Insulator ice recognition method, device, storage medium and equipment

Abstract

The invention discloses an insulator icing recognition method, comprising: training a Yolov3 target recognition model with a target icing image to obtain a trained Yolov3 target recognition model; obtaining an icing image to be tested, and reading its resolution to be tested and the number of an icing monitoring device to be tested; when the resolution to be tested meets a preset resolution condition, obtaining its preset shooting position to be tested; based on the trained Yolov3 target recognition model, obtaining an iced insulator interest region to be tested and an ice-free insulator interest region to be tested of the icing image to be tested; calculating the color change rate of the insulator before and after icing and the growth rate of the icing region of the insulator according to the iced insulator interest region to be tested and the ice-free insulator interest region; judging the icing degree of the insulator of the icing image to be tested according to the color change rate and the growth rate and issuing corresponding warning information. The embodiment of the invention can accurately and comprehensively grasp the icing degree of the insulator.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a method, device, storage medium and equipment for identifying ice coating on an insulator. Background Art

[0002] Icing seriously threatens the safety and stability of the power grid. For example, it will reduce the mechanical and electrical properties of insulators. In severe cases, it will cause line flashover tripping, insulator string loss, wire breakage, and even tower collapse. Therefore, accurately understanding the degree of icing on transmission line insulators is of great significance for timely and effective anti-icing measures and ensuring the safe operation of transmission lines in icy and snowy weather.

[0003] In order to solve the problem of image recognition of transmission line insulators under complex environmental conditions, experts and scholars have made a lot of useful attempts. However, the existing insulator ice recognition methods have poor accuracy. Summary of the invention

[0004] The embodiments of the present invention provide an insulator icing identification method, device, storage medium and equipment to solve the problem of poor accuracy of the insulator icing identification method in the prior art, and can accurately and comprehensively grasp the icing degree of the insulators of the transmission line, providing technical support for the intelligent anti-icing of the transmission line.

[0005] To achieve the above object, an embodiment of the present invention provides a method for identifying ice coating on an insulator, comprising:

[0006] Acquire a plurality of initial ice-covered images collected by a plurality of ice-covered monitoring devices, and pre-process the plurality of initial ice-covered images to obtain a plurality of target ice-covered images;

[0007] Building an image knowledge base based on parameter information of a plurality of target ice-covered images, wherein the parameter information includes a shooting preset position, a resolution, and an ice-covered monitoring device number;

[0008] The Yolo v3 target recognition model is trained using the target ice-covered image in the image knowledge base to obtain a trained Yolo v3 target recognition model;

[0009] Acquire an ice image to be measured collected in real time by any ice monitoring device, and read the resolution to be measured of the ice image to be measured and the number of the ice monitoring device to be measured;

[0010] When the resolution to be measured meets the preset resolution condition, the preset shooting position to be measured of the ice-covered image to be measured is obtained according to the number of targets to be measured, the size to be measured and the position to be measured of the insulator in the ice-covered image to be measured;

[0011] Based on the trained Yolo v3 target recognition model, the iced insulator region of interest to be tested of the iced image to be tested and the non-iced insulator region of interest of the target iced image having the same number as the preset shooting position to be tested and the iced monitoring device to be tested and the insulator icing state being non-iced are obtained;

[0012] According to the region of interest of the iced insulator to be tested and the region of interest of the non-iced insulator, the color change rate of the insulator before and after ice coating and the growth rate of the iced area of ​​the insulator are calculated;

[0013] According to the color change rate and the growth rate, the degree of icing on the insulator of the icing image to be measured is determined and corresponding warning information is issued.

[0014] As an improvement of the above scheme, the image knowledge base is constructed according to the parameter information of a plurality of target ice-covered images, wherein the parameter information includes the shooting preset position, resolution and ice-covered monitoring device number, including:

[0015] Calculating the number, size and position of insulators in a plurality of target ice-covered images;

[0016] Compare the target number, size and position of insulators in any two target icing images with the same icing monitoring device number to obtain a first comparison result, and number the shooting preset positions of a plurality of the target icing images according to the first comparison result until the plurality of the target icing images are traversed;

[0017] An image knowledge base is constructed according to the resolution of a plurality of numbered target ice-covered images and the number of the ice-covered monitoring device.

[0018] As an improvement of the above solution, the Yolo v3 target recognition model is trained using the target ice-covered image in the image knowledge base to obtain the trained Yolo v3 target recognition model, including:

[0019] Using at least one target ice-covered image of each ice-covered monitoring device and at least one target ice-covered image of each shooting preset position in the image knowledge base as a training image set;

[0020] Annotate the target ice-covered image in the training image set according to the ice-covered state of the insulator to obtain a training annotation set, wherein the file information of the training annotation set includes: the coordinates of the upper left corner vertex and the lower right corner vertex of the insulator target boundary rectangular box, and the ice-covered state code of the insulator;

[0021] The Yolo v3 target recognition model is trained using the target ice-covered image in the training image set and the files in the training annotation set to obtain a trained Yolo v3 target recognition model.

[0022] As an improvement of the above scheme, when the resolution to be measured meets the preset resolution condition, the preset position to be measured of the ice-covered image to be measured is obtained according to the number of targets to be measured, the size to be measured and the position to be measured of the insulator in the ice-covered image to be measured, including:

[0023] When the resolution to be measured meets the preset resolution condition, the number of targets to be measured, the size to be measured and the position to be measured of the insulator in the ice-covered image to be measured are calculated;

[0024] Compare the number of targets to be measured, the size to be measured and the position to be measured with the number, size and position of insulator targets in the target ice-covered image of the image knowledge base to obtain a second comparison result;

[0025] When the second comparison result meets the preset shooting preset position condition, the shooting preset position to be tested of the ice-covered image to be tested is obtained.

[0026] As an improvement of the above scheme, the method of obtaining the ice-covered insulator region of interest to be tested of the ice-covered image to be tested based on the trained Yolo v3 target recognition model, and the non-ice-covered insulator region of interest of the target ice-covered image having the same number as the preset shooting position to be tested and the ice-covered monitoring device to be tested, and the insulator ice-covered state is non-ice-covered, includes:

[0027] Input the ice-covered image to be tested into the trained Yolo v3 target recognition model to obtain the upper left corner vertex coordinates and the lower right corner vertex coordinates of the predicted insulator target boundary rectangular box of the ice-covered image to be tested and the ice-covered state of the insulator of the ice-covered image to be tested;

[0028] Calculate the lower left corner vertex coordinates and the upper right corner vertex coordinates of the predicted insulator target boundary rectangular box according to the upper left corner vertex coordinates and the lower right corner vertex coordinates;

[0029] The ice-covered image to be measured is cropped according to the upper left corner vertex coordinates, the lower right corner vertex coordinates, the lower left corner vertex coordinates and the upper right corner vertex coordinates to obtain a region of interest of the ice-covered insulator to be measured;

[0030] According to the upper left vertex coordinates, the lower right vertex coordinates, the lower left vertex coordinates and the upper right vertex coordinates, the target icing image having the same number as the preset shooting position to be tested and the icing monitoring device to be tested and the icing state of the insulator being no icing is cropped to obtain the insulator region of interest without icing.

[0031] As an improvement of the above solution, the color change rate of the insulator before and after icing and the growth rate of the icing area of ​​the insulator are calculated according to the ROI of the iced insulator to be tested and the ROI of the non-iced insulator, including:

[0032] According to the ice-covered insulator region of interest to be measured and the ice-free insulator region of interest, calculating the red component, green component and blue component of the ice-covered insulator region of interest to be measured and the red component, green component and blue component of the ice-free insulator region of interest;

[0033] Calculate the color change rate of the insulator before and after ice coating according to the red component, green component and blue component of the region of interest of the ice-covered insulator to be tested and the red component, green component and blue component of the region of interest of the non-ice-covered insulator;

[0034] Calculating the iced area of ​​the insulator according to the iced insulator interest region to be measured and the ice-free insulator interest region;

[0035] Binarizing the ice-covered area to obtain a binary ice-covered area;

[0036] Counting the number of white pixels in the binary ice-covered area;

[0037] The growth rate of the ice-covered area is calculated according to the number of white pixels.

[0038] As an improvement of the above solution, the step of determining the ice coverage degree of the insulator of the ice coverage image to be measured and issuing corresponding warning information according to the color change rate and the growth rate includes:

[0039] When (0≤C rate ≤25%)∪(0≤Region rate ≤25%), it is determined that the insulator icing degree of the icing image to be tested is not icing and a preset first warning message is issued, wherein C rate Indicates the color change rate, Region rate represents the growth rate;

[0040] When (25% ≤ C rate ≤50%)∪(25%≤Region rate ≤50%), it is determined that the ice coverage of the insulator in the ice coverage image to be tested is light and a preset second warning message is issued, wherein C rate Indicates the color change rate, Region rate represents the growth rate;

[0041] When (50%≤C rate ≤75%)∪(50%≤Regionrate ≤75%), it is determined that the ice coverage of the insulator in the ice coverage image to be tested is medium and a preset third warning message is issued, wherein C rate Indicates the color change rate, Region rate represents the growth rate;

[0042] When (75% ≤ C rate ≤100%)∪(75%≤Region rate ≤100%), it is determined that the ice coverage of the insulator in the ice coverage image to be tested is severe and a preset fourth warning message is issued, wherein C rate Indicates the color change rate, Region rate Represents the growth rate.

[0043] To achieve the above object, an embodiment of the present invention further provides an insulator ice recognition device, comprising:

[0044] A target ice-covered image acquisition module is used to acquire a plurality of initial ice-covered images collected by a plurality of ice-covered monitoring devices, and pre-process the plurality of initial ice-covered images to obtain a plurality of target ice-covered images;

[0045] An image knowledge base construction module, used to construct an image knowledge base according to parameter information of a plurality of target ice-covered images, wherein the parameter information includes a shooting preset position, a resolution and an ice-covered monitoring device number;

[0046] A Yolo v3 target recognition model training module, used to train the Yolo v3 target recognition model using the target ice-covered image in the image knowledge base to obtain a trained Yolo v3 target recognition model;

[0047] An ice cover image acquisition module to be tested is used to acquire an ice cover image to be tested collected in real time by any ice cover monitoring device, and read the resolution to be tested of the ice cover image to be tested and the number of the ice cover monitoring device to be tested;

[0048] A module for obtaining preset positions for shooting to be measured, used for obtaining preset positions for shooting to be measured of the ice-covered image to be measured according to the number of targets to be measured, the size to be measured and the position to be measured of the insulators in the ice-covered image to be measured when the resolution to be measured meets the preset resolution condition;

[0049] A region of interest acquisition module is used to acquire, based on the trained Yolo v3 target recognition model, a region of interest of the iced insulator to be tested of the iced image to be tested, and a region of interest of the non-iced insulator of the target iced image which has the same number as the preset shooting position to be tested and the iced monitoring device to be tested, and the insulator iced state is non-iced;

[0050] A calculation module, used for calculating the color change rate of the insulator before and after ice coating and the growth rate of the ice coating area of ​​the insulator according to the region of interest of the ice-covered insulator to be measured and the region of interest of the non-ice-covered insulator;

[0051] The recognition module is used to determine the ice coverage degree of the ice coverage image to be tested according to the color change rate and the growth rate and issue corresponding warning information.

[0052] To achieve the above objectives, an embodiment of the present invention further provides an insulator icing identification device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the insulator icing identification method as described in any one of the above items when executing the computer program.

[0053] To achieve the above objectives, an embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute the insulator icing identification method as described in any one of the above items.

[0054] Compared with the prior art, the embodiment of the present invention provides an insulator ice recognition method, device, storage medium and equipment. Through the parameter information of the target ice image, an image knowledge base is constructed, which can provide a detailed and comprehensive recognition scheme for insulator ice of different shooting angles, materials and forms. Through the trained Yolo v3 target recognition model, the iced insulator interest region to be tested and the non-iced insulator interest region of the iced image to be tested are obtained. According to the iced insulator interest region to be tested and the non-iced insulator interest region, the color change rate of the insulator before and after ice coating and the growth rate of the iced area of ​​the insulator are calculated. Finally, according to the color change rate and the growth rate, the ice degree of the insulator of the iced image to be tested is determined and the corresponding warning information is issued. It can be seen that the embodiment of the present invention can accurately and comprehensively grasp the ice degree of the transmission line insulator, and is closer to the actual operation and maintenance needs of the iced insulator of the transmission line in ice and snow weather, thereby providing technical support for the intelligent anti-icing of the transmission line, and has strong practicality. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 is a flow chart of a method for identifying ice coating on an insulator provided by an embodiment of the present invention;

[0056] Figure 2 It is a structural block diagram of an insulator ice recognition device provided by an embodiment of the present invention;

[0057] Figure 3 The present invention is a structural block diagram of an insulator ice coating identification device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] See also Figure 1 , Figure 1 : is a flow chart of a method for identifying ice coating on an insulator provided by an embodiment of the present invention, the method for identifying ice coating on an insulator comprising:

[0060] S1, obtaining a plurality of initial ice images collected by a plurality of ice monitoring devices, and preprocessing the plurality of initial ice images to obtain a plurality of target ice images;

[0061] S2. constructing an image knowledge base according to parameter information of a plurality of target ice-covered images, wherein the parameter information includes a shooting preset position, a resolution, and an ice-covered monitoring device number;

[0062] S3, training a Yolo v3 target recognition model using the target ice-covered image in the image knowledge base to obtain a trained Yolo v3 target recognition model;

[0063] S4, obtaining an ice image to be measured collected in real time by any ice monitoring device, and reading the resolution to be measured of the ice image to be measured and the number of the ice monitoring device to be measured;

[0064] S5. When the resolution to be measured meets the preset resolution condition, the preset shooting position to be measured of the ice-covered image to be measured is obtained according to the number of targets to be measured, the size to be measured and the position to be measured of the insulator in the ice-covered image to be measured;

[0065] S6. Based on the trained Yolo v3 target recognition model, obtain the region of interest of the iced insulator to be tested of the iced image to be tested, and the region of interest of the non-iced insulator of the target iced image which has the same number as the preset shooting position to be tested and the iced monitoring device to be tested, and the insulator iced state is non-iced;

[0066] S7, calculating the color change rate of the insulator before and after ice coating and the growth rate of the ice coating area of ​​the insulator according to the region of interest of the ice-covered insulator to be tested and the region of interest of the non-ice-covered insulator;

[0067] S8. Determine the ice coverage degree of the ice coverage image to be measured according to the color change rate and the growth rate, and issue corresponding warning information.

[0068] Specifically, in step S1, a plurality of initial icing period images from November of each year to March of the following year collected by each icing monitoring device of overhead lines in the southern region are obtained, wherein the icing monitoring device includes a camera installed on a pole tower;

[0069] And the initial icing images with serious dirt, freezing and fogging on the lens are eliminated from the initial icing images, and a number of target icing images with clear imaging and obvious insulator targets are screened out.

[0070] Specifically, in step S2, an image knowledge base is constructed according to parameter information of a plurality of target ice-covered images, wherein the parameter information includes a shooting preset position, a resolution and an ice-covered monitoring device number, and steps S21 to S23 are included:

[0071] S21, calculating the number, size and position of insulators in a plurality of target ice-covered images;

[0072] S22, comparing the target number, size and position of the insulators in any two target icing images with the same icing monitoring device number to obtain a first comparison result, and numbering the shooting preset positions of a plurality of the target icing images according to the first comparison result until the plurality of the target icing images are traversed;

[0073] S23, constructing an image knowledge base according to the resolution of the plurality of numbered target ice-covered images and the number of the ice-covered monitoring device.

[0074] It should be noted that in step S21, the number of insulator targets I in a plurality of target ice-covered images is first manually measured. o , the center point coordinates of the insulator area (x c , x y ), length value w of the insulator area i , width h i , and then calculate the insulator size I in several images of the target ice-covered image according to the center point coordinates, the length value and the width value. s =(w i +h i ) / 2 and position = (x c +x y ) / 2;

[0075] In step S22, when the first comparison result satisfies the constraint (I o,p =I o,q )∩(|I s,p -I s,q |≤10)∩(|I L,p -I L,q|≤20), it is determined that any two target ice-covered images are the same shooting preset position, where I o,p ,I s,p ,I L,p are the number, size and position of insulator targets in the target ice image p, I o,q ,I s,q ,I L,q are respectively the number, size and position of the insulator targets in the target ice-covered image q; it can be understood that the target ice-covered images at different shooting preset positions are numbered from 0 until a number of the target ice-covered images are traversed.

[0076] Furthermore, the parameter information also includes a shooting date and a shooting time. Then, in step S23, an image knowledge base is constructed according to the resolution of the plurality of target ice-covered images that have been numbered, the number of the ice-covered monitoring device, the shooting date and the shooting time.

[0077] It can be understood that the resolution, ice monitoring device number, shooting date and shooting time of the plurality of target ice images that have been numbered are read;

[0078] A first-level folder of the image knowledge base is established according to the resolution (length w×width h), and each first-level folder stores the target ice image of each ice monitoring device with the same resolution;

[0079] A secondary folder of the image knowledge base is established according to the number of the ice monitoring device, and each secondary folder stores target ice images of each shooting preset position with the same resolution and the same ice monitoring device number;

[0080] A three-level folder of the image knowledge base is established according to the shooting preset position, and each three-level folder stores the target ice image with the same resolution, the same ice monitoring device number, and the same shooting preset position;

[0081] In the third-level folder, the target ice images are arranged in ascending order according to the shooting time and shooting date, and are renamed in the form of "ice monitoring device number_hexadecimal code of target ice image_preset position number_shooting year / month / day / hour / minute", and the target ice images in the third-level folder are uniformly converted into JPG format.

