CN102425989A - Image detection-based two-dimensional characteristic size measurement method - Google Patents
Image detection-based two-dimensional characteristic size measurement method Download PDFInfo
- Publication number
- CN102425989A CN102425989A CN2011102417538A CN201110241753A CN102425989A CN 102425989 A CN102425989 A CN 102425989A CN 2011102417538 A CN2011102417538 A CN 2011102417538A CN 201110241753 A CN201110241753 A CN 201110241753A CN 102425989 A CN102425989 A CN 102425989A
- Authority
- CN
- China
- Prior art keywords
- curve
- image
- shape
- dimensional character
- carry out
- 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
Images
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention belongs to the technical field of vision detection of a computer, and relates to an image detection-based two-dimensional characteristic size measurement method. The method sequentially comprises the following steps of: (1) sequentially selecting a plurality of points on an acquired image along with a premeasured two-dimensional characteristic outline; (2) fitting a shape to ensure a preliminarily-selected shape curve; (3) expanding the same pixel distance towards two sides along with the normal vector of the curve by taking the preliminarily-selected shape curve as a center line, respectively generating two positioning curves, and limiting an image-processing region by taking the two curves as boundary lines; (4) searching the boundary lines and extracting a shape boundary line in the limited image-processing region by a gray level jumping and changing method; and (5) fitting the data by means of special shape constraint, so that a required shape parameter is obtained. The two-dimensional characteristic outline data can be accurately extracted, and the method has the characteristics of being high in precision, high in stability and the like.
Description
Technical field
The invention belongs to the Computer Vision Detection technical field, relate to a kind of two dimensional character dimension measurement method.
Background technology
Along with producing and the developing rapidly of science and technology, also increasingly high to the requirement of degree of accuracy, efficient and the automaticity of measuring method.Image detecting technique is therefrom extracted Useful Information with the image of the measurand carrier as information, realizes noncontact with it, and high precision reaches robotization fast and detects.Image measurement technology has adapted to measurement development of demand trend, becomes the important measuring method of two dimensional character sizes such as micro-structure, curved surface profile and pitch-row.
The two dimensional character size is to estimate the important evidence of machining precision, like the diameter of processing circular hole, the position relation between the circular hole, the spacing of groove array, the angle of wedge structure etc.Yet; Because images acquired information is complicated, directly image is carried out overall processing and can receive numerous The noise, and can not get accurate and stable two dimensional character information; Therefore, the two dimensional character measuring system of picture often adopts manually operated mode to carry out the extraction of characteristic information mostly.And when manually selecting; Owing to receive the influence of subjective sensation and click the uncertainty of position; The resolution of adding picture is high; When showing, can exist and dwindle demonstration, actually see that the position of selected element can exist the deviation of several pixels to can hardly be avoided, and has caused the inaccurate and unstable of manual selection equally.Therefore, be necessary to develop a kind of precise and stable two dimensional character dimension measurement method.
Summary of the invention
The objective of the invention is, overcome the above-mentioned deficiency of prior art, propose a kind of two dimensional character dimension measurement method that can improve cun measuring stability and precision.The present invention is a kind of man-machine interaction processing and local feature automatic positioning method of combining, and further, by B-spline curves non-regular contour is unified to describe, and also adapts to the measurement of more curves or labyrinth such as irregularly shaped.Technical scheme of the present invention is following:
A kind of two dimensional character dimension measurement method based on image detection, carry out the following step successively:
(1) selects some points successively at the two dimensional character profile of the image upper edge premeasuring of being gathered;
(2) carry out the shape match, confirm the pattern curve of initial option;
(3) pattern curve with this initial option is a center line, expands same pixel distance along the normal vector of this curve to both sides, generates two auditory localization cues respectively, is the zone that the boundary line limits Flame Image Process with these two curves.
(4) utilize the Gray Level Jump method in the zone of the Flame Image Process that is limited, carry out boundary search, extract shape border;
(5) shape border of extracting according to step (4) is carried out the data fitting of given shape constraint, thereby is obtained the required form parameter.
As preferred implementation, if the two dimensional character of curve is not straight line or quafric curve, step (2) adopts the method for B-spline Curve interpolation, the data point that obtains carrying out the shape match; Described pixel distance is 10～20 pixels; If confirm the pattern curve of initial option be v=f (u) or u=g (v), wherein (u v) is the horizontal ordinate of image coordinate, in step (4) according to horizontal stroke, the ordinate scope u of the pattern curve of initial option
RangAnd v
RangCarry out confirming of search loop direction, if u
Rang＞v
Rang, with horizontal ordinate as loop direction, otherwise be loop direction with the ordinate.
The present invention can accurately extract the outline data of two dimensional character, calculates benchmark with these data as characteristic quantity, and measurement result has been avoided the subjectivity of artificial selection, and therefore, measurement has characteristics such as precision height, stable height.Simultaneously, adopt B-spline Curve to carry out the selected element match, therefore, selected shape is not limited to regular shapes such as common straight line, circle, also can realize curve or erose selection location and measurement.
Description of drawings
Fig. 1 processing flow chart.
Process flow diagram is confirmed in Fig. 2 Flame Image Process zone.
Fig. 3 Flame Image Process zone is the location synoptic diagram automatically.
Fig. 4 Boundary Extraction process flow diagram.(a) main flow (b) boundary search module.
Fig. 5 boundary extraction algorithm synoptic diagram.
Fig. 6 cutter angle measuring design sketch.
Embodiment
Fig. 1 is a bulk treatment flow process of the present invention.At first, carry out IMAQ, obtain the image information of premeasuring structure.Traditional treatment method is direct some unique points through manual choice structure edge; And calculate the image coordinate of selected element, and then according to the transformational relation (system calibrating parameter, list of references) of image coordinate and physical size; Realize the calculating and the measurement of characteristic quantity, like dotted line flow process among Fig. 1.Can find out that manual selected element positional precision is the key of certainty of measurement, in view of the unstability of manual selection measurement and global image processing, the present invention has designed based on manual selection and has carried out the feature method of location automatically again.Manually selecting on the basis; Automatically carry out Flame Image Process in the peripheral cell territory of selected element; Accurately locate the profile of selecting the border through Boundary Extraction; Then the data boundary of accurate extraction is carried out the match of reservation shape, thereby the coupling system calibrating parameters is realized the accurate measurement of character shape parameter.
Fig. 2 selects to confirm automatically Flame Image Process zone process flow diagram according to the user.At first user's selected element array A is carried out the shape match, confirm that (v), wherein (u v) is the horizontal ordinate of image coordinate for initial option pattern curve equation v=f (u) or u=g.Be center line with this curve then; Normal vector along this curve is expanded same pixel distance d to both sides, generates two auditory localization cues respectively, is the zone that the boundary line limits Flame Image Process with these two curves; Here general 10～20 pixels of selecting of d are as shown in Figure 3.Then, in limiting good zone, carry out Flame Image Process, accurately extract shape border.
The method of carrying out Boundary Extraction is more, utilizes the Gray Level Jump principle to carry out boundary search here, and promptly the border is considered to gray-scale value trip point composition.Fig. 4 carries out the boundary search algorithm flow chart.At first according to the horizontal ordinate scope u that just selects shape
RangAnd v
RangCarry out confirming of search loop direction, if u
Rang＞v
Rang, with horizontal ordinate as loop direction, otherwise be loop direction with the ordinate.Here be example with horizontal ordinate as loop direction, suppose that the origin coordinates of horizontal ordinate is respectively u
StartAnd u
Stop, horizontal ordinate u is at [u
Start, u
Stop] in circulate arbitrfary point coordinate u wherein
i, bring curvilinear equation v=f (u) into, get ordinate v
i, find the solution this p (u simultaneously
i, v
i) tangent slope t=f ' (u) | u=u
i, the tangential tilt angle is θ=atan (t), and is as shown in Figure 5, find the solution this some place perpendicular to the straight-line equation u=tv+u of curve
i+ tv
iAlong carrying out Gray Level Jump search, i.e. [v in the scope of ordinate v on this vertical line
i-dcos (θ), v
i+ dcos (θ)] carry out cyclic search, relatively the gray scale difference of consecutive point finds gradation of image saltus step maximum p ', is the accurate frontier point in selected element p place.Cyclic search obtains all accurate frontier point array data B successively.Then, the data fitting that data array B is carried out given shape constraint like conic fittings such as straight line, circle, ellipses etc., thereby obtains and manually selects irrelevant precise and stable form parameter.
The present invention can carry out the characteristic quantity Boundary Extraction to common straight line, quafric curve regular shapes such as (circle, ellipse, para-curves etc.), and further realize air line distance, the characteristic quantities such as position relation of included angle of straight line, radius of circle, circle calculate.In addition; Selecting the profile peripheral region to carry out Flame Image Process because be; Therefore, for irregularly shaped, as long as the user along the border successively selected element just can realize the characteristic quantity Boundary Extraction of irregular figure; Here adopt B-spline Curve to describing irregularly shaped unification that the user selects
{ P wherein
iBe n+1 reference mark; Any one of variable u is worth point unique on the corresponding continuous curve; { N
I, p(u) } be p B spline base function, p=3 is cubic B-spline here.A carries out the B-spline curves interpolation fitting to the data array, promptly
A={Q wherein
k, k=0 ..., n.That is: n+1 equation can be confirmed in n+1 reference mark; Use least square method to be easy to obtain basis function parameter wherein through the solving equation group; Thereby confirm the B-spline Curve equation; The derivative C ' of curve (u) also just can further calculate, and for the Flame Image Process zone is confirmed, boundary extraction method etc. provides basis, its computation process is all introduced consistent with the front.
Fig. 6 is the actual processing figure of triangle cutting-tool angle (nominal value of cutter is 70.62 °) when measuring that carry out.Table 1 is when same width of cloth cutter photo is carried out measurement of angle; Only adopt and manually select to measure 10 times repeatability; The location point of in these group data, manually selecting is consistent as far as possible; Can find out that from data the change of manually selecting to obtain that takes measurement of an angle has roughly caused about 0.2 ° measurement instability.
Cutter photo to same carries out measurement of angle, is carrying out deliberately having carried out micro-deviation when cutter both sides straight line is selected, but is using method of the present invention to search out needed contour edge equally; Same duplicate measurements 10 times; As shown in table 2, from data, can find out the measurement data quite stable; Basically on two data, come back change, and the deviation of two data is only had an appointment 0.04 °.Can find out that algorithm has goodish stability.
Table 1 is manually selected repeatability
| Sequence number | Angle (°) | Sequence number | Angle (°) |
| 1 | 70.714 | 6 | 70.736 |
| 2 | 70.570 | 7 | 70.480 |
| 3 | 70.737 | 8 | 70.548 |
| 4 | 70.480 | 9 | 70.702 |
| 5 | 70.608 | 10 | 70.516 |
[0031]Table 2 is location repeatability automatically
| Sequence number | Angle (°) | Sequence number | Angle (°) |
| 1 | 70.693 | 6 | 70.651 |
| 2 | 70.693 | 7 | 70.693 |
| 3 | 70.651 | 8 | 70.693 |
| 4 | 70.693 | 9 | 70.693 |
| 5 | 70.693 | 10 | 70.693 |
The Another application instance is that circular hole is measured.When the camera acquisition image, the projective transformation of circular process becomes ellipse, and therefore, actual is to adopt oval correlation parameter to estimate.Point when profile is selected on the artificial selection elliptical aperture carries out the cubic B-spline match then, carries out the extraction of data boundary again, obtains number of boundary strong point shown in Figure 6, obtains accurate oval boundary profile through ellipse fitting, can further find the solution elliptic parameter.
For guaranteeing enforcement of the present invention; Need possess the necessary hardware environment, the image capturing system of promptly building, and the image of collection premeasuring two dimensional character by CCD/COMS video camera, optical lens and image data acquiring card; Then, realize dimensional measurement by following method:
(1) selects some points successively at the two dimensional character profile of images acquired upper edge premeasuring, and the data point image coordinate of selecting is recorded among the array A;
(2) to preselected two dimensional character contour feature array A is carried out corresponding secular equation and confirm that tentatively v=f (u) or u=g (v), are straight line like two dimensional character, then find the solution straight-line equation according to array A; If quafric curve then gets quafric curve or B-spline curves by array A match; If irregular curve is then by array A match B-spline curves;
(3) according to the horizontal ordinate scope u of selected shape
RangAnd v
RangCarry out confirming of search loop direction, if u
Rang＞v
Rang, with horizontal ordinate as loop direction, otherwise be loop direction with the ordinate;
(4) if u
Rang＞v
Rang, and the origin coordinates of hypothesis horizontal ordinate is respectively u
StartAnd u
StopIf arbitrfary point coordinate u
i=u
Start
(5) with u
iBring curvilinear equation v=f (u) into, get ordinate v
i, find the solution this p (u simultaneously
i, v
i) tangent slope t=f ' (u) | u=u
i, the tangential tilt angle is θ=atan (t); Find the solution the straight-line equation u=tv+u of this some place vertical curve
i+ tv
iIf temporary variable Gmax=0, and establish v=v
i-dcos (θ), v
1=v+1;
(6) with v and v
1Bring the vertical line equation into, (u is v) with (u to obtain two coordinate points respectively
1, v
1), the gray scale difference value absolute value G that finds the solution two coordinate points;
(7) if G＞Gmax, then write down coordinate points p '=(u, v); V increases progressively 1, v
1Increase progressively 1;
(8) circulation step (6)-(7) are until v
1=v
i+ dcos (θ), and p ' is stored among the array B, B [u made
i-u
Start]=p ' promptly obtains accurate number of boundary strong point;
(9) circulation step (5)-(8) are until u
i=u
StopObtain all accurate frontier point array data B;
(10) array B is carried out the data fitting of given shape constraint,, thereby obtain the required form parameter like conic fittings such as straight line, circle, ellipses etc.;
(11) if u
Rang≤v
Rang, and the origin coordinates of hypothesis ordinate is respectively v
StartAnd v
StopIf arbitrfary point coordinate v
i=v
Start
(12) with v
iBring curvilinear equation u=g into and (v), get horizontal ordinate u
i, find the solution this p (u simultaneously
i, v
i) tangent slope t=g ' (v) | v=v
i, the tangential tilt angle is θ=atan (t); Find the solution the straight-line equation v=tv+u of this some place vertical curve
i+ tv
iIf temporary variable Gmax=0, and establish u=u
i-dcos (θ), u
1=u+1;
(13) with u and u
1Bring the vertical line equation into, (u is v) with (u to obtain two coordinate points respectively
1, v
1), the gray scale difference value absolute value G that finds the solution two coordinate points;
(14) if G＞Gmax, then write down coordinate points p '=(u, v); U increases progressively 1, u
1Increase progressively 1;
(15) circulation step (13)-(14) are until u
1=u
i+ dcos (θ), and p ' is stored among the array B, B [u made
i-u
Start]=p ' promptly obtains accurate number of boundary strong point;
(16) circulation step (12)-(15) are until v
i=v
StopObtain all accurate frontier point array data B;
(17) array B is carried out the data fitting of given shape constraint,, thereby obtain the required form parameter like conic fittings such as straight line, circle, ellipses etc.
Claims (4)
1. based on the two dimensional character dimension measurement method of image detection, carry out the following step successively:
(1) selects some points successively at the two dimensional character profile of the image upper edge premeasuring of being gathered;
(2) carry out the shape match, confirm the pattern curve of initial option;
(3) pattern curve with this initial option is a center line, expands same pixel distance along the normal vector of this curve to both sides, generates two auditory localization cues respectively, is the zone that the boundary line limits Flame Image Process with these two curves.
(4) utilize the Gray Level Jump method in the zone of the Flame Image Process that is limited, carry out boundary search, extract shape border;
(5) shape border of extracting according to step (4) is carried out the data fitting of given shape constraint, thereby is obtained the required form parameter.
2. the two dimensional character dimension measurement method based on image detection according to claim 1; It is characterized in that; If the two dimensional character of curve is not straight line or quafric curve, step (2) adopts the method for B-spline Curve interpolation, the data point that obtains carrying out the shape match.
3. the two dimensional character dimension measurement method based on image detection according to claim 1 is characterized in that described pixel distance is 10～20 pixels.
4. the two dimensional character dimension measurement method based on image detection according to claim 1; It is characterized in that; If confirm the pattern curve of initial option be v=f (u) or u=g (v); Wherein (u v) is the horizontal ordinate of image coordinate, in step (4) according to horizontal stroke, the ordinate scope u of the pattern curve of initial option
RangAnd v
RangCarry out confirming of search loop direction, if u
Rang＞v
Rang, with horizontal ordinate as loop direction, otherwise be loop direction with the ordinate, utilize the Gray Level Jump method in the zone of the Flame Image Process that is limited, carry out boundary search.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011102417538A CN102425989A (en) | 2011-08-22 | 2011-08-22 | Image detection-based two-dimensional characteristic size measurement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011102417538A CN102425989A (en) | 2011-08-22 | 2011-08-22 | Image detection-based two-dimensional characteristic size measurement method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102425989A true CN102425989A (en) | 2012-04-25 |
Family
ID=45959995
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011102417538A Pending CN102425989A (en) | 2011-08-22 | 2011-08-22 | Image detection-based two-dimensional characteristic size measurement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102425989A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102980535A (en) * | 2012-12-12 | 2013-03-20 | 华为终端有限公司 | Angle measurement method and device |
| CN103630070A (en) * | 2013-04-08 | 2014-03-12 | 苏州工业园区凯艺精密科技有限公司 | Detection method for image detector and image detector |
| CN104655041A (en) * | 2015-01-05 | 2015-05-27 | 山东理工大学 | Industrial part contour line multi-feature extracting method with additional constraint conditions |
| CN105258681A (en) * | 2015-10-08 | 2016-01-20 | 凌云光技术集团有限责任公司 | Control for curve edge feature location and location method thereof |
| CN105865326A (en) * | 2015-01-21 | 2016-08-17 | 成都理想境界科技有限公司 | Object size measurement method and image database data acquisition method |
| CN106989672A (en) * | 2017-04-17 | 2017-07-28 | 天津大学 | A kind of workpiece measuring based on machine vision |
| CN107144222A (en) * | 2017-06-28 | 2017-09-08 | 中国航发南方工业有限公司 | Standard enlarged drawing measuring method, measurement apparatus and measuring system |
| CN108868742A (en) * | 2018-06-08 | 2018-11-23 | 中国石油天然气股份有限公司 | Determine the method, apparatus and storage medium in the source of tubing trouble of lost tool in hole |
| CN110641947A (en) * | 2019-10-16 | 2020-01-03 | 山东中衡光电科技有限公司 | Intelligent inspection robot system for bulk cargo conveyor and detection method thereof |
| CN112414316A (en) * | 2020-10-28 | 2021-02-26 | 西北工业大学 | Strain gauge sensitive grid size parameter measuring method |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0157299A1 (en) * | 1984-03-26 | 1985-10-09 | Hitachi, Ltd. | Image processing apparatus |
| CN1667351A (en) * | 2005-04-06 | 2005-09-14 | 北京航空航天大学 | Method for automatically extracting image feature points of workpiece with rough grain under the strong reflection background |
| CN1835547A (en) * | 2005-03-14 | 2006-09-20 | 株式会社其恩斯 | Image processing device and registration data generation method in image processing |
| US20080281543A1 (en) * | 2007-05-07 | 2008-11-13 | General Electric Company | Inspection system and methods with autocompensation for edge break gauging orientation |
| CN101558282A (en) * | 2007-02-13 | 2009-10-14 | 松下电器产业株式会社 | Image processing system, method, device and image format |
| CN101593272A (en) * | 2009-06-18 | 2009-12-02 | 电子科技大学 | A kind of human face characteristic positioning method based on the ASM algorithm |
| CN101620676A (en) * | 2009-07-02 | 2010-01-06 | 浙江省电力公司 | Fast image recognition method of insulator contour |
| CN101629805A (en) * | 2008-07-16 | 2010-01-20 | 中国科学院沈阳自动化研究所 | Method for measuring railway tank car volume based on computer vision |
| CN101685000A (en) * | 2008-09-25 | 2010-03-31 | 鸿富锦精密工业（深圳）有限公司 | Computer system and method for image boundary scan |
| CN101694376A (en) * | 2009-10-23 | 2010-04-14 | 北京航空航天大学 | Optical stripe sine evaluating method |
| CN101726256A (en) * | 2008-10-27 | 2010-06-09 | 鸿富锦精密工业（深圳）有限公司 | Computer system and method for searching inflection point from image contour |
| US20100166283A1 (en) * | 2008-12-30 | 2010-07-01 | Stefan Grosskopf | Method for determining a 2d contour of a vessel structure imaged in 3d image data |
| CN101894370A (en) * | 2010-07-14 | 2010-11-24 | 苏州大学 | Automatic generation method of shape parameter-adaptive oracle-bone inscription contour glyphs |
-
2011
- 2011-08-22 CN CN2011102417538A patent/CN102425989A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0157299A1 (en) * | 1984-03-26 | 1985-10-09 | Hitachi, Ltd. | Image processing apparatus |
| CN1835547A (en) * | 2005-03-14 | 2006-09-20 | 株式会社其恩斯 | Image processing device and registration data generation method in image processing |
| CN1667351A (en) * | 2005-04-06 | 2005-09-14 | 北京航空航天大学 | Method for automatically extracting image feature points of workpiece with rough grain under the strong reflection background |
| CN101558282A (en) * | 2007-02-13 | 2009-10-14 | 松下电器产业株式会社 | Image processing system, method, device and image format |
| US20080281543A1 (en) * | 2007-05-07 | 2008-11-13 | General Electric Company | Inspection system and methods with autocompensation for edge break gauging orientation |
| CN101629805A (en) * | 2008-07-16 | 2010-01-20 | 中国科学院沈阳自动化研究所 | Method for measuring railway tank car volume based on computer vision |
| CN101685000A (en) * | 2008-09-25 | 2010-03-31 | 鸿富锦精密工业（深圳）有限公司 | Computer system and method for image boundary scan |
| CN101726256A (en) * | 2008-10-27 | 2010-06-09 | 鸿富锦精密工业（深圳）有限公司 | Computer system and method for searching inflection point from image contour |
| US20100166283A1 (en) * | 2008-12-30 | 2010-07-01 | Stefan Grosskopf | Method for determining a 2d contour of a vessel structure imaged in 3d image data |
| CN101593272A (en) * | 2009-06-18 | 2009-12-02 | 电子科技大学 | A kind of human face characteristic positioning method based on the ASM algorithm |
| CN101620676A (en) * | 2009-07-02 | 2010-01-06 | 浙江省电力公司 | Fast image recognition method of insulator contour |
| CN101694376A (en) * | 2009-10-23 | 2010-04-14 | 北京航空航天大学 | Optical stripe sine evaluating method |
| CN101894370A (en) * | 2010-07-14 | 2010-11-24 | 苏州大学 | Automatic generation method of shape parameter-adaptive oracle-bone inscription contour glyphs |
Non-Patent Citations (2)
| Title |
|---|
| 吴良武等: "保持轮廓清晰光滑的灰度图像放大算法", 《计算机辅助设计与图形学学报》 * |
| 黄劼: "曲面孔位机器视觉测量系统研究", 《中国优秀博士学位论文全文数据库》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102980535A (en) * | 2012-12-12 | 2013-03-20 | 华为终端有限公司 | Angle measurement method and device |
| CN103630070A (en) * | 2013-04-08 | 2014-03-12 | 苏州工业园区凯艺精密科技有限公司 | Detection method for image detector and image detector |
| CN104655041A (en) * | 2015-01-05 | 2015-05-27 | 山东理工大学 | Industrial part contour line multi-feature extracting method with additional constraint conditions |
| CN104655041B (en) * | 2015-01-05 | 2018-11-23 | 山东理工大学 | A kind of industrial part contour line multi-feature extraction method of additional constraint condition |
| CN105865326A (en) * | 2015-01-21 | 2016-08-17 | 成都理想境界科技有限公司 | Object size measurement method and image database data acquisition method |
| CN105258681A (en) * | 2015-10-08 | 2016-01-20 | 凌云光技术集团有限责任公司 | Control for curve edge feature location and location method thereof |
| CN105258681B (en) * | 2015-10-08 | 2017-11-03 | 凌云光技术集团有限责任公司 | A kind of control and its localization method for curved edge feature location |
| CN106989672A (en) * | 2017-04-17 | 2017-07-28 | 天津大学 | A kind of workpiece measuring based on machine vision |
| CN107144222A (en) * | 2017-06-28 | 2017-09-08 | 中国航发南方工业有限公司 | Standard enlarged drawing measuring method, measurement apparatus and measuring system |
| CN108868742A (en) * | 2018-06-08 | 2018-11-23 | 中国石油天然气股份有限公司 | Determine the method, apparatus and storage medium in the source of tubing trouble of lost tool in hole |
| CN110641947A (en) * | 2019-10-16 | 2020-01-03 | 山东中衡光电科技有限公司 | Intelligent inspection robot system for bulk cargo conveyor and detection method thereof |
| CN112414316A (en) * | 2020-10-28 | 2021-02-26 | 西北工业大学 | Strain gauge sensitive grid size parameter measuring method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102425989A (en) | Image detection-based two-dimensional characteristic size measurement method | |
| Park et al. | Three-dimensional tracking of construction resources using an on-site camera system | |
| CN107025663B (en) | Clutter scoring system and method for 3D point cloud matching in vision system | |
| KR102035030B1 (en) | Automatic drawing method using lane information | |
| CN103400366B (en) | Based on the dynamic scene depth acquisition methods of fringe structure light | |
| US8315425B2 (en) | Method for comparison of 3D computer model and as-built situation of an industrial plant | |
| US20140362082A1 (en) | Automated Overpass Extraction from Aerial Imagery | |
| ATE525710T1 (en) | POSITION DETERMINATION THROUGH VIDEO NAVIGATION SYSTEM AND METHOD | |
| KR101858902B1 (en) | System for extracting position information of object in point cloud data by using component | |
| Chen et al. | Determination of stripe edge blurring for depth sensing | |
| DeWitt et al. | Creating high-resolution bare-earth digital elevation models (DEMs) from stereo imagery in an area of densely vegetated deciduous forest using combinations of procedures designed for lidar point cloud filtering | |
| CN104732553A (en) | Feature point extraction method based on multiple laser-assisted targets | |
| CN105389774A (en) | Method and device for aligning images | |
| US20140125667A1 (en) | Roof Generation And Texturing Of 3D Models | |
| CN103093223A (en) | Light spot image center quick locating method | |
| CN105222727A (en) | The measuring method of linear array CCD camera imaging plane and the worktable depth of parallelism and system | |
| CN103913166A (en) | Star extraction method based on energy distribution | |
| CN101776437A (en) | Calibration technology for vision sub-pixel of embedded type machine with optical path adjustment | |
| JP2023029441A (en) | Measuring device, measuring system, and vehicle | |
| JP2010506337A (en) | System and method for visualizing and measuring real-world 3-D spatial data | |
| Kaiser et al. | Automatic co-registration of photogrammetric point clouds with digital building models | |
| CN102360503A (en) | SAR (Specific Absorption Rate) image change detection method based on space approach degree and pixel similarity | |
| WO2012133371A1 (en) | Image capture position and image capture direction estimation device, image capture device, image capture position and image capture direction estimation method and program | |
| CN104537627A (en) | Depth image post-processing method | |
| CN110068826A (en) | A kind of method and device of ranging |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120425 |