CN117173647A - Insulator abnormality detection method and device, electronic equipment and storage medium - Google Patents
Insulator abnormality detection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117173647A CN117173647A CN202311157556.7A CN202311157556A CN117173647A CN 117173647 A CN117173647 A CN 117173647A CN 202311157556 A CN202311157556 A CN 202311157556A CN 117173647 A CN117173647 A CN 117173647A
- Authority
- CN
- China
- Prior art keywords
- insulator
- temperature
- current frame
- visible light
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000012212 insulator Substances 0.000 title claims abstract description 207
- 238000001514 detection method Methods 0.000 title claims abstract description 57
- 230000005856 abnormality Effects 0.000 title claims description 34
- 230000002159 abnormal effect Effects 0.000 claims abstract description 91
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000012549 training Methods 0.000 claims abstract description 11
- 238000013507 mapping Methods 0.000 claims abstract description 8
- 238000004590 computer program Methods 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 9
- 238000012545 processing Methods 0.000 description 7
- 239000013598 vector Substances 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000002372 labelling Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 239000012459 cleaning agent Substances 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000010891 electric arc Methods 0.000 description 1
- 239000003822 epoxy resin Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229920000647 polyepoxide Polymers 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Radiation Pyrometers (AREA)
Abstract
The application discloses an insulator anomaly detection method, device, system and computer readable storage medium, which are applied to the technical field of rail transit and are used for solving the problems of low detection efficiency and low accuracy of the existing insulator, and providing a method for acquiring a current frame visible light image and a current frame infrared image of the insulator; the visible light image of the current frame is identified by adopting a pre-established visible light image identification model, and a visible light insulator region is identified; the visible light image recognition model is obtained by training a plurality of visible light sample images based on insulators in advance; mapping the infrared image of the current frame onto the visible light image of the current frame, and identifying an infrared insulator region in the infrared image of the current frame based on the visible light insulator region; carrying out temperature anomaly identification on the infrared insulator region, and identifying an insulator fault region; the application can realize automatic detection of the abnormal condition of the insulator, has high detection efficiency and high accuracy, and is beneficial to improving the safety of the vehicle.
Description
Technical Field
The embodiment of the application relates to the technical field of rail transit, in particular to an insulator abnormality detection method, an insulator abnormality detection device, an insulator abnormality detection system and a computer readable storage medium.
Background
The insulator is a key part of a rail transit train high-voltage system and is used for supporting the pantograph, insulating the pantograph from the roof of the train and ensuring enough electric clearance. The insulator is mainly made of epoxy resin materials, surface dirt is adhered after the insulator runs for a period of time, the insulating performance is affected, common faults of the insulator are surface cracks or impact cracks under the running backgrounds of different vibration, different temperature and humidity, different weather and the like for a long time, electric arc burning and surface flashover discharging can be caused due to the reduction of the insulating performance, a high-voltage system can be seriously caused to discharge and burn a car body, the car body is burnt, a high-voltage circuit is pulled to be in short circuit failure, and a train loses power and stops suddenly to cause a secondary major accident.
According to the traditional insulator anomaly detection method, after a current traffic task of an operating train is completed and put in storage, a technician climbs the top to perform visual detection, the neutral cleaning agent and the rag are used for wiping the insulator to match with appearance detection to determine whether the insulator needs to be replaced or not, and the detection efficiency and accuracy are obviously affected in a manual detection mode, so that the safety of the vehicle is affected.
In view of this, how to improve the efficiency and accuracy of insulator abnormality detection and to improve the safety of a vehicle is a problem that needs to be solved by those skilled in the art.
Disclosure of Invention
The embodiment of the application aims to provide an insulator abnormality detection method, device and system and a computer readable storage medium, which can realize automatic detection of insulator abnormality in the use process, and are high in detection efficiency and accuracy and beneficial to improving vehicle safety.
In order to solve the above technical problems, an embodiment of the present application provides a method for detecting insulator abnormality, including:
collecting a current frame visible light image and a current frame infrared image of an insulator;
the visible light image of the current frame is identified by adopting a pre-established visible light image identification model, and a visible light insulator region is identified; the visible light image recognition model is obtained by training a plurality of visible light sample images based on insulators in advance;
mapping the infrared image of the current frame onto the visible light image of the current frame, and identifying an infrared insulator region in the infrared image of the current frame based on the visible light insulator region;
and carrying out temperature anomaly identification on the infrared insulator region to identify an insulator fault region.