[0082] Specifically, in step S3, the Yolo v3 target recognition model is trained using the target ice-covered image in the image knowledge base to obtain a trained Yolo v3 target recognition model, including steps S31 to S33:

[0083] S31, taking at least one target ice image of each ice monitoring device and at least one target ice image of each shooting preset position in the image knowledge base as a training image set;

[0084] Preferably, the total number of target ice images in the training image set is not less than 500. It can be understood that the target ice images in the training image set include at least one target ice image of each ice monitoring device and at least one target ice image of each shooting preset position;

[0085] S32, annotating the target ice-covered image in the training image set according to the ice-covered state of the insulator to obtain a training annotation set, wherein the file information of the training annotation set includes: the coordinates of the upper left corner vertex and the lower right corner vertex of the insulator target boundary rectangular box, and the ice-covered state code of the insulator;

[0086] As can be understood, the target ice-covered images in the training image set are labeled with vertical rectangular boxes that fit the boundaries of the insulator area using the open source image annotation tool LabelImg. Each vertical rectangular box is labeled and the icing status of the insulator is marked with a code. The label content is: "with ice", coded as 0; "without ice", coded as 1. After each target ice-covered image is labeled, a TXT format file is obtained, i.e., the training annotation set. Each file includes the following file information: the coordinates of the upper left corner vertex (x l ,y l ) and the coordinates of the lower right vertex (x r ,y r ), and the icing status code of the insulator; the number of files in TXT format in the training annotation set is consistent with the number of target icing images in JPG format in the training image set.

[0087] S33, training a Yolo v3 target recognition model using the target ice-covered image in the training image set and the files in the training annotation set to obtain a trained Yolo v3 target recognition model.

[0088] It can be understood that based on the Yolo v3 algorithm, the target ice-covered image in the training image set and the file in the training annotation set are used to train the Yolo v3 target recognition model, and the Yolo v3 algorithm is the third version of the Yolo series target detection algorithm; one or more images are input to the trained Yolo v3 target recognition model, and the Yolo v3 target recognition model can identify the insulator in the image, generate a TXT format file with the same name as the image, and output the upper left corner vertex coordinate (x l,p ,y l,p ) and the coordinates of the lower right vertex (x r,p ,y r,p ), and the insulator icing status code.

[0089] Specifically, in step S4, the step of acquiring the ice image to be measured collected in real time by any ice monitoring device, and reading the resolution to be measured of the ice image to be measured and the number of the ice monitoring device to be measured, includes steps S41 to S43:

[0090] S41, using a camera installed on the pole tower to take real-time images of ice coating on the insulator to be tested every hour during the ice coating period, and transmitting the ice coating images to be tested to the monitoring main station using a 4G / 5G network signal;

[0091] S42, reading the length and width pixel points of the ice-covered image to be measured, obtaining the resolution (w×h) of the ice-covered image to be measured, converting the format of the ice-covered image to be measured into JPG format, and transmitting it to the monitoring main station;

[0092] S43, reading the acquisition device of the ice-covered image to be measured and the ice-covered monitoring device where it is located, and obtaining the number of the ice-covered monitoring device that photographed the ice-covered image to be measured, that is, the number of the ice-covered monitoring device to be measured.

[0093] Specifically, in step S5, when the resolution to be measured meets the preset resolution condition, the preset shooting position to be measured of the ice-covered image to be measured is obtained according to the number of targets to be measured, the size to be measured and the position to be measured of the insulator in the ice-covered image to be measured, including steps S51 to S53:

[0094] S51, when the resolution to be measured meets the preset resolution condition, calculating the number of targets to be measured, the size to be measured and the position to be measured of the insulator in the ice-covered image to be measured;

[0095] It can be understood that when the resolution to be measured meets the preset resolution condition, the subsequent steps are performed. The embodiment of the present invention can adopt the calculation method of the number, size and position of the insulator targets in the above embodiment, which will not be repeated here;

[0096] S52, comparing the number of targets to be measured, the size to be measured and the position to be measured with the number, size and position of insulator targets in the target ice-covered image of the image knowledge base to obtain a second comparison result;

[0097] S53: When the second comparison result meets the preset shooting preset position condition, the shooting preset position to be tested of the ice-covered image to be tested is obtained.

[0098] It can be understood that the number of targets to be measured is ou , the size to be measured I su and the position to be measured I Lu The target number I of insulators with the target ice-covered image o , Size I s and position I LWhen the second comparison result meets the preset shooting preset position condition (I ou =I o )∩(|I su -I s |≤10)∩(|I Lu -I L |≤20), the preset shooting position to be tested of the ice-covered image to be tested is obtained. At this time, the ice-covered image to be tested is considered to be an image shot at the preset shooting position, and the ice-covered image to be tested is copied to the folder where the preset shooting position is located.

[0099] Specifically, in step S6, based on the trained Yolo v3 target recognition model, the region of interest of the iced insulator to be tested of the iced image to be tested and the region of interest of the non-iced insulator of the target iced image having the same number as the preset shooting position to be tested and the iced monitoring device to be tested and the insulator icing state being non-iced are obtained, including steps S61 to S64:

[0100] S61, inputting the ice-covered image to be tested into the trained Yolo v3 target recognition model, obtaining the upper left corner vertex coordinates and the lower right corner vertex coordinates of the predicted insulator target boundary rectangular box of the ice-covered image to be tested, and the ice-covered state of the insulator of the ice-covered image to be tested;

[0101] S62, calculating the lower left corner vertex coordinates and the upper right corner vertex coordinates of the predicted insulator target boundary rectangular box according to the upper left corner vertex coordinates and the lower right corner vertex coordinates;

[0102] S63, cropping the ice-covered image to be measured according to the upper left corner vertex coordinates, the lower right corner vertex coordinates, the lower left corner vertex coordinates and the upper right corner vertex coordinates to obtain a region of interest of the ice-covered insulator to be measured;

[0103] S64, according to the upper left vertex coordinates, the lower right vertex coordinates, the lower left vertex coordinates and the upper right vertex coordinates, crop the target icing image which has the same number as the preset shooting position to be tested and the icing monitoring device to be tested and the icing state of the insulator is no icing, to obtain the insulator region of interest without icing.

[0104] In a specific embodiment, the ice-covered image to be tested is input into the trained Yolo v3 target recognition model to obtain the upper left corner vertex coordinate (x l,p ,y l,p ) and the coordinates of the lower right corner (x r,p ,y r,p ), and the icing state of the insulator of the icing image to be measured;

[0105] According to the upper left corner vertex coordinate (x l,p ,y l,p ) and the lower right corner vertex coordinates (x r,p ,y r,p ) calculates the lower left corner vertex coordinates (x l,p,b ,y l,p,b ) and the coordinates of the upper right corner (x r,p,u ,y r,p,u ), where x l,p,b =x l,p ,y l,p,b =y r,p , x r,p,u =x r,p ,y r,p,u =y l,p ;

[0106] According to the upper left corner vertex coordinate (x l,p ,y l,p ), the lower right corner vertex coordinates (x r,p ,y r,p ), the lower left vertex coordinates (x l,p,b ,y l,p,b ) and the upper right corner vertex coordinates (x r,p,u ,y r,p,u ) Crop the ice-covered image to be tested to obtain a region of interest ROI of the ice-covered insulator to be tested ice ;

[0107] According to the upper left corner vertex coordinate (x l,p ,y l,p ), the lower right corner vertex coordinates (x r,p ,y r,p ), the lower left vertex coordinates (x l,p,b ,y l,p,b ) and the upper right corner vertex coordinates (x r,p,u ,y r,p,u ), cropping the target icing image with the same number as the preset shooting position to be tested and the icing monitoring device to be tested, and the icing state of the insulator is no icing, to obtain the ROI of the insulator without icing none .

[0108] Understandable, ROI none and ROI ice The same size and position.

[0109] Specifically, in step S7, the color change rate of the insulator before and after icing and the growth rate of the icing area of ​​the insulator are calculated according to the ROI of the iced insulator to be tested and the ROI of the non-iced insulator, including steps S71 to S76:

[0110] S71, calculating the red component, green component and blue component of the region of interest of the ice-covered insulator to be measured and the red component, green component and blue component of the region of interest of the non-iced insulator according to the region of interest of the ice-covered insulator to be measured and the region of interest of the non-iced insulator;

[0111] S72, calculating the color change rate of the insulator before and after ice coating according to the red component, green component and blue component of the region of interest of the ice-covered insulator to be tested and the red component, green component and blue component of the region of interest of the non-ice-covered insulator;

[0112] S73, calculating the iced area of ​​the insulator according to the region of interest of the iced insulator to be measured and the region of interest of the non-iced insulator;

[0113] S74, performing binarization processing on the ice-covered area to obtain a binary ice-covered area;

[0114] S75, counting the number of white pixels in the binary ice-covered area;

[0115] S76. Calculate the growth rate of the ice-covered area according to the number of white pixels.

[0116] It can be understood that the color change rate can be calculated first through steps S71-S72, and then the growth rate can be calculated through steps S73-S76, or the growth rate can be calculated first through steps S73-S76, and then the color change rate can be calculated through steps S71-S72, and no specific limitation is made here;

[0117] Preferably, in step S72, the color change rate of the insulator before and after ice coating is calculated based on the red component, green component and blue component of the region of interest of the ice-covered insulator to be measured and the red component, green component and blue component of the region of interest of the non-ice-covered insulator, including:

[0118] According to the red component of the region of interest of the iced insulator to be tested and the red component of the region of interest of the non-iced insulator, the change rate of the red component is calculated:

[0119] rate R =(|R none -R ice |) / R none ×100%

[0120] Among them, R iceis the red component of the area of ​​interest of the iced insulator to be tested, R none is the red component of the area of ​​interest of the insulator without ice;

[0121] According to the green component of the ice-covered insulator interest region to be measured and the green component of the non-ice-covered insulator interest region, the change rate of the green component is calculated:

[0122] rate G =(|G none -G ice |) / G none ×100%

[0123] Among them, G ice is the green component of the interested area of ​​the iced insulator to be tested, G none is the green component of the area of ​​interest of the insulator without ice coating;

[0124] According to the blue component of the ice-covered insulator interest region to be measured and the blue component of the non-ice-covered insulator interest region, the change rate of the blue component is calculated:

[0125] rate B =(|B none -B ice |) / B none ×100%

[0126] Among them, B ice is the blue component of the region of interest of the iced insulator to be tested, B none is the blue component of the area of ​​interest of the insulator without ice;

[0127] The color change rates of the insulators before and after ice coating are calculated according to the change rates of the red component, the green component and the blue component:

[0128] C rate =(rate R +rate G +rate B ) / 3

[0129] Among them, rate R is the rate of change of the red component, rate G is the rate of change of the green component, rate B is the rate of change of the blue component.

[0130] Preferably, in step S73, the calculating the iced area of ​​the insulator according to the iced insulator interest region to be measured and the ice-free insulator interest region includes:

[0131] The iced area of ​​the insulator is calculated according to the following formula:

[0132] Region ice =ROI none -ROI ice |

[0133] Among them, ROI ice ROI is the region of interest of the iced insulator to be tested. none The area of ​​interest is the ice-free insulator.

[0134] Preferably, in step S76, calculating the growth rate of the ice-covered area according to the number of white pixels includes:

[0135] The growth rate of the ice-covered area is calculated according to the following formula:

[0136] Region rate =C white / [x r,p -x l,p )×(y l,p -y r,p )×100%

[0137] Among them, C white is the number of white pixels in the binary ice-covered area, (x l,p ,y l,p )、(x r,p ,y r,p ) are the upper left corner vertex coordinates and lower right corner vertex coordinates of the predicted insulator target boundary rectangular box of the ice-covered image to be tested.

