CN107726990A - The collection of dot matrix grid image and recognition methods in a kind of Sheet metal forming strain measurement - Google Patents
The collection of dot matrix grid image and recognition methods in a kind of Sheet metal forming strain measurement Download PDFInfo
- Publication number
- CN107726990A CN107726990A CN201710842903.8A CN201710842903A CN107726990A CN 107726990 A CN107726990 A CN 107726990A CN 201710842903 A CN201710842903 A CN 201710842903A CN 107726990 A CN107726990 A CN 107726990A
- Authority
- CN
- China
- Prior art keywords
- dot matrix
- matrix grid
- grid image
- width
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000011159 matrix material Substances 0.000 title claims abstract description 215
- 238000000034 method Methods 0.000 title claims abstract description 63
- 239000002184 metal Substances 0.000 title claims abstract description 34
- 229910052751 metal Inorganic materials 0.000 title claims abstract description 34
- 238000005259 measurement Methods 0.000 title claims abstract description 24
- 238000000354 decomposition reaction Methods 0.000 claims description 8
- 230000004927 fusion Effects 0.000 claims description 6
- 238000000205 computational method Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 claims description 2
- 239000010931 gold Substances 0.000 claims description 2
- 229910052737 gold Inorganic materials 0.000 claims description 2
- 230000003287 optical effect Effects 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000011017 operating method Methods 0.000 abstract 1
- 238000012360 testing method Methods 0.000 description 19
- 230000006870 function Effects 0.000 description 10
- 230000003321 amplification Effects 0.000 description 5
- 238000003199 nucleic acid amplification method Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 238000000691 measurement method Methods 0.000 description 3
- 238000007493 shaping process Methods 0.000 description 3
- 238000010297 mechanical methods and process Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 241000416536 Euproctis pseudoconspersa Species 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 210000004209 hair Anatomy 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003913 materials processing Methods 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/16—Measuring arrangements characterised by the use of optical techniques for measuring the deformation in a solid, e.g. optical strain gauge
-
- 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 using two or more images, e.g. averaging or subtraction
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid 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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention discloses the collection of dot matrix grid image and recognition methods in a kind of Sheet metal forming strain measurement, belongs to optical 3-dimensional non-contact measuring technology field, and this method realizes that step includes the more exposure dot matrix grid images of 1) shooting;2) weight map is calculated;3) weight map Pyramid transform;4) expose dot matrix grid image Pyramid transform more;5) laplacian pyramid assigns power;6) laplacian pyramid merges;7) dot matrix grid image reconstructs;8) dot matrix grid image binaryzation;9) sub-pix Boundary Recognition;10) ellipse fitting.By the operating procedure, the present invention can eliminate the influence of metal blank surface reflection, improve dot matrix grid image acquisition quality, improve the discrimination of dot matrix grid image.
Description
Technical field
The invention belongs to optical 3-dimensional non-contact measuring technology field, is related in a kind of Sheet metal forming strain measurement
Dot matrix grid image gathers and recognition methods.A kind of dot matrix grid image based on the fusion of more exposure images is further related to adopt
Collection and recognition methods.
Background technology
Sheet metal forming is one of important branch in materials processing technology, Aero-Space, automobile, equipment manufacturing,
The all departments of the national economy such as electrical equipment are widely used.During Sheet metal forming, it is necessary to by measuring metal
The three dimensional strain of panel surface analyzes its shaping situation, so as to monitor critical strain position, solve complicated shaping, optimization punching press
Technique etc..It is non-that the three dimensional strain measurement means and method on metal blank surface mainly include Mechanical Method, electrical measuring method and optical 3-dimensional
Contact type measurement method etc..Wherein, optical 3-dimensional non-contact type measuring method is current Sheet metal forming three-dimensional whole field strain measurement
Main Means.
Chinese invention patent ZL201110263622.X discloses a kind of metal based on optical 3-dimensional non-contact measurement
Sheet forming strain measurement method.This method uses the point that digital camera or industrial CCD camera are prepared to metal blank surface
Battle array lattice is sampled shooting, obtains the three-dimensional reconstruction that grid images more than two width or two width is used for grid, and root
According to the change in size of three-dimensional grid before and after shaping, the three-dimensional whole field strain on metal blank surface is calculated.With Mechanical Method and electrical measurement
Method is compared, and this method has contactless, measurement efficiency is high, measurement accuracy is high, can obtain three-dimensional whole field to strain and be applicable to
The advantages that large scale Sheet metal forming product.However, due to the strong light-reflecting property on metal blank surface, generally, the point of collection
Light and shade differs greatly in battle array grid image, is especially only protected in some reflective serious regions, the imaging of grid node in the picture
Stay seldom part or can not be imaged so that grid node discrimination is low, and then influences the measurement of three dimensional strain.
The content of the invention
To solve drawbacks described above present in prior art, the invention provides a kind of point based on the fusion of more exposure images
The collection of battle array grid image and recognition methods, this method can eliminate the strong reflective influence in metal blank surface in sampling shooting process,
Improve dot matrix grid image shooting quality, improve the discrimination of dot matrix grid image.
To achieve the above objectives, the present invention adopts the technical scheme that:
The collection of dot matrix grid image and recognition methods, comprise the steps in a kind of Sheet metal forming strain measurement:
Step 1, shoot more exposure dot matrix grid images
Keep camera motionless, the different dot matrix grid image of some width light exposures is shot under black and white screening-mode;
Step 2, calculate weight map
Contrast and exposure that each width captured by step 1 exposes dot matrix grid image more are calculated respectively, and will
The contrast that each width calculated exposes dot matrix grid image more is multiplied with exposure, obtains each width and exposes dot matrix grid chart more
The weight map of picture;
Step 3, weight map Pyramid transform
The weight map that each width calculated step 2 exposes dot matrix grid image more carries out gaussian pyramid decomposition;
Step 4 expose dot matrix grid image Pyramid transform more
Expose dot matrix grid image more to each width captured by step 1 and carry out Laplacian pyramid, decomposition
The number of plies is identical with the number of plies for the weight map gaussian pyramid that step 3 is decomposed;
Step 5, laplacian pyramid assign power
Each width that step 4 is decomposed exposes the image on each layer of laplacian pyramid of dot matrix grid image more
The image in the weight map gaussian pyramid respective layer of dot matrix grid image is exposed with the width that step 3 is decomposed to be multiplied more, is obtained
Obtain entitled laplacian pyramid;
Step 6, laplacian pyramid fusion
Step 5 is obtained into entitled some width to expose on the laplacian pyramid identical layer of dot matrix grid image more
Image addition;
Step 7, the reconstruct of dot matrix grid image
The laplacian pyramid merged to step 6 carries out inverse turriform and converted, and reconstructs the new dot matrix grid chart of a width
Picture;
Step 8, dot matrix grid image binaryzation
The dot matrix grid image reconstructed to step 7 carries out local auto-adaptive binary conversion treatment, obtains bianry image;
Step 9, sub-pix Boundary Recognition
The whole pixel side of dot matrix grid node in the bianry image that step 8 obtained is identified using 8 connected domain rules
Boundary;On this basis, the sub-pix border of dot matrix grid node is identified using space moments method;
Step 10, ellipse fitting
The sub-pix border of the dot matrix grid node identified to step 9, ellipse is gone out using least square method iterative fitting
Centre coordinate, so as to obtain the coordinate of dot matrix grid node.
Further, the collection of dot matrix grid image also includes with recognition methods in the Sheet metal forming strain measurement,
Before the more exposure dot matrix grid images of step 1 shooting are carried out, first focus so that the dot matrix grid on metal blank surface
It can clearly be imaged, focal length is locked after regulation.
Further, when the step 1 shooting exposes dot matrix grid image more, camera is adjusted to black and white screening-mode, protected
It is stable to hold camera, adjusts light exposure, shoots the more than 3 width or 3 width dot matrix grid charts from under-exposure, normal exposure to overexposure
Picture.
Further, weight map computational methods are as follows in the step 2:
2.1) dot matrix grid image is exposed to each width captured by step 1 more, filtered using Laplace operator
Ripple, filter result is taken absolute value, just obtain the contrast factor that each width exposes dot matrix grid image more;
2.2) dot matrix grid image is exposed more to each width captured by step 1, its exposure factor uses equation below
Calculate:
Wherein, e represents natural constant, and k represents that kth width exposes dot matrix grid image more, and (i, j) represents pixel position,
Ik(i, j) represents that kth width exposes dot matrix grid image in the gray value of the pixel of (i, j) opening position, E morek(i, j) represents the
K width exposes the exposure factor of the dot matrix grid image in (i, j) opening position more, and σ represents kernel function width;
2.3) on the basis of the contrast factor that step 2.1) is calculated and the exposure factor 2.2) calculated, adopt
The weight factor of each width exposure dot matrix grid image more is calculated with equation below:
Wherein,Represent that kth width exposes dot matrix grid image in the weight factor of (i, j) opening position, C morek(i,j)
Represent that the kth width that step 2.1) is calculated exposes the comparison degree factor of the dot matrix grid image in (i, j) opening position more;
2.4) place is normalized in the weight factor that each width calculated step 2.3) exposes dot matrix grid image more
Reason, obtains the weight map that each width exposes dot matrix grid image more, and method for normalizing is as follows:
Wherein, Wk(i, j) represents that kth width exposes pixel of the weight map in (i, j) opening position of dot matrix grid image more
Gray value, N represents the width number of more exposure dot matrix grid images captured by step 1, and s represents that s width exposes dot matrix grid more
Image,Represent the s width that is calculated of step 2.3) expose more dot matrix grid image (i, j) opening position weight because
Son.
Further, the Laplace operator h used in the step 2.2) for:
Further, Pyramid transform number of plies L computational methods are as follows in the step 3:
Wherein, r and c represents the line numbers and columns of more exposure dot matrix grid images respectively, ln () represent using natural constant e as
The natural logrithm function at bottom, min (r, c) represent that the line number of more exposure dot matrix grid images and columns take minimum value function.
Further, dot matrix grid image local auto-adaptive binarization method is as follows in the step 8:
8.1) quick binaryzation is carried out using the dot matrix grid image reconstructed by window binaryzation method to step 7, obtained
Bianry image;
8.2) bianry image obtained to step 8.1) carries out connected component labeling, is more than for pixel number given
The connected region of threshold tau, further using binaryzation method pixel-by-pixel to all pixels point in connected region again binaryzation:
A) a binary-state threshold is calculated for any pixel point in the connected region more than given threshold value τ:
Wherein, (i, j) represents pixel position, and T (i, j) represents two of the pixel of (i, j) opening position in connected region
Value threshold value,Represent in the dot matrix grid image that step 7 is reconstructed
The average gray value of the pixel in u × v local windows centered on (i, j), u and v represent the length dimension of window respectively
And height dimension, m and n represent two integer variables, I '0The dot matrix grid image that (m, n) expression step 7 is reconstructed is at (m, n)
The gray value of the pixel of opening position,Represent step
The grey value profile of the pixel in u × v local windows in the rapid seven dot matrix grid images reconstructed centered on (i, j)
Standard deviation value, γ and offset is two constants;
B) according to the binary-state threshold that step a) is calculated to pixel again binaryzation:
Wherein, I ' (i, j) represents the picture of step 8.1) is obtained after binaryzation again bianry image in (i, j) opening position
The gray value of vegetarian refreshments, I '0Ash of the dot matrix grid image that (i, j) expression step 7 is reconstructed in the pixel of (i, j) opening position
Angle value.
Further, the value of threshold tau is τ=10000 in the step 8.2).
Further, in the step 10 in each iterative process, it is oval to being fitted to calculate each boundary point
Spacing and standard deviation value sigma, 3sigma boundary point is more than to spacing, is not involved in interative computation next time.
Compared with prior art, the inventive method has advantages below:
(1) the inventive method can eliminate the strong reflective influence in metal blank surface, collect the dot matrix grid chart of high quality
Picture;
(2) the dot matrix grid image quality of the inventive method collection is high, therefore the discrimination of dot matrix grid image is also corresponding
Improve;
(3) the dot matrix grid image quality of the inventive method collection is high, therefore the accuracy of identification of dot matrix grid image also phase
It should improve;
(4) the inventive method improves the discrimination and accuracy of identification of dot matrix grid image, therefore also improves indirectly
The reconstruction precision of three-dimensional grid and the measurement accuracy of three dimensional strain.
Brief description of the drawings
The flow chart of Fig. 1 concrete operation steps of the present invention.
The under-exposure dot matrix grid image of certain cupping test specimen of Fig. 2 a shootings.
Certain cupping test specimen normal exposure dot matrix grid image of Fig. 2 b shootings.
Certain cupping test specimen overexposure dot matrix grid image of Fig. 2 c shootings.
Certain cupping test specimen dot matrix grid image of Fig. 3 reconstruct.
Dot matrix grid image testing result that Fig. 4 cupping test specimens are under-exposure.
Fig. 5 cupping test specimen normal exposure dot matrix grid image testing results.
Fig. 6 cupping test specimen overexposure dot matrix grid image testing results.
Certain cupping test specimen dot matrix grid image testing result of Fig. 7 reconstruct.
Embodiment
The invention will be described in further detail with reference to the accompanying drawings and examples, but is not intended as doing any limit to invention
The foundation of system.
The present invention proposes the collection of dot matrix grid image and recognition methods, such as Fig. 1 in a kind of Sheet metal forming strain measurement
It is shown.When collection and the dot matrix grid image on a certain visual angle metal blank surface of identification, the first step, more exposure dot matrix grids are shot
Image.Before shooting, first focus so that the dot matrix grid on metal blank surface can be clearly imaged, and be locked after regulation
Focal length.It is variegated in order to reduce during shooting, camera is adjusted to black and white screening-mode, keeps camera stable, adjusts light exposure, shooting 3
Dot matrix grid image more than width or 3 width from under-exposure, normal exposure to overexposure.
Second step, calculate weight map.Calculate the weight map that each width captured by the first step exposes dot matrix grid image more.
Weight map calculation process comprises the following steps:
1) contrast factor is calculated.Dot matrix grid image is exposed more to each width captured by the first step, using La Pula
This operator h is filtered, and filter result is taken absolute value, just obtain each width more expose dot matrix grid image contrast because
Son.Used Laplace operator h is:
2) the exposure factor is calculated.Dot matrix grid image is exposed more to each width captured by the first step, using following public affairs
Formula calculates its exposure factor:
Wherein, e represents natural constant, and k represents that kth width exposes dot matrix grid image more, and (i, j) represents pixel position,
Ek(i, j) represents that kth width exposes dot matrix grid image in the exposure factor of (i, j) opening position, I morek(i, j) represents kth width
The gray values for exposing dot matrix grid images in the pixel of (i, j) opening position, σ represent kernel function width more, and its span is 0
< σ≤0.5, typically selects σ=0.2.
3) weight factor is calculated.In 1) contrast factor that step is calculated and 2) the exposure factor that step is calculated
On the basis of, using the weight factor of each width of equation below calculating exposure dot matrix grid image more:
Wherein,Represent that kth width exposes dot matrix grid image in the weight factor of (i, j) opening position, C morek(i,j)
Represent the 1) kth width that step is calculated expose the comparison degree factor of the dot matrix grid image in (i, j) opening position more.
4) weight factor normalizes.To the 3) each width that step is calculated expose the weight factor of dot matrix grid image more and enter
Row normalized, obtains the weight map that each width exposes dot matrix grid image more, and the normalization formula of use is as follows:
Wherein, Wk(i, j) represents that kth width exposes pixel of the weight map in (i, j) opening position of dot matrix grid image more
Gray value, N represents the width number of more exposure dot matrix grid images captured by the first step, and s represents that s width exposes dot matrix grid more
Image,Represent the 3) s width that step is calculated expose weight factor of the dot matrix grid image in (i, j) opening position more.
3rd step, weight map Pyramid transform.The each width calculated second step exposes the weight of dot matrix grid image more
Figure carries out gaussian pyramid decomposition.Decomposition process comprises the following steps:
1) the Pyramid transform number of plies is calculated.Pyramid transform number of plies L computational methods are as follows:
Wherein, r and c represent the line numbers and columns of more exposure dot matrix grid images respectively, ln () represent using natural constant e as
The natural logrithm function at bottom, min (r, c) represent that the line number of more exposure dot matrix grid images and columns take minimum value function.
2) the 0th layer of weight map gaussian pyramid is constructed.Each width that second step is calculated exposes dot matrix grid image more
Weight map as the image on the 0th layer of weight map gaussian pyramid:
Gk,0(i, j)=Wk(i, j),
Wherein, k represents that kth width exposes dot matrix grid image more, and (i, j) represents pixel position, Gk,0(i, j) represents kth
Ash of image of the width more on the 0th layer of the weight map Gauss pyramid of exposure dot matrix grid image in the pixel of (i, j) opening position
Angle value, Wk(i, j) represents that the kth width that second step is calculated exposes the weight map of dot matrix grid image in (i, j) opening position more
The gray value of pixel.
3) weight map gaussian pyramid t layers are constructed.By the image on weight map gaussian pyramid t-1 layers and one 5
× 5 window functions carry out convolution, then convolution results are made interlacing and just obtain weight map gaussian pyramid t layers every the down-sampled of row
On image:
Wherein, t represents pyramidal t layers, Gk,t(i, j) represents that kth width exposes the weight map height of dot matrix grid image more
In the gray value of the pixel of (i, j) opening position, m and n represent two integer variables, G for image on this pyramid t layerk,t-1
(2i+m, 2j+n) represents that kth width exposes the image on the weight map gaussian pyramid t-1 layers of dot matrix grid image in (2i more
+ m, 2j+n) opening position pixel gray value, λ (m, n) represent 5 × 5 window functions:
The 2) kth width that step is constructed expose more dot matrix grid image the 0th layer of weight map gaussian pyramid basis
On, according to the weight map gaussian pyramid t layer building methods, the power that kth width exposes dot matrix grid image more can be constructed
The 1st layer of multigraph gaussian pyramid, by that analogy, the weight map Gauss gold word that kth width exposes dot matrix grid image more can be constructed
Tower L layers.
4th step expose dot matrix grid image Pyramid transform more.Dot matrix net is exposed more to each width captured by the first step
Table images carry out Laplacian pyramid.Decomposition process comprises the following steps:
1) dot matrix grid image gaussian pyramid is exposed to decompose more.According to the weight map Pyramid transform side described in the 3rd step
Method, expose dot matrix grid image more to each width captured by the first step and carry out gaussian pyramid decomposition, and the height that will be decomposed
Image on this pyramid t layer is designated as G 'k,t, wherein, k represents that kth width exposes dot matrix grid image more;
2) laplacian pyramid L layers are constructed.Using the image on 1) gaussian pyramid L layers that step is decomposed as
Image on laplacian pyramid L layers:
LPk,L(i, j)=G 'k,L(i, j),
Wherein, (i, j) represents pixel position, and L represents the Pyramid transform number of plies that the 3rd step is calculated, LPk,L(i, j) table
Show that kth width exposes pixel of the image on dot matrix grid image laplacian pyramid L layers in (i, j) opening position more
Gray value, G 'k,L(i, j) represents the 1st) the kth width that is decomposed of step exposes on dot matrix grid image gaussian pyramid L layers more
Gray value of the image in the pixel of (i, j) opening position;
3) laplacian pyramid t layers are constructed.Laplacian pyramid t layer building methods are as follows:
A) image interpolation on the 1) gaussian pyramid t+1 layers that step is decomposed is amplified:
Wherein, t+1 represents pyramid t+1 layers,Represent the image after interpolation amplification in (i, j) opening position
The gray value of pixel,M and n
Two integer variables are represented,Represent the 1) kth width that step is decomposed expose dot matrix grid image Gauss more
Image on pyramid t+1 layers existsThe gray value of the pixel of opening position,Represent
One transition variable, λ (m, n) represent 5 × 5 window functions described in the 3rd step;
B) image on the 1) gaussian pyramid t layers that step is decomposed is done with the image after a) step interpolation amplification and subtracted
Method computing:
Wherein, LPk,t(i, j) represents that kth width exposes the image on dot matrix grid image laplacian pyramid t layers more
In the gray value of the pixel of (i, j) opening position, G 'k,t(i, j) represents the 1st) the kth width that is decomposed of step exposes dot matrix grid more
The gray value of image on image gaussian pyramid t layers in the pixel of (i, j) opening position;
According to the laplacian pyramid t layer building methods, laplacian pyramid L-1 layers can be constructed successively
To the 0th layer.
5th step, laplacian pyramid assign power.The each width decomposed to the 4th step exposes dot matrix grid image more
Laplacian pyramid, tax power is carried out with the following method:
LP′k,t(i, j)=Gk,t(i,j)×LPk,t(i,j),
Wherein, k represents that kth width exposes dot matrix grid image more, and t represents pyramid t layers, and (i, j) represents pixel position
Put, LP 'k,tThe kth width that (i, j) represents to assign after weighing exposes the image on dot matrix grid image laplacian pyramid t layers more
In the gray value of the pixel of (i, j) opening position, Gk,t(i, j) represents that the kth width that the 3rd step is decomposed exposes dot matrix grid more
Image on the weight map gaussian pyramid t layers of image is in the gray value of the pixel of (i, j) opening position, LPk,t(i, j) table
Show that kth width that the 4th step decomposed exposes the image on dot matrix grid image laplacian pyramid t layers in (i, j) position more
The gray value of the pixel at place, the gray value of two pixels of symbol × expression are multiplied.
6th step, laplacian pyramid fusion.Laplacian pyramid fusion method is as follows:
Wherein, k represents that kth width exposes dot matrix grid image more, and t represents pyramid t layers, and (i, j) represents pixel position
Putting, N represents the width number of more exposure dot matrix grid images captured by the first step,Represent Laplce's gold after fusion
Image on word tower t layers is in the gray value of the pixel of (i, j) opening position, LP 'k,t(i, j) represents the 5th step institute entitled the
Gray scale of image of the k width more on exposure dot matrix grid image laplacian pyramid t layers in the pixel of (i, j) opening position
Value.
7th step, the reconstruct of dot matrix grid image.The laplacian pyramid merged to the 6th step carries out inverse turriform and converted,
Construct the new dot matrix grid image of a width.Inverse turriform conversion comprises the following steps:
1) gaussian pyramid L layers are recovered.The image on laplacian pyramid L layers that 6th step is merged as
Image on gaussian pyramid L layers to be restored:
Wherein, (i, j) represents pixel position, and L represents the Pyramid transform number of plies that the 3rd step is calculated, I 'L(i, j) is represented
The image on gaussian pyramid L layers recovered the pixel of (i, j) opening position gray value,Represent the 6th
The gray value of pixel of the image in (i, j) opening position on the merged laplacian pyramid L layers of step;
2) gaussian pyramid t layers are recovered.Gaussian pyramid t layer restoration methods are as follows:
A) the image interpolation amplification on the laplacian pyramid t+1 layers for being merged the 6th step:
Wherein, t+1 represents pyramid t+1 layers,Represent picture of the image after interpolation amplification in (i, j) opening position
The gray value of vegetarian refreshments, m and n represent two integer variables, and λ (m, n) represents 5 × 5 window functions described in the 3rd step,Represent the 6th step
The image on laplacian pyramid t+1 layers merged existsThe gray value of the pixel of opening position,Represent a transition variable;
B) image on the laplacian pyramid t layers for being merged the image after a) step interpolation amplification with the 6th step
Do add operation:
Wherein, I 't(i, j) represents pixel of the image on recovered gaussian pyramid t layers in (i, j) opening position
Gray value,Represent the image on the laplacian pyramid t layers that the 6th step is merged in (i, j) opening position
The gray value of pixel;
According to the gaussian pyramid t layer restoration methods, gaussian pyramid L-1 layers can be recovered successively to the 0th layer, institute
Image I ' on the 0th layer of the gaussian pyramid of recovery0Dot matrix grid image exactly to be reconstructed.
8th step, dot matrix grid image self-adaption binaryzation.Self-adaption binaryzation flow comprises the following steps:
1) document " Circular grid pattern based surface strain measurement are used
system for sheet metal forming”(Shi B and Liang J,OPT LASER ENG,2012,50(9):
The dot matrix grid image reconstructed by window binaryzation method to step 7 described in 1186-1195) carries out quick binaryzation,
Obtain bianry image.
2) to the 1) bianry image that step is obtained carry out connected component labeling, be more than given threshold value for pixel number
τ region, further using binaryzation method pixel-by-pixel to all pixels point in connected region again binaryzation:
A) a binary-state threshold is calculated for any pixel point in the connected region more than given threshold value τ:
Wherein, (i, j) represents pixel position, and T (i, j) represents two of the pixel of (i, j) opening position in connected region
Value threshold value,Represent in the dot matrix grid image that the 7th step is reconstructed with
The average gray value of the pixel in u × v local windows centered on (i, j), m and n represent two integer variables, and u and v distinguishes
The length dimension and height dimension of window are represented, generally takes u=v=23, I '0(m, n) represents the dot matrix grid that step 7 is reconstructed
Image the pixel of (m, n) opening position gray value,
Represent the gray value of the pixel in u × v local windows in the dot matrix grid image that the 7th step is reconstructed centered on (i, j)
The standard deviation value of distribution, γ and offset is two constants, typically selects γ=0.1, offset=5.0, and threshold tau is positive integer,
Typically take τ=10000;
B) according to the binary-state threshold that step a) is calculated to pixel again binaryzation:
Wherein, I ' (i, j) represents the picture of step 8.1) is obtained after binaryzation again bianry image in (i, j) opening position
The gray value of vegetarian refreshments, I '0Ash of the dot matrix grid image that (i, j) expression step 7 is reconstructed in the pixel of (i, j) opening position
Angle value,.
9th step, sub-pix Boundary Recognition.Sub-pix Boundary Recognition method is as follows:
1) the whole pixel side of dot matrix grid node in the bianry image that the 8th step is obtained is identified using 8 connected domain rules
Boundary;
2) it is further using space moments method on the basis of 1) the whole pixel boundary for the dot matrix grid node that step is identified
Identify the sub-pix border of dot matrix grid node.
Tenth step, ellipse fitting.The sub-pix border of dot matrix grid node in the bianry image identified to the 9th step,
Using document " Least squares fitting of circles and ellipses " (W.Gander, G.H.Golub
And R.Strebel, BIT Numerical Mathematics, 1994,34:Least-squares iteration described by 558-578)
Method fits elliptical center coordinate.In order to reduce noise jamming, in each iterative process, each boundary point is calculated to being intended
The oval spacing and standard deviation value sigma of conjunction, 3sigma boundary point is more than to spacing, is not involved in iteration next time
Computing.The elliptical center coordinate being finally fitted is the coordinate of dot matrix grid node.
Below in conjunction with physical simulation experiment, the present invention will be described, and wherein the inventive method is put down in VS2010 and opengl
Realized on platform corresponding algorithm and Intel i7-4770CPU 3.4GHz, 16GB internal memories PC on run.
3 width cupping test specimens of shooting expose dot matrix grid image as shown in Fig. 2 a- Fig. 2 c more, wherein, Fig. 2 a are shown
The under-exposure dot matrix grid image of certain cupping test specimen of shooting, Fig. 2 b show certain cupping test specimen normal exposure dot matrix grid of shooting
Image, Fig. 2 c show certain cupping test specimen overexposure dot matrix grid image of shooting.Fig. 3 is shown according to 3 captured width
The new dot matrix grid image of the cupping test specimen width that exposure dot matrix grid image is reconstructed using the inventive method more.Pass through contrast
Fig. 2 a- Fig. 2 c and Fig. 3 can be seen that dot matrix grid in reconstructed dot matrix grid image and become apparent from.Fig. 4 to Fig. 7 is shown
Certain cupping test specimen is under-exposure dot matrix grid image, normal exposure dot matrix grid image, overexposure dot matrix grid image and reconstructed
Dot matrix grid node testing result in dot matrix grid image, dot matrix grid node discrimination is followed successively by 49.6%, 77.78%,
72.3%th, 86.87%.Wherein, white cross hairs represents the coordinate of detected dot matrix grid node.Schemed by comparison diagram 4-
7 as can be seen that the number that dot matrix grid node detects in the dot matrix grid image reconstructed is most, and dot matrix grid node identifies
Rate highest, it is 86.87%.It can also be illustrated by the present embodiment, it is strong reflective that the inventive method can eliminate metal blank surface
Influence, improve dot matrix grid image acquisition quality, improve the discrimination of dot matrix grid image.
Embodiments of the present invention are described above in conjunction with drawings and examples, but the present invention is not limited to above-mentioned reality
Apply mode, can also be before present inventive concept not be departed from one skilled in the relevant art's possessed knowledge
Put and make a variety of changes.
Claims (9)
1. the collection of dot matrix grid image and recognition methods in a kind of Sheet metal forming strain measurement, it is characterised in that including under
State step:
Step 1, shoot more exposure dot matrix grid images
Keep camera motionless, the different dot matrix grid image of some width light exposures is shot under black and white screening-mode;
Step 2, calculate weight map
Calculate contrast and exposure that each width captured by step 1 exposes dot matrix grid image more respectively, and will calculate
Each width expose the contrast of dot matrix grid image more and be multiplied with exposure, obtain the dot matrix grid image of exposure more than each width
Weight map;
Step 3, weight map Pyramid transform
The weight map that each width calculated step 2 exposes dot matrix grid image more carries out gaussian pyramid decomposition;
Step 4 expose dot matrix grid image Pyramid transform more
Expose dot matrix grid image more to each width captured by step 1 and carry out Laplacian pyramid, the number of plies of decomposition
It is identical with the number of plies for the weight map gaussian pyramid that step 3 is decomposed;
Step 5, laplacian pyramid assign power
Each width that step 4 is decomposed exposes image and step on each layer of laplacian pyramid of dot matrix grid image more
The image that rapid three width decomposed expose in the weight map gaussian pyramid respective layer of dot matrix grid image more is multiplied, and is assigned
The laplacian pyramid of power;
Step 6, laplacian pyramid fusion
Step 5 is obtained into figure of the entitled some width more on the laplacian pyramid identical layer of exposure dot matrix grid image
As being added;
Step 7, the reconstruct of dot matrix grid image
The laplacian pyramid merged to step 6 carries out inverse turriform and converted, and reconstructs the new dot matrix grid image of a width;
Step 8, dot matrix grid image binaryzation
The dot matrix grid image reconstructed to step 7 carries out local auto-adaptive binary conversion treatment, obtains bianry image;
Step 9, sub-pix Boundary Recognition
The whole pixel boundary of dot matrix grid node in the bianry image that step 8 obtained is identified using 8 connected domain rules;
On the basis of this, the sub-pix border of dot matrix grid node is identified using space moments method;
Step 10, ellipse fitting
The sub-pix border of the dot matrix grid node identified to step 9, elliptical center is gone out using least square method iterative fitting
Coordinate, so as to obtain the coordinate of dot matrix grid node.
2. the collection of dot matrix grid image and identification side in a kind of Sheet metal forming strain measurement according to claim 1
Method, it is characterised in that also include, before the more exposure dot matrix grid images of step 1 shooting are carried out, first focus so that gold
The dot matrix grid of category panel surface can be clearly imaged, and focal length is locked after regulation.
3. the collection of dot matrix grid image and identification side in a kind of Sheet metal forming strain measurement according to claim 1
Method, it is characterised in that when more exposure dot matrix grid images are shot in the step 1, camera is adjusted to black and white screening-mode, protected
It is stable to hold camera, adjusts light exposure, shoots the more than 3 width or 3 width dot matrix grid charts from under-exposure, normal exposure to overexposure
Picture.
4. the collection of dot matrix grid image and identification side in a kind of Sheet metal forming strain measurement according to claim 1
Method, it is characterised in that weight map computational methods are as follows in the step 2:
2.1) dot matrix grid image is exposed to each width captured by step 1 more, be filtered using Laplace operator, will
Filter result takes absolute value, and obtains the contrast factor that each width exposes dot matrix grid image more;
2.2) dot matrix grid image is exposed more to each width captured by step 1, its exposure factor uses equation below meter
Calculate:
Wherein, e represents natural constant, and k represents that kth width exposes dot matrix grid image more, and (i, j) represents pixel position, Ik(i,
J) represent that kth width exposes dot matrix grid image in the gray value of the pixel of (i, j) opening position, E morek(i, j) represents that kth width is more
The exposure factor of the dot matrix grid image in (i, j) opening position is exposed, σ represents kernel function width;
2.3) on the basis of the exposure factor that contrast factor and step 2.2) that step 2.1) is calculated are calculated, use
Equation below calculates the weight factor that each width exposes dot matrix grid image more:
Wherein,Represent that kth width exposes dot matrix grid image in the weight factor of (i, j) opening position, C morek(i, j) is represented
The kth width that step 2.1) is calculated exposes the comparison degree factor of the dot matrix grid image in (i, j) opening position more;
2.4) weight factor that each width calculated step 2.3) exposes dot matrix grid image more is normalized, and obtains
The weight map that each width exposes dot matrix grid image more is obtained, method for normalizing is as follows:
Wherein, WkGray scale of the weight map of (i, j) expression kth width exposure dot matrix grid image more in the pixel of (i, j) opening position
Value, N represent the width number of more exposure dot matrix grid images captured by step 1, and s represents that s width exposes dot matrix grid image more,Represent that the s width that step 2.3) is calculated exposes weight factor of the dot matrix grid image in (i, j) opening position more.
5. the collection of dot matrix grid image and identification side in a kind of Sheet metal forming strain measurement according to claim 4
Method, it is characterised in that the Laplace operator h used in the step 2.2) for:
6. the collection of dot matrix grid image and identification side in a kind of Sheet metal forming strain measurement according to claim 1
Method, it is characterised in that Pyramid transform number of plies L computational methods are as follows in the step 3:
Wherein, r and c represents the line number and columns of more exposure dot matrix grid images respectively, and ln () is represented using natural constant e the bottom of as
Natural logrithm function, min (r, c) represent that the line number of more exposure dot matrix grid images and columns take minimum value function.
7. the collection of dot matrix grid image and identification side in a kind of Sheet metal forming strain measurement according to claim 1
Method, it is characterised in that dot matrix grid image local auto-adaptive binarization method is as follows in the step 8:
8.1) quick binaryzation is carried out using the dot matrix grid image reconstructed by window binaryzation method to step 7, obtains two-value
Image;
8.2) bianry image obtained to step 8.1) carries out connected component labeling, is more than given threshold value for pixel number
τ connected region, further using binaryzation method pixel-by-pixel to all pixels point in connected region again binaryzation:
A) a binary-state threshold is calculated for any pixel point in the connected region more than given threshold value τ:
Wherein, (i, j) represents pixel position, and T (i, j) represents the binaryzation of the pixel of (i, j) opening position in connected region
Threshold value,Represent in the dot matrix grid image that is reconstructed of step 7 with (i,
J) average gray value of the pixel in u × v local windows centered on, u and v represent the length dimension and height of window respectively
Size, m and n represent two integer variables, I '0The dot matrix grid image that (m, n) expression step 7 is reconstructed is in (m, n) opening position
Pixel gray value,Represent step 7 institute
The standard deviation of the grey value profile of the pixel in u × v local windows in the dot matrix grid image of reconstruct centered on (i, j)
Difference, γ and offset is two constants;
B) according to the binary-state threshold that step a) is calculated to pixel again binaryzation:
Wherein, I ' (i, j) represents the pixel of step 8.1) is obtained after binaryzation again bianry image in (i, j) opening position
Gray value, I '0Gray value of the dot matrix grid image that (i, j) expression step 7 is reconstructed in the pixel of (i, j) opening position.
8. the collection of dot matrix grid image and identification side in a kind of Sheet metal forming strain measurement according to claim 7
Method, it is characterised in that the value of threshold tau is τ=10000 in the step 8.2).
9. the collection of dot matrix grid image and identification side in a kind of Sheet metal forming strain measurement according to claim 1
Method, it is characterised in that in the step 10 in each iterative process, calculate each boundary point to the oval spacing being fitted
And standard deviation value sigma, 3sigma boundary point is more than to spacing, is not involved in interative computation next time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710842903.8A CN107726990B (en) | 2017-09-18 | 2017-09-18 | The acquisition of dot matrix grid image and recognition methods in a kind of Sheet metal forming strain measurement |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710842903.8A CN107726990B (en) | 2017-09-18 | 2017-09-18 | The acquisition of dot matrix grid image and recognition methods in a kind of Sheet metal forming strain measurement |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107726990A true CN107726990A (en) | 2018-02-23 |
CN107726990B CN107726990B (en) | 2019-06-21 |
Family
ID=61207482
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710842903.8A Active CN107726990B (en) | 2017-09-18 | 2017-09-18 | The acquisition of dot matrix grid image and recognition methods in a kind of Sheet metal forming strain measurement |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107726990B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108507476A (en) * | 2018-04-27 | 2018-09-07 | 中国石油大学(北京) | Displacement field measurement method, device, equipment and storage medium for material surface |
CN109753766A (en) * | 2018-12-29 | 2019-05-14 | 中链科技有限公司 | Image artifacts verification information processing method and verification method based on block chain |
CN111832433A (en) * | 2020-06-24 | 2020-10-27 | 科络克电子科技(上海)有限公司 | Device for extracting object characteristics from image and working method thereof |
CN112935013A (en) * | 2021-02-10 | 2021-06-11 | 哈尔滨工业大学 | Method for measuring shear strain of viscous medium on plate blank |
CN113112470A (en) * | 2021-04-08 | 2021-07-13 | 西安道法数器信息科技有限公司 | Cold rolling process steel bending detection and analysis method based on artificial intelligence |
CN113155648A (en) * | 2021-05-18 | 2021-07-23 | 苏州大学 | Material microscopic deformation measuring method and system based on impact test |
CN116297336A (en) * | 2023-03-27 | 2023-06-23 | 佛山市顺德区豪锐五金制品有限公司 | Method for detecting defect points on surface of metal sheet for outer layer protection |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20000040421A (en) * | 1998-12-18 | 2000-07-05 | Inst Of Ind Science Pohang | System for measuring camber of slab using pyramid image |
CN101226635A (en) * | 2007-12-18 | 2008-07-23 | 西安电子科技大学 | Multisource image anastomosing method based on comb wave and Laplace tower-shaped decomposition |
CN101447072A (en) * | 2009-01-06 | 2009-06-03 | 覃征 | pyramidal empirical modal analyze image merge method |
CN104050639A (en) * | 2014-06-16 | 2014-09-17 | 西安电子科技大学 | Multi-view dense point cloud data fusion method based on two-sided filter |
CN104202538A (en) * | 2014-09-10 | 2014-12-10 | 浙江广播电视集团 | Double-registration method for different-exposure images in wide dynamic camera |
CN104835130A (en) * | 2015-04-17 | 2015-08-12 | 北京联合大学 | Multi-exposure image fusion method |
-
2017
- 2017-09-18 CN CN201710842903.8A patent/CN107726990B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20000040421A (en) * | 1998-12-18 | 2000-07-05 | Inst Of Ind Science Pohang | System for measuring camber of slab using pyramid image |
CN101226635A (en) * | 2007-12-18 | 2008-07-23 | 西安电子科技大学 | Multisource image anastomosing method based on comb wave and Laplace tower-shaped decomposition |
CN101447072A (en) * | 2009-01-06 | 2009-06-03 | 覃征 | pyramidal empirical modal analyze image merge method |
CN104050639A (en) * | 2014-06-16 | 2014-09-17 | 西安电子科技大学 | Multi-view dense point cloud data fusion method based on two-sided filter |
CN104202538A (en) * | 2014-09-10 | 2014-12-10 | 浙江广播电视集团 | Double-registration method for different-exposure images in wide dynamic camera |
CN104835130A (en) * | 2015-04-17 | 2015-08-12 | 北京联合大学 | Multi-exposure image fusion method |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108507476A (en) * | 2018-04-27 | 2018-09-07 | 中国石油大学(北京) | Displacement field measurement method, device, equipment and storage medium for material surface |
CN108507476B (en) * | 2018-04-27 | 2020-08-07 | 中国石油大学(北京) | Displacement field measuring method, device, equipment and storage medium for material surface |
CN109753766A (en) * | 2018-12-29 | 2019-05-14 | 中链科技有限公司 | Image artifacts verification information processing method and verification method based on block chain |
CN111832433A (en) * | 2020-06-24 | 2020-10-27 | 科络克电子科技(上海)有限公司 | Device for extracting object characteristics from image and working method thereof |
CN111832433B (en) * | 2020-06-24 | 2023-12-29 | 奇点微(上海)光电科技有限公司 | Device for extracting object characteristics from image and working method thereof |
CN112935013A (en) * | 2021-02-10 | 2021-06-11 | 哈尔滨工业大学 | Method for measuring shear strain of viscous medium on plate blank |
CN112935013B (en) * | 2021-02-10 | 2022-01-07 | 哈尔滨工业大学 | Method for measuring shear strain of viscous medium on plate blank |
CN113112470A (en) * | 2021-04-08 | 2021-07-13 | 西安道法数器信息科技有限公司 | Cold rolling process steel bending detection and analysis method based on artificial intelligence |
CN113112470B (en) * | 2021-04-08 | 2023-12-15 | 揭阳市柏亿不锈钢有限公司 | Cold rolling process steel bending detection analysis method based on artificial intelligence |
CN113155648A (en) * | 2021-05-18 | 2021-07-23 | 苏州大学 | Material microscopic deformation measuring method and system based on impact test |
CN116297336A (en) * | 2023-03-27 | 2023-06-23 | 佛山市顺德区豪锐五金制品有限公司 | Method for detecting defect points on surface of metal sheet for outer layer protection |
Also Published As
Publication number | Publication date |
---|---|
CN107726990B (en) | 2019-06-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107726990B (en) | The acquisition of dot matrix grid image and recognition methods in a kind of Sheet metal forming strain measurement | |
CN109903331B (en) | Convolutional neural network target detection method based on RGB-D camera | |
CN112733950A (en) | Power equipment fault diagnosis method based on combination of image fusion and target detection | |
CN108875821A (en) | The training method and device of disaggregated model, mobile terminal, readable storage medium storing program for executing | |
CN108510451B (en) | Method for reconstructing license plate based on double-layer convolutional neural network | |
CN111046880A (en) | Infrared target image segmentation method and system, electronic device and storage medium | |
Zhang et al. | Hyperspectral image denoising with realistic data | |
CN105405138B (en) | Waterborne target tracking based on conspicuousness detection | |
CN112614136A (en) | Infrared small target real-time instance segmentation method and device | |
CN101976436A (en) | Pixel-level multi-focus image fusion method based on correction of differential image | |
CN111178121B (en) | Pest image positioning and identifying method based on spatial feature and depth feature enhancement technology | |
CN113628261B (en) | Infrared and visible light image registration method in electric power inspection scene | |
CN113096023A (en) | Neural network training method, image processing method and device, and storage medium | |
CN107358625B (en) | SAR image change detection method based on SPP Net and region-of-interest detection | |
CN107220945A (en) | The restored method of the pole blurred picture of multiple degeneration | |
CN112507818B (en) | Illumination estimation method and system based on near infrared image | |
CN113378672A (en) | Multi-target detection method for defects of power transmission line based on improved YOLOv3 | |
Abraham et al. | A fuzzy based road network extraction from degraded satellite images | |
CN112924037A (en) | Infrared body temperature detection system and detection method based on image registration | |
CN116763295A (en) | Livestock scale measuring method, electronic equipment and storage medium | |
CN111127355A (en) | Method for finely complementing defective light flow graph and application thereof | |
CN116612272A (en) | Intelligent digital detection system for image processing and detection method thereof | |
CN115761241A (en) | Image enhancement method and application thereof | |
CN112116561B (en) | Power grid transmission line detection method and device based on image processing fusion network weight | |
CN114419443A (en) | Automatic remote-sensing image cultivated land block extraction method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20221026 Address after: 710086 Room 006, F1901, 19/F, Building 4-A, Xixian Financial Port, Fengdong New City Energy Jinmao District, Xixian New District, Xi'an, Shaanxi Patentee after: Xi'an Baochuang Suwei Intelligent Technology Co.,Ltd. Address before: 710065 No. 2 Taibai South Road, Yanta District, Xi'an, Shaanxi Patentee before: XIDIAN University |