In one embodiment, the identifying the abnormal area of the surface of the insulator by identifying the abnormal temperature of the infrared insulator area includes:
acquiring a gray level histogram corresponding to the infrared insulator region;
determining an abnormal area of the surface temperature of the insulator based on the gray histogram and a preset gray threshold;
and taking the abnormal surface temperature area of the insulator as an insulator fault area.
In one embodiment, further comprising:
and acquiring temperature data corresponding to each pixel point in the current frame image while acquiring the current frame infrared image.
In one embodiment, after determining the abnormal region of the insulator surface temperature based on the gray histogram and the preset gray threshold, the method further includes:
based on the temperature data, identifying whether the insulator surface temperature abnormal region is a real abnormal region; if yes, executing the next step.
In one embodiment, the identifying whether the insulator surface temperature anomaly area is a true anomaly area based on the temperature data includes:
and identifying whether the insulator surface temperature abnormal region is a real abnormal region or not based on the temperature data corresponding to the current frame infrared image and the temperature data corresponding to the history frame infrared images before the preset number.
In one embodiment, the identifying whether the insulator surface temperature anomaly area is a real anomaly area based on temperature data corresponding to the current frame of infrared images and temperature data corresponding to each of a preset number of previous historical frame of infrared images includes:
acquiring the current temperature of each pixel point corresponding to the insulator surface temperature abnormal region according to the temperature data corresponding to the infrared image of the current frame;
acquiring the historical temperature of each pixel point corresponding to the insulator surface temperature abnormal region according to the temperature data corresponding to the historical frame infrared image of each frame;
and determining whether the insulator surface temperature abnormal region is a real abnormal region according to each current temperature corresponding to the current frame infrared image and each historical temperature corresponding to each historical frame infrared image.
In one embodiment, the determining whether the abnormal area of the surface temperature of the insulator is a real abnormal area according to the current temperatures corresponding to the infrared images of the current frame and the historical temperatures corresponding to the infrared images of each historical frame includes:
for each group of two adjacent infrared images in the current frame infrared image and each history frame infrared image, according to sampling time sequence, the temperature of the previous frame infrared image and the temperature of the same pixel point in the next frame infrared image in the group of two adjacent infrared images are subjected to difference to obtain a corresponding point temperature difference;
obtaining an average point temperature difference according to the point temperature differences;
based on the point temperature differences and a first preset threshold, counting a first number of point temperature differences larger than the first preset threshold, and calculating a first duty ratio of the first number relative to the current temperature;
counting a second number of the temperatures greater than a second preset threshold according to the current temperatures of the infrared images of the current frame and the second preset threshold, and calculating a second duty ratio of the second number relative to the current temperatures;
calculating an average temperature according to each current temperature of the current frame infrared image;
calculating each current temperature difference according to each current temperature and the average temperature;
counting a third quantity of the current temperature difference exceeding a third preset threshold value, and calculating a third duty ratio of the third quantity relative to each current temperature;
when the average point temperature difference exceeds a fourth preset threshold value and the first duty ratio exceeds a first preset ratio, or the second duty ratio exceeds a second preset ratio, or the third duty ratio exceeds a third preset ratio, determining that a result corresponding to the group is abnormal;
and in the results corresponding to each group, determining that the abnormal area of the surface temperature of the insulator is a real abnormal area when the abnormal duty ratio reaches a preset value.
The embodiment of the application also provides an insulator abnormality detection device, which comprises:
the first acquisition module is used for acquiring a current frame visible light image and a current frame infrared image of the insulator;
the first recognition module is used for recognizing the current frame visible light image by adopting a pre-established visible light image recognition model, and recognizing a visible light insulator region; the visible light image recognition model is obtained by training a plurality of visible light sample images based on insulators in advance;
the second identification module is used for mapping the infrared image of the current frame onto the visible light image of the current frame and identifying an infrared insulator region in the infrared image of the current frame based on the visible light insulator region;
and the third identification module is used for carrying out temperature abnormality identification on the infrared insulator region and identifying an insulator fault region.
The embodiment of the application also provides electronic equipment, which comprises:
a memory for storing a computer program;
and a processor for implementing the steps of the insulator abnormality detection method as described above when executing the computer program.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the steps of the insulator abnormality detection method when being executed by a processor.
The embodiment of the application provides a method, a device and a system for detecting insulator abnormality and a computer readable storage medium, wherein the method comprises the following steps: collecting a current frame visible light image and a current frame infrared image of an insulator; the visible light image of the current frame is identified by adopting a pre-established visible light image identification model, and a visible light insulator region is identified; the visible light image recognition model is obtained by training a plurality of visible light sample images based on insulators in advance; mapping the infrared image of the current frame onto the visible light image of the current frame, and identifying an infrared insulator region in the infrared image of the current frame based on the visible light insulator region; and carrying out temperature anomaly identification on the infrared insulator region, and identifying an insulator fault region.
When the insulator is detected abnormally, the current frame visible light image and the current frame infrared image of the insulator are acquired, the current frame visible light image is identified by adopting a visible light image identification model, a visible light insulator region is identified, then the current frame infrared image is mapped to the current frame visible light image, a corresponding infrared insulator region is determined according to the visible light insulator region in the current frame infrared image, and then the temperature abnormality identification is carried out on the infrared insulator region, so that an insulator fault region is identified; the application can realize automatic detection of the abnormal condition of the insulator, has high detection efficiency and high accuracy, and is beneficial to improving the safety of the vehicle.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required in the prior art and the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of an insulator abnormality detection method according to an embodiment of the present application;
FIG. 2 is a table diagram of temperature data of infrared images of a current frame and a previous 3 frames according to an embodiment of the present application;
FIG. 3 is a table diagram of temperature vectors corresponding to an abnormal area of the surface temperature of an insulator in infrared images of a current frame and a previous 3 frames according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an insulator abnormality detection device according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a computer readable storage medium according to an embodiment of the present application.
Detailed Description
The embodiment of the application provides an insulator abnormality detection method, an insulator abnormality detection device, an insulator abnormality detection system and a computer readable storage medium, which can realize automatic detection of insulator abnormality in the use process, have high detection efficiency and high accuracy, and are beneficial to improving the safety of vehicles.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1, fig. 1 is a flow chart of an insulator anomaly detection method according to an embodiment of the present application. The method comprises the following steps:
s110: collecting a current frame visible light image and a current frame infrared image of an insulator;
in the embodiment of the application, the visible light detection equipment can be used for collecting the visible light video of the insulator on the vehicle, and simultaneously the infrared detection equipment can be used for synchronously collecting the infrared video, specifically, the visible light image of the current frame can be collected in real time through the visible light detection equipment, and simultaneously the infrared image of the corresponding current frame can be synchronously collected through the infrared detection equipment.
S120: the visible light image of the current frame is identified by adopting a pre-established visible light image identification model, and a visible light insulator region is identified; the visible light image recognition model is obtained by training a plurality of visible light sample images based on insulators in advance;
in practical application, the visible light image recognition model can be obtained by training after labeling the target area according to the obtained visible light sample image of the insulator, and specifically, the labeling of the target area can be performed by adopting a manual labeling mode. In addition, in order to improve the accuracy of the trained visible light image recognition model, after the data enhancement of the original visible light image is performed through noise adding, rotation and offset transformation, a visible light sample image is obtained, a target area is manually calibrated and sent into a convolutional neural network to perform model training, when a loss function loss value tends to be stable, the model training is finished, so that the visible light image recognition model is obtained, then the visible light image recognition model is adopted to recognize the visible light image of the current frame, and a visible light insulator area is recognized.
S130: mapping the infrared image of the current frame onto the visible light image of the current frame, and identifying an infrared insulator region in the infrared image of the current frame based on the visible light insulator region;
specifically, after the visible light insulator region is obtained based on the visible light image of the current frame, the infrared image of the current frame is mapped onto the visible light image of the current frame, and specifically, the coordinates of the upper left corner and the lower right corner estimated by the visible light insulator region can be mapped onto the infrared image of the current frame with the same scale, so that the corresponding infrared insulator region is determined on the infrared image of the current frame. According to the application, the infrared insulator region can be more accurately determined on the infrared image of the current frame through the visible light insulator region determined by the visible light image of the current frame, so that the identification accuracy is improved.
S140: and carrying out temperature anomaly identification on the infrared insulator region, and identifying an insulator fault region.
Specifically, after the infrared insulator region is determined on the infrared insulator image, the infrared insulator region can be identified by temperature abnormality, so that the insulator fault region is determined.
When the insulator is detected abnormally, the current frame visible light image and the current frame infrared image of the insulator are acquired, the current frame visible light image is identified by adopting a visible light image identification model, a visible light insulator region is identified, then the current frame infrared image is mapped to the current frame visible light image, a corresponding infrared insulator region is determined according to the visible light insulator region in the current frame infrared image, and then the temperature abnormality identification is carried out on the infrared insulator region, so that an insulator fault region is identified; the application can realize automatic detection of the abnormal condition of the insulator, has high detection efficiency and high accuracy, and is beneficial to improving the safety of the vehicle.
