CN106680217A - Method and device for monitoring failure of transformer respirator - Google Patents
Method and device for monitoring failure of transformer respirator Download PDFInfo
- Publication number
- CN106680217A CN106680217A CN201611189908.7A CN201611189908A CN106680217A CN 106680217 A CN106680217 A CN 106680217A CN 201611189908 A CN201611189908 A CN 201611189908A CN 106680217 A CN106680217 A CN 106680217A
- Authority
- CN
- China
- Prior art keywords
- color
- degree
- image
- detected
- character
- 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 50
- 238000012544 monitoring process Methods 0.000 title claims abstract description 27
- 239000003086 colorant Substances 0.000 claims description 113
- 241000532370 Atla Species 0.000 claims description 86
- 230000005484 gravity Effects 0.000 claims description 32
- 238000003709 image segmentation Methods 0.000 claims description 28
- 238000012806 monitoring device Methods 0.000 claims description 21
- 238000004458 analytical method Methods 0.000 claims description 19
- 239000011159 matrix material Substances 0.000 claims description 19
- 230000009466 transformation Effects 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 238000013507 mapping Methods 0.000 claims description 10
- 238000010191 image analysis Methods 0.000 claims description 4
- 230000004888 barrier function Effects 0.000 claims description 2
- 238000006243 chemical reaction Methods 0.000 claims 2
- 238000012545 processing Methods 0.000 abstract description 5
- 239000000463 material Substances 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 16
- 230000006870 function Effects 0.000 description 15
- 230000008569 process Effects 0.000 description 11
- 230000008859 change Effects 0.000 description 8
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 5
- 230000002093 peripheral effect Effects 0.000 description 5
- 239000000741 silica gel Substances 0.000 description 5
- 229910002027 silica gel Inorganic materials 0.000 description 5
- 230000008439 repair process Effects 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 238000002372 labelling Methods 0.000 description 3
- 210000000056 organ Anatomy 0.000 description 3
- 230000000241 respiratory effect Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000001050 lubricating effect Effects 0.000 description 2
- 230000007257 malfunction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000029058 respiratory gaseous exchange Effects 0.000 description 2
- 239000006096 absorbing agent Substances 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000004549 pulsed laser deposition Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
Abstract
The embodiment of the invention provides a method and a device for monitoring the failure of a transformer respirator, and relates to the technical field of image processing. The method comprises the following steps: firstly, obtaining an orthographic projection image of a color card and an image of a to-be-detected feature body; then, parsing the color degree of the image of the to-be-detected feature body; finally, judging whether the parsed color degree of the image of the to-be-detected feature body is consistent with the prestored standard color degree or not, and generating failure prompt information if the color degree of the image of the to-be-detected feature body is not consistent with the prestored standard color degree. The method and the device for monitoring the failure of the transformer respirator, provided by the invention, have the characteristics of more instantaneity and accuracy, and certain manpower and material resources can be reduced.
Description
Technical field
The present invention relates to technical field of image processing, in particular to a kind of transformer breather fault monitoring method
With device.
Background technology
When transformer oil temperature rise, the unnecessary air of inside transformer can be breathed out, and when temperature of oil in transformer is reduced, then
Extraneous air can be sucked.Due to containing moisture content in extraneous air, oil can be polluted into after inside transformer, so arranging
Transformer breather.Transformer breather is also moisture absorber of transformer, the moisture content and debris in its adsorbable air, makes transformation
Device oil is not invaded by moisture content in extraneous air, it is ensured that the dielectric strength of transformer oil.
Whether transformer breather normally runs, and can be sentenced by the change of character color to be detected in transformator
It is fixed.At present, typically the running status of transformer breather is checked by operation maintenance personnel periodical inspection, this traditional detection method is not
Substantial amounts of manpower and material resources are only wasted, and cannot rapidly and accurately realize 24 hours remote monitorings.
How to improve the problems referred to above, be the emphasis of those skilled in the art's concern.
The content of the invention
It is an object of the invention to provide a kind of transformer breather fault monitoring method and device, to realize monitoring automatically
The change of character color to be detected in transformer breather.
To achieve these goals, the technical scheme that the embodiment of the present invention is adopted is as follows：
In a first aspect, embodiments providing a kind of transformer breather fault monitoring method, the transformator is exhaled
Haustorium fault monitoring method includes：
The orthographic view and transformer breather for obtaining colour atla is presently in the image of environment, the transformator breathing
Device scene image includes the image of character to be detected, and the orthographic view of the colour atla includes multiple first color regions
With at least four first telltale marks；
According to image segmentation algorithm, by the second color region that the image segmentation of the body to be detected is different colours degree；
Color degree, each described first face according to each first color region of the orthographic view of the colour atla
Zone domain and the described first specifically labelled position relationship and the figure of each the second color region of the character to be detected
As the color of image degree of each the second color region of the parsing character to be detected；
Judge the color of image degree and pre-stored of each the second color region of the character described to be detected after parsing
Whether Standard Colors degree is consistent；
If inconsistent, fault cues information is generated.
Second aspect, the embodiment of the present invention additionally provides a kind of transformer breather fault monitoring device, the transformator
Respiratory organ fault monitoring device includes:
Image acquisition unit, the orthographic view and transformer breather for obtaining colour atla is presently in the figure of environment
Picture, the transformer breather scene image includes the image of character to be detected, and the orthographic view of the colour atla includes
There are multiple first color regions and at least four first telltale marks；
Image segmentation unit, for being different colours by the image segmentation of the body to be detected according to image segmentation algorithm
Second color region of degree；
Color degree resolution unit, for according to the face of each first color region of the orthographic view of the colour atla
Colourity, each described first color region and the described first specifically labelled position relationship and the character to be detected it is every
The color of image degree of each the second color region of character to be detected described in the image analysis of individual second color region；
Color degree judging unit, for judging the figure of each the second color region of the character described to be detected after parsing
Whether picture color degree is consistent with the Standard Colors degree of pre-stored；
Fault message signal generating unit, for parsing after character described to be detected the second color region color of image
When degree is inconsistent with the Standard Colors degree of pre-stored, fault cues information is generated.
Transformer breather fault monitoring method provided in an embodiment of the present invention and device, have the advantages that：
A kind of transformer breather fault monitoring method and device are embodiments provided, by obtaining colour atla just
Projected image and the image of character to be detected, parse the image of character to be detected, then according to the feature to be detected of parsing
Whether the color degree of the image of body is consistent with the Standard Colors degree of pre-stored, if it is inconsistent, fault cues information is generated, from
And the automatic purpose monitored is reached, staff can be tieed up in time by fault cues information to transformer breather
Repair, it is very accurate and very convenient.Compared with existing personal monitoring's method, the transformer breather malfunction monitoring that the present invention is provided
The characteristics of method and device has more real-time, accurate, can save certain man power and material.
To enable the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Description of the drawings
In order to be illustrated more clearly that the technical scheme of the embodiment of the present invention, below will be attached to what is used needed for embodiment
Figure is briefly described, it will be appreciated that the following drawings illustrate only certain embodiments of the present invention, thus be not construed as it is right
The restriction of scope, for those of ordinary skill in the art, on the premise of not paying creative work, can be with according to this
A little accompanying drawings obtain other related accompanying drawings.
The high-level schematic functional block diagram of the server that Fig. 1 is provided for present pre-ferred embodiments.
The schematic flow sheet of the transformer breather fault monitoring method that Fig. 2 is provided for present pre-ferred embodiments.
The schematic diagram of the color chart picture that Fig. 3 is provided for present pre-ferred embodiments.
The flow process of the orthographic view for obtaining the colour atla under current environment that Fig. 4 is provided for present pre-ferred embodiments is illustrated
Figure.
The orthographic view schematic diagram of the colour atla that Fig. 5 is provided for present pre-ferred embodiments.
The schematic flow sheet of the parsing character to be detected that Fig. 6 is provided for present pre-ferred embodiments.
The schematic flow sheet of the first the generation fault cues information that Fig. 7 is provided for present pre-ferred embodiments.
The schematic flow sheet of the second generation fault cues information that Fig. 8 is provided for present pre-ferred embodiments.
The schematic flow sheet of the third generation fault cues information that Fig. 9 is provided for present pre-ferred embodiments.
The submodule schematic diagram of the transformer breather fault monitoring device that Figure 10 is provided for present pre-ferred embodiments.
The submodule schematic diagram of the image acquisition unit that Figure 11 is provided for present pre-ferred embodiments.
The submodule schematic diagram of the color degree resolution unit that Figure 12 is provided for present pre-ferred embodiments.
The submodule schematic diagram of the first fault message signal generating unit that Figure 13 is provided for present pre-ferred embodiments.
The submodule schematic diagram of second fault message signal generating unit that Figure 14 is provided for present pre-ferred embodiments.
Icon：10- servers；11- transformer breather fault monitoring devices；12- memorizeies；13- storage controls；
14- processors；15- Peripheral Interfaces；111- image acquisition units；1111- image capture modules；1112- color chart pictures determine mould
Block；1113- perspective transformation matrix computing modules；1114- orthographic view mapping blocks；112- image segmentation units；113- face
Colourity resolution unit；1131- corresponding relation generation modules；1132- color of image degree parsing modules；114- colors degree judges single
Unit；115- fault message signal generating units；1152- position acquisition modules；1153- fail result analysis modules；1154- fault messages
Generation module；1156- area ratio computing modules.
Specific embodiment
Below in conjunction with accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Ground description, it is clear that described embodiment is only a part of embodiment of the invention, rather than the embodiment of whole.Generally exist
Herein the component of the embodiment of the present invention described and illustrated in accompanying drawing can be arranged and designed with a variety of configurations.Cause
This, below the detailed description of the embodiments of the invention to providing in the accompanying drawings is not intended to limit claimed invention
Scope, but it is merely representative of the selected embodiment of the present invention.Based on embodiments of the invention, those skilled in the art are not doing
The every other embodiment obtained on the premise of going out creative work, belongs to the scope of protection of the invention.
It should be noted that：Similar label and letter represents similar terms in following accompanying drawing, therefore, once a certain Xiang Yi
It is defined in individual accompanying drawing, then it need not be further defined and is explained in subsequent accompanying drawing.Meanwhile, the present invention's
In description, term " first ", " second " etc. are only used for distinguishing description, and it is not intended that indicating or implying relative importance.
As shown in figure 1, being the high-level schematic functional block diagram of the server 10 that the present invention is provided.The server 10 includes transformator
Respiratory organ fault monitoring device 11, memorizer 12, storage control 13, processor 14 and Peripheral Interface 15.
The memorizer 12, storage control 13, processor 14 and each element of Peripheral Interface 15 each other directly or
It is electrically connected with indirectly, to realize the transmission or interaction of data.For example, these elements each other can be logical by one or more
News bus or holding wire are realized being electrically connected with.The transformer breather fault monitoring device 11 can be with software including at least one
Or the form of firmware (firmware) is stored in the memorizer 12 or is solidificated in the operating system of the server 10
Software function module in (operating system, OS).The processor 14 be used for perform in memorizer 12 store can
Performing module, such as software function module or computer program that described transformer breather fault monitoring device 11 includes.
Wherein, memorizer 12 may be, but not limited to, random access memory (Random Access Memory,
RAM), read only memory (Read Only Memory, ROM), programmable read only memory (Programmable Read-Only
Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory, EPROM),
Electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only Memory, EEPROM) etc..
Wherein, memorizer 12 be used for storage program, the processor 14 after execute instruction is received, perform described program, aforementioned
Method performed by the server of the stream process definition that inventive embodiments any embodiment is disclosed can apply in processor 14,
Or realized by processor 14.
A kind of possibly IC chip of processor 14, the disposal ability with signal.Above-mentioned processor 14 can be with
It is general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network processing unit
(Network Processor, abbreviation NP) etc.；Can also be digital signal processor (DSP), special IC (ASIC),
Ready-made programmable gate array (FPGA) either other PLDs, discrete gate or transistor logic, discrete hard
Part component.Can realize or perform disclosed each method in the embodiment of the present invention, step and logic diagram.General processor
Can be microprocessor or the processor 14 can also be any conventional processor etc..
The Peripheral Interface 15 is by various input/output devices coupled to processor 14 and memorizer 12.In some realities
In applying example, Peripheral Interface 15, processor 14 and storage control 13 can be realized in one single chip.In some other example
In, they can be realized respectively by independent chip.
Fig. 2 is referred to, is the transformer breather malfunction monitoring being applied to shown in Fig. 1 that present pre-ferred embodiments are provided
The flow chart of method.The idiographic flow shown in Fig. 2 will be described in detail below.
Step S201, the orthographic view and transformer breather for obtaining colour atla is presently in the image of environment.
Wherein, transformer breather scene image includes the image of character to be detected, and character to be detected is a kind of
The object that water or oil can change colour is met, in this embodiment, from silica gel as character to be detected, also, described in the present embodiment
The orthographic view of colour atla includes multiple first color regions and at least four first telltale marks.Fig. 3 is referred to, in this reality
In applying example, colour atla is made up of 24 foursquare color blocks and 4 foursquare telltale marks；The length of side phase of each color block
Deng color is different；24 color blocks are arranged into the row of 4 row 6；The specifically labelled square for being characterized as 3 layers of nesting, from outward to
Interior color be followed successively by it is black, it is in vain, black.Telltale mark is divided into A, the classes of B two；The length of side of B classes is 2 times of A classes；Have 3 in 4 telltale marks
Individual A classes, wherein 1 B class, B classes labelling are located at the lower right corner of color chart picture.Due to being only provided with a B class telltale mark, and B
Class telltale mark is always positioned at the lower right of image, so, specifically labelled of different sizes according to A, B class, position is constant and B classes
Labelling is all the time in the bottom-right feature of image, it may be determined that other three elements of a fix are located at the position in color chart picture.
Certainly, in other specific embodiments, the color category of colour atla, the arrangement mode of color block, specifically labelled feature also may be used
To adopt other modes, such as, telltale mark may be alternatively provided as 6 or 8, and the specific embodiment of the present invention is not with this
It is limited.
Specifically, step S201 can be but be not limited to following two kinds：
The first：The orthographic view and transformer breather for obtaining the colour atla of pre-stored is presently in the scene of environment
Image.
The orthographic view of colour atla can be the image of pre-stored, and in acquisition transformer breather the figure of environment is presently in
As when only need to obtain the image of character to be detected.By the colour atla of image and the pre-stored of character to be detected that will obtain
Orthographic view is compared, you can obtain the color degree of character to be detected, and this mode is simple to operation.
Second：Fig. 4 is referred to, is that the orthographic view and transformer breather for obtaining colour atla is presently in environment
The flow chart of image.
Step S2011, gathers doubtful colour atla area image and the character to be detected being presently in the image of environment,
Wherein, doubtful colour atla area image includes color chart picture.
Specifically, colour atla is arranged at and is presently under environment simultaneously with character to be detected, in the orthographic projection for obtaining colour atla
When image and transformer breather are presently in the image of environment, the orthographic view of colour atla and spy to be detected can be simultaneously gathered
Levy the image of body.Gather color chart as when, because the image for collecting includes in color chart picture and transformer breather it
The image of his element, it is impossible to determine the concrete scope of color chart picture, so the simply doubtful colour atla area image for collecting, doubtful
Colour atla area image includes the image of color chart picture and other elements in transformer breather, then again to doubtful colour atla region
Image is processed.
It should be noted that in the present embodiment, using camera acquisition image, of course, in other examples,
Image, such as photographing unit can also be gathered by other equipment, the present embodiment is not limited this.
Step S2012, according to doubtful colour atla area image and at least four first telltale marks color chart picture is determined.
Specifically, in the present embodiment, because colour atla in actual applications and video camera have certain angle of inclination, no
Beneficial to the region segmentation of color chart picture, so the color chart picture for collecting should be converted into into orthographic view.It is current obtaining
Color chart in local environment as when, it is necessary first to determine the scope of color chart picture, otherwise other images may also be listed in
In color chart picture.So the transformer breather fault monitoring device 11 that the present embodiment is provided is worked as in collection transformer breather
During the image of front local environment, the doubtful colour atla area image that can be gathered first and the image of character to be detected, then, root
The scope of color chart picture is determined according to 4 telltale marks of color chart picture, so that it is determined that color chart picture.According to 4 of color chart picture
Telltale mark determines that the method for the scope of color chart picture is：Determine its region for surrounding by four telltale marks, then,
The particular location of color chart picture is located at according to each telltale mark, such as B classes telltale mark is located at the lower right of color chart picture, it is determined that
Color chart picture, so as to eliminate the image of other elements in the transformer breather for collecting.
Step S2013, is located at default according to described at least four first telltale marks of the orthographic view of the colour atla
Coordinate system in coordinate calculate perspective transform with least four second specifically labelled coordinates of the color chart picture for collecting
Matrix.
Specifically, calculating the specific method of perspective transformation matrix is：First, the color chart picture is changed into into gray-scale maps；
Then, according to maximum variance between clusters, the gray-scale maps are changed into into binary map；Finally, traveled through according to specifically labelled feature
Each profile, determines the first telltale mark and sets up coordinate system with the specifically labelled center origin of B classes first in the binary map
In coordinate.Obtain all coordinates of color chart picture, including four the first specifically labelled coordinate (x0, y0)、(x1, y1)、(x2,
y2) and (x3, y3), also, the second telltale mark of the orthographic view according to the colour atla of pre-stored, marked with the positioning of B classes second
Note center origin sets up coordinate system, obtains four the second specifically labelled coordinate (x0’,y0)、(x1’,y1’)、(x2’,y2') and
(x3’,y3’).According to perspective transform formulaWherein,
(x, y) is the coordinate in the color chart picture, and (x', y') is the coordinate being converted into after perspective transform in orthographic view, and H is
The perspective transformation matrix of 3X3Due to coordinate of known 4 the first telltale marks in the color chart picture
With coordinate of 4 the second telltale marks in the orthographic view, by 4 the first telltale marks in the color chart as in
The coordinate of coordinate and 4 the second telltale marks in the orthographic view brings respectively perspective transform formula into, tries to achieve perspective and becomes
Matrix H is changed, so as to obtain perspective transformation matrix H.
Step S2014, the colour atla is being mapped out just according to the perspective transformation matrix with the coordinate of the color chart picture
Projected image.
Specifically, simultaneously, colour atla can simultaneously be determined due in four the first specifically labelled coordinates for obtaining color chart picture
The coordinate of remainder image in image, so, bring the coordinate of remainder image in color chart picture into perspective transform formulaAll orthographic projections of color chart picture can be mapped out
Image.The orthographic view of colour atla is as shown in Figure 5.
Due in actual applications, if color chart picture is prestored be stored in transformer breather fault monitoring device 11,
So transformer breather fault monitoring device 11 from be presently in environment obtain be only character to be detected image,
Due to colour atla it is different from the environment residing for character to be detected, then may be due to extraneous factors such as illumination, the angles of video camera
Cause the color degree of the character to be detected of acquisition inconsistent with the color degree of reality, so as to cause the generation of error.So,
In the present embodiment, it is preferred that character to be detected is in the scene of current environment simultaneously with colour atla, transformer breather event
Barrier monitoring device 11 obtains the image and color chart picture of the character to be detected of the scene for being presently in environment simultaneously, so as to ensure
Character to be detected is identical with the environment residing for colour atla, even if there is the interference of extraneous factor, obtains the figure of character to be detected
As also can be interfered with color chart picture simultaneously, it is ensured that the color degree of the character to be detected of acquisition and actual color degree one
Cause, so as to not result in error.
Step S202, according to image segmentation algorithm, by character to be detected the second chromatic zones of different colours degree is divided into
Domain.
Specifically, in the present embodiment, according to image segmentation algorithm, using the image of character to be detected as one group of multidimensional
Data point, and using space position parameter and color parameter as the average drifting window of windows radius character to be detected figure
As upper movement, the institute that data peaks are converged to after window transform is a little connected, and be partitioned into the different area of color degree
Domain.
In the present embodiment, image segmentation is carried out using Mean Shift image segmentation algorithms, of course, other real
In applying example, it is also possible to which other image segmentation algorithms carry out image segmentation, the present embodiment is not particularly limited.Using Mean Shift
When image segmentation algorithm carries out image segmentation, Mean Shift vectors always point at the direction of density increase, can be expressed as down
Formula：
Wherein：
Wherein, (xi- x) it is sampled point xiRelative to the offset vector of origin x, H is the bandwidth matrices of the dxd of positive definite, G (x)
It is unit kernel function, w (xi) it is sampled point xiWeight.In the embodiment of the present invention, H is defined to the direct ratio matrix of unit matrix, i.e.,
H=h2I, Mean Shift vectors are represented by
Mh(x)=mh(x)-x
Wherein,
Given starting point x, tolerance ε, and kernel function G (x), Mean Shift algorithms constantly circulate execution following 3
Step, until it meets the condition of end.
(1) to mhX () is calculated
(2) by mhX () is assigned to x
(3) ifJust terminate this circulation；Otherwise perform (1).Mean Shift algorithms are used for image
During segmentation, because color space and locational space are separate, therefore kernel function is expressed as the product of the kernel function of two spaces, i.e. G
(x)=Ghr(xr)Ghs(xs), wherein hr is color bandwidth, and hs is spatial bandwidth.
Step S203, color degree according to each first color region of the orthographic view of the colour atla, each
First color region and the described first specifically labelled position relationship and each second face of the character to be detected
The color of image degree of each the second color region of character to be detected described in the image analysis in zone domain；
Step S203 also includes two kinds of implementations.
The first：When the orthographic view of colour atla is the image of pre-stored, the orthographic view of colour atla can be simultaneously stored
Each the first color region color degree and each first color region and the first specifically labelled position relationship, according to colour atla
The color degree of each the first color region of orthographic view, each first color region and the first specifically labelled position close
System, then by the way that the image of character to be detected is compared with the color chart picture of pre-stored, so as to parse spy to be detected
Levy the color of image degree of body.
Second, Fig. 6 is referred to, be the color of image degree flow chart for parsing character to be detected.
Step S2031, according to the color degree of each the 3rd color region of default orthographic view model and described
The color degree of each the first color region of the orthographic view of colour atla generates each the 3rd color region that there are mapping relations
With the color degree corresponding relation of first color region.
Specifically, the step of the orthographic view and transformer breather for obtaining colour atla is presently in the image of environment
Afterwards, each first color region of colour atla orthographic view and default orthographic view model under conditions present is also predefined
Each the 3rd color region color degree between corresponding relation, so as to carry out the parsing of color degree to character to be detected.
In default orthographic view model, there are 24 different regions of color degree, and can determine according to 4 telltale marks
The position in each region, the orthographic view of colour atla is contrasted with default orthographic view, due to the orthographic projection of colour atla
Image is the image in current environment, thus be obtained under current environment each first color region of colour atla orthographic view with
Corresponding relation between the color degree of each the 3rd color region of default orthographic view model.
Step S2032, the color degree of each the first color region of the orthographic view according to the colour atla, each
First color region and the first specifically labelled position relationship, the image of the character to be detected and each the 3rd chromatic zones
Domain parses the color of image degree of character to be detected with the color degree corresponding relation of first color region.
Specifically, because step S2031 has determined that corresponding relation, according to corresponding relation and character to be detected
The color degree of image, parses the color of image degree of character to be detected.
Step S204, judge parsing after character described to be detected each the second color region color of image degree with
Whether the Standard Colors degree of pre-stored is consistent；
Step S205, generating run regular prompt information.
Step S206, generates fault cues information.
Specifically, because step S203 has parsed the color degree of character to be detected, by character to be detected
Color degree is compared with the Standard Colors degree of pre-stored, you can judge whether the two is consistent.
Step S206 includes but is not limited to following three：
The first, refers to Fig. 7, if the mark of the color of image degree of the character described to be detected after parsing and pre-stored
Quasi- color degree is inconsistent, then perform the flow process for generating fault cues information.
Step S2062, obtains the center of gravity of each the second color region and the position according to center of gravity each described determines each
The second color region location.
Specifically, obtain the center of gravity of each the second color region after segmentation, by the comparison to center of gravity, determine each the
Particular location of the second colors region in whole character color to be detected, such as top or bottom.
Step S2063, according to second face inconsistent with the Standard Colors degree of pre-stored of the image of character to be detected
The color degree in zone domain and the second color region location analysis first inconsistent with the Standard Colors degree of pre-stored
Fail result.
Specifically, Fisrt fault result is analyzed according to formula result=f (x, y), wherein, x represent it is described each
Position of the center of gravity of the second color region in the character image to be detected, y represents the Standard Colors with the pre-stored
The color degree of the second inconsistent color region of degree, result represents the first concrete fail result, and f (x, y) represents that first analyzes
Equation.
Step S2064, generates fault cues information and Fisrt fault result.
