CN102169579A - Rapid and accurate registration method of dense point cloud model - Google Patents
Rapid and accurate registration method of dense point cloud model Download PDFInfo
- Publication number
- CN102169579A CN102169579A CN2011100801928A CN201110080192A CN102169579A CN 102169579 A CN102169579 A CN 102169579A CN 2011100801928 A CN2011100801928 A CN 2011100801928A CN 201110080192 A CN201110080192 A CN 201110080192A CN 102169579 A CN102169579 A CN 102169579A
- Authority
- CN
- China
- Prior art keywords
- point
- matrix
- registration
- model
- point cloud
- 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
Abstract
The invention discloses a rapid and accurate registration method of a dense point cloud model, comprising the following steps of: realizing the initial registration of a turbine blade dense point cloud model and a CAD (Computer-Aided Design) model through an alignment method; appropriately simplifying the obtained initially registered point cloud data; computing the rotation matrix and the translation matrix of each iteration in an SVD-ICP (Singular Value Decomposition-Iterative Closet Point) algorithm; and finally realizing the accurate registration of a control point set {P} and the CAD model by adopting the SVD-ICP algorithm. In the invention, under the premise of realizing the pre-registration of the point cloud model and the CAD model, the dense point cloud data are simplified; the simplified data are taken as a registered control point set; the total rotation matrix and the translation matrix are computed on the basis of the SVD-ICP algorithm; and the computed total transformation matrixes are applied to the original dense point cloud before the simplification so that the rapid registration of the dense point cloud and the CAD model is realized and the registration accuracy and the registration speed are considered simultaneously.
Description
Technical field
The present invention relates to a kind of coordinate system and unify method, relate in particular to the fast accurate method for registering of a kind of three-dimensional point of density cloud model and cad model, this method is applicable to the registration of the three-dimensional point of density cloud model of field parts such as medical science, Aero-Space, weapons.
Background technology
The registration of turbo blade point cloud model mainly is meant the spatial alternation that the point cloud model of measurement designs a model with respect to CAD, promptly realizes the unification of coordinate system.Current in a lot of fields, size detection and Measurement and analysis technology have crucial effects in raising manufacturing shape, dimensional accuracy with aspect ensuring the quality of products.Common measuring method has three-dimensional coordinates measurement, optical scanning to measure and CT measures.In recent years, along with the development of laser technology, the speed and the precision of optical measurement all are greatly improved, use also more and more widely, the data volume of its acquisition is very huge, though obtained more fully data message, has also brought inconvenience for follow-up Measurement and analysis simultaneously.Such as, the manufacturing accuracy of domestic air mail engine turbine blade is low, qualification rate is low, in order to improve manufacturing accuracy and qualification rate, product is measured, pass through then measurement data and cad model registration, carry out two dimension or three-dimensional variance analysis, relatively draw the deformation rule of product, utilize the reversible deformation technology that the mould of product, processing technology etc. are optimized design, thereby improve the precision and the qualification rate of product.
At present registration Algorithm roughly can be divided three classes: the iteration registration Algorithm, and based on the registration Algorithm of curved surface with based on how much feature registration algorithm.For iterative algorithm, the most representative is iterative closest point algorithms (the iterative closestpoint that Besl etc. proposes, ICP), it is right that algorithm at first utilizes Newton iteration or searching method to seek two groups of closest approaches of putting the cloud correspondences, and adopt Euclidean distance to carry out iteration, thereby obtain three-dimensional rigid body translation as objective function.Though the iterative algorithm degree of accuracy is very high, but there are a lot of limitation, at first be that the time complexity that its iterations causes too much increases, in addition, because the ICP algorithm is had relatively high expectations to 2 relative initial positions of some cloud, initial position between the some cloud can not differ too big, otherwise the convergence direction of ICP is uncertain, and this will cause the degree of accuracy of algorithm and speed of convergence to be affected, even also might be absorbed in locally optimal solution, thereby registration results also is insecure.Can be regarded as with a kind of method based on the registration Algorithm of surface description with based on the registration Algorithm of geometric properties, promptly based on the registration Algorithm of feature, this method registration efficient is higher, and for the cloud data overlapping as the part, applicability is better, but the method is mainly used in the pre-registration of model, and requires model to have tangible geometric properties, and significant limitation is arranged.
Because the precision of iterative algorithm is very high, on the basis of ICP algorithm, there is the people to propose method (the Singular Value Decomposition and Iterative Closest Point algorithm that svd and closest approach iterative algorithm are combined, SVD_ICP), this method is found the solution the transformation problem of two corresponding point sets by svd, progressively iteration realizes registration then, but the speed that the method registration calculates is slower.For the registration of magnanimity cloud data, how under the prerequisite that guarantees registration accuracy, improving registration speed is that the lot of domestic and international scholar is in the problem of making great efforts research.
Summary of the invention
Can not take into account the deficiency of registration accuracy and registration speed in order to overcome prior art, the invention provides a kind of rapid registering method of point of density cloud model, this method has the advantage that guarantees registration accuracy, improves registration speed.
The present invention realizes that the above-mentioned purpose technical solution may further comprise the steps:
Step 1
Choose on measurement point cloud model and the cad model any three groups of corresponding point respectively to (P
1, Q
1), (P
2, Q
2), (P
3, Q
3), P wherein
1, P
2, P
3Not on same plane.Order
Make vector v
3And w
3,
Make vector vector v
2And w
2,
v
1, v
2And v
3Constitute orthogonal coordinate system, be expressed as unit vector
In like manner
Any point P in the measurement point cloud model
iTransform to corresponding point Q
iRelational expression be: Q
i=RP
i+ T, wherein R=[w] [v]
-1, T=Q
1-[w] [v]
-1P
1
Step 2
The point of density cloud model that utilizes the uniform sampling method that step 1 is obtained is reduced to 10000-50000 point, and { P} seeks point set corresponding with it on the cad model { P ' } as the control point set with the some cloud after simplifying.
Step 3
{ P} is as the registration control points collection with control point set that step 2 obtains, calculate the rotation matrix and the translation matrix of per step iteration in the SVD_ICP algorithm: the utilization singular value decomposition method, the calculation control point set is with respect to the translation and the rotation matrix of cad model, and detailed process is as follows:
2) according to formula q
i=p
i-p and q '
i=p '
i-p ' calculates in two point sets { P} and { P ' } each point with respect to the displacement of its barycenter.
3) according to formula
Ask for matrix H, and by formula H=U Λ V
TMatrix H is carried out svd, and wherein U is the left singular matrix of H, and V is the right singular matrix of H, and the two is 3 * 3 orthogonal matrix.
4) according to formula R=VU
TAnd T=p '-Rp calculates the rotation matrix R of i step iteration
iWith the translation matrix T
i
Step 4
{ the accurate registration of P} and cad model, method is as follows: try to achieve every iteration rotation matrix R once according to step 3 to adopt the SVD_ICP algorithm to realize the control point set
iWith the translation matrix T
iThereby, utilize formula R
z=R
i* R
I-1* ... .*R
1And T
z=R
i* T
I-1+ T '
iTry to achieve control point set { the rotation matrix R that P} is total with respect to cad model
zWith the translation matrix T
z, R wherein
zBe 3 * 3 matrix, T
zIt is 3 * 1 matrix.By formula Q
i=R
zP
i+ T
z, P wherein
iBe any point in the point cloud model, Q
iFor after the conversion with P
iCorresponding point; R
zAnd T
zOriginal point cloud model before being applied to simplify is realized itself and the fast accurate registration of cad model.
The invention has the beneficial effects as follows: under the prerequisite that realizes point cloud model and the pre-registration of cad model, by intensive cloud data is simplified, with the data after simplifying as the registration control points collection, on the basis of SVD_ICP algorithm, calculate and try to achieve total rotation matrix and translation matrix, original point of density cloud before then total transformation matrix of trying to achieve being applied to simplify, realize the rapid registering of itself and cad model, taken into account registration accuracy and registration speed.
The present invention is further described below in conjunction with accompanying drawing and example.
Description of drawings
Fig. 1 is the schematic flow sheet of the method for the invention.
Fig. 2 is certain turbo blade point of density cloud model and cad model.
Fig. 3 is that the difference of point of density cloud model is simplified figure as a result, and wherein Fig. 3 (a) is the figure as a result that is reduced to 139240 points, and Fig. 3 (b) is the structural drawing that is reduced to 23206 points.
Fig. 4 is turbo blade point of density cloud model and cad model registration process figure as a result, and wherein Fig. 4 (a) is the pre-registration result of two models, and Fig. 4 (b) is that essence is joined figure as a result.
Embodiment
Below in conjunction with certain turbo blade point of density cloud model (counting 1392396) and cad model (referring to Fig. 2), elaborate operation steps of the present invention.
Step 1
Realize the initial registration of turbo blade point of density cloud model and cad model by the method for alignment, choose on measurement point cloud model and the cad model any three groups of corresponding point respectively (P
1, Q
1), (P
2, Q
2), (P
3, Q
3), P wherein
1, P
2, P
3Not on same plane.Order
Make vector v
3And w
3,
Make vector vector v
2And w
2,
v
1, v
2And v
3Constitute orthogonal coordinate system, be expressed as unit vector
In like manner
Any point P in the measurement point cloud model
iTransform to corresponding point Q
iRelational expression be: Q
i=RP
i+ T, wherein R=[w] [v]
-1, T=Q
1-[w] [v]
-1P
1The results are shown in Figure 4 (a).
Step 2
The initial registration cloud data that is obtained by step 1 is carried out suitable simplification, the point of density cloud model that utilizes the uniform sampling method that step 1) is obtained is reduced to 10000-50000 point, { P} seeks point set corresponding with it on the cad model { P ' } as the control point set with the some cloud after simplifying.The results are shown in Figure 3.
Step 3
The reduced data that obtains with step 2 calculates rotation and translation matrix in per step iteration in the SVD_ICP algorithm, with formula as the registration control points collection
Be objective function, the calculation control point set is with respect to the transformation matrix of cad model, and detailed process is as follows: 1. according to the method for search closest approach, try to achieve on the cad model and control point set { point set that P} is corresponding { P ' }, utilize formula
With
Ask for the barycenter p and the p ' of two point sets.2. according to formula q
i=p
i-p and q '
i=p '
i-p ' calculates 2 displacements of concentrating each point with respect to its barycenter.3. according to formula
Ask for matrix H, and by formula H=U Λ V
TMatrix H is carried out svd, and wherein U is the left singular matrix of H, and V is the right singular matrix of H, and the two is 3 * 3 orthogonal matrix.4. according to formula R=VU
TAnd T=p '-Rp calculates rotation matrix R and translation matrix T.
Step 4
Can utilize formula R then in the hope of the transformation matrix R and the T in per step in the iterative process by step 3
z=R
i* R
I-1* ... ..*R
1And T
z=R
i* T
I-1+ T '
i, the calculation control point set is with respect to total transformation matrix R of cad model
zAnd T
zThe total transformation matrix R that tries to achieve
zAnd T
zBy formula Q
i=R
zP
i+ T
zBe applied to original point of density cloud model, just realized the accurate registration fast of itself and cad model, see Fig. 4 (b).
Rapid registering according to above-mentioned steps realization intensive cloud data of turbo blade and cad model carries out three-dimensional variance analysis to the result behind the registration, and registration time when statistics is simplified the result as the reference mark with difference and deviation result are as table
1, shown in the table 2.
The used time statistical form of the different reference mark of table 1 registration
The three-dimensional deviation statistics table of table 2
By table 1, data result carries out accurate registration with the data after simplifying as the reference mark as can be seen in the table 2, and its registration speed is greatly improved.From three-dimensional deviation result, to compare with the result who carries out registration before the simplification, its deviation changes very little, can guarantee the accuracy requirement of registration.
In a word, can under the prerequisite that guarantees registration accuracy, realize the fast accurate registration of intensive cloud data and cad model according to above-mentioned steps.
Claims (1)
1. the fast accurate method for registering of point of density cloud model is characterized in that comprising the steps:
Step 1
Choose on measurement point cloud model and the cad model any three groups of corresponding point respectively to (P
1, Q
1), (P
2, Q
2), (P
3, Q
3), P wherein
1, P
2, P
3Not on same plane; Order
Make vector v
3And w
3,
Make vector vector v
2And w
2,
v
1, v
2And v
3Constitute orthogonal coordinate system, be expressed as unit vector
In like manner
Any point P in the measurement point cloud model
iTransform to corresponding point Q on the cad model
iRelational expression be: Q
i=RP
i+ T, wherein R=[w] [v]
-1, T=Q
1-[w] [v]
-1P
1
Step 2
The point of density cloud model that utilizes the uniform sampling method that step 1 is obtained is reduced to 10000-50000 point, and { P} seeks point set corresponding with it on the cad model { P ' } as the control point set with the some cloud after simplifying;
Step 3
The control point set that obtains with step 2 P} calculates the rotation matrix and the translation matrix of per step iteration in the SVD_ICP algorithm as the registration control points collection:
2) according to formula q
i=p
i-p and q '
i=p '
i-p ' calculates in two point sets { P} and { P ' } each point with respect to the displacement of its barycenter;
3) according to formula
Ask for matrix H, and by formula H=U Λ V
TMatrix H is carried out svd, and wherein U is the left singular matrix of H, and V is the right singular matrix of H, and the two is 3 * 3 orthogonal matrix;
4) according to formula R=VU
TAnd T=p '-Rp calculates the rotation matrix R of i step iteration
iWith the translation matrix T
i
Step 4
{ the accurate registration of P} and cad model, method is as follows: try to achieve every iteration rotation matrix R once according to step 3 to adopt the SVD_ICP algorithm to realize the control point set
iWith the translation matrix T
iThereby, utilize formula R
z=R
i* R
I-1* ... ..*R
1And T
z=R
i* T
I-1+ T '
iTry to achieve control point set { the rotation matrix R that P} is total with respect to cad model
zWith the translation matrix T
z, R wherein
zBe 3 * 3 matrix, T
zIt is 3 * 1 matrix; By formula Q
i=R
zP
i+ T
z, P wherein
iBe any point in the point cloud model, Q
iFor after the conversion with P
iCorresponding point; R
zAnd T
zOriginal point cloud model before being applied to simplify is realized itself and the fast accurate registration of cad model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011100801928A CN102169579A (en) | 2011-03-31 | 2011-03-31 | Rapid and accurate registration method of dense point cloud model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011100801928A CN102169579A (en) | 2011-03-31 | 2011-03-31 | Rapid and accurate registration method of dense point cloud model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102169579A true CN102169579A (en) | 2011-08-31 |
Family
ID=44490731
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2011100801928A Pending CN102169579A (en) | 2011-03-31 | 2011-03-31 | Rapid and accurate registration method of dense point cloud model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102169579A (en) |
Cited By (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102779345A (en) * | 2012-07-03 | 2012-11-14 | 河海大学 | Point cloud precise registering method based on gravity center Euclidean distance |
CN102903117A (en) * | 2012-10-24 | 2013-01-30 | 深圳大学 | 3D (three-dimensional) image registration method and device based on conformal geometric algebra |
CN103295239A (en) * | 2013-06-07 | 2013-09-11 | 北京建筑工程学院 | Laser-point cloud data automatic registration method based on plane base images |
CN104463826A (en) * | 2013-09-18 | 2015-03-25 | 镇江福人网络科技有限公司 | Novel point cloud parallel Softassign registering algorithm |
WO2015039375A1 (en) * | 2013-09-17 | 2015-03-26 | 中国科学院深圳先进技术研究院 | Method and system for automatically optimizing quality of point cloud data |
CN104616311A (en) * | 2015-02-13 | 2015-05-13 | 重庆大学 | Precise registration method of damaged part based on improved ICP (Inductively Coupled Plasma) algorithm |
CN104766325A (en) * | 2015-04-09 | 2015-07-08 | 泉州装备制造研究所 | Calculation method for vamp glue spray trajectory |
CN104778688A (en) * | 2015-03-27 | 2015-07-15 | 华为技术有限公司 | Method and device for registering point cloud data |
CN105078573A (en) * | 2014-05-11 | 2015-11-25 | 复旦大学 | Neuronavigation space aligning method based on handheld scanner |
CN106023156A (en) * | 2016-05-10 | 2016-10-12 | 中国商用飞机有限责任公司 | Point-cloud model and CAD model registering method based on detection features |
CN104166989B (en) * | 2014-07-04 | 2017-02-15 | 电子科技大学中山学院 | Rapid ICP method for two-dimensional laser radar point cloud matching |
CN107860346A (en) * | 2017-09-30 | 2018-03-30 | 北京卫星制造厂 | A kind of measuring coordinate system method for registering |
CN108022264A (en) * | 2016-11-01 | 2018-05-11 | 狒特科技(北京)有限公司 | Camera pose determines method and apparatus |
CN108507842A (en) * | 2018-03-06 | 2018-09-07 | 中国科学院武汉岩土力学研究所 | A kind of production method in rock three-dimensional natural structure face |
CN108544181A (en) * | 2018-03-27 | 2018-09-18 | 西北工业大学 | A kind of restorative procedure of blisk damaged blade |
CN109255806A (en) * | 2018-08-31 | 2019-01-22 | 影为医疗科技(上海)有限公司 | Two dimension and three-dimensional image registration method, system, storage medium, the aligner of medical image |
CN110211129A (en) * | 2019-05-17 | 2019-09-06 | 西安财经学院 | Low covering point cloud registration algorithm based on region segmentation |
CN110930443A (en) * | 2019-11-27 | 2020-03-27 | 中国科学院深圳先进技术研究院 | Image registration method and device and terminal equipment |
WO2020155049A1 (en) * | 2019-01-31 | 2020-08-06 | 西门子股份公司 | Method, apparatus, and device for recognizing model simplification feature |
US10769811B2 (en) | 2018-07-09 | 2020-09-08 | Institute For Information Industry | Space coordinate converting server and method thereof |
CN112308890A (en) * | 2020-10-29 | 2021-02-02 | 西北工业大学 | Reliable registration method for standard ball assisted industrial CT measurement coordinate system |
CN112432609A (en) * | 2020-11-24 | 2021-03-02 | 中铁十一局集团电务工程有限公司 | Rail contact net parameter measurement system |
CN112465732A (en) * | 2020-11-27 | 2021-03-09 | 武汉大学 | Registration method of vehicle-mounted laser point cloud and sequence panoramic image |
CN112484659A (en) * | 2020-11-12 | 2021-03-12 | 中国航发南方工业有限公司 | Non-contact type engine blade profile detection device |
CN112484660A (en) * | 2020-11-12 | 2021-03-12 | 中国航发南方工业有限公司 | Non-contact type engine blade profile detection method and engine blade |
CN112912927A (en) * | 2018-10-18 | 2021-06-04 | 富士通株式会社 | Calculation method, calculation program, and information processing apparatus |
CN115063458A (en) * | 2022-07-27 | 2022-09-16 | 武汉工程大学 | Material pile volume calculation method based on three-dimensional laser point cloud |
CN116342671A (en) * | 2023-05-23 | 2023-06-27 | 第六镜科技(成都)有限公司 | Point cloud and CAD model registration method, device, electronic equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2389500A (en) * | 2002-04-20 | 2003-12-10 | Virtual Mirrors Ltd | Generating 3D body models from scanned data |
US20050101855A1 (en) * | 2003-09-08 | 2005-05-12 | Vanderbilt University | Apparatus and methods of brain shift compensation and applications of the same |
CN101082988A (en) * | 2007-06-19 | 2007-12-05 | 北京航空航天大学 | Automatic deepness image registration method |
CN101645170A (en) * | 2009-09-03 | 2010-02-10 | 北京信息科技大学 | Precise registration method of multilook point cloud |
-
2011
- 2011-03-31 CN CN2011100801928A patent/CN102169579A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2389500A (en) * | 2002-04-20 | 2003-12-10 | Virtual Mirrors Ltd | Generating 3D body models from scanned data |
US20050101855A1 (en) * | 2003-09-08 | 2005-05-12 | Vanderbilt University | Apparatus and methods of brain shift compensation and applications of the same |
CN101082988A (en) * | 2007-06-19 | 2007-12-05 | 北京航空航天大学 | Automatic deepness image registration method |
CN101645170A (en) * | 2009-09-03 | 2010-02-10 | 北京信息科技大学 | Precise registration method of multilook point cloud |
Non-Patent Citations (3)
Title |
---|
张树森,等: "结构光栅测量系统中散乱点云配准算法研究", 《机械设计与制造》 * |
赵小平,等: "三维激光扫描技术边坡监测研究", 《测绘科学》 * |
龚正国,等: "基于光学扫描测量数据的叶片型面偏差分析研究", 《现代制造工程》 * |
Cited By (40)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102779345A (en) * | 2012-07-03 | 2012-11-14 | 河海大学 | Point cloud precise registering method based on gravity center Euclidean distance |
CN102779345B (en) * | 2012-07-03 | 2015-09-16 | 河海大学 | A kind of some cloud Precision Registration based on center of gravity Euclidean distance |
CN102903117A (en) * | 2012-10-24 | 2013-01-30 | 深圳大学 | 3D (three-dimensional) image registration method and device based on conformal geometric algebra |
CN103295239A (en) * | 2013-06-07 | 2013-09-11 | 北京建筑工程学院 | Laser-point cloud data automatic registration method based on plane base images |
CN103295239B (en) * | 2013-06-07 | 2016-05-11 | 北京建筑工程学院 | A kind of autoegistration method of the laser point cloud data based on datum plane image |
WO2015039375A1 (en) * | 2013-09-17 | 2015-03-26 | 中国科学院深圳先进技术研究院 | Method and system for automatically optimizing quality of point cloud data |
US9684817B2 (en) | 2013-09-17 | 2017-06-20 | Shenzhen Institutes Of Advanced Technology Chinese Academy Of Sciences | Method and system for automatically optimizing quality of point cloud data |
CN104463826A (en) * | 2013-09-18 | 2015-03-25 | 镇江福人网络科技有限公司 | Novel point cloud parallel Softassign registering algorithm |
CN105078573B (en) * | 2014-05-11 | 2017-12-01 | 复旦大学 | Use of Neuronavigation spatial registration method based on hand-held scanner |
CN105078573A (en) * | 2014-05-11 | 2015-11-25 | 复旦大学 | Neuronavigation space aligning method based on handheld scanner |
CN104166989B (en) * | 2014-07-04 | 2017-02-15 | 电子科技大学中山学院 | Rapid ICP method for two-dimensional laser radar point cloud matching |
CN104616311A (en) * | 2015-02-13 | 2015-05-13 | 重庆大学 | Precise registration method of damaged part based on improved ICP (Inductively Coupled Plasma) algorithm |
CN104778688A (en) * | 2015-03-27 | 2015-07-15 | 华为技术有限公司 | Method and device for registering point cloud data |
CN104778688B (en) * | 2015-03-27 | 2018-03-13 | 华为技术有限公司 | The method for registering and device of cloud data |
CN104766325A (en) * | 2015-04-09 | 2015-07-08 | 泉州装备制造研究所 | Calculation method for vamp glue spray trajectory |
CN104766325B (en) * | 2015-04-09 | 2017-12-19 | 泉州装备制造研究所 | A kind of computational methods of vamp glue spraying trajectory |
CN106023156A (en) * | 2016-05-10 | 2016-10-12 | 中国商用飞机有限责任公司 | Point-cloud model and CAD model registering method based on detection features |
CN108022264A (en) * | 2016-11-01 | 2018-05-11 | 狒特科技(北京)有限公司 | Camera pose determines method and apparatus |
CN108022264B (en) * | 2016-11-01 | 2023-06-13 | 北京墨土科技有限公司 | Method and equipment for determining camera pose |
CN107860346A (en) * | 2017-09-30 | 2018-03-30 | 北京卫星制造厂 | A kind of measuring coordinate system method for registering |
CN107860346B (en) * | 2017-09-30 | 2019-12-20 | 北京卫星制造厂 | Registration method for measuring coordinate system |
CN108507842A (en) * | 2018-03-06 | 2018-09-07 | 中国科学院武汉岩土力学研究所 | A kind of production method in rock three-dimensional natural structure face |
CN108544181A (en) * | 2018-03-27 | 2018-09-18 | 西北工业大学 | A kind of restorative procedure of blisk damaged blade |
US10769811B2 (en) | 2018-07-09 | 2020-09-08 | Institute For Information Industry | Space coordinate converting server and method thereof |
CN109255806B (en) * | 2018-08-31 | 2020-06-23 | 影为医疗科技(上海)有限公司 | Two-dimensional and three-dimensional image registration method, system, storage medium and registration device for medical images |
CN109255806A (en) * | 2018-08-31 | 2019-01-22 | 影为医疗科技(上海)有限公司 | Two dimension and three-dimensional image registration method, system, storage medium, the aligner of medical image |
CN112912927A (en) * | 2018-10-18 | 2021-06-04 | 富士通株式会社 | Calculation method, calculation program, and information processing apparatus |
WO2020155049A1 (en) * | 2019-01-31 | 2020-08-06 | 西门子股份公司 | Method, apparatus, and device for recognizing model simplification feature |
CN110211129A (en) * | 2019-05-17 | 2019-09-06 | 西安财经学院 | Low covering point cloud registration algorithm based on region segmentation |
CN110930443A (en) * | 2019-11-27 | 2020-03-27 | 中国科学院深圳先进技术研究院 | Image registration method and device and terminal equipment |
CN112308890A (en) * | 2020-10-29 | 2021-02-02 | 西北工业大学 | Reliable registration method for standard ball assisted industrial CT measurement coordinate system |
CN112308890B (en) * | 2020-10-29 | 2023-04-21 | 西北工业大学 | Standard ball-assisted reliable registration method for industrial CT measurement coordinate system |
CN112484659A (en) * | 2020-11-12 | 2021-03-12 | 中国航发南方工业有限公司 | Non-contact type engine blade profile detection device |
CN112484660A (en) * | 2020-11-12 | 2021-03-12 | 中国航发南方工业有限公司 | Non-contact type engine blade profile detection method and engine blade |
CN112484660B (en) * | 2020-11-12 | 2022-08-26 | 中国航发南方工业有限公司 | Non-contact type engine blade profile detection method |
CN112432609A (en) * | 2020-11-24 | 2021-03-02 | 中铁十一局集团电务工程有限公司 | Rail contact net parameter measurement system |
CN112465732A (en) * | 2020-11-27 | 2021-03-09 | 武汉大学 | Registration method of vehicle-mounted laser point cloud and sequence panoramic image |
CN115063458A (en) * | 2022-07-27 | 2022-09-16 | 武汉工程大学 | Material pile volume calculation method based on three-dimensional laser point cloud |
CN116342671A (en) * | 2023-05-23 | 2023-06-27 | 第六镜科技(成都)有限公司 | Point cloud and CAD model registration method, device, electronic equipment and storage medium |
CN116342671B (en) * | 2023-05-23 | 2023-08-08 | 第六镜科技(成都)有限公司 | Point cloud and CAD model registration method, device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102169579A (en) | Rapid and accurate registration method of dense point cloud model | |
CN101692257B (en) | Method for registering complex curved surface | |
CN109118574A (en) | A kind of fast reverse modeling method extracted based on three-dimensional feature | |
Du et al. | Probability iterative closest point algorithm for mD point set registration with noise | |
CN105654483B (en) | The full-automatic method for registering of three-dimensional point cloud | |
CN104123746B (en) | The computational methods of real-time normal vector in a kind of 3-D scanning point cloud | |
CN103955939A (en) | Boundary feature point registering method for point cloud splicing in three-dimensional scanning system | |
CN103236064A (en) | Point cloud automatic registration method based on normal vector | |
CN106780619A (en) | A kind of human body dimension measurement method based on Kinect depth cameras | |
Du et al. | Affine registration of point sets using ICP and ICA | |
CN105405119B (en) | Fetus median sagittal plane automatic testing method based on depth confidence network and threedimensional model | |
CN103914823B (en) | The method of the quick exact non-linear registration solid medical image based on rarefaction representation | |
CN105913444B (en) | Livestock figure profile reconstructing method and Body Condition Score method based on soft laser ranging | |
CN102262724A (en) | Object image characteristic points positioning method and object image characteristic points positioning system | |
US20130156281A1 (en) | Image registration method | |
CN101882150A (en) | Three-dimensional model comparison and search method based on nuclear density estimation | |
CN104657713A (en) | Three-dimensional face calibrating method capable of resisting posture and facial expression changes | |
CN110197503A (en) | Non-rigid point set method for registering based on enhanced affine transformation | |
CN107730587A (en) | One kind is based on picture quick three-dimensional Interactive Modeling method | |
CN111415379A (en) | Three-dimensional point cloud data registration method based on cuckoo optimization | |
CN103700135B (en) | A kind of three-dimensional model local spherical mediation feature extracting method | |
CN111062135A (en) | Accurate collision detection method | |
CN106682575A (en) | Human eye point cloud feature location with ELM (Eye Landmark Model) algorithm | |
CN111583309A (en) | Method for realizing Z-pin implantation on complex curved surface | |
CN100444191C (en) | Multiple expression whole face profile testing method based on moving shape model |
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: 20110831 |