Insulator detection method, device and equipment and storage medium

Abstract

The invention discloses an insulator detection method, device and equipment and a storage medium, and the method comprises the steps: carrying out the target detection of an infrared thermal image of an insulator chain, obtaining the actual detection information of the insulator chain, and enabling the actual detection information to comprise the actual detection region of each insulator in the insulator chain, configuration detection information corresponding to the insulator string is obtained, the configuration detection information comprises a configuration detection area of each insulator, the actual detection area is adjusted according to the configuration detection area, the adjusted actual detection area is obtained, and whether the temperature of each insulator is abnormal or not is detected based on the adjusted actual detection area; the actual detection information is rechecked through the configuration detection information corresponding to the insulator string, so that the actual detection information can be adjusted when visual angle deviation or inaccurate algorithm detection occurs, and the accuracy of insulator detection can be improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to an insulator detection method, device, equipment and storage medium. Background Art

[0002] At present, a thermal imaging PTZ camera (i.e., a Pan-Tilt-Zoom camera, in which the direction (horizontal rotation Pan), pitch angle (vertical tilt Tilt) and zoom (Zoom) of the camera are adjustable) is usually used to detect the temperature of the insulator.

[0003] However, the viewing angle of the device in the related insulator detection method will be offset before and after the thermal imaging PTZ camera moves (for example, when the thermal imaging PTZ camera is used to detect three-phase insulator strings, the A-phase insulator string is at preset point 1, the B-phase insulator string is at preset point 2, and the C-phase insulator string is at preset point 3. The camera collects infrared thermal images of each phase insulator string in a loop by rotating the camera, and the rotating camera will cause the viewing angle to shift. For example, the viewing angle of the camera when shooting the A-phase insulator this time may be different from the viewing angle of the camera when shooting the A-phase insulator last time due to the viewing angle shift caused by the rotation of the camera), and the related insulator recognition algorithm also has the problem of inaccurate insulator detection (such as false detection and missed detection), which leads to inaccurate insulator detection results. Summary of the invention

[0004] The main purpose of the present application is to provide an insulator detection method, device, equipment and storage medium, aiming to solve the technical problem that the insulator detection results are inaccurate when the camera angle of view is offset or the algorithm detection is inaccurate in the related insulator detection method.

[0005] To achieve the above object, the present application provides an insulator detection method, the insulator detection method comprising:

[0006] Performing target detection on the infrared thermal imaging image of the insulator string to obtain actual detection information of the insulator string, wherein the actual detection information includes the actual detection area of ​​each insulator in the insulator string;

[0007] Acquire configuration detection information corresponding to the insulator string, wherein the configuration detection information includes a configuration detection area of ​​each insulator;

[0008] adjusting the actual detection area according to the configured detection area to obtain an adjusted actual detection area;

[0009] Based on the adjusted actual detection area, it is detected whether the insulators have temperature abnormality.

[0010] Optionally, the actual detection information further includes the number of actually detected insulators, and the configured detection information further includes the number of configured insulators; and adjusting the actual detection area according to the configured detection area to obtain the adjusted actual detection area includes:

[0011] Detecting whether the number of insulators actually detected is consistent with the number of configured insulators;

[0012] If the number of insulators actually detected is inconsistent with the number of configured insulators, the actual detection area is adjusted according to the configured detection area to obtain an adjusted actual detection area.

[0013] Optionally, the actual detection information further includes an actual detection area corresponding to the insulator string, and the configuration detection information includes a configuration detection area corresponding to the insulator string;

[0014] If the number of actually detected insulators is inconsistent with the number of configured insulators, the actual detection area is adjusted according to the configured detection area, and before obtaining the adjusted actual detection area, the method further includes:

[0015] Calculating a coordinate mapping relationship according to the center point coordinates of the actual detection area and the center point coordinates of the configured detection area;

[0016] If the number of actually detected insulators is inconsistent with the number of configured insulators, adjusting the actual detection area according to the configured detection area to obtain the adjusted actual detection area includes:

[0017] If the number of insulators actually detected is inconsistent with the number of configured insulators, the actual detection area is adjusted according to the coordinate mapping relationship and the configured detection area to obtain an adjusted actual detection area.

[0018] Optionally, the actual detection information further includes an actual order of each insulator, and the configuration detection information further includes a configuration order of each insulator; if the number of the actually detected insulators is inconsistent with the number of configured insulators, adjusting the actual detection area according to the coordinate mapping relationship and the configured detection area to obtain the adjusted actual detection area includes:

[0019] If the number of actually detected insulators is greater than the number of configured insulators, and the actual order is different from the configured order, the tail insulator is determined according to the actual order, and the actual detection area corresponding to the tail insulator is deleted;

[0020] Determine whether the actual detection area and the configured detection area satisfy the coordinate mapping relationship, and delete the actual detection area that does not satisfy the coordinate mapping relationship;

[0021] After the deletion is completed, the deleted actual detection areas are reordered to obtain the adjusted actual detection areas.

[0022] Optionally, the actual detection information further includes an actual order of each insulator, and the configuration detection information further includes a configuration order of each insulator; if the number of the actually detected insulators is inconsistent with the number of configured insulators, adjusting the actual detection area according to the coordinate mapping relationship and the configured detection area to obtain the adjusted actual detection area includes:

[0023] If the number of actually detected insulators is greater than the number of configured insulators, and the actual order is the same as the configured order, then deleting the actual detection area that is not within the actual detection area;

[0024] Determine whether the actual detection area and the configured detection area satisfy the coordinate mapping relationship, and delete the actual detection area that does not satisfy the coordinate mapping relationship;

[0025] After the deletion is completed, the deleted actual detection areas are reordered to obtain the adjusted actual detection areas.

[0026] Optionally, the actual detection information further includes an actual order of each insulator, and the configuration detection information further includes a configuration order of each insulator; if the number of the actually detected insulators is inconsistent with the number of configured insulators, adjusting the actual detection area according to the coordinate mapping relationship and the configured detection area to obtain the adjusted actual detection area includes:

[0027] If the number of insulators actually detected is less than the number of configured insulators, and the actual sequence is different from the configured sequence, determining the first insulator according to the actual sequence;

[0028] Supplementing the actual detection area within the preset area of ​​the first insulator according to the mapping relationship;

[0029] After the supplementation is completed, the supplemented actual detection areas are reordered to obtain the adjusted actual detection areas.

[0030] Optionally, the actual detection information further includes an actual order of each insulator, and the configuration detection information further includes a configuration order of each insulator; if the number of the actually detected insulators is inconsistent with the number of configured insulators, adjusting the actual detection area according to the coordinate mapping relationship and the configured detection area to obtain the adjusted actual detection area includes:

[0031] If the number of actually detected insulators is less than the number of configured insulators, and the actual order is the same as the configured order, mapping the configured detection area according to the coordinate mapping relationship to obtain a mapped detection area;

[0032] Comparing the mapped detected area with the actual detected area, and completing the actual detected area according to the comparison result;

[0033] After the padding is completed, the padded actual detection areas are reordered to obtain the adjusted actual detection areas.

[0034] Optionally, after detecting whether the number of actually detected insulators is consistent with the number of configured insulators, the method further includes:

[0035] If the number of insulators actually detected is consistent with the number of configured insulators, determining whether the area overlap rate between the actual detection area and the configured detection area exceeds a preset threshold;

[0036] If the area overlap rate exceeds a preset threshold, detecting whether each insulator has temperature abnormality based on the configured detection area;

[0037] If the area overlap rate does not exceed a preset threshold, then whether the temperature of each insulator is abnormal is detected based on the actual detection area.

[0038] Optionally, the acquiring configuration detection information corresponding to the insulator string includes:

[0039] Acquire camera parameters of a thermal imaging camera when acquiring the infrared thermal imaging image, wherein the camera parameters include at least one of a horizontal rotation angle, a pitch angle, and a zoom parameter;

[0040] The photographed insulator string is determined according to the camera parameters, and configuration detection information corresponding to the photographed insulator string is searched.

[0041] Optionally, before performing target detection on the infrared thermal imaging image of the insulator string to obtain actual detection information of the insulator string, the method further includes:

[0042] Collecting infrared thermal imaging sample images of the insulator string, and obtaining detected sample information of the insulator string from the infrared thermal imaging sample images;

[0043] Displaying the detected sample information on a target user interface, and receiving a manual configuration operation fed back by a user based on the detected sample information;

[0044] The detected sample information is modified according to the manual configuration operation to obtain the configuration detection information of the insulator string.

[0045] In addition, to achieve the above-mentioned purpose, the present application also proposes an insulator detection device, the insulator detection device comprising:

[0046] A target detection module, used to perform target detection on the infrared thermal imaging image of the insulator string to obtain actual detection information of the insulator string, wherein the actual detection information includes the actual detection area of ​​each insulator in the insulator string;

[0047] An information acquisition module, used to acquire configuration detection information corresponding to the insulator string, wherein the configuration detection information includes a configuration detection area of ​​each insulator;

[0048] A coordinate correction module, used for adjusting the actual detection area according to the configured detection area to obtain an adjusted actual detection area;

[0049] The abnormality detection module is used to detect whether the temperature of each insulator is abnormal based on the adjusted actual detection area.

[0050] In addition, to achieve the above-mentioned purpose, the present application also proposes an insulator detection device, which includes a memory, a processor, and an insulator detection program stored in the memory and executable on the processor, and the insulator detection program is configured to implement the insulator detection method described above.

[0051] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, on which an insulator detection program is stored. When the insulator detection program is executed by a processor, the insulator detection method as described above is implemented.

[0052] One or more technical solutions proposed in this application have at least the following technical effects:

[0053] In the present application, target detection is performed on an infrared thermal imaging image of an insulator string to obtain actual detection information of the insulator string, wherein the actual detection information includes an actual detection area of ​​each insulator in the insulator string, configuration detection information corresponding to the insulator string is obtained, wherein the configuration detection information includes a configuration detection area of ​​each insulator, the actual detection area is adjusted according to the configuration detection area to obtain the adjusted actual detection area, and whether each insulator has a temperature abnormality is detected based on the adjusted actual detection area; since the present application verifies the actual detection information through the configuration detection information corresponding to the insulator string, the actual detection information can be adjusted when a viewing angle offset or an inaccurate algorithm detection occurs, thereby improving the accuracy of insulator detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0056] Figure 1 This is a flow chart of the first embodiment of the insulator detection method of the present application;

[0057] Figure 2 This is an infrared thermal imaging image of an embodiment of the insulator detection method of the present application;

[0058] Figure 3 This is a flow chart of a second embodiment of the insulator detection method of the present application;

[0059] Figure 4 This is a detection flow chart of an embodiment of an insulator detection method of the present application;

[0060] Figure 5 This is a flow chart of a third embodiment of the insulator detection method of the present application;

[0061] Figure 6 A coordinate mapping diagram of an embodiment of an insulator detection method of the present application;

[0062] Figure 7 This is a schematic diagram of a first misdetection scenario of an embodiment of an insulator detection method of the present application;

[0063] Figure 8 A schematic diagram of a second misdetection scenario of an embodiment of an insulator detection method of the present application;

[0064] Fig. 9 This is a schematic diagram of a first missed detection scenario of an embodiment of an insulator detection method of the present application;

[0065] Fig.10 This is a schematic diagram of a second missed detection scenario of an embodiment of an insulator detection method of the present application;

[0066] Fig.11 This is a flow chart of a fourth embodiment of the insulator detection method of the present application;

[0067] Fig.12 This is an overall flow chart of an embodiment of an insulator detection method of the present application;

[0068] Fig.13 This is a schematic diagram of the module structure of the insulator detection device according to an embodiment of the present application;

[0069] Fig.14 It is a schematic diagram of the equipment structure of the hardware operating environment involved in the insulator detection method in the embodiment of the present application.

[0070] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0071] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0072] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0073] In the field of power industry, how to detect the temperature of insulators has always been a difficult problem that plagues the industry. The relevant technology usually uses a thermal imaging PTZ camera (i.e. a Pan-Tilt-Zoom camera, with adjustable camera direction (horizontal rotation Pan), pitch angle (vertical tilt Tilt) and zoom) to detect the temperature of insulators.

[0074] However, the viewing angle of the device in the related insulator detection method will be offset before and after the thermal imaging PTZ camera moves (for example, when the thermal imaging PTZ camera is used to detect three-phase insulator strings, the A-phase insulator string is at preset point 1, the B-phase insulator string is at preset point 2, and the C-phase insulator string is at preset point 3. The camera collects infrared thermal images of each phase insulator string in a loop by rotating the camera, and the rotating camera will cause the viewing angle to shift. For example, the viewing angle of the camera when shooting the A-phase insulator this time may be different from the viewing angle of the camera when shooting the A-phase insulator last time due to the viewing angle shift caused by the rotation of the camera), and the related insulator recognition algorithm also has the problem of inaccurate insulator detection (such as false detection and missed detection), which leads to inaccurate insulator detection results.

[0075] Therefore, in order to overcome the above-mentioned defects, the present application provides a solution, which includes: performing target detection on the infrared thermal imaging image of the insulator string, obtaining actual detection information of the insulator string, wherein the actual detection information includes the actual detection area of ​​each insulator in the insulator string, obtaining configuration detection information corresponding to the insulator string, wherein the configuration detection information includes the configuration detection area of ​​each insulator, adjusting the actual detection area according to the configuration detection area, obtaining the adjusted actual detection area, and detecting whether each insulator has a temperature abnormality based on the adjusted actual detection area.

[0076] Since the present application verifies the actual detection information through the configuration detection information corresponding to the insulator string, the actual detection information can be adjusted when the viewing angle is offset or the algorithm detection is inaccurate, thereby improving the accuracy of insulator detection.

[0077] It should be noted that the executor of the embodiment of the present application may be an insulator detection device with data processing, network communication and program running functions, such as a thermal imaging PTZ camera, or other electronic devices that can achieve the same or similar functions, and this embodiment does not impose any restrictions on this.

[0078] Based on this, the embodiment of the present application provides an insulator detection method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the insulator detection method of the present application.

[0079] In a first embodiment, the insulator detection method includes:

[0080] Step S10: performing target detection on the infrared thermal imaging image of the insulator string to obtain actual detection information of the insulator string, wherein the actual detection information includes the actual detection area of ​​each insulator in the insulator string.

[0081] It should be understood that the application scenario of the embodiment of the present application may be to perform temperature detection on insulators through a thermal imaging PTZ camera (i.e., a Pan-Tilt-Zoom camera, the direction of the camera (horizontal rotation Pan), pitch angle (vertical tilt Tilt) and zoom (Zoom) are adjustable). In a specific implementation, the application scenario of the embodiment of the present application may be to detect three-phase insulator strings through a thermal imaging PTZ camera, with the A-phase insulator string at preset point 1, the B-phase insulator string at preset point 2, and the C-phase insulator string at preset point 3. The camera cyclically collects infrared thermal images of the insulator strings of each phase by rotating the camera head to perform temperature detection on the insulators on the insulator strings of each phase.

[0082] It is understandable that infrared thermal imaging technology can generate images using infrared radiation radiated from the surface of an object. In the power system, the insulator string is a key component, and the change in its surface temperature can reflect its working status and health. Therefore, in this embodiment, the infrared radiation radiated from the surface of the insulator string is captured by a thermal imaging PTZ camera, and the infrared radiation is converted into a visible infrared thermal imaging image, wherein different colors in the infrared thermal imaging image represent different temperatures. For ease of understanding, the following examples are provided, but the present application is not limited. As an example, assuming that the insulator string is an A-phase insulator string, when the thermal imaging PTZ camera rotates to the detection position corresponding to the A-phase insulator string, the thermal imaging PTZ camera shoots the A-phase insulator string, captures the infrared radiation radiated from the surface of the A-phase insulator string, and converts the infrared radiation into a visible infrared thermal imaging image to obtain an infrared thermal imaging image of the A-phase insulator string.

[0083] It should be understood that target detection can be to identify an object of interest (in this embodiment, an insulator) from an image or video. Performing target detection on the infrared thermal imaging image of the insulator string and obtaining the actual detection information of the insulator string can include the following steps: 1. Feature extraction: Analyzing the pixels and textures in the infrared thermal imaging image through a preset algorithm to identify features related to the insulator, such as shape, color (expressed as temperature difference in the infrared thermal imaging image) and edges, etc., wherein the preset algorithm can be pre-set, for example, the preset algorithm can be a neural network model, which is not limited in this embodiment; 2. After obtaining the features, the objects in the image can be classified as insulators or non-insulators according to the features to determine the actual detection area of ​​each insulator.

[0084] It should be noted that for each successfully identified insulator, the algorithm determines its actual detection area in the image. The actual detection area can be a rectangular frame surrounding the insulator, or a more complex shape to more accurately match the outline of the insulator, which is not limited in this embodiment. Of course, in order to facilitate more precise adjustments later, in this embodiment, the actual detection information can also include the actual order of each insulator.

[0085] For ease of understanding, refer to Figure 2 This invention is provided for illustration, but is not intended to limit the present application. Figure 2 This is an infrared thermal imaging diagram of an embodiment of the insulator detection method of the present application. Assuming that the insulator string is the A-phase insulator string, in the figure, the outermost red frame is the actual detection area, and there are 8 red small frames in the red frame, and the red small frames represent the actual detection areas of each insulator. Among them, since the distance between the leftmost red small frame and the boundary of the actual detection frame is greater than the distance between the rightmost red small frame and the boundary of the actual detection frame, the insulator corresponding to the leftmost red small frame is taken as the first insulator, and the actual order of each insulator can be determined as follows: Figure 2 As shown (i.e. from left to right).

[0086] Step S20: Acquire configuration detection information corresponding to the insulator string, wherein the configuration detection information includes a configuration detection area of ​​each insulator.

[0087] It should be noted that obtaining the configuration detection information corresponding to the insulator string may be obtaining the configuration detection information corresponding to the insulator string from a database or a configuration file, wherein the configuration detection information may include a configuration detection area of ​​each insulator. The configuration detection area may be pre-set based on factors such as the design size and installation position of the insulator, and this embodiment does not limit this.

[0088] Furthermore, in order to improve the reliability of the configuration detection information, in this embodiment, it is necessary to first determine which insulator string the thermal imaging camera is photographing, and then obtain the corresponding configuration information. The step S20 includes: obtaining camera parameters when the thermal imaging camera collects the infrared thermal imaging image, wherein the camera parameters include at least one of a horizontal rotation angle, a pitch angle, and a zoom parameter; determining the photographed insulator string according to the camera parameters, and searching for the configuration detection information corresponding to the photographed insulator string.

[0089] It should be understood that in the application scenario of the embodiment of the present application, the thermal imaging PTZ camera is used to detect the temperature of the insulators in the three-phase insulator strings set at different positions. Since the three-phase insulator strings are distributed in different positions, the camera parameters of the thermal imaging PTZ camera when shooting different insulator strings are different (partial parameters may be different, for example, the three-phase insulator strings are set at the same height and are close to the thermal imaging PTZ camera. Then, the pitch angle and zoom parameters of the thermal imaging PTZ camera when shooting different insulator strings may be the same, and the horizontal rotation angle is different. Therefore, the insulator string being photographed can be determined based on the horizontal rotation angle only.). Therefore, in this embodiment, the insulator string being photographed can be determined based on the camera parameters. In a specific implementation, the camera parameters can be matched with the camera parameter samples, and the insulator string corresponding to the successfully matched camera parameter samples is used as the insulator string being photographed, wherein the camera parameter samples corresponding to each insulator string can be pre-set by the user. For example, when the user configures the thermal imaging PTZ camera, the thermal imaging PTZ camera can be configured to collect the camera parameters of each insulator string.

