CN106447665A - Auxiliary positioning system and method of evaporator plate pipe locator based on visual identity - Google Patents
Auxiliary positioning system and method of evaporator plate pipe locator based on visual identity Download PDFInfo
- Publication number
- CN106447665A CN106447665A CN201610892566.9A CN201610892566A CN106447665A CN 106447665 A CN106447665 A CN 106447665A CN 201610892566 A CN201610892566 A CN 201610892566A CN 106447665 A CN106447665 A CN 106447665A
- Authority
- CN
- China
- Prior art keywords
- image
- pore
- coordinate
- localizer
- positioning system
- 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
- 238000000034 method Methods 0.000 title claims description 37
- 230000000007 visual effect Effects 0.000 title abstract description 4
- 238000004458 analytical method Methods 0.000 claims abstract description 39
- 230000008054 signal transmission Effects 0.000 claims abstract description 17
- 239000011148 porous material Substances 0.000 claims description 57
- 239000006200 vaporizer Substances 0.000 claims description 32
- 238000004891 communication Methods 0.000 claims description 27
- 238000001514 detection method Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 10
- 239000013307 optical fiber Substances 0.000 claims description 9
- 230000009467 reduction Effects 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 6
- 230000004807 localization Effects 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000001704 evaporation Methods 0.000 claims 1
- 239000000835 fiber Substances 0.000 claims 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract description 2
- 238000010223 real-time analysis Methods 0.000 abstract 1
- 238000007689 inspection Methods 0.000 description 15
- 238000012546 transfer Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 239000002826 coolant Substances 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000001629 suppression Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000004615 ingredient Substances 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 229910021529 ammonia Inorganic materials 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000018044 dehydration Effects 0.000 description 1
- 238000006297 dehydration reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000001627 detrimental effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003706 image smoothing Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- 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
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Monitoring And Testing Of Nuclear Reactors (AREA)
Abstract
The invention relates to an auxiliary positioning system of an evaporator plate pipe locator based on visual identity. The system comprises a network camera, a signal transmission system and an acquisition analysis computer; the network camera is arranged in a water chamber of an evaporator and shoots images of a plate pipe of the evaporator and the evaporator plate pipe locator on the plate pipe of the evaporator in real time; the signal transmission system is arranged between the network camera and the acquisition analysis computer, and sends the images shot by the network camera to the acquisition analysis computer; the acquisition analysis computer is arranged in an acquisition container out of a nuclear island, conducts real-time analysis on the images shot by the network camera so as to obtain coordinates of each pipe hole in the plate pipe, and displays the images superimposed and labeled with the coordinates of each pipe hole through a camera of the acquisition analysis computer. The auxiliary positioning system of the evaporator plate pipe locator based on the visual identity can automatically display the position coordinates on the plate pipe of the evaporator plate pipe locator in real time, can improve checking efficiency, and reduces possibilities of errors of people.
Description
Technical field
The present invention relates to a kind of alignment system of view-based access control model identification and method, in the steam generator heat transfer to nuclear power station
When pipe carries out eddy current inspection, position of the auxiliary positioning evaporator pipe sheet localizer on the tube sheet of vaporizer.
Background technology
Heat in primary Ioops coolant is passed to by the heat-exchange apparatus that functions primarily as of nuclear power station steam generator
Secondary circuit feeds water so as to which the power set for producing saturated vapor supply secondary circuit produce electric energy.As connection primary Ioops and two times
The equipment on road, steam generator is constituted between one, secondary circuit places the second protective barrier that leaks of radioactivity, concrete and
Speech, the tube sheet of steam generator and inverted U-tube are the ingredients of reactor coolant pressure boundary, with extremely important
Effect.
In CPR heap-type, steam generator heat-transfer pipe accounts for nearly the 80% of the primary Ioops pressure boundary gross area, in order to improve heat transfer
Efficiency, its tube wall is very thin, bears current scour and with the collision/friction of gripper shoe etc., with run time in running
Increase, it is easy to/the defect such as mechanical damage and corrosion such as thinning of wearing and tearing.The quality decline of heat-transfer pipe of evaporator is easily drawn
Send out the big safety problem of amount, one is potential in-service broken manage-style danger, and this accident can cause reactor dehydration, when serious, it is also possible to
Cause radioactivity release in environment;Two is reactor coolant leakage to secondary circuit.
For these reasons, during unit cold-refueling, it will usually carry out inservice inspection to heat-transfer pipe.Frequently with one
Probe moves along whole heat transfer inside pipe wall and carries out eddy current inspection, and the change of the signal that is beamed back according to coil can differentiate heat-transfer pipe
The type and degree of upper planar defect, so as to verify the current state of heat-transfer pipe.
As vaporizer hydroecium is the ingredient of primary Ioops, the Shutdown phase asks, although coolant has been discharged totally, but
Still there is very high radioactivity, Environmental dose rate is quite big.In view of in vaporizer hydroecium be high radioactivity environment, field conduct
During heat-transfer pipe of evaporator eddy current inspection, it is typically with evaporator pipe sheet localizer and moves on evaporator pipe sheet, will pop one's head in
Position to relevant position in the heat-transfer pipe of evaporator for need detection.Thereby it is ensured that correct, quick identification evaporator pipe sheet localizer
Position on tube sheet just becomes particularly significant.
The localization method for adopting at present is to place a photographic head in the hydroecium of vaporizer, by adjusting photographic head timing
Image taking is carried out, the pore quantity that then artificial contrast's evaporator pipe sheet localizer is differed with characteristic point on tube sheet is determining pipe
The physical location of plate localizer.This is a kind of method of subsequent supervision, it is impossible to carry out real-time positioning, and positioning is time-consuming longer every time,
For ensureing the efficiency of site inspection, typically often a location confirmation is carried out after a while.Although so can be to a certain degree
Accelerate inspection progress, but still occurring causes to confirm that the data for being gathered between position are all made twice due to location confirmation mistake
Useless situation.
Content of the invention
It is an object of the invention to provide one kind real-time, quickly and accurately can be positioned to evaporator pipe sheet localizer
Automated system and the localization method that adopted of the system.
For reaching above-mentioned purpose, the technical solution used in the present invention is:
A kind of aided positioning system of the evaporator pipe sheet localizer of view-based access control model identification, for real-time positioning evaporator tube
Position of the plate localizer on the tube sheet of vaporizer, which includes IP Camera, signal transmission system and collection analysises computer;
The IP Camera be arranged in the hydroecium of the vaporizer and the tube sheet of vaporizer described in captured in real-time and its
On the evaporator pipe sheet localizer image;
The signal transmission system is arranged between the IP Camera and the collection analysises computer and by the net
Image transmitting captured by network photographic head gives the collection analysises computer;
The collection analysises computer is arranged in the collection container outside nuclear island, and the collection analysises computer is to the network
Image captured by photographic head is analyzed in real time and is drawn the coordinate of each pore on the tube sheet, and superposition is labelled with respectively
The image of the coordinate of the pore is shown by its display.
Preferably, the signal transmission system include to be arranged in the room of the vaporizer place and with the network shooting
The first remote communication module that head is connected is connected with first remote communication module and by vaporizer place room
Cause the optical fiber in the outer collection container of nuclear island, be arranged at for being connected in the collection container and with the optical fiber
Two remote communication module, the collection analysises computer is connected with second remote communication module.
Preferably, first remote communication module, second remote communication module all include the network switch and light
Fine network commutator.
Preferably, the IP Camera is connected with first remote communication module by cable, the collection point
Analysis computer is connected with second remote communication module by netting twine
Preferably, the IP Camera is wide-angle camera.
The auxiliary positioning side that a kind of aided positioning system of the evaporator pipe sheet localizer of above-mentioned view-based access control model identification is adopted
Method, be:The evaporator pipe sheet localizer by the tube sheet of vaporizer described in the IP Camera captured in real-time and thereon
Image, and the collection analysises computer is sent to by the signal transmission system, the collection analysises computer is first to described
After image carries out pretreatment, then carry out center of circle detection and each pore and its center of circle in described image is identified, last foundation
The coordinate of predetermined benchmark pore group is determined the coordinate of each pore and each pore is labeled, and will
The image of the coordinate that superposition is labelled with each pore is shown by its display.
Preferably, the collection analysises computer carries out center of circle detection using Hough transformation.
Preferably, coloured image gray processing, image enhaucament, image noise reduction and edge inspection is included to the pretreatment of described image
Survey.
Preferably, the coloured image gray processing is carried out using weighted mean method;Described image is carried out using greyscale transformation
Strengthen;Described image noise reduction is carried out using median filter method;The rim detection is carried out using Canny operator
Preferably, the coordinate method for determining each pore is:Each benchmark in benchmark pore group described in advance manually determined
Pore coordinate in a coordinate system and putting down with the coordinate axess of the coordinate system of being determined by the center of circle of two benchmark pores
The datum line of row, and determine the unit length of coordinate system, then the distance of the center of circle according to each pore and the datum line
And the coordinate of the unit length, the benchmark pore determines the coordinate of the pore.
As technique scheme is used, the present invention has following advantages compared with prior art:The auxiliary of the present invention is fixed
Position system associated methods can in real time, automatically show position coordinateses of the evaporator pipe sheet localizer on tube sheet, so as to
Enough guarantee the ageing and accuracy of eddy current inspection institute gathered data, the efficiency of site inspection can be greatly improved and significantly reduced
The probability of human-equation error, is a kind of good aid system and the method for being evaporated the inspection of device heat-transfer pipe vortex.
Description of the drawings
Accompanying drawing 1 is the schematic diagram of the aided positioning system of the evaporator pipe sheet localizer of the view-based access control model identification of the present invention.
Accompanying drawing 2 is the flow chart of the assisted location method of the present invention.
Accompanying drawing 3 is the flow chart of Image semantic classification in the assisted location method of the present invention.
In the figures above:1st, IP Camera;2nd, signal transmission system 3, collection analysises computer;4th, cable;5th, first is remote
Journey communication module;6th, optical fiber;7th, the second remote communication module;8th, netting twine;9th, the hydroecium of vaporizer.
Specific embodiment
Lower song combines embodiment shown in the drawings, and the invention will be further described.
Embodiment one:In nuclear power station, vaporizer is arranged in the particular room in nuclear island, and operator are generally in core
To the monitoring state in nuclear island outside island.When the heat-transfer pipe to vaporizer carries out eddy current inspection, by following auxiliary positioning
The evaporator pipe sheet localizer that system is come in real-time positioning vaporizer hydroecium 9 with reference to assisted location method is on the tube sheet of vaporizer
Position.As shown in Figure 1, a kind of aided positioning system of the evaporator pipe sheet localizer of view-based access control model identification, including network
Photographic head 1, signal transmission system 2 and collection analysises computer 3.
IP Camera 1 is used for the image of the tube sheet of captured in real-time vaporizer and evaporator pipe sheet localizer thereon, it
It is arranged in the hydroecium 9 of vaporizer.In order to ensure that IP Camera 1 can cover tubesheet region as big as possible, preferably select wide
Angle photographic head.There are per platform vaporizer hot junction, two hydroeciums 9 of cold end, each hydroecium 9 respectively has one to use for sending out standby maintenance etc.
Manhole.During the work such as heat-transfer pipe of evaporator eddy current inspection in real time of scene, by the manhole, the ammonia devices such as repair apparatus are evaporated
On device tube sheet.Repair apparatus are installed after terminating, then by the manhole, IP Camera 1 are placed in vaporizer hydroecium 9, and will
1 connection cables 4 of IP Camera and draw vaporizer hydroecium 9.
Signal transmission system 2 is arranged between IP Camera 1 and collection analysises computer 3, and it can be by IP Camera 1
Captured image transmitting is to collection analysises computer 3.The signal transmission system 2 includes the first remote communication module 5,6 and of optical fiber
Second remote communication module 7.First remote communication module 5 be arranged on vaporizer place room in, it by cable 4 with net
Network photographic head 1 is connected, and the first remote communication module 5 includes the network switch and 6 network commutator of optical fiber.Optical fiber 6 is connected to
Between first remote communication module 5 and the second remote communication module 7, which is caused the collection collection outside nuclear island by vaporizer place room
In vanning.Second remote communication module 7 is arranged in the collection container outside nuclear island, and it includes the network switch and 6 net of optical fiber
Network transducer.
Collection analysises computer 3 is also disposed in the collection container outside nuclear island, and including main frame and display, it passes through netting twine
8 and be connected with the second remote communication module 7.Collection analysises computer 3 is used for carrying out reality to the image captured by IP Camera 1
When analysis and draw the coordinate of each pore on tube sheet, and the image of coordinate that superposition is labelled with each pore is shown by its display
Illustrate and.
Above-mentioned hardware system is mainly used in the picture signal transmission captured by the IP Camera 1 in vaporizer hydroecium 9
Collection analysises computer 3 to pickup area, after collection analysises computer 3 is processed to which by certain visual identification algorithm, will
The video signal for being superimposed pore coordinate is exported to display, is evaporated device tube sheet localizer with assist operators
Positioning, the simple control which can also be for operator's offer to IP Camera 1, such as operator pass through collection analysises computer
3 send instruction through signal transmission system 2 to IP Camera 1, realize the functions such as rotation, the focusing of IP Camera 1.
The assisted location method that the aided positioning system of the evaporator pipe sheet localizer of above-mentioned view-based access control model identification is adopted is such as
Shown in accompanying drawing 2, it is:The figure of evaporator pipe sheet localizer by the tube sheet of 1 captured in real-time vaporizer of IP Camera and thereon
Picture, and collection analysises computer 3 is sent to by signal transmission system 2 (sequentially pass through cable 4, the first remote communication module 5, light
Fine 6, second remote communication module 7, netting twine 8), collection analysises computer 3 is first carried out after pretreatment to image, then carries out center of circle detection
And each pore and the tool center of circle in image is identified, the last coordinate according to predetermined benchmark pore group determines each pore
Coordinate and each pore is labeled, and the image of coordinate that superposition is labelled with each pore is shown by its display.
For collection analysises computer 3, its specific handling process is as follows:
First, Image semantic classification
In actual applications, the quality of original image easily receives ectocine, and such as, the difference of intensity of illumination can make same
There is significant difference in the different images of target;Simultaneously, it is considered to when carrying out inservice inspection inspection project, 9 internal memory of vaporizer hydroecium
Irradiation can bring random noise to image, above a variety of factors are greatly lowered can the quality of image, be image recognition band
Carry out detrimental effect.Therefore, for the ease of follow-up image recognition, necessary pretreatment is carried out to original image so that figure
As edge contour sharpening, work efficiency and degree of accuracy that follow-up figure is identification is improved.
Pretreatment to image mainly includes coloured image gray processing, image enhaucament, image noise reduction and rim detection successively,
As shown in Figure 3.
1st, coloured image gray processing
In image procossing, conventional is RGB color space model.In the model, R (Red), G (Green), B (Blue)
256 grades are each separated into, from 0 to 255, other colors are mixed by different proportion by these three colors.And in ash
In degree image, gray scale is divided into 256 grades, from 0 to 255.Gray value more tends to 0, and corresponding pixel is more black, gray value
More tend to 255, corresponding pixel is whiter.By contrast, the quantity of information included by RGB image of comparable size is much larger than ash
Degree image.When recognizing the pore on evaporator pipe sheet, the appearance profile information of the only target image of major concern, color is believed
Breath is wholly redundant.Therefore, color image into gray level image and can both reduce amount of calculation, recognition speed is improved, and
Final recognition effect is not interfered with.
The gray processing of coloured image is completed using weighted mean method here, and specific algorithm is as follows:
Tri- color component C of RGB to coloured imager、Cg、CbIt is assigned to different weight wr、wg、wb, and cause wr+wg+
wb=1, the then corresponding gray value C of each pixelgray=wr·Cr+wg·Cg+wb·Cb, during Practical Calculation, it may be necessary to carry out
Floor operation.
2nd, image enhaucament
During generation, transmission in image etc., external disturbance is constantly present, and various noises can reduce image matter
Amount so that target characteristic is difficult to recognize, increased the difficulty of image recognition, it is possible to reduce the accuracy of image recognition.For this purpose,
Need to carry out the image after gray processing some process so that target to be detected is preferably separated with background.The present invention is using ash
Degree conversion strengthens to image.
In view of the image being identified in the present invention, there is definitely concordance, i.e.,:It is all 9 internal tube plate of vaporizer hydroecium
Image, therefore using piecewise linearity change carry out greyscale transformation.The algorithm can be to target area and background area using different
Change scaling method, under the clearly guidance of conversion purpose, preferable transform effect can be reached.
Specifically, piecewise linearity change divides the image into multiple continuous gray scale intervals, adopts in different gray scale intervals
Enter line translation with different linear functions, be to reduce operand, be divided into three intervals using by the image of gray processing here, each
An individual interval corresponding linear transformation function, can be by the gray scale span of acquirement image in advance, in images to be recognized region
Target area is further projected using larger function slope.
Specific function expression is as follows:
Each parameter in the function expression can be obtained by training, i.e.,:Take out the photograph of some 9 internal tube plates of vaporizer hydroecium
Then piece adjusts each parameter to obtain optimal target and background difference for the training set as parameter training collection.
3rd, image noise reduction
During Digital Image Processing, noise signal can experience each stage of image procossing, and noise signal has
Certain additivity.See, noise signal may be considered random error that there is no predictability in theory, typically adopt probability
The method of statistics is understood.Image noise reduction is called image smoothing again, is used for the low frequency trunk composition of prominent image, and suppression is high
Frequency noise jamming, reduces mutation gradient, so as to improve picture quality.The present invention intends carrying out image drop using median filter method
Make an uproar.
The principle of medium filtering is:Determine the box filter template of a N × N, the movement for making template orderly in the picture,
In template area, grey scale pixel value is ranked up, using pixel median as output.It can thus be seen that medium filtering is defeated
Going out is determined by the intermediate value in template area, thus insensitive to limit pixel value, can remove isolated noise point.The algorithm
Not only details can be retained but also effective noise reduction can be accomplished.
4th, rim detection
Target can be separated by rim detection with background, be the final step of Image semantic classification, while being also later image
The basis of identification.Edge is usually that edge pixel point is the catastrophe point of gray scale, the present invention by the discontinuous generation of pixel grey scale
Intend carrying out rim detection using Canny operator.
Algorithm substantially flow process is:
(1) two array P and Q for calculating partial derivative are divided using first difference:
P [i, j] ≈ (S [i, j+1]-S [i, j]+S [i+1, j+1]-S [i+1, j])/2
Q [i, j] ≈ (S [i, j]-S [i+1, j]+S [i, j+1]-S [i+1, j+1])/2
(2) amplitude and azimuth are calculated:
θ [i, j]=arctan (Q [i, j]/P [i, j])
(3) non-maxima suppression (NMS):
Ridge band in refinement magnitude image, i.e., only retain the point of amplitude localized variation maximum.Change model by gradient angle
Enclose and one of four sectors of circumference are reduced to, deflection and amplitude are respectively:
Non-maxima suppression is by suppressing the amplitude of all non-ridge peak values on gradient line come the gradient width in thin M [i, j]
Value ridge.The excursion of gradient angle θ [i, j] is reduced to one of four sectors of circumference by this algorithm first;
(4) threshold value is taken:
The all values that will be less than threshold value assign zero, obtain the edge array of image;
Threshold tau obtains too low → false edge;
Threshold tau obtains too high → partial contour and loses;
From two threshold values:More effective threshold scheme.
2nd, center of circle detection
Make { (xi, yi) | i=1,2 ..., n } be Circle in Digital Images after rim detection point set, if circle radius be r, circle
Heart coordinate is (a, b), then the parametric equation that justifies is (x-a)2+(y-b)2=r2.Intend in the present invention using Hough transform detection circle
The heart.Point on same circumference is mapped to the taper seat cluster for obtaining in parameter space and intersects at a point, and the point is contained in image
The information of circle, including the center of circle and radius.Parameter space is quantified, obtains the three-dimensional array (a, b, r) that adds up.In the picture,
Calculating with edge pixel apart from all of (d, b) of r, accumulating operation is done in accumulator array on this basis, in cubical array
Peak point contain the information of the center of circle and radius.
Comprising the following steps that for Hough transform is detected in the center of circle:
(1) span of a, b, r is determined according to the size of priori and image, sets up parameter space;
(2) array A (a, b, r) that adds up being set up in parameter space, and is initialized with 0;
(3) Hough transform is carried out to pixel, and cumulative array carries out accumulated counts, i.e. A (a, b, r)=A (a, b, r)+1;
(4) local maximum of cumulative array is found out, and this value is corresponding to the center of circle and the radius of certain circle.
The center of circle of tube sheet figure on each pore can just be identified accordingly.
3rd, pore coordinate is superimposed
In conjunction with the distribution of pore on tube sheet, the center of circle that identifies becomes matrix form to be distributed.Evaporator pipe sheet uploads heat pipe pore
Unique number is determined by line number R (x, y), row number C (x, y).For determining the pore coordinate for identifying, acquisition operations personnel are needed
When project starts, each benchmark pore coordinate in a coordinate system and by two benchmark in advance manually determined benchmark pore group
The datum line parallel with the coordinate axess of coordinate system that the center of circle of pore determines, and determine the unit length of coordinate system;Foundation again
The coordinate of the center of circle of each pore and the distance of datum line and unit length, benchmark pore determines the coordinate of pore.
Benchmark pore group is made up of the benchmark pore of three L-shaped distributions, according to determined by these three benchmark pores
Coordinate, it may be determined that line number, the increase direction of row number, so as to complete the mark of whole image inner tube number.
The annotation process of pore coordinate is as follows:
The intersecting point of dotted line shown in the figure is the pore center of circle for determining according to aforementioned image recognition, first manually determined A, B of needs,
The coordinate of tri- benchmark pores of C, it is assumed that respectively A (Ra, Ca)、B(Rb, Cb)、C(Rc, Cc), here with Rb=Ra, Cb=Ca+1, Rc
=Ra+ 1, Cc=CaAs a example by discuss D point line number, the calculating of row number.
Pixel point coordinates of 3 points of A, B, C, the D on image is made for A:(xa, ya)、B:(xb, yb)、C:(xc, yc)、D:(xd,
yd), then:
AB point-to-point transmission pixel distance isIt is adjacent that this may be considered column direction two
Unit length in spacing between pore, i.e. column direction;
Between 2 points of AC, pixel distance isThis may be considered two phases of line direction
Unit length in spacing between adjacent pore, i.e. line direction;
The linear equations of 2 points of AB determination are:
Can be reduced to:
It is designated as y+kx+b=0,
Then point D to straight line lABDistance
The hole count that then D point is differed in the row direction with A point
In the same manner, hole count R that D point is differed in a column direction with A point can be calculatedDA;
Then, the row, column number of D is
By above-mentioned flow process, the mark that IP Camera 1 sends back all pores in image can be completed, so as to the image that is added to
On obtain being superimposed the image of management and control coordinate, shown by the display of collection analysises computer 3, so that operator join
Examine, to grasp position of the evaporator pipe sheet localizer on tube sheet in real time.
The system associated methods of the present invention, can pore distribution on automatic identification evaporator pipe sheet, aided in by personnel or
Feature point recognition, mark position of the tube sheet localizer on tube sheet, is greatly improved inspection efficiency in real time, effectively reduces live people
The people of member's manual identification tube sheet locator position, because of error, is to be evaporated a kind of auxiliary well when device heat-transfer pipe vortex is checked
Method.
Above-described embodiment technology design only to illustrate the invention and feature, its object is to allow person skilled in the art
Scholar will appreciate that present disclosure and implement according to this, can not be limited the scope of the invention with this.All according to the present invention
Equivalence changes or modification that spirit is made, should all be included within the scope of the present invention.
Claims (10)
1. the aided positioning system of the evaporator pipe sheet localizer of a kind of view-based access control model identification, for real-time positioning evaporator pipe sheet
Position of the localizer on the tube sheet of vaporizer, it is characterised in that:Which includes IP Camera, signal transmission system and collection point
Analysis computer;
The IP Camera is arranged in the hydroecium of the vaporizer and the tube sheet of vaporizer described in captured in real-time and thereon
The image of the evaporator pipe sheet localizer;
The signal transmission system is arranged between the IP Camera and the collection analysises computer and takes the photograph the network
Image transmitting as captured by head gives the collection analysises computer;
The collection analysises computer is arranged in the collection container outside nuclear island, and the collection analysises computer is to the network shooting
Image captured by head is analyzed in real time and is drawn the coordinate of each pore on the tube sheet, and superposition is labelled with each described
The image of the coordinate of pore is shown by its display.
2. the aided positioning system of the evaporator pipe sheet localizer of view-based access control model according to claim 1 identification, its feature
It is:The signal transmission system includes to be arranged in the room of the vaporizer place and be connected with the IP Camera
First remote communication module is connected with first remote communication module and is caused outside nuclear island by vaporizer place room
Optical fiber in the collection container, it is arranged at the second telecommunication being connected in the collection container and with the optical fiber
Module, the collection analysises computer is connected with second remote communication module.
3. the aided positioning system of the evaporator pipe sheet localizer of view-based access control model according to claim 2 identification, its feature
It is:First remote communication module, second remote communication module all include the network switch and fiber optic network conversion
Device.
4. the aided positioning system of the evaporator pipe sheet localizer of view-based access control model according to claim 1 identification, its feature
It is:The IP Camera is connected with first remote communication module by cable, and the collection analysises computer passes through
Netting twine is connected with second remote communication module.
5. the aided positioning system of the evaporator pipe sheet localizer of view-based access control model according to claim 1 identification, its feature
It is:The IP Camera is wide-angle camera.
6. a kind of aided positioning system of the evaporator pipe sheet localizer of view-based access control model identification as claimed in claim 1 is adopted
Assisted location method, it is characterised in that:The assisted location method is:By evaporating described in the IP Camera captured in real-time
The tube sheet of device and the image of the evaporator pipe sheet localizer thereon, and described adopting is sent to by the signal transmission system
Set analysis computer, the collection analysises computer is first carried out after pretreatment to described image, then is carried out center of circle detection and identified institute
Each pore and its center of circle in image is stated, the last coordinate according to predetermined benchmark pore group determines each pipe
The coordinate in hole and each pore is labeled, and will superposition be labelled with each pore coordinate image by its display
Show.
7. what the aided positioning system of the evaporator pipe sheet localizer of view-based access control model identification according to claim 6 was adopted is auxiliary
Help localization method, it is characterised in that:The collection analysises computer carries out center of circle detection using Hough transformation.
8. what the aided positioning system of the evaporator pipe sheet localizer of view-based access control model identification according to claim 6 was adopted is auxiliary
Help localization method, it is characterised in that:Pretreatment to described image includes coloured image gray processing, image enhaucament, image noise reduction
And rim detection.
9. what the aided positioning system of the evaporator pipe sheet localizer of view-based access control model identification according to claim 8 was adopted is auxiliary
Help localization method, it is characterised in that:The coloured image gray processing is carried out using weighted mean method;Institute is carried out using greyscale transformation
State image enhaucament;Described image noise reduction is carried out using median filter method;The rim detection is carried out using Canny operator.
10. the aided positioning system of the evaporator pipe sheet localizer of view-based access control model identification according to claim 6 is adopted
Assisted location method, it is characterised in that:The coordinate method for determining each pore is:Benchmark pore group described in advance manually determined
In each benchmark pore coordinate in a coordinate system and determined by the center of circle of two benchmark pores with the coordinate system
The parallel datum line of coordinate axess, and the unit length of coordinate system is determined, then the center of circle according to each pore and the benchmark
The coordinate of the distance of line and the unit length, the benchmark pore determines the coordinate of the pore.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610892566.9A CN106447665A (en) | 2016-10-13 | 2016-10-13 | Auxiliary positioning system and method of evaporator plate pipe locator based on visual identity |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610892566.9A CN106447665A (en) | 2016-10-13 | 2016-10-13 | Auxiliary positioning system and method of evaporator plate pipe locator based on visual identity |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106447665A true CN106447665A (en) | 2017-02-22 |
Family
ID=58174386
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610892566.9A Pending CN106447665A (en) | 2016-10-13 | 2016-10-13 | Auxiliary positioning system and method of evaporator plate pipe locator based on visual identity |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106447665A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107962565A (en) * | 2017-10-31 | 2018-04-27 | 中广核检测技术有限公司 | A kind of localization method of video inspection device scanning position |
CN109451283A (en) * | 2018-12-21 | 2019-03-08 | 核动力运行研究所 | A kind of steam generator water chamber ambient image acquisition system |
CN109766783A (en) * | 2018-12-21 | 2019-05-17 | 杭州测质成科技有限公司 | A kind of aviation cable identifying system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040181342A1 (en) * | 1999-10-12 | 2004-09-16 | Yi-Xiong Zhou | System and method for automatically analyzing gene expression spots in a microarray |
CN101354785A (en) * | 2008-09-04 | 2009-01-28 | 湖南大学 | Method for accurately positioning vision in cleaning robot of condenser |
CN102152033A (en) * | 2011-02-14 | 2011-08-17 | 苏州工业园区华焊科技有限公司 | Image centralizing location method for automatic tube plate welding |
CN103913115A (en) * | 2013-01-04 | 2014-07-09 | 光道视觉科技股份有限公司 | Image coordinate system and real space coordinate system automatic corresponding correction method |
CN204789404U (en) * | 2015-07-01 | 2015-11-18 | 中核武汉核电运行技术股份有限公司 | Full -automatic heat exchanger pipe end angle welding checkout system |
-
2016
- 2016-10-13 CN CN201610892566.9A patent/CN106447665A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040181342A1 (en) * | 1999-10-12 | 2004-09-16 | Yi-Xiong Zhou | System and method for automatically analyzing gene expression spots in a microarray |
CN101354785A (en) * | 2008-09-04 | 2009-01-28 | 湖南大学 | Method for accurately positioning vision in cleaning robot of condenser |
CN102152033A (en) * | 2011-02-14 | 2011-08-17 | 苏州工业园区华焊科技有限公司 | Image centralizing location method for automatic tube plate welding |
CN103913115A (en) * | 2013-01-04 | 2014-07-09 | 光道视觉科技股份有限公司 | Image coordinate system and real space coordinate system automatic corresponding correction method |
CN204789404U (en) * | 2015-07-01 | 2015-11-18 | 中核武汉核电运行技术股份有限公司 | Full -automatic heat exchanger pipe end angle welding checkout system |
Non-Patent Citations (1)
Title |
---|
王利军等: "基于CCD图像处理的管板自动焊焊枪自动定位方法", 《焊接设备与材料》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107962565A (en) * | 2017-10-31 | 2018-04-27 | 中广核检测技术有限公司 | A kind of localization method of video inspection device scanning position |
CN109451283A (en) * | 2018-12-21 | 2019-03-08 | 核动力运行研究所 | A kind of steam generator water chamber ambient image acquisition system |
CN109766783A (en) * | 2018-12-21 | 2019-05-17 | 杭州测质成科技有限公司 | A kind of aviation cable identifying system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110297498B (en) | Track inspection method and system based on wireless charging unmanned aerial vehicle | |
CN103413139B (en) | Electric equipment abnormal heating detection method based on infrared inspection video data of power line inspection | |
CN110142785A (en) | A kind of crusing robot visual servo method based on target detection | |
CN104036488B (en) | Binocular vision-based human body posture and action research method | |
CN106340009B (en) | A kind of electric power line detecting method and system based on parallel binocular | |
CN105550670A (en) | Target object dynamic tracking and measurement positioning method | |
CN106447665A (en) | Auxiliary positioning system and method of evaporator plate pipe locator based on visual identity | |
CN111158358B (en) | Method and system for self-optimization routing inspection of transformer/converter station based on three-dimensional model | |
CN106127205A (en) | A kind of recognition methods of the digital instrument image being applicable to indoor track machine people | |
CN107610128A (en) | The method for inspecting and device of a kind of oil level indicator | |
CN104554344B (en) | Thread defect information detecting system and method | |
CN107392247A (en) | Atural object safe distance real-time detection method below a kind of power line | |
CN110084243A (en) | It is a kind of based on the archives of two dimensional code and monocular camera identification and localization method | |
CN107179479A (en) | Transmission pressure broken lot defect inspection method based on visible images | |
CN115100423B (en) | System and method for realizing real-time positioning based on view acquisition data | |
CN106920241A (en) | A kind of steam water-level monitoring method, apparatus and system | |
CN109697428A (en) | Positioning system is identified based on the unmanned plane of RGB_D and depth convolutional network | |
CN114941807A (en) | Unmanned aerial vehicle-based rapid monitoring and positioning method for leakage of thermal pipeline | |
CN105044800B (en) | A kind of lighting location device and method based on optical observation | |
CN113465522A (en) | Point cloud-based method for measuring distance of hidden danger in power transmission channel | |
CN113763484A (en) | Ship target positioning and speed estimation method based on video image analysis technology | |
CN112734732B (en) | Railway tunnel cable leakage clamp detection method based on improved SSD algorithm | |
CN116883999A (en) | Safety distance monitoring method for large-scale construction machinery and working area of transformer substation | |
CN110633623A (en) | Management and control method for operation process of transformer substation worker | |
CN206962973U (en) | A kind of centralized control system for substation inspection |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170222 |