An insulator anomaly detection method and device, electronic equipment and storage medium

Abstract

This invention discloses an insulator anomaly detection method, device, system, and computer-readable storage medium, applied in the field of rail transit technology. To address the problems of low efficiency and low accuracy in existing insulator detection methods, it proposes acquiring a current frame visible light image and a current frame infrared image of the insulator; using a pre-established visible light image recognition model to identify the visible light insulator region in the current frame visible light image; wherein the visible light image recognition model is pre-trained based on multiple visible light sample images of the insulator; mapping the current frame infrared image onto the current frame visible light image, and identifying the infrared insulator region in the current frame infrared image based on the visible light insulator region; and performing temperature anomaly identification on the infrared insulator region to identify the insulator fault area. This invention enables automatic detection of insulator anomalies with high efficiency and accuracy, thus improving vehicle safety.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of rail transit technology, and in particular to an insulator anomaly detection method, device, system, and computer-readable storage medium. Background Technology

[0002] Insulators are key components of the high-voltage system in rail transit trains. They support the pantograph, insulate it from the roof, and ensure sufficient electrical clearance. Insulators are primarily made of epoxy resin. After a period of operation, surface contaminants accumulate, affecting their insulation performance. Under prolonged operation under varying vibration, temperature, humidity, and weather conditions, common insulator failures include surface cracks or impact cracks. Decreased insulation performance can lead to arcing, surface flashover, and in severe cases, discharge from the high-voltage system to the train body, burning the car body, short-circuiting the traction high-voltage circuit, and causing the train to lose power and stop abruptly, resulting in serious secondary accidents.

[0003] Traditional methods for detecting insulator anomalies involve technicians visually inspecting the insulators after they have completed their route and entered the depot. This is done by using a neutral cleaning agent and a cloth to wipe the insulators and conducting a visual inspection to determine if replacement is necessary. Obviously, this manual inspection method is inefficient and inaccurate, which in turn affects vehicle safety.

[0004] Therefore, improving the efficiency and accuracy of insulator anomaly detection and enhancing vehicle safety has become a problem that needs to be solved by those skilled in the art. Summary of the Invention

[0005] The purpose of this invention is to provide an insulator anomaly detection method, device, system, and computer-readable storage medium, which can automatically detect insulator anomalies during use, with high detection efficiency and accuracy, thus improving vehicle safety.

[0006] To address the aforementioned technical problems, embodiments of the present invention provide an insulator anomaly detection method, comprising:

[0007] Acquire the current frame visible light image and the current frame infrared image of the insulator;

[0008] The visible light image of the current frame is identified using a pre-established visible light image recognition model to identify the visible light insulator region; wherein, the visible light image recognition model is obtained by pre-training based on multiple visible light sample images of the insulator;

[0009] The current frame infrared image is mapped onto the current frame visible light image, and the infrared insulator region in the current frame infrared image is identified based on the visible light insulator region;

[0010] Temperature anomalies are identified in the infrared insulator region to identify faulty areas in the insulator.

[0011] In one embodiment, the step of identifying temperature anomalies in the infrared insulator region, and identifying abnormal regions on the insulator surface, includes:

[0012] Obtain the grayscale histogram corresponding to the infrared insulator region;

[0013] Based on the grayscale histogram and the preset grayscale threshold, the abnormal temperature region on the insulator surface is determined.

[0014] The abnormal temperature area on the surface of the insulator is defined as the insulator fault area.

[0015] In one embodiment, it further includes:

[0016] While acquiring the current frame infrared image, temperature data corresponding to each pixel in the current frame image is also acquired.

[0017] In one embodiment, after determining the abnormal temperature region on the insulator surface based on the grayscale histogram and a preset grayscale threshold, the method further includes:

[0018] Based on the temperature data, identify whether the abnormal temperature area on the insulator surface is a real abnormal area; if so, proceed to the next step.

[0019] In one embodiment, identifying whether the abnormal temperature region on the insulator surface is a true abnormal region based on the temperature data includes:

[0020] Based on the temperature data corresponding to the current frame infrared image and the temperature data corresponding to a preset number of previous historical frame infrared images, it is determined whether the abnormal temperature area on the insulator surface is a real abnormal area.

[0021] In one embodiment, identifying whether the temperature anomaly region on the insulator surface is a true anomaly region based on the temperature data corresponding to the current frame infrared image and the temperature data corresponding to a preset number of previous historical frame infrared images includes:

[0022] Based on the temperature data corresponding to the current frame of the infrared image, obtain the current temperature of each pixel point corresponding to the abnormal temperature area on the surface of the insulator;

[0023] For each historical frame infrared image, the historical temperature of each pixel corresponding to the abnormal temperature area on the insulator surface is obtained based on the temperature data corresponding to the historical frame infrared image.

[0024] Based on the current temperatures corresponding to the current frame infrared image and the historical temperatures corresponding to each historical frame infrared image, determine whether the abnormal temperature area on the insulator surface is a real abnormal area.

[0025] In one embodiment, determining whether the abnormal temperature region on the insulator surface is a true abnormal region based on the current temperatures corresponding to the current frame infrared image and the historical temperatures corresponding to each historical frame infrared image includes:

[0026] For each pair of adjacent infrared images in the current frame infrared image and each of the historical frame infrared images, according to the sampling time, the temperature difference for the same pixel point in the previous frame infrared image and the next frame infrared image in the pair of adjacent frames is calculated to obtain the corresponding point temperature difference.

[0027] The average point temperature difference is obtained based on the temperature difference at each of the aforementioned points;

[0028] Based on the temperature difference at each point and the first preset threshold, count the first number of points with a temperature difference greater than the first preset threshold, and calculate the first proportion of the first number relative to each current temperature.

[0029] Based on the current temperature and the second preset threshold of the current frame infrared image, count the second number of temperatures greater than the second preset threshold, and calculate the second proportion of the second number relative to each current temperature;

[0030] The average temperature is calculated based on the current temperatures of each frame of the infrared image.

[0031] Calculate each current temperature difference based on the current temperature and the average temperature.

[0032] Count the number of current temperature differences that exceed the third preset threshold, and calculate the third proportion of the third number relative to each current temperature.

[0033] When the average point temperature difference exceeds the fourth preset threshold and the first proportion exceeds the first preset ratio, or the second proportion exceeds the second preset ratio, or the third proportion exceeds the third preset ratio, the result corresponding to the group is determined to be abnormal.

[0034] When the percentage of abnormalities in the results corresponding to each group reaches a preset value, the area with abnormal temperature on the insulator surface is determined to be a real abnormal area.

[0035] This invention also provides an insulator anomaly detection device, comprising:

[0036] The first acquisition module is used to acquire the current frame visible light image and the current frame infrared image of the insulator;

[0037] The first recognition module is used to recognize the current frame of visible light image using a pre-established visible light image recognition model, and to identify the visible light insulator region; wherein, the visible light image recognition model is obtained by pre-training based on multiple visible light sample images of the insulator;

[0038] The second identification module is used to map the current frame infrared image onto the current frame visible light image, and identify the infrared insulator region in the current frame infrared image based on the visible light insulator region;

[0039] The third identification module is used to identify temperature anomalies in the infrared insulator area and identify faulty areas in the insulator.

[0040] This invention also provides an electronic device, comprising:

[0041] Memory, used to store computer programs;

[0042] A processor is used to execute the computer program to implement the steps of the insulator anomaly detection method as described above.

[0043] This invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the insulator anomaly detection method described above.

[0044] This invention provides an insulator anomaly detection method, apparatus, system, and computer-readable storage medium. The method includes: acquiring a current frame visible light image and a current frame infrared image of the insulator; using a pre-established visible light image recognition model to identify the visible light insulator region in the current frame visible light image; wherein the visible light image recognition model is pre-trained based on multiple visible light sample images of the insulator; mapping the current frame infrared image onto the current frame visible light image, and identifying the infrared insulator region in the current frame infrared image based on the visible light insulator region; and performing temperature anomaly identification on the infrared insulator region to identify the insulator fault region.

