Garden disease prevention and control system based on spectral image

Abstract

The invention discloses a garden disease prevention and control system based on spectral images. The garden disease prevention and control system comprises an environment sample collection module, a disease feature extraction module, a disease track prediction module and a disease area grade module. The environment sample acquisition module is used for acquiring garden image data under different time periods, different weather conditions, different temperatures and different humidity to obtain corresponding observation data; the disease feature extraction module is used for extracting disease feature data of the observation data; the disease trajectory prediction module is used for constructing a trajectory prediction model to predict a disease area evaluation value and a disease route; and the disease area grade module is used for calculating the area overlapping degree and the route overlapping degree of the disease area evaluation value and the disease route, dividing the garden into different disease area grades according to the area overlapping degree and the route overlapping degree, and predicting the future disease condition of the garden area. The requirements of plant disease prevention and control under different natural environment factors can be met.

Description

Technical Field

[0001] The present invention relates to the technical field of disease prevention and control, and in particular to a garden disease prevention and control system based on spectral images. Background Art

[0002] In recent years, with the development of green and healthy concepts, the importance of green plants has become increasingly apparent. However, in the process of plant growth and development, plants often suffer losses due to various natural disasters, and pests and diseases are one of the important factors. Pests and diseases refer to forest plants in the process of their growth and development or their products and propagation materials in the storage and transportation process. They are infected by other organisms or affected by unsuitable environmental conditions, and the normal functions of their physiological processes are disturbed and destroyed, resulting in a series of abnormal physiological, organizational and morphological conditions of the plants, poor growth and development, and even death of the entire plant, ultimately causing economic losses and other losses to mankind. This phenomenon has both ecological and economic benefits. Therefore, timely and effective prevention and control of economic forest pests and diseases to ensure the health of the trees is the key to achieving good benefits.

[0003] At present, Chinese patent publication number CN 116740378 B discloses a garden pest evaluation system based on image processing, including an image acquisition module for acquiring images of plants in a garden area, a database module for storing leaf information of plants in the garden area, a detection module for detecting information of the plant images acquired by the image acquisition module, and a central control module for determining, according to the proportion of fitting contours measured by the detection module, that a single leaf is a tender leaf when it does not meet a preset standard, or that the leaf has pests and diseases, and determining the standard of the leaf having pests based on whether there is a concave edge contour. It can be seen that it is impossible to predict areas of future plant garden pests, and it is impossible to analyze target pest key prevention and control areas for various types of pests based on natural environmental factors. Summary of the invention

[0004] The technical problem solved by the present invention is that it is impossible to predict the area of ​​future plant garden pests and it is impossible to analyze the target pest key prevention and control areas of various types of pests according to natural environmental factors.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a garden disease prevention and control system based on spectral images, including an environmental sample collection module, a disease feature extraction module, a disease trajectory prediction module and a disease area grade module; The environmental sample collection module is used to collect garden image data under different time periods, different weather conditions, different temperatures and different humidity to obtain corresponding observation data; The disease feature extraction module is used to extract disease feature data of the observed data; The disease trajectory prediction module is used to construct a trajectory prediction model to predict the disease area evaluation value and the disease route; The diseased area grade module is used to calculate the diseased area evaluation value and the area overlap and route overlap of the diseased routes, and divide the garden into different diseased area grades according to the area overlap and route overlap.

[0006] As a preferred solution of the garden disease prevention and control system based on spectral images described in the present invention, wherein: using an ordinary camera to collect N groups of garden image data in the same time period, weather conditions, temperature and humidity; Collect L groups of garden image data under different time periods, different weather conditions, different temperatures and different humidity; Each of the L groups of garden image data is set as a group of observation data; The different time periods include daytime time periods and nighttime time periods; The different weather conditions include sunny conditions, cloudy conditions and rainy conditions.

