CN109902694A - A kind of extracting method of square hole feature - Google Patents
A kind of extracting method of square hole feature Download PDFInfo
- Publication number
- CN109902694A CN109902694A CN201910150080.1A CN201910150080A CN109902694A CN 109902694 A CN109902694 A CN 109902694A CN 201910150080 A CN201910150080 A CN 201910150080A CN 109902694 A CN109902694 A CN 109902694A
- Authority
- CN
- China
- Prior art keywords
- square hole
- point
- straight line
- point set
- fitting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012216 screening Methods 0.000 claims description 9
- 238000003708 edge detection Methods 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- ZFXYFBGIUFBOJW-UHFFFAOYSA-N theophylline Chemical compound O=C1N(C)C(=O)N(C)C2=C1NC=N2 ZFXYFBGIUFBOJW-UHFFFAOYSA-N 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 9
- 238000005259 measurement Methods 0.000 abstract description 7
- 238000004422 calculation algorithm Methods 0.000 abstract description 5
- 238000003754 machining Methods 0.000 abstract description 3
- 238000012360 testing method Methods 0.000 abstract description 3
- 239000012535 impurity Substances 0.000 abstract 1
- 238000012545 processing Methods 0.000 description 4
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 244000291564 Allium cepa Species 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a kind of extracting methods of square hole feature, utilize the left and right image of two CCD camera measure system acquisition square hole feature;Extract the two-dimensional points of square hole contour edge, the three-dimensional figure picture point of square hole contour edge is obtained again, semicircle feature contour point, the straight-segment profile point that impurity point fits square hole are picked by RANSAC algorithm to three-dimensional space point information, and the square hole profile obtained by Accurate Curve-fitting, final calculate obtain square hole characteristic parameter: square hole center, width and length.This method measurement accuracy can reach micron order, and time of measuring can satisfy the manufacturing testing requirements of the Precision Machinings such as automobile industry in Millisecond.
Description
Technical field
The present invention relates to optical three-dimensional measurement fields, and in particular to a kind of extracting method of square hole feature.
Background technique
In the production of part, process, due to being limited by equipment machining accuracy itself, production process control not
In place, inevitably there is deviation in the influence of external environmental change etc., the manufacture size and design size of part;Guarantee that dimensional discrepancy exists
In controllable range, there is very important effect for the guarantee and control of overall structure quality, adds especially for precision
Work, which manufactures industry, has pole for the processing and manufacturing precision of components such as automobile, aircraft, high-speed rail components and Auto-body manufacturing
Its stringent size requirement, it is therefore desirable to which efficient measurement means obtain the data of these part size deviations, guarantee whole matter
Amount.
Square hole is characterized in processing structure extremely common in process of manufacture, and the basic components of splicing, installation, because
This other side's hole characteristic is accurately extracted, analyzes size, there is highly important realistic meaning, at present for square hole feature extraction
Method mainly use edge detection operator carry out the extraction of square hole contour edge, such as Canny edge detection operator, the edge Sobel
Detective operators, Priwitt edge detection operator etc., but there are many result noise for carrying out edge extracting, are unable to satisfy to precision
The testing requirements of workpieces processing, it is therefore desirable to carry out edge fitting, common edge fitting method, such as least square method can not
It carries out miscellaneous point to reject, is easy to happen fitting mistake, fitting result inaccuracy.CN201710462540.5 discloses a kind of workpiece circle
The matching process of arc Edge Feature Points is fitted circular arc using RANSAC algorithm, obtains circle contour, and this method is intended to solve
Certainly there is notch in circular arc works in Binocular vision photogrammetry;But method disclosed in application is only to two-dimensional surface circular arc
It is fitted, carries out left images matching later, but the space circular arc profile after matching is not processed;
In Precision Machining manufacturing field, measurement accuracy often requires that micron order, and existing method measurement accuracy, which is unable to satisfy, to be wanted
It asks.
Summary of the invention
In order to solve the above technical problem, the present invention provides a kind of extracting methods of square hole feature, and measurement accuracy can
Reach 0.001-0.01mm, time of measuring can satisfy the requirement of high-precision detection, technical solution of the present invention is such as in Millisecond
Under:
A kind of extracting method of square hole feature, includes the following steps:
Step 1: utilizing the left and right image of two CCD camera measure system acquisition square hole feature;
Step 2: carrying out image preprocessing to the left and right image, the square hole contour edge two dimension of left and right image is extracted
Point;
Step 3: the square hole contour edge two-dimensional points in left and right image are transformed into three-dimensional space using polar curve matching process
Between, the three-dimensional point coordinate of square hole profile is obtained, point set N is denoted asj, j=1,2 ..., m, m is the number of the three-dimensional point of square hole profile;
Step 4: at random from the point set NjIn take at least two point, be denoted as reconnaissance to be fitted, carry out straight line fitting, obtain
Fitting a straight line I;
Step 5: the angle of the direction vector of digital simulation straight line I and square hole theory longitudinal direction vector;
When the theoretical length of square hole four edges is equal, wherein any a line it will be defined as theoretical long side, hung down with it
Straight side is theoretical short side;
If angle is 0 °~10 °, fitting a straight line I is the long side of square hole;
If angle is 85 °~95 °, fitting a straight line I is the short side of square hole;
If angle is other angles, return step four;
Record the long side or short side type of the fitting a straight line I;
Step 6: calculating Dj, j=1,2 ..., m;
DjFor point set NjDistance of the middle all the points to the fitting a straight line I;
Step 7: comparing DjWith preset threshold T1, D will be metj< T1Point be labeled as the unilateral space intra-office point of square hole;
Step 8: counting the quantity of the unilateral space intra-office point of the square hole, M value and three-dimensional coordinate information are recorded;
Step 9: carrying out q iteration to step 4~step 8;
The maximum value in M value is chosen, M is denoted asmax, it is final for recording the unilateral space intra-office point of the square hole corresponding to it
The unilateral image three-dimensional point set of square hole, is denoted as the image three-dimensional point set P of a lineh', h=1,2 ..., Mmax;
Step 10: from the point set NjMiddle rejecting image three-dimensional point set Ph' interior all the points, obtain point set Nj', j=1,
2 ..., m ', m ' are the number that square hole profile rejects remaining point after point set corresponding to a line;
From the point set Nj' in randomly select at least two point, be denoted as reconnaissance to be fitted, straight line fitting carried out, as fitting
Straight line I is denoted as point set P according to the corresponding three-dimensional point in method screening Article 2 side in step 5~step 9h″;
Step 11: from the point set Nj' middle rejecting point set Ph" corresponding point, obtains the tripleplane of second hole profile
Point set Nj", the number of remaining three-dimensional point after the point set of j=1,2 ..., m ", m " for two sides of square hole profile rejecting;
From the point set Nj" in randomly select at least two point, be denoted as reconnaissance to be fitted, fitting a straight line, as fitting a straight line
I is denoted as point set P according to the corresponding three-dimensional point in method screening Article 3 side in step 5~step 9h″′;
Step 12: from the point set NjIt is " middle to reject point set Ph" ' corresponding point, obtains point set Nj" ', j=1,2 ...,
M " ', m " ' for square hole profile reject square hole three edge point collection after remaining three-dimensional point number;
From the point set Nj" ' in randomly select at least two point, be denoted as reconnaissance to be fitted, fitting a straight line is straight as fitting
Line I is denoted as point set P according to the corresponding three-dimensional point in method screening Article 4 side in step 5~step 9h″″;
Step 13: respectively to point set Ph', point set Ph", point set Ph" ', point set Ph" " carries out straight line fitting, obtains first
Straight line L1, second straight line side L2, third straight line L3, the 4th straight line L4;
Solve first straight line side L1, second straight line side L2, third straight line L3, the 4th straight line L4The point intersected two-by-two, note
For the vertex of square hole: A (x1,y1,z1),B(x2,y2,z2),C(x3,y3,z3),D(x4,y4,z4);
Solve centre coordinate, the length and width of square hole.
Further, step 5 is replaced are as follows: the direction vector of digital simulation straight line I and square hole theory short side direction vector
Angle;
When the theoretical length of square hole four edges is equal, wherein any a line it will be defined as theoretical short side, with the side
Two vertical sides are theoretical long side;
If angle is 0 °~10 °, fitting a straight line I is the short side of square hole;
If angle is 85 °~95 °, fitting a straight line I is the long side of square hole;
If angle is other angles, return step five;
Record the long side or short side type of the fitting a straight line I.
Further, in step 8 further include: calculate Ratio '=M/m, preset ratio threshold value H, the preset ratio threshold value H
Value 0.2~0.5, if Ratio ' >=H, this time the unilateral fitting of square hole is correct, saves this M value and three-dimensional coordinate letter
Breath;Otherwise, this M value is not saved.
Further, the number of iterations q calculation formula is as follows:
P=1- (1-Ratio1'n)q;
In formula, n is the number of reconnaissance to be fitted;P is that n reconnaissances to be fitted are the long side of square hole or the space office of short side
The probability of interior point, Ratio1' is the ratio of the M and m that acquire for the first time.
Further, the threshold value T1=0~0.2mm.
It further, is least square method, Gauss curve fitting, Chebyshev's approximating method to the method that straight line is fitted.
Further, the left and right image is grayscale image.
Further, described image pretreatment includes gaussian filtering, binary image, edge detection.
RANSAC (Random Sample Consensus) algorithm is a kind of basis proposed by Fischler and Bolles
The input data set of one group of observation data with noise generates one by constantly randomly choosing the sample data set of data set
A model estimation, the algorithm random selection go out a sample set, use the computation model ginseng of this subset of minimum variance estimate
Number, is then calculated all sample datas and the deviation of the model, is compared using pre-set a threshold values and deviation, when inclined
When difference is less than threshold values, which belongs to sample point in model, i.e. " the intra-office point " of data, and records;It otherwise is the outer sample of model
This point, i.e. " point not in the know " of data, and record, repeat this process.It repeats all to record current optimal model parameter each time,
So-called is most preferably exactly sample point i.e. " point not in the know " accounting maximum in model.After repeating, optimum model parameter is exactly final
Model parameter estimation value.
Method provided by the present application is to carry out miscellaneous point to square hole contoured three-dimensional spatial point by RANSAC algorithm to reject;Successively
The fitting for carrying out four straight lines obtains high-precision square hole three-D profile information, increases plane restriction, laggard to space circle is fitted
The verifying of row space radius of circle, reduces cycle-index, improves detection accuracy, efficiency, finally obtains the accurate square hole feature ginseng of result
Number;This method measurement accuracy can reach 0.001-0.01mm, and time of measuring can satisfy the precisions such as automobile industry in Millisecond
The testing requirements of processing manufacturing industry.
Detailed description of the invention
Fig. 1 is the flow chart of the extracting method of square hole feature provided by the invention.
Specific embodiment
Technical solution of the present invention is described in detail below by way of specific embodiment:
A kind of extracting method of square hole feature, includes the following steps:
Step 1: the image is grayscale image using the left and right image of two CCD camera measure system acquisition square hole feature;
Step 2: carrying out image preprocessing to left and right image, the square hole contour edge two-dimensional points of left and right image are extracted;Figure
As pretreated method may is that gaussian filtering, binary image, edge detection;
Step 3: the square hole contour edge two-dimensional points in left and right image are transformed into three-dimensional space using polar curve matching process
Between, the three-dimensional point coordinate of square hole profile is obtained, point set N is denoted asj, j=1,2 ..., m, m is the number of the three-dimensional point of square hole profile;
Step 4: at random from point set NjIn take at least two point, be denoted as reconnaissance to be fitted, carry out straight line fitting, be fitted
Straight line I;When it is implemented, the method that straight line is fitted are as follows: least square method, Gauss curve fitting or Chebyshev's approximating method;
Step 5: the angle of the direction vector of digital simulation straight line I and square hole theory longitudinal direction vector;
When the theoretical length of square hole four edges is equal, wherein any a line it will be defined as theoretical long side, hung down with it
Straight side is theoretical short side;
If angle is 0 °~10 °, fitting a straight line I is the long side of square hole;
If angle is 85 °~95 °, fitting a straight line I is the short side of square hole;
If angle is other angles, return step four;
Record the long side or short side type of fitting a straight line I;
Step 6: calculating Dj, j=1,2 ..., m;
DjFor point set NjDistance of the middle all the points to fitting a straight line I;
Step 7: comparing DjWith preset threshold T1, D will be metj< T1Point be labeled as the unilateral space intra-office point of square hole;Make
For one embodiment of the present of invention, threshold value T1=0~0.2mm;
Step 8: the quantity of the statistics unilateral space intra-office point of square hole, records M value and three-dimensional coordinate information;It is preferred that also wrapping
Include, calculate Ratio '=M/m, preset ratio threshold value H, the preset ratio threshold value H value 0.2~0.5, if Ratio ' >=H,
Then this time the unilateral fitting of square hole is correct, saves this M value and three-dimensional coordinate information;Otherwise, this M value is not saved;
Step 9: carrying out q iteration to step 4~step 8;As an embodiment of the present invention, q passes through following public
Formula calculates:
P=1- (1-Ratio1'n)q;
In formula, n is the number of reconnaissance to be fitted;P is that n reconnaissances to be fitted are the long side of square hole or the space office of short side
The probability of interior point, Ratio1' is the ratio of the M and m that acquire for the first time.
The maximum value in M value is chosen, M is denoted asmax, it is final for recording the unilateral space intra-office point of the square hole corresponding to it
The unilateral image three-dimensional point set of square hole, is denoted as the image three-dimensional point set P of a lineh', h=1,2 ..., Mmax;
Step 10: from point set NjMiddle rejecting image three-dimensional point set Ph' interior all the points, obtain point set Nj', j=1,2 ...,
M ', m ' are the number that square hole profile rejects remaining point after point set corresponding to a line;
From point set Nj' in randomly select at least two point, be denoted as reconnaissance to be fitted, straight line fitting carried out, as fitting a straight line
I is denoted as point set P according to the corresponding three-dimensional point in method screening Article 2 side in step 5~step 9h″;
Step 11: from point set Nj' middle rejecting point set Ph" corresponding point, obtains tripleplane's point set of second hole profile
Nj" ,=1,2 ..., ", m " are the number that square hole profile rejects remaining three-dimensional point after the point set on two sides;
From point set Nj" in randomly select at least two point, be denoted as reconnaissance to be fitted, fitting a straight line is pressed as fitting a straight line I
According to the corresponding three-dimensional point in method screening Article 3 side in step 5~step 9, it is denoted as point set Ph″′;
Step 12: from point set NjIt is " middle to reject point set Ph" ' corresponding point, obtains point set Nj" ' ,=1,2 ..., " ', m " '
For the number of remaining three-dimensional point after three edge point collection of square hole profile rejecting square hole;
From point set Nj" ' in randomly select at least two point, be denoted as reconnaissance to be fitted, fitting a straight line, as fitting a straight line I,
According to the corresponding three-dimensional point in method screening Article 4 side in step 5~step 9, it is denoted as point set Ph″″;
Step 13: respectively to point set Ph', point set Ph", point set Ph" ', point set Ph" " carries out straight line fitting, obtains first
Straight line L1, second straight line side L2, third straight line L3, the 4th straight line L4;
Solve first straight line side L1, second straight line side L2, third straight line L3, the 4th straight line L4The point intersected two-by-two, note
For the vertex of square hole: A (x1,y1,z1),B(x2,y2,z2),C(x3,y3,z3),D(x4,y4,z4);
Solve centre coordinate, the length and width of square hole.
As one embodiment of the present invention, step 5 also be can be replaced: the direction vector of digital simulation straight line I and side
The angle of hole theory short side direction vector;
When the theoretical length of square hole four edges is equal, wherein any a line it will be defined as theoretical short side, with the side
Two vertical sides are theoretical long side;
If angle is 0 °~10 °, fitting a straight line I is the short side of square hole;
If angle is 85 °~95 °, fitting a straight line I is the long side of square hole;
If angle is other angles, return step five;
Record the long side or short side type of the fitting a straight line I.
The description that specific exemplary embodiment of the present invention is presented in front is for the purpose of illustration and description.Front
Description be not intended to become without missing, be not intended to limit the invention to disclosed precise forms, it is clear that root
It is possible for much changing and change all according to above-mentioned introduction.It selects exemplary implementation scheme and is described to be to explain this hair
Bright certain principles and practical application, so that others skilled in the art can be realized and utilize of the invention each
Kind exemplary implementation scheme and its different selection forms and modification.The scope of the present invention be intended to by the appended claims and
Its equivalent form is limited.
Claims (8)
1. a kind of extracting method of square hole feature, which comprises the steps of:
Step 1: utilizing the left and right image of two CCD camera measure system acquisition square hole feature;
Step 2: carrying out image preprocessing to the left and right image, the square hole contour edge two-dimensional points of left and right image are extracted;
Step 3: the square hole contour edge two-dimensional points in left and right image are transformed into three-dimensional space using polar curve matching process, obtain
The three-dimensional point coordinate for taking square hole profile is denoted as point set Nj, j=1,2 ..., m, m is the number of the three-dimensional point of square hole profile;
Step 4: at random from the point set NjIn take at least two point, be denoted as reconnaissance to be fitted, carry out straight line fitting, be fitted
Straight line I;
Step 5: the angle of the direction vector of digital simulation straight line I and square hole theory longitudinal direction vector;
When the theoretical length of square hole four edges is equal, wherein any a line it will be defined as theoretical long side, it is perpendicular
Side is theoretical short side;
If angle is 0 °~10 °, fitting a straight line I is the long side of square hole;
If angle is 85 °~95 °, fitting a straight line I is the short side of square hole;
If angle is other angles, return step four;
Record the long side or short side type of the fitting a straight line I;
Step 6: calculating Dj, j=1,2 ..., m;
DjFor point set NjDistance of the middle all the points to the fitting a straight line I;
Step 7: comparing DjWith preset threshold T1, D will be metj< T1Point be labeled as the unilateral space intra-office point of square hole;
Step 8: counting the quantity of the unilateral space intra-office point of the square hole, M value and three-dimensional coordinate information are recorded;
Step 9: carrying out q iteration to step 4~step 8;
The maximum value in M value is chosen, M is denoted asmax, recording the unilateral space intra-office point of the square hole corresponding to it is final square hole
Unilateral image three-dimensional point set is denoted as the image three-dimensional point set P of a lineh', h=1,2 ..., Mmax;
Step 10: from the point set NjMiddle rejecting image three-dimensional point set Ph' interior all the points, obtain point set Nj', j=1,2 ..., m ',
M ' is the number that square hole profile rejects remaining point after point set corresponding to a line;
From the point set Nj' in randomly select at least two point, be denoted as reconnaissance to be fitted, straight line fitting carried out, as fitting a straight line
I is denoted as point set P according to the corresponding three-dimensional point in method screening Article 2 side in step 5~step 9h″;
Step 11: from the point set Nj' middle rejecting point set Ph" corresponding point, obtains tripleplane's point set of second hole profile
Nj", the number of remaining three-dimensional point after the point set of j=1,2 ..., m ", m " for two sides of square hole profile rejecting;
From the point set Nj" in randomly select at least two point, be denoted as reconnaissance to be fitted, fitting a straight line is pressed as fitting a straight line I
According to the corresponding three-dimensional point in method screening Article 3 side in step 5~step 9, it is denoted as point set Ph″′;
Step 12: from the point set NjIt is " middle to reject point set Ph" ' corresponding point, obtains point set Nj" ', j=1,2 ..., m " ',
M " ' be square hole profile reject square hole three edge point collection after remaining three-dimensional point number;
From the point set Nj" ' in randomly select at least two point, be denoted as reconnaissance to be fitted, fitting a straight line is pressed as fitting a straight line I
According to the corresponding three-dimensional point in method screening Article 4 side in step 5~step 9, it is denoted as point set Ph″″;
Step 13: respectively to point set Ph', point set Ph", point set Ph" ', point set Ph" " carries out straight line fitting, obtains first straight line side
L1, second straight line side L2, third straight line L3, the 4th straight line L4;
Solve first straight line side L1, second straight line side L2, third straight line L3, the 4th straight line L4The point intersected two-by-two, the side of being denoted as
The vertex in hole: A (x1, y1, z1), B (x2, y2, z2), C (x3, y3, z3), D (x4, y4, z4);
Solve centre coordinate, the length and width of square hole.
2. the extracting method of square hole feature as described in claim 1, it is characterised in that: replace step 5 are as follows: digital simulation is straight
The direction vector of line I and the angle of square hole theory short side direction vector;
When the theoretical length of square hole four edges is equal, wherein any a line it will be defined as theoretical short side, it is vertical with the side
Two sides be theoretical long side;
If angle is 0 °~10 °, fitting a straight line I is the short side of square hole;
If angle is 85 °~95 °, fitting a straight line I is the long side of square hole;
If angle is other angles, return step five;
Record the long side or short side type of the fitting a straight line I.
3. the extracting method of square hole feature as claimed in claim 1 or 2, it is characterised in that: in step 8 further include: calculate
Ratio '=M/m, preset ratio threshold value H, the preset ratio threshold value H value 0.2~0.5, if Ratio ' >=H, this power
The unilateral fitting in hole is correct, saves this M value and three-dimensional coordinate information;Otherwise, this M value is not saved.
4. the extracting method of square hole feature as claimed in claim 1 or 2, it is characterised in that: the number of iterations q calculation formula is such as
Under:
P=1- (1-Ratio1′n)q;
In formula, n is the number of reconnaissance to be fitted;P is that n reconnaissances to be fitted are the long side of square hole or the space intra-office point of short side
Probability, Ratio1' for the ratio of M and m that acquires for the first time.
5. the extracting method of square hole feature as claimed in claim 1 or 2, it is characterised in that: the threshold value T1=0~0.2mm.
6. the extracting method of square hole feature as claimed in claim 1 or 2, it is characterised in that: be to the method that straight line is fitted
Least square method, Gauss curve fitting, Chebyshev's approximating method.
7. the extracting method of square hole feature as claimed in claim 1 or 2, it is characterised in that: the left and right image is grayscale image.
8. the extracting method of square hole feature as claimed in claim 1 or 2, it is characterised in that: described image pretreatment includes Gauss
Filtering, binary image, edge detection.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910150080.1A CN109902694B (en) | 2019-02-28 | 2019-02-28 | Extraction method of square hole characteristics |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910150080.1A CN109902694B (en) | 2019-02-28 | 2019-02-28 | Extraction method of square hole characteristics |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109902694A true CN109902694A (en) | 2019-06-18 |
CN109902694B CN109902694B (en) | 2022-02-18 |
Family
ID=66945932
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910150080.1A Active CN109902694B (en) | 2019-02-28 | 2019-02-28 | Extraction method of square hole characteristics |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109902694B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112529902A (en) * | 2021-01-26 | 2021-03-19 | 江苏卓玉智能科技有限公司 | Hole checking method of PCB (printed circuit board) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103679636A (en) * | 2013-12-23 | 2014-03-26 | 江苏物联网研究发展中心 | Rapid image splicing method based on point and line features |
CN104200496A (en) * | 2014-09-01 | 2014-12-10 | 西北工业大学 | High-precision detecting and locating method for rectangular identifiers on basis of least square vertical fitting of adjacent sides |
CN107220999A (en) * | 2017-06-19 | 2017-09-29 | 江南大学 | The research of workpiece circular arc Edge Feature Points matching process |
CN107220989A (en) * | 2017-06-19 | 2017-09-29 | 江南大学 | The elliptic contour detection method research of workpiece |
CN108182705A (en) * | 2016-12-08 | 2018-06-19 | 广州映博智能科技有限公司 | A kind of three-dimensional coordinate localization method based on machine vision |
-
2019
- 2019-02-28 CN CN201910150080.1A patent/CN109902694B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103679636A (en) * | 2013-12-23 | 2014-03-26 | 江苏物联网研究发展中心 | Rapid image splicing method based on point and line features |
CN104200496A (en) * | 2014-09-01 | 2014-12-10 | 西北工业大学 | High-precision detecting and locating method for rectangular identifiers on basis of least square vertical fitting of adjacent sides |
CN108182705A (en) * | 2016-12-08 | 2018-06-19 | 广州映博智能科技有限公司 | A kind of three-dimensional coordinate localization method based on machine vision |
CN107220999A (en) * | 2017-06-19 | 2017-09-29 | 江南大学 | The research of workpiece circular arc Edge Feature Points matching process |
CN107220989A (en) * | 2017-06-19 | 2017-09-29 | 江南大学 | The elliptic contour detection method research of workpiece |
Non-Patent Citations (3)
Title |
---|
张志佳 等: "基于深度图像和点云边缘特征的典型零部件识别", 《信息与控制》 * |
熊雪梅: "基于双目视觉的圆弧类工件轮廓的测量方法研究", 《中国优秀硕士学位论文全文数据库 工程科技I辑》 * |
王振宁 等: "基于直线段提取及其参数化的矩形重构方法研究", 《计算机工程与应用》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112529902A (en) * | 2021-01-26 | 2021-03-19 | 江苏卓玉智能科技有限公司 | Hole checking method of PCB (printed circuit board) |
Also Published As
Publication number | Publication date |
---|---|
CN109902694B (en) | 2022-02-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106338521B (en) | Increasing material manufacturing surface and internal flaw and pattern composite detection method and device | |
CN109801337B (en) | 6D pose estimation method based on instance segmentation network and iterative optimization | |
CN111062915A (en) | Real-time steel pipe defect detection method based on improved YOLOv3 model | |
CN109211198B (en) | Intelligent target detection and measurement system and method based on trinocular vision | |
CN109859206A (en) | A kind of extracting method of circular hole feature | |
CN111126174A (en) | Visual detection method for robot to grab parts | |
CN103292701A (en) | Machine-vision-based online dimensional measurement method of precise instrument | |
CN109855566A (en) | A kind of extracting method of slot feature | |
CN104121902A (en) | Implementation method of indoor robot visual odometer based on Xtion camera | |
CN111340834B (en) | Lining plate assembly system and method based on laser radar and binocular camera data fusion | |
CN115311629B (en) | Abnormal bending precision monitoring system of bending machine | |
CN103394973A (en) | Device and method for measuring high-speed orthogonal cutting process strain through digital image correlation method | |
CN110232682B (en) | Image-based track foreign matter detection method | |
CN104050660A (en) | Method for measuring workpiece round edges | |
CN115131268A (en) | Automatic welding system based on image feature extraction and three-dimensional model matching | |
CN108205645A (en) | A kind of reference map quality evaluating method of heterologous image matching system | |
CN116188544A (en) | Point cloud registration method combining edge features | |
CN109902694A (en) | A kind of extracting method of square hole feature | |
CN112991327A (en) | Steel grid welding system and method based on machine vision and terminal equipment | |
CN112434559A (en) | Robot identification and positioning method | |
Ni et al. | Visual positioning algorithm based on micro assembly line | |
CN110021027B (en) | Edge cutting point calculation method based on binocular vision | |
CN109242911A (en) | One kind being based on subregional binocular camera fundamental matrix calculation method | |
CN115164751A (en) | Riveting aperture size detection system and method | |
CN104050659A (en) | Method for measuring workpiece linear edges |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CP01 | Change in the name or title of a patent holder | ||
CP01 | Change in the name or title of a patent holder |
Address after: Room 495, building 3, 1197 Bin'an Road, Binjiang District, Hangzhou City, Zhejiang Province 310051 Patentee after: Yi Si Si (Hangzhou) Technology Co.,Ltd. Address before: Room 495, building 3, 1197 Bin'an Road, Binjiang District, Hangzhou City, Zhejiang Province 310051 Patentee before: ISVISION (HANGZHOU) TECHNOLOGY Co.,Ltd. |