[0045] As can be seen, in this embodiment of the invention, when detecting anomalies in insulators, the current frame visible light image and the current frame infrared image of the insulator are acquired. A visible light image recognition model is used to identify the visible light insulator region in the current frame visible light image. Then, the current frame infrared image is mapped onto the current frame visible light image. Based on the visible light insulator region in the current frame infrared image, the corresponding infrared insulator region is determined. Then, temperature anomaly identification is performed on the infrared insulator region to identify the fault area of ​​the insulator. This invention can realize automatic detection of insulator anomalies with high detection efficiency and high accuracy, which is beneficial to improving vehicle safety. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the prior art and embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 A flowchart illustrating an insulator anomaly detection method provided in an embodiment of the present invention;

[0048] Figure 2 A table of temperature data for the current frame and the previous three frames of infrared images provided in this embodiment of the invention;

[0049] Figure 3 A temperature vector table diagram showing the temperature anomaly regions on the surface of the insulator in the current frame and the previous three frames of infrared images provided in this embodiment of the invention.

[0050] Figure 4 This is a schematic diagram of the structure of an insulator anomaly detection device provided in an embodiment of the present invention;

[0051] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention;

[0052] Figure 6 This is a schematic diagram of the structure of a computer-readable storage medium provided in an embodiment of the present invention. Detailed Implementation

[0053] This invention provides an insulator anomaly detection method, device, system, and computer-readable storage medium. During use, it can automatically detect insulator anomalies with high efficiency and accuracy, thereby improving vehicle safety.

[0054] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating an insulator anomaly detection method provided in an embodiment of the present invention. The method includes:

[0056] S110: Acquire the current frame visible light image and the current frame infrared image of the insulator;

[0057] It should be noted that a suitable area near the location of the roof insulator where a stable data signal stream can be collected can be selected in advance to install visible light detection equipment and infrared detection equipment. In this embodiment of the invention, visible light video of the insulator on the vehicle can be collected by visible light detection equipment, and infrared video can be collected simultaneously by infrared detection equipment. Specifically, visible light detection equipment can collect the current frame of visible light image in real time, and infrared detection equipment can collect the corresponding current frame of infrared image simultaneously.

[0058] S120: The visible light image of the current frame is identified using a pre-established visible light image recognition model to identify the visible light insulator region; wherein, the visible light image recognition model is obtained by pre-training based on multiple visible light sample images of the insulator;

[0059] It should be noted that in practical applications, a visible light image recognition model can be trained by annotating the target region based on the acquired visible light sample image of the insulator. Specifically, manual annotation of the target region can be used. Furthermore, to improve the accuracy of the trained visible light image recognition model, the original visible light image can be augmented by adding noise, rotating, and shifting transformations to obtain a visible light sample image. The target region is then manually labeled and fed into a convolutional neural network for model training. When the loss function value stabilizes, the model training ends, resulting in the visible light image recognition model. This model is then used to identify the visible light insulator region in the current frame of the visible light image.

[0060] S130: Map the current frame infrared image onto the current frame visible light image, and identify the infrared insulator region in the current frame infrared image based on the visible light insulator region;

[0061] Specifically, after obtaining the visible light insulator region based on the current frame's visible light image, the current frame's infrared image is mapped onto the current frame's visible light image. Specifically, the estimated upper-left and lower-right coordinates of the visible light insulator region can be mapped onto the current frame's infrared image of the same scale, thereby determining the corresponding infrared insulator region on the current frame's infrared image. In this invention, the visible light insulator region determined by the current frame's visible light image can more accurately determine the infrared insulator region on the current frame's infrared image, thus improving recognition accuracy.

[0062] S140: Identify temperature anomalies in the infrared insulator area and identify faulty areas in the insulator.

[0063] Specifically, after identifying the infrared insulator region on the infrared insulator image, the fault area of ​​the insulator can be determined by identifying temperature anomalies in the infrared insulator region.

[0064] As can be seen, in this embodiment of the invention, when detecting anomalies in insulators, the current frame visible light image and the current frame infrared image of the insulator are acquired. A visible light image recognition model is used to identify the visible light insulator region in the current frame visible light image. Then, the current frame infrared image is mapped onto the current frame visible light image. Based on the visible light insulator region in the current frame infrared image, the corresponding infrared insulator region is determined. Then, temperature anomaly identification is performed on the infrared insulator region to identify the fault area of ​​the insulator. This invention can realize automatic detection of insulator anomalies with high detection efficiency and high accuracy, which is beneficial to improving vehicle safety.