In one embodiment, the process of identifying the abnormal area on the surface of the insulator by identifying the abnormal temperature of the infrared insulator area in S140 may specifically include:
acquiring a gray histogram corresponding to the infrared insulator region;
determining an abnormal area of the surface temperature of the insulator based on the gray histogram and a preset gray threshold;
and taking the abnormal surface temperature area of the insulator as an insulator fault area.
In practical application, gray histogram statistics can be performed on the infrared insulator region in the infrared image of the current frame, pixel gray value distribution is constructed, and an insulator gray threshold value can be determined in advance according to the insulator state of the known label. The infrared image is a thermal imaging image of temperature, the temperature distribution of the surface of the insulator is reflected, the insulator is generally represented as abnormal temperature rise when abnormal occurs, the heat radiation intensity of the insulator is abnormally increased, so that the gray value of a pixel region with high energy of external radiation in the infrared insulator region is obviously increased, the abnormal high-temperature region of the surface of the insulator can be extracted by adopting an image threshold segmentation method, the outline of the abnormal high-temperature region of the surface of the insulator can be extracted, the area of the region can be calculated, and the abnormal temperature region of the surface of the insulator can be obtained, thereby realizing abnormal detection of the insulator and obtaining the fault region of the insulator.
In one embodiment, the method may further comprise:
and acquiring temperature data corresponding to each pixel point in the current frame image while acquiring the current frame infrared image.
Specifically, in practical application, the infrared detection device can collect the point temperature corresponding to each pixel point on the infrared image of the current frame while collecting the infrared image of the current frame, so as to obtain corresponding temperature data.
In one embodiment, after determining the abnormal region of the insulator surface temperature based on the gray histogram and the preset gray threshold value, the method further includes:
based on the temperature data, identifying whether the temperature abnormal area on the surface of the insulator is a real abnormal area; if yes, executing the next step.
In practical application, in order to improve detection accuracy, after determining the abnormal area of the surface temperature of the insulator, the abnormal area of the surface temperature of the insulator may be further identified according to temperature data corresponding to the infrared image of the current frame, whether the abnormal area of the surface temperature of the insulator is a real abnormal area is determined, and when determining that the abnormal area of the surface temperature of the insulator is a real abnormal area, the abnormal area of the surface temperature of the insulator is taken as an insulator fault area, so that accuracy of detection and identification is improved.
In an embodiment, the process of identifying whether the abnormal temperature area on the surface of the insulator is a real abnormal area based on the temperature data may include:
and identifying whether the surface temperature abnormal region of the insulator is a real abnormal region or not based on the temperature data corresponding to the infrared images of the current frame and the temperature data corresponding to the infrared images of the historical frames before the preset number.
It should be noted that, a preset number of front history frame infrared images located before the current frame infrared image may be obtained, for example, the history frame infrared images of the front 4 frames may be obtained, and specifically, whether the surface temperature abnormal area of the insulator is a real abnormal area may be further identified according to the temperature data corresponding to the current frame infrared image and the temperature data corresponding to the preset number of front history frame infrared images.
In an embodiment, the process of identifying whether the abnormal temperature area on the surface of the insulator is a real abnormal area based on the temperature data corresponding to the infrared image of the current frame and the temperature data corresponding to the infrared images of the history frame before the preset number of the infrared images of the history frame specifically may include:
acquiring the current temperature of each pixel point corresponding to the abnormal temperature area on the surface of the insulator according to the temperature data corresponding to the infrared image of the current frame;
acquiring the historical temperature of each pixel point corresponding to the insulator surface temperature abnormal region according to the temperature data corresponding to the historical frame infrared image of each frame;
and determining whether the surface temperature abnormal region of the insulator is a real abnormal region according to each current temperature corresponding to the infrared image of the current frame and each historical temperature corresponding to the infrared image of each historical frame.
It should be noted that in the embodiment of the present application, the current temperature corresponding to each pixel point in the abnormal area of the surface of the insulator may be extracted from the temperature data corresponding to the infrared image of the current frame, and the historical temperature corresponding to each pixel point in the abnormal area of the surface of the insulator may be also extracted from the temperature data corresponding to the infrared image of the historical frame for each infrared image of the historical frame, and then the abnormal area of the surface of the insulator may be analyzed according to the current temperature corresponding to each pixel point in the abnormal area of the surface of the insulator and each historical temperature, so as to further determine whether the abnormal area of the surface of the insulator is a real abnormal area.
For example, stretching temperature data (i.e. a temperature matrix) corresponding to the infrared image of the current frame into a one-dimensional vector, for example, acquiring the infrared image of the current frame and the historical infrared image of the previous 3 frames from a buffer memory, wherein the total temperature data of the infrared image of 4 frames is 4 frames of temperature data of each frame of image corresponding to the current frame and the historical frame; the temperature vectors of the current frame (4 th frame) and the previous 3 frames are schematically shown in fig. 2.
The characteristic segments of the temperature vectors are formed by mapping the coordinates of the temperature anomaly area on the surface of the insulator to the temperature vectors of the infrared image of the current frame and the infrared image of the previous 3 frames, as shown in fig. 3, wherein the temperature characteristic segment of the 4 th frame comprises T4m to T4n, the temperature characteristic segment of the 3 rd frame comprises T3m to T3n, the temperature characteristic segment of the 2 nd frame comprises T2m to T2n, and the temperature characteristic segment of the 1 st frame comprises T1m to T1n.
In an embodiment, the process of determining whether the abnormal area of the surface temperature of the insulator is a real abnormal area according to the current temperatures corresponding to the infrared image of the current frame and the historical temperatures corresponding to the infrared image of each historical frame may specifically include:
for each group of two adjacent infrared images in the current frame infrared image and each historical frame infrared image, according to sampling time sequence, the temperature of the previous frame infrared image in the group of two adjacent infrared images and the temperature of the same pixel point in the next frame infrared image are subjected to difference, and corresponding point temperature difference is obtained;
obtaining an average point temperature difference according to the temperature differences based on the points;
based on the temperature differences of all the points and a first preset threshold value, counting a first quantity of the temperature differences of the points larger than the first preset threshold value, and calculating a first duty ratio of the first quantity relative to each current temperature;
according to each current temperature of the current frame infrared image and a second preset threshold value, counting a second number of which the temperature is larger than the second preset threshold value, and calculating a second duty ratio of the second number relative to each current temperature;
calculating an average temperature according to each current temperature of the infrared image of the current frame;
calculating each current temperature difference according to each current temperature and the average temperature;
counting a third quantity of the current temperature difference exceeding a third preset threshold value, and calculating a third duty ratio of the third quantity relative to each current temperature;
when the average point temperature difference exceeds a fourth preset threshold value and the first duty ratio exceeds a first preset ratio, or the second duty ratio exceeds a second preset ratio, or the third duty ratio exceeds a third preset ratio, determining that the result corresponding to the group is abnormal;
and in the results corresponding to each group, determining that the abnormal area of the surface temperature of the insulator is a real abnormal area when the abnormal duty ratio reaches a preset value.
Specifically, in the embodiment of the present application, a 3 rd frame, a 2 nd frame and a 1 st frame of a three-frame historical infrared image located before a 4 th frame of an infrared image of a current frame are taken as examples to describe in detail:
each element value of each vector in fig. 3 is called "point temperature", and the same feature extraction algorithm is adopted by the "point temperature" cycle of the same positions of the 4 th frame and the 3 rd frame, the 3 rd frame and the 2 nd frame, and the 2 nd frame and the 1 st frame, respectively, and the embodiment of the present application takes the 4 th frame and the 3 rd frame as examples as follows:
(1) Obtaining each point temperature difference through the difference of the point temperatures at the same position of the back and front frames, namely, obtaining the point temperature difference corresponding to each position by the difference of the point temperatures at the same position of the 4 th frame and the 3 rd frame, then adding the point temperature differences, dividing by the number of the point temperatures in the 4 th frame to obtain an image average point temperature temp of the back and front frames (the 4 th frame and the 3 rd frame) (wherein the application is described as ideal condition, invalid data and dirty data generated by sensor faults and the like can be removed in actual use); meanwhile, the temperature difference of each point can be compared with a first preset threshold value, when the temperature difference of the point exceeds the first preset threshold value (corresponding alarm threshold value), the corresponding temperature rising point exceeding the alarm threshold value is increased by 1 count, and the number of all the temperature rising points exceeding the alarm threshold value (namely, the first number that the temperature difference of the statistical point is larger than the first preset threshold value) is counted as iNumcount; wherein temp is calculated as follows:
where n represents the last element in the temperature signature, m represents the first element in the temperature signature, and i represents the i-th element in the temperature signature.
Specifically, a first duty ratio p1 of the first number nnumcount relative to the total number of the current temperatures in the feature segments extracted from the infrared image of the current frame may also be calculated.
(2) Counting a second number of points with the temperature being greater than a second preset threshold according to each current temperature of the infrared image of the current frame and the second preset threshold, namely counting the number of points with the actual temperature value of the point temperature of the current frame exceeding the second preset threshold to obtain a second number (marked as iNumcount 2);
specifically, a second duty cycle p2 of the second number with respect to each current temperature may also be calculated.
