Farmland parcel intelligent segmentation and crop distribution big data analysis system and method

Abstract

The invention relates to the technical field of environmental data monitoring, and discloses a farmland plot intelligent segmentation and crop distribution big data analysis system and method, and the method comprises the steps: taking the boundary information of a to-be-operated plot as a farmland segmentation layer; generating a planting environment code of a plant species information query condition based on farmland segmentation layer associated plot planting information; collecting a peripheral planting area of the to-be-operated land parcel through a satellite, and analyzing to obtain a crop selection list; querying plant planting indication information corresponding to crop types in a crop selection list in a vegetation science big database through the planting environment codes, and evaluating and analyzing the plant planting indication information and initial planting indication information in the crop selection list to obtain target planting indication information; selecting and adjusting crop types of the to-be-operated land parcels based on the plant planting indication information; on the basis of segmentation and identification results, multi-source data are collected and integrated, correction and denoising processing are carried out, and the accuracy and credibility of analysis are improved.

Description

Technical Field

[0001] The present invention relates to the field of environmental data monitoring technology, and more specifically, to a system and method for intelligent segmentation of farmland plots and crop distribution big data analysis. Background Art

[0002] With the rapid development of remote sensing technology, computer vision and big data analysis technology, agricultural production management is moving towards intelligence and precision. Traditional agricultural management methods rely on manual experience and ground surveys, which are inefficient and have limited coverage, and cannot meet the needs of modern large-scale farmland management. Remote sensing technology obtains high-resolution images through satellites or drones, providing a rich source of data for farmland monitoring and management. At present, farmland plots are mainly analyzed through the following processing methods: (1) Methods based on traditional image processing: Traditional image processing methods rely on artificially designed features and rules to segment farmland plots through edge detection, threshold segmentation, and morphological processing. However, when faced with complex and changing farmland landscapes, artificially designed features and rules cannot cover all situations, resulting in low segmentation and recognition accuracy, and the results are often unsatisfactory.

[0003] (2) Machine learning-based methods: Machine learning methods segment farmland plots and identify crop types by training classifiers (such as support vector machines and random forests). Machine learning models have limited adaptability to complex environments, feature selection and extraction rely on experience, and have limited effects, making it difficult to effectively extract and utilize all information.

[0004] (3) Methods based on deep learning: The deep learning model training process requires a lot of computing resources and labeled data. The model is highly complex and difficult to deploy and apply. The demand for computing resources and data limits its widespread use in practical agricultural applications. The training and reasoning efficiency of the model is low, which limits its widespread application.

[0005] In view of this, the present invention proposes a system and method for intelligent segmentation of farmland plots and big data analysis of crop distribution. Summary of the invention In order to overcome the shortcomings of the prior art, the present invention provides a system and method for intelligent segmentation of farmland plots and crop distribution big data analysis, which has the advantage of more precise operation.

[0006] In a first aspect, the present invention provides a method for intelligent segmentation of farmland plots and crop distribution big data analysis, comprising the following steps: Based on the satellite remote sensing image, the edge information of the land to be operated is preliminarily identified, the edge information is locally segmented to determine the boundary information of the land to be operated, and the boundary information of the land to be operated is used as the farmland segmentation layer; Based on the farmland segmentation layer, the plot planting information is associated with the plot planting information, wherein the plot planting information includes the geographical location, climate conditions and soil information, and the planting environment code of the plant species information query condition is generated based on the plot planting information; Collect the peripheral planting area of ​​the plot to be operated through satellite, analyze the vegetation index of the peripheral planting area to obtain the crop types and distribution, and obtain a crop selection list based on the crop types and distribution; Through the planting environment coding, the plant planting instruction information corresponding to the crop types in the crop selection list is queried in the vegetation science big data database, the plant planting instruction information and the initial planting instruction information in the crop selection list are evaluated and analyzed to obtain the target planting instruction information, and the crop types of the to-be-operated plots are selected and adjusted based on the plant planting instruction information.

[0007] As a preferred technical solution of the first aspect of the present invention, the logic for obtaining the farmland segmentation layer is: Extracting satellite remote sensing images with timestamps, and marking areas in the satellite remote sensing images where brightness, color and / or texture mutations occur as edge information of the plot to be operated; For the edge information of the work plot, a local segmentation window is selected according to the preset pixel window, and preliminary marking is performed in the local segmentation window according to the similarity of pixel values, and the probability of the category of each marked pixel block is assigned; Based on the edge information of the plot to be operated, the adjacent surfaces between different pixel blocks are determined, and the virtual edges between the adjacent surfaces are assigned correlations. Then, the satellite remote sensing image is segmented with the image segmentation algorithm to obtain the segmentation line; The boundary information of the independently separated plots to be worked on is generated according to the dividing lines, and the boundary information of the plots to be worked on is superimposed and integrated into the geographic information system to produce the farmland segmentation layer.

[0008] As a preferred technical solution of the first aspect of the present invention, the plot planting information is combined by technical personnel with the plot planting information uploaded by the geographic information system, and the plot planting information is associated with the corresponding farmland segmentation layer in the form of annotations. The geographic location includes longitude information, latitude information and altitude information; the soil information includes soil type and soil moisture, and multiple plant species information is matched based on the plot planting information, and the plant species information includes periodically observed crop growth conditions.

[0009] As a preferred technical solution of the first aspect of the present invention, the matching logic of the plant species information is: Carry out plot analysis on plot planting information to obtain plot planting characteristics and historical crop types; Extract plant planting information with timestamps of historical crop types within a preset time period from the vegetation science database, the plant planting information including sowing and planting information, stage growth information, fertilization record information, disease control record information and plant production information; Preprocess the plant planting information, remove duplicate, erroneous or invalid data records, fill in missing data points, or use interpolation methods to estimate their approximate values; convert data from different sources and formats into a unified format and standard, sort the planting information by timestamp and construct a time series data set; Crop growth indicators are extracted based on time series data sets, and the periodic changes of crop growth indicators are analyzed. By comparing data from different years or different plots, a differential assessment report on crop growth conditions is obtained. Based on the differential assessment report on crop growth conditions, appropriate plant species information is selectively matched to the plots.

[0010] As a preferred technical solution of the first aspect of the present invention, the generation logic of the planting environment code is: The planting environment code includes plot number, location code, climate code and soil code; Based on the farmland segmentation layer, the farmland is divided into several independent plots with clear boundaries; each plot has a unique identifier in the layer marked as the plot number; Based on the on-site investigation of the technicians and uploading the planting information of the plot, a digital evaluation is performed based on the planting information of the plot to obtain a plot planting query condition; The planting environment code, plot planting information and generated planting environment query conditions are integrated together to form a planting environment code, and the planting environment code is stored in digital or character form.

[0011] As a preferred technical solution of the first aspect of the present invention, the logic for obtaining the crop selection list is: Combined with ground survey data, record the plot planting information, take the plot to be operated as the center, set the peripheral planting area in advance according to the preset range, and analyze the vegetation index in the peripheral planting area to obtain the crop type and distribution; Extracting vegetation index time series images of corresponding farmlands in the corresponding peripheral planting areas from the vegetation science database; training the vegetation index time series images through the first machine learning algorithm to obtain crop types and distribution conditions; The crop types and distribution conditions are arranged in a matrix according to the orientation of the plots to be operated, so as to obtain a crop selection list, the vegetation index in the crop selection list is marked as initial planting indication information, and the priority of selecting the crop types for the plots to be operated is set according to the size of the vegetation index.

[0012] As a preferred technical solution of the first aspect of the present invention, the logic for obtaining the target planting indication information is as follows: By using the planting environment code, the plant planting instruction information corresponding to the crop types in the crop selection list is searched in the vegetation science database, and the plant planting instruction information is associated with the initial planting instruction information in the crop selection list to obtain the first planting instruction information. Assigning a value to the first planting indication information according to the user's selection intention, and reordering the assigned first planting indication information to obtain second planting indication information; The second planting instruction information is combined with expert prior knowledge to perform data evaluation on the crop types in the crop selection list to obtain target planting instruction information, and the crop types for the plot to be operated are adaptively selected based on the target planting instruction information.

[0013] In a second aspect, the farmland plot intelligent segmentation and crop distribution big data analysis system of the present invention is based on the implementation of the farmland plot intelligent segmentation and crop distribution big data analysis method described in the first aspect, and includes a farmland plot determination module, a planting environment analysis module, a crop distribution collection module and a crop distribution adjustment module, and each module is connected by wire or wirelessly; The farmland plot determination module preliminarily identifies the edge information of the plot to be operated based on the satellite remote sensing image, performs local segmentation on the edge information to determine the boundary information of the plot to be operated, and uses the boundary information of the plot to be operated as the farmland segmentation layer; A planting environment analysis module, which associates the plot planting information based on the farmland segmentation layer, wherein the plot planting information includes the geographical location, climate conditions and soil information, and generates a planting environment code for a plant species information query condition based on the plot planting information; The crop distribution collection module collects the peripheral planting area of ​​the plot to be operated through satellites, analyzes the vegetation index of the peripheral planting area to obtain the crop types and distribution conditions, and obtains a crop selection list based on the crop types and distribution conditions; The crop distribution adjustment module queries the plant planting instruction information corresponding to the crop types in the crop selection list in the vegetation science database through the planting environment coding, evaluates and analyzes the plant planting instruction information and the initial planting instruction information in the crop selection list to obtain the target planting instruction information, and selects and adjusts the crop types of the plot to be operated based on the plant planting instruction information.

[0014] In a third aspect, the present invention provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the method for intelligent segmentation of farmland plots and big data analysis of crop distribution described in the first aspect by calling the computer program stored in the memory.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the method for intelligent segmentation of farmland plots and big data analysis of crop distribution as described in the first aspect.

[0016] Compared with the prior art, the present invention has the following beneficial effects: Through satellite remote sensing images and big data analysis technology, the present invention can efficiently and accurately identify and manage farmland plots, optimize crop planting structure, improve agricultural production efficiency and resource utilization efficiency, while supporting the development of precision agriculture and promoting environmental protection and sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the framework of the agricultural environment comprehensive monitoring support system of the present invention; Figure 2 It is a schematic diagram of the agricultural environment comprehensive monitoring support method of the present invention; Figure 3 The figure is a schematic diagram of the structure of an electronic device of the present invention. DETAILED DESCRIPTION

[0018] 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.

[0019] Example 1: Figure 1 As shown, the present invention provides a farmland plot intelligent segmentation and crop distribution big data analysis system, including a farmland plot determination module 100, a planting environment analysis module 200, a crop distribution collection module 300 and a crop distribution adjustment module 400, and each module is connected by wire or wirelessly; The farmland plot determination module 100 preliminarily identifies edge information of the plot to be operated based on the satellite remote sensing image, performs local segmentation on the edge information to determine the boundary information of the plot to be operated, and uses the boundary information of the plot to be operated as a farmland segmentation layer; Specifically, the logic for obtaining the farmland segmentation layer is as follows: Extract satellite remote sensing images with timestamps, and mark the areas with sudden changes in brightness, color and / or texture in the satellite remote sensing images as edge information of the plots to be worked on; satellite remote sensing images with timestamps are helpful in tracking and analyzing farmland conditions that change over time. Automatically identifying areas with sudden changes in brightness, color and / or texture is a preliminary processing process, and the sudden changes are preliminarily marked as boundaries between different plots or important features within the plots. Extracting edge information in the preliminary processing process is a relatively mature technology, which can facilitate the refined analysis of orderly farmland segmentation and provide clearer edge information.

[0020] For the edge information of the working plot, a local segmentation window is selected according to the preset pixel window, and preliminary marking is performed in the local segmentation window according to the similarity of pixel values, and the probability of the category to which each marked pixel block belongs is assigned; wherein, local segmentation of the edge information of the working plot according to the preset pixel window means that the system will select a small local segmentation window area in the image, and perform preliminary marking in the area according to the similarity of pixel values. In this process, each marked pixel block will be assigned a probability value, indicating the possibility that it belongs to a specific category (such as different crops or different types of soil). Rice is used as a crop type for explanation. Under ideal conditions, pixel block assignment is used to distinguish between rice, weeds and rice fields; however, in actual applications, the crop growth environment is complex, and there are many types of rice. If the rice variety is impure, different pixel blocks will have different assignments, which can distinguish different types of rice. Rice. During its growth, rice may cover the ridge area and affect the recognition of farmland edge information. However, there will be pixel differences between normal rice planting areas and ridge-covered areas. In this way, in the local segmentation window, through refined analysis, the differences in pixel blocks are assigned values, which can simplify the distinction steps. In order to achieve the purpose of assignment, technicians can operate according to prior knowledge, which has high requirements on the professional knowledge of operators. In order to achieve a more automated process, it can be identified by combining machine learning models (such as fuzzy algorithms) with the professional knowledge of technicians. The reason why machine learning models are not emphasized here is that there are relatively few data in the current farmland field, and there are large errors in relying solely on machine learning models. Combining the professional knowledge of technicians can serve the purpose of verification. As the data set expands, the assignment process can eventually be fully realized through machine learning models.

[0021] Based on the edge information of the plot to be operated, the adjacent faces between different pixel blocks are determined, and the virtual edges between the adjacent faces are assigned correlation values. Then, the satellite remote sensing image is segmented with the image segmentation algorithm to obtain segmentation lines; the virtual edges (i.e. segmentation boundaries) between the pixel blocks adjacent in space are assigned correlation values ​​by the system, which can help the system understand the connection and difference between different plots, and use the image segmentation algorithm to segment the satellite remote sensing image to obtain segmentation lines. These segmentation lines define the boundaries of different plots, so that each plot can be independently identified and analyzed.

[0022] The boundary information of the independent and separated plots to be operated is generated according to the segmentation line, and the boundary information of the plots to be operated is superimposed and integrated into the geographic information system to produce the farmland segmentation layer. The boundary information of the farmland plots can be automatically extracted from the satellite remote sensing image and the farmland segmentation layer can be generated. This layer provides important spatial data support for subsequent crop distribution analysis and planting decisions.

[0023] It should be noted that: through local segmentation, the module can extract the boundary information of the plots to be worked on, integrate the extracted boundary information into the geographic information system (GIS), and produce the farmland segmentation layer. It can clearly display the boundary, shape, area and other information of the plots to be worked on. Compared with traditional manual measurement and mapping methods, this module has higher efficiency and accuracy. It can quickly process a large amount of satellite remote sensing image data and automatically extract the boundary information of farmland plots. In addition, with the continuous development of advanced technologies such as deep learning, the recognition accuracy and robustness of this module are also constantly improving.

[0024] The planting environment analysis module 200 associates the plot planting information based on the farmland segmentation layer, wherein the plot planting information includes the geographical location, climate conditions and soil information, and generates the planting environment code of the plant species information query condition based on the plot planting information; Specifically, the plot planting information is combined by technical personnel with the plot planting information uploaded by the geographic information system, and the plot planting information is associated with the corresponding farmland segmentation layer in the form of annotations. The geographic location includes longitude information, latitude information and altitude information; soil information includes soil type and soil moisture, and multiple plant species information is matched based on the plot planting information, and the plant species information includes periodically observed crop growth conditions.

[0025] More specifically, the matching logic of the plant species information is: Carry out plot analysis on plot planting information to obtain plot planting characteristics and historical crop types; Extract plant planting information with timestamps of historical crop types within a preset time period from the vegetation science database, the plant planting information including sowing and planting information, stage growth information, fertilization record information, disease control record information and plant production information; Preprocess the plant planting information, remove duplicate, erroneous or invalid data records, fill in missing data points, or use interpolation methods to estimate their approximate values; convert data from different sources and formats into a unified format and standard, sort the planting information by timestamp and construct a time series data set; Crop growth indicators are extracted based on time series data sets, and the periodic changes of crop growth indicators are analyzed. By comparing data from different years or different plots, a differential assessment report on crop growth conditions is obtained. Based on the differential assessment report on crop growth conditions, appropriate plant species information is selectively matched to the plots.

[0026] It should be noted that by analyzing the plot planting information, extracting the plant planting information with timestamps, preprocessing the plant planting information, and obtaining the crop growth status of periodic observations, it is possible to accurately monitor and manage the crop growth status. This process provides scientific data support and decision-making basis for agricultural production, which helps to improve the efficiency and benefits of agricultural production.

[0027] Furthermore, the generation logic of the planting environment code is: The planting environment code includes plot number, location code, climate code and soil code; Based on the farmland segmentation layer, the farmland is divided into several independent plots with clear boundaries; each plot has a unique identifier in the layer marked as the plot number; Based on the on-site investigation of the technicians and uploading the planting information of the plot, a digital evaluation is performed based on the planting information of the plot to obtain a plot planting query condition; The planting environment code, plot planting information and generated planting environment query conditions are integrated together to form a planting environment code, and the planting environment code is stored in digital or character form.

[0028] The crop distribution collection module 300 collects the peripheral planting area of ​​the plot to be operated through satellites, analyzes the vegetation index of the peripheral planting area to obtain the crop types and distribution conditions, and obtains a crop selection list based on the crop types and distribution conditions; Specifically, the logic for obtaining the crop selection list is as follows: Combined with ground survey data, record the plot planting information, take the plot to be operated as the center, set the peripheral planting area in advance according to the preset range, and analyze the vegetation index in the peripheral planting area to obtain the crop type and distribution; Extracting vegetation index time series images of corresponding farmlands in the corresponding peripheral planting areas from the vegetation science database; training the vegetation index time series images through the first machine learning algorithm to obtain crop types and distribution conditions; It should be noted that the vegetation index time series image is the vegetation index time series image data of the farmland plot after normalization processing.

[0029] The crop types and distribution conditions are arranged in a matrix according to the orientation of the plots to be operated, so as to obtain a crop selection list, the vegetation index in the crop selection list is marked as initial planting indication information, and the priority of selecting the crop types for the plots to be operated is set according to the size of the vegetation index.

[0030] It should be noted that: Ground survey: Record the planting information of the plots through field investigations, use the planting information of the plots as measured data, and use it as a verification data set in the subsequent training and learning process of the first machine learning algorithm. Extract the vegetation index (such as NDVI data) time series images of the corresponding farmland in the corresponding peripheral planting area from the vegetation science big data database. The vegetation index of the peripheral planting area can be obtained by using remote sensing technology, such as satellites or drones. The obtained vegetation index data is analyzed to identify the types and distribution of different crops, and the extracted vegetation index time series images are normalized to eliminate the differences between data collected by different sensors and at different times.

[0031] Select appropriate machine learning algorithms (such as random forests, support vector machines, neural networks, etc.) to train vegetation index time series images to reflect the dynamic changes in crop growth, which helps to more accurately identify crop types and growth conditions. Through training, the model can identify and predict crop types and their distribution, mark and display vegetation indices, so as to quickly identify and select suitable crop types, provide a scientific basis for agricultural planting, optimize crop planting structure, and improve agricultural production efficiency and economic benefits.

[0032] The crop distribution adjustment module 400 queries the plant planting indication information corresponding to the crop types in the crop selection list in the vegetation science big data database through the planting environment coding, evaluates and analyzes the plant planting indication information and the initial planting indication information in the crop selection list to obtain the target planting indication information, and selects and adjusts the crop types of the to-be-operated land based on the plant planting indication information.

[0033] Specifically, the logic for obtaining the target planting instruction information is as follows: By using the planting environment code, the plant planting instruction information corresponding to the crop types in the crop selection list is searched in the vegetation science database, and the plant planting instruction information is associated with the initial planting instruction information in the crop selection list to obtain the first planting instruction information. It should be noted that by setting and configuring the planting environment code for the farmland plots, the plant planting instruction information corresponding to each crop type in the crop selection list can be retrieved more accurately in the scientific big data database.

[0034] Assigning a value to the first planting indication information according to the user's selection intention, and reordering the assigned first planting indication information to obtain second planting indication information; The second planting instruction information is combined with expert prior knowledge to perform data evaluation on the crop types in the crop selection list to obtain target planting instruction information, and the crop types for the plot to be operated are adaptively selected based on the target planting instruction information.

[0035] It should be noted that: by utilizing the plant planting indication information in the vegetation science big data database, combined with the specific planting environment coding, the crop types of the to-be-operated plots can be scientifically selected and adjusted to achieve the best planting effects and economic benefits. This not only improves the scientificity and accuracy of crop planting, but also helps to optimize the utilization of agricultural resources and protect the agricultural ecological environment.

[0036] Based on the results of crop distribution collection and planting environment coding, evaluate the rationality of the current crop distribution to compare the growth performance and yield potential of different crops in different environments, and propose optimization adjustments based on plant planting instructions, including adjusting crop planting structure, optimizing planting layout, improving agricultural management measures, etc. Implement the optimization and adjustment suggestions and continue to monitor crop growth and yield changes. This step requires the use of remote sensing monitoring technology and big data analysis technology to achieve real-time monitoring and precise management of crop growth.

[0037] Example 2: Please refer to Figure 2 As shown, the part not described in detail in this embodiment is described in Example 1. This embodiment provides an agricultural environment comprehensive monitoring support method based on multi-source data fusion, including the following steps: Based on the satellite remote sensing image, the edge information of the land to be operated is preliminarily identified, the edge information is locally segmented to determine the boundary information of the land to be operated, and the boundary information of the land to be operated is used as the farmland segmentation layer; The logic for obtaining the farmland segmentation layer is as follows: Extracting satellite remote sensing images with timestamps, and marking areas in the satellite remote sensing images where brightness, color and / or texture mutations occur as edge information of the plot to be operated; For the edge information of the work plot, a local segmentation window is selected according to the preset pixel window, and preliminary marking is performed in the local segmentation window according to the similarity of pixel values, and the probability of the category of each marked pixel block is assigned; Based on the edge information of the plot to be operated, the adjacent surfaces between different pixel blocks are determined, and the virtual edges between the adjacent surfaces are assigned correlations. Then, the satellite remote sensing image is segmented with the image segmentation algorithm to obtain the segmentation line; The boundary information of the independently separated plots to be worked on is generated according to the dividing lines, and the boundary information of the plots to be worked on is superimposed and integrated into the geographic information system to produce the farmland segmentation layer.

[0038] Based on the farmland segmentation layer, the plot planting information is associated with the plot planting information, wherein the plot planting information includes the geographical location, climate conditions and soil information, and the planting environment code of the plant species information query condition is generated based on the plot planting information; Furthermore, the plot planting information is combined by technical personnel with the plot planting information uploaded by the geographic information system, and the plot planting information is associated with the corresponding farmland segmentation layer in the form of annotations. The geographic location includes longitude information, latitude information and altitude information; the soil information includes soil type and soil moisture, and multiple plant species information is matched based on the plot planting information, and the plant species information includes periodically observed crop growth conditions.

[0039] Furthermore, the matching logic of the plant species information is: Carry out plot analysis on plot planting information to obtain plot planting characteristics and historical crop types; Extract plant planting information with timestamps of historical crop types within a preset time period from the vegetation science database, the plant planting information including sowing and planting information, stage growth information, fertilization record information, disease control record information and plant production information; Preprocess the plant planting information, remove duplicate, erroneous or invalid data records, fill in missing data points, or use interpolation methods to estimate their approximate values; convert data from different sources and formats into a unified format and standard, sort the planting information by timestamp and construct a time series data set; Crop growth indicators are extracted based on time series data sets, and the periodic changes of crop growth indicators are analyzed. By comparing data from different years or different plots, a differential assessment report on crop growth conditions is obtained. Based on the differential assessment report on crop growth conditions, appropriate plant species information is selectively matched to the plots.

[0040] Furthermore, the generation logic of the planting environment code is: The planting environment code includes plot number, location code, climate code and soil code; Based on the farmland segmentation layer, the farmland is divided into several independent plots with clear boundaries; each plot has a unique identifier in the layer marked as the plot number; Based on the on-site investigation of the technicians and uploading the planting information of the plot, a digital evaluation is performed based on the planting information of the plot to obtain a plot planting query condition; The planting environment code, plot planting information and generated planting environment query conditions are integrated together to form a planting environment code, and the planting environment code is stored in digital or character form.

[0041] Collect the peripheral planting area of ​​the plot to be operated through satellite, analyze the vegetation index of the peripheral planting area to obtain the crop types and distribution, and obtain a crop selection list based on the crop types and distribution; Furthermore, the logic for obtaining the crop selection list is as follows: Combined with ground survey data, record the plot planting information, take the plot to be operated as the center, set the peripheral planting area in advance according to the preset range, and analyze the vegetation index in the peripheral planting area to obtain the crop type and distribution; Extracting vegetation index time series images of corresponding farmlands in the corresponding peripheral planting areas from the vegetation science database; training the vegetation index time series images through the first machine learning algorithm to obtain crop types and distribution conditions; The crop types and distribution conditions are arranged in a matrix according to the orientation of the plots to be operated, so as to obtain a crop selection list, the vegetation index in the crop selection list is marked as initial planting indication information, and the priority of selecting the crop types for the plots to be operated is set according to the size of the vegetation index.

[0042] Through the planting environment coding, the plant planting instruction information corresponding to the crop types in the crop selection list is queried in the vegetation science big data database, the plant planting instruction information and the initial planting instruction information in the crop selection list are evaluated and analyzed to obtain the target planting instruction information, and the crop types of the to-be-operated plots are selected and adjusted based on the plant planting instruction information.

[0043] Furthermore, the logic for obtaining the target planting indication information is as follows: By using the planting environment code, the plant planting instruction information corresponding to the crop types in the crop selection list is searched in the vegetation science database, and the plant planting instruction information is associated with the initial planting instruction information in the crop selection list to obtain the first planting instruction information. Assigning a value to the first planting indication information according to the user's selection intention, and reordering the assigned first planting indication information to obtain second planting indication information; The second planting instruction information is combined with expert prior knowledge to perform data evaluation on the crop types in the crop selection list to obtain target planting instruction information, and the crop types for the plot to be operated are adaptively selected based on the target planting instruction information.

[0044] Example 3 An electronic device according to an exemplary embodiment includes: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the above-mentioned farmland plot intelligent segmentation and crop distribution big data analysis method by calling the computer program stored in the memory.

[0045] Figure 3 It is a structural diagram of an electronic device provided in an embodiment of the present application. The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement the farmland plot intelligent segmentation and crop distribution big data analysis method provided in the above-mentioned various method embodiments. The electronic device may also include other components for realizing the functions of the device. For example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface for input and output. The embodiments of the present application are not described in detail here.

[0046] Example 4 According to an exemplary embodiment, a computer-readable storage medium is shown, on which a rewritable computer program is stored; When the computer program runs on a computer device, the computer device executes the above-mentioned farmland plot intelligent segmentation and crop distribution big data analysis method.

[0047] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including at least one computer program, and the at least one computer program is executable by a processor to complete the farmland plot intelligent segmentation and crop distribution big data analysis method in the above embodiment. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0048] In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or the computer program comprising one or more program codes, the one or more program codes being stored in a computer-readable storage medium. One or more processors of an electronic device can read the one or more program codes from the computer-readable storage medium, and the one or more processors execute the one or more program codes, so that the electronic device can perform the above-mentioned farmland plot intelligent segmentation and crop distribution big data analysis method.

[0049] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0050] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0051] A person of ordinary skill in the art will understand that all or part of the steps to implement the above embodiments can be completed by hardware, or can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. The above-mentioned storage medium can be a read-only memory, a disk or an optical disk, etc.

[0052] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0053] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0054] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0055] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0056] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for intelligent segmentation of farmland plots and analysis of crop distribution big data, characterized in that: The steps include: Based on the satellite remote sensing image, the edge information of the land to be operated is preliminarily identified, the edge information is locally segmented to determine the boundary information of the land to be operated, and the boundary information of the land to be operated is used as the farmland segmentation layer; Based on the farmland segmentation layer, the plot planting information is associated with the plot planting information, wherein the plot planting information includes the geographical location, climate conditions and soil information, and the planting environment code of the plant species information query condition is generated based on the plot planting information; Collect the peripheral planting area of ​​the plot to be operated through satellite, analyze the vegetation index of the peripheral planting area to obtain the crop types and distribution, and obtain a crop selection list based on the crop types and distribution; Through the planting environment coding, the plant planting instruction information corresponding to the crop types in the crop selection list is queried in the vegetation science big data database, the plant planting instruction information and the initial planting instruction information in the crop selection list are evaluated and analyzed to obtain the target planting instruction information, and the crop types of the to-be-operated plots are selected and adjusted based on the plant planting instruction information.

2. The method for intelligent segmentation of farmland plots and analysis of crop distribution big data according to claim 1, characterized in that: The logic for obtaining the farmland segmentation layer is as follows: Extracting satellite remote sensing images with timestamps, and marking areas in the satellite remote sensing images where brightness, color and / or texture mutations occur as edge information of the plot to be operated; For the edge information of the work plot, a local segmentation window is selected according to the preset pixel window, and preliminary marking is performed in the local segmentation window according to the similarity of pixel values, and the probability of the category of each marked pixel block is assigned; Based on the edge information of the plot to be operated, the adjacent surfaces between different pixel blocks are determined, and the virtual edges between the adjacent surfaces are assigned correlations. Then, the satellite remote sensing image is segmented with the image segmentation algorithm to obtain the segmentation line; The boundary information of the independently separated plots to be worked on is generated according to the dividing lines, and the boundary information of the plots to be worked on is superimposed and integrated into the geographic information system to produce the farmland segmentation layer.

3. The method for intelligent segmentation of farmland plots and analysis of crop distribution big data according to claim 2, characterized in that: The plot planting information is combined by technical personnel with the plot planting information uploaded by the geographic information system, and the plot planting information is associated with the corresponding farmland segmentation layer in the form of annotations. The geographic location includes longitude information, latitude information and altitude information; soil information includes soil type and soil moisture, and multiple plant species information is matched based on the plot planting information, and the plant species information includes periodically observed crop growth conditions.

4. The method for intelligent segmentation of farmland plots and analysis of crop distribution big data according to claim 3, characterized in that: The matching logic of the plant species information: Conduct plot analysis on plot planting information to obtain plot planting characteristics and historical crop types; Extract plant planting information with timestamps of historical crop types within a preset time period from the vegetation science database, the plant planting information including sowing and planting information, stage growth information, fertilization record information, disease control record information and plant production information; Preprocess the plant planting information, remove duplicate, erroneous or invalid data records, fill in missing data points, or use interpolation methods to estimate their approximate values; convert data from different sources and formats into a unified format and standard, sort the planting information by timestamp and construct a time series data set; Crop growth indicators are extracted based on time series data sets, and the periodic changes of crop growth indicators are analyzed. By comparing data from different years or different plots, a differential assessment report on crop growth conditions is obtained. Based on the differential assessment report on crop growth conditions, appropriate plant species information is selectively matched to the plots.

5. The method for intelligent segmentation of farmland plots and analysis of crop distribution big data according to claim 4, characterized in that: The generation logic of the planting environment code: The planting environment code includes plot number, location code, climate code and soil code; Based on the farmland segmentation layer, the farmland is divided into several independent plots with clear boundaries; each plot has a unique identifier in the layer marked as the plot number; Based on the on-site investigation of the technicians and uploading the planting information of the plot, a digital evaluation is performed based on the planting information of the plot to obtain a plot planting query condition; The planting environment code, plot planting information and generated planting environment query conditions are integrated together to form a planting environment code, and the planting environment code is stored in digital or character form.

6. The method for intelligent segmentation of farmland plots and analysis of crop distribution big data according to claim 5, characterized in that: The logic for obtaining the crop selection list is as follows: Combined with ground survey data, record the plot planting information, take the plot to be operated as the center, set the peripheral planting area in advance according to the preset range, and analyze the vegetation index in the peripheral planting area to obtain the crop type and distribution; Extracting vegetation index time series images of corresponding farmlands in the corresponding peripheral planting areas from the vegetation science database; training the vegetation index time series images through the first machine learning algorithm to obtain crop types and distribution conditions; The crop types and distribution conditions are arranged in a matrix according to the orientation of the plots to be operated, so as to obtain a crop selection list, the vegetation index in the crop selection list is marked as initial planting indication information, and the priority of selecting the crop types for the plots to be operated is set according to the size of the vegetation index.

7. The method for intelligent segmentation of farmland plots and analysis of crop distribution big data according to claim 6, characterized in that: The logic for obtaining the target planting instruction information: By using the planting environment code, the plant planting instruction information corresponding to the crop types in the crop selection list is searched in the vegetation science database, and the plant planting instruction information is associated with the initial planting instruction information in the crop selection list to obtain the first planting instruction information. Assigning a value to the first planting indication information according to the user's selection intention, and reordering the assigned first planting indication information to obtain second planting indication information; The second planting instruction information is combined with expert prior knowledge to perform data evaluation on the crop types in the crop selection list to obtain target planting instruction information, and the crop types for the plot to be operated are adaptively selected based on the target planting instruction information.

8. A system for intelligent segmentation of farmland plots and analysis of crop distribution big data, based on the implementation of the method for intelligent segmentation of farmland plots and analysis of crop distribution big data according to any one of claims 1 to 7, characterized in that: It comprises a farmland plot determination module (100), a planting environment analysis module (200), a crop distribution collection module (300) and a crop distribution adjustment module (400), wherein the modules are connected to each other via wired or wireless connections; A farmland plot determination module (100) preliminarily identifies edge information of a plot to be operated based on satellite remote sensing images, performs local segmentation on the edge information to determine boundary information of the plot to be operated, and uses the boundary information of the plot to be operated as a farmland segmentation layer; A planting environment analysis module (200) is configured to associate plot planting information based on the farmland segmentation layer, wherein the plot planting information includes geographical location, climate conditions and soil information, and to generate a planting environment code for a plant species information query condition based on the plot planting information; The crop distribution collection module (300) collects the peripheral planting area of ​​the plot to be operated through satellites, analyzes the vegetation index of the peripheral planting area to obtain the crop types and distribution conditions, and obtains a crop selection list based on the crop types and distribution conditions; The crop distribution adjustment module (400) searches the vegetation science database for plant planting instruction information corresponding to the crop types in the crop selection list through the planting environment code, evaluates and analyzes the plant planting instruction information and the initial planting instruction information in the crop selection list to obtain target planting instruction information, and selects and adjusts the crop types of the plot to be operated based on the plant planting instruction information.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the method for intelligent segmentation of farmland plots and crop distribution big data analysis as described in any one of claims 1 to 7 by calling the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes the method for intelligent segmentation of farmland plots and crop distribution big data analysis as described in any one of claims 1 to 7.

Images