Method and device for obtaining phenotype of crop population

Abstract

The present invention provides a method and device for obtaining crop population phenotypes, belonging to the field of agricultural information technology. The method and device comprise: obtaining target point cloud data of a crop population within a target plot; performing three-dimensional point cloud segmentation on the target point cloud data based on the planting patterns of the crop population within the target plot to determine a crop point cloud for each planting plot; and performing phenotypic analysis on the crop point cloud for each planting plot to obtain the phenotypes of the crops within the target plot. The present invention provides a method and device for obtaining crop population phenotypes by automatically segmenting point cloud data acquired by a track-based phenotyping platform to obtain point cloud data containing only the crops in each planting plot, thereby rapidly analyzing the crop phenotypes. This enables automated, batch processing and analysis of high-sequence point cloud data acquired by the phenotyping platform.

Description

Technical Field

[0001] The present invention relates to the field of agricultural information technology, and in particular to a method and device for obtaining the phenotype of a crop population. Background Art

[0002] Phenotyping platforms acquire phenotypic data in the form of images, point clouds, and spectra. Phenotyping analysis involves converting this data into usable phenotypes for agronomists. Given the complex morphology of crop populations in the field, automated segmentation of plot point clouds is a key challenge in 3D phenotyping of crop populations.

[0003] Currently, manual operations are mostly relied upon to segment the point cloud, and then the point cloud of each planting plot is used to extract the phenotype.

[0004] However, the above method has a large workload and low processing speed for data processing in a large number of coverage cells. Summary of the Invention

[0005] The crop population phenotypic acquisition method and device provided by the present invention are used to solve the defects of the existing technology in that the data processing workload is large and the processing speed is low when covering many small areas, and realize the real-time automatic, batch processing and analysis of the high-time-series point cloud data obtained by the phenotyping platform.

[0006] The present invention provides a method for obtaining phenotypes of a crop population, comprising:

[0007] Obtain target point cloud data of crop groups within the target plot;

[0008] According to the planting pattern of the crop groups in the target plot, the target point cloud data is segmented into three-dimensional point clouds to determine the crop point clouds of each planting plot;

[0009] Phenotypic analysis is performed on the crop point cloud of each planting plot to obtain the phenotype of the crops in the target plot.

[0010] According to a method for obtaining phenotypes of a crop population provided by the present invention, obtaining target point cloud data of a crop population in a target plot includes:

[0011] Acquire initial point cloud data of the target plot; the initial point cloud data is collected by the track-type phenotyping platform on the target plot;

[0012] Performing noise reduction processing on the initial point cloud data to determine noise-reduced point cloud data;

[0013] The noise reduction point cloud data is uniformly downsampled to determine simplified point cloud data to obtain the target point cloud data.

[0014] According to the method for obtaining phenotypes of a crop population provided by the present invention, after uniformly downsampling the noise-reduced point cloud data to determine simplified point cloud data, the method further includes:

[0015] Rotating the simplified point cloud data to determine standardized point cloud data;

[0016] The standardized point cloud data is positionally calibrated using a three-dimensional coordinate system, so as to segment the calibrated standardized point cloud data along a plane where the ground is located, thereby determining the target point cloud data.

[0017] According to a method for obtaining a phenotype of a crop population provided by the present invention, the method performs three-dimensional point cloud segmentation on the target point cloud data according to the planting pattern of the crop population in the target plot, and determines the crop point cloud of each planting plot, including:

[0018] Based on the plane where the ground is located in the three-dimensional coordinate system, the target point cloud data is segmented according to a preset step size to obtain a plurality of grid point cloud data;

[0019] Determine the highest point of each grid point cloud data in the direction perpendicular to the ground;

[0020] Based on the highest point of each grid point cloud data and the cell planting method of the crop group in the target plot, the target point cloud data is segmented to obtain the cell crop point cloud of each planting cell.

[0021] According to a method for obtaining a phenotype of a crop population provided by the present invention, the target point cloud data is segmented based on the highest point of each grid point cloud data and the planting pattern of the crop population in the target plot to obtain a crop point cloud of each planting plot, including:

[0022] Based on the highest point of each grid point cloud data, the target point cloud data is segmented using a sliding window to obtain crop group point cloud data;

[0023] Based on the highest point of each grid point cloud data in the crop group point cloud data, the crop group point cloud data is segmented using a cell window group to determine the cell crop point cloud of each planting cell; the sliding window and cell window group are determined based on the cell planting method, as well as the size and position relationship of the planting cell.

[0024] According to a method for obtaining phenotypes of a crop population provided by the present invention, performing phenotype analysis on the crop point cloud of each planting plot to obtain the phenotypes of the crops in the target plot includes:

[0025] According to the plant-row spacing of the crop groups in each planting plot, the crop point cloud of each planting plot is grid-divided to determine the grid point cloud of a single plant;

[0026] Determine the highest point perpendicular to the ground in the grid point cloud of the single plant as the maximum plant height;

[0027] The phenotype of the crops in the target plot is determined according to the maximum plant height of each single plant grid point cloud.

[0028] The present invention also provides a device for obtaining a phenotype of a crop population, comprising:

[0029] An acquisition module is used to obtain target point cloud data of crop groups within a target plot;

[0030] A segmentation module is used to perform three-dimensional point cloud segmentation on the target point cloud data according to the planting pattern of the crop groups in the target plot, and determine the crop point cloud of each planting plot;

[0031] The parsing module is used to perform phenotypic analysis on the crop point cloud of each planting plot to obtain the phenotype of the crops in the target plot.

[0032] The present invention also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for obtaining the phenotype of a crop population as described above is implemented.

[0033] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for obtaining the phenotype of a crop population.

[0034] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned methods for obtaining the phenotype of a crop population.

[0035] The method and device for obtaining the phenotype of a crop population provided by the present invention automatically segment the point cloud data obtained based on the track-based phenotyping platform, thereby obtaining point cloud data containing only the crops in each planting area, and then quickly analyzing the phenotype of the crops, thereby realizing automated, batch processing and analysis of the high-time-series point cloud data obtained by the phenotyping platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 Schematic diagram of the process of obtaining the phenotype of a crop population provided by the present invention;

[0038] Figure 2 This is a schematic diagram of point cloud cutting provided by the present invention;

[0039] Figure 3 Schematic diagram of the structure of the device for obtaining the phenotype of a crop population provided by the present invention;

[0040] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0041] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0042] High-throughput crop phenotyping and analysis technology and equipment have become a new direction in crop science research. Breeding institutions and research institutes are developing numerous high-throughput crop phenotyping platforms to automatically acquire high-throughput, time-series, multi-scale crop phenotypic data. For example, by deploying track-mounted phenotyping platforms in greenhouses or fields and attaching sensors such as image, point cloud, and spectral sensors, phenotypic data can be automatically acquired throughout the entire growth period of a crop population. Based on this phenotypic data, a series of phenotypes can be derived that reflect changes in the crop population's appearance and growth throughout its growth period.

[0043] The present invention proposes a method and device for automatically processing time-series point cloud data acquired by a greenhouse / field track-type phenotyping platform, which can realize non-interactive, automated and batch time-series three-dimensional (3D) phenotyping analysis of crop populations.

[0044] In the description of the present invention, it should be understood that the terms "first," "second," etc. are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first," "second," etc. may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0045] The following combination Figures 1-4 The present invention provides a method and apparatus for obtaining phenotypes of a crop population according to an embodiment of the present invention.

[0046] Figure 1 Schematic diagram of the process for obtaining the phenotype of a crop population provided by the present invention. Figure 1 As shown, including but not limited to the following steps:

[0047] First, in step S1, target point cloud data of the crop group in the target plot is obtained.

[0048] The crop population phenotyping method provided in embodiments of the present invention may be implemented by an electronic device or software, a functional module, or a functional entity within the electronic device that implements the crop population phenotyping method. In embodiments of the present invention, the electronic device includes, but is not limited to, a server of a track-based phenotyping platform. It should be noted that the aforementioned implementation entities do not constitute limitations on the present invention.

[0049] Among them, the crop population in the target plot can be crops such as corn, cotton, broccoli, etc. planted in single plants or single clusters, and the corresponding phenotypes correspond to each plant or each cluster of crops. In the subsequent embodiments of the present invention, the phenotype acquisition of corn is used as an example for explanation, which is not regarded as limiting the scope of protection of the present invention.

[0050] The target plot includes multiple planting plots of crops. A planting plot is the smallest unit for crop sowing. Generally, the sides of each planting plot are the same, and the distance between two adjacent planting plots is the same.

[0051] The target point cloud data of the crop population in the target plot needs to be obtained, which can be collected by the track-type phenotyping platform or obtained after preprocessing the initial point cloud collected by the track-type phenotyping platform.

[0052] Optionally, obtaining target point cloud data of a crop group in a target plot includes:

[0053] Acquire initial point cloud data of the target plot; the initial point cloud data is collected by the track-type phenotyping platform on the target plot;

[0054] Performing noise reduction processing on the initial point cloud data to determine noise-reduced point cloud data;

[0055] The noise reduction point cloud data is uniformly downsampled to determine simplified point cloud data to obtain the target point cloud data.

[0056] The track-type phenotyping platform moves along the track beside the target plot and collects point cloud data. Since the track is straight, the collected initial point cloud data appears as a long rectangle when viewed from above in the height direction.

[0057] The initial point cloud data may be a three-dimensional point cloud of a crop population collected by a track-type phenotyping platform on the target plot.

[0058] By using denoising methods such as the 3D point cloud denoising network (PCN), mean absolute difference (MAD) or local outlier factor (CLOF) algorithm to remove outliers in the initial point cloud data, denoised point cloud data can be obtained; then, the denoised point cloud data can be simplified by using the uniform downsampling method to obtain simplified point cloud data.

[0059] According to the crop population phenotypic acquisition method provided by the present invention, the accuracy of the phenotyping can be improved by denoising the point cloud data, and the density of the point cloud can be effectively reduced by uniform downsampling, thereby significantly improving the efficiency of subsequent point cloud processing.

[0060] Optionally, after uniformly downsampling the noise-reduced point cloud data to determine simplified point cloud data, the method further includes:

[0061] Rotating the simplified point cloud data to determine standardized point cloud data;

[0062] The standardized point cloud data is positionally calibrated using a three-dimensional coordinate system, so as to segment the calibrated standardized point cloud data along a plane where the ground is located, thereby determining the target point cloud data.

[0063] The obtained simplified point cloud data includes crop point cloud, weed point cloud and ground point cloud in the target plot.

[0064] A coordinate system is established for the simplified point cloud data, where the y-axis is on the ground and points perpendicular to the track, the x-axis is on the ground and points parallel to the track, and the z-axis points perpendicular to the ground. The plane of the ground is the xoy plane.

[0065] The simplified point cloud data is a strip of point cloud data consisting of n planting plots and the ground. A ground point cloud is obtained using a Random Sample Consensus (RANSAC) plane fitting algorithm or a Cloth Simulation Filtering (CSF) algorithm. The normal of the ground point cloud is calculated as the direction of the z-axis. The principal components of the point cloud after removing the ground are calculated, with the direction of the first principal component as the x-axis and the second principal component as the y-axis. The entire point cloud is rotated until it aligns with the coordinate axes.

[0066] The point cloud after normalization is translated to the ground height of 0, and the ground point cloud data is removed, and the non-ground point cloud data is retained, so the crop group point cloud data is obtained, that is, the target point cloud data P original .

[0067] In the target point cloud data P original In the figure, the planting plots are arranged in a single row in the y-axis direction and at equal intervals in the x-axis direction, which is determined by the collection characteristics of the point cloud data by the track-type phenotyping platform.

[0068] According to the crop population phenotype acquisition method provided by the present invention, point cloud data on the ground can be obtained by calibrating and cutting point cloud data, providing a basis for analyzing the phenotype of the crops.

[0069] Furthermore, in step S2, the target point cloud data is segmented into three-dimensional point clouds according to the planting pattern of the crop groups in the target plot, and the crop point clouds of each planting plot are determined.

[0070] After obtaining the target point cloud data located above the ground after segmentation, the point cloud data can be cut using a sliding window in the x-axis direction and the y-axis direction according to the arrangement pattern of the planting pattern of the planting plot in the target point cloud data.

[0071] Different window determination strategies are used in the x-axis and y-axis directions, which may include:

[0072] In the y-axis direction, the sliding window can be two planes with a certain width, which are perpendicular to the y-axis. The width of the sliding window is equal to the side length of the planting area in the y-axis direction. The sliding window slides along the y-axis direction. For the point cloud inside the sliding window, the maximum value of the sum of the coordinates of all the point cloud data on the z-axis can be calculated as the basis for cutting. The point cloud data inside the sliding window at this time is retained, and the weed point cloud outside the planting area can be cut off in the direction perpendicular to the y-axis. On this basis, a second cutting is performed;

[0073] For the x-axis direction, multiple cell windows are set, and each cell window is two planes with a certain width. The order of the cell windows and the width of the cell windows are determined according to the side length of the planting cell in the x-axis direction. The distance between two adjacent cell windows is determined according to the interval between the two adjacent cells in the x-axis direction. The cell window group composed of each cell window slides along the x-axis direction. For the point cloud located inside each cell window, the standard deviation of the coordinates of all point cloud data on the z-axis can be calculated, and the position of the minimum value of the standard deviation is determined as the cutting basis. The point cloud data located inside each cell window at this time is retained as the cell crop point cloud of each planting cell, and the weed point cloud outside the planting cell can be cut off in the direction perpendicular to the x-axis.

[0074] Optionally, performing three-dimensional point cloud segmentation on the target point cloud data according to the planting pattern of the crop groups in the target plot to determine the crop point cloud of each planting plot includes:

[0075] Based on the plane where the ground is located in the three-dimensional coordinate system, the target point cloud data is segmented according to a preset step size to obtain a plurality of grid point cloud data;

[0076] Determine the highest point of each grid point cloud data in the direction perpendicular to the ground;

[0077] Based on the highest point of each grid point cloud data and the cell planting method of the crop group in the target plot, the target point cloud data is segmented to obtain the cell crop point cloud of each planting cell.

[0078] Specifically, the target point cloud data P is calculated respectively original The length l in the x-axis direction x , and the length l in the y-axis direction y ; Among them, the preset step size is based on the target point cloud data P original The length l of the bottom surface that coincides with the ground (xoy plane) on the x-axis x and the length l on the y-axis y Sure.

[0079] The target point cloud data P original Discretize on the ground (xoy plane). Set the number of point cloud divisions in the x-axis direction to n x , the number of point cloud segmentations in the y-axis direction is n y , then the step lengths in the x-axis and y-axis directions are s respectively x =l x / n x , s y =l y / n y . The point cloud is divided into the x-axis and y-axis directions according to s xand s y The entire point cloud is divided into n points on the xoy plane. x ×n y Then calculate the maximum value z of the z-axis of each grid point cloud data. max The point cloud is taken as the highest point.

[0080] The method for obtaining the phenotype of a crop population provided by the present invention can effectively reduce the difficulty of data processing by discretizing and segmenting point cloud data, thereby greatly improving the data processing speed while ensuring accuracy.

[0081] Optionally, segmenting the target point cloud data based on the highest point of each grid point cloud data and the cell planting pattern of the crop group in the target plot to obtain the cell crop point cloud of each planting cell includes:

[0082] Based on the highest point of each grid point cloud data, the target point cloud data is segmented using a sliding window to obtain crop group point cloud data;

[0083] Based on the highest point of each grid point cloud data in the crop group point cloud data, the crop group point cloud data is segmented using a cell window group to determine the cell crop point cloud of each planting cell; the sliding window and cell window group are determined based on the cell planting method, as well as the size and position relationship of the planting cell.

[0084] The grids in the same row or column are grouped into a strip.

[0085] In the direction perpendicular to the y-axis, calculate the maximum height of the highest point of all grids on each strip on the z-axis. For example, on the first strip, there are n x grid, find this n x The maximum value of the highest point of the grid on the z-axis is taken as the maximum height of the first strip perpendicular to the y-axis. Similarly, we can get n y The maximum height.

[0086] For example, the length of each planting area of ​​the crop group in the target plot in the y-axis direction is d y To avoid missing some point clouds, the planting area covers the number of grids N in the y-axis direction. y =d y / s y +1, and N y <n y . With N yThe width of the sliding window is n grids. By moving the sliding window along the y-axis, the target point cloud data is traversed in the direction perpendicular to the y-axis, and the average of the maximum heights in the sliding window at each position is found. The number of times the sliding window is moved is n. y -N y , the single moving distance is s y . Then in the sliding window n y -N y In the point cloud intercepted by the movement, the average of the maximum height of each time is calculated, and the range covered by the sliding window corresponding to the maximum average height is determined, that is, the point cloud area of ​​the crop group perpendicular to the y-axis direction.

[0087] Figure 2 This is a schematic diagram of point cloud cutting provided by the present invention, such as Figure 2 As shown, all point clouds outside the sliding window are removed, and the point cloud cutting perpendicular to the y-axis direction is completed. The obtained crop group point cloud data is recorded as P strip ,for Figure 2 The point cloud within the dotted area delineated in .

[0088] The crop group point cloud data P perpendicular to the y-axis direction obtained by segmentation strip After that, it is also necessary to convert the crop group point cloud data P strip Cut into small crop point clouds, that is, perform point cloud segmentation in the direction perpendicular to the x-axis. Suppose the crop group point cloud data P strip There are n crop population plots in Figure 2 In, n=7.

[0089] Calculate crop group point cloud data P strip The standard deviation h of the height values ​​of the highest points of all grids in each strip perpendicular to the x-axis std For example, there are n y grid, find this n y The standard deviation of the height values ​​of the highest points of the grids on the z-axis is used as the height value of the first strip perpendicular to the x-axis. Similarly, we can get n x A height value.

[0090] For example, let the length of each cell in the x-axis direction be d x , the distance between adjacent cell centers is d PP To avoid missing some point clouds, the number of grids covered by each cell in the direction perpendicular to the x-axis is N. x =d x / s x +1, and N x <n x .

[0091] Suppose there are n length dx The distance between the center points of adjacent cell windows is d PP , group these n windows into a cell window group. This cell window group slides in the x-axis direction, sliding one grid each time. Calculate the standard deviation h of the height values ​​of the cell window coverage area of ​​each cell window group during each sliding std The mean value of i , the large window can slide t=(d PP -d x ) / s x times, 1≤i≤t. From t w i Find w i The position corresponding to the smallest cell window group is the cutting position. After the cutting is completed, n cells can be obtained. Figure 2 Point cloud of the crop plot in the solid line area.

[0092] According to the crop population phenotype acquisition method provided by the present invention, crops in the target point cloud data are located by means of a sliding window, and the point cloud of each planting area can be accurately and quickly segmented, thereby providing a basis for obtaining the crop phenotype.

[0093] Furthermore, in step S3, phenotypic analysis is performed on the crop point cloud of each planting plot to obtain the phenotype of the crops in the target plot.

[0094] The crop point cloud of each planting plot is divided according to the spacing between plants. After the division, Danyun can analyze the crop phenotype. The crop can be a single plant or a cluster, which can be determined by the planting method and the spacing between plants.

[0095] Optionally, performing phenotypic analysis on the crop point cloud of each planting plot to obtain the phenotype of the crops in the target plot includes:

[0096] According to the plant-row spacing of the crop groups in each planting plot, the crop point cloud of each planting plot is grid-divided to determine the grid point cloud of a single plant;

[0097] Determine the highest point perpendicular to the ground in the grid point cloud of the single plant as the maximum plant height;

[0098] The phenotype of the crops in the target plot is determined according to the maximum plant height of each single plant grid point cloud.

[0099] After obtaining the crop point cloud of each planting plot, the crop point cloud of each plot is used to extract the phenotype, which mainly includes four dimensions: maximum plant height, average plant height, uniformity and coverage.

[0100] According to the plant spacing in each planting area, the crop point cloud of each planting area is gridded again so that each grid contains a plant. The maximum value of the point cloud in each grid on the z-axis is calculated, and the maximum value is used as the plant height of the plant in the current grid.

[0101] According to the plant height in each grid, the maximum plant height in the entire planting area can be taken as the maximum plant height;

[0102] You can also set a certain percentage of the maximum plant height as a threshold, for example, 50%. If the plant height value in a grid is less than the threshold, it is considered that the crop in the grid is not growing normally and is not included in the calculation of the average plant height. The remaining grids are considered valid grids. The average value of the plant heights of the valid grids is the average plant height.

[0103] Calculate the standard deviation of plant height of all grids, which is the uniformity.

[0104] In addition, the point cloud in each grid is projected onto the xoy plane. If there is a point in the grid, it is not empty. The number of non-empty grids is counted and divided by the total number of grids, which is the coverage of the current planting area.

[0105] The crop population phenotypic acquisition method provided by the present invention automatically segments the point cloud data obtained based on the track-based phenotyping platform to obtain point cloud data containing only the crops in each planting area, thereby quickly analyzing the crop phenotypes, thereby realizing automated, batch processing and analysis of the high-time-series point cloud data obtained by the phenotyping platform.

[0106] The following describes the device for obtaining the phenotype of a crop population provided by the present invention. The device for obtaining the phenotype of a crop population described below and the method for obtaining the phenotype of a crop population described above can be referred to in correspondence with each other.

[0107] Figure 3 Schematic diagram of the structure of the crop population phenotype acquisition device provided by the present invention, such as Figure 3 Shown, including:

[0108] An acquisition module 301 is used to acquire target point cloud data of a crop group in a target plot;

[0109] The segmentation module 302 is used to perform three-dimensional point cloud segmentation on the target point cloud data according to the planting pattern of the crop group in the target plot, and determine the crop point cloud of each planting plot;

[0110] The parsing module 303 is configured to perform phenotypic analysis on the crop point cloud of each planting plot to obtain the phenotype of the crops in the target plot.

[0111] During the operation of the device, the acquisition module 301 acquires the target point cloud data of the crop group in the target plot; the segmentation module 302 performs three-dimensional point cloud segmentation on the target point cloud data according to the planting method of the crop group in the target plot, and determines the crop point cloud of each planting plot; the analysis module 303 performs phenotypic analysis on the crop point cloud of each planting plot to obtain the phenotype of the crops in the target plot.

[0112] The crop population phenotypic acquisition device provided by the present invention automatically segments the point cloud data obtained based on the track-based phenotyping platform, thereby obtaining point cloud data containing only the crops in each planting area, and then quickly analyzing the crop phenotypes, thereby realizing automated, batch processing and analysis of the high-time-series point cloud data obtained by the phenotyping platform.

[0113] Figure 4 Schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other via the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute a method for obtaining a phenotype of a crop population, the method comprising: obtaining target point cloud data of a crop population within a target plot; performing three-dimensional point cloud segmentation on the target point cloud data based on the planting pattern of the crop population within the target plot to determine a crop point cloud for each planting plot; and performing phenotypic analysis on the crop point cloud for each planting plot to obtain the phenotype of the crops within the target plot.

[0114] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0115] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the crop population phenotypic acquisition method provided by the above methods, which includes: obtaining target point cloud data of the crop population in the target plot; performing three-dimensional point cloud segmentation on the target point cloud data according to the cell planting method of the crop population in the target plot, and determining the cell crop point cloud of each planting cell; performing phenotypic analysis on the cell crop point cloud of each planting cell to obtain the phenotype of the crop in the target plot.

[0116] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the crop population phenotypic acquisition method provided by the above-mentioned methods, the method comprising: obtaining target point cloud data of the crop population in the target plot; performing three-dimensional point cloud segmentation on the target point cloud data according to the cell planting method of the crop population in the target plot, and determining the cell crop point cloud of each planting cell; performing phenotypic analysis on the cell crop point cloud of each planting cell, and obtaining the phenotype of the crops in the target plot.

[0117] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0118] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0119] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for obtaining phenotypes of a crop population, characterized in that: include: Obtain target point cloud data of crop groups within the target plot; According to the planting pattern of the crop groups in the target plot, the target point cloud data is segmented into three-dimensional point clouds to determine the crop point clouds of each planting plot; Performing phenotypic analysis on the crop point cloud of each planting plot to obtain the phenotype of the crops in the target plot; The step of obtaining target point cloud data of a crop group in a target plot includes: Acquire initial point cloud data of the target plot; the initial point cloud data is collected by the track-type phenotyping platform on the target plot; Performing noise reduction processing on the initial point cloud data to determine noise-reduced point cloud data; uniformly downsampling the noise-reduced point cloud data to determine simplified point cloud data to obtain the target point cloud data; After uniformly downsampling the noise-reduced point cloud data to determine simplified point cloud data, the method further includes: Rotating the simplified point cloud data to determine standardized point cloud data; Using a three-dimensional coordinate system, positionally calibrating the standardized point cloud data, segmenting the calibrated standardized point cloud data along a plane where the ground lies, and determining the target point cloud data; The step of performing three-dimensional point cloud segmentation on the target point cloud data according to the planting pattern of the crop groups in the target plot to determine the crop point cloud of each planting plot includes: Based on the plane where the ground is located in the three-dimensional coordinate system, the target point cloud data is segmented according to a preset step size to obtain a plurality of grid point cloud data; Determine the highest point of each grid point cloud data in the direction perpendicular to the ground; Segmenting the target point cloud data based on the highest point of each grid point cloud data and the cell planting pattern of the crop group in the target plot to obtain a cell crop point cloud of each planting cell; The target point cloud data is segmented based on the highest point of each grid point cloud data and the planting pattern of the crop group in the target plot to obtain the crop point cloud of each planting plot, including: Based on the highest point of each grid point cloud data, the target point cloud data is segmented using a sliding window to obtain crop group point cloud data; Based on the highest point of each grid point cloud data in the crop group point cloud data, the crop group point cloud data is segmented using a cell window group to determine the cell crop point cloud of each planting cell; the sliding window and cell window group are determined based on the cell planting method, as well as the size and position relationship of the planting cell.

2. The method for obtaining phenotypes of a crop population according to claim 1, wherein: The performing phenotypic analysis on the crop point cloud of each planting plot to obtain the phenotype of the crop in the target plot includes: According to the plant-row spacing of the crop groups in each planting plot, the crop point cloud of each planting plot is grid-divided to determine the grid point cloud of a single plant; Determine the highest point perpendicular to the ground in the grid point cloud of the single plant as the maximum plant height; The phenotype of the crops in the target plot is determined according to the maximum plant height of each single plant grid point cloud.

3. A device for obtaining phenotypes of crop populations, characterized in that: include: An acquisition module is used to obtain target point cloud data of crop groups within a target plot; A segmentation module is used to perform three-dimensional point cloud segmentation on the target point cloud data according to the planting pattern of the crop groups in the target plot, and determine the crop point cloud of each planting plot; An analysis module is used to perform phenotypic analysis on the crop point cloud of each planting plot to obtain the phenotype of the crop in the target plot; The step of obtaining target point cloud data of a crop group in a target plot includes: Acquire initial point cloud data of the target plot; the initial point cloud data is collected by the track-type phenotyping platform on the target plot; Performing noise reduction processing on the initial point cloud data to determine noise-reduced point cloud data; uniformly downsampling the noise-reduced point cloud data to determine simplified point cloud data to obtain the target point cloud data; After uniformly downsampling the noise-reduced point cloud data to determine simplified point cloud data, the method further includes: Rotating the simplified point cloud data to determine standardized point cloud data; Using a three-dimensional coordinate system, positionally calibrating the standardized point cloud data, segmenting the calibrated standardized point cloud data along a plane where the ground lies, and determining the target point cloud data; The step of performing three-dimensional point cloud segmentation on the target point cloud data according to the planting pattern of the crop groups in the target plot to determine the crop point cloud of each planting plot includes: Based on the plane where the ground is located in the three-dimensional coordinate system, the target point cloud data is segmented according to a preset step size to obtain a plurality of grid point cloud data; Determine the highest point of each grid point cloud data in the direction perpendicular to the ground; Segmenting the target point cloud data based on the highest point of each grid point cloud data and the cell planting pattern of the crop group in the target plot to obtain a cell crop point cloud of each planting cell; The target point cloud data is segmented based on the highest point of each grid point cloud data and the planting pattern of the crop group in the target plot to obtain the crop point cloud of each planting plot, including: Based on the highest point of each grid point cloud data, the target point cloud data is segmented using a sliding window to obtain crop group point cloud data; Based on the highest point of each grid point cloud data in the crop group point cloud data, the crop group point cloud data is segmented using a cell window group to determine the cell crop point cloud of each planting cell; the sliding window and cell window group are determined based on the cell planting method, as well as the size and position relationship of the planting cell.

4. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for obtaining the phenotype of a crop population as claimed in claim 1 or 2 is implemented.

5. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for obtaining the phenotype of a crop population as claimed in claim 1 or 2 is implemented.

6. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for obtaining the phenotype of a crop population as claimed in claim 1 or 2 is implemented.

Images