According to formula result1=f (x1,y1), the first concrete fail result is generated, wherein, x1Represent and the pre-stored
Inconsistent the second color region of Standard Colors degree first position of the center of gravity in the character image to be detected, y1Table
Show the first color degree of second color region inconsistent with the Standard Colors degree of the pre-stored, result1Represent that first has
Body fail result, f (x1,y1) represent that first analyzes formula；
Or according to formula result2=f (x2,y1), the second concrete fail result is generated, wherein, x2Expression prestores with described
The second position of the center of gravity of the second inconsistent color region of the Standard Colors degree of storage in the character image to be detected, y1
Represent the first color degree of second color region inconsistent with the Standard Colors degree of the pre-stored, result2Represent second
Concrete fail result, f (x2,y1) represent that second analyzes formula；
Or according to formula result3=f (x1,y2), the 3rd concrete fail result is generated, wherein, x1Expression prestores with described
First position of the center of gravity of the second inconsistent color region of the Standard Colors degree of storage in the character image to be detected, y2
Represent the second color degree of second color region inconsistent with the Standard Colors degree of the pre-stored, result3Represent the 3rd
Concrete fail result, f (x1,y2) represent that the 3rd analyzes formula；
Or according to formula result4=f (x2,y2), the 4th concrete fail result is generated, wherein, x2Expression prestores with described
The second position of the center of gravity of the second inconsistent color region of the Standard Colors degree of storage in the character image to be detected, y2
Represent the second color degree of second color region inconsistent with the Standard Colors degree of the pre-stored, result4Represent the 4th
Concrete fail result, f (x2,y2) represent that the 4th analyzes formula.
Will be exemplified below, be red when moist as blueness when being dried with character color to be detected in the present embodiment
Color, is to illustrate as a example by black when being polluted by the oil., wherein, the scope of blue corresponding color degree is A to B, red corresponding
The scope of color degree is C to D, and the scope of the corresponding color degree of black is E to F, certainly, in other specific embodiments
In, character to be detected can also be under various regimes other colors, and the specific embodiment of the present invention is not limited thereto,
result1=f (x=tops, y=y1), Fisrt fault result is represented, conservator inner corrugated pipe is problematic, needs dimension
Repair, wherein, y1Color degree value between E to F.
Result2=f (x=bottoms, y=y1), the second fail result is represented, the oily suck-back in lubricating cup causes silica gel dirty
Dye, needs to change silica gel, reduces the oil in lubricating cup, wherein, y1Color degree value between E to F.
Result3=f (x=tops, y=y2), the 3rd fail result is represented, respiratory organ seal failure needs to pacify again
Dress, wherein, y2Color degree value between C to D.
Result4=f (x=bottoms, y=y2), the 4th fail result is represented, silica gel humidity is excessive, needs to change silica gel,
Wherein, y2Color degree value between C to D.
Second, Fig. 8 is referred to, if the mark of the color of image degree of the character described to be detected after parsing and pre-stored
Quasi- color degree is inconsistent, then the flow process in execution flow chart.
Step S2072, calculates the area in the different region of each color degree and the image of the character to be detected
Area, and calculate the area in the different region of the color degree account for the character to be detected image area ratio.
Specifically, according to segmentation after the second different color regions, the face of each the second color region can be calculated
The long-pending gross area with the image of character to be detected, the area for thus calculating the different region of the color degree accounts for described to be checked
Survey the ratio of the area of the image of character.
Step S2073, according to the area inconsistent with the Standard Colors degree of the pre-stored character to be detected is accounted for
Image area the fail result of proportion grading second.
Specifically, the second fail result is analyzed according to formula result=f (y, z), wherein, y is represented and the pre-stored
Inconsistent the second color region of Standard Colors degree color degree, z represents inconsistent with the Standard Colors degree of the pre-stored
The second color region area account for the character image to be detected area ratio, result represents the second concrete failure
As a result, f (y, z) represents the second analysis equation formula.
Step S2074, generates fault cues information and the second fail result.
According to formula result5=f (y1,z1), the 5th concrete fail result is generated, wherein, y1Represent and the pre-stored
Inconsistent the second color region of Standard Colors degree the first color degree, z1Represent with the Standard Colors degree of the pre-stored not
The area of the second consistent color region accounts for the first scope of the ratio of the area of the character image to be detected；result5
Represent the 5th concrete fail result；
Or according to formula result6=f (y2,z1), the 6th concrete fail result is generated, wherein, y2Expression prestores with described
Second color degree of the second inconsistent color region of the Standard Colors degree of storage, z1Represent the Standard Colors degree with the pre-stored
The area of the second inconsistent color region accounts for the first scope of the ratio of the area of the character image to be detected,
result6Represent the 6th concrete fail result；
Or according to formula result7=f (y1,z2), the 7th concrete fail result is generated, wherein, y1Expression prestores with described
First color degree of the second inconsistent color region of the Standard Colors degree of storage, z2Represent the Standard Colors degree with the pre-stored
The area of the second inconsistent color region accounts for the second scope of the ratio of the area of the character image to be detected,
result7Represent the 7th concrete fail result；
Or according to formula result8=f (y2,z2), the 8th concrete fail result is generated, wherein, y2Expression prestores with described
Second color degree of the second inconsistent color region of the Standard Colors degree of storage, z2Represent the Standard Colors degree with the pre-stored
The area of the second inconsistent color region accounts for the second scope of the ratio of the area of the character image to be detected,
result8Represent the 8th concrete fail result.
Will be exemplified below, result5=f (y=y1,z>10%), the 5th fail result, transformer breather are represented
A kind of element in interior is damaged, and damages relatively light, wherein, y1Color degree value between E to F.
Result6=f (y=y2,z>10%) another kind of element in, representing in the 6th fail result, transformer breather
It is damaged, and damages relatively light, wherein, y2Color degree value between C to D.
Result7=f (y=y1,z>80%) a kind of element in, representing in the 7th fail result, transformer breather meets with
To damage, and damage heavier, wherein, y1Color degree value between E to F.
Result8=f (y=y2,z>80%) another kind of element in, representing in the 8th fail result, transformer breather
It is damaged, and damages heavier, wherein, y2Color degree value between C to D.
The third, refers to Fig. 9, if the mark of the color of image degree of the character described to be detected after parsing and pre-stored
Quasi- color degree is inconsistent, then the flow process in execution flow chart.
Step S2082, obtains the center of gravity of each the second color region and the position according to center of gravity each described determines each
The second color region location, calculates the area and the feature to be detected in the different region of each color degree
The area of the image of body, and calculate the area that the area in the different region of the color degree accounts for the image of the character to be detected
Ratio.
Step S2083, according to the character to be detected image it is inconsistent with the Standard Colors degree of the pre-stored
The second color region color degree and the inconsistent second color region location of Standard Colors degree of the pre-stored
And the area inconsistent with the Standard Colors degree of the pre-stored accounts for the ratio of the area of the image of the character to be detected
Analyze the 3rd fail result.
Step S2084, generates fault cues information and the 3rd fail result.
For example, concrete fail result is analyzed according to formula result=f (x, y, z), wherein, x represents the mark with pre-stored
The second inconsistent color region location of quasi- color degree, y represents inconsistent with the Standard Colors degree of pre-stored second
The color of color region, it is described that z represents that the area of second color region inconsistent with the Standard Colors degree of the pre-stored is accounted for
The ratio of the area of the image of character to be detected, result represents concrete fail result, and f (x, y, z) represents analysis equation formula.
In the present embodiment, analyze concrete fail result according to formula result=f (x, y, z) to be completed by software, the false code of software
For：
It should be noted that before above-mentioned false code is performed, can first judge y by program1With y2Value whether arrive in A
Between B, C to D, or the codomain of E to F.
Refer to Figure 10, be present pre-ferred embodiments provide Fig. 1 shown in transformer breather fault monitoring device
11 functional unit schematic diagram.It should be noted that the transformer breather fault monitoring device 11 that the present embodiment is provided, its
Ultimate principle and the technique effect of generation are identical with above-described embodiment, are brief description, and embodiment of the present invention part does not refer to it
Place, refers to corresponding contents in the above embodiments.It is single that the transformer breather fault monitoring device 11 includes that image is obtained
Unit 111, image segmentation unit 112, color degree resolution unit 113, color degree judging unit 114 and fault message signal generating unit
115。
Image acquisition unit 111, the orthographic view and transformer breather for obtaining colour atla is presently in environment
Image, the transformer breather scene image includes the image of character to be detected, the orthographic view of the colour atla
Include multiple first color regions and at least four first telltale marks.
It is to be appreciated that can perform step S201 by image acquisition unit 111.
Specifically, wherein, image acquisition unit 111 obtain image mode include two kinds：
The first：Image acquisition unit 111 is used for the orthographic view of the colour atla for obtaining pre-stored and transformator breathing
Device is presently in the image that the orthographic view of the scene image of environment, i.e. colour atla can be pre-stored.
Second：Transformer breather fault monitoring device 11 obtains the color chart picture that is presently in environment and treats simultaneously
The image of detection character, then by the color chart picture of acquisition is transformed into the orthographic view of colour atla again.
Figure 11 is that the functions of modules of image acquisition unit 111 is shown when the orthographic view of colour atla is obtained for current environment
It is intended to.The image acquisition unit 111 includes image capture module 1111, color chart as determining module 1112, perspective transformation matrix
Computing module 1113 and orthographic view mapping block 1114.
Image capture module 1111, is being presently in for gathering doubtful colour atla area image and the character to be detected
The image of environment, wherein, doubtful colour atla area image includes color chart picture.
It is to be appreciated that can perform step S2011 by image capture module 1111.
Color chart as determining module 1112, for according to the doubtful colour atla area image and described at least four first
Telltale mark determines color chart picture.
It is to be appreciated that by color chart as determining module 1112 can perform step S2012.
Perspective transformation matrix computing module 1113, for described at least four according to the orthographic view of the colour atla
The coordinate that one positioning labelling is located in default coordinate system is specifically labelled with least four second of the color chart picture for collecting
Coordinate calculates perspective transformation matrix.
It is to be appreciated that can perform step S2013 by perspective transformation matrix computing module 1113.
Orthographic view mapping block 1114, for reflecting with the coordinate of the color chart picture according to the perspective transformation matrix
Project the orthographic view of the colour atla.
It is to be appreciated that can perform step S2014 by orthographic view mapping block 1114.
Image segmentation unit 112, for being different face by the image segmentation of the body to be detected according to image segmentation algorithm
Second color region of colourity.
It is to be appreciated that can perform step S202 by image segmentation unit 112.
Figure 12 is the functions of modules of color degree resolution unit 113 when the orthographic view of colour atla is obtained for current environment
Schematic diagram.
Color degree resolution unit 113, for according to each described first color region of the orthographic view of the colour atla
Color degree, each described first color region and the described first specifically labelled position relationship and the character to be detected
Image analysis described in character to be detected color of image degree.
It is to be appreciated that can perform step S203 by color degree resolution unit 113.
The color degree resolution unit 113 includes corresponding relation generation module 1131 and color of image degree parsing module 1132.
Corresponding relation generation module 1131, for according to each the 3rd color region of default orthographic view model
The color degree of each the first color region of the orthographic view of color degree and the colour atla is generated has the every of mapping relations
The color degree corresponding relation of individual 3rd color region and first color region.
It is to be appreciated that can perform step S2031 by corresponding relation generation module 1131.
Color of image degree parsing module 1132, for each first color of the orthographic view according to the colour atla
The color degree in region, each first color region and the described first specifically labelled position relationship, the character to be detected
The color degree corresponding relation of image and each the 3rd color region and second color region parses the feature to be detected
The color of image degree of body.
It is to be appreciated that can perform step S2032 by color of image degree parsing module 1132.
Color degree judging unit 114, for judging the color of image degree of the character described to be detected after parsing and prestoring
Whether the Standard Colors degree of storage is consistent.
It is to be appreciated that can perform step S204 by color degree judging unit 114.
Fault message signal generating unit 115, if for parsing after character described to be detected color of image degree with prestore
When the Standard Colors degree of storage is inconsistent, fault cues information is generated.
It is to be appreciated that can perform step S206 by fault message signal generating unit 115.
In the present embodiment, the mode of the generation of fault message signal generating unit 115 failure is including but not limited to following two：
The first, refers to Figure 13, and fault message signal generating unit 115 includes:
Position acquisition module 1152, for obtaining the center of gravity of each the second color region and according to the position of center of gravity each described
Put and determine each described second color region location.
It is to be appreciated that can perform step S2062 by position acquisition module 1152.
Fail result analysis module 1153, for according to the mark with the pre-stored of the image of the character to be detected
The color degree of the second inconsistent color region of quasi- color degree and inconsistent with the Standard Colors degree of the pre-stored second
Color region location analyzes Fisrt fault result.
It is to be appreciated that can perform step S2063 by fail result analysis module 1153.
Fault message generation module 1154, for generating fault cues information and Fisrt fault object information.
It is to be appreciated that can perform step S2064 by fault message generation module 1154.
Specifically, fault message generation module 1154 is used to be analyzed Fisrt fault according to formula result=f (x, y)
As a result, wherein, x represents position of the center of gravity of each second color region in the character image to be detected, and y is represented
The color degree of second color region inconsistent with the Standard Colors degree of the pre-stored, result represents Fisrt fault result, f
(x, y) represents the first analysis equation formula；
Fault message generation module 1154 is used for according to formula result1=f (x1,y1), generate the first concrete failure knot
Really, wherein, x1The center of gravity of expression second color region inconsistent with the Standard Colors degree of the pre-stored is described to be detected
First position in character image, y1Represent the of second color region inconsistent with the Standard Colors degree of the pre-stored
One color degree, result1Represent the first concrete fail result, f (x1,y1) represent that first analyzes formula；
Or according to formula result2=f (x2,y1), the second concrete fail result is generated, wherein, x2Expression prestores with described
The second position of the center of gravity of the second inconsistent color region of the Standard Colors degree of storage in the character image to be detected, y1
Represent the first color degree of second color region inconsistent with the Standard Colors degree of the pre-stored, result2Represent second
Concrete fail result, f (x2,y1) represent that second analyzes formula；
Or according to formula result3=f (x1,y2), the 3rd concrete fail result is generated, wherein, x1Expression prestores with described
First position of the center of gravity of the second inconsistent color region of the Standard Colors degree of storage in the character image to be detected, y2
Represent the second color degree of second color region inconsistent with the Standard Colors degree of the pre-stored, result3Represent the 3rd
Concrete fail result, f (x1,y2) represent that the 3rd analyzes formula；
Or according to formula result4=f (x2,y2), the 4th concrete fail result is generated, wherein, x2Expression prestores with described
The second position of the center of gravity of the second inconsistent color region of the Standard Colors degree of storage in the character image to be detected, y1
Represent the second color degree of second color region inconsistent with the Standard Colors degree of the pre-stored, result4Represent the 4th
Concrete fail result, f (x2,y2) represent that the 4th analyzes formula.
Second, Figure 14 is referred to, fault message signal generating unit 115 includes:
Area ratio computing module 1156, the area for calculating the different region of each color degree is to be checked with described
The area of the image of character is surveyed, and calculates the image that the area in the different region of the color degree accounts for the character to be detected
Area ratio.
It is to be appreciated that can perform step S2072 by area ratio computing module 1156.
Fail result analysis module 1153, for the foundation area inconsistent with the Standard Colors degree of the pre-stored institute is accounted for
State the fail result of proportion grading second of the area of the image of character to be detected.
It is to be appreciated that can perform step S2073 by fail result analysis module 1153.
Fault message generation module 1154, for generating fault cues information and the second fail result.
It is to be appreciated that can perform step S2074 by fault message generation module 1154.
Specifically, fail result analysis module 1153 is used to analyze the second failure knot according to formula result=f (y, z)
Really, wherein, y represents the color degree of second color region inconsistent with the Standard Colors degree of the pre-stored, z represent with it is described
The area of the second inconsistent color region of the Standard Colors degree of pre-stored accounts for the ratio of the area of the character image to be detected
Example, result represents the second fail result, and f (y, z) represents the second analysis equation formula；
Fault message generation module 1154 is used for according to formula result5=f (y1,z1), generate the 5th concrete failure knot
Really, wherein, y1Represent the first color degree of second color region inconsistent with the Standard Colors degree of the pre-stored, z1Represent
The area of second color region inconsistent with the Standard Colors degree of the pre-stored accounts for the face of the character image to be detected
First scope of long-pending ratio；result5Represent the 5th concrete fail result, f (y1,z1) represent that the 5th analyzes formula；
Or according to formula result6=f (y2,z1), the 6th concrete fail result is generated, wherein, y2Expression prestores with described
Second color degree of the second inconsistent color region of the Standard Colors degree of storage, z1Represent the Standard Colors degree with the pre-stored
The area of the second inconsistent color region accounts for the first scope of the ratio of the area of the character image to be detected,
result6Represent the 6th concrete fail result, f (y2,z1) represent that the 6th analyzes formula；
Or according to formula result7=f (y1,z2), the 7th concrete fail result is generated, wherein, y1Expression prestores with described
First color degree of the second inconsistent color region of the Standard Colors degree of storage, z2Represent the Standard Colors degree with the pre-stored
The area of the second inconsistent color region accounts for the second scope of the ratio of the area of the character image to be detected,
result7Represent the 7th concrete fail result, f (y1,z2) represent that the 7th analyzes formula；
Or according to formula result8=f (y2,z2), the 8th concrete fail result is generated, wherein, y2Expression prestores with described
Second color degree of the second inconsistent color region of the Standard Colors degree of storage, z2Represent the Standard Colors degree with the pre-stored
The area of the second inconsistent color region accounts for the second scope of the ratio of the area of the character image to be detected,
result8Represent the 8th concrete fail result, f (y2,z2) represent that the 8th analyzes formula.
In sum, a kind of transformer breather fault monitoring method and device are embodiments provided, by obtaining
The orthographic view of colour atla and the image of character to be detected are taken, the image of character to be detected is parsed, then according to parsing
Whether the color degree of the image of character to be detected is consistent with the Standard Colors degree of pre-stored, if it is inconsistent, generating failure
Information, so as to reach monitoring automatically.Compared with existing personal monitoring's method, the transformer breather failure that the present invention is provided
The characteristics of monitoring method and device have more real-time, accurate, can save certain man power and material.
In several embodiments provided herein, it should be understood that disclosed apparatus and method, it is also possible to pass through
Other modes are realized.Device embodiment described above is only schematic, for example, the flow chart and block diagram in accompanying drawing
Show the device of multiple embodiments of the invention, the architectural framework in the cards of method and computer program product,
Function and operation.At this point, each square frame in flow chart or block diagram can represent the one of module, program segment or a code
Part a, part for the module, program segment or code is used to realize holding for the logic function of regulation comprising one or more
Row instruction.It should also be noted that at some as in the implementations replaced, the function of being marked in square frame can also be being not used in
The order marked in accompanying drawing occurs.For example, two continuous square frames can essentially be performed substantially in parallel, and they are sometimes
Can perform in the opposite order, this is depending on involved function.It is also noted that block diagram or each side in flow chart
The combination of frame and block diagram or the square frame in flow chart, can be with the function or action for performing regulation it is special based on hardware
System realizing, or can be realized with the combination of computer instruction with specialized hardware.
In addition, each functional module in each embodiment of the invention can integrate to form an independent portion
Divide, or modules individualism, it is also possible to which two or more modules are integrated to form an independent part.
If the function is realized and as independent production marketing or when using using in the form of software function module, can be with
In being stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be individual
People's computer, server, or network equipment etc.) perform all or part of step of each embodiment methods described of the invention.
And aforesaid storage medium includes：USB flash disk, portable hard drive, read only memory (ROM, Read-Only Memory), random access memory are deposited
Reservoir (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.Need
Illustrate, herein, such as first and second or the like relational terms be used merely to by an entity or operation with
Another entity or operation make a distinction, and not necessarily require or imply these entities or there is any this reality between operating
The relation or order on border.And, term " including ", "comprising" or its any other variant are intended to the bag of nonexcludability
Contain, so that a series of process, method, article or equipment including key elements is not only including those key elements, but also including
Other key elements being not expressly set out, or also include the key element intrinsic for this process, method, article or equipment.
In the absence of more restrictions, the key element for being limited by sentence "including a ...", it is not excluded that including the key element
Process, method, article or equipment in also there is other identical element.
The preferred embodiments of the present invention are the foregoing is only, the present invention is not limited to, for the skill of this area
For art personnel, the present invention can have various modifications and variations.It is all within the spirit and principles in the present invention, made any repair
Change, equivalent, improvement etc., should be included within the scope of the present invention.It should be noted that：Similar label and letter exists
Similar terms is represented in figure below, therefore, once being defined in a certain Xiang Yi accompanying drawing, then it is not required in subsequent accompanying drawing
It is further defined and is explained.
The above, the only specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, all should contain
Cover within protection scope of the present invention.Therefore, protection scope of the present invention described should be defined by scope of the claims.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or deposit between operating
In any this actual relation or order.And, term " including ", "comprising" or its any other variant are intended to
Nonexcludability is included, so that a series of process, method, article or equipment including key elements not only will including those
Element, but also including other key elements being not expressly set out, or also include for this process, method, article or equipment
Intrinsic key element.In the absence of more restrictions, the key element for being limited by sentence "including a ...", it is not excluded that
Also there is other identical element in process, method, article or equipment including the key element.
The preferred embodiments of the present invention are the foregoing is only, the present invention is not limited to, for the skill of this area
For art personnel, the present invention can have various modifications and variations.It is all within the spirit and principles in the present invention, made any repair
Change, equivalent, improvement etc., should be included within the scope of the present invention.It should be noted that：Similar label and letter exists
Similar terms is represented in figure below, therefore, once being defined in a certain Xiang Yi accompanying drawing, then it is not required in subsequent accompanying drawing
It is further defined and is explained.
Claims (10)
1. a kind of transformer breather fault monitoring method, it is characterised in that the transformer breather fault monitoring method bag
Include：
The orthographic view and transformer breather for obtaining colour atla is presently in the image of environment, the transformer breather field
Scape image includes the image of character to be detected, the orthographic view of the colour atla include multiple first color regions with extremely
Few four the first telltale marks；
According to image segmentation algorithm, by the second color region that the image segmentation of the body to be detected is different colours degree；
Color degree, each described first chromatic zones according to each first color region of the orthographic view of the colour atla
Domain and the described first specifically labelled position relationship and the image solution of each the second color region of the character to be detected
Analyse the color of image degree of each the second color region of the character to be detected；
Judge the color of image degree and the standard of pre-stored of each the second color region of the character described to be detected after parsing
Whether color degree is consistent；
If inconsistent, fault cues information is generated.
2. transformer breather fault monitoring method according to claim 1, it is characterised in that if described inconsistent,
The step of generating fault cues information includes：
Obtain the center of gravity of each the second color region and the position according to center of gravity each described determines each described second chromatic zones
Domain location；
According to second color region inconsistent with the Standard Colors degree of the pre-stored of the image of the character to be detected
Color degree and inconsistent with the Standard Colors degree of the pre-stored the second color region location analysis first therefore
Barrier result；Including：
Fisrt fault result is analyzed according to formula result=f (x, y), wherein, x represents described each second color region
Position of the center of gravity in the character image to be detected, y represents inconsistent with the Standard Colors degree of the pre-stored
The color degree in second colors region, result represents Fisrt fault result, and f (x, y) represents the first analysis equation formula；
The step of generation fault cues information and Fisrt fault result, includes:
According to formula result1=f (x1, y1), the first concrete fail result is generated, wherein, x1 is represented and the pre-stored
First position of the center of gravity of the second inconsistent color region of Standard Colors degree in the character image to be detected, y1 is represented
First color degree of second color region inconsistent with the Standard Colors degree of the pre-stored, result1 represents that first is concrete
Fail result, f (x1, y1) represents that first analyzes formula；
Or according to formula result2=f (x2, y1), the second concrete fail result is generated, wherein, x2 is represented and the pre-stored
Inconsistent the second color region of Standard Colors degree the second position of the center of gravity in the character image to be detected, y1 tables
Show the first color degree of second color region inconsistent with the Standard Colors degree of the pre-stored, result2 represents the second tool
Body fail result, f (x2, y1) represents that second analyzes formula；
Or according to formula result3=f (x1, y2), the 3rd concrete fail result is generated, wherein, x1 is represented and the pre-stored
Inconsistent the second color region of Standard Colors degree first position of the center of gravity in the character image to be detected, y2 tables
Show the second color degree of second color region inconsistent with the Standard Colors degree of the pre-stored, result3 represents the 3rd tool
Body fail result, f (x1, y2) represents that the 3rd analyzes formula；
Or according to formula result4=f (x2, y2), the 4th concrete fail result is generated, wherein, x2 is represented and the pre-stored
Inconsistent the second color region of Standard Colors degree the second position of the center of gravity in the character image to be detected, y2 tables
Show the second color degree of second color region inconsistent with the Standard Colors degree of the pre-stored, result4 represents the 4th tool
Body fail result, f (x2, y2) represents that the 4th analyzes formula；
Generate fault cues information and Fisrt fault result.
