Crop monitoring method and device based on multispectrum, medium and product

Abstract

The invention relates to the technical field of crop monitoring, in particular to a multi-spectrum-based crop monitoring method and device, a medium and a product, and the method comprises the steps: carrying out the flight planning of an unmanned plane based on a farmland monitoring area, determining the flight information, and transmitting the flight information to an unmanned plane terminal which carries out the data collection. Then, in order to improve the accuracy and reliability of the multispectral image data, performing preprocessing based on the multispectral image data to obtain target image data; and performing multi-dimensional monitoring analysis based on the target image data, and determining a crop multi-dimensional monitoring result. And finally, performing visual display based on the crop multi-dimensional monitoring result to obtain a multi-dimensional monitoring display map. The multispectral image data can reveal spectral characteristic changes of crops in different growth stages and under different environmental conditions, and the richer and more comprehensive multispectral image data is used for crop monitoring, so that the accuracy of crop monitoring is improved.

Description

Technical Field

[0001] The present application relates to the technical field of crop monitoring, and in particular to a multi-spectral-based crop monitoring method, equipment, medium and product. Background Art

[0002] In modern agriculture, crop monitoring is a key link to ensure the healthy growth of crops, improve agricultural production efficiency and ensure food security. With the advancement of science and technology, crop monitoring technology has developed from traditional manual inspection to intelligent and automated directions. Spectral analysis technology, as a non-destructive and rapid detection method, has been widely used in the field of crop monitoring.

[0003] In related technologies, a single spectral band sensor is usually used to monitor crops, and the growth status of crops is evaluated by analyzing spectral data. However, due to the singleness of spectral information, the crop monitoring method cannot accurately identify the various growth states and potential problems of crops, resulting in low accuracy of crop monitoring results.

[0004] Therefore, how to improve the accuracy of crop monitoring is an urgent problem to be solved by those skilled in the art. Summary of the invention

[0005] The purpose of this application is to provide a multi-spectral based crop monitoring method, equipment, medium and product to solve at least one of the above technical problems.

[0006] The above invention objectives of the present application are achieved through the following technical solutions: In the first aspect, the present application provides a method for monitoring crops based on multispectral, which adopts the following technical solution: A multi-spectral crop monitoring method, comprising: Acquire a farmland monitoring area, perform drone flight planning based on the farmland monitoring area, determine flight information, and send the flight information to a drone terminal that performs data collection, so as to control the drone terminal equipped with a multispectral sensor to perform a flight mission according to the flight information; Acquire multispectral image data collected by the UAV terminal, and perform preprocessing based on the multispectral image data to obtain target image data; Performing multi-dimensional monitoring and analysis based on the target image data to determine the multi-dimensional monitoring results of crops, wherein the multi-dimensional monitoring and analysis includes: crop growth status monitoring and analysis, pest and disease monitoring and analysis, and soil environment monitoring and analysis; Based on the multi-dimensional monitoring results of the crops, a visual display is performed to obtain a multi-dimensional monitoring display map, wherein the multi-dimensional monitoring display map is used to intuitively display the growth status of the crops, the pest situation and the soil condition.

[0007] By adopting the above technical solution, in order to ensure that the drone can fully cover the farmland monitoring area when performing flight missions and reduce repeated flights and invalid flights, the drone flight planning is carried out based on the farmland monitoring area, the flight information is determined, and the flight information is sent to the drone terminal that performs data collection. Then, the multispectral image data collected by the drone terminal is obtained. In order to improve the accuracy and reliability of the multispectral image data, the multispectral image data is preprocessed to obtain the target image data. In order to enable agricultural managers to fully understand the production of crops in the farmland monitoring area, multidimensional monitoring and analysis are carried out based on the target image data to determine the multidimensional monitoring results of crops. The multidimensional monitoring results of crops provide accurate data support for agricultural production. Through automated and intelligent multidimensional monitoring and analysis, real-time monitoring and precise management of the entire process of crop growth are realized, and the intelligent level of agricultural production is improved. Finally, a visual display is performed based on the multidimensional monitoring results of crops to obtain a multidimensional monitoring display map. Multispectral image data covers light of different wavelengths, which can reveal the changes in the spectral characteristics of crops at different growth stages and under different environmental conditions. Using richer and more comprehensive multispectral image data for crop monitoring can more accurately reflect the growth status and potential problems of crops, thereby improving the accuracy of crop monitoring.

[0008] In a preferred example, the present application may be further configured as follows: the preprocessing based on the multispectral image data to obtain the target image data includes: Performing radiation correction based on the multispectral image data to obtain first multispectral image data, wherein the radiation correction is used to correct image radiation distortion caused by factors such as sensors, atmospheric conditions, and sun angles; Performing geometric correction based on the first multispectral image data to obtain second multispectral image data, wherein the geometric correction is used to correct geometric distortion of the image; The target image data is obtained by trimming and splicing based on the second multispectral image data, wherein the trimming and splicing are used to remove irrelevant areas and merge them into an image covering the complete area.

[0009] In a preferred example, the present application may be further configured as follows: performing multi-dimensional monitoring analysis based on the target image data to determine the multi-dimensional monitoring results of crops includes: For the crop growth status monitoring and analysis, spectral band extraction is performed based on the target image data to determine spectral band data, and vegetation index calculation is performed based on the spectral band data to determine the vegetation index value; Monitoring the growth status of crops based on the vegetation index value and determining a growth status monitoring result; For the pest monitoring and analysis, extract pest features based on the target image data to determine pest features, and classify and identify the pest features to determine pest monitoring results; For the soil environment monitoring and analysis, soil feature extraction is performed based on the target image data to determine soil spectral features, and soil index calculation is performed based on the soil spectral features to determine the soil index value; Perform soil environment monitoring and analysis based on the soil index value to determine the soil environment monitoring result; The multi-dimensional monitoring results of crops are determined by comprehensively combining the growth status monitoring results, the pest and disease monitoring results and the soil environment monitoring results.

[0010] In a preferred example, the present application may be further configured as follows: after performing multi-dimensional monitoring analysis based on the target image data and determining the multi-dimensional monitoring results of the crops, the present application may further include: Performing abnormality detection based on the multi-dimensional monitoring results of the crops, determining abnormal information of the crops, and generating abnormality warning information based on the abnormal information of the crops, wherein the abnormality warning information is used to identify risks in the growth process of the crops; Accordingly, the visual display based on the multi-dimensional monitoring results of the crops is performed to obtain a multi-dimensional monitoring display map, including: Based on the multi-dimensional monitoring results of the crops and the abnormal information of the crops, a visual display is performed to obtain a multi-dimensional monitoring display map, wherein the display situation corresponding to the abnormal information of the crops is marked in the multi-dimensional monitoring display map.

[0011] In a preferred example, the present application may be further configured as follows: the visual display based on the multi-dimensional monitoring results of the crops is performed to obtain a multi-dimensional monitoring display map, including: Acquire geographic information of the farmland monitoring area, construct a map based on the geographic information, and determine a farmland area map; Performing a production status visualization display based on the growth status monitoring results and the farmland area map, wherein the production status visualization display uses color coding to display the current growth status of the crops and displays the growth change trend of the crops by drawing a time series; Performing a visual display of pests and diseases based on the pest and disease monitoring results and the farmland area map, wherein the visual display of pests and diseases is to mark the occurrence area and severity of pests and diseases on the map using multiple element symbols; Performing a soil environment visualization display based on the soil environment monitoring results and the farmland area map, wherein the soil environment visualization display displays soil environment parameters by layer overlay; Based on the farmland area map, the production status visualization display, the pest and disease visualization display and the soil environment visualization display, a multi-dimensional monitoring display map is obtained.

[0012] In a preferred example, the present application can be further configured as follows: the drone flight planning based on the farmland monitoring area and determining the flight information include: Performing terrain analysis based on the farmland monitoring area to determine obstacle distribution information, wherein the terrain analysis is used to control the drone to avoid obstacles during flight; Performing full-course flight planning based on the farmland monitoring area and the obstacle distribution information to determine the full-course flight trajectory; Acquire the drone endurance information, perform collaborative flight analysis based on the full flight trajectory and the drone endurance information, and determine the local flight trajectory corresponding to each drone; Acquire sensor parameters of the multispectral sensor carried by the drone, perform flight parameter analysis based on the sensor parameters, and determine the flight altitude and flight speed corresponding to each drone; The flight information is obtained by integrating the local flight trajectory, flight altitude and flight speed corresponding to each UAV.

[0013] In a second aspect, the present application provides an electronic device, which adopts the following technical solution: at least one processor; Memory; At least one application, wherein the at least one application is stored in the memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the above-mentioned multi-spectral-based crop monitoring method.

[0014] In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program, which, when executed in a computer, causes the computer to execute the above-mentioned multi-spectral-based crop monitoring method.

[0015] In a fourth aspect, the present application provides a computer program product, which adopts the following technical solution: A computer program product comprises a computer program, wherein when the computer program is executed by a processor, the multi-spectral-based crop monitoring method is implemented.

[0016] In summary, the present application includes at least one of the following beneficial technical effects: In order to ensure that the drone can fully cover the farmland monitoring area when performing flight missions and reduce repeated flights and invalid flights, the drone flight planning is carried out based on the farmland monitoring area, the flight information is determined, and the flight information is sent to the drone terminal that performs data collection. Then, the multispectral image data collected by the drone terminal is obtained. In order to improve the accuracy and reliability of the multispectral image data, the multispectral image data is preprocessed to obtain the target image data. In order to enable agricultural managers to fully understand the production of crops in the farmland monitoring area, multidimensional monitoring and analysis are carried out based on the target image data to determine the multidimensional monitoring results of crops. The multidimensional monitoring results of crops provide accurate data support for agricultural production. Through automated and intelligent multidimensional monitoring and analysis, real-time monitoring and precise management of the entire process of crop growth are realized, and the intelligent level of agricultural production is improved. Finally, a multidimensional monitoring display map is obtained based on the multidimensional monitoring results of crops. Multispectral image data covers light of different wavelengths, which can reveal the changes in the spectral characteristics of crops at different growth stages and under different environmental conditions. Using richer and more comprehensive multispectral image data for crop monitoring can more accurately reflect the growth status and potential problems of crops, and improve the accuracy of crop monitoring.

[0017] Based on the multi-dimensional monitoring results of crops, anomaly detection is performed to determine the abnormal information of crops, and based on the abnormal information of crops, abnormal warning information is generated. An early warning mechanism is set up so that agricultural managers can promptly discover abnormal conditions in the growth process of crops, which helps to take timely treatment measures to ensure the normal growth of crops and improve agricultural production efficiency. Furthermore, based on the multi-dimensional monitoring results of crops and the abnormal information of crops, a visual display is performed to obtain a multi-dimensional monitoring display map. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flowchart of a method for monitoring crops based on multi-spectrum according to one embodiment of the present application; Figure 2 It is a structural schematic diagram of a multi-spectral crop monitoring device according to one embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device according to one embodiment of the present application. DETAILED DESCRIPTION

[0019] The following combination Figures 1 to 3 This application is described in further detail.

[0020] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, a person skilled in the art may make non-creative modifications to the present embodiment as needed, but such modifications are protected by the patent law as long as they are within the scope of the present application.

[0021] In order to make the purpose, technical scheme and advantages of the embodiment of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described in conjunction with the drawings in the embodiment of the present application. Obviously, the described embodiment is a part of the embodiment of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application. It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the data related to the object is involved in the embodiment of the present application, it needs to be obtained through the authorization and consent of the object, the authorization and consent of the relevant departments, and in accordance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiment, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained, and the embodiment also needs to be implemented with the authorization and consent of the object.

[0022] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0023] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0024] The embodiment of the present application provides a method for monitoring crops based on multispectral, which is performed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. Figure 1 As shown, the method includes step S101, step S102, step S103 and step S104, wherein: Step S101: Acquire the farmland monitoring area, perform UAV flight planning based on the farmland monitoring area, determine flight information, and send the flight information to the UAV terminal that performs data collection to control the UAV terminal equipped with a multispectral sensor to perform the flight mission according to the flight information.

[0025] For the embodiments of the present application, the farmland monitoring area is a pre-demarcated area that needs to monitor the growth of crops, pest conditions, and soil environment. The farmland monitoring area includes, but is not limited to, multi-dimensional information such as the geographical location of the farmland, the area of ​​the farmland, the shape of the farmland, and the edge of the farmland. Accurately divided farmland monitoring areas help subsequent drones to fully detect multi-spectral image data of the farmland monitoring area. In order to ensure that the drone can fully cover the farmland monitoring area when performing flight missions and reduce repeated flights and invalid flights, drone flight planning is performed based on the farmland monitoring area to determine flight information, where the flight information includes, but is not limited to, drone information, flight trajectory, flight altitude, flight speed, etc. There are many ways to plan the flight of unmanned aerial vehicles, which are not limited in the embodiments of the present application. In one achievable method, terrain analysis is performed based on the farmland monitoring area to determine the obstacle distribution information, wherein the terrain analysis is used to control the unmanned aerial vehicle to avoid obstacles during flight; full flight planning is performed based on the farmland monitoring area and the obstacle distribution information to determine the full flight trajectory; the unmanned aerial vehicle endurance information is obtained, and a collaborative flight analysis is performed based on the full flight trajectory and the unmanned aerial vehicle endurance information to determine the local flight trajectory corresponding to each unmanned aerial vehicle; the sensor parameters of the multispectral sensor carried are obtained, and the flight parameter analysis is performed based on the sensor parameters to determine the flight altitude and flight speed corresponding to each unmanned aerial vehicle; the local flight trajectory, flight altitude and flight speed corresponding to each unmanned aerial vehicle are integrated to obtain flight information. Of course, when executing the flight planning of the unmanned aerial vehicle, the meteorological conditions can also be considered, and the time period with good meteorological conditions can be selected to fly the unmanned aerial vehicle to ensure the safety of the unmanned aerial vehicle flight and to ensure the quality of the collected multispectral image data. Furthermore, the flight information is sent to the unmanned aerial vehicle terminal that performs data collection to control the unmanned aerial vehicle terminal equipped with a multispectral sensor to perform the flight mission according to the flight information.

[0026] Step S102: Acquire multispectral image data collected by the UAV terminal, and perform preprocessing based on the multispectral image data to obtain target image data.

[0027] For the embodiment of the present application, when the drone terminal performs tasks according to flight information, the multispectral sensor will automatically collect multispectral image data of the farmland area according to preset shooting parameters, and then the drone terminal will transmit the collected multispectral image data to the electronic device in real time or regularly, wherein the drone terminal and the electronic device are connected by wireless communication. However, the multispectral image data collected by the drone may include various noises, and may also be affected by various factors, resulting in geometric distortion, radiation distortion and other problems in the collected multispectral image data. In order to improve the accuracy and reliability of the multispectral image data, preprocessing is performed based on the multispectral image data to obtain the target image data, wherein the preprocessing includes but is not limited to: radiation correction, geometric correction and cropping and splicing.

[0028] Step S103: Perform multi-dimensional monitoring and analysis based on the target image data to determine the multi-dimensional monitoring results of crops, wherein the multi-dimensional monitoring and analysis includes: crop growth status monitoring and analysis, pest and disease monitoring and analysis, and soil environment monitoring and analysis.

[0029] For the embodiments of the present application, in order to enable agricultural managers to fully understand the production conditions of crops in the farmland monitoring area, multi-dimensional monitoring and analysis are performed based on target image data to determine the multi-dimensional monitoring results of crops, which provide accurate data support for agricultural production. Through automated and intelligent multi-dimensional monitoring and analysis, real-time monitoring and accurate management of the entire process of crop growth are achieved, improving the level of intelligence in agricultural production. There are many ways to perform multidimensional monitoring and analysis, which are not limited in the embodiments of the present application. In one achievable method, for monitoring and analyzing the growth status of crops, spectral band extraction is performed based on the target image data to determine the spectral band data, and vegetation index is calculated based on the spectral band data to determine the vegetation index value; crop growth status is monitored based on the vegetation index value to determine the growth status monitoring result; for monitoring and analyzing pests and diseases, pest and disease feature extraction is performed based on the target image data to determine the pest and disease feature, and classification and identification are performed based on the pest and disease feature to determine the pest and disease monitoring result; for monitoring and analyzing the soil environment, soil feature extraction is performed based on the target image data to determine the soil spectral feature, and soil index is calculated based on the soil spectral feature to determine the soil index value; soil environment monitoring and analysis is performed based on the soil index value to determine the soil environment monitoring result; and the growth status monitoring results, pest and disease monitoring results, and soil environment monitoring results are comprehensively considered to determine the multidimensional monitoring results of crops.

[0030] Compared with single-spectrum crop monitoring methods, multispectral imaging data covers light of different wavelengths, which can reveal changes in the spectral characteristics of crops at different growth stages and under different environmental conditions. Using richer and more comprehensive multispectral imaging data for crop monitoring can more accurately reflect the growth status and potential problems of crops, thereby improving the accuracy of crop monitoring.

[0031] Step S104: Visual display is performed based on the multi-dimensional monitoring results of crops to obtain a multi-dimensional monitoring display map, wherein the multi-dimensional monitoring display map is used to intuitively display the growth status of crops, pest conditions and soil conditions.

[0032] For the embodiments of the present application, in order to make the multi-dimensional monitoring results of crops more intuitive and easy to understand, the overall condition of the farmland can be quickly understood without complex data analysis. Therefore, a visual display is performed based on the multi-dimensional monitoring results of crops to obtain a multi-dimensional monitoring display map. The specific implementation process for the visual display is: select a map of the farmland monitoring area as the basis for the visual display, and superimpose the monitoring result data such as crop growth status, pests and diseases, and soil environment in the multi-dimensional monitoring results of crops on the map base map in the form of layers, and use different colors, symbols or icons to mark and distinguish different types of monitoring results to ensure the intuitiveness and readability of the farmland monitoring results. At the same time, add interactive functions to the multi-dimensional monitoring display map, such as zooming, panning, clicking to query, etc., to facilitate agricultural managers to view monitoring information in different areas and at different levels as needed; data filtering and filtering result display functions can also be provided, allowing agricultural managers to select specific monitoring results for viewing according to their needs.

[0033] It can be seen that in the embodiment of the present application, in order to ensure that the drone can fully cover the farmland monitoring area when performing flight missions and reduce repeated flights and invalid flights, the drone flight planning is performed based on the farmland monitoring area, the flight information is determined, and the flight information is sent to the drone terminal that performs data collection. Then, the multispectral image data collected by the drone terminal is obtained, and in order to improve the accuracy and reliability of the multispectral image data, pre-processing is performed based on the multispectral image data to obtain the target image data. In order to enable agricultural managers to fully understand the production of crops in the farmland monitoring area, multidimensional monitoring and analysis are performed based on the target image data to determine the multidimensional monitoring results of crops. The multidimensional monitoring results of crops provide accurate data support for agricultural production. Through automated and intelligent multidimensional monitoring and analysis, real-time monitoring and precise management of the entire process of crop growth are achieved, and the intelligent level of agricultural production is improved. Finally, a visual display is performed based on the multidimensional monitoring results of crops to obtain a multidimensional monitoring display map. Multispectral image data covers light of different wavelengths, which can reveal the changes in the spectral characteristics of crops at different growth stages and under different environmental conditions. Using richer and more comprehensive multispectral image data for crop monitoring can more accurately reflect the growth status and potential problems of crops, thereby improving the accuracy of crop monitoring.

[0034] Furthermore, in order to improve the accuracy and reliability of the multispectral image data, in the embodiment of the present application, preprocessing is performed based on the multispectral image data to obtain target image data, including: Performing radiation correction based on the multispectral image data to obtain first multispectral image data, wherein the radiation correction is used to correct image radiation distortion caused by factors such as sensors, atmospheric conditions, and sun angles; Performing geometric correction based on the first multispectral image data to obtain second multispectral image data, wherein the geometric correction is used to correct geometric distortion of the image; The target image data is obtained by trimming and splicing based on the second multispectral image data, wherein the trimming and splicing is used to remove irrelevant areas and merge them into an image covering the complete area.

[0035] For the embodiments of the present application, the multispectral image data collected by the drone may include various noises and may be affected by various factors, resulting in geometric distortion, radiation distortion and other problems in the collected multispectral image data. In order to improve the accuracy and reliability of the multispectral image data, preprocessing is performed based on the multispectral image data to obtain target image data, wherein the preprocessing includes but is not limited to: radiation correction, geometric correction and cropping and splicing.

[0036] Specifically, radiation correction is performed based on multispectral image data to obtain first multispectral image data. Radiation correction is used to correct image radiation distortion caused by sensors, atmospheric conditions, and sun angle factors to ensure the accuracy and reliability of the first multispectral image data. Radiation correction includes but is not limited to: sensor correction (also known as radiation calibration), atmospheric correction, and sun angle correction. For sensor correction, it is used to eliminate the radiation error caused by the sensor itself and convert the dimensionless digital quantization value recorded by the sensor into an apparent radiation brightness value or reflectivity value of the top layer of the atmosphere with actual physical meaning; for atmospheric correction, it is used to eliminate the influence of atmospheric absorption, scattering and other factors on image radiation and restore the true reflectivity or radiation brightness of crops. Atmospheric correction can be achieved through correction models, such as the 6S radiation transfer model and the MODTRAN model; for sun angle correction, the influence of changes in solar altitude and azimuth angles on image radiation is eliminated so that images taken at different times and angles have the same radiation conditions, that is, the multispectral image data is corrected by calculating the influence of solar altitude and azimuth angles on radiation.

[0037] The purpose of geometric correction is to correct the geometric distortion in the first multispectral image data so that the objects in the image can correctly reflect their position and shape in the actual geographic space, that is, the first multispectral image data is geometrically corrected using information such as satellite attitude, orbital parameters, and ground control points. The geometric correction usually includes two steps: rough geometric correction and fine geometric correction based on ground control points, so as to obtain the second multispectral image data. Then, the second multispectral image data is clipped and spliced ​​to obtain the target image data, wherein clipping and splicing is the process of clipping and splicing the second multispectral image data that has been radiometrically corrected and geometrically corrected as needed. Clipping is usually to remove the parts of the image that are not related to the farmland monitoring area, and splicing is to merge multiple images into an image covering a larger area. Of course, in the process of splicing, it is necessary to ensure that the hue and brightness between adjacent images are consistent to avoid obvious seams. In the process of preprocessing multispectral image data, radiometric correction, geometric correction, and clipping and splicing are three indispensable steps in preprocessing. They are combined in the above order and logic to ensure that the target image data has high quality and accuracy.

[0038] It can be seen that in the embodiment of the present application, in order to improve the accuracy and reliability of the multispectral image data, radiation correction is performed based on the multispectral image data to obtain the first multispectral image data, and then geometric correction is performed based on the first multispectral image data to obtain the second multispectral image data, and then, trimming and splicing are performed based on the second multispectral image data to obtain the target image data. Furthermore, in order to improve the accuracy and comprehensiveness of crop monitoring and achieve a comprehensive assessment of the farmland ecosystem, in the embodiment of the present application, multi-dimensional monitoring analysis is performed based on the target image data to determine the multi-dimensional monitoring results of crops, including: For crop growth status monitoring and analysis, spectral bands are extracted based on target image data to determine spectral band data, and vegetation index is calculated based on spectral band data to determine vegetation index values; Monitor the growth status of crops based on the vegetation index value and determine the growth status monitoring results; For the embodiments of the present application, in the process of executing multidimensional monitoring and analysis, monitoring and analysis are carried out from three dimensions: crop growth status, pest and disease conditions, and soil environment, thereby achieving a comprehensive assessment of the farmland ecosystem and improving the accuracy and comprehensiveness of crop monitoring.

[0039] For crop growth status monitoring and analysis, spectral band extraction is performed based on target image data to determine spectral band data, wherein the spectral band data includes but is not limited to: red band, green band and near infrared band, etc. Then, vegetation index calculation is performed based on spectral band data to determine the vegetation index value, wherein vegetation index calculation includes: normalized vegetation index calculation and green normalized vegetation index calculation. For normalized vegetation index calculation, the reflectance data of near infrared band and red band are used to calculate the normalized vegetation index of each pixel according to the following calculation formula. The normalized vegetation index can reflect the growth status and coverage of vegetation and is an important indicator for evaluating the growth status of crops. The formula for normalized vegetation index calculation is: NDVI = (NIR - R) / (NIR + R), wherein NDVI is the normalized vegetation index, NIR is the near infrared band, and R is the red band. For the calculation of the green normalized vegetation index, the reflectance data of the near-infrared band and the green band are used to calculate the green normalized vegetation index of each pixel according to the following calculation formula. The green normalized vegetation index can further refine the assessment of vegetation greenness and help to more accurately understand the chlorophyll content and growth status of crops. The formula for calculating the green normalized vegetation index is: GNDVI = (NIR - Green) / (NIR + Green), where GNDVI is the green normalized vegetation index, NIR is the near-infrared band, and Green is the green band. Vegetation index values ​​include: green normalized vegetation index and normalized vegetation index.

[0040] Furthermore, the growth status of crops is monitored based on the vegetation index value, and the growth status monitoring results are determined. The analysis dimensions for crop growth status monitoring can be performed from the following aspects, and the evaluation and analysis results of each aspect together constitute the growth status monitoring results. On the one hand, the growth status of crops is evaluated based on the vegetation index value to determine the growth status of crops. For example, when the green normalized vegetation index and the normalized vegetation index continue to rise, it means that the crops are in a rapid growth period; when the green normalized vegetation index and the normalized vegetation index suddenly drop, it indicates that the crops may be affected by adversities such as pests and diseases and drought. On the other hand, the vegetation index values ​​are spatially displayed using GIS technology, which is convenient for intuitively seeing the differences in the growth status of crops in different regions, and through spatial distribution analysis, the areas with good growth and areas that need to be focused on are determined. On the third hand, the historical vegetation index values ​​are obtained, and time series data are constructed based on the historical vegetation index values ​​and the vegetation index values, and the change trend analysis of the time series data is performed to determine the growth cycle and growth rate of crops.

[0041] For pest monitoring and analysis, the pest features are extracted based on the target image data, the pest features are determined, and the pest features are classified and identified based on the pest features to determine the pest monitoring results; For the embodiment of the present application, pest and disease feature extraction is performed based on the target image data to determine the pest and disease features, wherein the pest and disease features include: spectral features (e.g., changes in chlorophyll content, changes in water content, abnormal reflectivity in a specific band), texture features (e.g., roughness, directionality, contrast) and morphological features (e.g., shape and size of lesions, leaf deformity). For pest and disease feature extraction, it can be performed from three dimensions: spectral feature extraction, texture feature extraction and morphological feature extraction. For spectral feature extraction, pests and diseases will affect the spectral characteristics of crops, and spectral features related to pests and diseases are extracted. For example, some pests and diseases will cause the chlorophyll content of leaves to decrease, thereby reducing the reflectivity in the near-infrared band; while other pests and diseases may cause changes in the surface structure of leaves, affecting the reflectivity characteristics of the visible light band. For texture feature extraction, texture analysis technology is used to extract the texture features of the leaf surface, and the texture features are used as auxiliary information for pest and disease identification. For morphological feature extraction, image segmentation, morphological processing and other technologies are used to extract the morphological features of crops, which are used as auxiliary information for pest and disease identification.

[0042] A pest and disease classification and identification model is obtained, pest and disease characteristics are input into the pest and disease classification and identification model, the model is controlled to automatically perform classification and identification, and the pest and disease monitoring results are determined, wherein the pest and disease monitoring results include but are not limited to: types of pests and diseases, scope of occurrence, severity and other information; meanwhile, the pest and disease classification and identification model is obtained by training the classification model using a large amount of known pest and disease sample data.

[0043] For soil environmental monitoring and analysis, soil features are extracted based on target image data to determine soil spectral features, and soil index is calculated based on soil spectral features to determine soil index values; Conduct soil environmental monitoring and analysis based on soil index values ​​to determine soil environmental monitoring results; The multi-dimensional monitoring results of crops are determined by integrating the growth status monitoring results, pest and disease monitoring results and soil environment monitoring results.

[0044] For the embodiment of the present application, for soil environmental monitoring and analysis, soil feature extraction is performed based on the target image data, soil spectral features are determined, and soil index calculation is performed based on the soil spectral features to determine the soil index value, wherein the soil index value includes but is not limited to: soil moisture index, soil nutrient content index. For the calculation process of the soil moisture index, the soil moisture index is calculated using the difference in reflectivity of the soil in a specific band (for example, near infrared and short-wave infrared bands). Commonly used methods include normalized water index, corrected normalized water index, etc., that is, by comparing the difference in reflectivity of different bands to reflect the soil moisture content, thereby realizing the monitoring of soil moisture. For the calculation process of the soil nutrient content index, the nutrient content is estimated by analyzing the specific absorption features in the soil spectrum. For example, the spectral reflectivity of the visible light and near infrared bands is used to estimate the nutrient content of nitrogen, phosphorus, potassium, etc. in the soil. Furthermore, soil environmental monitoring and analysis are carried out based on the soil index value to determine the soil environmental monitoring results, that is, according to the soil moisture index, the spatial distribution and temporal variation trend of soil moisture are analyzed; according to the soil nutrient content index, the content levels of various nutrients in the soil are analyzed.

[0045] It can be seen that in the embodiment of the present application, for the monitoring and analysis of crop growth status, spectral band extraction is performed based on the target image data to determine the spectral band data, vegetation index calculation is performed based on the spectral band data to determine the vegetation index value, and crop growth status monitoring is performed based on the vegetation index value to determine the growth status monitoring result. On the other hand, for the monitoring and analysis of pests and diseases, pest and disease feature extraction is performed based on the target image data to determine the pest and disease feature, and classification and identification are performed based on the pest and disease feature to determine the pest and disease monitoring result. At the same time, for the monitoring and analysis of soil environment, soil feature extraction is performed based on the target image data to determine the soil spectral feature, and soil index calculation is performed based on the soil spectral feature to determine the soil index value, and then, soil environment monitoring and analysis is performed based on the soil index value to determine the soil environment monitoring result. Finally, the growth status monitoring results, pest and disease monitoring results and soil environment monitoring results are integrated to determine the multidimensional monitoring results of crops. In the process of performing multidimensional monitoring and analysis, monitoring and analysis are performed from three dimensions: crop growth status, pest and disease situation and soil environment, respectively, to achieve a comprehensive assessment of the farmland ecosystem and improve the accuracy and comprehensiveness of crop monitoring.

[0046] Furthermore, in order to timely discover abnormal conditions during the growth of crops and improve agricultural production efficiency, in the embodiment of the present application, after performing multi-dimensional monitoring and analysis based on target image data and determining the multi-dimensional monitoring results of crops, the following is also included: Perform anomaly detection based on the multi-dimensional monitoring results of crops, determine the abnormal information of crops, and generate abnormal warning information based on the abnormal information of crops, wherein the abnormal warning information is used to identify risks in the growth process of crops; Accordingly, a multi-dimensional monitoring display map is obtained based on the visual display of the multi-dimensional monitoring results of crops, including: Based on the visual display of the multi-dimensional monitoring results of crops and the abnormal information of crops, a multi-dimensional monitoring display map is obtained, wherein the growth conditions corresponding to the abnormal information of crops are marked in the multi-dimensional monitoring display map.

[0047] For the embodiment of the present application, the data range of the normal mode of crops in each monitoring dimension is pre-stored in the electronic device, and the data range under the normal mode is used to reflect the data range corresponding to the normal state of crops in different growth stages and different environmental conditions. Then, based on the data range of the normal mode and the data in the multi-dimensional monitoring results of crops, anomaly detection is performed to identify abnormal data items that deviate from the data range, and the relevant information corresponding to the abnormal data items is recorded as crop abnormal information. Furthermore, based on the crop abnormal information, abnormal warning information is generated, the electronic device pre-stores the template required for the abnormal warning information, and the abnormal warning information is sent to the agricultural manager terminal by wireless transmission. An early warning mechanism is set up so that agricultural managers can promptly discover abnormal conditions in the growth process of crops, which helps to take timely treatment measures to ensure the normal growth of crops and improve agricultural production efficiency.

[0048] Correspondingly, based on the visual display of the crop multidimensional monitoring results and crop abnormality information, a multidimensional monitoring display map is obtained, and the display situation corresponding to the crop abnormality information is marked in the multidimensional monitoring display map. The crop abnormality information is highlighted in the multidimensional monitoring display map through special markings, which helps to improve the visibility and recognition of the abnormal information, so that agricultural managers can intuitively and accurately locate the location of the abnormality in the map, thereby improving the effect of crop monitoring.

[0049] It can be seen that in the embodiment of the present application, anomaly detection is performed based on the multidimensional monitoring results of crops, abnormal information of crops is determined, and abnormal warning information is generated based on the abnormal information of crops. An early warning mechanism is set up so that agricultural managers can promptly discover abnormal conditions in the growth process of crops, which helps to take timely treatment measures to ensure the normal growth of crops and improve agricultural production efficiency. Furthermore, a visual display is performed based on the multidimensional monitoring results of crops and the abnormal information of crops to obtain a multidimensional monitoring display map.

[0050] Furthermore, in order to make the multi-dimensional monitoring results of crops more intuitive and understandable, in an embodiment of the present application, a multi-dimensional monitoring display map is obtained based on the multi-dimensional monitoring results of crops, including: Obtaining geographic information of the farmland monitoring area, constructing a map based on the geographic information, and determining a farmland area map; Visualize the production status based on the growth status monitoring results and farmland area maps. The visualization of production status uses color coding to display the current growth status of crops and draws time series to display the growth trend of crops. Pest and disease visualization is performed based on pest and disease monitoring results and farmland area maps. Pest and disease visualization uses a variety of element symbols to mark the occurrence areas and severity of pests and diseases on the map; Visualize the soil environment based on soil environment monitoring results and farmland area maps. The soil environment visualization displays soil environment parameters by overlaying layers. Based on the farmland area map, production status visualization, pest and disease visualization and soil environment visualization, a multi-dimensional monitoring display map is obtained.

[0051] For the embodiments of the present application, in order to make the multi-dimensional monitoring results of crops more intuitive and easy to understand, the overall condition of the farmland can be quickly understood without complex data analysis. Therefore, a visual display is performed based on the multi-dimensional monitoring results of crops to obtain a multi-dimensional monitoring display map.

[0052] Specifically, satellite remote sensing technology, drone aerial photography, GIS system and other means are used to collect geographic information of the farmland monitoring area. The geographic information includes but is not limited to: longitude and latitude coordinates, topography, soil type, distribution of irrigation facilities, etc. Of course, the administrative division information of the farmland monitoring area can also be obtained to accurately mark the ownership and boundaries of the farmland on the map. Then, GIS software is used to map the geographic information and determine the farmland area map, in which the farmland area map clearly divides the farmland area and marks the boundaries, numbers, areas and other information of the farmland. At the same time, other related layers are superimposed on the farmland area map, such as roads, water systems, settlements, etc., so that the farmland area map can fully display all the conditions of the farmland monitoring area.

[0053] Furthermore, the production status is visualized based on the growth status monitoring results and the farmland area map. The production status visualization uses color coding to display the current growth status of crops. The color coding scheme is pre-set and stored in the electronic device. Users can adjust it according to the situation. For example, green is used to represent normal growth status, yellow is used to represent slow growth or mild stress, and red is used to represent serious pests or abnormal growth. At the same time, a time series curve or chart is drawn on the farmland area map to show the growth cycle and growth rate of crops, that is, different colors or line thicknesses are used to represent the growth status data at different time points.

[0054] Furthermore, pests and diseases are visualized based on the pest and disease monitoring results and farmland area maps. The pest and disease visualization is to use a variety of element symbols to mark the occurrence areas and severity of pests and diseases on the map, that is, use point, line or surface elements to mark the occurrence areas and severity of pests and diseases on the map. The relationship between element symbols and the severity of pests and diseases is pre-set, and users can adjust it according to the situation. At the same time, soil environment visualization is performed based on soil environment monitoring results and farmland area maps. The soil environment visualization displays soil environmental parameters by overlaying layers. For example, different colors are used to represent soil moisture and nutrient content. Each layer can use different colors, symbols or gradient effects to represent different value ranges or levels of soil environmental parameters. Of course, in the process of layer overlay, ensure that the transparency and contrast between layers are moderate so that each soil environmental parameter can be clearly viewed.

[0055] It can be seen that in the embodiment of the present application, in order to make the multi-dimensional monitoring results of crops more intuitive and easy to understand, the overall situation of the farmland can be quickly understood without complex data analysis, the geographical information of the farmland monitoring area is obtained, and the map is constructed based on the geographical information to determine the farmland area map. Then, the production status is visualized based on the growth status monitoring results and the farmland area map. The production status visualization is to use color coding to display the current growth status of the crops, and the growth change trend of the crops is displayed by drawing a time series. Furthermore, the pests and diseases are visualized based on the pest monitoring results and the farmland area map. The pests and diseases are visualized to mark the occurrence area and severity of the pests and diseases on the map using multiple element symbols. Then, the soil environment is visualized based on the soil environment monitoring results and the farmland area map. The soil environment visualization displays soil environment parameters by layer overlay. Finally, based on the farmland area map, the production status visualization, the pests and diseases visualization, and the soil environment visualization, a multi-dimensional monitoring display map is obtained.

[0056] Furthermore, in order to improve the safety and reliability of drone flight, in an embodiment of the present application, drone flight planning is performed based on the farmland monitoring area to determine flight information, including: Perform terrain analysis based on the farmland monitoring area to determine obstacle distribution information. The terrain analysis is used to control the drone to avoid obstacles during flight. Conduct full flight planning based on farmland monitoring areas and obstacle distribution information to determine the full flight trajectory; Obtain the drone's endurance information, conduct collaborative flight analysis based on the full flight trajectory and drone endurance information, and determine the local flight trajectory corresponding to each drone; Obtain the sensor parameters of the multispectral sensor on board, perform flight parameter analysis based on the sensor parameters, and determine the flight altitude and flight speed corresponding to each UAV; The flight information is obtained by integrating the local flight trajectory, flight altitude and flight speed corresponding to each UAV.

[0057] For the embodiment of the present application, in order to ensure that the drone can fully cover the farmland monitoring area when performing flight missions, reduce repeated flights and invalid flights, and improve the safety and reliability of drone flights. Therefore, when executing drone flight planning, the terrain and drone endurance are combined to ensure that the planned flight information can meet the needs of data collection.

[0058] Specifically, obstacles in the farmland monitoring area will affect the safety of UAV flight to a certain extent. Therefore, terrain analysis is performed based on the farmland monitoring area to determine the obstacle distribution information. Through terrain analysis, it can ensure that the UAV can effectively avoid obstacles during flight, such as trees, electric poles, buildings, etc., which greatly reduces the risk of collision between the UAV and ground obstacles and improves the safety and reliability of flight. Obstacle distribution information includes but is not limited to: obstacle type, obstacle location, obstacle size and shape, obstacle height and obstacle buffer zone, etc. Then, full flight planning is performed based on the farmland monitoring area and obstacle distribution information to determine the full flight trajectory. The specific implementation process of full flight planning is as follows: According to the farmland monitoring area map and obstacle distribution information, the flight area of ​​the UAV is determined. The flight area should cover all farmland areas that need to be monitored and avoid obstacles. Then, a suitable path planning algorithm is selected, and path planning is performed according to the terrain characteristics and obstacle distribution information of the flight area to generate a path that meets the flight requirements. The generated path should be as short as possible to reduce flight time and energy consumption; at the same time, all obstacles should be avoided to ensure flight safety. Then, the planned flight path is smoothed and the entire flight trajectory is finally determined to reduce sharp turns and turbulence of the drone during flight and improve flight stability and shooting quality.

[0059] However, when the farmland monitoring area is large, the endurance of a single UAV is often unable to meet the monitoring of the entire farmland monitoring area. Therefore, it is necessary to conduct collaborative flight analysis based on the UAV endurance information and the full flight trajectory, so that the overall flight mission can be reasonably allocated to multiple UAVs, which can not only make full use of the UAV's endurance, but also avoid the interruption of the mission due to insufficient endurance of a single UAV. Then, the UAV endurance information is obtained, and collaborative flight analysis is performed based on the full flight trajectory and the UAV endurance information to determine the local flight trajectory corresponding to each UAV. That is, the maximum endurance time and maximum flight distance of the UAV are pre-set in the UAV endurance information. Therefore, the full flight trajectory is segmented according to the endurance of the UAV, and each trajectory can be used as a local flight trajectory of a UAV. A handover point is set between the local flight trajectories of adjacent UAVs to ensure that the UAVs can smoothly hand over tasks and data. In order to ensure that the multispectral sensor can collect high-quality and high-resolution multispectral image data, setting a reasonable flight altitude and flight speed can ensure that the multispectral sensor can operate in the best state, thereby obtaining more accurate and comprehensive farmland information. Therefore, the sensor parameters of the multispectral sensor are obtained, wherein the sensor parameters include but are not limited to: spectral band, resolution, field of view, signal-to-noise ratio, dynamic range, etc. The flight parameters are analyzed based on the sensor parameters to determine the flight altitude and flight speed corresponding to each UAV, that is, the appropriate flight altitude is calculated according to the field of view of the sensor and the required ground resolution. Generally speaking, the lower the flight altitude, the higher the ground resolution; the image quality requirements of the collected data are obtained, and the appropriate flight speed is selected based on the image quality requirements, sensor parameters and lighting conditions. Finally, the flight information is obtained by integrating the local flight trajectory, flight altitude and flight speed corresponding to each UAV.

[0060] It can be seen that in the embodiment of the present application, in order to ensure that the drone can fully cover the farmland monitoring area when performing flight missions, reduce repeated flights and invalid flights, and improve the safety and reliability of drone flights. Based on the farmland monitoring area, terrain analysis is performed to determine the obstacle distribution information, and full flight planning is performed based on the farmland monitoring area and obstacle distribution information to determine the full flight trajectory. Then, collaborative flight analysis is performed based on the full flight trajectory and drone endurance information to determine the local flight trajectory corresponding to each drone. Furthermore, flight parameter analysis is performed based on sensor parameters to determine the flight altitude and flight speed corresponding to each drone. Finally, the flight information is obtained by combining the local flight trajectory, flight altitude and flight speed corresponding to each drone.

[0061] The above embodiment introduces a multi-spectral crop monitoring method from the perspective of method flow, and the following embodiment introduces a multi-spectral crop monitoring device from the perspective of a virtual module or a virtual unit. For details, please refer to the following embodiment.

[0062] The present application embodiment provides a multi-spectral crop monitoring device, such as Figure 2 As shown, the multi-spectral-based crop monitoring device may specifically include: The flight planning module 210 is used to obtain the farmland monitoring area, perform UAV flight planning based on the farmland monitoring area, determine flight information, and send the flight information to the UAV terminal that performs data collection, so as to control the UAV terminal equipped with a multispectral sensor to perform the flight mission according to the flight information; A preprocessing module 220 is used to obtain multispectral image data collected by the UAV terminal, and perform preprocessing based on the multispectral image data to obtain target image data; The multi-dimensional monitoring and analysis module 230 is used to perform multi-dimensional monitoring and analysis based on the target image data to determine the multi-dimensional monitoring results of crops, wherein the multi-dimensional monitoring and analysis includes: crop growth status monitoring and analysis, pest and disease monitoring and analysis, and soil environment monitoring and analysis; The visualization display module 240 is used to perform visualization based on the multi-dimensional monitoring results of crops to obtain a multi-dimensional monitoring display map, wherein the multi-dimensional monitoring display map is used to intuitively display the growth status of crops, pest conditions and soil conditions.

[0063] For the embodiment of the present application, in order to ensure that the drone can fully cover the farmland monitoring area when performing flight missions and reduce repeated flights and invalid flights, drone flight planning is performed based on the farmland monitoring area, flight information is determined, and the flight information is sent to the drone terminal that performs data collection. Then, the multispectral image data collected by the drone terminal is obtained, and in order to improve the accuracy and reliability of the multispectral image data, preprocessing is performed based on the multispectral image data to obtain target image data. In order to enable agricultural managers to fully understand the production of crops in the farmland monitoring area, multidimensional monitoring and analysis are performed based on the target image data to determine the multidimensional monitoring results of crops. The multidimensional monitoring results of crops provide accurate data support for agricultural production. Through automated and intelligent multidimensional monitoring and analysis, real-time monitoring and precise management of the entire process of crop growth are achieved, and the level of intelligence in agricultural production is improved. Finally, a visual display is performed based on the multidimensional monitoring results of crops to obtain a multidimensional monitoring display map. Multispectral image data covers light of different wavelengths, which can reveal the changes in the spectral characteristics of crops at different growth stages and under different environmental conditions. Using richer and more comprehensive multispectral image data for crop monitoring can more accurately reflect the growth status and potential problems of crops, thereby improving the accuracy of crop monitoring.

[0064] In a possible implementation of the embodiment of the present application, when the preprocessing module 220 performs preprocessing based on the multispectral image data to obtain the target image data, it is used to: Performing radiation correction based on the multispectral image data to obtain first multispectral image data, wherein the radiation correction is used to correct image radiation distortion caused by factors such as sensors, atmospheric conditions, and sun angles; Performing geometric correction based on the first multispectral image data to obtain second multispectral image data, wherein the geometric correction is used to correct geometric distortion of the image; The target image data is obtained by trimming and splicing based on the second multispectral image data, wherein the trimming and splicing is used to remove irrelevant areas and merge them into an image covering the complete area.

[0065] In a possible implementation of the embodiment of the present application, when the multi-dimensional monitoring and analysis module 230 performs multi-dimensional monitoring and analysis based on target image data to determine the multi-dimensional monitoring results of crops, it is used to: For crop growth status monitoring and analysis, spectral bands are extracted based on target image data to determine spectral band data, and vegetation index is calculated based on spectral band data to determine vegetation index values; Monitor the growth status of crops based on the vegetation index value and determine the growth status monitoring results; For pest monitoring and analysis, the pest features are extracted based on the target image data, the pest features are determined, and the pest features are classified and identified based on the pest features to determine the pest monitoring results; For soil environmental monitoring and analysis, soil features are extracted based on target image data to determine soil spectral features, and soil index is calculated based on soil spectral features to determine soil index values; Conduct soil environmental monitoring and analysis based on soil index values ​​to determine soil environmental monitoring results; The multi-dimensional monitoring results of crops are determined by integrating the growth status monitoring results, pest and disease monitoring results and soil environment monitoring results.

[0066] A possible implementation of the embodiment of the present application is a multi-spectral crop monitoring device, which further includes: The abnormal warning module is used to perform abnormal detection based on the multi-dimensional monitoring results of crops, determine the abnormal information of crops, and generate abnormal warning information based on the abnormal information of crops, wherein the abnormal warning information is used to identify the risks in the growth process of crops; Accordingly, when the visualization display module 240 performs visualization based on the multi-dimensional monitoring results of crops and obtains a multi-dimensional monitoring display map, it is used to: Based on the visual display of the multi-dimensional monitoring results of crops and the abnormal information of crops, a multi-dimensional monitoring display map is obtained, wherein the display situation corresponding to the abnormal information of crops is marked in the multi-dimensional monitoring display map.

[0067] In a possible implementation of the embodiment of the present application, when the visualization display module 240 performs visualization based on the multi-dimensional monitoring results of crops to obtain a multi-dimensional monitoring display map, it is used to: Obtaining geographic information of the farmland monitoring area, constructing a map based on the geographic information, and determining a farmland area map; Visualize the production status based on the growth status monitoring results and farmland area maps. The visualization of production status uses color coding to display the current growth status of crops and draws time series to display the growth trend of crops. Pest and disease visualization is performed based on pest and disease monitoring results and farmland area maps. Pest and disease visualization uses a variety of element symbols to mark the occurrence areas and severity of pests and diseases on the map; Visualize the soil environment based on soil environment monitoring results and farmland area maps. The soil environment visualization displays soil environment parameters by overlaying layers. Based on the farmland area map, production status visualization, pest and disease visualization and soil environment visualization, a multi-dimensional monitoring display map is obtained.

[0068] In a possible implementation of the embodiment of the present application, the flight planning module 210 is used to: Perform terrain analysis based on the farmland monitoring area to determine obstacle distribution information. The terrain analysis is used to control the drone to avoid obstacles during flight. Conduct full flight planning based on farmland monitoring areas and obstacle distribution information to determine the full flight trajectory; Obtain the drone's endurance information, conduct collaborative flight analysis based on the full flight trajectory and drone endurance information, and determine the local flight trajectory corresponding to each drone; Obtain the sensor parameters of the multispectral sensor on board, perform flight parameter analysis based on the sensor parameters, and determine the flight altitude and flight speed corresponding to each UAV; The flight information is obtained by integrating the local flight trajectory, flight altitude and flight speed corresponding to each UAV.

[0069] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the multi-spectral-based crop monitoring device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0070] An electronic device is provided in an embodiment of the present application, such as Figure 3 As shown, Figure 3 The electronic device 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0071] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0072] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0073] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0074] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0075] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0076] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0077] The embodiment of the present application provides a computer program product, which includes a computer program, which implements the method in any of the above embodiments when executed by a processor. Compared with the related art, in order to ensure that the drone can fully cover the farmland monitoring area when performing a flight mission and reduce repeated flights and invalid flights, the embodiment of the present application performs drone flight planning based on the farmland monitoring area, determines flight information, and sends the flight information to the drone terminal that performs data collection. Then, the multispectral image data collected by the drone terminal is obtained, and in order to improve the accuracy and reliability of the multispectral image data, pre-processing is performed based on the multispectral image data to obtain target image data. In order to enable agricultural managers to fully understand the production of crops in the farmland monitoring area, multidimensional monitoring and analysis are performed based on the target image data to determine the multidimensional monitoring results of crops. The multidimensional monitoring results of crops provide accurate data support for agricultural production. Through automated and intelligent multidimensional monitoring and analysis, real-time monitoring and precise management of the entire process of crop growth are achieved, and the intelligent level of agricultural production is improved. Finally, a visual display is performed based on the multidimensional monitoring results of crops to obtain a multidimensional monitoring display map. Multispectral image data covers light of different wavelengths, which can reveal the changes in the spectral characteristics of crops at different growth stages and under different environmental conditions. Using richer and more comprehensive multispectral image data for crop monitoring can more accurately reflect the growth status and potential problems of crops, thereby improving the accuracy of crop monitoring.

[0078] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0079] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for monitoring crops based on multispectral, characterized in that: include: Acquire a farmland monitoring area, perform drone flight planning based on the farmland monitoring area, determine flight information, and send the flight information to a drone terminal that performs data collection, so as to control the drone terminal equipped with a multispectral sensor to perform a flight mission according to the flight information; Acquire multispectral image data collected by the UAV terminal, and perform preprocessing based on the multispectral image data to obtain target image data; Performing multi-dimensional monitoring and analysis based on the target image data to determine the multi-dimensional monitoring results of crops, wherein the multi-dimensional monitoring and analysis includes: crop growth status monitoring and analysis, pest and disease monitoring and analysis, and soil environment monitoring and analysis; Based on the multi-dimensional monitoring results of the crops, a visual display is performed to obtain a multi-dimensional monitoring display map, wherein the multi-dimensional monitoring display map is used to intuitively display the growth status of the crops, the pest situation and the soil condition.

2. The method for crop monitoring based on multispectral according to claim 1, characterized in that: The preprocessing based on the multispectral image data to obtain target image data includes: Performing radiation correction based on the multispectral image data to obtain first multispectral image data, wherein the radiation correction is used to correct image radiation distortion caused by factors such as sensors, atmospheric conditions, and sun angles; Performing geometric correction based on the first multispectral image data to obtain second multispectral image data, wherein the geometric correction is used to correct geometric distortion of the image; The target image data is obtained by trimming and splicing based on the second multispectral image data, wherein the trimming and splicing are used to remove irrelevant areas and merge them into an image covering the complete area.

3. The method for crop monitoring based on multispectral according to claim 1, characterized in that: The multi-dimensional monitoring analysis based on the target image data to determine the multi-dimensional monitoring results of crops includes: For the crop growth status monitoring and analysis, spectral band extraction is performed based on the target image data to determine spectral band data, and vegetation index calculation is performed based on the spectral band data to determine the vegetation index value; Monitoring the growth status of crops based on the vegetation index value and determining a growth status monitoring result; For the pest monitoring and analysis, extract pest features based on the target image data to determine pest features, and classify and identify the pest features to determine pest monitoring results; For the soil environment monitoring and analysis, soil feature extraction is performed based on the target image data to determine soil spectral features, and soil index calculation is performed based on the soil spectral features to determine the soil index value; Perform soil environment monitoring and analysis based on the soil index value to determine the soil environment monitoring results; The multi-dimensional monitoring results of crops are determined by comprehensively combining the growth status monitoring results, the pest and disease monitoring results and the soil environment monitoring results.

4. The method for crop monitoring based on multispectral according to claim 3, characterized in that: After performing multi-dimensional monitoring analysis based on the target image data and determining the multi-dimensional monitoring results of crops, the method further includes: Performing abnormality detection based on the multi-dimensional monitoring results of the crops, determining abnormal information of the crops, and generating abnormality warning information based on the abnormal information of the crops, wherein the abnormality warning information is used to identify risks in the growth process of the crops; Accordingly, the visual display based on the multi-dimensional monitoring results of the crops is performed to obtain a multi-dimensional monitoring display map, including: Based on the multi-dimensional monitoring results of the crops and the abnormal information of the crops, a visual display is performed to obtain a multi-dimensional monitoring display map, wherein the display situation corresponding to the abnormal information of the crops is marked in the multi-dimensional monitoring display map.

5. The method for crop monitoring based on multispectral according to claim 3, characterized in that: The visual display based on the multi-dimensional monitoring results of the crops to obtain a multi-dimensional monitoring display map includes: Acquire geographic information of the farmland monitoring area, construct a map based on the geographic information, and determine a farmland area map; Performing a production status visualization display based on the growth status monitoring results and the farmland area map, wherein the production status visualization display uses color coding to display the current growth status of the crops and displays the growth change trend of the crops by drawing a time series; Performing a visual display of pests and diseases based on the pest and disease monitoring results and the farmland area map, wherein the visual display of pests and diseases is to mark the occurrence area and severity of pests and diseases on the map using multiple element symbols; Performing a soil environment visualization display based on the soil environment monitoring results and the farmland area map, wherein the soil environment visualization display displays soil environment parameters by layer overlay; Based on the farmland area map, the production status visualization display, the pest and disease visualization display and the soil environment visualization display, a multi-dimensional monitoring display map is obtained.

6. The method for crop monitoring based on multispectral according to claim 1, characterized in that: The drone flight planning based on the farmland monitoring area and determining the flight information include: Performing terrain analysis based on the farmland monitoring area to determine obstacle distribution information, wherein the terrain analysis is used to control the drone to avoid obstacles during flight; Performing full-course flight planning based on the farmland monitoring area and the obstacle distribution information to determine the full-course flight trajectory; Acquire the drone endurance information, perform collaborative flight analysis based on the full flight trajectory and the drone endurance information, and determine the local flight trajectory corresponding to each drone; Acquire sensor parameters of the multispectral sensor carried by the drone, perform flight parameter analysis based on the sensor parameters, and determine the flight altitude and flight speed corresponding to each drone; The flight information is obtained by integrating the local flight trajectory, flight altitude and flight speed corresponding to each UAV.

7. An electronic device, characterized in that: include: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the multi-spectral based crop monitoring method according to any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the multi-spectral-based crop monitoring method according to any one of claims 1 to 6.

9. A computer program product, characterized in that It comprises a computer program, wherein the computer program is executed by a processor to implement the multi-spectral crop monitoring method according to any one of claims 1 to 6.

Images