Internet of Things system for space-air-ground integrated agricultural information processing

Abstract

The invention relates to the technical field of agricultural information processing, in particular to an internet of things system for space-air-ground integrated agricultural information processing. The internet of things system comprises a sensing system, an internet of things system, a data processing platform, a decision making system and a reality system. According to the invention, environment and crop information is acquired from multiple aspects of the sky and the ground through the Internet of Things system, and the acquired environment and crop information is processed by using the data platform, so that a corresponding management decision is generated based on a corresponding processing result, and scientific management is carried out on crops, so that manual inspection is avoided, and intelligent management is realized; in addition, the acquired environment and crop information, the processing result and the management decision can be displayed in real time, so that a worker can make a more reasonable management decision according to the display.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural information processing, and more specifically, to an Internet of Things system for integrated air-space-ground-integrated agricultural information processing. Background Art

[0002] Agriculture is not only the foundation of people's production and life, but also occupies an important position in the national social and economic development.

[0003] Traditional crop management methods are easily affected by the environment, and in terms of crop management, manual inspections are generally required to achieve crop management, which is not only troublesome but also greatly limits the yield and quality of crops. In order to continue to accelerate agricultural development, the use of scientific and technological means to transform traditional agriculture into information-based smart agriculture and realize scientific and intelligent management of crops is one of the problems that need to be solved urgently at this stage. Summary of the Invention

[0004] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides an Internet of Things system for integrated air-space-ground agricultural information processing, which helps to achieve intelligent and scientific management of crops.

[0005] In a first aspect, the present invention provides an Internet of Things system for integrated air-space-ground agricultural information processing, comprising: Perception system, used to obtain environmental and crop information from multiple angles, including the sky and the ground; Internet of Things system, which is used to obtain the environment and crop information perceived by the perception system and upload it to the data processing platform; A data processing platform for storing and analyzing environmental and crop information uploaded through the IoT system and generating analysis results; A decision-making system, which uses machine learning algorithms to establish a farmland management decision model based on the analysis results generated by the data processing platform to generate corresponding management decisions for the farmland; The display system is used to display the agricultural production-related environmental and crop information obtained by the perception system, the analysis results generated by the data processing platform, and the management decisions generated by the decision-making system.

[0006] Furthermore, the perception system includes: Space monitoring system, used to obtain aerial imaging data of crops through satellite remote sensing; Aerial monitoring system, used to obtain aerial image data of crops through drones; Ground monitoring system for collecting various environmental parameters of farmland; Meteorological monitoring system, used to obtain local meteorological data in real time.

[0007] Furthermore, the data platform includes: Aerospace data processing system, used to process aerospace image data; An aerial data processing system is used to process aerial image data to obtain processed aerial images; A ground data processing system is used to process various environmental parameters of farmland collected by the ground monitoring system to remove abnormal values; A meteorological data processing system is used to obtain real-time meteorological data for each area within the monitoring range using a Kriging interpolation method based on the acquired real-time meteorological data and the monitoring range; The crop positioning and identification system is used to locate and identify crop types and pest and disease conditions in various areas based on aerospace and aerial images.

[0008] Furthermore, the crop positioning and identification system includes: Image integration module, used to integrate aerospace images and aerial images; The positioning and recognition module is used to extract features from the integrated aerospace images and aerial images to extract the characteristics of ground crops, thereby determining the crop types and pest and disease conditions in each area.

[0009] Furthermore, the crop positioning and identification system includes: Convolutional neural network feature extraction module: It is used to extract features from the integrated aerospace and aerial images to obtain feature maps; A feature mapping module is used to map the obtained feature map into a fixed-size feature map block through maximum pooling or average pooling operation, and to map the original feature map into a fixed-size region of interest feature map block; The region proposal network is used to generate and output the region of interest based on the obtained feature patches; Region of Interest Pooling Module: corresponds each output ROI to the original feature map and splices the feature map blocks of the region of interest; The target detection network is used to locate and determine the crop type and pest and disease conditions in each area based on the received stitched feature blocks of the region of interest.

[0010] Furthermore, the processing of the aerial image data includes the following steps: Perform reflectivity calibration on aerial image data to ensure the accuracy and consistency of aerospace image data; Align the rectified aerial image data to ensure they are in the same coordinates; Generate a 3D point cloud model using aligned aerospace image data; Generate a digital elevation model based on the generated 3D point cloud model to display the elevation information of the surface; Construct orthomosaic images based on the generated digital elevation model to eliminate the distortion of aerial images caused by terrain; Perform raster transformation on the orthomosaic image to obtain the aerial image.

