Corn ear height measurement method, device, system and storage medium

Abstract

The present application provides a kind of corn ear site height measurement method, device, system and storage medium, the method comprises: obtaining the three-dimensional point cloud information of corn vegetation in target area;Height stratification and voxel processing are carried out to the three-dimensional point cloud information, determine the voxel of each height layer containing point cloud information and all voxels of each height layer;Based on the number of the containing point cloud information voxels of each height layer and the number of all voxels of each height layer, determine the leaf area density of each height layer;Based on the height of the height layer corresponding to the maximum value in the leaf area density of each layer, determine the corn ear site height of the target area.The present application can effectively determine the corn ear site height of target area, can greatly improve the efficiency of corn ear site height measurement, effectively realizes the high-throughput rapid measurement of corn ear site height.

Description

Technical Field

[0001] This invention relates to the field of machine vision inspection technology, and in particular to a method, apparatus, system and storage medium for measuring the height of corn ears. Background Technology

[0002] Ear height in maize refers to the height from the ground to the bottom of the uppermost ear of the maize plant. It is one of the important agronomic traits that constitute maize plant architecture and an important indicator in the DUS (Discretionary Unit Testing) of maize varieties. In maize breeding, breeders need to conduct high-throughput phenotypic measurements of ear height on a large scale in breeding plots to help them screen for ideal phenotypic traits.

[0003] Currently, existing methods for measuring the height of corn ears include: (1) ruler: relying on manual sampling with rulers for measurement, which is the mainstream method at present, but the sample representativeness is poor, the workload is large, time-consuming and labor-intensive, the efficiency is low and the subjectivity is strong; (2) portable sensor: using handheld sensors to measure the height of ears, relying on the automatic identification of ears and recording the distance from the sensor to the ground to measure the height of ears; (3) unmanned vehicle: using unmanned vehicles in the field equipped with some visible light or depth cameras, using image recognition or target detection methods to identify ears and determine the height of ears. This method requires reserving a dedicated driving lane for unmanned vehicles, consuming additional land area. The latter two schemes are both limited by the effect of ear target detection. When corn leaves cover the ears or the ears are the same color as the leaves, the accuracy of target detection will be directly affected. The above three methods have low operating efficiency and low measurement accuracy, which restricts the large-scale development of corn breeding and delays the discovery and breeding cycle of new varieties.

[0004] Therefore, how to effectively achieve high-throughput and rapid measurement of corn ear height has become a technical problem that the industry urgently needs to solve. Summary of the Invention

[0005] This invention provides a method, apparatus, system, and storage medium for measuring the height of corn ears, which can effectively achieve high-throughput and rapid measurement of the height of corn ears.

[0006] This invention provides a method for measuring the height of a maize ear, comprising:

[0007] Obtain three-dimensional point cloud information of corn vegetation within the target area;

[0008] The three-dimensional point cloud information is subjected to height layering and voxelization to determine the voxels containing point cloud information in each height layer and all voxels in each height layer.

[0009] Based on the number of voxels containing point cloud information in each altitude layer and the total number of all voxels in each altitude layer, the leaf area density of each altitude layer is determined.

[0010] The height of the corn ear in the target area is determined based on the height of the height layer corresponding to the maximum value of the leaf area density in each layer.

[0011] According to a method for measuring the ear height of maize provided by the present invention, after determining the leaf area density of each height layer based on the number of voxels containing point cloud information and the total number of all voxels in each height layer, the method further includes:

[0012] The leaf area density at each height level is fitted to obtain the vertical leaf area density distribution curve of the target area.

[0013] The maximum leaf area density is determined based on the vertical leaf area density distribution curve.

[0014] The ear height of the maize in the target area is determined based on the height layer corresponding to the maximum leaf area density.

[0015] According to a method for measuring the height of maize ears provided by the present invention, determining the height of maize ears in a target area based on the height layer corresponding to the maximum leaf area density includes:

[0016] Determine the layer number of the height layer corresponding to the maximum leaf area density and the maize plant height in the target area;

[0017] The target height is determined based on the layer number, the corn plant height in the target area, and the total number of layers in the three-dimensional point cloud information. The target height is then corrected based on a preset layer threshold and a preset deviation value to obtain the corn ear height in the target area.

[0018] According to a method for measuring the height of maize ears provided by the present invention, a target height is determined based on the layer number, the maize plant height in the target area, and the total number of layers of the three-dimensional point cloud information. The target height is then corrected based on a preset layer threshold and a preset deviation value to obtain the height of maize ears in the target area. The method includes:

[0019] Using the following formula:

[0020] The corn ear height in the target area was obtained;

[0021] Where EH represents the corn ear height in the target area, and H max The target area represents the maize plant height; ΔH represents the preset stratification threshold; C represents the preset deviation value, which is the deviation between the height of the height layer corresponding to the maximum leaf area density and the actual ear height, and is related to the maize variety; L (LAD(max)) L represents the number of the height layer corresponding to the maximum leaf area density, and L represents the total number of layers of the three-dimensional point cloud information.

[0022] According to a method for measuring the height of maize ears provided by the present invention, before acquiring the three-dimensional point cloud information of maize vegetation within the target area, the method further includes:

[0023] Acquire the original three-dimensional point cloud information of the monitoring area; the original three-dimensional point cloud information is the original point cloud information under multiple different flight paths;

[0024] The original 3D point cloud information is processed to obtain 3D point cloud information in the target format;

[0025] Data registration is performed on the target format three-dimensional point cloud information under each route to obtain the registered three-dimensional point cloud information;

[0026] According to preset boundary conditions, the registered 3D point cloud information is segmented into regions to obtain the 3D point cloud information in each target region.

[0027] Ground point cloud filtering is performed on the three-dimensional point cloud information in each of the target areas to obtain the three-dimensional point cloud information of corn vegetation in each of the target areas.

[0028] According to a method for measuring the ear height of maize provided by the present invention, the leaf area density of each height layer is determined by the following formula:

[0029]

[0030] Where, n I (k) represents the number of voxels containing point cloud information in the k-th height layer; n T (k) represents the number of all voxels in the k-th height layer; ΔH represents the preset layer threshold; θ represents the incident angle of the laser beam used to measure the point cloud information.

[0031] The present invention also provides a device for measuring the height of corn ears, comprising:

[0032] The acquisition module is used to acquire three-dimensional point cloud information of corn vegetation within the target area;

[0033] The layering module is used to perform height layering and voxelization processing on the three-dimensional point cloud information, and to determine the voxels containing point cloud information in each height layer and all voxels in each height layer.

[0034] The first processing module is used to determine the leaf area density of each height layer based on the number of voxels containing point cloud information and the total number of all voxels in each height layer.

[0035] The second processing module is used to determine the corn ear height in the target area based on the height of the height layer corresponding to the maximum value of the leaf area density in each layer.

[0036] The present invention also provides a corn ear height measurement system, comprising:

[0037] A drone equipped with a lidar sensor and a data processing module;

[0038] The drone equipped with lidar is used to acquire three-dimensional point cloud information of the monitoring area and send the three-dimensional point cloud information of the monitoring area to the data processing module;

[0039] The data processing module includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements any of the corn ear height measurement methods described above.

[0040] 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 the corn ear height measurement method as described above.

[0041] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the corn ear height measurement method as described above.

[0042] The method, apparatus, system, and storage medium for measuring corn ear height provided by this invention fully explore the growth pattern of corn ears and utilize the characteristic that the leaves growing at the location of the corn ear have the largest leaf area. By using a drone equipped with lidar for measurement, three-dimensional point cloud information of corn vegetation in the target area can be obtained. By performing height layering and voxelization processing on the three-dimensional point cloud information, and using the number of voxels containing point cloud information in each height layer and the total number of voxels in each height layer, the leaf area density of each vertically distributed height layer can be obtained. Thus, the height of the corn ear in the target area can be effectively determined based on the height layer corresponding to the maximum value of the leaf area density in each layer. This can significantly improve the efficiency of corn ear height measurement and effectively realize high-throughput and rapid measurement of corn ear height. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0044] Figure 1 This is a flowchart illustrating the method for measuring the height of corn ears provided by the present invention;

[0045] Figure 2This is a schematic diagram of the structure of the corn ear height measuring device provided by the present invention;

[0046] Figure 3 This is a schematic diagram of the physical structure of the data processing module in the corn ear height measurement system provided by the present invention. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0048] In the description of the invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0049] The following is combined Figures 1-3 The present invention describes a method, apparatus, system, and storage medium for measuring the height of corn ears.

[0050] Figure 1 This is a flowchart illustrating the method for measuring the height of corn ears provided by the present invention, as shown below. Figure 1 As shown, it includes steps 110, 120, 130 and 140.

