High-voltage wall bushing detection method, device, computer equipment and storage medium

Abstract

The present application relates to a method, device, computer equipment and storage medium for detecting high-voltage wall bushings. The method comprises: obtaining an original infrared image containing a high-voltage wall bushing, as well as a maximum temperature value and a minimum temperature value of the original infrared image, extracting an image area corresponding to the high-voltage wall bushing from the original infrared image, constructing a temperature distribution map corresponding to the high-voltage wall bushing according to the maximum temperature value, the minimum temperature value and the pixel values ​​in the image area, and determining the detection result of the high-voltage wall bushing according to the temperature distribution map. The use of this method can improve the timeliness and accuracy of high-voltage wall bushing detection, thereby ensuring the safety of power transmission.

Description

Technical Field

[0001] The present application relates to the technical field of bushing detection, and in particular to a method, device, computer equipment and storage medium for detecting a high-voltage wall bushing. Background Art

[0002] As the demand for electric energy increases year by year, in order to facilitate power transmission in complex environments, high-voltage wall bushings can be used to pass through obstacles (e.g., buildings) for power transmission. Therefore, in order to ensure the safety of high-voltage wall bushings, a detection method for high-voltage wall bushings has emerged. The infrared image of the high-voltage wall bushing can be directly obtained by a mobile device (e.g., a mobile robot equipped with an infrared device), and then, based on the temperature reflected by the infrared image, it is determined whether the high-voltage wall bushing is abnormal.

[0003] However, with the current detection method, the temperature conditions reflected by the infrared image are directly used as the temperature distribution of the high-voltage wall bushing. The accuracy of such inverted temperature distribution for detecting abnormalities is not high, which in turn affects the safety of power transmission. Summary of the invention

[0004] Based on this, it is necessary to provide a high-voltage wall bushing detection method, device, computer equipment and storage medium that can improve the timeliness of detection in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for detecting a high-voltage wall bushing. The method comprises:

[0006] Acquire the original infrared image containing the high-voltage wall bushing, as well as the maximum temperature value and the minimum temperature value of the original infrared image;

[0007] Extract the image area corresponding to the high-voltage wall bushing from the original infrared image;

[0008] According to the maximum temperature value, the minimum temperature value and the pixel value in the image area, a temperature distribution map corresponding to the high-voltage wall bushing is constructed;

[0009] According to the temperature distribution diagram, the test results of the high-voltage wall bushing are determined.

[0010] In one embodiment, extracting an image area corresponding to the high-voltage wall bushing from the original infrared image includes:

[0011] According to the placement orientation information of the high-voltage wall bushing in the actual scene and the shooting orientation information corresponding to the original infrared image, the candidate boundary line corresponding to the high-voltage wall bushing in the original infrared image is determined; according to the coordinate data of the candidate boundary line in the original infrared image, the target boundary line of the high-voltage wall bushing in the original infrared image is constructed; according to the target boundary line, the image area corresponding to the high-voltage wall bushing is extracted from the original infrared image.

[0012] In one embodiment, according to the placement orientation information of the high-voltage wall bushing in the actual scene and the shooting orientation information corresponding to the original infrared image, determining the candidate boundary line corresponding to the high-voltage wall bushing in the original infrared image includes:

[0013] According to the placement orientation information of the high-voltage wall bushing in the actual scene and the shooting orientation information corresponding to the original infrared image, the layout angle of the high-voltage wall bushing in the original infrared image is determined; the straight line passing through the central area of ​​the original infrared image is used as the initial boundary line; and the boundary line in the initial boundary line that matches the layout angle is used as the candidate boundary line corresponding to the high-voltage wall bushing in the original infrared image.

[0014] In one embodiment, constructing a target boundary line of the high-voltage wall bushing in the original infrared image according to the coordinate data of the candidate boundary line in the original infrared image includes:

[0015] According to the coordinate data of the candidate boundary line in the original infrared image, the convex hull vertices that can contain the candidate boundary line are constructed; according to the convex hull vertices, the extended boundary line is selected from other boundary lines; wherein the other boundary lines are boundary lines other than the candidate boundary line in the original infrared image; according to the coordinate data of the candidate boundary line in the original infrared image and the coordinate data of the extended boundary line in the original infrared image, the target boundary line of the high-voltage wall bushing in the original infrared image is constructed.

[0016] In one embodiment, constructing a target boundary line of the high-voltage wall bushing in the original infrared image according to the coordinate data of the candidate boundary line in the original infrared image and the coordinate data of the expanded boundary line in the original infrared image includes:

[0017] According to the coordinate data of the candidate boundary line in the original infrared image and the coordinate data of the expanded boundary line in the original infrared image, the boundary center point and the boundary slope are determined; according to the boundary center point, the boundary slope, the coordinate data of the candidate boundary line in the original infrared image, and the coordinate data of the expanded boundary line in the original infrared image, the target boundary line of the high-voltage wall bushing in the original infrared image is constructed.

[0018] In one embodiment, constructing a target boundary line of the high-voltage wall bushing in the original infrared image according to the boundary center point, the boundary slope, the coordinate data of the candidate boundary line in the original infrared image, and the coordinate data of the expanded boundary line in the original infrared image includes:

[0019] According to the boundary center point and the boundary slope, the boundary center line of the high-voltage wall bushing in the original infrared image is determined; according to the coordinate data of the candidate boundary line in the original infrared image, the coordinate data of the expanded boundary line in the original infrared image, and the coordinate data of the boundary center line, the positional relationship between the candidate boundary line and the boundary center line, and the positional relationship between the expanded boundary line and the boundary center line are determined; according to the positional relationship between the candidate boundary line and the boundary center line, the positional relationship between the expanded boundary line and the boundary center line, the coordinate data of the candidate boundary line in the original infrared image, and the coordinate data of the expanded boundary line in the original infrared image, the target boundary line of the high-voltage wall bushing in the original infrared image is constructed.

[0020] In one embodiment, a temperature distribution map corresponding to the high-voltage wall bushing is constructed according to the maximum temperature value, the minimum temperature value and the pixel value in the image area, including:

[0021] Based on the anomaly detection model, the available pixel values ​​in the image area are determined according to the pixel values ​​in the image area; wherein the anomaly detection model includes at least one of a single classification detection model, a local classification detection model and a random forest detection model; and a temperature distribution map corresponding to the high-voltage wall bushing is constructed according to the available pixel values, the maximum temperature value and the minimum temperature value.

[0022] In one embodiment, determining the detection result of the high-voltage wall bushing according to the temperature distribution diagram includes:

[0023] The detection result of the high-voltage wall bushing is determined based on the temperature distribution diagram and the preset temperature threshold.

[0024] In a second aspect, the present application also provides a detection device for a high-voltage wall bushing. The device comprises:

[0025] An acquisition module is used to acquire an original infrared image containing the high-voltage wall bushing, as well as a maximum temperature value and a minimum temperature value of the original infrared image;

[0026] A region extraction module is used to extract the image region corresponding to the high-voltage wall bushing from the original infrared image;

[0027] A construction module is used to construct a temperature distribution map corresponding to the high-voltage wall bushing according to the maximum temperature value, the minimum temperature value and the pixel value in the image area;

[0028] The detection module is used to determine the detection result of the high-voltage wall bushing according to the temperature distribution diagram.

[0029] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0030] Acquire the original infrared image containing the high-voltage wall bushing, as well as the maximum temperature value and the minimum temperature value of the original infrared image;

[0031] Extract the image area corresponding to the high-voltage wall bushing from the original infrared image;

[0032] According to the maximum temperature value, the minimum temperature value and the pixel value in the image area, a temperature distribution map corresponding to the high-voltage wall bushing is constructed;

[0033] Determine the test results of the high-voltage wall bushing based on the temperature distribution diagram.

[0034] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0035] Acquire the original infrared image containing the high-voltage wall bushing, as well as the maximum temperature value and the minimum temperature value of the original infrared image;

[0036] Extract the image area corresponding to the high-voltage wall bushing from the original infrared image;

[0037] According to the maximum temperature value, the minimum temperature value and the pixel value in the image area, a temperature distribution map corresponding to the high-voltage wall bushing is constructed;

[0038] Determine the test results of the high-voltage wall bushing based on the temperature distribution diagram.

[0039] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0040] Acquire the original infrared image containing the high-voltage wall bushing, as well as the maximum temperature value and the minimum temperature value of the original infrared image;

[0041] Extract the image area corresponding to the high-voltage wall bushing from the original infrared image;

[0042] According to the maximum temperature value, the minimum temperature value and the pixel value in the image area, a temperature distribution map corresponding to the high-voltage wall bushing is constructed;

[0043] Determine the test results of the high-voltage wall bushing based on the temperature distribution diagram.

[0044] The above-mentioned detection method, device, computer equipment and storage medium of the high-voltage wall bushing, after extracting the image area corresponding to the high-voltage wall bushing from the original infrared image, constructs a temperature distribution map corresponding to the high-voltage wall bushing according to the maximum temperature value, the minimum temperature value and the pixel value in the image area of ​​the original infrared image, and then determines the detection result of the high-voltage wall bushing according to the temperature distribution map. Compared with the prior art, in which the temperature of the infrared image is used to directly represent the temperature of the high-voltage wall bushing, the above-mentioned method, on the one hand, by extracting the image area corresponding to the high-voltage wall bushing from the original infrared image and constructing the temperature distribution map of the image area, can avoid the other areas in the original infrared image except the area where the high-voltage wall bushing is located from affecting the detection result of the high-voltage wall bushing, thereby ensuring the accuracy of the detection of the high-voltage wall bushing; on the other hand, because the temperature distribution map can characterize the temperature at each position in the image area, it can timely locate the abnormal position when there is an abnormality in the high-voltage wall bushing, thereby ensuring the safety of power transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is an application environment diagram of a method for detecting a high-voltage wall bushing in one embodiment;

[0046] Figure 2A It is a schematic flow chart of a method for detecting a high-voltage wall bushing in one embodiment;

[0047] Figure 2B is a temperature distribution diagram in one embodiment;

[0048] Figure 3 A schematic diagram of a process for determining an image region in one embodiment;

[0049] Figure 4 A schematic diagram of a process for determining a target boundary line in one embodiment;

[0050] Figure 5 A schematic diagram of a flow chart of determining a target boundary line in another embodiment;

[0051] Fig. 6A A schematic diagram of a flow chart of eliminating an interference area in one embodiment;

[0052] Figure 6B is a comparison diagram of an image region before and after abnormality detection in one embodiment;

[0053] Figure 7 It is a schematic flow chart of a method for detecting a high-voltage wall bushing in another embodiment;

[0054] Figure 8 It is a structural block diagram of a detection device for a high-voltage wall bushing in one embodiment;

[0055] Fig. 9 It is a structural block diagram of a detection device for a high-voltage wall bushing in another embodiment;

[0056] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] The detection method of the high-voltage wall bushing provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the mobile detection terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. For example, original infrared image data, etc. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. For example, the server 104 obtains the original infrared image containing the high-voltage wall bushing, as well as the maximum temperature value and the minimum temperature value of the original infrared image through the mobile detection terminal 102, extracts the image area corresponding to the high-voltage wall bushing from the original infrared image, and constructs the temperature distribution map corresponding to the high-voltage wall bushing according to the maximum temperature value, the minimum temperature value and the pixel value in the image area, and determines the detection result of the high-voltage wall bushing according to the temperature distribution map. Among them, the mobile detection terminal 102 can be, but is not limited to, a mobile robot equipped with an infrared device. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0059] As the demand for electric energy increases year by year, in order to facilitate power transmission in complex environments, high-voltage wall bushings can be used to pass through obstacles (e.g., buildings) for power transmission. Therefore, in order to ensure the safety of high-voltage wall bushings, a detection method for high-voltage wall bushings has emerged. The infrared image of the high-voltage wall bushing can be directly obtained by a mobile device (e.g., a mobile robot equipped with an infrared device), and then, based on the temperature reflected by the infrared image, it is determined whether the high-voltage wall bushing is abnormal.