3. transformer breather fault monitoring method according to claim 1, it is characterised in that if described inconsistent,
The step of generating fault cues information includes：
The area in the different region of each color degree and the area of the image of the character to be detected are calculated, and calculates institute
State the different region of color degree area account for the character to be detected image area ratio；
The image of the character to be detected is accounted for according to the area in the region inconsistent with the Standard Colors degree of the pre-stored
The fail result of proportion grading second of area；Including：
Second fail result is analyzed according to formula result=f (y, z), wherein, y represents the Standard Colors degree with the pre-stored
The color degree of the second inconsistent color region, z represents second chromatic zones inconsistent with the Standard Colors degree of the pre-stored
The area in domain accounts for the ratio of the area of the character image to be detected, and result represents the second fail result, and f (y, z) is represented
Second analysis equation formula；
According to formula result5=f (y1, z1), the 5th concrete fail result is generated, wherein, y1 is represented and the pre-stored
First color degree of the second inconsistent color region of Standard Colors degree, z1 is represented and differed with the Standard Colors degree of the pre-stored
The area of the second color region for causing accounts for the first scope of the ratio of the area of the character image to be detected；Result5 tables
Show the 5th concrete fail result, f (y1, z1) represents that the 5th analyzes formula；
Or according to formula result6=f (y2, z1), the 6th concrete fail result is generated, wherein, y2 is represented and the pre-stored
Inconsistent the second color region of Standard Colors degree the second color degree, z1 represented with the Standard Colors degree of the pre-stored not
The area of the second consistent color region accounts for the first scope of the ratio of the area of the character image to be detected, result6
The 6th concrete fail result is represented, f (y2, z1) represents that the 6th analyzes formula；
Or according to formula result7=f (y1, z2), the 7th concrete fail result is generated, wherein, y1 is represented and the pre-stored
Inconsistent the second color region of Standard Colors degree the first color degree, z2 represented with the Standard Colors degree of the pre-stored not
The area of the second consistent color region accounts for the second scope of the ratio of the area of the character image to be detected, result7
The 7th concrete fail result is represented, f (y1, z2) represents that the 7th analyzes formula；
Or according to formula result8=f (y2, z2), the 8th concrete fail result is generated, wherein, y2 is represented and the pre-stored
Inconsistent the second color region of Standard Colors degree the second color degree, z2 represented with the Standard Colors degree of the pre-stored not
The area of the second consistent color region accounts for the second scope of the ratio of the area of the character image to be detected, result8
The 8th concrete fail result is represented, f (y2, z2) represents that the 8th analyzes formula；
Generate fault cues information and the second fail result.
4. transformer breather fault monitoring method according to claim 1, it is characterised in that described according to image segmentation
Algorithm, by the image segmentation of the body to be detected for different colours degree the second color region the step of include：
According to image segmentation algorithm, using the image of character to be detected as one group of multidimensional data point, and with space position parameter
Move on the image of the character to be detected with average drifting window of the color parameter as windows radius, will be through window
The institute that data peaks are converged to after conversion a little connects, and is partitioned into the different region of color degree.
5. transformer breather fault monitoring method according to claim 1, it is characterised in that the acquisition colour atla is just
The step of projected image and transformer breather are presently in the image of environment includes：
Doubtful colour atla area image and the character to be detected are gathered being presently in the image of environment, wherein, it is described doubtful
Colour atla area image includes color chart picture；
Determine color chart picture according to the doubtful colour atla area image and at least four first telltale mark；
The seat being located at according to described at least four first telltale marks of the orthographic view of the colour atla in default coordinate system
Mark calculates perspective transformation matrix with least four second specifically labelled coordinates of the color chart picture for collecting；
The orthographic view of the colour atla is mapped out according to the perspective transformation matrix and the coordinate of the color chart picture；
It is described after the step of orthographic view and transformer breather for obtaining colour atla is presently in the image of environment
Transformer breather fault monitoring method also includes：
According to the color degree and the orthograph of the colour atla of each the 3rd color region of default orthographic view model
The color degree of each the first color region of picture generates each the 3rd color region and first color that there are mapping relations
The color degree corresponding relation in region；
The color degree of each first color region of the orthographic view according to the colour atla, each described first face
Zone domain and the described first specifically labelled position relationship and the figure of each the second color region of the character to be detected
The step of spending as the color of image of each the second color region of the parsing character to be detected includes：
Color degree, each first color region according to each the first color region of the orthographic view of the colour atla with it is described
First specifically labelled position relationship, the image of the character to be detected and each the 3rd color region and second face
The color degree corresponding relation in zone domain parses the color of image degree of the character to be detected.
6. a kind of transformer breather fault monitoring device, it is characterised in that the transformer breather fault monitoring device bag
Include：
Image acquisition unit, the orthographic view and transformer breather for obtaining colour atla is presently in the image of environment,
The transformer breather scene image includes the image of character to be detected, and the orthographic view of the colour atla includes many
Individual first color region and at least four first telltale marks；
Image segmentation unit, for being different colours degree by the image segmentation of the body to be detected according to image segmentation algorithm
Second color region；
Color degree resolution unit, for according to the color of each first color region of the orthographic view of the colour atla
Each of degree, each described first color region and the described first specifically labelled position relationship and the character to be detected
The color of image degree of each the second color region of character to be detected described in the image analysis of the second color region；
Color degree judging unit, for judging the image face of each the second color region of the character described to be detected after parsing
Whether colourity is consistent with the Standard Colors degree of pre-stored；
Fault message signal generating unit, if the standard of the color of image degree and pre-stored for the character described to be detected after parsing
When color degree is inconsistent, fault cues information is generated.
7. transformer breather fault monitoring device according to claim 6, it is characterised in that the fault message is generated
Unit includes：
Position acquisition module, determines often for obtaining the center of gravity of each the second color region and the position according to center of gravity each described
The individual second color region location；
Fail result analysis module, for according to the Standard Colors degree with the pre-stored of the image of the character to be detected
The color degree of the second inconsistent color region and second color region inconsistent with the Standard Colors degree of the pre-stored
Location analyzes Fisrt fault result；
Fisrt fault result is analyzed according to formula result=f (x, y), wherein, x represents described each second color region
Position of the center of gravity in the character image to be detected, y represents inconsistent with the Standard Colors degree of the pre-stored
The color degree in second colors region, result represents Fisrt fault result, and f (x, y) represents the first analysis equation formula；
The fault message generation module is used for according to formula result1=f (x1, y1), generates the first concrete fail result, its
In, x1 represents the center of gravity of second color region inconsistent with the Standard Colors degree of the pre-stored in the character to be detected
First position in image, y1 represents the first color of second color region inconsistent with the Standard Colors degree of the pre-stored
Degree, result1 represents the first concrete fail result, and f (x1, y1) represents that first analyzes formula；
Or according to formula result2=f (x2, y1), the second concrete fail result is generated, wherein, x2 is represented and the pre-stored
Inconsistent the second color region of Standard Colors degree the second position of the center of gravity in the character image to be detected, y1 tables
Show the first color degree of second color region inconsistent with the Standard Colors degree of the pre-stored, result2 represents the second tool
Body fail result, f (x2, y1) represents that second analyzes formula；
Or according to formula result3=f (x1, y2), the 3rd concrete fail result is generated, wherein, x1 is represented and the pre-stored
Inconsistent the second color region of Standard Colors degree first position of the center of gravity in the character image to be detected, y2 tables
Show the second color degree of second color region inconsistent with the Standard Colors degree of the pre-stored, result3 represents the 3rd tool
Body fail result, f (x1, y2) represents that the 3rd analyzes formula；
Or according to formula result4=f (x2, y2), the 4th concrete fail result is generated, wherein, x2 is represented and the pre-stored
Inconsistent the second color region of Standard Colors degree the second position of the center of gravity in the character image to be detected, y1 tables
Show the second color degree of second color region inconsistent with the Standard Colors degree of the pre-stored, result4 represents the 4th tool
Body fail result, f (x2, y2) represents that the 4th analyzes formula；
Fault message generation module, for generating fault cues information and Fisrt fault object information.
8. transformer breather fault monitoring device according to claim 6, it is characterised in that the fault message is generated
Unit includes：
Area ratio computing module, for calculating the area and the character to be detected in the different region of each color degree
Image area, and calculate the area that the area in the different region of the color degree accounts for the image of the character to be detected
Ratio；
Fail result analysis module, accounts for described to be detected for the foundation area inconsistent with the Standard Colors degree of the pre-stored
The fail result of proportion grading second of the area of the image of character；
Second fail result is analyzed according to formula result=f (y, z), wherein, y represents the Standard Colors degree with the pre-stored
The color degree of the second inconsistent color region, z represents second chromatic zones inconsistent with the Standard Colors degree of the pre-stored
The area in domain accounts for the ratio of the area of the character image to be detected, and result represents the second fail result, and f (y, z) is represented
Second analysis equation formula；
The fault message generation module generates the 5th concrete fail result according to formula result5=f (y1, z1), wherein,
Y1 represents the first color degree of second color region inconsistent with the Standard Colors degree of the pre-stored, and z1 represents pre- with described
The area of the second inconsistent color region of the Standard Colors degree of storage accounts for the ratio of the area of the character image to be detected
The first scope；Result5 represents the 5th concrete fail result, and f (y1, z1) represents that the 5th analyzes formula；
Or according to formula result6=f (y2, z1), the 6th concrete fail result is generated, wherein, y2 is represented and the pre-stored
Inconsistent the second color region of Standard Colors degree the second color degree, z1 represented with the Standard Colors degree of the pre-stored not
The area of the second consistent color region accounts for the first scope of the ratio of the area of the character image to be detected, result6
The 6th concrete fail result is represented, f (y2, z1) represents that the 6th analyzes formula；
Or according to formula result7=f (y1, z2), the 7th concrete fail result is generated, wherein, y1 is represented and the pre-stored
Inconsistent the second color region of Standard Colors degree the first color degree, z2 represented with the Standard Colors degree of the pre-stored not
The area of the second consistent color region accounts for the second scope of the ratio of the area of the character image to be detected, result7
The 7th concrete fail result is represented, f (y1, z2) represents that the 7th analyzes formula；
Or according to formula result8=f (y2, z2), the 8th concrete fail result is generated, wherein, y2 is represented and the pre-stored
Inconsistent the second color region of Standard Colors degree the second color degree, z2 represented with the Standard Colors degree of the pre-stored not
The area of the second consistent color region accounts for the second scope of the ratio of the area of the character image to be detected, result8
The 8th concrete fail result is represented, f (y2, z2) represents that the 8th analyzes formula；
Fault message generation module, for generating fault cues information and the second fail result information.
