Power equipment infrared image edge detection method and system based on multi-strategy grey wolf algorithm, monitoring device and storage medium

Abstract

The invention provides a power equipment infrared image edge detection method and system based on a multi-strategy grey wolf algorithm, a monitoring device and a storage medium. The detection method adopts Kapur entropy as a grey wolf algorithm calculation discriminant; performing differential processing and iterative updating on the gray wolf population, calculating a position vector of each gray wolf individual, performing threshold segmentation on the gray image to obtain a Kapur entropy, and selecting the gray wolf individuals with higher Kapur entropy to form a new gray wolf population so as to quickly and accurately find an optimal segmentation threshold vector. The optimal segmentation threshold vector is used for binary segmentation of the grayscale image, so that the image segmentation effect is improved; meanwhile, according to the detection method, the edge information of the segmented image is accurately extracted by adopting erosion operation, so that the problem of poor infrared image edge detection effect in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method, system, monitoring device and storage medium for infrared image edge detection of electric power equipment based on a multi-strategy grey wolf algorithm. Background Art

[0002] The infrared thermal imaging system is based on the principle of thermal radiation. It uses the infrared radiation difference between the imaging target and the surrounding environment to form an infrared image. It has unique advantages such as all-weather monitoring, strong detection capability, accurate target tracking, and long detection distance. By deeply analyzing the infrared thermal distribution map of electrical equipment, various types of overheating defects that may exist inside and outside the equipment can be quickly diagnosed, such as poor contact of parts, component damage, equipment corrosion and oxidation, unstable load current, etc., and the operating status of electrical equipment can be effectively monitored and its faults can be accurately diagnosed, which can effectively improve the safety and stability of the power system.

[0003] The edge of an image is the boundary of an area where the grayscale value in the image changes dramatically, and it represents some key information in the image. Image edge detection technology effectively extracts the boundary between the subject and the background in the target image through appropriate operators, and it has become a key support for applications in the fields of image recognition and computer vision. Due to the shortcomings of infrared images such as lack of stereoscopic perception, low spatial resolution, blurred edges, low contrast, complex and diverse noise, and non-uniformity, there are many difficulties and challenges in the field of infrared image edge detection, and the detection method needs to be further enhanced and improved.

[0004] In summary, there is an urgent need for an infrared image edge detection method, system, monitoring device and storage medium for power equipment based on a multi-strategy grey wolf algorithm to solve the problems existing in the prior art. Summary of the invention

[0005] The purpose of the present invention is to provide a method for edge detection of infrared images of power equipment based on a multi-strategy gray wolf algorithm, aiming to solve the problem that the adaptive threshold segmentation effect of infrared images in the prior art is poor. The specific technical solution is as follows: A method for edge detection of infrared images of power equipment based on a multi-strategy grey wolf algorithm, comprising: Step S1, obtaining an infrared image of the power equipment and converting it into a grayscale image; Step S2: Initialize the gray wolf algorithm parameters, including the number of gray wolf populations N , maximum number of iterations and population crossover probability ; Step S3, generating an initial gray wolf population using a chaotic mapping method; Step S4, performing differential processing on the initial gray wolf population, and calculating the Kapur entropy of the gray wolf population before and after the differential, respectively, and retaining gray wolf individuals with higher Kapur entropy values; Step S5, perform an iterative process, update the gray wolf population position vector and calculate the Kapur entropy of the gray wolf population, perform crossover and selection operations on the updated gray wolf population, and select gray wolf individuals with higher Kapur entropy values ​​to form the latest population; when the number of iterations reaches the maximum number of iterations When , the final gray wolf population is output, and the position vector of each gray wolf in the final gray wolf population is used as the optimal segmentation threshold to perform threshold segmentation on the grayscale image to obtain a segmented image; Step S6: Using corrosion operation to extract image edge information from the segmented image to obtain edge detection results of the infrared image of the power equipment.

[0006] In the above technical solution, preferably, in step S3, the circle chaos mapping method is used to generate the initial gray wolf population, which is expressed as: in, mod is the remainder function, is the individual gray wolf in the gray wolf population location, is [1, N ], is the ratio of pi.

[0007] In the above technical solution, the initial gray wolf population is preferably subjected to differential processing, which is expressed as: in, For the The mutation vector generated by the gray wolf individuals, is the currently selected gray wolf individual, and are two gray wolf individuals randomly selected from the current gray wolf population. 、 and All are [1, N ], R is the calculation parameter.

[0008] The preferred method in the above technical solution is to calculate the Kapur entropy of the gray wolf population, specifically: in, They are: in, is the Kapur entropy of the gray wolf population, , , , , They represent the Kapur entropy of each part obtained after threshold segmentation of the grayscale image. 、 、 、 All are individual matrix components of gray wolves; is the gray value in the grayscale image The probability of occurrence; Represents the matrix component of the gray wolf individual The weight parameter, Represents the matrix component of the gray wolf individual The weight parameter, Represents the matrix component of the gray wolf individual The weight parameter, Represents the matrix component of the gray wolf individual The weight parameter, Represents the remaining gray wolf individual matrix weight parameters.

[0009] The preferred technical solution is as follows: when the current number of iterations is lower than the maximum number of iterations T max When , the iteration process is continued to update the position vector of the gray wolf population. The iteration process is described as: in, , Indicates the current iteration number, , α , β , The gray wolf individuals are the top three gray wolf individuals in the gray wolf population in terms of Kapur entropy. α Kapur entropy > gray wolf individual β Kapur entropy > gray wolf individual Kapur entropy, For the Gray wolf individuals in the secondary cycle αLocation, For the Gray wolf individuals in the secondary cycle β Location, For the Gray wolf individuals in the secondary cycle Location, For the The current location of the gray wolf in the cycle, For the The position of the current gray wolf individual in the cycle, Indicates the current gray wolf individual and the gray wolf individual α The distance between Indicates the current gray wolf individual and the gray wolf individual β The distance between Indicates the current gray wolf individual and the gray wolf individual The distance between 、 、 are all random numbers between [0, 2]. For gray wolf individuals α The corresponding coefficient factor is, For gray wolf individuals β The corresponding coefficient factor is, For gray wolf individuals The corresponding coefficient factor is, 、 are all random values ​​in the interval [0, 1]. is the number of iterations The relevant nonlinear convergence parameters, Indicates that the current gray wolf individual is moving towards the gray wolf individual α Move the location, Indicates that the current gray wolf individual is moving towards the gray wolf individual β Move the location, Indicates that the current gray wolf individual is moving towards the gray wolf individual Move the position.

[0010] In the above technical solution, preferably, in step S6, the segmented image is subjected to corrosion operation to extract image edge information, and the edge detection result of the infrared image of the power equipment is obtained, specifically: Assumptions P To segment the image, S is a structural element, then Representing structural elements S Pan X The result after Represents structural element S The symmetric set about the origin, The mathematical expression is: Then the corrosion operation is performed. The calculation formula of the corrosion operation process is: Finally, mathematical morphology boundary extraction, the specific calculation formula is: in, ED ( P ) is the edge detection result, represents the erosion operation, Represents structural element S The amplitude at each position within.

[0011] The present invention also provides an infrared image edge detection system for electric power equipment based on a multi-strategy grey wolf algorithm. The detection system adopts the infrared image edge detection method for electric power equipment based on a multi-strategy grey wolf algorithm. The detection system comprises: Grayscale image conversion unit: used to obtain infrared images of power equipment and convert the infrared images of power equipment into grayscale images; Initialization unit: used to initialize the parameters of the gray wolf algorithm and generate the initial gray wolf population using the chaotic mapping method; Kapur entropy calculation unit: calculates the Kapur entropy of the grayscale image segmentation by the position vector of each gray wolf individual; Iteration judgment unit: judge whether the current number of iterations has reached the maximum number of iterations. If so, the final gray wolf population is sent to the image segmentation unit; otherwise, the gray wolf position vector is updated iteratively, and the Kapur entropy calculation unit is called to calculate the Kapur entropy of the gray image segmentation of each gray wolf individual position vector, and the gray wolf individuals with higher Kapur entropy values ​​are selected to form the latest population; Image segmentation unit: using the position vector of each gray wolf in the final gray wolf population as the optimal segmentation threshold to perform threshold segmentation on the grayscale image to obtain a segmented image; Edge detection unit: Use corrosion operation to extract image edge information from the segmented image to obtain the edge detection result of the infrared image of the power equipment.

[0012] The present invention also provides an infrared image edge detection system for electric power equipment based on a multi-strategy grey wolf algorithm. The detection system includes a processor and a memory connected to each other. When the processor runs the computer instructions stored in the memory, the infrared image edge detection method for electric power equipment based on the multi-strategy grey wolf algorithm is executed.

[0013] The present invention also provides an electric power equipment monitoring device, comprising an infrared probe and a computer device interconnected by a cable, wherein the computer device comprises a processor and a memory connected to each other, and when the processor runs the computer instructions stored in the memory, the electric power equipment infrared image edge detection method based on the multi-strategy gray wolf algorithm is executed.

[0014] The present invention also provides a storage medium, in which the method for detecting edge of infrared images of electric equipment based on the multi-strategy grey wolf algorithm is stored.

[0015] The application of the technical solution of the present invention has the following beneficial effects: The present invention adopts Kapur entropy (i.e., maximum entropy) as a discriminant for calculating the gray wolf algorithm, performs differential processing on the gray wolf population, and calculates the Kapur entropy of the position vector of each gray wolf individual after iterative updating to perform threshold segmentation on the grayscale image, and selects gray wolf individuals with higher Kapur entropy to form a new gray wolf population, thereby realizing fast and accurate search for the optimal segmentation threshold vector, and using the optimal segmentation threshold vector for binary segmentation of the grayscale image to improve the image segmentation effect; and adopts corrosion operation to accurately extract the edge information of the segmented image to overcome the problem that the edge detection effect of the infrared image in the prior art is poor.

[0016] In addition to the above-described purposes, features and advantages, the present invention has other purposes, features and advantages. The present invention will be further described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings constituting a part of this application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 It is a flow chart of the edge detection method of infrared image of power equipment based on multi-strategy grey wolf algorithm of the present invention; Figure 2 It is the original infrared image of the power equipment; Figure 3 This is the infrared image segmentation result of power equipment using the traditional threshold segmentation method (Canny algorithm); Figure 4 It is the infrared image segmentation result of the electric power equipment obtained by adopting the invented detection method. DETAILED DESCRIPTION

[0018] In order to facilitate the understanding of the present invention, the present invention will be described more fully below, and preferred embodiments of the present invention are provided. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present invention more thorough and comprehensive.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0020] Embodiment 1: See also Figure 1 This embodiment provides a method for edge detection of infrared images of power equipment based on a multi-strategy grey wolf algorithm, comprising: Step S1, obtaining an infrared image of the power equipment and converting it into a grayscale image; Step S2: Initialize the gray wolf algorithm parameters, including the number of gray wolf populations N , maximum number of iterations T max and population crossover probability ; Step S3, generating an initial gray wolf population using a chaotic mapping method; Step S4, performing differential processing on the initial gray wolf population, and calculating the Kapur entropy (i.e., maximum entropy) of the gray wolf population before and after the differential, respectively, and retaining gray wolf individuals with higher Kapur entropy values; Step S5, perform an iterative process, update the gray wolf population position vector and calculate the Kapur entropy of the gray wolf population, perform crossover and selection operations on the updated gray wolf population, and select gray wolf individuals with higher Kapur entropy values ​​to form the latest population; when the number of iterations reaches the maximum number of iterations T max When , the final gray wolf population is output, and the position vector of each gray wolf in the final gray wolf population is used as the optimal segmentation threshold to perform threshold segmentation on the grayscale image to obtain a segmented image; Step S6: Using corrosion operation to extract image edge information from the segmented image to obtain edge detection results of the infrared image of the power equipment.

[0021] Preferably, in step S1, the infrared image of the electric power equipment is converted into a grayscale image by dimming processing in a computer. This is common knowledge in the art, and therefore will not be described in detail in this embodiment.

[0022] Preferably, in step S3, the circle chaos mapping method is used to generate the initial gray wolf population, which is expressed as: in, mod is the remainder function, is the individual gray wolf in the gray wolf population j location, For a 1 line A matrix of columns, j is [1, N ], is the circumference of a circle, Indicates the threshold number for segmenting the image.

[0023] Preferably, in some embodiments, those skilled in the art may use other chaotic mapping methods to generate the initial gray wolf population, such as Logistic chaotic mapping, Singer chaotic mapping, Tent chaotic mapping, etc. The specific implementation of each chaotic mapping method can be found in the prior art, and will not be listed one by one in this embodiment.

[0024] Preferably, in step S4, the initial gray wolf population is subjected to differential processing, which is expressed as: in, For the The mutation vector generated by the gray wolf individuals, is the currently selected gray wolf individual, and are two gray wolf individuals randomly selected from the current gray wolf population. 、 and All are [1, N ], R is the calculation parameter, .

[0025] Furthermore, in this embodiment, the Kapur entropy of the gray wolf population is calculated, specifically: in, , , , , They are: in, is the Kapur entropy of the gray wolf population, , , , , They represent the Kapur entropy of each part obtained after threshold segmentation of the grayscale image. 、 、 、 are all gray wolf individual matrix components, and the order of gray wolf individual matrix components from small to large is as follows: 、 、 、 、 ; is the gray value in the grayscale image The probability of occurrence, 255 is the maximum gray value; Represents the matrix component of the gray wolf individual The weight parameter, Represents the matrix component of the gray wolf individual The weight parameter, Represents the matrix component of the gray wolf individual The weight parameter, Represents the matrix component of the gray wolf individual The weight parameter, Represents the remaining gray wolf individual matrix weight parameters.

[0026] Preferably, when the current number of iterations is lower than the maximum number of iterations T max When , the iteration process is continued to update the position vector of the gray wolf population. The iteration process is described as: in, , Indicates the current iteration number, , α , β , The gray wolf individuals are the top three gray wolf individuals in the gray wolf population in terms of Kapur entropy. αKapur entropy > gray wolf individual β Kapur entropy > gray wolf individual Kapur entropy, For the Gray wolf individuals in the secondary cycle α Location, For the Gray wolf individuals in the secondary cycle β Location, For the Gray wolf individuals in the secondary cycle Location, For the The current location of the gray wolf in the cycle, For the The position of the current gray wolf individual in the cycle, Indicates the current gray wolf individual and the gray wolf individual α The distance between Indicates the current gray wolf individual and the gray wolf individual β The distance between Indicates the current gray wolf individual and the gray wolf individual The distance between 、 、 are all random numbers between [0, 2]. For gray wolf individuals α The corresponding coefficient factor is, For gray wolf individuals β The corresponding coefficient factor is, For gray wolf individuals The corresponding coefficient factor is, 、 are all random values ​​in the interval [0, 1]. is the number of iterations The relevant nonlinear convergence parameters, Indicates that the current gray wolf individual is moving towards the gray wolf individual α Move the location, Indicates that the current gray wolf individual is moving towards the gray wolf individual β Move the location, Indicates that the current gray wolf individual is moving towards the gray wolf individual Move the position.

[0027] When the number of iterations reaches the maximum number of iterations T max When the final gray wolf population is output, the grayscale image is segmented by taking the position of each gray wolf in the population as the threshold. PContains 5 parts, and the grayscale value of each part is the same.

[0028] Preferably, in step S6, the image edge information is extracted by using corrosion operation on the segmented image to obtain the edge detection result of the infrared image of the power equipment, specifically: Assumptions P To segment the image, S is a structural element, then Representing structural elements S Pan X The result after Represents structural element S The symmetric set about the origin, The mathematical expression is: Then the corrosion operation is performed. The calculation formula of the corrosion operation process is: Finally, mathematical morphology boundary extraction, the specific calculation formula is: in, ED ( P ) is the edge detection result, represents the erosion operation, Represents structural element S The amplitude at each position within.

[0029] See also Figure 2-Figure 4 , this embodiment also provides a comparison of the results of the detection method of this embodiment and the traditional threshold segmentation method (Canny algorithm); wherein, Figure 2 is an original infrared image of an electric power equipment. Figure 3 This is the infrared image segmentation result of power equipment using the traditional threshold segmentation method (Canny algorithm). Figure 4 The infrared image segmentation result of the power equipment obtained by the detection method of this embodiment. Further, in the specific processing process, the detection method of this embodiment sets the number of gray wolf populations N =50, maximum number of iterations T max =100, population crossover probability The structural similarity (SSIM) is selected as the parameter to evaluate the edge effect of the two methods in detecting infrared images of power equipment. The expression of SSIM is as follows: in, is the original infrared image, is the edge detection result, and They are and The amplitude value of the middle pixel, and They are and The variance of pixel amplitude values ​​in the points, express The pixel amplitude value and The covariance between the amplitude values ​​of the pixels in , and are constants, , Indicates the range of pixel values ​​in the image. In this case Take 255, Take 0.01, Take 0.03.

[0030] According to the comparison between the detection method of this embodiment and the traditional threshold segmentation method, when the original image to be detected is Figure 2 When the detection method of this embodiment is used, the SSIM value is 0.996, and the SSIM value of the traditional Canny algorithm is 0.964; this shows that compared with the traditional method, the infrared image edge detection method of power equipment based on the multi-strategy gray wolf algorithm in this embodiment can obtain a result that is more consistent with the original image.

[0031] Embodiment 2: This embodiment provides an infrared image edge detection system for electric power equipment based on a multi-strategy gray wolf algorithm. The detection system adopts the infrared image edge detection method for electric power equipment based on a multi-strategy gray wolf algorithm in Example 1. The detection system includes: Grayscale image conversion unit: used to obtain infrared images of power equipment and convert the infrared images of power equipment into grayscale images through dimming processing; Initialization unit: used to initialize the parameters of the gray wolf algorithm and generate the initial gray wolf population using the circle chaos mapping method; Kapur entropy calculation unit: calculates the Kapur entropy of the grayscale image segmentation by the position vector of each gray wolf individual; Iteration judgment unit: judge whether the current number of iterations has reached the maximum number of iterations. If so, the final gray wolf population is sent to the image segmentation unit; otherwise, the gray wolf position vector is updated iteratively, and the Kapur entropy calculation unit is called to calculate the Kapur entropy of the gray image segmentation of each gray wolf individual position vector, and the gray wolf individuals with higher Kapur entropy values ​​are selected to form the latest population; Image segmentation unit: using the position vector of each gray wolf in the final gray wolf population as the optimal segmentation threshold to perform threshold segmentation on the grayscale image to obtain a segmented image; Edge detection unit: Use corrosion operation to extract image edge information from the segmented image to obtain the edge detection result of the infrared image of the power equipment.

[0032] The detection system of this embodiment can realize edge detection of infrared images of power equipment.

[0033] Embodiment 3: The present embodiment provides an infrared image edge detection system for electric power equipment based on a multi-strategy grey wolf algorithm. The detection system includes a processor and a memory connected to each other. When the processor runs the computer instructions stored in the memory, the infrared image edge detection method for electric power equipment based on a multi-strategy grey wolf algorithm in Example 1 is executed, thereby realizing edge detection of infrared images of electric power equipment.

[0034] Embodiment 4: The present embodiment provides an electric power equipment monitoring device, comprising an infrared probe and a computer device interconnected by a cable, wherein the infrared probe is used to obtain an infrared image of the electric power equipment, and the computer device comprises a processor and a memory connected to each other, and when the processor runs the computer instructions stored in the memory, the electric power equipment infrared image edge detection method based on the multi-strategy grey wolf algorithm in Example 1 is executed, thereby realizing edge detection of the infrared image of the electric power equipment.

[0035] Embodiment 5: This embodiment provides a storage medium, in which the method for edge detection of infrared images of electric power equipment based on the multi-strategy grey wolf algorithm in Embodiment 1 is stored, thereby realizing edge detection of infrared images of electric power equipment.

[0036] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for edge detection of infrared images of power equipment based on a multi-strategy grey wolf algorithm, characterized in that: include: Step S1, obtaining an infrared image of the power equipment and converting it into a grayscale image; Step S2: Initialize the gray wolf algorithm parameters, including the number of gray wolf populations N , maximum number of iterations and population crossover probability ; Step S3, generating an initial gray wolf population using a chaotic mapping method; Step S4, performing differential processing on the initial gray wolf population, and calculating the Kapur entropy of the gray wolf population before and after the differential, respectively, and retaining gray wolf individuals with higher Kapur entropy values; Step S5, perform an iterative process, update the gray wolf population position vector and calculate the Kapur entropy of the gray wolf population, perform crossover and selection operations on the updated gray wolf population, and select gray wolf individuals with higher Kapur entropy values ​​to form the latest population; when the number of iterations reaches the maximum number of iterations T max When , the final gray wolf population is output, and the position vector of each gray wolf in the final gray wolf population is used as the optimal segmentation threshold to perform threshold segmentation on the grayscale image to obtain a segmented image; Step S6: Using corrosion operation to extract image edge information from the segmented image to obtain edge detection results of the infrared image of the power equipment.

2. The power equipment infrared image edge detection method based on the multi-strategy grey wolf algorithm according to claim 1 is characterized in that: In step S3, the circle chaos mapping method is used to generate the initial gray wolf population, which is expressed as: in, mod is the remainder function, is the individual gray wolf in the gray wolf population j location, j is [1, N ], is the ratio of pi.

3. The power equipment infrared image edge detection method based on the multi-strategy grey wolf algorithm according to claim 1 is characterized in that: The initial gray wolf population is subjected to differential processing, which is expressed as: in, For the The mutation vector generated by the gray wolf individuals, is the currently selected gray wolf individual, and are two gray wolf individuals randomly selected from the current gray wolf population. 、 and All are [1, N ], R is the calculation parameter.

4. The method for detecting edge of infrared image of power equipment based on multi-strategy grey wolf algorithm according to claim 3 is characterized in that: Calculate the Kapur entropy of the gray wolf population, specifically: in, They are: in, is the Kapur entropy of the gray wolf population, They represent the Kapur entropy of each part obtained after threshold segmentation of the grayscale image. All are individual matrix components of gray wolves; is the gray value in the grayscale image The probability of occurrence; Represents the matrix component of the gray wolf individual The weight parameter, Represents the matrix component of the gray wolf individual The weight parameter, Represents the matrix component of the gray wolf individual The weight parameter, Represents the matrix component of the gray wolf individual The weight parameter, Represents the remaining gray wolf individual matrix weight parameters.

5. The method for edge detection of infrared images of power equipment based on multi-strategy grey wolf algorithm according to claim 1 is characterized in that: When the current number of iterations is lower than the maximum number of iterations When , the iteration process is continued to update the position vector of the gray wolf population. The iteration process is described as: in, , Indicates the current iteration number, , α , β , The gray wolf individuals are the top three gray wolf individuals in the gray wolf population in terms of Kapur entropy. α Kapur entropy > gray wolf individual β Kapur entropy > gray wolf individual Kapur entropy, For the Gray wolf individuals in the secondary cycle α Location, For the Gray wolf individuals in the secondary cycle β Location, For the Gray wolf individuals in the secondary cycle Location, For the The current location of the gray wolf in the cycle, For the The position of the current gray wolf individual in the cycle, Indicates the current gray wolf individual and the gray wolf individual α The distance between Indicates the current gray wolf individual and the gray wolf individual β The distance between Indicates the current gray wolf individual and the gray wolf individual The distance between 、 、 are all random numbers between [0, 2]. For gray wolf individuals α The corresponding coefficient factor is, For gray wolf individuals β The corresponding coefficient factor is, For gray wolf individuals The corresponding coefficient factor is, 、 are all random values ​​in the interval [0, 1]. is the number of iterations t The relevant nonlinear convergence parameters, Indicates that the current gray wolf individual is moving towards the gray wolf individual α Move the location, Indicates that the current gray wolf individual is moving towards the gray wolf individual β Move the location, Indicates that the current gray wolf individual is moving towards the gray wolf individual Move the position.

6. The power equipment infrared image edge detection method based on the multi-strategy grey wolf algorithm according to claim 1 is characterized in that: In step S6, the segmented image is subjected to corrosion operation to extract the image edge information, and the edge detection result of the infrared image of the power equipment is obtained, which is specifically: Assumptions P To segment the image, S is a structural element, then Representing structural elements S Pan X The result after Represents structural element S The symmetric set about the origin, The mathematical expression is: Then the corrosion operation is performed. The calculation formula of the corrosion operation process is: Finally, mathematical morphology boundary extraction, the specific calculation formula is: in, is the edge detection result, represents the erosion operation, Represents structural element S The amplitude at each position within.

7. An infrared image edge detection system for power equipment based on a multi-strategy grey wolf algorithm, characterized in that: The detection system adopts the infrared image edge detection method of power equipment based on the multi-strategy grey wolf algorithm as described in any one of claims 1 to 6, and the detection system includes: Grayscale image conversion unit: used to obtain infrared images of power equipment and convert the infrared images of power equipment into grayscale images; Initialization unit: used to initialize the parameters of the gray wolf algorithm and generate the initial gray wolf population using the chaotic mapping method; Kapur entropy calculation unit: calculates the Kapur entropy of the grayscale image segmentation by the position vector of each gray wolf individual; Iteration judgment unit: judge whether the current number of iterations has reached the maximum number of iterations. If so, the final gray wolf population is sent to the image segmentation unit; otherwise, the gray wolf position vector is updated iteratively, and the Kapur entropy calculation unit is called to calculate the Kapur entropy of the gray image segmentation of each gray wolf individual position vector, and the gray wolf individuals with higher Kapur entropy values ​​are selected to form the latest population; Image segmentation unit: using the position vector of each gray wolf in the final gray wolf population as the optimal segmentation threshold to perform threshold segmentation on the grayscale image to obtain a segmented image; Edge detection unit: Use corrosion operation to extract image edge information from the segmented image to obtain the edge detection result of the infrared image of the power equipment.

8. An infrared image edge detection system for power equipment based on a multi-strategy grey wolf algorithm, characterized in that: The detection system includes a processor and a memory connected to each other. When the processor runs the computer instructions stored in the memory, it executes the infrared image edge detection method of power equipment based on the multi-strategy grey wolf algorithm as described in any one of claims 1 to 6.

9. A power equipment monitoring device, characterized in that: It comprises an infrared probe and a computer device interconnected by a cable, wherein the computer device comprises a processor and a memory connected to each other, and when the processor runs the computer instructions stored in the memory, the infrared image edge detection method of electric power equipment based on the multi-strategy grey wolf algorithm as described in any one of claims 1 to 6 is executed.

10. A storage medium, characterized in that: The storage medium stores the infrared image edge detection method for power equipment based on the multi-strategy grey wolf algorithm as described in any one of claims 1 to 6.

Images