[0060] However, using the current detection method, directly taking the temperature reflected by the infrared image as the temperature of the high-voltage wall bushing will reduce the accuracy of abnormality detection and thus affect the safety of power transmission.

[0061] Based on this, in one embodiment, Figure 2A As shown, a method for detecting a high-voltage wall bushing is provided. Figure 1 The server in the example is used as an example to illustrate the specific steps:

[0062] S201, acquiring an original infrared image containing a high-voltage wall bushing, and a maximum temperature value and a minimum temperature value of the original infrared image.

[0063] The original infrared image refers to the unprocessed infrared image.

[0064] Optionally, the moving path of the mobile detection equipment and the shooting direction corresponding to each high-voltage wall bushing can be pre-set based on the deployment position of each high-voltage wall bushing; then, the mobile detection equipment can collect the original infrared image of each high-voltage wall bushing according to the moving path and the shooting direction, and feed it back to the server.

[0065] Furthermore, after receiving the original infrared image fed back by the mobile detection device, the server can input the original infrared image into a trained temperature model, and the temperature model determines the maximum temperature value and the minimum temperature value of the original infrared image based on the original infrared image and model parameters.

[0066] S202, extracting the image area corresponding to the high-voltage wall bushing from the original infrared image.

[0067] The image area refers to the area of ​​the high-voltage wall bushing in the original infrared image.

[0068] Optionally, in order to ensure the accuracy of determining the image area, straight line information in the original infrared image may be extracted first; then, based on the straight line information in the original infrared image, the image area corresponding to the high-voltage wall bushing may be extracted from the original infrared image.

[0069] Exemplarily, the original infrared image can be converted into a grayscale image, and Gaussian denoising is used to perform a denoising operation on the grayscale image corresponding to the original infrared image to obtain a first infrared image after denoising; then, the first infrared image is contour processed to obtain a contour map of the first infrared image, and the contour map of the first infrared image is sharpened by upper and lower threshold filtering to obtain a second infrared image. For example, pixel values ​​less than 40 in the first infrared image can be set to 0, and pixel values ​​greater than 45 can be set to 255; finally, a line extraction algorithm (Line Segment Detector) and a Hough transform (HoughLines) algorithm are used to extract straight line information in the second infrared image to determine the straight line information in the original infrared image.

[0070] S203: construct a temperature distribution map corresponding to the high-voltage wall bushing according to the maximum temperature value, the minimum temperature value and the pixel values ​​in the image area.

[0071] The temperature distribution map is used to characterize the temperature distribution corresponding to the image area.

[0072] Optionally, in order to make the temperature distribution map represent the temperature conditions in the image area in more detail, after determining the image area corresponding to the high-voltage wall bushing, the maximum temperature value, the minimum temperature value and the pixel value in the image area can be simultaneously input into a trained distribution map construction model. The distribution map construction model constructs a temperature distribution map corresponding to the high-voltage wall bushing based on the maximum temperature value, the minimum temperature value, the pixel value in the image area and the model parameters.

[0073] The distribution map construction model is a trained neural network. In the process of constructing the temperature distribution map, the image area will be evenly divided into multiple areas to be detected in advance; then, for each area to be detected, the average temperature of the area to be detected can be determined based on the maximum temperature value and the minimum temperature value, as well as the pixel value in the area to be detected.

[0074] For example, refer to Figure 2B It can be seen that the distribution map construction model evenly divides the image area into 20 areas to be detected, and marks the areas to be detected with regional codes in the order from left to right and then from top to bottom to obtain a regional division map, wherein the area to be detected in the upper left corner of the image area is area to be detected 1, and the area to be detected in the lower right corner is area to be detected 20; accordingly, the average temperature corresponding to each area to be detected can be output in the order from left to right and then from top to bottom. At this time, the regional division map and the temperature output results are spliced ​​to construct the temperature distribution map corresponding to the high-voltage wall bushing.

[0075] S204, determining the detection result of the high-voltage wall bushing according to the temperature distribution diagram.

[0076] Optionally, after determining the temperature distribution map corresponding to the high-voltage wall bushing, the detection result of the high-voltage wall bushing can be determined according to the average temperature of each area to be detected in the temperature distribution map. Exemplarily, the detection result of the high-voltage wall bushing is determined according to the temperature distribution map and a preset temperature threshold. The preset temperature threshold is a value used to measure whether the temperature of the high-voltage wall bushing is abnormal.

[0077] Optionally, for each area to be detected, the average temperature of the area to be detected can be compared with a preset high temperature threshold to obtain a first detection result. Exemplarily, if the average temperature of the area to be detected is greater than the high temperature threshold, it is determined that the area to be detected is abnormal; if the average temperature of the area to be detected is less than or equal to the high temperature threshold, it is determined that the area to be detected is normal.

[0078] Furthermore, for each high-voltage wall bushing, the average temperatures of the areas to be detected in the high-voltage wall bushing can be sorted according to the size relationship. After determining the maximum area temperature and the minimum area temperature in each area to be detected in the high-voltage wall bushing, the maximum temperature difference of the high-voltage wall bushing can be determined according to the maximum area temperature and the minimum area temperature; then, the maximum temperature difference can be compared with the temperature difference threshold to obtain a second detection result. Exemplarily, if the maximum temperature difference is greater than the temperature difference threshold, it is determined that the high-voltage wall bushing is abnormal; if the maximum temperature difference is less than or equal to the temperature difference threshold, it is determined that the high-voltage wall bushing is normal.

