CN109900366A - A kind of method and device detecting arrester temperature anomaly point - Google Patents
A kind of method and device detecting arrester temperature anomaly point Download PDFInfo
- Publication number
- CN109900366A CN109900366A CN201910221734.5A CN201910221734A CN109900366A CN 109900366 A CN109900366 A CN 109900366A CN 201910221734 A CN201910221734 A CN 201910221734A CN 109900366 A CN109900366 A CN 109900366A
- Authority
- CN
- China
- Prior art keywords
- point
- arrester
- pixel
- temperature
- temperature value
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000001514 detection method Methods 0.000 claims abstract description 74
- 238000003860 storage Methods 0.000 claims abstract description 17
- 239000003550 marker Substances 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 11
- 238000012800 visualization Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims 1
- 230000002159 abnormal effect Effects 0.000 abstract description 13
- 230000000694 effects Effects 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 5
- 238000013136 deep learning model Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Landscapes
- Radiation Pyrometers (AREA)
Abstract
本发明公开了一种检测避雷器温度异常点的方法，包括：获取标注有检测区域的避雷器红外图像，并获取避雷器红外图像中的检测区域内的所有像素点对应的温度值，组成温度值集合；遍历温度值集合，将温度值集合中高于平均值的温度值对应的像素点确定为目标像素点，得到目标像素点集合；根据不同目标像素点之间的欧氏距离，将目标像素点集合中的目标像素点划分为多个像素组；将像素点个数超过预设阈值的像素组覆盖的区域标记为温度异常点。该方法实现了避雷器温度异常点的自动检测，提高了检测效率和准确率，在一定程度上可避免电力事故的发生。相应地，本发明公开的一种检测避雷器温度异常点的装置、设备及可读存储介质，也同样具有上述技术效果。
The invention discloses a method for detecting abnormal temperature points of an arrester, comprising: acquiring an infrared image of the arrester marked with a detection area, and acquiring the temperature values corresponding to all the pixels in the detection area in the infrared image of the arrester to form a temperature value set; Traverse the temperature value set, determine the pixel point corresponding to the temperature value higher than the average value in the temperature value set as the target pixel point, and obtain the target pixel point set; according to the Euclidean distance between different target pixel points, the target pixel point set is The target pixel points are divided into multiple pixel groups; the area covered by the pixel group whose number of pixel points exceeds the preset threshold is marked as the temperature abnormal point. The method realizes the automatic detection of the temperature abnormal point of the arrester, improves the detection efficiency and accuracy, and can avoid the occurrence of electric accidents to a certain extent. Correspondingly, the apparatus, device and readable storage medium for detecting an abnormal temperature point of a lightning arrester disclosed in the present invention also have the above technical effects.
Description
Technical field
The present invention relates to infrared image processing technology fields, more specifically to a kind of detection arrester temperature anomaly
Method, apparatus, equipment and the readable storage medium storing program for executing of point.
Background technique
Along with extensive use of the infrared equipment in arrester live detection, power supply company has accumulated a large amount of arrester
O&M infrared image.For these arrester infrared images, it usually needs category filter manually is carried out to these infrared images,
To detect that there is the arrester infrared image of abnormal temperature point.
And since the quantity of arrester is more, corresponding infrared image is also just more, therefore detects the task amount of operation
It is larger.And the efficiency of artificial detection is slow, also inevitably will appear mistakes and omissions.If failing to detect to take shelter from the thunder in the presence of abnormal in time
Device is then likely to cause electric power accident.Therefore the prior art has the shortcomings that inefficiency, accuracy rate are difficult to ensure.
Therefore, the detection efficiency and accuracy rate for how improving arrester temperature anomaly point are those skilled in the art's needs
It solves the problems, such as.
Summary of the invention
It detects the method, apparatus of arrester temperature anomaly point, equipment the purpose of the present invention is to provide a kind of and readable deposits
Storage media, to improve the detection efficiency and accuracy rate of arrester temperature anomaly point.
To achieve the above object, the embodiment of the invention provides following technical solutions:
A method of detection arrester temperature anomaly point, comprising:
The arrester infrared image for being labeled with detection zone is obtained, and obtains the detection zone in the arrester infrared image
The corresponding temperature value of all pixels point in domain forms temperature value set；
The temperature value set is traversed, the corresponding pixel of temperature value that average value is higher than in the temperature value set is true
It is set to target pixel points, obtains object pixel point set；Wherein, the average value is all temperature in the temperature value set
The average value of value；
According to the Euclidean distance between the different target pixel in the object pixel point set, by the object pixel
Target pixel points in point set are divided into multiple pixel groups；
The pixel number in each pixel group is calculated separately, and the pixel group that pixel number is more than preset threshold is covered
The zone marker of lid is temperature anomaly point.
