CN109544497A - Image interfusion method and electronic equipment for transmission line faultlocating - Google Patents
Image interfusion method and electronic equipment for transmission line faultlocating Download PDFInfo
- Publication number
- CN109544497A CN109544497A CN201811388764.7A CN201811388764A CN109544497A CN 109544497 A CN109544497 A CN 109544497A CN 201811388764 A CN201811388764 A CN 201811388764A CN 109544497 A CN109544497 A CN 109544497A
- Authority
- CN
- China
- Prior art keywords
- image
- transmission line
- visible images
- temperature field
- line faultlocating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
Abstract
A kind of image interfusion method and electronic equipment for transmission line faultlocating, wherein method includes: the visible images and UV image for obtaining transmission line faultlocating scene；Visible images and UV image are handled respectively to generate corresponding enhancing visible images and enhancing UV image；Fusion treatment is carried out to generate blending image to enhancing visible images and enhancing UV image.Image interfusion method and electronic equipment provided in an embodiment of the present invention for transmission line faultlocating, the visible images and UV image of transmission line of electricity under same visual field are acquired simultaneously, and the two is merged, to show the electric discharge corona of faulty equipment on visible images, and then be able to use family while detecting power failure and easily identify specific faulty equipment information, realize the electric inspection process of automation.
Description
Technical field
The present invention relates to electric inspection process technical fields, and in particular to a kind of image interfusion method for transmission line faultlocating
And electronic equipment.
Background technique
With the development of national economy and the continuous improvement of living standards of the people, electric grid investment scale constantly expands, network
Structure becomes increasingly complex.The reliability service of power network line and grid equipment directly influences production safety and the society of electric power enterprise
Meeting benefit, affects the stability of power grid.Power department is to guarantee that electric power facility operates normally, and will monthly formulate inspection meter
It draws, dispatching personnel is to including that the power supply facilities such as shaft tower, conducting wire, transformer, capacitor are maked an inspection tour, so that timely discovering device lacks
It falls into and security risk, and operating condition equipment and defect information summarize and regularly analysis statistics.Power grid is maked an inspection tour
Increasing with the workload of maintenance, traditional transmission line of electricity and substation's manual patrol mode of operation can not meet efficiently
Power grid inspection job requirement.For this purpose, State Grid Corporation of China widelys popularize unmanned plane line data-logging, robot substation inspection
Using work, by applied robot, unmanned plane etc., intelligently equipment carries out real-time data acquisition and status monitoring to electric power facility,
Discovery defect in time, improves the efficiency of electric power maintenance and maintenance conscientiously, effectively increases electric network state control ability and lean
Change management level, ensures electricity net safety stable.
Currently, state's net transport inspection department large-scale promotion intelligent patrol detection service application.Nearly 2 years, Guo Wang company applied small-sized rotation
Wing unmanned plane is total to 4825 base shaft tower of inspection, 832 base shaft tower of inspection is total to using medium-sized unmanned helicopter, using large-scale unmanned helicopter
Altogether 562 base shaft tower of inspection, be total to 4221.9 kilometers of inspection using fixed-wing unmanned plane, tentatively foundation complete helicopter, nobody
Machine and artificial collaboration inspection new model.With large-scale use of the smart machines such as unmanned plane, robot in power grid inspection, state
The production of intelligent degree of net company is improved, while also proposing to equipment routing inspection acquisition data intelligent processing higher
Requirement.At this stage, unmanned plane, helicopter routing inspection return data are of low quality, data volume is big, sort out query processing low efficiency,
Based on video image, common problem is return data: picture largely repeats, low-quality image can not reject for shooting,
Data volume is big, data content is complicated, calculates by the processing of artificial or normal image and acquisition data are screened, analyzed and located
It manages very time-consuming.
Summary of the invention
The application provides a kind of image interfusion method and electronic equipment for transmission line faultlocating, to realize to power transmission line
The automatic detection of field device electric discharge is detected on road, improves the working efficiency of polling transmission line.
According in a first aspect, being wrapped the embodiment of the invention provides a kind of image interfusion method for transmission line faultlocating
It includes: obtaining the visible images and UV image at transmission line faultlocating scene；The visible images and the ultraviolet line chart
As sharing same visual field through same image-forming objective lens；The visible images and the UV image are handled with life respectively
At corresponding enhancing visible images and enhancing UV image；To the enhancing visible images and the ultraviolet line chart of enhancing
As carrying out fusion treatment to generate blending image.
With reference to first aspect, in first aspect first embodiment, the UV image is to filter by ultraviolet narrowband
The UV image of mating plate processing.
With reference to first aspect or first aspect first embodiment, in first aspect second embodiment, to it is described can
The method that light-exposed image and the UV image are handled includes method either in enhancing, denoising and sharpening.
With reference to first aspect or first aspect first or second embodiment, in first aspect third embodiment, institute
The image interfusion method for transmission line faultlocating stated, further include: obtain the infrared figure at the transmission line faultlocating scene
Picture；The visual field of the infrared image is parallel with the visual field of the visible images and the UV image.
Third embodiment with reference to first aspect, in the 4th embodiment of first aspect, described is used for transmission line of electricity
The image interfusion method of detection, further includes: the infrared image is pre-processed, pretreated infrared image is generated；It is right
The pretreated infrared image carries out temperature field dividing processing, extracts corresponding temperature field data；According to the temperature field
Data extract corresponding Characteristics of Temperature Field.
4th embodiment with reference to first aspect, in the 5th embodiment of first aspect, the Characteristics of Temperature Field includes
Defect center point；The defect center point is determined according to the following formula:
Wherein,Indicate the gray value of pixel in the temperature field data；aveIndicate pixel in the temperature field data
Average gray；stdIndicate the standard deviation of pixel grey scale in the temperature field data；kFor proportional control factor.
4th or the 5th embodiment with reference to first aspect, it is described to described pre- in first aspect sixth embodiment
Treated, and infrared image carries out temperature field dividing processing, extracts corresponding temperature field data, comprising: to described pretreated
Infrared image carries out gray proces, generates corresponding gray level image；To the gray level image carry out closing operation of mathematical morphology be connected to
Domain calculates, and generates corresponding temperature field data；The temperature field data include thermoisopleth and connected domain in the gray level image.
Any embodiment with reference to first aspect or in first aspect, it is described in the 7th embodiment of first aspect
The Infrared Image Processing Method for transmission line faultlocating, further include: according to the visible images identify faulty equipment.
According to second aspect, the embodiment of the invention provides a kind of servers, comprising: memory, for storing program；Place
Device is managed, for the program by executing the memory storage to realize such as first aspect or first aspect any embodiment institute
The method stated.
According to the third aspect, the embodiment of the invention provides a kind of computer readable storage medium, including program, the journey
Sequence can be executed by processor to realize the method as described in first aspect or first aspect any embodiment.
Image interfusion method and electronic equipment provided in an embodiment of the present invention for transmission line faultlocating, while acquiring same
The visible images and UV image of transmission line of electricity under one visual field, and the two is merged, to be shown on visible images
The electric discharge corona for the equipment that is out of order, and then be able to use family while detecting power failure and easily identify specific failure
Facility information realizes the electric inspection process of automation.In addition, the image provided in an embodiment of the present invention for transmission line faultlocating melts
Conjunction method and electronic equipment carry out pretreatment by the infrared image to transmission line of electricity and Characteristics of Temperature Field are extracted, realize pair
The automatic detection and identification of infrared image, are conducive to provide the working efficiency of electric inspection process.In addition, due to equipment infared spectrum master
The regularity of distribution for embodying temperature, it is provided in an embodiment of the present invention for transmitting electricity for the unobvious of equipment characteristic details presentation
The image interfusion method and electronic equipment of wireline inspection, while being automatically processed to infrared image, also to it is corresponding can
Light-exposed image is identified, to identify faulty equipment information therein, establishes bi-directional device type marking model, by can
Light-exposed identification information and infared spectrum identification information carry out Link Ratio pair, to record the feature of typical fault.
Detailed description of the invention
It is specific for one of image interfusion method of transmission line faultlocating that Fig. 1 shows one of embodiment of the present invention
Exemplary flow chart；
Fig. 2 shows the light channel structure schematic diagrames in the embodiment of the present invention；
Fig. 3 shows double spectral measurement structure design frame charts in the embodiment of the present invention；
Fig. 4 shows a specific example of one of the embodiment of the present invention for the image fusion device of transmission line faultlocating
Structural schematic diagram；
Fig. 5 shows the structural schematic diagram of a specific example of one of embodiment of the present invention server.
Specific embodiment
Below by specific embodiment combination attached drawing, invention is further described in detail.Wherein different embodiments
Middle similar component uses associated similar element numbers.In the following embodiments, many datail descriptions be in order to
The application is better understood.However, those skilled in the art can recognize without lifting an eyebrow, part of feature
It is dispensed, or can be substituted by other elements, material, method in varied situations.In some cases, this Shen
Please it is relevant it is some operation there is no in the description show or describe, this is the core in order to avoid the application by mistake
More descriptions are flooded, and to those skilled in the art, these relevant operations, which are described in detail, not to be necessary, they
Relevant operation can be completely understood according to the general technology knowledge of description and this field in specification.
It is formed respectively in addition, feature described in this description, operation or feature can combine in any suitable way
Kind embodiment.Meanwhile each step in method description or movement can also can be aobvious and easy according to those skilled in the art institute
The mode carry out sequence exchange or adjustment seen.Therefore, the various sequences in the description and the appended drawings are intended merely to clearly describe a certain
A embodiment is not meant to be necessary sequence, and wherein some sequentially must comply with unless otherwise indicated.
The embodiment of the invention provides a kind of image interfusion methods for transmission line faultlocating, as shown in Figure 1, the figure
As fusion method may comprise steps of:
Step S11: the visible images and UV image at transmission line faultlocating scene are obtained.Specifically, visible images and
UV image shares same visual field through same image-forming objective lens.For the ultraviolet light image of high-tension apparatus, imaging is only equipment electricity
Corona image, no device context image, can not position the position of corona discharge.Therefore it must accurately be indicated by a kind of mode
Electric discharge position.Visible images instruction is undoubtedly best selection.In actual electric power automatic tour inspection system, system design packet
Ultraviolet and visible two sets of optical paths are included, same visual field are shared by image-forming objective lens (such as reflection microscope group), by adjusting reflection microscope group
And visible light lens focusing is observed under same visual field, same optical path to ensure that ultraviolet imagery detection is detected with visual light imaging
Object.Since the visible images and UV image at transmission line faultlocating scene are to adopt under same visual field, same optical path
Collection, the coordinate of the two is identical, this is just that subsequent image co-registration provides convenience.In addition, to detect the electric discharge of high-tension apparatus
Corona, the ultraviolet wavelength range for needing to make to finally enter ultraviolet detector must be single at present between the nm of 240 nm~280
The ultraviolet lens of one material production are unable to satisfy this condition, it is therefore necessary to design ultraviolet filter, pass through ultraviolet narrow-band-filter
Piece eliminates the interference of background, designs " full-time blind " ultraviolet narrow band filter, first passes around high-tension apparatus UV image ultraviolet
Narrow band filter processing, wiping out background interference, can be used instrument in the sun.