[0011] The beneficial effects of the present invention are: (1) The present invention uses an Internet of Things system to acquire environmental and crop information from multiple locations, including the sky and the ground. The data platform processes the acquired environmental and crop information, generating management decisions based on the processing results. This allows for scientific management of crops, thereby eliminating manual inspections and achieving intelligent management. Furthermore, the acquired environmental and crop information, processing results, and management decisions can be displayed in real time, enabling staff to make more reasonable management decisions based on the display.

[0012] (2) The present invention uses a positioning and recognition module including an RPN network and a region of interest pooling module to integrate remotely sensed aerial and aerospace images, extract features, and identify the crop types and pest and disease conditions in each area, which helps to improve the detection speed and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0014] Figure 1 A block diagram of the principles of an Internet of Things system for integrated air-space-ground agricultural information processing provided by an embodiment of the present invention; Figure 2 This is a flowchart of aerial image data processing according to one embodiment of the present invention; Figure 3 FIG. 1 is a structural diagram of a positioning and identification module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0015] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0016] It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the present invention. Unless otherwise specified, each technical and scientific term used in this embodiment has the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0017] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0018] In the present invention, terms such as "upper", "lower", "left", "right", "front", "back", "vertical", "horizontal", "side", "bottom", etc. indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. They are relational words determined only for the convenience of describing the structural relationships of the various parts or elements of the present invention, and do not specifically refer to any part or element in the present invention, and should not be understood as limiting the present invention.

[0019] In the present invention, terms such as "fixed connection," "connected," and "connection" should be interpreted broadly to mean a fixed connection, an integral connection, or a detachable connection; a direct connection or an indirect connection through an intermediary. Relevant researchers or technicians in this field may determine the specific meanings of these terms in the present invention based on specific circumstances, and they should not be construed as limitations of the present invention.

[0020] Example 1: like Figure 1 As shown, this embodiment provides an Internet of Things system for integrated air-space-ground agricultural information processing, including: (1) Perception system, used to obtain environmental and crop information related to agricultural production.

[0021] The environmental and crop data include: aerospace image data, aerial image data, meteorological data and growth environment data The perception system includes: aerospace monitoring system, aviation monitoring system and ground detection system; The aerospace monitoring system is used to obtain aerospace image data of crops through satellite remote sensing to understand the basic situation of crop production.

[0022] Aerial monitoring systems are used to obtain aerial image data of crops using drones. Specifically, drones can be equipped with visual sensors such as visible light, multispectral, and infrared to obtain aerial image data.

[0023] The ground monitoring system is used to collect various environmental parameters of farmland, including soil moisture and temperature, air temperature and humidity, soil conductivity, wind direction, and growth images.

[0024] Among them, the ground monitoring system includes multiple sensor nodes, and multiple sensor nodes are deployed in various key locations in the farmland.

[0025] The meteorological monitoring system is used to obtain local meteorological data in real time, including rainfall and temperature.

[0026] (2) Internet of Things system: The Internet of Things system is used to upload the environment and crop information perceived by the perception system to the data processing platform.

[0027] The IoT system can adopt 4G / 5G cellular network or NB-IoT narrowband IoT networking solution.

[0028] (3) Data processing platform: used to store and analyze environmental and crop information uploaded through the Internet of Things system and generate analysis results.

[0029] The data processing platform includes aviation data processing system, aerospace data processing system, ground data processing system, meteorological data processing system and display system.

[0030] A: Aerospace data processing system, used to process aerospace image data.

[0031] The processing of aerospace image data comprises the following steps: A-1: Radiometric calibration of aerospace image data is performed to convert the pixel values ​​of the aerospace image data into the physical quantity of the corresponding pixel's radiometry or reflectivity, thereby achieving quantification of the aerospace image data; A-2: Perform atmospheric correction on the radiometrically calibrated aerospace image data to eliminate radiometric errors caused by atmospheric influences.

[0032] A-3: Perform image mosaicking on the atmospherically corrected aerospace image data. Specifically, multiple pre-processed aerospace image data are mathematically stitched together to form a single image. Image mosaicking ensures that the geometric positions of the aerospace image data are strictly aligned and the grayscale and color are evenly balanced. A-4: Perform edge cropping on the mosaicked aerospace image data to obtain cropped aerospace image data.

[0033] B: Aerial data processing system, used to process aerial image data to obtain processed aerial images; like Figure 2 As shown, the processing of aerial image data includes the following steps: B-1: Perform reflectivity calibration on aerial image data to ensure the accuracy and consistency of aerial image data; B-2: Align the rectified aerospace image data to ensure they are in the same coordinates; B-3: Generate a 3D point cloud model using aligned aerospace image data; B-4: Generate a digital elevation model (DEM) based on the generated 3D point cloud model to display the elevation information of the surface; B-5: Construct an orthomosaic image based on the generated digital elevation model to eliminate the distortion of aerial images caused by terrain; B-6: Perform raster transformation on the orthomosaic image to obtain an aerial image, wherein the aerial image is, for example, a GeoTIFF image.

[0034] C: Meteorological data processing system, used to obtain real-time meteorological data for each area of ​​the monitoring range using the Kriging interpolation method based on the acquired real-time meteorological data and the monitoring range, where the monitoring range is known in advance.

[0035] D: Ground data processing system, used to process various environmental parameters of farmland collected by the ground monitoring system to remove outliers.

[0036] E: Crop positioning and identification system, used to locate and identify crop types and pest and disease conditions in various areas based on aerospace and aerial images.

[0037] The crop positioning and identification system includes: an image integration module and a crop type and pest identification module; The image integration module is used to integrate aerospace images and aerial images.

[0038] The positioning and recognition module is used to extract features from the integrated aerospace images and aerial images to extract the characteristics of ground crops, thereby determining the crop types and pest and disease conditions in each area.

[0039] Among them, Figure 3 As shown in the figure, the positioning and recognition module includes: a convolutional neural network feature extraction module, a region proposal network (RPN), a region of interest pooling (ROIPooling) module and a target detection network.

[0040] The convolutional neural network feature extraction module is used to extract features from the integrated input aerospace images and aerial images to obtain a feature map; wherein the convolutional neural network feature extraction module includes a convolution layer, a pooling layer, an activation function and a fully connected layer.

[0041] The feature map module is used to map the obtained feature map into a fixed-size feature map block through maximum pooling or average pooling operations.

[0042] RPN network is used to quickly generate and output the region of interest (ROI) based on the obtained feature patches; The specific steps include: (1) Slide a fixed-size window (usually a 3×3 window) on a fixed-size feature map and predict several regions of interest (ROIs) at each window position.

[0043] Specifically, at each window position, RPN generates a ROI, each ROI consists of an anchor box and an offset; based on the offset, ROIs of different scales and aspect ratios can be generated by scaling and offsetting the anchor box.

[0044] (2) Perform binary classification (whether it contains an object) and regression (adjust the position of the region of interest) on each ROI to determine the ROI containing the target and output it.

[0045] The ROI pooling module maps each output ROI to the original feature map and sends it to the feature mapping module for maximum pooling or average pooling to map it into fixed-size ROI feature map tiles. These ROI feature map tiles are then concatenated as the output of the ROI pooling module and sent to the object detection network.

[0046] The target detection network is used to locate and determine the crop type and pest and disease conditions in each area based on the received stitched feature blocks of the region of interest.

[0047] It should be noted that the target detection network is also used to determine the normalized vegetation index (NDVI) of each area.

[0048] This neural network-based feature extraction model introduces the RPN network, which can quickly generate regions of interest, avoids the sliding window detection method of all image pixels, and greatly improves the detection speed; it has higher accuracy, and the RPN can generate more accurate regions of interest. The ROIPooling module can accurately extract the feature information in each region of interest, further improving the detection accuracy.

[0049] D: Farmland drought prediction system is used to calculate the drought index based on the collected multiple environmental parameters of the farmland, the real-time meteorological data of each area in the monitoring range, and the calculation formula is as follows:

[0050] in, 、 and 、 , are the fitting coefficients of the “dry side” and “wet side” equations respectively; is soil temperature; NDVI is the Normalized Difference Vegetation Index.

[0051] (4) A decision-making system, which is used to establish a farmland management decision-making model based on the analysis results generated by the data processing platform using a machine learning algorithm to generate corresponding management decisions for the farmland.

[0052] Among them, the decision-making models include: fertilization and irrigation decision-making model and pesticide spraying model, etc. The fertilization and irrigation model is used to scientifically and rationally determine the fertilization time nodes, fertilizer types, and application dosages based on the crop types and predicted drought conditions in each region, to avoid resource waste and yield loss due to excessive or insufficient fertilization.

[0053] The pesticide spraying model is used to develop scientific pest and disease control plans based on the crop pest and disease conditions in each region. It can not only ensure the prevention and control effect, but also minimize the use of chemical pesticides, which is beneficial to the quality safety of agricultural products and the protection of the ecological environment.

[0054] The soil moisture measurement and control model is used to collect statistics on various environmental parameters of pre-treated farmland and generate real-time alarms based on the statistical data. It also regularly sends meteorological data to the monitoring platform or the manager's app through the Internet of Things system to guide production.

[0055] (5) A display system used to display the environmental and crop information related to agricultural production obtained by the perception system, the analysis results generated by the data processing platform, and the management decisions generated by the decision-making system.

[0056] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the terminal embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiment.

[0057] In the several embodiments provided by the present invention, it should be understood that the disclosed system and method can It can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of units is merely a logical functional division. In actual implementation, other divisions may be used. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not implemented. In addition, the coupling or direct coupling or communication connection shown or discussed between each other may be through some interface, or the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.

[0058] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0059] In addition, it should be noted that the flowcharts in the accompanying drawings show the methods of the embodiments of the present disclosure. In the descriptions corresponding to the flowcharts or block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in an order different from that disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be performed substantially in parallel, or sometimes in the opposite order, which may depend on the functions involved. Each block in the block diagram and / or flow chart, and the combination of blocks in the block diagram and / or flow chart, can be implemented using a dedicated hardware-based system that performs the specified functions or actions, or can be implemented using a combination of dedicated hardware and computer instructions.

[0060] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. An Internet of Things system for integrated air-space-ground agricultural information processing, characterized in that: include: Perception system, used to obtain environmental and crop information related to agricultural production; Internet of Things system, which is used to obtain the environment and crop information perceived by the perception system and upload it to the data processing platform; A data processing platform for storing and analyzing environmental and crop information uploaded through the IoT system and generating analysis results; A decision-making system, which uses machine learning algorithms to establish a farmland management decision model based on the analysis results generated by the data processing platform to generate corresponding management decisions for the farmland; The display system is used to display the agricultural production-related environmental and crop information obtained by the perception system, the analysis results generated by the data processing platform, and the management decisions generated by the decision-making system.

2. The Internet of Things system for integrated air-space-ground agricultural information processing according to claim 1 is characterized in that: The perception system includes: Space monitoring system, used to obtain aerial imaging data of crops through satellite remote sensing; Aerial monitoring system, used to obtain aerial image data of crops through drones; Ground monitoring system for collecting various environmental parameters of farmland; Meteorological monitoring system, used to obtain local meteorological data in real time.

3. The Internet of Things system for integrated air-ground-space agricultural information processing according to claim 2 is characterized in that: The data platform includes: Aerospace data processing system, used to process aerospace image data; An aerial data processing system is used to process aerial image data to obtain processed aerial images; A ground data processing system is used to process various environmental parameters of farmland collected by the ground monitoring system to remove abnormal values; A meteorological data processing system is used to obtain real-time meteorological data for each area within the monitoring range using a Kriging interpolation method based on the acquired real-time meteorological data and the monitoring range; The crop positioning and identification system is used to locate and identify crop types and pest and disease conditions in various areas based on aerospace and aerial images.

4. The Internet of Things system for integrated air-ground-space agricultural information processing according to claim 3 is characterized in that: The crop positioning and identification system includes: Image integration module, used to integrate aerospace images and aerial images; The positioning and recognition module is used to extract features from the integrated aerospace images and aerial images to extract the characteristics of ground crops, thereby determining the crop types and pest and disease conditions in each area.

5. The Internet of Things system for integrated air-space-ground agricultural information processing according to claim 4 is characterized in that: The crop positioning and identification system includes: Convolutional neural network feature extraction module: used to extract features from the integrated aerospace and aerial images to obtain feature maps; A feature mapping module is used to map the obtained feature map into a fixed-size feature map block through maximum pooling or average pooling operation, and to map the original feature map into a fixed-size feature map block of the region of interest; The region proposal network is used to generate and output the region of interest based on the obtained feature patches; Region of Interest Pooling Module: corresponds each output ROI to the original feature map and splices the feature map blocks of the region of interest; The target detection network is used to locate and determine the crop type and pest and disease conditions in each area based on the received stitched feature blocks of the region of interest.

6. The Internet of Things system for integrated air-space-ground agricultural information processing according to claim 3 is characterized in that: The processing of the aerial image data includes the following steps: Perform reflectivity calibration on aerial image data to ensure the accuracy and consistency of aerospace image data; Align the rectified aerial image data to ensure they are in the same coordinates; Generate a 3D point cloud model using aligned aerospace image data; Generate a digital elevation model based on the generated 3D point cloud model to display the elevation information of the surface; Construct orthomosaic images based on the generated digital elevation model to eliminate the distortion of aerial images caused by terrain; Perform raster transformation on the orthomosaic image to obtain the aerial image.

Images