Soybean identification index image data acquisition method, soybean spatial distribution drawing model training method, soybean spatial distribution drawing model using method and related products

Abstract

The invention discloses a soybean identification index image data acquisition method, a soybean spatial distribution charting model training method, a soybean spatial distribution charting model using method and a related product, and relates to the technical field of crop identification, the image data acquisition method comprises the following steps: acquiring soybean identification index image data by using a soybean identification index model; wherein blue, red, red edge 2, near-red and short-wave infrared 1 wave bands of a satellite are used in the soybean identification index model. The soybean identification index model is used for soybean spatial distribution mapping. According to the soybean identification index model, the characteristics of visible light, near infrared, red edge and short wave infrared are comprehensively used, the novel soybean identification index model is provided, the index model can improve the separability of soybeans and other crops in the same period, a new identification characteristic is provided for soybean remote sensing mapping, and improvement of the soybean distribution mapping precision is facilitated.

Description

Technical Field

[0001] The present application relates to the field of crop identification technology, and in particular to a method for acquiring soybean identification index image data, training a soybean spatial distribution mapping model, and using the method and related products. Background Art

[0002] Accurate spatial distribution of crops is crucial for monitoring and assessing farmland conditions, precision agriculture management, agricultural disaster response, and agricultural policy formulation. Traditional agricultural surveys for crop classification and mapping are often time-consuming and labor-intensive. However, remote sensing technology, with its ability to rapidly acquire data at a macroscopic scale, has become a crucial tool for crop mapping, significantly saving manpower, material resources, financial resources, and time, effectively addressing the shortcomings of traditional survey methods. In recent years, the application of high-resolution (temporal and spatial) remote sensing data for crop identification has become increasingly widespread.

[0003] Spectral characteristics vary depending on crop type, providing key information for precise crop classification. Therefore, they are the most fundamental characteristics for identifying crop types and play a vital role in crop identification. Vegetation indices, derived through mathematical calculations of multiple bands in remote sensing imagery, can enhance vegetation spectral characteristics and are often used for crop type identification and distribution mapping. Some researchers are also focused on developing spectral indices tailored to identify specific crop types. This approach reduces the amount of remote sensing data input and simplifies the calculation process, while enhancing the specific spectral characteristics of that crop.

[0004] Accurately identifying soybean planting areas is crucial for ensuring food security. Dynamic classification mapping and monitoring of soybean spatial distribution provide a crucial basis for agricultural decision-making. Farmers and policymakers can use this data to adjust planting plans, optimize soybean planting layouts and resource allocation, and ultimately achieve optimal soybean production benefits. To this end, many researchers are focusing on developing soybean remote sensing identification indices.

[0005] However, soybeans and corn are planted almost simultaneously in many regions, and their phenological stages are highly similar, making them easily confused. Therefore, there is an urgent need for a technical solution that can effectively improve the separability of soybeans and other crops grown at the same time. Summary of the Invention

[0006] The purpose of this application is to provide a method for acquiring soybean identification index image data, training and using a soybean spatial distribution mapping model, and related products. The soybean identification index image data can effectively improve the separability of soybeans and other crops of the same period.

[0007] To achieve the above objectives, this application provides the following solutions: In a first aspect, the present application provides a method for acquiring soybean identification index image data, comprising: The soybean identification index image data is obtained using the soybean identification index model; the soybean identification index model is: ; ; in, NSII represents the calculated soybean identification index image data; EVI represents the enhanced vegetation index; Blue 、Re d 、 RE2 、 NIR and SWIR 1 are the satellite's blue, red, red-edge 2, near-red, and short-wave infrared 1 bands; G =2.5; C 1 =6; C 2 =7.5; L =1; the soybean identification index model is used for soybean spatial distribution mapping.

[0008] Optionally, Blue 、Re d 、 RE2 、 NIR and SWIR The specific bands of 1 are: B2, B4, B6, B8 and B11.

[0009] In a second aspect, the present application provides a training method for a soybean spatial distribution mapping model, comprising: Acquire training data; the training data includes: satellite multispectral imagery and sample data; the sample data is sample data that has been differentiated into soybean and non-soybean; the sample data is soybean and non-soybean samples of the monitoring area during a predetermined monitoring period obtained through an open and shared sample database, existing high-precision soybean mapping products, field surveys, and digital interpretation of high-resolution remote sensing imagery; The soybean identification index image data is calculated using the satellite multispectral image as input using a soybean identification index model; the soybean identification index model is the soybean identification index model described above; Determining a segmentation threshold, and performing image segmentation on the soybean identification index image data using the segmentation threshold to obtain an image segmentation result; According to the soybean spatial distribution map, the F1 score of the image segmentation result is calculated, and the step of "determining a segmentation threshold, and using the segmentation threshold to perform image segmentation on the soybean identification index image data to obtain an image segmentation result" is returned to iterate until the F1 scores in two adjacent iterations are the same, thereby obtaining an optimal segmentation threshold; the optimal segmentation threshold is the optimal segmentation threshold of the soybean spatial distribution mapping model.

[0010] Optionally, when determining the segmentation threshold, the initial segmentation threshold is T1, where T1=(T min +T max ) / 2; where T min Indicates the minimum value of cultivated land pixels in the soybean identification index image data, T max Indicates the maximum value of cultivated land pixels in the soybean identification index image data.

[0011] Optionally, the F1 score of the image segmentation result is calculated according to the soybean spatial distribution map, and during the iterative process of returning to the step of "determining a segmentation threshold, and performing image segmentation on the soybean identification index image data using the segmentation threshold to obtain an image segmentation result", the method for determining the segmentation threshold for the next iterative step includes: Calculating the precision and recall of the image segmentation result in the current iteration step based on the sample data; When the precision is greater than the recall rate, the segmentation threshold of the next iteration step is T3; T3=(T2+T max ) / 2, where T2 is the segmentation threshold in the current iteration step; When the precision is less than the recall rate, the segmentation threshold of the next iteration step is T4; T4=(T min +T2) / 2.

[0012] Optionally, the F1 score is calculated as: ; in, F1 represents the F1 score; P Indicates accuracy, R Represents the recall rate.

[0013] In a third aspect, the present application provides a method for using a soybean spatial distribution mapping model, comprising: Obtain satellite multispectral images of the area to be monitored; Using the satellite multispectral image as input, the soybean identification index image data of the area to be monitored is calculated using a soybean identification index model; the soybean identification index model is the soybean identification index model described above; The soybean identification index image data of the monitored area is segmented using the optimal segmentation threshold of the soybean spatial distribution mapping model to obtain a soybean spatial distribution map; the soybean spatial distribution mapping model is trained by the training method of any of the soybean spatial distribution mapping models described above.

[0014] In a fourth aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method for acquiring soybean identification index image data or the method for training a soybean spatial distribution mapping model or the method for using a soybean spatial distribution mapping model.

[0015] In a fifth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the soybean identification index image data acquisition method or the soybean spatial distribution mapping model training method or the soybean spatial distribution mapping model using method described above.

[0016] In a sixth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the soybean identification index image data acquisition method or the soybean spatial distribution mapping model training method or the soybean spatial distribution mapping model using method described above.

[0017] According to the specific embodiments provided in this application, this application discloses the following technical effects: The present application provides a method for acquiring soybean identification index image data, training and using a soybean spatial distribution mapping model, and related products. The image data acquisition method includes: acquiring soybean identification index image data using a soybean identification index model; the soybean identification index model is: ; ;in, NSII represents the calculated soybean identification index image data; EVI represents the enhanced vegetation index; Blue 、Re d 、 RE2 、 NIR and SWIR 1 are the satellite's blue, red, red-edge 2, near-red, and short-wave infrared 1 bands; G =2.5; C 1 =6; C 2 =7.5; L= 1; the soybean identification index model is used for mapping soybean spatial distribution. This application proposes a novel soybean identification index model by comprehensively utilizing visible light, near-infrared, red-edge, and short-wave infrared features. This index model can improve the separability of soybeans from other crops grown during the same period, providing a new identification feature for soybean remote sensing mapping and helping to improve the accuracy of soybean distribution mapping. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 This is an application environment diagram of the soybean identification index image data acquisition method, soybean spatial distribution mapping model training method or usage method provided in the embodiments of the present application.

[0020] Figure 2 A flowchart of a method for training a soybean spatial distribution mapping model provided in one embodiment of the present application.

[0021] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0023] This application comprehensively uses the characteristics of visible light, near-infrared, red edge and short-wave infrared to develop a new soybean identification index. This index improves the separability of soybeans and other crops of the same period, provides a new identification feature for soybean remote sensing mapping, and helps to improve the accuracy of soybean distribution mapping.

[0024] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0025] The soybean identification index image data acquisition method and the soybean spatial distribution mapping model training method or use method provided in the embodiments of the present application can be applied to Figure 1In the application environment shown, the terminal 102 communicates with the server 104 via a network. The data storage system can store data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers.

[0026] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, and tablet computers. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or a cloud server.

[0027] Example 1: In an exemplary embodiment, a method for obtaining soybean identification index image data is provided. The method is executed by a computer device, specifically a computer device such as a terminal or a server, or a terminal and a server. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps. The soybean identification index image data is obtained using the soybean identification index model; the soybean identification index model is: ; ; in, NSII represents the calculated soybean identification index image data; EVI represents the enhanced vegetation index; Blue 、Re d 、 RE2 、 NIR and SWIR 1 are respectively the blue, red, red-edge 2, near-red and shortwave infrared 1 bands of the Sentinel-2 satellite. For the Sentinel-2 satellite, the specific bands in this embodiment are bands 2, 4, 6, 8 and 11, i.e., bands B2, B4, B6, B8 and B11; G =2.5; C 1 =6; C 2 =7.5; L =1; the soybean identification index model is used for soybean spatial distribution mapping.

[0028] In addition, this embodiment also provides a method for constructing a soybean identification index model, the specific steps of which are as follows: 1. Sample data acquisition: Based on the Cropland Data Layer (CDL) of the most recent year within the monitoring area downloaded from the official website of the United States, we masked the areas of the CDL crop layer with a confidence level greater than 95% using areas with less than 15% cloud cover throughout the year in Sentinel-2 multispectral imagery. We then used the masked CDL data to select random points representing different crop types (soybean, corn, wheat, cotton, and rice). These random points were then merged into two types: soybean and non-soybean, and used as sample data.

[0029] 2. Image Acquisition: Sentinel-2 multispectral images of the monitoring area corresponding to the CDL year were acquired using the Google Earth Engine platform. Cloud removal was performed using the QA band. The images were then resampled to 10-meter resolution and a 10-day median composite was performed on the images. Finally, a 10-day median composite image with a 10-meter resolution was generated.

[0030] 3. Characteristic index calculation: Based on Sentinel-2 multispectral synthetic imagery, 35 remote sensing indices are calculated. The specific formula is as follows: Bi Indicates the number of Sentinel-2 i bands.

[0031] Normalized Difference Vegetation Index (NDVI): .

[0032] Normalized Difference Red Edge 1 Index (NDre1): .

[0033] Normalized Difference Red Edge 2 Index (NDre2): .

[0034] Land Surface Water Index (LSWI): .

[0035] Soil Adjusted Vegetation Index (SAVI): .

[0036] Normalized Difference Water Index (NDWI): .

[0037] Plant Senescence Reflectance Index (PSRI): .

[0038] Normalized Difference Vegetation Index Red Edge 1 (NDVIre1): .

[0039] Normalized Difference Vegetation Index Red Edge 2 (NDVIre2): .

[0040] New Inverted Red Edge Chlorophyll Index (IRECI): .

[0041] Red edge chlorophyll index (Cire): .

[0042] Ratio Vegetation Index (RVI): .

[0043] Wide Dynamic Range Vegetation Index (WDRVI): .

[0044] Nonlinear Vegetation Index (NLI): .

[0045] Modified Nonlinear Vegetation Index (MNLI): .

[0046] Optimized Soil Adjusted Vegetation Index (OSAVI): .

[0047] Enhanced Vegetation Index (EVI): .

[0048] Difference Vegetation Index (DVI): .

[0049] Bare Soil Index (BSI): .

[0050] Winter Rapeseed Index (WRI): .

[0051] Green ratio vegetation index (RVI Green ): .

[0052] The red light to red edge band ratio vegetation index (SR Red / Green ): .

[0053] Visible atmospheric impedance index (VARI) Green ): .

[0054] Triangular Vegetation Index (TVI): , .

[0055] MERIS Terrestrial Chlorophyll Index (MTCI): .

[0056] Modified Normalized Difference Vegetation Index (MNDVI): .

[0057] Modified Simple Ratio Vegetation Index (MSAVI): .

[0058] Modified Simple Ratio Red Edge Index (MSRre): .

[0059] Modified Simple Ratio Narrow Red Edge Index (MSRren): .

[0060] Renormalized Difference Vegetation Index (RDVI): .

[0061] Simple Ratio (SR): .

[0062] Red Edge Position (REP): .

[0063] Normalized Burning Index (NBR): .

[0064] Greenness and Water Composite Index (GWCCI): .

[0065] Soybean Charting Composite Index (SMCI): , , ,in, GVCI Represents the green chlorophyll vegetation index.

[0066] 4. Feature Separability Analysis and Determination of the Optimal Monitoring Time Window: The JM (Joven-Matthias-Mattithia) distance (JM) was used as a separability metric to analyze the separability of soybeans from other crops of the same period based on different characteristics. The JM distance ranges from 0 to 2, with greater differences in the characteristics between the two crops indicating a higher JM distance. The different characteristics include the 10 Sentinel-2 bands (bands 2, 3, 4, 5, 6, 7, 8, 8A, 11, and 12, respectively, bands B2, B3, B4, B5, B6, B7, B8, B8A, B11, and B12), as well as the 35 remote sensing indices calculated in the previous step. The JM distances calculated for different characteristics at different times were compared; larger JM distances indicate higher separability. The characteristics and time period with the highest separability were identified, and the period with the highest separability was designated as the optimal monitoring window.

[0067] 5. Determination of the Soybean Identification Index Model (NSII): Based on the principle of fully utilizing and minimizing feature redundancy, within the optimal monitoring window, a new index is formed by combining highly resolved features from 10 spectral bands and 35 indices through arithmetic operations such as addition, subtraction, multiplication, division, and inverse transformation. Bands with high resolution among the 10 spectral bands include the red-edge bands (RE2, RE3, and RE4), the near-infrared band (NIR), and the short-wave infrared bands (SWIR1 and SWIR2). Of the three red-edge bands, RE2 performed best; of the two short-wave infrared bands, SWIR1 performed better. Among the 35 indices, the SMCI, GWCCI, and EVI all performed well. The SMCI utilizes eight bands and already takes the EVI into account; the GWCCI is the product of SWIR1 and NDVI, utilizing the red, near-infrared, and short-wave infrared bands. To comprehensively utilize information from different spectral bands and reduce feature redundancy, we selected RE2 from the three red-edge bands, SWIR1 from the two shortwave infrared bands, and the EVI from the SMCI, GWCCI, and EVI indices, which provides complementary information from the red and near-infrared bands but does not involve red-edge and shortwave infrared bands. This led to the construction of a new soybean identification index (NSII). Mathematical manipulations (such as addition, subtraction, multiplication, division, and reciprocal transformations) were performed on the three basic features of RE2, SWIR1, and EVI to enhance soybean feature information. The final NSII calculation formula was determined by maximizing the average separation within the optimal time window. The details are as follows: ; ; in, NSII represents the calculated soybean identification index image data; EVI represents the enhanced vegetation index; Blue 、Re d 、 RE2 、 NIR and SWIR 1 are the blue, red, red-edge 2, near-red, and shortwave infrared 1 bands of the Sentinel-2 satellite, specifically bands 2, 4, 6, 8, and 11, namely bands B2, B4, B6, B8, and B11; G =2.5; C 1 =6; C 2 =7.5; L =1.

[0068] Compared with related technologies, the soybean identification index model (NSII index) in this embodiment has the following advantages: 1) It is lightweight. It uses a simple and easy-to-understand calculation process. By screening spectral bands and remote sensing indices, it efficiently combines bands and indices with high JM distances for soybean identification. This reduces the complexity of the calculation process, saves data processing time and computing resources, and thus improves the overall efficiency of mapping.

[0069] 2) It has better soybean identification capabilities. Analysis of the JM distance shows that the separation of the NSII exceeds that of the Soybean Mapping Composite Index (SMCI) and that of the Greenness and Water Composite Index (GWCCI). Furthermore, the soybean identification accuracy based on the NSII is higher than that based on the SMCI.

[0070] 3) It has excellent stability and portability. The NSII index has been tested for three years in multiple regions with different planting structures and climatic conditions, achieving excellent accuracy (over 80%), demonstrating its strong temporal and spatial portability.

[0071] 4) It has the potential for mid-season mapping. NSII does not require data from the entire growing season; soybean distribution mapping can begin as long as data within the optimal time window is obtained. This optimal time window is relatively long, which facilitates the collection of high-quality data and, to a certain extent, improves the practical application of NSII.

[0072] Example 2: like Figure 2 As shown, the embodiment of the present application also provides a training method for a soybean spatial distribution mapping model, comprising the following steps: S1. Obtain training data; the training data includes: satellite multispectral images and sample data; the sample data is sample data that has been distinguished into soybeans and non-soybeans; the sample data is soybean and non-soybean samples of the monitoring area during the preset monitoring period obtained through an open and shared sample database, existing high-precision soybean mapping products, field surveys, and digital interpretation of high-resolution remote sensing images. The sample data in this embodiment is soybean and non-soybean samples of the monitoring area during the preset monitoring period obtained through an open and shared sample database, existing high-precision soybean mapping products, field surveys, and digital interpretation of high-resolution remote sensing images. The sample data in this embodiment is soybean and non-soybean samples of the monitoring area during the preset monitoring period obtained through existing high-precision soybean mapping products, and is used to calculate the F1 score of the image segmentation result for training.

[0073] The obtained samples were randomly divided into two parts in a ratio of 7:3, 70% of which were used for threshold determination and 30% for accuracy verification.

[0074] Sentinel-2 multispectral images within the optimal soybean monitoring time window of the monitoring area in the monitoring year were obtained based on the Google Earth Engine platform. Cloud removal was performed using the QA band. The images were then resampled to a 10-meter resolution and median composited to generate a 10-meter resolution median composite image within the optimal monitoring time window.

[0075] S2. Using the multispectral satellite image of Sentinel-2 as input, calculate soybean identification index image data using a soybean identification index model; the soybean identification index model is the soybean identification index model described in Example 1.

[0076] The 10-meter resolution median composite image within the optimal soybean monitoring time window obtained in the previous step is used as input. The NSII within the optimal soybean monitoring time window is calculated according to the NSII calculation formula (soybean identification index model) to obtain the NSII image (soybean identification index image data).

[0077] S3. Determine a segmentation threshold, and use the segmentation threshold to perform image segmentation on the soybean identification index image data to obtain an image segmentation result.

[0078] S4. Calculate the F1 score of the image segmentation result based on the sample data, and return to the step of "determining a segmentation threshold, and using the segmentation threshold to perform image segmentation on the soybean identification index image data to obtain an image segmentation result" to iterate until the F1 scores in two adjacent iterations are the same, thereby obtaining an optimal segmentation threshold; the optimal segmentation threshold is the optimal segmentation threshold for the soybean spatial distribution mapping model.

[0079] When determining the segmentation threshold, the initial segmentation threshold is T1, where T1=(T min +T max ) / 2; where T min Indicates the minimum value of cultivated land pixels in the soybean identification index image data, T max Represents the maximum value of cultivated land pixels in the soybean identification index image data. Cultivated land pixels refer to pixels in the image that exclude buildings and other objects. Use this segmentation threshold to split the NSII image into two parts.

[0080] In the iterative process, the method for determining the segmentation threshold of the next iterative step includes: According to the soybean spatial distribution map, the precision and recall rate of the image segmentation result in the current iteration step are calculated.

[0081] When the precision is greater than the recall rate (indicating that the number of misclassifications is greater than the number of omissions and the threshold is low), the segmentation threshold for the next iterative step is T3; T3=(T2+T max) / 2, where T2 is the segmentation threshold in the current iteration step.

[0082] When the precision is less than the recall rate (indicating that the number of missed points is greater than the number of wrong points, and the threshold is higher), the segmentation threshold of the next iterative step is T4; T4=(T min +T2) / 2.

[0083] Then, the F1 scores before and after the updated threshold are compared. If the F1 score improves, the same logic is used to iterate. This process is repeated until the optimal segmentation threshold is obtained. The NSII image is segmented based on the optimal segmentation threshold, resulting in the final soybean distribution map.

[0084] The calculation formula of F1 score is: ; in, F1 represents the F1 score; P Indicates accuracy, R Represents the recall rate.

[0085] Finally, this embodiment also provides an accuracy verification process: Using the remaining 30% of the samples, we calculated the error matrix to verify the accuracy of the soybean distribution map. The error matrix is calculated as follows: In the error matrix, n represents the number of categories. The columns of the error matrix represent the reference images, and the rows represent the number of samples that have misclassification between the evaluated image and the corresponding category of the reference image.

[0086] The main diagonal elements in the table (x 11 ,x 22 ,…,x nn ) represents the number of samples that are correctly classified, while the elements outside the diagonal represent the number of samples that are incorrectly classified relative to the reference image. The row total represents the total number of samples of this category on the evaluated image, and the column total represents the total number of samples of this category on the reference image, as shown in the following table.

[0087] Table 1 Error matrix

[0088] Based on the error matrix, a series of accuracy evaluation indicators are calculated to evaluate the classification extraction results. The basic evaluation indicators are as follows: (1) Overall classification accuracy: ; Among them, OA represents the overall classification accuracy, x kkrepresents the number of correctly classified samples in the kth class, n represents the number of correctly classified sample categories, and N represents the total number of samples. Overall classification accuracy is the ratio of the number of correctly classified samples to the total number of samples, and is an important indicator in accuracy assessment. The number of correctly classified samples is the sum of the elements on the main diagonal of the error matrix, and the total sample size represents the sum of all samples.

[0089] (2) User precision (for class i): ; Among them, UA represents user accuracy, x ii Indicates the i The number of samples in the class that are consistent with the reference image category, x i+ Indicates the number of the evaluated data i The total number of samples in a class; user accuracy represents the ratio of the number of samples correctly classified into this class to the total number of samples of this class in the evaluated data.

[0090] (3) Cartographic accuracy (for category i): ; Among them, PA represents the mapping accuracy, x jj Indicates that the entire image is correctly classified into j The number of samples in the class, x +j Indicates the reference image j The mapping accuracy refers to the ratio of the number of samples correctly classified into this class in the entire image to the total number of samples of this category in the reference image.

[0091] (4) Kappa coefficient: ; Where n represents the total number of evaluated data feature categories participating in the assessment; x ii Refers to the values on the main diagonal of the error matrix; x i+ and x +i where is the total number of samples in row i and column i, respectively; N is the total number of samples in the precision assessment. The Kappa coefficient ranges from 0 to 1, with the closer it is to 1, the better the consistency.

[0092] Example 3: The present application also provides a method for using a soybean spatial distribution mapping model, comprising the following steps: Acquire a satellite multispectral image of the area to be monitored; in this embodiment, the acquired image is a Sentinel-2 satellite multispectral image.

[0093] Using the satellite multispectral image as input, the soybean identification index image data of the area to be monitored is calculated using a soybean identification index model; the soybean identification index model is the soybean identification index model described above; The soybean identification index image data of the monitored area is segmented using the optimal segmentation threshold of the soybean spatial distribution mapping model to obtain a soybean spatial distribution map; the soybean spatial distribution mapping model is trained using the soybean spatial distribution mapping model training method described in Example 2.

[0094] It should be noted that in this embodiment, when the satellite multispectral image changes, the soybean spatial distribution mapping model needs to be retrained. The change of the satellite multispectral image mainly refers to the change of the monitoring area location and time.

[0095] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for acquiring soybean identification index image data or a method for training a soybean spatial distribution mapping model or a method for using a soybean spatial distribution mapping model is implemented.

[0096] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0097] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0098] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0099] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0100] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0101] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0102] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0103] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0104] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for acquiring soybean identification index image data, characterized in that: include: The soybean identification index image data is obtained using the soybean identification index model; the soybean identification index model is: ; ； in, NSII represents the calculated soybean identification index image data; EVI represents the enhanced vegetation index; Blue 、Re d 、 RE2 、 NIR and SWIR 1 are the satellite's blue, red, red-edge 2, near-red, and short-wave infrared 1 bands; G =2.5; C 1 =6; C 2 =7.5; L =1; the soybean identification index model is used for soybean spatial distribution mapping.

2. The method for acquiring soybean identification index image data according to claim 1, characterized in that: Blue 、Re d 、 RE2 、 NIR and SWIR The specific bands of 1 are the 2nd, 4th, 6th, 8th and 11th bands of Sentinel 2, namely bands B2, B4, B6, B8 and B11.

3. A training method for a soybean spatial distribution mapping model, characterized in that: include: Acquire training data; the training data includes: satellite multispectral imagery and sample data; the sample data is sample data that has been differentiated into soybean and non-soybean; the sample data is soybean and non-soybean samples of the monitoring area during a predetermined monitoring period obtained through an open and shared sample database, existing high-precision soybean mapping products, field surveys, and digital interpretation of high-resolution remote sensing imagery; Taking the satellite multispectral image as input, soybean identification index image data is calculated using a soybean identification index model; the soybean identification index model is the soybean identification index model according to claim 1; Determining a segmentation threshold, and performing image segmentation on the soybean identification index image data using the segmentation threshold to obtain an image segmentation result; Based on the sample data, the F1 score of the image segmentation result is calculated, and the process returns to the step of "determining a segmentation threshold, and performing image segmentation on the soybean identification index image data using the segmentation threshold to obtain an image segmentation result" and iterates until the F1 scores in two adjacent iterations are the same, thereby obtaining an optimal segmentation threshold; the optimal segmentation threshold is the optimal segmentation threshold for the soybean spatial distribution mapping model.

4. The training method for soybean spatial distribution mapping model according to claim 3, characterized in that: When determining the segmentation threshold, the initial segmentation threshold is T1, where T1=(T min +T max ) / 2; where T min Indicates the minimum value of cultivated land pixels in the soybean identification index image data, T max Indicates the maximum value of cultivated land pixels in the soybean identification index image data.

5. The training method for soybean spatial distribution mapping model according to claim 4, characterized in that: Calculating the F1 score of the image segmentation result according to the soybean spatial distribution map, and returning to the step of "determining a segmentation threshold, and performing image segmentation on the soybean identification index image data using the segmentation threshold to obtain an image segmentation result" for iteration, the method for determining the segmentation threshold for the next iterative step includes: Calculating the precision and recall of the image segmentation result in the current iteration step according to the soybean spatial distribution map; When the precision is greater than the recall rate, the segmentation threshold of the next iteration step is T3; T3=(T2+T max ) / 2, where T2 is the segmentation threshold in the current iteration step; When the precision is less than the recall rate, the segmentation threshold of the next iteration step is T4; T4=(T min +T2) / 2.

6. The training method for soybean spatial distribution mapping model according to claim 3, characterized in that: The calculation formula of F1 score is: ; in, F1 represents the F1 score; P Indicates accuracy, R Represents the recall rate.

7. A method for using a soybean spatial distribution mapping model, characterized in that: include: Obtain satellite multispectral images of the area to be monitored; Using the satellite multispectral image as input, the soybean identification index image data of the area to be monitored is calculated using a soybean identification index model; the soybean identification index model is the soybean identification index model according to claim 1; The soybean identification index image data of the monitored area is segmented using the optimal segmentation threshold of the soybean spatial distribution mapping model to obtain a soybean spatial distribution map; the soybean spatial distribution mapping model is trained by the soybean spatial distribution mapping model training method according to any one of claims 3 to 6.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the soybean identification index image data acquisition method of claim 1 or 2, or the training method of the soybean spatial distribution mapping model of any one of claims 3-6, or the method for using the soybean spatial distribution mapping model of claim 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the soybean identification index image data acquisition method described in claim 1 or 2, or the training method of the soybean spatial distribution mapping model described in any one of claims 3-6, or the method for using the soybean spatial distribution mapping model described in claim 7.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, it implements the soybean identification index image data acquisition method described in claim 1 or 2, or the training method of the soybean spatial distribution mapping model described in any one of claims 3-6, or the method for using the soybean spatial distribution mapping model described in claim 7.

Images