To UV light path, as it is desirable that the ultraviolet image of its energy display device itself, it is therefore desirable to which production is suitable ultraviolet
For camera lens to reduce the noise of non-ultraviolet light and bias light, camera lens requires light passing in 0.2 μm~0.4 μm (model of general ultraviolet wavelength
Enclose) spectral region.It is whole according to system, in conjunction with the needs of actual measurement, camera lens is in addition to requiring certain visual field, to point on axis
Except correct aberrations, it is necessary to correct off-axis point aberration.Interfere the main aberration of its field expander first is that the curvature of field.Therefore, exist
When designing camera lens, first have to the correction for considering the curvature of field, i.e., it is thick using the thin lens structure or falcate of positive and negative focal power separation
Lens.This ultraviolet lens is designed for this purpose, can choose with the structure type of double Gauss objective.Its initial structure parameter is general
The identical or close structural parameters of domestic and international technical conditions can be first consulted, actually detected required value is zoomed to.With primary as
The poor theoretical initial configuration for determining it, considers further that higher order aberrations, solves initial structure parameter method.Double Gauss objective is a kind of symmetrical
Type structure, it is only necessary to consider that spherical aberration, astigmatism, the curvature of field, chromatism of position these fourth types longitudinal aberration of correction half portion system, holohedral symmetry are closed
Cheng Hou, the axial aberration that hangs down are cancelled automatically.In half portion system, with thick lens correction as face bending coefficient, with adding no focal power double
Thin lens spherical aberration corrector coefficient, with choosing aperture diaphragm position correction astigmatism coefficient, then in thick lens plus achromatism division is saturating
The method of mirror corrects position chromatic aberration coefficient.The structure design of ultraviolet lens includes two lens groups, an adjustable diaphragm and one
Day blind optical filter.Design adjustable diaphragm is to prevent to control the luminous flux for entering ultraviolet detector in measurement intense radiation target
When cause signal supersaturated.
Step S12: visible images and UV image are handled respectively to generate corresponding enhancing visible light figure
Picture and enhancing UV image.In a specific real-time mode, light channel structure design uses double light design, as shown in Fig. 2, i.e.
Ultraviolet light image is detected all the way, and enhancing amplification is carried out to ultraviolet light image；Another way detects background image, i.e. visible light figure
Picture, it is seen that light image is direct detection.Two-way image is separately handled, including enhancing, denoising, sharpening etc., can be reduced in this way
Energy difference between two kinds of light be detected two kinds of images can.
Step S13: fusion treatment is carried out to generate blending image to enhancing visible images and enhancing UV image.It is logical
The superposition of two-way image is crossed, visible images can be not only seen on piece image but also sees ultraviolet light image, that is, meets detection
With the requirement of positioning., can be by UV light path image upper in a specific real-time mode, it is seen that optical path image under, thus
Realize the superposition of two-way image.In this light channel structure, it is seen that optical path can be by lens imaging and two secondary mirrors twice
Reflection, so that making it just is not in mirror image and the inverted image to turn upside down reversed left to right, UV light path can also be by two
Secondary lens imaging is also not in inverted image.As shown in figure 3, for a specific double spectral measurement structure design frame charts.This design
It is provided convenience while simplifying structure, improving signal coupling efficiency, and for last image co-registration, reduces image
The workload of processing is also laid a good foundation for the miniaturization of equipment.Ultraviolet image is by the ultraviolet worry light microscopic in day blind narrowband, into purple
Ultraviolet image (corona image) is presented in outer camera lens on ultraviolet CCD；Visible images inject visible light microscopic by two secondary mirrors
Head is imaged on Visible-light CCD；The visual field of two-way image is identical, can be directly can by two-way image sampling fusion treatment
Electric discharge corona is accurately positioned on light-exposed image.
Optionally, following steps can also be added, after step s 11 to realize the infrared inspection to transmission line of electricity simultaneously
It surveys:
Step S14: the infrared image at transmission line faultlocating scene is obtained.In order to allow users on the transmission line of electricity observed simultaneously
Ultraviolet image, visible images and the infrared image of same position, the visual field of infrared image should be with visible images and ultraviolet
The visual field of line image is parallel.
Step S15: pre-processing infrared image, generates pretreated infrared image.Infrared chart spectrum have with
Under feature:
A. due to scenery thermal balance, optical wavelength, long transmission distance, atmospheric attenuation etc., infrared image space correlation is caused
Property is strong, contrast is low, visual effect is fuzzy；
B. the Temperature Distribution of thermal-induced imagery characterization scenery, is gray level image, without colored or shade, therefore to the human eye, point
Resolution is low, it is poor to differentiate potentiality；
C. the detectivity and spatial resolution of thermal imaging system are lower than Visible-light CCD array, so that infrared image is clear
Degree is lower than visible images；
D. the random disturbances of external environment and thermal imaging system is not perfect, brings diversified noise to infrared image, than
Such as thermal noise, shot noise, photon-electron fluctuation noise.The noise of these complex distributions makes the signal-to-noise ratio of infrared image
It is lower than normal television picture；
E. since the response characteristic of each probe unit of infrared detector is inconsistent, due to optical mechaical scanning system defect etc., causes red
The heterogeneity of outer image is presented as fixed pattern noise, crosstalk, distortion of image etc..
It is found that infrared image is generally darker from analysis above, target image is low with background contrasts, and edge compares mould
It pastes, noise is big etc..According to these features of infared spectrum, it is necessary first to mean filter and median filtering algorithm be taken to reach smooth
The infared spectrum for removing noise pre-processes purpose.
Mean filter is typical linear filtering algorithm, it refers on the image to object pixel to a template, the mould
Plate includes surrounding adjacent pixels point and itself pixel.Original is replaced with the average value of the entire pixels in template again
Carry out pixel value.Mean filter is also referred to as linear filtering, and the main method used is neighborhood averaging.The original substantially of linear filtering
Reason is each pixel value replaced in original image with mean value, i.e., to current pixel point (x, y) to be processed, selects a template,
The template is made of its neighbouring several pixel, the mean value for the middle all pixels that seek template, then assigns current pixel point the mean value
(x, y), as the gray value g(x, y of image after processing at that point), i.e. g(x, y)=1/m ∑ f(x, y), m is in the template
Include the total number of pixels including current pixel.Mean filter can effectively filter out the additive noise in image, but mean filter
Itself have the defects that intrinsic, i.e., it cannot protect image detail well, also destroy image while image denoising
Detail section, so that image be made to thicken.Mean filter mainly has arithmetic equal value filtering, and geometric mean filters, and harmonic wave is equal
Value filtering and inverse harmonic wave mean filter, the quasi- verifying arithmetic equal value filtering of this project, geometric mean filtering and inverse harmonic wave mean value are filtered
The noise reduction effect of wave.
Median filtering is a kind of common Nonlinear Smoothing Filter, the basic principle is that digital picture or Serial No.
In the value of some point a neighborhood in the intermediate value of each point value replace, major function is to allow surrounding pixel gray value differences
Not bigger pixel changes to take the value close with the pixel value of surrounding, so as to eliminate isolated noise spot, so intermediate value is filtered
Wave is highly effective for the salt-pepper noise for filtering out image.Conventional median filters can play the noise of long streaking probability distribution good
Good smooth effect.Moreover, it also has the advantages that protect boundary information while eliminating noise, to certain in image
A little details play a protective role, thus have obtained comparing in image denoising processing and be widely applied.But Conventional median filters
The performance of impulsive noise is gone to be affected by filter window size, and it is inhibiting two aspect of picture noise and protection details
There are certain contradictions: the filter window taken is smaller, so that it may preferably certain details in protection image, but filter out the ability of noise
It will receive limitation；Conversely, the filter window taken is bigger can to reinforce noise inhibiting ability, but the protective capability of details can be subtracted
It is weak.This contradiction shows particularly evident when noise jamming is larger in the picture.Rule of thumb: being greater than in impulsive noise intensity
The effect of routine median filtering just seems unsatisfactory when 0.2.Therefore, only schemed using the method for Conventional median filtering
As denoising application in be it is far from being enough, this needs to seek new innovatory algorithm just to solve this contradiction.Adaptive intermediate value filter
The filtering mode of wave device all uses the window Sxy of a rectangular area as conventional median filter, the difference is that filtering
During wave, sef-adapting filter can change according to certain setting condition and (increase) size of spectral window, while when judgement
When the pixel for filtering window center is noise, which is replaced with intermediate value, does not otherwise change its current pixel value.In this way with filter
Output carrys out at replacement pixels (x, y) value of (i.e. the coordinate of filtering window center at present).Median filtering algorithm by optimization can be with
The bigger impulsive noise of noise probability is handled, while image detail can be preferably kept.
Step S16: temperature field dividing processing is carried out to pretreated infrared image, extracts corresponding temperature field data.
Infrared Image Features refer to the parameters such as the gradient in temperature field in infrared image, isothermal shape, temperature grade, they and electric power
The type and abort situation of equipment thermal fault have very close relationship, and research finds out temperature field by the method for image procossing
Form parameter and extract identified areas.The purpose of Infrared Image Features information extraction is in order to carry out images match, in turn
The similitude of thermal image to be diagnosed Yu pervious failure form is found out by images match, and the purpose of image temperature field segmentation is
In order to establish power equipment thermal fault infrared image sample database.Infared spectrum all has the rich colors by regular gradual change,
And the region of gradient color is exactly to divide isothermal primary identity, in order to carry out isothermal identification and then complete dividing for temperature field
It cuts, needs to carry out gray processing processing first to infrared image, show the morphological feature in temperature field is more specific.Then into
The morphologic closed operation of row, highlights thermoisopleth as needed.Connected domain calculating is finally carried out, similar temperature field is split
Mark.The algorithm principle used in the process can be summarized as follows:
A. image gray processing is handled
It is all to use RGB color mode since photo is all color image, it, be respectively to tri- kinds points of RGB when handling image
Amount is handled, and actually RGB can not reflect the morphological feature of image, and the tune of color is only carried out from optical principle
Match.
Now with a lot of other color modes, such as HSI mode, HSI is by tone, saturation degree, three components of brightness
To indicate color.HSI ratio RGB more meets human vision property.
The color of each pixel in color image has tri- components of R, G, B to determine, and each component has 255 intermediate values can
It takes, such a pixel can have the variation range of the color of more than 1,600 ten thousand (255*255*255).And gray level image be R, G,
The special color image of the identical one kind of tri- components of B, the variation range of one of pixel is 255 kinds, so in number
The image of various formats is generally first transformed into gray level image so that the calculation amount of subsequent image becomes few one by image procossing kind
A bit.The description of gray level image still reflects the entirety of entire image and the coloration and brightness degree of part as color image
Distribution and feature.
Method is in the color space according to YUV, and the physical significance of the component of Y is the brightness of point, reflects brightness by the value
It is corresponding with tri- color components of R, G, B can to establish brightness Y according to the variation relation of RGB and YUV color space for grade: Y=
0.3R+0.59G+0.11B, with the gray value of this brightness value expression image.
B. closing operation of mathematical morphology
Closing operation of mathematical morphology be used to eliminate wisp, at very thin point while the boundary of separating objects, smooth larger object simultaneously
Unobvious its area of change.Morphological erosion operation is a kind of elimination boundary point, the process for shrinking boundary internally.It can use
Small and meaningless object is eliminated, specifically, the structural element of 3x3, each pixel of scan image can be used；Use structure
The bianry image that element is covered with it does with operation；If being all 1, the pixel of result images is 1.It otherwise is 0；It can be by two
It is worth image and reduces a circle.Expansion is that all background dots contacted with object are merged into the object, expands boundary to outside
Process.It can be used to fill up the cavity in object, specifically, the structural element of 3x3, each picture of scan image can be used
Element；With operation is done with the bianry image that structural element is covered with it；If being all 0, the pixel of result images is 0.Otherwise
It is 1；Bianry image can be expanded to a circle.Image first carried out to expansion algorithm carry out erosion algorithm i.e. completion morphology again to close fortune
It calculates.
C. connected domain calculates
So-called connected domain refers to the set being made of several pixels, and the pixel in the set has characteristics that 1. all pixels
Grey level be respectively less than or equal to connected domain rank；2. the pixel in the same connected domain communicates two-by-two, i.e., any two
The access being made of completely this element gathered between a pixel there are one.Connected component labeling, which refers to, to meet certain in image
The pixel logo of kind connection rule is same target, designs the mark that suitable data structure saves target belonging to each pixel
Number, and save the attribute of relevant target.
By then carrying out closing operation of mathematical morphology, then carry out connected domain calculating to the processing of infrared image gray processing, so that it may
The temperature field data for obtaining different temperatures, joins including the gradient in temperature field, isothermal shape, temperature grade etc. in infrared image
Number.
Step S17: corresponding Characteristics of Temperature Field is extracted according to temperature field data.Generic failure infared spectrum have one very
Small region is the highest region of temperature, forms the temperature for having temperature grade from this region start temperature to ambient radiation
, and maximum temperature be a point perhaps a pocket by this point be known as maximum temperature point or defect center point.It is infrared
Thermal imaging system is the height that temperature is indicated with color, and the more black local temperature of color is lower, and the whiter local temperature of color is higher.
Thermal image colored after original image gray processing is become into gray level image, it, generally can be with defect center come really in Infrared Fault Diagnosis
Determine Gu Zhang Wei Catching-rabbits, and the characteristics of according to infrared image, defect center often corresponds to image pixel contrast highest or minimum
Point, after infrared image gray processing, defect center is exactly the maximum region of gray value or point, therefore searches for formula and can indicate are as follows:
Wherein,Indicate the gray value of pixel in the temperature field data；Ave indicates pixel in the temperature field data
Average gray；Std indicates the standard deviation of pixel grey scale in the temperature field data；K is proportional control factor, such as its
Value can be 1.From infared spectrum as can be seen that the gray scale in most of region is the same, in order to quickly position in defect
The heart should first acquire the average gray value of image in practical applications, then be the largest condition according to the gray value of defect center
Pixel to be greater than average gray value to gray value scans for comparing, and then rapidly finds out defect center.Pass through algorithm
Processing, can easily find out the coordinate of the highest region point of temperature very much, then fix again in original image subscript and make to extract special
Sign processing, to obtain the mark of infared spectrum defect center point.
Due to the regularity of distribution of equipment infared spectrum major embodiment temperature, equipment characteristic details are presented unobvious.
Therefore, the identification of power equipment infared spectrum need to carry out identification mark to equipment by visible light, establish bi-directional device kind category
Injection molding type.For this purpose, following steps can be added after step S17, to identify faulty equipment:
Step S18: faulty equipment is identified according to visible images.It, can be first for there is the image of text label in image-region
First visible images are pre-processed, including the enhancing of image denoising, edge, edge detection etc., digital picture passes through at image
Adjustment method positions and cuts out area-of-interest, on the basis of area-of-interest, is required according to specific tasks, continues segmentation and extracts
Dependency structure.Secondly, carrying out feature extraction to image, the alphanumeric image of discretization is subjected to characteristic vector pickup, it is crucial
It is to extract the high feature vector of intercharacter difference degree.Again, pattern-recognition is carried out to feature vector, inputs the feature extracted
Vector is identified and is described by pattern matching algorithm, and character is correctly distinguished, and completes image processing tasks.Finally, according to identification
As a result image is labeled, so that it is determined that faulty equipment.
For the image without text label in image-region, first with the bottom of image processing techniques extract equipment image
Visual signature, including color, texture, shape and spatial information etc., the metadata as image.To a width power equipment image mark
When note, mark problem is considered as image classification problem, is broadly divided into two stages:
I) marking model training stage (with image training classifier of largely having classified): submission represents the specific vision requirement of project
Image, using oneself mark image set, building be successively iterated from image bottom visual signature to high-level semantics feature, by
The abstract depth network mapping model of layer；
The ii) image labeling stage: the similarity with all images in training library is calculated, image most like therewith is returned, root
It is categorized into classification predetermined according to the visual information of test image, each keyword is considered as an independent class name
Claim, and a corresponding classifier, to more accurately mark the power equipment image of unknown sample.
By the faulty equipment information identified according to visible images and the defect center phase that is identified according to infrared image
Association, can conveniently and efficiently find faulty equipment and its fault point, provide conveniently for equipment repairing.
The embodiment of the invention also provides a kind of image fusion devices for transmission line faultlocating, as shown in figure 4, should
Image fusion device may include: image acquisition unit 41, image processing unit 42 and image fusion unit 43.
Wherein, image acquisition unit 41, for obtaining the visible images and UV image at transmission line faultlocating scene,
Visible images and UV image share same visual field through same image-forming objective lens；Its detailed operation can be found in the above method
In embodiment described in step S11.
Image processing unit 42, for being handled visible images and UV image respectively to generate corresponding increasing
Strong visible images and enhancing UV image；Its detailed operation can be found in above method embodiment described in step S12.
Image fusion unit 43, for carrying out fusion treatment to enhancing visible images and enhancing UV image to generate
Blending image, detailed operation can be found in above method embodiment described in step S13.
The embodiment of the invention also provides a kind of servers, as shown in figure 5, the server may include 501 He of processor
Memory 502, wherein processor 501 can be connected with memory 502 by bus or other modes, by total in Fig. 5
For line connection.
Processor 501 can be central processing unit (Central Processing Unit, CPU).Processor 501 may be used also
Think other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
The combination of the chips such as discrete hardware components or above-mentioned all kinds of chips.
Memory 502 is used as a kind of non-transient computer readable storage medium, can be used for storing non-transient software program, non-
Transient computer executable program and module, such as the image interfusion method for transmission line faultlocating in the embodiment of the present invention
Corresponding program instruction/module is (for example, image acquisition unit shown in Fig. 4 41, image processing unit 42 and image fusion unit
43).Non-transient software program, instruction and the module that processor 501 is stored in memory 502 by operation, thereby executing
The various function application and data processing of processor, i.e. the control side based on fortune inspection business in realization above method embodiment
Method.
Memory 502 may include storing program area and storage data area, wherein storing program area can store operation system
Application program required for system, at least one function；It storage data area can the data etc. that are created of storage processor 501.In addition,
Memory 502 may include high-speed random access memory, can also include non-transient memory, and a for example, at least disk is deposited
Memory device, flush memory device or other non-transient solid-state memories.In some embodiments, it includes opposite that memory 502 is optional
In the remotely located memory of processor 501, these remote memories can pass through network connection to processor 501.Above-mentioned net
The example of network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
One or more of modules are stored in the memory 502, when being executed by the processor 501, are held
The image interfusion method for transmission line faultlocating in row embodiment as shown in Figure 1.
Above-mentioned server detail can correspond to refering to fig. 1 shown in embodiment corresponding associated description and effect into
Row understands that details are not described herein again.
It is that can lead to it will be understood by those skilled in the art that realizing all or part of the process in above-described embodiment method
Computer program is crossed to instruct relevant hardware and complete, the program can be stored in a computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can for magnetic disk,
CD, read-only memory (Read-Only Memory, ROM), random access memory (Random Access
Memory, RAM), flash memory (Flash Memory), hard disk (Hard Disk Drive, abbreviation: HDD) or solid state hard disk
(Solid-State Drive, SSD) etc.；The storage medium can also include the combination of the memory of mentioned kind.
Use above specific case is illustrated the present invention, is merely used to help understand the present invention, not to limit
The system present invention.For those skilled in the art, according to the thought of the present invention, can also make several simple
It deduces, deform or replaces.
Claims (10)
1. a kind of image interfusion method for transmission line faultlocating characterized by comprising
Obtain the visible images and UV image at transmission line faultlocating scene；The visible images and the ultraviolet line chart
As sharing same visual field through same image-forming objective lens；
The visible images and the UV image are handled respectively with generate corresponding enhancing visible images and
Enhance UV image；
Fusion treatment is carried out to generate blending image to the enhancing visible images and the enhancing UV image.
2. the image interfusion method according to claim 1 for transmission line faultlocating, which is characterized in that described ultraviolet
Line image is the UV image by the processing of ultraviolet narrow band filter.
3. the image interfusion method according to claim 1 or 2 for transmission line faultlocating, which is characterized in that described
The method that visible images and the UV image are handled includes method either in enhancing, denoising and sharpening.
4. the image interfusion method according to any one of claim 1 to 3 for transmission line faultlocating, feature exist
In, further includes: obtain the infrared image at the transmission line faultlocating scene；The visual field of the infrared image and the visible light figure
Picture is parallel with the visual field of the UV image.
5. the image interfusion method according to claim 4 for transmission line faultlocating, which is characterized in that further include:
The infrared image is pre-processed, pretreated infrared image is generated；
Temperature field dividing processing is carried out to the pretreated infrared image, extracts corresponding temperature field data；
Corresponding Characteristics of Temperature Field is extracted according to the temperature field data.
6. the Infrared Image Processing Method according to claim 5 for transmission line faultlocating, which is characterized in that described
Characteristics of Temperature Field includes defect center point；
The defect center point is determined according to the following formula:
Wherein,Indicate the gray value of pixel in the temperature field data；aveIndicate pixel in the temperature field data
Average gray；stdIndicate the standard deviation of pixel grey scale in the temperature field data；kFor proportional control factor.
7. the Infrared Image Processing Method according to claim 5 or 6 for transmission line faultlocating, which is characterized in that institute
It states and temperature field dividing processing is carried out to the pretreated infrared image, extract corresponding temperature field data, comprising:
Gray proces are carried out to the pretreated infrared image, generate corresponding gray level image；
Closing operation of mathematical morphology is carried out to the gray level image and connected domain calculates, generates corresponding temperature field data；The temperature
Field data includes thermoisopleth and connected domain in the gray level image.
8. the Infrared Image Processing Method according to any one of claim 1 to 7 for transmission line faultlocating, special
Sign is, further includes: identifies faulty equipment according to the visible images.
9. a kind of electronic equipment characterized by comprising
Memory, for storing program；
Processor, for the program by executing the memory storage to realize as of any of claims 1-8
Method.
10. a kind of computer readable storage medium, which is characterized in that including program, described program can be executed by processor with
Realize such as method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811388764.7A CN109544497A (en) | 2018-11-21 | 2018-11-21 | Image interfusion method and electronic equipment for transmission line faultlocating |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811388764.7A CN109544497A (en) | 2018-11-21 | 2018-11-21 | Image interfusion method and electronic equipment for transmission line faultlocating |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109544497A true CN109544497A (en) | 2019-03-29 |
Family
ID=65848879
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811388764.7A Pending CN109544497A (en) | 2018-11-21 | 2018-11-21 | Image interfusion method and electronic equipment for transmission line faultlocating |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109544497A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110412547A (en) * | 2019-07-24 | 2019-11-05 | 中国电子科技集团公司第三十六研究所 | The echo signal identifying system of equipment and ground installation is carried based on rotor wing unmanned aerial vehicle |
| CN110634115A (en) * | 2019-08-30 | 2019-12-31 | 国网河南省电力公司平顶山供电公司 | Power distribution equipment monitoring method and system based on double-light fusion |
| CN111127445A (en) * | 2019-12-26 | 2020-05-08 | 智洋创新科技股份有限公司 | Distribution network line high-temperature area detection method and system based on deep learning |
| CN111289860A (en) * | 2020-03-23 | 2020-06-16 | 云南电网有限责任公司电力科学研究院 | Method for detecting partial discharge position of electrical equipment |
| CN111553194A (en) * | 2020-04-01 | 2020-08-18 | 国网宁夏电力有限公司电力科学研究院 | Method and system for detecting foreign matters in GIS equipment based on double light sources |
| CN112381784A (en) * | 2020-11-12 | 2021-02-19 | 国网浙江省电力有限公司信息通信分公司 | Equipment detecting system based on multispectral image |
| CN112809705A (en) * | 2021-02-22 | 2021-05-18 | 国网陕西省电力公司榆林供电公司 | Tower-staying type intelligent multispectral vision inspection robot |
| CN113609901A (en) * | 2021-06-25 | 2021-11-05 | 国网山东省电力公司泗水县供电公司 | Power transmission and transformation equipment fault monitoring method and system |
| CN113744197A (en) * | 2021-08-09 | 2021-12-03 | 福建工程学院 | Cable fault detection method based on red and ultraviolet composite imaging |
| CN114663672A (en) * | 2022-03-11 | 2022-06-24 | 四川大学 | Method and system for detecting corrosion of steel member of power transmission line tower |
| CN115018784A (en) * | 2022-05-31 | 2022-09-06 | 广东电网有限责任公司 | Method, device, equipment and medium for detecting defect of strand scattering of lead |
| CN115855961A (en) * | 2023-02-16 | 2023-03-28 | 广东靖邦电器有限公司 | Distribution box fault detection method used in operation |
| CN116342433A (en) * | 2023-05-25 | 2023-06-27 | 山东省青东智能科技有限公司 | Image intelligent denoising method for 3D industrial camera |
| CN116977184A (en) * | 2023-08-01 | 2023-10-31 | 南方电网数字电网研究院有限公司 | Transmission line image acquisition method, device, computer equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101551435A (en) * | 2009-05-15 | 2009-10-07 | 湖北省电力试验研究院 | Method for detecting corona discharging and device thereof |
| CN103634565A (en) * | 2013-09-24 | 2014-03-12 | 北京环境特性研究所 | OMAP-based ultraviolet and visible light dual-channel image acquisition, processing and display system |
| US20150356341A1 (en) * | 2013-01-07 | 2015-12-10 | Bae Systems Plc | Fusion of multi-spectral and range image data |
| CN105301542A (en) * | 2015-11-13 | 2016-02-03 | 广东电网有限责任公司电力科学研究院 | Full-solar-blind ultraviolet imaging quantified detection method based on photon counting technology |
| CN105738779A (en) * | 2016-01-26 | 2016-07-06 | 国网上海市电力公司 | Partial discharge detection method based on multi-source image fusion |
| CN106932692A (en) * | 2017-03-07 | 2017-07-07 | 北京瑞盈智拓科技发展有限公司 | Detection means and detection method based on infrared and ultraviolet visual image fusion |
| CN107505546A (en) * | 2017-08-25 | 2017-12-22 | 国家电网公司 | A kind of method that corona discharge is monitored using ultraviolet imager |
| CN108389137A (en) * | 2018-02-06 | 2018-08-10 | 国网山西省电力公司电力科学研究院 | Power fault detection early warning system based on infared spectrum technology |
-
2018
- 2018-11-21 CN CN201811388764.7A patent/CN109544497A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101551435A (en) * | 2009-05-15 | 2009-10-07 | 湖北省电力试验研究院 | Method for detecting corona discharging and device thereof |
| US20150356341A1 (en) * | 2013-01-07 | 2015-12-10 | Bae Systems Plc | Fusion of multi-spectral and range image data |
| CN103634565A (en) * | 2013-09-24 | 2014-03-12 | 北京环境特性研究所 | OMAP-based ultraviolet and visible light dual-channel image acquisition, processing and display system |
| CN105301542A (en) * | 2015-11-13 | 2016-02-03 | 广东电网有限责任公司电力科学研究院 | Full-solar-blind ultraviolet imaging quantified detection method based on photon counting technology |
| CN105738779A (en) * | 2016-01-26 | 2016-07-06 | 国网上海市电力公司 | Partial discharge detection method based on multi-source image fusion |
| CN106932692A (en) * | 2017-03-07 | 2017-07-07 | 北京瑞盈智拓科技发展有限公司 | Detection means and detection method based on infrared and ultraviolet visual image fusion |
| CN107505546A (en) * | 2017-08-25 | 2017-12-22 | 国家电网公司 | A kind of method that corona discharge is monitored using ultraviolet imager |
| CN108389137A (en) * | 2018-02-06 | 2018-08-10 | 国网山西省电力公司电力科学研究院 | Power fault detection early warning system based on infared spectrum technology |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110412547B (en) * | 2019-07-24 | 2021-02-26 | 中国电子科技集团公司第三十六研究所 | Target signal identification system based on rotor unmanned aerial vehicle carries equipment and ground equipment |
| CN110412547A (en) * | 2019-07-24 | 2019-11-05 | 中国电子科技集团公司第三十六研究所 | The echo signal identifying system of equipment and ground installation is carried based on rotor wing unmanned aerial vehicle |
| CN110634115A (en) * | 2019-08-30 | 2019-12-31 | 国网河南省电力公司平顶山供电公司 | Power distribution equipment monitoring method and system based on double-light fusion |
| CN110634115B (en) * | 2019-08-30 | 2022-04-01 | 国网河南省电力公司平顶山供电公司 | Power distribution equipment monitoring method and system based on double-light fusion |
| CN111127445A (en) * | 2019-12-26 | 2020-05-08 | 智洋创新科技股份有限公司 | Distribution network line high-temperature area detection method and system based on deep learning |
| CN111289860A (en) * | 2020-03-23 | 2020-06-16 | 云南电网有限责任公司电力科学研究院 | Method for detecting partial discharge position of electrical equipment |
| CN111553194B (en) * | 2020-04-01 | 2023-04-18 | 国网宁夏电力有限公司电力科学研究院 | Method and system for detecting foreign matters in GIS equipment based on double light sources |
| CN111553194A (en) * | 2020-04-01 | 2020-08-18 | 国网宁夏电力有限公司电力科学研究院 | Method and system for detecting foreign matters in GIS equipment based on double light sources |
| CN112381784A (en) * | 2020-11-12 | 2021-02-19 | 国网浙江省电力有限公司信息通信分公司 | Equipment detecting system based on multispectral image |
| CN112809705A (en) * | 2021-02-22 | 2021-05-18 | 国网陕西省电力公司榆林供电公司 | Tower-staying type intelligent multispectral vision inspection robot |
| CN113609901A (en) * | 2021-06-25 | 2021-11-05 | 国网山东省电力公司泗水县供电公司 | Power transmission and transformation equipment fault monitoring method and system |
| CN113744197B (en) * | 2021-08-09 | 2024-01-02 | 福建工程学院 | Cable fault detection method based on infrared and ultraviolet composite imaging |
| CN113744197A (en) * | 2021-08-09 | 2021-12-03 | 福建工程学院 | Cable fault detection method based on red and ultraviolet composite imaging |
| CN114663672A (en) * | 2022-03-11 | 2022-06-24 | 四川大学 | Method and system for detecting corrosion of steel member of power transmission line tower |
| CN114663672B (en) * | 2022-03-11 | 2023-04-07 | 四川大学 | Method and system for detecting corrosion of steel member of power transmission line tower |
| CN115018784A (en) * | 2022-05-31 | 2022-09-06 | 广东电网有限责任公司 | Method, device, equipment and medium for detecting defect of strand scattering of lead |
| CN115018784B (en) * | 2022-05-31 | 2024-03-12 | 广东电网有限责任公司 | Method, device, equipment and medium for detecting wire strand scattering defect |
| CN115855961A (en) * | 2023-02-16 | 2023-03-28 | 广东靖邦电器有限公司 | Distribution box fault detection method used in operation |
| CN116342433A (en) * | 2023-05-25 | 2023-06-27 | 山东省青东智能科技有限公司 | Image intelligent denoising method for 3D industrial camera |
| CN116977184A (en) * | 2023-08-01 | 2023-10-31 | 南方电网数字电网研究院有限公司 | Transmission line image acquisition method, device, computer equipment and storage medium |
| CN116977184B (en) * | 2023-08-01 | 2024-03-19 | 南方电网数字电网研究院股份有限公司 | Transmission line image acquisition method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109544497A (en) | Image interfusion method and electronic equipment for transmission line faultlocating | |
| CN109448009A (en) | Infrared Image Processing Method and device for transmission line faultlocating | |
| CN108389137A (en) | Power fault detection early warning system based on infared spectrum technology | |
| CN107133943B (en) | A kind of visible detection method of stockbridge damper defects detection | |
| Fu et al. | Hyperspectral image super-resolution with optimized RGB guidance | |
| Rachmadi et al. | Vehicle color recognition using convolutional neural network | |
| CN103034838B (en) | A kind of special vehicle instrument type identification based on characteristics of image and scaling method | |
| Izadi et al. | A new intelligent method for minerals segmentation in thin sections based on a novel incremental color clustering | |
| CN106384117B (en) | A kind of vehicle color identification method and device | |
| CN109961003A (en) | A kind of airborne auxiliary inspection device of embedded transmission line of electricity based on FPGA | |
| CN103164695A (en) | Fruit identification method based on multi-source image information fusion | |
| CN109711466A (en) | A kind of CNN hyperspectral image classification method retaining filtering based on edge | |
| Liu et al. | Soft prototyping camera designs for car detection based on a convolutional neural network | |
| CN115830585A (en) | Port container number identification method based on image enhancement | |
| Gupta et al. | Fast single image haze removal method for inhomogeneous environment using variable scattering coefficient | |
| CN108416357A (en) | A kind of extracting method of colored drawing class historical relic implicit information | |
| CN111898427A (en) | Multispectral pedestrian detection method based on feature fusion deep neural network | |
| Zhe et al. | Authentication of splicing manipulation by exposing inconsistency in color shift | |
| CN107403192A (en) | A kind of fast target detection method and system based on multi-categorizer | |
| Guo et al. | Fault diagnosis of power equipment based on infrared image analysis | |
| Yang et al. | Improved single-illumination estimation accuracy via redefining the illuminant-invariant descriptor and the grey pixels | |
| CN112633142A (en) | Power transmission line violation building identification method and related device | |
| CN114092441A (en) | Product surface defect detection method and system based on dual neural network | |
| Baumer et al. | Automatic Image Compositing and Snow Segmentation for Alpine Snow Cover Monitoring | |
| Gao et al. | Color image retrieval and analysis using image color measures |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190329 |
|
| RJ01 | Rejection of invention patent application after publication |