A Crop Pest and Disease Monitoring and Early Warning System Based on Satellite Remote Sensing and AI Algorithms

Abstract

The present invention relates to the technical field of environmental data monitoring, and discloses a crop pest and disease monitoring and early warning system based on satellite remote sensing and AI algorithms, including the following steps: regularly collect multi-spectral images of farmland covering the farmland area through satellite remote sensing technology, and preprocess the multi-spectral images of farmland to obtain three-dimensional spatial images of farmland; perform pest and disease analysis on the three-dimensional spatial images of farmland to extract pest and disease images and their spatial distributions, analyze historical pest and disease data based on the AI algorithm analysis model, obtain the induced pest and disease impact factors corresponding to different target types of pests, and obtain the development trend of pests and diseases corresponding to the target type of pests based on the induced pest and disease impact factors; write the pest and disease impact degree corresponding to the current pest and disease image into a smart contract, record the timestamp of the pest and disease impact degree in the smart contract, and establish a pest and disease early warning strategy based on evaluation reports of different time periods.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural monitoring. More specifically, the present invention relates to a crop pest and disease monitoring and early warning system based on satellite remote sensing and AI algorithms. Background Art

[0002] Traditional methods for monitoring crop pests and diseases often rely on manual field surveys. This method is not only time-consuming and laborious, but also difficult to cover large areas, resulting in low monitoring efficiency and untimely early warnings. In addition, although existing ground sensor-based monitoring systems can provide local information, there are still monitoring blind spots for vast farmlands.

[0003] In the field of agricultural environment, with the application of machine learning models, such as the Chinese authorized patent: CN111985370B, which discloses a fine-grained recognition method for crop pests and diseases based on an improved hybrid attention module, constructs a convolutional network using Inception and residual learning ideas, which can reduce the mapping interval and retain the details of the original image;

[0004] It mainly focuses on identifying pests and diseases in the collected images. However, in actual applications, due to the large area of farmland, it is impossible to collect accurate real-time images of pests and diseases. Usually, basic pest and disease information is provided, and there is no integrated intelligent prediction and decision support system. Agricultural managers can only make decisions based on experience, which may lead to inaccurate or untimely prevention and control measures.

[0005] In view of this, the present invention proposes a crop pest and disease monitoring and early warning system based on satellite remote sensing and AI algorithms. Summary of the Invention

[0006] In order to overcome the deficiencies of the prior art, the present invention provides a crop pest and disease monitoring and early warning system based on satellite remote sensing and AI algorithms, which has the advantage of more accurate operation.

[0007] In a first aspect, the present invention provides a crop pest and disease monitoring and early warning system based on satellite remote sensing and AI algorithms, including a data acquisition module, a data analysis module, a trend prediction module, and an early warning decision module, and each module is connected by wire or wirelessly;

[0008] The data acquisition module regularly collects multi-spectral images of farmland covering the farmland area through satellite remote sensing technology, and preprocesses the multi-spectral images of farmland to obtain a three-dimensional spatial image of the farmland;

[0009] The data analysis module performs pest and disease analysis on the three-dimensional spatial image of the farmland to extract pest and disease images and their spatial distributions, and the pest and disease images include at least one target type of pest image;

[0010] The trend prediction module analyzes historical pest and disease data based on an AI algorithm analysis model to obtain the induced pest impact factors corresponding to different target types of pests, assigns probabilities to the pest and disease disaster levels based on the induced pest impact factors, and conducts statistics based on the probability assignments of the pest and disease disaster levels to obtain the development trend of pests and diseases corresponding to the target types of pests.

[0011] The early warning decision-making module writes the pest and disease impact degree corresponding to the current pest and disease image into a smart contract, records the timestamp of the pest and disease impact degree in the smart contract, and evaluates the actual pest and disease impact considering the transmission time, thereby generating evaluation reports with different time effects, and establishing a pest and disease early warning strategy based on the evaluation reports with different time effects.

[0012] As a preferred technical solution of the first aspect of the present invention, multiple satellites are used to regularly obtain multi-spectral images of farmland covering multiple bands, and the multi-spectral images of farmland include spectral images of band b1, spectral images of band b2, spectral images of band b3, and spectral images of band b4; the multi-spectral images of farmland are subjected to image segmentation through spectral feature analysis to extract the farmland planting area.

