A power grid emergency repair and restoration management system

Abstract

The invention belongs to the field of image processing, and discloses a power grid emergency repair and recovery management system, comprising an image acquisition device, an image processing device and a computing device; the image acquisition device is used to acquire an image of the appearance of a power equipment to be repaired; the image processing device comprises a noise reduction module and a recognition module, the noise reduction module is used to perform noise reduction processing on the image acquired by the image acquisition device to obtain a processed image, and the recognition module is used to obtain the damage level of the power equipment based on the processed image; the computing device is used to calculate the emergency repair coefficient of the power equipment according to the damage level; the invention can perform noise reduction processing on a large number of images more quickly, thereby improving the speed of obtaining the result of the damage level of the power equipment, and facilitating timely emergency repair of the damaged power equipment in the power grid.

Description

Technical Field

[0001] The invention relates to the field of image processing, and in particular to a power grid emergency repair and restoration management system. Background Art

[0002] After natural disasters such as typhoons or floods, it is necessary to repair the power equipment in the power grid in a timely manner to restore power supply as soon as possible; in the process of power grid repair, it is usually necessary to determine the repair priority of the power equipment to be repaired, and then give priority to repairing those power equipment with a large impact range but low repair difficulty, so as to more quickly reduce the impact range caused by the damage to the power equipment.

[0003] In order to obtain the damage status of the damaged power equipment as quickly as possible, drones can usually be used to photograph the damaged power equipment and obtain images of the power equipment. The degree of damage to the power equipment is then determined based on the images. The order of repairing the power equipment is then determined based on the degree of damage, and a corresponding repair work order is generated and sent to the corresponding repair team.

[0004] Before inputting the image value of the power equipment into the pre-trained neural network model, it is generally necessary to perform denoising on the image first to reduce the noise of the image and improve the accuracy of the degree of damage determined by the model; the denoising method in the prior art generally directly performs denoising on all pixels, which also results in denoising the pixels belonging to the image background. Since the calculation process of denoising algorithms with good edge preservation effects such as non-local mean denoising is complex, the denoising of a single image takes a long time. When a large number of images of damaged power equipment need to be processed, the obtained images of the power equipment cannot be quickly denoised, which affects the speed of obtaining the results of the degree of damage, thereby affecting the efficiency of emergency repairs. Summary of the invention

[0005] The purpose of the present invention is to disclose a power grid emergency repair and recovery management system to solve the technical problem of how to improve the efficiency of noise reduction when using a neural network model to identify the degree of damage to power equipment during power grid emergency repair, so that the images of a large number of damaged power equipment can be denoised more quickly, the speed of obtaining the results of the degree of damage to the power equipment can be increased, and the efficiency of emergency repair can be improved.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: the present invention provides a power grid emergency repair and restoration management system, comprising an image acquisition device, an image processing device and a computing device; the image acquisition device is used to acquire an image of the appearance of the power equipment to be repaired; the image processing device comprises a noise reduction module and a recognition module, the noise reduction module is used to perform noise reduction processing on the image acquired by the image acquisition device to obtain a processed image, and the recognition module is used to obtain the damage level of the power equipment based on the processed image; the computing device is used to calculate the emergency repair coefficient of the power equipment according to the damage level; wherein, performing noise reduction processing on the image acquired by the image acquisition device to obtain a processed image comprises: a first step of converting the image acquired by the image acquisition device into a grayscale image; a second step of performing region growing processing on the grayscale image to obtain multiple connected domains; a third step of performing splicing processing on the connected domains to obtain a target area; a fourth step of performing noise reduction processing on the pixels in the target area to obtain a processed image.

[0007] Preferably, the image acquisition device includes a drone; the drone is used to photograph the appearance of the power equipment to be repaired, and obtain an image of the appearance of the power equipment to be repaired.

[0008] Preferably, it also includes a task allocation device; the task allocation device is used to generate an emergency repair work order according to the emergency repair coefficient.

[0009] Preferably, it also includes a terminal device; the task allocation device is used to send the emergency repair work order to the terminal device; the terminal device is used to display the emergency repair work order.

[0010] Preferably, a region growing process is performed on the grayscale image to obtain multiple connected domains, including: S1, storing all pixel points in the grayscale image into a set PU; S2, randomly selecting a pixel point from the PU as a seed pixel point; S3, performing region growing calculation on the seed pixel point to obtain the connected domain where the seed pixel point is located; S4, deleting the pixel points of the connected domain obtained in S3 from the PU; S5, judging whether the number of pixel points in the PU is greater than or equal to 1, if so, entering S2, if not, terminating the calculation.

