Remote sensing extraction method, system and product for soybean and corn strip interplanting area

Abstract

This invention discloses a remote sensing extraction method, system, and product for soybean-maize strip intercropping areas, relating to the field of crop remote sensing monitoring. The method includes acquiring images of a target area and its multispectral bands; determining the mean texture features of the shortwave infrared bands; determining a vegetation index based on the target area image; performing band synthesis on the multispectral bands and the vegetation index to generate synthesized data; performing principal component analysis on the synthesized data to generate multiple principal components; constructing a decision tree model based on the mean texture features, the vegetation index, and the first three principal components; and extracting the soybean-maize strip intercropping area from the target area image based on the decision tree model; the first three principal components include a first principal component, a second principal component, and a third principal component. This invention can effectively identify soybean-maize strip intercropping areas.

Description

Technical Field

[0001] This invention relates to the field of remote sensing monitoring of crops, and in particular to a remote sensing extraction method, system and product for soybean-corn strip intercropping areas. Background Technology

[0002] Soybean-maize strip intercropping is an effective way to stabilize maize production and expand soybean production. The rapid development of remote sensing provides an effective technical means for scientifically and quickly obtaining the distribution of soybean-maize strip plantings.

[0003] Currently, in crop identification, commonly used remote sensing methods include machine learning-supervised classification based on spectra and vegetation indices, or time-series extraction based on the entire growth period of crops. However, these methods are insufficient for the effective identification of specific crops and their intercropping patterns. Summary of the Invention

[0004] The purpose of this invention is to provide a remote sensing extraction method, system, and product for soybean-maize strip intercropping areas to solve the problem of difficulty in identifying specific crop intercropping patterns.

[0005] To achieve the above objectives, the present invention provides the following solution:

[0006] A remote sensing method for extracting soybean-corn strip intercropping areas includes:

[0007] Acquire an image of the target area and the multispectral bands of the target area image; the multispectral bands include blue light band, green light band, red light band, near-infrared band and short-wave infrared band;

[0008] Determine the mean texture features of the shortwave infrared band;

[0009] Vegetation indices are determined based on the image of the target area; the vegetation indices include normalized vegetation index, difference vegetation index, vegetation moisture content index, and ratio vegetation index.

[0010] The multispectral bands and the vegetation index are combined to generate synthesized data.

[0011] Principal component analysis was performed on the synthesized data to generate multiple principal components;

[0012] A decision tree model is constructed based on the mean texture features, the vegetation index, and the first three principal components, and the soybean-maize strip intercropping area in the target area image is extracted based on the decision tree model; the first three principal components include the first principal component, the second principal component, and the third principal component.

[0013] Optionally, determining the mean texture features of the shortwave infrared band specifically includes:

[0014] The mean texture features of the shortwave infrared band are determined based on the gray-level co-occurrence matrix.

[0015] Optionally, the step of performing principal component analysis on the synthesized data to generate multiple principal components specifically includes:

[0016] The synthesized data is subjected to mean-removing processing to generate mean-removed features;

[0017] The covariance of the element values ​​of any two features after mean processing is used to form a covariance matrix, and the eigenvalues ​​and eigenvectors of the covariance matrix are determined.

[0018] The eigenvalues ​​are sorted in descending order, and the first K eigenvalues ​​and their corresponding eigenvectors are selected to form an eigenvector matrix.

[0019] The synthesized data is projected onto the feature vector matrix, and multiple principal components are generated based on the transformed feature vector matrix.

[0020] Optionally, the step of constructing a decision tree model based on the mean texture features, the vegetation index, and the first three principal components, and extracting the soybean-maize strip intercropping area in the target region image based on the decision tree model, specifically includes:

[0021] The image of the target region is distinguished into vegetated and non-vegetated areas based on the normalized vegetation index and the first principal component.

[0022] The soybean planting area in the vegetation region is determined based on the difference vegetation index.

[0023] Based on the mean texture features, the second principal component, and the third principal component, the corn planting area and the soybean-corn strip intercropping area in the vegetation area of ​​the non-soybean planting area are distinguished.

[0024] A remote sensing extraction system for soybean-corn strip intercropping areas includes:

[0025] A multispectral band acquisition module is used to acquire an image of a target area and the multispectral bands of the target area image; the multispectral bands include blue light band, green light band, red light band, near-infrared band, and short-wave infrared band;

[0026] The mean texture feature determination module is used to determine the mean texture features of the shortwave infrared band.

[0027] The vegetation index determination module is used to determine the vegetation index based on the target area image; the vegetation index includes normalized vegetation index, difference vegetation index, vegetation moisture content index and ratio vegetation index.

[0028] The synthesis module is used to perform band synthesis of the multispectral bands and the vegetation index to generate synthesized data.

[0029] The principal component analysis module is used to perform principal component analysis on the synthesized data and generate multiple principal components.

[0030] The soybean-maize strip intercropping area extraction module is used to construct a decision tree model based on the mean texture features, the vegetation index, and the first three principal components, and to extract the soybean-maize strip intercropping area in the target area image based on the decision tree model; the first three principal components include a first principal component, a second principal component, and a third principal component.

[0031] Optionally, the mean texture feature determination module specifically includes:

[0032] The mean texture feature determination unit is used to determine the mean texture features of the shortwave infrared band based on the gray-level co-occurrence matrix.

[0033] Optionally, the principal component analysis module specifically includes:

[0034] The mean-removing processing unit is used to perform mean-removing processing on the synthesized data to generate mean-removed features;

[0035] The eigenvalue and eigenvector determination unit is used to form a covariance matrix by taking the covariance of the element values ​​of any two features after mean processing, and to determine the eigenvalue and eigenvector of the covariance matrix.

[0036] The feature vector matrix composition unit is used to sort the feature values ​​in descending order and select the first K feature values ​​and their corresponding feature vectors to form a feature vector matrix;

[0037] The principal component generation unit is used to project and transform the synthesized data onto the feature vector matrix, and generate multiple principal components based on the transformed feature vector matrix.

[0038] Optionally, the soybean-corn strip intercropping extraction module specifically includes:

[0039] A vegetation and non-vegetation area differentiation unit is used to differentiate vegetation areas and non-vegetation areas in the target area image based on the normalized vegetation index and the first principal component.

[0040] A soybean planting area determination unit is used to determine soybean planting areas in the vegetation area based on the difference vegetation index.

[0041] The unit for distinguishing corn and soybean-corn strip intercropping areas is used to distinguish corn planting areas and soybean-corn strip intercropping areas in vegetation areas outside soybean planting areas based on the mean texture features, the second principal component, and the third principal component.

[0042] An electronic device includes a memory and a processor, the memory storing a computer program, and the processor running the computer program to enable the electronic device to perform the remote sensing extraction method for soybean-maize strip intercropping areas described above.

[0043] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the remote sensing extraction method for soybean-corn strip intercropping areas described above.

[0044] According to specific embodiments provided by the present invention, the following technical effects are disclosed: The present invention provides a remote sensing extraction method, system, and product for soybean-maize strip intercropping areas. By synthesizing multispectral bands and vegetation indices from images of the target area, and performing principal component analysis on the synthesized data, a decision tree model is constructed based on the mean texture features of different land features and multiple principal components. Based on this decision tree model, soybean-maize strip intercropping areas in the target area image are extracted. For remote sensing extraction of soybean-maize strip intercropping areas, the present invention extracts soybean-maize strip intercropping areas based on the characteristics of soybean-maize strip planting patterns and according to spectral and mean texture features, which can effectively identify soybean-maize strip intercropping areas. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 Flowchart of the remote sensing extraction method for soybean-maize strip intercropping areas provided by the present invention;

[0047] Figure 2 The first three principal component results provided by this invention;

[0048] Figure 3 This is a flowchart of remote sensing extraction of soybean-corn strip intercropping areas provided by the present invention;

[0049] Figure 4 This is an image showing the extraction results of a soybean-corn strip intercropping area provided by the present invention. Detailed Implementation

[0050] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0051] The purpose of this invention is to provide a remote sensing extraction method, system, and product for soybean-corn strip intercropping areas, which can effectively identify soybean-corn strip intercropping areas.

[0052] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0053] Example 1

[0054] Figure 1 The flowchart of the remote sensing extraction method for soybean-maize strip intercropping areas provided by this invention is as follows: Figure 1 As shown, this invention provides a remote sensing method for extracting data from soybean-maize strip intercropping areas, comprising:

[0055] Step 101: Acquire the target area image and the multispectral bands of the target area image; the multispectral bands include blue light band, green light band, red light band, near-infrared band and short-wave infrared band.

[0056] In practical applications, this invention uses Senltinel 2 Level-2A image data, taken in mid-August, a period of vigorous growth for soybeans and corn. The downloaded images have already undergone preprocessing such as radiometric calibration and atmospheric correction; here, only band synthesis and cropping are performed. Five bands—Blue, Green, Red, Near-Infrared (NIR), and Short-Wave Infrared (SWIR)—are selected for synthesis.

[0057] Image cropping is performed using the vector range of the study area to obtain images of the target region.

[0058] Step 102: Determine the mean texture features of the shortwave infrared band.

[0059] In practical applications, step 102 specifically includes: determining the mean texture features of the shortwave infrared band based on the gray-level co-occurrence matrix.

[0060] Texture calculations for different land features are based on the Gray Level Co-Occurrence Matrix (GLCM). A GLCM is a matrix that describes the gray-level relationship between adjacent pixels or two pixels within a certain distance in an image region. Its elements are defined as follows: This represents the probability of gray level j appearing starting from gray level i, given a distance d and a direction θ (generally, it counts the number of times a target pixel pair appears).

[0061] Based on preliminary research and analysis, this invention selects the mean statistical attribute to calculate its mean texture features.

[0062] Step 103: Determine the vegetation index based on the target area image; the vegetation index includes normalized vegetation index, difference vegetation index, vegetation moisture content index and ratio vegetation index.

[0063] In practical applications, the Normalized Difference Vegetation Index (NDVI) has a significant advantage in distinguishing between vegetation and non-vegetation, and is the ratio of the difference in reflectance between the near-infrared and red light bands to the sum of the two values.

[0064] Difference Vegetation Index (DVI) R-G The Difference Vegetation Index (DVI) represents the difference between red and green light bands and has some ability to distinguish between soybean-corn intercropping plots and pure soybean planting plots. R-G Used to distinguish between soybean planting areas and soybean-corn strip intercropping areas.

[0065] The Land Surface Water Index (LSWI) is the ratio of the difference in reflectance between the near-infrared band and the short-wave infrared band to the sum of the two values. It is relatively sensitive to the moisture content of crops.

[0066] The Ratio Vegetation Index (RVI) is the ratio of near-infrared to red light reflectance. RVI is highly correlated with chlorophyll content and is relatively sensitive to vegetation.

[0067] The formulas for calculating each vegetation index are defined as follows:

[0068]

[0069] DVI R-G =ρ Red -ρ Green (2)

[0070]

[0071]

[0072] Where, ρ Red ρ Green ρ Nir ρ Swir These are the reflectances for the red light band, green light band, near-infrared band, and short-wave infrared band, respectively.

[0073] Step 104: Combine the multispectral bands and the vegetation index to generate composite data.

[0074] Step 105: Perform principal component analysis on the synthesized data to generate multiple principal components; the principal components include a first principal component PCA1, a second principal component PCA2, and a third principal component PCA3. In this invention, nine principal components are generated, among which the first three principal components contain more than 98% of the information, therefore the first three principal components are selected for subsequent extraction.

[0075] In practical applications, a single spectral or vegetation index is insufficient to distinguish soybean-maize strip intercropping from other crops or vegetation. Using multiple indicators in combination leads to data redundancy and makes it difficult to obtain crucial information for crop classification. This invention utilizes multispectral bands and multiple vegetation indices (NDVI, DVI) R-G By combining RVI and LSWI, and through Principal Component Analysis (PCA), data dimensionality reduction is achieved, and important information in the data is effectively extracted.

[0076] Multispectral bands with NDVI, DVI R-G Band synthesis was performed using RVI and LSWI, and then principal component analysis was performed on the synthesized data.

[0077] This invention selects principal component analysis based on eigenvalue decomposition. Principal component analysis, also known as principal component transformation, mainly consists of several steps: removing the mean, finding the covariance matrix, finding the eigenvalues ​​and eigenvectors of the covariance matrix, sorting the eigenvalues, retaining the top K largest eigenvalues ​​and their corresponding eigenvectors, and performing projection transformation on the features.

[0078] The process of removing the mean involves calculating the mean of all elements for each feature and then subtracting the mean of the corresponding feature from each data point.

[0079] Find the covariance matrix by combining the covariances of any two element values.

[0080] Then, find the eigenvalues and eigenvectors of the covariance matrix, sort the eigenvalues, select the top K eigenvalues with the largest values and the corresponding eigenvectors to form an eigenvector matrix, and finally project the original features onto the new matrix.

[0081] The present invention combines spectral bands with multiple vegetation indices for PCA to compress data information, thereby further obtaining the characteristics of soybean-corn strip intercropping.

[0082] Step 106: Construct a decision tree model based on the mean texture feature, the vegetation index, and the first three principal components, and extract the soybean-corn strip intercropping area in the target area image according to the decision tree model; the first three principal components include the first principal component, the second principal component, and the third principal component.

[0083] In practical applications, step 106 specifically includes: distinguishing the vegetation area and the non-vegetation area in the target area image according to the normalized vegetation index and the first principal component; determining the soybean planting area in the vegetation area according to the difference vegetation index; distinguishing the corn planting area and the soybean-corn strip intercropping area in the vegetation area other than the soybean planting area according to the mean texture feature, the second principal component, and the third principal component.

[0084] In practical applications, S1: First, use NDVI and the first principal component (PCA1) to distinguish vegetation from non-vegetation (such as water bodies, buildings, roads, etc.), set the conditions NDVI>T1 and PCA1<T2. When the conditions are false, the pixel is marked as "non-vegetation". When the above conditions are true, execute S2 for judgment.

[0085] S2: Use DVI R-G to剔除soybeans, and DVI R-G is the difference vegetation index constructed through sample analysis, which can distinguish soybeans (purely planted soybeans) from the soybean-corn strip intercropping area. Set the condition DVI R-G >T3. When the condition is false, it is marked as "soybean". When the condition is true, enter S3 for judgment.

[0086] It should be noted that the text "剔除soybeans" in the original seems to be an incorrect expression. It might be a misspelling or an unclear term. If it's a specific term in Chinese that needs to be accurately translated, more context or clarification is required. Here, I translated it as "to exclude soybeans" for the sake of a complete translation.S3: There are certain differences in the spectrum and texture between the strip - intercropped soybean - maize and maize (only maize planted) and other vegetation. The texture mean (SWIR_Mean) in the SWIR band is more obvious in differentiating strip - intercropped soybean - maize from maize and other crops. In addition, the information extracted by the second principal component (PCA2) and the third principal component (PCA3) separates the target crops from the characteristics of maize and other vegetation to a certain extent. Therefore, three indicators, SWIR_Mean, PCA2, and PCA3, are used to jointly set parameters to distinguish the strip - intercropped soybean - maize area from maize and other vegetation. The set conditions are SWIR_Mean > T4, T5 < PCA2 < T6, and PCA3 > T7. When the conditions are false, the pixel is marked as "maize or other vegetation", and when the conditions are true, the pixel is marked as "strip - intercropped soybean - maize area".

[0087] Example Two

[0088] Some areas in Zhecheng County and Suiyang District of Shangqiu City, Henan Province are selected as case areas, and Sentinel - 2 images are used as the data source for crop extraction. The time of the Sentinel - 2 image is August 12, 2022.

[0089] Step 1: Data acquisition and pre - processing.

[0090] Download the Level - 2A Sentinel - 2 image after atmospheric correction, perform band synthesis. The synthesized bands include Blue, Green, Red, NIR, and SWIR, and crop the synthesized image.

[0091] Step 2: Calculate vegetation indices such as NDVI, DVI R-G , RVI, LSWI, etc.

[0092] Calculate each vegetation index using the green, red, near - infrared, and short - wave infrared bands of the pre - processed Sentinel - 2 image. The calculation formulas are as follows:

[0093]

[0094] DVI R-G = ρ Red - ρ Green

[0095]

[0096]

[0097] Among them, ρ Red , ρ Green , ρ Nir , ρ swir are the reflectances of the red - light band, green - light band, near - infrared, and short - wave infrared bands respectively.

[0098] Step 3: Combine multispectral bands and vegetation indices for principal component analysis.

[0099] Multispectral bands and previously calculated vegetation indices were combined, and principal component analysis was performed on the combined data, using the covariance matrix as the calculation matrix. The first three principal components in the principal component analysis contained over 98% of the information; therefore, these three principal components were selected for subsequent target crop extraction. Figure 2 As shown.

[0100] Step 4: Texture calculation.

[0101] Texture was calculated based on the gray-level co-occurrence matrix, with the mean value chosen as the statistical indicator. The moving window was set to 3×3, and the gray-level levels were set to 64. Based on the analysis, the mean texture value in the short-wave infrared band was selected for subsequent model construction.

[0102] Step 5: Construct a remote sensing extraction model for soybean and corn strip planting.

[0103] S1: Set the conditions NDVI > 0.42 and PCA1 < 0.5. When the conditions are false, the pixel is marked as "non-vegetation". When the above conditions are true, execute the S2 judgment.

[0104] S2: Setting Conditions for DVI R-G >-235, when the condition is false, the cell is marked as "soybean", when the condition is true, enter S3 to perform the judgment.

[0105] S3: Set the conditions SWIR_Mean > 16.6, 10 < PCA2 < 1300 and PCA3 > 30. When the conditions are false, the cell is labeled as "corn and other vegetation". When the conditions are true, the cell is labeled as "soybean and corn strip intercropping".

[0106] Figure 3 This is a flowchart of remote sensing extraction of soybean-corn strip intercropping areas provided by the present invention. Figure 3 The "Soybean" category indicates that only soybeans are grown, while the "Corn" category under "Corn or other vegetation" indicates that only corn is grown.

[0107] Step Six: Result Post-processing and Accuracy Verification.

[0108] Based on the decision tree classification results, the soybean-corn strip intercropping category is extracted, and speckle noise and boundary misextractions caused by mixed pixels are removed. Samples are obtained using high-resolution imagery or field sampling to verify the accuracy of the extraction results. The overall classification accuracy is calculated using a confusion matrix. If the accuracy reaches 90% or higher, the requirement is met; if it is lower than 90%, the process returns to step five to readjust the model parameter thresholds, repeating steps five and six until the requirement is met. In this embodiment, the overall classification accuracy is 91.82%, which meets the requirement.

[0109] Figure 4 The image shows the extraction results of the soybean-corn strip intercropping area provided by this invention, as follows: Figure 4 As shown, the soybean-maize strip intercropping category is extracted from the decision tree classification results and post-processed. Since pixel-based classification suffers from speckle noise and boundary misextraction due to mixed pixels, post-processing is necessary for the extracted soybean-maize strip intercropping distribution results. The main post-processing steps include filtering and small patch removal.

[0110] This invention utilizes Sentinel-2 multispectral imagery to calculate multiple vegetation indices and performs principal component transformation to extract important information. Simultaneously, it calculates and obtains mean texture features. By combining the obtained multiple index information, a decision tree model for remote sensing extraction of soybean-maize strip planting is constructed, thereby achieving the goal of extracting the distribution of soybean-maize strip intercropping based on satellite imagery.

[0111] Example 3

[0112] In order to implement the method corresponding to Embodiment 1 above and achieve the corresponding functions and technical effects, a remote sensing extraction system for soybean-corn strip intercropping areas is provided below.

[0113] A remote sensing extraction system for soybean-corn strip intercropping areas includes:

[0114] A multispectral band acquisition module is used to acquire images of a target area and the multispectral bands of the target area image; the multispectral bands include blue light band, green light band, red light band, near-infrared band and short-wave infrared band.

[0115] The mean texture feature determination module is used to determine the mean texture features of the shortwave infrared band.

[0116] In practical applications, the mean texture feature determination module specifically includes: a mean texture feature determination unit, used to determine the mean texture features of the shortwave infrared band based on the gray-level co-occurrence matrix.

[0117] The vegetation index determination module is used to determine the vegetation index based on the target area image; the vegetation index includes the normalized vegetation index, the difference vegetation index, the vegetation moisture content index, and the ratio vegetation index.

[0118] The synthesis module is used to perform band synthesis of the multispectral bands and the vegetation index to generate synthesized data.

[0119] The principal component analysis module is used to perform principal component analysis on the synthesized data and generate multiple principal components; the principal components include a first principal component, a second principal component, and a third principal component.

[0120] In practical applications, the principal component analysis module specifically includes: a mean-removal processing unit, used to remove the mean from the synthesized data to generate mean-removed features; an eigenvalue and eigenvector determination unit, used to form a covariance matrix by combining the covariances of the element values ​​of any two mean-removed features, and to determine the eigenvalues ​​and eigenvectors of the covariance matrix; an eigenvector matrix composition unit, used to sort the eigenvalues ​​in descending order, select the first K eigenvalues ​​and their corresponding eigenvectors to form an eigenvector matrix; and a principal component generation unit, used to project and transform the synthesized data onto the eigenvector matrix, and generate multiple principal components based on the transformed eigenvector matrix.

[0121] The soybean-maize strip intercropping area extraction module is used to construct a decision tree model based on the mean texture features, the vegetation index, and the first three principal components, and to extract the soybean-maize strip intercropping area in the target area image based on the decision tree model; the first three principal components include a first principal component, a second principal component, and a third principal component.

[0122] In practical applications, the soybean-maize strip intercropping extraction module specifically includes: a vegetation and non-vegetation area differentiation unit, used to differentiate vegetation areas and non-vegetation areas in the target area image based on the normalized vegetation index and the first principal component; a soybean planting area determination unit, used to determine soybean planting areas within the vegetation areas based on the difference vegetation index; and a corn and soybean-maize strip intercropping area differentiation unit, used to differentiate corn planting areas and soybean-maize strip intercropping areas within the vegetation areas of non-soybean planting areas based on the mean texture feature, the second principal component, and the third principal component.

[0123] Example 4

[0124] This invention provides an electronic device including a memory and a processor. The memory stores a computer program, and the processor runs the computer program to enable the electronic device to perform the remote sensing extraction method for soybean-corn strip intercropping areas provided in Embodiment 1.

[0125] In practical applications, the aforementioned electronic devices can be servers.

[0126] In practical applications, electronic devices include: at least one processor, memory, bus, and communication interface.

[0127] The processor, communication interface, and memory communicate with each other via a communication bus.

[0128] A communication interface is used to communicate with other devices.

[0129] The processor is used to execute programs, specifically the methods described in the above embodiments.

[0130] Specifically, the program may include program code, which includes computer operation instructions.

[0131] The processor may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The electronic device may include one or more processors of the same type, such as one or more CPUs; or it may include processors of different types, such as one or more CPUs and one or more ASICs.

[0132] Memory is used to store programs. Memory may include high-speed RAM, and may also include non-volatile memory, such as at least one disk drive.

[0133] Based on the description of the above embodiments, this application provides a storage medium storing computer program instructions thereon, which can be executed by a processor to implement the methods described in any embodiment.

[0134] The remote sensing extraction system for soybean-maize strip intercropping areas provided in this application exists in various forms, including but not limited to:

[0135] (1) Mobile communication devices: These devices are characterized by their mobile communication capabilities and primarily aim to provide voice and data communication. These terminals include: smartphones (e.g., iPhones), multimedia phones, feature phones, and low-end phones, etc.

[0136] (2) Ultra-mobile personal computer devices: These devices fall under the category of personal computers, possessing computing and processing capabilities, and generally also have mobile internet access capabilities. These terminals include PDAs, MIDs, and UMPCs, such as the iPad.

[0137] (3) Portable entertainment devices: These devices can display and play multimedia content. This category includes: audio and video players (such as iPods), handheld game consoles, e-books, as well as smart toys and portable car navigation devices.

[0138] (4) Other electronic devices with data interaction functions.

[0139] Specific embodiments of the subject matter have now been described. Other embodiments are within the scope of the appended claims. In some cases, the actions described in the claims can be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing can be advantageous.

[0140] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0141] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware components. Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0142] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0143] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0144] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0145] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0146] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0147] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, and CD-ROM.

[0148] Digital multifunction optical disc (DVD) or other optical storage, magnetic cassette tape, magnetic tape, disk storage or other magnetic storage devices

[0149] Or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transient media, such as modulated data signals and carrier waves.

[0150] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0151] This application can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific transactions or implement specific abstract data types. This application can also be practiced in distributed computing environments where transactions are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0152] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0153] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A remote sensing method for extracting data from soybean-corn strip intercropping areas, characterized in that, include: Acquire an image of the target area and the multispectral bands of the target area image; the multispectral bands include blue light band, green light band, red light band, near-infrared band and short-wave infrared band; Determine the mean texture features of the shortwave infrared band; Vegetation indices are determined based on the image of the target area; the vegetation indices include normalized vegetation index, difference vegetation index, vegetation moisture content index, and ratio vegetation index. The multispectral bands and the vegetation index are combined to generate synthesized data. Principal component analysis was performed on the synthesized data to generate multiple principal components, specifically including: The synthesized data is subjected to mean-removing processing to generate mean-removed features; The covariance of the element values ​​of any two features after mean processing is used to form a covariance matrix, and the eigenvalues ​​and eigenvectors of the covariance matrix are determined. The eigenvalues ​​are sorted in descending order, and the first K eigenvalues ​​and their corresponding eigenvectors are selected to form an eigenvector matrix. The synthesized data is projected onto the feature vector matrix, and multiple principal components are generated based on the transformed feature vector matrix. A decision tree model is constructed based on the mean texture features, the vegetation index, and the first three principal components. The soybean-maize strip intercropping area in the target region image is then extracted using the decision tree model, specifically including: The vegetated and non-vegetated areas in the target region image are distinguished based on the normalized vegetation index and the first principal component. The soybean planting area in the vegetation region is determined based on the difference vegetation index. The mean texture features, the second principal component, and the third principal component are used to distinguish between corn planting areas and soybean-corn strip intercropping areas in vegetation areas outside soybean planting areas; the first three principal components include the first principal component, the second principal component, and the third principal component.

2. The remote sensing extraction method for soybean-maize strip intercropping areas according to claim 1, characterized in that, Determining the mean texture features of the shortwave infrared band specifically includes: The mean texture features of the shortwave infrared band are determined based on the gray-level co-occurrence matrix.

3. A remote sensing extraction system for soybean-corn strip intercropping areas, characterized in that, include: A multispectral band acquisition module is used to acquire an image of a target area and the multispectral bands of the target area image; the multispectral bands include blue light band, green light band, red light band, near-infrared band, and short-wave infrared band; The mean texture feature determination module is used to determine the mean texture features of the shortwave infrared band. The vegetation index determination module is used to determine the vegetation index based on the target area image; the vegetation index includes normalized vegetation index, difference vegetation index, vegetation moisture content index and ratio vegetation index. The synthesis module is used to perform band synthesis of the multispectral bands and the vegetation index to generate synthesized data. The principal component analysis module is used to perform principal component analysis on the synthesized data and generate multiple principal components. The principal component analysis module specifically includes: The mean-removing processing unit is used to perform mean-removing processing on the synthesized data to generate mean-removed features; The eigenvalue and eigenvector determination unit is used to form a covariance matrix by taking the covariance of the element values ​​of any two features after mean processing, and to determine the eigenvalue and eigenvector of the covariance matrix. The feature vector matrix composition unit is used to sort the feature values ​​in descending order and select the first K feature values ​​and their corresponding feature vectors to form a feature vector matrix; The principal component generation unit is used to project and transform the synthesized data onto the feature vector matrix, and generate multiple principal components based on the transformed feature vector matrix. The soybean-maize strip intercropping area extraction module is used to construct a decision tree model based on the mean texture features, the vegetation index, and the first three principal components, and to extract the soybean-maize strip intercropping area in the target region image based on the decision tree model; the first three principal components include a first principal component, a second principal component, and a third principal component; The soybean-corn strip intercropping zone extraction module specifically includes: A vegetation and non-vegetation area differentiation unit is used to differentiate vegetation areas and non-vegetation areas in the target area image based on the normalized vegetation index and the first principal component. A soybean planting area determination unit is used to determine soybean planting areas in the vegetation area based on the difference vegetation index. The unit for distinguishing corn and soybean-corn strip intercropping areas is used to distinguish corn planting areas and soybean-corn strip intercropping areas in vegetation areas outside soybean planting areas based on the mean texture features, the second principal component, and the third principal component.

4. The remote sensing extraction system for soybean-corn strip intercropping areas according to claim 3, characterized in that, The mean texture feature determination module specifically includes: The mean texture feature determination unit is used to determine the mean texture features of the shortwave infrared band based on the gray-level co-occurrence matrix.

5. An electronic device, characterized in that, The device includes a memory and a processor, the memory being used to store a computer program, and the processor running the computer program to enable the electronic device to perform the remote sensing extraction method for soybean-maize strip intercropping areas as described in any one of claims 1-2.

6. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed by a processor, implements the remote sensing extraction method for soybean-maize strip intercropping areas as described in any one of claims 1-2.

Images