CN108876903B - Corn variety distinguishing method and system based on corn tassel three-dimensional phenotype - Google Patents

Corn variety distinguishing method and system based on corn tassel three-dimensional phenotype Download PDF

Info

Publication number
CN108876903B
CN108876903B CN201810508702.9A CN201810508702A CN108876903B CN 108876903 B CN108876903 B CN 108876903B CN 201810508702 A CN201810508702 A CN 201810508702A CN 108876903 B CN108876903 B CN 108876903B
Authority
CN
China
Prior art keywords
tassel
dimensional
target
corn
dimensional model
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201810508702.9A
Other languages
Chinese (zh)
Other versions
CN108876903A (en
Inventor
杨贵军
杨浩
杨小冬
李振海
徐新刚
赵晓庆
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Research Center for Information Technology in Agriculture
Original Assignee
Beijing Research Center for Information Technology in Agriculture
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Research Center for Information Technology in Agriculture filed Critical Beijing Research Center for Information Technology in Agriculture
Priority to CN201810508702.9A priority Critical patent/CN108876903B/en
Publication of CN108876903A publication Critical patent/CN108876903A/en
Application granted granted Critical
Publication of CN108876903B publication Critical patent/CN108876903B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00Three dimensional [3D] modelling, e.g. data description of 3D objects
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/60Analysis of geometric attributes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30181Earth observation
    • G06T2207/30188Vegetation; Agriculture

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Geometry (AREA)
  • Quality & Reliability (AREA)
  • Computer Graphics (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention provides a corn variety distinguishing method and system based on a corn tassel three-dimensional phenotype, wherein the method comprises the following steps: marking a plurality of characteristic points around the target corn tassel, and collecting images of the target corn tassel at a plurality of viewing angles; constructing a three-dimensional model of the target corn tassel according to the images under the multiple viewing angles; acquiring three-dimensional phenotypic parameters of the target maize tassel based on the three-dimensional model, wherein the three-dimensional phenotypic parameters comprise an outer envelope volume, a total branch vertical projection area, a plane aggregation degree, a space aggregation degree, a main shaft variation coefficient, a crown-to-height ratio, a head-to-stem ratio and a gravity center; and distinguishing the corn varieties of the target corn tassel according to the three-dimensional phenotype parameters. The method and the system scientifically define the three-dimensional phenotypic parameters of the maize tassel from a three-dimensional angle, accurately realize the differentiation of maize varieties by using the difference of the three-dimensional phenotypic parameters of different maize varieties, are favorable for accelerating the maize breeding process, and effectively improve the breeding efficiency and level.

Description

Corn variety distinguishing method and system based on corn tassel three-dimensional phenotype
Technical Field
The invention relates to the technical field of three-dimensional image processing, in particular to a corn variety distinguishing method and system based on a corn tassel three-dimensional phenotype.
Background
Maize tassel is the branched structure atop the pollen-producing plant. After the male florets develop and mature, the pollen falls onto the corn stigma of the corn female ear along with wind to finish pollination. The size and morphology of the tassel can affect the yield of pollen, which in turn affects the maintenance of inbred lines, progeny of crosses, and subsequent agricultural yield. Breeding hybrids with moderately large tassels is a trend in maize breeding in breeding practice.
At present, the conventional breeding means mainly extracts plant phenotype information by means of manual sampling measurement, and the process is time-consuming and labor-consuming and cannot ensure the precision of a measurement result. Although a method for acquiring plant phenotype information based on an image exists at present, the conventional corn tassel phenotype mainly adopts two-dimensional image expression, and includes a small amount of statistical information such as branch number, length and the like, and the corn tassel two-dimensional phenotype information of different corn varieties is probably the same, so that the corn varieties are difficult to accurately distinguish according to the corn tassel two-dimensional phenotype information in the prior art.
Disclosure of Invention
The invention provides a corn variety distinguishing method and system based on a three-dimensional corn tassel phenotype, aiming at solving the problem that in the prior art, corn varieties are distinguished only according to two-dimensional corn tassel phenotype information, and the two-dimensional corn tassel phenotype information of different corn varieties is possibly the same, so that the corn varieties are difficult to distinguish accurately.
In one aspect, the invention provides a corn variety distinguishing method based on a corn tassel three-dimensional phenotype, comprising the following steps:
s1, marking a plurality of characteristic points around the target corn tassel, and collecting images of the target corn tassel at a plurality of viewing angles;
s2, constructing a three-dimensional model of the target corn tassel according to the images under the multiple viewing angles;
s3, acquiring three-dimensional phenotype parameters of the target corn tassel based on the three-dimensional model, wherein the three-dimensional phenotype parameters comprise an outer envelope volume, a total area of branch vertical projection, a plane aggregation degree, a space aggregation degree, a main shaft change coefficient, a crown-to-stem ratio, a head-to-stem ratio and a gravity center;
and S4, distinguishing the corn varieties of the target corn tassel according to the three-dimensional phenotype parameters.
Preferably, the step S2 further includes:
acquiring all the feature points from the images under the multiple viewing angles, and calculating the position conversion relation of the same feature point under the multiple viewing angles;
mapping point clouds in the images under the multiple visual angles to a three-dimensional coordinate system by using an aerial triangulation method according to the position conversion relation and the angles of the multiple visual angles to obtain three-dimensional point clouds;
and constructing a three-dimensional model of the target corn tassel according to the three-dimensional point cloud by utilizing a Poisson surface reconstruction algorithm.
Preferably, the obtaining the outer envelope volume of the target corn tassel based on the three-dimensional model in step S3 further comprises:
dividing point clouds in the three-dimensional model into a plurality of layers from top to bottom according to a preset interval;
acquiring an envelope convex surface of each layer of point cloud, and calculating the surface area of each envelope convex surface;
and obtaining the outer envelope volume of the target corn tassel according to the surface area of each envelope convex surface and the preset interval.
Preferably, the obtaining of the total branched vertical projection area of the target corn tassel based on the three-dimensional model in step S3 further comprises:
projecting all point clouds in the three-dimensional model to a horizontal plane, and obtaining projection points corresponding to all the point clouds on the horizontal plane;
and obtaining an outer envelope convex hull formed by all the projection points, calculating the area of the outer envelope convex hull, and determining the area of the outer envelope convex hull as the total area of the branch vertical projection of the target corn tassel.
Preferably, the step S3 of obtaining the planar aggregation and the spatial aggregation of the target corn tassel based on the three-dimensional model further comprises:
acquiring the branch number of the target corn tassel based on the three-dimensional model;
and obtaining the plane aggregation of the target maize tassel according to the total area of the vertical projection of the branches and the number of the branches, and obtaining the space aggregation of the target maize tassel according to the outer envelope volume and the number of the branches.
Preferably, the step S3 of obtaining the principal axis variation coefficient of the target corn tassel based on the three-dimensional model further includes:
obtaining the height of a main shaft, the maximum diameter of the main shaft and the minimum diameter of the main shaft of the target corn tassel based on the three-dimensional model;
and calculating the difference value between the maximum diameter of the main shaft and the minimum diameter of the main shaft, and determining the main shaft change coefficient of the target corn tassel according to the difference value and the height of the main shaft.
Preferably, the step S3 of obtaining the crown-to-stem ratio and the head-to-stem ratio of the target corn tassel based on the three-dimensional model further comprises:
selecting point clouds at the bottom of the ear stems from the three-dimensional model to fit into a circle, and taking the circle center of the circle as a reference point;
calculating the distances between all point clouds in the three-dimensional model and the reference point on a horizontal plane, determining the maximum value of the distances as the maximum ear crown radius, and obtaining the maximum ear crown diameter according to the maximum ear crown radius;
and obtaining the crown height ratio of the target corn tassel according to the maximum ear crown diameter and the main shaft length, and obtaining the head-stem ratio of the target corn tassel according to the maximum ear crown diameter and the main shaft maximum diameter.
Preferably, the step S3 of obtaining the center of gravity of the target corn tassel based on the three-dimensional model further comprises:
taking the maximum ear crown diameter as a boundary in the three-dimensional model, and acquiring a first distance from the boundary to the top of the tassel and a second distance from the boundary to the lowest end branch of the tassel;
and obtaining the gravity center of the target corn tassel according to the first distance and the second distance.
In one aspect, the invention provides a corn variety differentiation system based on a three-dimensional phenotype of a corn tassel, comprising:
the image acquisition module is used for marking a plurality of characteristic points on the periphery of the target corn tassel and acquiring images of the target corn tassel at a plurality of visual angles;
the model building module is used for building a three-dimensional model of the target corn tassel according to the images under the multiple viewing angles;
a parameter obtaining module, configured to obtain three-dimensional phenotype parameters of the target maize tassel based on the three-dimensional model, where the three-dimensional phenotype parameters include an outer envelope volume, a total area of branch vertical projections, a planar aggregation degree, a spatial aggregation degree, a main axis variation coefficient, a crown-to-stem ratio, a head-to-stem ratio, and a center of gravity;
and the variety distinguishing module is used for distinguishing the corn varieties of the target corn tassel according to the three-dimensional phenotype parameters.
In one aspect, the invention provides a corn variety distinguishing device based on a three-dimensional corn tassel phenotype, comprising:
at least one processor; and
at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor, the processor being capable of performing any of the methods described above when invoked by the processor.
The invention provides a corn variety distinguishing method and system based on a three-dimensional phenotype of a corn tassel. The method and the system scientifically define the three-dimensional phenotypic parameters of the maize tassel from a three-dimensional angle, accurately distinguish maize varieties by using the difference of the three-dimensional phenotypic parameters of different maize varieties, can be used for maize breeding with low cost, high efficiency and accuracy, quickly acquire the three-dimensional phenotypic parameters of the maize tassel for breeding experts, perform gene association analysis based on the three-dimensional phenotypic parameters, locate the genes with the optimal maize tassel three-dimensional structure, are favorable for accelerating the maize breeding process and effectively improve the breeding efficiency and level.
Drawings
FIG. 1 is a schematic overall flow chart of a corn variety discrimination method based on a three-dimensional corn tassel phenotype according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a three-dimensional phenotypic parameter of a maize tassel according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of the overall structure of a corn variety differentiating system based on the three-dimensional phenotype of the tassel of corn according to an embodiment of the present invention;
FIG. 4 is a schematic structural framework diagram of an apparatus of a corn variety distinguishing method based on a three-dimensional phenotype of a corn tassel according to an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Fig. 1 is a schematic overall flow chart of a method for distinguishing corn varieties based on a three-dimensional phenotype of a corn tassel according to an embodiment of the present invention, and as shown in fig. 1, the present invention provides a method for distinguishing corn varieties based on a three-dimensional phenotype of a corn tassel, including:
s1, marking a plurality of characteristic points around the target corn tassel, and collecting images of the target corn tassel at a plurality of viewing angles;
s2, constructing a three-dimensional model of the target corn tassel according to the images under the multiple viewing angles;
s3, acquiring three-dimensional phenotype parameters of the target corn tassel based on the three-dimensional model, wherein the three-dimensional phenotype parameters comprise an outer envelope volume, a total area of branch vertical projection, a plane aggregation degree, a space aggregation degree, a main shaft change coefficient, a crown-to-stem ratio, a head-to-stem ratio and a gravity center;
and S4, distinguishing the corn varieties of the target corn tassel according to the three-dimensional phenotype parameters.
In particular, a large number of field observations and tests show that the differences of the three-dimensional characteristics of the tassels of different varieties of corn are obvious, so that when the corn varieties need to be distinguished, the corn varieties can be distinguished through the differences of the three-dimensional characteristics of the tassels of different varieties of corn, and the method is specifically realized as follows:
sampling the corn tassels from the field to obtain target corn tassels; a plurality of feature points are marked on the periphery of the target corn tassel, and in practical application, the target corn tassel can be inserted into a pre-manufactured reference plate, and the feature points are marked on the reference plate in advance. In other embodiments, the feature points may also be labeled in other manners, which are not specifically limited herein.
On the basis of the technical scheme, images of the target corn tassel at multiple viewing angles are collected, in this embodiment, in order to facilitate subsequent construction of a three-dimensional model of the target corn tassel, 2 images with the overlapping degree larger than 60% are shot along the side surface and the top surface of the target corn tassel crown layer in each horizontal direction to form binocular stereoscopic vision measurement, then the camera is sequentially rotated around the main axis direction of the target corn tassel, the image shooting is repeatedly executed at 15 degrees every angle, the shooting is totally performed 24 times after the rotation is completed for one week, and finally 48 multi-viewing-angle images are obtained for each target corn tassel. In this embodiment, a camera used when images of a target corn tassel at multiple viewing angles are collected is a nikon D5600 digital camera, the effective pixel number 2416 ten thousand, and in other embodiments, other common consumption digital cameras may also be used, which is not specifically limited herein. In addition, in this embodiment, when adopting the camera to carry out image shooting, can place target maize tassel indoor to try hard to ensure indoor light even.
Further, after the images of the target corn tassel at the multiple viewing angles are obtained, due to the fact that the images at the multiple viewing angles comprise the pre-marked feature points, point clouds in the images at the multiple viewing angles can be mapped into a three-dimensional coordinate system by performing stereo measurement analysis on the feature points, a high-density three-dimensional point cloud is obtained, and then a three-dimensional model of the target corn tassel is constructed by the high-density three-dimensional point cloud.
Further, based on the obtained three-dimensional model of the target corn tassel, three-dimensional phenotype parameters of the target corn tassel are obtained, wherein the three-dimensional phenotype parameters comprise an outer envelope volume, a total area of branch vertical projection, a plane aggregation degree, a space aggregation degree, a main shaft variation coefficient, a crown-to-stem ratio, a head-to-stem ratio, a gravity center and the like. Wherein the outer envelope volume is the volume of a three-dimensional space formed by connecting all point clouds in the three-dimensional model of the target corn tassel; the total vertical projection area of the branches is the total area of a convex hull formed by projecting all point clouds in the three-dimensional model of the target corn tassel to the horizontal plane; the plane aggregation degree is the ratio of the total area of the vertical projection of the branches of the target maize tassel to the number of the branches; the spatial aggregation degree is the ratio of the outer envelope volume of the target maize tassel to the number of branches; the main shaft variation coefficient is the ratio of the difference between the maximum diameter and the minimum diameter of the main shaft of the target corn tassel to the height of the main shaft; the crown height ratio is the ratio of the maximum crown diameter of the target corn tassel to the height of the main shaft; the head-stem ratio is the ratio of the maximum crown diameter of the target corn tassel to the maximum diameter of the main shaft; the center of gravity is the geometric center of the target corn tassel. The three-dimensional phenotypic parameters in the embodiment are scientifically defined from a three-dimensional perspective in advance, and the tassels of different varieties of corn have obvious differences on the three-dimensional phenotypic parameters.
Furthermore, on the basis of obtaining various three-phenotype parameters of the target corn tassel through measurement, the corn varieties of the target corn tassel are distinguished according to the three-dimensional phenotype parameters, and when any three-dimensional phenotype parameter of the three-dimensional phenotype parameters of the two corn tassels is different, the two corn tassels can be determined to be the corns of different varieties.
The invention provides a corn variety distinguishing method based on a three-dimensional phenotype of a corn tassel, which is characterized in that a plurality of characteristic points are marked on the periphery of a target corn tassel, the target corn tassel is subjected to stereo shooting to obtain images of the target corn tassel under a plurality of visual angles, a three-dimensional model of the target corn tassel is constructed through the images under the plurality of visual angles, three-dimensional phenotype parameters such as an outer envelope volume, a branch vertical projection total area, a plane aggregation degree, a space aggregation degree, a main shaft change coefficient, a crown-height ratio, a head-stem ratio, a gravity center and the like which represent the three-dimensional characteristics of the target corn tassel are calculated based on the three-dimensional model, and finally, the corn variety of the target corn tassel is accurately distinguished through the three-dimensional phenotype parameters. The method scientifically defines the three-dimensional phenotypic parameters of the maize tassel from a three-dimensional angle, accurately distinguishes maize varieties by using the difference of the three-dimensional phenotypic parameters of different maize varieties, can be used for maize breeding with low cost, high efficiency and accuracy, quickly obtains the three-dimensional phenotypic parameters of the maize tassel for breeding experts, and then performs gene association analysis based on the three-dimensional phenotypic parameters to locate the genes of the optimal maize tassel three-dimensional structure, is favorable for accelerating the maize breeding process, and effectively improves the breeding efficiency and level.
Based on any one of the above embodiments, there is provided a method for distinguishing corn varieties based on three-dimensional maize tassel phenotype, where the step S2 further includes:
acquiring all the feature points from the images under the multiple viewing angles, and calculating the position conversion relation of the same feature point under the multiple viewing angles;
mapping point clouds in the images under the multiple visual angles to a three-dimensional coordinate system by using an aerial triangulation method according to the position conversion relation and the angles of the multiple visual angles to obtain three-dimensional point clouds;
and constructing a three-dimensional model of the target corn tassel according to the three-dimensional point cloud by utilizing a Poisson surface reconstruction algorithm.
Specifically, after the images of the target corn tassel at multiple viewing angles are obtained, since the images at the multiple viewing angles include pre-labeled feature points, the feature points in the images at the multiple viewing angles can be extracted by using a descriptor, and the position conversion relationship at the multiple viewing angles can be calculated by performing stereo measurement analysis on the feature points. Because the shooting visual angle of each image is determined, the point clouds in the images under multiple visual angles are mapped into a three-dimensional coordinate system by using an aerial triangulation method according to the position conversion relation and the shooting visual angle of each image, and high-density three-dimensional point clouds are obtained. On the basis, a three-dimensional model of the target corn tassel is constructed according to the high-density three-dimensional point cloud by utilizing a Poisson surface reconstruction algorithm. In addition, in other embodiments, on the basis of obtaining the images of the target corn tassel at multiple viewing angles, a three-dimensional model of the target corn tassel may also be obtained in other manners, which is not specifically limited herein.
The invention provides a corn variety distinguishing method based on a three-dimensional phenotype of a corn tassel, which is characterized in that aiming at images of a target corn tassel under multiple visual angles, all characteristic points are obtained from the images under the multiple visual angles, and the position conversion relation of the same characteristic point under the multiple visual angles is calculated; mapping point clouds in the images under the multiple visual angles to a three-dimensional coordinate system by using an aerial triangulation method according to the position conversion relation and the angles of the multiple visual angles to obtain three-dimensional point clouds; and finally, constructing a three-dimensional model of the target corn tassel according to the three-dimensional point cloud by utilizing a Poisson surface reconstruction algorithm. The method can accurately obtain the three-dimensional model of the target corn tassel, thereby being beneficial to obtaining the three-dimensional phenotype parameter of the target corn tassel based on the three-dimensional model and further being beneficial to accurately distinguishing the corn variety of the target corn tassel through the three-dimensional phenotype parameter.
Based on any of the above embodiments, there is provided a method for distinguishing corn varieties based on a three-dimensional phenotype of a corn tassel, wherein the step S3 of obtaining an outer envelope volume of the target corn tassel based on the three-dimensional model further includes:
dividing point clouds in the three-dimensional model into a plurality of layers from top to bottom according to a preset interval;
acquiring an envelope convex surface of each layer of point cloud, and calculating the surface area of each envelope convex surface;
and obtaining the outer envelope volume of the target corn tassel according to the surface area of each envelope convex surface and the preset interval.
Specifically, the three-dimensional phenotype parameters obtained based on the three-dimensional model of the target corn tassel include an outer envelope volume of the target corn tassel, and the outer envelope volume is a volume of a three-dimensional space formed by connecting all point clouds in the three-dimensional model of the target corn tassel. In this embodiment, the specific process of calculating the outer envelope volume of the target maize tassel based on the three-dimensional model of the target maize tassel is as follows:
first, in order to ensure the accuracy of measurement, the point cloud in the three-dimensional model is divided into a plurality of layers from top to bottom according to a preset interval. The preset distance is determined according to the height of the target corn tassel, the height of the target corn tassel can be determined through the difference value of the maximum Z-axis coordinate and the minimum Z-axis coordinate of the point cloud in the three-dimensional model in the three-dimensional coordinate system, the preset distance with the proper size is determined by combining the height of the target corn tassel, the specific value of the preset distance can be determined according to the actual requirement, and the specific limitation is not made here. In the embodiment, the point cloud in the three-dimensional model is divided into 30 layers from top to bottom, in other embodiments, the point cloud can be divided into other layers according to actual conditions, and the specific limitation is not made here.
Further, after the point clouds in the three-dimensional model are subjected to hierarchical division, envelope convex surfaces of each layer of point clouds are obtained, and the surface area of the envelope convex surfaces of each layer of point clouds is calculated, wherein the convex surfaces are composed of Delaunay triangulation networks, each layer of point clouds can be subjected to a triangulation network based on each layer of point clouds, the Delaunay triangulation networks are a special mode and can maximize a minimum internal angle, and meanwhile, any triangle does not contain other points.
Further, according to the obtained surface area of each layer of point cloud enveloping convex surface, summing the surface areas of all the layers of point cloud enveloping convex surfaces to obtain a total surface area, and multiplying the total surface area by the preset interval to obtain the outer enveloping volume of the target corn tassel.
The corn variety distinguishing method based on the three-dimensional phenotype of the corn tassel is based on a three-dimensional model, firstly, point clouds in the three-dimensional model are divided into a plurality of layers from top to bottom according to a preset interval, then, envelope convex surfaces of each layer of point clouds are obtained, the surface area of each envelope convex surface is calculated, finally, the outer envelope volume of the target corn tassel is obtained according to the surface area of each envelope convex surface and the preset interval, the outer envelope volume of the target corn tassel can be accurately obtained, and the corn variety distinguishing method based on the three-dimensional phenotype of the corn tassel is beneficial to accurately distinguishing the corn variety of the target corn tassel according to the outer envelope volume.
Based on any of the above embodiments, there is provided a corn variety distinguishing method based on a three-dimensional corn tassel phenotype, wherein the step S3 of obtaining a total area of a branch vertical projection of the target corn tassel based on the three-dimensional model further includes:
projecting all point clouds in the three-dimensional model to a horizontal plane, and obtaining projection points corresponding to all the point clouds on the horizontal plane;
and obtaining an outer envelope convex hull formed by all the projection points, calculating the area of the outer envelope convex hull, and determining the area of the outer envelope convex hull as the total area of the branch vertical projection of the target corn tassel.
Specifically, the three-dimensional phenotype parameters obtained based on the three-dimensional model of the target corn tassel include a total area of branch vertical projections of the target corn tassel, and the total area of the branch vertical projections is the total area of a convex hull formed by projection of all point clouds in the three-dimensional model of the target corn tassel onto a horizontal plane. In this embodiment, the specific process of calculating the total area of the branch vertical projection of the target maize tassel based on the three-dimensional model of the target maize tassel is as follows:
in a three-dimensional coordinate system, projecting all point clouds in a three-dimensional model of the target corn tassel to a horizontal plane formed by an X axis and a Y axis, and further obtaining projection points corresponding to all the point clouds on the horizontal plane.
And aiming at all projection points on the horizontal plane, acquiring an outer envelope convex hull formed by all the projection points, calculating the area of the outer envelope convex hull, and finally determining the area of the outer envelope convex hull as the total area of the branch vertical projection of the target corn tassel. For all the projection points on the two-dimensional horizontal plane, a convex polygon formed by connecting the outermost points is an outer envelope convex hull, and the convex polygon can contain all the projection points.
The corn variety distinguishing method based on the three-dimensional phenotype of the corn tassel, provided by the invention, is based on a three-dimensional model, all point clouds in the three-dimensional model are projected to a horizontal plane, projection points corresponding to all the point clouds are obtained on the horizontal plane, an outer envelope convex hull formed by all the projection points is obtained, the area of the outer envelope convex hull is calculated, and finally the area of the outer envelope convex hull is determined as the total area of the branch vertical projection of the target corn tassel, so that the total area of the branch vertical projection of the target corn tassel can be accurately obtained, and the corn variety of the target corn tassel can be accurately distinguished according to the total area of the branch vertical projection.
Based on any of the above embodiments, there is provided a method for distinguishing corn varieties based on a three-dimensional phenotype of a corn tassel, wherein the step S3 of obtaining the planar aggregation and the spatial aggregation of the target corn tassel based on the three-dimensional model further includes:
acquiring the branch number of the target corn tassel based on the three-dimensional model;
and obtaining the plane aggregation of the target maize tassel according to the total area of the vertical projection of the branches and the number of the branches, and obtaining the space aggregation of the target maize tassel according to the outer envelope volume and the number of the branches.
Specifically, the three-dimensional phenotype parameters obtained based on the three-dimensional model of the target maize tassel include a plane aggregation degree and a space aggregation degree of the target maize tassel, wherein the plane aggregation degree is a ratio of a total area of a branch vertical projection of the target maize tassel to the number of branches, and the space aggregation degree is a ratio of an outer envelope volume of the target maize tassel to the number of branches. In this embodiment, the specific process of calculating the planar aggregation and the spatial aggregation of the target maize tassel based on the three-dimensional model of the target maize tassel is as follows:
firstly, the branch number of the target corn tassel is obtained based on the three-dimensional model. Specifically, selecting a spike stalk part point cloud from a three-dimensional model, and fitting the spike stalk part point cloud into a cylinder; determining the direction vector of the main shaft of the target corn tassel according to the coordinates of the circle centers of the upper bottom surface and the lower bottom surface of the cylinder; on the basis, the maximum radius of the upper bottom surface and the lower bottom surface of the fitted cylinder is used as the radius of a new cylinder, and a new cylinder is fitted; traversing all point clouds in the three-dimensional model, and removing the point clouds in the new cylinder; and for the residual point cloud, counting the number of branches based on a DBSCAN algorithm. The DBSCAN algorithm is a density-based spatial clustering algorithm, and in this embodiment, the experimentally determined algorithm parameters are as follows: the minimum number of points is 12 and the neighborhood radius is 0.001. In other embodiments, the branch count statistics may also be performed by other algorithms or setting other algorithm parameters, and may be set according to actual requirements, which is not specifically limited herein.
Further, on the basis of obtaining the branch number of the target maize tassel, determining the ratio of the total branch vertical projection area of the target maize tassel to the branch number as the plane aggregation degree of the target maize tassel by combining the total branch vertical projection area of the target maize tassel obtained by the calculation; and determining the ratio of the outer envelope volume of the target maize tassel to the number of branches as the spatial aggregation degree of the target maize tassel by combining the outer envelope volume of the target maize tassel obtained by the calculation.
According to the corn variety distinguishing method based on the three-dimensional phenotype of the corn tassel, the branch number of the target corn tassel is obtained based on the three-dimensional model, the plane aggregation degree of the target corn tassel is obtained according to the total branch vertical projection area and the branch number of the target corn tassel, the space aggregation degree of the target corn tassel is obtained according to the outer envelope volume and the branch number of the target corn tassel, the plane aggregation degree and the space aggregation degree of the target corn tassel can be accurately obtained, and the corn variety distinguishing method based on the three-dimensional phenotype of the corn tassel is beneficial to accurately distinguishing the corn variety of the target corn tassel according to the plane aggregation degree and the space aggregation degree.
Based on any of the above embodiments, there is provided a method for distinguishing corn varieties based on a three-dimensional phenotype of a corn tassel, wherein the step S3 of obtaining a principal axis variation coefficient of the target corn tassel based on the three-dimensional model further includes:
obtaining the height of a main shaft, the maximum diameter of the main shaft and the minimum diameter of the main shaft of the target corn tassel based on the three-dimensional model;
and calculating the difference value between the maximum diameter of the main shaft and the minimum diameter of the main shaft, and determining the main shaft change coefficient of the target corn tassel according to the difference value and the height of the main shaft.
Specifically, the three-dimensional phenotype parameters obtained based on the three-dimensional model of the target corn tassel include a main axis variation coefficient of the target corn tassel, wherein the main axis variation coefficient is a ratio of a difference between a maximum diameter and a minimum diameter of a main axis of the target corn tassel to a height of the main axis. In this embodiment, the specific process of calculating the principal axis variation coefficient of the target maize tassel based on the three-dimensional model of the target maize tassel is as follows:
firstly, in a three-dimensional model of the target corn tassel, the difference value of the maximum Z-axis coordinate in all point clouds and the Z-axis coordinate of the point cloud at the lowest end branch of the target corn tassel is used as the main shaft height of the target corn tassel.
Further, selecting the spike stalk part point cloud from the three-dimensional model, fitting the spike stalk part point cloud into a cylinder, determining a direction vector of a main shaft of the target corn tassel according to circle center coordinates of the upper bottom surface and the lower bottom surface of the cylinder, taking the direction vector of the main shaft as a reference, extracting main shaft part point cloud data by using distance parameters, then clustering, wherein the maximum clustering result is the main shaft of the target corn tassel, and finally, performing layered fitting on the main shaft point cloud data to obtain the maximum diameter and the minimum diameter of the main shaft.
Further, on the basis of obtaining the main shaft height, the main shaft maximum diameter and the main shaft minimum diameter of the target corn tassel through calculation, the difference value between the main shaft maximum diameter and the main shaft minimum diameter is further calculated, and the ratio of the difference value to the main shaft height is determined as the main shaft variation coefficient of the target corn tassel.
The method for distinguishing the corn varieties based on the three-dimensional phenotype of the corn tassels, provided by the invention, comprises the steps of obtaining the main shaft height, the main shaft maximum diameter and the main shaft minimum diameter of a target corn tassels based on a three-dimensional model, calculating the difference value between the main shaft maximum diameter and the main shaft minimum diameter, determining the ratio of the difference value and the main shaft height as the main shaft change coefficient of the target corn tassels, accurately obtaining the main shaft change coefficient of the target corn tassels, and being beneficial to accurately distinguishing the corn varieties of the target corn tassels according to the main shaft change coefficient.
Based on any of the above embodiments, there is provided a corn variety distinguishing method based on a three-dimensional phenotype of a corn tassel, wherein the step S3 of obtaining a crown height ratio and a head-stem ratio of the target corn tassel based on the three-dimensional model further includes:
selecting point clouds at the bottom of the ear stems from the three-dimensional model to fit into a circle, and taking the circle center of the circle as a reference point;
calculating the distances between all point clouds in the three-dimensional model and the reference point on a horizontal plane, determining the maximum value of the distances as the maximum ear crown radius, and obtaining the maximum ear crown diameter according to the maximum ear crown radius;
and obtaining the crown height ratio of the target corn tassel according to the maximum ear crown diameter and the main shaft length, and obtaining the head-stem ratio of the target corn tassel according to the maximum ear crown diameter and the main shaft maximum diameter.
Specifically, the three-dimensional phenotype parameters obtained based on the three-dimensional model of the target corn tassel include a crown height ratio and a head-stem ratio of the target corn tassel, wherein the crown height ratio is a ratio of the maximum crown diameter of the target corn tassel to the height of the main shaft, and the head-stem ratio is a ratio of the maximum crown diameter of the target corn tassel to the maximum diameter of the main shaft. In this embodiment, the specific process of calculating the crown-height ratio and the head-stem ratio of the target maize tassel based on the three-dimensional model of the target maize tassel is as follows:
selecting point clouds at the bottom of a tassel handle from a three-dimensional model of a target corn tassel to fit into a circle, taking the circle center of the circle as a reference point, calculating the distances between all the point clouds in the three-dimensional model and the reference point on a horizontal plane, determining the maximum value of the calculated distances as the maximum ear crown radius, and further obtaining the maximum ear crown diameter according to the maximum ear crown radius.
Further, on the basis of obtaining the maximum ear crown diameter of the target corn tassel, determining the ratio of the maximum ear crown diameter of the target corn tassel to the main shaft height as the crown height ratio of the target corn tassel by combining the calculated main shaft height of the target corn tassel; and determining the ratio of the maximum crown diameter of the target corn tassel to the maximum diameter of the main shaft as the head-stem ratio of the target corn tassel by combining the calculated maximum diameter of the main shaft of the target corn tassel.
The invention provides a corn variety distinguishing method based on a three-dimensional phenotype of a corn tassel, which is characterized in that a point cloud at the bottom of a tassel handle is selected from a three-dimensional model to fit into a circle based on the three-dimensional model, the circle center of the circle is used as a reference point, the distances between all the point clouds in the three-dimensional model and the reference point on a horizontal plane are calculated, the maximum value of the distances is determined as the maximum ear crown radius, the maximum ear crown diameter is obtained according to the maximum ear crown radius, the crown height ratio of a target corn tassel is finally obtained according to the maximum ear crown diameter and the main shaft length, the head-stem ratio of the target corn tassel is obtained according to the maximum ear crown diameter and the main shaft maximum diameter, the crown height ratio and the head-stem ratio of the target corn tassel can be accurately obtained, and the corn variety of the target corn tassel can be accurately distinguished according to the crown height ratio and the head-stem ratio.
Based on any of the above embodiments, there is provided a corn variety distinguishing method based on a three-dimensional corn tassel phenotype, wherein the step S3 of obtaining the center of gravity of the target corn tassel based on the three-dimensional model further includes:
taking the maximum ear crown diameter as a boundary in the three-dimensional model, and acquiring a first distance from the boundary to the top of the tassel and a second distance from the boundary to the lowest end branch of the tassel;
and obtaining the gravity center of the target corn tassel according to the first distance and the second distance.
Specifically, the three-dimensional phenotype parameters obtained based on the three-dimensional model of the target corn tassel include the gravity center of the target corn tassel, and the gravity center is the geometric center of the target corn tassel. In this embodiment, the specific process of calculating the center of gravity of the target corn tassel based on the three-dimensional model of the target corn tassel is as follows:
selecting point clouds at the bottom of a tassel handle from a three-dimensional model of a target corn tassel to fit into a circle, taking the circle center of the circle as a reference point, calculating the distances between all the point clouds in the three-dimensional model and the reference point on a horizontal plane, determining the maximum value of the calculated distances as the maximum ear crown radius, and further obtaining the maximum ear crown diameter according to the maximum ear crown radius.
Further, a first distance from the boundary to the top of the tassel and a second distance from the boundary to the lowest branch of the tassel are obtained by taking the maximum ear crown diameter as the boundary in the three-dimensional model, the ratio of the first distance to the second distance is used as the coordinate of the center of gravity of the target maize tassel in the Z-axis direction, and the center of gravity is obtained in the main axis direction of the target maize tassel according to the obtained coordinate in the Z-axis direction.
According to the corn variety distinguishing method based on the three-dimensional phenotype of the corn tassel, the maximum crown diameter of the corn tassel is taken as a boundary line in a three-dimensional model, the first distance from the boundary line to the top of the tassel and the second distance from the boundary line to the lowest branch of the tassel are obtained, the gravity center of the target corn tassel is obtained according to the first distance and the second distance, the gravity center of the target corn tassel can be accurately obtained, and the corn variety of the target corn tassel can be accurately distinguished according to the gravity center.
To better understand the three-dimensional phenotypic parameters of the tassel of corn of the present invention, the following example is used for specific explanation, fig. 2 shows a schematic diagram of the three-dimensional phenotypic parameters of the tassel of corn according to an embodiment of the present invention, as shown in fig. 2, which only shows a part of the three-dimensional phenotypic parameters of the tassel of corn, wherein Vt is the outer envelope volume of the tassel of corn; dm is the maximum diameter of the main shaft; dn is the minimum diameter of the main shaft; hx is the height of the main shaft; dc is the maximum ear crown diameter; o is the center of the circle with the maximum ear crown diameter; hc is the distance from the maximum ear crown diameter to the top of the corn tassel; hb is the distance from the maximum crown diameter to the lowest branch of the corn tassel.
Fig. 3 is a schematic diagram of an overall structure of a corn variety distinguishing system based on a three-dimensional corn tassel phenotype according to an embodiment of the present invention, and as shown in fig. 3, the present invention provides a corn variety distinguishing system based on a three-dimensional corn tassel phenotype, including:
the image acquisition module 1 is used for marking a plurality of characteristic points around the target corn tassel and acquiring images of the target corn tassel at a plurality of viewing angles;
the model building module 2 is used for building a three-dimensional model of the target corn tassel according to the images under the multiple viewing angles;
the parameter obtaining module 3 is used for obtaining three-dimensional phenotype parameters of the target corn tassel based on the three-dimensional model, wherein the three-dimensional phenotype parameters comprise an outer envelope volume, a total area of branch vertical projection, a plane aggregation degree, a space aggregation degree, a main shaft change coefficient, a crown-to-stem ratio, a head-to-stem ratio and a gravity center;
and the variety distinguishing module 4 is used for distinguishing the corn varieties of the target corn tassel according to the three-dimensional phenotype parameters.
Specifically, the invention provides a corn variety distinguishing system based on a three-dimensional corn tassel phenotype, which comprises an image acquisition module 1, a model construction module 2, a parameter acquisition module 3 and a variety distinguishing module 4, wherein the corn variety distinguishing method based on the three-dimensional corn tassel phenotype in any embodiment is realized through the cooperation of the modules, and is specifically realized as follows:
sampling the corn tassels from the field to obtain target corn tassels; the image acquisition module 1 is utilized to mark a plurality of feature points on the periphery of the target corn tassel, and in practical application, the target corn tassel can be inserted on a pre-manufactured reference plate, and the feature points are marked on the reference plate in advance. In other embodiments, the feature points may also be labeled in other manners, which are not specifically limited herein.
On the basis of the technical scheme, the image acquisition module 1 is used for acquiring images of the target corn tassel at multiple viewing angles, in this embodiment, in order to facilitate the subsequent construction of a three-dimensional model of the target corn tassel, the image acquisition module 1 is used for shooting 2 images with the overlapping degree of more than 60% along the side surface and the top surface of the target corn tassel crown layer at each horizontal position to form binocular stereoscopic vision measurement, then the camera position is sequentially rotated around the main axis direction of the target corn tassel, the image shooting is repeatedly executed at 15 degrees at intervals, the shooting is totally carried out for 24 times after the rotation is completed for one week, and finally 48 images with multiple viewing angles are obtained for each target corn tassel.
Further, after the images of the target corn tassel at the multiple viewing angles are obtained, because the images at the multiple viewing angles include the pre-labeled feature points, the point cloud in the images at the multiple viewing angles can be mapped into the three-dimensional coordinate system by performing stereo measurement and analysis on the feature points by using the model building module 2, so as to obtain a high-density three-dimensional point cloud, and further, the high-density three-dimensional point cloud is used for building a three-dimensional model of the target corn tassel.
Further, the parameter obtaining module 3 is used for obtaining three-dimensional phenotype parameters of the target corn tassel based on the obtained three-dimensional model of the target corn tassel, wherein the three-dimensional phenotype parameters comprise an outer envelope volume, a total branch vertical projection area, a plane aggregation degree, a space aggregation degree, a main axis variation coefficient, a crown-height ratio, a head-stem ratio, a gravity center and the like. Wherein the outer envelope volume is the volume of a three-dimensional space formed by connecting all point clouds in the three-dimensional model of the target corn tassel; the total vertical projection area of the branches is the total area of a convex hull formed by projecting all point clouds in the three-dimensional model of the target corn tassel to the horizontal plane; the plane aggregation degree is the ratio of the total area of the vertical projection of the branches of the target maize tassel to the number of the branches; the spatial aggregation degree is the ratio of the outer envelope volume of the target maize tassel to the number of branches; the main shaft variation coefficient is the ratio of the difference between the maximum diameter and the minimum diameter of the main shaft of the target corn tassel to the height of the main shaft; the crown height ratio is the ratio of the maximum crown diameter of the target corn tassel to the height of the main shaft; the head-stem ratio is the ratio of the maximum crown diameter of the target corn tassel to the maximum diameter of the main shaft; the center of gravity is the geometric center of the target corn tassel. The three-dimensional phenotypic parameters in the embodiment are scientifically defined from a three-dimensional perspective in advance, and the tassels of different varieties of corn have obvious differences on the three-dimensional phenotypic parameters.
Furthermore, on the basis of obtaining various three-phenotype parameters of the target corn tassel through measurement, the variety distinguishing module 4 is used for distinguishing corn varieties of the target corn tassel according to the three-dimensional phenotype parameters, and when any three-dimensional phenotype parameter of the three-dimensional phenotype parameters of the two corn tassels is different, the two corn tassels can be determined to be corns of different varieties.
The invention provides a corn variety distinguishing system based on a three-dimensional phenotype of a corn tassel, which is characterized in that a plurality of feature points are marked on the periphery of the target corn tassel, the target corn tassel is subjected to stereo shooting to obtain images of the target corn tassel under a plurality of visual angles, a three-dimensional model of the target corn tassel is constructed through the images under the plurality of visual angles, three-dimensional phenotype parameters such as an outer envelope volume, a total area of branch vertical projection, a plane aggregation degree, a space aggregation degree, a main shaft change coefficient, a crown-height ratio, a head-stem ratio, a gravity center and the like which represent the three-dimensional feature of the target corn tassel are calculated based on the three-dimensional model, and finally, the corn variety of the target corn tassel is accurately distinguished through the three-dimensional phenotype parameters. The system scientifically defines the three-dimensional phenotypic parameters of the maize tassel from a three-dimensional angle, accurately distinguishes maize varieties by using the difference of the three-dimensional phenotypic parameters of different maize varieties, can be used for maize breeding with low cost, high efficiency and accuracy, quickly obtains the three-dimensional phenotypic parameters of the maize tassel for breeding experts, and then performs gene association analysis based on the three-dimensional phenotypic parameters to locate the genes of the optimal maize tassel three-dimensional structure, is favorable for accelerating the maize breeding process, and effectively improves the breeding efficiency and level.
FIG. 4 shows a block diagram of an apparatus for a corn variety differentiation method based on a three-dimensional corn tassel phenotype according to an embodiment of the present invention. Referring to fig. 4, the apparatus of the corn variety distinguishing method based on the three-dimensional phenotype of the corn tassel comprises: a processor (processor)41, a memory (memory)42, and a bus 43; wherein, the processor 41 and the memory 42 complete the communication with each other through the bus 43; the processor 41 is configured to call program instructions in the memory 42 to perform the methods provided by the above-mentioned method embodiments, including: marking a plurality of characteristic points around the target corn tassel, and collecting images of the target corn tassel at a plurality of viewing angles; constructing a three-dimensional model of the target corn tassel according to the images under the multiple viewing angles; acquiring three-dimensional phenotypic parameters of the target maize tassel based on the three-dimensional model, wherein the three-dimensional phenotypic parameters comprise an outer envelope volume, a total branch vertical projection area, a plane aggregation degree, a space aggregation degree, a main shaft variation coefficient, a crown-to-height ratio, a head-to-stem ratio and a gravity center; and distinguishing the corn varieties of the target corn tassel according to the three-dimensional phenotype parameters.
The present embodiment discloses a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the method provided by the above-mentioned method embodiments, for example, comprising: marking a plurality of characteristic points around the target corn tassel, and collecting images of the target corn tassel at a plurality of viewing angles; constructing a three-dimensional model of the target corn tassel according to the images under the multiple viewing angles; acquiring three-dimensional phenotypic parameters of the target maize tassel based on the three-dimensional model, wherein the three-dimensional phenotypic parameters comprise an outer envelope volume, a total branch vertical projection area, a plane aggregation degree, a space aggregation degree, a main shaft variation coefficient, a crown-to-height ratio, a head-to-stem ratio and a gravity center; and distinguishing the corn varieties of the target corn tassel according to the three-dimensional phenotype parameters.
The present embodiments provide a non-transitory computer-readable storage medium storing computer instructions that cause the computer to perform the methods provided by the above method embodiments, for example, including: marking a plurality of characteristic points around the target corn tassel, and collecting images of the target corn tassel at a plurality of viewing angles; constructing a three-dimensional model of the target corn tassel according to the images under the multiple viewing angles; acquiring three-dimensional phenotypic parameters of the target maize tassel based on the three-dimensional model, wherein the three-dimensional phenotypic parameters comprise an outer envelope volume, a total branch vertical projection area, a plane aggregation degree, a space aggregation degree, a main shaft variation coefficient, a crown-to-height ratio, a head-to-stem ratio and a gravity center; and distinguishing the corn varieties of the target corn tassel according to the three-dimensional phenotype parameters.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
The above-described embodiments of the apparatus and the like for the corn variety distinguishing method based on the three-dimensional corn tassel phenotype are merely illustrative, wherein the units described as the separating means may or may not be physically separated, and the means displayed as the units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, the method of the present application is only a preferred embodiment and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (9)

1. A corn variety distinguishing method based on a corn tassel three-dimensional phenotype is characterized by comprising the following steps:
s1, marking a plurality of characteristic points around the target corn tassel, and collecting images of the target corn tassel at a plurality of viewing angles;
s2, constructing a three-dimensional model of the target corn tassel according to the images under the multiple viewing angles;
s3, acquiring three-dimensional phenotype parameters of the target corn tassel based on the three-dimensional model, wherein the three-dimensional phenotype parameters comprise an outer envelope volume, a total area of branch vertical projection, a plane aggregation degree, a space aggregation degree, a main shaft change coefficient, a crown-to-stem ratio, a head-to-stem ratio and a gravity center;
s4, distinguishing the corn varieties of the target corn tassel according to the three-dimensional phenotype parameters;
the step S2 further includes:
acquiring all the feature points from the images under the multiple viewing angles, and calculating the position conversion relation of the same feature point under the multiple viewing angles;
mapping point clouds in the images under the multiple visual angles to a three-dimensional coordinate system by using an aerial triangulation method according to the position conversion relation and the angles of the multiple visual angles to obtain three-dimensional point clouds;
and constructing a three-dimensional model of the target corn tassel according to the three-dimensional point cloud by utilizing a Poisson surface reconstruction algorithm.
2. The method of claim 1, wherein obtaining the outer envelope volume of the target corn tassel based on the three-dimensional model in step S3 further comprises:
dividing point clouds in the three-dimensional model into a plurality of layers from top to bottom according to a preset interval;
acquiring an envelope convex surface of each layer of point cloud, and calculating the surface area of each envelope convex surface;
and obtaining the outer envelope volume of the target corn tassel according to the surface area of each envelope convex surface and the preset interval.
3. The method of claim 2, wherein the obtaining of the total branched vertical projection area of the target corn tassel based on the three-dimensional model in step S3 further comprises:
projecting all point clouds in the three-dimensional model to a horizontal plane, and obtaining projection points corresponding to all the point clouds on the horizontal plane;
and obtaining an outer envelope convex hull formed by all the projection points, calculating the area of the outer envelope convex hull, and determining the area of the outer envelope convex hull as the total area of the branch vertical projection of the target corn tassel.
4. The method of claim 3, wherein the obtaining the planar concentration and the spatial concentration of the target corn tassel based on the three-dimensional model in step S3 further comprises:
acquiring the branch number of the target corn tassel based on the three-dimensional model;
and obtaining the plane aggregation of the target maize tassel according to the total area of the vertical projection of the branches and the number of the branches, and obtaining the space aggregation of the target maize tassel according to the outer envelope volume and the number of the branches.
5. The method of claim 1, wherein obtaining the principal axis coefficient of change of the target corn tassel based on the three-dimensional model in step S3 further comprises:
obtaining the height of a main shaft, the maximum diameter of the main shaft and the minimum diameter of the main shaft of the target corn tassel based on the three-dimensional model;
and calculating the difference value between the maximum diameter of the main shaft and the minimum diameter of the main shaft, and determining the main shaft change coefficient of the target corn tassel according to the difference value and the height of the main shaft.
6. The method of claim 5, wherein obtaining the crown-to-stem ratio and the head-to-stem ratio of the target corn tassel based on the three-dimensional model in step S3 further comprises:
selecting point clouds at the bottom of the ear stems from the three-dimensional model to fit into a circle, and taking the circle center of the circle as a reference point;
calculating the distances between all point clouds in the three-dimensional model and the reference point on a horizontal plane, determining the maximum value of the distances as the maximum ear crown radius, and obtaining the maximum ear crown diameter according to the maximum ear crown radius;
and obtaining the crown height ratio of the target corn tassel according to the maximum ear crown diameter and the main shaft length, and obtaining the head-stem ratio of the target corn tassel according to the maximum ear crown diameter and the main shaft maximum diameter.
7. The method of claim 6, wherein obtaining the center of gravity of the target corn tassel based on the three-dimensional model in step S3 further comprises:
taking the maximum ear crown diameter as a boundary in the three-dimensional model, and acquiring a first distance from the boundary to the top of the tassel and a second distance from the boundary to the lowest end branch of the tassel;
and obtaining the gravity center of the target corn tassel according to the first distance and the second distance.
8. A corn variety discrimination system based on a three-dimensional phenotype of a corn tassel, comprising:
the image acquisition module is used for marking a plurality of characteristic points on the periphery of the target corn tassel and acquiring images of the target corn tassel at a plurality of visual angles;
the model building module is used for building a three-dimensional model of the target corn tassel according to the images under the multiple viewing angles;
a parameter obtaining module, configured to obtain three-dimensional phenotype parameters of the target maize tassel based on the three-dimensional model, where the three-dimensional phenotype parameters include an outer envelope volume, a total area of branch vertical projections, a planar aggregation degree, a spatial aggregation degree, a main axis variation coefficient, a crown-to-stem ratio, a head-to-stem ratio, and a center of gravity;
the variety distinguishing module is used for distinguishing the corn varieties of the target corn tassel according to the three-dimensional phenotype parameters;
the model building module is further configured to acquire all the feature points from the images under the multiple viewing angles, and calculate a position conversion relationship of the same feature point under the multiple viewing angles;
mapping point clouds in the images under the multiple visual angles to a three-dimensional coordinate system by using an aerial triangulation method according to the position conversion relation and the angles of the multiple visual angles to obtain three-dimensional point clouds;
and constructing a three-dimensional model of the target corn tassel according to the three-dimensional point cloud by utilizing a Poisson surface reconstruction algorithm.
9. The equipment of the corn variety distinguishing method based on the corn tassel three-dimensional phenotype is characterized by comprising the following steps of:
at least one processor; and
at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of any of claims 1 to 7.
CN201810508702.9A 2018-05-24 2018-05-24 Corn variety distinguishing method and system based on corn tassel three-dimensional phenotype Active CN108876903B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810508702.9A CN108876903B (en) 2018-05-24 2018-05-24 Corn variety distinguishing method and system based on corn tassel three-dimensional phenotype

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810508702.9A CN108876903B (en) 2018-05-24 2018-05-24 Corn variety distinguishing method and system based on corn tassel three-dimensional phenotype

Publications (2)

Publication Number Publication Date
CN108876903A CN108876903A (en) 2018-11-23
CN108876903B true CN108876903B (en) 2022-04-08

Family

ID=64333820

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810508702.9A Active CN108876903B (en) 2018-05-24 2018-05-24 Corn variety distinguishing method and system based on corn tassel three-dimensional phenotype

Country Status (1)

Country Link
CN (1) CN108876903B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111578837B (en) * 2020-04-30 2022-03-01 北京农业智能装备技术研究中心 Plant shape visual tracking measurement method for agricultural robot operation
CN111950436A (en) * 2020-08-07 2020-11-17 中国农业大学 Corn ear phenotype measuring method and system
CN112489214B (en) * 2020-11-24 2024-08-06 上海市建工设计研究总院有限公司 Modeling method for crown branches of outer packing tree
CN114066967B (en) * 2022-01-11 2022-04-22 安徽高哲信息技术有限公司 Training method and device of volume estimation model and volume estimation method and device

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101667302A (en) * 2009-09-22 2010-03-10 北京农业信息技术研究中心 Three-dimensional configuration virtual modeling method for maize tassel
CN104823834A (en) * 2015-04-23 2015-08-12 湖北大学 Method for breeding novel cockscomb specie by epigenetics principle and distant hybirdization
CN105335705A (en) * 2015-10-16 2016-02-17 中国农业大学 Corn abnormal cluster screening method based on computer vision, device and system
CN105340413A (en) * 2015-10-26 2016-02-24 中国农业大学 Corn ear three-dimensional information detection method and system thereof
CN106056050A (en) * 2016-05-23 2016-10-26 武汉盈力科技有限公司 Multi-view gait identification method based on adaptive three dimensional human motion statistic model
CN106483135A (en) * 2016-10-12 2017-03-08 河北农业大学 Corn kernel detection and identification device and method based on machine vision under complex background

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2329243A2 (en) * 2008-08-22 2011-06-08 Pioneer Hi-Bred International, Inc. Apparatus and systems for counting corn silks or other plural elongated strands and use of the count for characterizing the strands or their origin
US9872452B2 (en) * 2014-12-22 2018-01-23 Hm.Clause, Inc. Hybrid sweet corn plant HMX4369BS

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101667302A (en) * 2009-09-22 2010-03-10 北京农业信息技术研究中心 Three-dimensional configuration virtual modeling method for maize tassel
CN104823834A (en) * 2015-04-23 2015-08-12 湖北大学 Method for breeding novel cockscomb specie by epigenetics principle and distant hybirdization
CN105335705A (en) * 2015-10-16 2016-02-17 中国农业大学 Corn abnormal cluster screening method based on computer vision, device and system
CN105340413A (en) * 2015-10-26 2016-02-24 中国农业大学 Corn ear three-dimensional information detection method and system thereof
CN106056050A (en) * 2016-05-23 2016-10-26 武汉盈力科技有限公司 Multi-view gait identification method based on adaptive three dimensional human motion statistic model
CN106483135A (en) * 2016-10-12 2017-03-08 河北农业大学 Corn kernel detection and identification device and method based on machine vision under complex background

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
"Monitoring model of maize lodging based on sentinel-1 radar image";Yang guijun等;《Transactions of the Chinese society of agricultural engineering》;20180131;第166-172页 *
"基于机器视觉的玉米果穗形态特征提取技术研究";朱雪慧;《中国优秀硕士学位论文全文数据库 农业科技辑》;20180415;全文 *
"玉米果穗点云分割方法研究";温维亮等;《系统仿真学报》;20171231;第29卷(第12期);第3030-3035页 *

Also Published As

Publication number Publication date
CN108876903A (en) 2018-11-23

Similar Documents

Publication Publication Date Title
CN108876903B (en) Corn variety distinguishing method and system based on corn tassel three-dimensional phenotype
CN109785379B (en) Method and system for measuring size and weight of symmetrical object
CN109816664B (en) Three-dimensional point cloud segmentation method and device
CN112418188A (en) Crop growth whole-course digital assessment method based on unmanned aerial vehicle vision
CN111474443B (en) Method and device for measuring power transmission line
CN107767454A (en) A kind of three-dimensional mobile fast modeling method of outdoor scene, apparatus and system
CN112990063B (en) Banana maturity grading method based on shape and color information
CN115082815A (en) Tea bud picking point positioning method and device based on machine vision and picking system
CN104240229B (en) A kind of adaptive method for correcting polar line of infrared binocular camera
Xiang et al. Field‐based robotic leaf angle detection and characterization of maize plants using stereo vision and deep convolutional neural networks
CN112507768A (en) Target detection method and device and image acquisition method and device
CN109598215A (en) Orchard modeling analysis system and method based on positioning shooting of unmanned aerial vehicle
CN116309625A (en) Data processing method suitable for intelligent agriculture
CN115082254A (en) Lean control digital twin system of transformer substation
CN113011221A (en) Crop distribution information acquisition method and device and measurement system
CN108399631A (en) A kind of inclination image of scale invariability regards dense Stereo Matching method more
CN114332134A (en) Building facade extraction method and device based on dense point cloud
CN110348067B (en) Method, system, medium and equipment for extracting physical parameters of airflow characterization
CN111833435A (en) Unmanned aerial vehicle near-field remote sensing mature crop density high-flux measurement method
CN104992448A (en) Automatic positioning method for robot picking grapes in a damage-free way
CN113222025B (en) Feasible region label generation method based on laser radar
CN107463629A (en) Image data base method for building up and system based on 3D technology
CN110610438A (en) Crop canopy petiole included angle calculation method and system
CN105340413B (en) A kind of corn ear three-dimensional information detection method and system
CN118097465A (en) Unmanned aerial vehicle image and deep learning-based field rice spike positioning and identifying method

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