[0011] Preferably, a regional growth calculation is performed on the seed pixel point to obtain a connected domain where the seed pixel point is located, including: S31, storing the seed pixel point in a set BU; S32, obtaining a set SU of pixel points in the 8-neighborhood of the seed pixel point that belong to the set PU and do not belong to the set BU; S33, respectively calculating the connectivity value of each pixel point in SU; S34, obtaining the maximum connectivity value MAXC; S35, judging whether MAXC is greater than the adaptive connectivity value threshold, if so, taking the pixel point corresponding to MAXC in SU as a new seed pixel point and entering S36, if not, terminating the calculation and forming a connected domain by the pixel points in BU; S36, storing the pixel point corresponding to MAXC in SU in a set BU; S37, deleting all the pixel points in SU and entering S32.

[0012] Preferably, the calculation formula of the connectivity value is: ; sd represents the seed pixel, b represents a pixel in SU, Represents the connectivity value of pixel b, and Represent the grayscale values ​​of sd and b respectively.

[0013] Preferably, the process of obtaining the adaptive connectivity value threshold is as follows: for the seed pixel sd, if the gray value of sd is greater than althr, the adaptive connectivity value threshold is calculated using the following formula: ; If the gray value of pixel b is less than or equal to althr, the following formula is used to calculate the adaptive connectivity threshold: ; represents the adaptive connectivity threshold corresponding to sd, Represents the median grayscale value of the pixel in the 8-neighborhood of sd. Indicates the standard deviation of the grayscale values ​​of pixels in the grayscale image whose grayscale values ​​are greater than althr. It represents the standard deviation of the grayscale values ​​of pixels whose grayscale values ​​are less than or equal to althr in the grayscale image. Althr represents the segmentation threshold of the grayscale image calculated using the Otsu algorithm.

[0014] Preferably, the connected domains are spliced ​​to obtain the target area, including: storing all connected domains into a set CNU; calculating the representative value of each connected domain in the CNU respectively; and splicing the connected domains based on the representative value to obtain the target area.

[0015] Preferably, performing noise reduction processing on the pixels in the target area to obtain a processed image includes: performing noise reduction processing on the pixels in the target area using a preset noise reduction algorithm to obtain a processed image.

[0016] Beneficial effect: In the process of denoising the image of the appearance of the power equipment, the present invention obtains the target area through region growing processing, stitching processing and the like, and then only performs denoising processing on the pixels in the target area, thereby effectively reducing the number of pixels involved in the denoising process and effectively improving the overall denoising efficiency; due to the improvement in the denoising efficiency of a single image, the present invention can perform denoising processing on a large number of images more quickly, thereby improving the speed of obtaining the results of the degree of damage of the power equipment, and facilitating timely repair of damaged power equipment in the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 The present invention is a schematic diagram of a power grid emergency repair and restoration management system.

[0019] Figure 2 A schematic diagram of the noise reduction process of the present invention. DETAILED DESCRIPTION

[0020] 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. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations; therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the invention claimed for protection, but only represents the selected embodiments of the present invention; based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts belong to the scope of protection of the present invention.

[0021] like Figure 1 In one embodiment shown, the present invention provides a power grid emergency repair and restoration management system, comprising an image acquisition device, an image processing device and a computing device; the image acquisition device is used to acquire an image of the appearance of the power equipment to be repaired; the image processing device comprises a noise reduction module and a recognition module, the noise reduction module is used to perform noise reduction processing on the image acquired by the image acquisition device to obtain a processed image, and the recognition module is used to obtain the damage level of the power equipment based on the processed image; the computing device is used to calculate the emergency repair coefficient of the power equipment according to the damage level; wherein, Figure 2As shown, the image obtained by the image acquisition device is subjected to noise reduction processing to obtain a processed image, including: a first step, converting the image obtained by the image acquisition device into a grayscale image; a second step, performing region growing processing on the grayscale image to obtain multiple connected domains; a third step, performing splicing processing on the connected domains to obtain a target area; a fourth step, performing noise reduction processing on the pixel points in the target area to obtain a processed image.

[0022] In the process of denoising the image of the appearance of the power equipment, the target area is obtained by region growing processing, splicing processing, etc., and then only the pixels in the target area are subjected to denoising processing, thereby effectively reducing the number of pixels involved in the denoising processing process and effectively improving the overall denoising efficiency. Due to the improvement of the denoising efficiency of a single image, the present invention can perform denoising processing on a large number of images more quickly, improve the speed of obtaining the results of the degree of damage of the power equipment, and facilitate timely repair of damaged power equipment in the power grid.

[0023] The time complexity of denoising algorithms with good edge preservation effect, such as non-local mean denoising, is usually around In the above, N represents the total number of pixels, and Q represents the size of the denoising window; and the region growing process of the present invention has a time complexity of only O(N), therefore, after obtaining the target region, since the number of pixels in the target region is significantly less than N, a faster denoising speed can be obtained; moreover, the target region of the present invention includes a real foreground region, therefore, denoising the target region can significantly reduce the total number of pixels belonging to the background part of the image participating in the denoising process, thereby effectively improving the denoising efficiency.

[0024] Preferably, the image acquisition device includes a drone; the drone is used to photograph the appearance of the power equipment to be repaired, and obtain an image of the appearance of the power equipment to be repaired.

[0025] Specifically, the staff responsible for emergency repairs can use remote-controlled drones to quickly repair the power equipment that needs to be repaired.

[0026] Preferably, a monitoring device is also included, and the monitoring device is used to monitor whether the status of the power equipment is normal.

[0027] Specifically, the monitoring device includes current measuring equipment, voltage measuring equipment, etc.; these measuring devices obtain current, voltage and other data during the operation of the power equipment and transmit these data to the monitoring center. The monitoring center determines whether the power identification status is normal based on the transmitted data. If the data transmitted by the measuring device is not received within a set time length (for example, 0.5 hours) or the transmitted data exceeds the monitoring threshold set in advance (for example, the voltage exceeds the set voltage range, and the current exceeds the set current range), it means that the power equipment is power equipment that needs emergency repair.

[0028] This is because if the power equipment is damaged by a natural disaster, the monitoring device is likely to be damaged as well. Therefore, if no data transmitted by the measuring device is received for a long time, it means that the power equipment is more likely to be damaged.

[0029] Preferably, the damage level of the power equipment is obtained based on the processed image, including: performing image segmentation on the processed image to obtain an image PA belonging to the power equipment in the processed image; calculating the similarity between PA and PB, where PB is an image taken of a brand new power equipment; and determining the damage level based on the similarity.

[0030] The damage level is determined by calculating the similarity. For the same power equipment, the higher the similarity between the appearance image obtained after a natural disaster and the appearance image in a brand new state, the lower the damage level and the lower the degree of damage.

[0031] Specifically, performing image segmentation on the processed image includes: performing image segmentation on the processed image using a segmentation algorithm.

[0032] Segmentation algorithms include Felzenszwalb, Huttenlocher, U-Net and other algorithms.

[0033] Preferably, determining the damage level based on the similarity includes: when the similarity is in the interval When the similarity is in the range When the similarity is in the interval When the similarity is in the interval When the similarity is in the interval , the damage level is 1.

[0034] Specifically, the damage level can be changed as needed. For example, when 10 damage levels are set, the length of the similarity interval corresponding to each damage level is 0.1.

[0035] Preferably, the calculation formula of the emergency repair coefficient is: ; represents the repair coefficient of power equipment c, represents the design life of the power equipment c, represents the cumulative service time of power equipment c, Indicates the maximum value of the damage level, Indicates the damage level of the power equipment c, Indicates the area of ​​power outage only when power equipment c is damaged. Indicates the area of ​​power outage when all power equipment to be repaired is damaged. represents the damage level weight, represents the time weight, Indicates the influence range weight.

[0036] The emergency repair coefficient of the present invention takes into comprehensive consideration three aspects: damage level, cumulative service time, and power outage area. When the damage level is smaller, the cumulative service time is longer, and the power outage area is larger, the emergency repair coefficient is larger, indicating that the power equipment should be given priority for emergency repair. In this way, emergency repair can be given priority to power equipment with low damage level but large impact range, thereby reducing the impact range of the power outage in a timely manner.

[0037] Preferably, the damage level weight is 0.4, the time weight is 0.2, and the impact range weight is 0.4.

[0038] Preferably, it also includes a task allocation device; the task allocation device is used to generate an emergency repair work order according to the emergency repair coefficient.

[0039] Specifically, a repair work order is generated according to the repair coefficient, including: periodically obtaining a set K of currently idle repair teams; using NK to represent the number of repair teams in K; determining the repair team corresponding to each power equipment to be repaired according to the principle of minimum distance for the first NK power equipment to be repaired with the largest repair coefficient; and generating a repair work order based on the location, number, and number of the repair team of the power equipment to be repaired.

[0040] For example, the set K of currently idle repair teams may be obtained every hour.

[0041] According to the principle of minimum distance, the repair team corresponding to each power equipment to be repaired is determined respectively, including: for the power equipment h to be repaired, the repair team closest to h is used as the repair team corresponding to h.

[0042] Preferably, it also includes a terminal device; the task allocation device is used to send the emergency repair work order to the terminal device; the terminal device is used to display the emergency repair work order.

[0043] Specifically, the terminal device is also used to send the status of the repair team to the task allocation device. For example, when the repair team completes the previous repair work order, it can send a notification message to the task allocation device. The notification message is used to inform the task allocation device that the repair team is in an idle state.

[0044] Preferably, a region growing process is performed on the grayscale image to obtain multiple connected domains, including: S1, storing all pixel points in the grayscale image into a set PU; S2, randomly selecting a pixel point from the PU as a seed pixel point; S3, performing region growing calculation on the seed pixel point to obtain the connected domain where the seed pixel point is located; S4, deleting the pixel points of the connected domain obtained in S3 from the PU; S5, judging whether the number of pixel points in the PU is greater than or equal to 1, if so, entering S2, if not, terminating the calculation.

[0045] After obtaining the connected domain, the present invention deletes the connected domain from the PU, thus effectively avoiding repeated region growing processing, improving the accuracy of the region growing processing, and improving the efficiency of the region growing processing.

[0046] Preferably, a regional growth calculation is performed on the seed pixel point to obtain a connected domain where the seed pixel point is located, including: S31, storing the seed pixel point in a set BU; S32, obtaining a set SU of pixel points in the 8-neighborhood of the seed pixel point that belong to the set PU and do not belong to the set BU; S33, respectively calculating the connectivity value of each pixel point in SU; S34, obtaining the maximum connectivity value MAXC; S35, judging whether MAXC is greater than the adaptive connectivity value threshold, if so, taking the pixel point corresponding to MAXC in SU as a new seed pixel point and entering S36, if not, terminating the calculation and forming a connected domain by the pixel points in BU; S36, storing the pixel point corresponding to MAXC in SU in a set BU; S37, deleting all the pixel points in SU and entering S32.

[0047] In the process of performing regional growth on seed pixels of the present invention, whether the pixel points in the neighborhood should be included in the connected domain where the seed pixel points are located is judged based on the adaptive connectivity value threshold. Such a threshold can change with the change of information in the grayscale image, and a more accurate regional growth result can be obtained.

[0048] Preferably, the calculation formula of the connectivity value is: ; sd represents the seed pixel, b represents a pixel in SU, Represents the connectivity value of pixel b, and Represent the grayscale values ​​of sd and b respectively.

[0049] The calculation process of the connectivity value adopts the absolute value method to calculate, so that the pixels in the neighborhood with grayscale values ​​greater than or less than the seed pixel point are likely to be selected as the next seed pixel point, which is beneficial to improving the integrity of the connected domain of the present invention.

[0050] Preferably, the process of obtaining the adaptive connectivity value threshold is as follows: for the seed pixel sd, if the gray value of sd is greater than althr, the adaptive connectivity value threshold is calculated using the following formula: ; If the gray value of pixel b is less than or equal to althr, the following formula is used to calculate the adaptive connectivity threshold: ; represents the adaptive connectivity threshold corresponding to sd, Represents the median grayscale value of the pixel in the 8-neighborhood of sd. Indicates the standard deviation of the grayscale values ​​of pixels in the grayscale image whose grayscale values ​​are greater than althr. It represents the standard deviation of the grayscale values ​​of pixels whose grayscale values ​​are less than or equal to althr in the grayscale image. Althr represents the segmentation threshold of the grayscale image calculated using the Otsu algorithm.

[0051] The adaptive connectivity value threshold of the present invention first considers the relationship between the gray value of the seed pixel and the segmentation threshold when calculating, so that when the probability that the seed pixel belongs to the area of ​​the power equipment is large, the connectivity domain threshold can be adaptively calculated based on the standard deviation of the gray value of the pixel whose gray value is greater than althr in the gray image and the median of the gray value of the pixel in the 8 neighborhoods, and when the probability that the seed pixel belongs to the area of ​​the power equipment is small, the connectivity domain threshold can be adaptively calculated based on the standard deviation of the gray value of the pixel whose gray value is less than or equal to althr in the gray image and the median of the gray value of the pixel in the 8 neighborhoods, so that the connectivity value threshold can be more targeted. The connectivity value threshold of the present invention can change adaptively with the change of the median, effectively improving the effectiveness of the connectivity domain threshold.

[0052] Preferably, the connected domains are spliced ​​to obtain the target area, including: storing all connected domains into a set CNU; calculating the representative value of each connected domain in the CNU respectively; and splicing the connected domains based on the representative value to obtain the target area.

[0053] By performing stitching processing through representative values ​​instead of only considering a single grayscale value difference, combined with the stitching method of the present invention, a more rapid and accurate stitching result can be obtained.

[0054] Preferably, the calculation formula of the representative value is: ; ; represents the representative value of the connected domain t, represents the distance between the center of the connected domain t and the center of the grayscale image, Represents the maximum value of the distance between the connected domain and the center of the grayscale image, represents the mean gray value of the pixels in the connected domain t, neit represents the set of other connected domains adjacent to the connected domain t, represents the total number of connected domains in neit, Represents the mean gray value of the pixels in the connected domain m; represents the distance weight, represents the first grayscale weight, represents the second grayscale weight, Represents the minimum value of the mean grayscale value of the pixels in the connected domain in neit.

[0055] The representative value of the present invention is comprehensively calculated from three types of data from multiple angles, namely, the distance from the center of the grayscale image, the grayscale value difference from the althr, and the grayscale value difference from the surrounding connectivity thresholds. The foreground pixels are generally close to the center of the image. Therefore, the closer the connected domain is to the center of the grayscale image, the greater the grayscale difference from the althr, and the smaller the difference between the grayscale value means of other surrounding connected domains, the greater the representative value of the present invention, indicating that the possibility that the connected domain belongs to the area where the power equipment is located is greater, so that in the subsequent splicing process, a more accurate representative value comparison object can be obtained, that is, the connected domain with the largest representative value.

[0056] Preferably, the distance weight, the first grayscale weight and the second grayscale weight are all .

[0057] Preferably, the connected domains are spliced ​​based on the representative values ​​to obtain the target area, including: S10, obtaining the connected domain MZ with the largest representative value; S20, storing all the connected domains into a set LU; S30, respectively calculating the absolute value of the difference between the representative value of each connected domain of LU and MZ; S40, storing the connected domains in LU whose absolute value is less than the set absolute value threshold into a set FU; S50, forming the target area from all the connected domains in FU.

[0058] When performing splicing processing, the present invention does not calculate the similarity between adjacent connected domains separately and perform splicing based on the similarity, but calculates the absolute value of the difference between the representative value of each connected domain of LU and MZ based on the connected domain with the largest representative value. In this way, the connected domain similar to the connected domain with the largest representative value, that is, the connected domain similar to the local area where the power equipment is located, can be quickly determined, thereby realizing rapid splicing processing and being beneficial to improving the efficiency of noise reduction.

[0059] Preferably, the absolute value threshold is set to .

[0060] Preferably, performing noise reduction processing on the pixels in the target area to obtain a processed image includes: performing noise reduction processing on the pixels in the target area using a preset noise reduction algorithm to obtain a processed image.

[0061] Specifically, the preset noise reduction algorithm includes a non-local mean noise reduction algorithm.