[0079] Optionally, the detection result of the high-voltage wall bushing can be determined based on the first detection result and the second detection result. For example, if both the first detection result and the second detection result are normal, the detection result of the high-voltage wall bushing is normal; if there is a detection abnormality in the first detection result or the second detection result, the detection result of the high-voltage wall bushing is abnormal; then, feedback is provided to the operation and maintenance personnel based on the detection result of the high-voltage wall bushing.

[0080] For example, continue to refer to Figure 2B It can be seen that if the temperature threshold is 18.9, the detection results of the detection area 10 and the detection area 20 are abnormal, and the detection results of other detection areas are normal. At this time, the detection result of the high-voltage wall bushing is that the bushing is abnormal. At the same time, the position information and temperature information of the detection area 10 and the detection area 20 will be fed back to the operation and maintenance personnel for the operation and maintenance personnel to handle the exception.

[0081] Alternatively, the average temperature of the area to be detected 4 is the minimum average temperature of 18.0, and the average temperature of the area to be detected 10 is the minimum average temperature of 19.1. If the temperature difference threshold is 1.0, the detection result of the high-voltage wall bushing is that the bushing is abnormal. At the same time, the information that the temperature difference between the area to be detected 4 and the area to be detected 10 is too large will be fed back to the operation and maintenance personnel for the operation and maintenance personnel to handle the abnormality.

[0082] In the above-mentioned detection method of high-voltage wall bushing, after extracting the image area corresponding to the high-voltage wall bushing from the original infrared image, a temperature distribution map corresponding to the high-voltage wall bushing is constructed according to the maximum temperature value, the minimum temperature value and the pixel value in the image area of ​​the original infrared image, and then the detection result of the high-voltage wall bushing is determined according to the temperature distribution map. Compared with the prior art, in which the temperature of the infrared image is directly used to represent the temperature of the high-voltage wall bushing, the above-mentioned method, on the one hand, by extracting the image area corresponding to the high-voltage wall bushing from the original infrared image and constructing the temperature distribution map of the image area, can avoid the other areas in the original infrared image except the area where the high-voltage wall bushing is located from affecting the detection result of the high-voltage wall bushing, thereby ensuring the accuracy of the detection of the high-voltage wall bushing; on the other hand, because the temperature distribution map can characterize the temperature at each position in the image area, it can timely locate the abnormal position when there is an abnormality in the high-voltage wall bushing, thereby ensuring the safety of power transmission.

[0083] In order to ensure the accuracy of image region determination, based on the above embodiments, in this embodiment, an optional method for determining an image region is provided, such as Figure 3 As shown, the specific steps include:

[0084] S301, determining a candidate boundary line corresponding to the high-voltage wall bushing in the original infrared image according to the placement orientation information of the high-voltage wall bushing in the actual scene and the shooting orientation information corresponding to the original infrared image.

[0085] Among them, placement orientation information refers to information related to the placement orientation of the high-voltage wall bushing, which may include placement direction and placement angle; shooting orientation information refers to shooting information of the mobile detection device when shooting the original infrared image, which may include shooting angle; boundary line refers to the line used to characterize the contours of each device in the original infrared image; candidate boundary line is used to characterize the boundary line that may be the contour of the high-voltage wall bushing.

[0086] Optionally, after contouring the original infrared image and determining the straight line information of the original infrared image, the placement orientation information of the high-voltage wall bushing in the actual scene and the shooting orientation information corresponding to the original infrared image can be input into the boundary line determination model at the same time. The boundary line determination model determines the candidate boundary line corresponding to the high-voltage wall bushing from the straight line information of the original infrared image based on the placement orientation information, shooting orientation information and model parameters.

[0087] Alternatively, the following steps may be used to determine the candidate boundary line corresponding to the high-voltage wall bushing.

[0088] The first step is to determine the arrangement angle of the high-voltage wall bushing in the original infrared image according to the placement orientation information of the high-voltage wall bushing in the actual scene and the shooting orientation information corresponding to the original infrared image.

[0089] Optionally, based on a preset angle calculation formula, the placement orientation information of the high-voltage wall bushing in the actual scene and the shooting orientation information corresponding to the original infrared image can be substituted into the preset angle calculation formula to determine the layout angle of the high-voltage wall bushing in the original infrared image.

[0090] In the second step, a straight line passing through the central area of ​​the original infrared image is used as an initial boundary line.

[0091] It is understandable that since the mobile detection device will adjust the high-voltage wall bushing to the central area of ​​the original infrared image when photographing it, the straight line passing through the central area of ​​the original infrared image can be used as the initial boundary line.

[0092] In the third step, the boundary lines in the initial boundary lines that match the arrangement angle are used as candidate boundary lines corresponding to the high-voltage wall bushing in the original infrared image.

[0093] Optionally, for each initial boundary line, the angle of the initial boundary line may be compared with the layout angle. If the angle of the initial boundary line is the same as the layout angle, the initial boundary line is used as a candidate boundary line corresponding to the high-voltage wall bushing in the original infrared image.

[0094] It can be understood that in order to ensure the accuracy of the candidate boundary line determination, for each initial boundary line, the angle of the initial boundary line can be compared with the angle range of the layout angle. If the angle of the initial boundary line is within the angle range, the initial boundary line is used as the candidate boundary line corresponding to the high-voltage wall bushing in the original infrared image. For example, if the layout angle is 45 degrees, 40 degrees to 50 degrees can be used as the angle range.

[0095] S302: constructing a target boundary line of the high-voltage wall bushing in the original infrared image according to the coordinate data of the candidate boundary line in the original infrared image.

[0096] Optionally, the coordinate data of the candidate boundary line in the original infrared image can be simultaneously input into the first boundary line construction model, and the first boundary line construction model constructs the target boundary line of the high-voltage wall bushing in the original infrared image based on the coordinate data of the candidate boundary line in the original infrared image.

[0097] S303, extracting the image area corresponding to the high-voltage wall bushing from the original infrared image according to the target boundary line.

[0098] Optionally, after the target boundary line is determined, the image area corresponding to the high-voltage wall bushing may be directly extracted from the original infrared image according to the coordinate data of the target boundary line in the original infrared image.

[0099] In this embodiment, candidate boundary lines are introduced, and according to the coordinate data of the candidate boundary lines, the target boundary lines of the high-voltage wall bushings in the original infrared image are constructed, and then the image area is determined, which can ensure the accuracy of the image area determination.

[0100] In order to ensure the accuracy of the target boundary line determination, based on the above embodiment, in this embodiment, an optional method for determining the target boundary line is provided, such as Figure 4 As shown, the specific steps include:

[0101] S401, constructing convex hull vertices that can contain the candidate boundary line according to the coordinate data of the candidate boundary line in the original infrared image.

[0102] Optionally, in order to avoid missing an initial boundary line related to a target boundary line, convex hull vertices that can contain the candidate boundary line may be pre-constructed according to coordinate data of the candidate boundary line in the original infrared image.

[0103] S402: Select an extended boundary line from other boundary lines according to the convex hull vertices.

[0104] Among them, other boundary lines are boundary lines other than candidate boundary lines in the original infrared image; and expanded boundary lines refer to boundary lines other than candidate boundary lines that are screened out and used to construct target boundary lines.

[0105] Optionally, after constructing the convex hull vertex, other boundary lines located near the convex hull vertex can be used as extended boundary lines. Exemplarily, for each other boundary line, the minimum distance between the other boundary line and the convex hull vertex can be compared with a preset distance threshold, and if the minimum distance between the other boundary line and the convex hull vertex is less than the distance threshold, the other boundary line is used as an extended boundary line.

[0106] S403, constructing a target boundary line of the high-voltage wall bushing in the original infrared image according to the coordinate data of the candidate boundary line in the original infrared image and the coordinate data of the expanded boundary line in the original infrared image.

[0107] Optionally, the coordinate data of the selected boundary line in the original infrared image and the coordinate data of the expanded boundary line in the original infrared image can be input into the second boundary line construction model at the same time. The second boundary line construction model constructs the target boundary line of the high-voltage wall bushing in the original infrared image based on the coordinate data of the candidate boundary line in the original infrared image, the coordinate data of the expanded boundary line in the original infrared image and the model parameters.

[0108] Alternatively, the boundary center point and boundary slope can be determined based on the coordinate data of the candidate boundary line in the original infrared image and the coordinate data of the expanded boundary line in the original infrared image; then, the target boundary line of the high-voltage wall bushing in the original infrared image is constructed based on the boundary center point, the boundary slope, the coordinate data of the candidate boundary line in the original infrared image, and the coordinate data of the expanded boundary line in the original infrared image.

[0109] The boundary center point is used to represent the center point of the candidate boundary line and the expanded boundary line; the boundary slope is used to represent the average slope of the candidate boundary line and the expanded boundary line.

[0110] Optionally, after determining the candidate boundary line and the expanded boundary line, the boundary center point and the boundary slope may be calculated based on the coordinate data of the candidate boundary line in the original infrared image and the coordinate data of the expanded boundary line in the original infrared image.

[0111] Furthermore, the coordinate data of the boundary center point, the boundary slope, the candidate boundary line in the original infrared image, and the coordinate data of the expanded boundary line in the original infrared image can be simultaneously input into a trained third boundary line construction model. The third boundary line construction model constructs the target boundary line of the high-voltage wall bushing in the original infrared image based on the boundary center point, the boundary slope, the coordinate data of the candidate boundary line, the coordinate data of the expanded boundary line, and the model parameters.

[0112] In this embodiment, an extended boundary line is introduced, and a target boundary line is determined according to the candidate boundary line and the extended boundary line, so that the accuracy of determining the target boundary line can be ensured.

[0113] In order to ensure the accuracy of the target boundary line determination, based on the above embodiment, in this embodiment, another optional method for determining the target boundary line is provided, such as Figure 5 As shown, the specific steps include:

[0114] S501, determining a boundary center line of the high-voltage wall bushing in the original infrared image according to the boundary center point and the boundary slope.

[0115] Optionally, after the boundary center point and the boundary slope are determined, a boundary center line of the high-voltage wall bushing in the original infrared image may be constructed according to the boundary center point and the boundary slope.

[0116] S502, determining the positional relationship between the candidate boundary line and the boundary center line, and the positional relationship between the expanded boundary line and the boundary center line based on the coordinate data of the candidate boundary line in the original infrared image, the coordinate data of the expanded boundary line in the original infrared image, and the coordinate data of the boundary center line.

[0117] Optionally, the coordinate data of the candidate boundary line in the original infrared image and the coordinate data of the expanded boundary line in the original infrared image can be compared with the coordinate data of the boundary center line, respectively, to determine the positional relationship between the candidate boundary line and the boundary center line, as well as the positional relationship between the expanded boundary line and the boundary center line.

[0118] S503, constructing the target boundary line of the high-voltage wall bushing in the original infrared image according to the positional relationship between the candidate boundary line and the boundary center line, the positional relationship between the expanded boundary line and the boundary center line, the coordinate data of the candidate boundary line in the original infrared image, and the coordinate data of the expanded boundary line in the original infrared image.

[0119] Optionally, the endpoints of the target boundary line can be determined from the coordinate data of the candidate boundary line in the original infrared image and the coordinate data of the expanded boundary line in the original infrared image based on the positional relationship between the candidate boundary line and the boundary center line, and the positional relationship between the expanded boundary line and the boundary center line, thereby constructing the target boundary line of the high-voltage wall bushing in the original infrared image.

[0120] It is understandable that, since some line segments may be removed as noise when extracting the straight line information of the initial infrared image, in order to ensure the accuracy of the target boundary line, after the target boundary line is determined, the target boundary line can be completed based on the coordinate data of the two target boundary lines in the original infrared image and the lengths of the two target boundary lines, and then the completed target boundary line can be determined.

[0121] In this embodiment, a boundary center line is introduced, and a target boundary line of the high-voltage wall bushing in the original infrared image is constructed based on the boundary center line, which can ensure the accuracy of determining the target boundary line.

[0122] Since the original infrared image directly obtained by the mobile detection device may have some interference areas, in order to ensure the accuracy of the temperature distribution map, based on the above embodiment, in this embodiment, Fig. 6A As shown, an optional method for eliminating the interference area is provided, which specifically includes the following steps:

[0123] S601, based on an anomaly detection model, determine available pixel values ​​in the image area according to pixel values ​​in the image area.

[0124] Among them, the anomaly detection model includes at least one of a single classification (One Class SVM) detection model, a local classification (LocalOutlier Factor) detection model and a random forest (Isolation_Forest) detection model.

[0125] It is understandable that due to the presence of an umbrella skirt structure in the high-voltage wall bushing, that is, the surface of the high-voltage wall bushing is not flat, and the infrared radiation emission varies at different angles, the original infrared image acquired by the mobile detection device will have some interference areas. At this time, if the temperature distribution map is directly constructed based on the original infrared image, it is easy to cause problems such as large temperature differences between the areas to be detected, thereby triggering an abnormal alarm and reducing the accuracy of the temperature distribution map. Moreover, since the number and distribution of interference areas depend on unstable factors such as the angle, distance, and environment during shooting, using fixed parameters to denoise the interference area will reduce the accuracy of the denoising process.

[0126] Based on this, after determining the image area, the convolution processing method can be used to convert the pixel values ​​in the image area into a data sequence; then, the data sequence is input into the trained anomaly detection model, and the anomaly detection model determines whether the data sequence is normal based on the data sequence and model parameters, and then determines the available pixel values ​​in the image area.

[0127] It can be understood that, when there are multiple anomaly detection models, if the detection result of a certain anomaly detection model is that the data sequence is abnormal, then the pixel value corresponding to the data sequence is the abnormal pixel value; if the detection results of all anomaly detection models are that the data sequence is normal, then the pixel value corresponding to the data sequence is the available pixel value.

[0128] Exemplarily, a 2*2 convolution kernel is used to slide and extract pixel values ​​in the image area, which not only retains the local phenomenon but also better distinguishes the low-temperature area generated by the casing shed structure; then, the extracted pixel values ​​are converted into a data sequence.

[0129] Furthermore, for each data sequence, the data sequence can be input into a single classification detection model, a local classification detection model, and a random forest detection model, respectively. When the output results of the single classification detection model, the local classification detection model, and the random forest detection model are all normal, the pixel value corresponding to the data sequence is determined to be an available pixel value, and the abnormal pixel value is removed. For example, Figure 6B This is a comparison chart of the image area after abnormality detection. The image area at the top is the pixel distribution corresponding to the original image area that has not been detected for abnormalities, and the image area at the bottom is the pixel distribution corresponding to the image area after abnormality detection. The black part is the abnormal pixel that has been removed.

[0130] S602: Construct a temperature distribution map corresponding to the high-voltage wall bushing according to the available pixel values, the maximum temperature value, and the minimum temperature value.

[0131] Optionally, after determining the available pixel value, the temperature corresponding to the available pixel value can be determined based on the available pixel value, the maximum temperature value and the minimum temperature value; then, for each area to be detected, the average value of the temperatures corresponding to all available pixel values ​​in the area to be detected can be used as the temperature value of the area to be detected, thereby constructing a temperature distribution map corresponding to the high-voltage wall bushing.

[0132] In this embodiment, the available pixel values ​​in the image area are determined by the anomaly detection model, so that the interference area in the image area can be accurately removed, thereby eliminating the influence of the interference area on the temperature distribution map, thereby ensuring the accuracy of the temperature distribution map.

[0133] Figure 7 FIG. 1 is a flow chart of a method for detecting a high-voltage wall bushing in another embodiment. Based on the above embodiment, this embodiment provides an optional example of a method for detecting a high-voltage wall bushing. Figure 7 The specific implementation process is as follows:

[0134] S701, acquiring an original infrared image including the high-voltage wall bushing, and a maximum temperature value and a minimum temperature value of the original infrared image.

[0135] S702: Determine the arrangement angle of the high-voltage wall bushing in the original infrared image according to the placement orientation information of the high-voltage wall bushing in the actual scene and the shooting orientation information corresponding to the original infrared image.

[0136] S703: taking a straight line in the original infrared image that passes through the central area of ​​the original infrared image as an initial boundary line.

[0137] S704: Use the boundary lines in the initial boundary lines that match the arrangement angle as candidate boundary lines corresponding to the high-voltage wall bushing in the original infrared image.

[0138] S705 , constructing convex hull vertices that can contain the candidate boundary line according to the coordinate data of the candidate boundary line in the original infrared image.

[0139] S706: Select an extended boundary line from other boundary lines according to the convex hull vertices.

[0140] The other boundary lines are boundary lines other than the candidate boundary lines in the original infrared image.

[0141] S707, determining the boundary center point and the boundary slope according to the coordinate data of the candidate boundary line in the original infrared image and the coordinate data of the expanded boundary line in the original infrared image.

[0142] S708, constructing a target boundary line of the high-voltage wall bushing in the original infrared image according to the boundary center point, the boundary slope, the coordinate data of the candidate boundary line in the original infrared image, and the coordinate data of the expanded boundary line in the original infrared image.

