Crop planting distribution plot identification method, device and equipment

Abstract

Embodiments of the present application provide a crop planting distribution plot identification method, device and equipment, wherein the method comprises: acquiring SAR time series data, high-resolution remote sensing image data and time series optical data corresponding to a measured area; determining a suspected crop planting area in the measured area based on the SAR time series data and in combination with the phenological characteristics of different crop planting sub-regions corresponding to the measured area; determining an agricultural planting plot from the measured area based on the high-resolution remote sensing image data; performing superimposition processing on a distribution map of the suspected crop planting area and a distribution map of the agricultural planting plot to obtain a suspected crop planting plot distribution map; and determining a crop planting distribution plot distribution map based on the suspected crop planting plot distribution map and the time series optical data.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of remote sensing, and relate to but are not limited to a crop planting distribution plot identification method, device and equipment. BACKGROUND

[0002] Grain is not only an important commodity, but also an important strategic material for the country, and its importance is self-evident. Stabilizing grain sowing area and increasing grain yield is a hard task to ensure national food security and social stability. Therefore, the demand for accurate, comprehensive and timely grain production information by the agricultural authorities is increasingly urgent to ensure that the decision-making is scientific, effective and accurate. As we all know, remote sensing technology is one of the most important monitoring techniques in precision agriculture. In China, rice is one of the important grain crops, and more than 60% of the population in China mainly eats rice, so rice remote sensing monitoring has important practical value.

[0003] Currently, remote sensing technology carries out rice planting monitoring mainly by using the typical spectral characteristics and changes of rice presented on multi-temporal remote sensing images to extract the planting area of rice. Optical images are more widely used and have relatively high accuracy. However, in mountainous areas, due to weather conditions, there are often problems such as missing images in the key growth period, and gradually developed into rice planting identification technology based on synthetic aperture radar (SAR) images. In recent years, it has developed into a rice identification method that comprehensively utilizes the respective advantages of optical and SAR images.

[0004] However, in the related technology, single SAR time series data or high-resolution remote sensing image data is used, which is easily affected by bad weather conditions such as clouds, rain and snow, and cannot accurately obtain the required image data, in addition, it also causes the image data of the rice growth cycle and the key growth period to be missing, which greatly limits the application of rice remote sensing identification technology. Therefore, the scheme in the related technology cannot quickly and accurately extract the rice planting distribution plot distribution map. SUMMARY

[0005] Embodiments of the present application provide a crop planting distribution plot identification method, device and equipment.

[0006] The technical scheme of the embodiments of the present application is as follows:

[0007] The embodiments of the present application provide a crop planting distribution plot identification method, which comprises:

[0008] The SAR time series data corresponding to the measured region, high-resolution remote sensing image data and time series optical data are acquired; based on the SAR time series data, combined with the phenological characteristics corresponding to different crop plant phenological sub-regions in the measured region, a suspected crop planting area in the measured region is determined; based on the high-resolution remote sensing image data, an agricultural planting plot in the measured region is determined; the distribution map of the suspected crop planting area and the distribution map of the agricultural planting plot are superimposed to obtain a suspected crop planting plot distribution map; based on the suspected crop planting plot distribution map and the time series optical data, a planting distribution plot distribution map of the crop is determined.

[0009] In some embodiments, before acquiring the SAR time series data corresponding to the measured region, high-resolution remote sensing image data and time series optical data, the method further comprises: acquiring regional attribute parameters of the measured region, wherein the regional attribute parameters include: terrain data, climate data and soil parent material data; based on the regional attribute parameters, the measured region is divided into a plurality of crop plant phenological sub-regions.

[0010] In some embodiments, based on the SAR time series data, combined with the phenological characteristics corresponding to different crop plant phenological sub-regions in the measured region, the suspected crop planting area in the measured region is determined, comprising: acquiring SAR time series data of each crop plant phenological sub-region in the plurality of crop plant phenological sub-regions; based on the SAR time series data of each crop plant phenological sub-region, the backscattering coefficient characteristics corresponding to each pixel at each time point in the crop plant phenological sub-region are determined; based on the backscattering coefficient characteristics corresponding to each time point, a feature time series curve of all pixels in each crop plant phenological sub-region is constructed; based on the feature time series curve, a suspected crop planting pixel is determined from each crop plant phenological sub-region; a planting area composed of a plurality of adjacent suspected crop planting pixels is determined as a suspected crop planting area.

[0011] In some embodiments, based on the feature time series curve, a suspected crop planting pixel is determined from each crop plant phenological sub-region, comprising: determining the slope change characteristics corresponding to each feature time series curve; acquiring a preset slope change threshold; each pixel with a slope change characteristic greater than the slope change threshold is determined as the suspected crop planting pixel.

[0012] In some embodiments, based on the high-resolution remote sensing image data, an agricultural planting plot in the measured region is determined, comprising: based on the high-resolution remote sensing image data, extracting plot boundary information in the measured region; based on the plot boundary information, a polygon vector map of the measured region is constructed; based on the polygon vector map, the agricultural planting plot in the measured region is determined.

[0013] In some embodiments, the suspected crop planting plot distribution map includes a plurality of suspected crop planting plots; and the determining the planting distribution plot distribution of the crop based on the suspected crop planting plot distribution map and the time-series optical data includes: superimposing the suspected crop planting plot distribution map and the image corresponding to the time-series optical data to obtain a plot time-series curve of a plot feature of each suspected crop planting plot changing over time; and determining the planting distribution plot distribution of the crop based on the plot time-series curve.

[0014] In some embodiments, the determining the planting distribution plot distribution of the crop based on the plot time-series curve includes: obtaining a sample time-series curve of the crop from a sample data set; determining a curve similarity between the plot time-series curve of each suspected crop planting plot and the sample time-series curve; determining a suspected crop planting plot with a curve similarity greater than a similarity threshold as a planting distribution plot of the crop; and constructing the planting distribution plot distribution based on the planting distribution plot of the crop.

[0015] In some embodiments, the method further includes: determining the curve similarity of each suspected crop planting plot as a confidence level when the suspected crop planting plot is identified; determining a suspected crop planting plot with a confidence level greater than a confidence level threshold as an expansion sample; and adding a plot time-series curve corresponding to the expansion sample to the sample data set.

[0016] Embodiments of the present application provide a crop planting distribution plot identification device, the device includes:

[0017] The acquisition module is configured to acquire SAR time-series data, high-resolution remote sensing image data, and time-series optical data corresponding to a measured region; the determination module is configured to determine a suspected crop planting area in the measured region based on the SAR time-series data and in combination with phenological characteristics corresponding to different crop phenological sub-regions in the measured region; the determination module is further configured to determine an agricultural planting plot in the measured region based on the high-resolution remote sensing image data; the superimposition module is configured to superimpose a distribution map of the suspected crop planting area and a distribution map of the agricultural planting plot to obtain a suspected crop planting plot distribution map; and the determination module is further configured to determine a planting distribution plot distribution of the crop based on the suspected crop planting plot distribution map and the time-series optical data.

[0018] Embodiments of the present application provide a crop planting distribution plot identification device, the device includes:

[0019] The memory is used to store executable instructions; the processor is used to implement the above-mentioned method for identifying crop planting distribution plots when executing the executable instructions stored in the memory.

[0020] This application provides a computer program product or computer program, which includes executable instructions stored in a computer-readable storage medium; wherein, when the processor for identifying crop planting distribution plots reads the executable instructions from the computer-readable storage medium and executes the executable instructions, it implements the above-mentioned method for identifying crop planting distribution plots.

[0021] This application provides a computer-readable storage medium storing executable instructions, which, when executed by a processor, implement the above-mentioned method for identifying crop planting distribution plots.

[0022] The method, apparatus, and equipment for identifying crop planting areas and plots provided in this application, based on SAR time-series data and high-resolution remote sensing image data, respectively determine suspected crop planting areas and agricultural planting plots. Then, the distribution maps of the suspected crop planting areas and agricultural planting plots are overlaid to obtain a distribution map of suspected crop planting plots. Finally, based on the distribution map of suspected crop planting plots and time-series optical data, a distribution map of actual crop planting plots is determined. In this way, a more accurate distribution map of agricultural planting plots can be obtained through high-resolution remote sensing imagery, improving the accuracy of subsequent crop planting plot distribution map identification. Simultaneously, utilizing time-series variation information makes the identification of crop planting plots more consistent with natural and planting patterns, further improving the accuracy of planting plot distribution map identification. Attached Figure Description

[0023] Figure 1 This is a schematic diagram of the structure of the crop planting distribution plot identification system provided in the embodiments of this application;

[0024] Figure 2 This is a flowchart illustrating the method for identifying crop planting distribution plots provided in the embodiments of this application. Figure 1 ;

[0025] Figure 3 This is a flowchart illustrating the method for identifying crop planting distribution plots provided in the embodiments of this application. Figure 2 ;

[0026] Figure 4 This is a flowchart illustrating the method for identifying crop planting distribution plots provided in the embodiments of this application. Figure 3 ;

[0027] Figure 4 This is a flowchart illustrating the method for identifying crop planting distribution plots provided in the embodiments of this application.Figure 5 ;

[0028] Figure 6 is a schematic diagram of a feature time sequence curve provided by an embodiment of the present application;

[0029] Figure 7 is a schematic diagram of a slope change feature curve provided by an embodiment of the present application;

[0030] Figure 8 is a schematic diagram of a normalized vegetation index reconstruction curve provided by an embodiment of the present application;

[0031] Figure 9 is a schematic diagram of the composition structure of a crop planting distribution land parcel identification device provided by an embodiment of the present application;

[0032] Figure 10 is a schematic diagram of the composition structure of a crop planting distribution land parcel identification device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings, and the described embodiments should not be regarded as limiting the present application. All other embodiments obtained by those of ordinary skill in the art without making creative labor belong to the scope of protection of the present application.

[0034] In the following description, "some embodiments" are described, which describe a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. Unless otherwise defined, all technical and scientific terms used in the embodiments of the present application are the same as understood by those skilled in the art to which the embodiments of the present application belong. The terms used in the embodiments of the present application are only for the purpose of describing the embodiments of the present application, and are not intended to limit the present application.

[0035] In the related art, there are usually the following problems in the identification of crop planting distribution plots: 1) coarse classification and segmentation are performed on a single optical image, and because crops have different growth cycles, the optical image will show large spectral differences in the case of a large area to be measured, so that the accuracy of the coarse classification result and the accuracy of the crop identification object obtained by segmentation are greatly affected; 2) due to the influence of planting location, terrain and other factors, the growth cycle of the crops in the measured area often differs, such as the growth cycle of crops on the mountain and the growth cycle of crops on the mountain, which will differ by one month, such as the growth cycle of crops in flat areas and the growth cycle of crops in rugged areas, which will differ by half a month, resulting in a large difference in the key growth period, and the features on the image at the same time are not consistent, thereby directly leading to misjudgment when determining the key growth period features; 3) the key growth period features are obtained by random extraction, which has great uncertainty and randomness, and has a great influence on the accuracy of the identification result; 4) for sensitive features and key growth period features, machine learning methods are used for crop identification, but further processing of the identification result is not involved.

[0036] Based on the above at least one problem in the related art, the embodiments of the present application provide a crop planting distribution plot identification method, based on SAR time series data and high-resolution remote sensing image data, respectively determining a suspected crop planting area and an agricultural planting plot; then, the distribution map of the suspected crop planting area and the distribution map of the agricultural planting plot are superimposed to obtain a suspected crop planting plot distribution map; and then based on the suspected crop planting plot distribution map and time series optical data, a crop planting distribution plot distribution map is determined. In this way, the high-resolution remote sensing image can obtain a more accurate agricultural planting plot distribution map, improving the accuracy of subsequent crop planting distribution plot distribution map identification, and at the same time, using the change information on the time series also makes the identification of the crop planting distribution plot more in line with the natural law and planting law, further improving the identification accuracy of the planting distribution plot distribution map.

[0037] The following describes an exemplary application of the crop planting distribution plot recognition device of the embodiments of the present application. The crop planting distribution plot recognition device provided by the embodiments of the present application can be implemented as a terminal or a server. In one implementation, the crop planting distribution plot recognition device provided by the embodiments of the present application can be implemented as various types of terminals such as a notebook computer, a tablet computer, a desktop computer, a mobile device, etc. In another implementation, the crop planting distribution plot recognition device provided by the embodiments of the present application can also be implemented as a server. The server can be a standalone physical server, a server cluster composed of multiple physical servers, or a distributed system. The server can also be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and basic cloud computing services such as big data and artificial intelligence platforms, etc. The terminal and the server can be directly or indirectly connected through wired or wireless communication, which is not limited in the embodiments of the present application. In the following, an exemplary application of the crop planting distribution plot recognition device implemented as a server will be described.

[0038] participate Figure 1 , Figure 1 FIG. 1 is a structural schematic diagram of a crop planting distribution plot recognition system provided by the embodiments of the present application. To realize the recognition of the crop planting distribution plot, the embodiments of the present application can provide a crop planting distribution plot recognition platform, which can be implemented as a crop planting distribution plot recognition application. The crop planting distribution plot recognition system 10 provided by the embodiments of the present application includes a terminal 100, a network 200, and a server 300. The server 300 is a server of the crop planting distribution plot recognition application. The server 300 can constitute the crop planting distribution plot recognition device of the embodiments of the present application. The terminal 100 is connected to the server 300 through the network 200. The network 200 can be a wide area network or a local area network, or a combination of the two.

[0039] In some embodiments, please refer to Figure 1In the process of identifying the crop planting distribution plot, the terminal 100 sends remote sensing image data of the measured area to the server 300 through the network 200, wherein the remote sensing image data at least includes the following types of data: SAR time series data corresponding to the measured area, high-resolution remote sensing image data, and time series optical data. The server 300 determines the suspected crop planting area in the measured area based on the SAR time series data and in combination with the phenological characteristics of different crop planting sub-regions in the measured area; determines the agricultural planting plot in the measured area based on the high-resolution remote sensing image data; then, performs superposition processing on the distribution map of the suspected crop planting area and the distribution map of the agricultural planting plot to obtain a suspected crop planting plot distribution map; finally, determines the crop planting distribution plot distribution map based on the suspected crop planting plot distribution map and the time series optical data. After obtaining the crop planting distribution plot distribution map, the server 300 sends the planting distribution plot distribution map to the terminal through the network 200, so as to realize identification of the crop planting distribution plot.

[0040] The crop planting distribution plot identification method provided in the embodiments of the present application can also be realized based on a cloud platform and through cloud technology, for example, the server 300 described above can be a cloud server. The cloud server is used to determine the crop planting distribution plot distribution map.

[0041] It should be noted that the cloud technology refers to a hosting technology that unifies a series of resources such as hardware, software, and network to realize data calculation, storage, processing, and sharing in a wide area network or a local area network. The cloud technology is a general term of network technology, information technology, integration technology, management platform technology, and application technology applied based on a cloud computing business model, can form a resource pool, and is used on demand, flexibly and conveniently. The cloud computing technology will become an important support. The background service of a technical network system needs a large amount of calculation and storage resources, such as a video website, a picture website, and more portals. With the high development and application of the Internet industry, in the future, every item can have its own identification mark and needs to be transmitted to the background system for logical processing. Different levels of data will be processed separately, and the data of various industries needs strong system support, which can only be realized through cloud computing.

[0042] The embodiments of the present application provide a crop planting distribution plot identification method, which is shown in Figure 2 , Figure 2 is a flowchart of the crop planting distribution plot identification method provided in the embodiments of the present application Figure 1 , which will be described in combination with the steps shown in Figure 2 .

[0043] In step S201, SAR time series data, high-resolution remote sensing image data and time series optical data corresponding to the measured area are acquired.

[0044] In some embodiments, the seed plants of the measured area include, but are not limited to, any type of crops such as rice, wheat, rape, etc., and the embodiments of the present application can be used to identify the planting distribution plots of rice.

[0045] In some embodiments, the SAR (Synthetic Aperture Radar) is a high-resolution microwave imaging radar that uses the synthetic aperture principle, and has the characteristics of all-day, all-weather, high resolution, large swath, etc. The SAR is a coherent imaging radar system with high resolution. The SAR transmits energy to an object through an antenna, and also receives energy through the SAR. All the energy is recorded by electronic equipment, and finally an image is formed. The SAR time series data refers to a radar image data set formed in a time sequence at a high frequency within a certain period of time. The high-resolution remote sensing image data refers to a remote sensing image data set less than a certain accuracy, for example, the certain accuracy can be 5 meters. In the embodiments of the present application, since the plots of the measured area can be a region formed by a plurality of small area plots discontinuously distributed, the remote sensing image data set less than the certain accuracy can also be a remote sensing image data set less than 0.8 to 1 meter. The time series optical data refers to a time series optical remote sensing data set from a plurality of satellites.

[0046] In some embodiments, before acquiring the SAR time series data, high-resolution remote sensing image data and time series optical data of the measured area, the server can perform atmospheric correction and geometric correction on the SAR time series image data, high-resolution remote sensing image data and time series optical image data to improve the accuracy of the remote sensing image data. Here, the atmospheric correction refers to that the total radiation brightness of the ground target finally measured by the sensor is not a reflection of the true reflectivity of the ground surface, and includes radiation error caused by atmospheric absorption, especially scattering. Atmospheric correction is the process of eliminating the radiation error caused by atmospheric influence and retrieving the true surface reflectivity of the object. Geometric correction refers to correcting and eliminating the deformation of the original image caused by the inconsistency between the geometric position, shape, size, orientation, etc. of each object on the original image and the expression requirements in the reference system due to the deformation of the photographic material, lens distortion, atmospheric refraction, earth curvature, earth rotation, terrain undulation, etc.

[0047] In some embodiments, the server can acquire the SAR time series data, high-resolution remote sensing image data and time series optical data of the measured area input by the user, or the server can directly acquire the SAR time series data, high-resolution remote sensing image data and time series optical data of the measured area from the database.

[0048] Step S202, based on the SAR time series data, in combination with the phenological characteristics corresponding to the different crop phenological sub-regions in the measured region, determine the suspected crop planting area in the measured region.

[0049] In some embodiments, the crop phenological sub-region can be based on the regional attribute parameters of the measured region, and the geographical sub-region is developed by the agricultural production characteristics of local crops. Based on the above-mentioned regional attribute parameters, the measured region can be divided into a plurality of phenological sub-regions with relatively consistent growth cycle and key growth period, that is, divided into a plurality of crop phenological sub-regions. Here, the regional attribute parameters can include but are not limited to the following types of data, such as: topographic data, climate data and soil parent material data.

[0050] In some embodiments, the suspected crop planting area can be understood as the region most likely to plant crops obtained by the server after dividing the measured region based on the SAR time series data, that is, from the plurality of crop phenological sub-regions obtained by division, each crop phenological sub-region can select a suspected crop planting area and a non-crop planting area. Here, the suspected crop planting area can be part of one or more crop phenological sub-regions.

[0051] Step S203, based on high-resolution remote sensing image data, determine the agricultural planting plot from the measured region.

[0052] In some embodiments, the agricultural planting plot can be understood as the agricultural planting plot obtained by the server after dividing the measured region based on the high-resolution remote sensing image data, removing the regions that are obviously buildings, roads, forests, water and other objects.

[0053] Step S204, superimpose the distribution map of the suspected crop planting area and the distribution map of the agricultural planting plot to obtain the suspected crop planting plot distribution map.

[0054] In some embodiments, the suspected crop planting plot can be understood as a region with smaller area range, more accurate accuracy, clear plot boundary, and most likely to plant crops, relative to the suspected crop planting area.

[0055] In the embodiments of the present application, the server superimposes the distribution map of the suspected crop planting area and the distribution map of the agricultural planting plot to obtain a more accurate suspected crop planting plot distribution map. Superimposition refers to the superposition of the distribution map of the suspected crop planting area and the distribution map of the agricultural planting plot, and the superimposed part of the suspected crop planting area and the agricultural planting plot is determined as the suspected crop planting plot.

[0056] Step S205, determining the planting distribution plot distribution map of the crops based on the suspected crop planting plot distribution map and the time-series optical data.

[0057] In the embodiment of the present application, the server can determine the planting distribution plot distribution map of the crops based on the suspected crop planting plot distribution map and the time-series optical data obtained in step S204.