[0065] In one embodiment, the process of identifying temperature anomalies in the infrared insulator region in S140, specifically identifying abnormal regions on the insulator surface, may include:

[0066] Obtain the grayscale histogram corresponding to the infrared insulator region;

[0067] Based on the grayscale histogram and the preset grayscale threshold, the abnormal temperature region on the insulator surface was determined.

[0068] Areas with abnormal surface temperature of the insulator are considered as fault areas of the insulator.

[0069] It should be noted that in practical applications, grayscale histogram statistics can be performed on the infrared insulator region in the current frame of the infrared image to construct the pixel grayscale value distribution. Furthermore, the grayscale threshold of the insulator can be pre-determined based on the known insulator status. Since infrared images are thermal images of temperature, reflecting the temperature distribution on the insulator surface, abnormal insulator temperatures generally increase when an anomaly occurs, leading to an abnormal increase in thermal radiation intensity. Therefore, the grayscale values ​​of pixels radiating high energy outwards in the infrared insulator region will significantly increase. Image thresholding can be used to extract abnormally high-temperature regions on the insulator surface. Additionally, the contours of these abnormally high-temperature regions can be extracted and their areas calculated to obtain the abnormal temperature regions on the insulator surface, thereby enabling anomaly detection and identifying faulty insulator regions.

[0070] In one embodiment, the method may further include:

[0071] While acquiring the current frame of infrared image, temperature data corresponding to each pixel in the current frame image is also acquired.

[0072] Specifically, in practical applications, infrared detection devices can also collect the point temperature corresponding to each pixel in the current frame of infrared image while acquiring the current frame of infrared image, and obtain the corresponding temperature data.

[0073] In one embodiment, after determining the abnormal temperature region on the insulator surface based on the grayscale histogram and a preset grayscale threshold, the method further includes:

[0074] Based on the temperature data, identify whether the abnormal temperature area on the insulator surface is a real abnormal area; if so, proceed to the next step.

[0075] It should be noted that, in practical applications, in order to improve detection accuracy, after identifying the abnormal temperature area on the insulator surface, the abnormal temperature area on the insulator surface can be further identified based on the temperature data corresponding to the current frame of the infrared image. This determines whether the abnormal temperature area on the insulator surface is a real abnormal area. If the abnormal temperature area on the insulator surface is determined to be a real abnormal area, it can be regarded as the fault area of ​​the insulator, thereby improving the accuracy of detection and identification.

[0076] In one embodiment, the process of identifying whether an abnormal temperature region on the insulator surface is a true abnormal region based on temperature data may specifically include:

[0077] Based on the temperature data corresponding to the current frame of infrared image and the temperature data corresponding to each of the preset number of previous historical frames of infrared image, it is determined whether the temperature abnormal area on the insulator surface is a real abnormal area.

[0078] It should be noted that a preset number of previous historical infrared images preceding the current frame infrared image can be obtained, such as the previous 4 frames of historical infrared images. Specifically, based on the temperature data corresponding to the current frame infrared image and the temperature data corresponding to the preset number of previous historical infrared images, it is possible to further identify whether the abnormal temperature area on the insulator surface is a real abnormal area.

[0079] In one embodiment, the process of identifying whether an abnormal temperature region on the insulator surface is a true abnormal region based on the temperature data corresponding to the current frame infrared image and the temperature data corresponding to a preset number of previous historical frame infrared images may specifically include:

[0080] Based on the temperature data corresponding to the current frame of the infrared image, obtain the current temperature of each pixel corresponding to the abnormal temperature area on the surface of the insulator.

[0081] For each historical frame infrared image, the historical temperature of each pixel corresponding to the abnormal temperature area on the insulator surface is obtained based on the temperature data corresponding to the historical frame infrared image.

[0082] Based on the current temperatures corresponding to the current frame infrared image and the historical temperatures corresponding to each historical frame infrared image, determine whether the temperature anomaly area on the insulator surface is a real anomaly area.

[0083] It should be noted that, in this embodiment of the invention, the current temperature corresponding to each pixel in the abnormal temperature region of the insulator surface can be extracted from the temperature data corresponding to the current frame infrared image, and the historical temperature corresponding to each pixel in the abnormal temperature region of the insulator surface can also be extracted from the temperature data corresponding to the historical frame infrared image for each frame. Then, based on the current temperature and historical temperature corresponding to each pixel in the abnormal temperature region of the insulator surface, the abnormal temperature region of the insulator surface is analyzed to further determine whether the abnormal temperature region of the insulator surface is a real abnormal region.