9. transformer breather fault monitoring device according to claim 6, it is characterised in that described image splits module
For according to image segmentation algorithm, using the image of character to be detected as one group of multidimensional data point, and with space position parameter
Move on the image of the character to be detected with average drifting window of the color parameter as windows radius, will be through window
The institute that data peaks are converged to after conversion a little connects, and is partitioned into the different region of color degree.
10. transformer breather fault monitoring device according to claim 6, it is characterised in that described image obtains single
Unit includes：
Image capture module, for gathering doubtful colour atla area image and the character to be detected the figure of environment is being presently in
Picture, wherein, doubtful colour atla area image includes color chart picture；
Color chart as determining module, for according to the doubtful colour atla area image and at least four first telltale mark
Determine color chart picture；
Perspective transformation matrix computing module, for the described at least four first positioning marks according to the orthographic view of the colour atla
Coordinate of the note in default coordinate system is calculated with least four second of the color chart picture for collecting specifically labelled coordinates
Go out perspective transformation matrix；
Orthographic view mapping block, it is described for mapping out according to the perspective transformation matrix and the coordinate of the color chart picture
The orthographic view of colour atla；
The color degree resolution unit also includes：
Corresponding relation generation module, for according to the color degree of each the 3rd color region of default orthographic view model with
And the color degree of each the first color region of the orthographic view of the colour atla generates each the 3rd face that there are mapping relations
Zone domain and the color degree corresponding relation of first color region；
Color of image degree parsing module, for according to the color of each the first color region of the orthographic view of the colour atla
Degree, each first color region and the described first specifically labelled position relationship, the image of the character to be detected and every
The color degree corresponding relation of individual 3rd color region and second color region parses the image face of the character to be detected
Colourity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611189908.7A CN106680217B (en) | 2016-12-21 | 2016-12-21 | Transformer breather fault monitoring method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611189908.7A CN106680217B (en) | 2016-12-21 | 2016-12-21 | Transformer breather fault monitoring method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106680217A true CN106680217A (en) | 2017-05-17 |
| CN106680217B CN106680217B (en) | 2019-09-06 |
Family
ID=58870771
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611189908.7A Active CN106680217B (en) | 2016-12-21 | 2016-12-21 | Transformer breather fault monitoring method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106680217B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116804597A (en) * | 2023-08-22 | 2023-09-26 | 梁山华鲁专用汽车制造有限公司 | Trailer connection state detection device and detection method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090216464A1 (en) * | 2008-02-21 | 2009-08-27 | Korea Institute Of Science & Technology | Integrated in-line oil monitoring apparatus |
| CN104408459A (en) * | 2014-10-27 | 2015-03-11 | 国家电网公司 | Image identification method applied to power equipment monitoring |
| CN204964639U (en) * | 2015-07-30 | 2016-01-13 | 浙江金冠特种变压器有限公司 | Detection device for transformer |
| CN105868722A (en) * | 2016-04-05 | 2016-08-17 | 国家电网公司 | Identification method and system of abnormal power equipment images |
-
2016
- 2016-12-21 CN CN201611189908.7A patent/CN106680217B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090216464A1 (en) * | 2008-02-21 | 2009-08-27 | Korea Institute Of Science & Technology | Integrated in-line oil monitoring apparatus |
| CN104408459A (en) * | 2014-10-27 | 2015-03-11 | 国家电网公司 | Image identification method applied to power equipment monitoring |
| CN204964639U (en) * | 2015-07-30 | 2016-01-13 | 浙江金冠特种变压器有限公司 | Detection device for transformer |
| CN105868722A (en) * | 2016-04-05 | 2016-08-17 | 国家电网公司 | Identification method and system of abnormal power equipment images |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116804597A (en) * | 2023-08-22 | 2023-09-26 | 梁山华鲁专用汽车制造有限公司 | Trailer connection state detection device and detection method |
| CN116804597B (en) * | 2023-08-22 | 2023-12-15 | 梁山华鲁专用汽车制造有限公司 | Trailer connection state detection device and detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106680217B (en) | 2019-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106407981B (en) | A kind of licence plate recognition method, apparatus and system | |
| Yu et al. | An experimental study of real-time identification of construction workers' unsafe behaviors | |
| CN103035013B (en) | A kind of precise motion shadow detection method based on multi-feature fusion | |
| CN103632158B (en) | Forest fire prevention monitor method and forest fire prevention monitor system | |
| Lu et al. | A volumetric approach to population estimation using LiDAR remote sensing | |
| CN109598794B (en) | Construction method of three-dimensional GIS dynamic model | |
| CN108710913A (en) | A kind of switchgear presentation switch state automatic identification method based on deep learning | |
| Lee et al. | Leveraging pre-trained 3d object detection models for fast ground truth generation | |
| Huang et al. | Foreground/background segmentation of color images by integration of multiple cues | |
| CN104463138B (en) | The text positioning method and system of view-based access control model structure attribute | |
| CN103514430B (en) | The method and apparatus of detection flame | |
| CN108229524A (en) | A kind of chimney and condensing tower detection method based on remote sensing images | |
| CN109544516A (en) | Image detecting method and device | |
| CN111209864A (en) | Target identification method for power equipment | |
| CN110689000A (en) | Vehicle license plate identification method based on vehicle license plate sample in complex environment | |
| Ortega et al. | Generating 3D city models from open LiDAR point clouds: Advancing towards smart city applications | |
| Huang et al. | A knowledge-based approach to urban feature classification using aerial imagery with lidar data | |
| CN106680217A (en) | Method and device for monitoring failure of transformer respirator | |
| CN104881663B (en) | Distinguish the method and device of the selected results of check box | |
| CN107274361A (en) | Landsat TM remote sensing image datas remove cloud method and system | |
| CN114120141A (en) | All-weather remote sensing monitoring automatic analysis method and system thereof | |
| Menardi | Nonparametric clustering for image segmentation | |
| CN111598033A (en) | Cargo positioning method, device and system and computer readable storage medium | |
| CN115982824A (en) | Construction site worker space management method and device, electronic equipment and storage medium | |
| CN109636838A (en) | A kind of combustion gas Analysis of Potential method and device based on remote sensing image variation detection |
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 | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Two Lu Tian Hua high tech Zone of Chengdu City, Sichuan province 610017 No. 219 Tianfu Software Park C District 10 Building 16 layer Patentee after: Huayan Intelligent Technology (Group) Co.,Ltd. Address before: Two Lu Tian Hua high tech Zone of Chengdu City, Sichuan province 610017 No. 219 Tianfu Software Park C District 10 Building 16 layer Patentee before: SICHUAN WHAYER INFORMATION INDUSTRY Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Transformer respirator fault monitoring method and device Effective date of registration: 20220811 Granted publication date: 20190906 Pledgee: Chengdu SME financing Company Limited by Guarantee Pledgor: Huayan Intelligent Technology (Group) Co.,Ltd. Registration number: Y2022980012348 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20221117 Granted publication date: 20190906 Pledgee: Chengdu SME financing Company Limited by Guarantee Pledgor: Huayan Intelligent Technology (Group) Co.,Ltd. Registration number: Y2022980012348 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Fault Monitoring Method and Device for Transformer Breather Effective date of registration: 20230308 Granted publication date: 20190906 Pledgee: Chengdu SME financing Company Limited by Guarantee Pledgor: Huayan Intelligent Technology (Group) Co.,Ltd. Registration number: Y2023980034390 |