Intelligent sampling, detecting and analyzing method for crop diseases and insect pests

Abstract

The invention belongs to the technical field of sampling detection and analysis of plant diseases and insect pests, and particularly discloses an intelligent sampling detection and analysis method for crop plant diseases and insect pests, which comprises the following steps: searching growth points of abnormal plants through spectrum equipment and positioning equipment carried by an unmanned aerial vehicle, and dividing corresponding sampling areas of different abnormal types; determining the sampling quantity in the areas by analyzing the air environment and the soil environment of different sampling areas, determining the sampling positions in the areas by dividing the unusual degree grades of unusual plant growing points, generating a sampling environment information set, and importing data as a training model; meanwhile, a biochemical feature set of the sampled leaves is generated through biochemical measurement and serves as exported data, a training model is established, and the mapping relation from leaf features and environmental data to biochemical features is reflected. According to the mode, the dynamic adjustment of a sampling strategy is realized, and the scientificity and representativeness of crop detection analysis are improved.

Description

Technical Field

[0001] The invention belongs to the technical field of sampling, detection and analysis of pests and diseases, and relates to an intelligent sampling, detection and analysis method for crop pests and diseases. Background Art

[0002] Crop pests and diseases are important factors affecting agricultural production. Traditional pest and disease detection methods mainly rely on manual inspections and sampling, which have problems such as low efficiency, small coverage, and insufficient accuracy. With the development of drone technology and spectral analysis technology, modern agriculture has gradually introduced intelligent detection methods. In existing technologies, drones equipped with spectral equipment can quickly scan farmland, identify abnormal reflection bands of plants, and thus locate pest and disease areas.

[0003] On this basis, traditional detection methods have many problems in the sampling process, such as the determination of sampling location and quantity often lacks scientific basis, is relatively random, and cannot fully and accurately reflect the true distribution of farmland pests and diseases, which may lead to deviations in the test results and affect the formulation and implementation of subsequent prevention and control measures. Therefore, the development of an intelligent sampling, detection and analysis method for crop pests and diseases has important practical significance and application value.

[0004] In the prior art, there are some solutions related to crop pest detection and analysis. For example, the Chinese patent publication number CN106338492A discloses a crop census system based on a small drone-mounted imaging spectrometer, which includes: a small drone platform and mission system, ground support equipment; the mission system includes: a measurement and control module, a GPS module, a small near-infrared imaging spectrometer, a data transmission module, and installation accessories; the crop census system uses a push-broom mode to obtain the target spectral image cube; the ground support equipment is responsible for completing the measurement and control of the small drone and the mission system and the reception of observation data. It can realize the census work for field crops, obtain the target near-infrared infrared spectral image cube data, provide rich infrared image and spectral information, and has extremely high detection sensitivity and a relatively complete evaluation system.

[0005] Compared with the above solutions, the following limitations exist: only a general survey of farmland crops is conducted to obtain spectral image cubic data, without accurate positioning and classification of different abnormal plants. In the detection and analysis of crop diseases and insect pests, the impact of air and soil environments on the occurrence and development of diseases and insect pests is not comprehensively considered, making it difficult to fully understand the causes and background of disease and insect pests, which is not conducive to in-depth analysis of disease and insect pest problems and the formulation of effective prevention and control strategies. In addition, the value of multi-source data cannot be fully utilized, resulting in a lack of depth and breadth in the analysis of crop diseases and insect pests. Summary of the invention

[0006] In view of this, in order to solve the problems raised in the above background technology, an intelligent sampling, detection and analysis method for crop pests and diseases is now proposed.

[0007] The objective of the present invention can be achieved through the following technical scheme: The present invention provides an intelligent sampling, detection and analysis method for crop diseases and insect pests, comprising the following steps: step 1, using an unmanned aerial vehicle equipped with a spectral device and a positioning device, screening out abnormal plant growth points in the leaf surface reflection band through spectral analysis, and marking the point cloud information of each abnormal plant growth point, including point cloud coordinates, abnormal category and abnormal degree.

[0008] Step 2: After clustering the point cloud coordinates of the growth points of each abnormal plant, mark the pest and disease areas corresponding to each abnormal category, and deploy sensor nodes to detect the sampling compensation weights of each pest and disease area corresponding to each abnormal category affected by the air environment and soil environment, and determine the sampling quantity of each pest and disease area corresponding to each abnormal category.

[0009] Step 3. Classify the degree of abnormality according to the number of samples taken, and determine the sampling locations in each pest and disease area corresponding to each abnormality category.

[0010] Step 4: Use the sampling equipment carried by the drone to puncture and sample each sampling location in each pest and disease area corresponding to each abnormal category, and temporarily store and mark the sampled leaf information according to the address range.

[0011] Step 5. After exporting the sampled leaves, perform secondary image analysis and physiological and biochemical index determination before physiological and biochemical experiments to generate a mapping relationship between leaf characteristics and environmental data.

[0012] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The present invention simultaneously acquires soil dynamic environmental data and air dynamic environmental data, constructs dual-source environmental compensation weights for integrated analysis, and explores the potential relationship between environmental data and leaf characteristics. This intelligent analysis method can more deeply understand the occurrence mechanism and law of crop diseases and insect pests, more accurately identify the ecological heterogeneity of disease-pest related areas, improve the scientificity and representativeness of sampling, and thus provide more effective decision-making support for the prevention and control of diseases and insect pests.

[0013] (2) The present invention determines the number of samples to be taken in different sampling areas within the farmland by differentiation, and optimizes the sampling positions within the area according to the degree of abnormality of the growth points of the abnormal plants, thereby achieving dynamic adjustment of the sampling strategy and avoiding the limitations of the traditional fixed sampling method. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0015] Figure 1 The present invention is a schematic flow chart of the steps for implementing the method.

[0016] Figure 2 It is a schematic diagram of constructing the space coordinate system of the present invention.

[0017] Figure 3 This is a structural diagram showing the sampling equipment carried by the drone of the present invention.

[0018] Figure numerals: 1. reference plane, 2. spatial height plane, 3. sampling arm component, 4. puncture tube component, 5. guide rail component, 6. storage device. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0020] See also Figure 1 As shown, the present invention provides an intelligent sampling, detection and analysis method for crop diseases and insect pests, the method comprising the following steps: step 1, using an unmanned aerial vehicle equipped with a spectral device and a positioning device, screening out abnormal plant growth points in the leaf surface reflection band through spectral analysis, and marking the point cloud information of each abnormal plant growth point, including point cloud coordinates, abnormal category and abnormal degree.

[0021] In the implementation, the spectral analysis is used to screen out the abnormal plant growth points in the leaf surface reflection band, and the point cloud information of each abnormal plant growth point is marked, including: constructing a corresponding spectral characteristic band adaptation library for each abnormal category of crops, and each abnormal category includes each growth defect category and each disease defect category. Among them, the growth defect category refers to the height, thickness and other dimensions of the crop plant during the growth cycle that do not conform to the standard dimensions of this cycle, and the disease defect category refers to the leaf defects and fungal erosion of the crop plant due to insect erosion or bacterial production.

[0022] Specifically, the adaptation library of spectral characteristic bands corresponding to various abnormal categories of crops includes characteristic bands of various growth defect categories and characteristic bands of various disease defect categories, wherein each growth defect category includes a plant height defect category, a coarseness defect category, etc., and each disease defect category includes a curling defect category, a yellowing defect category, a rust defect category, etc.

[0023] See also Figure 2 As shown, whether the reflection band of crop leaves belongs to the corresponding spectral characteristic band of the abnormal category in the adaptation library is identified according to the difference in spectral reflection characteristics, and the point cloud position statistics of the crop leaves belonging to the corresponding spectral characteristic band of the abnormal category are performed using a positioning device to generate each point cloud coordinate, which is defined as the point cloud coordinate of each abnormal plant growth point, and the abnormal category of each abnormal plant growth point is marked. The point cloud coordinates use the ground plane as the reference plane (xy coordinate system), and any vertical plane of the reference plane is the spatial height plane (yz coordinate system) to construct an xyz spatial coordinate system.

[0024] By extracting the corresponding spectral characteristic bands of the growth points of each abnormal plant, the abnormal degree of each abnormal plant growth point can be determined. Specifically, the spectral data of the growth point of a healthy plant can be selected as a reference standard, and the degree of abnormality can be evaluated by comparing the spectral differences between abnormal plants and healthy plants in the characteristic bands. For example, the difference in spectral reflectance in the characteristic band is calculated as an indicator to measure the degree of abnormality.

[0025] It should be noted that the spectral equipment is an instrument used to measure the intensity distribution of light with wavelength. Its principle mainly involves the dispersion of light, detection and conversion of optical signals, and other processes. There are obvious differences in spectral reflectance between normal plant leaves and leaves that suffer from pests and diseases or have growth defects. For example, the adaptation library records the typical reflectance spectral characteristics of healthy wheat leaves in the visible light band (400-760nm) and the near-infrared band (760-1100nm), as well as the spectral characteristic band range under different abnormal conditions (abnormal items) such as rust infection and water shortage. The spectral equipment was used to measure the spectrum of an actual wheat leaf and obtain its reflectance data at various wavelengths. It was found that the reflectance of this wheat leaf at around 550nm was significantly lower than that of the healthy wheat leaf in the adaptation library, and it was consistent with the low reflectance characteristics of the spectral characteristics of wheat infected with rust recorded in the adaptation library in the 530-570nm band. At the same time, the reflectivity at 800-850nm in the near-infrared band also increased abnormally, which also matches the spectral characteristics of wheat rust infection. Therefore, it can be judged that the reflectance band of this wheat leaf belongs to the spectral characteristic band corresponding to the rust defect category in the adaptation library, and thus it can be determined that this wheat leaf belongs to an abnormal plant growth point, and its abnormal category is the rust defect category.

[0026] In addition, hyperspectral equipment can not only extract spectral information but also spatial information by collecting hyperspectral images. For example, if the thickness of plants is different, their surface texture features will be different, and these texture features will be reflected in the hyperspectral images. The specific method is to obtain the hyperspectral image of the plant, use image analysis technology to analyze the plant texture in the image, extract texture feature parameters such as grayscale co-occurrence matrix and local binary pattern, and judge whether the thickness of the plant is normal by analyzing and comparing these texture feature parameters, and identify whether there is a thickness defect category corresponding to the growth category.

[0027] Step 2: After clustering the point cloud coordinates of the growth points of each abnormal plant, mark the pest and disease areas corresponding to each abnormal category, and deploy sensor nodes to detect the sampling compensation weights of each pest and disease area corresponding to each abnormal category affected by the air environment and soil environment, and determine the sampling quantity of each pest and disease area corresponding to each abnormal category.

[0028] In an implementation manner, the point cloud coordinates of each abnormal plant growth point are clustered and divided to mark each pest and disease area corresponding to each abnormal category, including: by aggregating each abnormal plant growth point of the same abnormal category, each abnormal plant growth point corresponding to each abnormal category is obtained.

[0029] According to the point cloud coordinates, all the abnormal plant growth points corresponding to each abnormal category are circled into spatial regions, and the geometric center point of each spatial region is located as the reference point of each abnormal category.

[0030] The Euclidean distance between each reference point and the growth point of the abnormal plant was calculated, and the points whose Euclidean distance exceeded a certain multiple of the mean were regarded as noise points and removed.

[0031] A clustering algorithm is used to perform cluster analysis on the denoised points to form clusters of cluster points corresponding to each abnormal category, and then the areas circled by the cluster points corresponding to each abnormal category are defined as the pest and disease areas corresponding to each abnormal category.

[0032] Through cluster analysis, the growth points of abnormal plants of the same abnormal category are formed into corresponding clusters and pest and disease areas, and the specific distribution areas of different pests and diseases in the farmland are clearly divided, providing a basis for subsequent targeted prevention and control.

[0033] In a further embodiment, the sampling compensation weights of each pest and disease area corresponding to each abnormal category affected by the air environment and the soil environment are detected by deploying sensor nodes, and the sampling quantity of each pest and disease area corresponding to each abnormal category is determined, which includes: step 2-1, counting the number of all abnormal plant growth points corresponding to each abnormal category and the number of point cloud coordinates in each pest and disease area corresponding to each abnormal category, dividing the number of point cloud coordinates in each pest and disease area corresponding to each abnormal category by the number of all abnormal plant growth points corresponding to each abnormal category, and obtaining the sampling quantity ratio of each pest and disease area corresponding to each abnormal category. , Indicates the number of each different category, , Indicates the number of each pest area, .

[0034] step2-2. By deploying a variety of sensor nodes, such as temperature sensors, humidity sensors, etc., the dynamic environmental data of farmland are collected in stages to generate a farmland historical environmental distribution database, which includes the soil dynamic environmental data and air dynamic environmental data that normally appear in different areas of farmland. The soil dynamic environmental data includes variable parameters such as pesticide accumulation content and water accumulation content, and the air dynamic environmental data includes variable parameters such as wind direction, wind speed, sunshine intensity, and rainfall intensity.

[0035] Step 2-3: Determine the soil accumulation structure of each abnormal category corresponding to each pest and disease area based on soil dynamic environmental data, and then analyze the sampling compensation weight of each abnormal category corresponding to each pest and disease area. .

[0036] Step 2-4: Determine the air accumulation structure of each abnormal category corresponding to each pest area based on the air dynamic environment data, and then analyze the second-class sampling compensation weight of each abnormal category corresponding to each pest area .

[0037] Step 2-5: Get the total number of planned samples , determine the number of samples to be taken for each pest and disease area for each abnormal category The total planned sampling quantity is the quantity set by the technicians based on sampling experience, and the actual sampling quantity determined may have a certain error.

[0038] The sampling quantity method for each abnormal category corresponding to each pest and disease area is as follows: , Indicates rounding down. The comprehensive weight of the sampling quantity of each pest and disease area corresponding to each abnormal category is indicated, and the sampling quantity of each pest and disease area corresponding to each abnormal category is determined as follows:

[0039] Table 1: Example of the number of samples for each pest and disease area

[0040]

[0041] In a further implementation, the step 2-3 includes: performing a tendency analysis on the soil dynamic environment data, generating soil accumulation structure and soil tendency data corresponding to each disease and insect pest area of ​​each different category, the soil accumulation structure including pesticide irrigation component accumulation areas, plant excess light areas and light deficiency areas, and soil waterlogging areas, the soil tendency data including the corresponding accumulation amount of pesticide irrigation component accumulation areas, the corresponding excess amount of plant excess light areas and the corresponding deficiency amount of light deficiency areas, and the corresponding waterlogging amount of soil waterlogging areas.

[0042] Specifically, the soil accumulation structure refers to the sub-areas in which each disease and insect pest area of ​​each anomaly category has accumulation of pesticide irrigation components, excessive plant light, lack of light, and soil waterlogging in multiple stages. The soil habit data generated is the mean value of different variable parameters in the soil dynamic environment data in multiple stages.

[0043] After converting the variable parameters contained in the soil habit data into dimensionless form through the normalization method, the corresponding variable parameters of the dimensionless soil habit data are weighted based on the entropy weight method, such as pesticide content 0.4, light 0.3, and water accumulation 0.3, to eliminate the influence of different indicator dimensions and orders of magnitude and make the data comparable.

[0044] After mapping and multiplying the weighted values ​​and the corresponding variable parameters of the dimensionless soil habit data one by one, the soil environmental complexity of each pest and disease area corresponding to each abnormal category is accumulated.

[0045] The soil environment complexity is converted into a probability value ranging from 0 to 1 through the Sigmoid function, which is defined as a sampling compensation weight for each disease and insect pest area corresponding to each heterogeneous category. The greater the complexity of the soil environment, the more diverse the farmland structure, which in turn requires a higher number of crop samples.

[0046] Specifically, the mathematical expression of the Sigmoid function is: , where A is the independent variable, is the probability value, and e is a natural constant.

[0047] In a further implementation, the step 2-4 includes: performing a tendency analysis on the air dynamic environment data to generate air accumulation structures and air tendency data for each anomaly category corresponding to each pest and disease area, wherein the air accumulation structure refers to sub-areas containing hurricanes, sunshine, rainfall and other phenomena in multiple stages corresponding to each anomaly category in each pest and disease area, and the air tendency data is the mean value of different variable parameters in the air dynamic environment data in multiple stages.

[0048] The corresponding variable parameters of the air potential data are normalized, assigned, mapped, multiplied, accumulated and transformed to generate the probability value of the air environment complexity transformation corresponding to each pest and disease area for each abnormal category, which is similar to the above-mentioned soil environment complexity transformation method.

[0049] The farmland spatial compensation structure is obtained, and the position distance of the farmland spatial compensation structure relative to each pest and disease area corresponding to each heterogeneous category is determined. Each position distance is converted into an environmental gradient difference through a spatial interpolation algorithm. The spatial compensation structure includes a tree obstruction structure, a nearby factory structure, etc.

[0050] The spatial interpolation algorithm, such as spline interpolation, processes the distance data to generate a continuous spatial surface, and then divides the environmental gradient difference according to different distance ranges to generate environmental gradient differences in different areas, so that the result is more consistent with the actual geographic spatial distribution.

[0051] The probability value of the air environment complexity conversion corresponding to each pest and disease area according to each abnormal category and environmental gradient difference , determine the second-class sampling compensation weights for each pest and disease area for each abnormal category ,for , Used to reflect the degree of influence of the space compensation structure on the deviation of the air environment complexity.

[0052] Specifically, the obstructions in farmland, such as trees and buildings, will lead to uneven spatial distribution of environmental factors such as light, temperature, and humidity in the farmland, increasing spatial heterogeneity. In order to accurately reflect the impact of this heterogeneity on research objects such as pests and diseases, it is necessary to increase the number of samples to cover samples in areas with different degrees of obstruction. At the same time, suitable temperature and humidity are important conditions for the breeding and spread of pests and diseases. Slight changes in temperature and humidity may lead to significant differences in the degree of occurrence of pests and diseases. In order to timely grasp the relationship between the occurrence of pests and diseases and temperature and humidity, it is necessary to increase the sampling frequency and number in complex environmental areas with large changes in temperature and humidity.

[0053] The present invention simultaneously acquires soil dynamic environmental data and air dynamic data, constructs dual-source environmental compensation weights for integrated analysis, and explores the potential relationship between environmental data and leaf characteristics. This intelligent analysis method can provide a deeper understanding of the occurrence mechanism and laws of crop diseases and pests, more accurately identify the ecological heterogeneity of disease- and pest-related areas, improve the scientificity and representativeness of sampling, and thus provide more effective decision-making support for the prevention and control of diseases and pests.

[0054] Step 3. Classify the degree of abnormality according to the number of samples taken, and determine the sampling locations in each pest and disease area corresponding to each abnormality category.

[0055] In an implementation manner, the abnormality degree is divided into grades according to the number of samples, and each sampling location in each pest and disease area corresponding to each abnormality category is determined, including: obtaining the corresponding leaf area of ​​the abnormal plant growth point in each area, and setting an area threshold to eliminate the abnormal plant growth points whose leaf area is lower than the area threshold.

[0056] According to the number of samples taken, all abnormal plant growth points in each abnormal category corresponding to each pest and disease area after the removal operation are divided into abnormality levels. Specifically, the number of samples taken is equivalent to the number of abnormality levels. The abnormality levels can be divided into level 0, level 1, level 2, level 3..., and the healthy leaves in the area are taken as the initial level, that is, level 0 is taken as the healthy leaf level. Samples with different abnormality levels can be obtained, so as to obtain a series of continuous and graded data in subsequent biochemical tests.

[0057] An abnormal plant growth point with different abnormality levels in each area is selected respectively, and the sampling positions of each abnormal category corresponding to each pest and disease area are obtained by counting. For example, if the number of samples of a certain abnormal category corresponding to a certain pest and disease area is 10, then the healthy leaves are set to level 0, and then an abnormal plant growth point with leaves at level 0, level 1, level 2...level 10 is selected respectively, and 10 sampling positions of the abnormal category corresponding to the pest and disease area are obtained.

[0058] In the above implementation, by obtaining the integrity of the leaves and setting a threshold to eliminate abnormal plant growth points with low integrity, it can be ensured that the sample leaves used for biochemical determination have a certain integrity and stability in structure and function, and only leaves with a certain integrity can more accurately reflect their biochemical characteristics in normal physiological state or under the influence of pests and diseases, avoiding abnormal fluctuations in biochemical indicators due to severe leaf damage, which affects the accuracy and reliability of the determination results. With healthy leaves as level 0, plant growth points with different abnormalities are selected according to the level classification, so that the samples cover various states from health to different degrees of pests and diseases, which matches the needs of subsequent biochemical determination to study the effects of pests and diseases on plant physiology and biochemistry, and can comprehensively analyze the changes in biochemical indicators in plants at different stages of pest and disease development.

[0059] The present invention determines the sampling quantity of different sampling areas in the farmland by differentiation, and optimizes the sampling position in the area according to the abnormality level of the abnormal plant growth point, thereby realizing dynamic adjustment of the sampling strategy and avoiding the limitations of the traditional fixed sampling method.

[0060] Step 4: Use the sampling equipment carried by the drone to puncture and sample each sampling location in each pest and disease area corresponding to each abnormal category, and temporarily store and mark the sampled leaf information according to the address range.

[0061] See also Figure 3 As shown, in an embodiment, the sampling device includes a sampling arm component, a puncture cylinder component, a guide rail component and a storage device.

[0062] In a further embodiment, the sampling device carried by the drone is used to puncture and sample each sampling position in each pest and disease area corresponding to each anomaly category, and the sampled leaf information is temporarily stored and marked according to the address range. The specific content is: after the puncture tube component is sent to each sampling position by the sampling arm component, the puncture tube component is used to puncture and sample the plant leaves at each sampling position to obtain the sampling leaves, and then the sampling leaves are sent to the memory through the guide rail component, and the address range of the sampling leaves in each pest and disease area corresponding to each anomaly category is divided and marked in the memory, so that the sampling leaves in each same area form a leaf group, and the corresponding sampling leaf information of each sampling position is marked through the memory, and the sampling leaf information includes environmental information and growth defect information.

[0063] The environmental information includes soil dynamic environmental data and air dynamic environmental data, and the growth defect information includes abnormality type and abnormality degree.

[0064] Step 5. After exporting the sampled leaves, perform secondary image analysis and physiological and biochemical index determination before physiological and biochemical experiments to generate a mapping relationship between leaf characteristics and environmental data.

[0065] In an implementation manner, after the sampled leaves are exported, secondary image analysis and physiological and biochemical index determination are performed before physiological and biochemical experiments to generate a mapping relationship between leaf characteristics and environmental data, including: sequentially exporting leaf groups in different regions according to address ranges.

[0066] The morphological feature data, color feature data and texture feature data of each sampled leaf are detected to generate a corresponding sampling feature set of leaf groups corresponding to each pest and disease area for each abnormal category.

[0067] The morphological feature data include leaf area, leaf shape, etc., the color feature data include chlorophyll content-related color values, other pigment content-related color values, and the texture feature data include surface roughness, leaf vein characteristics, etc.

[0068] Physiological and biochemical indicators of each leaf group were measured to generate a corresponding biochemical characteristic set of leaf groups of each category corresponding to each pest and disease area, which included photosynthetic physiological indicators (such as chlorophyll content, photosynthetic gas exchange parameters, fluorescence parameters), nutritional indicators (such as nitrogen, phosphorus, potassium content and trace element content), and stress resistance related indicators (such as antioxidant enzyme activity and osmotic regulation substance content).

[0069] The corresponding sampling feature set of each leaf group and the sampled leaf information are used as the training model import data, and the biochemical feature set is used as the export data, and then a mapping relationship from leaf features and environmental data to biochemical features is established in the training model.

[0070] In the above implementation, by establishing a training model, it is helpful to gain a deeper understanding of the growth and development mechanism of crops, reveal the intrinsic relationship between leaf characteristics, environmental factors and biochemical characteristics, provide a theoretical basis for agricultural scientific research, and promote the development of basic agricultural research. For example, based on the training model, it can be learned that in a specific environment, the chlorophyll content of leaves with certain color and texture characteristics is usually in what range.

[0071] The above contents are merely examples and explanations of the concept of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. A method for intelligent sampling, detection and analysis of crop pests and diseases, characterized in that: The method comprises the following steps: Step 1: Use drones equipped with spectral equipment and positioning equipment to screen out abnormal plant growth points in the leaf surface reflection band through spectral analysis, and mark the point cloud information of each abnormal plant growth point, including point cloud coordinates, abnormality category and abnormality degree; Step 2: After clustering the point cloud coordinates of the growth points of each abnormal plant, mark the pest and disease areas corresponding to each abnormal category, and deploy sensor nodes to detect the sampling compensation weights of each pest and disease area corresponding to each abnormal category affected by the air environment and soil environment, and determine the sampling quantity of each pest and disease area corresponding to each abnormal category; Step 3: Classify the degree of abnormality according to the number of samples, and determine the sampling locations in each pest and disease area corresponding to each abnormality category; Step 4: Use the drone equipped with sampling equipment to puncture and sample each sampling location in each pest and disease area of ​​each abnormal category, and temporarily store and mark the sampled leaf information according to the address range; Step 5. After exporting the sampled leaves, perform secondary image analysis and physiological and biochemical index determination before physiological and biochemical experiments to generate a mapping relationship between leaf characteristics and environmental data.

2. The method for intelligent sampling, detection and analysis of crop pests and diseases according to claim 1, characterized in that: The method of screening out abnormal plant growth points in the leaf surface reflection band through spectral analysis and marking point cloud information of each abnormal plant growth point includes: Construct a library of spectral characteristic band adaptations for different types of crops; According to the difference in spectral reflectance characteristics, it is identified whether the reflection band of the crop leaves belongs to the corresponding spectral characteristic band of the abnormal category in the adaptation library, and the positioning equipment is used to perform point cloud position statistics on the crop leaves belonging to the corresponding spectral characteristic band of the abnormal category, and each point cloud coordinate is generated, which is defined as the point cloud coordinate of each abnormal plant growth point, and the abnormal category of each abnormal plant growth point is marked; By extracting the corresponding spectral characteristic bands of the growth points of various abnormal plants, the abnormal degree of the growth points of various abnormal plants can be determined.

3. The intelligent sampling, detection and analysis method for crop pests and diseases according to claim 2 is characterized in that: After clustering the point cloud coordinates of the growth points of each abnormal plant, the pest and disease areas corresponding to each abnormal category are marked, including: By gathering the growth points of different plants of the same different category, the growth points of different plants corresponding to different categories are obtained; According to the point cloud coordinates, all the abnormal plant growth points corresponding to each abnormal category are circled into spatial regions, and the geometric center point of each spatial region is located as the reference point of each abnormal category; Calculate the Euclidean distance between each reference point and the growth point of the abnormal plant, and remove the points whose Euclidean distance exceeds a certain multiple of the mean as noise points; A clustering algorithm is used to perform cluster analysis on the denoised points to form clusters of cluster points corresponding to each abnormal category, and then the areas circled by the cluster points corresponding to each abnormal category are defined as the pest and disease areas corresponding to each abnormal category.

4. The method for intelligent sampling, detection and analysis of crop pests and diseases according to claim 1, characterized in that: The method of deploying sensor nodes to detect the sampling compensation weights of the pest and disease areas corresponding to each abnormal category affected by the air environment and the soil environment, and determining the sampling quantity of each pest and disease area corresponding to each abnormal category, includes: Step 2-1, count the number of all abnormal plant growth points corresponding to each abnormal category and the number of point cloud coordinates in each pest and disease area corresponding to each abnormal category, and generate the proportion of the number of samples corresponding to each pest and disease area for each abnormal category; Step 2-2, by deploying a variety of sensor nodes, the dynamic environmental data of farmland is collected periodically to generate a farmland historical environmental distribution database, which includes the soil dynamic environmental data and air dynamic environmental data that normally appear in different areas of the farmland; Step 2-3, determine the soil accumulation structure of each abnormal category corresponding to each pest and disease area based on soil dynamic environmental data, and then analyze the sampling compensation weight of each abnormal category corresponding to each pest and disease area; Step 2-4: Determine the air accumulation structure of each abnormal category corresponding to each pest and disease area based on the air dynamic environment data, and then analyze the second-class sampling compensation weight of each abnormal category corresponding to each pest and disease area; Step 2-5, obtain the total planned sampling quantity and determine the sampling quantity for each anomaly category corresponding to each pest and disease area.

5. The method for intelligent sampling, detection and analysis of crop pests and diseases according to claim 4, characterized in that: The step 2-3 includes: Performing habit analysis on soil dynamic environment data to generate soil accumulation structure and soil habit data corresponding to each pest and disease area of ​​each abnormal category, wherein the soil accumulation structure includes pesticide irrigation component accumulation area, plant excessive light area and light deficiency area, and soil water accumulation area, and the soil habit data includes the corresponding accumulation amount of pesticide irrigation component accumulation area, the corresponding excess amount of plant excessive light area and the corresponding deficiency amount of light deficiency area, and the corresponding water accumulation amount of soil water accumulation area; After the variable parameters contained in the soil habit data are converted into dimensionless form by normalization method, the corresponding variable parameters of the dimensionless soil habit data are weighted based on the entropy weight method; After mapping and multiplying the weighted values ​​and the corresponding variable parameters of the dimensionless soil habit data one by one, the soil environmental complexity of each disease and insect pest area corresponding to each abnormal category is accumulated; The soil environmental complexity was converted into a probability value ranging from 0 to 1 through the Sigmoid function, which was defined as a sampling compensation weight for each anomaly category corresponding to each pest and disease area.

6. The method for intelligent sampling, detection and analysis of crop pests and diseases according to claim 5, characterized in that: Step 2-4 includes: Conduct a trend analysis on the dynamic air environment data to generate the air accumulation structure and air trend data corresponding to each pest and disease area of ​​each category; Normalize, assign values, map products, accumulate and transform the corresponding variable parameters of the air habitus data to generate the probability value of the air environment complexity transformation corresponding to each pest and disease area for each abnormal category; Obtain the farmland spatial compensation structure, determine the location distance of the farmland spatial compensation structure relative to each pest and disease area corresponding to each heterogeneous category, and convert each location distance into an environmental gradient difference through a spatial interpolation algorithm; According to the probability value of the transformation of the air environment complexity of each anomaly category corresponding to each pest and disease area and the difference in environmental gradient, the second-category sampling compensation weight of each anomaly category corresponding to each pest and disease area is determined.

7. The method for intelligent sampling, detection and analysis of crop pests and diseases according to claim 1, characterized in that: The abnormality degree is divided into grades according to the number of samples, and the sampling locations in each pest and disease area corresponding to each abnormality category are determined, including: Obtain the corresponding leaf areas of abnormal plant growth points in each region, set an area threshold, and remove abnormal plant growth points whose leaf areas are lower than the area threshold; According to the number of samples, all abnormal plant growth points after culling in each pest and disease area of ​​each abnormal category are classified into abnormal degree levels; An abnormal plant growth point with different abnormality levels in each area is selected respectively, and the sampling positions of each abnormality category corresponding to each pest and disease area are statistically obtained.

8. The intelligent sampling, detection and analysis method for crop pests and diseases according to claim 1, characterized in that: The sampling device comprises a sampling arm component, a puncture cylinder component, a guide rail component and a storage device.

9. The intelligent sampling, detection and analysis method for crop pests and diseases according to claim 8, characterized in that: The method uses a sampling device mounted on an unmanned aerial vehicle to perform puncture sampling on each sampling position in each pest and disease area corresponding to each abnormal category, and temporarily stores and marks the sampled leaf information according to the address range. The specific content is: after the puncture tube component is sent to each sampling position by the sampling arm component, the puncture tube component is used to puncture and sample the plant leaves at each sampling position to obtain the sampled leaves, and then the sampled leaves are sent to the memory through the guide rail component. In the memory, the address range of the sampled leaves in each pest and disease area corresponding to each abnormal category is divided and marked, so that the sampled leaves in each same area form a leaf group, and the corresponding sampled leaf information of each sampling position is marked through the memory, and the sampled leaf information includes environmental information and growth defect information.

10. The method for intelligent sampling, detection and analysis of crop pests and diseases according to claim 9, characterized in that: After the sampled leaves are exported, secondary image analysis and physiological and biochemical index determination are performed before the physiological and biochemical experiment to generate a mapping relationship between leaf characteristics and environmental data, including: Export leaf groups in different regions sequentially by address range; Detect the morphological feature data, color feature data and texture feature data of each sampled leaf, and generate a corresponding sampling feature set of leaf groups corresponding to each pest and disease area for each abnormal category; The physiological and biochemical indexes of each leaf group were measured to generate the corresponding biochemical characteristic set of leaf groups of each heterogeneous category corresponding to each pest and disease area; The corresponding sampling feature set of each leaf group and the sampled leaf information are used as the training model import data, and the biochemical feature set is used as the export data, and then a mapping relationship from leaf features and environmental data to biochemical features is established in the training model.

Images