-coated area corresponding to the transmission line, obtaining the transmission line area corresponding to the transmission line; if the transmission line area satisfies the preset length-width relationship, then determining that the ice coating type of the transmission line is glaze; if the transmission line area does not satisfy the preset length-width relationship, then performing second-order curve fitting on the pixel points in the transmission line area to obtain a fitting result; and based on the fitting result, identifying the ice coating type of the transmission line as rime or mixed rime. The embodiments of the present application adopt the following strategy to identify the ice coating type; among them, the first step is to judge whether the transmission line in the transmission line image is ice-coated, converting the multi-ice coating type identification problem into a binary classification problem of "yes or no"; the second step is to extract the transmission line in the ice-coated state through computer vision to obtain the transmission line area corresponding to the transmission line, and then to identify the ice coating type by judging the integrity and continuity of the transmission line, that is, to identify the ice coating type based on the characteristics of different ice coating types, without the need to identify the ice coating type through a neural network model, which can greatly reduce the computing power requirements, and the above strategy can effectively improve the identification accuracy and reliability of the ice coating type of the transmission line, and can reduce the dependence on computing resources.

[0076] Figure 2The flowchart of the transmission line icing type recognition method provided in another embodiment of this application. On the basis of the above embodiment, the embodiment of this application further describes the transmission line icing type recognition method. As Figure 2 shown, the transmission line icing type recognition method of the embodiment of this application may include:

[0077] S201. Obtain the transmission line image.

[0078] For the specific description of this step, reference may be made to the relevant description of S101 in the Figure 1 shown embodiment, which will not be elaborated here.

[0079] In the embodiment of this application, Figure 1 step S102 in may further include the following three steps of S202 to S204:

[0080] S202. Input the transmission line image into the icing detection model for transmission line icing detection, and obtain the detection result output by the icing detection model. The icing detection model is constructed based on the U-net++ architecture.

[0081] In this step, the icing detection model can be constructed based on the U-net++ architecture, and the icing detection model is trained with training samples to obtain a trained icing detection model. For how to specifically train and obtain the icing detection model, reference can be made to the subsequent embodiments, which will not be elaborated here. Exemplarily, inputting the transmission line image into the icing detection model for transmission line icing detection can obtain the detection result output by the icing detection model. If the transmission line is iced, the detection result includes the icing area; if the transmission line is not iced, the detection result does not include the icing area.

[0082] S203. If the detection result includes the icing area, it is determined that the transmission line is iced, and step S205 is continued to be executed.

[0083] S204. If the detection result does not include the icing area, it is determined that the transmission line is not iced, and the process ends.

[0084] Exemplarily, if the detection result includes the icing area, it can be determined that the transmission line is iced, and then the icing type can be further identified; if the detection result does not include the icing area, it can be determined that the transmission line is not iced, and there is no need to identify the icing type. Exemplarily, Figure 3 The schematic diagram of the detection result including the icing area provided for the embodiment of this application Figure 1 is as Figure 3 shown, showing the corresponding icing area 301 in the case where the icing type is rime. Figure 4 The schematic diagram of the detection result including the icing area provided for the embodiment of this application Figure 2 is as Figure 4As shown, the ice-covered area 401 corresponding to the case where the ice type is mixed rime is shown. Figure 5 The schematic diagram of the detection result including the ice-covered area provided by the embodiment of the present application Figure 3 , such as Figure 5 As shown, the ice-covered area 501 corresponding to the case where the ice type is glaze is shown. Refer to Figure 3 , Figure 4 and Figure 5 It can be known that the ice-covered areas corresponding to different ice types are different.

[0085] In the embodiment of the present application, Figure 1 Step S103 in it may further include the following three steps of S205 to S207:

[0086] S205: Convert the transmission line image to the HSV color space to obtain the converted image.

[0087] Exemplarily, considering that the characteristics of glaze are more obvious compared with rime and mixed rime, the color feature of glaze is usually semi-transparent. When the temperature is lower than minus five degrees, glaze will present a shiny transparent structure, resulting in the exposure of the transmission line and the color being clearly visible. While rime and mixed rime are mostly white or milky white, the transmission line is not completely wrapped or is completely wrapped under the ice-covered state, and the transmission line is faintly visible or completely invisible. Considering that the color of the transmission line is usually black, therefore, the transmission line image (such as represented by F) can be converted to the HSV color space to obtain the converted image (such as represented by F hsv ) to more accurately obtain the transmission line area corresponding to the transmission line.

