Agricultural land use system monitoring and management method, platform and storage medium

Abstract

The present invention discloses a method, system and storage medium for monitoring and managing an agricultural land use system. The method includes: obtaining a first agricultural image of a target area collected by a remote sensing satellite; dividing the first agricultural image into cells, and calculating a first image quality parameter of each cell according to a radiation transmission model; obtaining a low-quality area in the first agricultural image according to the first image quality parameter corresponding to the cell; obtaining a second agricultural image of the low-quality area through an unmanned aerial vehicle, and embedding the second agricultural image into the first agricultural image to obtain a remote sensing corrected image with enhanced temporal and spatial resolution and information volume; calculating agricultural land use data of the target area based on the remote sensing corrected image; integrating the change trend of agricultural land use data into a decision support model to provide a decision basis for the agricultural land use system. The present invention can improve the quality of remote sensing data to achieve more accurate and effective monitoring and management of agricultural land use systems.

Description

Technical Field

[0001] The present invention relates to the technical field of land use monitoring and management, and in particular to a monitoring and management method, system and storage medium for an agricultural land use system. Background Art

[0002] As we explore in depth how to innovate ways to ensure food security, it is not difficult to find that optimizing the management of agricultural land use systems and improving capacity building are of great practical significance to current agricultural development.

[0003] Faced with the current situation of weak innovation in agricultural land use system management paths and technical platform support, existing technologies have proposed an innovative method: building an agricultural land use system management platform based on remote sensing data monitoring and model simulation technology, thereby providing strong technical support for the sustainable development of agricultural production.

[0004] However, although existing technologies have achieved certain results, due to the limitations of remote sensing data quality, the accuracy of monitoring and management results of agricultural land use systems is still insufficient. Summary of the invention

[0005] The embodiments of the present invention provide a method, system and storage medium for monitoring and managing an agricultural land use system, which can improve the quality of remote sensing data to achieve more accurate and effective monitoring and management of an agricultural land use system.

[0006] An embodiment of the present invention provides a method for monitoring and managing an agricultural land use system, comprising:

[0007] Acquire the first agricultural image of the target area collected by remote sensing satellites;

[0008] Dividing the first agricultural image into cells, and calculating a first image quality parameter of each cell according to a radiation transfer model; wherein the radiation transfer model is used to describe the atmosphere thickness, aerosol thickness, and water vapor thickness between the atmosphere and the surface;

[0009] Obtaining a low-quality area in the first agricultural image according to a first image quality parameter corresponding to the cell;

[0010] Acquire a second agricultural image of the low-quality area by using a drone, and embed the second agricultural image into the first agricultural image to obtain a remote sensing corrected image with enhanced temporal and spatial resolution and information content;

[0011] Calculating the agricultural land use data of the target area based on the remote sensing corrected image, and obtaining the change trend of the agricultural land use data based on the time series of the remote sensing corrected image; wherein the agricultural land use data includes crop area, land cover type, soil type and pest and disease status;

[0012] The changing trend of the agricultural land use data is integrated into the decision support model to provide a decision basis for the agricultural land use system.

[0013] As an improvement of the above solution, dividing the first agricultural image into cells and calculating the first image quality parameter of each cell according to the radiation transfer model includes:

[0014] The radiative transfer model calculates the atmospheric thickness by the following formula:

[0015]

[0016] Where h is the atmospheric thickness of the unit cell, θ sun is the solar zenith angle, n ave is the average refractive index of the atmosphere in the cell, n g is the surface refractive index within the cell;

[0017] The radiative transfer model calculates the aerosol thickness by the following formula:

[0018]

[0019] Where h is the atmospheric thickness of the unit cell, T a (λ) is the optical thickness of the aerosol at wavelength λ, σ(λ,p) is the cross-sectional scattering coefficient of the unit volume aerosol at wavelength λ;

[0020] The radiation transfer model calculates the water vapor thickness by the following formula:

[0021]

[0022] Where, T w (λ) is the optical thickness of water vapor at wavelength λ, k w is the wavelength coefficient, w a is the water vapor content in the cell, P is the atmospheric pressure value, and t is the temperature value in the cell;

[0023] The radiation transfer model calculates the model error value of the radiation value by the following formula:

[0024]

[0025] In the formula, I ER is the model error value, R act(λ) is the radiation observation value, R0(λ) is the radiation intensity at the top of the atmosphere, h is the atmospheric thickness of the cell, T a (λ) is the optical thickness of the aerosol, T w (λ) is the optical thickness of water vapor;

[0026] The radiation transfer model is iterated to adjust the atmospheric thickness, aerosol thickness and water vapor thickness parameter values ​​until the model error value I ER Less than a preset threshold;

[0027] The atmospheric thickness, aerosol thickness and water vapor thickness obtained by inversion are output, and the first image quality parameter of each cell is obtained according to the atmospheric thickness, aerosol thickness and water vapor thickness.

[0028] As an improvement of the above solution, obtaining the first image quality parameter of each cell according to the atmosphere thickness, aerosol thickness and water vapor thickness includes:

[0029]

[0030] Where Q1 is the first image quality parameter, h is the atmospheric thickness of the cell, and T a (λ) is the optical thickness of the aerosol at wavelength λ, T w (λ) is the optical thickness of water vapor at wavelength λ, and q1, q2, and q3 are the weight coefficients corresponding to the atmosphere thickness, aerosol thickness, and water vapor thickness, respectively.

[0031] As an improvement of the above solution, the step of acquiring a first agricultural image of a target area collected by a remote sensing satellite includes:

[0032] Preprocessing the first initial image data collected by the remote sensing satellite to obtain the first agricultural image;

[0033] The preprocessing includes: eliminating sensor errors, dimensional alignment and geometric correction.

[0034] As an improvement of the above solution, the second agricultural image of the low-quality area is obtained by using a drone, and the second agricultural image is embedded in the first agricultural image to obtain a remote sensing corrected image with enhanced spatiotemporal resolution and information content, including:

[0035] Preprocessing the second initial image acquired by the UAV to obtain the second agricultural image that can be geometrically aligned and scale-aligned with the first agricultural image;

[0036] The second agricultural image is divided into boundaries according to the edge of the low-quality area, and the divided second agricultural image is embedded into the first agricultural image to obtain the remote sensing corrected image through fusion.

[0037] As an improvement of the above scheme, the agricultural land use data of the target area is calculated based on the remote sensing corrected image, and the change trend of the agricultural land use data is obtained based on the time sequence of the remote sensing corrected image, including:

[0038] Performing agricultural land boundary recognition on the remote sensing corrected image and obtaining the agricultural land utilization area;

[0039] Using a classification algorithm to classify the agricultural land in the remote sensing corrected image, and obtaining the agricultural land use data of each land use area by feature extraction;

[0040] Based on the time series of the remote sensing corrected images, change detection analysis is performed on the land use areas at different times to identify the change trend of the agricultural land use data.

[0041] As an improvement of the above scheme, it also includes:

[0042] storing the first agricultural image, the first image quality parameter, the second agricultural image, the remote sensing corrected image and the change trend of the agricultural land use data via a cloud computing platform;

[0043] And set data access permissions for the cloud computing platform.

[0044] Another embodiment of the present invention provides an agricultural land use system monitoring and management platform, including:

[0045] An image collection module, used for acquiring a first agricultural image of a target area collected by a remote sensing satellite;

[0046] An image quality calculation module, used for dividing the first agricultural image into cells, and calculating a first image quality parameter of each cell according to a radiation transfer model; wherein the radiation transfer model is used to describe the atmosphere thickness, aerosol thickness and water vapor thickness between the atmosphere and the surface;

[0047] A region identification module, used for obtaining a low-quality region in the first agricultural image according to a first image quality parameter corresponding to the cell;

[0048] An image enhancement module is used to acquire a second agricultural image of the low-quality area through a drone, and embed the second agricultural image into the first agricultural image to obtain a remote sensing corrected image with enhanced temporal and spatial resolution and information content;

[0049] An agricultural data calculation module, used to calculate the agricultural land use data of the target area based on the remote sensing corrected image, and obtain the change trend of the agricultural land use data based on the time sequence of the remote sensing corrected image; wherein the agricultural land use data includes crop area, land cover type, soil type and pest and disease status;

[0050] The decision support module is used to integrate the changing trend of the agricultural land use data into the decision support model to provide a decision basis for the agricultural land use system.

[0051] Another embodiment of the present invention provides an agricultural land use system monitoring and management platform, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the agricultural land use system monitoring and management method described in the above-mentioned embodiment of the invention.

[0052] Another embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the agricultural land use system monitoring and management method as described in the above-mentioned embodiment of the invention.

[0053] Compared with the prior art, in the embodiments of the present invention, image quality analysis is performed on satellite remote sensing images through image influencing factors between the atmosphere and the surface; areas with low image quality are resampled using drones, thereby improving the quality of remote sensing data and providing a highly accurate data foundation for precise and effective monitoring and management of agricultural land use systems; by combining large-scale data obtained by remote sensing technology with the powerful data processing capabilities of cloud computing, a breakthrough has been achieved in the systematic monitoring and management of agricultural land use, which not only provides strong technical support for the systematic management of agricultural land use, but also plays a vital role in optimizing land use efficiency and improving agricultural productivity. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a flow chart of a method for monitoring and managing an agricultural land utilization system provided by one embodiment of the present invention;

[0055] Figure 2 It is a structural diagram of an agricultural land utilization system monitoring and management platform provided by an embodiment of the present invention;

[0056] Figure 3 It is a structural diagram of an agricultural land utilization system monitoring and management platform provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] See also Figure 1 , is a flow chart of a method for monitoring and managing an agricultural land use system provided by an embodiment of the present invention, including steps S101 to S106:

[0059] S101, acquiring a first agricultural image of a target area collected by a remote sensing satellite;

[0060] Specifically, in order to obtain agricultural land use data for a specific target area, this embodiment collects data through remote sensing satellite technology. This process involves using a high-resolution remote sensing camera to capture the surface conditions of the area. These first agricultural images will then be transmitted to a ground receiving station. The first agricultural image will provide the agricultural utilization system with information on the crop area, land cover type, soil type, pest and disease status, and its changing trends in the target area, providing raw materials for further data analysis and application. It can be seen that this step is the basis of agricultural land use research and is of great significance for guiding agricultural production, optimizing resource allocation, and protecting the ecological environment.

[0061] S102, dividing the first agricultural image into cells, and calculating a first image quality parameter of each cell according to a radiation transfer model; wherein the radiation transfer model is used to describe the atmosphere thickness, aerosol thickness, and water vapor thickness between the atmosphere and the surface;

[0062] Specifically, in satellite remote sensing images, atmospheric scattering and absorption will cause changes in the reflectivity of the surface of the objects, and the images after atmospheric correction cannot fully meet the image quality requirements. Therefore, it is necessary to judge the image quality parameters based on the atmospheric thickness, aerosol thickness and water vapor thickness.

[0063] S103, obtaining a low-quality area in the first agricultural image according to a first image quality parameter corresponding to the cell;

[0064] Specifically, based on the first image quality parameter corresponding to the cell, the areas of the first agricultural image with low quality due to atmospheric factors can be identified and located, thereby identifying the areas that need to be resampled to improve the overall quality and practicality of the image. In particular, in the field of agricultural land use monitoring and analysis, the acquisition of high-quality images is of great significance for accurately identifying and analyzing crop growth conditions, detecting pests and diseases, and effectively managing resources.

[0065] S104, acquiring a second agricultural image of the low-quality area by using a drone, and embedding the second agricultural image into the first agricultural image to obtain a remote sensing corrected image with enhanced temporal and spatial resolution and information content;

[0066] Specifically, this embodiment uses drone technology to capture the second agricultural image corresponding to the areas with lower quality in the satellite remote sensing image. Since the resolution of the second agricultural image is relatively high, after the second agricultural image is embedded in the first agricultural image, the spatiotemporal resolution of the embedded image can be significantly improved, and the amount of information contained in the image is also greatly enhanced. At the same time, it is not necessary to use drones for image acquisition in the entire area, which reduces the acquisition cost while ensuring image quality.

[0067] S105, calculating agricultural land use data of the target area based on the remote sensing corrected image, and obtaining a change trend of the agricultural land use data based on the time series of the remote sensing corrected image; wherein the agricultural land use data includes crop area, land cover type, soil type and pest and disease status;

[0068] Specifically, the corrected images can clearly reveal the changing trends of agricultural land use data over time through time series analysis. These data cover the crop area on agricultural land, different land cover types such as forests, grasslands, water bodies, etc., soil types and their fertility, and possible pests and diseases.

[0069] S106. Integrate the changing trend of agricultural land use data into the decision support model to provide decision-making basis for the agricultural land use system.

[0070] Specifically, through the above detailed agricultural land use data, we can have a comprehensive and in-depth understanding of the agricultural land use status in the target area, so as to provide scientific guidance for agricultural production, help to reasonably arrange planting plans, and provide decision-making support for agricultural management, such as reasonably allocating land resources and optimizing agricultural production structure.

[0071] In addition, by analyzing the changing trends of agricultural land use data, we can also predict the direction of future changes in agricultural land use, which is crucial for formulating agricultural sustainable development strategies. For example, through prediction, we can prepare in advance to deal with possible land resource shortages, or adjust crop planting structures to adapt to environmental problems such as climate change. This will not only help protect the agricultural ecological environment, but also ensure the stability and sustained growth of agricultural production, providing strong data support and decision-making basis for food security and agricultural sustainable development.

[0072] In this embodiment, preferably, dividing the first agricultural image into cells and calculating the first image quality parameter of each cell according to the radiation transfer model includes:

[0073] The radiative transfer model calculates the atmospheric thickness using the following equation:

[0074]

[0075] Where h is the atmospheric thickness of the unit cell, θ sun is the solar zenith angle, n ave is the average refractive index of the atmosphere in the cell, n g is the surface refractive index within the cell;

[0076] The radiative transfer model calculates the aerosol thickness using the following formula:

[0077]

[0078] Where h is the atmospheric thickness of the unit cell, T a (λ) is the optical thickness of the aerosol at wavelength λ, σ(λ,p) is the cross-sectional scattering coefficient of the unit volume aerosol at wavelength λ;

[0079] The radiative transfer model calculates the water vapor thickness using the following equation:

[0080]

[0081] Where, T w (λ) is the optical thickness of water vapor at wavelength λ, k w is the wavelength coefficient, w a is the water vapor content in the cell, P is the atmospheric pressure value, and t is the temperature value in the cell;

[0082] The radiative transfer model calculates the model error value of the radiation value through the following formula:

[0083]

[0084] In the formula, I ER is the model error value, R act (λ) is the radiation observation value, R0(λ) is the radiation intensity at the top of the atmosphere, h is the atmospheric thickness of the cell, T a (λ) is the optical thickness of the aerosol, T w (λ) is the optical thickness of water vapor;

[0085] The radiation transfer model is iterated to adjust the atmospheric thickness, aerosol thickness and water vapor thickness parameters until the model error value I ER Less than a preset threshold;

[0086] The inverted atmospheric thickness, aerosol thickness and water vapor thickness are output, and the first image quality parameter of each cell is obtained according to the atmospheric thickness, aerosol thickness and water vapor thickness.

[0087] Specifically, before the calculation, parameters are input into the radiation transfer model, including the solar zenith angle corresponding to the cell at the acquisition time of the first agricultural image, the average atmospheric refractive index, the surface albedo, the atmospheric pressure value, the temperature value, the radiation observation value, the radiation intensity at the top of the atmosphere and other parameters required by the model.

[0088] Specifically, a band suitable for atmospheric thickness calculation is selected in the remote sensing image, such as a band in the near infrared (NIR) or short wave infrared (SWIR) range, because the atmosphere has less absorption in these bands.

[0089] Specifically, the above-mentioned atmospheric thickness can be expressed by optical thickness, which is a measure of the absorption and scattering of the atmosphere in a specific band.

[0090] Specifically, based on the radiation intensity R0(λ) at the top of the atmosphere, the atmospheric thickness h of the cell, and the optical thickness T of the aerosol a (λ) and the optical thickness of water vapor T w After the theoretical value of radiation intensity is calculated, the theoretical value of radiation intensity is compared with the actual radiation observation value, and the atmospheric thickness parameter is adjusted by an iterative method until the model error value I of the two is equal. ER If the value is less than the preset threshold, the matching degree meets the system requirements. At this time, the atmospheric thickness h and the optical thickness T of the aerosol of the corresponding cell can be output. a (λ) and the optical thickness of water vapor T w (λ) data.

[0091] In this embodiment, preferably, the first image quality parameter of each cell is obtained according to the atmosphere thickness, the aerosol thickness and the water vapor thickness, including:

[0092]

[0093] Where Q1 is the first image quality parameter, h is the atmospheric thickness of the cell, and T a (λ) is the optical thickness of the aerosol at wavelength λ, T w (λ) is the optical thickness of water vapor at wavelength λ, and q1, q2, and q3 are the weight coefficients corresponding to the atmosphere thickness, aerosol thickness, and water vapor thickness, respectively.

[0094] Specifically, this embodiment adopts a method of weighted calculation of the inverse of the thickness data. For data with large errors, the inverse weight is small, so the impact on the final result will also be reduced, which helps to reduce the negative impact of abnormal values ​​or inaccurate data on the overall analysis results. When the uncertainty or accuracy of the data is not uniformly distributed, the inverse weighting method can more reasonably reflect the distribution characteristics of the data.

[0095] In this embodiment, preferably, obtaining a first agricultural image of a target area collected by a remote sensing satellite includes:

[0096] Preprocessing the first initial image data collected by the remote sensing satellite to obtain a first agricultural image;

[0097] Among them, preprocessing includes: eliminating sensor errors, size alignment and geometric correction.

[0098] Specifically, after the remote sensing satellite collects the first initial image, it conducts a preliminary check on the data integrity and quality; then it eliminates sensor errors, including inconsistencies in radiation response, through a radiation correction process to ensure that the image data reflects the true reflective characteristics of the surface.

[0099] Furthermore, size alignment may be performed, that is, the image data may be size aligned to ensure that each pixel in the image corresponds to an accurate position on the ground surface.

[0100] Furthermore, geometric correction can be performed by using ground control points or satellite geolocation data to perform geometric correction on the image to ensure consistency between the image and the actual terrain.

[0101] In addition, image enhancement, such as histogram equalization or contrast stretching, can be performed to improve the visual effect of the image and make agricultural features more obvious.

[0102] In this embodiment, preferably, a second agricultural image of a low-quality area is acquired by a drone, and the second agricultural image is embedded in the first agricultural image to obtain a remote sensing corrected image with enhanced spatiotemporal resolution and information content, including:

[0103] Preprocessing the second initial image acquired by the UAV to obtain a second agricultural image that can be geometrically aligned and scale-aligned with the first agricultural image;

[0104] According to the edge of the low-quality area, the boundary of the second agricultural image is divided, and the divided second agricultural image is embedded in the first agricultural image to obtain a remote sensing corrected image.

[0105] Specifically, drone technology can be used to obtain high-quality agricultural area images. At this time, the second initial image obtained by the drone can be geometrically aligned and scale-aligned with the first agricultural image to ensure that corresponding pixel points in the images can overlap.

[0106] In a specific embodiment, since the low-quality area in the first agricultural image has been obtained according to the first image quality parameter corresponding to the cell in the aforementioned steps, after the images are aligned, the boundary of the second agricultural image can be divided based on the low-quality area in the first agricultural image to obtain a replacement area with the same shape and size as the low-quality area. At this time, the replacement area is embedded in the first agricultural image of the low-quality area, and fused to obtain a high-quality and high-precision remote sensing corrected image.

[0107] In another specific embodiment, after the images are aligned, the edges of the second agricultural image can be determined based on the low-quality area in the first agricultural image, and the determined edges can be expanded outward at a preset interval to obtain a replacement area that has the same shape as the low-quality area but a larger area; at this time, the replacement area is embedded in the first agricultural image of the low-quality area, the part of the replacement area that overlaps with the low-quality area is replaced, and the part of the replacement area that expands outside the low-quality area is subjected to image fusion to achieve a smooth transition of resolution.

[0108] Among them, the image fusion method can be: scaling the resolution of the part to be fused so that the resolution from the edge of the low-quality area to the edge of the expanded part of the replacement area decreases; then, through the interpolation algorithm, a smoother transition is made between different resolutions in the image, thereby retaining as many details as possible while reducing the visual incoherence caused by the resolution difference.

[0109] In summary, the problem of low image quality caused by atmospheric factors is avoided, so that the final remote sensing corrected image has higher practicality and accuracy in the agricultural field, fully utilizes the image information obtained at different time points, effectively overcomes the problem of insufficient image quality at a single time point, and provides strong technical support for agricultural remote sensing monitoring.

[0110] In this embodiment, preferably, the agricultural land use data of the target area is calculated based on the remote sensing corrected image, and the change trend of the agricultural land use data is obtained based on the time sequence of the remote sensing corrected image, including:

[0111] Identify agricultural land boundaries on remote sensing corrected images and obtain agricultural land use area;

[0112] The classification algorithm is used to classify the agricultural land in the remote sensing corrected image, and the agricultural land use data of each land use area is obtained through feature extraction;

[0113] Based on the time series of remote sensing corrected images, change detection analysis is performed on land use areas at different times to identify the changing trends of agricultural land use data.

[0114] Specifically, the classification algorithm can be a supervised classification or an unsupervised classification algorithm, such as a support vector machine (SVM), a random forest algorithm, a K-means clustering algorithm, etc., to perform land classification and identification on the remote sensing corrected image.

[0115] Specifically, the change areas between different time points can be identified through image difference, normalized difference vegetation index (NDVI) difference analysis, principal component analysis (PCA) and other scattered algorithms.

[0116] Specifically, the analysis results of the changing trends of agricultural land use data can be integrated into the Geographic Information System (GIS) to facilitate spatial analysis and visualization.

[0117] In this embodiment, preferably, it also includes:

[0118] storing the first agricultural image, the first image quality parameter, the second agricultural image, the remote sensing corrected image and the change trend of agricultural land use data via a cloud computing platform;

[0119] And set data access permissions for the cloud computing platform.

[0120] Specifically, the cloud computing platform can not only store image data, but also record the changing trends of agricultural land use data, which can reflect the crop area, land cover type, soil type, and pest and disease status of agricultural land. In order to protect the security of these data, data access rights can be set for the cloud computing platform, and only authorized users can access these data, thereby reducing local computing pressure and improving computing efficiency, while enhancing data security.

[0121] In summary, in the embodiments of the present invention, the image quality analysis of the satellite remote sensing image is performed through the image influencing factors between the atmosphere and the surface; the areas with low image quality are resampled by using drones, thereby improving the quality of remote sensing data and providing a high-accuracy data foundation for precise and effective monitoring and management of agricultural land use systems; by combining the large-scale data obtained by remote sensing technology with the powerful data processing capabilities of cloud computing, a breakthrough has been achieved in the systematic monitoring and management of agricultural land use, which not only provides strong technical support for the systematic management of agricultural land use, but also plays a vital role in optimizing land use efficiency and improving agricultural productivity.

[0122] See also Figure 2 , is a structural diagram of an agricultural land use system monitoring and management platform provided by an embodiment of the present invention, including:

[0123] An image collection module 201 is used to obtain a first agricultural image of a target area collected by a remote sensing satellite;

[0124] The image quality calculation module 202 is used to divide the first agricultural image into cells and calculate the first image quality parameter of each cell according to the radiation transfer model; wherein the radiation transfer model is used to describe the atmosphere thickness, aerosol thickness and water vapor thickness between the atmosphere and the surface;

[0125] A region identification module 203, used for obtaining a low-quality region in the first agricultural image according to a first image quality parameter corresponding to a cell;

[0126] The image enhancement module 204 is used to obtain a second agricultural image of the low-quality area through the UAV, and embed the second agricultural image into the first agricultural image to obtain a remote sensing corrected image with enhanced spatiotemporal resolution and information content;

[0127] The agricultural data calculation module 205 is used to calculate the agricultural land use data of the target area based on the remote sensing corrected image, and obtain the change trend of the agricultural land use data based on the time series of the remote sensing corrected image; wherein the agricultural land use data includes the crop area, land cover type, soil type and pest and disease status;

[0128] The decision support module 206 is used to integrate the changing trend of agricultural land use data into the decision support model to provide a decision basis for the agricultural land use system.

[0129] Furthermore, the first agricultural image is divided into cells, and the first image quality parameter of each cell is calculated according to the radiation transfer model, including:

[0130] The radiative transfer model calculates the atmospheric thickness using the following equation:

[0131]

[0132] Where h is the atmospheric thickness of the unit cell, θ sun is the solar zenith angle, n ave is the average refractive index of the atmosphere in the cell, n g is the surface refractive index within the cell;

[0133] The radiative transfer model calculates the aerosol thickness using the following formula:

[0134]

[0135] Where h is the atmospheric thickness of the unit cell, T a (λ) is the optical thickness of the aerosol at wavelength λ, σ(λ,p) is the cross-sectional scattering coefficient of the unit volume aerosol at wavelength λ;

[0136] The radiative transfer model calculates the water vapor thickness using the following equation:

[0137]

[0138] Where, T w (λ) is the optical thickness of water vapor at wavelength λ, k w is the wavelength coefficient, w a is the water vapor content in the cell, P is the atmospheric pressure value, and t is the temperature value in the cell;

[0139] The radiative transfer model calculates the model error value of the radiation value through the following formula:

[0140]

[0141] In the formula, I ER is the model error value, R act (λ) is the radiation observation value, R0(λ) is the radiation intensity at the top of the atmosphere, h is the atmospheric thickness of the cell, T a (λ) is the optical thickness of the aerosol, T w (λ) is the optical thickness of water vapor;

[0142] The radiation transfer model is iterated to adjust the atmospheric thickness, aerosol thickness and water vapor thickness parameters until the model error value I ER Less than a preset threshold;

[0143] The inverted atmospheric thickness, aerosol thickness and water vapor thickness are output, and the first image quality parameter of each cell is obtained according to the atmospheric thickness, aerosol thickness and water vapor thickness.

[0144] Furthermore, the first image quality parameter of each cell is obtained according to the atmosphere thickness, the aerosol thickness and the water vapor thickness, including:

[0145]

[0146] Where Q1 is the first image quality parameter, h is the atmospheric thickness of the cell, and T a (λ) is the optical thickness of the aerosol at wavelength λ, T w (λ) is the optical thickness of water vapor at wavelength λ, and q1, q2, and q3 are the weight coefficients corresponding to the atmosphere thickness, aerosol thickness, and water vapor thickness, respectively.

[0147] Further, obtaining a first agricultural image of the target area collected by a remote sensing satellite includes:

[0148] Preprocessing the first initial image data collected by the remote sensing satellite to obtain a first agricultural image;

[0149] Among them, preprocessing includes: eliminating sensor errors, size alignment and geometric correction.

[0150] Furthermore, a second agricultural image of the low-quality area is obtained by using a drone, and the second agricultural image is embedded in the first agricultural image to obtain a remote sensing corrected image with enhanced spatiotemporal resolution and information content, including:

[0151] Preprocessing the second initial image acquired by the UAV to obtain a second agricultural image that can be geometrically aligned and scale-aligned with the first agricultural image;

[0152] According to the edge of the low-quality area, the boundary of the second agricultural image is divided, and the divided second agricultural image is embedded in the first agricultural image to obtain a remote sensing corrected image.

[0153] Furthermore, the agricultural land use data of the target area is calculated based on the remote sensing corrected image, and the change trend of the agricultural land use data is obtained based on the time series of the remote sensing corrected image, including:

[0154] Identify agricultural land boundaries on remote sensing corrected images and obtain agricultural land use area;

[0155] The classification algorithm is used to classify the agricultural land in the remote sensing corrected image, and the agricultural land use data of each land use area is obtained through feature extraction;

[0156] Based on the time series of remote sensing corrected images, change detection analysis is performed on land use areas at different times to identify the changing trends of agricultural land use data.

[0157] Furthermore, it also includes:

[0158] storing the first agricultural image, the first image quality parameter, the second agricultural image, the remote sensing corrected image and the change trend of agricultural land use data via a cloud computing platform;

[0159] And set data access permissions for the cloud computing platform.

[0160] In summary, in the embodiments of the present invention, the image quality analysis of the satellite remote sensing image is performed through the image influencing factors between the atmosphere and the surface; the areas with low image quality are resampled by using drones, thereby improving the quality of remote sensing data and providing a high-accuracy data foundation for precise and effective monitoring and management of agricultural land use systems; by combining the large-scale data obtained by remote sensing technology with the powerful data processing capabilities of cloud computing, a breakthrough has been achieved in the systematic monitoring and management of agricultural land use, which not only provides strong technical support for the systematic management of agricultural land use, but also plays a vital role in optimizing land use efficiency and improving agricultural productivity.

[0161] See also Figure 3, is a schematic diagram of an agricultural land use system monitoring and management platform provided by an embodiment of the present invention. The agricultural land use system monitoring and management platform of this embodiment includes: a processor 1, a memory 2, and a computer program stored in the memory 2 and executable on the processor, such as an agricultural land use system monitoring and management program. When the processor 1 executes the computer program, the steps in the above-mentioned agricultural land use system monitoring and management method embodiments are implemented. Alternatively, when the processor 1 executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented.

[0162] Exemplarily, the computer program can be divided into one or more modules / units, one or more modules / units are stored in a memory and executed by a processor to complete the present invention. One or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the agricultural land use system monitoring and management platform.

[0163] The agricultural land use system monitoring and management platform may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram is merely an example of the agricultural land use system monitoring and management platform and does not constitute a limitation on the agricultural land use system monitoring and management platform. The agricultural land use system monitoring and management platform may include more or fewer components than shown in the diagram, or may combine certain components, or different components. For example, the agricultural land use system monitoring and management platform may also include input and output devices, network access devices, CAN buses, etc.

[0164] An embodiment of the present invention provides a computer-readable storage medium, characterized in that the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the agricultural land use system monitoring and management method such as the first embodiment of the present invention.

[0165] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the agricultural land use system monitoring and management platform, and uses various interfaces and lines to connect various parts of the entire agricultural land use system monitoring and management platform.

[0166] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the agricultural land use system monitoring and management platform by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0167] Among them, if the module / unit integrated in the monitoring and management platform of the agricultural land use system is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0168] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0169] The above are preferred embodiments of the present invention. It should be noted that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for monitoring and managing agricultural land use system, characterized in that: include: Acquire the first agricultural image of the target area collected by remote sensing satellites; Dividing the first agricultural image into cells, and calculating a first image quality parameter of each cell according to a radiation transfer model; wherein the radiation transfer model is used to describe the atmosphere thickness, aerosol thickness, and water vapor thickness between the atmosphere and the surface; Obtaining a low-quality area in the first agricultural image according to a first image quality parameter corresponding to the cell; Acquire a second agricultural image of the low-quality area by using a drone, and embed the second agricultural image into the first agricultural image to obtain a remote sensing corrected image with enhanced temporal and spatial resolution and information content; Calculating the agricultural land use data of the target area based on the remote sensing corrected image, and obtaining the change trend of the agricultural land use data based on the time series of the remote sensing corrected image; wherein the agricultural land use data includes crop area, land cover type, soil type and pest and disease status; The changing trend of the agricultural land use data is integrated into the decision support model to provide a decision basis for the agricultural land use system.

2. The agricultural land use system monitoring and management method according to claim 1, characterized in that: The step of dividing the first agricultural image into cells and calculating the first image quality parameter of each cell according to the radiation transfer model includes: The radiative transfer model calculates the atmospheric thickness by the following formula: Where h is the atmospheric thickness of the unit cell, θ sun is the solar zenith angle, n ave is the average refractive index of the atmosphere within the cell, n g is the surface refractive index within the cell; The radiative transfer model calculates the aerosol thickness by the following formula: Where h is the atmospheric thickness of the unit cell, T a (λ) is the optical thickness of the aerosol at wavelength λ, p is the integral variable, representing each position that the light passes through during the propagation from 0 to h, and σ(λ,p) is the cross-sectional scattering coefficient of the unit volume of aerosol at wavelength λ; The radiation transfer model calculates the water vapor thickness by the following formula: Where, T w (λ) is the optical thickness of water vapor at wavelength λ, k w is the wavelength coefficient, w a is the water vapor content in the cell, P is the atmospheric pressure value, and t is the temperature value in the cell; The radiation transfer model calculates the model error value of the radiation value by the following formula: In the formula, I ER is the model error value, R act (λ) is the radiation observation value, R0(λ) is the radiation intensity at the top of the atmosphere, h is the atmospheric thickness of the cell, T a (λ) is the optical thickness of the aerosol, T w (λ) is the optical thickness of water vapor; The radiation transfer model is iterated to adjust the atmospheric thickness, aerosol thickness and water vapor thickness parameter values ​​until the model error value I ER Less than a preset threshold; The atmospheric thickness, aerosol thickness and water vapor thickness obtained by inversion are output, and the first image quality parameter of each cell is obtained according to the atmospheric thickness, aerosol thickness and water vapor thickness.

3. The agricultural land use system monitoring and management method according to claim 2, characterized in that: The obtaining the first image quality parameter of each cell according to the atmosphere thickness, the aerosol thickness and the water vapor thickness includes: Where Q1 is the first image quality parameter, h is the atmospheric thickness of the cell, and T a (λ) is the optical thickness of the aerosol at wavelength λ, T w (λ) is the optical thickness of water vapor at wavelength λ, and q1, q2, and q3 are the weight coefficients corresponding to the atmosphere thickness, aerosol thickness, and water vapor thickness, respectively.

4. The agricultural land utilization system monitoring and management method according to claim 1, characterized in that: The step of acquiring a first agricultural image of a target area collected by a remote sensing satellite comprises: Preprocessing the first initial image data collected by the remote sensing satellite to obtain the first agricultural image; The preprocessing includes: eliminating sensor errors, dimensional alignment and geometric correction.

5. The agricultural land use system monitoring and management method according to claim 2, characterized in that: The method of acquiring a second agricultural image of the low-quality area by using a drone and embedding the second agricultural image into the first agricultural image to obtain a remote sensing corrected image with enhanced temporal and spatial resolution and information content includes: Preprocessing the second initial image acquired by the UAV to obtain the second agricultural image that can be geometrically aligned and scale-aligned with the first agricultural image; The second agricultural image is divided into boundaries according to the edge of the low-quality area, and the divided second agricultural image is embedded into the first agricultural image to obtain the remote sensing corrected image through fusion.

6. The agricultural land utilization system monitoring and management method according to claim 1, characterized in that: The calculating the agricultural land use data of the target area based on the remote sensing corrected image, and obtaining the change trend of the agricultural land use data based on the time sequence of the remote sensing corrected image, includes: Performing agricultural land boundary recognition on the remote sensing corrected image and obtaining the agricultural land utilization area; Using a classification algorithm to classify the agricultural land in the remote sensing corrected image, and obtaining the agricultural land use data of each land use area by feature extraction; Based on the time series of the remote sensing corrected images, change detection analysis is performed on the land use areas at different times to identify the change trend of the agricultural land use data.

7. The agricultural land utilization system monitoring and management method according to claim 1, characterized in that: Also includes: storing the first agricultural image, the first image quality parameter, the second agricultural image, the remote sensing corrected image and the change trend of the agricultural land use data via a cloud computing platform; And set data access permissions for the cloud computing platform.

8. An agricultural land use system monitoring and management platform, characterized in that: include: An image collection module, used for acquiring a first agricultural image of a target area collected by a remote sensing satellite; An image quality calculation module, used for dividing the first agricultural image into cells, and calculating a first image quality parameter of each cell according to a radiation transfer model; wherein the radiation transfer model is used to describe the atmosphere thickness, aerosol thickness and water vapor thickness between the atmosphere and the surface; A region identification module, used for obtaining a low-quality region in the first agricultural image according to a first image quality parameter corresponding to the cell; An image enhancement module is used to acquire a second agricultural image of the low-quality area through a drone, and embed the second agricultural image into the first agricultural image to obtain a remote sensing corrected image with enhanced temporal and spatial resolution and information content; An agricultural data calculation module, used to calculate the agricultural land use data of the target area based on the remote sensing corrected image, and obtain the change trend of the agricultural land use data based on the time sequence of the remote sensing corrected image; wherein the agricultural land use data includes crop area, land cover type, soil type and pest and disease status; The decision support module is used to integrate the changing trend of the agricultural land use data into the decision support model to provide a decision basis for the agricultural land use system.

9. An agricultural land use system monitoring and management platform, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements an agricultural land use system monitoring and management method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the agricultural land use system monitoring and management method as described in any one of claims 1 to 7.

Images