Wherein, further includes:
It is suspicious temperature anomaly point by the zone marker that pixel number is less than the pixel group covering of the preset threshold.
Wherein, described that the corresponding pixel of temperature value for being higher than average value in the temperature value set is determined as target picture
Vegetarian refreshments, comprising:
The temperature value for being higher than the average value in the temperature value set is determined as effective temperature value, obtains effective temperature
Value set；
The effective temperature value set is traversed, the effective temperature of effective average value will be higher than in the effective temperature value set
It is worth corresponding pixel and is determined as the target pixel points；Wherein, effective average value is in the effective temperature value set
All effective temperature values average value.
Wherein, the Euclidean distance between the different target pixel according in the object pixel point set, by institute
It states the target pixel points in object pixel point set and is divided into multiple pixel groups, comprising:
From point centered on a target pixel points optional in the object pixel point set, by the Europe with the central point
Family name's distance is that the target pixel points of default value and the central point are divided to object pixel group；
It regard each target pixel points in the object pixel group in addition to the central point as the central point, and holds
Row is described to be divided to target picture with the Euclidean distance of the central point for the target pixel points of default value and the central point
The step of element group, until there is no the Euclideans with the target pixel points in the object pixel group in the object pixel point set
Distance is the target pixel points of the numerical value；
The target pixel points for being divided to the object pixel group are deleted from the object pixel point set, and execute institute
The step of putting centered on a target pixel points optional in the object pixel point set is stated, until the target pixel points
Unallocated target pixel points are not present in set.
Wherein, it is described by pixel number be more than preset threshold pixel group cover zone marker be temperature anomaly point it
Afterwards, further includes:
The temperature anomaly point is marked in the arrester infrared image, obtains infrared mark image.
Wherein, it is described obtain infrared mark image after, further includes:
The identification information correspondence of arrester in the infrared mark image and the infrared mark image is stored to pre-
If file destination.
Wherein, the identification information by the arrester in the infrared mark image and the infrared mark image is corresponding
It stores to preset file destination, further includes:
The file destination is shown by preset visualization tool.
A kind of device detecting arrester temperature anomaly point, comprising:
Module is obtained, for obtaining the arrester infrared image for being labeled with detection zone, and it is infrared to obtain the arrester
The corresponding temperature value of all pixels point in detection zone in image forms temperature value set；
Computing module will be higher than the temperature value of average value for traversing the temperature value set in the temperature value set
Corresponding pixel is determined as target pixel points, obtains object pixel point set；Wherein, the average value is the temperature value collection
The average value of all temperature values in conjunction；
Division module, for according to the Euclidean distance between the different target pixel in the object pixel point set,
Target pixel points in the object pixel point set are divided into multiple pixel groups；
Mark module is more than default for calculating separately the pixel number in each pixel group, and by pixel number
The zone marker of the pixel group covering of threshold value is temperature anomaly point.
A kind of equipment detecting arrester temperature anomaly point, comprising:
Memory, for storing computer program；
Processor realizes that detection arrester temperature described in above-mentioned any one is different when for executing the computer program
The step of method often put.
A kind of readable storage medium storing program for executing is stored with computer program, the computer program quilt on the readable storage medium storing program for executing
Processor realizes the step of method that arrester temperature anomaly point is detected described in above-mentioned any one when executing.
By above scheme it is found that a kind of method for detecting arrester temperature anomaly point provided in an embodiment of the present invention, packet
It includes: obtaining the arrester infrared image for being labeled with detection zone, and obtain the institute in the detection zone in arrester infrared image
There is the corresponding temperature value of pixel, forms temperature value set；Temperature value set is traversed, average value will be higher than in temperature value set
The corresponding pixel of temperature value is determined as target pixel points, obtains object pixel point set；Average value is in temperature value set
The average value of all temperature values；According to the Euclidean distance between the different target pixel in object pixel point set, by target
Target pixel points in pixel collection are divided into multiple pixel groups；The pixel number in each pixel group is calculated separately, and
The zone marker that the pixel group that pixel number is more than preset threshold is covered is temperature anomaly point.
As it can be seen that the method can be calculated automatically from detection zone based on the arrester infrared image for being labeled with detection zone
The interior pixel with abnormal temperature, so that the automatic detection of arrester temperature anomaly point is realized, instead of artificial detection
Process, to improve detection efficiency and accuracy rate.Wherein, due to improving detection efficiency, so can detect exist in time
Abnormal arrester, to a certain extent can be to avoid the generation of electric power accident.
Correspondingly, provided in an embodiment of the present invention a kind of to detect the device of arrester temperature anomaly point, equipment and readable deposit
Storage media similarly has above-mentioned technique effect.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of method flow diagram for detecting arrester temperature anomaly point disclosed by the embodiments of the present invention；
Fig. 2 is the method flow diagram of another detection arrester temperature anomaly point disclosed by the embodiments of the present invention；
Fig. 3 is a kind of schematic device for detecting arrester temperature anomaly point disclosed by the embodiments of the present invention；
Fig. 4 is a kind of equipment schematic diagram for detecting arrester temperature anomaly point disclosed by the embodiments of the present invention；
Fig. 5 is a kind of arrester infrared image schematic diagram for being labeled with detection zone disclosed by the embodiments of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The embodiment of the invention discloses a kind of method, apparatus, equipment and readable storages for detecting arrester temperature anomaly point
Medium, to improve the detection efficiency and accuracy rate of arrester temperature anomaly point.
Referring to Fig. 1, a kind of method detecting arrester temperature anomaly point provided in an embodiment of the present invention, comprising:
S101, acquisition are labeled with the arrester infrared image of detection zone, and obtain the detection in arrester infrared image
The corresponding temperature value of all pixels point in region forms temperature value set；
It should be noted that the mode for obtaining arrester infrared image can be with are as follows: obtained from database by software interface
It takes, is obtained from storage medium by hardware interface, or the arrester that reception image transmitting terminal is sent by network line is infrared
Image etc..
Wherein, the arrester infrared image for being labeled with detection zone refers to Fig. 5, and the rectangle frame in Fig. 5 indicates detection zone
Domain.It should be noted that each pixel in detection zone corresponds to a temperature value, temperature value is higher, and arrester exists
Abnormal probability is higher.
S102, traversal temperature value set determine the corresponding pixel of temperature value for being higher than average value in temperature value set
For target pixel points, object pixel point set is obtained；
Specifically, ergodic algorithm progress can be used when traversal temperature value set.Average value is all in temperature value set
The average value of temperature value.
S103, according to the Euclidean distance between the different target pixel in object pixel point set, by target pixel points
Target pixel points in set are divided into multiple pixel groups；
Wherein, the Euclidean distance in the present embodiment is the distance between two target pixel points.
S104, pixel number in each pixel group is calculated separately, and is more than the picture of preset threshold by pixel number
The zone marker of element group covering is temperature anomaly point.
Wherein, further includes: being by the zone marker that pixel number is less than the pixel group covering of the preset threshold can
Doubt temperature anomaly point.It should be noted that arrester infrared image is after treatment, wherein there may be the pixel of distortion,
Therefore the zone marker for pixel number being less than to the pixel group covering of the preset threshold is suspicious temperature anomaly point.Also
It is to say, suspicious temperature anomaly point may be temperature anomaly point, it is also possible to as caused by the distortion of arrester infrared image.
As it can be seen that present embodiments providing a kind of method for detecting arrester temperature anomaly point, the method is based on being labeled with
The arrester infrared image of detection zone can be calculated automatically from the pixel with abnormal temperature in detection zone, thus real
The automatic detection for having showed arrester temperature anomaly point, instead of artificial detection process, to improve detection efficiency and accuracy rate.
It wherein,, to a certain extent can be to avoid so can detect in time in the presence of abnormal arrester due to improving detection efficiency
The generation of electric power accident.
The embodiment of the invention discloses the method for another detection arrester temperature anomaly point, relative to a upper embodiment,
The present embodiment has made further instruction and optimization to technical solution.
Referring to fig. 2, the method for another detection arrester temperature anomaly point provided in an embodiment of the present invention, comprising:
S201, acquisition are labeled with the arrester infrared image of detection zone, and obtain the detection in arrester infrared image
The corresponding temperature value of all pixels point in region forms temperature value set；
The temperature value for being higher than average value in temperature value set is determined as effective temperature value by S202, traversal temperature value set,
Obtain effective temperature value set；
Wherein, average value is the average value of all temperature values in temperature value set；
S203, traversal effective temperature value set will be higher than the effective temperature value of effective average value in effective temperature value set
Corresponding pixel is determined as target pixel points；
Wherein, effective average value is the average value of all effective temperature values in effective temperature value set；
S204, according to the Euclidean distance between the different target pixel in object pixel point set, by target pixel points
Target pixel points in set are divided into multiple pixel groups；
S205, pixel number in each pixel group is calculated separately, and is more than the picture of preset threshold by pixel number
The zone marker of element group covering is temperature anomaly point.
In the present embodiment, in order to filter out the higher extraordinary image vegetarian refreshments of temperature out of detection zone, and it is multiple to reduce calculating
Miscellaneous degree has carried out the secondary target pixel points in object pixel point set deleted, obtained to the corresponding temperature value of pixel
Quantity has certain reduction.