[0090] It is understandable that after determining the photographed insulator string, the configuration detection information corresponding to the photographed insulator string can be searched in the configuration relationship table. Among them, the configuration relationship table includes the correspondence between the insulator string and the configuration detection information, and the correspondence between the insulator string and the configuration detection information can be preset by the user. In a specific implementation, for example, the infrared thermal imaging sample image of the insulator string is collected, and the detection sample information of the insulator string is obtained from the infrared thermal imaging sample image; the detection sample information is displayed on the target user interface, and the manual configuration operation feedback from the user based on the detection sample information is received; the detection sample information is modified according to the manual configuration operation, the configuration detection information of the insulator string is obtained, and the correspondence between the insulator string and the configuration detection information is established to obtain the configuration relationship table.

[0091] Step S30: adjusting the actual detection area according to the configured detection area to obtain an adjusted actual detection area.

[0092] It can be understood that adjusting the actual detection area according to the configured detection area can be at least one of adding a detection area, deleting a detection area, and modifying a detection area, wherein adding a detection area can refer to adding a detection area at a position where an insulator is not identified in the image, and specifically, the position of adding the detection area can be determined by comparing the configured detection area with the actual detection area. Deleting a detection area can refer to deleting the detection area corresponding to an object that is mistakenly identified as an insulator in the image, and specifically, the actual detection area to be deleted can be determined by comparing the configured detection area with the actual detection area. Modifying a detection area can mean that if the actual detected insulator position deviates from the position in the configured detection information, or the identified insulator shape does not match expectations, the position or shape of the detection area can be adjusted to more accurately match the actual insulator position and contour.

[0093] Step S40: Detecting whether the insulators have temperature anomalies based on the adjusted actual detection area.

[0094] It should be understood that the steps of detecting whether each insulator has a temperature abnormality based on the adjusted actual detection area may include: 1. extracting the contour of the insulator and removing the background in the adjusted actual detection area; 2. measuring the temperature of the insulator in the processed detection area to determine whether the insulator has a temperature abnormality.

[0095] It is understood that insulator contour extraction can refer to accurately identifying and outlining the edges and shapes of insulators from an image. This can be achieved through image processing techniques such as edge detection, threshold segmentation, morphological operations, etc. Insulator contour extraction within the adjusted actual detection area can more accurately locate the insulator and provide accurate boundaries for its subsequent temperature analysis. Background removal can refer to removing parts that do not belong to the insulator from the infrared thermal imaging image in order to more clearly observe and analyze the temperature distribution of the insulator. This can be achieved through image segmentation technology to distinguish the insulator from the background, other objects or noise. Background removal within the adjusted actual detection area can ensure that the temperature analysis is only for the insulator itself, thereby improving the accuracy and reliability of the analysis.

[0096] After the insulator contour extraction and background removal are completed, the temperature of the insulator is measured and whether the insulator has temperature anomalies is determined. The specific steps include the following: 1. Temperature measurement: Using the temperature measurement function of the thermal imaging PTZ camera, the temperature of each insulator (or its key part) is measured in the processed detection area. This can generate a series of temperature data points representing the temperature distribution on the surface of the insulator. 2. Temperature analysis: Statistical analysis is performed on the measured temperature data, such as calculating the average temperature, the highest temperature, the lowest temperature, etc. These statistical data can be compared with the preset temperature threshold to evaluate the temperature state of the insulator. 3. Abnormal judgment: According to the temperature analysis results and the preset temperature threshold, it is determined whether the insulator has temperature anomalies. Temperature anomalies may be manifested as too high or too low temperature or uneven temperature distribution. If the temperature of the insulator exceeds the preset threshold range, it can be considered that the insulator has temperature anomalies. 4. Alarm and recording: If a temperature anomaly is detected, the thermal imaging PTZ camera can trigger an alarm mechanism to notify relevant personnel to handle it. At the same time, the abnormal information will also be recorded for subsequent analysis and tracking.

[0097] Of course, in order to further improve the accuracy of the insulator detection results, in this embodiment, the step S40 may also include: if the area overlap rate between the adjusted actual detection area and the configured detection area exceeds a preset threshold, then based on the configured detection area, detect whether each insulator has a temperature abnormality; if the area overlap rate between the adjusted actual detection area and the configured detection area does not exceed the preset threshold, then based on the adjusted actual detection area, detect whether each insulator has a temperature abnormality, wherein the preset threshold can be pre-set, for example, the preset threshold can be pre-set to 80%.

[0098] This embodiment verifies the actual detection information through the configuration detection information corresponding to the insulator string, so that when the viewing angle is offset or the algorithm detection is inaccurate, the actual detection information can be adjusted, thereby improving the accuracy of insulator detection.

[0099] Reference Figure 3 , Figure 3 This is a flow chart of the second embodiment of the insulator detection method of the present application, based on the above Figure 1 The first embodiment shown provides a second embodiment of the insulator detection method of the present application.

[0100] In the second embodiment, the actual detection information further includes the number of actually detected insulators, and the configured detection information further includes the number of configured insulators; and the step S30 includes:

[0101] Step S301: Detect whether the number of insulators actually detected is consistent with the number of configured insulators.

[0102] It should be understood that in order to improve the efficiency of adjusting the actual detection information, in this embodiment, it is first detected whether the number of actually detected insulators is consistent with the number of configured insulators. If they are inconsistent, the actual detection area will be adjusted according to the configured detection area.

[0103] It should be noted that the actual number of detected insulators may refer to the number of insulators successfully identified and located in the infrared thermal imaging image. This number may be the same as the number of insulators actually installed in the insulator string, or it may be different (for example, if an insulator is blocked, damaged, or cannot be identified due to poor image quality). Configuration detection information may also include the number of insulators that should be in the insulator string (i.e., the number of configured insulators).

[0104] For ease of understanding, refer to Figure 2 This invention is provided for illustration, but is not intended to limit the present application. Figure 2 This is an infrared thermal imaging diagram of an embodiment of the insulator detection method of the present application. Assuming that the insulator string is the A-phase insulator string, in the figure, the outermost red large frame is the actual detection area. There are 8 red small frames in the red large frame, and the actual number of insulators detected is 8.

[0105] Furthermore, after step S301, it also includes: if the number of insulators actually detected is consistent with the number of configured insulators, determining whether the area overlap rate between the actual detection area and the configured detection area exceeds a preset threshold; if the area overlap rate exceeds the preset threshold, detecting whether temperature abnormalities occur in each insulator based on the configured detection area; if the area overlap rate does not exceed the preset threshold, detecting whether temperature abnormalities occur in each insulator based on the actual detection area.

[0106] It should be understood that if the number of insulators actually detected is consistent with the number of configured insulators, it means that the algorithm has no false detection or missed detection. At this time, it is necessary to determine which detection area is used as the reference area to calculate whether the insulator has a temperature abnormality more accurately. Considering that the configuration detection area has higher accuracy, therefore, when the difference between the actual detection area and the configuration detection area is not large, this embodiment uses the configuration detection area as the reference area to calculate whether the insulator has a temperature abnormality. Specifically, if the area overlap rate between the actual detection area and the configuration detection area exceeds a preset threshold, then the configuration detection area is used to detect whether each insulator has a temperature abnormality; if the area overlap rate between the actual detection area and the configuration detection area does not exceed the preset threshold, then the actual detection area is used to detect whether each insulator has a temperature abnormality, wherein the preset threshold can be preset, for example, the preset threshold can be preset to 80%.

[0107] Step S302: If the number of actually detected insulators is inconsistent with the number of configured insulators, the actual detection area is adjusted according to the configured detection area to obtain an adjusted actual detection area.

[0108] It should be understood that if the number of insulators actually detected is inconsistent with the number of configured insulators, it means that some insulators have not been correctly identified, or the image may contain some additional objects that do not belong to the insulator string. In this case, the detection area can be adjusted to ensure that each insulator can be accurately detected.

[0109] It can be understood that adjusting the actual detection area according to the configured detection area can be at least one of adding a detection area, deleting a detection area, and modifying a detection area, wherein adding a detection area can mean that if the number of actually detected insulators is less than the number of configured insulators, a detection area can be added at a position where the insulator is not identified in the image, and specifically, the added position of the detection area can be determined by comparing the configured detection area with the actual detection area. Deleting a detection area can mean that if the number of actually detected insulators is greater than the number of configured insulators, the detection area corresponding to the object mistakenly identified as an insulator in the image can be deleted, and specifically, the actual detection area to be deleted can be determined by comparing the configured detection area with the actual detection area. Modifying a detection area can mean that if the position of the actually detected insulator deviates from the position in the configured detection information, or the identified shape of the insulator does not match the expectation, the position or shape of the detection area can be adjusted to more accurately match the position and contour of the actual insulator.

[0110] For ease of understanding, refer to Figure 4 This invention is provided for illustration, but is not intended to limit the present application. Figure 4This is a detection flow chart of an embodiment of the insulator detection method of the present application. In the figure, if the number of insulators actually detected is consistent with the number of configured insulators, it is determined whether the regional overlap rate between the actual detection area and the configured detection area exceeds a preset threshold; if the regional overlap rate exceeds the preset threshold, whether the temperature of each insulator is abnormal is detected based on the configured detection area; if the regional overlap rate does not exceed the preset threshold, whether the temperature of each insulator is abnormal is detected based on the actual detection area; if the number of insulators actually detected is inconsistent with the number of configured insulators, the actual detection area is adjusted according to the configured detection area to obtain the adjusted actual detection area; it is determined whether the regional overlap rate between the adjusted actual detection area and the configured detection area exceeds the preset threshold; if the regional overlap rate exceeds the preset threshold, whether the temperature of each insulator is abnormal is detected based on the configured detection area; if the regional overlap rate does not exceed the preset threshold, whether the temperature of each insulator is abnormal is detected based on the adjusted actual detection area.

[0111] This embodiment first detects whether the number of actually detected insulators is consistent with the number of configured insulators. If they are inconsistent, the actual detection area is adjusted according to the configured detection area, thereby improving the adjustment efficiency of the actual detection information.

[0112] Reference Figure 5 , Figure 5 This is a flow chart of the third embodiment of the insulator detection method of the present application. Figure 3 The second embodiment shown provides a third embodiment of the insulator detection method of the present application.

[0113] In a third embodiment, the actual detection information further includes an actual detection area corresponding to the insulator string, and the configuration detection information includes a configuration detection area corresponding to the insulator string;

[0114] Before step S302, the method further includes:

[0115] Step S310: Calculate a coordinate mapping relationship according to the center point coordinates of the actual detection area and the center point coordinates of the configured detection area.

[0116] It should be understood that in order to improve the accuracy of the detection area adjustment, in this embodiment, the coordinate mapping relationship is also calculated based on the actual detection area and the configured detection area corresponding to the insulator string, and when the actual number of detected insulators is inconsistent with the number of configured insulators, the actual detection area is adjusted based on the coordinate mapping relationship and the configured detection area to obtain the adjusted actual detection area.

[0117] For ease of understanding, refer to Figure 6 This invention is provided for illustration, but is not intended to limit the present application. Figure 6This is a coordinate mapping diagram of an embodiment of the insulator detection method of the present application. In the figure, as an example, it is assumed that the outermost large frame is the detection area corresponding to the insulator string, and the small frame in the large frame is the detection area of ​​each insulator. The coordinates of the center point of the configuration detection area are M(x 1 ,y 1 ), the center point coordinates of the actual detection area are N(x 2 ,y 2 ), then when x 1 =x 2 When the coordinate mapping relationship is y, the ordinate t = y 2 -y 1 , horizontal axis: x 1 =x 2 Therefore, the center point coordinates of the configured detection area and the center point coordinates of the actual detection area should satisfy: the y interval is t, and the x coordinates are equal. 1 ≠x 2 When the coordinate mapping relationship is: 1. Slope k = (y 2 -y 1 ) / (x 2 -x 1 ),distance Therefore, the center point coordinates of the configured detection area and the center point coordinates of the actual detection area should satisfy the following: 1. The slope of the center point coordinates of the configured detection area and the center point coordinates of the actual detection area is k; 2. The distance between the center point coordinates of the configured detection area and the center point coordinates of the actual detection area is d.

[0118] Accordingly, the step S302 includes:

[0119] Step S302': if the number of actually detected insulators is inconsistent with the number of configured insulators, the actual detection area is adjusted according to the coordinate mapping relationship and the configured detection area to obtain an adjusted actual detection area.

[0120] It is understandable that if the number of insulators actually detected is inconsistent with the number of configured insulators, it means that there are missed detections or false detections in real-time detection. Therefore, it is necessary to adjust the actual detection area according to the coordinate mapping relationship and the configured detection area. Specifically, when the number of insulators actually detected is greater than the number of configured insulators, this is a false detection scenario in the algorithm detection anomaly (non-insulator targets or highly similar targets are mistakenly detected as insulator targets), and the actual detection area that does not meet the coordinate mapping relationship needs to be deleted; when the number of insulators actually detected is less than the number of configured insulators, this is a missed detection scenario in the algorithm detection anomaly, and it is necessary to map the configured detection area to the mapped detection area according to the coordinate mapping relationship, compare the mapped detection area with the actual detection area, and fill the actual detection area according to the comparison result.

[0121] This embodiment also calculates a coordinate mapping relationship based on the actual detection area and the configured detection area corresponding to the insulator string, and when the number of actually detected insulators is inconsistent with the number of configured insulators, the actual detection area is adjusted based on the coordinate mapping relationship and the configured detection area to obtain the adjusted actual detection area, thereby improving the accuracy of the detection area adjustment.

[0122] Furthermore, when the actual detection area generates an overlapping false detection at the head of the actual detection area corresponding to the insulator string, the order of the first and last insulators will be reversed. Therefore, in order to improve the accuracy of the detection area adjustment in this scenario, the actual detection information also includes the actual order of each insulator, and the configuration detection information also includes the configuration order of each insulator. The step S302' includes: if the number of the actual detected insulators is greater than the number of configured insulators, and the actual order is different from the configuration order, then the tail insulator is determined according to the actual order, and the actual detection area corresponding to the tail insulator is deleted; whether the coordinate mapping relationship is satisfied between the actual detection area and the configuration detection area, and the actual detection area that does not satisfy the coordinate mapping relationship is deleted; after the deletion is completed, the deleted actual detection area is reordered to obtain the adjusted actual detection area.

[0123] For ease of understanding, refer to Figure 7 This invention is provided for illustration, but is not intended to limit the present application. Figure 7 This is a schematic diagram of the first false detection scenario of an embodiment of the insulator detection method of the present application. In the figure, it is assumed that the outermost large frame is the detection area corresponding to the insulator string, and the small frame in the large frame is the detection area of ​​each insulator. The first false detection scenario is that the actual detection area produces overlapping false detection at the head of the actual detection area corresponding to the insulator string, thereby causing the order of the head and tail insulators to be reversed. The detection area adjustment method under the first false detection scenario includes: when the head and tail order of the insulators changes (that is, the actual order is different from the configured order), the actual detection area corresponding to the tail insulator (that is, the virtual frame area corresponding to the insulator labeled 9) can be eliminated by configuring the order, and then the actual detection area that does not satisfy the coordinate mapping relationship is deleted, and the deleted actual detection area is reordered to obtain the adjusted actual detection area.

[0124] Furthermore, when some actual detection areas are falsely detected, in order to improve the accuracy of detection area adjustment in this scenario, the step S302' also includes: if the number of actually detected insulators is greater than the number of configured insulators, and the actual sorting is the same as the configured sorting, then deleting the actual detection areas that are not within the actual detection area; judging whether the coordinate mapping relationship is satisfied between the actual detection area and the configured detection area, and deleting the actual detection areas that do not satisfy the coordinate mapping relationship; after the deletion is completed, reordering the deleted actual detection areas to obtain adjusted actual detection areas.

[0125] For ease of understanding, refer to Figure 8 This invention is provided for illustration, but is not intended to limit the present application. Figure 8 This is a schematic diagram of the second false detection scenario of an embodiment of the insulator detection method of the present application. In the figure, it is assumed that the outermost large frame is the detection area corresponding to the insulator string, and the small frame in the large frame is the detection area of ​​each insulator. The second false detection scenario is that part of the actual detection area is a false detection. The detection area adjustment method under the second false detection scenario includes: first, eliminating the actual detection area that is not in the actual detection area corresponding to the insulator string (that is, the virtual frame area corresponding to insulator No. 10 in the figure), and then deleting the actual detection area that does not satisfy the coordinate mapping relationship (that is, the virtual frame area corresponding to insulator No. 5 in the figure), and reordering the deleted actual detection areas to obtain the adjusted actual detection areas.

[0126] Furthermore, when the tail insulator is lost, the order of the first and last insulators will be reversed. Therefore, in order to improve the accuracy of the detection area adjustment in this scenario. The step S302' also includes: if the number of actually detected insulators is less than the number of configured insulators, and the actual order is different from the configured order, then the first insulator is determined according to the actual order; the actual detection area is supplemented within the preset area of ​​the first insulator according to the mapping relationship; after the supplementation is completed, the supplemented actual detection area is reordered to obtain the adjusted actual detection area.

[0127] For ease of understanding, refer to Fig. 9 This invention is provided for illustration, but is not intended to limit the present application. Fig. 9This is a schematic diagram of the first missed detection scenario of an embodiment of the insulator detection method of the present application. In the figure, it is assumed that the outermost large frame is the detection area corresponding to the insulator string, and the small frame in the large frame is the detection area of ​​each insulator. The first missed detection scenario is that the tail insulator is lost, which causes the order of the head and tail insulators to be reversed. The detection area adjustment method in the first missed detection scenario includes: when the tail insulator is missed, the order will change. If the actual order is different from the configured order, the first insulator is determined according to the actual order, and the actual detection area corresponding to the first insulator is supplemented according to the mapping relationship (that is, the virtual frame area corresponding to insulator No. 8 in the figure); after the supplement is completed, the supplemented actual detection area is reordered to obtain the adjusted actual detection area.

[0128] Furthermore, the step S302' also includes: if the number of insulators actually detected is less than the number of configured insulators, and the actual order is the same as the configured order, mapping the configured detection area according to the coordinate mapping relationship to obtain the mapped detection area; comparing the mapped detection area with the actual detection area, and filling the actual detection area according to the comparison result; after the filling is completed, re-ordering the filled actual detection area to obtain the adjusted actual detection area.

[0129] For ease of understanding, refer to Fig.10 This invention is provided for illustration, but is not intended to limit the present application. Fig.10 This is a schematic diagram of a second missed detection scenario of an embodiment of an insulator detection method of the present application. In the figure, it is assumed that the outermost large frame is the detection area corresponding to the insulator string, and the small frame in the large frame is the detection area of ​​each insulator. The second missed detection scenario is that the head insulator or the middle string is lost, or there is a scenario where the head and the tail are lost at the same time. The detection area adjustment method under the second missed detection scenario includes: mapping the configured detection area according to the coordinate mapping relationship to obtain the mapped detection area, comparing the mapped detection area with the actual detection area, and determining according to the comparison result that the actual detection area corresponding to insulator No. 1 (i.e., the virtual frame area corresponding to insulator No. 1 in the figure), the actual detection area corresponding to insulator No. 6 (i.e., the virtual frame area corresponding to insulator No. 6 in the figure), and the actual detection area corresponding to insulator No. 8 (i.e., the virtual frame area corresponding to insulator No. 8 insulator in the figure) need to be filled, and then the filled actual detection areas are reordered to obtain the adjusted actual detection areas.

[0130] Reference Fig.11 , Fig.11 This is a flow chart of a fourth embodiment of the insulator detection method of the present application. Based on the above embodiments, a fourth embodiment of the insulator detection method of the present application is proposed.

[0131] In the fourth embodiment, before step S10, the method further includes:

[0132] Step S01: collecting infrared thermal imaging sample images of an insulator string, and obtaining detected sample information of the insulator string from the infrared thermal imaging sample images.

[0133] It should be understood that in order to meet the actual needs of users and improve the accuracy of insulator detection, in this embodiment, the user can also manually configure the configuration detection information of the insulator string. Specifically, when the thermal imaging PTZ camera detects the insulator string for the first time, it can first collect an infrared thermal imaging sample image of the insulator string, and obtain the detection sample information of the insulator string from the infrared thermal imaging sample image, wherein the detection sample information may include the number of detected insulators, the detection area of ​​each insulator, and the detection order of each insulator.

[0134] Step S02: displaying the detected sample information on the target user interface, and receiving a manual configuration operation from the user based on the detected sample information.

[0135] It is understandable that after obtaining the detected sample information, the detected sample information can be displayed on the target user interface, and the user can manually add missing insulators, delete redundant detected insulators, and the head and tail directions of the insulators (for example, the sequence number 1 represents the position of the first insulator) on the target user interface. Manual configuration settings only need to be made once, and the corresponding configuration will be saved for coordinate matching during subsequent equipment movement, without the need for manual configuration each time.

[0136] Step S03: modifying the detected sample information according to the manual configuration operation to obtain configuration detection information of the insulator string.

[0137] For ease of understanding, refer to Fig.12 This invention is provided for illustration, but is not intended to limit the present application. Fig.12 This is an overall flow chart of an embodiment of the insulator detection method of the present application. In the figure, the insulator detection method includes:

[0138] 1. Obtaining detected sample information of the insulator string: collecting infrared thermal imaging sample images of the insulator string, and obtaining detected sample information of the insulator string from the infrared thermal imaging sample images.

[0139] 2. Manually configure the configuration detection information of the insulator string based on the detected sample information: display the detected sample information on the target user interface, and receive the manual configuration operation feedback from the user based on the detected sample information; modify the detected sample information according to the manual configuration operation to obtain the configuration detection information of the insulator string.

[0140] 3. Collecting actual detection information of the insulator string; performing target detection on the infrared thermal imaging image of the insulator string to obtain the actual detection information of the insulator string.

[0141] 4. Review the actual detection information according to the configured detection information and determine the target detection area: if the actual number of detected insulators is consistent with the configured number of insulators, determine whether the area overlap rate between the actual detection area and the configured detection area exceeds the preset threshold; if the area overlap rate exceeds the preset threshold, the configured detection area is used as the target detection area; if the area overlap rate does not exceed the preset threshold, the actual detection area is used as the target detection area; if the actual number of detected insulators is inconsistent with the configured number of insulators, adjust the actual detection area according to the configured detection area to obtain the adjusted actual detection area; determine whether the area overlap rate between the adjusted actual detection area and the configured detection area exceeds the preset threshold; if the area overlap rate exceeds the preset threshold, the configured detection area is used as the target detection area; if the area overlap rate does not exceed the preset threshold, the adjusted actual detection area is used as the target detection area.

[0142] 5. Detect whether each insulator has temperature abnormality based on the target detection area: 1. Extract the contour of the insulator and remove the background in the target detection area; 2. Measure the temperature of the insulator in the processed target detection area to determine whether the insulator has temperature abnormality.

[0143] In this embodiment, the configuration detection information of the insulator string can also be manually configured by the user, thereby meeting the actual needs of the user and improving the accuracy of insulator detection.

[0144] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the insulator detection method of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0145] This application also provides an insulator detection device, please refer to Fig.13 , the insulator detection device comprises:

[0146] The target detection module 10 is used to perform target detection on the infrared thermal imaging image of the insulator string to obtain actual detection information of the insulator string, wherein the actual detection information includes the actual detection area of ​​each insulator in the insulator string;

[0147] An information acquisition module 20 is used to acquire configuration detection information corresponding to the insulator string, wherein the configuration detection information includes a configuration detection area of ​​each insulator;

[0148] A coordinate correction module 30, used for adjusting the actual detection area according to the configured detection area to obtain an adjusted actual detection area;

[0149] The abnormality detection module 40 is used to detect whether the temperature of each insulator is abnormal based on the adjusted actual detection area.

[0150] The insulator detection device provided by the present application adopts the insulator detection method in the above embodiment, which can solve the technical problem that the insulator detection result is inaccurate when the camera angle of view is offset or the algorithm detection is inaccurate in the related insulator detection method. Compared with the related art, the beneficial effect of the insulator detection device provided by the present application is the same as the beneficial effect of the insulator detection method provided by the above embodiment, and the other technical features in the insulator detection device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0151] The present application provides an insulator detection device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the insulator detection method in the above-mentioned embodiment 1.

[0152] Reference below Fig.14 , which shows a schematic diagram of the structure of an insulator detection device suitable for implementing the embodiment of the present application. The insulator detection device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.14 The insulator detection device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0153] like Fig.14As shown, the insulator detection device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to the program stored in the ROM (Read Only Memory) 1002 or the program loaded from the storage device 1003 to the RAM (Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the insulator detection device are also stored. The processing device 1001, the ROM 1002 and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, an LCD (Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the insulator detection device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an insulator detection device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0154] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0155] The insulator detection device provided by the present application adopts the insulator detection method in the above embodiment, which can solve the technical problem that the insulator detection result is inaccurate when the camera angle of view is offset or the algorithm detection is inaccurate in the related insulator detection method. Compared with the related art, the beneficial effect of the insulator detection device provided by the present application is the same as the beneficial effect of the insulator detection method provided by the above embodiment, and the other technical features in the insulator detection device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0156] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0157] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0158] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the insulator detection method in the above-mentioned embodiment.

[0159] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, or infrared systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory), optical fiber, CD-ROM (CD-Read Only Memory, portable compact disk read-only memory), optical storage device, magnetic storage device, or any suitable combination of the above. In the present embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0160] The computer-readable storage medium may be included in the insulator detection device; or may exist independently without being assembled into the insulator detection device.

[0161] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the insulator detection device, the insulator detection device executes the insulator detection method in the above embodiment.

[0162] The computer program code for performing the operation of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a LAN (Local Area Network) or a WAN (Wide Area Network), or it can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0163] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0164] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0165] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned insulator detection method, and can solve the technical problem that the insulator detection result is inaccurate when the camera angle of view is offset or the algorithm detection is inaccurate in the related insulator detection method. Compared with the related art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the insulator detection method provided by the above-mentioned embodiment, and will not be repeated here.

[0166] The above descriptions are only some embodiments of the present application, and are not intended to limit the scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the protection scope of the present application.

Claims

1. An insulator detection method, characterized in that: The insulator detection method comprises: Performing target detection on the infrared thermal imaging image of the insulator string to obtain actual detection information of the insulator string, wherein the actual detection information includes the actual detection area of ​​each insulator in the insulator string; Acquire configuration detection information corresponding to the insulator string, wherein the configuration detection information includes a configuration detection area of ​​each insulator; adjusting the actual detection area according to the configured detection area to obtain an adjusted actual detection area; Based on the adjusted actual detection area, it is detected whether the insulators have temperature abnormality.

2. The insulator detection method according to claim 1, characterized in that: The actual detection information also includes the number of actually detected insulators, and the configured detection information also includes the number of configured insulators; and adjusting the actual detection area according to the configured detection area to obtain the adjusted actual detection area includes: Detecting whether the number of insulators actually detected is consistent with the number of configured insulators; If the number of insulators actually detected is inconsistent with the number of configured insulators, the actual detection area is adjusted according to the configured detection area to obtain an adjusted actual detection area.

3. The insulator detection method according to claim 2, characterized in that: The actual detection information also includes an actual detection area corresponding to the insulator string, and the configuration detection information includes a configuration detection area corresponding to the insulator string; If the number of actually detected insulators is inconsistent with the number of configured insulators, the actual detection area is adjusted according to the configured detection area, and before obtaining the adjusted actual detection area, the method further includes: Calculating a coordinate mapping relationship according to the center point coordinates of the actual detection area and the center point coordinates of the configured detection area; If the number of actually detected insulators is inconsistent with the number of configured insulators, adjusting the actual detection area according to the configured detection area to obtain the adjusted actual detection area includes: If the number of insulators actually detected is inconsistent with the number of configured insulators, the actual detection area is adjusted according to the coordinate mapping relationship and the configured detection area to obtain an adjusted actual detection area.

4. The insulator detection method according to claim 3, characterized in that: The actual detection information also includes the actual order of each insulator, and the configuration detection information also includes the configuration order of each insulator; if the number of the actually detected insulators is inconsistent with the number of configured insulators, the actual detection area is adjusted according to the coordinate mapping relationship and the configured detection area to obtain the adjusted actual detection area, including: If the number of actually detected insulators is greater than the number of configured insulators, and the actual order is different from the configured order, the tail insulator is determined according to the actual order, and the actual detection area corresponding to the tail insulator is deleted; Determine whether the actual detection area and the configured detection area satisfy the coordinate mapping relationship, and delete the actual detection area that does not satisfy the coordinate mapping relationship; After the deletion is completed, the deleted actual detection areas are reordered to obtain the adjusted actual detection areas.

5. The insulator detection method according to claim 3, characterized in that: The actual detection information also includes the actual order of each insulator, and the configuration detection information also includes the configuration order of each insulator; if the number of the actually detected insulators is inconsistent with the number of configured insulators, the actual detection area is adjusted according to the coordinate mapping relationship and the configured detection area to obtain the adjusted actual detection area, including: If the number of actually detected insulators is greater than the number of configured insulators, and the actual order is the same as the configured order, then deleting the actual detection area that is not within the actual detection area; Determine whether the actual detection area and the configured detection area satisfy the coordinate mapping relationship, and delete the actual detection area that does not satisfy the coordinate mapping relationship; After the deletion is completed, the deleted actual detection areas are reordered to obtain the adjusted actual detection areas.

6. The insulator detection method according to claim 3, characterized in that: The actual detection information also includes the actual order of each insulator, and the configuration detection information also includes the configuration order of each insulator; if the number of the actually detected insulators is inconsistent with the number of configured insulators, the actual detection area is adjusted according to the coordinate mapping relationship and the configured detection area to obtain the adjusted actual detection area, including: If the number of insulators actually detected is less than the number of configured insulators, and the actual sequence is different from the configured sequence, determining the first insulator according to the actual sequence; Supplementing the actual detection area within the preset area of ​​the first insulator according to the mapping relationship; After the supplementation is completed, the supplemented actual detection areas are reordered to obtain the adjusted actual detection areas.

7. The insulator detection method according to claim 3, characterized in that: The actual detection information also includes the actual order of each insulator, and the configuration detection information also includes the configuration order of each insulator; if the number of the actually detected insulators is inconsistent with the number of configured insulators, the actual detection area is adjusted according to the coordinate mapping relationship and the configured detection area to obtain the adjusted actual detection area, including: If the number of actually detected insulators is less than the number of configured insulators, and the actual order is the same as the configured order, mapping the configured detection area according to the coordinate mapping relationship to obtain a mapped detection area; Comparing the mapped detected area with the actual detected area, and completing the actual detected area according to the comparison result; After the padding is completed, the padded actual detection areas are reordered to obtain the adjusted actual detection areas.

8. The insulator detection method according to claim 2, characterized in that: After detecting whether the number of actually detected insulators is consistent with the number of configured insulators, the method further includes: If the number of insulators actually detected is consistent with the number of configured insulators, determining whether the area overlap rate between the actual detection area and the configured detection area exceeds a preset threshold; If the area overlap rate exceeds a preset threshold, detecting whether each insulator has temperature abnormality based on the configured detection area; If the area overlap rate does not exceed a preset threshold, then whether the temperature of each insulator is abnormal is detected based on the actual detection area.

9. The insulator detection method according to any one of claims 1 to 8, characterized in that: The obtaining of configuration detection information corresponding to the insulator string includes: Acquire camera parameters of a thermal imaging camera when acquiring the infrared thermal imaging image, wherein the camera parameters include at least one of a horizontal rotation angle, a pitch angle, and a zoom parameter; The photographed insulator string is determined according to the camera parameters, and configuration detection information corresponding to the photographed insulator string is searched.

10. The insulator detection method according to any one of claims 1 to 8, characterized in that: Before performing target detection on the infrared thermal imaging image of the insulator string to obtain actual detection information of the insulator string, the method further includes: Collecting infrared thermal imaging sample images of the insulator string, and obtaining detected sample information of the insulator string from the infrared thermal imaging sample images; Displaying the detected sample information on a target user interface, and receiving a manual configuration operation fed back by a user based on the detected sample information; The detected sample information is modified according to the manual configuration operation to obtain the configuration detection information of the insulator string.

11. An insulator detection device, characterized in that: The insulator detection device comprises: A target detection module, used to perform target detection on the infrared thermal imaging image of the insulator string to obtain actual detection information of the insulator string, wherein the actual detection information includes the actual detection area of ​​each insulator in the insulator string; An information acquisition module, used to acquire configuration detection information corresponding to the insulator string, wherein the configuration detection information includes a configuration detection area of ​​each insulator; A coordinate correction module, used for adjusting the actual detection area according to the configured detection area to obtain an adjusted actual detection area; The abnormality detection module is used to detect whether the temperature of each insulator is abnormal based on the adjusted actual detection area.

12. An insulator detection device, characterized in that: The insulator detection device comprises: a memory, a processor, and an insulator detection program stored in the memory and executable on the processor. When the insulator detection program is executed by the processor, the insulator detection method according to any one of claims 1 to 10 is implemented.

13. A storage medium, characterized in that: An insulator detection program is stored on the storage medium, and when the insulator detection program is executed by the processor, the insulator detection method according to any one of claims 1 to 10 is implemented.

Images