[0138] Specifically, in step S8, judging the ice coverage degree of the insulator of the ice coverage image to be measured according to the color change rate and the growth rate and issuing corresponding warning information includes:

[0139] When (0≤C rate ≤25%)∪(0≤Region rate ≤25%), it is determined that the insulator icing degree of the icing image to be tested is not icing and a preset first warning message is issued, wherein C rate Indicates the color change rate, Region rate represents the growth rate;

[0140] When (25% ≤ C rate ≤50%)∪(25%≤Region rate ≤50%), it is determined that the ice coverage of the insulator in the ice coverage image to be tested is light and a preset second warning message is issued, wherein C rate Indicates the color change rate, Region rate represents the growth rate;

[0141] When (50%≤C rate ≤75%)∪(50%≤Region rate ≤75%), it is determined that the ice coverage of the insulator in the ice coverage image to be tested is medium and a preset third warning message is issued, wherein C rate Indicates the color change rate, Region rate represents the growth rate;

[0142] When (75% ≤ C rate ≤100%)∪(75%≤Region rate ≤100%), it is determined that the ice degree of the insulator in the ice-covered image to be tested is severe and a preset fourth warning message is issued, wherein C rate Indicates the color change rate, Region rate Represents the growth rate.

[0143] Optionally, the first warning information specifically indicates that the insulator is not covered with ice; the second warning information specifically indicates that the insulator is covered with ice; the third warning information specifically indicates that close observation and preparation for de-icing of the insulator are required; and the fourth warning information specifically indicates that the insulator needs to be de-iced urgently.

[0144] Furthermore, when (75% ≤ C rate ≤100%)∪(75%≤Region rate ≤100%), an alarm is issued, where C rate Indicates the color change rate, Region rate Represents the growth rate.

[0145] In the embodiment of the present invention, the degree of insulator icing is quantified by the color change rate and growth rate, and the degree of insulator icing is graded, which can comprehensively and accurately identify the degree of insulator icing and provide technical support for intelligent anti-icing of transmission lines.

[0146] See also Figure 2 , Figure 2 : is a structural block diagram of an insulator ice recognition device 10 provided in an embodiment of the present invention, and the insulator ice recognition device 10 includes:

[0147] The target ice-covered image acquisition module 11 is used to acquire a plurality of initial ice-covered images collected by a plurality of ice-covered monitoring devices, and pre-process the plurality of initial ice-covered images to obtain a plurality of target ice-covered images;

[0148] An image knowledge base construction module 12 is used to construct an image knowledge base according to parameter information of a plurality of target ice-covered images, wherein the parameter information includes a shooting preset position, a resolution and an ice-covered monitoring device number;

[0149] A Yolo v3 target recognition model training module 13, used to train a Yolo v3 target recognition model using the target ice-covered image in the image knowledge base to obtain a trained Yolo v3 target recognition model;

[0150] The ice image acquisition module 14 is used to acquire the ice image to be measured collected by any ice monitoring device in real time, and read the resolution to be measured of the ice image to be measured and the number of the ice monitoring device to be measured;

[0151] The module 15 for obtaining the preset positions for shooting to be measured is used to obtain the preset positions for shooting to be measured of the ice-covered image to be measured according to the number of targets to be measured, the sizes to be measured and the positions to be measured of the insulators in the ice-covered image to be measured when the resolution to be measured meets the preset resolution condition;

[0152] The region of interest acquisition module 16 is used to acquire the region of interest of the iced insulator to be tested of the iced image to be tested, and the region of interest of the non-iced insulator of the target iced image which has the same number as the preset shooting position to be tested and the iced monitoring device to be tested, and the insulator iced state is non-iced, based on the trained Yolo v3 target recognition model;

[0153] A calculation module 17, configured to calculate the color change rate of the insulator before and after ice coating and the growth rate of the ice coating area of ​​the insulator according to the ice coating insulator interest region to be measured and the non-ice coating insulator interest region;

[0154] The identification module 18 is used to determine the ice coverage degree of the ice coverage image to be detected according to the color change rate and the growth rate and issue corresponding warning information.

[0155] It is worth noting that the working process of each module in the insulator ice recognition device 10 described in the embodiment of the present invention can refer to the working process of the insulator ice recognition method described in the above embodiment, and will not be repeated here.

[0156] An embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute the insulator ice coating identification method as described in the above embodiment.

[0157] See also Figure 3 , Figure 3: is a structural block diagram of an insulator ice recognition device 20 provided in an embodiment of the present invention, and the insulator ice recognition device 20 includes: a processor 21, a memory 22, and a computer program stored in the memory 22 and executable on the processor 21. When the processor 21 executes the computer program, the steps in the above-mentioned insulator ice recognition method embodiment are implemented. Alternatively, when the processor 21 executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented.

[0158] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory 22 and executed by the processor 21 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the insulator ice recognition device 20.

[0159] The insulator ice recognition device 20 may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The insulator ice recognition device 20 may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art may understand that the schematic diagram is only an example of the insulator ice recognition device 20 and does not constitute a limitation on the insulator ice recognition device 20. The insulator ice recognition device 20 may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the insulator ice recognition device 20 may also include input and output devices, network access devices, buses, etc.

[0160] The processor 21 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 21 is the control center of the insulator ice recognition device 20, and uses various interfaces and lines to connect various parts of the entire insulator ice recognition device 20.

[0161] The memory 22 can be used to store the computer program and / or module. The processor 21 realizes various functions of the insulator ice recognition device 20 by running or executing the computer program and / or module stored in the memory 22 and calling the data stored in the memory 22. The memory 22 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 22 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0162] Wherein, if the module / unit integrated in the insulator ice recognition device 20 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor 21, the steps of the above-mentioned method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium.

[0163] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0164] The embodiment of the present invention provides an insulator ice recognition method, device, storage medium and equipment. Through the parameter information of the target ice image, an image knowledge base is constructed, which can provide a detailed and comprehensive recognition scheme for insulator ice of different shooting angles, materials and forms. Through the trained Yolo v3 target recognition model, the iced insulator interest region to be tested and the non-iced insulator interest region of the iced image to be tested are obtained. The color change rate of the insulator before and after ice coating and the growth rate of the iced area of ​​the insulator are calculated according to the iced insulator interest region to be tested and the non-iced insulator interest region. Finally, according to the color change rate and the growth rate, the ice degree of the insulator of the iced image to be tested is determined and the corresponding warning information is issued. It can be seen that the embodiment of the present invention can accurately and comprehensively grasp the ice degree of the transmission line insulator, and is closer to the actual operation and maintenance needs of the iced insulator of the transmission line in ice and snow weather, thereby providing technical support for the intelligent anti-icing of the transmission line, and has strong practicality.

[0165] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for identifying ice coating on an insulator, characterized in that: include: Acquire a plurality of initial ice-covered images collected by a plurality of ice-covered monitoring devices, and pre-process the plurality of initial ice-covered images to obtain a plurality of target ice-covered images; Building an image knowledge base based on parameter information of a plurality of target ice-covered images, wherein the parameter information includes a shooting preset position, a resolution, and an ice-covered monitoring device number; The Yolo v3 target recognition model is trained using the target ice-covered image in the image knowledge base to obtain a trained Yolo v3 target recognition model; Acquire an ice image to be measured collected in real time by any ice monitoring device, and read the resolution to be measured of the ice image to be measured and the number of the ice monitoring device to be measured; When the resolution to be measured meets the preset resolution condition, the preset shooting position to be measured of the ice-covered image to be measured is obtained according to the number of targets to be measured, the size to be measured and the position to be measured of the insulator in the ice-covered image to be measured; Based on the trained Yolo v3 target recognition model, the iced insulator region of interest to be tested of the iced image to be tested and the non-iced insulator region of interest of the target iced image having the same number as the preset shooting position to be tested and the iced monitoring device to be tested and the insulator icing state being non-iced are obtained; According to the region of interest of the iced insulator to be tested and the region of interest of the non-iced insulator, the color change rate of the insulator before and after ice coating and the growth rate of the iced area of ​​the insulator are calculated; According to the color change rate and the growth rate, determining the ice coverage degree of the insulator in the ice coverage image to be measured and issuing corresponding warning information; The step of calculating the color change rate of the insulator before and after ice coating and the growth rate of the ice coating area of ​​the insulator according to the ice coating insulator region of interest to be measured and the non-ice coating insulator region of interest includes: According to the ice-covered insulator region of interest to be measured and the ice-free insulator region of interest, calculating the red component, green component and blue component of the ice-covered insulator region of interest to be measured and the red component, green component and blue component of the ice-free insulator region of interest; Calculate the color change rate of the insulator before and after ice coating according to the red component, green component and blue component of the region of interest of the ice-covered insulator to be tested and the red component, green component and blue component of the region of interest of the non-ice-covered insulator; Calculating the iced area of ​​the insulator according to the iced insulator interest region to be measured and the ice-free insulator interest region; Binarizing the ice-covered area to obtain a binary ice-covered area; Counting the number of white pixels in the binary ice-covered area; Calculating the growth rate of the ice-covered area according to the number of white pixels; The step of determining the ice coverage degree of the insulator of the ice coverage image to be measured according to the color change rate and the growth rate and issuing corresponding warning information includes: When (0≤C rate ≤25%)∪(0≤Region rate ≤25%), it is determined that the insulator icing degree of the icing image to be tested is not icing and a preset first warning message is issued, wherein C rate Indicates the color change rate, Region rate represents the growth rate; When (25% ≤ C rate ≤50%)∪(25%≤Region rate ≤50%), it is determined that the ice coverage of the insulator in the ice coverage image to be tested is light and a preset second warning message is issued, wherein C rate Indicates the color change rate, Region rate represents the growth rate; When (50%≤C rate ≤75%)∪(50%≤Region rate ≤75%), it is determined that the ice coverage of the insulator in the ice coverage image to be tested is medium and a preset third warning message is issued, wherein C rate Indicates the color change rate, Region rate represents the growth rate; When (75% ≤ C rate ≤100%)∪(75%≤Region rate ≤100%), it is determined that the ice coverage of the insulator in the ice coverage image to be tested is severe and a preset fourth warning message is issued, wherein C rate Indicates the color change rate, Region rate Represents the growth rate.

2. The insulator ice recognition method according to claim 1, characterized in that: The image knowledge base is constructed based on the parameter information of a plurality of target ice-covered images, wherein the parameter information includes the shooting preset position, resolution and ice-covered monitoring device number, including: Calculating the number, size and position of insulators in a plurality of target ice-covered images; Compare the target number, size and position of insulators in any two target icing images with the same icing monitoring device number to obtain a first comparison result, and number the shooting preset positions of a plurality of the target icing images according to the first comparison result until the plurality of the target icing images are traversed; An image knowledge base is constructed according to the resolution of a plurality of numbered target ice-covered images and the number of the ice-covered monitoring device.

3. The insulator ice recognition method according to claim 1, characterized in that: The method of training the Yolo v3 target recognition model using the target ice-covered image in the image knowledge base to obtain the trained Yolo v3 target recognition model includes: Using at least one target ice-covered image of each ice-covered monitoring device and at least one target ice-covered image of each shooting preset position in the image knowledge base as a training image set; Annotate the target ice-covered image in the training image set according to the ice-covered state of the insulator to obtain a training annotation set, wherein the file information of the training annotation set includes: the coordinates of the upper left corner vertex and the lower right corner vertex of the insulator target boundary rectangular box, and the ice-covered state code of the insulator; The Yolo v3 target recognition model is trained using the target ice-covered image in the training image set and the files in the training annotation set to obtain a trained Yolo v3 target recognition model.

4. The method for identifying ice coating on insulators according to claim 1, characterized in that: When the resolution to be measured meets the preset resolution condition, obtaining the preset shooting position to be measured of the ice-covered image to be measured according to the number of targets to be measured, the size to be measured and the position to be measured of the insulator in the ice-covered image to be measured, including: When the resolution to be measured meets the preset resolution condition, the number of targets to be measured, the size to be measured and the position to be measured of the insulator in the ice-covered image to be measured are calculated; Compare the number of targets to be measured, the size to be measured and the position to be measured with the number, size and position of insulator targets in the target ice-covered image of the image knowledge base to obtain a second comparison result; When the second comparison result meets the preset shooting preset position condition, the shooting preset position to be tested of the ice-covered image to be tested is obtained.

5. The method for identifying ice coating on insulators according to claim 1, characterized in that: The method of obtaining the ice-covered insulator region of interest to be tested of the ice-covered image to be tested based on the trained Yolov3 target recognition model and the non-ice-covered insulator region of interest of the target ice-covered image having the same number as the preset shooting position to be tested and the ice-covered monitoring device to be tested and the insulator icing state being non-ice-covered includes: Input the ice-covered image to be tested into the trained Yolo v3 target recognition model to obtain the upper left corner vertex coordinates and the lower right corner vertex coordinates of the predicted insulator target boundary rectangular box of the ice-covered image to be tested and the ice-covered state of the insulator of the ice-covered image to be tested; Calculate the lower left corner vertex coordinates and the upper right corner vertex coordinates of the predicted insulator target boundary rectangular box according to the upper left corner vertex coordinates and the lower right corner vertex coordinates; The ice-covered image to be measured is cropped according to the upper left corner vertex coordinates, the lower right corner vertex coordinates, the lower left corner vertex coordinates and the upper right corner vertex coordinates to obtain a region of interest of the ice-covered insulator to be measured; According to the upper left vertex coordinates, the lower right vertex coordinates, the lower left vertex coordinates and the upper right vertex coordinates, the target icing image having the same number as the preset shooting position to be tested and the icing monitoring device to be tested and the icing state of the insulator being no icing is cropped to obtain the insulator region of interest without icing.

6. An insulator ice recognition device, characterized in that: include: A target ice-covered image acquisition module is used to acquire a plurality of initial ice-covered images collected by a plurality of ice-covered monitoring devices, and pre-process the plurality of initial ice-covered images to obtain a plurality of target ice-covered images; An image knowledge base construction module, used to construct an image knowledge base according to parameter information of a plurality of target ice-covered images, wherein the parameter information includes a shooting preset position, a resolution and an ice-covered monitoring device number; A Yolo v3 target recognition model training module, used to train the Yolo v3 target recognition model using the target ice-covered image in the image knowledge base to obtain a trained Yolo v3 target recognition model; An ice cover image acquisition module to be tested is used to acquire an ice cover image to be tested collected in real time by any ice cover monitoring device, and read the resolution to be tested of the ice cover image to be tested and the number of the ice cover monitoring device to be tested; A module for obtaining preset positions for shooting to be measured, used for obtaining preset positions for shooting to be measured of the ice-covered image to be measured according to the number of targets to be measured, the size to be measured and the position to be measured of the insulators in the ice-covered image to be measured when the resolution to be measured meets the preset resolution condition; A region of interest acquisition module is used to acquire, based on the trained Yolo v3 target recognition model, a region of interest of the iced insulator to be tested of the iced image to be tested, and a region of interest of the non-iced insulator of the target iced image which has the same number as the preset shooting position to be tested and the iced monitoring device to be tested, and the insulator iced state is non-iced; A calculation module, used for calculating the color change rate of the insulator before and after ice coating and the growth rate of the ice coating area of ​​the insulator according to the region of interest of the ice-covered insulator to be measured and the region of interest of the non-ice-covered insulator; an identification module, used to determine the degree of icing on the insulator of the icing image to be measured according to the color change rate and the growth rate and issue corresponding warning information; The step of calculating the color change rate of the insulator before and after ice coating and the growth rate of the ice coating area of ​​the insulator according to the ice coating insulator region of interest to be measured and the non-ice coating insulator region of interest includes: According to the ice-covered insulator region of interest to be measured and the ice-free insulator region of interest, calculating the red component, green component and blue component of the ice-covered insulator region of interest to be measured and the red component, green component and blue component of the ice-free insulator region of interest; Calculate the color change rate of the insulator before and after ice coating according to the red component, green component and blue component of the region of interest of the ice-covered insulator to be tested and the red component, green component and blue component of the region of interest of the non-ice-covered insulator; Calculating the iced area of ​​the insulator according to the iced insulator interest region to be measured and the ice-free insulator interest region; Binarizing the ice-covered area to obtain a binary ice-covered area; Counting the number of white pixels in the binary ice-covered area; Calculating the growth rate of the ice-covered area according to the number of white pixels; The step of determining the ice coverage degree of the insulator of the ice coverage image to be measured according to the color change rate and the growth rate and issuing corresponding warning information includes: When (0≤C rate ≤25%)∪(0≤Region rate ≤25%), it is determined that the insulator icing degree of the icing image to be tested is not icing and a preset first warning message is issued, wherein C rate Indicates the color change rate, Region rate represents the growth rate; When (25% ≤ C rate ≤50%)∪(25%≤Region rate ≤50%), it is determined that the ice coverage of the insulator in the ice coverage image to be tested is light and a preset second warning message is issued, wherein C rate Indicates the color change rate, Region rate represents the growth rate; When (50%≤C rate ≤75%)∪(50%≤Region rate ≤75%), it is determined that the ice coverage of the insulator in the ice coverage image to be tested is medium and a preset third warning message is issued, wherein C rate Indicates the color change rate, Region rate represents the growth rate; When (75% ≤ C rate ≤100%)∪(75%≤Region rate ≤100%), it is determined that the ice coverage of the insulator in the ice coverage image to be tested is severe and a preset fourth warning message is issued, wherein C rate Indicates the color change rate, Region rate Represents the growth rate.

7. An insulator ice coating identification device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the insulator ice coating identification method according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program; wherein, when the computer program is run, it controls the device where the computer-readable storage medium is located to execute the insulator ice coating identification method according to any one of claims 1 to 5.

Images