If in temperature value set including 3 temperature values, respectively 80 DEG C, 98 DEG C, 100 DEG C, 110 DEG C, then its average value
Are as follows: 97 DEG C, then delete 80 DEG C, remaining 98 DEG C, 100 DEG C, 110 DEG C of corresponding pixels be target pixel points, composition
Object pixel point set.If desired secondary to delete, then it regard 98 DEG C, 100 DEG C, 110 DEG C as effective temperature value, what is be calculated has
Imitating average value is 102.67 DEG C, then deletes 98 DEG C and 100 DEG C, 110 DEG C of corresponding pixels are target pixel points.
As it can be seen that the method for present embodiments providing another detection arrester temperature anomaly point, the method are based on mark
There is the arrester infrared image of detection zone that can be calculated automatically from the pixel with abnormal temperature in detection zone, thus
The automatic detection for realizing arrester temperature anomaly point, instead of artificial detection process, to improve detection efficiency and accurate
Rate.It wherein,, to a certain extent can be with so can detect in time in the presence of abnormal arrester due to improving detection efficiency
Avoid the generation of electric power accident.
Based on above-mentioned any embodiment, it should be noted that according to the different target pixel in object pixel point set
Between Euclidean distance, the target pixel points in object pixel point set are divided into multiple pixel groups, comprising:
From point centered on a target pixel points optional in object pixel point set, it is by the Euclidean distance with central point
The target pixel points and central point of default value are divided to object pixel group；
By each target pixel points in object pixel group in addition to central point it is equal centered on point, and execute will be with central point
Euclidean distance be default value target pixel points and central point the step of being divided to object pixel group, until target pixel points
There is no the target pixel points for the Euclidean distance of the target pixel points in object pixel group being numerical value in set；
The target pixel points for being divided to object pixel group are deleted from object pixel point set, and are executed from object pixel
The step of being put centered on an optional target pixel points in point set, until there is no unallocated in object pixel point set
Target pixel points.
Above-mentioned partition process specifically:
4 target pixel points if it exists: A, B, C, D, and A is 1 at a distance from B, C, D, 1,5, C is at a distance from B, D are as follows: 2,
2, B be 5 at a distance from D；And default value is 1, then an optional target pixel points A, will be 1 target picture at a distance from A
Vegetarian refreshments and A are divided to a pixel group, then have pixel group 1:A, B, C.By B and C it is equal centered on point, but there is no eligible
Target pixel points, therefore A, B, C are deleted from object pixel point set, only residue D in object pixel point set, and do not deposit
In qualified target pixel points, so dividing terminates, pixel group 1:A, B, C can be respectively as follows: to two pixel groups；Pixel
Group 2:D.
Based on above-mentioned any embodiment, it should be noted that cover the pixel group that pixel number is more than preset threshold
Zone marker be temperature anomaly point after, further includes: in arrester infrared image mark temperature anomaly point, obtain infrared mark
Infuse image.
Wherein, after obtaining infrared mark image, further includes: will be lightning-arrest in infrared mark image and infrared mark image
The identification information correspondence of device is stored to preset file destination.
Wherein, the identification information correspondence of the arrester in infrared mark image and infrared mark image is stored to preset
After file destination, further includes: show file destination by preset visualization tool.
Can know it is which arrester according to the identification information of arrester, therefore by infrared mark image and infrared mark figure
The identification information correspondence of arrester as in is stored to preset file destination, can be convenient for O&M technical staff by searching for target
Which arrester file knows, and there are what kind of temperature anomaly points.Corresponding storage is to be stored with one-to-one relationship,
Such as corresponding deposit has the table of prescribed form, records these information, in a unified format in order to follow-up management and analysis.
Based on above-mentioned any embodiment, it should be noted that the arrester infrared image for being labeled with detection zone can pass through
Deep learning model obtains.That is: the collected arrester infrared image of infrared terminal is inputted into deep learning model, output is lightning-arrest
Location information (i.e. detection zone) of the device in infrared image, and then location information is labeled in former infrared image, to obtain
It is labeled with the arrester of detection zone.Wherein, deep learning model can be obtained by the training of SSD algorithm.Deep learning model
Training process can refer to the prior art (convolutional neural networks model etc.), and TensorFlow can be used in training frame.
Below to it is provided in an embodiment of the present invention it is a kind of detect arrester temperature anomaly point device be introduced, hereafter retouch
A kind of device for the detection arrester temperature anomaly point stated and a kind of above-described method for detecting arrester temperature anomaly point
It can be cross-referenced.
Referring to Fig. 3, a kind of device detecting arrester temperature anomaly point provided in an embodiment of the present invention, comprising:
Module 301 is obtained, for obtaining the arrester infrared image for being labeled with detection zone, and obtains the infrared figure of arrester
The corresponding temperature value of all pixels point in detection zone as in, forms temperature value set；
Computing module 302, it is for traversing temperature value set, the temperature value that average value is higher than in temperature value set is corresponding
Pixel is determined as target pixel points, obtains object pixel point set；Wherein, average value is all temperature in temperature value set
The average value of value；
Division module 303, for inciting somebody to action according to the Euclidean distance between the different target pixel in object pixel point set
Target pixel points in object pixel point set are divided into multiple pixel groups；
Mark module 304 is more than pre- for calculating separately the pixel number in each pixel group, and by pixel number
If the zone marker that the pixel group of threshold value covers is temperature anomaly point.
Wherein, computing module includes:
Determination unit is had for the temperature value for being higher than average value in temperature value set to be determined as effective temperature value
Imitate temperature value set；
Computing unit will be higher than having for effective average value for traversing effective temperature value set in effective temperature value set
The corresponding pixel of effect temperature value is determined as target pixel points；Wherein, effective average value is all in effective temperature value set
The average value of effective temperature value.
Wherein, division unit is specifically used for:
From point centered on a target pixel points optional in object pixel point set, it is by the Euclidean distance with central point
The target pixel points and central point of default value are divided to object pixel group；By each mesh in object pixel group in addition to central point
Point centered on mark pixel is equal, and execute the target pixel points and central point with the Euclidean distance of central point for default value
The step of being divided to object pixel group, until being not present and the target pixel points in object pixel group in object pixel point set
Euclidean distance is the target pixel points of numerical value；The target pixel points for being divided to object pixel group are deleted from object pixel point set
It removes, and executes the step of putting centered on a target pixel points optional in object pixel point set, until target pixel points
Unallocated target pixel points are not present in set.
Wherein, further includes:
Labeling module obtains infrared mark image for marking temperature anomaly point in arrester infrared image.
Wherein, further includes:
Memory module, for the identification information of the arrester in infrared mark image and infrared mark image to be corresponded to storage
To preset file destination.
Wherein, further includes:
Display module, for showing file destination by preset visualization tool.
Wherein, further includes:
Suspicious temperature anomaly point mark module, the area that the pixel group for pixel number to be less than to preset threshold covers
Field mark is suspicious temperature anomaly point.
As it can be seen that present embodiments providing a kind of device for detecting arrester temperature anomaly point, comprising: obtain module, calculate
Module, division module and mark module.The arrester infrared image for being labeled with detection zone is obtained by acquisition module first, and
The corresponding temperature value of all pixels point in the detection zone in arrester infrared image is obtained, temperature value set is formed；Then
Computing module traverses temperature value set, and the corresponding pixel of temperature value that average value is higher than in temperature value set is determined as target
Pixel obtains object pixel point set；Average value is the average value of all temperature values in temperature value set；And then divide mould
Root tuber is according to the Euclidean distance between the different target pixel in object pixel point set, by the target in object pixel point set
Pixel is divided into multiple pixel groups；Last mark module calculates separately the pixel number in each pixel group, and by pixel
Point number is more than that the zone marker of the pixel group covering of preset threshold is temperature anomaly point.Divide the work between such modules and closes
Make, Each performs its own functions, to realize the automatic detection of arrester temperature anomaly point, improves detection efficiency and accuracy rate.
Below to it is provided in an embodiment of the present invention it is a kind of detect arrester temperature anomaly point equipment be introduced, hereafter retouch
A kind of equipment for the detection arrester temperature anomaly point stated and a kind of above-described method for detecting arrester temperature anomaly point
And device can be cross-referenced.
Referring to fig. 4, a kind of equipment detecting arrester temperature anomaly point provided in an embodiment of the present invention, comprising:
Memory 401, for storing computer program；
Processor 402 realizes detection arrester described in above-mentioned any embodiment when for executing the computer program
The step of method of temperature anomaly point.
A kind of readable storage medium storing program for executing provided in an embodiment of the present invention is introduced below, one kind described below is readable to deposit
Storage media with it is above-described it is a kind of detect arrester temperature anomaly point method, device and equipment can be cross-referenced.
A kind of readable storage medium storing program for executing is stored with computer program, the computer program quilt on the readable storage medium storing program for executing
The step of method of the detection arrester temperature anomaly point as described in above-mentioned any embodiment is realized when processor executes.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.