[0051] Step 110: Obtain the three-dimensional point cloud information of corn vegetation within the target area;

[0052] Specifically, the target area described in this embodiment of the invention refers to a local corn-growing area used for monitoring the height of corn ears, where the corn plants are growing at a relatively uniform rate. Specifically, it can be an area measuring 3.6 meters × 2.5 meters.

[0053] In an embodiment of the present invention, the maize breeding base can be divided into breeding plots, each of which can be used as a target area. The size of the breeding plot can be set to 3.6m × 2.5m, with a plot spacing of 1.5m.

[0054] In an embodiment of the present invention, a corn ear height measurement system is provided, comprising: a drone equipped with a LiDAR radar and a data processing module; the drone equipped with the LiDAR radar is used to acquire three-dimensional point cloud information of the monitoring area and send the three-dimensional point cloud information of the monitoring area to the data processing module for processing. By using remote sensing and a drone with LiDAR, it is possible to acquire the vertical distribution of leaf area in various target areas.

[0055] In an embodiment of the present invention, during the corn tasseling stage, a drone equipped with a LiDAR (LiDAR radar) can acquire three-dimensional point cloud data of the target area. The drone LiDAR system mainly consists of four parts: the drone, the LiDAR, the antenna (for acquiring satellite signals), and the base station. The data acquisition parameters of the drone LiDAR can be set as follows: drone flight altitude of 15m, speed of 3.5m / s, laser pulse emission frequency of 550kHz, spot divergence of 0.35mrad, and field of view of 330°. A suitable flight path is selected to ensure the laser pulse incident angle is within (-40°, 40°), guaranteeing a point cloud density of no less than 100 points / m². 2 .

[0056] Based on the above embodiments, as an optional embodiment, before acquiring the three-dimensional point cloud information of maize vegetation within the target area, the method further includes:

[0057] Acquire the original 3D point cloud information of the monitoring area; the original 3D point cloud information consists of original point cloud information under multiple different flight paths.

[0058] The original 3D point cloud information is processed to obtain the 3D point cloud information in the target format;

[0059] Data registration is performed on the target format three-dimensional point cloud information under each route to obtain the registered three-dimensional point cloud information;

[0060] According to the preset boundary conditions, the registered 3D point cloud information is segmented into regions to obtain the 3D point cloud information in each target region.

[0061] Ground point cloud filtering is performed on the 3D point cloud information of each target area to obtain the 3D point cloud information of corn vegetation in each target area.

[0062] Specifically, the monitoring area described in the embodiments of the present invention refers to the global maize planting area used to monitor the ear height of maize, which may include multiple target areas, and each target area can be measured as a breeding plot.

[0063] The preset boundary conditions described in the embodiments of the present invention are determined based on the coordinate positions of the boundaries of each target region and can be used to characterize the boundaries of each target region.

[0064] In an embodiment of the present invention, laser point cloud data is generated by using a drone equipped with a LiDAR to measure and obtain the original three-dimensional point cloud information of the monitoring area under multiple different flight paths.

[0065] Furthermore, by performing data preprocessing on the original three-dimensional point cloud information of the monitoring area, including data calculation, registration of data from different flight paths, cell segmentation, and ground point filtering, three-dimensional point cloud information of maize vegetation in each breeding cell can be obtained.

[0066] Specifically, the process begins with data processing of the raw 3D point cloud information of the monitoring area, which includes two steps: trajectory calculation and raw laser data processing. Precise drone trajectory data is obtained by differential calculation and inverse calculation of GPS base station data and UAV POS RAW data. Then, laser point cloud data processing software is used to process the raw laser data, i.e., the raw 3D point cloud information, including waveform calculation, trajectory data matching, and 3D point cloud visualization. Finally, the data is exported as LAS format point cloud data to obtain the target format 3D point cloud information.

[0067] Then, the data registration operation for different flight paths is performed. By registering the 3D point cloud information of the target format under different flight paths of the UAV, the registered 3D point cloud information is determined, and complete point cloud data under the same coordinates is obtained.

[0068] Further, cell segmentation is performed. Based on the registered 3D point cloud information and according to preset boundary conditions, vector boundary lines of each target region are drawn, and the boundary lines and point cloud data are adjusted to be at the same height. Then, cell segmentation is performed on the point cloud data of each flight path in batches in the laser point cloud data processing software to perform regional segmentation of the point cloud data and obtain the 3D point cloud information of each target region.

[0069] Furthermore, ground point filtering is performed. In an embodiment of the present invention, a Cloth Simulation Filter (CSF) algorithm is used to perform ground point cloud filtering on the three-dimensional point cloud information in each target area, separating the corn vegetation point cloud information and the ground point cloud information in the three-dimensional point cloud information, thereby obtaining the three-dimensional point cloud information of corn vegetation in each target area.

[0070] The method of this invention, through data preprocessing operations such as data calculation, registration of different flight path data, cell segmentation and ground point filtering on the raw three-dimensional point cloud data obtained by LiDAR measurement, can ensure the accuracy of the three-dimensional point cloud information of maize vegetation in each target area, provide reliable data for subsequent calculation of maize ear height in the target area, and help improve the accuracy of maize ear height measurement.

[0071] Step 120: Perform height layering and voxelization processing on the three-dimensional point cloud information of maize vegetation in the target area to determine the voxels containing point cloud information in each height layer and all voxels in each height layer.

[0072] Specifically, in embodiments of the present invention, the three-dimensional point cloud information of maize vegetation within a target area can be hierarchically segmented according to a preset segmentation threshold. The preset segmentation threshold can be set to 5 cm to 10 cm. This allows the maize plant height to be horizontally divided into multiple height layers.

[0073] Furthermore, in an embodiment of the present invention, the three-dimensional point cloud information of corn vegetation in the target area is voxelized. The voxel size can be set according to a preset layering threshold. For example, if the preset layering threshold is set to 5 cm, the voxel size can also be set to 5 cm.

[0074] Specifically, in an embodiment of the present invention, the three-dimensional point cloud information of corn vegetation within the target area can be divided into i×j×s voxel grids of size Δi×Δj×Δs based on the boundary of the point cloud data using formula (1). Then, it is determined whether each grid contains point cloud information; grids containing point cloud information are represented as 1, and grids without point cloud information are represented as 0. The grids without point cloud information represent the pore spaces in the vegetation canopy. The voxel size can be set to 5 cm, then Δi = Δj = Δs = 5 cm.

[0075]

[0076] Therefore, by performing height-level layering and voxelization processing on the three-dimensional point cloud information of maize vegetation in the target area using the above method, we can obtain voxels containing point cloud information in each height layer and all voxels in each height layer.

[0077] Step 130: Determine the leaf area density (LAD) of each height layer based on the number of voxels containing point cloud information and the total number of voxels in each height layer.

[0078] Specifically, in embodiments of the present invention, after obtaining the voxels containing point cloud information at each height layer and all voxels at each height layer, the number of voxels containing point cloud information at each height layer and the number of all voxels at each height layer can be counted. It is understood that the number of all voxels at each height layer is equal to the sum of the number of voxels containing point cloud information at each height layer and the number of voxels not containing point cloud information at each height layer.

[0079] Based on the above embodiments, the leaf area density of each height layer can be determined by the following formula (2):

[0080]

[0081] Where, n I (k) represents the number of voxels containing point cloud information in the k-th height layer; n T (k) represents the number of voxels in the k-th height layer; ΔH represents the preset layer threshold, which can characterize the horizontal layer thickness as a leaf area density distribution; θ represents the incident angle of the laser beam used to measure point cloud information, i.e., the angle between the direction of the laser pulse emitted by the LiDAR and the zenith direction; the unit of LAD is meters. 2 / m 3 .

[0082] The method of this invention, by performing layering and voxelization processing on point cloud data, can effectively determine the vertical leaf area distribution characteristics of maize based on the distribution of voxels containing point cloud information in each layer, thereby improving the accuracy of leaf area density calculation results.

[0083] Step 140: Determine the ear height of the maize in the target area based on the height of the height layer corresponding to the maximum value of the leaf area density in each layer.

[0084] It should be noted that, based on the growth pattern of corn, the leaves at the ear position are the widest and longest, with the largest leaf area. The ear-position leaf and the leaves above and below it are called the "three-leaf head," which have the largest leaf area, the strongest photosynthetic activity, and the longest functional period, coinciding with the grain formation period. Therefore, from top to bottom, the leaf area of ​​a corn plant gradually increases, reaching its maximum at the ear position, and then gradually decreases. In other words, the position of the largest leaf area on a single corn plant often corresponds to the position of the corn ear.

[0085] In an embodiment of the present invention, based on the agronomic laws of maize cultivation, the characteristic that the leaves (three-leaf clumps) growing at the location of the maize ear have the largest leaf area is utilized. By calculating the distribution of vertical leaf area density of maize, the three-leaf clumps layer corresponding to the maximum leaf area density is found, thereby accurately measuring the height of the maize ear in the target area.

[0086] Furthermore, after obtaining the leaf area density of each height layer, the discrete distribution of the leaf area density of each height layer can be determined. By determining the height of the height layer corresponding to the maximum value from the leaf area density of each layer, the ear height of the maize in the target area can be directly obtained.

[0087] In an embodiment of the present invention, after obtaining the measurement results of the corn ear height in each target area of ​​the monitoring area, different colored stripes can be assigned to the target areas to represent different corn ear heights based on the measurement results of the corn ear height in each target area, thereby realizing spatial mapping of corn ear height and facilitating breeders to intuitively obtain the results of high-throughput phenotypic measurement of corn ear height.

[0088] In this embodiment of the invention, by fully exploring the agronomical patterns of maize cultivation and employing remote sensing techniques, specifically a UAV LiDAR, the vertical distribution of leaf area in each breeding plot can be acquired, enabling high-throughput measurement of maize ear height in the breeding plots. This method does not require complex individual ear identification and positioning; instead, it utilizes the point cloud statistical information of the breeding plot population to determine the average ear height of the breeding plot. Furthermore, this method relies on acquiring the vertical leaf area density distribution of maize; the UAV LiDAR point cloud data can effectively reflect the vertical leaf area distribution of maize, improving the accuracy of ear height extraction.

[0089] In an embodiment of the present invention, by comparing the measured ear height with that of a certain year, the accuracy of the measurement method of the present invention can reach R. 2 =0.59, the root mean square error (RMSE) can reach 14.90 cm; two years later, a comparison with the measured ear height was conducted to verify that the accuracy can reach R 2 =0.39, and the root mean square error (RMSE) can reach 18.40cm.

[0090] In this embodiment of the invention, based on the rule that the location of the maximum vertical leaf area density is the same as the location of the ear, a method of "determining the ear by leaf" is proposed. This method uses a drone LiDAR to monitor the height of the maximum leaf area density and then measures the ear height of the maize breeding plot in a high-throughput manner.

[0091] The method described in this invention is of great significance for improving the ear height trait of maize, developing targeted breeding programs, and breeding high-yield maize.

[0092] Furthermore, with the continuous reduction in the price of drones and LiDAR sensors, this method provides a good solution for high-throughput rapid measurement of ear height. It can serve maize breeding in a low-cost, efficient, and accurate manner, enabling breeding experts to quickly obtain phenotypic information on ear height. Based on this information, gene association analysis can be performed to locate the gene for optimal maize ear height, thereby accelerating the maize breeding process and improving breeding efficiency and level. It has good application prospects and huge market value.

[0093] The method for measuring the height of corn ears provided in this invention fully explores the growth pattern of corn ears and utilizes the characteristic that the leaves growing at the location of the corn ear have the largest leaf area. By using a drone equipped with a lidar, it can acquire three-dimensional point cloud information of corn vegetation in the target area. By performing height layering and voxelization processing on the three-dimensional point cloud information, and using the number of voxels containing point cloud information in each height layer and the total number of voxels in each height layer, the leaf area density of each vertically distributed height layer can be obtained. Thus, based on the height of the height layer corresponding to the maximum value of the leaf area density in each layer, the height of corn ears in the target area can be effectively determined, which can significantly improve the efficiency of corn ear height measurement and effectively realize high-throughput rapid measurement of corn ear height.

[0094] Based on the above embodiments, as an optional embodiment, after determining the leaf area density of each altitude layer based on the number of voxels containing point cloud information and the total number of voxels in each altitude layer, the method further includes:

[0095] By fitting the leaf area density at each height level, the vertical leaf area density distribution curve of the target area is obtained.

[0096] The maximum leaf area density is determined based on the vertical leaf area density distribution curve;

[0097] The ear height of maize in the target area is determined based on the height layer corresponding to the maximum leaf area density.

[0098] Specifically, the vertical leaf area density distribution curve described in the embodiments of the present invention refers to a curve used to characterize the vertical leaf area density distribution of maize in the target area.

[0099] In an embodiment of the present invention, after determining the leaf area density of each height layer based on the number of voxels containing point cloud information and the total number of voxels in each height layer, the information of the discrete distribution of leaf area density of each height layer is obtained. By fitting the leaf area density of each height layer, the continuous distribution of leaf area density of each height layer can be obtained, and the vertical leaf area density distribution curve of the target area is obtained.

[0100] It should be noted that the fitting algorithm used in the embodiments of the present invention may be a bispline curve fitting algorithm, a polynomial fitting algorithm, or other algorithms that can perform curve fitting. The present invention does not specifically limit these algorithms.

[0101] Optionally, in an embodiment of the present invention, the vertical leaf area density distribution curve of each breeding plot is obtained by fitting a double spline curve based on the leaf area density at different heights.

[0102] Furthermore, based on the vertical leaf area density distribution curve, the first peak of the curve from top to bottom is identified to determine the maximum leaf area density. Based on the height layer corresponding to the maximum leaf area density, the ear height of the maize in the target area can be effectively determined.

[0103] The method of this invention obtains the vertical leaf area density distribution curve of the target area by fitting the discrete distribution information of leaf area density at each height layer, and extracts corn ear height data based on the vertical leaf area density distribution curve, which can effectively improve the accuracy of corn ear height measurement.

[0104] Based on the above embodiments, as an optional embodiment, determining the ear height of maize in a target area based on the height layer corresponding to the maximum leaf area density includes:

[0105] Determine the layer number corresponding to the height layer with the maximum leaf area density and the maize plant height in the target area;

[0106] The target height is determined based on the layer number, the corn plant height in the target area, and the total number of layers in the 3D point cloud information. The target height is then corrected based on the preset layer threshold and preset deviation value to obtain the corn ear height in the target area.

[0107] It should be noted that maize plant height refers to the length from the ground to the highest point of the leaves when they are naturally extended before tasseling, and the height from the ground to the tip of the tassel after tasseling. Maize plant height is one of the most important plant type traits, which has a significant impact on maize growth, photosynthesis, lodging resistance, and harvesting by agricultural machinery. It is one of the key factors determining maize yield, and it can be measured and calculated using existing remote sensing technology.

[0108] Specifically, the target height described in this embodiment of the invention refers to the estimated height of the maize ear height calculated based on the determined maximum leaf area density. It can be calculated based on the parameter relationship between the layer number corresponding to the maximum leaf area density, the maize plant height in the target area, and the total number of layers in the three-dimensional point cloud information.

[0109] The preset deviation value described in the embodiments of the present invention refers to the deviation between the height of the height layer corresponding to the maximum leaf area density and the actual ear height. It is related to the corn variety. In other words, different and appropriate preset deviation values ​​can be selected for different corn varieties.

[0110] Since the target height is based on the middle of the corn ear as a reference point, and the growth posture of the corn ears in the target area is not the same, the target height needs to be further corrected in order to accurately calculate the height of the corn ears in the target area.

[0111] In an embodiment of the present invention, the target height is calculated based on the number of the height layer corresponding to the maximum leaf area density, the corn plant height in the target area, and the total number of layers of the three-dimensional point cloud information. The target height is then further corrected based on a preset layering threshold and a preset deviation value.

[0112] Based on the above embodiments, the target height is determined according to the layer number, the corn plant height in the target area, and the total number of layers of the 3D point cloud information. The target height is then corrected based on a preset layer threshold and a preset deviation value to obtain the corn ear height in the target area, including:

[0113] By using the following formula (3):

[0114] The height of the corn ears in the target area was obtained;

[0115] Where EH represents the ear height of the maize in the target area, and H represents the ear height in the target area. max ΔH represents the maize plant height in the target area; ΔH represents the preset stratification threshold, which characterizes the thickness of the 3D point cloud information stratification in the target area; C represents the preset deviation value, which represents the deviation between the height of the height layer corresponding to the maximum leaf area density and the actual ear height, and is related to the maize variety; L (LAD(max)) The height layer corresponding to the maximum leaf area density is indicated by L, where L represents the total number of layers in the 3D point cloud information, such as H. max / ΔH.

[0116] In this embodiment of the invention, by taking into account the deviation from the actual ear height, the relationship between the height layer corresponding to the maximum leaf area density, the corn plant height in the target area, and the total number of layers of the three-dimensional point cloud information is fully explored to achieve accurate calculation of the corn ear height.

[0117] Furthermore, in an embodiment of the present invention, the target height is further corrected according to the above formula (3) to accurately obtain the corn ear height in the target area.

[0118] The method of this invention, by taking into account the different growth patterns of different maize varieties, fully explores the correlation between the height layer corresponding to the maximum leaf area density on the vertical leaf area density distribution curve and maize plant parameters, and can accurately calculate the ear height of maize in the target area, further improving the accuracy of maize ear height measurement.

[0119] The measurement method described in this invention aims to provide a high-throughput, rapid, and automated measurement technology for maize ear height in breeding plots, providing scientific methods and technical support for applications such as screening for ideal maize plant type traits and discovering genomic fragments that control ear height, thereby promoting the large-scale development of maize breeding.

[0120] The corn ear height measuring device provided by the present invention is described below. The corn ear height measuring device described below can be referred to in correspondence with the corn ear height measuring method described above.

[0121] Figure 2 This is a schematic diagram of the structure of the corn ear height measuring device provided by the present invention, as shown below. Figure 2 As shown, it includes:

[0122] The acquisition module 210 is used to acquire three-dimensional point cloud information of corn vegetation within the target area;

[0123] The layering module 220 is used to perform height layering and voxelization processing on the 3D point cloud information, and to determine the voxels containing point cloud information in each height layer and all voxels in each height layer.

[0124] The first processing module 230 is used to determine the leaf area density of each height layer based on the number of voxels containing point cloud information in each height layer and the total number of all voxels in each height layer.

[0125] The second processing module 240 is used to determine the corn ear height in the target area based on the height of the height layer corresponding to the maximum value of the leaf area density in each layer.

[0126] The corn ear height measuring device described in this embodiment can be used to perform the corn ear height measuring method embodiment described above. Its principle and technical effect are similar, and will not be repeated here.

[0127] The corn ear height measurement device provided in this invention fully explores the growth pattern of corn ears and utilizes the characteristic that the leaves growing at the location of the corn ear have the largest leaf area. By using a drone equipped with lidar for measurement, it can acquire three-dimensional point cloud information of corn vegetation in the target area. By performing height layering and voxelization processing on the three-dimensional point cloud information, and using the number of voxels containing point cloud information in each height layer and the total number of voxels in each height layer, the leaf area density of each vertically distributed height layer can be obtained. Thus, based on the height of the height layer corresponding to the maximum value of the leaf area density in each layer, the corn ear height in the target area can be effectively determined, which can significantly improve the efficiency of corn ear height measurement and effectively realize high-throughput rapid measurement of corn ear height.

[0128] On the other hand, the present invention also provides a corn ear height measurement system, comprising: a drone equipped with a lidar and a data processing module; the drone equipped with the lidar is used to acquire three-dimensional point cloud information of the monitoring area and send the three-dimensional point cloud information of the monitoring area to the data processing module for processing.

[0129] in, Figure 3 This is a schematic diagram of the physical structure of the data processing module in the corn ear height measurement system provided by the present invention, as shown below. Figure 3As shown, the data processing module may include a processor 310, a communication interface 320, a memory 330, and a communication bus 340. The processor 310, communication interface 320, and memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute the corn ear height measurement method provided by the above methods. This method includes: acquiring three-dimensional point cloud information of corn vegetation within a target area; performing height layering and voxelization processing on the three-dimensional point cloud information to determine the voxels containing point cloud information in each height layer and all voxels in each height layer; determining the leaf area density of each height layer based on the number of voxels containing point cloud information and the number of all voxels in each height layer; and determining the corn ear height of the target area based on the height of the height layer corresponding to the maximum value of the leaf area density in each layer.

[0130] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0131] On the other hand, the present invention also provides a computer program product, which includes a computer program that 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 corn ear height measurement method provided by the above methods. The method includes: acquiring three-dimensional point cloud information of corn vegetation in a target area; performing height layering and voxelization processing on the three-dimensional point cloud information to determine the voxels containing point cloud information in each height layer and all voxels in each height layer; determining the leaf area density of each height layer based on the number of voxels containing point cloud information in each height layer and the number of all voxels in each height layer; and determining the corn ear height in the target area based on the height of the height layer corresponding to the maximum value of the leaf area density in each layer.

[0132] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the method for measuring the height of maize ears provided by the methods described above. This method includes: acquiring three-dimensional point cloud information of maize vegetation within a target area; performing height layering and voxelization processing on the three-dimensional point cloud information to determine the voxels containing point cloud information in each height layer and all voxels in each height layer; determining the leaf area density of each height layer based on the number of voxels containing point cloud information in each height layer and the number of all voxels in each height layer; and determining the height of the maize ear in the target area based on the height of the height layer corresponding to the maximum value of the leaf area density in each layer.

[0133] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0134] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0135] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for measuring the height of a corn ear, characterized in that, include: Obtain three-dimensional point cloud information of corn vegetation within the target area; The three-dimensional point cloud information is subjected to height layering and voxelization to determine the voxels containing point cloud information in each height layer and all voxels in each height layer. Based on the number of voxels containing point cloud information in each altitude layer and the total number of all voxels in each altitude layer, the leaf area density of each altitude layer is determined. The ear height of the maize in the target region is determined based on the height of the height layer corresponding to the maximum value of the leaf area density in each layer, including: Determine the layer number corresponding to the height layer with the maximum leaf area density and the maize plant height in the target area; The target height is determined based on the layer number, the corn plant height in the target area, and the total number of layers in the three-dimensional point cloud information. The target height is then corrected based on a preset layer threshold and a preset deviation value to obtain the corn ear height in the target area. The formula is as follows: The corn ear height in the target area is obtained; in, This indicates the height of the corn ears in the target area. This indicates the height of the corn plants in the target area; Indicates the preset stratification threshold; The preset deviation value represents the deviation between the height of the height layer corresponding to the maximum leaf area density and the actual ear height, and is related to the corn variety. This indicates the layer number of the height layer corresponding to the maximum leaf area density. This indicates the total number of layers in the three-dimensional point cloud information.

2. The method for measuring the height of maize ears according to claim 1, characterized in that, After determining the leaf area density of each height layer based on the number of voxels containing point cloud information and the total number of all voxels in each height layer, the method further includes: The leaf area density at each height level is fitted to obtain the vertical leaf area density distribution curve of the target area. The maximum leaf area density is determined based on the vertical leaf area density distribution curve. The ear height of the maize in the target area is determined based on the height layer corresponding to the maximum leaf area density.

3. The method for measuring the height of maize ears according to claim 1, characterized in that, Before acquiring the three-dimensional point cloud information of maize vegetation within the target area, the method further includes: Acquire the original three-dimensional point cloud information of the monitoring area; the original three-dimensional point cloud information is the original point cloud information under multiple different flight paths; The original 3D point cloud information is processed to obtain 3D point cloud information in the target format; Data registration is performed on the target format three-dimensional point cloud information under each route to obtain the registered three-dimensional point cloud information; According to preset boundary conditions, the registered 3D point cloud information is segmented into regions to obtain the 3D point cloud information in each target region. Ground point cloud filtering is performed on the three-dimensional point cloud information in each of the target areas to obtain the three-dimensional point cloud information of corn vegetation in each of the target areas.

4. A device for measuring the height of a corn ear, characterized in that, include: The acquisition module is used to acquire three-dimensional point cloud information of corn vegetation within the target area; The layering module is used to perform height layering and voxelization processing on the three-dimensional point cloud information, and to determine the voxels containing point cloud information in each height layer and all voxels in each height layer. The first processing module is used to determine the leaf area density of each height layer based on the number of voxels containing point cloud information and the total number of all voxels in each height layer. The second processing module is used to determine the corn ear height in the target area based on the height of the height layer corresponding to the maximum value of the leaf area density in each layer; The device is also used to determine the number of the height layer corresponding to the maximum leaf area density and the height of the maize plant in the target area. The target height is determined based on the layer number, the corn plant height in the target area, and the total number of layers in the three-dimensional point cloud information. The target height is then corrected based on a preset layer threshold and a preset deviation value to obtain the corn ear height in the target area. The formula is as follows: The corn ear height in the target area is obtained; in, This indicates the height of the corn ears in the target area. This indicates the height of the corn plants in the target area; Indicates the preset stratification threshold; The preset deviation value represents the deviation between the height of the height layer corresponding to the maximum leaf area density and the actual ear height, and is related to the corn variety. This indicates the layer number of the height layer corresponding to the maximum leaf area density. This indicates the total number of layers in the three-dimensional point cloud information.

5. A corn ear height measurement system, characterized in that, include: A drone equipped with a lidar sensor and a data processing module; The drone equipped with lidar is used to acquire three-dimensional point cloud information of the monitoring area and send the three-dimensional point cloud information of the monitoring area to the data processing module; The data processing module includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the corn ear height measurement method as described in any one of claims 1 to 3.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the corn ear height measurement method as described in any one of claims 1 to 3.

7. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the corn ear height measurement method as described in any one of claims 1 to 3.

Images