(3) And calculating the average temperature according to each current temperature of the infrared image of the current frame. That is, calculating an average temperature temp2 of each current temperature in the feature vector corresponding to the infrared image of the current frame;
wherein,
(4) And calculating each current temperature difference according to each current temperature and the average temperature. Specifically, the difference between the "point temperature" of the current frame and the "average point temperature" of the current frame (i.e., t_4m—temp2, t_ (4m+1) -temp2,) is counted to obtain each current temperature difference, and then a third amount that the current temperature difference exceeds a third preset threshold is counted and recorded as nnumcount 3. A third duty cycle p3 of the third quantity with respect to the respective current temperature may also be calculated.
(5) And when the average point temperature difference exceeds a fourth preset threshold value and the first duty ratio exceeds a first preset ratio, or the second duty ratio exceeds a second preset ratio, or the third duty ratio exceeds a third preset ratio, determining that the result corresponding to the group is abnormal. That is, if a, temp is met to exceed the fourth preset threshold and the p1 duty cycle exceeds the first preset ratio; or b, p2 ratio exceeds a second preset ratio, or c, p3 ratio exceeds a third preset ratio; a. the b and c3 cases satisfy 1 and are regarded as abnormal results of the comparison group consisting of the 4 th frame and the 3 rd frame, and an abnormal count may be recorded.
Based on the steps (1) to (5), a comparison group formed by the 3 rd frame and the 2 nd frame can be further analyzed to obtain a corresponding result; and analyzing the comparison group formed by the 2 nd frame and the 1 st frame to obtain corresponding results, and determining that the abnormal temperature area of the surface of the insulator is a real abnormal area when the abnormal duty ratio reaches a preset value in the results corresponding to each group. Specifically, when it is determined that three results corresponding to each group are abnormal, that is, when the recorded abnormal count is 3, it is determined that the abnormal area of the surface temperature of the insulator is a real abnormal area, so that the accuracy of insulator detection is improved.
Of course, in practical application, 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 embodiment of the present application may be determined according to actual needs, which is not limited in particular.
As can be seen from the above, in the embodiment of the present application, the method of using the threshold segmentation of the infrared image outputs the region suggestion coordinates, so that the traversal range of the temperature matrix can be reduced, the invalid temperature data analysis region is deleted, the calculation efficiency is greatly improved, and the false alarm caused by the environmental temperature acquisition distortion of the non-target distant view such as sky, cloud, etc. is effectively removed. In addition, the application effectively avoids the false alarm phenomenon caused by single-point temperature jump, data disturbance and the like by constructing a specific temperature characteristic fusion extraction method instead of a single-point comparison mode of a single temperature threshold value as judgment output, and further eliminates the false alarm phenomenon caused by the condition of environmental mutation and the like by adopting a multi-frame (4-frame) temperature comparison comprehensive judgment mode.
On the basis of the foregoing embodiment, the embodiment of the present application further provides an insulator anomaly detection device, referring specifically to fig. 4, where the device includes:
the first acquisition module 11 is used for acquiring a current frame visible light image and a current frame infrared image of the insulator;
the first recognition module 12 is configured to recognize a visible light image of a current frame by using a pre-established visible light image recognition model, and recognize a visible light insulator region; the visible light image recognition model is obtained by training a plurality of visible light sample images based on insulators in advance;
the second identifying module 13 is configured to map the current frame infrared image onto the current frame visible light image, and identify an infrared insulator region in the current frame infrared image based on the visible light insulator region;
and the third identification module 14 is used for identifying temperature abnormality of the infrared insulator region and identifying an insulator fault region.
It should be noted that, the insulator abnormality detection device provided in the embodiment of the present application has the same advantages as the insulator abnormality detection method provided in the above embodiment, and for the specific description of the insulator abnormality detection method provided in the embodiment of the present application, reference is made to the above embodiment, and the disclosure is not repeated here.
Fig. 5 is a block diagram of an electronic device according to an embodiment of the present application, where, as shown in fig. 5, the electronic device includes: a memory 20 for storing a computer program;
a processor 21 for implementing the steps of the insulator abnormality detection method of the above embodiment when executing a computer program.
The electronic device provided in this embodiment may include, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, or the like.
Processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 may be implemented in at least one hardware form of DSP (Digital Signal Processing ), FPGA (Field-Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array ). The processor 21 may also comprise a main processor, which is a processor for processing data in an awake state, also called CPU (Central Processing Unit ); a coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 21 may integrate a GPU (Graphics Processing Unit, image processor) for rendering and drawing of content required to be displayed by the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence ) processor for processing computing operations related to machine learning.
Memory 20 may include one or more computer-readable storage media, which may be non-transitory. Memory 20 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In this embodiment, the memory 20 is at least used for storing a computer program 201, which, when loaded and executed by the processor 21, is capable of implementing the relevant steps of the insulator anomaly detection method disclosed in any one of the foregoing embodiments. In addition, the resources stored in the memory 20 may further include an operating system 202, data 203, and the like, where the storage manner may be transient storage or permanent storage. The operating system 202 may include Windows, unix, linux, among others. The data 203 may include, but is not limited to, a set offset, etc.
In some embodiments, the electronic device may further include a display 22, an input-output interface 23, a communication interface 24, a power supply 25, and a communication bus 26.
Those skilled in the art will appreciate that the structure shown in fig. 5 is not limiting of the electronic device and may include more or fewer components than shown.
It will be appreciated that if the insulator anomaly detection method in the above-described embodiment is implemented in the form of a software functional unit and sold or used as a separate product, it may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in part or in whole or in part in the form of a software product stored in a storage medium for performing all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random-access Memory (Random Access Memory, RAM), an electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, a magnetic disk, or an optical disk, etc. various media capable of storing program codes.
Based on this, as shown in fig. 6, the embodiment of the present application further provides a computer readable storage medium, on which a computer program 31 is stored in the computer readable storage medium 30, and the computer program 31 implements the steps of the insulator abnormality detection method described above when executed by a processor.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
It should also be noted that in this specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended 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 (10)
1. An insulator anomaly detection method, characterized by comprising:
collecting a current frame visible light image and a current frame infrared image of an insulator;
the visible light image of the current frame is identified by adopting a pre-established visible light image identification model, and a visible light insulator region is identified; the visible light image recognition model is obtained by training a plurality of visible light sample images based on insulators in advance;
mapping the infrared image of the current frame onto the visible light image of the current frame, and identifying an infrared insulator region in the infrared image of the current frame based on the visible light insulator region;
and carrying out temperature anomaly identification on the infrared insulator region to identify an insulator fault region.
2. The method for detecting insulator anomalies according to claim 1, wherein the identifying the insulator surface anomalies by identifying the infrared insulator regions includes:
acquiring a gray level histogram corresponding to the infrared insulator region;
determining an abnormal area of the surface temperature of the insulator based on the gray histogram and a preset gray threshold;
and taking the abnormal surface temperature area of the insulator as an insulator fault area.
3. The insulator abnormality detection method according to claim 1, further comprising:
and acquiring temperature data corresponding to each pixel point in the current frame image while acquiring the current frame infrared image.
4. The insulator anomaly detection method according to claim 3, further comprising, after the insulator surface temperature anomaly region is determined based on the gray level histogram and a preset gray level threshold value:
based on the temperature data, identifying whether the insulator surface temperature abnormal region is a real abnormal region; if yes, executing the next step.
5. The insulator anomaly detection method of claim 3, wherein the identifying whether the insulator surface temperature anomaly region is a true anomaly region based on the temperature data comprises:
and identifying whether the insulator surface temperature abnormal region is a real abnormal region or not based on the temperature data corresponding to the current frame infrared image and the temperature data corresponding to the history frame infrared images before the preset number.
6. The method according to claim 5, wherein the identifying whether the insulator surface temperature anomaly area is a true anomaly area based on temperature data corresponding to the current frame of infrared image and temperature data corresponding to each of a predetermined number of previous historical frames of infrared images, comprises:
acquiring the current temperature of each pixel point corresponding to the insulator surface temperature abnormal region according to the temperature data corresponding to the infrared image of the current frame;
acquiring the historical temperature of each pixel point corresponding to the insulator surface temperature abnormal region according to the temperature data corresponding to the historical frame infrared image of each frame;
and determining whether the insulator surface temperature abnormal region is a real abnormal region according to each current temperature corresponding to the current frame infrared image and each historical temperature corresponding to each historical frame infrared image.