Professional further appreciates that, unit described in conjunction with the examples disclosed in the embodiments of the present disclosure
And algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software generally describes each exemplary composition and step according to function in the above description.These
Function is implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Profession
Technical staff can use different methods to achieve the described function each specific application, but this realization is not answered
Think beyond the scope of this invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can directly be held with hardware, processor
The combination of capable software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (10)
1. a kind of method for detecting arrester temperature anomaly point characterized by comprising
The arrester infrared image for being labeled with detection zone is obtained, and is obtained in the detection zone in the arrester infrared image
The corresponding temperature value of all pixels point, form temperature value set；
The temperature value set is traversed, the corresponding pixel of temperature value that average value is higher than in the temperature value set is determined as
Target pixel points obtain object pixel point set；Wherein, the average value is all temperature values in the temperature value set
Average value；
According to the Euclidean distance between the different target pixel in the object pixel point set, by the object pixel point set
Target pixel points in conjunction are divided into multiple pixel groups；
The pixel number in each pixel group is calculated separately, and the pixel group that pixel number is more than preset threshold is covered
Zone marker is temperature anomaly point.
2. the method for detection arrester temperature anomaly point according to claim 1, which is characterized in that further include:
It is suspicious temperature anomaly point by the zone marker that pixel number is less than the pixel group covering of the preset threshold.
3. the method for detection arrester temperature anomaly point according to claim 2, which is characterized in that described by the temperature
The corresponding pixel of temperature value in value set higher than average value is determined as target pixel points, comprising:
The temperature value for being higher than the average value in the temperature value set is determined as effective temperature value, obtains effective temperature value collection
It closes；
The effective temperature value set is traversed, the effective temperature value pair of effective average value will be higher than in the effective temperature value set
The pixel answered is determined as the target pixel points；Wherein, effective average value is the institute in the effective temperature value set
There is the average value of effective temperature value.
4. the method for detection arrester temperature anomaly point according to claim 3, which is characterized in that described according to the mesh
The Euclidean distance between the different target pixel in pixel collection is marked, by the object pixel in the object pixel point set
Point is divided into multiple pixel groups, comprising:
From point centered on a target pixel points optional in the object pixel point set, by with the Euclidean of the central point away from
From for default value target pixel points and the central point be divided to object pixel group；
It regard each target pixel points in the object pixel group in addition to the central point as the central point, and executes institute
Object pixel group will be divided to the Euclidean distance of the central point for the target pixel points of default value and the central point by stating
The step of, until there is no the Euclidean distances with the target pixel points in the object pixel group in the object pixel point set
For the target pixel points of the numerical value；
The target pixel points for being divided to the object pixel group are deleted from the object pixel point set, and execute it is described from
The step of being put centered on an optional target pixel points in the object pixel point set, until the object pixel point set
In be not present unallocated target pixel points.
5. the method for detection arrester temperature anomaly point according to any one of claims 1-4, which is characterized in that described
The zone marker that the pixel group that pixel number is more than preset threshold is covered is after temperature anomaly point, further includes:
The temperature anomaly point is marked in the arrester infrared image, obtains infrared mark image.
6. the method for detection arrester temperature anomaly point according to claim 5, which is characterized in that described to obtain infrared mark
After note image, further includes:
The identification information correspondence of arrester in the infrared mark image and the infrared mark image is stored to preset
File destination.
7. it is according to claim 6 detection arrester temperature anomaly point method, which is characterized in that it is described will be described infrared
The identification information of mark image and the arrester in infrared mark image correspondence is stored to preset file destination, also
Include:
The file destination is shown by preset visualization tool.
8. a kind of device for detecting arrester temperature anomaly point characterized by comprising
Module is obtained, for obtaining the arrester infrared image for being labeled with detection zone, and obtains the arrester infrared image
In detection zone in the corresponding temperature value of all pixels point, form temperature value set；
Computing module, it is for traversing the temperature value set, the temperature value that average value is higher than in the temperature value set is corresponding
Pixel be determined as target pixel points, obtain object pixel point set；Wherein, the average value is in the temperature value set
All temperature values average value；
Division module, for according to the Euclidean distance between the different target pixel in the object pixel point set, by institute
It states the target pixel points in object pixel point set and is divided into multiple pixel groups；
Mark module is more than preset threshold for calculating separately the pixel number in each pixel group, and by pixel number
Pixel group covering zone marker be temperature anomaly point.
9. a kind of equipment for detecting arrester temperature anomaly point characterized by comprising
Memory, for storing computer program；
Processor realizes the detection arrester as described in claim 1-7 any one when for executing the computer program
The step of method of temperature anomaly point.
10. a kind of readable storage medium storing program for executing, which is characterized in that be stored with computer program, the meter on the readable storage medium storing program for executing
The side of the detection arrester temperature anomaly point as described in claim 1-7 any one is realized when calculation machine program is executed by processor
The step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910221734.5A CN109900366B (en) | 2019-03-22 | 2019-03-22 | Method and device for detecting abnormal temperature of arrester |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910221734.5A CN109900366B (en) | 2019-03-22 | 2019-03-22 | Method and device for detecting abnormal temperature of arrester |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109900366A true CN109900366A (en) | 2019-06-18 |
| CN109900366B CN109900366B (en) | 2021-05-07 |
Family
ID=66952447
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910221734.5A Active CN109900366B (en) | 2019-03-22 | 2019-03-22 | Method and device for detecting abnormal temperature of arrester |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109900366B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110824311A (en) * | 2019-11-22 | 2020-02-21 | 南京信息工程大学 | A device and method for detecting breakdown point of zinc oxide valve plate based on image recognition |
| CN110864809A (en) * | 2019-06-28 | 2020-03-06 | 武钢集团昆明钢铁股份有限公司 | Tank monitoring method |
| CN111044149A (en) * | 2019-12-19 | 2020-04-21 | 国网重庆市电力公司电力科学研究院 | Method and device for detecting temperature abnormal point of voltage transformer and readable storage medium |
| CN111366602A (en) * | 2020-03-19 | 2020-07-03 | 三一筑工科技有限公司 | Method, device and system for detecting compactness of concrete in prefabricated cavity wall |
| CN111680567A (en) * | 2020-05-12 | 2020-09-18 | 深圳数联天下智能科技有限公司 | Living body detection method, living body detection device, computer equipment and storage medium |
| CN113343841A (en) * | 2021-06-03 | 2021-09-03 | 国网北京市电力公司 | Method and device for determining abnormal condition of power tunnel |
| CN113610830A (en) * | 2021-08-18 | 2021-11-05 | 常州领创电气科技有限公司 | Detection system and method for lightning arrester |
| CN114049336A (en) * | 2021-11-18 | 2022-02-15 | 国网重庆市电力公司电力科学研究院 | GIS casing temperature anomaly detection method, device, equipment and readable storage medium |
| CN114119518A (en) * | 2021-11-16 | 2022-03-01 | 国网重庆市电力公司电力科学研究院 | A method and system for detecting abnormal temperature points in infrared images of current transformers |
| CN117297557A (en) * | 2023-09-26 | 2023-12-29 | 长沙观谱红外科技有限公司 | Method for determining regional state parameters, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030183765A1 (en) * | 2002-03-26 | 2003-10-02 | Lockheed Martin Corporation | Method and system for target detection using an infra-red sensor |
| CN106920245A (en) * | 2017-03-13 | 2017-07-04 | 深圳怡化电脑股份有限公司 | A kind of method and device of border detection |
| CN107305563A (en) * | 2016-04-21 | 2017-10-31 | 北京暖流科技有限公司 | A kind of abnormal deviation data examination method and system based on distance |
| CN107314817A (en) * | 2017-06-14 | 2017-11-03 | 浙江大华系统工程有限公司 | The diagnostic method and device of a kind of electrical equipment fault |
| CN107606493A (en) * | 2017-10-27 | 2018-01-19 | 华润电力技术研究院有限公司 | A kind of pipeline leakage checking system |
| CN108154152A (en) * | 2017-12-15 | 2018-06-12 | 中国大唐集团科学技术研究院有限公司火力发电技术研究所 | A kind of flame temp measuring method |
| CN109308447A (en) * | 2018-07-29 | 2019-02-05 | 国网上海市电力公司 | Method for Automatically Extracting Equipment Operating Parameters and Operating Status in Electric Power Remote Monitoring |
-
2019
- 2019-03-22 CN CN201910221734.5A patent/CN109900366B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030183765A1 (en) * | 2002-03-26 | 2003-10-02 | Lockheed Martin Corporation | Method and system for target detection using an infra-red sensor |
| CN107305563A (en) * | 2016-04-21 | 2017-10-31 | 北京暖流科技有限公司 | A kind of abnormal deviation data examination method and system based on distance |
| CN106920245A (en) * | 2017-03-13 | 2017-07-04 | 深圳怡化电脑股份有限公司 | A kind of method and device of border detection |
| CN107314817A (en) * | 2017-06-14 | 2017-11-03 | 浙江大华系统工程有限公司 | The diagnostic method and device of a kind of electrical equipment fault |
| CN107606493A (en) * | 2017-10-27 | 2018-01-19 | 华润电力技术研究院有限公司 | A kind of pipeline leakage checking system |
| CN108154152A (en) * | 2017-12-15 | 2018-06-12 | 中国大唐集团科学技术研究院有限公司火力发电技术研究所 | A kind of flame temp measuring method |
| CN109308447A (en) * | 2018-07-29 | 2019-02-05 | 国网上海市电力公司 | Method for Automatically Extracting Equipment Operating Parameters and Operating Status in Electric Power Remote Monitoring |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110864809A (en) * | 2019-06-28 | 2020-03-06 | 武钢集团昆明钢铁股份有限公司 | Tank monitoring method |
| CN110864809B (en) * | 2019-06-28 | 2021-07-09 | 武钢集团昆明钢铁股份有限公司 | Tank monitoring method |
| CN110824311A (en) * | 2019-11-22 | 2020-02-21 | 南京信息工程大学 | A device and method for detecting breakdown point of zinc oxide valve plate based on image recognition |
| CN111044149A (en) * | 2019-12-19 | 2020-04-21 | 国网重庆市电力公司电力科学研究院 | Method and device for detecting temperature abnormal point of voltage transformer and readable storage medium |
| CN111366602A (en) * | 2020-03-19 | 2020-07-03 | 三一筑工科技有限公司 | Method, device and system for detecting compactness of concrete in prefabricated cavity wall |
| CN111680567B (en) * | 2020-05-12 | 2023-08-29 | 深圳数联天下智能科技有限公司 | Living body detection method, living body detection device, computer equipment and storage medium |
| CN111680567A (en) * | 2020-05-12 | 2020-09-18 | 深圳数联天下智能科技有限公司 | Living body detection method, living body detection device, computer equipment and storage medium |
| CN113343841A (en) * | 2021-06-03 | 2021-09-03 | 国网北京市电力公司 | Method and device for determining abnormal condition of power tunnel |
| CN113343841B (en) * | 2021-06-03 | 2024-06-14 | 国网北京市电力公司 | Method and device for determining abnormal condition of power tunnel |
| CN113610830A (en) * | 2021-08-18 | 2021-11-05 | 常州领创电气科技有限公司 | Detection system and method for lightning arrester |
| CN113610830B (en) * | 2021-08-18 | 2023-12-29 | 常州领创电气科技有限公司 | Detection system and method for lightning arrester |
| CN114119518A (en) * | 2021-11-16 | 2022-03-01 | 国网重庆市电力公司电力科学研究院 | A method and system for detecting abnormal temperature points in infrared images of current transformers |
| CN114049336A (en) * | 2021-11-18 | 2022-02-15 | 国网重庆市电力公司电力科学研究院 | GIS casing temperature anomaly detection method, device, equipment and readable storage medium |
| CN117297557A (en) * | 2023-09-26 | 2023-12-29 | 长沙观谱红外科技有限公司 | Method for determining regional state parameters, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109900366B (en) | 2021-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109900366A (en) | A kind of method and device detecting arrester temperature anomaly point | |
| CN114706933A (en) | Spraying area determining method and device based on unmanned aerial vehicle operation | |
| CN109948613A (en) | Infrared image recognition method and device for arrester | |
| CN105652300A (en) | Correction method for global positioning system data based on speed constraint | |
| CN104965876B (en) | A kind of method and device carrying out the excavation of user job unit based on location information | |
| CN109255632A (en) | A kind of user community recognition methods, device, equipment and medium | |
| CN108986044A (en) | A kind of image removes misty rain method, apparatus, equipment and storage medium | |
| CN107729367A (en) | A kind of moving line recommends method, apparatus and storage medium | |
| CN108776999A (en) | Grid isoplethes drawing method based on ocean Internet of Things | |
| CN111984930A (en) | A method and system for identifying outliers in groundwater level monitoring data | |
| CN110109991A (en) | A kind of subway station inner region passenger flow estimation method, system and electronic equipment | |
| CN107357894A (en) | A kind of road traffic facility data acquisition method for correcting error and system | |
| CN109410290A (en) | The method and apparatus for determining operating area boundary | |
| CN109684320A (en) | The method and apparatus of monitoring data on-line cleaning | |
| CN108694716A (en) | A kind of workpiece inspection method, model training method and equipment | |
| CN109670064A (en) | Photo archiving method, device and electronic equipment | |
| CN107832386A (en) | A kind of error correction method and apparatus of electronic map | |
| CN105893938A (en) | Oil temperature gauge reading method and system | |
| CN107240113B (en) | A kind of semi-automatic water body scope extracting method based on special sections line | |
| CN105467100A (en) | County territory soil erosion time-space dynamic monitoring method based on remote sensing and GIS | |
| CN106780435A (en) | A kind of object count method and device | |
| CN105893943B (en) | Method and system for detecting oil level | |
| CN105512803B (en) | Processing method and processing device of power data | |
| CN109615140B (en) | Method and device for predicting pedestrian movement | |
| CN103117887A (en) | Visualization method and device of network flow change |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |