Regenerated crop rolling-resistant variety identification method based on unmanned aerial vehicle laser radar point cloud

Abstract

The invention provides a regeneration crop rolling-resistant variety identification method based on unmanned aerial vehicle laser radar point cloud, and the method comprises the steps: obtaining three-dimensional point cloud data of a target monitoring region from a crop multi-temporal global image collected by unmanned aerial vehicle laser radar equipment, rolling row crop points and non-rolling row crop points are extracted from the three-dimensional point cloud data; respectively extracting rolling resistance indexes of the crops from the rolling row crop points and the non-rolling row crop points; and predicting the rolling resistance of the crop according to the rolling resistance indexes corresponding to the rolling row crop points and the non-rolling row crop points, and determining whether the crop is a rolling-resistant variety or not according to the rolling resistance of the crop. According to the method, high-throughput identification is automatically performed on the rolling-resistant varieties of the regenerated crops, and the screening efficiency of the high-yield varieties of the regenerated crops can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of rapid acquisition of regenerated rice crop attribute information, and in particular to a method for identifying regenerated crop crushing-resistant varieties based on unmanned aerial vehicle laser radar point cloud. Background Art

[0002] Ratoon rice refers to a planting model in which dormant buds on rice stubble grow into ears through reasonable cultivation measures after rice is harvested, and then harvested for another season. It has the advantages of increasing production, income and efficiency. The full mechanization of the production of ratoon rice is an important way to further reduce labor intensity and labor costs, and promote the improvement of ratoon rice production capacity and modernization.

[0003] However, during the first season of mechanical harvesting of ratoon rice, the crushing of the harvester tracks causes damage to the rice piles, which affects the growth of the ratoon season and is not conducive to the high and stable yield of ratoon rice. At the same time, the lack of crushing-resistant varieties limits the improvement of the yield and quality of mechanically harvested ratoon rice. Therefore, screening crushing-resistant varieties under field conditions is helpful to improve the yield of the ratoon season.

[0004] At present, the commonly used method for screening regenerated rice crushing-resistant varieties is manual field sampling survey. This method has problems such as large manual errors, large labor input, low work efficiency, and small sample coverage, and cannot meet the needs of agricultural production. Summary of the invention

[0005] The present invention provides a method for identifying crushing-resistant varieties of regenerated crops based on unmanned aerial vehicle (UAV) laser radar point cloud, so as to solve the defects that the screening of crushing-resistant varieties of regenerated rice in the prior art adopts manual field sampling survey, which is time-consuming, labor-intensive and inefficient, and realizes high-throughput identification of crushing-resistant varieties of regenerated rice.

[0006] The present invention provides a method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud, comprising:

[0007] Acquire three-dimensional point cloud data of the target monitoring area from the multi-temporal global image of crops collected by the UAV laser radar equipment, and extract the rolled crop row points and non-rolled crop row points from the three-dimensional point cloud data;

[0008] Extracting the crop crushing resistance index from the crushing row crop points and the non-crushing row crop points respectively;

[0009] The crushing resistance of the crop is predicted based on the crushing resistance indexes corresponding to the crushing row crop points and the non-crushing row crop points, and whether the crop is a crushing resistant variety is determined based on the crushing resistance of the crop.

[0010] According to a method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud provided by the present invention, the crushing-resistant index of the crop includes one or more of the canopy traits, stem inclination angle, stem resilience and growth status of regenerated buds in the crushed row of the crop;

[0011] The canopy traits include crop canopy height, density and volume, and one or more of canopy coverage, three-dimensional canopy surface area and three-dimensional canopy index.

[0012] According to a method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud provided by the present invention, crushing resistance indexes of crops are extracted from the crushing row crop points and the non-crushing row crop points respectively, including:

[0013] Selecting three-dimensional points whose heights are greater than a first preset ratio of the maximum height of the rolling crop points from the rolling crop points and the non-rolling crop points, and using the average height of the three-dimensional points as the crop canopy height;

[0014] Selecting a second preset ratio of three-dimensional points whose heights are greater than the maximum height of the rolling crop points from the rolling crop points and the non-rolling crop points as a canopy point cloud, and calculating the canopy coverage according to a top view of the canopy point cloud;

[0015] The two-dimensional projection image of the canopy point cloud is converted into a spectrum diagram by two-dimensional Fourier transform, and the zero-frequency component of the spectrum diagram is moved to the center of the spectrum. The frequency and amplitude of the height value in the spectrum diagram are fitted by Gaussian fitting and a curve is drawn, and the three-dimensional canopy index 3DCI is obtained according to the area under the curve;

[0016] The canopy point cloud is voxelized, a canopy triangular mesh model is reconstructed according to the voxelized canopy point cloud, and the three-dimensional canopy surface area is obtained according to the canopy triangular mesh model.

[0017] According to a method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud provided by the present invention, the three-dimensional canopy surface area is obtained according to the canopy triangular mesh model by the following formula:

[0018]

[0019] Among them, S CS represents the three-dimensional canopy surface area, S CM represents the surface area of ​​the canopy triangular mesh model, S P represents the sampling area, and k is the surface area coefficient of the canopy triangular mesh model.

[0020] According to a method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud provided by the present invention, the stalk inclination angle is calculated by the following formula:

[0021]

[0022] Wherein, θ is the inclination angle of the stem, H R Indicates the crop canopy height corresponding to the rolling row crop point, H N Indicates the crop canopy height corresponding to the non-rolled row crop point.

[0023] According to a method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud provided by the present invention, the stem resilience is calculated by the following formula:

[0024] RD i =θ t1 -θ t2

[0025] Among them, the stem resilience calculated for the i-th time after the crop is harvested, θ t1 and θ t2 The inclination angles of the stems are obtained by sampling at two sampling times t1 and t2 in different growth periods.

[0026] According to a method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud provided by the present invention, the crushing resistance of the crop is predicted according to the crushing resistance index corresponding to the crushing row crop points and the non-crushing row crop points by the following formula:

[0027]

[0028] Wherein, RI is the rolling resistance of the crop, RD i is the stem resilience calculated at different periods, n is the number of calculations of the stem resilience, S csR and S csN The canopy surface areas of the rolling crop points and the non-rolling crop points are respectively R and H N are the crop canopy heights of the crushed crop points and the non-crushed crop points respectively, and a, b and c are weight coefficients.

[0029] According to a method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud provided by the present invention, crushing row crop points and non-crushing row crop points are extracted from the three-dimensional point cloud data, comprising:

[0030] After removing noise points in the three-dimensional point cloud data, the three-dimensional point cloud data is divided into ground points and crop points;

[0031] The crop points are divided into the rolled row crop points and the non-rolled row crop points.

[0032] The present invention also provides a device for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud, comprising:

[0033] An identification module is used to obtain three-dimensional point cloud data of the target monitoring area from the multi-temporal global image of the crop collected by the UAV laser radar equipment, and extract the rolled crop row points and non-rolled crop row points from the three-dimensional point cloud data;

[0034] An extraction module, used for extracting the crop crushing resistance index from the crushing row crop points and the non-crushing row crop points respectively;

[0035] The identification module is used to predict the crushing resistance of the crop according to the crushing resistance indicators corresponding to the crushing row crop points and the non-crushing row crop points, and determine whether the crop is a crushing resistant variety according to the crushing resistance of the crop.

[0036] 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. When the processor executes the program, it implements any of the above-mentioned methods for identifying crushing-resistant varieties of regenerated crops based on UAV lidar point clouds.

[0037] 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, the method for identifying crushing-resistant varieties of regenerated crops based on UAV lidar point clouds as described in any of the above is implemented.

[0038] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for identifying crushing-resistant varieties of regenerated crops based on drone lidar point clouds.

[0039] The method for identifying crushing-resistant varieties of regenerated crops based on UAV lidar point clouds provided by the present invention can generate high-density point clouds by using multi-temporal global images of crops collected by UAV lidar, and extract crushing resistance indicators of crops based on this large-scale and high-throughput method, thereby automatically performing high-throughput identification of crushing-resistant varieties of regenerated crops based on the extracted crushing resistance indicators, which is beneficial to improving the screening efficiency of high-yield varieties of regenerated crops and is suitable for large-scale and high-throughput evaluation of crushing resistance and field growth conditions of regenerated rice varieties. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces 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 creative work.

[0041] Figure 1 This is one of the flow diagrams of the method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud provided by the present invention;

[0042] Figure 2 This is the second flow chart of the method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud provided by the present invention;

[0043] Figure 3 It is a structural schematic diagram of a device for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud provided by the present invention;

[0044] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] Combine the following Figure 1 The present invention describes a method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud, comprising:

[0047] Step 101, acquiring three-dimensional point cloud data of a target monitoring area from a multi-temporal global image of crops collected by a UAV laser radar device, and extracting crushed row crop points and non-crushed row crop points from the three-dimensional point cloud data;

[0048] The crop in this embodiment may be regenerated rice or other crops.

[0049] Laser radar is not easily affected by weather, has strong penetrating power, and can accurately, quickly, efficiently, and at low cost extract the growth information of regenerated rice populations over a large area. Therefore, this embodiment uses a drone equipped with laser radar to generate a high-density point cloud, and based on this, extract rice field information over a large area and with high throughput.

[0050] The UAV laser radar measurement system used in this embodiment includes a multi-rotor UAV, a laser radar sensor, a GPS (Global Positioning System) positioning system and an inertial navigation system.

[0051] UAV lidar equipment can be used to collect multi-temporal global images of crops in regenerated rice fields, and the data can be pre-processed to obtain three-dimensional point cloud data of the target monitoring area.

[0052] The multi-temporal global images may include the day of harvest of the first season of ratoon rice, 1 day after harvest, 7 days after harvest, 21 days after harvest, heading stage and maturity stage of the ratoon season.

[0053] Preprocessing of multi-temporal global images of crops may include: using Zhitu software to generate LAS format point clouds from the collected point cloud data, and reconstructing them to obtain three-dimensional point cloud data containing RGB images; using ArcGIS software to draw the target plot and obtain a vector file of the area of ​​interest; and using the ExtractLas tool in the arcpy library in ArcGIS to extract the LAS point cloud data of the specified area from the LAS point cloud data.

[0054] The three-dimensional point cloud data can be divided into ground points and crop points, and the crop points can be partitioned into rolled row crop points and non-rolled row crop points.

[0055] The three-dimensional point cloud data can be converted into two-dimensional raster data to generate DSM (Digital Surface Model) and DEM (Digital Elevation Model) models, and the crop canopy model DHM (Digital Height Model) can be generated by subtracting them in ArcGIS. The coordinate points of crop distribution are extracted, and the statistical values ​​representing the top of the canopy and the ground elevation values ​​are extracted respectively. The elevation values ​​are divided into rolling rows and non-rolling rows using cluster analysis and machine learning models, and the geographic coordinates of the boundary vertices of rolling rows and non-rolling rows are obtained. The algorithm uses the transform function to obtain the affine transformation matrix and converts the pixel coordinates of these vertices into corresponding geographic coordinates. The algorithm batch outputs Shapefile files corresponding to the geographic coordinates of the vertices of each plot, namely ESRI Shapefile, and finally uses the clip_lidar_to_polygon function to complete the segmentation and preservation of the three-dimensional point cloud of rolling rows and non-rolling rows in the field.

[0056] After segmenting each plot point cloud, the directions of different rows of DHM are automatically calibrated for subsequent automated trait processing. First, the cornerHarris function is used to extract the turning points of the plot image, and four vertices are selected in combination with the image edge value; then the getPerspectiveTransform function is used to perform a two-dimensional perspective transformation on the image, and the direction calibration of all rolled rows and non-rolled point clouds in the object field is completed through iteration.

[0057] Step 102, extracting the crop crushing resistance index from the crushing row crop points and the non-crushing row crop points respectively;

[0058] The crop canopy height can be calculated, and the inclination angle of the stems and the canopy surface area of ​​the rolling row at different stages can be extracted. The rolling resistance of the crop can be determined by combining the stem resilience of the rolling row after the first season harvest and the canopy characteristics of the rolling row during the regeneration season. The complete flow chart is as follows: Figure 2 shown.

[0059] Step 103, predicting the crushing resistance of the crop according to the crushing resistance indexes corresponding to the crushing row crop points and the non-crushing row crop points, and determining whether the crop is a crushing resistant variety according to the crushing resistance of the crop.

[0060] This embodiment uses multi-phase global images of crops collected by drone lidar to generate high-density point clouds, and based on this large-scale and high-throughput extraction of crop crushing resistance indicators, automatically conduct high-throughput identification of crushing-resistant varieties of regenerated crops based on the extracted crushing resistance indicators, which is beneficial to improving the screening efficiency of high-yield varieties of regenerated crops and is suitable for large-scale and high-throughput evaluation of the crushing resistance and field growth conditions of regenerated rice varieties.

[0061] On the basis of the above embodiment, the crushing resistance index of the crop in this embodiment includes one or more of the canopy characteristics, stem inclination angle, stem resilience and growth status of regenerated buds in the crushed row of the crop;

[0062] The canopy traits include crop canopy height, density and volume, and one or more of canopy coverage, three-dimensional canopy surface area and three-dimensional canopy index.

[0063] The stalk inclination angle is the angle between the stalk and the ground at different sampling times after the first season harvester rolled over it. The stalk resilience is the change in the angle between the stalk and the ground after the rolled row was rolled over by the harvester.

[0064] On the basis of the above embodiment, in this embodiment, the crop crushing resistance index is extracted from the crushing row crop points and the non-crushing row crop points respectively, including:

[0065] Selecting three-dimensional points whose heights are greater than a first preset ratio of the maximum height of the rolling crop points from the rolling crop points and the non-rolling crop points, and using the average height of the three-dimensional points as the crop canopy height;

[0066] Selecting a second preset ratio of three-dimensional points whose heights are greater than the maximum height of the rolling crop points from the rolling crop points and the non-rolling crop points as a canopy point cloud, and calculating the canopy coverage according to a top view of the canopy point cloud;

[0067] The two-dimensional projection image of the canopy point cloud is converted into a spectrum diagram by two-dimensional Fourier transform, and the zero-frequency component of the spectrum diagram is moved to the center of the spectrum. The frequency and amplitude of the height value in the spectrum diagram are fitted by Gaussian fitting and a curve is drawn. The three-dimensional canopy index 3DCI (Three-dimensional Canopy Index) is obtained according to the area under the curve;

[0068] The canopy point cloud is voxelized, a canopy triangular mesh model is reconstructed according to the voxelized canopy point cloud, and the three-dimensional canopy surface area is obtained according to the canopy triangular mesh model.

[0069] For crop canopy height, three-dimensional points that are greater than 90% of the maximum canopy height of the plot can be selected, and the average height of these three-dimensional points can be used as the average canopy height of the plot to reduce the error caused by differences in plant heights in the plot.

[0070] For the canopy coverage trait, the canopy point cloud can be extracted with a threshold height of 60% of the maximum canopy height; then, based on the top view of the canopy point cloud, the threshold_local function is used to obtain a binary image of the corresponding cell canopy area to calculate the canopy coverage at the cell scale. The canopy coverage ranges from 0 to 1, and the closer the value is to 1, the higher the canopy coverage of the cell.

[0071] For the calculation of 3DCI traits, the acquired cell image was converted into the frequency domain (spectrum diagram) through two-dimensional Fourier transform, and the zero-frequency component was moved to the center of the spectrum; then the frequency and amplitude of the height value in the spectrum diagram were fitted using Gaussian fitting and the curve was drawn; the trapz function was used to obtain the area under the curve, and the 3DCI was obtained after normalization.

[0072] For the three-dimensional canopy surface area characteristics, the voxel_down_sample function is used to voxelize the canopy point cloud, and the calibration of key three-dimensional spatial points is completed after reducing the point cloud density; then the creat_from_point_cloud_alpha_shape function is used to reconstruct the canopy triangular mesh model; finally, the get_surface_area function is used to obtain the three-dimensional surface area of ​​the canopy in the cell.

[0073] On the basis of the above embodiment, in this embodiment, the three-dimensional canopy surface area is obtained according to the canopy triangular mesh model by the following formula:

[0074]

[0075] Among them, S CS represents the three-dimensional canopy surface area, S CM represents the surface area of ​​the canopy triangular mesh model, S P represents the sampling area, and k is the surface area coefficient of the canopy triangular mesh model.

[0076] Due to the different number of point clouds in different plots, the three-dimensional grid model of the canopy in plots with sparse point clouds will be incomplete, so the three-dimensional canopy surface area is calculated using formula (1). The value range of k can be 0.6 to 0.7, which is close to 1 standard deviation.

[0077] Based on the above embodiment, in this embodiment, the stalk inclination angle is calculated by formula (2):

[0078]

[0079] Wherein, θ is the inclination angle of the stem, H R Indicates the crop canopy height corresponding to the rolling row crop point, H N Indicates the crop canopy height corresponding to the non-rolled row crop point.

[0080] Based on the above embodiment, in this embodiment, the stem resilience is calculated by formula (3):

[0081] RD i =θ t1 -θ t2 (3)

[0082] Among them, the stem resilience calculated for the i-th time after the crop is harvested, θ t1 and θ t2 The inclination angles of the stems are obtained by sampling at two sampling times t1 and t2 in different growth periods.

[0083] RD iIt is the degree of rebound at different growth stages after harvest, ranging from 0 to 90°, where 0 means no rebound and 90° means complete rebound.

[0084] On the basis of the above embodiment, in this embodiment, the rolling resistance of the crop is predicted according to the rolling resistance index corresponding to the rolling crop point and the non-rolling crop point by formula (4):

[0085]

[0086] Wherein, RI is the rolling resistance of the crop, RD i is the stem resilience calculated at different periods, n is the number of calculations of the stem resilience, S csR and S csN The canopy surface areas of the rolling crop points and the non-rolling crop points are respectively R and H N are the crop canopy heights of the crushed crop points and the non-crushed crop points respectively, and a, b and c are weight coefficients.

[0087] Rolling resistance (RI) refers to the growth condition of the rolled rows at different periods after being rolled. The higher the rolling resistance, the more easily the variety is rolled.

[0088] On the basis of the above embodiments, in this embodiment, the rolling crop points and non-rolling crop points are extracted from the three-dimensional point cloud data, including:

[0089] After removing noise points in the three-dimensional point cloud data, the three-dimensional point cloud data is divided into ground points and crop points;

[0090] The crop points are divided into the rolled row crop points and the non-rolled row crop points.

[0091] Remove noise from 3D point cloud data and keep ground point and crop point data. You can use the statistical outlier removal denoising algorithm to remove noise. The specific steps are as follows:

[0092] (1) For each point i in the 3D point cloud data, find all its neighboring points j and calculate the distance d from each point to its neighboring points ij The distance parameter is modeled using the Gaussian distribution model d~N(μ,σ), and the mean μ and standard deviation σ of the distance between each point and its neighboring points are calculated. These values ​​reflect the distribution characteristics of the distance between the point and its neighboring points.

[0093] (2) Traverse all points and calculate the distance d between each point and its neighboring points ij , if the mean of its distance is greater than the specified confidence level of the Gaussian distribution, it is removed.

[0094] The device for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud provided by the present invention is described below. The device for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud described below and the method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud described above can be referenced to each other.

[0095] like Figure 3 As shown, the device includes a recognition module 301, an extraction module 302 and an identification module 303, wherein:

[0096] The recognition module 301 is used to obtain three-dimensional point cloud data of the target monitoring area from the crop multi-temporal global image collected by the UAV laser radar equipment, and extract the rolled crop row points and non-rolled crop row points from the three-dimensional point cloud data;

[0097] The extraction module 302 is used to extract the crop crushing resistance index from the crushing row crop points and the non-crushing row crop points respectively;

[0098] The identification module 303 is used to predict the crushing resistance of the crop according to the crushing resistance indicators corresponding to the crushing row crop points and the non-crushing row crop points, and determine whether the crop is a crushing-resistant variety according to the crushing resistance of the crop.

