CN110866948B - New method for estimating volume morphological parameters of grains by utilizing three-dimensional scanning point cloud - Google Patents
New method for estimating volume morphological parameters of grains by utilizing three-dimensional scanning point cloud Download PDFInfo
- Publication number
- CN110866948B CN110866948B CN201911170635.5A CN201911170635A CN110866948B CN 110866948 B CN110866948 B CN 110866948B CN 201911170635 A CN201911170635 A CN 201911170635A CN 110866948 B CN110866948 B CN 110866948B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- grain
- point
- grains
- background plate
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000000877 morphologic effect Effects 0.000 title claims abstract description 13
- 235000013339 cereals Nutrition 0.000 claims abstract description 113
- 241000209094 Oryza Species 0.000 claims abstract description 29
- 235000007164 Oryza sativa Nutrition 0.000 claims abstract description 29
- 235000009566 rice Nutrition 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 10
- 101000624947 Homo sapiens Nesprin-1 Proteins 0.000 claims description 6
- 102100023306 Nesprin-1 Human genes 0.000 claims description 6
- 101150008740 cpg-1 gene Proteins 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 4
- 241001061225 Arcos Species 0.000 claims description 3
- 238000003780 insertion Methods 0.000 claims description 3
- 230000037431 insertion Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 239000004464 cereal grain Substances 0.000 claims 1
- 238000005259 measurement Methods 0.000 abstract description 10
- 238000004364 calculation method Methods 0.000 abstract description 5
- 230000009466 transformation Effects 0.000 abstract description 5
- 238000004458 analytical method Methods 0.000 abstract description 2
- 238000000691 measurement method Methods 0.000 abstract description 2
- 238000004445 quantitative analysis Methods 0.000 abstract description 2
- 239000007787 solid Substances 0.000 abstract description 2
- 230000004907 flux Effects 0.000 description 4
- 108090000623 proteins and genes Proteins 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 108700028369 Alleles Proteins 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012165 high-throughput sequencing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- 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)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geometry (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a novel method for obtaining volume morphological parameters of grain point cloud measurement by using a three-dimensional scanner. The invention relates to the technical fields of measurement methods, laser point cloud processing, image geometric transformation, numerical calculation and the like. The method comprises the steps of point cloud image acquisition, laser point cloud processing, image geometric transformation, numerical calculation of volume and the like. According to the invention, the laser point clouds of the rice grains are obtained in batches in a three-dimensional scanning mode, the single laser point clouds of the rice grains are extracted based on image geometric transformation and point cloud clustering, and the volumes of the rice grains are extracted through numerical analysis of the laser point clouds of the rice grains. The method can be used for quantitative analysis of grain morphology of different varieties, classification of blighted grains and solid grains, quantitative measurement of grain fullness and estimation of thousand grain weight of grains.
Description
Technical Field
The invention relates to a novel method for measuring volume morphological parameters of grains, and relates to the technical fields of measurement methods, laser point cloud processing, image geometric transformation, numerical calculation and the like.
Background
The grain shape of rice is one of the important factors constituting the yield of rice, and also affects the appearance quality of rice. With the improvement of the living standard of people and the opening of the rice market, the rice is required to be higher and higher, so that the rice has proper taste and attractive appearance. Meanwhile, the morphological characters of the grains are controlled by genes, researchers locate and clone genes for controlling the length and the yield of the grains in the rice by means of modern high-throughput sequencing technology, and the expression products can negatively regulate the size and the weight of the grains, for example, the large-grain alleles of the genes can be introduced into a main cultivated variety 'Huanghua' to improve the yield by more than 10 percent.
Therefore, the grain morphology is an important phenotypic index of grains and is an important index for rice variety breeding and variety evaluation. Because the grain shape is small and irregular, the existing method for measuring the grain shape index by using the vernier caliper has the defects of high operation difficulty, low flux and high precision, is greatly influenced by human factors, and cannot meet the requirements of modern rice character research. The existing method for measuring the grain morphological indexes by using image processing effectively solves the problem of measuring the length and width of grains, but has the defect that the volume of grains cannot be measured.
The invention discloses a method for obtaining grain point cloud measurement grain volume by using a three-dimensional scanner. According to the invention, the laser point clouds of the rice grains are obtained in batches in a three-dimensional scanning mode, the laser point clouds of the single rice grains are extracted based on image geometric transformation, and the volumes of the rice grains are extracted through numerical analysis of the laser point clouds of the rice grains. The method for estimating the grain volume has the advantages of high flux and good precision, and can be used for comparing and analyzing the grain characters.
Disclosure of Invention
The invention aims to provide a novel method for obtaining grain point cloud measurement grain volume morphological parameters by using a three-dimensional scanner, which improves measurement flux and obtains volume parameters with higher accuracy.
1. A novel method for measuring volumetric morphological parameters of grain, characterized in that the method comprises the steps of:
s1, acquiring an image (as shown in FIG. 2), and scanning by using a Blue Light three-dimensional scanner 530P/A (Blue Light 3D Scanning System 530P/A) to obtain laser point cloud data BGCP (x, y, z) of a background plate, wherein x, y, z are the space coordinates of point clouds; and placing the rice grains on the background plate in batches to obtain laser point cloud data CPG1 (x, y, z) of the rice grains and the background plate, wherein x, y and z are the space coordinates of the point cloud, rotating the background plate for placing the rice grains in batches by 180 degrees, and obtaining laser point cloud data CPG2 (x, y, z) of the rice grains and the background plate again, wherein x, y and z are the space coordinates of the point cloud.
S2, using matlab programming point cloud processing, calculating grain volume, wherein the processing procedure is as follows:
s2-1, taking the center BGCPc (x 0, y0, z 0) of the background plate BGCP (x, y, z), and translating the background plate: bgcp=bgcp-BGCPc,
let the center point BGCPc be the origin, fit the background plate point cloud BGCP (x, y, z) using a spatial plane function, calculate the background plate plane a×bgcpx+b×bgcpy+c×bgcpz+d=0, the normal vector of the background plate plane is n= (a, b, c), calculate the included angle θ=arcos (n 1/n 1) where n 1= (0, 1) is the normal vector of the xoy plane.
S2-2, grain point cloud splicing (the result is shown in figure 4), and based on EinScan-S series_v2.7.0.8, splicing grain point cloud CPG1 (x, y, z) and grain point cloud CPG2 (x, y, z) by using self-contained software to eliminate holes of single scanning, wherein the spliced point cloud is marked as CPG.
S2-3, translating the point cloud CPG, still recorded as CPG, and translating the equation: CPG = CPG-BGCPc;
s2-4, rotating the point cloud CPG around the X axis based on the included angle theta between the background plate plane and the xoy plane, so that the basic plane of the point cloud CPG is positioned on the xoy plane, and the coordinate rotation function is that
，
The rotated point cloud coordinates are CPGH (CPGHx, CPGHy, CPGHz).
S2-5, removing points with the vertical coordinates of the point cloud CPGH being zero (the result is shown in figure 5).
S2-6, clustering point cloud CPGH (the result is shown in figure 6), clustering point cloud CPGH by using Euclidean distance, wherein the clustering process is as follows:
(a) GLLmax is the maximum diameter of the grain, JGLmin is the minimum distance of Gu Lijian;
(b) Selecting a point Pi in the point cloud CPGH, recording a point set museri= { Pi }, and deleting the Pi from the CPGH;
(c) Calculating Euclidean distance from Pi to CPGH midpoint, and sorting from small to large;
(d) Selecting a point set PL with the Euclidean distance from the CPGH to the Pi being less than 2 GLLmax;
(e) Selecting a set of points from PL that are less than JGLmin apart from the set of points museri, merging to museri, and deleting these points from CPGH and PL;
(f) Repeating the step (d), wherein no point with the distance smaller than JGLmin from the point set museri exists in the PL is guided to obtain a point class, namely, the point cloud museri of one grain is recorded as grain GLi, the number of the point cloud is recorded as Ni, and the transverse and longitudinal sitting marks are (GLix, GLiy);
(g) Repeating (a) - (e) until CPGH is an empty set.
S2-7, meterCalculating the thickness of the grains, wherein the thickness of the grains GLi is as follows:。
s2-8, calculating the volume of the grain, and calculating the volume of the grain GLiy based on triangulation (figure 7), wherein the steps are as follows:
a) Constructing a super triangle, including all scattered points mussterixy, and putting the super triangle into a triangle set GTr;
b) Sequentially inserting scattered points in the point set mussterixy, finding out triangles with the inserted points in the triangle set, deleting common edges affecting the triangles, connecting the inserted points with all vertexes affecting the triangles, and completing the insertion of one point in the triangle set;
c) And optimizing the locally newly formed triangle according to an optimization criterion. Putting the formed triangle into a triangle set GTr;
d) Circularly executing the step 2 until all scattered points are inserted;
e) Calculating the volume of the grainWherein GTr is a triangle set of projection SGLTYI of grain GLi on an xoy plane, P1 (x 1, y 1), P2 (x 2, y 2), P3 (x 3, y 3) are dot tops in the triangle set GTr, d1, d2, d3 are lengths of sides P2P3, P1P3, P1P2 respectively,h1, H2, H3 are Z-axis coordinates of points in the grain GLi point cloud corresponding to points P1, P2, P3.
Drawings
FIG. 1 is a flow chart of the technical scheme adopted by the invention.
Fig. 2 shows a point cloud acquisition apparatus used in the present invention.
FIG. 3 is an image of grain processed in accordance with the present invention.
FIG. 4 is a spliced grain point cloud of the present invention.
Fig. 5 the invention removes the point cloud of the background plate.
FIG. 6 is a point cloud of cereal kernels after separation according to the present invention.
FIG. 7 grain splitting of the present invention.
Fig. 8 shows the calculation result of the present invention.
Detailed Description
The invention aims to provide a novel method for obtaining grain volume morphological parameters of grain point cloud measurement by using a three-dimensional scanner, which improves measurement flux and obtains grain volume with higher accuracy.
A novel method for measuring volumetric morphological parameters of grain, characterized in that the method comprises the steps of:
s1, acquiring an image (as shown in FIG. 2), and scanning by using a Blue Light three-dimensional scanner 530P/A (Blue Light 3D Scanning System 530P/A) to obtain laser point cloud data BGCP (x, y, z) of a background plate, wherein x, y, z are the space coordinates of point clouds; the method comprises the steps of placing rice grains on a background plate in batches, obtaining laser point cloud data CPG1 (x, y, z) of the rice grains and the background plate, wherein x, y and z are space coordinates of point clouds, rotating the background plate for placing the rice grains in batches by 180 degrees, obtaining laser point cloud data CPG2 (x, y, z) of the rice grains and the background plate again, wherein x, y and z are space coordinates of the point clouds), and ensuring that the distance between the grains is larger than 2mm for ensuring the effect of post-treatment.
S2, using matlab programming point cloud processing, calculating grain volume, wherein the processing procedure is as follows:
s2-1, taking the center BGCPc (x 0, y0, z 0) of the background plate BGCP (x, y, z), and translating the background plate: bgcp=bgcp-BGCPc,
let the center point BGCPc be the origin, fit the background plate point cloud BGCP (x, y, z) using a spatial plane function, calculate the background plate plane a×bgcpx+b×bgcpy+c×bgcpz+d=0, the normal vector of the background plate plane is n= (a, b, c), calculate the included angle θ=arcos (n 1/n 1) where n 1= (0, 1) is the normal vector of the xoy plane.
S2-2, grain point cloud splicing (the result is shown in figure 4), and based on EinScan-S series_v2.7.0.8, splicing grain point cloud CPG1 (x, y, z) and grain point cloud CPG2 (x, y, z) by using self-contained software to eliminate holes of single scanning, wherein the spliced point cloud is marked as CPG.
S2-3, translating the point cloud CPG, still recorded as CPG, and translating the equation: CPG = CPG-BGCPc.
S2-4, rotating the point cloud CPG around the X axis based on the included angle theta between the background plate plane and the xoy plane, so that the basic plane of the point cloud CPG is positioned on the xoy plane, and the coordinate rotation function is that
，
The rotated point cloud coordinates are CPGH (CPGHx, CPGHy, CPGHz).
S2-5, removing points with the vertical coordinates of the point cloud CPGH being zero (the result is shown in figure 5).
S2-6, clustering point cloud CPGH (the result is shown in figure 6), clustering point cloud CPGH by using Euclidean distance, wherein the clustering process is as follows:
(a) GLLmax is the maximum diameter of the grain, JGLmin is the minimum distance of Gu Lijian;
(b) Selecting a point Pi in the point cloud CPGH, recording a point set museri= { Pi }, and deleting the Pi from the CPGH;
(c) Calculating Euclidean distance from Pi to CPGH midpoint, and sorting from small to large;
(d) Selecting a point set PL with the Euclidean distance from the CPGH to the Pi being less than 2 GLLmax;
(e) Selecting a set of points from PL that are less than JGLmin apart from the set of points museri, merging to museri, and deleting these points from CPGH and PL;
(f) Repeating the step (d), wherein no point with the distance smaller than JGLmin from the point set museri exists in the PL is guided to obtain a point class, namely, the point cloud museri of one grain is recorded as grain GLi, the number of the point cloud is recorded as Ni, and the transverse and longitudinal sitting marks are (GLix, GLiy);
(g) Repeating (a) - (e) until CPGH is an empty set.
S2-7, calculating the thickness of grains, wherein the thickness of the grains GLi is as follows:。
s2-8, calculating the volume of the grain, and calculating the volume of the grain GLiy based on triangulation (figure 7), wherein the steps are as follows:
a) Constructing a super triangle, including all scattered points mussterixy, and putting the super triangle into a triangle set GTr;
b) Sequentially inserting scattered points in the point set mussterixy, finding out triangles with the inserted points in the triangle set, deleting common edges affecting the triangles, connecting the inserted points with all vertexes affecting the triangles, and completing the insertion of one point in the triangle set;
c) And optimizing the locally newly formed triangle according to an optimization criterion. Putting the formed triangle into a triangle set GTr;
d) Circularly executing the step 2 until all scattered points are inserted;
e) Calculating the volume of the grainWherein GTr is a triangle set of projection SGLTYI of grain GLi on an xoy plane, P1 (x 1, y 1), P2 (x 2, y 2), P3 (x 3, y 3) are dot tops in the triangle set GTr, d1, d2, d3 are lengths of sides P2P3, P1P3, P1P2 respectively,h1, H2, H3 are Z-axis coordinates of points in the grain GLi point cloud corresponding to points P1, P2, P3.
Based on the novel method for obtaining the grain volume of the grain point cloud measurement by using the three-dimensional scanner, the grain volume is estimated, the effect is obvious, and the precision is high. Taking the grain shown in fig. 3 as an example, after the grain point cloud is spliced, the point cloud shown in fig. 4 is obtained, after the background point cloud is processed and removed, the point cloud shown in fig. 5 is obtained, after the grain is separated, the point cloud shown in fig. 6 is obtained, the data (shown in fig. 8) of the volume of the grain is obtained through three divisions of the point cloud and calculation of the convex hull (shown in fig. 7) of the point cloud, and the malted grains (middle columns, numbers 7, 8, 9 and 10) and the full grains can be obviously distinguished from the volume data of the grain. The invention can thus be used for the measurement of morphological volume of grains. The method can be used for quantitative analysis of grain morphology of different varieties, classification of blighted grains and solid grains, quantitative measurement of grain fullness and estimation of thousand grain weight of grains.
Claims (1)
1. A novel method for rapidly estimating volumetric morphological parameters of cereal grains, characterized in that it comprises the steps of:
s1, acquiring an image, namely acquiring laser point cloud data BGCP (x, y, z) of a background plate by using a blue light three-dimensional scanner 530P/A for scanning, wherein x, y and z are the space coordinates of point clouds; placing rice grains on a background plate in batches to obtain laser point cloud data CPG1 (x, y, z) of the rice grains and the background plate, wherein x, y and z are space coordinates of point clouds, rotating the background plate for placing the rice grains in batches by 180 degrees, and obtaining laser point cloud data CPG2 (x, y, z) of the rice grains and the background plate again, wherein x, y and z are space coordinates of the point clouds;
s2, using matlab programming to perform point cloud processing, calculating volume morphological parameters of grains, wherein the processing process is as follows:
s2-1, taking the center BGCPc (x 0, y0, z 0) of the background plate BGCP (x, y, z), and translating the background plate:
BGCP＝BGCP-BGCPc，
let the center point BGCPc be the origin, fit the background plate point cloud BGCP (x, y, z) using a spatial plane function, calculate the background plate plane a×bgcpx+b×bgcpy+c×bgcpz+d=0, the normal vector of the background plate plane is n= (a, b, c), calculate the included angle θ=arcos (n 1/n 1) where n 1= (0, 1) is the normal vector of the xoy plane.
S2-2, splicing grain point clouds, namely splicing grain point cloud CPG1 (x, y, z) and grain point cloud CPG2 (x, y, z) based on EinScan-S services_v2.7.0.8 self-contained software so as to eliminate holes of single scanning, wherein the spliced point clouds are marked as CPG.
S2-3, translating the point cloud CPG, still recorded as CPG, and translating the equation: CPG = CPG-BGCPc;
s2-4, rotating the point cloud CPG around the X axis based on the included angle theta between the background plate plane and the xoy plane, so that the basic plane of the point cloud CPG is positioned on the xoy plane, and the coordinate rotation function is that
，
The rotated point cloud coordinates are CPGH (CPGHx, CPGHy, CPGHz);
s2-5, removing points with zero vertical coordinates of the point cloud CPGH, namely removing the point cloud of the background plate;
s2-6, clustering point cloud CPGH, namely using Euclidean distance to cluster the point cloud CPGH, wherein the clustering process is as follows:
(a) GLLmax is the maximum diameter of the grain, JGLmin is the minimum distance of Gu Lijian;
(b) Selecting a point Pi in the point cloud CPGH, recording a point set museri= { Pi }, and deleting the Pi from the CPGH;
(c) Calculating Euclidean distance from Pi to CPGH midpoint, and sorting from small to large;
(d) Selecting a point set PL with the Euclidean distance from the CPGH to the Pi being less than 2 GLLmax;
(e) A set of points from PL that is less than JGLmin apart from the set of points museri is selected, merged into museri, and these points are deleted from CPGH and PL.
(f) Repeating the step (d) until no point with the distance from the point set museri smaller than JGLmin exists in the PL, so as to obtain a point class, namely a point cloud museri of one grain, which is marked as grain GLi, the number of the point cloud is marked as Ni, and the horizontal and vertical sitting marks are marked as (GLix, GLiy);
(g) Repeating (a) - (e) until CPGH is an empty set;
s2-7, calculating grain thickness, wherein the grain thickness represented by the dot set museri is as follows:
s2-8, calculating the volume of the grain, and calculating the volume of the grain GLiy based on triangulation, wherein the steps are as follows:
a) A super triangle is constructed, containing all the scattered points mussterixy, put into the triangle set GTr.
b) The scattered points in the point set muserixy are sequentially inserted, triangles with the inserted points in the circumscribed circles are found out in the triangle set, the public sides affecting the triangles are deleted, the inserted points are connected with all vertexes affecting the triangles, and the insertion of one point in the triangle set is completed.
c) And optimizing the locally newly formed triangle according to an optimization criterion. The triangle formed is put into a triangle set GTr.
d) And (3) circularly executing the step (2) until all the scattered points are inserted.
e) Calculating the volume of the grain
Wherein GTr is a triangle set of projection SGLTYI of grains GLi on an xoy plane, P1 (x 1, y 1), P2 (x 2, y 2) and P3 (x 3, y 3) are dot tops in the triangle set GTr, d1, d2 and d3 are lengths of sides P2P3, P1P3 and P1P2 respectively, p= (d1+d2+d3)/2, and H1, H2 and H3 are Z-axis coordinates of points in the grain GLi point cloud corresponding to the points P1, P2 and P3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911170635.5A CN110866948B (en) | 2019-11-26 | 2019-11-26 | New method for estimating volume morphological parameters of grains by utilizing three-dimensional scanning point cloud |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911170635.5A CN110866948B (en) | 2019-11-26 | 2019-11-26 | New method for estimating volume morphological parameters of grains by utilizing three-dimensional scanning point cloud |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110866948A CN110866948A (en) | 2020-03-06 |
| CN110866948B true CN110866948B (en) | 2023-11-24 |
Family
ID=69656319
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911170635.5A Active CN110866948B (en) | 2019-11-26 | 2019-11-26 | New method for estimating volume morphological parameters of grains by utilizing three-dimensional scanning point cloud |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110866948B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106204547A (en) * | 2016-06-29 | 2016-12-07 | 山东科技大学 | The method automatically extracting shaft-like atural object locus from Vehicle-borne Laser Scanning point cloud |
| WO2017187249A1 (en) * | 2016-04-26 | 2017-11-02 | Agco Corporation | A combine harvester having a grain bin |
-
2019
- 2019-11-26 CN CN201911170635.5A patent/CN110866948B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017187249A1 (en) * | 2016-04-26 | 2017-11-02 | Agco Corporation | A combine harvester having a grain bin |
| CN106204547A (en) * | 2016-06-29 | 2016-12-07 | 山东科技大学 | The method automatically extracting shaft-like atural object locus from Vehicle-borne Laser Scanning point cloud |
Non-Patent Citations (1)
| Title |
|---|
| 基于点云的谷粒高通量表型信息自动提取技术;黄霞;郑顺义;桂力;赵丽科;马浩;;农业机械学报(04);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110866948A (en) | 2020-03-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5703396B2 (en) | Tolerance evaluation with reduced measurement points | |
| CN107672180B (en) | A kind of 3D printing accuracy checking method based on reverse Engineering Technology | |
| CN108053433B (en) | Multi-mode carotid artery MRI registration method based on physical alignment and contour matching | |
| CN109118574A (en) | A kind of fast reverse modeling method extracted based on three-dimensional feature | |
| CA2858166C (en) | Method and system for characterising plant phenotype | |
| CN105783786B (en) | Part chamfering measuring method and device based on structured light vision | |
| CN105654483B (en) | The full-automatic method for registering of three-dimensional point cloud | |
| CN108303037A (en) | A kind of detection method and device of the workpiece surface shape difference based on cloud analysis | |
| CN116402866A (en) | Point cloud-based part digital twin geometric modeling and error assessment method and system | |
| CN109532021A (en) | The molten product layer-by-layer detection method of defect of 3D printing based on the actinic abnormal point of structure | |
| CN114241160B (en) | Single-view-angle blade three-dimensional reconstruction method based on deep learning | |
| CN110926341A (en) | Novel method for measuring grain length, width and thickness morphological parameters by using three-dimensional scanning point cloud | |
| CN117474873B (en) | Surface treatment system before brazing of high-chromium wear-resistant castings | |
| CN110942464A (en) | PET image segmentation method fusing 2-dimensional and 3-dimensional models | |
| CN116642904A (en) | Aircraft skin defect detection and measurement method based on three-dimensional point cloud | |
| CN110866948B (en) | New method for estimating volume morphological parameters of grains by utilizing three-dimensional scanning point cloud | |
| CN112927287B (en) | Phenotype data analysis method of target object, storage medium and terminal | |
| CN115797414A (en) | Complex curved surface measurement point cloud data registration method considering measuring head radius | |
| CN110866947B (en) | Novel method for measuring grain surface area and projection parameters | |
| CN106228417A (en) | A kind of bra fit detection method | |
| CN105279320B (en) | A kind of method for generating FDTD grids | |
| Zeraatkar et al. | High‐Precision Laser Scanning System for Three‐Dimensional Modeling of Saffron Flower | |
| CN110084887B (en) | Three-dimensional reconstruction method for space non-cooperative target relative navigation model | |
| CN118552734B (en) | Tooth segmentation recognition method for denture restoration | |
| CN117315002B (en) | Method, system and device for measuring three-dimensional phenotype of object to be measured |
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 |