CN103236043A - Plant organ point cloud restoration method - Google Patents
Plant organ point cloud restoration method Download PDFInfo
- Publication number
- CN103236043A CN103236043A CN2013101544003A CN201310154400A CN103236043A CN 103236043 A CN103236043 A CN 103236043A CN 2013101544003 A CN2013101544003 A CN 2013101544003A CN 201310154400 A CN201310154400 A CN 201310154400A CN 103236043 A CN103236043 A CN 103236043A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- cloud
- template
- plant organ
- feature
- 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
Images
Landscapes
- Processing Or Creating Images (AREA)
Abstract
The invention provides a plant organ point cloud restoration method, which relates to the field of three-dimensional image restoration. The plant organ point cloud restoration method includes the following steps: (S1) plant organ point cloud templates are constructed, so that a point cloud template set is generated; (S2) a missing organ point cloud is matched with the point cloud template set in order to find out a point cloud template which is closest to the missing organ point cloud; and (S3) on the basis of the closest point cloud template, the missing point cloud is restored. By solving the problem on how to restore missing bulk plant organ point cloud data, complete point cloud data can be obtained in the process of plant scanning by the plant organ point cloud restoration method. The accuracy of restoration is high, restored point clouds and original point clouds can be merged perfectly, and restored parts can reflect the main features of plant organs.
Description
Technical field
The present invention relates to the reparation field of 3-D view, be specifically related to a kind of plant organ point cloud restorative procedure.
Background technology
In recent years, along with reaching its maturity of three-dimensional laser scanning technique and extensively popularizing of pertinent instruments equipment, utilize the 3 D laser scanning data to carry out three-dimensional reconstruction and become the research focus, aspect phytomorph structure measurement and analysis, the collecting method of traditional-handwork exists speed slow, shortcomings such as precision is low, be difficult to satisfy the scientific research requirement, and the 3 D laser scanning measuring technique can overcome the limitation that traditional-handwork is measured to a great extent, adopt noncontact active metering system directly to obtain the high-precision three-dimensional data, can scan arbitrary objects, and it is fast to have sweep velocity, real-time, characteristics such as precision height.But the phytomorph structure is comparatively complicated, utilizing spatial digitizer to carry out in the three dimensional point cloud acquisition process of plant organ, blocking between the wax attribute on Chang Yinwei plant organ surface (as pepper fruit, apple fruit) or organ (being wrapped in the female fringe of corn as maize leaf), scanning result is subject to the interference of luminous environment, therefore directly from the three dimensional point cloud that plant scanning obtains, often there is more missing data, and the part that lacks mostly is bulk point cloud disappearance, and is different with the small holes disappearance of other field.These disappearance parts not only make and are difficult to make up the plant organ geometric model, model is carried out area, volume etc. calculate for how much, also can influence the follow-up processing of model etc.Therefore, the reparation of plant organ point cloud is based on an important process of the Plant Morphologic of laser three-dimensional scanning data.
Carrying out a few thing aspect the hole reparation of three-dimensional point cloud both at home and abroad, the domestic patent of finding of typically working has following several pieces:
First piece is " based on the method for filling dot cloud hole of the 3-D scanning of B-spline surface ", this disclosure of the Invention a kind of method for filling dot cloud hole based on the 3-D scanning of B-spline surface that the surface fitting degree of accuracy can be provided.
Second piece is the complementing method of the monumented point hole of neural network " in the 3-D scanning point cloud based on ", this invention provide a kind of can guarantee the hole data filled up and ambient data continuously and some cloud character representation better based on the method for filling dot cloud hole of the 3-D scanning of neural network, this invention has the simple advantage of method.
The 3rd piece is " method for filling dot cloud hole of 3-D scanning ", disclosure of the Invention a kind of method for filling dot cloud hole of the 3-D scanning based on the triangular domain bezier surface, it comprises mock-up, 3-D data collection, data pre-service, curve and surface reconstruct and analysis, surface fitting, cad model modeling, data programing processing, part, measured database, CAD simulated reservoir link.This invention adopts surface fitting method can obtain the curved surface of scattered point set around the accurate match hole, thereby can guarantee higher fitting precision when curved surface is got a some perforations adding.
The 4th piece " thin-wall complicated curved surface part three-dimensional machining preprocessing method " utilizes completion method in kind by sweep trace repair mode one by one, realizes the rectangle topology reparation to whole thin-wall complicated curved surface cloud data; Pre-service is repaired in hole or skewness zone in the sweep trace point cloud raw data of thin-wall complicated curved surface part.
In the above-mentioned prior art, method mostly be at a fritter dot cloud hole or targetedly industrial part carry out, research at plant organ cloud data disappearance is less, and substantially all can't solve the reparation problem of bulk plant organ cloud data disappearance, be that these methods are mostly at specific disappearance zone, aspect repairing at plant organ point cloud disappearance, still there is not more perfect work.
Summary of the invention
(1) technical matters of Xie Jueing
At the deficiencies in the prior art, the invention provides a kind of plant organ point cloud restorative procedure.Conventional some cloud is repaired and mostly is that utilization waits that the geometric properties of repairing a cloud itself repairs, of the present inventionly considered that plant sample is more, has higher similarity between homolog, again disappearance point cloud and template are contrasted the reparation that realizes disappearance point cloud based on making up template earlier, solved the reparation problem of bulk plant organ cloud data disappearance, made in the plant scanning process, to obtain complete cloud data.
(2) technical scheme
For realizing above purpose, the present invention is achieved by the following technical programs:
A kind of plant organ point cloud restorative procedure comprises following steps:
S1, structure plant organ point cloud template generate some cloud template set;
S2, will lack organ point cloud and described some cloud template set mates, find out the some cloud template that approaches the most with described disappearance organ point cloud;
S3, based on the described some cloud template that approaches the most a disappearance point cloud is repaired.
Wherein, step S1 comprises following steps:
S11, utilize spatial digitizer that the plant organ A of pre-structure template is carried out 3-D scanning, with the initial three dimensional point cloud of plant organ A carry out that a cloud is cut apart, denoising and resampling handle, and obtains the some cloud template E of plant organ
i
The method of S12, employing step S11 makes up N the form plant organ point cloud template similar to the disappearance organ, generates a some cloud template set V
A={ E
i, i=1, L, N}, and the some feature histogram PFH information of calculating each point cloud is as a feature of cloud template.
Wherein, the some feature histogram PFH computing method of step S12 mid point cloud are: use the Harris key point to survey subalgorithm to the each point cloud and obtain key point, then by a feature histogram FPFH feature method of estimation to a cloud computing feature.
Wherein, step S2 comprises following steps:
S21, will lack organ point cloud and be designated as A
#, calculate A
#Some feature histogram PFH feature;
S22, at V
AIn find out and A by feature matching method
#Feature is points of proximity cloud template E the most
k, calculate described A respectively
#With described E
kBounding box, with described E
kBounding box according to A
#The length and width of bounding box are carried out equal proportion convergent-divergent, E at high proportion
kTemplate behind the convergent-divergent is designated as
Wherein, step S3 comprises following steps:
S31, with described A
#Generate corresponding triangle gridding, be designated as M
AWith described
Generate corresponding triangle gridding, be designated as M
E
S32, employing grid deforming method are with described M
EBe deformed into
, wherein
Be M
ACorresponding zone, distortion back,
Be M
AThe disappearance zone;
S33, with described
With M
ACarry out the grid fairing and merge, namely finish the some cloud reparation of disappearance organ after the fusion.
Wherein, adopted the constraint that makes the deformation energy minimum in the deformation process of the grid deforming method that adopts among the step S32.
Wherein, adopt the guarantor's feature triangle gridding fairing algorithm based on weighted least-squares to carry out grid fairing fusion among the step S33.
(3) beneficial effect
The present invention by solving the reparation problem of bulk plant organ cloud data disappearance, can obtain complete cloud data by a kind of plant organ point cloud restorative procedure is provided in the plant scanning process.This method is repaired the accuracy height, and it is good to repair some cloud and original point cloud amalgamation, repairs the principal character that part can reflect plant organ.
Description of drawings
Fig. 1, plant organ point cloud restorative procedure process flow diagram;
The stem stalk three-dimensional point cloud atlas of Fig. 2, disappearance;
The stem stalk three-dimensional point cloud atlas of Fig. 3, reparation;
The synoptic diagram of Fig. 4, calculation level feature histogram PFH.
Embodiment
Regard to a kind of plant organ point cloud restorative procedure proposed by the invention down, describe in detail in conjunction with the accompanying drawings and embodiments.
Embodiment 1:
At first setting up various plants organ point cloud template, mainly is to repair at the some cloud disappearance problem that produces in the whole plant 3-D scanning process.
The organ template: popular organ template is exactly to build up the organ point cloud of some complete form earlier, and they are as template, and the organ point cloud of disappearance and its contrast replenish the part that lacks in the organ; Same organ template set is topological isomorphic with the disappearance organ.
The flow process of present embodiment is: it is A that note has the A organ point cloud of a disappearance
#, the organ (N sample) that we select to be similar to its form carries out the destructiveness sampling, sets up complete organ template respectively, forms organ template set V
A={ E
i, i=1 ..., N}, wherein E
iBe i template.The work that we will do is exactly from V
AIn select an immediate template E of form with it
k, and with A
#The part of disappearance is repaired by the method for coupling.
Specific implementation process comprises following steps:
S1, structure plant organ point cloud template generate some cloud template set;
Step S1 comprises following steps:
S11, utilize spatial digitizer that the plant organ A of pre-structure template is carried out 3-D scanning, with the initial three dimensional point cloud of plant organ A carry out that a cloud is cut apart, denoising and resampling handle, and obtains the some cloud template E of plant organ
i, E
iBe complete crop organ's three-dimensional point cloud geometric model.
The method of S12, employing step S11 makes up N the form plant organ point cloud template similar to the disappearance organ at the disappearance organ, generates a cloud template set V
A={ E
i, i=1 ..., N}, and calculate the wherein some feature histogram PFH(Point Feature Histograms of each point cloud) and information is as a feature of cloud template.
The point feature histogram PFH computing method of step S12 mid point cloud are: use the Harris key point to survey subalgorithm to the each point cloud and obtain key point, then by quick some feature histogram FPFH(Fast Point Feature Histograms) the feature method of estimation is to a cloud computing feature.
The point feature histogram concrete grammar that calculates the set point cloud is as follows:
At first the point in the arbitrfary point K neighborhood in the reply point cloud to the some calculation level feature composition characteristic vector of source data point K neighborhood, obtains exporting histogram with all result's statistics more at last to determining the source data point.Concrete steps are as follows:
(1) to P
iArbitrfary point in the some K-neighborhood is to determining the source data point;
At first, ask for any three-dimensional point P in a cloud
iThe average curvature of curved surface that the place produces.Namely to P
iSearch is at P
iThe normal vector (K-neighborhood) of the neighborhood point in the r radius ball of point.After obtaining all normal vectors, utilize the visual angle information that exists to reorientate them.If
N so
Pi=-n
PiWherein, n
PiBe p
iNormal vector, v is the visual angle, || v-p
i|| be v-p
iMould.
To the arbitrfary point in the P point K neighborhood to p
i, p
j(j＜i) and estimation technique vector n
i, n
j, select a source data point P
sAnd number of targets strong point P
tThe P here
sPoint is estimate vector and P
t-P
sThe point that vector angle is less, even＜n
i, p
j-p
iThe n of 〉≤＜
j, p
i-p
j, P then
s=P
i, P
t=P
jOtherwise, P
s=P
j, P
t=P
i
(2) calculate four kinds of features, to the some cloud computing point feature histogram PFH of k value neighborhood;
In source data point, do as giving a definition: u=n
s, v=(P
t-P
s) * u, w=u * v is illustrated in figure 4 as the synoptic diagram of calculation level feature histogram PFH;
Four features are designated as f respectively
1, f
2, f
3, f
4, by calculating as giving a definition:
f
1=<v,n
1>
f
2=||P
t-P
s||
f
3=<u,P
t-P
s>/f
2
f
4=a?tan(<w,n
t>,<u,n
t>)
Wherein, four kinds of normal vector and measurements of the angle between the distance vector that feature is point-to-point transmission point.f
1And f
3Be the cosine value of tri-vector angle, f
4Be n
tWith the angle that u forms, f
2Be P
tWith P
sBetween distance value.
Four features are divided into a plurality of intervals compare power with each feature of diacritical point centering, to feature f
iThe set-point s of setting one in its span
iIt is divided into two intervals, with step (s
i, f
i) power of representation feature carries out evaluation.If f
i＜s
i, make step (s
i, f
i) wait 0.Otherwise, be 1.Try to achieve the idx value by following formula again, all result's statistics are obtained exporting histogram.Wherein, to calculating, idx is in order to the every stack features vector of mark to the point in all K neighborhoods of cloud P point.In histogram, horizontal ordinate is that its corresponding ordinate value of idx value represents to comprise the shared number percent of always counting of the source point that has this feature in the neighborhood.
In order to improve travelling speed, adopt the PFH account form of simplifying to calculate the geometric properties of cloud data, namely put feature histogram (FPFH) fast.At first calculate 3 eigenwerts except distance feature between query point and its neighborhood, form the some feature histogram of simplifying (SPFH).Redefine the K neighborhood of each point then, use contiguous SPFH value to calculate the final FPFH of query point.FPFH has synthesized histogram by decomposing three eigenwerts simplification, and each eigenwert average mark is slit into 11 intervals, then each characteristic dimension is drawn separately, and the statistics that links together at last generates a feature histogram.
S2, will lack organ point cloud and described some cloud template set mates, find out the some cloud template that approaches the most with described disappearance organ point cloud;
Step S2 comprises following steps:
S21, will lack organ point cloud and be designated as A
#, calculate A
#The PFH feature;
S22, at V
AIn find out and A by feature matching method
#Feature is points of proximity cloud template E the most
k(concrete grammar is with A
#The some feature histogram and the some feature histogram of all templates compare, and find out the most similar one group), calculate A respectively
#With E
kBounding box, with template E
kBounding box is according to A
#The length and width of bounding box are carried out equal proportion convergent-divergent, E at high proportion
kTemplate behind the convergent-divergent is designated as
S3, based on the described some cloud template that approaches the most a disappearance point cloud is repaired;
Step S3 comprises following steps:
S31, with described A
#Generate corresponding triangle gridding, be designated as M
AWith described
Generate corresponding triangle gridding, be designated as M
E
Method by a cloud generating mesh adopts Delaunay triangulation method.
S32, employing grid deforming method are with described M
EBe deformed into
, wherein
Be M
ACorresponding zone, distortion back,
Be M
AThe disappearance part;
S33, with described
With M
ACarry out the grid fairing and merge, namely finish the some cloud reparation of disappearance organ after the fusion;
Wherein, adopted the constraint that makes deformation energy (as characteristic energy, rigidity energy etc.) minimum in the deformation process of the grid deforming method that adopts among the step S32.
In the guarantor's feature grid deformation method process that adopts based on differential coordinate energy function:
The energy function of distortion of the mesh is the constraint condition as the control mesh local geometric features, based on the energy function form of differential coordinate is:
T wherein
iBe partial transformation,
It is vertex v
iFace and connect vertex set, w
IjRepresented vertex v
iAnd v
jBetween power, satisfy
It calculates and adopts w
Ij=1/N (i).By minimizing the deformation energy function, calculate the new apex coordinate that the apex coordinate that obtains is distortion back grid, its mathematic(al) representation is:
V=argmin
VE(V)
This formula can be converted into matrix form, and employing Cholesky decomposition method is found the solution the grid after this problem namely obtains being out of shape.
Wherein, adopt the guarantor's feature triangle gridding fairing algorithm based on weighted least-squares to carry out grid fairing fusion among the step S33.
Embodiment 2:
Be example with the corn fruit; some is wrapped up the corn fruit by stem stalk and blade; must carry out the destructiveness sampling if normally obtain complete some cloud; but so just damaged the one-piece construction of milpa; we can utilize the fruit of other plant (do not carry out whole plant scanning) to make up template so; finish the some cloud reparation of disappearance corn fruit on the pre-modeling plant then, be illustrated in figure 2 as the stem stalk three-dimensional point cloud atlas of corn disappearance, Fig. 3 is the model after repairing well.
Above embodiment only is used for explanation the present invention; and be not limitation of the present invention; the those of ordinary skill in relevant technologies field; under the situation that does not break away from the spirit and scope of the present invention; can also make a variety of changes and modification; therefore all technical schemes that are equal to also belong to category of the present invention, and scope of patent protection of the present invention should be defined by the claims.
Claims (7)
1. a plant organ point cloud restorative procedure is characterized in that, comprises following steps:
S1, structure plant organ point cloud template generate some cloud template set;
S2, will lack organ point cloud and described some cloud template set mates, find out the some cloud template that approaches the most with described disappearance organ point cloud;
S3, based on the described some cloud template that approaches the most a disappearance point cloud is repaired.
2. a kind of plant organ point cloud restorative procedure as claimed in claim 1 is characterized in that step S1 comprises following steps:
S11, utilize spatial digitizer that the plant organ A of pre-structure template is carried out 3-D scanning, with the initial three dimensional point cloud of plant organ A carry out that a cloud is cut apart, denoising and resampling handle, and obtains the some cloud template E of plant organ
i
The method of S12, employing step S11 makes up N the form plant organ point cloud template similar to the disappearance organ, generates a some cloud template set V
A={ E
i, i=1 ..., N}, and the some feature histogram PFH information of calculating each point cloud is as a feature of cloud template.
3. a kind of plant organ point cloud restorative procedure as claimed in claim 2, it is characterized in that, the point feature histogram PFH computing method of step S12 mid point cloud are: use the Harris key point to survey subalgorithm to the each point cloud and obtain key point, then by a feature histogram FPFH feature method of estimation to a cloud computing feature.
4. a kind of plant organ point cloud restorative procedure as claimed in claim 2 is characterized in that step S2 comprises following steps:
S21, will lack organ point cloud and be designated as A
#, calculate A
#Some feature histogram PFH feature;
S22, at V
AIn find out and A by feature matching method
#Feature is points of proximity cloud template E the most
k, calculate described A respectively
#With described E
kBounding box, with described E
kBounding box according to A
#The length and width of bounding box are carried out equal proportion convergent-divergent, E at high proportion
kTemplate behind the convergent-divergent is designated as
5. a kind of plant organ point cloud restorative procedure as claimed in claim 4 is characterized in that step S3 comprises following steps:
S31, with described A
#Generate corresponding triangle gridding, be designated as M
AWith described
Generate corresponding triangle gridding, be designated as M
E
S32, employing grid deforming method are with described M
EBe deformed into
Wherein
Be M
ACorresponding zone, distortion back,
Be M
AThe disappearance zone;
S33, with described
With M
ACarry out the grid fairing and merge, namely finish the some cloud reparation of disappearance organ after the fusion.
6. a kind of plant organ point cloud restorative procedure as claimed in claim 5 is characterized in that, has adopted the constraint that makes the deformation energy minimum in the deformation process of the grid deforming method that adopts among the step S32.
7. a kind of plant organ point cloud restorative procedure as claimed in claim 5 is characterized in that, adopts the guarantor's feature triangle gridding fairing algorithm based on weighted least-squares to carry out grid fairing fusion among the step S33.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310154400.3A CN103236043B (en) | 2013-04-28 | 2013-04-28 | A kind of plant organ point cloud restoration method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310154400.3A CN103236043B (en) | 2013-04-28 | 2013-04-28 | A kind of plant organ point cloud restoration method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103236043A true CN103236043A (en) | 2013-08-07 |
| CN103236043B CN103236043B (en) | 2015-10-28 |
Family
ID=48884082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310154400.3A Active CN103236043B (en) | 2013-04-28 | 2013-04-28 | A kind of plant organ point cloud restoration method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103236043B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106845416A (en) * | 2017-01-20 | 2017-06-13 | 百度在线网络技术（北京）有限公司 | Obstacle recognition method and device, computer equipment and computer-readable recording medium |
| CN107343148A (en) * | 2017-07-31 | 2017-11-10 | 广东欧珀移动通信有限公司 | Image completion method, apparatus and terminal |
| CN107369211A (en) * | 2017-07-13 | 2017-11-21 | 云南数云信息科技有限公司 | Ancient building three-dimensional point cloud acquisition system and model review one's lessons by oneself correction method |
| CN107784138A (en) * | 2016-08-26 | 2018-03-09 | 上海宝冶集团有限公司 | Point cloud gravity deformation modification method based on structure mechanics analysis |
| CN108198145A (en) * | 2017-12-29 | 2018-06-22 | 百度在线网络技术（北京）有限公司 | For the method and apparatus of point cloud data reparation |
| CN111161352A (en) * | 2019-12-30 | 2020-05-15 | 熵智科技(深圳)有限公司 | Object identification method and device based on triangular mesh simplified template |
| CN111444811A (en) * | 2020-03-23 | 2020-07-24 | 复旦大学 | Method for detecting three-dimensional point cloud target |
| CN112700537A (en) * | 2020-12-31 | 2021-04-23 | 广东美的白色家电技术创新中心有限公司 | Tire point cloud construction method, tire point cloud assembly method, tire point cloud control device, and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101887597A (en) * | 2010-07-06 | 2010-11-17 | 中国科学院深圳先进技术研究院 | Construction three-dimensional model building method and system |
| CN201739718U (en) * | 2010-07-27 | 2011-02-09 | 上海航天汽车机电股份有限公司太阳能系统工程分公司 | Portable and collapsible rack |
| US20110157176A1 (en) * | 2009-12-29 | 2011-06-30 | Hong Fu Jin Precision Industry (Shenzhen) Co., Ltd. | System and method for constructing triangular mesh surface of point cloud |
| CN103065352A (en) * | 2012-12-20 | 2013-04-24 | 北京农业信息技术研究中心 | Plant three-dimensional reconstruction method based on image and scanning data |
-
2013
- 2013-04-28 CN CN201310154400.3A patent/CN103236043B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110157176A1 (en) * | 2009-12-29 | 2011-06-30 | Hong Fu Jin Precision Industry (Shenzhen) Co., Ltd. | System and method for constructing triangular mesh surface of point cloud |
| CN101887597A (en) * | 2010-07-06 | 2010-11-17 | 中国科学院深圳先进技术研究院 | Construction three-dimensional model building method and system |
| CN201739718U (en) * | 2010-07-27 | 2011-02-09 | 上海航天汽车机电股份有限公司太阳能系统工程分公司 | Portable and collapsible rack |
| CN103065352A (en) * | 2012-12-20 | 2013-04-24 | 北京农业信息技术研究中心 | Plant three-dimensional reconstruction method based on image and scanning data |
Non-Patent Citations (1)
| Title |
|---|
| 张冬梅等: "《保特征的加权最小二乘三角网格光顺算法》", 《计算机辅助设计与图形学学报》, vol. 22, no. 9, 30 September 2010 (2010-09-30) * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107784138A (en) * | 2016-08-26 | 2018-03-09 | 上海宝冶集团有限公司 | Point cloud gravity deformation modification method based on structure mechanics analysis |
| CN107784138B (en) * | 2016-08-26 | 2021-03-26 | 上海宝冶集团有限公司 | Point cloud gravity deformation correction method based on structural mechanics analysis |
| CN106845416A (en) * | 2017-01-20 | 2017-06-13 | 百度在线网络技术（北京）有限公司 | Obstacle recognition method and device, computer equipment and computer-readable recording medium |
| CN107369211A (en) * | 2017-07-13 | 2017-11-21 | 云南数云信息科技有限公司 | Ancient building three-dimensional point cloud acquisition system and model review one's lessons by oneself correction method |
| CN107343148A (en) * | 2017-07-31 | 2017-11-10 | 广东欧珀移动通信有限公司 | Image completion method, apparatus and terminal |
| CN107343148B (en) * | 2017-07-31 | 2019-06-21 | Oppo广东移动通信有限公司 | Image completion method, apparatus and terminal |
| CN108198145A (en) * | 2017-12-29 | 2018-06-22 | 百度在线网络技术（北京）有限公司 | For the method and apparatus of point cloud data reparation |
| CN111161352A (en) * | 2019-12-30 | 2020-05-15 | 熵智科技(深圳)有限公司 | Object identification method and device based on triangular mesh simplified template |
| CN111161352B (en) * | 2019-12-30 | 2023-11-03 | 熵智科技(深圳)有限公司 | Object identification method and device based on triangular mesh simplified template |
| CN111444811A (en) * | 2020-03-23 | 2020-07-24 | 复旦大学 | Method for detecting three-dimensional point cloud target |
| CN111444811B (en) * | 2020-03-23 | 2023-04-28 | 复旦大学 | Three-dimensional point cloud target detection method |
| CN112700537A (en) * | 2020-12-31 | 2021-04-23 | 广东美的白色家电技术创新中心有限公司 | Tire point cloud construction method, tire point cloud assembly method, tire point cloud control device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103236043B (en) | 2015-10-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103236043B (en) | A kind of plant organ point cloud restoration method | |
| CN110516388B (en) | Harmonic mapping-based curved surface discrete point cloud model circular cutter path generation method | |
| CN103985155B (en) | Scattered point cloud Delaunay triangulation curved surface reconstruction method based on mapping method | |
| CN103942837B (en) | The direct building method of blade point cloud model cross section curve based on Successive linear programming | |
| CN107301648B (en) | Redundant point cloud removing method based on overlapping area boundary angle | |
| CN103258345A (en) | Method for extracting parameters of tree branches based on ground laser radar three-dimensional scanning | |
| CN106874580A (en) | A kind of bend pipe model reconstruction method based on cloud data | |
| CN108776993A (en) | The modeling method and buried cable work well modeling method of three-dimensional point cloud with hole | |
| AU2012350138A1 (en) | Method and system for characterising plant phenotype | |
| CN105761312A (en) | Micro-terrain surface reconstruction method | |
| CN105066915A (en) | Mold curved surface machining error and surface roughness on-machine detection device and detection method | |
| CN107526875A (en) | A kind of aerial blade type face mismachining tolerance method for visualizing | |
| CN106091923A (en) | The central point rapid assay methods of industrial bolt circular hole based on three-dimensional laser scanning technique | |
| CN107622530B (en) | Efficient and robust triangulation network cutting method | |
| CN103617336B (en) | A kind of method for drafting of aircraft noise isogram | |
| CN102853763A (en) | Method for measuring volumes of historical relics with irregular surfaces | |
| CN112233249A (en) | B spline surface fitting method and device based on dense point cloud | |
| CN104422396B (en) | Assembling product gap three dimensional analysis system and method | |
| CN113168729B (en) | 3D shape matching method and device based on local reference coordinate system | |
| CN103810271A (en) | Three-dimensional point cloud object shape feature matching method based on path following | |
| CN101783016A (en) | Crown appearance extract method based on shape analysis | |
| Wu et al. | Plant 3D reconstruction based on LiDAR and multi-view sequence images | |
| CN113763529B (en) | Substation modeling method based on three-dimensional scanning | |
| CN103824323B (en) | A kind of three-dimensional rebuilding method based on single width two dimensional image | |
| CN101739718A (en) | Parameter template-based corn leaf virtual simulation modeling method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |