Unmanned aerial vehicle monitoring system and method for automatic agricultural production

Abstract

The invention discloses an unmanned aerial vehicle monitoring system and method for automatic agricultural production, and belongs to the field of general control systems, crop growth images, soil data and future period weather data are integrated, crop growth conditions are comprehensively analyzed, crop lodging conditions under the influence of future weather are estimated, and crop lodging conditions under the influence of future weather are estimated. According to the crop lodging early warning method and system, crop lodging early warning efficiency and accuracy are improved, crop growth conditions are comprehensively analyzed, growth implicit features are analyzed to obtain a growth condition analysis result, and crop lodging early warning efficiency and accuracy are improved. And then the growth condition analysis result is merged into the crop lodging trend analysis model to carry out crop lodging trend comprehensive analysis, so that the crop lodging trend analysis efficiency and accuracy are further improved.

Description

Technical Field

[0001] The present invention belongs to the general field of control systems, and more specifically, to an unmanned aerial vehicle monitoring system and method for automated agricultural production. Background Art

[0002] Drone monitoring plays an important role in automated agricultural production. It can monitor farmland efficiently and accurately, obtain information such as crop growth, soil nutrients, pests and diseases, and provide farmers with scientific decision-making support. At the same time, drones can also perform plant protection operations, such as spraying pesticides and fertilizing, to improve agricultural production efficiency and quality. Drone monitoring of automated agricultural production has significant advantages in improving agricultural production efficiency, accuracy and safety. With the continuous advancement and popularization of technology, the application of drones in agricultural production will become more and more extensive, injecting new vitality into the development of modern agriculture;

[0003] However, in the prior art, when conducting agricultural plant lodging warning, drones are usually used to take pictures of agricultural plants and then perform lodging image analysis. The prior art is unable to comprehensively analyze crop growth conditions in harsh environments by integrating crop growth data, soil data, and future periodic weather data, and is thus unable to predict crop lodging conditions under the influence of future weather, resulting in low efficiency and accuracy in early warning of crop lodging. Most of the prior art have the above problems. In response to the technical problems raised by this background technology, the present application designs a drone monitoring system and method for automated agricultural production. Summary of the invention

[0004] In view of the shortcomings of the existing technology, the present invention proposes a drone monitoring system and method for automated agricultural production, which is used to solve the technical problem that the existing technology is unable to integrate crop growth data, soil data and future periodic weather data to conduct a comprehensive analysis of crop growth conditions in harsh environments, and thus is unable to predict the lodging of crops under the influence of future weather, resulting in low early warning efficiency and accuracy for crop lodging.

[0005] To achieve the above objectives, the present invention provides the following technical solutions: In a first aspect, a method for monitoring an automated agricultural production using a drone is provided, which comprises the following specific steps:

[0006] Step 1: The drone flies in the field to obtain crop growth images, soil data and weather data;

[0007] Step 2: Obtain growth images of crops by field flight and import them into the lodging trend analysis strategy to perform lodging trend analysis;

[0008] Step 3: Obtain soil data and weather data and import them into the lodging impact analysis strategy to conduct lodging impact analysis;

[0009] Step 4: Import the obtained lodging trend analysis results and lodging impact analysis results into the lodging anomaly analysis model to perform lodging anomaly analysis;

[0010] Step 5: Provide crop lodging warning based on the obtained lodging abnormality analysis results.

[0011] As a preferred technical solution for a drone monitoring method for automated agricultural production, the drone flies in the field to obtain growth images of crops, and at the same time obtains soil data and weather data. The specific contents are:

[0012] S11, launching a drone to fly in the field to obtain images of agricultural crops, obtaining height data, diameter data, and growth density data of the agricultural crops from the images, and storing the data in a first storage component;

[0013] S12. Obtain viscosity and water content data of the soil sample, and simultaneously obtain precipitation data and wind data of future period weather estimated by the weather forecast, and store the obtained data in a storage component.

[0014] As a preferred technical solution for a drone monitoring method for automated agricultural production, the method of obtaining growth images of crops obtained by field flight and importing them into a lodging trend analysis strategy for lodging trend analysis includes the following specific steps:

[0015] S21, obtaining each crop planting image acquired by the drone, obtaining the stem image of the crop, dividing the crop into an upper part and a lower part at the middle position of the stem, obtaining the volume ratio of the upper part to the lower part of the crop as the volume ratio, obtaining the height data of the crop and the average diameter data of the crop. It should be noted that the average diameter of the crop here is obtained by obtaining the diameter data at the vertical height of the crop, integrating it at the vertical height and then averaging it, and importing it into the growth anomaly value calculation formula to calculate the growth anomaly value, wherein the growth anomaly value calculation formula is: , where a is the height ratio, pi is the crop height data, pim is the standard crop height data of the planting cycle, Li is the average crop diameter data, and Lim is the standard crop diameter data of the planting cycle;

[0016] S22, obtaining the volume ratio, height data, average diameter data, growth density data and growth abnormal value data of each crop, and importing them into the lodging trend abnormal value calculation formula to calculate the lodging trend abnormal value, wherein the lodging trend abnormal value calculation formula is: , where n is the number of data types of volume ratio and height data of each crop, bj is the weight of the jth item in the data types of volume ratio and height data of crops, kj is the actual value of the jth item in the data types of volume ratio and height data of crops, kjm is the standard value of the jth item in the data types of volume ratio and height data of crops, N is the number of data types of average diameter data and growth density data of crops, cv is the proportion coefficient of the vth item in the data types of average diameter data and growth density data of crops, qv is the actual data of the vth item in the data types of average diameter data and growth density data of crops, qvm is the standard value of the vth item in the data types of average diameter data and growth density data of crops, and exp() is the power of the natural constant e.

[0017] As a preferred technical solution for a drone monitoring method for automated agricultural production, the acquisition of soil data and weather data and importing them into a lodging impact analysis strategy for lodging impact analysis includes the following specific steps:

[0018] S31, obtaining the viscosity and water content data of the soil samples at each collection point, and importing the viscosity and water content data of the soil samples at each collection point into a soil lodging influence value calculation formula to calculate the soil lodging influence value, wherein the soil lodging influence value calculation formula is: , where D is the number of collection points, C is the soil viscosity ratio, kzd is the soil viscosity of the dth collection point, kzdm is the standard value of soil viscosity, sd is the soil water content of the dth collection point, and sdm is the standard value of soil water content;

[0019] S32, obtaining weather data for a future period, and importing the obtained weather data for a future period into a weather lodging impact value calculation formula to calculate the weather lodging impact value, wherein the weather lodging impact value calculation formula is: , where T is the cycle duration, Ft is the estimated wind force at time t, Fm is the maximum safe wind force that crops can withstand, u is the wind force influence ratio, Vt is the estimated precipitation in the future cycle, and Vm is the safe precipitation;

[0020] S33, obtaining the calculated soil lodging influence value and weather lodging influence value and importing them into the lodging anomaly analysis value calculation formula to calculate the lodging anomaly analysis value, wherein the lodging anomaly analysis value calculation formula is: ,in, is the proportion of soil lodging impact.

[0021] It should be noted here that crop lodging is mostly caused by the combined effects of wind and rain, where the soil tension is insufficient to hold the roots of the crops. Therefore, we comprehensively analyze the impact of lodging by combining soil and weather anomalies.

[0022] As a preferred technical solution for a drone monitoring method for automated agricultural production, the method of importing the obtained lodging trend analysis results and lodging impact analysis results into a lodging anomaly analysis model for lodging anomaly analysis includes the following specific steps:

[0023] Obtain the calculated lodging trend anomaly value and lodging anomaly analysis value and substitute them into the lodging anomaly value calculation formula to calculate the lodging anomaly value, where the lodging anomaly value calculation formula is: Among them, R is the number of crops in the planting area, and Dfr is the abnormal value of the lodging trend of the rth crop in the planting area.

[0024] As a preferred technical solution for a drone monitoring method for automated agricultural production, the crop lodging warning according to the obtained lodging abnormality analysis results includes the following specific contents:

[0025] The calculated lodging abnormality value is compared with the set lodging abnormality threshold. If the obtained lodging abnormality value is greater than or equal to the set lodging abnormality threshold, a crop lodging warning is issued to remind planting personnel to reinforce the crops against wind. If the obtained lodging abnormality value is less than the set lodging abnormality threshold, no crop lodging warning is issued.

[0026] In a second aspect, a drone monitoring system for automated agricultural production is provided, which is implemented based on the above-mentioned drone monitoring method for automated agricultural production, and specifically includes an information acquisition module, a lodging trend analysis module, a lodging impact analysis module, a lodging anomaly analysis module and a lodging warning module;

[0027] The information acquisition module is used for the drone to fly in the field to obtain growth images of crops, and to obtain soil data and weather data at the same time;

[0028] The lodging trend analysis module is used to obtain growth images of crops obtained by field flight and import them into the lodging trend analysis strategy to perform lodging trend analysis;

[0029] The lodging impact analysis module is used to obtain soil data and weather data and import them into the lodging impact analysis strategy to perform lodging impact analysis;

[0030] The lodging anomaly analysis module is used to import the acquired lodging trend analysis results and lodging impact analysis results into the lodging anomaly analysis model to perform lodging anomaly analysis;

[0031] The lodging warning module is used to provide crop lodging warning according to the obtained lodging abnormality analysis results;

[0032] It also includes a control module, which is used for controlling the operation of the information acquisition module, the lodging trend analysis module, the lodging impact analysis module, the lodging anomaly analysis module and the lodging warning module.

[0033] In a third aspect, an electronic device is provided, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0034] The processor executes the above-mentioned drone monitoring method for automated agricultural production by calling the computer program stored in the memory.

[0035] In a fourth aspect, a computer-readable storage medium is provided, storing instructions, which, when executed on a computer, enable the computer to execute a method for monitoring automated agricultural production using a drone as described above.

[0036] Compared with the prior art, the beneficial effects of this application are:

[0037] This application integrates crop growth images, soil data and future periodic weather data to conduct a comprehensive analysis of crop growth conditions, and then estimates the crop lodging conditions under the influence of future weather, and provides early warning, thereby improving the efficiency and accuracy of early warning of crop lodging;

[0038] The present application conducts a comprehensive analysis of the growth conditions of crops, analyzes the implicit characteristics of growth to obtain growth analysis results, and then incorporates the growth analysis results into a crop lodging trend analysis model to conduct a comprehensive analysis of crop lodging trends, thereby further improving the efficiency and accuracy of crop lodging trend analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0040] Figure 1 This is a schematic diagram of the overall process of a drone monitoring method for automated agricultural production of the present invention;

[0041] Figure 2 This is a specific flow chart of step 3 of a method for monitoring automated agricultural production using a drone according to the present invention;

[0042] Figure 3 This is a schematic diagram of the overall framework of a drone monitoring system for automated agricultural production according to the present invention;

[0043] Figure 4 This is a schematic diagram of the crop data acquisition process of the present invention;

[0044] Figure 5 This is a schematic diagram of the division of the upper and lower parts of the crop of the present invention;

[0045] Figure 6 This is a schematic diagram of the location for obtaining soil samples in the present invention. DETAILED DESCRIPTION

[0046] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the embodiments of the specification.

[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0048] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0049] Example 1 In order to solve the technical problems raised in the background technology, the present invention provides a preferred embodiment: Figure 1-Figure 2 As shown, this embodiment provides a drone monitoring method for automated agricultural production, which includes the following specific steps:

[0050] Step 1: The drone flies in the field to obtain crop growth images, soil data and weather data;

[0051] In one specific embodiment, the drone flies in the field to obtain growth images of crops, and the specific contents of obtaining soil data and weather data are as follows:

[0052] S11, launching a drone to fly in the field to obtain images of agricultural crops, obtaining height data, diameter data, and growth density data of the agricultural crops from the images, and storing the data in a first storage component;

[0053] like Figure 4 As shown, the specific steps of using a drone to fly in a field to obtain images of agricultural crops and obtaining height data, diameter data, and growth density data of the agricultural crops from the images can be as follows:

[0054] S111. UAV flight and image acquisition: First, plan the flight route and altitude of the drone according to the specific conditions and needs of the farmland to ensure that the drone can capture the crops in the farmland at an appropriate angle and resolution. During the flight, the high-definition camera or other imaging equipment carried by the drone will capture images of the farmland;

[0055] S112, image preprocessing: importing the acquired images into image processing software and performing necessary preprocessing steps, which may include noise removal, contrast adjustment, color correction, etc., to improve the quality and clarity of the image;

[0056] S113, Image segmentation and recognition: Use image processing software or machine learning algorithms to segment and recognize the pre-processed images. This step aims to separate the crops from the background and identify each individual crop.

[0057] S114, height data extraction: For height data extraction, the image can be calibrated using a scale bar or a known reference object in the image. Then, by measuring the pixel height of each individual crop in the image, combined with the flight altitude and camera parameters of the drone, the actual height of the crop can be calculated.

[0058] S115, diameter data extraction: The diameter data can be extracted by measuring the width of the crop in the image. Similarly, a scale or reference object needs to be used for calibration, and the pixel width of each individual crop is measured to calculate the actual diameter.

[0059] S116, growth density data extraction: Growth density data can be obtained by counting the number of crop individuals in the image. First, a suitable area needs to be determined, and then the number of crop individuals in the area is calculated to obtain the growth density;

[0060] S12, obtaining viscosity and water content data of the soil sample, and simultaneously obtaining precipitation data and wind data of future period weather estimated by the weather forecast, and storing the obtained data in a storage component; Figure 6 The figure shows a schematic diagram of the location for obtaining soil samples, where sampling points are set at the corners and the center of the planting area to collect soil samples;

[0061] At the same time, generally speaking, weather forecasts will provide weather forecasts for different time ranges such as the next few hours, one day, three days, and one week. These data may include precipitation, precipitation probability, wind force, wind direction, etc. At the same time, some weather forecast services will also provide weather warnings and tips to help people better cope with future weather changes;

[0062] Step 2: Obtain growth images of crops by field flight and import them into the lodging trend analysis strategy to perform lodging trend analysis;

[0063] In one specific embodiment, obtaining growth images of crops obtained by field flight and importing them into a lodging trend analysis strategy for lodging trend analysis includes the following specific steps:

[0064] S21, obtaining the planting images of various crops collected by the drone, and obtaining the stem images of the crops, such as Figure 5 As shown, the crops are divided into the upper part and the lower part at the middle position of the stem, the volume ratio of the upper part to the lower part of the crop is obtained as the volume ratio, and the height data of the crop and the average diameter data of the crop are obtained. It should be noted that the average diameter of the crop here is obtained by obtaining the diameter data at the vertical height of the crop, integrating it at the vertical height and then averaging it, and importing it into the growth anomaly value calculation formula to calculate the growth anomaly value, wherein the growth anomaly value calculation formula is: , where a is the height ratio, pi is the crop height data, pim is the standard crop height data of the planting cycle, Li is the average crop diameter data, and Lim is the standard crop diameter data of the planting cycle;

[0065] S22, obtaining the volume ratio, height data, average diameter data, growth density data and growth abnormal value data of each crop, and importing them into the lodging trend abnormal value calculation formula to calculate the lodging trend abnormal value, wherein the lodging trend abnormal value calculation formula is: , where n is the number of data types of volume ratio and height data of each crop, bj is the weight of the jth item in the data types of volume ratio and height data of the crop, kj is the actual value of the jth item in the data types of volume ratio and height data of the crop, kjm is the standard value of the jth item in the data types of volume ratio and height data of the crop, N is the number of data types of average diameter data and growth density data of the crop, cv is the proportion coefficient of the vth item in the number of data types of average diameter data and growth density data of the crop, qv is the actual data of the vth item in the number of data types of average diameter data and growth density data of the crop, qvm is the standard value of the vth item in the number of data types of average diameter data and growth density data of the crop, and exp() is the natural constant e Power of times. It should be noted here that, for crops, the larger the volume ratio and height, the worse the stability and the more likely it is to lodging. Therefore, the lodging trend abnormal value is proportional to the volume ratio and height of the crops. For the average diameter data and growth density data, the larger the average diameter data and growth density data, the more difficult it is for the crops to lodging. Therefore, the lodging trend abnormal value is inversely proportional to the average diameter data and growth density data of the crops. Different factors must have different influences on lodging, so different weights are set. At the same time, the lodging resistance is definitely proportional to the growth and health of the crops. At the same time, it should be noted that the standard value of the crop parameters here is the parameter value of the plant with the best growth status judged by experts.

[0066] Step 3: Obtain soil data and weather data and import them into the lodging impact analysis strategy to conduct lodging impact analysis;

[0067] In one specific embodiment, obtaining soil data and weather data and importing them into the lodging impact analysis strategy to perform lodging impact analysis includes the following specific steps:

[0068] S31, obtaining the viscosity and water content data of the soil samples at each collection point, and importing the viscosity and water content data of the soil samples at each collection point into a soil lodging influence value calculation formula to calculate the soil lodging influence value, wherein the soil lodging influence value calculation formula is: , where D is the number of collection points, C is the soil viscosity ratio, kzd is the soil viscosity of the dth collection point, kzdm is the standard value of soil viscosity, sd is the soil water content of the dth collection point, and sdm is the standard value of soil water content;

[0069] S32, obtaining weather data for a future period, and importing the obtained weather data for a future period into a weather lodging impact value calculation formula to calculate the weather lodging impact value, wherein the weather lodging impact value calculation formula is: , where T is the cycle duration, Ft is the estimated wind force at time t, Fm is the maximum safe wind force that crops can withstand, u is the wind force influence ratio, Vt is the estimated precipitation in the future cycle, and Vm is the safe precipitation;

[0070] S33, obtaining the calculated soil lodging influence value and weather lodging influence value and importing them into the lodging anomaly analysis value calculation formula to calculate the lodging anomaly analysis value, wherein the lodging anomaly analysis value calculation formula is: ,in, is the proportion of soil lodging impact;

[0071] It should be noted here that crop lodging is mostly caused by the combined effects of wind and rain, where the soil tension is insufficient to hold the roots of the crops. Therefore, we analyze the impact of lodging by combining soil and weather anomalies;

[0072] Step 4: Import the obtained lodging trend analysis results and lodging impact analysis results into the lodging anomaly analysis model to perform lodging anomaly analysis;

[0073] In one specific embodiment, importing the obtained lodging trend analysis results and lodging impact analysis results into the lodging anomaly analysis model to perform lodging anomaly analysis includes the following specific steps:

[0074] Obtain the calculated lodging trend abnormal value and lodging abnormal analysis value and substitute them into the lodging abnormal value calculation formula to calculate the lodging abnormal value, where the lodging abnormal value calculation formula is: Among them, R is the number of crops in the planting area, and Dfr is the abnormal value of the lodging trend of the rth crop in the planting area;

[0075] Step 5: Perform crop lodging warning according to the obtained lodging abnormality analysis results;

[0076] In one specific embodiment, the crop lodging warning according to the obtained lodging abnormality analysis result includes the following specific contents:

[0077] The calculated lodging abnormality value is compared with the set lodging abnormality threshold. If the obtained lodging abnormality value is greater than or equal to the set lodging abnormality threshold, a crop lodging warning is issued to remind planting personnel to reinforce the crops against wind. If the obtained lodging abnormality value is less than the set lodging abnormality threshold, no crop lodging warning is issued.

[0078] In this embodiment, it should be specifically explained that the weight of the jth item in the data type of volume ratio and height data of crops, the height proportion coefficient, the vth item in the number of data types of average diameter data and growth density data of crops, the soil viscosity proportion coefficient, the wind influence proportion coefficient, the soil lodging influence proportion and the lodging abnormality threshold are determined as follows: 5000 groups of growth images, soil data and weather data of crops are obtained, and the lodging abnormality value calculation formula is imported to calculate the lodging abnormality, and the judgment result of whether the crops in the next cycle have lodged is obtained, and the judgment result of whether the crops in the next cycle have lodged and the calculated lodging abnormality value are imported into the fitting software, and the weight of the jth item in the data type of volume ratio and height data of crops, the height proportion coefficient, the vth item in the number of data types of average diameter data and growth density data of crops, the soil viscosity proportion coefficient, the wind influence proportion coefficient, the soil lodging influence proportion and the lodging abnormality threshold are output that meet the maximum judgment accuracy.

[0079] The advantages of this embodiment over the prior art are as follows: it integrates crop growth images, soil data and future periodic weather data to conduct a comprehensive analysis of crop growth conditions, and then predicts the crop lodging conditions under the influence of future weather, and conducts early warnings, thereby improving the efficiency and accuracy of early warnings for crop lodging. By conducting a comprehensive analysis of crop growth conditions and analyzing implicit growth characteristics to obtain growth condition analysis results, the growth condition analysis results are then incorporated into a crop lodging trend analysis model to conduct a comprehensive analysis of crop lodging trends, thereby further improving the efficiency and accuracy of crop lodging trend analysis.

[0080] Example 2 like Figure 3 As shown, this embodiment provides a drone monitoring system for automated agricultural production, which is implemented based on the above-mentioned drone monitoring method for automated agricultural production, and specifically includes an information acquisition module, a lodging trend analysis module, a lodging impact analysis module, a lodging anomaly analysis module and a lodging warning module;

[0081] Among them, the information acquisition module is used for the drone to fly in the field to obtain the growth images of crops, and at the same time obtain soil data and weather data;

[0082] Lodging trend analysis module, used to obtain growth images of crops obtained by field flight and import them into lodging trend analysis strategy to conduct lodging trend analysis;

[0083] Lodging impact analysis module, used to obtain soil data and weather data and import them into the lodging impact analysis strategy to conduct lodging impact analysis;

[0084] A lodging anomaly analysis module, used for importing the obtained lodging trend analysis results and lodging impact analysis results into the lodging anomaly analysis model to perform lodging anomaly analysis;

[0085] A lodging warning module is used to provide crop lodging warning based on the obtained lodging anomaly analysis results;

[0086] It also includes a control module, which is used for controlling the operation of the information acquisition module, the lodging trend analysis module, the lodging impact analysis module, the lodging anomaly analysis module and the lodging warning module.

[0087] Example 3 This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0088] The processor executes the above-mentioned drone monitoring method for automated agricultural production by calling the computer program stored in the memory.

[0089] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement a drone monitoring method for automated agricultural production provided by the above method embodiment. The electronic device may also include other components for implementing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input / output interface to input and output data. This embodiment will not be described in detail here.

[0090] Example 4 This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0091] When the computer program runs on a computer device, the computer device executes the above-mentioned drone monitoring method for automated agricultural production.

[0092] For example, the computer readable storage medium can be a read-only memory, a random access memory, a read-only CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0093] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the above examples, those skilled in the art can still modify the technical solutions described in the above embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A drone monitoring method for automated agricultural production, characterized in that: It includes the following specific steps: Step 1: The drone flies in the field to obtain crop growth images, soil data and weather data; Step 2: Obtain growth images of crops by field flight and import them into the lodging trend analysis strategy to perform lodging trend analysis; Step 3: Obtain soil data and weather data and import them into the lodging impact analysis strategy to conduct lodging impact analysis; Step 4: Import the obtained lodging trend analysis results and lodging impact analysis results into the lodging anomaly analysis model to perform lodging anomaly analysis; Step 5: Provide crop lodging warning based on the obtained lodging abnormality analysis results.

2. The method for monitoring automated agricultural production by a drone according to claim 1, characterized in that: The drone flies in the field to obtain crop growth images, and the specific contents of soil data and weather data are as follows: S11, launching a drone to fly in the field to obtain images of agricultural crops, obtaining height data, diameter data, and growth density data of the agricultural crops from the images, and storing the data in a first storage component; S12. Obtain viscosity and water content data of the soil sample, and simultaneously obtain precipitation data and wind data of future period weather estimated by the weather forecast, and store the obtained data in a storage component.

3. The method for monitoring automated agricultural production by a drone as claimed in claim 2, characterized in that: The method of obtaining the growth images of crops obtained by field flight and importing them into the lodging trend analysis strategy for lodging trend analysis comprises the following specific steps: S21, obtaining each crop planting image acquired by the drone, obtaining the stem image of the crop, dividing the crop into an upper part and a lower part at the middle position of the stem, obtaining the volume ratio of the upper part to the lower part of the crop as the volume ratio, obtaining the height data of the crop and the average diameter data of the crop, and importing them into the growth anomaly value calculation formula to calculate the growth anomaly value, wherein the growth anomaly value calculation formula is: , where a is the height ratio, pi is the crop height data, pim is the standard crop height data of the planting cycle, Li is the average crop diameter data, and Lim is the standard crop diameter data of the planting cycle; S22, obtaining the volume ratio, height data, average diameter data, growth density data and growth abnormal value data of each crop, and importing them into the lodging trend abnormal value calculation formula to calculate the lodging trend abnormal value, wherein the lodging trend abnormal value calculation formula is: , where n is the number of data types of volume ratio and height data of each crop, bj is the weight of the jth item in the data types of volume ratio and height data of crops, kj is the actual value of the jth item in the data types of volume ratio and height data of crops, kjm is the standard value of the jth item in the data types of volume ratio and height data of crops, N is the number of data types of average diameter data and growth density data of crops, cv is the proportion coefficient of the vth item in the data types of average diameter data and growth density data of crops, qv is the actual data of the vth item in the data types of average diameter data and growth density data of crops, qvm is the standard value of the vth item in the data types of average diameter data and growth density data of crops, and exp() is the power of the natural constant e.

4. The method for monitoring automated agricultural production by a drone as claimed in claim 3, characterized in that: The method of obtaining soil data and weather data and importing them into the lodging impact analysis strategy to perform lodging impact analysis includes the following specific steps: S31, obtaining the viscosity and water content data of the soil samples at each collection point, and importing the viscosity and water content data of the soil samples at each collection point into a soil lodging influence value calculation formula to calculate the soil lodging influence value, wherein the soil lodging influence value calculation formula is: , where D is the number of collection points, C is the soil viscosity ratio, kzd is the soil viscosity of the dth collection point, kzdm is the standard value of soil viscosity, sd is the soil water content of the dth collection point, and sdm is the standard value of soil water content; S32, obtaining weather data for a future period, and importing the obtained weather data for a future period into a weather lodging impact value calculation formula to calculate the weather lodging impact value, wherein the weather lodging impact value calculation formula is: , where T is the cycle duration, Ft is the estimated wind force at time t, Fm is the maximum safe wind force that crops can withstand, u is the wind force influence ratio, Vt is the estimated precipitation in the future cycle, and Vm is the safe precipitation; S33, obtaining the calculated soil lodging influence value and weather lodging influence value and importing them into the lodging anomaly analysis value calculation formula to calculate the lodging anomaly analysis value, wherein the lodging anomaly analysis value calculation formula is: ,in, is the proportion of soil lodging impact.

5. The method for monitoring automated agricultural production by unmanned aerial vehicles according to claim 4, characterized in that: The step of importing the obtained lodging trend analysis results and lodging impact analysis results into the lodging anomaly analysis model to perform lodging anomaly analysis comprises the following specific steps: Obtain the calculated lodging trend abnormal value and lodging abnormal analysis value and substitute them into the lodging abnormal value calculation formula to calculate the lodging abnormal value, where the lodging abnormal value calculation formula is: Among them, R is the number of crops in the planting area, and Dfr is the abnormal value of the lodging trend of the rth crop in the planting area.

6. The method for monitoring automated agricultural production by unmanned aerial vehicles according to claim 5, characterized in that: The crop lodging warning according to the obtained lodging abnormality analysis results includes the following specific contents: The calculated lodging abnormality value is compared with the set lodging abnormality threshold. If the obtained lodging abnormality value is greater than or equal to the set lodging abnormality threshold, a crop lodging warning is issued to remind planting personnel to reinforce the crops against wind. If the obtained lodging abnormality value is less than the set lodging abnormality threshold, no crop lodging warning is issued.

7. An unmanned aerial vehicle monitoring system for automated agricultural production, which is implemented based on the unmanned aerial vehicle monitoring method for automated agricultural production according to any one of claims 1 to 6, characterized in that: It specifically includes an information acquisition module, a lodging trend analysis module, a lodging impact analysis module, a lodging anomaly analysis module and a lodging warning module; The information acquisition module is used for the drone to fly in the field to obtain growth images of crops, and to obtain soil data and weather data at the same time; The lodging trend analysis module is used to obtain growth images of crops obtained by field flight and import them into the lodging trend analysis strategy to perform lodging trend analysis; The lodging impact analysis module is used to obtain soil data and weather data and import them into the lodging impact analysis strategy to perform lodging impact analysis; The lodging anomaly analysis module is used to import the acquired lodging trend analysis results and lodging impact analysis results into the lodging anomaly analysis model to perform lodging anomaly analysis; The lodging warning module is used to provide crop lodging warning according to the obtained lodging abnormality analysis results; It also includes a control module, which is used for controlling the operation of the information acquisition module, the lodging trend analysis module, the lodging impact analysis module, the lodging anomaly analysis module and the lodging warning module.

8. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; It is characterized in that the processor executes the drone monitoring method for automated agricultural production as described in any one of claims 1 to 6 by calling the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes a drone monitoring method for automated agricultural production as described in any one of claims 1-6.

Images