[0013] As a preferred technical solution of the first aspect of the present invention, the acquisition logic of the three-dimensional space image of the farmland is as follows:

[0014] Geometric positioning, edge trimming, and noise removal processing are performed on the farmland planting area to obtain a pre-processed farmland image;

[0015] At least one fixed marker is found in the pre-processed farmland image, the fixed marker is marked as a reference point, and spatial alignment is performed based on the reference point to obtain a reference farmland image;

[0016] The reference farmland image grayscales the image using the weighted average method, uses the Rank transformation result of the grayscale image as a matching primitive, and uses a region matching algorithm based on the normalized absolute difference sum measure function to obtain a dense disparity map of the scene;

[0017] The spatial coordinates of the scene are calculated according to the principle of parallel binocular vision imaging, and a three-dimensional point cloud map is generated; a three-dimensional space image of the farmland is generated based on the three-dimensional point cloud map.

[0018] As a preferred technical solution of the first aspect of the present invention, the acquisition logic of the pest and disease image is as follows:

[0019] The measured species grayscale values of the species corresponding to the three-dimensional space image of the farmland are collected, and the measured species grayscale values are compared with the species reference grayscale interval corresponding to the same time sequence information. The species reference grayscale interval is the grayscale pixel interval value of the normal growth of the current species in the experimental planting environment obtained based on the analysis of the historical database.

[0020] Screen the pixel blocks whose measured gray values of the actual species are not within the reference gray value range of the species, take the pixel blocks not within the reference gray value range of the species as abnormal image blocks, and mark the spatial positions corresponding to the abnormal image blocks as abnormal spatial positions;

[0021] According to the pre-set continuous time series interval, count the abnormal support degree and abnormal co-occurrence degree corresponding to the abnormal spatial positions within the continuous time series interval, where the abnormal support degree is used to represent the total number of abnormal marks corresponding to the same abnormal spatial position within the continuous time series interval, and the abnormal co-occurrence degree is used to represent the number of times that different abnormal spatial positions appear together within the continuous time series interval;

[0022] When the abnormal support degree within the continuous time series interval is greater than the preset abnormal support threshold and the abnormal co-occurrence degree is greater than the preset abnormal expansion threshold, mark the corresponding abnormal image block as a pest and disease image, and the pest and disease image includes at least one target type of pest image and the spatial distribution of the corresponding target type of pest.

[0023] As a preferred technical solution of the first aspect of the present invention, the acquisition logic of the target type of pest image:

[0024] Perform texture analysis on the pest and disease image, extract the pest and disease texture features through the gray level co-occurrence matrix, and obtain the pest and disease texture feature correlation quantity;

[0025] Calculate the similarity according to the normalization calculation formula between the pest and disease texture feature correlation quantity and the pest and disease texture features defined in the historical database, screen the abnormal image blocks within the pest and disease similarity threshold range, and mark the abnormal image blocks as the target type of pest image.

[0026] As a preferred technical solution of the first aspect of the present invention, the acquisition logic of the development trend of the pest and disease is:

[0027] Matrix-aggregate the target type of pest images corresponding to different types of pests and diseases according to the abnormal spatial positions to obtain the spatial distribution corresponding to the target type of pest images;

[0028] Construct an AI algorithm analysis model, and use meteorological data, different types of target type of pest images and their spatial distributions as input factors to output the induced pest impact factors corresponding to different types of target type of pest images;

[0029] Based on the induced pest impact factors, assign probabilities to the pest and disease disaster levels. The greater the probability assignment, the greater the probability of the occurrence of the pest and disease disaster. Superimpose the probability assignments of different types of pests and diseases to the pest and disease disaster levels to obtain the pest and disease impact degree corresponding to the current pest and disease image, and characterize the development trend of the pest and disease based on the pest and disease impact degree.

[0030] As a preferred technical solution of the first aspect of the present invention, the acquisition logic of the pest and disease warning strategy is as follows:

[0031] Obtain the spatial distribution and collection timestamps corresponding to different types of target pests; store the current pest and disease impact degree based on the timestamps, and map the historical pest and disease records corresponding to the target pests based on the timestamps;

[0032] Based on the analysis of historical pest and disease records, and combined with the transmission time, evaluate the actual pest and disease impact, record the evaluation reports of different time limits, rewrite the timestamps according to different time limits, and display them in the pest and disease warning strategy corresponding to the smart contract.

[0033] In the second aspect, the present invention provides a method for monitoring and warning crop pests and diseases based on satellite remote sensing and AI algorithms. Based on the implementation of a system for monitoring and warning crop pests and diseases based on satellite remote sensing and AI algorithms described in the first aspect, the method includes the following steps:

[0034] Regularly collect multi-spectral images of farmland covering the farmland area through satellite remote sensing technology, and preprocess the multi-spectral images of farmland to obtain three-dimensional spatial images of farmland;

[0035] Perform pest and disease analysis on the three-dimensional spatial images of farmland to extract pest and disease images and their spatial distributions, where the pest and disease images include at least one target pest image;

[0036] Analyze historical pest and disease data based on the AI algorithm analysis model to obtain the induced pest and disease impact factors corresponding to different target pests, assign probabilities to the pest and disease disaster levels based on the induced pest and disease impact factors, and perform statistics based on the probability assignments of the pest and disease disaster levels to obtain the development trends of pests and diseases corresponding to the target pests;

[0037] Write the pest and disease impact degree corresponding to the current pest and disease image into a smart contract, record the timestamp of the pest and disease impact degree in the smart contract, and consider the transmission time to evaluate the actual pest and disease impact, so as to generate evaluation reports of different time limits, and establish a pest and disease warning strategy based on the evaluation reports of different time limits.

[0038] In the third aspect, the present invention provides an electronic device, including: a processor and a memory, where a computer program that can be called by the processor is stored in the memory;

[0039] The processor executes a system for monitoring and warning crop pests and diseases based on satellite remote sensing and AI algorithms described in the first aspect by calling the computer program stored in the memory.

[0040] Fourthly, the present invention provides a computer-readable storage medium storing instructions, which, when run on a computer, cause the computer to execute the crop pest and disease monitoring and early warning system based on satellite remote sensing and AI algorithms described in the first aspect.

[0041] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0042] The monitoring system of the present invention integrates satellite remote sensing technology and artificial intelligence algorithms, which can significantly reduce the cost of traditional farmland pest and disease monitoring, improve the monitoring efficiency and accuracy, realize early warning of pests and diseases, and provide scientific support for agricultural decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a schematic diagram of the framework of the crop pest and disease monitoring and early warning system of the present invention;

[0044] Figure 2 is a schematic diagram of the method for monitoring crop pests and diseases in the agricultural environment of the present invention;

[0045] Figure 3 is a flowchart of the method for monitoring and early warning of crop pests and diseases of the present invention;

[0046] Figure 4 is a schematic diagram of the structure of an electronic device of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0048] Embodiment 1: As Figure 1-2 shown, the present invention provides a crop pest and disease monitoring and early warning system based on satellite remote sensing and AI algorithms, including a data acquisition module 100, a data analysis module 200, a trend prediction module 300, and an early warning decision module 400, and each module is connected by wire or wirelessly;

[0049] The data acquisition module 100 regularly collects multi-spectral images of farmland covering the farmland area through satellite remote sensing technology, and preprocesses the multi-spectral images of farmland to obtain a three-dimensional spatial image of the farmland;

[0050] Specifically, multiple high-resolution satellites are used to regularly obtain multi-spectral images of farmland covering multiple bands such as infrared and visible light. The multi-spectral images of farmland include spectral images of band b1, spectral images of band b2, spectral images of band b3, and spectral images of band b4. The multi-spectral images of farmland are subjected to image segmentation through spectral feature analysis to extract the farmland planting area, laying a foundation for subsequent vegetation index calculation and pest and disease identification.

[0051] The acquisition logic of the three-dimensional spatial image of farmland is as follows:

[0052] Geometric positioning, edge trimming, and noise removal are performed on the farmland planting area to obtain a pre-processed farmland image. The pre-processed farmland image is a farmland image after radiometric correction and atmospheric correction of the farmland planting area, eliminating the influence of atmospheric scattering and absorption to obtain physically quantified apparent radiance, so as to ensure the accuracy of subsequent analysis.

[0053] It should be noted that: Distortions caused by satellite attitude changes and terrain undulations are corrected. In addition, techniques such as median filtering and Gaussian filtering are used to denoise the image, improving the signal-to-noise ratio of the image.

[0054] At least one fixed marker is searched for in the pre-processed farmland image, and the fixed marker is marked as a reference point. Based on the reference point, spatial alignment is performed to obtain a reference farmland image for subsequent time series analysis.

[0055] The reference farmland image grayscales the image using the weighted average method, uses the Rank transform result of the grayscale image as a matching primitive, and uses a region matching algorithm based on the normalized absolute difference and measure function to obtain a dense disparity map of the scene.

[0056] The spatial coordinates of the scene are calculated according to the parallel binocular vision imaging principle, and a three-dimensional point cloud map is generated. A three-dimensional spatial image of the farmland is generated based on the three-dimensional point cloud map.

[0057] It should be noted that: A three-dimensional modeling method for farmland scenes based on Rank transform is adopted. This method grayscales the image using the weighted average method and uses the Rank transform result as a matching primitive to improve the robustness of the matching.

[0058] The data analysis module 200 performs pest and disease analysis on the three-dimensional spatial image of the farmland to extract pest and disease images and their spatial distributions. The pest and disease images include at least one target type of pest image.

[0059] It should be noted that: The types and spatial distributions of pests and diseases are automatically identified, and the results are intuitively overlaid on the remote sensing image to show the location and severity of pest and disease occurrences.

[0060] Specifically, the acquisition logic of the pest and disease images is as follows:

[0061] Collect the measured species gray values of the corresponding species in the three-dimensional space image of the farmland, and compare the measured species gray values with the species reference gray value range corresponding to the same time series information. The species reference gray value range is the gray pixel value range of the normal growth of the current species in the experimental planting environment obtained by analyzing the historical database;

[0062] Screen the pixel blocks whose measured species gray values are not within the species reference gray value range, regard the pixel blocks not within the species reference gray value range as abnormal image blocks, and mark the spatial positions corresponding to the abnormal image blocks as abnormal spatial positions;

[0063] According to the pre-set continuous time series interval, count the abnormal support degree and abnormal co-occurrence degree corresponding to the abnormal spatial positions within the continuous time series interval. Among them, the abnormal support degree is used to represent the total number of abnormal marks corresponding to the same abnormal spatial position within the continuous time series interval, and the abnormal co-occurrence degree is used to represent the number of times that different abnormal spatial positions appear together within the continuous time series interval;

[0064] The continuous time series interval is the continuous time stamps of the satellite collecting the multi-spectral images of the farmland; when the abnormal support degree within the continuous time series interval is greater than the preset abnormal support threshold and the abnormal co-occurrence degree is greater than the preset abnormal expansion threshold, mark the corresponding abnormal image blocks as pest and disease images. The pest and disease images include at least one target type of pest image and the spatial distribution of the corresponding target type of pest.

[0065] The acquisition logic of the target type of pest image:

[0066] Perform texture analysis on the pest and disease images, extract the pest and disease texture features through the gray-level co-occurrence matrix, and obtain the pest and disease texture feature correlation quantity;

[0067] Calculate the similarity according to the normalization calculation formula between the pest and disease texture feature correlation quantity and the pest and disease texture features defined in the historical database, screen the abnormal image blocks within the pest and disease similarity threshold range, and mark the abnormal image blocks as the target type of pest images.

[0068] The trend prediction module 300 analyzes the historical pest and disease data based on the AI algorithm analysis model, obtains the induced pest impact factors corresponding to different target types of pests, assigns probabilities to the pest and disease disaster levels based on the induced pest impact factors, and conducts statistics based on the probability assignments of the pest and disease disaster levels to obtain the development trends of the pests and diseases corresponding to the target types of pests;

[0069] Specifically, the acquisition logic of the pest and disease development trend is:

[0070] The target pest images corresponding to different types of pests and diseases are matrixed according to the abnormal spatial positions to obtain the spatial distribution corresponding to the target pest images;

[0071] Construct an AI algorithm analysis model, using meteorological data, images of different target species of pests and their spatial distribution as input factors, and output the induced pest impact factors corresponding to the images of different target species of pests;

[0072] The probability of pest disaster level is assigned based on the pest-inducing impact factor. The larger the probability value, the greater the probability of pest disaster. The probability assignment of different types of pests to the pest disaster level is superimposed to obtain the pest impact degree corresponding to the current pest image, and the pest development trend is characterized based on the pest impact degree.

[0073] The early warning decision module 400 compiles a smart contract for the degree of impact of pests and diseases corresponding to the current pest and disease image, records the timestamp of the degree of impact of pests and diseases in the smart contract, and evaluates the actual impact of pests and diseases considering the transmission time, thereby generating evaluation reports of different time limits, and establishing a pest and disease early warning strategy based on the evaluation reports of different time limits.

[0074] Specifically, the acquisition logic of the pest and disease early warning strategy is:

[0075] Obtain the spatial distribution and collection timestamps of different target pests; store the current pest impact based on the timestamp, and map the historical pest records corresponding to the target pests based on the timestamp;

[0076] Based on the analysis of historical pest and disease records, and combined with the transmission time, the actual impact of pests and diseases is evaluated, and assessment reports of different time limits are recorded. The timestamps are rewritten according to different time limits, and displayed in the pest and disease early warning strategy corresponding to the smart contract.

[0077] It should be noted that in order to provide more effective prevention and control measures, the system will compare and analyze the identification results with historical pest and disease data, use time series models to analyze the development trend of pests and diseases, and predict the peak period in the future. Based on these prediction results, pest and disease monitoring reports are automatically generated to help farmers take prevention and control measures in advance.

[0078] This embodiment supports automated and regular remote sensing image acquisition. By regularly acquiring remote sensing images of farmland, the system can achieve continuous monitoring of farmland health conditions, avoid the limitations of manual inspections, and have a wide coverage and high efficiency. Using multispectral image processing technology and deep learning models, the system can automatically identify the types and distribution of pests and diseases, with high analysis accuracy and fast recognition speed, greatly improving the efficiency and accuracy of data analysis. The system combines historical data with current recognition results, infers the development trend of pests and diseases through prediction models, and provides real-time early warning information. Agricultural managers can take prevention and control measures in advance based on this information to avoid further spread of pests and diseases. Combined with meteorological data and environmental factors, the system provides accurate prevention and control suggestions to help agricultural managers make scientific decisions. This function makes farmland management more intelligent and precise. Through automated and regular remote sensing image acquisition and intelligent analysis, the system reduces dependence on manual inspections, improves detection efficiency, and ensures that farmland pests and diseases can be discovered in a timely manner. Through advanced image processing and deep learning technologies, the system can accurately identify the types and distribution of pests and diseases, and provide early warning information in combination with prediction models, ensuring that agricultural managers can take measures before pests and diseases spread on a large scale. The intelligent decision-making support function provided by the system enables agricultural managers to formulate more scientific and accurate prevention and control strategies based on real-time monitoring data and prediction results, thereby improving the effectiveness of pest and disease prevention and control and reducing crop losses. Combined with multi-source data (such as meteorological data and historical pest and disease data), the system can conduct a comprehensive analysis of farmland, provide all-round management support, and improve the overall level of agricultural management.

[0079] Example 2: Please refer to Figure 3 As shown, the part not described in detail in this embodiment is described in Example 1. This embodiment provides a crop disease and insect pest monitoring and early warning method based on satellite remote sensing and AI algorithm, including the following steps:

[0080] The multispectral images of farmland covering the farmland area are collected regularly through satellite remote sensing technology, and the multispectral images of farmland are preprocessed to obtain the three-dimensional spatial images of farmland;

[0081] Performing pest and disease analysis on the three-dimensional spatial image of the farmland to extract pest and disease images and their spatial distribution, wherein the pest and disease images include at least one target type of pest image;

[0082] Analyze historical pest data based on AI algorithm analysis model, obtain the pest inducing factors corresponding to different target pest types, assign probability values ​​to pest disaster levels based on the pest inducing factors, perform statistics based on the probability values ​​of pest disaster levels, and obtain pest development trends corresponding to target pest types;

[0083] Write an intelligent contract for the degree of pest and disease impact corresponding to the current pest and disease image, record the timestamp of the pest and disease impact degree in the intelligent contract, and consider the transmission time to evaluate the actual pest and disease impact, so as to generate evaluation reports with different time limits, and establish a pest and disease early warning strategy based on the evaluation reports with different time limits.

[0084] Regularly obtain multi-spectral images of farmland covering multiple bands by using multiple satellites. The multi-spectral images of farmland include spectral images of band b1, spectral images of band b2, spectral images of band b3, and spectral images of band b4; the multi-spectral images of farmland are subjected to image segmentation through spectral feature analysis to extract the farmland planting area.

[0085] The acquisition logic of the three-dimensional space image of the farmland is as follows:

[0086] Perform geometric positioning, edge trimming, and noise removal on the farmland planting area to obtain a pre-processed farmland image;

[0087] Find at least one fixed marker in the pre-processed farmland image, perform identification processing on the fixed marker as a reference point, and perform spatial alignment based on the reference point to obtain a reference farmland image;

[0088] The reference farmland image grayscales the image using the weighted average method, takes the Rank transformation result of the grayscale image as the matching primitive, and uses a region matching algorithm based on the normalized absolute difference sum measure function to obtain a dense disparity map of the scene;

[0089] Calculate the spatial coordinates of the scene according to the parallel binocular vision imaging principle and generate a three-dimensional point cloud map; generate a three-dimensional space image of the farmland based on the three-dimensional point cloud map.

[0090] The acquisition logic of the pest and disease image is as follows:

[0091] Collect the measured species grayscale values of the species corresponding to the three-dimensional space image of the farmland, and compare the measured species grayscale values with the species reference grayscale interval corresponding to the same time sequence information. The species reference grayscale interval is the grayscale pixel interval value of the normal growth of the current species in the experimental planting environment obtained based on the analysis of the historical database;

[0092] Screen the pixel blocks whose measured species grayscale values are not within the species reference grayscale interval, take the pixel blocks not within the species reference grayscale interval as abnormal image blocks, and mark the spatial positions corresponding to the abnormal image blocks as abnormal spatial positions;

[0093] According to the pre-set continuous time series interval, the abnormal support and abnormal co-occurrence corresponding to the abnormal spatial position in the continuous time series interval are counted, wherein the abnormal support is used to indicate the total number of abnormal marks corresponding to the same abnormal spatial position in the continuous time series interval, and the abnormal co-occurrence is used to indicate the number of times different abnormal spatial positions in the continuous time series interval co-occur;

[0094] The continuous time series interval is a continuous timestamp of the multispectral images of farmland collected by satellites; when the anomaly support in the continuous time series interval is greater than a preset anomaly support threshold and the anomaly co-occurrence is greater than a preset anomaly expansion threshold, the corresponding abnormal image block is marked as a pest image, and the pest image includes at least one target type pest image and the spatial distribution of the corresponding target type pest.

[0095] The logic for acquiring the target type pest image:

[0096] Performing texture analysis on the pest image, extracting pest texture features through a gray-level co-occurrence matrix, and obtaining a pest texture feature correlation amount;

[0097] The similarity is calculated based on the normalized calculation formula according to the pest texture feature correlation quantity and the pest texture feature defined in the historical database, and the abnormal image blocks with similarity within the pest similarity threshold range are screened out, and the abnormal image blocks are marked as target species pest images.

[0098] The logic for obtaining the development trend of pests and diseases is as follows:

[0099] The target pest images corresponding to different types of pests and diseases are matrixed according to the abnormal spatial positions to obtain the spatial distribution corresponding to the target pest images;

[0100] Construct an AI algorithm analysis model, using meteorological data, images of different target species of pests and their spatial distribution as input factors, and output the induced pest impact factors corresponding to the images of different target species of pests;

[0101] The probability of pest disaster level is assigned based on the pest-inducing impact factor. The larger the probability value, the greater the probability of pest disaster. The probability assignment of different types of pests to the pest disaster level is superimposed to obtain the pest impact degree corresponding to the current pest image, and the pest development trend is characterized based on the pest impact degree.

[0102] The acquisition logic of the pest and disease early warning strategy is:

[0103] Obtain the spatial distribution and collection timestamps of different target pests; store the current pest impact based on the timestamp, and map the historical pest records corresponding to the target pests based on the timestamp;

[0104] Based on the analysis of historical pest and disease records, combined with the transmission time, evaluate the actual impact of pests and diseases, record the evaluation reports at different time periods, rewrite the timestamps according to different time periods, and display them in the corresponding pest and disease warning strategies of the smart contract.

[0105] Example 3

[0106] An electronic device according to an exemplary embodiment includes: a processor and a memory, wherein a computer program callable by the processor is stored in the memory;

[0107] The processor executes the above-mentioned crop pest and disease monitoring and warning system based on satellite remote sensing and AI algorithms by calling the computer program stored in the memory.

[0108] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. This electronic device may have relatively large differences due to different configurations or performances, and can include one or more processors (Central Processing Units, CPUs) and one or more memories. Among them, at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement the above-mentioned crop pest and disease monitoring and warning system provided by each method embodiment. This electronic device can also include other components for realizing the functions of the device. For example, this electronic device can also have components such as wired or wireless network interfaces and input / output interfaces for input / output. The embodiments of the present application will not be elaborated here.

[0109] Example 4

[0110] A computer-readable storage medium according to an exemplary embodiment has a rewritable computer program stored thereon;

[0111] When the computer program runs on a computer device, the computer device is caused to execute the above-mentioned crop pest and disease monitoring and warning system based on satellite remote sensing and AI algorithms.

[0112] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including at least one computer program. The at least one computer program can be executed by a processor to complete a crop pest and disease monitoring and early warning system based on satellite remote sensing and AI algorithms in the above embodiment. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.

[0113] In an exemplary embodiment, a computer program product or a computer program is also provided. The computer program product or the computer program includes one or more program codes, and the one or more program codes are stored in a computer-readable storage medium. One or more processors of an electronic device can read the one or more program codes from the computer-readable storage medium, and the one or more processors execute the one or more program codes, so that the electronic device can execute the above crop pest and disease monitoring and early warning system based on satellite remote sensing and AI algorithms.

[0114] It should be understood that in various embodiments of the present application, the magnitudes of the serial numbers of the above processes do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0115] It should be understood that determining B based on A does not mean determining B only based on A, and B can also be determined based on A and / or other information.

[0116] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above embodiment can be completed by hardware, or can be completed by a program instructing relevant hardware. The program can be stored in a computer-readable storage medium, and the above-mentioned storage medium can be a read-only memory, a magnetic disk, or an optical disc, etc.

[0117] The above description is only an optional embodiment of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0118] In several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only one way, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0119] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0120] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0121] As described above, this is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A crop pest monitoring and early warning system based on satellite remote sensing and AI algorithm, characterized in that: It comprises a data acquisition module (100), a data analysis module (200), a trend prediction module (300) and an early warning decision module (400), wherein each module is connected via wired or wireless connections; A data acquisition module (100) is used to regularly collect multi-spectral images of farmland covering the farmland area through satellite remote sensing technology, and to pre-process the multi-spectral images of the farmland to obtain a three-dimensional spatial image of the farmland; The data analysis module (200) compares the measured species grayscale values ​​of the three-dimensional spatial image of the farmland with the species reference grayscale intervals in the historical database, screens out abnormal image blocks, and finally marks the pest and disease images and their spatial distribution based on the abnormal support and abnormal co-occurrence in the continuous time series interval, wherein the pest and disease images include at least one target species pest image; The acquisition logic of the pest and disease image is: Collect the measured species grayscale values ​​of the species corresponding to the three-dimensional spatial image of the farmland, and compare the measured species grayscale values ​​with the species reference grayscale interval corresponding to the same time series information, wherein the species reference grayscale interval is the grayscale pixel interval value of the normal growth of the current species in the experimental planting environment obtained based on the analysis of the historical database; Screening pixel blocks whose measured species grayscale values ​​are not within the species reference grayscale interval, treating the pixel blocks that are not within the species reference grayscale interval as abnormal image blocks, and marking the spatial position corresponding to the abnormal image block as an abnormal spatial position; According to the pre-set continuous time series interval, the abnormal support and abnormal co-occurrence corresponding to the abnormal spatial position in the continuous time series interval are counted, wherein the abnormal support is used to indicate the total number of abnormal marks corresponding to the same abnormal spatial position in the continuous time series interval, and the abnormal co-occurrence is used to indicate the number of times different abnormal spatial positions in the continuous time series interval co-occur; The continuous time series interval is a continuous time stamp of the multispectral image of the farmland collected by the satellite; when the abnormal support in the continuous time series interval is greater than a preset abnormal support threshold, and the abnormal co-occurrence is greater than a preset abnormal expansion threshold, the corresponding abnormal image block is marked as a pest image, and the pest image includes at least one target type pest image and the spatial distribution of the corresponding target type pest; The trend prediction module (300) analyzes historical pest data based on an AI algorithm analysis model, obtains pest inducing impact factors corresponding to different target pest types, assigns probability values ​​to pest disaster levels based on the pest inducing impact factors, performs statistics based on the probability values ​​of pest disaster levels, and obtains pest development trends corresponding to target pest types; The early warning decision module (400) compiles a smart contract for the degree of pest impact corresponding to the current pest image, records the timestamp of the degree of pest impact in the smart contract, and evaluates the actual pest impact by considering the transmission time, thereby generating evaluation reports of different time limits, and establishing pest early warning strategies based on the evaluation reports of different time limits.

2. The crop pest monitoring and early warning system based on satellite remote sensing and AI algorithm according to claim 1, characterized in that: Multiple satellites are used to regularly acquire farmland multispectral images covering multiple bands, wherein the farmland multispectral images include b1 band spectral images, b2 band spectral images, b3 band spectral images and b4 band spectral images; the farmland multispectral images are segmented and the farmland planting areas are extracted through spectral feature analysis.

3. The crop pest monitoring and early warning system based on satellite remote sensing and AI algorithm according to claim 2 is characterized by: The logic for acquiring the three-dimensional spatial image of farmland is as follows: Perform geometric positioning, edge trimming and noise removal on the farmland planting area to obtain the initial processed farmland image; Searching for at least one fixed marker in the initially processed farmland image, marking the fixed marker as a reference point, and performing spatial alignment based on the reference point to obtain a reference farmland image; The reference farmland image is grayed out using a weighted average method, the Rank transformation result of the gray image is used as a matching primitive, and a region matching algorithm based on normalized absolute difference and a measurement function is used to obtain a dense disparity map of the scene; The spatial coordinates of the scene are calculated based on the principle of parallel binocular vision imaging, and a three-dimensional point cloud map is generated; a three-dimensional spatial image of the farmland is generated based on the three-dimensional point cloud map.

4. The crop pest monitoring and early warning system based on satellite remote sensing and AI algorithm according to claim 3 is characterized by: The logic for acquiring the target type pest image: Performing texture analysis on the pest image, extracting pest texture features through a gray-level co-occurrence matrix, and obtaining a pest texture feature correlation amount; The similarity is calculated based on the normalized calculation formula according to the pest texture feature correlation quantity and the pest texture feature defined in the historical database, and the abnormal image blocks with similarity within the pest similarity threshold range are screened out, and the abnormal image blocks are marked as target species pest images.

5. The crop pest monitoring and early warning system based on satellite remote sensing and AI algorithm according to claim 4 is characterized by: The logic for obtaining the development trend of pests and diseases is as follows: The target pest images corresponding to different types of pests and diseases are matrixed according to the abnormal spatial positions to obtain the spatial distribution corresponding to the target pest images; Construct an AI algorithm analysis model, using meteorological data, images of different target species of pests and their spatial distribution as input factors, and output the induced pest impact factors corresponding to the images of different target species of pests; The probability of pest disaster level is assigned based on the pest-inducing impact factor. The larger the probability value, the greater the probability of pest disaster. The probability assignment of different types of pests to the pest disaster level is superimposed to obtain the pest impact degree corresponding to the current pest image, and the pest development trend is characterized based on the pest impact degree.

6. The crop pest monitoring and early warning system based on satellite remote sensing and AI algorithm according to claim 5, characterized in that: The acquisition logic of the pest and disease early warning strategy is: Obtain the spatial distribution and collection timestamps corresponding to different types of target pests; Store the current degree of impact of pests and diseases based on timestamps, and map the historical pest and disease records corresponding to the target pest types based on timestamps; Based on the analysis of historical pest and disease records, and combined with the transmission time, the actual impact of pests and diseases is evaluated, and assessment reports of different time limits are recorded. The timestamps are rewritten according to different time limits, and displayed in the pest and disease early warning strategy corresponding to the smart contract.

7. A crop pest and disease monitoring and early warning method based on satellite remote sensing and AI algorithm, based on the implementation of a crop pest and disease monitoring and early warning system based on satellite remote sensing and AI algorithm according to any one of claims 1 to 6, characterized in that: The following steps are involved: The multispectral images of farmland covering the farmland area are collected regularly through satellite remote sensing technology, and the multispectral images of farmland are preprocessed to obtain the three-dimensional spatial images of farmland; Performing pest and disease analysis on the three-dimensional spatial image of the farmland to extract pest and disease images and their spatial distribution, wherein the pest and disease images include at least one target type of pest image; Analyze historical pest data based on AI algorithm analysis model, obtain the pest inducing factors corresponding to different target pest types, assign probability values ​​to pest disaster levels based on the pest inducing factors, perform statistics based on the probability values ​​of pest disaster levels, and obtain pest development trends corresponding to target pest types; The degree of pest and disease impact corresponding to the current pest and disease image is written into a smart contract, the timestamp of the degree of pest and disease impact is recorded in the smart contract, and the actual pest and disease impact is evaluated considering the transmission time, so as to generate evaluation reports of different time limits, and establish a pest and disease early warning strategy based on the evaluation reports of different time limits.

8. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the crop disease and pest monitoring and early warning system based on satellite remote sensing and AI algorithm as described in any one of claims 1 to 6 by calling the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes a crop disease and insect pest monitoring and early warning system based on satellite remote sensing and AI algorithm as described in any one of claims 1 to 6.

Images