CN106846304A - Electrical equipment detection method and device based on infrared detection - Google Patents
Electrical equipment detection method and device based on infrared detection Download PDFInfo
- Publication number
- CN106846304A CN106846304A CN201710002290.7A CN201710002290A CN106846304A CN 106846304 A CN106846304 A CN 106846304A CN 201710002290 A CN201710002290 A CN 201710002290A CN 106846304 A CN106846304 A CN 106846304A
- Authority
- CN
- China
- Prior art keywords
- gray
- scale map
- image
- electrical equipment
- difference
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20224—Image subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Radiation Pyrometers (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The embodiment of the present invention provides a kind of electrical equipment detection method and device based on infrared detection.The method includes：According to the corresponding Standard Thermal of electrical equipment, the target thermal image of electrical equipment is obtained；Target thermal image and Standard Thermal are compared, obtains comparing the result of analysis；According to the result for comparing analysis, determine whether electrical equipment occurs exception.Electrical equipment detection method and device based on infrared detection provided in an embodiment of the present invention, by according to the corresponding Standard Thermal of electrical equipment, obtaining the target thermal image of electrical equipment；Target thermal image and Standard Thermal are compared, obtains comparing the result of analysis；According to the result for comparing analysis, determine whether electrical equipment occurs exception, realize target thermography compares with standard thermography automatically, reduce the workload of testing staff.
Description
Technical field
The present embodiments relate to field of equipment failure detection, more particularly to a kind of electrical equipment inspection based on infrared detection
Survey method and device.
Background technology
Electrical equipment is the core of electromechanical integration equipment, power equipment, electronic system etc., play electrical energy transmission,
The function of electric signal conduction, its running status will influence great to whole system.
The design of electrical equipment is unreasonable, device aging or abrasion, bad connection, accidental injury etc. are all likely to result in electricity
The damage of gas equipment.The reason for most electrical equipments break down is insulation ag(e)ing, failure generation, and its external manifestation is
The heat obvious increase that produces when a few hours are all than normal work before failure appearance.
At present, testing staff obtains the thermal image of electrical equipment to be detected using infrared detection technology, by thermal image
It is analyzed, rule of thumb judges whether electrical equipment occurs exception.When needing to carry out electrical equipment multiple discrete inspection
During survey, it usually needs repeatedly shot, manual analysis is carried out to the multiple thermal image for shooting, analysis difficulty is high, testing staff
Working strength is big.
The content of the invention
The embodiment of the present invention provides a kind of electrical equipment detection method and device based on infrared detection, right at present to solve
When electrical equipment carries out multiple discrete detection, manual analysis need to be carried out to the multiple thermal image for shooting, analysis difficulty is high, inspection
Survey the big problem of person works' intensity.
The one side of the embodiment of the present invention is to provide a kind of electrical equipment detection method based on infrared detection, including：
According to the corresponding Standard Thermal of electrical equipment, the target thermal image of the electrical equipment is obtained；
The target thermal image is compared with Standard Thermal, obtains comparing the result of analysis；
According to the result for comparing analysis, determine whether the electrical equipment occurs exception.
The other side of the embodiment of the present invention is to provide a kind of device of the electrical equipment detection based on infrared detection, bag
Include：
Acquisition module, for according to the corresponding Standard Thermal of electrical equipment, obtaining the target thermal map of the electrical equipment
Picture；
Analysis module is compared, for being compared with Standard Thermal to the target thermal image, is obtained comparing and is divided
The result of analysis；
Abnormal determining module, for according to the result for comparing analysis, determining whether the electrical equipment occurs exception.
Electrical equipment detection method and device based on infrared detection provided in an embodiment of the present invention, are electrically set by basis
Standby corresponding Standard Thermal, obtains the target thermal image of the electrical equipment；To the target thermal image and Standard Thermal
Compare, obtain comparing the result of analysis；According to the result for comparing analysis, determine whether the electrical equipment is sent out
It is raw abnormal, realize the automatic target thermal image to obtaining and analyzed with the comparison of Standard Thermal, it is possible to analyzed according to comparing
Result determines whether the electrical equipment occurs exception, reduces the workload of testing staff.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of the electrical equipment detection method based on infrared detection that the embodiment of the present invention one is provided；
Fig. 2 is the schematic flow sheet of the electrical equipment detection method based on infrared detection that the embodiment of the present invention two is provided；
Fig. 3 is the schematic flow sheet of the electrical equipment detection method based on infrared detection that the embodiment of the present invention three is provided；
Fig. 4 is the structural representation of the electrical equipment detection means based on infrared detection that the embodiment of the present invention four is provided；
Fig. 5 is the structural representation of the electrical equipment detection means based on infrared detection that the embodiment of the present invention five is provided；
Fig. 6 is the structural representation of the electrical equipment detection means based on infrared detection that the embodiment of the present invention six is provided.
Specific embodiment
It is right below in conjunction with the accompanying drawing in the embodiment of the present invention to make technical scheme and advantage clearer
Technical scheme is clearly and completely described, it is clear that described embodiment is a part of embodiment of the invention,
Rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative labor
The every other embodiment obtained under the premise of dynamic, belongs to the scope of protection of the invention.
Embodiment one
Fig. 1 is the schematic flow sheet of the electrical equipment detection method based on infrared detection that the embodiment of the present invention one is provided.
When the embodiment of the present invention for multiple discrete detection is carried out to electrical equipment at present, the multiple thermal image for shooting need to be carried out
Manual analysis, analysis difficulty is high, the big problem of testing staff's working strength, there is provided the electrical equipment detection based on infrared detection
Method.As shown in figure 1, the method is comprised the following steps that：
Step S101, according to the corresponding Standard Thermal of electrical equipment, obtain the target thermal image of electrical equipment.
In the present embodiment, the need for being detected to electrical equipment, can periodically, irregularly or continuous several times treat
The electrical equipment of detection is shot, and obtains nearest target thermal image, and the electricity is determined with according to the nearest target thermal image
Whether gas equipment there is exception.Detection frequency to electrical equipment can be set by technical staff according to actually detected needs
Fixed, the embodiment of the present invention is not specifically limited to this.For example：To the detection frequency of electrical equipment can for it is annual, each
The moon is once or once a day etc..
In the present embodiment, one or more electric components in electrical equipment or electrical equipment can be detected.Can
Selection of land, before this step, also including obtaining the corresponding Standard Thermal of electrical equipment, the coverage of the Standard Thermal is covered
Electrical equipment entirety to be detected, or the part to be detected for covering the electrical equipment are covered.
Specifically, it is possible to use infrared optics acquisition system, the thermograph that electrical equipment starts under state is obtained, as
The corresponding Standard Thermal of the electrical equipment.For example, state that can be when electrical equipment is put on record every time is used as beginning shape
State, the thermograph of collection now electrical equipment, as the electrical equipment for Standard Thermal.Wherein, infrared optics is adopted
Collecting system can be the equipment such as infrared camera, Infrared Detectors, thermal infrared imager.
In addition, after the Standard Thermal for obtaining electrical equipment to be detected, to same electrical equipment or same
Before each detection of the electric component in electrical equipment, without obtaining its corresponding Standard Thermal again.
Step S102, target thermal image and Standard Thermal are compared, obtain comparing the result of analysis.
Because the tonal range of the thermal image collected so far using infrared optics acquisition system is generally smaller, in the step
Image enhaucament is carried out to Standard Thermal and target thermal image, and extracts the characteristic value of the two images, and extract image respectively
Two characteristic points of image obtained after enhancing, calculate the difference diagram of default target area internal standard thermal image and target image
Picture, and the abnormal pixel larger to the temperature difference in difference diagram be marked, and obtains difference mark image.
Wherein, default target area is the sense delimited in advance on Standard Thermal by technical staff on Standard Thermal
Interest region, default target area is corresponding with the target area on Standard Thermal on target thermal image on target thermal image
Region.
In the present embodiment, image enhaucament is carried out by Standard Thermal and target thermal image so that Standard Thermal and
The gray value of all pixels point is completely covered 0-255 in target thermal image, and ensures to Standard Thermal and target thermal image
Carry out identical image enhaucament so that there is equal gray value in Standard Thermal and target thermal image before image enhaucament
Pixel, the gray value after image enhaucament is equal.
Step S103, the result according to comparison analysis, determine whether electrical equipment occurs exception.
In the step, according to above-mentioned comparison analysis result, pixel abnormal in default target area is determined, calculate
Ratio in default target area shared by abnormal pixel, the ratio in default target area shared by abnormal pixel
When more than or equal to default outlier threshold, determine whether electrical equipment occurs exception.
The embodiment of the present invention is by according to the corresponding Standard Thermal of electrical equipment, obtaining the target thermal map of electrical equipment
Picture；Target thermal image and Standard Thermal are compared, obtains comparing the result of analysis；According to the knot for comparing analysis
Really, determine whether electrical equipment occurs exception, realize the ratio of the automatic target thermal image to each acquisition and Standard Thermal
To analysis, it is possible to determine whether electrical equipment occurs exception according to analysis result is compared, reduce the workload of testing staff.
Embodiment two
Fig. 2 is the schematic flow sheet of the electrical equipment detection method based on infrared detection that the embodiment of the present invention two is provided.
On the basis of above-described embodiment, as shown in Fig. 2 according to the corresponding Standard Thermal of electrical equipment, obtaining the target of electrical equipment
Thermal image, can specifically be realized using following steps：
Step S201, with Standard Thermal as background, gather electrical equipment current thermal image.
In the present embodiment, when the current thermal image of electrical equipment is obtained, the visual angle and scope shot to this are adjusted
It is whole so that the current thermal image that this shooting is obtained is consistent with the shooting angle and scope of Standard Thermal；Or both
Coverage rate reaches default covering threshold value, now it is considered that both shooting angle and scope are basically identical.
Specifically, can be by adjusting the shooting angle of camera, adjusting the distance between camera and electrical equipment, tune
Whole shooting grease head highness, the adjustment mode such as camera focal length, the visual angle and scope that this is shot adjust to Standard Thermal one
Cause or basically identical.
It is alternatively possible to thermal image as background, when this shoots so that the visual angle found a view during this shooting and background
It is completely superposed, or substantially overlaps, thereby may be ensured that the consistent of the content that shoots covering twice.
Step S202, Standard Thermal is converted to the first gray-scale map, grey linear transformation is carried out to the first gray-scale map, with
Make the scope of the gray value of all pixels point in the first gray-scale map between 0-255.
Wherein, by the gray value of all pixels point in the first gray-scale map obtained after the treatment of the step scope in 0-
Minimum value is 0 between 255, and in the gray value of each pixel in the first gray-scale map, and maximum is 255.That is the first gray scale
The gray value of pixel is completely covered the tonal range of 0-255 in figure.
In the present embodiment, can using in the prior art any one thermal image is converted into the method for gray-scale map by standard
Thermal image is converted to the first gray-scale map, can be using any one grey linear transformation method in the prior art to first gray scale
Figure carries out grey linear transformation, and the embodiment of the present invention is not specifically limited to this.
Step S203, current thermal image is converted into the second gray-scale map, grey linear transformation is carried out to the second gray-scale map, with
Make the scope of the gray value of all pixels point in the second gray-scale map between 0-255.
Wherein, by the gray value of all pixels point in the second gray-scale map obtained after the treatment of the step scope in 0-
Minimum value is 0 between 255, and in the gray value of each pixel in the second gray-scale map, and maximum is 255.That is the second gray scale
The gray value of pixel is completely covered the tonal range of 0-255 in figure.
In the step, will during current thermal image is converted into the method that the second gray-scale map is used, with above-mentioned steps S202
The method that Standard Thermal is converted to the first gray-scale map is consistent；And carry out what grey linear transformation was used to the second gray-scale map
Method, it is consistent with the grey linear transformation method employed in above-mentioned steps S202, so that Standard Thermal and current thermal image
In there is the pixel of equal gray value, after the treatment for carrying out above-mentioned steps S202-S203, the first gray-scale map for obtaining and
The gray value of corresponding pixel is still equal in second gray-scale map.
Above-mentioned steps S202-S203 is the process that image enhaucament is carried out to Standard Thermal and current thermal image, by inciting somebody to action
The two images are converted to gray-scale map, and gray-scale map to obtaining carries out grey linear transformation so that the first ash for finally giving
The gray value coverage of pixel is maximum in degree image and the second gray level image, and Standard Thermal and works as before image enhaucament
Pixel with equal gray value in preceding thermal image, the gray value after image enhaucament is still equal.
The coverage rate of step S204, the second gray-scale map of calculating relative to the first gray-scale map.
In the present embodiment, the second gray-scale map, relative to the coverage rate of the first gray-scale map, refers to the target in the first gray-scale map
Coverage rate of the pixel matched with the second gray-scale map in region in the first gray-scale map.
Specifically, the step can specifically be realized in the following way：
Extract the characteristic point of the first gray-scale map and the characteristic point of the second gray-scale map, the characteristic point to the first gray-scale map and second
The characteristic point of gray-scale map is matched, and calculates projection mapping matrix according to matching result.According to projection mapping matrix and in advance
If target area, calculate in the target area in the first gray-scale map the pixel that is matched with the second gray-scale map in the first gray scale
Coverage rate in figure, obtains coverage rate of second gray-scale map relative to the first gray-scale map.
Preferably due to the feature extraction side of SURF (Speeded Up Robust Features accelerate robust feature)
Method has scale invariability and rotational invariance, can successfully manage the difference of the shooting distance and angle when obtaining two images
It is different, SURF feature extracting methods are used in the present embodiment, extract the characteristic point of the first gray-scale map and the SURF spies of the second gray-scale map
Levy, and obtain characteristic point.Alternatively, it is also possible to using the method for any one feature extraction in the prior art, the embodiment of the present invention
Repeat no more.
Alternatively, FLANN (Fast Library for Approximate Nearest Neighbors) algorithm is used
The characteristic point of characteristic point and the second gray-scale map to the first gray-scale map is matched.
If step S205, coverage rate are more than or equal to default covering threshold value, it is determined that current thermal image is target thermal map
Picture.
In the present embodiment, if coverage rate can be determined in default target more than or equal to default covering threshold value
In region, the second gray-scale map is higher with the matching degree of characteristic point in the first gray-scale map, then can determine current thermal image and standard
Electrical equipment captured by thermal image is same class electrical equipment, or same class electric component, can be shot this
The current thermal image can determine that the current thermal image is target thermal image as the thermal image of electrical equipment to be detected.
Wherein, default coverage rate can according to actual needs be set by technical staff.For example, default covering threshold value can
Think 80%.
If step S206, coverage rate are less than default covering threshold value, again with Standard Thermal as background, collection is lower for the moment
The thermal image of electrical equipment is carved, until determining target thermal image.
In the present embodiment, if coverage rate can be determined in default target area less than default covering threshold value, the
Two gray-scale maps are very low with the matching degree of characteristic point in the first gray-scale map, then can determine that current thermal image is clapped with Standard Thermal
The electrical equipment taken the photograph is not same class electrical equipment, nor same class electric component, the current thermal image cannot be used as target
Thermal image.At this time, it may be necessary to step S201-S206 is re-executed, until determining target thermal image.
Alternatively, under it is determined that coverage rate is less than default covering threshold value, it is necessary to be gathered as background with Standard Thermal again
During the thermal image of one moment electrical equipment, default alarm signal is sent so that technical staff adopts again according to the alarm signal
Collect the thermal image of subsequent time electrical equipment.The default alarm signal can be to send alarm sound, alarm lamp to dodge
The mode such as bright realizes that the embodiment of the present invention is not specifically limited to this.
The embodiment of the invention provides the target thermal map that electrical equipment is obtained according to the corresponding Standard Thermal of electrical equipment
The detailed process of picture.
Embodiment three
Fig. 3 is the schematic flow sheet of the electrical equipment detection method based on infrared detection that the embodiment of the present invention three is provided.
On the basis of above-described embodiment, in the embodiment of the present invention, to being compared to current thermal image and Standard Thermal, obtain
The result of analysis is compared, according to the result for comparing analysis, determines whether electrical equipment occurs abnormal process and carry out specifically
It is bright.As shown in figure 3, the method that the present embodiment is provided is comprised the following steps：
Step S301, according to the corresponding Standard Thermal of electrical equipment, obtain the target thermal image of electrical equipment.
In the present embodiment, the step specifically realizes that here is omitted using the method in above-described embodiment two.
Step S302, according to default target area, corresponding first gray-scale map of Standard Thermal and target thermal image
Corresponding second gray-scale map, image difference treatment is carried out by the first gray-scale map and the second gray-scale map, obtains difference image.
Wherein, default target area is the area-of-interest delimited in advance on Standard Thermal by technical staff, mesh
Default target area on mark thermal image is region corresponding with the target area on Standard Thermal on target thermal image.
In the present embodiment, corresponding first gray-scale map of Standard Thermal and corresponding second gray-scale map of target thermal image,
Obtained during the target thermal image that electrical equipment can be obtained in above-mentioned steps S301.
In the step, the first gray-scale map and the second gray-scale map are carried out into image difference treatment, specially by the first gray-scale map
Image difference treatment is carried out in goal-selling region with the second gray-scale map, obtains corresponding to the corresponding difference in goal-selling region
Image.
The temperature difference of the gray value mark of each pixel in step S303, calculating difference image.
In the present embodiment, the gray value of any pixel point is actual in the first gray-scale map and the second gray-scale map in difference image
The difference of the gray value of two pixels corresponding with the pixel, for thermal image, the gray value of pixel can be used
The temperature value at the corresponding position of the pixel in electrical equipment is identified, the gray value of any pixel point can be with the difference image
For identifying：Shooting moment and standard thermal map of the temperature value at the corresponding position of the pixel in target thermal image in electrical equipment
The temperature difference at the shooting moment of picture.According to the gray value of each pixel in difference image, the corresponding temperature of the gray value can be calculated
Difference.
In the step, according to the rule of correspondence set in advance, the gray value mark of each pixel in difference image is calculated
The temperature difference.Wherein the rule of correspondence has technical staff to be preset according to actual conditions.
Step S304, the temperature difference identified according to the gray value of each pixel in difference image, temperature difference threshold is more than by the temperature difference
The gray value of pixel be set to the first preset value, the temperature difference is set less than or equal to the gray value of the pixel of temperature difference threshold
The second preset value is set to, the first difference mark image is obtained.
Alternatively, the first preset value can be 255, and the second preset value can be 0.First preset value and the second preset value can
It is set as two different values with by technical staff, visually can substantially distinguishes, the embodiment of the present invention is not done to this
It is specific to limit.
In the present embodiment, the temperature difference is the pixel for having temperature anomaly more than the pixel of temperature difference threshold in difference image, will
The gray value of the pixel of this class is set to the first preset value, labeled as extraordinary image vegetarian refreshments；In difference image the temperature difference be less than or
The pixel that person is equal to temperature difference threshold is normal pixel, the gray value of the pixel of this class is set into second and is preset
Value, labeled as normal pixel point.
Step S305, to the first difference mark image carry out Denoising disposal, obtain the second difference mark image, second is poor
Minute mark note image is the result for comparing analysis.
In the step, Denoising disposal, the orphan in removal the first difference mark image are carried out to the first difference mark image
Miscellaneous point is found, the second difference mark image is obtained.
In the present embodiment, carrying out the denoising method for acoustic that Denoising disposal used to the first difference mark image can use
The method of any one denoising realizes that the present embodiment is not specifically limited to this in the prior art.
Above-mentioned steps S302-S305 is that current thermal image and Standard Thermal are compared, and obtains comparing analysis
Result process.
Step S306, image is marked according to the second difference, it is the pixel of the first preset value in difference diagram to calculate gray value
The shared ratio as in.
In the present embodiment, gray value is that the pixel of the first preset value is and is marked as temperature in the second difference mark image
Abnormal extraordinary image vegetarian refreshments is spent, the ratio shared in difference image by calculating pixel that gray value is the first preset value,
The shared ratio in difference image of extraordinary image vegetarian refreshments can be obtained.
Specifically, can be by the area shared by the pixel of the first preset value of calculating and the gross area in goal-selling region
Ratio, or the ratio of pixel sum is counted in number and the goal-selling region of the pixel for calculating the first preset value
Calculate the ratio shared in difference image of pixel that gray value is the first preset value.
If the ratio shared in difference image of pixel that step S307, gray value are the first preset value be more than or
Equal to default outlier threshold, it is determined that electrical equipment occurs abnormal.
In the present embodiment, if the shared ratio in difference image of the pixel of the first preset value is less than default exception threshold
Value, it is determined that electrical equipment does not occur exception.
Alternatively, after it is determined that electrical equipment occurs exception, the second gray-scale map can be shown, and to the second ash
In degree figure, pixel corresponding with the pixel that gray value is the first preset value carries out alert flag.For example, by the second gray-scale map
In pixel corresponding with the pixel that gray value is the first preset value it is shown in red.
Alternatively, it is determined that after electrical equipment no exceptions, the second gray-scale map can be shown, and to second
Goal-selling region carries out normal labeled in gray-scale map.For example, the pixel in goal-selling region in the second gray-scale map is shown
It is shown as green.
Above-mentioned steps S205-S307 is, according to the result for comparing analysis, to determine whether electrical equipment occurs abnormal process.
The embodiment of the present invention is according to default target area, corresponding first gray-scale map of Standard Thermal and target heat
Corresponding second gray-scale map of image, image difference treatment is carried out by by the first gray-scale map and the second gray-scale map, obtains difference diagram
Picture, calculates the temperature difference of the gray value mark of each pixel in difference image, according to the gray value mark of each pixel in difference image
The temperature difference of knowledge, marks extraordinary image vegetarian refreshments and normal pixel point, and carries out Denoising disposal, obtains the second difference mark image,
As the result for comparing analysis；By the ratio shared by extraordinary image vegetarian refreshments in calculating the second difference mark image, it is determined that electrically setting
It is standby whether exception to occur, automatically to being compared to target thermal image and Standard Thermal, and can be analyzed according to comparing
Result, determine whether electrical equipment occurs exception.
Example IV
Fig. 4 is the structural representation of the electrical equipment detection means based on infrared detection that the embodiment of the present invention four is provided.
The device of the electrical equipment detection based on infrared detection provided in an embodiment of the present invention can be performed based on the electric of infrared detection
The handling process that equipment detection method embodiment is provided, as shown in figure 4, the device includes：Acquisition module 401, comparison analysis mould
Block 402 and abnormal determining module 403.
Wherein, acquisition module 401 is used to be obtained according to the corresponding Standard Thermal of electrical equipment the target heat of electrical equipment
Image；
Comparing analysis module 402 is used to compare target thermal image and Standard Thermal, obtains comparing analysis
Result；
Abnormal determining module 403 is used to, according to the result for comparing analysis, determine whether electrical equipment occurs exception.
Device provided in an embodiment of the present invention can be specifically for performing the method that above-described embodiment one is provided, specific work(
Here is omitted for energy.
The embodiment of the present invention is by according to the corresponding Standard Thermal of electrical equipment, obtaining the target thermal map of electrical equipment
Picture；Target thermal image and Standard Thermal are compared, obtains comparing the result of analysis；According to the knot for comparing analysis
Really, determine whether electrical equipment occurs exception, realize the ratio of the automatic target thermal image to each acquisition and Standard Thermal
To analysis, it is possible to determine whether electrical equipment occurs exception according to analysis result is compared, reduce the workload of testing staff.
Embodiment five
Fig. 5 is the structural representation of the electrical equipment detection means based on infrared detection that the embodiment of the present invention five is provided.
As shown in figure 5, on the basis of above-described embodiment four, acquisition module 401 includes：Collection submodule 4011, transform subblock
4012nd, the first calculating sub module 4013 and the first determination sub-module 4014.
Wherein, collection submodule 4011 is used for Standard Thermal as background, gathers the current thermal image of electrical equipment.
Transform subblock 4012 is used to for Standard Thermal to be converted to the first gray-scale map, and grey level is carried out to the first gray-scale map
Property conversion so that the scope of the gray value of all pixels point is between 0-255 in the first gray-scale map.
Transform subblock 4012 is additionally operable to for current thermal image to be converted to the second gray-scale map, and gray scale is carried out to the second gray-scale map
Linear transformation, so that the scope of the gray value of all pixels point is between 0-255 in the second gray-scale map.
First calculating sub module 4013 is used to calculate coverage rate of second gray-scale map relative to the first gray-scale map.
Specifically, the first calculating sub module 4013 is additionally operable to：Extract the characteristic point and second gray-scale map of the first gray-scale map
Characteristic point；The characteristic point of characteristic point and the second gray-scale map to the first gray-scale map is matched, and calculates throwing according to matching result
Shadow mapping matrix；According to projection mapping matrix and default target area, calculate in the target area in the first gray-scale map and
Coverage rate of the pixel of the second gray-scale map matching in the first gray-scale map, obtains the second gray-scale map relative to the first gray-scale map
Coverage rate.
If the first determination sub-module 4014 is used for coverage rate more than or equal to default covering threshold value, it is determined that current thermal map
As being target thermal image.
If the first determination sub-module 4014 is additionally operable to coverage rate less than default covering threshold value, it is with Standard Thermal again
Background, gathers the thermal image of subsequent time electrical equipment, until determining target thermal image.
Device provided in an embodiment of the present invention can be specifically for performing the method that above-described embodiment two is provided, specific work(
Here is omitted for energy.
The embodiment of the invention provides the target thermal map that electrical equipment is obtained according to the corresponding Standard Thermal of electrical equipment
The detailed process of picture.
Embodiment six
Fig. 6 is the structural representation of the electrical equipment detection means based on infrared detection that the embodiment of the present invention six is provided.
As shown in fig. 6, on the basis of above-described embodiment five, comparing analysis module 402 includes：Difference submodule 4021, second is calculated
Submodule 4022, difference marks submodule 4023 and denoising submodule 4024.
Wherein, difference submodule 4021 be used for according to default target area, corresponding first gray-scale map of Standard Thermal,
And corresponding second gray-scale map of target thermal image, the first gray-scale map and the second gray-scale map are carried out into image difference treatment, obtain
Difference image.
Second calculating sub module 4022 is used to calculate the temperature difference of the gray value mark of each pixel in difference image.
Difference mark submodule 4023 is used for the temperature difference identified according to the gray value of each pixel in difference image, by the temperature difference
The first preset value is set to more than the gray value of the pixel of temperature difference threshold, the pixel by the temperature difference less than or equal to temperature difference threshold
The gray value of point is set to the second preset value, obtains the first difference mark image.
Denoising submodule 4024 is used to carry out Denoising disposal to the first difference mark image, obtains the second difference mark
Note image, the second difference mark image is the result for comparing analysis.
In the present embodiment, abnormal determining module 403 includes：3rd calculating sub module 4031 and the second determination sub-module
4032。
Wherein, the 3rd calculating sub module 4031 is used to mark image according to the second difference, and it is first default to calculate gray value
The shared ratio in difference image of the pixel of value；
If it is shared in difference image that the second determination sub-module 4032 is used for the pixel that gray value is the first preset value
Ratio be more than or equal to default outlier threshold, it is determined that electrical equipment occurs abnormal.
Device provided in an embodiment of the present invention can be specifically for performing the method that above-described embodiment three is provided, specific work(
Here is omitted for energy.
The embodiment of the present invention is according to default target area, corresponding first gray-scale map of Standard Thermal and target heat
Corresponding second gray-scale map of image, image difference treatment is carried out by by the first gray-scale map and the second gray-scale map, obtains difference diagram
Picture, calculates the temperature difference of the gray value mark of each pixel in difference image, according to the gray value mark of each pixel in difference image
The temperature difference of knowledge, marks extraordinary image vegetarian refreshments and normal pixel point, and carries out Denoising disposal, obtains the second difference mark image,
As the result for comparing analysis；By the ratio shared by extraordinary image vegetarian refreshments in calculating the second difference mark image, it is determined that electrically setting
It is standby whether exception to occur, automatically to being compared to target thermal image and Standard Thermal, and can be analyzed according to comparing
Result, determine whether electrical equipment occurs exception.
In several embodiments provided by the present invention, it should be understood that disclosed apparatus and method, can be by it
Its mode is realized.For example, device embodiment described above is only schematical, for example, the division of the unit, only
Only a kind of division of logic function, can there is other dividing mode when actually realizing, such as multiple units or component can be tied
Another system is closed or is desirably integrated into, or some features can be ignored, or do not perform.It is another, it is shown or discussed
Coupling each other or direct-coupling or communication connection can be the INDIRECT COUPLINGs or logical of device or unit by some interfaces
Letter connection, can be electrical, mechanical or other forms.
The unit that is illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part for showing can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be according to the actual needs selected to realize the mesh of this embodiment scheme
's.
In addition, during each functional unit in each embodiment of the invention can be integrated in a processing unit, it is also possible to
It is that unit is individually physically present, it is also possible to which two or more units are integrated in a unit.Above-mentioned integrated list
Unit can both be realized in the form of hardware, it would however also be possible to employ hardware adds the form of SFU software functional unit to realize.
The above-mentioned integrated unit realized in the form of SFU software functional unit, can store and be deposited in an embodied on computer readable
In storage media.Above-mentioned SFU software functional unit storage is in a storage medium, including some instructions are used to so that a computer
Equipment (can be personal computer, server, or network equipment etc.) or processor (processor) perform the present invention each
The part steps of embodiment methods described.And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (Read-
Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disc or CD etc. it is various
Can be with the medium of store program codes.
Those skilled in the art can be understood that, for convenience and simplicity of description, only with above-mentioned each functional module
Division carry out for example, in practical application, can distribute complete by different functional modules by above-mentioned functions as needed
Into, will the internal structure of device be divided into different functional modules, to complete all or part of function described above.On
The specific work process of the device of description is stated, the corresponding process in preceding method embodiment is may be referred to, be will not be repeated here.
Finally it should be noted that：Various embodiments above is merely illustrative of the technical solution of the present invention, rather than its limitations；To the greatest extent
Pipe has been described in detail with reference to foregoing embodiments to the present invention, it will be understood by those within the art that：Its according to
The technical scheme described in foregoing embodiments can so be modified, or which part or all technical characteristic are entered
Row equivalent；And these modifications or replacement, the essence of appropriate technical solution is departed from various embodiments of the present invention technology
The scope of scheme.
Claims (10)
1. a kind of electrical equipment detection method based on infrared detection, it is characterised in that including：
According to the corresponding Standard Thermal of electrical equipment, the target thermal image of the electrical equipment is obtained；
The target thermal image is compared with Standard Thermal, obtains comparing the result of analysis；
According to the result for comparing analysis, determine whether the electrical equipment occurs exception.
2. method according to claim 1, it is characterised in that described according to the corresponding Standard Thermal of electrical equipment, obtains
The target thermal image of the electrical equipment is taken, including：
With the Standard Thermal as background, the current thermal image of the electrical equipment is gathered；
The Standard Thermal is converted into the first gray-scale map, grey linear transformation is carried out to first gray-scale map, so that institute
The scope of gray value of all pixels point in the first gray-scale map is stated between 0-255；
The current thermal image is converted into the second gray-scale map, grey linear transformation is carried out to second gray-scale map, so that institute
The scope of gray value of all pixels point in the second gray-scale map is stated between 0-255；
Calculate coverage rate of second gray-scale map relative to first gray-scale map；
If the coverage rate is more than or equal to default covering threshold value, determine that the current thermal image is the target thermal map
Picture；
If the coverage rate is less than the default covering threshold value, again with the Standard Thermal as background, collection is lower for the moment
The thermal image of the electrical equipment is carved, until determining the target thermal image.
3. method according to claim 2, it is characterised in that calculating second gray-scale map is relative to described first
The coverage rate of gray-scale map, including：
Extract the characteristic point of first gray-scale map and the characteristic point of second gray-scale map；
The characteristic point of characteristic point and second gray-scale map to first gray-scale map is matched, and according to matching result meter
Calculate projection mapping matrix；
According to the projection mapping matrix and default target area, the target area in first gray-scale map is calculated
Coverage rate of the interior pixel matched with second gray-scale map in first gray-scale map, obtains second gray-scale map
Relative to the coverage rate of first gray-scale map.
4. according to the method in claim 2 or 3, it is characterised in that described to the target thermal image and Standard Thermal
Compare, obtain comparing the result of analysis, including：
According to default target area, corresponding first gray-scale map of the Standard Thermal and the target thermal image
Corresponding second gray-scale map, image difference treatment is carried out by first gray-scale map and second gray-scale map, poor
Partial image；
Calculate the temperature difference of the gray value mark of each pixel in difference image；
The temperature difference that gray value according to each pixel in the difference image is identified, by the temperature difference more than the pixel of temperature difference threshold
Gray value is set to the first preset value, and the temperature difference is set into the less than or equal to the gray value of the pixel of the temperature difference threshold
Two preset values, obtain the first difference mark image；
Denoising disposal is carried out to first difference mark image, the second difference mark image, the second difference mark is obtained
Note image is the result for comparing analysis.
5. method according to claim 4, it is characterised in that described according to the result for comparing analysis, it is determined that described
Whether electrical equipment there is exception, including：
Image is marked according to second difference, calculating gray value is the pixel of first preset value in the difference image
In shared ratio；
If the ratio shared in the difference image of pixel that gray value is first preset value is more than or equal to
Default outlier threshold, it is determined that the electrical equipment occurs abnormal.
6. the device that a kind of electrical equipment based on infrared detection is detected, it is characterised in that including：
Acquisition module, for according to the corresponding Standard Thermal of electrical equipment, obtaining the target thermal image of the electrical equipment；
Analysis module is compared, for comparing the target thermal image with Standard Thermal, obtains comparing analysis
As a result；
Abnormal determining module, for according to the result for comparing analysis, determining whether the electrical equipment occurs exception.
7. device according to claim 6, it is characterised in that the acquisition module includes：
Collection submodule, for the Standard Thermal as background, gathering the current thermal image of the electrical equipment；
Transform subblock, for the Standard Thermal to be converted into the first gray-scale map, gray scale is carried out to first gray-scale map
Linear transformation, so that the scope of the gray value of all pixels point is between 0-255 in first gray-scale map；
The transform subblock is additionally operable to for the current thermal image to be converted to the second gray-scale map, and second gray-scale map is carried out
Grey linear transformation, so that the scope of the gray value of all pixels point is between 0-255 in second gray-scale map；
First calculating sub module, for calculating coverage rate of second gray-scale map relative to first gray-scale map；
First determination sub-module, if determining the current heat more than or equal to default covering threshold value for the coverage rate
Image is the target thermal image；
If first determination sub-module is additionally operable to the coverage rate less than the default covering threshold value, again with the standard
Thermal image is background, the thermal image of electrical equipment described in collection subsequent time, until determining the target thermal image.
8. device according to claim 7, it is characterised in that first calculating sub module is additionally operable to：
Extract the characteristic point of first gray-scale map and the characteristic point of second gray-scale map；
The characteristic point of characteristic point and second gray-scale map to first gray-scale map is matched, and according to matching result meter
Calculate projection mapping matrix；
According to the projection mapping matrix and default target area, the target area in first gray-scale map is calculated
Coverage rate of the interior pixel matched with second gray-scale map in first gray-scale map, obtains second gray-scale map
Relative to the coverage rate of first gray-scale map.
9. the device according to claim 7 or 8, it is characterised in that the comparison analysis module includes：
Difference submodule, for according to default target area, corresponding first gray-scale map of the Standard Thermal and
Corresponding second gray-scale map of the target thermal image, image difference is carried out by first gray-scale map and second gray-scale map
Office is managed, and obtains difference image；
Second calculating sub module, the temperature difference that the gray value for calculating each pixel in difference image is identified；
Difference marks submodule, for the temperature difference that the gray value according to each pixel in the difference image is identified, the temperature difference is big
The first preset value is set in the gray value of the pixel of temperature difference threshold, the picture by the temperature difference less than or equal to the temperature difference threshold
The gray value of vegetarian refreshments is set to the second preset value, obtains the first difference mark image；
Denoising submodule, for carrying out Denoising disposal to first difference mark image, obtains the second difference mark
Image, the second difference mark image is the result for comparing analysis.
10. device according to claim 9, it is characterised in that the abnormal determining module includes：
3rd calculating sub module, for marking image according to second difference, it is first preset value to calculate gray value
The shared ratio in the difference image of pixel；
Second determination sub-module, if shared in the difference image for pixel that gray value is first preset value
Ratio be more than or equal to default outlier threshold, it is determined that the electrical equipment occurs abnormal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710002290.7A CN106846304B (en) | 2017-01-03 | 2017-01-03 | Electrical equipment detection method and device based on infrared detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710002290.7A CN106846304B (en) | 2017-01-03 | 2017-01-03 | Electrical equipment detection method and device based on infrared detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106846304A true CN106846304A (en) | 2017-06-13 |
| CN106846304B CN106846304B (en) | 2020-08-04 |
Family
ID=59117656
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710002290.7A Active CN106846304B (en) | 2017-01-03 | 2017-01-03 | Electrical equipment detection method and device based on infrared detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106846304B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108919373A (en) * | 2018-06-29 | 2018-11-30 | 珠海格力电器股份有限公司 | Target analyte detection controls equipment and its detection control method, device and storage medium |
| CN108961202A (en) * | 2017-12-12 | 2018-12-07 | 北京视联动力国际信息技术有限公司 | A kind of detection method and device regarding networked devices |
| CN108960169A (en) * | 2018-07-12 | 2018-12-07 | 杭州电子科技大学 | Instrument and equipment state on_line monitoring method and system based on computer vision |
| CN111156655A (en) * | 2019-12-24 | 2020-05-15 | 珠海格力电器股份有限公司 | Air conditioner main control board fault self-detection method and air conditioner |
| CN112288747A (en) * | 2020-12-28 | 2021-01-29 | 江苏金恒信息科技股份有限公司 | Intelligent detection method and device for steel billets |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102175953A (en) * | 2011-02-28 | 2011-09-07 | 长沙理工大学 | Discharge online monitoring and fault positioning method for power transmission line insulator |
| CN102840918A (en) * | 2012-08-17 | 2012-12-26 | 中国电力科学研究院 | Method for managing and analyzing infrared spectrogram of electric transmission and transformation equipment |
| CN104331521A (en) * | 2014-11-27 | 2015-02-04 | 国家电网公司 | Automatic power transformation equipment abnormity identification method based on image processing |
| CN104361314A (en) * | 2014-10-21 | 2015-02-18 | 华北电力大学（保定） | Method and device for positioning power transformation equipment on basis of infrared and visible image fusion |
-
2017
- 2017-01-03 CN CN201710002290.7A patent/CN106846304B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102175953A (en) * | 2011-02-28 | 2011-09-07 | 长沙理工大学 | Discharge online monitoring and fault positioning method for power transmission line insulator |
| CN102840918A (en) * | 2012-08-17 | 2012-12-26 | 中国电力科学研究院 | Method for managing and analyzing infrared spectrogram of electric transmission and transformation equipment |
| CN104361314A (en) * | 2014-10-21 | 2015-02-18 | 华北电力大学（保定） | Method and device for positioning power transformation equipment on basis of infrared and visible image fusion |
| CN104331521A (en) * | 2014-11-27 | 2015-02-04 | 国家电网公司 | Automatic power transformation equipment abnormity identification method based on image processing |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108961202A (en) * | 2017-12-12 | 2018-12-07 | 北京视联动力国际信息技术有限公司 | A kind of detection method and device regarding networked devices |
| CN108919373A (en) * | 2018-06-29 | 2018-11-30 | 珠海格力电器股份有限公司 | Target analyte detection controls equipment and its detection control method, device and storage medium |
| CN108919373B (en) * | 2018-06-29 | 2019-12-24 | 珠海格力电器股份有限公司 | Target detection control equipment, target detection control method and device and storage medium |
| CN108960169A (en) * | 2018-07-12 | 2018-12-07 | 杭州电子科技大学 | Instrument and equipment state on_line monitoring method and system based on computer vision |
| CN111156655A (en) * | 2019-12-24 | 2020-05-15 | 珠海格力电器股份有限公司 | Air conditioner main control board fault self-detection method and air conditioner |
| CN112288747A (en) * | 2020-12-28 | 2021-01-29 | 江苏金恒信息科技股份有限公司 | Intelligent detection method and device for steel billets |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106846304B (en) | 2020-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106846304A (en) | Electrical equipment detection method and device based on infrared detection | |
| CN108846418B (en) | Cable equipment temperature abnormity positioning and identifying method | |
| CN107133943B (en) | A kind of visible detection method of stockbridge damper defects detection | |
| CN109977921B (en) | Method for detecting hidden danger of power transmission line | |
| CN104331521B (en) | Transformer anomaly identification method based on image procossing | |
| WO2021042682A1 (en) | Method, apparatus and system for recognizing transformer substation foreign mattter, and electronic device and storage medium | |
| CN106844492B (en) | A kind of method of recognition of face, client, server and system | |
| CN109961398B (en) | Fan blade image segmentation and grid optimization splicing method | |
| CN110045656B (en) | Heating equipment fault monitoring system based on cloud computing | |
| CN110674790B (en) | Abnormal scene processing method and system in video monitoring | |
| CN109377713B (en) | Fire early warning method and system | |
| CN105096305A (en) | Method and device for analyzing state of insulators | |
| CN107547852A (en) | A kind of big data storage system | |
| CN112750104B (en) | Method and device for automatically matching optimal camera by monitoring ship through multiple cameras | |
| CN112184628B (en) | Infrared duplex wave image and cloud early warning system and method for flood prevention and danger detection of dike | |
| CN115861210B (en) | Transformer substation equipment abnormality detection method and system based on twin network | |
| CN111241926A (en) | Attendance checking and learning condition analysis method, system, equipment and readable storage medium | |
| CN110751667A (en) | Method for detecting infrared dim small target under complex background based on human visual system | |
| CN113627321A (en) | Image identification method and device based on artificial intelligence and computer equipment | |
| CN117409083A (en) | Cable terminal identification method and device based on infrared image and improved YOLOV5 | |
| CN116977907A (en) | Image recognition-based power inspection fault diagnosis method and system | |
| CN107358343A (en) | Power engineering safe early warning method based on view data feature difference | |
| CN107895365B (en) | Image matching method and monitoring system for power transmission channel external damage protection | |
| CN110852172A (en) | Method for expanding crowd counting data set based on Cycle Gan picture collage and enhancement | |
| Chen et al. | Attention mechanism-based CNN for surface damage detection of wind turbine blades |
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 |