[0058] The method for identifying the planting distribution plot of the crops provided in the embodiment of the present application can determine the suspected crop planting area and the agricultural planting plot based on the SAR time-series data and the high-resolution remote sensing image data, respectively; then, the distribution map of the suspected crop planting area and the distribution map of the agricultural planting plot are superimposed to obtain the suspected crop planting plot distribution map; and then, the planting distribution plot distribution map of the crops is determined based on the suspected crop planting plot distribution map and the time-series optical data. In this way, the distribution map of the agricultural planting plot can be obtained more accurately by using the high-resolution remote sensing image, the accuracy of the subsequent identification of the planting distribution plot distribution map of the crops is improved, and at the same time, the identification of the planting distribution plot of the crops is more in line with the natural law and the planting law by using the change information in the time sequence, and the identification accuracy of the planting distribution plot distribution map is further improved.

[0059] In some embodiments, before the SAR time-series data, the high-resolution remote sensing image data and the time-series optical data corresponding to the measured region are obtained, the measured region can be divided into a plurality of crop planting candidate sub-regions based on the regional attribute parameters of the measured region, so as to ensure that each crop planting candidate sub-region has relatively consistent growth periods and key growth periods, for example, each crop planting candidate sub-region has relatively consistent transplanting periods, sowing periods, earing periods and maturing periods, etc. Based on the foregoing embodiment, the present embodiment provides a method for identifying the planting distribution plot of the crops, which can be executed by a server, Figure 3 is a flowchart of the method for identifying the planting distribution plot of the crops provided in the embodiment of the present application Figure 2 As shown in Figure 3 Before step S201 is executed, steps S301 to S302 can also be executed.

[0060] Step S301, the server obtains the regional attribute parameters of the measured region, wherein the regional attribute parameters include: topographic data, climate data and soil parent material data.

[0061] In some embodiments, the terrain data refers to data capable of representing the ups and downs of the earth's surface, i.e., data with elevation information. The climate data refers to data capable of representing the state of environmental climate change, i.e., data with temperature information. The soil parent material refers to loose detritus formed after rock weathering, which is the source of soil minerals, and its mineral composition, chemical composition and mechanical composition (particle size) affect the formation and properties of soil.

[0062] In step S302, the server divides the measured area into a plurality of crop species phenophase sub-zones based on the area attribute parameters.

[0063] In some embodiments, first, the server extracts two different height contour lines from the obtained terrain data according to the influence of elevation on temperature, etc., thereby dividing the measured area into three elevation intervals; second, the server calculates the effective annual accumulated temperature and the average temperature in combination with the daily meteorological data of many years, extracts the effective annual accumulated temperature line of the minimum effective accumulated temperature of crops and the isotherm line of the minimum temperature for transplanting crops, and uses the effective annual accumulated temperature line and the isotherm line as the basis for phenophase sub-zoning; finally, the sub-zoning map based on terrain data, the sub-zoning map based on climate data and the sub-zoning map based on soil parent material data are superimposed, thereby obtaining the sub-zoning map of the plurality of crop species phenophase sub-zones after division.

[0064] In some embodiments, the effective annual accumulated temperature refers to the total of the daily average temperature during the period when the daily average temperature is ≥10℃ within a year, i.e., the total of the active temperature.

[0065] In the embodiments of the present application, the measured area is divided into crop species phenophase sub-zones based on area attribute parameters, which directly utilizes crop growth environment factors (temperature, heat and soil) to divide a large range of measured areas, so that the planting and growth process of crops in the small areas after division is basically consistent, avoiding the precision of crop planting distribution plots caused by spectral differences due to crops in different growth periods.

[0066] Please continue to refer to Figure 3 In some embodiments, step S202 can be implemented by steps S303 to S307:

[0067] In step S303, the server obtains SAR time series data of each crop species phenophase sub-zone in the plurality of crop species phenophase sub-zones.

[0068] In the embodiments of the present application, for crop species phenophase sub-zones with different growth cycles and key growth periods, the server can obtain SAR time series data of crop species phenophase sub-zones in the same growth cycle and key growth period.

[0069] In step S304, the server determines the backscattering coefficient feature corresponding to each pixel in each crop plant growth subzone at each time point based on the SAR time series data of each crop plant growth subzone.

[0070] In some embodiments, a pixel refers to the minimum unit of the sensor scanning and sampling the ground scene when the server performs SAR time series data collection (e.g., scanning imaging). In digital image processing, a pixel is a sampling point when scanning and digitizing an analog image, is a basic unit of a remote sensing digital image, and is a sampling point in the remote sensing imaging process.

[0071] In the embodiments of the present application, the server calculates the backscattering coefficient feature corresponding to each time point based on the SAR time series data obtained above. The process of calculating the backscattering coefficient feature corresponding to each time point will be explained in detail below.

[0072] In step S305, the server constructs a feature time series curve of all pixels in each crop plant growth subzone based on the backscattering coefficient feature corresponding to each time point.

[0073] In some embodiments, the server can represent the backscattering coefficient feature corresponding to each time point in a graph with the growth time axis as the horizontal coordinate and the backscattering coefficient as the vertical coordinate. Since the instability of remote sensing data may cause fluctuations to a certain extent in actual applications, filtering and smoothing processing is performed. Here, the Savizky-Glolay filter fitting method can be used for filtering and smoothing processing, so as to obtain a relatively accurate feature time series curve. In general, in order to ensure the continuity and integrity of the SAR time series data, the abnormal points in the SAR time series data can be filtered and smoothed, so as to obtain a feature time series curve that conforms to the actual growth law of crops.

[0074] In some embodiments, the Savizky-Glolay filter fitting method can effectively remove noise and improve the quality of the SAR time series data, while retaining the key growth periods and growth cycles within the crop growth period.

[0075] In step S306, the server determines the suspected crop planting pixels in each crop plant growth subzone based on the feature time series curve.

[0076] In step S307, the server determines a planting area formed by a plurality of adjacent suspected crop planting pixels as a suspected crop planting area.

[0077] In some embodiments, the step S307 can be implemented by the following manner: first, the server determines the slope change feature corresponding to each feature time series curve, and the server acquires a preset slope change threshold. Then, the server determines each pixel with the slope change feature greater than the slope change threshold as a suspected crop planting pixel.

[0078] Here, the slope change of the feature time series curve can be represented by the slope k of the tangent line at any time point on the feature time series curve. For any straight line L, the slope formula of the straight line L can be: k = (y2-y1) / (x2-x1). If the straight line L is perpendicular to the x-axis, the tangent value of the right angle is infinite, so the straight line L does not exist the slope; when the slope of the straight line L exists, for a linear function y = kx + b (slope intercept form), k is the slope of the function image (straight line). That is, the slope change feature corresponding to the feature time series curve can be the difference between the curve slope at the next time point and the curve slope at the previous time point, that is, the slope change feature is k2-k1.

[0079] In some embodiments, the server can acquire a pre-stored slope change threshold, compare the acquired slope change feature with the slope change threshold, and determine the suspected crop planting area. Here, the crop planting area with the slope change feature greater than the slope change threshold can be determined as the suspected crop planting area.

[0080] In some embodiments, the agricultural planting plot can be obtained based on the high-resolution remote sensing image data. Based on the foregoing embodiments, the present embodiment provides a crop planting distribution plot identification method, which can be executed by a server, Figure 4 is a flowchart of the crop planting distribution plot identification method provided by the present embodiment Figure 3 As shown in Figure 4 , the step S203 can be implemented by the following steps S401 to S403:

[0081] Step S401, the server extracts plot boundary information in the measured area based on the high-resolution remote sensing image data. In some embodiments, the plot boundary information refers to the polygon vector graph of the boundary of the crop forming the plot. Here, the extraction of the plot boundary information refers to the extraction of the edge line by using the edge, texture and other features of the plot on the remote sensing image. In actual application, the extraction of the plot boundary information can be performed by using a model with deep learning, which includes main steps such as sample labeling, model training, and edge feature extraction.

[0082] Step S402, the server constructs a polygon vector graph of the measured area based on the plot boundary information.

[0083] Step S403, the server determines the agricultural planting plot from the measured area based on the polygon vector map.

[0084] Please continue to refer to Figure 4 In some embodiments, step S205 can be implemented by the following steps S404 to step S405:

[0085] Step S404, the server superimposes the suspected crop planting plot distribution map and the image corresponding to the time-series optical data to obtain the plot time-series curve of the plot feature of each suspected crop planting plot changing over time.

[0086] Step S405, the server determines the planting distribution plot of the crop based on the plot time-series curve.

[0087] In some embodiments, the plot feature can be any one of the normalized vegetation index, the enhanced vegetation index, and the spectral value of the pixel. Of course, it can also be other forms of vegetation index, and the embodiments of the present application do not make specific limitations thereto.

[0088] In some embodiments, the above-obtained distribution map of the suspected crop planting area and the distribution map of the agricultural planting plot are superimposed and processed, and through spatial statistics, when more than 50% of the area in a plot polygon is determined to be a suspected crop planting area, the plot is marked as a suspected crop planting plot. Finally, through attribute screening, a distribution map of suspected crop planting plots is obtained. Here, attribute screening refers to adding an attribute identification field in the vector layer, which is used to identify whether more than 50% of the area in the polygon plot is a suspected crop planting area. For the plot in which more than 50% of the area is a suspected crop planting area, the attribute value of the plot is marked as 1, and for the plot in which 50% of the area is not a suspected crop planting area, the attribute value of the plot is marked as 0. Then, through spatial statistics of the marked attribute value, the polygon plot marked as 1 in the attribute identification field is determined as a suspected crop planting plot.

[0089] In some embodiments, the above step S405 can be implemented in the following way:

[0090] First, the server obtains the sample time-series curve of the crop from the sample data set. Then, the server determines the curve similarity between the plot time-series curve of each suspected crop planting plot and the sample time-series curve. Then, the server determines the suspected crop planting plot with a curve similarity greater than a similarity threshold as the planting distribution plot of the crop. Finally, the server constructs the planting distribution plot distribution map based on the planting distribution plot of the crop.

[0091] Here, the sample data set refers to a data set storing a plurality of sample time series curves. The sample time series curve can be a characteristic time series curve corresponding to a manually collected sample, or a characteristic time series curve corresponding to a plot with the highest confidence in historical data. Of course, the sample time series curve can also be determined by other means, which is not limited in the embodiments of the present application.

[0092] In some embodiments, the similarity can be determined by a specific algorithm. In general, the server can determine the similarity between the plot time series curve and the sample time series curve according to the best alignment curve between the plot time series curve and the sample time series curve. The server can directly obtain the standard curve of the normalized difference vegetation index (NDVI) and the enhanced vegetation index (EVI) of the crop sample. Then, the similarity between the plot time series curve and the sample time series curve can be determined by squaring the normalized difference vegetation index time series of each suspected crop planting plot and the standard normalized difference vegetation index time series of the crop sample, adding the enhanced vegetation index time series of each suspected crop planting plot and the standard enhanced vegetation index of the crop sample, and multiplying by the negative power of 2. After determining the similarity between the plot time series curve and the sample time series curve, the similarity is compared with the preset similarity threshold, and each suspected crop planting plot with a similarity greater than the similarity threshold is determined as a crop planting distribution plot.

[0093] In some embodiments, when the server determines the crop planting distribution plot, the curve similarity of each suspected crop planting plot obtained before can be used as the confidence of each suspected crop planting plot. At the same time, the confidence is compared with the preset confidence threshold, and each suspected crop planting plot with a confidence greater than the confidence threshold is determined as an expansion sample. Finally, the plot time series curve corresponding to the expansion sample is added to the sample data set.

[0094] In the embodiments of the present application, based on the similarity analysis of the characteristic time series curve, automatic expansion of the sample can be realized, which can greatly reduce the workload of manual collection and speed up the iterative optimization efficiency of the crop planting distribution plot recognition device. At the same time, the change trend of the characteristics of the crop on the remote sensing image over time (i.e., the characteristic time series curve) also shows the growth process of the crop and the phenological characteristics of the crop. That is, the similarity of the characteristic time series curve can represent the probability that each suspected crop planting plot is a crop, i.e., the plot with high similarity of the characteristic time series curve can be used as a crop sample, and the plot with low similarity of the characteristic time series curve needs to be verified.

[0095] Below, an exemplary application of the embodiments of the present application in an actual application scenario will be described.

[0096] The embodiments of the present application provide a rice planting distribution plot identification method, which is executed by a server, Figure 5 is a flowchart of the rice planting distribution plot identification method provided by the embodiments of the present application Figure 4 As shown in Figure 5 , the embodiments of the present application will be described in combination with the flowchart shown in Figure 5 .

[0097] In step S501, the server performs phenological zoning on the measured area based on the terrain data 501, the climate data 502 and the soil parent material data 503, and determines a distribution map 504 of the rice phenological zoning.

[0098] In some embodiments, the server can perform phenological zoning on the measured area based on the regional terrain data, the climate data and the soil parent material data, and the local rice agricultural production characteristics, and divide the measured area into multiple rice phenological zoning. Each rice phenological zoning has a consistent growth cycle and key growth period, such as the period of soaking the field, transplanting and harvesting.

[0099] In some embodiments, first, the server can use the terrain data to extract the 400-meter and 900-meter contour lines according to the influence of elevation on temperature, etc., so as to divide the measured area into three elevation intervals of 400 meters or less, 400 to 900 meters, and 900 or more; second, in combination with the daily meteorological data of multiple years (10 years of data are currently used), the effective annual accumulated temperature and the average temperature of ≥10 degrees Celsius are calculated, and the 2000-degree effective accumulated temperature line and the 15-degree isotherm line are extracted; finally, the distribution map of the terrain zoning, the distribution map of the accumulated temperature zoning, the distribution map of the average temperature zoning and the distribution map of the soil parent material zoning are superimposed to determine the rice phenological zoning map.

[0100] In step S502, the distribution map 506 of the suspected rice planting area is determined based on the SAR time series data 505.

[0101] ​In some embodiments, first, for different periods of rice plant candidate sub-zones, such as rice seedling period and transplanting period, the server can directly select the SAR time series data of the rice plant candidate sub-zone of the corresponding period; then, the server can calculate the backscattering coefficient feature corresponding to each time point SAR time series data; then, based on the backscattering coefficient features of multiple time points at the same location, a time series curve of the backscattering coefficient features is constructed; then, the slope change feature of the feature time series curve is calculated; finally, the slope change feature is compared with the slope change threshold to extract the significant feature that the feature time series curve of the backscattering coefficient feature before and after rice transplanting presents a downward-upward V shape, and then when the significant feature of the downward-upward V shape appears, the server determines the crop plant candidate sub-zone with the slope change feature greater than the slope change threshold as a suspected crop planting area.

[0102] In order to facilitate understanding of the feature time series curve, Figure 6 Further explanation is made, Figure 6 is a schematic diagram of the feature time series curve of the embodiments of the present application. As Figure 6 shown, the feature time series curves of single-crop rice, double-crop rice, urban and rural areas, forests and grasslands, corn and soybeans, cotton and peanuts, vegetables, aquaculture and water are shown in the figure.

[0103] Please continue to refer to Figure 6 , the arrow in the figure marks the significant feature of the downward-upward V shape of single-crop rice in the seeding and transplanting period. The feature time series curve before and after the rice seeding and transplanting period presents the significant feature of the downward-upward V shape, which is mainly due to the existence of the seedling period in the rice planting process and a large amount of water after transplanting. Then, when determining the backscattering coefficient feature based on the SAR time series data, the current backscattering coefficient feature value will be significantly reduced when encountering water signals; when the water signal decreases, the current backscattering coefficient feature will be significantly increased, so the feature of the downward-upward V shape is formed.

[0104] In some embodiments, the curve slope change feature of the feature time series curve is usually used to determine the downward-upward V shape feature of the feature time series curve, and the plot with this downward-upward V shape feature is determined as a suspected rice planting area.

[0105] In some embodiments, the server can correspond to the backscattering coefficient feature at each time point, characterized in a curve graph with the growth time axis as the horizontal coordinate and the backscattering coefficient as the vertical coordinate. Due to the instability of remote sensing data in actual application, a certain degree of fluctuation will occur, and therefore filtering and smoothing processing will be performed to obtain a more accurate feature time sequence curve. Generally, in order to ensure the continuity and integrity of the SAR time sequence data, the abnormal points in the SAR time sequence data can be filtered and smoothed to obtain a feature time sequence curve in line with the actual growth law of crops.

[0106] In order to facilitate the understanding of the slope change feature curve, Figure 7 This is further explained and described, Figure 7 is a schematic diagram of the slope change feature curve of the embodiments of the present application.

[0107] As shown in the figure, the slope change trend of the feature time sequence curve can be described by the slope k of the tangent line at any time point on the feature time sequence curve. For any straight line L, the slope formula of the straight line L can be: k=(y2-y1) / (x2-x1). If the straight line is perpendicular to the x-axis, the tangent value of the right angle is infinite, and therefore the slope of the straight line does not exist; when the slope of the straight line exists, for a linear function y=kx+b (slope-intercept form), k is the slope of the function image (straight line). Then, the slope difference of the feature time sequence curve is the difference between the slope of the curve at the next time point (for example, the slope of the point corresponding to June 10 on the feature time sequence curve) and the slope of the curve at the previous time point (for example, the slope of the point corresponding to May 10 on the feature time sequence curve): k2-k1.

[0108] In step S503, the distribution map of the agricultural planting plot is determined based on the high-resolution remote sensing image data 507.

[0109] In the embodiments of the present application, the server first extracts the boundary information of the agricultural planting plot based on the high-resolution remote sensing image data by using the visual deep learning method, determines the distribution map of the agricultural planting plot, and then superimposes the distribution map of the agricultural planting plot and the distribution map of the suspected rice planting area to determine the distribution map of the suspected rice planting plot.

[0110] In some embodiments, first, the server extracts the boundary information of the agricultural planting plot based on the high-resolution remote sensing image with a resolution less than 1 meter by using the semantic segmentation method of machine vision, such as the U-NET, VGC16, etc. model; second, the vectorization processing and post-processing tool are used to obtain the distribution map of the agricultural planting plot. Here, semantic segmentation refers to labeling each point in the target class of the image according to "semantics", so that different kinds of things are distinguished on the image, which can be understood as a pixel-level classification task.

[0111] Step S504, superimposes the suspected rice planting area distribution map 506 and the agricultural planting plot distribution map 508 to determine a suspected rice planting plot distribution map 509.

[0112] In some embodiments, the distribution map of the suspected rice planting area obtained in step S502 is superimposed with the distribution map of the agricultural planting plot, and through spatial statistics, when more than 50% of the area in a plot polygon is determined to be a suspected crop planting area, the plot is marked as a suspected crop planting plot. Finally, through attribute screening, a suspected rice planting plot distribution map is obtained. Here, the boundary information extraction refers to extracting the edge property using the edge, texture and other characteristics of the plot on the remote sensing image. Generally, some models with deep learning can be used to extract the boundary information of the plot. Here, attribute screening refers to adding an attribute identification field in the vector layer, which is used to identify whether there is an area with more than 50% of the area in the polygon plot as a suspected crop planting area. For the plot with more than 50% of the area in the polygon plot as a suspected crop planting area, the attribute value of the plot is marked as 1. For the plot without more than 50% of the area in the polygon plot as a suspected crop planting area, the attribute value of the plot is marked as 0. Finally, through spatial statistics of the attribute value marked, the polygon plot with the attribute identification field marked as 1 is determined as the suspected crop planting plot.

[0113] Step S505, determines a rice planting distribution plot distribution map 511 based on the suspected rice planting plot 509 and the time-series optical data 510.

[0114] In the embodiments of the present application, the suspected rice planting plot is taken as a unit, and based on the time-series optical data, the rice planting distribution plot is extracted by constructing the time-series curve of the plot, calculating the similarity between the time-series curve of each plot and the sample time-series curve through the dynamic time warping algorithm, and the like.

[0115] In some embodiments, first, the spectral values and feature values (e.g., normalized difference vegetation index NDVI, enhanced vegetation index EVI, etc.) of the pixels completely within the polygon are calculated by superimposing the remote sensing image corresponding to each period on the constraint condition of the polygon of the suspected rice planting plot; second, the feature curve of each unit changing over time, i.e., the plot time curve, is constructed by taking the suspected rice planting plot as a unit; then, the curve is filtered and smoothed by using the Savizky-Glolay filter fitting method; finally, the similarity between the plot time curve and the sample time curve is calculated by using the dynamic time warping algorithm (DTW, Dynamic Time Warping), and the obtained similarity is compared with the preset similarity threshold to determine the suspected crop planting plot. Here, the suspected rice planting plot with a similarity greater than the similarity threshold can be determined as the rice planting distribution plot.

[0116] Here, the dynamic time warping algorithm DTW is an algorithm that can calculate the similarity between the plot time curve and the sample time curve according to the best alignment curve between the plot time curve and the sample time curve. That is, the DTW distance between each suspected rice planting plot and the standard curve of the normalized difference vegetation index NDVI or the enhanced vegetation index EVI can be calculated, as shown in formula (1), and each suspected rice planting plot with a DTW distance higher than the preset DTW distance threshold can be determined as the rice planting distribution plot.

[0117]

[0118] wherein NDVI s1 , EVI s1 are the NDVI and EVI time series of each suspected rice planting plot, NDVI s2 , EVI s2 are the standard NDVI and EVI time series of the rice sample.

[0119] In order to facilitate the understanding of the normalized difference vegetation index reconstruction curve, Figure 8 which is further explained, Figure 8 is a schematic diagram of the normalized difference vegetation index reconstruction curve of the embodiments of the present application. As shown in the figure, the normalized difference vegetation index observation value, the key time phase point of the normalized difference vegetation index, and the normalized difference vegetation index reconstruction curve are shown in the figure.

[0120] In some embodiments, the server can correspond the normalized vegetation index features of each point to a curve graph with the growth time axis as the horizontal coordinate and the normalized vegetation index as the vertical coordinate. Due to the instability of remote sensing data in actual application, a certain degree of fluctuation will occur, and thus filtering and smoothing processing is performed to obtain a more accurate normalized vegetation index curve. Generally, in order to ensure the continuity and integrity of multi-source time-series optical data, the abnormal points in the multi-source time-series optical data can be filtered and smoothed to obtain a normalized vegetation index curve in line with the actual growth law of crops.

[0121] In some embodiments, the server determines a rice planting plot as a plot whose similarity between the time-series curve samples is greater than a similarity threshold, and outputs the similarity as a confidence of rice. Then, the plot with high confidence is added to the sample dataset as an expanded sample, which, together with the manually collected sample input, can be used for iteration of the model and optimization of the result.

[0122] In the embodiments of the present application, high-resolution remote sensing images can realize the characterization of geographic object monomers. By using the spectral, texture and edge features of the images, the boundary information of agricultural planting can be accurately extracted to form a smaller range of geographic analysis objects, i.e., plots. Compared with the plots obtained by using segmentation methods, the plots extracted by the embodiments of the present application are more accurate, which can ensure that the same type of crops is in the unit and effectively reduces the problem of reduced accuracy due to mixed pixels and other factors in subsequent analysis. In the embodiments of the present application, on the basis of the rice planting phenophase partition, the time interval of the key development period of the rice transplanting, development and harvesting in each rice planting phenophase partition becomes a kind of prior data, which can be used to analyze the time-series images in the key recognition time period according to the rice planting phenophase partition. For example, the rice transplanting in the plain area is completed in March to April, while the rice transplanting in the area with higher altitude is completed in late April to May. The SAR time-series images corresponding to the time period can be selected to capture important features in the key period of transplanting, which greatly reduces the mixed partition of crops with similar features at different time points and the misclassification of rice due to phenological differences.

[0123] Figure 9 is a schematic diagram of the composition structure of the crop planting distribution plot recognition device provided by the embodiments of the present application, as shown in Figure 9As shown, the crop planting distribution plot identification device 900 comprises: an acquisition module 901 configured to acquire SAR time series data, high-resolution remote sensing image data and time series optical data corresponding to a measured area; a determination module 902 configured to determine a suspected crop planting area in the measured area based on the SAR time series data and in combination with the phenological characteristics of different crop phenological sub-regions in the measured area; the determination module 902 is further configured to determine an agricultural planting plot in the measured area based on the high-resolution remote sensing image data; a superposition module 903 configured to perform superposition processing on a distribution map of the suspected crop planting area and a distribution map of the agricultural planting plot to obtain a suspected crop planting plot distribution map; and the determination module 902 is further configured to determine a crop planting distribution plot distribution map based on the suspected crop planting plot distribution map and the time series optical data.

[0124] In some embodiments, the crop planting distribution plot identification device further comprises a division module configured to acquire regional attribute parameters of the measured area, wherein the regional attribute parameters comprise topographic data, climate data and soil parent material data; and divide the measured area into a plurality of crop phenological sub-regions based on the regional attribute parameters.

[0125] In some embodiments, the determination module is further configured to acquire SAR time series data of each crop phenological sub-region of the plurality of crop phenological sub-regions; determine a backscattering coefficient feature corresponding to each pixel in each time point in each crop phenological sub-region based on the SAR time series data of each crop phenological sub-region; construct a feature time series curve of all pixels in each crop phenological sub-region based on the backscattering coefficient feature corresponding to each time point; determine a suspected crop planting unit from each crop phenological sub-region based on the feature time series curve; and determine a planting area composed of a plurality of adjacent suspected crop planting units as a suspected crop planting area.

[0126] In some embodiments, the determination module is further configured to determine a slope change feature corresponding to each feature time series curve; acquire a preset slope change threshold; and determine each pixel with a slope change feature greater than the slope change threshold as a suspected crop planting pixel.

[0127] In some embodiments, the determination module is further configured to extract plot boundary information in the measured area based on the high-resolution remote sensing image data; construct a polygon vector map of the measured area based on the plot boundary information; and determine the agricultural planting plot in the measured area based on the polygon vector map.

[0128] In some embodiments, the suspected crop planting plot distribution map includes a plurality of suspected crop planting plots; the determination module is further configured to superimpose the suspected crop planting plot distribution map and the image corresponding to the time-series optical data to obtain a plot time-series curve of a plot feature of each suspected crop planting plot changing over time; and determine the planting distribution plot distribution map of the crop based on the plot time-series curve.

[0129] In some embodiments, the determination module is further configured to obtain a sample time-series curve of the crop from a sample data set; determine a curve similarity between the plot time-series curve of each suspected crop planting plot and the sample time-series curve; determine a suspected crop planting plot with a curve similarity greater than a similarity threshold as the planting distribution plot of the crop; and construct the planting distribution plot distribution map based on the planting distribution plot of the crop.

[0130] In some embodiments, the crop planting distribution plot identification apparatus further includes an adding module configured to determine the curve similarity of each suspected crop planting plot as a confidence level when the suspected crop planting plot is identified; determine a suspected crop planting plot with a confidence level greater than a confidence level threshold as an expanded sample; and add a plot time-series curve corresponding to the expanded sample to the sample data set.

[0131] It should be noted that the description of the device embodiments of the present application is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments, and thus is not described in detail. For technical details not disclosed in the device embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

[0132] It should be noted that in the embodiments of the present application, if the crop planting distribution plot identification method described above is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions for causing a terminal to execute all or part of the method described in the embodiments of the present application. The storage medium described above includes: a U disk, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk, and various storage media that can store program codes. Thus, the embodiments of the present application are not limited to any specific hardware and software combination.

[0133] Correspondingly, the embodiments of the present application provide a crop planting distribution plot identification device, Figure 10is a component structure schematic diagram of a crop planting distribution plot recognition device provided by an embodiment of the present application, as shown in Figure 10 The crop planting distribution plot recognition device 1000 at least includes a processor 1001 and a computer readable storage medium 1002 configured to store executable instructions, wherein the processor 1001 generally controls the overall operation of the crop planting distribution plot recognition device. The computer readable storage medium 1002 is configured to store instructions and applications executable by the processor 1001, and can also cache data to be processed by the processor 1001 and various modules in the crop planting distribution plot recognition device 1000, and can be implemented by FLASH or Random Access Memory (RAM).

[0134] An embodiment of the present application provides a storage medium storing executable instructions, wherein the executable instructions, when executed by a processor, cause the processor to perform the method provided by an embodiment of the present application, for example, the method shown in Figure 2 .

[0135] In some embodiments, the storage medium can be a computer readable storage medium, for example, a Ferroelectric Memory (FRAM), a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Programmable Read Only Memory (E PROM), an Electrically Erasable Programmable Read Only Memory (EEPR OM), a flash memory, a magnetic surface memory, an optical disc, or a Compact Disk-Read Only Memory (CD-ROM), etc. It can also be various devices including one or any combination of the above storage medium.

[0136] In some embodiments, the executable instructions can be in the form of a program, software, software module, script or code, written in any form of programming language (including a compiled or interpreted language, or a declarative or procedural language), and can be deployed in any form, including being deployed as a standalone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0137] By way of example, an executable instruction can be, but is not limited to, a file, a part of a file, containing high level code, a lower level code, or even machine code that can be stored as an object in a file system or in a memory. The executable instructions can be stored in a file or files that are stored in a memory of a computer, a server, a client, a database, etc. The executable instructions can be executed by a processor of a computer, a server, a client, a database, etc. The executable instructions can be deployed to execute on one electronic device, or on multiple electronic devices located at one site, or on multiple electronic devices distributed across multiple sites and interconnected through a communication network.

[0138] The above merely provides an example, but does not limit the protective scope of the present application. Any modification, equivalent replacement, and improvement made within the spirit and scope of the present application shall fall into the protective scope of the present application.

[0139] It should be understood that the description of "one embodiment" or "an embodiment" throughout the specification means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing in various places throughout the specification does not necessarily refer to the same embodiment. In addition, these particular features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that the sequence of the above-mentioned processes does not mean the execution order in various embodiments of the present application. The execution order of the processes should be determined according to the function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages or disadvantages of the embodiments.

[0140] It should be noted that, in this document, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements, but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without more limitations, the element defined by the statement "comprises a" does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element. In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The above-described device embodiments are only illustrative, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0141] The above merely provides the implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of the change or replacement within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for identifying crop planting distribution plots, characterized by, The method comprises: obtaining SAR time series data, high-resolution remote sensing image data and time series optical data corresponding to the measured area; obtaining SAR time series data of each crop plant candidate subzone in a plurality of crop plant candidate subzones; determining the backscattering coefficient feature of each pixel in the crop plant candidate subzone at each time point based on the SAR time series data of each crop plant candidate subzone; constructing a feature time series curve of all pixels in each crop plant candidate subzone based on the backscattering coefficient feature corresponding to each time point; determining the slope change feature corresponding to each feature time series curve; obtaining a preset slope change threshold; determining each pixel with a slope change feature greater than the slope change threshold as a suspected crop planting pixel; determining a planting area composed of a plurality of adjacent suspected crop planting pixels as a suspected crop planting area; determining an agricultural planting plot from the measured area based on the high-resolution remote sensing image data; superimposing the distribution map of the suspected crop planting area and the distribution map of the agricultural planting plot to obtain a suspected crop planting plot distribution map; the suspected crop planting plot distribution map includes a plurality of suspected crop planting plots; superimposing the suspected crop planting plot distribution map and the image corresponding to the time series optical data to obtain a plot time series curve of the plot feature of each suspected crop planting plot changing with time; determining the planting distribution plot distribution map of the crop based on the plot time series curve.

2. The method of claim 1, wherein, Before obtaining the SAR time series data, high-resolution remote sensing image data and time series optical data corresponding to the measured area, the method further comprises: obtaining regional attribute parameters of the measured area, wherein the regional attribute parameters include topographic data, climate data and soil parent material data; dividing the measured area into a plurality of crop plant candidate subzones based on the regional attribute parameters.

3. The method of claim 1, wherein, The method further comprises: extracting plot boundary information in the measured area based on the high-resolution remote sensing image data; constructing a polygon vector map of the measured area based on the plot boundary information; determining the agricultural planting plot from the measured area based on the polygon vector map.

4. The method of claim 1, wherein, The method further comprises: obtaining a sample time series curve of the crop from a sample data set; determining the curve similarity between the plot time series curve of each suspected crop planting plot and the sample time series curve; determining the suspected crop planting plot with a curve similarity greater than a similarity threshold as the planting distribution plot of the crop; constructing the planting distribution plot distribution map based on the planting distribution plot of the crop.

5. The method of claim 4, wherein, The method further comprises: determining the curve similarity of each suspected crop planting plot as the confidence degree when the suspected crop planting plot is identified; determining the suspected crop planting plot with a confidence degree greater than a confidence degree threshold as an expanded sample. Add the extended sample corresponding plot time curve to the sample data set.

6. A device for identifying the distribution of crop planting areas, characterized in that, The device comprises: An acquisition module is configured to acquire SAR time series data, high-resolution remote sensing image data, and time series optical data corresponding to a measured area. The determination module is configured to acquire SAR time series data of each crop plant candidate sub-region in a plurality of crop plant candidate sub-regions; determine a backscattering coefficient feature corresponding to each pixel in each crop plant candidate sub-region at each time point based on the SAR time series data of each crop plant candidate sub-region; construct a feature time curve of all pixels in each crop plant candidate sub-region based on the backscattering coefficient feature corresponding to each time point; determine a slope change feature corresponding to each feature time curve; acquire a preset slope change threshold; determine each pixel with a slope change feature greater than the slope change threshold as a suspected crop planting pixel; and determine a planting area composed of a plurality of adjacent suspected crop planting pixels as a suspected crop planting area. The determination module is further configured to determine an agricultural planting plot from the measured area based on the high-resolution remote sensing image data. A superposition module is configured to superimpose a distribution map of the suspected crop planting area and a distribution map of the agricultural planting plot to obtain a suspected crop planting plot distribution map; and the suspected crop planting plot distribution map includes a plurality of suspected crop planting plots. The determination module is further configured to superimpose the suspected crop planting plot distribution map and an image corresponding to the time series optical data to obtain a plot time curve of a plot feature change over time of each suspected crop planting plot; and determine a crop planting distribution plot distribution map based on the plot time curve.

7. A device for identifying the distribution of crop planting areas, characterized in that, The device comprises: A memory is configured to store executable instructions; A processor is configured to execute the executable instructions stored in the memory to implement the crop planting distribution plot identification method in any one of claims 1 to 5.

Images