Power Equipment Infrared Image Segmentation Method and System Based on Improved Grey Wolf Algorithm

Abstract

The present invention discloses a method and system for infrared image segmentation of power equipment based on an improved grey wolf algorithm, including: initializing the improved grey wolf algorithm to determine the maximum number of iterations and the position vectors of grey wolf individuals in the grey wolf population; using exponential entropy as the discriminant of the improved grey wolf algorithm to calculate the exponential entropy of the position vectors of each grey wolf individual for segmenting the infrared image of the power equipment to be segmented; if the number of iterations reaches the maximum number of iterations, obtaining the position vector of the grey wolf individual corresponding to the maximum exponential entropy from the grey wolf population as the threshold vector for optimal multi-threshold segmentation, and performing multi-threshold segmentation on the infrared image of the power equipment to be segmented according to the threshold vector for optimal multi-threshold segmentation, so as to obtain a segmented image. The purpose of the present invention is to achieve adaptive multi-threshold segmentation of the infrared image of power equipment based on the exponential entropy of the improved grey wolf algorithm to overcome the problem of poor image segmentation effect in the prior art.

Description

Technical Field

[0001] The invention belongs to the technical field of image processing of infrared images of electric power equipment, and in particular relates to an infrared image segmentation method and system for electric power equipment based on an improved grey wolf algorithm. Background Art

[0002] The infrared image of power equipment reflects the temperature of the equipment during operation and is an effective means to detect and diagnose whether the power equipment has overheating defects. The traditional single threshold segmentation method of infrared images of power equipment can only simply divide the environmental background and the outline of the power equipment, and has the disadvantages of poor segmentation effect, manual threshold selection, and much information loss. Binary segmentation of infrared images alone cannot effectively reflect the defects of power equipment. Therefore, it is very necessary to develop a multi-threshold segmentation method for infrared images with adaptive threshold selection, which provides important support for improving fault detection efficiency and meeting the real-time diagnosis needs of equipment. Liu Peijin et al. proposed a multi-threshold segmentation method for infrared images based on firefly algorithm and maximum cumulative variance, and applied it to two types of electrical equipment: overloaded motors and through-line electric pipes. Wu Xueqiong et al. used the inverse trigonometric function to optimize the bat algorithm, constructed a fitness function model of two-dimensional entropy, and realized the multi-threshold segmentation of distribution network equipment. The above two methods preliminarily solved the problem of improper threshold selection in the process of multi-valued image segmentation, but the segmentation effect is still difficult to meet the requirements of real-time extraction and analysis of current power equipment. Summary of the invention

[0003] Technical problem to be solved by the present invention: In view of the above-mentioned problems in the prior art, a method and system for infrared image segmentation of power equipment based on an improved grey wolf algorithm are provided. The present invention aims to realize adaptive multi-threshold segmentation of infrared images of power equipment based on the exponential entropy of the improved grey wolf algorithm, so as to overcome the problem of poor image segmentation effect in the prior art.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0005] A method for infrared image segmentation of power equipment based on an improved grey wolf algorithm, comprising:

[0006] S101, initializing the improved gray wolf algorithm, determining the maximum number of iterations and the position vector of the gray wolf individuals in the gray wolf population;

[0007] S102, using exponential entropy as a discriminant of the improved grey wolf algorithm, respectively calculating the exponential entropy of the position vector of each grey wolf individual for the infrared image segmentation of the power equipment to be segmented;

[0008] S103. Increment the iteration count by 1, and check if the iteration count has reached the maximum number of iterations. If it has reached the maximum number of iterations, then jump to step S104; otherwise, update the position vector of the grey wolf and jump back to step S103 to continue the iteration.

[0009] S104. Obtain the position vector of the grey wolf individual corresponding to the maximum exponential entropy from the grey wolf population as the threshold vector for optimal multi-threshold segmentation. Perform multi-threshold segmentation on the infrared image of the power equipment to be segmented according to the threshold vector for optimal multi-threshold segmentation, thereby obtaining the segmented image.

[0010] Optionally, when determining the maximum number of iterations and the position vectors of the grey wolf individuals in the grey wolf population in step S101, determining the position vector of each grey wolf individual includes taking num random integers between [1, 255] as the num components in the position vector.

[0011] Optionally, when determining the maximum number of iterations and the position vectors of the grey wolf individuals in the grey wolf population in step S101, determining the position vector of each grey wolf individual further includes arranging the num components in the position vector in ascending order to form the position vector.

[0012] Optionally, when performing multi-threshold segmentation on the infrared image of the power equipment to be segmented according to the threshold vector for optimal multi-threshold segmentation in step S104, the obtained segmented image contains num + 1 parts, and the gray value of each part is the same.

[0013] Optionally, the function expression used when calculating the exponential entropy of the infrared image of the power equipment to be segmented by the position vectors of each grey wolf individual in step S102 is:

[0014] H = H0 + 1 +... + H num ,

[0015] In the above formula, H represents the exponential entropy of the grey wolf, and H0 to H n respectively represent the exponential entropies of the num + 1 parts obtained by segmenting the infrared image of the power equipment to be segmented by the position vector;

[0016]

[0017]

[0018]

[0019] In the above formula, th1 to th num respectively represent the num components in the position vector, and th j represents any j-th component in the position vector; P iis the occurrence probability of the gray value i in the grayscale image, 255 is the maximum gray value; ω1 to ω num respectively represent the weight parameters of num components in the position vector, ω j represents the weight parameter of any j-th component in the position vector, where j is greater than 0 and less than num.

[0020] Optionally, the position vector of the gray wolf includes 4 components.

[0021] In addition, the present invention also provides a power equipment infrared image segmentation system based on an improved gray wolf algorithm, including:

[0022] An initialization program unit for initializing the improved gray wolf algorithm to determine the maximum number of iterations and the position vectors of the gray wolf individuals in the gray wolf population;

[0023] An exponential entropy calculation program unit for using exponential entropy as the discriminant of the improved gray wolf algorithm to calculate the exponential entropy of the position vectors of each gray wolf individual for segmenting the power equipment infrared image to be segmented;

[0024] An iteration judgment program unit for adding 1 to the number of iterations, judging whether the number of iterations reaches the maximum number of iterations, and if it reaches the maximum number of iterations, calling the image segmentation program unit; otherwise, updating the position vector of the gray wolf and calling the exponential entropy calculation program unit to continue the iteration;

[0025] An image segmentation program unit for obtaining the position vector of the gray wolf individual corresponding to the maximum exponential entropy in the gray wolf population as the threshold vector for optimal multi-threshold segmentation, and performing multi-threshold segmentation on the power equipment infrared image to be segmented according to the threshold vector for optimal multi-threshold segmentation, thereby obtaining a segmented image.

[0026] In addition, the present invention also provides a power equipment infrared image segmentation system based on an improved gray wolf algorithm, including a microprocessor and a memory connected to each other, and the microprocessor is programmed or configured to execute the power equipment infrared image segmentation method based on the improved gray wolf algorithm.

[0027] In addition, the present invention also provides an exponential entropy power equipment monitoring device, including an infrared probe and a computer device connected to each other through a cable, the computer device includes a microprocessor and a memory connected to each other, and the microprocessor is programmed or configured to execute the power equipment infrared image segmentation method based on the improved gray wolf algorithm.

[0028] In addition, the present invention also provides a computer-readable storage medium, in which a computer program is stored, and the computer program is used to be programmed or configured by a microprocessor to execute the power equipment infrared image segmentation method based on the improved gray wolf algorithm.

[0029] Compared with the prior art, the present invention mainly has the following advantages: improving the initialization of the gray wolf algorithm, determining the maximum number of iterations and the position vectors of gray wolf individuals in the gray wolf population; using exponential entropy as the discriminant of the improved gray wolf algorithm, and calculating the exponential entropy of the position vectors of each gray wolf individual for segmenting the infrared image of the power equipment to be segmented; if the number of iterations reaches the maximum number of iterations, obtaining the position vector of the gray wolf individual corresponding to the maximum exponential entropy from the gray wolf population as the threshold vector for optimal multi-threshold segmentation, and performing multi-threshold segmentation on the infrared image of the power equipment to be segmented according to the threshold vector for optimal multi-threshold segmentation, so as to obtain a segmented image. The present invention uses exponential entropy as the evaluation criterion for the pros and cons of the improved gray wolf algorithm, realizes quickly and accurately finding the optimal segmentation threshold vector in the infrared image, and uses it for the multi-valued segmentation of the received image, improving the segmentation effect of the image to overcome the problem of poor image segmentation effect in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic diagram of the basic flow of the method in the embodiment of the present invention.

[0031] Figure 2 They are the original images of two infrared images of power equipment in the embodiment of the present invention.

[0032] Figure 3 They are the segmentation results obtained by the traditional gray wolf algorithm for comparison in the embodiment of the present invention.

[0033] Figure 4 They are the segmentation results obtained by the improved gray wolf algorithm adopted in the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0034] As Figure 1 shown, the method for segmenting the infrared image of the power equipment based on the improved gray wolf algorithm in this embodiment includes:

[0035] S101, performing the initialization of the improved gray wolf algorithm, determining the maximum number of iterations (denoted as Iter in this embodiment) and the position vectors of gray wolf individuals in the gray wolf population;

[0036] S102, using exponential entropy as the discriminant of the improved gray wolf algorithm, and calculating the exponential entropy of the position vectors of each gray wolf individual for segmenting the infrared image of the power equipment to be segmented;

[0037] S103, adding 1 to the number of iterations, determining whether the number of iterations reaches the maximum number of iterations Iter, if it reaches the maximum number of iterations Iter, then jumping to step S104; otherwise, updating the position vectors of the gray wolves, and jumping to step S103 to continue the iteration;

[0038] S104. Obtain the position vector of the gray wolf individual corresponding to the maximum exponential entropy in the gray wolf population as the threshold vector for optimal multi-threshold segmentation, and perform multi-threshold segmentation on the infrared image of the power equipment to be segmented according to the threshold vector for optimal multi-threshold segmentation, so as to obtain a segmented image.

[0039] See Figure 1 It can be seen that as an optional implementation manner, in this embodiment, the method of obtaining the infrared image of the power equipment to be segmented at the beginning is selected. In addition, according to needs, the infrared image of the power equipment to be segmented can also be read when it is needed, and the existence verification of the infrared image of the power equipment to be segmented can be performed at the beginning, etc., which will not be elaborated here.

[0040] In this embodiment, when determining the maximum number of iterations and the position vectors of gray wolf individuals in the gray wolf population in step S101, determining the position vector of each gray wolf individual includes taking num random integers between [1, 255] as num components in the position vector. As an optional implementation manner, this embodiment further includes initializing the quantity of num (the number of thresholds num) in step S101, so that the number of components of the threshold vector for the required multi-threshold segmentation can be flexibly specified according to needs. In this embodiment, when determining the maximum number of iterations and the position vectors of gray wolf individuals in the gray wolf population in step S101, determining the position vector of each gray wolf individual further includes arranging the num components in the position vector in ascending order to form the position vector, so as to ensure that the thresholds in the obtained threshold vector for optimal multi-threshold segmentation are arranged in ascending order.

[0041] In this embodiment, when performing multi-threshold segmentation on the infrared image of the power equipment to be segmented according to the threshold vector for optimal multi-threshold segmentation in step S104, the obtained segmented image includes num + 1 parts, and the gray value of each part is the same.

[0042] In this embodiment, the function expression used to calculate the exponential entropy of the infrared image of the power equipment to be segmented by the position vectors of each gray wolf individual in step S102 is:

[0043] H = H0 + 1 +... + H num ,

[0044] In the above formula, H represents the exponential entropy of the gray wolf, and H0 to H n respectively represent the exponential entropies of the num + 1 parts obtained by segmenting the infrared image of the power equipment to be segmented by the position vector;

[0045]

[0046]

[0047]

[0048] In the above formula, th1 to th num respectively represent num components in the position vector, and th j represents any j-th component in the position vector; P i is the occurrence probability of the gray value i in the grayscale image, and 255 is the maximum gray value; ω1 to ω num respectively represent the weight parameters of num components in the position vector, and ω j represents the weight parameter of any j-th component in the position vector, where j is greater than 0 and less than num. Referring to the above function expression, it can be seen that in step S102, when calculating the exponential entropy of the position vector of each gray wolf individual for segmenting the infrared image of the power equipment to be segmented, in the function expression used, multi-threshold segmentation optimization is performed using the gray value of the pixel point and its neighborhood average gray value, greatly reducing the influence of the noise and uneven contrast existing in the original infrared image on the segmentation effect of the infrared thermal image of the power equipment, and improving the accuracy of image segmentation.

[0049] In this embodiment, the position vector of the gray wolf includes 4 components, and the position vector can be expressed as:

[0050] pos = [h1, h2, h3, h4],

[0051] Using the position vector as the threshold to segment the infrared image of the electrical equipment, the image is divided into 5 parts, and the exponential entropy corresponding to each part is as follows:

[0052]

[0053]

[0054]

[0055]

[0056]

[0057] The exponential entropy of the overall image is the sum of each part, written as H = H0 + 1 +... + H4. When the exponential entropy H increases, the position vector pos of the gray wolf is updated after each iteration. It should be noted that the method of updating the position vector pos of the gray wolf in this embodiment is the same as the traditional gray wolf algorithm, so it will not be elaborated here.

[0058] After reaching the maximum number of iterations, the calculation ends. The position of the gray wolf corresponding to the maximum exponential entropy is the optimal threshold vector for image segmentation. According to the optimal threshold vector, multi-threshold segmentation is performed on the target image, and the final result is output. In this embodiment, when the calculation reaches the maximum number of iterations Iter = 50, the optimal position pos corresponding to the gray wolf with the maximum exponential entropy is output * , and its expression is:

[0059]

[0060] where is the threshold vector for optimal multi-threshold segmentation. According to pos * threshold segmentation is performed on the image, and the final result is output. Figure 2 In (a) and (b) in Figure 3 are the original images of two infrared images of power equipment, Figure 3 is the segmentation result obtained by using the traditional gray wolf algorithm, Figure 2 in (a) and (b) and Figure 4 in the original images (a) and (b) in Figure 4 correspond; Figure 2 shows the segmentation result obtained by using the improved gray wolf algorithm based on this embodiment,

[0061]

[0062] In the above formula, SSIM(x, y) represents the structural similarity between x and y, and x and y respectively represent the original infrared image and the threshold segmentation result. μ x and μ y are respectively the average amplitudes of the pixel points in x and y, and are respectively the variances of the pixel point amplitudes in x and y. σ xy represents the covariance between x and y. c1 = (k1L) 2 and c2 = (k2L) 2 are constants used to maintain stability. L represents the dynamic value range of the pixel values in the picture. Here, L takes 255, k1 takes 0.01, and k2 takes 0.03. The value range of SSIM is [0, 1]. The larger the SSIM value, the closer the two pictures are under the human visual perception. When the two pictures are exactly the same, SSIM takes 1. The segmentation results corresponding to this embodiment and the traditional gray wolf algorithm are compared. When the original image to be segmented is Figure 2 in (a), the SSIM value of the result of this embodiment is 0.9794. At the same time, the SSIM value of the result of the traditional gray wolf algorithm is 0.9622; when the original image isFigure 2 When it comes to (b) in [specific context], the SSIM value of the result of this embodiment is 0.9833. At the same time, the SSIM value of the result of the traditional gray wolf algorithm is 0.9790. The above comparison shows that compared with the traditional gray wolf algorithm, the power equipment infrared image segmentation method based on the improved gray wolf algorithm can obtain a result with a higher degree of coincidence with the original image, and more detailed information of the power equipment in the original image is still retained after segmentation.

[0063] In summary, the power equipment infrared image segmentation method based on the improved gray wolf algorithm in this embodiment includes obtaining an infrared image and converting the infrared image into a grayscale image; setting the initial parameters of the improved gray wolf algorithm and releasing the gray wolf population; using the exponential entropy discrimination function as the formula for evaluating the superiority and inferiority of gray wolves in the improved gray wolf algorithm to carry out iterative optimization calculations; after reaching the maximum number of iterations, returning the position information of the wolf pack as the optimal image segmentation threshold obtained by this algorithm, and outputting the result after threshold segmentation. Compared with the existing infrared image threshold segmentation methods, the present invention improves the image segmentation accuracy, realizes adaptive multi-threshold selection, effectively solves the difficulties in power equipment infrared image segmentation, and lays a foundation for subsequent fault analysis and diagnosis.

[0064] In addition, this embodiment also provides a power equipment infrared image segmentation system based on the improved gray wolf algorithm, including:

[0065] An initialization program unit for initializing the improved gray wolf algorithm, determining the maximum number of iterations and the position vectors of gray wolf individuals in the gray wolf population;

[0066] An exponential entropy calculation program unit for using exponential entropy as the discriminant of the improved gray wolf algorithm and calculating the exponential entropy of the position vectors of each gray wolf individual for segmenting the power equipment infrared image to be segmented;

[0067] An iteration judgment program unit for adding 1 to the iteration count, judging whether the iteration count reaches the maximum number of iterations. If it reaches the maximum number of iterations, it calls the image segmentation program unit; otherwise, it updates the position vectors of the gray wolves and calls the exponential entropy calculation program unit to continue the iteration;

[0068] An image segmentation program unit for obtaining the position vector of the gray wolf individual corresponding to the maximum exponential entropy from the gray wolf population as the threshold vector for optimal multi-threshold segmentation, and performing multi-threshold segmentation on the power equipment infrared image to be segmented according to the threshold vector for optimal multi-threshold segmentation, so as to obtain the segmented image.

[0069] In addition, this embodiment also provides a power equipment infrared image segmentation system based on the improved gray wolf algorithm, including a microprocessor and a memory connected to each other, and the microprocessor is programmed or configured to execute the power equipment infrared image segmentation method based on the improved gray wolf algorithm.

[0070] In addition, this embodiment also provides an exponential entropy power equipment monitoring device, including an infrared probe and a computer device interconnected by a cable. The computer device includes a microprocessor and a memory interconnected with each other. The microprocessor is programmed or configured to execute the power equipment infrared image segmentation method based on the improved grey wolf algorithm.

[0071] In addition, this embodiment also provides a computer-readable storage medium. A computer program is stored in the computer-readable storage medium, and the computer program is used to be programmed or configured by the microprocessor to execute the power equipment infrared image segmentation method based on the improved grey wolf algorithm.

[0072] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes. The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks. These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device realizes the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks. These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for realizing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0073] The above are only the preferred embodiments of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions falling within the concept of the present invention belong to the protection scope of the present invention. It should be noted that for those of ordinary skill in the art, several improvements and refinements made without departing from the principle of the present invention should also be regarded as within the protection scope of the present invention.

Claims

1. An infrared image segmentation method for power equipment based on an improved grey wolf algorithm, characterized in that, Including: S101, perform the initialization of the improved grey wolf algorithm to determine the maximum number of iterations and the position vectors of grey wolf individuals in the grey wolf population; S102, use exponential entropy as the discriminant of the improved grey wolf algorithm, and calculate the exponential entropy of the position vectors of each grey wolf individual for segmenting the infrared image of the power equipment to be segmented; S103, increment the iteration count by 1, and determine whether the iteration count has reached the maximum number of iterations. If the maximum number of iterations is reached, jump to step S104; otherwise, update the position vector of the grey wolf and jump to step S103 to continue the iteration; S104, obtain the position vector of the grey wolf individual corresponding to the maximum exponential entropy from the grey wolf population as the threshold vector for optimal multi-threshold segmentation, and perform multi-threshold segmentation on the infrared image of the power equipment to be segmented according to the threshold vector for optimal multi-threshold segmentation, so as to obtain a segmented image; When calculating the exponential entropy of the position vectors of each grey wolf individual for segmenting the infrared image of the power equipment to be segmented in step S102, the function expression used is: ， In the above formula, represents the exponential entropy of the gray wolf, ~ respectively represent the exponential entropies of the num+1 parts obtained by segmenting the infrared image of the power equipment to be segmented with the position vector; ， ， ， ， ， ， In the above formula, to respectively represent num components in the position vector, represents any j-th component in the position vector; is the occurrence probability of the gray value in the grayscale image, and 255 is the maximum gray value; to respectively represent the weight parameters of the num + 1 parts obtained by segmentation, represents the weight parameter of the (j + 1)-th part obtained by segmentation, where j is greater than 0 and less than or equal to num.

2. The infrared image segmentation method for power equipment based on an improved grey wolf algorithm according to claim 1, characterized in that, When determining the maximum number of iterations and the position vectors of grey wolf individuals in the grey wolf population in step S101, determining the position vector of each grey wolf individual includes taking num random integers between [1, 255] as num components in the position vector.

3. The infrared image segmentation method for power equipment based on an improved grey wolf algorithm according to claim 2, characterized in that, When determining the maximum number of iterations and the position vectors of grey wolf individuals in the grey wolf population in step S101, determining the position vector of each grey wolf individual further includes arranging the num components in the position vector in ascending order to form the position vector.

4. The infrared image segmentation method for power equipment based on an improved grey wolf algorithm according to claim 3, characterized in that, When performing multi-threshold segmentation on the infrared image of the power equipment to be segmented according to the threshold vector for optimal multi-threshold segmentation in step S104, the obtained segmented image includes num + 1 parts, and the gray values of each part are the same.

5. The infrared image segmentation method for power equipment based on an improved grey wolf algorithm according to claim 1, characterized in that, The position vector of the grey wolf includes 4 components.

6. An infrared image segmentation system for power equipment for performing the infrared image segmentation method for power equipment based on an improved grey wolf algorithm according to any one of claims 1 to 5, characterized in that, Including: An initialization program unit for performing the initialization of the improved grey wolf algorithm to determine the maximum number of iterations and the position vectors of grey wolf individuals in the grey wolf population; An exponential entropy calculation program unit for using exponential entropy as the discriminant of the improved grey wolf algorithm and calculating the exponential entropy of the position vectors of each grey wolf individual for segmenting the infrared image of the power equipment to be segmented; An iteration judgment program unit for incrementing the iteration count by 1, determining whether the iteration count has reached the maximum number of iterations, and if the maximum number of iterations is reached, calling the image segmentation program unit; otherwise, updating the position vector of the grey wolf and calling the exponential entropy calculation program unit to continue the iteration; An image segmentation program unit for obtaining the position vector of the grey wolf individual corresponding to the maximum exponential entropy from the grey wolf population as the threshold vector for optimal multi-threshold segmentation, and performing multi-threshold segmentation on the infrared image of the power equipment to be segmented according to the threshold vector for optimal multi-threshold segmentation, so as to obtain a segmented image.

7. An infrared image segmentation system for power equipment based on an improved grey wolf algorithm, comprising a microprocessor and a memory connected to each other, characterized in that, The microprocessor is programmed or configured to execute the method for segmenting the infrared image of the power equipment based on the improved grey wolf algorithm according to any one of claims 1 to 5.

8. An exponential entropy power equipment monitoring device, comprising an infrared probe and a computer device connected to each other through a cable, characterized in that, The computer device includes a microprocessor and a memory connected to each other, and the microprocessor is programmed or configured to execute the infrared image segmentation method of power equipment based on the improved grey wolf algorithm according to any one of claims 1 to 5.

9. A computer-readable storage medium, in which a computer program is stored, characterized in that, The computer program is used to be programmed or configured by a microprocessor to execute the infrared image segmentation method of power equipment based on the improved grey wolf algorithm according to any one of claims 1 to 5.

Images