7. The method according to claim 6, wherein determining whether the insulator surface temperature anomaly area is a true anomaly area according to each current temperature corresponding to the current frame infrared image and each historical temperature corresponding to each historical frame infrared image comprises:
for each group of two adjacent infrared images in the current frame infrared image and each history frame infrared image, according to sampling time sequence, the temperature of the previous frame infrared image and the temperature of the same pixel point in the next frame infrared image in the group of two adjacent infrared images are subjected to difference to obtain a corresponding point temperature difference;
obtaining an average point temperature difference according to the point temperature differences;
based on the point temperature differences and a first preset threshold, counting a first number of point temperature differences larger than the first preset threshold, and calculating a first duty ratio of the first number relative to the current temperature;
counting a second number of the temperatures greater than a second preset threshold according to the current temperatures of the infrared images of the current frame and the second preset threshold, and calculating a second duty ratio of the second number relative to the current temperatures;
calculating an average temperature according to each current temperature of the current frame infrared image;
calculating each current temperature difference according to each current temperature and the average temperature;
counting a third quantity of the current temperature difference exceeding a third preset threshold value, and calculating a third duty ratio of the third quantity relative to each current temperature;
when the average point temperature difference exceeds a fourth preset threshold value and the first duty ratio exceeds a first preset ratio, or the second duty ratio exceeds a second preset ratio, or the third duty ratio exceeds a third preset ratio, determining that a result corresponding to the group is abnormal;
and in the results corresponding to each group, determining that the abnormal area of the surface temperature of the insulator is a real abnormal area when the abnormal duty ratio reaches a preset value.
8. An insulator abnormality detection device, characterized by comprising:
the first acquisition module is used for acquiring a current frame visible light image and a current frame infrared image of the insulator;
the first recognition module is used for recognizing the current frame visible light image by adopting a pre-established visible light image recognition model, and recognizing a visible light insulator region; the visible light image recognition model is obtained by training a plurality of visible light sample images based on insulators in advance;
the second identification module is used for mapping the infrared image of the current frame onto the visible light image of the current frame and identifying an infrared insulator region in the infrared image of the current frame based on the visible light insulator region;
and the third identification module is used for carrying out temperature abnormality identification on the infrared insulator region and identifying an insulator fault region.
9. An electronic device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the insulator abnormality detection method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the insulator abnormality detection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311157556.7A CN117173647A (en) | 2023-09-08 | 2023-09-08 | Insulator abnormality detection method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311157556.7A CN117173647A (en) | 2023-09-08 | 2023-09-08 | Insulator abnormality detection method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117173647A true CN117173647A (en) | 2023-12-05 |
Family
ID=88944648
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311157556.7A Pending CN117173647A (en) | 2023-09-08 | 2023-09-08 | Insulator abnormality detection method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117173647A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117969533A (en) * | 2024-03-27 | 2024-05-03 | 宁德时代新能源科技股份有限公司 | Insulation coating detection method, device, system, equipment and storage medium |
-
2023
- 2023-09-08 CN CN202311157556.7A patent/CN117173647A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117969533A (en) * | 2024-03-27 | 2024-05-03 | 宁德时代新能源科技股份有限公司 | Insulation coating detection method, device, system, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108182383B (en) | Vehicle window detection method and device | |
| CN109284674A (en) | A kind of method and device of determining lane line | |
| CN111126165B (en) | Black smoke vehicle detection method and device and electronic equipment | |
| CN110346699B (en) | Insulator discharge information extraction method and device based on ultraviolet image processing technology | |
| CN108399403B (en) | Vehicle distance detection method based on license plate size calculation | |
| CN109376740A (en) | A kind of water gauge reading detection method based on video | |
| CN110458126B (en) | Pantograph state monitoring method and device | |
| CN117173647A (en) | Insulator abnormality detection method and device, electronic equipment and storage medium | |
| CN101738394A (en) | Method and system for detecting indoor smog | |
| CN111723656B (en) | Smog detection method and device based on YOLO v3 and self-optimization | |
| CN107564018A (en) | It is a kind of to utilize the method for improving iterative algorithm extraction target image | |
| CN111145222A (en) | Fire detection method combining smoke movement trend and textural features | |
| CN111275040A (en) | Positioning method and device, electronic equipment and computer readable storage medium | |
| CN108109146A (en) | A kind of pavement marker line defect detection device | |
| CN105469054A (en) | Model construction method of normal behaviors and detection method of abnormal behaviors | |
| CN110458144A (en) | Object area intrusion detection method, system, device and readable storage medium storing program for executing | |
| CN108921826A (en) | The transmission line of electricity that super-pixel segmentation is combined with deep learning invades object detecting method | |
| CN115239646A (en) | Defect detection method and device for power transmission line, electronic equipment and storage medium | |
| CN112784642B (en) | Vehicle detection method and device | |
| CN116434346A (en) | Method and device for detecting customer behaviors in unattended store and storage medium | |
| CN113362330B (en) | Pantograph cavel real-time detection method, device, computer equipment and storage medium | |
| CN115063765A (en) | Road side boundary determining method, device, equipment and storage medium | |
| CN114757888A (en) | Windshield dirt detection method based on textural features | |
| CN111160224B (en) | High-speed rail contact net foreign matter detection system and method based on FPGA and horizon line segmentation | |
| CN113643234A (en) | Composite insulator damage detection method, terminal equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |