CN109859206A - A kind of extracting method of circular hole feature - Google Patents
A kind of extracting method of circular hole feature Download PDFInfo
- Publication number
- CN109859206A CN109859206A CN201910150106.2A CN201910150106A CN109859206A CN 109859206 A CN109859206 A CN 109859206A CN 201910150106 A CN201910150106 A CN 201910150106A CN 109859206 A CN109859206 A CN 109859206A
- Authority
- CN
- China
- Prior art keywords
- point
- circular hole
- circle
- space
- 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.)
- Pending
Links
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a kind of extracting method of circular hole feature, the present invention acquires the left and right image of circular hole feature using two CCD camera measure system；Extract the two-dimensional image point of circular hole contour edge, miscellaneous point is carried out to two-dimensional image point based on RANSAC algorithm to reject, further, obtain the three-dimensional figure picture point of circular hole contour edge, impurity point, clarifying space radius of circle are picked by RANSAC algorithm to three-dimensional image information, finally obtain the accurate circular hole three-dimensional information of result, this method measurement accuracy can reach 0.01~0.001mm, 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 circular hole feature.
Background technique
Circle is the basic geometry of object, due to the geometrical characteristic of circle itself, so that many parts in industry
Round or approximate circle profile, such as hole, axis etc. is all presented in section, accurately determines these circle features, and then obtain round feature
Geometric center three-dimensional space position and the geometric parameters such as radius, in industry spot, especially Automated inspection and assembly neck
Domain has a wide range of applications.
By taking auto manufacturing as an example, in the automobile manufacture stage, vehicle body is the maximum assembly of automobile, and moulding process is various,
The precision of part is difficult to control and guarantees, needs efficient measurement means.The data for obtaining these part size deviations, for vehicle
The guarantee and control of weight have very important effect, can objectively evaluate the quality of production of vehicle body parts in turn accordingly
It makes adjustment.
Edge detection operator is mainly used to carry out the extraction of circular hole contour edge the method for circular hole feature extraction at present, such as
Canny edge detection operator, Sobel edge detection operator, Priwitt edge detection operator etc., but carry out edge extracting
As a result there are many noise, are unable to satisfy the testing requirements to Precision Machining workpiece, it is therefore desirable to carry out edge fitting, common edge
Approximating method, such as least square method can not carry out miscellaneous point and reject, and be easy to happen fitting mistake, fitting result inaccuracy.
CN201710462540.5 discloses a kind of matching process of workpiece circular arc Edge Feature Points, using RANSAC algorithm to circular arc
It is fitted, obtains elliptic contour, this method aims to solve the problem that circular arc works have notch in Binocular vision photogrammetry；But
Be that the disclosed method of application is only fitted two-dimensional surface circular arc, carries out left images matching later, but to matching after
Space circular arc profile does not process, although improving measuring accuracy to a certain extent, in Precision Machining manufacturing field, such as vapour
The needs such as vehicle manufacture, aircraft manufacturing industry accurately know circular hole characteristic 3 D geometric parameter data, and measurement accuracy often requires that micro-
Meter level, existing method precision are unable to satisfy requirement.
Summary of the invention
In order to solve the above technical problem, the present invention provides a kind of extracting methods of circular hole feature, and measurement accuracy can
Reach 0.01~0.001mm, time of measuring can satisfy the requirement of high-precision detection, for this purpose, technology of the invention in Millisecond
Scheme is as follows:
A kind of extracting method of circular hole feature, includes the following steps:
Step 1: utilizing the left and right image of two CCD camera measure system acquisition circular hole feature；
Step 2: carrying out image preprocessing to the left and right image, all circular hole contour edges in left and right image are extracted
Two-dimensional points coordinate is denoted as point set Nt, t=1,2 ... s；S is the number of the circular hole contour edge two-dimensional points；
Step 3: the circular hole profile point in left and right image is transformed into space three-dimensional using polar curve matching process, circle is obtained
The three-dimensional point coordinate data of hole profile point, are denoted as point set Nj', j=1,2 ..., m, m are the number of circular hole profile point；
Step 4: at random from the point set Nj' in take at least three point, be denoted as reconnaissance to be fitted, utilize least square method will
The chosen_point fitting plane to be fitted and space circle obtain fit Plane I and fitting space circle I；
Step 5: calculating Fj, Dj, j=1,2 ..., m；
FjFor point set Nj' in j point to the distance to the fit Plane I；
DjFor point set Nj' in j point to it is described fitting space circle I the center of circle distance and fitting space circle I radius difference
Absolute value；
Step 6: being preset with distance threshold T1With difference threshold T2, meet F when simultaneouslyj< T1, Dj< T2When, then correspond to j point
It is space intra-office point, traverses point set Nj' in all the points, calculate Fj、DjValue, marks all space intra-office points；
Step 7: counting the number of the space intra-office point, it is denoted as M, calculates the ratio R atio ' of M and m, preset ratio threshold
Value parameter is H, if Ratio ' >=H, this time space circle fitting is correct, records this M value and the space office corresponding to it
Interior coordinate information；
Otherwise, this time space circle is fitted mistake, does not save this M value and the space intra-office point coordinate corresponding to it
Information；
Step 8: being iterated to step 4~step 7, the number of iterations is q times；
Maximum value is selected from multiple M being recorded, the space intra-office point corresponding to it is special as final circular hole
Levy image three-dimensional point；
Step 9: seeking central coordinate of circle and radius using the circular hole characteristic image three-dimensional point that step 8 obtains.
In order to further increase the precision for finally obtaining result, following steps are first carried out after the step 2, then into
Row step 3；
Step I, the circular hole contour edge two-dimensional points coordinate N of the left and right image obtained from the step 2tIn randomly select
K point, k >=3 carry out round fitting, labeled as circle II；
Step II, point set N is calculatedtFor middle all the points to the circle center distance of circle II, it is poor to make with circular hole fit radius, takes absolutely
Value, is denoted as point set Ft′；
Step III, preset difference value threshold value is T, traverses point set Ft' interior all the points, when meeting FtWhen ' < T, it is believed that at this time
The circular hole contour edge two-dimensional points of left and right image are intra-office points, traverse all circular hole contour edge two-dimensional points Nt, mark all offices
Interior point；
Step IV, the number for counting the intra-office point is denoted as S, the ratio R atio of S and s is calculated, if Ratio >=G, G take
Value 0.5~0.9, then the circle fitting in step I is correct；If Ratio < G, circle fitting mistake；
Step V, step I~step IV is iterated, the number of iterations q1It is secondary；
Step VI, q is chosen1Maximum value in+1 S, using the intra-office point corresponding to it as in the step 3 a left side,
Circular hole profile point in right image.
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 in step 4；P is that n reconnaissances to be fitted are the general of space intra-office point
Rate, Ratio1' for the ratio of M and m sought for the first time.
Further, the number of iterations q1Calculation formula is as follows:
In formula, k is that step I is carried out when circle is fitted for the first time in point set NtThe quantity of middle reconnaissance；p1It is randomly selected a little for k
It is the probability of intra-office point；Ratio is the ratio of the S and s that seek for the first time.
Further, after the step 4, the radius and theoretical half for the fitting space circle I that step 4 obtains is calculated first
Diameter R0Deviation, by the absolute value of the deviation compared with preset threshold value d, if the deviation be less than or equal to threshold value d,
Then the space circle fitting is correct, continues step 5；Conversely, then the fitting space circle I fitting is incorrect, return to
Step 4 carries out space circle fitting.
Further, the left and right image is grayscale image.
Further, described image pretreatment includes gaussian filtering, binary image, edge detection.
It is preferred that the proportion threshold value parameter H takes 0.5~0.9.
It is preferred that the distance threshold T1Take 0.2-0.5；Difference threshold T2Take 0.2-0.5.
It is preferred that the difference threshold T value 0.2~0.5.
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 circular hole profile two dimensional image by RANSAC algorithm to reject；Using double
Item stereo vision carries out the Stereo matching of left images, obtains the three-dimensional coordinate information of tested circular hole, meanwhile, increase plane about
Beam carries out RANSAC algorithm to the three-D profile information of circular hole again, carries out the verifying of space circle radius after fitting space circle, subtracts
Few cycle-index, improves detection accuracy, efficiency, finally obtains the accurate circular hole three-dimensional information of result, this method measurement accuracy energy
Enough reach micron order, time of measuring can satisfy the manufacturing testing requirements of the Precision Machinings such as automobile industry in Millisecond.
Detailed description of the invention
Fig. 1 is the flow chart of the extracting method of circular hole feature provided by the invention；
Fig. 2 is the flow chart of one embodiment of the extracting method of circular hole feature provided by the invention.
Specific embodiment
Technical solution of the present invention is described in detail below in conjunction with specific embodiment.
A kind of extracting method of circular hole feature, includes the following steps:
Step 1: utilizing the left and right gray level image of two CCD camera measure system acquisition circular hole feature；
Step 2: being carried out to the left and right gray level image using the methods of gaussian filtering, binary image, edge detection
Pretreatment, proposes all circular hole contour edge two-dimensional points coordinates in image, is denoted as point set Nt, t=1,2 ... s；S is the circular hole
The number of contour edge two-dimensional points；
Step 3: the circular hole profile point in left and right gray level image is transformed into space three-dimensional using polar curve matching process, obtain
The three-dimensional point coordinate data for taking circular hole profile point, are denoted as point set Nj', j=1,2 ..., m, m are the number of circular hole profile point；
Step 4: at random from the point set Nj' in take at least three point, be denoted as reconnaissance to be fitted, utilize least square method will
The chosen_point fitting plane to be fitted and space circle obtain fit Plane I and fitting space circle I；
Step 5: calculating Fj, Dj, j=1,2 ..., m；
FjFor point set Nj' in j point to the distance to the fit Plane I；
DjFor point set Nj' in j point to it is described fitting space circle I the center of circle distance and fitting space circle I radius difference
Absolute value；
Step 6: being preset with distance threshold T1With difference threshold T2, meet F when simultaneouslyj< T1, Dj< T2When, then correspond to j point
It is space intra-office point, traverses point set Nj' in all the points, calculate Fj、DjValue, marks all space intra-office points；It is preferred that apart from threshold
Value T1=0.2~0.5；Difference threshold T2=0.2~0.5；
Step 7: counting the number of the space intra-office point, it is denoted as M, calculates the ratio R atio ' of M and m, preset ratio threshold
Value parameter is H, if Ratio ' >=H, this time space circle fitting is correct, records this M value and the space office corresponding to it
Interior coordinate information；It is preferred that H=0.5~0.9；
Otherwise, this time space circle is fitted mistake, does not save this M value and the space intra-office point coordinate corresponding to it
Information；
Step 8: being iterated to step 4~step 7, the number of iterations is q times；It is preferred that the number of iterations q calculation formula
It is as follows:
P=1- (1-Ratio1′n)q；
In formula, n is the number of reconnaissance to be fitted in step 4；P is that n reconnaissances to be fitted are the general of space intra-office point
Rate, Ratio1' for the ratio of M and m sought for the first time；
Maximum value is selected from multiple M being recorded, the space intra-office point corresponding to it is special as final circular hole
Levy image three-dimensional point；
Step 9: seeking central coordinate of circle and radius using the circular hole characteristic image three-dimensional point that step 8 obtains.
As an embodiment of the present invention, after step 4 obtains fit Plane I and fitting space circle I, step is first calculated
The radius and principal radii R of rapid four obtained fitting space circle I0Deviation, by the absolute value of the deviation with it is preset
Threshold value d compares, if the deviation is less than or equal to threshold value d, the space circle fitting is correct, continues step 5；Conversely,
Then the fitting space circle I fitting is incorrect, returns to step 4 and carries out space circle fitting.The priori before carrying out subsequent calculating
Card step 4 obtains fit Plane I and whether fitting space circle I is correct, is conducive to the precision for improving final result.
As a kind of optimization of technical solution of the present invention, following steps are first carried out after the step 2, then walked
Rapid three；
Step I, the circular hole contour edge two-dimensional points coordinate N of the left and right image obtained from the step 2tIn randomly select
K point, k >=3 carry out round fitting, labeled as circle II；
Step II, point set N is calculatedtFor middle all the points to the circle center distance of circle II, it is poor to make with circular hole fit radius, takes absolutely
Value, is denoted as point set Ft′；
Step III, preset difference value threshold value is T, traverses point set Ft' interior all the points, when meeting FtWhen ' < T, it is believed that at this time
The circular hole contour edge two-dimensional points of left and right image are intra-office points, traverse all circular hole contour edge two-dimensional points Nt, mark all offices
Interior point；It is preferred that difference threshold T=0.2~0.5；
Step IV, the number for counting the intra-office point is denoted as S, the ratio R atio of S and s is calculated, if Ratio >=G, G take
Value 0.5~0.9, then the circle fitting in step I is correct；If Ratio < G, circle fitting mistake；
Step V, step I~step IV is iterated, the number of iterations q1It is secondary；Wherein, the number of iterations q1Calculation formula is such as
Under:
p1=1- (1-Ratiok)q1；
In formula, k is that step I is carried out when circle is fitted for the first time in point set NtThe quantity of middle reconnaissance；p1It is randomly selected a little for k
It is the probability of intra-office point；Ratio is the ratio of the S and s that seek for the first time；
Step VI, q is chosen1Maximum value in+1 S, using the intra-office point corresponding to it as in the step 3 a left side,
Circular hole profile point in right image.
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 (10)
1. a kind of extracting method of circular hole feature, which comprises the steps of:
Step 1: utilizing the left and right image of two CCD camera measure system acquisition circular hole feature；
Step 2: carrying out image preprocessing to the left and right image, all circular hole contour edge two dimensions in left and right image are extracted
Point coordinate, is denoted as point set Nt, t=1,2 ... s；S is the number of the circular hole contour edge two-dimensional points；
Step 3: the circular hole profile point in left and right image is transformed into space three-dimensional using polar curve matching process, circular hole wheel is obtained
The three-dimensional point coordinate data of exterior feature point, are denoted as point set Nj', j=1,2 ..., m, m are the number of circular hole profile point；
Step 4: at random from the point set Nj' in take at least three point, be denoted as reconnaissance to be fitted, will be described using least square method
Chosen_point fitting plane and space circle to be fitted obtain fit Plane I and fitting space circle I；
Step 5: calculating Fj, Dj, j=1,2 ..., m；
FjFor point set Nj' in j point to the distance to the fit Plane I；
DjFor point set Nj' in j point to it is described fitting space circle I the center of circle distance be fitted space circle I radius difference it is exhausted
To value；
Step 6: being preset with distance threshold T1With difference threshold T2, meet F when simultaneouslyj< T1, Dj< T2When, then it is empty for corresponding to j point
Between intra-office point, traverse point set Nj' in all the points, calculate Fj、DjValue, marks all space intra-office points；
Step 7: counting the number of the space intra-office point, it is denoted as M, calculates the ratio R atio ' of M and m, preset ratio threshold value ginseng
Number is H, if Ratio ' >=H, this time space circle fitting is correct, records this M value and the space intra-office point corresponding to it
Coordinate information；
Otherwise, this time space circle is fitted mistake, does not save this M value and the space intra-office point coordinate information corresponding to it；
Step 8: being iterated to step 4~step 7, the number of iterations is q times；
Maximum value is selected from multiple M being recorded, using the space intra-office point corresponding to it as final circular hole characteristic pattern
As three-dimensional point；
Step 9: seeking central coordinate of circle and radius using the circular hole characteristic image three-dimensional point that step 8 obtains.
2. the extracting method of circular hole feature as described in claim 1, it is characterised in that: first carried out after the step 2 as follows
Step, then carry out step 3；
Step I, the circular hole contour edge two-dimensional points coordinate N of the left and right image obtained from the step 2tIn randomly select k
Point, k >=3 carry out round fitting, labeled as circle II；
Step II, point set N is calculatedtFor middle all the points to the circle center distance of circle II, it is poor to make with circular hole fit radius, takes absolute value, is denoted as
Point set Ft′；
Step III, preset difference value threshold value is T, traverses point set Ft' interior all the points, when meeting FtWhen ' < T, it is believed that at this time left and right
The circular hole contour edge two-dimensional points of image are intra-office points, traverse all circular hole contour edge two-dimensional points Nt, mark all intra-office points；
Step IV, the number for counting the intra-office point is denoted as S, the ratio R atio of S and s is calculated, if Ratio >=G, G value 0.5
~0.9, then the circle fitting in step I is correct；If Ratio < G, circle fitting mistake；
Step V, step I~step IV is iterated, the number of iterations q1It is secondary；
Step VI, q is chosen1Maximum value in+1 S, using the intra-office point corresponding to it as the left and right image in the step 3
In circular hole profile point.
3. the extracting method of circular hole feature as described in the appended claim 1, 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 in step 4；P is the probability that n reconnaissances to be fitted are space intra-office point,
Ratio1' for the ratio of M and m sought for the first time.
4. the extracting method of circular hole feature as stated in claim 2, it is characterised in that: the number of iterations q1Calculation formula is such as
Under:
In formula, k is that step I is carried out when circle is fitted for the first time in point set NtThe quantity of middle reconnaissance；p1It is randomly selected for k and is a little
The probability of intra-office point；Ratio is the ratio of the S and s that seek for the first time.
5. the extracting method of circular hole feature as described in claim 1, it is characterised in that: after the step 4, calculate first
The radius and principal radii R for the fitting space circle I that step 4 obtains0Deviation, by the absolute value of the deviation and default
Threshold value d compare, if the deviation is less than or equal to threshold value d, space circle fitting is correct, continues step 5；Instead
It, then the fitting space circle I fitting is incorrect, returns to step 4 and carries out space circle fitting.
6. the extracting method of circular hole feature as described in claim 1, it is characterised in that: the left and right image is grayscale image.
7. the extracting method of circular hole feature as described in claim 1, it is characterised in that: described image pretreatment includes that Gauss filters
Wave, binary image, edge detection.
8. the extracting method of circular hole feature as described in claim 1, it is characterised in that: the proportion threshold value parameter H takes 0.5~
0.9。
9. the extracting method of circular hole feature as described in claim 1, it is characterised in that: the distance threshold T1Take 0.2-0.5；Difference
It is worth threshold value T2Take 0.2-0.5.
10. the extracting method of circular hole feature as claimed in claim 2, it is characterised in that: the difference threshold T value 0.2~
0.5。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910150106.2A CN109859206A (en) | 2019-02-28 | 2019-02-28 | A kind of extracting method of circular hole feature |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910150106.2A CN109859206A (en) | 2019-02-28 | 2019-02-28 | A kind of extracting method of circular hole feature |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109859206A true CN109859206A (en) | 2019-06-07 |
Family
ID=66899403
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910150106.2A Pending CN109859206A (en) | 2019-02-28 | 2019-02-28 | A kind of extracting method of circular hole feature |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109859206A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109506580A (en) * | 2018-11-26 | 2019-03-22 | 清华大学 | Spot-facing quality determining method based on line laser 3-D scanning |
| CN110986778A (en) * | 2019-12-25 | 2020-04-10 | 电子科技大学 | System and method for detecting size of rivet hole of carbon fiber composite material |
| CN111724366A (en) * | 2020-06-16 | 2020-09-29 | 武汉工程大学 | Laser cavity identification method and device |
| CN112132886A (en) * | 2020-09-30 | 2020-12-25 | 哈尔滨理工大学 | Circular hole center rapid positioning and roundness detection method for aviation part |
| CN112465892A (en) * | 2020-11-09 | 2021-03-09 | 北方爆破科技有限公司 | Improved RANSAC algorithm-based blast hole identification method |
| 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) |
| CN112747671A (en) * | 2020-12-10 | 2021-05-04 | 北京天远三维科技股份有限公司 | Three-dimensional detection system and three-dimensional detection method |
| CN113160172A (en) * | 2021-04-22 | 2021-07-23 | 沧澜智能科技(昆山)有限公司 | Anti-interference circle detection algorithm capable of achieving sub-pixel level precision simultaneously |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101261115A (en) * | 2008-04-24 | 2008-09-10 | 吉林大学 | Spatial circular geometric parameter binocular stereo vision measurement method |
| CN106767401A (en) * | 2016-11-26 | 2017-05-31 | 江苏瑞伯特视觉科技股份有限公司 | A kind of shaft hole series part based on cross laser and machine vision determines appearance localization method |
| CN106934809A (en) * | 2017-03-29 | 2017-07-07 | 厦门大学 | Unmanned plane based on binocular vision autonomous oiling rapid abutting joint air navigation aid in the air |
| CN107220999A (en) * | 2017-06-19 | 2017-09-29 | 江南大学 | The research of workpiece circular arc Edge Feature Points matching process |
-
2019
- 2019-02-28 CN CN201910150106.2A patent/CN109859206A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101261115A (en) * | 2008-04-24 | 2008-09-10 | 吉林大学 | Spatial circular geometric parameter binocular stereo vision measurement method |
| CN106767401A (en) * | 2016-11-26 | 2017-05-31 | 江苏瑞伯特视觉科技股份有限公司 | A kind of shaft hole series part based on cross laser and machine vision determines appearance localization method |
| CN106934809A (en) * | 2017-03-29 | 2017-07-07 | 厦门大学 | Unmanned plane based on binocular vision autonomous oiling rapid abutting joint air navigation aid in the air |
| CN107220999A (en) * | 2017-06-19 | 2017-09-29 | 江南大学 | The research of workpiece circular arc Edge Feature Points matching process |
Non-Patent Citations (2)
| Title |
|---|
| 化春键 等: "工件圆弧边缘特征点检测与匹配方法", 《传感器与微系统》 * |
| 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》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109506580A (en) * | 2018-11-26 | 2019-03-22 | 清华大学 | Spot-facing quality determining method based on line laser 3-D scanning |
| CN109506580B (en) * | 2018-11-26 | 2019-11-29 | 清华大学 | Spot-facing quality determining method based on line laser 3-D scanning |
| CN110986778A (en) * | 2019-12-25 | 2020-04-10 | 电子科技大学 | System and method for detecting size of rivet hole of carbon fiber composite material |
| CN110986778B (en) * | 2019-12-25 | 2021-10-08 | 电子科技大学 | System and method for detecting size of rivet hole of carbon fiber composite material |
| CN111724366A (en) * | 2020-06-16 | 2020-09-29 | 武汉工程大学 | Laser cavity identification method and device |
| CN111724366B (en) * | 2020-06-16 | 2023-08-25 | 武汉工程大学 | Laser cavity identification method and device |
| CN112132886A (en) * | 2020-09-30 | 2020-12-25 | 哈尔滨理工大学 | Circular hole center rapid positioning and roundness detection method for aviation part |
| CN112465892A (en) * | 2020-11-09 | 2021-03-09 | 北方爆破科技有限公司 | Improved RANSAC algorithm-based blast hole identification method |
| CN112747671A (en) * | 2020-12-10 | 2021-05-04 | 北京天远三维科技股份有限公司 | Three-dimensional detection system and three-dimensional detection method |
| 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) |
| CN113160172A (en) * | 2021-04-22 | 2021-07-23 | 沧澜智能科技(昆山)有限公司 | Anti-interference circle detection algorithm capable of achieving sub-pixel level precision simultaneously |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109859206A (en) | A kind of extracting method of circular hole feature | |
| CN109978901B (en) | Quick and accurate circular detection and circle center positioning method | |
| CN109211198B (en) | Intelligent target detection and measurement system and method based on trinocular vision | |
| CN113205486A (en) | Surface defect detection method and device based on three-dimensional point cloud and storage medium | |
| CN106204610A (en) | Peg-in-hole assembly automatic centering system based on image procossing | |
| CN112489094B (en) | Multi-line airborne laser radar point cloud data registration method | |
| CN103292701A (en) | Machine-vision-based online dimensional measurement method of precise instrument | |
| CN108917591A (en) | Rail profile autoegistration method and device under a kind of dynamic environment | |
| CN113034485A (en) | Circle detection method integrating Hough transformation and caliper clustering | |
| CN108009494A (en) | A kind of intersection wireless vehicle tracking based on unmanned plane | |
| CN113610917A (en) | Circular array target center image point positioning method based on blanking points | |
| CN113516695B (en) | Point cloud registration strategy in laser profiler flatness measurement | |
| CN113042939A (en) | Workpiece weld joint positioning method and system based on three-dimensional visual information | |
| CN109855566A (en) | A kind of extracting method of slot feature | |
| CN108994844A (en) | A kind of scaling method and device of sanding operation arm trick relationship | |
| CN107358628A (en) | Linear array images processing method based on target | |
| CN104050660A (en) | Method for measuring workpiece round edges | |
| CN112669379A (en) | Image feature rapid extraction method based on auxiliary mark points | |
| CN110763136A (en) | High-precision three-dimensional workpiece size detection system and method | |
| CN108205645A (en) | A kind of reference map quality evaluating method of heterologous image matching system | |
| CN116402792A (en) | Space hole site butt joint method based on three-dimensional point cloud | |
| CN103679713A (en) | Two-dimensional image registration method for partially matched images | |
| CN112651943A (en) | Three-dimensional image mark point extraction method | |
| CN109934860A (en) | A kind of method for registering images rejected based on SIFT-FLANN and Mismatching point | |
| CN109902694B (en) | Extraction method of square hole characteristics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190607 |