[0088] S206: Extract the transmission line based on the hue component value, saturation component value, and brightness component value corresponding to the converted image to obtain the initial transmission line area.

[0089] In this step, after obtaining the converted image in the HSV color space, the transmission line can be extracted based on the hue (H) component value, saturation (S) component value, and brightness (V) component value corresponding to the converted image to obtain the initial transmission line area (such as represented by R1).

[0090] Further, optionally, extracting the transmission line based on the hue component value, saturation component value, and brightness component value corresponding to the converted image to obtain the initial transmission line area may include: extracting the transmission line in the converted image according to the first upper limit of the hue component value, the second upper limit of the saturation component value, and the third upper limit of the brightness component value corresponding to the color of the transmission line in the HSV color space to obtain the initial transmission line area, and the third upper limit is determined according to the mean value of the brightness component values of the pixel points included in the converted image and the background illumination of the converted image.

[0091] Exemplarily, considering that the color of the transmission line is usually black, the value range of the hue component corresponding to black in the HSV color space is, for example, 0 - 180, the value range of the saturation component is, for example, 0 - 255, and the value range of the brightness component is, for example, 0 - 46. Among them, the first upper limit is 180, the second upper limit is 255, and the third upper limit is 46. The transmission line in the converted image can be extracted according to the first upper limit of the hue component value, the second upper limit of the saturation component value, and the third upper limit of the brightness component value corresponding to the color of the transmission line in the HSV color space, so as to obtain the initial transmission line area. Among them, the inventor found in actual tests that the value of the third upper limit of the brightness component value has a great influence on the extraction of the transmission line. When the third upper limit is too large, the background part will be extracted, and when the third upper limit is too small, the transmission line cannot be accurately extracted. By analyzing the extraction of the transmission line from the converted image with different upper limit values of the brightness component value, the value of the third upper limit can be determined according to the mean value of the brightness component values of the pixel points included in the converted image and the background illumination of the converted image. The third upper limit satisfies the following formula two:

[0092]

[0093] Among them, up represents the third upper limit; represents the mean value of the brightness component values of the pixel points included in the converted image.

[0094] S207. Perform background elimination processing on the initial transmission line area through the icing area to obtain the transmission line area.

[0095] Exemplarily, after obtaining the initial transmission line area, the initial transmission line area may contain pixel points in the area outside the area where the transmission line is located. This pixel point is the pixel point corresponding to the background mis-extracted in the HSV color space. Therefore, it is necessary to perform background elimination processing on the initial transmission line area through the icing area. Specifically, the following formula three can be used to achieve background elimination processing on the initial transmission line area through the icing area, that is, to eliminate the interference of the background mis-extracted in the HSV color space, so as to obtain the transmission line area.

[0096] R pl = R1 & R fg Formula three

[0097] Among them, R pl represents the transmission line area; R fg represents the icing area; R1 is the initial transmission line area.

[0098] S208. If the transmission line area meets the preset length-width relationship, determine that the icing type of the transmission line is glaze.

[0099] For the specific description of this step, reference can be made to Figure 1 the relevant description of S104 in the illustrated embodiment. Exemplarily, Figure 6 FIG. is a schematic diagram of the transmission line area provided by the embodiment of the present application Figure 1 , such as Figure 6 shown, which shows the transmission line area corresponding to the case where the icing type is rime, that is, Figure 6 the white area in Figure 7 FIG. is a schematic diagram of the transmission line area provided by the embodiment of the present application Figure 2 , such as Figure 7 shown, which shows the transmission line area corresponding to the case where the icing type is mixed glaze, that is, Figure 7 the white area in Figure 8 FIG. is a schematic diagram of the transmission line area provided by the embodiment of the present application Figure 3 , such as Figure 8 shown, which shows the transmission line area corresponding to the case where the icing type is glaze, that is, Figure 8 the white area in. Referring to Figure 6 , Figure 7 and Figure 8 , it can be seen that different icing types correspond to different obtained transmission line areas.

[0100] In the embodiment of the present application, Figure 1 step S105 in

[0101] S209. If the transmission line area does not satisfy the preset length-width relationship, the random sample consensus (RANSAC) algorithm is used to perform a second-order curve fitting on the pixel points in the transmission line area to obtain a fitting result.

[0102] Exemplarily, considering that the distribution of rime on the transmission line is granular, discrete rather than continuous on the transmission line, there are gaps between them, and it looks relatively rough and cannot completely wrap the transmission line; mixed glaze is formed by rain continuously dripping on rime, which will cause two different icing types inside and outside, its color is milky white, and its shape is relatively irregular, and it can completely wrap the transmission line. Therefore, when the transmission line area does not satisfy the preset length-width relationship, the random sample consensus (RANSAC) algorithm is used to perform a second-order curve fitting on the pixel points in the transmission line area to obtain a fitting result, and then based on the fitting result, the icing type of the transmission line can be identified as rime or mixed glaze.

[0103] Specifically, the process of performing a second-order curve fitting on the pixel points in the transmission line area by using the RANSAC algorithm may include the following three steps:

[0104] Step 1: Randomly sample within the transmission line area, for example, randomly sample 5 pixel points;

[0105] Step 2: Perform second-order curve fitting through the above 5 pixel points to obtain a well-fitted second-order curve. The well-fitted second-order curve can also be understood as a second-order curve model;

[0106] Step 3: Obtain the distance from other pixel points within the transmission line area to the second-order curve model. If the distance is less than the distance threshold, determine that the corresponding pixel point is on the second-order curve. This pixel point is the inlier, and count the number of inliers;

[0107] Iteratively execute the above Step 1 to Step 3 until the maximum number of iterations is reached. Select the second-order curve model with the largest number of inliers as the fitting result. Correspondingly, the second-order curve expression f(x) of the pixel points conforming to most transmission lines can be obtained. For any extracted pixel point (x, y) of the transmission line within the transmission line area, if |y - f(x)| < t, where t is the preset error, determine that this pixel point is on the second-order curve.

[0108] S210: According to the fitting result, if the ratio of the first quantity to the second quantity is less than or equal to the preset threshold, determine that the icing type of the transmission line is mixed rime. The first quantity is the number of pixel points on the second-order curve within the transmission line area, and the second quantity is the number of pixel points within the transmission line area.

[0109] Exemplarily, the preset threshold is, for example, 0.6. The first quantity is the number of pixel points on the second-order curve within the transmission line area, denoted by S for example; the second quantity is the number of pixel points within the transmission line area, denoted by P for example. If S / P ≤ 0.6, determine that the icing type of the transmission line is mixed rime.

[0110] S211: If the ratio is greater than the preset threshold, determine whether the pixel points on the second-order curve are in a discrete state; if they are in a discrete state, determine that the icing type of the transmission line is glaze, and if they are not in a discrete state, determine that the icing type of the transmission line is mixed rime.

[0111] Exemplarily, if S / P > 0.6, it is also necessary to continue to determine whether the pixel points on the second-order curve are in a discrete state. If they are in a discrete state, determine that the icing type of the transmission line is glaze, and if they are not in a discrete state, determine that the icing type of the transmission line is mixed rime.

[0112] It should be noted that the embodiments of the present application do not limit the execution order of steps S210 and S211.

[0113] Optionally, determining whether the pixel points on the second-order curve are in a discrete state may include: sorting the pixel points on the second-order curve according to the x coordinate of the pixel points to obtain the sorted pixel points; if the distance between the x coordinates of two adjacent pixel points in the sorted pixel points is less than the distance threshold, determining that the two adjacent pixel points are a continuous block; if the number of continuous blocks is less than the number threshold, determining that the pixel points on the second-order curve are in a discrete state; if the number of continuous blocks is greater than or equal to the number threshold, determining that the pixel points on the second-order curve are not in a discrete state.

[0114] Exemplarily, the number threshold is, for example, 5. Sort the x coordinates of S pixel points on the second-order curve in the transmission line area in ascending order to obtain the x coordinate set X s ={x1, x2, x3, …, x s}. For two adjacent elements x s and x i in X i+1 , if it satisfies x i+1 - x i < d th , then it can be determined that x i and x i+1 belong to a continuous block, where d th represents the distance threshold, and the value of d th is, for example, 2. Based on the number threshold 5, judge the number B s of continuous blocks in X c . If B c satisfies B c < 5, it can be determined that the elements in X s are discretely distributed, that is, it is determined that the pixel points on the second-order curve are in a discrete state, and then it can be determined that the icing type of the transmission line is rime; if B c satisfies B c ≥ 5, it can be determined that the elements in X s are not in a discrete state, that is, it is determined that the pixel points on the second-order curve are not in a discrete state, and then it can be determined that the icing type of the transmission line is mixed glaze.

[0115] The ice coating type recognition method provided by the embodiment of the present application obtains a transmission line image, inputs the transmission line image into an ice coating detection model for ice coating detection of the transmission line, and obtains a detection result output by the ice coating detection model; if the detection result includes an ice coating area, it is determined that the transmission line is ice-coated, the transmission line image is converted to the HSV color space to obtain a converted image, and the transmission line is extracted based on the hue component value, saturation component value, and brightness component value corresponding to the converted image to obtain an initial transmission line area; the initial transmission line area is subjected to background removal processing through the ice coating area to obtain a transmission line area; if the transmission line area meets a preset length-width relationship, it is determined that the ice coating type of the transmission line is glaze, and if the transmission line area does not meet the preset length-width relationship, the random sample consensus algorithm is used to perform second-order curve fitting on the pixel points in the transmission line area to obtain a fitting result; according to the fitting result, if the ratio of the first quantity to the second quantity is less than or equal to a preset threshold, it is determined that the ice coating type of the transmission line is mixed glaze, the first quantity is the number of pixel points in the transmission line area on the second-order curve, and the second quantity is the number of pixel points in the transmission line area; if the ratio is greater than the preset threshold, it is determined whether the pixel points on the second-order curve are in a discrete state; if they are in a discrete state, it is determined that the ice coating type of the transmission line is rime, and if they are not in a discrete state, it is determined that the ice coating type of the transmission line is mixed glaze. First, the ice coating detection model is used in the embodiment of the present application to determine whether the transmission line in the transmission line image is ice-coated, and the multi-ice coating type recognition problem is transformed into a binary classification problem of "yes or no"; in the case of determining that the transmission line is ice-coated, the transmission line under the ice-coated state is extracted based on the transmission line image to obtain a transmission line area corresponding to the transmission line, and then the ice coating type is recognized based on the characteristics of different ice coating types, without the need to recognize the ice coating type through a neural network model, which can greatly reduce the computing power requirement, effectively improve the recognition accuracy and reliability of the ice coating type of the transmission line, and reduce the dependence on computing resources.

[0116] Based on the above embodiment, Figure 9 is a flowchart of a training method for an ice coating detection model provided by an embodiment of the present application. As Figure 9 shown, the training method for the ice coating detection model in the embodiment of the present application includes:

[0117] S901. Obtain training samples, where the training samples include transmission line ice coating sample images, transmission line non-ice coating sample images, and reference ice coating areas corresponding to the transmission line ice coating sample images.

[0118] Exemplarily, a large number of iced transmission line sample images and non-iced transmission line sample images can be collected. Through a preset annotation software, pixel points in the iced area corresponding to the transmission line in the iced transmission line sample images are manually annotated to obtain the reference iced area corresponding to the iced transmission line sample images, and the annotated iced transmission line sample images are obtained. Figure 10 The following is a schematic diagram of the annotated iced transmission line sample image provided by an embodiment of the present application. As Figure 10 shown, pixel points in the iced areas corresponding to the three transmission lines (i.e., 1001, 1002, and 1003) in the iced transmission line sample image have all been manually annotated, and the unannotated black pixel points are the background. A plurality of iced transmission line sample images, a plurality of non-iced transmission line sample images, and the reference iced area corresponding to each iced transmission line sample image constitute the dataset D corresponding to the training samples.

[0119] S902. Based on the training samples, iteratively train the icing detection model until the calculated loss function value meets the preset evaluation condition or the number of iterations reaches the preset number of iterations, and obtain the trained icing detection model. The icing detection model is constructed based on the U-net++ architecture.

[0120] Exemplarily, the icing detection model is constructed based on the U-net++ architecture. The dataset D corresponding to the training samples can be divided into a training set, a validation set, and a test set according to 7:2:1. Through deep learning, the icing detection model is trained based on the U-net++ architecture through the training set. Among them, when the non-iced transmission line sample image is input into the icing detection model, no predicted icing area will be output, indicating that the transmission line is not iced; when the iced transmission line sample image is input into the icing detection model, the predicted icing area output by the icing detection model can be obtained. According to the predicted icing area and the reference icing area corresponding to the iced transmission line sample image, the loss function value is obtained. Furthermore, according to the loss function value, the parameters of the icing detection model can be adjusted until the calculated loss function value meets the preset evaluation condition or the number of iterations reaches the preset number of iterations, and the trained icing detection model is obtained; the validation set is used for hyperparameter tuning of the icing detection model and selection of the best model architecture to prevent overfitting; the test set is used to evaluate the final performance of the icing detection model.

[0121] The training method of the icing detection model provided by the embodiment of the present application obtains training samples, where the training samples include icing sample images of transmission lines, non-icing sample images of transmission lines, and the corresponding reference icing areas of the icing sample images of transmission lines. Based on the training samples, the icing detection model is iteratively trained until the calculated loss function value meets the preset evaluation conditions or the number of iterations reaches the preset number of iterations, and a trained icing detection model is obtained. The icing detection model is constructed based on the U-net++ architecture. The icing detection model trained by the embodiment of the present application can accurately distinguish whether the transmission line is iced, and when it is determined that the transmission line is iced, accurately output the icing area corresponding to the transmission line.

[0122] The following is an embodiment of the device of the present application, which can be used to execute the method embodiment of the present application. For the details not disclosed in the embodiment of the device of the present application, please refer to the method embodiment of the present application.

[0123] Figure 11 It is a schematic structural diagram of a device for identifying the icing type of a transmission line provided by an embodiment of the present application. As Figure 11 shown, the device 1100 for identifying the icing type of a transmission line in the embodiment of the present application includes: a first acquisition module 1101, a first determination module 1102, a second acquisition module 1103, a second determination module 1104, and a processing module 1105. Among them:

[0124] The first acquisition module 1101 is used to acquire an image of a transmission line.

[0125] The first determination module 1102 is used to determine whether the transmission line is iced according to the image of the transmission line.

[0126] The second acquisition module 1103 is used to, if the transmission line is iced, acquire the transmission line area corresponding to the transmission line based on the image of the transmission line and the icing area corresponding to the transmission line.

[0127] The second determination module 1104 is used to determine that the icing type of the transmission line is glaze if the transmission line area meets the preset length-width relationship.

[0128] The processing module 1105 is used to, if the transmission line area does not meet the preset length-width relationship, perform a second-order curve fitting on the pixel points in the transmission line area to obtain a fitting result; based on the fitting result, identify the icing type of the transmission line as rime or mixed rime.

[0129] In some embodiments, the second acquisition module 1103 may be specifically configured to: convert the transmission line image to the HSV color space to obtain a converted image; extract the transmission line based on the hue component value, saturation component value, and brightness component value corresponding to the converted image to obtain an initial transmission line area; perform background removal processing on the initial transmission line area through the icing area to obtain the transmission line area.

[0130] Optionally, when the second acquisition module 1103 is used to extract the transmission line based on the hue component value, saturation component value, and brightness component value corresponding to the converted image to obtain an initial transmission line area, it may be specifically configured to: extract the transmission line in the converted image according to the first upper limit of the hue component value, the second upper limit of the saturation component value, and the third upper limit of the brightness component value corresponding to the color of the transmission line in the HSV color space to obtain an initial transmission line area, and the third upper limit is determined according to the mean value of the brightness component values of the pixel points included in the converted image and the background illumination of the converted image.

[0131] Optionally, when the processing module 1105 is used to perform a second-order curve fitting on the pixel points in the transmission line area to obtain a fitting result, it may be specifically configured to: use the random sample consensus algorithm to perform a second-order curve fitting on the pixel points in the transmission line area to obtain a fitting result.

[0132] Optionally, when the processing module 1105 is used to identify the icing type of the transmission line as rime or mixed rime based on the fitting result, it may be specifically configured to: according to the fitting result, if the ratio of the first quantity to the second quantity is less than or equal to a preset threshold, determine that the icing type of the transmission line is mixed rime, where the first quantity is the number of pixel points in the transmission line area on the second-order curve, and the second quantity is the number of pixel points in the transmission line area; if the ratio is greater than the preset threshold, determine whether the pixel points on the second-order curve are in a discrete state; if they are in a discrete state, determine that the icing type of the transmission line is rime, and if they are not in a discrete state, determine that the icing type of the transmission line is mixed rime.

[0133] Optionally, when the processing module 1105 is used to determine whether the pixel points on the second-order curve are in a discrete state, it may be specifically configured to: sort the pixel points on the second-order curve according to the x coordinate of the pixel points to obtain the sorted pixel points; if the distance between the x coordinates of two adjacent pixel points in the sorted pixel points is less than a distance threshold, determine that the two adjacent pixel points are a continuous block; if the number of continuous blocks is less than a quantity threshold, determine that the pixel points on the second-order curve are in a discrete state; if the number of continuous blocks is greater than or equal to the quantity threshold, determine that the pixel points on the second-order curve are not in a discrete state.

[0134] In some embodiments, the first determination module 1102 may be specifically configured to: input the transmission line image into an icing detection model for icing detection of the transmission line to obtain a detection result output by the icing detection model, where the icing detection model is constructed based on the U-net++ architecture; if the detection result includes an icing area, determine that the transmission line is iced; if the detection result does not include an icing area, determine that the transmission line is not iced.

[0135] Optionally, the transmission line icing type identification device 1100 may further include a training module ( Figure 11 not shown in the figure) for training and obtaining the icing detection model in the following manner: obtaining training samples, where the training samples include transmission line icing sample images, transmission line non-icing sample images, and reference icing areas corresponding to the transmission line icing sample images; based on the training samples, iteratively training the icing detection model until the calculated loss function value meets a preset evaluation condition or the number of iterations reaches a preset number of iterations, to obtain a trained icing detection model, where the icing detection model is constructed based on the U-net++ architecture.

[0136] The device in the embodiments of the present application can be used to execute the technical solutions of any of the above-described method embodiments. The implementation principles and technical effects are similar and will not be elaborated here.

[0137] Figure 12 This is a schematic structural diagram of an electronic device provided in an embodiment of the present application. As Figure 12 shown, the electronic device 1200 may include: at least one processor 1201 and a memory 1202.

[0138] The memory 1202 is used to store a program. Specifically, the program may include program code, and the program code includes computer execution instructions.

[0139] The memory 1202 may include a high-speed random access memory (Random Access Memory, RAM), and may also include a non-volatile memory, such as at least one disk memory.

[0140] The processor 1201 is used to execute the computer-executable instructions stored in the memory 1202 to implement the transmission line icing type recognition method described in the foregoing method embodiments. Among them, the processor 1201 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. Specifically, when implementing the transmission line icing type recognition method described in the foregoing method embodiments, the electronic device may be an electronic device with processing functions such as a terminal.

[0141] Optionally, the electronic device 1200 may further include a communication interface 1203. In specific implementation, if the communication interface 1203, the memory 1202, and the processor 1201 are independently implemented, the communication interface 1203, the memory 1202, and the processor 1201 may be interconnected through a bus and communicate with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc., but it does not mean that there is only one bus or one type of bus.

[0142] Optionally, in specific implementation, if the communication interface 1203, the memory 1202, and the processor 1201 are integrated on a chip, the communication interface 1203, the memory 1202, and the processor 1201 may communicate through an internal interface.

[0143] The present application also provides a computer-readable storage medium, in which computer program instructions are stored. When the processor executes the computer program instructions, the solution of the transmission line icing type recognition method as described above is implemented.

[0144] The present application also provides a computer program product, including a computer program, which implements the solution of the transmission line icing type recognition method as described above when executed.

[0145] The above-mentioned computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disk. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0146] An exemplary readable storage medium is coupled to the processor so that the processor can read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit. Of course, the processor and the readable storage medium can also exist as discrete components in the device for identifying the icing type of a transmission line.

[0147] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps included in the above method embodiments; and the foregoing storage medium includes various media that can store program codes, such as ROM, RAM, a magnetic disk, or an optical disk.

[0148] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for identifying icing types of transmission lines, characterized in that Including: Obtaining an image of a transmission line; Determining whether the transmission line is ice-covered based on the image of the transmission line; If the transmission line is ice-covered, obtaining the transmission line area corresponding to the transmission line based on the image of the transmission line and the ice-covered area corresponding to the transmission line; If the transmission line area satisfies a preset length-width relationship, determining that the ice-covered type of the transmission line is glaze; If the transmission line area does not satisfy the preset length-width relationship, performing a second-order curve fitting on the pixel points within the transmission line area to obtain a fitting result; based on the fitting result, identifying the ice-covered type of the transmission line as rime or mixed rime.

2. The method for identifying the icing type of a transmission line according to claim 1, characterized in that The obtaining the transmission line area corresponding to the transmission line based on the image of the transmission line and the ice-covered area corresponding to the transmission line includes: Converting the image of the transmission line to the HSV color space to obtain a converted image; Extracting the transmission line based on the hue component value, saturation component value, and brightness component value corresponding to the converted image to obtain an initial transmission line area; Performing background removal processing on the initial transmission line area through the ice-covered area to obtain the transmission line area.

3. The method for identifying the icing type of a transmission line according to claim 2, wherein The extracting the transmission line based on the hue component value, saturation component value, and brightness component value corresponding to the converted image to obtain an initial transmission line area includes: Extracting the transmission line in the converted image according to the first upper limit of the hue component value, the second upper limit of the saturation component value, and the third upper limit of the brightness component value corresponding to the color of the transmission line in the HSV color space to obtain the initial transmission line area, where the third upper limit is determined according to the mean value of the brightness component values of the pixel points included in the converted image and the background illumination of the converted image.

4. The method for identifying the icing type of a transmission line according to claim 1, characterized in that, The performing a second-order curve fitting on the pixel points within the transmission line area to obtain a fitting result includes: Using the random sample consensus algorithm to perform a second-order curve fitting on the pixel points within the transmission line area to obtain the fitting result.

5. The method for identifying the icing type of a transmission line according to claim 1, wherein The identifying the ice-covered type of the transmission line as rime or mixed rime based on the fitting result includes: According to the fitting result, if the ratio of the first quantity to the second quantity is less than or equal to a preset threshold, determining that the ice-covered type of the transmission line is mixed rime, where the first quantity is the number of pixel points within the transmission line area on the second-order curve, and the second quantity is the number of pixel points within the transmission line area; If the ratio is greater than the preset threshold, determining whether the pixel points on the second-order curve are in a discrete state; if in a discrete state, determining that the ice-covered type of the transmission line is rime, and if not in a discrete state, determining that the ice-covered type of the transmission line is mixed rime.

6. The method for identifying the icing type of a transmission line according to claim 5, wherein The determining whether the pixel points on the second-order curve are in a discrete state includes: Sorting the pixel points on the second-order curve according to the x coordinate of the pixel points to obtain sorted pixel points; If the distance between the x coordinates of two adjacent pixel points among the sorted pixel points is less than a distance threshold, determining that the two adjacent pixel points are a continuous block; If the number of the continuous blocks is less than the number threshold, determine that the pixel points on the second-order curve are in a discrete state; If the number of the continuous blocks is greater than or equal to the number threshold, determine that the pixel points on the second-order curve are not in a discrete state.

7. The method for identifying the icing type of a transmission line according to any one of claims 1 to 6, characterized in that, The determining whether the transmission line is iced according to the transmission line image includes: Inputting the transmission line image into an icing detection model for icing detection of the transmission line to obtain a detection result output by the icing detection model, where the icing detection model is constructed based on the U-net++ architecture; If the detection result includes the icing area, determine that the transmission line is iced; If the detection result does not include the icing area, determine that the transmission line is not iced.

8. The method for identifying the icing type of a transmission line according to claim 7, wherein, The icing detection model is obtained by training in the following manner: Obtain training samples, where the training samples include transmission line icing sample images, transmission line non-icing sample images, and the corresponding reference icing areas of the transmission line icing sample images; Based on the training samples, iteratively train the icing detection model until the calculated loss function value meets the preset evaluation condition or the number of iterations reaches the preset number of iterations to obtain a trained icing detection model, where the icing detection model is constructed based on the U-net++ architecture.

9. An ice coating type identification device for a transmission line, characterized in that including: A first acquisition module for acquiring a transmission line image; A first determination module for determining whether the transmission line is iced according to the transmission line image; A second acquisition module for, if the transmission line is iced, acquiring the transmission line area corresponding to the transmission line based on the transmission line image and the icing area corresponding to the transmission line; A second determination module for determining that the icing type of the transmission line is glaze if the transmission line area meets the preset length-width relationship; A processing module for, if the transmission line area does not meet the preset length-width relationship, performing second-order curve fitting on the pixel points in the transmission line area to obtain a fitting result; and identifying the icing type of the transmission line as rime or mixed rime based on the fitting result.

10. An electronic device, characterized in that, including: A processor and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the transmission line icing type identification method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, Computer program instructions are stored in the computer-readable storage medium, and when the computer program instructions are executed, the transmission line icing type identification method according to any one of claims 1 to 8 is implemented.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed, the transmission line icing type identification method according to any one of claims 1 to 8 is implemented.

Images