[0062] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention; therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A power grid emergency repair and restoration management system, characterized in that: It includes an image acquisition device, an image processing device and a computing device; the image acquisition device is used to acquire an image of the appearance of the power equipment to be repaired; the image processing device includes a noise reduction module and a recognition module, the noise reduction module is used to perform noise reduction processing on the image acquired by the image acquisition device to obtain a processed image, and the recognition module is used to obtain the damage level of the power equipment based on the processed image; The calculation device is used to calculate the repair coefficient of the power equipment according to the damage level; wherein, the image obtained by the image acquisition device is subjected to noise reduction processing to obtain a processed image, including: the first step of converting the image obtained by the image acquisition device into a grayscale image; the second step of performing region growing processing on the grayscale image to obtain multiple connected domains; the third step of performing splicing processing on the connected domains to obtain a target area; the fourth step of performing noise reduction processing on the pixels in the target area to obtain a processed image; the connected domains are subjected to splicing processing to obtain the target area, including: storing all connected domains in a set CNU; calculating the representative value of each connected domain in the CNU respectively; splicing the connected domains based on the representative value to obtain the target area; the calculation formula of the representative value is: ; ; represents the representative value of the connected domain t, represents the distance between the center of the connected domain t and the center of the grayscale image, Represents the maximum value of the distance between the connected domain and the center of the grayscale image, represents the mean gray value of the pixels in the connected domain t, neit represents the set of other connected domains adjacent to the connected domain t, represents the total number of connected domains in neit, Represents the mean gray value of the pixels in the connected domain m; represents the distance weight, represents the first grayscale weight, represents the second grayscale weight, Representing the minimum value of the mean grayscale value of the pixel points of the connected domain in neit; splicing the connected domains based on the representative value to obtain the target area, including: S10, obtaining the connected domain MZ with the largest representative value; S20, storing all the connected domains in the set LU; S30, respectively calculating the absolute value of the difference between the representative value of each connected domain of LU and MZ; S40, storing the connected domains in LU whose absolute value is less than the set absolute value threshold into the set FU; S50, forming the target area from all the connected domains in FU.

2. A power grid emergency repair and restoration management system according to claim 1, characterized in that: The image acquisition device includes a drone; the drone is used to photograph the appearance of the power equipment to be repaired, and obtain an image of the appearance of the power equipment to be repaired.

3. A power grid emergency repair and restoration management system according to claim 1, characterized in that: It also includes a task allocation device; the task allocation device is used to generate an emergency repair work order according to the emergency repair coefficient.

4. A power grid emergency repair and restoration management system according to claim 3, characterized in that: It also includes a terminal device; the task allocation device is used to send the emergency repair work order to the terminal device; the terminal device is used to display the emergency repair work order.

5. A power grid emergency repair and restoration management system according to claim 1, characterized in that: Performing region growing processing on the grayscale image to obtain multiple connected domains, including: S1, storing all pixel points in the grayscale image into a set PU; S2, randomly selecting a pixel point from PU as a seed pixel point; S3, performing region growing calculation on the seed pixel point to obtain the connected domain where the seed pixel point is located; S4, deleting the pixel points of the connected domain obtained in S3 from PU; S5, judging whether the number of pixel points in PU is greater than or equal to 1, if so, entering S2, if not, ending the calculation.

6. A power grid emergency repair and restoration management system according to claim 5, characterized in that: Perform regional growth calculation on the seed pixel point to obtain the connected domain where the seed pixel point is located, including: S31, store the seed pixel point into the set BU; S32, obtain the set SU of pixel points in the 8-neighborhood of the seed pixel point that belong to the set PU and do not belong to the set BU; S33, calculate the connectivity value of each pixel point in SU respectively; S34, obtain the maximum connectivity value MAXC; S35, determine whether MAXC is greater than the adaptive connectivity value threshold, if so, use the pixel point corresponding to MAXC in SU as the new seed pixel point and enter S36, if not, end the calculation, and form a connected domain by the pixel points in BU; S36, store the pixel point corresponding to MAXC in SU into the set BU; S37, delete all the pixel points in SU and enter S32.

7. A power grid emergency repair and restoration management system according to claim 6, characterized in that: The calculation formula of connectivity value is: , sd represents the seed pixel, b represents a pixel in SU, Represents the connectivity value of pixel b, and Represent the grayscale values ​​of sd and b respectively.

8. A power grid emergency repair and restoration management system according to claim 6, characterized in that: The process of obtaining the adaptive connectivity threshold is as follows: for the seed pixel sd, if the gray value of sd is greater than althr, the adaptive connectivity threshold is calculated using the following formula: ; If the gray value of pixel b is less than or equal to althr, the following formula is used to calculate the adaptive connectivity threshold: ; represents the adaptive connectivity threshold corresponding to sd, Represents the median grayscale value of the pixel in the 8-neighborhood of sd. Indicates the standard deviation of the grayscale values ​​of pixels in the grayscale image whose grayscale values ​​are greater than althr. It represents the standard deviation of the grayscale values ​​of pixels whose grayscale values ​​are less than or equal to althr in the grayscale image. Althr represents the segmentation threshold of the grayscale image calculated using the Otsu algorithm.

9. A power grid emergency repair and restoration management system according to claim 1, characterized in that: Performing noise reduction processing on the pixel points in the target area to obtain a processed image includes: performing noise reduction processing on the pixel points in the target area using a preset noise reduction algorithm to obtain a processed image.

Images