[0099] This embodiment uses multi-phase global images of crops collected by drone lidar to generate high-density point clouds, and based on this large-scale and high-throughput extraction of crop crushing resistance indicators, automatically conduct high-throughput identification of crushing-resistant varieties of regenerated crops based on the extracted crushing resistance indicators, which is beneficial to improving the screening efficiency of high-yield varieties of regenerated crops and is suitable for large-scale and high-throughput evaluation of the crushing resistance and field growth conditions of regenerated rice varieties.

[0100] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4As 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 through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute a method for identifying regenerated crop crushing-resistant varieties based on a UAV laser radar point cloud, the method comprising: acquiring three-dimensional point cloud data of a target monitoring area from a multi-temporal global image of crops collected by a UAV laser radar device, extracting crushing row crop points and non-crushing row crop points from the three-dimensional point cloud data; extracting the crushing resistance index of the crop from the crushing row crop points and the non-crushing row crop points respectively; predicting the crushing resistance of the crop according to the crushing resistance index corresponding to the crushing row crop points and the non-crushing row crop points, and determining whether the crop is a crushing-resistant variety according to the crushing resistance of the crop.

[0101] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, 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, which is stored in a storage medium and includes several instructions for 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 disk or an optical disk.

[0102] On the other hand, the present invention also provides a computer program product, which includes a computer program, and the computer program 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 method for identifying crushing-resistant varieties of regenerated crops based on UAV lidar point cloud provided by the above-mentioned methods, and the method includes: acquiring three-dimensional point cloud data of the target monitoring area from the multi-temporal global image of the crop collected by the UAV lidar equipment, extracting crushing row crop points and non-crushing row crop points from the three-dimensional point cloud data; extracting crushing resistance indicators of the crop from the crushing row crop points and the non-crushing row crop points respectively; predicting the crushing resistance of the crop according to the crushing resistance indicators corresponding to the crushing row crop points and the non-crushing row crop points, and determining whether the crop is a crushing-resistant variety according to the crushing resistance of the crop.

[0103] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the method for identifying crushing-resistant varieties of regenerated crops based on UAV lidar point cloud provided by the above-mentioned methods, the method comprising: acquiring three-dimensional point cloud data of the target monitoring area from the multi-temporal global image of the crop collected by the UAV lidar equipment, extracting crushing row crop points and non-crushing row crop points from the three-dimensional point cloud data; extracting crushing resistance indicators of the crop from the crushing row crop points and the non-crushing row crop points respectively; predicting the crushing resistance of the crop according to the crushing resistance indicators corresponding to the crushing row crop points and the non-crushing row crop points, and determining whether the crop is a crushing-resistant variety according to the crushing resistance of the crop.

[0104] The device embodiments described above are merely illustrative, wherein the units described by the crop separation components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. Those of ordinary skill in the art may understand and implement the present invention without creative effort.

[0105] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for 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 some parts of the embodiments.

[0106] 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 embodiments of the present invention.

Claims

1. A method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud, characterized in that: include: Acquire three-dimensional point cloud data of the target monitoring area from the multi-temporal global image of crops collected by the UAV laser radar equipment, and extract the rolled crop row points and non-rolled crop row points from the three-dimensional point cloud data; Extracting the crop crushing resistance index from the crushing row crop points and the non-crushing row crop points respectively; The crushing resistance of the crop is predicted based on the crushing resistance indexes corresponding to the crushing row crop points and the non-crushing row crop points, and whether the crop is a crushing resistant variety is determined based on the crushing resistance of the crop.

2. The method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud according to claim 1, characterized in that: The crop crushing resistance index includes one or more of the crop canopy characteristics, stem inclination angle, stem resilience and growth status of regenerated buds in the crushed row; The canopy traits include crop canopy height, density and volume, and one or more of canopy coverage, three-dimensional canopy surface area and three-dimensional canopy index.

3. The method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud according to claim 2, characterized in that: Extracting the crop crushing resistance index from the crushing row crop points and the non-crushing row crop points respectively includes: Selecting three-dimensional points whose heights are greater than a first preset ratio of the maximum height of the rolling crop points from the rolling crop points and the non-rolling crop points, and using the average height of the three-dimensional points as the crop canopy height; Selecting a second preset ratio of three-dimensional points whose heights are greater than the maximum height of the rolling crop points from the rolling crop points and the non-rolling crop points as a canopy point cloud, and calculating the canopy coverage according to a top view of the canopy point cloud; The two-dimensional projection image of the canopy point cloud is converted into a spectrum diagram by two-dimensional Fourier transform, and the zero-frequency component of the spectrum diagram is moved to the center of the spectrum. The frequency and amplitude of the height value in the spectrum diagram are fitted by Gaussian fitting and a curve is drawn, and the three-dimensional canopy index 3DCI is obtained according to the area under the curve; The canopy point cloud is voxelized, a canopy triangular mesh model is reconstructed according to the voxelized canopy point cloud, and the three-dimensional canopy surface area is obtained according to the canopy triangular mesh model.

4. The method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud according to claim 3 is characterized in that: The three-dimensional canopy surface area is obtained from the canopy triangular mesh model by the following formula: Among them, S CS represents the three-dimensional canopy surface area, S CM represents the surface area of ​​the canopy triangular mesh model, S P represents the sampling area, and k is the surface area coefficient of the canopy triangular mesh model.

5. The method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud according to claim 2, characterized in that: The stalk inclination angle is calculated by the following formula: Wherein, θ is the inclination angle of the stem, H R Indicates the crop canopy height corresponding to the rolling row crop point, H N Indicates the crop canopy height corresponding to the non-rolled row crop point.

6. The method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud according to claim 5, characterized in that: The stem resilience is calculated by the following formula: RD i =θ t1 -θ t2 Among them, the stem resilience calculated for the i-th time after the crop is harvested, θ t1 and θ t2 The inclination angles of the stems are obtained by sampling at two sampling times t1 and t2 in different growth periods.

7. The method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud according to claim 2, characterized in that: The crushing resistance of the crop is predicted according to the crushing resistance indexes corresponding to the crushing crop points and the non-crushing crop points by the following formula: Wherein, RI is the rolling resistance of the crop, RD i is the stem resilience calculated at different periods, n is the number of calculations of the stem resilience, S csR and S csN The canopy surface areas of the rolling crop points and the non-rolling crop points are respectively R and H N are the crop canopy heights of the crushed crop points and the non-crushed crop points respectively, and a, b and c are weight coefficients.

8. The method for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud according to any one of claims 1 to 7, characterized in that: Extracting rolled crop points and non-rolled crop points from the three-dimensional point cloud data includes: After removing noise points in the three-dimensional point cloud data, the three-dimensional point cloud data is divided into ground points and crop points; The crop points are divided into the rolled row crop points and the non-rolled row crop points.

9. A device for identifying crushing-resistant varieties of regenerated crops based on UAV laser radar point cloud, characterized in that: include: An identification module is used to obtain three-dimensional point cloud data of the target monitoring area from the multi-temporal global image of the crop collected by the UAV laser radar equipment, and extract the rolled crop row points and non-rolled crop row points from the three-dimensional point cloud data; An extraction module, used for extracting the crop crushing resistance index from the crushing row crop points and the non-crushing row crop points respectively; The identification module is used to predict the crushing resistance of the crop according to the crushing resistance indicators corresponding to the crushing row crop points and the non-crushing row crop points, and determine whether the crop is a crushing resistant variety according to the crushing resistance of the crop.

10. 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, it implements the method for identifying crushing-resistant varieties of regenerated crops based on UAV lidar point cloud as described in any one of claims 1 to 8.

Images