[0143] Optionally, the boundary center line of the high-voltage wall bushing in the original infrared image can be determined based on the boundary center point and the boundary slope; the positional relationship between the candidate boundary line and the boundary center line, and the positional relationship between the expanded boundary line and the boundary center line can be determined based on the coordinate data of the candidate boundary line in the original infrared image, the coordinate data of the expanded boundary line in the original infrared image, and the coordinate data of the boundary center line; the target boundary line of the high-voltage wall bushing in the original infrared image is constructed based on the positional relationship between the candidate boundary line and the boundary center line, the positional relationship between the expanded boundary line and the boundary center line, the coordinate data of the candidate boundary line in the original infrared image, and the coordinate data of the expanded boundary line in the original infrared image.

[0144] S709, extracting an image area corresponding to the high-voltage wall bushing from the original infrared image according to the target boundary line.

[0145] S710, based on the anomaly detection model, determine the available pixel values ​​in the image area according to the pixel values ​​in the image area.

[0146] Among them, the anomaly detection model includes at least one of a single classification detection model, a local classification detection model and a random forest detection model.

[0147] S711, constructing a temperature distribution map corresponding to the high-voltage wall bushing according to the available pixel values, the maximum temperature value, and the minimum temperature value.

[0148] S712: Determine the detection result of the high-voltage wall bushing according to the temperature distribution diagram and the preset temperature threshold.

[0149] The specific process of S701-S712 above can refer to the description of the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0150] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0151] Based on the same inventive concept, the embodiment of the present application also provides a high-voltage wall bushing detection device for implementing the high-voltage wall bushing detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more high-voltage wall bushing detection devices provided below can refer to the limitations of the high-voltage wall bushing detection method above, and will not be repeated here.

[0152] In one embodiment, Figure 8 As shown, a high-voltage wall bushing detection device 1 is provided, comprising: an acquisition module 10, a region extraction module 20, a construction module 30 and a detection module 40, wherein:

[0153] An acquisition module 10 is used to acquire an original infrared image containing the high-voltage wall bushing, as well as a maximum temperature value and a minimum temperature value of the original infrared image;

[0154] A region extraction module 20, used to extract an image region corresponding to the high-voltage wall bushing from the original infrared image;

[0155] A construction module 30, for constructing a temperature distribution map corresponding to the high-voltage wall bushing according to the maximum temperature value, the minimum temperature value and the pixel values ​​in the image area;

[0156] The detection module 40 is used to determine the detection result of the high-voltage wall bushing according to the temperature distribution diagram.

[0157] In one embodiment, Fig. 9 As shown, the region extraction module 20 includes:

[0158] A first determining unit 21 is used to determine a candidate boundary line corresponding to the high-voltage wall bushing in the original infrared image according to the placement orientation information of the high-voltage wall bushing in the actual scene and the shooting orientation information corresponding to the original infrared image;

[0159] A second determining unit 22, configured to construct a target boundary line of the high-voltage wall bushing in the original infrared image according to the coordinate data of the candidate boundary line in the original infrared image;

[0160] The region extraction unit 23 is used to extract the image region corresponding to the high-voltage wall bushing from the original infrared image according to the target boundary line.

[0161] In one embodiment, the first determining unit 21 is specifically configured to:

[0162] According to the placement orientation information of the high-voltage wall bushing in the actual scene and the shooting orientation information corresponding to the original infrared image, the layout angle of the high-voltage wall bushing in the original infrared image is determined; the straight line passing through the central area of ​​the original infrared image is used as the initial boundary line; and the boundary line in the initial boundary line that matches the layout angle is used as the candidate boundary line corresponding to the high-voltage wall bushing in the original infrared image.

[0163] In one embodiment, the second determining unit 22 includes:

[0164] A first construction subunit is used to construct convex hull vertices that can contain the candidate boundary line according to the coordinate data of the candidate boundary line in the original infrared image;

[0165] A selection subunit is used to select an extended boundary line from other boundary lines according to the convex hull vertices; wherein the other boundary lines are boundary lines other than the candidate boundary lines in the original infrared image;

[0166] The second construction subunit is used to construct the target boundary line of the high-voltage wall bushing in the original infrared image according to the coordinate data of the candidate boundary line in the original infrared image and the coordinate data of the expanded boundary line in the original infrared image.

[0167] In one embodiment, the second construction subunit is specifically used for:

[0168] According to the coordinate data of the candidate boundary line in the original infrared image and the coordinate data of the expanded boundary line in the original infrared image, the boundary center point and the boundary slope are determined; according to the boundary center point, the boundary slope, the coordinate data of the candidate boundary line in the original infrared image, and the coordinate data of the expanded boundary line in the original infrared image, the target boundary line of the high-voltage wall bushing in the original infrared image is constructed.

[0169] In one embodiment, the second construction subunit is further used for:

[0170] According to the boundary center point and the boundary slope, the boundary center line of the high-voltage wall bushing in the original infrared image is determined; according to the coordinate data of the candidate boundary line in the original infrared image, the coordinate data of the expanded boundary line in the original infrared image, and the coordinate data of the boundary center line, the positional relationship between the candidate boundary line and the boundary center line, and the positional relationship between the expanded boundary line and the boundary center line are determined; according to the positional relationship between the candidate boundary line and the boundary center line, the positional relationship between the expanded boundary line and the boundary center line, the coordinate data of the candidate boundary line in the original infrared image, and the coordinate data of the expanded boundary line in the original infrared image, the target boundary line of the high-voltage wall bushing in the original infrared image is constructed.

[0171] In one embodiment, the building module 30 is specifically used to:

[0172] Based on the anomaly detection model, the available pixel values ​​in the image area are determined according to the pixel values ​​in the image area; wherein the anomaly detection model includes at least one of a single classification detection model, a local classification detection model and a random forest detection model; and a temperature distribution map corresponding to the high-voltage wall bushing is constructed according to the available pixel values, the maximum temperature value and the minimum temperature value.

[0173] In one embodiment, the detection module 40 is specifically used for:

[0174] The detection result of the high-voltage wall bushing is determined based on the temperature distribution diagram and the preset temperature threshold.

[0175] Each module in the above-mentioned high-voltage wall bushing detection device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0176] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig.10As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store raw infrared image data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for detecting a high-voltage wall bushing is implemented.

[0177] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0178] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0179] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0180] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0181] It should be noted that the data involved in this application (including but not limited to original infrared image data, etc.) are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0182] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0183] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0184] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for detecting a high-voltage wall bushing, characterized in that: The method comprises: Acquire an original infrared image containing the high-voltage wall bushing, and a maximum temperature value and a minimum temperature value of the original infrared image; Determine the arrangement angle of the high-voltage wall bushing in the original infrared image according to the placement orientation information of the high-voltage wall bushing in the actual scene and the shooting orientation information corresponding to the original infrared image; Taking a straight line in the original infrared image that passes through the central area of ​​the original infrared image as an initial boundary line; Using the boundary line in the initial boundary line that matches the arrangement angle as a candidate boundary line corresponding to the high-voltage wall bushing in the original infrared image; Constructing a target boundary line of the high-voltage wall bushing in the original infrared image according to the coordinate data of the candidate boundary line in the original infrared image; According to the target boundary line, extracting an image area corresponding to the high-voltage wall bushing from the original infrared image; Constructing a temperature distribution map corresponding to the high-voltage wall bushing according to the maximum temperature value, the minimum temperature value and the pixel values ​​in the image area; According to the temperature distribution diagram, the detection result of the high-voltage wall bushing is determined.

2. The method according to claim 1, characterized in that The step of constructing a target boundary line of the high-voltage wall bushing in the original infrared image according to the coordinate data of the candidate boundary line in the original infrared image includes: Constructing convex hull vertices that can contain the candidate boundary line according to the coordinate data of the candidate boundary line in the original infrared image; According to the convex hull vertices, an extended boundary line is selected from other boundary lines; wherein the other boundary lines are boundary lines in the original infrared image other than the candidate boundary lines; A target boundary line of the high-voltage wall bushing in the original infrared image is constructed according to the coordinate data of the candidate boundary line in the original infrared image and the coordinate data of the expanded boundary line in the original infrared image.

3. The method according to claim 2, characterized in that The step of constructing a target boundary line of the high-voltage wall bushing in the original infrared image according to the coordinate data of the candidate boundary line in the original infrared image and the coordinate data of the expanded boundary line in the original infrared image comprises: Determine a boundary center point and a boundary slope according to the coordinate data of the candidate boundary line in the original infrared image and the coordinate data of the expanded boundary line in the original infrared image; The target boundary line of the high-voltage wall bushing in the original infrared image is constructed according to the boundary center point, the boundary slope, the coordinate data of the candidate boundary line in the original infrared image, and the coordinate data of the expanded boundary line in the original infrared image.

4. The method according to claim 3, characterized in that The step of constructing a target boundary line of the high-voltage wall bushing in the original infrared image according to the boundary center point, the boundary slope, the coordinate data of the candidate boundary line in the original infrared image, and the coordinate data of the expanded boundary line in the original infrared image includes: Determine the boundary center line of the high-voltage wall bushing in the original infrared image according to the boundary center point and the boundary slope; Determine the positional relationship between the candidate boundary line and the boundary center line, and the positional relationship between the expanded boundary line and the boundary center line according to the coordinate data of the candidate boundary line in the original infrared image, the coordinate data of the expanded boundary line in the original infrared image, and the coordinate data of the boundary center line; According to the positional relationship between the candidate boundary line and the boundary center line, the positional relationship between the expanded boundary line and the boundary center line, the coordinate data of the candidate boundary line in the original infrared image, and the coordinate data of the expanded boundary line in the original infrared image, the target boundary line of the high-voltage wall bushing in the original infrared image is constructed.

5. The method according to claim 1, characterized in that The step of constructing a temperature distribution map corresponding to the high-voltage wall bushing according to the maximum temperature value, the minimum temperature value and the pixel values ​​in the image area includes: Based on the anomaly detection model, determining the available pixel values ​​in the image area according to the pixel values ​​in the image area; wherein the anomaly detection model includes at least one of a single classification detection model, a local classification detection model and a random forest detection model; A temperature distribution map corresponding to the high-voltage wall bushing is constructed according to the available pixel values, the maximum temperature value, and the minimum temperature value.

6. The method according to claim 1, characterized in that Determining the detection result of the high-voltage wall bushing according to the temperature distribution diagram includes: The detection result of the high-voltage wall bushing is determined according to the temperature distribution diagram and a preset temperature threshold.

7. A detection device for a high-voltage wall bushing, characterized in that: The device comprises: An acquisition module, used to acquire an original infrared image containing the high-voltage wall bushing, and a maximum temperature value and a minimum temperature value of the original infrared image; A region extraction module is used to determine the arrangement angle of the high-voltage wall bushing in the original infrared image according to the placement orientation information of the high-voltage wall bushing in the actual scene and the shooting orientation information corresponding to the original infrared image; take the straight line in the original infrared image that passes through the central area of ​​the original infrared image as the initial boundary line; take the boundary line in the initial boundary line that matches the arrangement angle as the candidate boundary line corresponding to the high-voltage wall bushing in the original infrared image; construct the target boundary line of the high-voltage wall bushing in the original infrared image according to the coordinate data of the candidate boundary line in the original infrared image; and extract the image area corresponding to the high-voltage wall bushing from the original infrared image according to the target boundary line; A construction module, used to construct a temperature distribution map corresponding to the high-voltage wall bushing according to the maximum temperature value, the minimum temperature value and the pixel values ​​in the image area; A detection module is used to determine the detection result of the high-voltage wall bushing according to the temperature distribution diagram.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images