[0084] For example, the temperature data (i.e., the temperature matrix) corresponding to the current frame of the infrared image can be stretched into a one-dimensional vector. This can be achieved by retrieving the temperature data from the current frame of the infrared image and the previous three historical infrared images, totaling four frames. Each frame corresponds to four frames of temperature data, including the current frame and historical frames. The temperature vectors of the current frame (the fourth frame) and the previous three frames are illustrated as follows: Figure 2 As shown.

[0085] By mapping the coordinates of abnormal temperature regions on the insulator surface to the temperature vectors of the current frame infrared image and the previous three frames infrared images, a feature segment of the temperature vector is formed, specifically as follows: Figure 3As shown, the temperature feature segments of the 4th frame include T4m to T4n, the temperature feature segments of the 3rd frame include T3m to T3n, the temperature feature segments of the 2nd frame include T2m to T2n, and the temperature feature segments of the 1st frame include T1m to T1n.

[0086] In one embodiment, the process of determining whether an abnormal temperature region on the insulator surface is a true abnormal region based on the current temperatures corresponding to the current frame infrared image and the historical temperatures corresponding to each historical frame infrared image may specifically include:

[0087] For each pair of adjacent infrared images in the current frame and each historical frame, according to the sampling time, the temperature difference for the same pixel in the previous frame and the next frame of the pair of adjacent infrared images is calculated to obtain the corresponding point temperature difference.

[0088] The average point temperature difference is obtained based on the temperature difference at each point.

[0089] Based on the temperature difference at each point and the first preset threshold, count the first number of points with a temperature difference greater than the first preset threshold, and calculate the first proportion of the first number relative to each current temperature.

[0090] Based on the current temperatures of the current frame infrared image and the second preset threshold, count the second number of temperatures greater than the second preset threshold, and calculate the second proportion of the second number relative to each current temperature.

[0091] Calculate the average temperature based on the current temperatures of each frame of the infrared image.

[0092] Calculate the current temperature difference based on the current temperature and the average temperature;

[0093] Count the number of current temperature differences that exceed the third preset threshold, and calculate the third proportion of the third number relative to each current temperature;

[0094] When the average point temperature difference exceeds the fourth preset threshold and the first proportion exceeds the first preset ratio, or the second proportion exceeds the second preset ratio, or the third proportion exceeds the third preset ratio, the result corresponding to the group is determined to be abnormal.

[0095] When the percentage of abnormalities in the results corresponding to each group reaches a preset value, the area with abnormal temperature on the insulator surface is determined to be a real abnormal area.

[0096] Specifically, in this embodiment of the invention, the 3rd, 2nd, and 1st frames of historical infrared images located before the 4th frame of the current infrared image are used as examples for detailed explanation:

[0097] Figure 3Each element value of each vector in the vector is called a "point temperature". The same feature extraction algorithm is used cyclically on the "point temperatures" at the same positions in frames 4 and 3, 3 and 2, and 2 and 1 respectively. The embodiment of the present invention takes frames 4 and 3 as an example for detailed description as follows:

[0098] (1) The temperature difference of each point is obtained by subtracting the "point temperature" at the same position in the previous frame. That is, the temperature difference of the point at the same position in the 4th frame is obtained by subtracting the temperature at the same position in the 3rd frame. Then, the temperature differences of each point are added together and divided by the number of "point temperatures" in the 4th frame to obtain the "average point temperature difference" temp of the previous frame (4th frame and 3rd frame). (The present invention describes the ideal situation. In actual use, invalid data and dirty data caused by sensor failure will be removed.) At the same time, each point temperature difference can be compared with a first preset threshold. When the point temperature difference exceeds the first preset threshold (corresponding alarm threshold), the corresponding temperature rise point exceeding the alarm threshold is counted by 1. The total number of temperature rise points exceeding the alarm threshold (that is, the first number of point temperature differences greater than the first preset threshold) is counted as iNumcount. The temp is calculated as follows:

[0099] Where n represents the last element in the temperature feature segment, m represents the first element in the temperature feature segment, and i represents the i-th element in the temperature feature segment.

[0100] Specifically, the first proportion p1 of the first quantity iNumcount relative to the total number of current temperatures in the feature segments extracted from the current frame infrared image can also be calculated.

[0101] (2) Based on the current temperature of each infrared image in the current frame and the second preset threshold, count the second number of points whose temperature is greater than the second preset threshold, that is, count the number of points whose actual temperature value of the current frame “point temperature” exceeds the second preset threshold, and obtain the second number (denoted as iNumcount2).

[0102] Specifically, the second proportion p2 of the second quantity relative to each current temperature can also be calculated.

[0103] (3) Calculate the average temperature based on the current temperatures of the current frame infrared image. That is, calculate the "average temperature" temp2 of each current temperature in the feature vector corresponding to the current frame infrared image;

[0104] in,

[0105] (4) Calculate the current temperature difference based on the current temperature and the average temperature. Specifically, count the difference between the current frame "point temperature" and the current frame "average point temperature" (i.e., T_4m-temp2, T_(4m+1)-temp2, ..., T_4n-temp2) to obtain the current temperature difference. Then, count the number of current temperature differences that exceed the third preset threshold, denoted as iNumcount3. The third proportion p3 of the third proportion relative to each current temperature can also be calculated.

[0106] (5) If any one of the following conditions is met: the average point temperature difference exceeds the fourth preset threshold and the first proportion exceeds the first preset ratio, or the second proportion exceeds the second preset ratio, or the third proportion exceeds the third preset ratio, the result corresponding to that group is determined to be abnormal. That is, if a) temp exceeds the fourth preset threshold and the p1 proportion exceeds the first preset ratio; or b) the p2 proportion exceeds the second preset ratio, or c) the p3 proportion exceeds the third preset ratio; or if one of the three conditions a, b, and c is met, the result of the comparison group consisting of the fourth frame and the third frame is considered abnormal, and the abnormality count can be recorded.

[0107] Based on the above steps (1) to (5), the comparison group consisting of the 3rd frame and the 2nd frame can be further analyzed to obtain the corresponding results; the comparison group consisting of the 2nd frame and the 1st frame can be analyzed to obtain the corresponding results. Then, when the proportion of abnormalities in the results corresponding to each group reaches a preset value, the abnormal temperature area on the insulator surface can be determined as a real abnormal area. Specifically, when three results corresponding to each group are determined to be abnormal, that is, when the abnormality count is recorded as 3, the abnormal temperature area on the insulator surface is determined to be a real abnormal area, thereby improving the accuracy of insulator detection.

[0108] Of course, in practical applications, the specific values ​​of the first preset threshold, the second preset threshold, the third preset threshold, the fourth preset threshold, and the preset value in the embodiments of the present invention can be determined according to actual needs, and the embodiments of the present invention do not impose any special limitations on this.

[0109] As described above, the infrared image threshold segmentation method used in this embodiment of the invention outputs suggested coordinates for the temperature matrix, thereby reducing the traversal range of the temperature matrix, eliminating invalid temperature data analysis areas, greatly improving computational efficiency, and effectively removing false alarms caused by environmental temperature acquisition distortion due to non-target distant scenes such as the sky and clouds. Furthermore, this invention effectively avoids false alarms caused by single-point temperature threshold comparisons and other factors by constructing a specific temperature feature fusion extraction method, rather than using a single temperature threshold for single-point comparison as the judgment output. Moreover, the use of multi-frame (4-frame) temperature comparison for comprehensive judgment further eliminates false alarms caused by only using two-frame comparisons in cases of sudden environmental changes.

[0110] Based on the above embodiments, this invention also provides an insulator anomaly detection device, please refer to the following for details. Figure 4 The device includes:

[0111] The first acquisition module 11 is used to acquire the current frame visible light image and the current frame infrared image of the insulator;

[0112] The first recognition module 12 is used to recognize the visible light image of the current frame using a pre-established visible light image recognition model, and to identify the visible light insulator region; wherein, the visible light image recognition model is obtained by pre-training based on multiple visible light sample images of the insulator;

[0113] The second identification module 13 is used to map the current frame infrared image onto the current frame visible light image, and identify the infrared insulator region in the current frame infrared image based on the visible light insulator region.

[0114] The third identification module 14 is used to identify temperature anomalies in the infrared insulator area and identify fault areas in the insulator.

[0115] It should be noted that the insulator anomaly detection device provided in the embodiments of the present invention has the same beneficial effects as the insulator anomaly detection method provided in the above embodiments, and for a detailed description of the insulator anomaly detection method provided in the embodiments of the present invention, please refer to the above embodiments, which will not be repeated here.

[0116] Figure 5 A structural diagram of an electronic device provided in an embodiment of this application, such as... Figure 5 As shown, the electronic device includes: a memory 20 for storing computer programs;

[0117] The processor 21 is used to execute a computer program to implement the steps of the insulator anomaly detection method as described in the above embodiment.

[0118] The electronic devices provided in this embodiment may include, but are not limited to, smartphones, tablets, laptops, or desktop computers.

[0119] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0120] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 20 is used to store at least the following computer program 201, which, after being loaded and executed by the processor 21, is capable of implementing the relevant steps of the insulator anomaly detection method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, and the storage method may be temporary or permanent storage. The operating system 202 may include Windows, Unix, Linux, etc. The data 203 may include, but is not limited to, set offsets.

[0121] In some embodiments, the electronic device may further include a display screen 22, an input / output interface 23, a communication interface 24, a power supply 25, and a communication bus 26.

[0122] Those skilled in the art will understand that Figure 5 The structures shown do not constitute a limitation on electronic devices and may include more or fewer components than those shown.

[0123] It is understood that if the insulator anomaly detection method in the above embodiments is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes: USB flash drive, mobile hard disk, read-only memory (ROM), random access memory (RAM), electrically erasable programmable ROM, register, hard disk, removable disk, CD-ROM, magnetic disk, or optical disk, and other media capable of storing program code.

[0124] Based on this, such as Figure 6 As shown, this embodiment of the invention also provides a computer-readable storage medium 30, on which a computer program 31 is stored. When the computer program 31 is executed by a processor, it implements the steps of the insulator anomaly detection method described above.

[0125] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0126] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0127] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0128] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0129] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for detecting insulator anomalies, characterized in that, include: Acquire the current frame visible light image and the current frame infrared image of the insulator, and simultaneously acquire the temperature data corresponding to each pixel in the current frame image while acquiring the current infrared image; The visible light image of the current frame is identified using a pre-established visible light image recognition model to identify the visible light insulator region; wherein, the visible light image recognition model is obtained by pre-training based on multiple visible light sample images of the insulator; The current frame infrared image is mapped onto the current frame visible light image, and the infrared insulator region in the current frame infrared image is identified based on the visible light insulator region; Temperature anomaly identification is performed on the infrared insulator area to identify insulator fault areas; The step of identifying temperature anomalies in the infrared insulator region and identifying fault areas on the insulator surface includes: Obtain the grayscale histogram corresponding to the infrared insulator region; The image thresholding method is used to determine the abnormal temperature region on the insulator surface based on the grayscale histogram and the preset grayscale threshold. Based on the temperature data corresponding to the current frame of the infrared image, obtain the current temperature of each pixel point corresponding to the abnormal temperature area on the surface of the insulator; Obtain a preset number of previous historical infrared images located before the current frame infrared image. For each historical frame infrared image, obtain the historical temperature of each pixel corresponding to the abnormal temperature area on the insulator surface based on the temperature data corresponding to the historical frame infrared image. Based on the current temperature corresponding to the current frame infrared image and the historical temperature corresponding to each historical frame infrared image, determine whether the abnormal temperature area on the insulator surface is a real abnormal area. If so, the area with abnormal temperature on the surface of the insulator shall be regarded as the fault area of ​​the insulator. The step of determining whether the abnormal temperature region on the insulator surface is a true abnormal region based on the current temperature corresponding to the current frame infrared image and the historical temperature corresponding to each historical frame infrared image includes: For each pair of adjacent infrared images in the current frame infrared image and each of the historical frame infrared images, according to the sampling time, the temperature difference for the same pixel point in the previous frame infrared image and the next frame infrared image in the pair of adjacent frames is calculated to obtain the corresponding point temperature difference. The average point temperature difference is obtained based on the temperature difference at each of the aforementioned points; Based on the temperature difference at each point and the first preset threshold, count the first number of points with a temperature difference greater than the first preset threshold, and calculate the first proportion of the first number relative to each current temperature. Based on the current temperature and the second preset threshold of the current frame infrared image, count the second number of temperatures greater than the second preset threshold, and calculate the second proportion of the second number relative to each current temperature; The average temperature is calculated based on the current temperatures of each frame of the infrared image. Calculate each current temperature difference based on the current temperature and the average temperature. Count the number of current temperature differences that exceed the third preset threshold, and calculate the third proportion of the third number relative to each current temperature. When the average point temperature difference exceeds the fourth preset threshold and the first proportion exceeds the first preset ratio, or the second proportion exceeds the second preset ratio, or the third proportion exceeds the third preset ratio, the result corresponding to the group is determined to be abnormal. When the percentage of abnormalities in the results corresponding to each group reaches a preset value, the area with abnormal temperature on the insulator surface is determined to be a real abnormal area.

2. An insulator anomaly detection device, characterized in that, include: The first acquisition module is used to acquire the current frame visible light image and the current frame infrared image of the insulator, and at the same time acquire the temperature data corresponding to each pixel in the current frame image. The first recognition module is used to recognize the current frame of visible light image using a pre-established visible light image recognition model, and to identify the visible light insulator region; wherein, the visible light image recognition model is obtained by pre-training based on multiple visible light sample images of the insulator; The second identification module is used to map the current frame infrared image onto the current frame visible light image, and identify the infrared insulator region in the current frame infrared image based on the visible light insulator region; The third identification module is used to identify temperature anomalies in the infrared insulator area and identify fault areas in the insulator. The third identification module is used for: Obtain the grayscale histogram corresponding to the infrared insulator region; The image thresholding method is used to determine the abnormal temperature region on the insulator surface based on the grayscale histogram and the preset grayscale threshold. Based on the temperature data corresponding to the current frame of the infrared image, obtain the current temperature of each pixel point corresponding to the abnormal temperature area on the surface of the insulator; Obtain a preset number of previous historical infrared images located before the current frame infrared image. For each historical frame infrared image, obtain the historical temperature of each pixel corresponding to the abnormal temperature area on the insulator surface based on the temperature data corresponding to the historical frame infrared image. Based on the current temperature corresponding to the current frame infrared image and the historical temperature corresponding to each historical frame infrared image, determine whether the abnormal temperature area on the insulator surface is a real abnormal area. The abnormal temperature area on the surface of the insulator is defined as the fault area of ​​the insulator. The step of determining whether the abnormal temperature region on the insulator surface is a true abnormal region based on the current temperature corresponding to the current frame infrared image and the historical temperature corresponding to each historical frame infrared image includes: For each pair of adjacent infrared images in the current frame infrared image and each of the historical frame infrared images, according to the sampling time, the temperature difference for the same pixel point in the previous frame infrared image and the next frame infrared image in the pair of adjacent frames is calculated to obtain the corresponding point temperature difference. The average point temperature difference is obtained based on the temperature difference at each of the aforementioned points; Based on the temperature difference at each point and the first preset threshold, count the first number of points with a temperature difference greater than the first preset threshold, and calculate the first proportion of the first number relative to each current temperature. Based on the current temperature and the second preset threshold of the current frame infrared image, count the second number of temperatures greater than the second preset threshold, and calculate the second proportion of the second number relative to each current temperature; The average temperature is calculated based on the current temperatures of each frame of the infrared image. Calculate each current temperature difference based on the current temperature and the average temperature. Count the number of current temperature differences that exceed the third preset threshold, and calculate the third proportion of the third number relative to each current temperature. When the average point temperature difference exceeds the fourth preset threshold and the first proportion exceeds the first preset ratio, or the second proportion exceeds the second preset ratio, or the third proportion exceeds the third preset ratio, the result corresponding to the group is determined to be abnormal. When the percentage of abnormalities in the results corresponding to each group reaches a preset value, the area with abnormal temperature on the insulator surface is determined to be a real abnormal area.

3. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor is configured to implement the steps of the insulator anomaly detection method as described in claim 1 when executing the computer program.

4. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the insulator anomaly detection method as described in claim 1.

Images