[0007] As a preferred solution of the garden disease prevention and control system based on spectral images described in the present invention, wherein: the disease feature extraction module is used to extract disease feature data of the observed data, and the disease features include garden plant contour features and pest thermal external force features; Extracting the outline features of the garden plants specifically includes: Using an edge detection algorithm to perform edge recognition on the garden image data of the observation data, detect the edge shape of the leaf, and obtain the garden plant contour features of the leaf; Extracting the pest thermal external force characteristics specifically includes: Use a spectrometer camera to photograph N groups of garden areas and obtain the pest thermal external force characteristics corresponding to all observation data; The garden plant contour features include area data and defect shape data of leaf defects; The pest thermal external force characteristics include pest shape data, size data, and quantity data of the pests.

[0008] As a preferred solution of the garden disease prevention and control system based on spectral images described in the present invention, wherein: the disease trajectory prediction module is used to construct a trajectory prediction model to predict the disease area evaluation value and the disease route; The specific process of establishing the trajectory prediction model is as follows: Using the initial position data, initial speed data, initial direction data and environmental parameter data of the pest as inputs of the trajectory prediction model; The output of the trajectory prediction model is the flight speed data, flight direction data and flight altitude data of the pests under different time periods, different weather conditions, different temperatures and different humidity; The flight speed data, flight direction data and flight altitude data are input into a trajectory prediction model to obtain the disease route of the corresponding pest.

[0009] As a preferred solution of the garden disease prevention and control system based on spectral images described in the present invention, the process of obtaining the initial position data, initial speed data, initial direction data and environmental parameter data is as follows: Retrieving comparison data in the data storage center platform, the comparison data including pest leaf shape defect comparison data and pest infrared information comparison data; Compare the area data and the shape data of the leaf defects with the comparison data of the shape defects of the leaf caused by the pests on the data storage center platform to determine whether the leaf defects are caused by the pests; If the leaf defect is caused by pests, determine the location of the leaf defect and obtain initial location data of the pests; If the leaf defect is not caused by pests, the location of the leaf defect is ignored; Acquire two initial position data that are the same as the area data of the blade defect and the blade shape data, wherein the two initial position data include first initial position data and second initial position data, and acquire first time point data and second time point data when the first initial position data and the second initial position data are acquired; Initial speed data = first initial position data - second initial position data / first time point data - second time point data; The posture of the pest is determined according to the shape data of the leaf defect to obtain the initial direction data of the pest; the environmental parameter data includes time period data, weather conditions, temperature and humidity data of different time periods, different weather conditions, different temperatures and different humidities.

[0010] As a preferred solution of the garden disease prevention and control system based on spectral images described in the present invention, the pest infrared information comparison data is compared with the pest shape data, size data, and quantity data to determine the type of pest, the age of the pest, and the number of pests of each type and age.

[0011] As a preferred solution of the garden disease prevention and control system based on spectral images described in the present invention, wherein: the flight speed data, flight direction data, flight altitude data, the type of pests, the age of pests and the number of pests of each type and age are input into a trajectory prediction model to obtain the disease route of the corresponding pests; the route extension speed of the disease route is determined according to the flight speed data; Determine the extension direction of the disease route according to the flight direction data; Determine the line extension height of the diseased route according to the flight altitude data; Determine the disease route of the corresponding pest according to the route extension speed, route extension direction and route extension height; The evaluation value of the diseased area of ​​the corresponding pests is determined according to the type of the pests, the age of the pests and the number of pests of each type and age.

[0012] As a preferred solution of the garden disease prevention and control system based on spectral images described in the present invention, the mathematical expression of the disease area evaluation value is: ; Where D represents the disease area evaluation value, set X 1 =0.64,X 1 represents the pest type coefficient, set X 2 =0.82,X 2 Indicates the pest age coefficient, set X 3 =0.91,X 3 represents the pest population coefficient, H 1 Indicates the pest type, H 2 Indicates the age of the pest, H 3 Indicates the number of pests.

[0013] As a preferred solution of the garden disease prevention and control system based on spectral images of the present invention, wherein: marking N groups of garden image data as area data of the leaf defects judged to be caused by pests, and obtaining initial area data A and initial position data C; Obtain the disease area evaluation value and the disease route overlapping times B and the disease route overlapping times T corresponding to the N groups of garden image data; The mathematical expression for calculating the area overlap of the disease area evaluation value is: ; Where M represents the area overlap, set V 1 =0.75, V 2 =0.43, V 3 =0.66, A represents the initial area data, B represents the number of overlapping diseased areas, and D represents the diseased area evaluation value; The mathematical expression for calculating the route overlap of the disease route is: ; Among them, Y represents the route overlap, and R is set 1 =0.96, set R 2=0.77, C represents the initial position data, and T represents the number of overlapping disease routes.

[0014] As a preferred solution of the garden disease prevention and control system based on spectral images described in the present invention, wherein: the area overlap is compared with a set area overlap threshold; When the area overlap is less than the area overlap threshold, it is recorded as the first area comparison result; When the area overlap is greater than the area overlap threshold, it is recorded as the second area comparison result; Compare the line overlap with the set area overlap threshold; When the line overlap is less than the line overlap threshold, it is recorded as the first line comparison result; When the line overlap is greater than the line overlap threshold, it is recorded as the second line comparison result; When the group of garden areas is the second area comparison result and the second line comparison result, the area is the first disease area; When the group of garden areas is the first area comparison result and the second line comparison result, the area is the second most dangerous disease area; When the group of garden areas is the second area comparison result and the first line comparison result, the area is the third disease area; When the group of garden areas is the first area comparison result and the first line comparison result, the area is the fourth disease area.

[0015] The beneficial effects of the present invention are as follows: by collecting N garden image data under different time periods, different weather conditions, different temperatures and different humidity, using an edge detection algorithm to extract garden plant contour features, using a spectrometer camera to shoot L groups of garden areas, the pest thermal external force features of each group of garden areas can be obtained, and the garden plant contour features can be used to determine whether the defects of plant leaves in the garden area are caused by pests and the size and position of the leaf defect area, and the type of pests, the age of pests and the number of pests of each type and age can be determined by extracting pest thermal external force feature data, and a pest trajectory prediction model is constructed to predict the pest disease trajectory and the pest disease area under different natural environmental factors, and the number of pest trajectories and the number of diseased areas of each group of N garden areas passing through other areas of the pest trajectory and the number of diseased area overlaps are counted, and the original leaf defect area and position of the group of garden areas are integrated to calculate the area overlap and line overlap of the group of garden areas, so that not only the current garden plant disease situation can be detected, but also the future disease situation of the group of garden areas can be predicted, and the needs of plant disease prevention and control under different natural environmental factors can be met, so that the detection and prevention of plant diseases are more comprehensive. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1A schematic diagram of the basic process of a garden disease prevention and control system based on spectral images provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0017] 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 drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0018] Example, see Figure 1 , which is an embodiment of the present invention, provides a garden disease prevention and control system based on spectral images, including an environmental sample collection module, a disease feature extraction module, a disease trajectory prediction module and a disease area grade module; The environmental sample collection module is used to collect garden image data under different time periods, different weather conditions, different temperatures and different humidity to obtain corresponding observation data; The disease feature extraction module is used to extract disease feature data of the observed data; The disease trajectory prediction module is used to construct a trajectory prediction model to predict the disease area evaluation value and the disease route; The diseased area grade module is used to calculate the diseased area evaluation value and the area overlap and route overlap of the diseased routes, and divide the garden into different diseased area grades according to the area overlap and route overlap.

[0019] Use ordinary cameras to collect N groups of garden image data under the same time period, weather conditions, temperature and humidity; Collect L groups of garden image data under different time periods, different weather conditions, different temperatures and different humidity; Each of the L groups of garden image data is set as a group of observation data; The different time periods include daytime time periods and nighttime time periods; The different weather conditions include sunny conditions, cloudy conditions and rainy conditions.

[0020] In this embodiment, the garden to be inspected is divided into N groups of areas, and garden image data of the N groups of areas in the same time period, same weather conditions, same temperature and same humidity are collected respectively. At this time, the natural environmental factors of each group of garden image data are the same, and L groups of garden image data with different natural environmental factors are collected respectively to obtain L groups of observation data, and each group of observation data includes N groups of garden image data.

[0021] The disease feature extraction module is used to extract disease feature data of the observation data, wherein the disease features include garden plant outline features and pest thermal external force features; Extracting the outline features of the garden plants specifically includes: Using an edge detection algorithm to perform edge recognition on the garden image data of the observation data, detect the edge shape of the leaf, and obtain the garden plant contour features of the leaf; Extracting the pest thermal external force characteristics specifically includes: Use a spectrometer camera to photograph N groups of garden areas and obtain the pest thermal external force characteristics corresponding to all observation data; The garden plant contour features include area data and defect shape data of leaf defects; The pest thermal external force characteristics include pest shape data, size data, and quantity data of the pests.

[0022] In this embodiment, the contour features of the garden plants themselves and the thermal external force features of the pests on the surface of the plants are collected respectively, so as to obtain the area size and shape of the defects of the plants. The thermal external force information of the pests on the surface of the plants is extracted, so as to obtain the shape data, size data and quantity data of the pests.

[0023] The disease trajectory prediction module is used to construct a trajectory prediction model to predict the disease area evaluation value and the disease route; The specific process of establishing the trajectory prediction model is as follows: Using the initial position data, initial speed data, initial direction data and environmental parameter data of the pest as inputs of the trajectory prediction model; The output of the trajectory prediction model is the flight speed data, flight direction data and flight altitude data of the pests under different time periods, different weather conditions, different temperatures and different humidity; The flight speed data, flight direction data and flight altitude data are input into a trajectory prediction model to obtain the disease route of the corresponding pest.

[0024] In this embodiment, the living habits of pests are different in different time periods, different weather conditions, different temperatures and different humidities. Insects are sensitive to specific temperatures, which may affect their physiological activities and reproductive capacity. Insects have a specific survival temperature range, within which they can grow and reproduce normally. Exceeding this range will cause the insects to have a decreased activity or even die. Within a suitable temperature range, an increase in temperature can accelerate the development of insects and shorten their lifespan relatively, while a decrease in temperature will slow down the development of insects and extend their lifespan relatively. A large temperature difference between day and night may cause the insects to be inactive or enter a dormant state. Establishing a trajectory prediction model can predict the flight speed data, flight direction data and flight altitude data of pests in different natural environments, thereby obtaining the future flight route of the pests.

[0025] The process of obtaining the initial position data, initial velocity data, initial direction data and environmental parameter data is as follows: Retrieving comparison data in the data storage center platform, the comparison data including pest leaf shape defect comparison data and pest infrared information comparison data; Compare the area data and the shape data of the leaf defects with the comparison data of the shape defects of the leaf caused by the pests on the data storage center platform to determine whether the leaf defects are caused by the pests; If the leaf defect is caused by pests, determine the location of the leaf defect and obtain initial location data of the pests; If the leaf defect is not caused by pests, the location of the leaf defect is ignored; Acquire two initial position data that are the same as the area data of the blade defect and the blade shape data, wherein the two initial position data include first initial position data and second initial position data, and acquire first time point data and second time point data when the first initial position data and the second initial position data are acquired; Initial speed data = first initial position data - second initial position data / first time point data - second time point data; Determining the posture of the pest according to the shape data of the leaf defect, and obtaining the initial direction number of the pest; The environmental parameter data includes time period data, weather conditions, temperature and humidity data of different time periods, different weather conditions, different temperatures and different humidities.

[0026] In this embodiment, leaf defects of garden plants are not necessarily caused by pests, so it is necessary to first retrieve the pest leaf shape defect comparison data and pest infrared information in the data storage center platform to compare with the actual area data and leaf shape data to determine whether it is indeed caused by pests. The data storage center platform stores the pest leaf shape defect comparison data and the pest infrared information comparison data. The pest leaf shape defect comparison data and the pest infrared information comparison data specifically include pictures of garden plants, insects and corresponding edge contour data, animal infrared thermal data, and disease data corresponding to plant shapes.

[0027] The pest infrared information comparison data is compared with the pest shape data, size data, and quantity data to determine the type of pest, the age of the pest, and the number of pests of each type and age.

[0028] In this embodiment, different pests have different shape data and size data. The type of pest, the age of the pest and the number of pests of each type and age can be determined based on the infrared information comparison data of the pests. Different pests, different ages of pests and different numbers of pests have different degrees of disease damage to the same plant.

[0029] Inputting the flight speed data, flight direction data, flight altitude data, the type of pests, the age of pests and the number of pests of each type and age into a trajectory prediction model to obtain the disease route of the corresponding pests; determining the route extension speed of the disease route according to the flight speed data; Determine the extension direction of the disease route according to the flight direction data; Determine the line extension height of the diseased route according to the flight altitude data; Determine the disease route of the corresponding pest according to the route extension speed, route extension direction and route extension height; The evaluation value of the diseased area of ​​the corresponding pests is determined according to the type of the pests, the age of the pests and the number of pests of each type and age.

[0030] The mathematical expression of the disease area evaluation value is: ; Where D represents the disease area evaluation value, set X 1 =0.64,X 1 represents the pest type coefficient, set X 2 =0.82,X 2 Indicates the pest age coefficient, set X 3 =0.91,X 3 represents the pest population coefficient, H 1 Indicates the pest type, H 2 Indicates the age of the pest, H 3 Indicates the number of pests.

[0031] In this embodiment, each group of garden areas and different natural environmental factors correspond to different disease area evaluation values. The size of the disease area evaluation value of each group can reflect the degree of pest and disease damage to the garden areas in this group in the future. The larger the disease area evaluation value, the higher the degree of disease damage, and the smaller the disease area evaluation value, the lower the degree of disease damage.

[0032] Marking N groups of garden image data as area data of the leaf defects determined to be caused by pests, and obtaining initial area data A and initial position data C; Obtain the disease area evaluation value and the disease route overlapping times B and the disease route overlapping times T corresponding to the N groups of garden image data; The mathematical expression for calculating the area overlap of the disease area evaluation value is: ; Where M represents the area overlap, set V 1 =0.75, V 2 =0.43, V 3=0.66, A represents the initial area data, B represents the number of overlapping diseased areas, and D represents the diseased area evaluation value; The mathematical expression for calculating the route overlap of the disease route is: ; Among them, Y represents the route overlap, and R is set 1 =0.96, set R 2 =0.77, C represents the initial position data, and T represents the number of overlapping disease routes.

[0033] In this embodiment, each group of garden areas and different natural environmental factors have different area overlaps and line overlaps corresponding to diseases. The area overlap of each group of garden areas is equal to the initial area data of the garden areas currently affected, the disease area evaluation values ​​of other groups of garden areas and the number of overlaps of the disease areas of this group of garden areas. The line overlap of each group of garden areas is equal to the initial position data of the garden areas currently affected and the number of overlaps of the disease routes of other groups of garden areas. The size of the area overlap can reflect the size of the area of ​​the garden areas that will be affected by pests and diseases in the future, and the size of the line overlap can reflect the specific routes of the garden areas that will be affected by pests and diseases in the future.

[0034] Compare the area overlap with the set area overlap threshold; When the area overlap is less than the area overlap threshold, it is recorded as the first area comparison result; When the area overlap is greater than the area overlap threshold, it is recorded as the second area comparison result; Compare the line overlap with the set area overlap threshold; When the line overlap is less than the line overlap threshold, it is recorded as the first line comparison result; When the line overlap is greater than the line overlap threshold, it is recorded as the second line comparison result; When the group of garden areas is the second area comparison result and the second line comparison result, the area is the first disease area; When the group of garden areas is the first area comparison result and the second line comparison result, the area is the second most dangerous disease area; When the group of garden areas is the second area comparison result and the first line comparison result, the area is the third disease area; When the group of garden areas is the first area comparison result and the first line comparison result, the area is the fourth disease area.

[0035] In this embodiment, the area overlap threshold is set to 0.8, the line overlap threshold is set to 0.7, and the diseased area reflects the degree of disease of the group of garden areas in the future caused by pests and diseases. The degree of disease in the first diseased area, the second diseased area, the third diseased area and the fourth diseased area decreases in sequence.

[0036] By collecting N garden image data under different time periods, different weather conditions, different temperatures and different humidity, using edge detection algorithm to extract garden plant contour features, and using spectrometer camera to shoot L groups of garden areas, the pest thermal external force characteristics of each group of garden areas can be obtained. Through the garden plant contour characteristics, it is possible to determine whether the defects of the current plant leaves in the garden area are caused by pests and the size and location of the leaf defect area. Through the extraction of pest thermal external force feature data, the type of pests, the age of pests and the number of pests of each type and age can be determined. A pest trajectory prediction model is constructed to predict the disease trajectory of pests and the disease area of ​​pests under different natural environmental factors. The number of times each garden area of ​​N groups of garden areas passes through other areas and the number of times the disease area overlaps are counted. The original leaf defect area and position of the garden area are integrated to calculate the area overlap and line overlap of the garden area. Not only can the current disease situation of garden plants be detected, but also the future disease situation of the garden area can be predicted. It can adapt to the needs of plant disease prevention and control under different natural environmental factors, making the detection and prevention of plant diseases more comprehensive.

[0037] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0038] 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 preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. The garden disease prevention and control system based on spectral images is characterized by: It includes environmental sample collection module, disease feature extraction module, disease trajectory prediction module and disease area grade module; The environmental sample collection module is used to collect garden image data under different time periods, different weather conditions, different temperatures and different humidity to obtain corresponding observation data; The disease feature extraction module is used to extract disease feature data of the observed data; The disease trajectory prediction module is used to construct a trajectory prediction model to predict the disease area evaluation value and the disease route; The diseased area grade module is used to calculate the diseased area evaluation value and the area overlap and route overlap of the diseased routes, and divide the garden into different diseased area grades according to the area overlap and route overlap.

2. The garden disease prevention and control system based on spectral image according to claim 1, characterized in that: Use cameras to collect N groups of garden image data under the same time period, weather conditions, temperature and humidity; Collect L groups of garden image data under different time periods, different weather conditions, different temperatures and different humidity; Each of the L groups of garden image data is set as a group of observation data; The different time periods include daytime time periods and nighttime time periods; The different weather conditions include sunny conditions, cloudy conditions and rainy conditions.

3. The garden disease prevention and control system based on spectral image according to claim 2, characterized in that: The disease feature extraction module is used to extract disease feature data of the observation data, wherein the disease features include garden plant outline features and pest thermal external force features; Extracting the outline features of the garden plants specifically includes: Using an edge detection algorithm to perform edge recognition on the garden image data of the observation data, detect the edge shape of the leaf, and obtain the garden plant contour features of the leaf; Extracting the pest thermal external force characteristics specifically includes: Use a spectrometer camera to photograph N groups of garden areas and obtain the pest thermal external force characteristics corresponding to all observation data; The garden plant contour features include area data and defect shape data of leaf defects; The pest thermal external force characteristics include pest shape data, size data, and quantity data of the pests.

4. The garden disease prevention and control system based on spectral image according to claim 3, characterized in that: The disease trajectory prediction module is used to construct a trajectory prediction model to predict the disease area evaluation value and the disease route; The specific process of establishing the trajectory prediction model is as follows: Using the initial position data, initial speed data, initial direction data and environmental parameter data of the pest as inputs of the trajectory prediction model; The output of the trajectory prediction model is the flight speed data, flight direction data and flight altitude data of the pests under different time periods, different weather conditions, different temperatures and different humidity; The flight speed data, flight direction data and flight altitude data are input into a trajectory prediction model to obtain the disease route of the corresponding pest.

5. The garden disease prevention and control system based on spectral images according to claim 4, characterized in that: The process of obtaining the initial position data, initial velocity data, initial direction data and environmental parameter data is as follows: Retrieving comparison data in the data storage center platform, the comparison data including pest leaf shape defect comparison data and pest infrared information comparison data; Compare the area data and the shape data of the leaf defects with the comparison data of the shape defects of the leaf caused by the pests on the data storage center platform to determine whether the leaf defects are caused by the pests; If the leaf defect is caused by pests, determine the location of the leaf defect and obtain initial location data of the pests; If the leaf defect is not caused by pests, the location of the leaf defect is ignored; Acquire two initial position data that are the same as the area data of the blade defect and the blade shape data, wherein the two initial position data include first initial position data and second initial position data, and acquire first time point data and second time point data when the first initial position data and the second initial position data are acquired; Initial speed data = (first initial position data - second initial position data) / (first time point data - second time point data); The posture of the pest is determined according to the shape data of the leaf defect, and the initial direction data of the pest is obtained; the environmental parameter data includes time period data, weather conditions, temperature and humidity data of different time periods, different weather conditions, different temperatures and different humidities.

6. The garden disease prevention and control system based on spectral images according to claim 5, characterized in that: The pest infrared information comparison data is compared with the pest shape data, size data, and quantity data to determine the type of pest, the age of the pest, and the number of pests of each type and age.

7. The garden disease prevention and control system based on spectral images according to claim 6, characterized in that: Inputting the flight speed data, flight direction data, flight altitude data, pest type, pest age, and the number of pests of each type and age into a trajectory prediction model to obtain a disease route of the corresponding pest; Determining a route extension speed of the disease route according to the flight speed data; Determine the extension direction of the disease route according to the flight direction data; Determine the line extension height of the diseased route according to the flight altitude data; Determine the disease route of the corresponding pest according to the route extension speed, route extension direction and route extension height; The evaluation value of the diseased area of ​​the corresponding pests is determined according to the type of the pests, the age of the pests and the number of pests of each type and age.

8. The garden disease prevention and control system based on spectral images according to claim 7, characterized in that: The mathematical expression of the disease area evaluation value is: ； Wherein, D represents the disease area evaluation value, X1=0.64 is set, X1 represents the pest type coefficient, X2=0.82 is set, X2 represents the pest age coefficient, X3=0.91 is set, X3 represents the pest quantity coefficient, H1 represents the pest type, H2 represents the pest age, and H3 represents the pest quantity.

9. The garden disease prevention and control system based on spectral images according to claim 8, characterized in that: Marking N groups of garden image data as area data of the leaf defects determined to be caused by pests, and obtaining initial area data A and initial position data C; Obtain the disease area evaluation value and the disease route overlapping times B and the disease route overlapping times T corresponding to the N groups of garden image data; The mathematical expression for calculating the area overlap of the disease area evaluation value is: ； Wherein, M represents the area overlap, V1=0.75, V2=0.43, V3=0.66 are set, A represents the initial area data, B represents the number of overlaps of the diseased area, and D represents the evaluation value of the diseased area; The mathematical expression for calculating the route overlap of the disease route is: ； Among them, Y represents the route overlap, R1 is set to 0.96, R2 is set to 0.77, C represents the initial position data, and T represents the number of times the disease route overlaps.

10. The garden disease prevention and control system based on spectral images according to claim 9, characterized in that: Compare the area overlap with the set area overlap threshold; When the area overlap is less than the area overlap threshold, it is recorded as the first area comparison result; When the area overlap is greater than the area overlap threshold, it is recorded as the second area comparison result; Compare the line overlap with the set area overlap threshold; When the line overlap is less than the line overlap threshold, it is recorded as the first line comparison result; When the line overlap is greater than the line overlap threshold, it is recorded as the second line comparison result; When the group of garden areas is the second area comparison result and the second line comparison result, the area is the first disease area; When the group of garden areas is the first area comparison result and the second line comparison result, the area is the second most dangerous disease area; When the group of garden areas is the second area comparison result and the first line comparison result, the area is the third disease area; When the group of garden areas is the first area comparison result and the first line comparison result, the area is the fourth disease area.

Images