High-standard farmland sky-ground integrated intelligent supervision method and system

Abstract

The invention relates to the field of farmland supervision, and particularly discloses a high-standard farmland sky-ground integrated intelligent supervision method and system, and the method comprises the steps: obtaining a farmland picture shot by a satellite and a farmland picture shot by an unmanned plane, and building a three-dimensional model of the farmland; dividing the farmland into different areas according to the three-dimensional model, and collecting historical data and real-time data in each area; establishing a growth model according to historical data; and substituting real-time data into the growth model, and executing a corresponding countermeasure according to a result. According to the method, a satellite on the sky and an unmanned aerial vehicle in the air are utilized to shoot farmland photos and generate a three-dimensional model, then the farmland is divided into different areas according to different crops, then a growth model is established according to historical data such as soil, pests and the atmospheric environment, real-time data are substituted into the growth model, and the three-dimensional model is established. Therefore, the actual condition and the corresponding countermeasure of the farmland can be obtained, and the accuracy is higher.

Description

Technical Field

[0001] This invention relates to the field of farmland supervision, specifically to a method and system for integrated air-ground intelligent supervision of high-standard farmland. Background Technology

[0002] Farmland, also known as arable land, refers to land that can be used to grow crops, providing essential resources for people's lives, such as rice, wheat, and cotton.

[0003] With the advancement of technology, people are using it in farmland to ensure that farmland can produce higher yields and better quality crops. However, various parameters of farmland are changing, so people monitor farmland to ensure the healthy growth of crops.

[0004] Existing monitoring methods only measure the soil composition in farmland, and at most monitor the water quality in farmland. Although they can provide data on soil and water, the monitoring is relatively one-sided and the accuracy needs to be improved. Summary of the Invention

[0005] The purpose of this invention is to provide a high-standard farmland integrated smart monitoring method and system to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A high-standard farmland integrated air-ground intelligent monitoring method, the method comprising:

[0008] Acquire photos of farmland taken by satellite and drones, and create a 3D model of the farmland;

[0009] Based on the three-dimensional model, the farmland is divided into different areas, and historical and real-time data are collected in each area. The historical and real-time data include pest data, atmospheric environmental data, water quality data, and soil data at different locations and depths.

[0010] Establish growth models based on historical data;

[0011] Real-time data is fed into the growth model, and corresponding countermeasures are implemented based on the results.

[0012] As a further aspect of the present invention: the step of acquiring farmland photos taken by satellite and drones, and establishing a three-dimensional model of the farmland includes:

[0013] Acquire photos of farmland taken by satellite and drones;

[0014] Different photos of farmland are rotated, projected, and stitched together to obtain a three-dimensional model of the farmland.

[0015] As a further aspect of the present invention: before establishing the growth model based on historical data, the following is also included:

[0016] Remove unreasonable data from historical data and perform data cleaning on the deleted historical data.

[0017] As a further aspect of the present invention: the step of establishing a growth model based on historical data includes:

[0018] Historical data is randomly divided into training set, test set and validation set, with the ratio of the number of data in the training set, test set and validation set being 7:2:1;

[0019] The initial growth model is obtained based on the training set;

[0020] Substitute the test set and validation set into the initial growth model, and determine the growth model based on the results.

[0021] The present invention also provides a high-standard farmland integrated air-ground intelligent monitoring system, the system comprising:

[0022] The 3D model generation module is used to acquire farmland photos taken by satellite and drones and build 3D models of the farmland.

[0023] The data acquisition module is used to divide farmland into different areas based on the 3D model and collect historical and real-time data for each area. The historical and real-time data include pest data, atmospheric environmental data, water quality data, and soil data at different locations and depths.

[0024] The growth model generation module is used to build growth models based on historical data.

[0025] The strategy generation module is used to input real-time data into the growth model and execute corresponding strategies based on the results.

[0026] As a further aspect of the present invention: the three-dimensional model generation module includes:

[0027] The photo acquisition unit is used to acquire photos of farmland taken by satellite and drones;

[0028] The 3D model generation unit is used to rotate, project, and stitch different farmland photos to obtain a 3D model of the farmland.

[0029] As a further aspect of the present invention: the high-standard farmland integrated air-ground intelligent monitoring system also includes:

[0030] The data processing module is used to delete unreasonable data from historical data and clean the deleted historical data.

[0031] As a further aspect of the present invention: the growth model generation module includes:

[0032] The partitioning unit is used to randomly divide historical data into training set, test set and validation set, with the ratio of the number of data in the training set, test set and validation set being 7:2:1;

[0033] The initial model generation unit is used to obtain the initial growth model based on the training set.

[0034] The growth model generation unit is used to substitute the test set and validation set into the initial growth model and determine the growth model based on the results.

[0035] Compared with existing technologies, the beneficial effects of this invention are: This invention uses satellites in the sky and drones in the air to take pictures of farmland and generate three-dimensional models. Then, the farmland is divided into different areas according to different crops. Then, a growth model is established based on historical data such as soil, pests, and atmospheric environment. Then, real-time data is substituted into the growth model to obtain the actual condition of the farmland and corresponding countermeasures, with higher accuracy. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention.

[0037] Figure 1 A flowchart illustrating the integrated air-ground intelligent monitoring method for high-standard farmland.

[0038] Figure 2 This is the first sub-process flowchart of the integrated air-ground intelligent supervision method for high-standard farmland.

[0039] Figure 3 This is the third sub-process flowchart of the integrated air-ground intelligent supervision method for high-standard farmland.

[0040] Figure 4 This is a structural diagram of the integrated air-ground intelligent monitoring system for high-standard farmland.

[0041] Figure 5 This is a structural diagram of the 3D model generation module in the high-standard farmland integrated smart monitoring system.

[0042] Figure 6 This is a structural diagram of the growth model generation module in the high-standard farmland integrated smart monitoring system. Detailed Implementation

[0043] Currently, it is still necessary to manually assess the situation captured by the cameras before taking any action. Monitoring personnel monitor multiple cameras simultaneously and rely on their experience to make judgments. This may lead to unsafe behaviors being judged as safe behaviors due to the experience of the monitoring personnel, or the monitoring personnel failing to detect unsafe behaviors in a timely manner.

[0044] To make the technical problems to be solved, the technical solutions, and the beneficial effects of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention.

[0045] Example 1: Figure 1 The flowchart illustrates a method for integrated air-ground intelligent monitoring of high-standard farmland. In this embodiment of the invention, a method for integrated air-ground intelligent monitoring of high-standard farmland includes:

[0046] Step S100: Acquire farmland photos taken by satellite and drones, and build a 3D model of the farmland;

[0047] Satellites in the sky are used to take overall photos of farmland, clearly showing the length, width, and shape of each part of the farmland. Drones in the air can capture details of the farmland, such as the height and types of crops. Combining these images and data, a three-dimensional model of the farmland can be created, showing the types and heights of crops planted in each part of the farmland.

[0048] Step S200: Divide the farmland into different areas based on the three-dimensional model, and collect historical and real-time data for each area. The historical and real-time data include pest data, atmospheric environmental data, water quality data, and soil data at different locations and depths.

[0049] Farmland is divided into different zones based on the types of crops planted. Each zone grows the same type of crop and can be numbered 1, 2, 3, etc., or simply named after the crop type, such as a wheat zone, a corn zone, etc. Pests, atmospheric conditions (including temperature and humidity), water quality, and soil characteristics all affect crop growth. More pests mean more crops will be eaten or destroyed. A suitable atmospheric environment promotes healthy crop growth, while an unsuitable environment hinders growth. Different types of crops have different requirements for water quality and soil nutrients. Historical data shows the overall growth status of each crop under different pest conditions, atmospheric conditions, water quality, and soil characteristics. Real-time data includes actual pest data, atmospheric conditions, water quality data, and soil data at different locations and depths within a specific zone.

[0050] Step S300: Establish a growth model based on historical data.

[0051] By utilizing historical data, intelligent computers, and corresponding computer algorithms, growth models for specific crops can be established. Different types of crops have different growth models because their growth conditions vary, including temperature, soil pH, and nutrient requirements. Knowing the growth model of a particular crop allows us to determine, based on actual data, whether its growth status is poor, average, good, or excellent, enabling corresponding adjustments to increase its yield and quality.

[0052] Step S400: Substitute the real-time data into the growth model and execute corresponding countermeasures based on the results.

[0053] A growth model for a certain crop was established. By inputting real-time data into the model, the growth status of the crop can be determined. Each growth status of all types of crops corresponds to a specific adjustment measure. Based on the growth status of the crop, the corresponding strategy can be retrieved from the strategy library and then executed to make the crop grow towards higher yield and higher quality. When the growth status is excellent, the corresponding strategy is to not change the existing conditions, that is, to take no action.

[0054] Before building a growth model based on historical data, the process includes: removing unreasonable data from the historical data and cleaning the removed historical data. The purpose of removing unreasonable data and cleaning the data is to improve the quality of the data and ensure that subsequent data modeling can produce an accurate and realistic model.

[0055] Historical data may contain inconsistencies due to factors such as component malfunctions and on-site interference. This data indicates significant quality issues. Analyzing these inconsistencies can reveal loopholes and deficiencies in the data measurement and processing workflow, prompting the server to take measures to improve data quality. Furthermore, if inconsistencies are included in growth models, they will cause the models to be unrealistic, reducing accuracy. When real-time data is used in the growth model, the results will also be inaccurate. Therefore, it is necessary to identify and remove inconsistencies.

[0056] Data cleaning is an indispensable part of the entire data analysis process. It directly affects the effectiveness of the growth model, removing duplicate information, correcting errors, and ensuring data consistency. Because historical data is extracted from multiple different sensors, and due to variations in sensor usage and transmission conditions, errors are inevitable during measurement or transmission. For example, some data may be missing, some may be duplicated, and some may conflict. These missing, duplicate, or conflicting data are obviously undesirable. The server must "wash" this out according to certain rules—this is data cleaning. It typically targets incomplete data (missing essential information), erroneous data, and duplicate data. Removing these or completing incomplete data helps improve the accuracy of subsequent modeling, ensuring that the growth model accurately reflects the actual conditions of the farmland.

[0057] Figure 2 The first sub-process flowchart of the high-standard farmland integrated air-ground intelligent monitoring method includes the following steps: acquiring farmland photos taken by satellite and drones, and establishing a 3D model of the farmland.

[0058] Acquire photos of farmland taken by satellite and drones;

[0059] Satellites take overall photos of farmland from outer space, as well as high-resolution aerial photos, which can reveal information such as the outline and type of farmland. Drones take photos of farmland from various angles and distances in the sky, showing detailed information such as the color and height of crops at close range.

[0060] Different photos of farmland are rotated, projected, and stitched together to obtain a three-dimensional model of the farmland.

[0061] By rotating and projecting satellite and drone photos of farmland from the same location to the same angle, a 3D image containing all the details of the farmland at that location can be obtained. Stitching these 3D images together at consecutive points creates a complete 3D model of the farmland.

[0062] Figure 3 The third sub-process flowchart of the high-standard farmland integrated air-ground intelligent monitoring method includes the step of establishing a growth model based on historical data, which comprises:

[0063] Historical data is randomly divided into training set, test set and validation set, with the ratio of the number of data in the training set, test set and validation set being 7:2:1;

[0064] The training set is used to train the model, the test set is used to evaluate the model's final performance, and the validation set is used to tune the model's hyperparameters and evaluate its performance. Randomly splitting historical data is to evaluate the model's performance and tune its hyperparameters, ensuring that the model not only performs well on the training data but can also generalize to unseen data, making it easier to apply real-time data later and obtain accurate results.

[0065] The initial growth model is obtained based on the training set;

[0066] By substituting the training set data into a pre-defined artificial neural network, an initial growth model can be obtained. An artificial neural network is an algorithmic mathematical model that mimics the behavioral characteristics of animal neural networks, performing distributed parallel information processing. This type of network, depending on the complexity of the system, adjusts the relationships between a large number of internal nodes to achieve the purpose of information processing, and possesses self-learning and adaptive capabilities. Common types include backpropagation (BP) neural networks, learning vector quantization (LVQ) networks, and Hopfield neural networks; the pre-defined artificial neural network in this invention can be any of these.

[0067] Substitute the test set and validation set into the initial growth model, and determine the growth model based on the results.

[0068] The model obtained from the training set may not necessarily satisfy all historical data and needs further adjustment and validation. The validation set, which provides an independent dataset, is used to evaluate the model's performance under different hyperparameter settings, thus selecting the optimal hyperparameter combination. The test set is then used to test the generalization ability of the initial growth model. Only the initial growth model, adjusted through the validation set and tested through the test set, becomes the desired growth model.

[0069] Example 2: Figure 4 This is a structural block diagram of a high-standard farmland integrated air-ground intelligent monitoring system. In this embodiment of the invention, a high-standard farmland integrated air-ground intelligent monitoring system includes:

[0070] The 3D model generation module is used to acquire farmland photos taken by satellite and drones and build 3D models of the farmland.

[0071] The data acquisition module is used to divide farmland into different areas based on the 3D model and collect historical and real-time data for each area. The historical and real-time data include pest data, atmospheric environmental data, water quality data, and soil data at different locations and depths.

[0072] The growth model generation module is used to build growth models based on historical data.

[0073] The strategy generation module is used to input real-time data into the growth model and execute corresponding strategies based on the results.

[0074] The high-standard farmland integrated air-ground intelligent monitoring system also includes:

[0075] The data processing module is used to delete unreasonable data from historical data and clean the deleted historical data.

[0076] Figure 5 The diagram shows the structural composition of the 3D model generation module in the high-standard farmland integrated air-ground intelligent monitoring system. In this embodiment of the invention, the 3D model generation module includes:

[0077] The photo acquisition unit is used to acquire photos of farmland taken by satellite and drones;

[0078] The 3D model generation unit is used to rotate, project, and stitch different farmland photos to obtain a 3D model of the farmland.

[0079] Figure 6 The structural block diagram of the growth model generated in the high-standard farmland integrated sky-ground intelligent monitoring system is shown in this embodiment of the invention. The growth model generation module includes:

[0080] The partitioning unit is used to randomly divide historical data into training set, test set and validation set, with the ratio of the number of data in the training set, test set and validation set being 7:2:1;

[0081] The initial model generation unit is used to obtain the initial growth model based on the training set.

[0082] The growth model generation unit is used to substitute the test set and validation set into the initial growth model and determine the growth model based on the results.

[0083] The functions of the high-standard farmland integrated sky-ground intelligent monitoring method are all performed by computer equipment, which includes one or more processors and one or more memories. The one or more memories store at least one piece of program code, which is loaded and executed by the one or more processors to realize the functions of the big data-based user behavior prediction method.

[0084] The processor fetches instructions from memory one by one, analyzes the instructions, and then performs the corresponding operations according to the instructions, generating a series of control commands to enable the various parts of the computer to act automatically, continuously, and in a coordinated manner, forming an organic whole. This enables the input of programs and data, as well as the calculation and output of results. The arithmetic or logical operations generated in this process are all performed by the arithmetic unit. The memory includes a read-only memory (ROM), which is used to store computer programs. The memory is equipped with external protection devices.

[0085] For example, a computer program can be divided into one or more modules, one or more of which are stored in memory and executed by a processor to perform the present invention. The one or more modules can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in a terminal device.

[0086] Those skilled in the art will understand that the above description of the service equipment is merely an example and does not constitute a limitation on the terminal equipment. It may include more or fewer components than described above, or a combination of certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0087] The processor referred to can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. This processor is the control center of the terminal device, connecting various parts of the user terminal via various interfaces and lines.

[0088] The aforementioned memory can be used to store computer programs and / or modules. The aforementioned processor implements various functions of the aforementioned terminal device by running or executing the computer programs and / or modules stored in the memory, and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as information collection template display function, product information publishing function, etc.); the data storage area may store data created based on the use of the berth status display system (such as product information collection templates corresponding to different product types, product information that different product providers need to publish, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0089] If the modules / units integrated into the terminal device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the modules / units in the systems of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the functions of the various system embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0090] It should be noted that, in this document, the term "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0091] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A high-standard farmland integrated air-ground intelligent monitoring method, characterized in that, The method includes: Acquire photos of farmland taken by satellite and drones, and create a 3D model of the farmland; Based on the three-dimensional model, the farmland is divided into different areas, and historical and real-time data are collected in each area. The historical and real-time data include pest data, atmospheric environmental data, water quality data, and soil data at different locations and depths. Establish growth models based on historical data; Real-time data is fed into the growth model, and corresponding countermeasures are implemented based on the results.

2. The high-standard farmland integrated air-ground intelligent monitoring method according to claim 1, characterized in that, The steps of acquiring farmland photos taken by satellite and drones, and establishing a 3D model of the farmland include: Acquire photos of farmland taken by satellite and drones; Different photos of farmland are rotated, projected, and stitched together to obtain a three-dimensional model of the farmland.

3. The high-standard farmland integrated air-ground intelligent monitoring method according to claim 1 or 2, characterized in that, Before establishing the growth model based on historical data, the following also applies: Remove unreasonable data from historical data and perform data cleaning on the deleted historical data.

4. The high-standard farmland integrated air-ground intelligent monitoring method according to claim 1, characterized in that, The steps for establishing a growth model based on historical data include: Historical data is randomly divided into training set, test set and validation set, with the ratio of the number of data in the training set, test set and validation set being 7:2:1; The initial growth model is obtained based on the training set; Substitute the test set and validation set into the initial growth model, and determine the growth model based on the results.

5. A high-standard farmland integrated air-ground intelligent monitoring system, characterized in that, The system includes: The 3D model generation module is used to acquire farmland photos taken by satellite and drones and build 3D models of the farmland. The data acquisition module is used to divide farmland into different areas based on the 3D model and collect historical and real-time data for each area. The historical and real-time data include pest data, atmospheric environmental data, water quality data, and soil data at different locations and depths. The growth model generation module is used to build growth models based on historical data. The strategy generation module is used to input real-time data into the growth model and execute corresponding strategies based on the results.

6. The high-standard farmland integrated air-ground intelligent monitoring system according to claim 5, characterized in that, The 3D model generation module includes: The photo acquisition unit is used to acquire photos of farmland taken by satellite and drones; The 3D model generation unit is used to rotate, project, and stitch different farmland photos to obtain a 3D model of the farmland.

7. The high-standard farmland integrated air-ground intelligent monitoring system according to claim 5 or 6, characterized in that, The high-standard farmland integrated air-ground intelligent monitoring system also includes: The data processing module is used to delete unreasonable data from historical data and clean the deleted historical data.

8. The high-standard farmland integrated air-ground intelligent monitoring system according to claim 5, characterized in that, The growth model generation module includes: The partitioning unit is used to randomly divide historical data into training set, test set and validation set, with the ratio of the number of data in the training set, test set and validation set being 7:2:1; The initial model generation unit is used to obtain the initial growth model based on the training set. The growth model generation unit is used to substitute the test set and validation set into the initial growth model and determine the growth model based on the results.

Images