CN105678757B - A kind of ohject displacement measuring method - Google Patents
A kind of ohject displacement measuring method Download PDFInfo
- Publication number
- CN105678757B CN105678757B CN201511034482.3A CN201511034482A CN105678757B CN 105678757 B CN105678757 B CN 105678757B CN 201511034482 A CN201511034482 A CN 201511034482A CN 105678757 B CN105678757 B CN 105678757B
- Authority
- CN
- China
- Prior art keywords
- coordinate
- interpolation
- template
- point
- 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.)
- Active
Links
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
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of ohject displacement measuring method, comprise the following steps：1st, any one two field picture M1 after the first two field picture P1 and the first frame is chosen；2nd, gray processing processing is carried out to image；3rd, P2 and M2 are obtained；4th, specific region is outlined in P1 as template T1；5th, the matching area similar to T1 is obtained；6th, pixel matching is realized；7th, each pixel Point correlation coefficient in n*n regions is calculated, chooses the coordinate of maximum for the curved surface that fitting obtains as match point；8th, the corresponding coordinate position in M2 is obtained；9th, using masterplate T1, it is chosen at corresponding template T2 in P2；10th, related coefficients of the T2 on each point is calculated；11st, by compared with coordinate in P1 of coordinate value corresponding to optimal match point and template；12nd, repeat step 4~11 calculates the assembly average of displacement, and final mean annual increment movement result is used as using assembly average.Have the advantages that computational efficiency is high.
Description
Technical field
The present invention relates to a kind of Displacement e measurement technology of digital picture, more particularly to a kind of ohject displacement measurement side
Method, the ohject displacement measuring method can be widely applied to the measurement of displacement, deformation and the strain of object, can also to object into
Row vibration analysis.
Background technology
To test as means, using the method for optical measurement, using study displacement, stress and strain as main task flash ranging
Mechanics, is combined with the cross discipline that multiple subject technologies are integrated, it has been obtained widely in many tests and detection field
Using, and play very important effect.
Loading by means of digital image correlation method (Digital Image Correlation Method, DICM) is used as a kind of optical measurement mechanics
Technology, have the advantages that measurement of full field, it is lossless, to measuring environment require it is relatively low.Quick development is obtained.It is in recent years, right
Substantial amounts of research work has been carried out in digital image correlation technique theory and engineer application, many scholars, has achieved certain grind
Study carefully achievement.With constantly improve, its application field is more and more broader, and more and more important work will be played in engineering field
With.
Related operation is the key issue in digital image correlation technique, improves the measurement accuracy of Digital Image Correlation Method
It is an urgent demand of construction quality Non-Destructive Testing.By lift hardware improve the cost of measurement accuracy be costliness and unrealistic
, and from the angle of optimization algorithm, the thought for improving image sub-pixel position accuracy is economically viable.Whole pixel search
Algorithm it is very ripe and perfect at present, in contrast, calculate time-consuming fewer, and sub-pixel positioning is computational accuracy
Key, and wherein relatively time-consuming link, it directly affects the efficiency, computational accuracy and stability of relevant search.
The whole pixel positioning accuracy of most relevant search algorithm is consistent, simply in calculation amount, computational efficiency, anti-
Some differences of noiseproof feature, stability etc., therefore the principal element of the computational accuracy of decision Digital Image Correlation Method is
Sub-pixel position accuracy, common method have sub-pix gray-level interpolation method, Surface Fitting, univariate search technique, newton-La Pu
Gloomy method, quasi-Newton method, gradient method, frequency domain correlation method, genetic algorithm, neural network algorithm etc., these algorithms are attainable fixed
Position precision pixel from 0.005 to 0.1 differs.
The requirement of gray-level interpolation method carries out sub-pixel reconstruct, simplest ash to discrete gray scale field by the method for interpolation
It is that nearest-neighbor interpolation method and both interpolation method precision of bilinear interpolation are very low to spend interpolation method, and interpolation reconstruction can produce mould
Paste.The higher interpolation method of precision has Lagrange's interpolation, cube interpolation, bicubic spline interpolation, Fifth system.It is logical
Cross the method that interpolation is passed through to discrete gray scale field so that digital picture becomes approximate consecutive image, then carries out smart search,
The position of related coefficient maximum is chosen as Optimum Matching position.This method calculation amount is huge, less efficient.
The content of the invention
The shortcomings that it is an object of the invention to overcome the prior art and deficiency, there is provided a kind of ohject displacement measuring method, should
Ohject displacement measuring method, which is met, measures high-precision requirement in Practical Project, ensure that the reasonability of computational efficiency.
The purpose of the present invention can be achieved through the following technical solutions：A kind of ohject displacement measuring method, it is main include with
Lower step：
S1：The position of fixed image capture device, then gathers the continuous of target to be measured using image capture device and moves
Motion video；The position of image capture device can not change, to obtain the image of reaction target movement；Choose the first two field picture
(P1) any one two field picture (M1) and after the first frame；
S2：If image is coloured image, gray processing processing first is carried out to it；
S3：Using interpolation algorithm to P1 and M1 into k times of row interpolation, P2 and M2 are respectively obtained after interpolation；
S4：A specific region comprising obvious characteristic is outlined in P1 as template (T1), writes down the upper left of Prototype drawing T1
Coordinate (x of the angle point in P10,y0)；
S5：Matched using climbing method in M1, obtain the matching area substantially similar with T1；
S6:In region obtained in the previous step, using SDA SSD algorithms accurately matching obtain the coordinate (x of template image1,
y1), realize pixel matching；
S7:With (x1,y1) centered on, the related coefficient of each pixel in n*n regions is calculated, utilizes the phase relation of acquisition
Number carries out surface fitting, chooses the coordinate of maximum of fitting rear curved surface as match point (x2,y2)；
S8：Matching coordinate position (x in the M1 that step S7 is obtained2,y2) be mapped in M2, obtain corresponding in M2
Coordinate position (x3,y3)；
S9：Using the masterplate figure (T1) chosen in P1, its corresponding Prototype drawing (T2) in P2 is chosen；
S10：In M2, with (x3,y3) it is starting point, repeat step S6, finds the coordinate of optimal match point, with the coordinate
Centered on, the rectangular area of m*m is chosen, calculates related coefficients of the T2 on each point；
S11：Surface fitting is carried out using the related coefficient obtained in previous step, chooses the coordinate of the maximum after fitting
(x4,y4) optimal match point is used as, and the coordinate value is mapped back into corresponding coordinate value (x in M15,y5), and by (x5,y5) and mould
Coordinate (the x in P1 of plate0,y0) be compared, to realize that the precise displacement of target measures (Δ x, Δ y)；
S12：Above step S4 to step S11 circulations are performed p times, different Prototype drawings is chosen every time, calculates displacement
Assembly average, final mean annual increment movement result is used as using the value.
The calculation formula that the NCC algorithms use of related coefficient is calculated in above step S5, S6, S10 is as follows：
In above formula, rxyBe with point (x, y) for origin m*n subregions with the related coefficient between template image, Sx,y
What is represented is with the m*n subregions that point (x, y) is origin interception, S in image to be matchedx,y(i, j) refers to coordinate on the subregion
The gray value of (i, j) point,Refer to the average value of gray scale on the subregion.Tx,y(i, j) refers to the ash of coordinate (i, j) point on masterplate
Angle value,Refer to the average value of the gray scale in template.M, n represent the columns and line number of template respectively.
In above step S7, S11, carrying out the method for surface fitting has conicoid fitting, cubic surface fitting process, height
This Surface Fitting, two-dimentional Lagrangian method surface fitting；Conicoid fitting is taken under normal circumstances.Quadratic surface is intended
The Binary quadratic functions of legal use are as follows：
r(xi,yi)=a0+a1xi+a2yi+a3x2+a4xiyi+a5yi 2,
In formula, r (xi,yi) represent Prototype drawing in coordinate (xi,yi) related coefficient that is calculated of place, coefficient a0~a5For this
Quadric coefficient.The coordinate formula of quadric maximum is as follows：
In formula, x, y represent the abscissa and ordinate of quadric maximum, coefficient a respectively0~a5For the secondary song
The coefficient in face.
The formula that coordinate maps in above step S8 is as follows：
x′3=(x2-1)*n+1
y′3=(y2- 1) * n+1,
In formula, coordinate (x2,y2) the matching coordinate position of the template that represents to obtain in step S7 in M1, coordinate (x'3,
y'3) denotation coordination mapping as a result, coordinate position (x3,y3) represent template corresponding coordinate position in M2.
The specific method of above step S9 is as follows：First by the upper left angle point of Prototype drawing T1 P1 coordinate (x0,y0) mapping
Coordinate into P2, is denoted as (x0',y0'), while coordinate of the Prototype drawing T1 bottom rights angle point in P1 is chosen, and map that to P2
In coordinate, be denoted as (x0",y0"), then template T2 is taken as coordinate (x0',y0') and coordinate (x0",y0Rectangle region between ")
Domain.Coordinate mapping equation is as follows：
x2=(x1-1)*k+1
y2=(y1- 1) * k+1,
Wherein, coordinate (x1,y1) and (x2,y2) it is respectively corresponding coordinate in P1 and P2, k represents interpolation in step s3
Multiple.
In above step S11, coordinate mapping equation is as follows：
In formula, coordinate (x4,y4) represent the total best match coordinates of M2, coordinate (x5,y5) represent that the best match in M1 is sat
Mark, it is obtained by above-mentioned mapping equation, and k represents the multiple of interpolation in step s3.
In above step S11, displacement calculation formula is as follows：
In formula, coordinate (x5,y5) represent M1 in best match coordinate, coordinate (x0,y0) represent Prototype drawing T1 in step S4
Coordinate of the upper left angle point in P1, Δ x represents precise displacement of the target on abscissa direction, and Δ y represents that target is sat vertical
Mark the precise displacement on direction.
The value of k, n, m and p in step S3, S7, S10 and S12 can be any positive integer, and value more macrooperation amount is more
Greatly, value range is preferably [1,10].
In step S3, S7, S8, S9, S10 and S11, the sub-pixel interpolation algorithm and curved surface of classical relevant search are intended
It is legal to combine, drastically increase the precision of sub-pixel displacement measurement；At the same time in the image before interpolation and after interpolation
Matched, significantly reduce computation complexity.
The purpose of the present invention can also be achieved through the following technical solutions：A kind of ohject displacement measuring method, including it is following
Step：(1) the continuous dislocation image of object to be measured is gathered using image capture device；(2) using interpolation algorithm to being gathered
Image into row interpolation；(3) Prototype drawing is chosen in first frame, then using climbing method and SDA SSD algorithms find template rear
Rough coordinates position in continuous image；(4) it is fitted, obtains similitude curved surface, ask for curved surface peak coordinate, with artwork
In coordinate be compared, calculate displacement；(5) repeat (3)~(4) step several times, calculate the average value of displacement as most
Terminate fruit.The method of the present invention is repeatedly chosen Prototype drawing and is measured in engineer application, while image before interpolation and after interpolation
In calculated, and combine interpolation algorithm and Algorithm for Surface Fitting are ingenious, improve the efficiency of calculating, realize essence
True sub-pixel displacement measurement.
The present invention is had the following advantages relative to the prior art and effect：
Surface Fitting assumes that the correlation matrix of whole pixel displacement relevant search result and its consecutive points can be fitted to
Continuous curve surface, then using the center of the extreme point position of curved surface image subsection as after deforming.Curved surface for fitting
Type has quadratic surface, cubic surface, Gauss curved and the Lagrangian curved surface of two dimension etc..The method computational accuracy of surface fitting
Height, noise resisting ability are stronger.The present invention Displacement is measured in gray-level interpolation method and Surface Fitting dexterously tie
Altogether so that the precision of calculating is greatly improved；Pass through calculation template on the picture first before interpolation at the same time
The advantages of matched position, is then then transferred to the exact position of calculation template figure on the picture after interpolation, this mode is
Picture before movement is matched, and the size of Prototype drawing and artwork is all smaller, and computational efficiency is higher, compared to directly after interpolation
Calculation template figure on picture, computational efficiency are greatly improved；And choose multiple matching figures, last counting statistics it is equal
Value, to obtain more accurate result.
Brief description of the drawings
Fig. 1 is the specific implementation flow chart of hill-climbing algorithm.
Fig. 2 is the specific implementation flow chart of the present invention.
Embodiment
With reference to embodiment and attached drawing, the present invention is described in further detail, but embodiments of the present invention are unlimited
In this.
Embodiment
As shown in Fig. 2, a kind of ohject displacement measuring method, specifically includes following steps：
S1：The position of fixed image capture device, then gathers the continuous of target to be measured using image capture device and moves
Motion video；The position of image capture device can not change, to obtain the image of reaction target movement；Choose the first two field picture
(P1) any one two field picture (M1) and after the first frame；And in order to obtain higher measurement accuracy, acquired photo should
There is sufficiently high quality.
S2：If image is coloured image, gray processing processing first is carried out to it；
S3：Using interpolation algorithm to P1 and M1 into k times of row interpolation, P2 and M2 are respectively obtained after interpolation；What can be selected inserts
Value-based algorithm is very much, can obtain the higher picture of precision, the multiple of interpolation using cube sum algorithm under normal circumstances
10 times should be generally taken depending on the actual needs of computational efficiency.
S4：The specific region comprising obvious characteristic is outlined in P1 as template (T1), writes down the upper left corner of Prototype drawing T1
Coordinate (x of the point in P10,y0)；The big I of template is generally taken as 41*41 pixels depending on the actual needs of computational efficiency
Or 51*51 pixels.
S5：Matched using climbing method in M1, obtain the matching area substantially similar with T1；；
S6:In region obtained in the previous step, using SDA SSD algorithms accurately matching obtain the coordinate (x of template image1,
y1), realize pixel matching；
S7:With (x1,y1) centered on, the related coefficient of each pixel in n*n regions is calculated, utilizes the phase relation of acquisition
Number carries out surface fitting, chooses the coordinate of maximum of fitting rear curved surface as match point (x2,y2)；The choosing of curved surface fitting method
Taking can be depending on the requirement of specific computational efficiency, under normal circumstances, and choosing conicoid fitting can meet the requirements.
S8：Matching coordinate position (x in the M1 that step S7 is obtained2,y2) be mapped in M2, obtain corresponding in M2
Coordinate position (x3,y3)；
S9：Using the masterplate figure (T1) chosen in P1, its corresponding Prototype drawing (T2) in P2 is chosen；
S10：In M2, using T2 as Prototype drawing, with (x3,y3) it is starting point, repeat step S6, finds optimal match point
Coordinate, centered on the coordinate, chooses the rectangular area of m*m, calculates related coefficients of the T2 on each point；By step S8 institutes
Matched position (the x of acquisition2,y2) very close to actual matched position, so this step is searching for whole pixel using step S6
The coordinate speed of point Optimum Matching point is very fast.
S11：Surface fitting is carried out using the related coefficient of acquisition, chooses the coordinate (x of the maximum after fitting4,y4) make
For optimal match point, and the coordinate value is mapped back into corresponding coordinate value (x in M15,y5), and by (x5,y5) exist with template
Coordinate (x in P10,y0) be compared, to obtain the precise displacement of target (Δ x, Δ y)；
S12：Repeat above S4~S11 steps p times, choose different Prototype drawings every time, calculate the statistical average of displacement
Value, final mean annual increment movement result is used as using the value；It is specific to need repetition how many times be depending on the computational efficiency being actually subjected to.
The performance of search by hill climbing method in above-mentioned steps S5 is by masterplate and image size to be matched, the gray scale of template image point
The very multifactor influences such as cloth, the algorithm for calculating related coefficient.As shown in Figure 1, step S5 can be further divided into：
S5.1：It is all in selection climbing method initially to climb the mountain according to the relative size relation of subgraph to be matched and masterplate subgraph
Horizontal and vertical spacing between starting point, generates all starting points of climbing the mountain in image to be matched.If the target actually measured is moved
Dynamic scope is smaller, all initial starting points of climbing the mountain can be set in coordinate (x0,y0) near, to improve the speed climbed the mountain.In order to
Enough more accurately reaction artworks should be uniformly distributed as far as possible with the degree of correlation between masterplate subgraph, selected starting point of climbing the mountain, and
Distance between starting point is moderate.
S5.2：The related coefficient of all starting points of climbing the mountain is calculated, and they are reversed.Risen by the Rational choice of S5.1
Point, it is believed that there are certain positive correlation the distance between with the maximum of related coefficient with it for the related coefficient size of starting point
Relation, examines these starting points quickly to find target according to related coefficient backward.
S5.3：According to the requirement to matching accuracy, a suitable related coefficient upper limit is selected, was searched for for terminating
Journey.In addition, in S5.1 step Rational choices on the basis of starting point of climbing the mountain, it is believed that related coefficient too small point with target point away from
It is too far away, can directly it give up.The selection of this lower limit is closely related with the selection of starting point in S5.1, is taken in embodiment
0.25。
S5.4：After determining current point, the related coefficient of each point in surrounding 3*3 matrixes is calculated successively.If there is related coefficient
The point of bigger, then be treated as new starting point and continue to search for, and enters in next step if not.
S5.5：Maximum correlation coefficient that S5.4 is found is judged either with or without the upper limit set more than step S5.3, if without if
Calculate and check next starting point of climbing the mountain, otherwise it is assumed that satisfactory point has been found, directly terminate hill climbing process.
Above-described embodiment is the preferable embodiment of the present invention, but embodiments of the present invention and from above-described embodiment
Limitation, other any Spirit Essences without departing from the present invention with made under principle change, modification, replacement, combine, simplification,
Equivalent substitute mode is should be, is included within protection scope of the present invention.
Claims (4)
1. a kind of ohject displacement measuring method, it is characterised in that comprise the following steps：
The position of S1, fixed image capture device, then gather the continuous moving figure of target to be measured using image capture device
Picture；Choose any one two field picture M1 after the first two field picture P1 and the first frame；
If S2, image are coloured image, gray processing processing first is carried out to it；
S3, using interpolation algorithm to P1 and M1 into k times of computing of row interpolation, respectively obtain P2 and M2 after interpolation；
S4, outline a specific region comprising obvious characteristic as template T1 in P1；
S5, matched using climbing method in M1, obtains the matching area substantially similar with T1；
S6, in region obtained in the previous step, using SDA SSD algorithms accurately matching obtain the coordinate (x of template image1,y1),
Realize pixel matching；
S7, with (x1,y1) centered on, calculate the related coefficient of each pixel in n*n regions, using acquisition related coefficient into
Row surface fitting, chooses the coordinate of maximum for the curved surface that fitting obtains as match point (x2,y2)；
Matching coordinate position (x in S8, the M1 for obtaining step S72,y2) be mapped in M2, obtain the corresponding coordinate in M2
Position (x3,y3)；
S9, using the masterplate T1 chosen in P1, choose its corresponding template T2 in P2；
S10, in M2, using T2 as Prototype drawing, with (x3,y3) it is starting point, repeat step S6, finds the coordinate of optimal match point,
Centered on the coordinate, the rectangular area of m*m is chosen, calculates related coefficients of the T2 on each point；
S11, carry out surface fitting, the coordinate (x of the maximum for the curved surface that selection fitting obtains using the related coefficient of acquisition4,y4)
Corresponding coordinate value (x in M1 is mapped back as optimal match point, and by the coordinate value5,y5), and by (x5,y5) exist with template
Coordinate in P1 is compared；
S12, perform the step S4~step S11 circulation p times, the assembly average of displacement is calculated, with assembly average
As final mean annual increment movement result.
2. ohject displacement measuring method as claimed in claim 1, it is characterised in that k in step S3, S7, S10 and S12,
N, the value of m and p is any positive integer.
3. ohject displacement measuring method as claimed in claim 2, it is characterised in that the value range of k, n, m and p for [1,
10]。
4. ohject displacement measuring method as claimed in claim 1, it is characterised in that in step S3, S7, S8, S9, S10 and S11
In, sub-pixel interpolation algorithm and Surface Fitting are combined, while is matched in the image before interpolation and after interpolation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511034482.3A CN105678757B (en) | 2015-12-31 | 2015-12-31 | A kind of ohject displacement measuring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511034482.3A CN105678757B (en) | 2015-12-31 | 2015-12-31 | A kind of ohject displacement measuring method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105678757A CN105678757A (en) | 2016-06-15 |
| CN105678757B true CN105678757B (en) | 2018-04-13 |
Family
ID=56190053
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511034482.3A Active CN105678757B (en) | 2015-12-31 | 2015-12-31 | A kind of ohject displacement measuring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105678757B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107341773A (en) * | 2017-06-13 | 2017-11-10 | 浙江大学 | A kind of vignetting bearing calibration of multispectral image |
| CN107590502B (en) * | 2017-09-18 | 2020-05-22 | 西安交通大学 | Full-field dense point fast matching method |
| CN109672818B (en) * | 2017-10-16 | 2020-12-22 | 华为技术有限公司 | Method and device for adjusting image quality |
| CN108387184A (en) * | 2018-03-20 | 2018-08-10 | 山西和信基业科技股份有限公司 | A kind of measurement method and system of deflection of bridge span |
| CN108871185B (en) * | 2018-05-10 | 2020-12-29 | 苏州大学 | Method, device and equipment for detecting parts and computer readable storage medium |
| CN109883333A (en) * | 2019-03-14 | 2019-06-14 | 武汉理工大学 | A kind of non-contact displacement strain measurement method based on characteristics of image identification technology |
| CN110146024B (en) * | 2019-06-06 | 2023-03-14 | 重庆大学 | Double-precision displacement measurement method based on self-adaptive search |
| CN110608676B (en) * | 2019-08-26 | 2021-10-26 | 中国科学院重庆绿色智能技术研究院 | Shear displacement measurement method, shear displacement measurement module and multi-parameter combined monitoring system |
| CN111829439B (en) * | 2020-07-21 | 2021-06-25 | 中山大学 | High-precision translation measuring method and device |
| CN113947689B (en) * | 2021-09-30 | 2023-10-10 | 西安交通大学 | Method for rapidly measuring large movement of structure based on computer vision |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101569543A (en) * | 2008-04-29 | 2009-11-04 | 香港理工大学 | Two-dimension displacement estimation method of elasticity imaging |
| CN103729849A (en) * | 2013-12-31 | 2014-04-16 | 南京航空航天大学 | Method for calculating digital image morphing initial value |
| CN105203033A (en) * | 2015-10-08 | 2015-12-30 | 重庆平伟实业股份有限公司 | Method for measuring in-plane displacement of MEMS |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4909859B2 (en) * | 2007-09-28 | 2012-04-04 | 株式会社日立ハイテクノロジーズ | Inspection apparatus and inspection method |
| US9147251B2 (en) * | 2012-08-03 | 2015-09-29 | Flyby Media, Inc. | Systems and methods for efficient 3D tracking of weakly textured planar surfaces for augmented reality applications |
-
2015
- 2015-12-31 CN CN201511034482.3A patent/CN105678757B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101569543A (en) * | 2008-04-29 | 2009-11-04 | 香港理工大学 | Two-dimension displacement estimation method of elasticity imaging |
| CN103729849A (en) * | 2013-12-31 | 2014-04-16 | 南京航空航天大学 | Method for calculating digital image morphing initial value |
| CN105203033A (en) * | 2015-10-08 | 2015-12-30 | 重庆平伟实业股份有限公司 | Method for measuring in-plane displacement of MEMS |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105678757A (en) | 2016-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105678757B (en) | A kind of ohject displacement measuring method | |
| CN106097348A (en) | A kind of three-dimensional laser point cloud and the fusion method of two dimensional image | |
| CN103218812B (en) | Method for rapidly acquiring tree morphological model parameters based on photogrammetry | |
| CN104794713B (en) | Chamber crop digitalized image method based on ARM and binocular vision | |
| CN106600553A (en) | DEM super-resolution method based on convolutional neural network | |
| CN107016649A (en) | A kind of vision data complementing method estimated based on local low-rank tensor | |
| CN105046743A (en) | Super-high-resolution three dimensional reconstruction method based on global variation technology | |
| CN104240264A (en) | Height detection method and device for moving object | |
| CN110187143A (en) | A kind of chromatography PIV reconstructing method and device based on deep neural network | |
| CN113343822B (en) | Light field saliency target detection method based on 3D convolution | |
| CN105957107A (en) | Pedestrian detecting and tracking method and device | |
| CN109859178A (en) | A kind of infrared remote sensing image real-time target detection method based on FPGA | |
| CN106600632A (en) | Improved matching cost aggregation stereo matching algorithm | |
| CN104268880A (en) | Depth information obtaining method based on combination of features and region matching | |
| CN114396877B (en) | Intelligent three-dimensional displacement field and strain field measurement method for mechanical properties of materials | |
| CN113506372A (en) | Environment reconstruction method and device | |
| CN115326025B (en) | Binocular image measurement and prediction method for sea waves | |
| CN107590347A (en) | One kind is based on the identification of matching isolated point and delet method and the system of designing a model | |
| CN116071424A (en) | Fruit space coordinate positioning method based on monocular vision | |
| CN113822825B (en) | Optical building target three-dimensional reconstruction method based on 3D-R2N2 | |
| CN103310461B (en) | Based on the image edge extraction method of block Kalman filtering | |
| CN106018198A (en) | Bubble particle size back calculation method | |
| CN108507476A (en) | Displacement field measurement method, device, equipment and storage medium for material surface | |
| CN111739163A (en) | Unmanned aerial vehicle image data modeling method for intelligent acceptance of open stope | |
| CN115638731B (en) | Super-resolution-based vibrating table test computer vision displacement measurement method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |