CN105043250A - Dual-view-angle data alignment method based on at least two common mark points - Google Patents
Dual-view-angle data alignment method based on at least two common mark points Download PDFInfo
- Publication number
- CN105043250A CN105043250A CN201510289607.0A CN201510289607A CN105043250A CN 105043250 A CN105043250 A CN 105043250A CN 201510289607 A CN201510289607 A CN 201510289607A CN 105043250 A CN105043250 A CN 105043250A
- Authority
- CN
- China
- Prior art keywords
- gauge point
- point
- image space
- visual angle
- order
- 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 46
- 230000000007 visual effect Effects 0.000 claims description 33
- 230000008878 coupling Effects 0.000 claims description 13
- 238000010168 coupling process Methods 0.000 claims description 13
- 238000005859 coupling reaction Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 11
- 238000003384 imaging method Methods 0.000 claims description 10
- 230000009466 transformation Effects 0.000 claims description 7
- 230000002093 peripheral effect Effects 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 238000005259 measurement Methods 0.000 abstract description 21
- 230000007246 mechanism Effects 0.000 description 10
- 230000007423 decrease Effects 0.000 description 6
- 238000012913 prioritisation Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 230000000903 blocking effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a dual-view-angle data alignment method based on at least two common mark points, which comprises the steps of reconstructing mark point central positions and normal vector information at adjacent view angles, and calculating a rotation-translation relation of the adjacent view angles based on the reconstructed common mark point central positions and the normal vector information. Compared with a traditional data alignment method which only depends on the mark point central positions, the method disclosed by the invention can make full of the information provided by the mark points, and reliable data alignment can be realized by only seeing two common mark points at the adjacent view angles, thereby reducing the number of mark points required to be attached to the surface of an object and covering of the mark points for the measured object. The dual-view-angle data alignment method disclosed by the invention is easy to implement and reliable in result, and can be applied to any fields in which mark points are adopted to assist to alignment of different view-angle measurement data.
Description
Technical field
The present invention relates to a kind of Double-visual angle data alignment method based at least two common indicium points, belong to image procossing and vision measurement field.
Background technology
Vision measurement is a kind of technology utilizing collected by camera object being measured surface image also therefrom to recover its three-dimensional profile.Line-structured light is measured and area-structure light measurement is two kinds of implementations conventional in many vision measuring methods.No matter adopting which kind of vision measuring method, in order to obtain complete body surface data, needing to measure object with multiple angle in multiple position.This is with regard under needing the measurement data of different coordinates under multiple angle to be fused to a unified coordinate system, to correct because the data dislocation brought is moved in measurement mechanism position.
At present, under different visual angles of aliging, the algorithm of measurement data roughly can be divided into the method based on motion, the method based on ICP and method three class based on gauge point:
Then first kind method relies on the numerical value reading motion scrambler to obtain the transformation relation of coordinate system between visual angle, as measurement mechanism is arranged on sixdegree-of-freedom simulation by the people such as Lin Na by being fixed on by measurement mechanism on specific motion; Measurement mechanism combines with rotation platform and measures by the people such as Wu Yu.Adopting the defect of carrying out alignment of data is in this way, the working range of measurement mechanism is subject to the restriction of motion stroke, and easily forms measurement dead angle.
Equations of The Second Kind method using two perspective data middle distance closest approaches as match point, and calculate according to this one rotate translation relation.Carry out above-mentioned steps iteratively, namely can draw final Double-visual angle transformation relation.But this method is only applicable to area-structure light metering system, and there is requirement to two perspective data initial positional relationship, if data dislocation is serious, then likely can not get correct alignment result.
3rd class methods are passed through at object being measured surface mount gauge point, and the common indicium point (for computational stability generally adopts four) utilizing the topological relation at gauge point center to search in two visual angles realizes alignment of data.Because gauge point center has very high positioning precision, therefore, the data fusion precision based on the method is very high.Meanwhile, owing to there is no the constraint of motion, can infinitely splice in theory.But gauge point covers object parts surface, therefore, the data of the part that is blocked can only rely on the later stage to repair and obtain, have impact on integrality and the accuracy of data acquisition.
Summary of the invention
Technical matters to be solved by this invention is to provide a kind of Double-visual angle data alignment method based at least two common indicium points, gauge point quantity has been reduced to two by the present invention, decrease the quantity at object exterior pasting gauge point, and then decrease the body surface area being labeled and a little blocking, improve the integrality of data.
The present invention is for solving the problems of the technologies described above by the following technical solutions:
The invention provides a kind of Double-visual angle data alignment method based at least two common indicium points, Double-visual angle has two common indicium points at least, and the method includes the steps of:
Step 1, object being measured pastes circular markers, and left and right order camera takes object being measured respectively, obtains left and right order image;
Step 2, extracts gauge point edge imaging position in the left and right order image obtained from step 1, utilizes ellipse fitting algorithm to obtain left and right target note dot center image space;
Step 3, carries out Stereo matching by the left and right target note dot center image space obtained in step 2, and according to matching result, completes the coupling of gauge point edge imaging position in the order image of left and right;
Step 4, utilizes binocular trigonometry to rebuild the three-dimensional coordinate of gauge point center and peripheral position;
Step 5, utilizes step 4 to rebuild the three-dimensional coordinate fit Plane of the gauge point center and peripheral position obtained, obtains the normal information of gauge point place part plan;
Step 6, under another visual angle, utilizes left and right order camera to take object being measured respectively, repeats step 2 ~ step 5, obtains the three-dimensional coordinate at the gauge point center under this visual angle and the normal information of place part plan thereof;
Step 7, searches for the common indicium point under two visual angles, utilizes the central three-dimensional coordinate of common indicium point and the normal information of place part plan thereof that search, calculates coordinate system between two visual angles and rotates translation relation, thus complete Double-visual angle alignment of data.
As further prioritization scheme of the present invention, the circular markers in step 1 is coding or non-coding gauge point.
As further prioritization scheme of the present invention, position binding mark point comparatively smooth on object being measured in step 1.
As further prioritization scheme of the present invention, in step 1, the intrinsic parameter of left and right order camera and the rigid body transformation relation of left and right order camera coordinates system are demarcated in advance.
As further prioritization scheme of the present invention, in step 3, the left and right target note dot center image space obtained in step 2 is carried out Stereo matching, concrete steps are as follows:
If 5.1 adopt circle codification gauge point, then the encoded radio according to gauge point completes left and right target note dot center image space Stereo matching;
If 5.2 adopt non-coding gauge point, then according to being divided into following two kinds:
1) if adopt area-structure light principle to carry out single-view DATA REASONING, then the phase value relying on gauge point center image space completes Stereo matching, is specially:
1. for any gauge point center image space in left order, its polar curve equation in right order image is calculated according to the fundamental matrix of left order camera;
2. search for the gauge point center image space being arranged in 1. polar curve both sides in right order image, find wherein remember with left target dot center's image space phase place immediate that as matched pixel point, complete the coupling of left and right target note dot center image space;
2) if adopt line-structured light principle to carry out single-view DATA REASONING, be then specially:
1. for any gauge point center image space in left order, its polar curve equation in right order image is calculated according to the fundamental matrix of left order camera;
2. the gauge point center image space being positioned at polar curve both sides in right order image is searched for, as the potential match point of left target note dot center image space;
3. gradient of disparity is utilized to retrain structure Matching support function;
4. by relaxation method Optimized Matching function for support, the coupling of left and right target note dot center image space is completed.
As further prioritization scheme of the present invention, mark the coupling of point edge image space in the order image of left and right in step 3, concrete steps are as follows:
6.1 choose arbitrarily 1 p in left target note point edge image space
l, calculate its polar curve equation L in right order image according to the fundamental matrix of left order camera
l;
The ellipse of all gauge point edge imaging position matching gained in the right order image of 6.2 note is e
r, find polar curve L
lwith oval e
rtwo intersection point p
r1and p
r2;
6.3 hypothesis left and right order matched indicia dot center image spaces are c
land c
r, then according to Stereo matching Ordinal Consistency principle, choose
with
in with vector
the little person of angle, as match point, completes p
lthe coupling of edge imaging position in the order image of left and right at place.
As further prioritization scheme of the present invention, the topological relation searched in step 7 between the common indicium point dependence gauge point under two visual angles has come.
The present invention adopts above technical scheme compared with prior art, has following technique effect:
1. relative to the method that tradition is alignd based on gauge point, minimum gauge point used for alignment is reduced to 2 by 4 by the method for the invention, which reduce the quantity at object exterior pasting gauge point, and then decrease the body surface area being labeled and a little blocking, improve the integrality of data;
2. owing to only needing to see two common indicium points in adjacent view, therefore, the measurement mechanism adopting the inventive method to carry out alignment of data can have measures attitude more flexibly, greatly facilitates measurement operation, decreases the existence of measuring dead angle;
3. result of calculation of the present invention, can for providing good iterative initial value based on the alignment schemes of ICP;
4. the present invention can be applicable to all needs to rely on circular markers to carry out the occasion of two visual angle measured data registration, and the line-structured light such as based on laser is measured, white light measurement and the measurement of TOF camera etc.
Accompanying drawing explanation
Fig. 1 is the invention process many laser line scannings device schematic diagram used.
Wherein, about 1-order camera; 2-mono-wordline generating laser; 3-skeleton.
Fig. 2 is the process flow diagram that application this method carries out Double-visual angle measured data registration.
Fig. 3 is gauge point edge matching schematic diagram.
Embodiment
Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:
Fig. 1 is the present embodiment line-structured light measurement mechanism used, and it is made up of left and right order camera and a wordline generating laser.Left and right order camera all adopts the DMK23U445 industrial camera of TheImagingSource company, and its sensor is 1/3 " CCD, the way of output is USB3.0, and ComputarM0814-MP2 Megapixel prime lens selected by camera lens; Two cameras are rigidly connected by skeleton, and order camera angle of optical axis, left and right is about 40 °, and parallax range is about 25cm.One word line laser device is positioned at two camera centre positions.Before enforcement concrete steps, measurement mechanism parameter is demarcated, and described parameter comprises: the rigid body translation parameter between left and right order camera intrinsic parameter, left and right order camera coordinates system and optic plane equations.
As shown in Figure 2, applying this method, to carry out the concrete steps of Double-visual angle alignment of data as follows:
Step 1: at object being measured surface mount non-coding circular markers.
Step 2: call camera driver, utilizes left and right order camera shooting measured object volume image, remembers that the left and right order image gathered is I respectively
land I
r.Suppose left order image I
lon have m
1individual gauge point, right order image I
ron have n
1individual gauge point.
Step 3: the image space extracting the non-coding circular markers in left and right order image, its key step is as follows:
1) Canny edge extracting is carried out to image;
2) each edge line at Canny edge is verified, and filtering edge length or edge minimum area-encasing rectangle major and minor axis ratio exceeds the edge line of zone of reasonableness;
3) edge line after utilizing Equation of ellipse matching to filter, and filtering error of fitting exceeds the edge of tolerance limit ε further, obtains marked circle center image space eventually through Equation of ellipse.
Step 4: coupling left and right target note dot center image space, key step is as follows:
1) for any marked circle center image space in left order, its polar curve equation in right order image is calculated according to camera fundamental matrix.
2) the gauge point center image space being positioned at polar curve both sides in right order image is searched for, as the potential match point of left target note dot center image space.
3) utilize gradient of disparity to retrain and construct Matching support function.
4) coupling at gauge point center is completed by relaxation method Optimized Matching function for support.
Step 5: coupling left and right target note point edge image space, as shown in Figure 3, for the oval e of the left order mating center image space
le oval with right order
r, adopt following steps 1) and to step 3) complete edge imaging location matches:
1) 1 p in the imaging of left target note rounded edge is chosen arbitrarily
l, calculate its polar curve equation L in right order image according to camera fundamental matrix
l.
2) remember that all image space matching gained ellipses of this gauge point edge in right order image are e
r, and find described polar curve L
lwith oval e
rtwo intersection point p
r1and p
r2.
3) suppose that left and right order matched indicia dot center image space is c
land c
r, according to Stereo matching Ordinal Consistency principle, choose
with
in with vector
the little person of angle as match point (as the p in Fig. 3
r1point).
Step 6: utilize binocular trigonometry to rebuild the three-dimensional coordinate of gauge point center and peripheral position, be specially:
According to matching relationship and measurement mechanism parameter, calculate each dot center of matched indicia and the three-dimensional coordinate of marginal point under left order camera coordinates system.Suppose any one matched indicia point image space in left and right order image be respectively p
l(u
l, v
l) and p
r(u
r, v
r), and there is rigid body transformation relation R, T between two camera coordinate systems.Remember that this some coordinate under left and right order camera coordinates system is respectively (x
l, y
l, z
l), (x
r, y
r, z
r), according to national forest park in Xiaokeng
Again, according to left and right order camera position transformation relation
Above-mentioned three expression formulas of simultaneous, can this coordinate under left camera coordinates system be:
Wherein, A=(u
r-c
rx)/f
rx, B=(v
r-c
ry)/f
ry, C=(u
l-c
lx)/f
lx, D=(v
l-c
ly)/f
ly, f
lx, f
ly, f
rx, f
rybe respectively the focal length of left and right order camera, (c
lx, c
ly), (c
rx, c
ry) be respectively order camera image center, left and right.
Step 7: the normal vector of matching gauge point place part plan, be specially: respectively plane fitting is carried out to the center and peripheral three-dimensional coordinate of each gauge point of step 6 gained, obtain the normal information of its place part plan of gauge point, and ensure that the z-axis component of earning approach vector is greater than 0, the ambiguity pointed to null method vector.
Step 8: traverse measuring device to next visual angle, and takes left and right order image, should ensure that two visual angles at least exist two common indicium points time mobile.
Step 9: process according to step 3 ~ step 7 image under the second visual angle, obtains the three-dimensional coordinate at the gauge point center under this visual angle and the normal information of place part plan thereof.
Step 10: search for the common indicium point in the first visual angle and the second visual angle.Suppose that the gauge point quantity reconstructed in first and second visual angle is respectively m and n, so, for any gauge point in the first visual angle
the scheme that dependence topological relation searches for its correspondence markings point in the second visual angle is as follows:
1) calculate
under the first visual angle, the distance at other gauge point centers, obtains distance vector
for
distance alpha=1 at other α gauge point center under the first visual angle, 2 ..., m-1;
2) for each gauge point in the second visual angle, calculate its distance to other gauge point centers under this visual angle, obtain following Distance matrix D
2:
Wherein,
it is the arbitrary gauge point in the second visual angle
the distance vector at other gauge point centers under this visual angle,
for
the distance at other β gauge point center under this visual angle, j=1,2 ..., n;
3) will
successively with
compare, and find the number wherein comprising identical element.Decision element
with
identical criterion is
wherein δ is feature tolerance.Will
with
the number of middle identical element is filled in vectorial N in turn, N=[n
1n
2n
n].
4) the sequence number k of greatest member in vectorial N is found, k=1,2 ..., n, if this element value is greater than 3, judge
set up with the reference points matching relation of the kth in the second visual angle.
Step 11: utilize the common indicium point searched, calculates coordinate system between two visual angles by biquaternion method and rotates translation relation, the rigid transformation relation R namely between two visual angles and T, thus complete Double-visual angle alignment of data.
Suppose to search g (g>=2) common indicium point altogether, the normal information of its three-dimensional coordinate and place part plan thereof under the first angular view coordinate system is expressed as
be expressed as under the second angular view coordinate system
concrete solution procedure is as follows:
1) compute matrix C
1, C
2
Wherein,
γ=[γ
x, γ
y, γ
z] be Arbitrary 3 D vector;
2) 4 × 4 symmetric matrix A are calculated,
3) calculate the eigen vector of A, in note eigenwert, maximum that is λ
1, its characteristic of correspondence vector is γ;
4) R, T so, is calculated as follows:
T=-W
T(γ)·C
2·γ
A kind of Double-visual angle data alignment method based at least two common indicium points of the present invention, propose a kind of data alignment method based on gauge point center and normal information, minimum gauge point used for alignment is reduced to 2 by 4, which reduce the quantity at object exterior pasting gauge point, and then decrease the body surface area being labeled and a little blocking, improve the integrality of data; Meanwhile, owing to only needing to see two common indicium points in adjacent view, therefore, the measurement mechanism adopting the inventive method to carry out alignment of data can have measures attitude more flexibly, greatly facilitates measurement operation, decreases the existence of measuring dead angle.
The above; be only the embodiment in the present invention; but protection scope of the present invention is not limited thereto; any people being familiar with this technology is in the technical scope disclosed by the present invention; the conversion or replacement expected can be understood; all should be encompassed in and of the present inventionly comprise within scope, therefore, protection scope of the present invention should be as the criterion with the protection domain of claims.
Claims (7)
1. based on a Double-visual angle data alignment method at least two common indicium points, it is characterized in that, Double-visual angle has two common indicium points at least, and the method includes the steps of:
Step 1, object being measured pastes circular markers, and left and right order camera takes object being measured respectively, obtains left and right order image;
Step 2, extracts gauge point edge imaging position in the left and right order image obtained from step 1, utilizes ellipse fitting algorithm to obtain left and right target note dot center image space;
Step 3, carries out Stereo matching by the left and right target note dot center image space obtained in step 2, and according to matching result, completes the coupling of gauge point edge imaging position in the order image of left and right;
Step 4, utilizes binocular trigonometry to rebuild the three-dimensional coordinate of gauge point center and peripheral position;
Step 5, utilizes step 4 to rebuild the three-dimensional coordinate fit Plane of the gauge point center and peripheral position obtained, obtains the normal information of gauge point place part plan;
Step 6, under another visual angle, utilizes left and right order camera to take object being measured respectively, repeats step 2 ~ step 5, obtains the three-dimensional coordinate at the gauge point center under this visual angle and the normal information of place part plan thereof;
Step 7, searches for the common indicium point under two visual angles, utilizes the central three-dimensional coordinate of common indicium point and the normal information of place part plan thereof that search, calculates coordinate system between two visual angles and rotates translation relation, thus complete Double-visual angle alignment of data.
2. a kind of Double-visual angle data alignment method based at least two common indicium points according to claim 1, is characterized in that, the circular markers in step 1 is coding or non-coding gauge point.
3. a kind of Double-visual angle data alignment method based at least two common indicium points according to claim 1, is characterized in that, position binding mark point comparatively smooth on object being measured in step 1.
4. a kind of Double-visual angle data alignment method based at least two common indicium points according to claim 1, is characterized in that, in step 1, the intrinsic parameter of left and right order camera and the rigid body transformation relation of left and right order camera coordinates system are demarcated in advance.
5. a kind of Double-visual angle data alignment method based at least two common indicium points according to claim 2, is characterized in that, in step 3, the left and right target note dot center image space obtained in step 2 is carried out Stereo matching, concrete steps are as follows:
If 5.1 adopt circle codification gauge point, then the encoded radio according to gauge point completes left and right target note dot center image space Stereo matching;
If 5.2 adopt non-coding gauge point, then according to being divided into following two kinds:
1) if adopt area-structure light principle to carry out single-view DATA REASONING, then the phase value relying on gauge point center image space completes Stereo matching, is specially:
1. for any gauge point center image space in left order, its polar curve equation in right order image is calculated according to the fundamental matrix of left order camera;
2. search for the gauge point center image space being arranged in 1. polar curve both sides in right order image, find wherein remember with left target dot center's image space phase place immediate that as matched pixel point, complete the coupling of left and right target note dot center image space;
2) if adopt line-structured light principle to carry out single-view DATA REASONING, be then specially:
1. for any gauge point center image space in left order, its polar curve equation in right order image is calculated according to the fundamental matrix of left order camera;
2. the gauge point center image space being positioned at polar curve both sides in right order image is searched for, as the potential match point of left target note dot center image space;
3. gradient of disparity is utilized to retrain structure Matching support function;
4. by relaxation method Optimized Matching function for support, the coupling of left and right target note dot center image space is completed.
6. a kind of Double-visual angle data alignment method based at least two common indicium points according to claim 1, is characterized in that, mark the coupling of point edge image space in the order image of left and right in step 3, concrete steps are as follows:
6.1 choose arbitrarily 1 p in left target note point edge image space
l, calculate its polar curve equation L in right order image according to the fundamental matrix of left order camera
l;
The ellipse of all gauge point edge imaging position matching gained in the right order image of 6.2 note is e
r, find polar curve L
lwith oval e
rtwo intersection point p
r1and p
r2;
6.3 hypothesis left and right order matched indicia dot center image spaces are c
land c
r, then according to Stereo matching Ordinal Consistency principle, choose
with
in with vector
the little person of angle, as match point, completes p
lthe coupling of edge imaging position in the order image of left and right at place.
7. a kind of Double-visual angle data alignment method based at least two common indicium points according to claim 1, is characterized in that, the topological relation searched in step 7 between the common indicium point dependence gauge point under two visual angles has come.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510289607.0A CN105043250B (en) | 2015-05-29 | 2015-05-29 | A kind of double-visual angle data alignment method based on 1 common indicium points |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510289607.0A CN105043250B (en) | 2015-05-29 | 2015-05-29 | A kind of double-visual angle data alignment method based on 1 common indicium points |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105043250A true CN105043250A (en) | 2015-11-11 |
CN105043250B CN105043250B (en) | 2017-08-11 |
Family
ID=54449990
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510289607.0A Expired - Fee Related CN105043250B (en) | 2015-05-29 | 2015-05-29 | A kind of double-visual angle data alignment method based on 1 common indicium points |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105043250B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106524904A (en) * | 2016-09-19 | 2017-03-22 | 天津大学 | Rapid mutual scanning directional method for multiple laser trackers |
CN107192348A (en) * | 2016-03-14 | 2017-09-22 | 武汉小狮科技有限公司 | A kind of high-precision 3D vision measuring methods |
CN108519215A (en) * | 2018-03-28 | 2018-09-11 | 华勤通讯技术有限公司 | Interpupillary distance adaptive testing system and method, test main frame |
CN110006370A (en) * | 2019-05-10 | 2019-07-12 | 苏州大学 | The concentricity automatic calibration method of multiaxis grinding device, device and system |
CN111833392A (en) * | 2019-04-16 | 2020-10-27 | 杭州思看科技有限公司 | Multi-angle scanning method, system and device for mark points |
CN112033286A (en) * | 2020-08-19 | 2020-12-04 | 哈尔滨工业大学 | Binocular vision-based structural six-degree-of-freedom motion measurement system and measurement method thereof |
CN113012126A (en) * | 2021-03-17 | 2021-06-22 | 武汉联影智融医疗科技有限公司 | Mark point reconstruction method and device, computer equipment and storage medium |
CN113074661A (en) * | 2021-03-26 | 2021-07-06 | 华中科技大学 | Projector corresponding point high-precision matching method based on polar line sampling and application thereof |
CN114322849A (en) * | 2020-09-29 | 2022-04-12 | 昆山午力电子有限公司 | Article characteristic positioning system based on image recognition |
CN115439630A (en) * | 2022-08-04 | 2022-12-06 | 思看科技(杭州)股份有限公司 | Mark point splicing method, photogrammetry method, device and electronic device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07287764A (en) * | 1995-05-08 | 1995-10-31 | Omron Corp | Stereoscopic method and solid recognition device using the method |
EP1175104A2 (en) * | 2000-07-19 | 2002-01-23 | Pohang University of Science and Technology Foundation | Stereoscopic image disparity measuring system |
CN103236064A (en) * | 2013-05-06 | 2013-08-07 | 东南大学 | Point cloud automatic registration method based on normal vector |
CN103542981A (en) * | 2013-09-28 | 2014-01-29 | 大连理工大学 | Method for measuring rotary inertia through binocular vision |
CN104484648A (en) * | 2014-11-27 | 2015-04-01 | 浙江工业大学 | Variable-viewing angle obstacle detection method for robot based on outline recognition |
-
2015
- 2015-05-29 CN CN201510289607.0A patent/CN105043250B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07287764A (en) * | 1995-05-08 | 1995-10-31 | Omron Corp | Stereoscopic method and solid recognition device using the method |
EP1175104A2 (en) * | 2000-07-19 | 2002-01-23 | Pohang University of Science and Technology Foundation | Stereoscopic image disparity measuring system |
CN103236064A (en) * | 2013-05-06 | 2013-08-07 | 东南大学 | Point cloud automatic registration method based on normal vector |
CN103542981A (en) * | 2013-09-28 | 2014-01-29 | 大连理工大学 | Method for measuring rotary inertia through binocular vision |
CN104484648A (en) * | 2014-11-27 | 2015-04-01 | 浙江工业大学 | Variable-viewing angle obstacle detection method for robot based on outline recognition |
Non-Patent Citations (2)
Title |
---|
杨苗: "基于双目立体视觉的3D检测***优化研究", 《中国优秀硕士学位论文全文数据库(电子期刊)信息科技辑》 * |
聂建辉: "自标定实物数字化技术研究", 《《中国博士学位论文全文数据库(电子期刊)工程科技Ⅱ辑》 * |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107192348A (en) * | 2016-03-14 | 2017-09-22 | 武汉小狮科技有限公司 | A kind of high-precision 3D vision measuring methods |
CN106524904B (en) * | 2016-09-19 | 2018-01-12 | 天津大学 | A kind of more laser trackers quickly mutually take aim at orientation method |
CN106524904A (en) * | 2016-09-19 | 2017-03-22 | 天津大学 | Rapid mutual scanning directional method for multiple laser trackers |
CN108519215B (en) * | 2018-03-28 | 2020-10-16 | 华勤技术有限公司 | Pupil distance adaptability test system and method and test host |
CN108519215A (en) * | 2018-03-28 | 2018-09-11 | 华勤通讯技术有限公司 | Interpupillary distance adaptive testing system and method, test main frame |
CN111833392A (en) * | 2019-04-16 | 2020-10-27 | 杭州思看科技有限公司 | Multi-angle scanning method, system and device for mark points |
CN110006370A (en) * | 2019-05-10 | 2019-07-12 | 苏州大学 | The concentricity automatic calibration method of multiaxis grinding device, device and system |
CN112033286A (en) * | 2020-08-19 | 2020-12-04 | 哈尔滨工业大学 | Binocular vision-based structural six-degree-of-freedom motion measurement system and measurement method thereof |
CN114322849A (en) * | 2020-09-29 | 2022-04-12 | 昆山午力电子有限公司 | Article characteristic positioning system based on image recognition |
CN113012126A (en) * | 2021-03-17 | 2021-06-22 | 武汉联影智融医疗科技有限公司 | Mark point reconstruction method and device, computer equipment and storage medium |
CN113012126B (en) * | 2021-03-17 | 2024-03-22 | 武汉联影智融医疗科技有限公司 | Method, device, computer equipment and storage medium for reconstructing marking point |
CN113074661A (en) * | 2021-03-26 | 2021-07-06 | 华中科技大学 | Projector corresponding point high-precision matching method based on polar line sampling and application thereof |
CN113074661B (en) * | 2021-03-26 | 2022-02-18 | 华中科技大学 | Projector corresponding point high-precision matching method based on polar line sampling and application thereof |
CN115439630A (en) * | 2022-08-04 | 2022-12-06 | 思看科技(杭州)股份有限公司 | Mark point splicing method, photogrammetry method, device and electronic device |
CN115439630B (en) * | 2022-08-04 | 2024-04-19 | 思看科技(杭州)股份有限公司 | Mark point splicing method, photogrammetry method, device and electronic device |
Also Published As
Publication number | Publication date |
---|---|
CN105043250B (en) | 2017-08-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105043250A (en) | Dual-view-angle data alignment method based on at least two common mark points | |
CN109000582B (en) | Scanning method and system of tracking type three-dimensional scanning device, storage medium and equipment | |
CN102435188B (en) | Monocular vision/inertia autonomous navigation method for indoor environment | |
CN102679959B (en) | Omnibearing 3D (Three-Dimensional) modeling system based on initiative omnidirectional vision sensor | |
CN100429476C (en) | Double-sensor laser visual measuring system calibrating method | |
WO2016037486A1 (en) | Three-dimensional imaging method and system for human body | |
CN103927739B (en) | A kind of rover localization method based on stitching image | |
CN105913410A (en) | Long-distance moving object height measurement apparatus and method based on machine vision | |
CN101408422B (en) | Traffic accident on-site mapper based on binocular tridimensional all-directional vision | |
CN104268876A (en) | Camera calibration method based on partitioning | |
CN103226840B (en) | Full-view image splicing and measurement system and method | |
CN102692214A (en) | Narrow space binocular vision measuring and positioning device and method | |
CN102519434B (en) | Test verification method for measuring precision of stereoscopic vision three-dimensional recovery data | |
CN107464264A (en) | A kind of camera parameter scaling method based on GPS | |
CN105160702A (en) | Stereoscopic image dense matching method and system based on LiDAR point cloud assistance | |
CN102519433B (en) | Method for inverting geometric calibrating parameter of satellite-borne linear array sensor by using RPC (Remote Position Control) | |
CN103971353A (en) | Splicing method for measuring image data with large forgings assisted by lasers | |
CN105509733A (en) | Measuring method for relative pose of non-cooperative spatial circular object | |
CN102679961B (en) | Portable four-camera three-dimensional photographic measurement system and method | |
CN106019264A (en) | Binocular vision based UAV (Unmanned Aerial Vehicle) danger vehicle distance identifying system and method | |
CN104835158A (en) | 3D point cloud acquisition method based on Gray code structure light and polar constraints | |
CN105716542A (en) | Method for three-dimensional data registration based on flexible feature points | |
CN104613929A (en) | Method for automatic collimation of cubic mirror based on machine vision | |
CN104539928A (en) | Three-dimensional printing image synthesizing method for optical grating | |
CN102693543B (en) | Method for automatically calibrating Pan-Tilt-Zoom in outdoor environments |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170811 |