CN106548484A - Product model dispersion point cloud Boundary characteristic extraction method based on two-dimentional convex closure - Google Patents
Product model dispersion point cloud Boundary characteristic extraction method based on two-dimentional convex closure Download PDFInfo
- Publication number
- CN106548484A CN106548484A CN201610956616.5A CN201610956616A CN106548484A CN 106548484 A CN106548484 A CN 106548484A CN 201610956616 A CN201610956616 A CN 201610956616A CN 106548484 A CN106548484 A CN 106548484A
- Authority
- CN
- China
- Prior art keywords
- point
- convex closure
- dimentional
- characteristic extraction
- product model
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Processing Or Creating Images (AREA)
Abstract
The present invention provides a kind of product model dispersion point cloud Boundary characteristic extraction method based on two-dimentional convex closure, point cloud density is calculated by sampling analyses, traversal point cloud obtains the k neighbours of impact point, the fit Plane of impact point and its k neighbours is solved using least square method, impact point and its k neighbours are projected to into fit Plane, data for projection convex closure is obtained using value adding method, and product model scattered point cloud data Boundary characteristic extraction is realized based on convex closure.The method is applied to arbitrarily complicated product point cloud model, Boundary characteristic extraction processing efficient, stable, practical.
Description
Technical field
The present invention relates to product reverse Engineering Technology field, and in particular to a kind of product dispersion point cloud based on two-dimentional convex closure
Boundary characteristic extraction method.
Background technology
Reverse Engineering Technology mainly includes：The processes such as Model Digitization, the pretreatment in numeric type face and surface reconstruction.Its
In, the digitized of model is the measurement problem for studying mock-up, and in manufacturing, conventional method is set using 3-D scanning
The standby surface-type feature information for obtaining product.The pretreatment of numeric type face refers to the treatment technology to measurement data.Surface reconstruction is handle
The data of measurement are converted to CAD model, for actual processing.When being reconstructed using cloud data, to overall number
According to process it is more complicated, or even be difficult to, need the edge feature point or line of first identification model, data are divided,
Then piecemeal is processed, and finally realizes the CAD modelings of product.In addition, the Boundary Recognition technology of point cloud is restored to a cloud filling-up hole, historical relic
And repair etc. aspect suffer from important application.
Zhang Xianying etc. is in academic journal to be found to prior art literature retrieval《Chinese image graphics journal》2003,8
(10), in the scientific paper " boundary extraction method of D Triangulation curved surface ", delivered on P1223-1226, produced by setting up
The STL grid models of product model point cloud extract point cloud boundary characteristics, and the method Boundary characteristic extraction accurately, but is adapted to any at present
The Triangulation Algorithm of point cloud data does not also obtain fully effective solution, and Triangulation Algorithm time complexity itself is high, needs consumption
Take substantial amounts of system resource, the speed of service is slow.Sun Dianzhu is in its technical paper《Surface Feature Analysis For Scatter Data Points
Research and application》(mechanical engineering journal, 2007,43 (6)：Point cloud local profile is obtained in 133-136) and refers to point set, match point
Collection reference plane simultaneously will project to plane with reference to point set, by extracting point cloud boundary characteristics, the calculation to data for projection angle changing rate
The boundary characteristic point set that method is extracted includes partial interior point, and extraction accuracy is low.
In sum, the defect of prior art presence is：Boundary characteristic extraction precision is low, and the scope of application is little, it is impossible to meet
The needs of CAD modelings and rapid shaping design in reverse-engineering.
The content of the invention
The present invention provides a kind of product dispersion point cloud Boundary characteristic extraction method based on two-dimentional convex closure, and the method is applied to
Arbitrarily complicated product point cloud model, it is Boundary characteristic extraction processing efficient, stable, practical.
The technical scheme is that：A kind of product model dispersion point cloud Boundary characteristic extraction side based on two-dimentional convex closure
Method, comprises the following steps：
Step 1, product model scattered point cloud data is read in storage device, and calculates a cloud density p；
Step 2, for arbitrary target points v, travels through cloud data, and its nearest k strong point of Search Length is used as impact point v
K- Neighbor Points；
Step 3, solves fit Plane P of impact point v and its k- Neighbor Points using least square method；
Impact point v and its k- Neighbor Points are projected to fit Plane P, and solve the two-dimentional convex closure Q of subpoint by step 4；
Step 5, realizes product model dispersion point cloud Boundary characteristic extraction based on convex closure Q.
Further, in step 1, the computational methods of calculating point cloud density p are：N point is randomly selected in cloud data,
To the arbitrfary point po being drawn intoi, all over cloud data is taken, the m point nearest with which is searched for, and calculates each in m nearest point
Individual point and poiApart from dI, j, then put cloud densityWherein i=0,1 ... n, j=0,1 ... m.
Further, in step 3, the method for solving of fit Plane P is：If plane equation is c1x+c2y+C3z+c4=0, its
Matrix equation is HC=0, wherein：
Then the equation of fit Plane P is
The equation of fit Plane P is solved using the characteristic vector estimation technique, to matrix HTH carries out singular value decomposition and obtains
Wherein U and V be orthogonal matrix, w1、w2、w3、w4For HTThe corresponding feature of the eigenvalue of H, wherein minimal eigenvalue to
Amount is the least square solution of the equation of fit Plane P, so as to try to achieve fit Plane P.
Further, in step 4, if set of projections of the impact point v and its k- Neighbor Points in fit Plane P is combined into VP, then
The solution procedure of the two-dimentional convex closure Q of subpoint is：
Step 4.1, arbitrarily chooses not conllinear three-point shape into initial convex closure, three sides of initial convex closure is added to convex closure
Set QEIn；
Step 4.2, by convex closure internal point and convex closure summit by VPMiddle deletion；
Step 4.3, if VPFor sky, EP (end of program), now convex hull set QEThe two-dimentional convex closure Q of the subpoint for as solving；It is no
Then execution step 4.4；
Step 4.4, by VPIn optional 1 point of rt(at, bt, dt), convex closure data are carried out using value adding method and is updated and is returned step
Rapid 4.2.
Further, in step 4.2, VPWhether middle data point is that the determination methods of convex closure internal point are：Using formula
Calculate convex hull set QEVertex set center of gravity O (ao, bo, do), wherein (al, bl, dl) for VPThe seat of middle data point
Mark, s is VPThe number of middle data point；For VPMiddle Arbitrary Digit strong point rt(at, bt, dt), travel through convex hull set QEIn all convex closures
Side E is satisfied by (F1ao+F2bo+F3do+F4)(F1at+F2bt+F3dt+F4) >=0, then rt(at, bt, dt) for convex closure internal point, otherwise
rt(at, bt, dt) for convex closure external point；F1a+F2b+F3d+F4=0 represents through convex closure side E and perpendicular to the flat of fit Plane P
Face.
Further, in step 4.4, what convex closure data updated comprises the concrete steps that：
Step 4.4.1, query point rt(at, bt, dt) visible line set；
Step 4.4.2, from convex hull set QEThe middle each bar side deleted in visible line set；
Step 4.4.3, junction point rt(at, bt, dt) two end points with convex closure residue line set, new border is formed, is added
It is added to convex hull set QEIn.
Further, in step 4.4.1, to any convex closure side E, if through convex closure side E and perpendicular to the flat of fit Plane P
Face equation is F1a+F2b+F3d+F4=0, then whether convex closure side E is point rt(at, bt, dt) the determination methods of visible edge be：Calculate
Convex hull set QEVertex set center of gravity O (ao, bo, do), if (F1ao+F2bo+F3do+F4)(F1at+F2bt+F3dt+F4) ＜ 0, then
Convex closure side E is visible edge, and otherwise, convex closure is when E is invisible.
Further, in step 5, the concrete grammar of Boundary characteristic extraction is：If throwings of the impact point v in fit Plane P
Shadow belongs to the summit of two-dimentional convex closure Q, then boundary points of the impact point v for product model, its boarder probability anglePr (v)=1.0,
Otherwise, if v ' is projections of the impact point v in fit Plane P, v 'gv′g+1For the side on two-dimentional convex closure Q, v 'g、v′g+1For side
Two end points, wherein, g=0,1 ..., GN；As g=GN, GN+1=0, GN are convex closure number of vertex；The two-dimentional convex closure Q's of traversal is each
Bar side, obtains point v ' and side v 'gv′g+1The maximum angle β of two end point connecting line compositiong, maximum angle βgFor ∠ v 'gv′v′g+1Most
Big to be worth, then the boarder probability of impact point v is：
AnglePr (v) is compared with predetermined threshold value σ, if anglePr (v) >=σ, impact point v is boundary point, otherwise mesh
Punctuate v is internal point.
The present invention compared with prior art, with advantages below：
1) fit Plane is obtained using method of least square, product model dispersion point cloud is obtained by plane projection data convex closure
Boundary characteristic extraction, it is simple with geometry, process the advantages of facilitating；
2) by constructing convex closure center of gravity, realize that visible face is recognized, and then realize that data for projection convex closure builds, it is to avoid tradition
The time loss found visible edge and cause is calculated by vector in convex closure building process, precision reliability high with operational efficiency
The characteristics of；
3) dispersion point cloud density is calculated by sampled data, and target data k- neighbour is obtained to point cloud model traversal, can
The point cloud model of various complex profiles is applied to, data adaptability is stronger.
Description of the drawings
Fig. 1 is specific embodiment of the invention flow chart.
Fig. 2 is specific embodiment of the invention product point cloud model schematic diagram.
Fig. 3 is specific embodiment of the invention product point cloud model Boundary characteristic extraction result schematic diagram.
Specific embodiment
The present invention will be described in detail below in conjunction with the accompanying drawings and by specific embodiment, and following examples are to the present invention
Explanation, and the invention is not limited in implementation below.
As shown in figure 1, the product model dispersion point cloud Boundary characteristic extraction method based on two-dimentional convex closure that the present invention is provided
Flow process be：Data read-in programme is read into the cloud data that Products Digital equipment is exported in storage device, and formation can be with
For the linear linked list of data access；Data sampling is carried out to cloud data, point cloud density is calculated, for arbitrary target points v, is adopted
Its k- neighbour's data point is obtained with k- NN Query programs, and using least square fitting impact point v and its k- neighbour most
A young waiter in a wineshop or an inn takes advantage of fit Plane P, and impact point v and its k- neighbour is projected to fit Plane P；The two of data for projection are solved using value-added approach
Dimension convex closure Q, realizes product model dispersion point cloud Boundary characteristic extraction based on two-dimentional convex closure Q.
Concretely comprise the following steps：
Step 1, product model scattered point cloud data is read in storage device, and calculates a cloud density p.
The computational methods of the step point cloud density p are：N point is randomly selected in product model dispersion point cloud, to taking out
The arbitrfary point po for gettingi, all over product model scattered point cloud data is taken, the m point nearest with which is searched for, and calculates nearest m
Each point and po in pointiApart from dI, j, then point Yun MizhanWherein i=0,1 ... n, j=0,1,
...m.The value of m, n is adjusted according to a cloud distribution situation, and general n takes full by 1/1000 a, m of cloud sum takes 8～20
Foot is required.
Step 2, for arbitrary target points v, travels through product model scattered point cloud data, Search Length its nearest k evidence
K- Neighbor Points of the point as impact point v.
Step 3, solves fit Plane P of impact point v and its k- Neighbor Points using least square method.
The method for solving of fit Plane P is：If plane equation is c1x+c2y+c3z+c4=0, its matrix equation is HC=0,
Wherein：
Then the equation of fit Plane P is
The equation of fit Plane P is solved using the characteristic vector estimation technique, to matrix HTH carries out singular value decomposition and obtains
Wherein U and V be orthogonal matrix, w1、w2、w3、w4For HTThe corresponding feature of the eigenvalue of H, wherein minimal eigenvalue to
Amount is the least square solution of the equation of fit Plane P, so as to try to achieve fit Plane P.
Impact point v and its k- Neighbor Points are projected to fit Plane P, and solve the two-dimentional convex closure Q of subpoint by step 4.
Set of projections of the impact point v and its k- Neighbor Points in fit Plane P is set in the step and is combined into VP, then the two of subpoint
Dimension convex closure Q solution procedure be：
Step 4.1, arbitrarily chooses not conllinear three-point shape into initial convex closure, three sides of initial convex closure is added to convex closure
Set QEIn.
Step 4.2, by convex closure internal point and convex closure summit by VPMiddle deletion.The determination methods of convex closure internal point are：Using
Formula
Calculate convex hull set QEVertex set center of gravity O (ao, bo, do), wherein (al, bl, dl) for VPThe seat of middle data point
Mark, s is VPThe number of middle data point；For VPMiddle Arbitrary Digit strong point rt(at, bt, dt), travel through convex hull set QEIn all convex closures
Side E is satisfied by (F1ao+F2bo+F3do+F4)(F1at+F2bt+F3dt+F4) >=0, then rt(at, bt, dt) for internal point, otherwise rt(at,
bt, dt) for external point；Wherein F1a+F2b+F3d+F4=0 is through convex closure side E and perpendicular to the plane of fit Plane P.
Step 4.3, if VPFor sky, otherwise EP (end of program), execution step 4.4.
Step 4.4, by VPIn optional 1 point of rt(at, bt, dt), convex closure data are carried out using value adding method and is updated and is returned step
Rapid 4.2.What convex closure data updated comprises the concrete steps that：
Step 4.4.1, query point rt(at, bt, dt) visible line set.It is to any convex closure side E, through convex closure side E and vertical
It is directly F with the plane equation of fit Plane P1a+F2b+F3d+F4=0, then whether convex closure side E is point rt(at, bt, dt) visible edge
Determination methods be：Calculate convex hull set QEVertex set center of gravity O (ao, bo, do), if (F1ao+F2bo+F3do+F4)(F1at+
F2bt+F3dt+F4) ＜ 0, then convex closure side E is visible edge, and otherwise, convex closure is when E is invisible.
Step 4.4.2, from QEThe middle each bar side deleted in visible line set.
Step 4.4.3, junction point rt(at, bt, dt) two end points with convex closure residue line set, new border is formed, is added
It is added to QEIn.
Step 5, realizes product model dispersion point cloud Boundary characteristic extraction based on convex closure Q.
In the step, the concrete grammar of Boundary characteristic extraction is：If the subpoint of impact point v belongs to two-dimentional convex closure Q summits,
Then impact point v be product model boundary point, its boarder probability anglePr (v)=1.0, otherwise, if v ' be impact point v fitting
Projection in plane P, v 'gv′g+1For the side on convex closure, v 'g、v′g+1For two end points on side, wherein, g=0,1 ..., GN；Its
Middle GN is convex closure number of vertex.As g=GN, GN+1=0, will constitute two-dimentional convex closure Q orderly point concentrate last point with
0th point constitutes side, to carry out following angle calculation and compare；Each bar side of the two-dimentional convex closure Q of traversal, obtains point v ' and convex closure
Side v 'gv′g+1The maximum angle β of two end point connecting line compositiong, maximum angle βgFor ∠ v 'gv′v′g+1Maximum, then impact point v
Boarder probability be：
AnglePr (v) is compared with predetermined threshold value σ, if anglePr (v) >=σ, impact point v is boundary point, otherwise mesh
Punctuate v is internal point.σ values can be adjusted according to a cloud density, and when density is larger, value is suitably larger, general desirable
0.8～1.0.
Below by taking the product point cloud model shown in Fig. 2 as an example, product point cloud model Boundary characteristic extraction is carried out.
Product cloud data is read in storage organization, cloud data is 58720, therefrom randomly selects 60 points, to taking out
The arbitrfary point po for gettingi(i=0,1 ..., 60), travel through cloud data, search for 8 points nearest with which, and calculate each point and
poiApart from dI, j(j=0,1 ..., 8), then point Yun MizhanInvocation point cloud density is 0.036mm.For appoint
Meaning impact point v, travels through cloud data, obtains the nearest k strong points of distance objective point v as the k- neighbours of v, and k takes 12.By mesh
Punctuate v and its k- neighbour is used as a set VP, fit Plane P of the set is solved using method of least square, and by impact point v
And its k- Neighbor Points project to fit Plane P.The convex closure of data for projection is solved using value-added approach, concrete grammar is：1. arbitrarily select
Take not conllinear 3 point and form initial convex closure, three sides of initial convex closure are added to into convex hull set QEIn；2. by convex closure internal point
And convex closure summit is by VPMiddle deletion；If 3. VPFor sky, EP (end of program), otherwise execution step are 4.；4. by VPIn optional 1 point of rt(at,
bt, dt), using value adding method carry out convex closure data update and return to step 2..After obtaining data for projection convex closure, impact point is judged
The relation of v, subpoint and convex closure v ' and convex closure, if belonging to convex closure summit, the boarder probability of the point is 1.0, Boundary Extraction knot
Beam；Otherwise, if v ' is projections of the impact point v in fit Plane P, v 'gv′g+1For the side on convex closure, v 'g、v′g+1For the two of side
Individual end points, wherein, g=0,1 ..., GN；As g=GN, GN+1=0, GN are convex closure number of vertex；Each bar of the two-dimentional convex closure Q of traversal
Side, obtains point v ' and convex closure side v 'gv′g+1The maximum angle β of two end point connecting line compositiong, maximum angle βgFor ∠ v 'gv′v′g+1's
Maximum, then the boarder probability of impact point v be：
AnglePr (v) is compared with predetermined threshold value σ, if anglePr (v) >=σ, impact point v is boundary point, otherwise mesh
Punctuate v is internal point.From a cloud density, point cloud distribution is closeer, so σ values accordingly increase, takes 0.95.
Disclosed above is only the preferred embodiment of the present invention, but the present invention is not limited to this, any this area
What technical staff can think does not have a creative change, and some improvement made without departing from the principles of the present invention and
Retouching, should all be within the scope of the present invention.
Claims (8)
1. a kind of product model dispersion point cloud Boundary characteristic extraction method based on two-dimentional convex closure, it is characterised in that including following
Step：
Step 1, product model scattered point cloud data is read in storage device, and calculates a cloud density p；
Step 2, for arbitrary target points v, travels through cloud data, k- of its nearest k strong point of Search Length as impact point v
Neighbor Points；
Step 3, solves fit Plane P of impact point v and its k- Neighbor Points using least square method；
Impact point v and its k- Neighbor Points are projected to fit Plane P, and solve the two-dimentional convex closure Q of subpoint by step 4；
Step 5, realizes product model dispersion point cloud Boundary characteristic extraction based on convex closure Q.
2. the product model dispersion point cloud Boundary characteristic extraction method based on two-dimentional convex closure according to claim 1, which is special
Levy and be, the computational methods that point cloud density p is calculated in step 1 are：N point is randomly selected in cloud data, to what is be drawn into
Arbitrfary point poi, all over cloud data is taken, the m point nearest with which is searched for, and calculates each point and po in m nearest pointi's
Apart from di,j, then put cloud densityWherein i=0,1 ... n, j=0,1 ... m.
3. the product model dispersion point cloud Boundary characteristic extraction method based on two-dimentional convex closure according to claim 1, which is special
Levy and be, the method for solving of fit Plane P is in step 3：If plane equation is c1x+c2y+c3z+c4=0, its matrix equation is
HC=0, wherein：
Then the equation of fit Plane P is
The equation of fit Plane P is solved using the characteristic vector estimation technique, to matrix HTH carries out singular value decomposition and obtains
Wherein U and V be orthogonal matrix, w1、w2、w3、w4For HTThe corresponding characteristic vector of the eigenvalue of H, wherein minimal eigenvalue is
For the least square solution of the equation of fit Plane P, so as to try to achieve fit Plane P.
4. the product model dispersion point cloud Boundary characteristic extraction method based on two-dimentional convex closure according to claim 1, which is special
Levy and be, in step 4, if set of projections of the impact point v and its k- Neighbor Points in fit Plane P is combined into VP, then the two of subpoint
Dimension convex closure Q solution procedure be：
Step 4.1, arbitrarily chooses not conllinear three-point shape into initial convex closure, three sides of initial convex closure is added to convex hull set
QEIn；
Step 4.2, by convex closure internal point and convex closure summit by VPMiddle deletion；
Step 4.3, if VPFor sky, EP (end of program), now convex hull set QEThe two-dimentional convex closure Q of the subpoint for as solving；Otherwise hold
Row step 4.4；
Step 4.4, by VPIn optional 1 point of rt(at,bt,dt), convex closure data are carried out using value adding method and is updated and return to step
4.2。
5. the product model dispersion point cloud Boundary characteristic extraction method based on two-dimentional convex closure according to claim 4, which is special
Levy and be, in step 4.2, VPWhether middle data point is that the determination methods of convex closure internal point are：Using formula
Calculate convex hull set QEVertex set center of gravity O (ao,bo,do), wherein (al, bl, dl) for VPThe coordinate of middle data point, s is
VPThe number of middle data point；For VPMiddle Arbitrary Digit strong point rt(at,bt,dt), travel through convex hull set QEIn all convex closure side E it is full
Foot (F1ao+F2bo+F3do+F4)(F1at+F2bt+F3dt+F4) >=0, then rt(at,bt,dt) for convex closure internal point, otherwise rt(at,bt,
dt) for convex closure external point；F1a+F2b+F3d+F4=0 represents through convex closure side E and perpendicular to the plane of fit Plane P.
6. the product model dispersion point cloud Boundary characteristic extraction method based on two-dimentional convex closure according to claim 4, which is special
Levy and be, in step 4.4, what convex closure data updated comprises the concrete steps that：
Step 4.4.1, query point rt(at,bt,dt) visible line set；
Step 4.4.2, from convex hull set QEThe middle each bar side deleted in visible line set；
Step 4.4.3, junction point rt(at,bt,dt) two end points with convex closure residue line set, new border is formed, is added to
Convex hull set QEIn.
7. the product model dispersion point cloud Boundary characteristic extraction method based on two-dimentional convex closure according to claim 6, which is special
Levy and be, in step 4.4.1, to any convex closure side E, if the plane equation through convex closure side E and perpendicular to fit Plane P is
F1a+F2b+F3d+F4=0, then whether convex closure side E is point rt(at,bt,dt) the determination methods of visible edge be：Calculate convex hull set
QEVertex set center of gravity O (ao,bo,do), if (F1ao+F2bo+F3do+F4)(F1at+F2bt+F3dt+F4)<0, then convex closure side E be
Visible edge, otherwise, convex closure is when E is invisible.
8. the product model dispersion point cloud Boundary characteristic extraction method based on two-dimentional convex closure according to claim 1, which is special
Levy and be, in step 5, the concrete grammar of Boundary characteristic extraction is：If projections of the impact point v in fit Plane P belongs to two dimension
The summit of convex closure Q, then impact point v for product model boundary point, its boarder probability anglePr (v)=1.0, otherwise, if v' is
Projections of the impact point v in fit Plane P, v 'gv′g+1For the side on two-dimentional convex closure Q, v 'g、v′g+1For two end points on side, its
In, g=0,1 ..., GN；As g=GN, GN+1=0, GN are convex closure number of vertex；Each bar side of the two-dimentional convex closure Q of traversal, obtains point
V' and side v 'gv′g+1The maximum angle β of two end point connecting line compositiong, maximum angle βgFor ∠ vg′v′v′g+1Maximum, then target
The boarder probability of point v is：
AnglePr (v) is compared with predetermined threshold value σ, if anglePr (v) >=σ, impact point v be boundary point, otherwise impact point v
For internal point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610956616.5A CN106548484A (en) | 2016-10-27 | 2016-10-27 | Product model dispersion point cloud Boundary characteristic extraction method based on two-dimentional convex closure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610956616.5A CN106548484A (en) | 2016-10-27 | 2016-10-27 | Product model dispersion point cloud Boundary characteristic extraction method based on two-dimentional convex closure |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106548484A true CN106548484A (en) | 2017-03-29 |
Family
ID=58393137
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610956616.5A Pending CN106548484A (en) | 2016-10-27 | 2016-10-27 | Product model dispersion point cloud Boundary characteristic extraction method based on two-dimentional convex closure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106548484A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107452065A (en) * | 2017-07-05 | 2017-12-08 | 山东理工大学 | The border spot identification method of surface sampled data in kind |
| KR20190030788A (en) * | 2017-07-31 | 2019-03-25 | 주식회사 자이언소프트 | 3-dimension clothing data creating system |
| CN109974725A (en) * | 2017-12-28 | 2019-07-05 | 北京三快在线科技有限公司 | A kind of road network topology construction method, guidance path calculation method and device |
| CN110230980A (en) * | 2019-05-05 | 2019-09-13 | 广东省计量科学研究院（华南国家计量测试中心） | Dead amount bottom measuring method, system and storage medium based on three-dimensional point cloud |
| CN110321910A (en) * | 2018-03-29 | 2019-10-11 | 中国科学院深圳先进技术研究院 | Feature extracting method, device and equipment towards cloud |
| CN111105490A (en) * | 2020-02-07 | 2020-05-05 | 武汉玄景科技有限公司 | Rapid normal vector orientation method for scattered point clouds |
| CN111127312A (en) * | 2019-12-25 | 2020-05-08 | 武汉理工大学 | Method for extracting circle from point cloud of complex object and scanning device |
| CN111179290A (en) * | 2019-12-26 | 2020-05-19 | 东软睿驰汽车技术（沈阳）有限公司 | Method and related device for determining convex hull |
| CN112710313A (en) * | 2020-12-31 | 2021-04-27 | 广州极飞科技股份有限公司 | Overlay path generation method and device, electronic equipment and storage medium |
| CN112825791A (en) * | 2020-12-25 | 2021-05-25 | 河南科技大学 | Milk cow body condition scoring method based on deep learning and point cloud convex hull characteristics |
| CN116740114A (en) * | 2023-08-11 | 2023-09-12 | 之江实验室 | Object boundary fitting method and device based on convex hull detection |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101510308A (en) * | 2009-03-26 | 2009-08-19 | 山东理工大学 | Method for rapidly extracting product model point cloud boundary characteristics |
-
2016
- 2016-10-27 CN CN201610956616.5A patent/CN106548484A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101510308A (en) * | 2009-03-26 | 2009-08-19 | 山东理工大学 | Method for rapidly extracting product model point cloud boundary characteristics |
Non-Patent Citations (3)
| Title |
|---|
| ADRIANO MOREIRA AND MARIBEL YASMINA SANTOS: "CONCAVE HULL: A K-NEAREST NEIGHBOURS APPROACH FOR THE COMPUTATION OF THE REGION OCCUPIED BY A SET OF POINTS", 《GRAPP 2007 - INTERNATIONAL CONFERENCE ON COMPUTER GRAPHICS THEORY AND APPLICATIONS》 * |
| GERHARD H. BENDELS ET AL: "Detecting Holes in Point Set Surfaces", 《WSCG’2006》 * |
| 杨振清 等: "基于点云切片的边界提取", 《计算机应用与软件》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107452065A (en) * | 2017-07-05 | 2017-12-08 | 山东理工大学 | The border spot identification method of surface sampled data in kind |
| KR102042551B1 (en) | 2017-07-31 | 2019-11-12 | 주식회사 자이언소프트 | 3-dimension clothing data creating system |
| KR20190030788A (en) * | 2017-07-31 | 2019-03-25 | 주식회사 자이언소프트 | 3-dimension clothing data creating system |
| CN109974725A (en) * | 2017-12-28 | 2019-07-05 | 北京三快在线科技有限公司 | A kind of road network topology construction method, guidance path calculation method and device |
| CN109974725B (en) * | 2017-12-28 | 2022-03-08 | 北京三快在线科技有限公司 | Road network topology construction method, navigation path calculation method and device |
| CN110321910A (en) * | 2018-03-29 | 2019-10-11 | 中国科学院深圳先进技术研究院 | Feature extracting method, device and equipment towards cloud |
| CN110321910B (en) * | 2018-03-29 | 2021-05-28 | 中国科学院深圳先进技术研究院 | Point cloud-oriented feature extraction method, device and equipment |
| CN110230980A (en) * | 2019-05-05 | 2019-09-13 | 广东省计量科学研究院（华南国家计量测试中心） | Dead amount bottom measuring method, system and storage medium based on three-dimensional point cloud |
| CN111127312A (en) * | 2019-12-25 | 2020-05-08 | 武汉理工大学 | Method for extracting circle from point cloud of complex object and scanning device |
| CN111127312B (en) * | 2019-12-25 | 2023-08-22 | 武汉理工大学 | Method for extracting circles from point clouds of complex objects and scanning device |
| CN111179290B (en) * | 2019-12-26 | 2023-04-28 | 东软睿驰汽车技术（沈阳）有限公司 | Method and related device for determining convex hull |
| CN111179290A (en) * | 2019-12-26 | 2020-05-19 | 东软睿驰汽车技术（沈阳）有限公司 | Method and related device for determining convex hull |
| CN111105490B (en) * | 2020-02-07 | 2023-03-31 | 武汉玄景科技有限公司 | Rapid normal vector orientation method for scattered point clouds |
| CN111105490A (en) * | 2020-02-07 | 2020-05-05 | 武汉玄景科技有限公司 | Rapid normal vector orientation method for scattered point clouds |
| CN112825791A (en) * | 2020-12-25 | 2021-05-25 | 河南科技大学 | Milk cow body condition scoring method based on deep learning and point cloud convex hull characteristics |
| CN112825791B (en) * | 2020-12-25 | 2023-02-10 | 河南科技大学 | Milk cow body condition scoring method based on deep learning and point cloud convex hull characteristics |
| CN112710313A (en) * | 2020-12-31 | 2021-04-27 | 广州极飞科技股份有限公司 | Overlay path generation method and device, electronic equipment and storage medium |
| CN116740114A (en) * | 2023-08-11 | 2023-09-12 | 之江实验室 | Object boundary fitting method and device based on convex hull detection |
| CN116740114B (en) * | 2023-08-11 | 2023-11-21 | 之江实验室 | Object boundary fitting method and device based on convex hull detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106548484A (en) | Product model dispersion point cloud Boundary characteristic extraction method based on two-dimentional convex closure | |
| Wang et al. | Lidar point clouds to 3-D urban models $: $ A review | |
| CN106127857B (en) | The on-board LiDAR data modeling method of integrated data driving and model-driven | |
| CN103413133B (en) | Automatically-extracting power line method in random laser point cloud data | |
| CN103310481B (en) | A kind of point cloud compressing method based on fuzzy entropy iteration | |
| CN107392875A (en) | A kind of cloud data denoising method based on the division of k neighbours domain | |
| CN106780458B (en) | Point cloud framework extraction method and device | |
| CN102890828B (en) | Point cloud data compacting method based on normal included angle | |
| CN101477529B (en) | Three-dimensional object retrieval method and apparatus | |
| CN104299260A (en) | Contact network three-dimensional reconstruction method based on SIFT and LBP point cloud registration | |
| CN108920765B (en) | Hypothetical plane fitting method based on building three-dimensional line segment model | |
| CN105572687A (en) | Method for manufacturing building digital line map based on vehicle-mounted laser radar point cloud | |
| Galvanin et al. | Extraction of building roof contours from LiDAR data using a Markov-random-field-based approach | |
| CN105224935A (en) | A kind of real-time face key point localization method based on Android platform | |
| CN106886980A (en) | A kind of enhanced method of point cloud density based on three-dimensional laser radar target identification | |
| CN111340822B (en) | Multi-scale self-adaptive airborne LiDAR point cloud building single segmentation method | |
| CN103839274B (en) | A kind of Extended target tracking based on geometric proportion relation | |
| CN103345774A (en) | Method for building three-dimensional multi-scale vectorization model | |
| CN104965928A (en) | Chinese character image retrieval method based on shape matching | |
| Chen et al. | Plane segmentation for a building roof combining deep learning and the RANSAC method from a 3D point cloud | |
| CN104063893A (en) | Urban building visualization method based on Gestalt psychological criterions and multi-tag graph cut minimization | |
| CN112634458B (en) | Oral model point cloud simplifying method based on feature significance evaluation | |
| CN105426626B (en) | Multiple-Point Geostatistics modeling method based on set of metadata of similar data pattern cluster | |
| Mateo et al. | Hierarchical, Dense and Dynamic 3D Reconstruction Based on VDB Data Structure for Robotic Manipulation Tasks | |
| CN100552722C (en) | Method for extracting multi-dimension curvature characteristic on triangle gridding |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170329 |