CN110378917A - Tooth dividing method based on peak value cluster - Google Patents
Tooth dividing method based on peak value cluster Download PDFInfo
- Publication number
- CN110378917A CN110378917A CN201910641265.2A CN201910641265A CN110378917A CN 110378917 A CN110378917 A CN 110378917A CN 201910641265 A CN201910641265 A CN 201910641265A CN 110378917 A CN110378917 A CN 110378917A
- Authority
- CN
- China
- Prior art keywords
- demarcation
- point
- line
- tooth
- peak value
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30036—Dental; Teeth
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a kind of tooth dividing methods based on peak value cluster, comprising the following steps: S1, extracts three-dimensional corona model boundary, that is, gums line of demarcation B, and B is divided into preceding line of demarcation B2With rear line of demarcation B1；S2, the point progress peak value on the B of gums line of demarcation is clustered to obtain candidate tooth seam points；S3, candidate tooth seam points are matched to obtain seam points pair；S4, to each seam points pair, seek its geodetic path on three-dimensional corona model, geodetic path of the three-dimensional corona model between seam points pair be split, single tooth model is obtained.The present invention is directed to the characteristics of tooth model gums line of demarcation, density peaks cluster is carried out by using three-dimensional boundary information to obtain borderline seam points as cut-point, by the method for cluster the complicated boundary shape of sawtooth like shape will not be had a huge impact to result, and the interaction of user is not needed, automatically and efficiently tooth model can be split.
Description
Technical field
The present invention relates to graph and image processing technical fields, and in particular to a kind of tooth segmentation side based on peak value cluster
Method.
Background technique
For the dividing method of tooth mesh model, following classification can be divided into: (1) based on curvature
(curvature) dividing method；(2) it is based on the dividing method of projected image (image)；(3) based on reconciliation field (harmonic
Field dividing method).
Wherein, the dividing method of (1) based on curvature (curvature) is specific as follows:
Dividing method based on curvature generally calculates minimum principal curvatures (the minimum principal of grid surface
Curvature) or average curvature (mean curvature), possible tooth boundary is extracted by the way that the threshold value of curvature is arranged
The characteristic area on (tooth-tooth boundary and tooth-gingiva boundary), due to including many garbages in field of curvature, so
There are certain methods to will use Morphological skeleton (morphologic skeleton operations/morphologic
Operator) Lai Youhua boundary characteristic region and by extract region skeleton obtain the boundary line of tooth, fastmarching
Watersheds is that user one face of label first on every tooth of a tooth model is known as mark point (marker), so
After calculate field of curvature, then to each mark point (marker) using curvature carry out region growth (region growing) obtain
Dough sheet region corresponding to each tooth.There are also some other methods such as flood-fill, snake-based method
It is directly to be split using these regions.
The main deficiency of these methods is the dependence to curvature feature, needs to be arranged a global threshold value, some sides
Method be using one be arranged definite value, method be to be arranged by the interaction of user.The setting of threshold value can largely
It is upper influence segmentation as a result, and be difficult to meet the tooth model of different shape, it is easy to lead to over-segmentation (over-
Segmentation) or less divided (under-segmentation), on the other hand, curvature of curved surface is very sensitive to noise, drop
The low reliability of this kind of method.
(2) dividing method based on projected image (image) is specific as follows:
Zou etc. proposes the interaction tooth partitioning scheme based on reconciliation field, and Liao etc. is proposed based on the automatic of reconciliation field
Tooth dividing method, such methods identify characteristic point (cusp on tooth) and occlusal surface on tooth first, and find one
A section come it is rough separates gingival areas, using the knowledge of these priori of front as constraint with specific weight definition,
Laplace's equation is solved by least squares error and obtains a reconciliation field on curved surface, selects suitable contour
The boundary of every tooth is obtained, and then tooth is split, obtains segmentation result.
(3) dividing method based on reconciliation field (harmonic field) is specific as follows:
Dividing method based on projected image by interaction or calculate a plane, then by model projection arrive this
The two dimensional image projected in plane, by carrying out processing segmentation to two-dimentional boundary, then using two dimension segmentation result come
Obtain the segmentation result of three-dimensional tooth model.Kim etc. seeks two-dimentional tooth side by the method that polar coordinates local extremum judges
Seam points in boundary between adjacent teeth as cut-point and match, and are mapped on threedimensional model and seek between two o'clock
Geodetic path divide adjacent tooth.This method due to boundary itself complexity and only be used only two-dimensional information,
It may generate far more than actual cut-point.
Yang etc. equally seeks on tooth model boundary cut-point between adjacent teeth, is selected by user's interaction
Borderline point (control points) calculates the geodetic path between two adjacent control points then to obtain single tooth
The boundary of tooth, it is available good by the interaction of user as a result, still user need to rotate or mobility model repeatedly come
Specific point is marked, too many interaction is so that this method is cumbersome and inefficient.
Summary of the invention
The purpose of the present invention is to solve drawbacks described above in the prior art, provide a kind of tooth based on peak value cluster
Dividing method.
The purpose of the present invention can be reached by adopting the following technical scheme that:
It is a kind of based on peak value cluster tooth dividing method, the tooth dividing method the following steps are included:
S1, three-dimensional corona model boundary, that is, gums line of demarcation B is extracted, and B is divided into preceding line of demarcation B2With rear line of demarcation
B1；
S2, the point progress peak value on the B of gums line of demarcation is clustered to obtain candidate tooth seam points；
S3, candidate tooth seam points are matched to obtain seam points pair；
S4, to each seam points pair, its geodetic path on three-dimensional corona model is sought, by three-dimensional corona model along connecing
Geodetic path of the seam point between is split, and obtains single tooth model.
Further, the step S1 process is as follows:
Given one has separated the three-dimensional corona model of gum, seeks the boundary i.e. gums point of three-dimensional corona model first
Then boundary line B is divided gums line of demarcation B for preceding line of demarcation B by boundary two-end-point a, b2With rear line of demarcation B1, wherein a, b point
For maximum a pair of of the point of geodesic distance on three-dimensional corona model.
Further, gums line of demarcation B is divided for preceding line of demarcation B in the step S12With rear line of demarcation B1Process is such as
Under:
It is solved by the method for iteration, randomly selects a point p on three-dimensional corona model first1For initial point, three are sought
Tie up point p farthest with its geodesic distance on corona model2, then to point p2Seek the point p farthest with its geodesic distance3, and so on,
Obtain the point range p being located on gums line of demarcation1,p2,…,pm, they meet: | | p1p2||≤||p2p3||≤…≤||
pm-1pm||；
Given number of iterations, the result p that last time iteration is acquiredm,pm+1Boundary is divided as model boundary cut-point
It cuts open.
Further, the step S2, on the B of gums line of demarcation point carry out peak value cluster to obtain candidate tooth seam
The process of point is as follows:
S21, the preceding line of demarcation B according to three-dimensional corona model2With rear line of demarcation B1Calculate every bit q on the B of gums line of demarcationi
Dominance index ρi, i=1,2 ..., n；
S22, every bit q on the B of gums line of demarcation is calculatediRelative distance index δi；
S23, every bit q on the B of gums line of demarcation is calculatediPriority γi；
S24, the boundary point for exporting weight γ > t are candidate seam points, and wherein t is given threshold value.
Further, the every bit qiDominance index ρiIt is defined as follows:
qi,qjBelong to not ipsilateral gums line of demarcation, wherein dijIt is every on the B of gums line of demarcation
One point q1,q2,…,qnBetween mutual linear distance, i, j=1,2 ..., n.
Further, the every bit qiRange index δiIt is defined as follows:
qi,qjBelong to the gums line of demarcation of the same side, i, j=1,2 ..., n.
Further, the every bit qiPriority γiIt is defined as follows:
γi=ρi×δi, i, j=1,2 ..., n.
Further, the step S3, the process for being matched to obtain seam points pair to candidate tooth seam points are as follows:
The candidate tooth seam points for being located at two sides gum line are obtained according to peak value clustering algorithm, for each point,
The other side and the shortest point of its space length are sought, for the closest approach of the point, if closest approach, this two o'clock constitute one to two o'clock each other
Otherwise seam points pair abandon the point.
The present invention has the following advantages and effects with respect to the prior art:
The present invention is directed to the characteristics of tooth model gums line of demarcation, carries out density peaks by using three-dimensional boundary information
It clusters to obtain borderline seam points as cut-point, the complicated boundary shape of sawtooth like shape is made by the method for cluster
Shape will not have a huge impact result, and not need the interaction of user, can automatically and efficiently to tooth model into
Row segmentation.
Detailed description of the invention
Fig. 1 is the boundary schematic diagram that the three-dimensional corona model of gum has been separated in the embodiment of the present invention；
Fig. 2 is the cutting procedure schematic diagram one of three-dimensional corona model in the embodiment of the present invention；
Fig. 3 is the cutting procedure schematic diagram two of three-dimensional corona model in the embodiment of the present invention；
Fig. 4 is the cutting procedure schematic diagram three of three-dimensional corona model in the embodiment of the present invention；
Fig. 5 is the cutting procedure schematic diagram four of three-dimensional corona model in the embodiment of the present invention；
Fig. 6 is the schematic diagram of the candidate tooth seam points of gained in the embodiment of the present invention；
Fig. 7 is the process step figure of the tooth dividing method based on peak value cluster disclosed in the embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Embodiment
As shown in fig. 7, present embodiment discloses a kind of tooth dividing method based on peak value cluster, the tooth dividing method
The following steps are included:
S1, three-dimensional corona model boundary is divided into preceding line of demarcation B2With rear line of demarcation B1；
Given one has separated the three-dimensional corona model of gum, seeks the boundary i.e. gums point of three-dimensional corona model first
Boundary line B, as shown in Figure 1, then being divided gums line of demarcation B for preceding line of demarcation B by boundary two-end-point a, b2With rear line of demarcation B1,
As shown in Figure 2.
A, b point is maximum a pair of of the point of geodesic distance on three-dimensional corona model.
It is solved by the method for iteration, randomly selects a point p on three-dimensional corona model first1For initial point, three are sought
Tie up point p farthest with its geodesic distance on corona model2, then to p2Seek the point p farthest with its geodesic distance3, and so on, it obtains
The point range p being located on gums line of demarcation to one1,p2,…,pm, they meet: | | p1p2||≤||p2p3||≤…≤||pm-1pm
||。
Given number of iterations, the result p that last time iteration is acquiredm,pm+1Boundary is divided as model boundary cut-point
It cuts open, as shown in Figure 2.
As shown in Figure 3 and Figure 4, using the result of 2 iteration.
S2, the point progress peak value on the B of gums line of demarcation is clustered to obtain candidate tooth seam points；
Gums line of demarcation is as shown in Figure 1, gums line of demarcation is distributed in eckband shape, and each eckband is by four tooth seam points
(such as Fig. 6) is at wrapping a tooth.
The present embodiment solves the tooth seam points on the B of gums line of demarcation by density peaks clustering algorithm.Firstly for
Each point q on the B of gums line of demarcation1,q2,…,qn, find out the mutual linear distance d between themij, obtain matrix D=
(dij)n×n, i, j=1,2 ..., n；
Define each point qiDominance it is as follows:
qi,qjBelong to not ipsilateral gums line of demarcation；It is bigger that it means that tooth seam points have
Dominance (has closer distance to the gums line of demarcation of opposite end)；
Secondly, being each point qiDefine a range index δi:
qi,qjBelong to the gums line of demarcation of the same side；This means that if two close proximities
Words at most have a point to be likely to become tooth seam points (even if the dominance of the two is all very big).
Both the above combined factors are got up, product γ is passed throughi=ρi×δiSize determine the preferential of tooth seam points
Grade.In other words, γiIt is bigger, qiMore it is likely to be the seam points for needing to find.
The process for seeking candidate tooth seam points is as follows:
S21, the preceding line of demarcation B according to three-dimensional corona model2With rear line of demarcation B1Calculate every bit q on the B of gums line of demarcationi
Dominance index ρi；
S22, every bit q on the B of gums line of demarcation is calculatediRelative distance index δi；
S23, every bit q on the B of gums line of demarcation is calculatediPriority γi；
S24, the boundary point for exporting weight γ > t are candidate seam points, and wherein t is that (the present embodiment is set as given threshold value
0.2)。
As shown in figure 5, being gained candidate tooth seam points.
S3, candidate tooth seam points are matched to obtain seam points pair；
By above-mentioned peak value clustering algorithm, the candidate tooth seam points p for being located at two sides gum line is obtained1,p2,...,
pmAnd q1,q2,...,qn, for each point, the other side and the shortest point of its space length are sought, for the closest approach of the point, if
Two o'clock closest approach each other, then this two o'clock pi,qjA seam points pair are constituted, otherwise abandon the point.Each seam as shown in Figure 6
Point pair.
S4, separation of tooth monomer；
To each seam points pair, its geodetic path on three-dimensional corona model is sought；I.e. two o'clock is on corona model
Shortest path, the cut-off rule between seam points as shown in Figure 6；
Geodetic path of the three-dimensional corona model between seam points pair is split, single tooth model is obtained.
The above embodiment is a preferred embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, other any changes, modifications, substitutions, combinations, simplifications made without departing from the spirit and principles of the present invention,
It should be equivalent substitute mode, be included within the scope of the present invention.
Claims (8)
1. a kind of tooth dividing method based on peak value cluster, which is characterized in that the tooth dividing method includes following step
It is rapid:
S1, three-dimensional corona model boundary, that is, gums line of demarcation B is extracted, and B is divided into preceding line of demarcation B2With rear line of demarcation B1；
S2, the point progress peak value on the B of gums line of demarcation is clustered to obtain candidate tooth seam points；
S3, candidate tooth seam points are matched to obtain seam points pair；
S4, to each seam points pair, its geodetic path on three-dimensional corona model is sought, by three-dimensional corona model along seam points
Geodetic path between is split, and obtains single tooth model.
2. the tooth dividing method according to claim 1 based on peak value cluster, which is characterized in that the step S1 mistake
Journey is as follows:
Given one has separated the three-dimensional corona model of gum, seeks the boundary i.e. gums line of demarcation of three-dimensional corona model first
Then B is divided gums line of demarcation B for preceding line of demarcation B by boundary two-end-point a, b2With rear line of demarcation B1, wherein a, b point are three
Tie up maximum a pair of of the point of geodesic distance on corona model.
3. the tooth dividing method according to claim 1 based on peak value cluster, which is characterized in that in the step S1
Gums line of demarcation B is divided for preceding line of demarcation B2With rear line of demarcation B1Process is as follows:
It is solved by the method for iteration, randomly selects a point p on three-dimensional corona model first1For initial point, three-dimensional corona is sought
The point p farthest with its geodesic distance on model2, then to point p2Seek the point p farthest with its geodesic distance3, and so on, obtain one
A point range p on gums line of demarcation1,p2,…,pm, they meet: | | p1p2||≤||p2p3||≤…≤||pm-1pm||；
Given number of iterations, the result p that last time iteration is acquiredm,pm+1Boundary segmentation is opened as model boundary cut-point.
4. the tooth dividing method according to claim 1 based on peak value cluster, which is characterized in that the step S2,
The process for clustering to obtain candidate tooth seam points to the point progress peak value on the B of gums line of demarcation is as follows:
S21, the preceding line of demarcation B according to three-dimensional corona model2With rear line of demarcation B1Calculate every bit q on the B of gums line of demarcationiSystem
Control power index ρi, i=1,2 ..., n；
S22, every bit q on the B of gums line of demarcation is calculatediRelative distance index δi；
S23, every bit q on the B of gums line of demarcation is calculatediPriority γi；
S24, the boundary point for exporting weight γ > t are candidate seam points, and wherein t is given threshold value.
5. the tooth dividing method according to claim 4 based on peak value cluster, which is characterized in that the every bit qi
Dominance index ρiIt is defined as follows:
qi,qjBelong to not ipsilateral gums line of demarcation, wherein dijIt is each on the B of gums line of demarcation
Point q1,q2,…,qnBetween mutual linear distance, i, j=1,2 ..., n.
6. the tooth dividing method according to claim 4 based on peak value cluster, which is characterized in that the every bit qi
Range index δiIt is defined as follows:
qi,qjBelong to the gums line of demarcation of the same side, i, j=1,2 ..., n.
7. the tooth dividing method according to claim 4 based on peak value cluster, which is characterized in that the every bit qi
Priority γiIt is defined as follows:
γi=ρi×δi, i, j=1,2 ..., n.
8. the tooth dividing method according to claim 4 based on peak value cluster, which is characterized in that the step S3,
The process for being matched to obtain seam points pair to candidate tooth seam points is as follows:
Each point is sought according to the candidate tooth seam points that peak value clustering algorithm obtains being located at two sides gum line
The other side and the shortest point of its space length, for the closest approach of the point, if closest approach, this two o'clock constitute a seam to two o'clock each other
Point pair, otherwise abandons the point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910641265.2A CN110378917B (en) | 2019-07-16 | 2019-07-16 | Tooth segmentation method based on peak value clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910641265.2A CN110378917B (en) | 2019-07-16 | 2019-07-16 | Tooth segmentation method based on peak value clustering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110378917A true CN110378917A (en) | 2019-10-25 |
| CN110378917B CN110378917B (en) | 2023-04-07 |
Family
ID=68253499
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910641265.2A Active CN110378917B (en) | 2019-07-16 | 2019-07-16 | Tooth segmentation method based on peak value clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110378917B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11055850B1 (en) | 2021-01-06 | 2021-07-06 | Oxilio Ltd | Systems and methods for tooth segmentation |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678747A (en) * | 2015-12-30 | 2016-06-15 | 青岛兰信医学科技有限公司 | Tooth mesh model automatic segmentation method based on principal curvature |
| JP2017026430A (en) * | 2015-07-21 | 2017-02-02 | 日本電信電話株式会社 | Marker detection device, method, and program |
| CN108629783A (en) * | 2018-05-02 | 2018-10-09 | 山东师范大学 | Image partition method, system and medium based on the search of characteristics of image density peaks |
| CN109145964A (en) * | 2018-08-01 | 2019-01-04 | 武汉大学 | A kind of method and system for realizing color of image cluster |
| CN109582003A (en) * | 2018-12-03 | 2019-04-05 | 东北林业大学 | Based on pseudo label semi-supervised kernel part Fei Sheer discriminant analysis bearing failure diagnosis |
-
2019
- 2019-07-16 CN CN201910641265.2A patent/CN110378917B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2017026430A (en) * | 2015-07-21 | 2017-02-02 | 日本電信電話株式会社 | Marker detection device, method, and program |
| CN105678747A (en) * | 2015-12-30 | 2016-06-15 | 青岛兰信医学科技有限公司 | Tooth mesh model automatic segmentation method based on principal curvature |
| CN108629783A (en) * | 2018-05-02 | 2018-10-09 | 山东师范大学 | Image partition method, system and medium based on the search of characteristics of image density peaks |
| CN109145964A (en) * | 2018-08-01 | 2019-01-04 | 武汉大学 | A kind of method and system for realizing color of image cluster |
| CN109582003A (en) * | 2018-12-03 | 2019-04-05 | 东北林业大学 | Based on pseudo label semi-supervised kernel part Fei Sheer discriminant analysis bearing failure diagnosis |
Non-Patent Citations (3)
| Title |
|---|
| HONG ZHU ET AL.: "Medical Image Segmentation Using Fruit Fly Optimization and Density Peaks Clustering", 《COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE》 * |
| 朱红 等: "面向医学图像分割的蚁群密度峰值聚类", 《南京师大学报（自然科学版）》 * |
| 邹旭华 等: "一种密度峰值聚类的彩色图像分割方法", 《小型微型计算机***》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11055850B1 (en) | 2021-01-06 | 2021-07-06 | Oxilio Ltd | Systems and methods for tooth segmentation |
| US11625831B2 (en) | 2021-01-06 | 2023-04-11 | Oxilio Ltd | Systems and methods for determining an orthodontic treatment for a subject based on tooth segmentation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110378917B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106815847B (en) | Trees dividing method and single tree extracting method based on laser radar point cloud | |
| KR102154470B1 (en) | 3D Human Hairstyle Generation Method Based on Multiple Feature Search and Transformation | |
| CN105046750B (en) | A kind of method of the full jaw tooth triangle grid model of automatic segmentation | |
| CN104134234B (en) | A kind of full automatic three-dimensional scene construction method based on single image | |
| CN104715475B (en) | A kind of tooth jaw threedimensional model based on mediation field splits the method for whole coronas automatically | |
| CA2858166C (en) | Method and system for characterising plant phenotype | |
| CN109118574A (en) | A kind of fast reverse modeling method extracted based on three-dimensional feature | |
| CN103400372B (en) | A kind of three-dimensional topology information extracting method described based on Reeb figure | |
| CN106504331A (en) | Tooth modeling method based on three-dimensional model search | |
| CN103871102A (en) | Road three-dimensional fine modeling method based on elevation points and road outline face | |
| CN107464223B (en) | Point cloud hole repairing method based on slices | |
| EP3341753B1 (en) | Method for identifying individual trees in airborne lidar data and corresponding computer program product | |
| CN108338848B (en) | Stripping type laser tooth preparation method, apparatus, equipment and medium | |
| CN108919295A (en) | Airborne LiDAR point cloud road information extracting method and device | |
| CN111710022B (en) | Rapid forming slice processing method for avoiding contour intersection | |
| CN115205690B (en) | Method and device for extracting street tree in monomer mode based on MLS point cloud data | |
| CN107292951B (en) | Tooth restoration method based on multiple sets of templates | |
| CN103632371A (en) | Compatibility mesh segmentation based skeleton parameter computation method | |
| CN108765478A (en) | It is a kind of to build the density clustering algorithm that separating monomer is built in point cloud | |
| CN110378917A (en) | Tooth dividing method based on peak value cluster | |
| CN108304811B (en) | RGBD information-based three-dimensional face value scoring method, device and system | |
| CN116051980B (en) | Building identification method, system, electronic equipment and medium based on oblique photography | |
| CN115423935B (en) | Visual field analysis method and system for historical culture neighborhood | |
| CN115937466A (en) | Three-dimensional model generation method, system and storage medium integrating GIS | |
| CN107492148A (en) | It is extensive without demarcation surface points cloud reconstruction face of cylinder method based on SVM and K Means |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |