Remote sensing identification method and device for irrigated land

Abstract

The invention provides a remote sensing identification method for a irrigated field. The method comprises the following steps: inverting soil moisture of a target date according to a backscattering value of a pixel point; acquiring an average value of soil moisture in a set range around the pixel points; and obtaining a difference value between the soil moisture of the pixel point and the average value, and determining that the pixel point with the difference value greater than a first set threshold is irrigated. The invention further provides a device for implementing the method. The problem that errors are introduced due to the fact that irrigated land recognition through the remote sensing technology is affected by climate and environment is solved.

Description

Technical Field

[0001] The present application relates to the field of earth remote sensing technology, and in particular to a method and device for remote sensing identification of irrigated land. Background Art

[0002] Irrigated agriculture is crucial to ensuring food production. Although irrigated agriculture accounts for only 20% of global agriculture, it provides 40% of global food production. In order to assess the impact of irrigation on the environment and manage water resources, it is necessary to understand the quantity and spatial distribution of irrigated land. In addition, due to climate change and population growth, the demand for agricultural production continues to increase, which further expands the demand for irrigated land detection.

[0003] Remote sensing technology provides a technical method for mapping irrigated land. Microwave remote sensing is less affected by clouds and fog and has the advantages of working in all weather and all day. However, there are relatively few studies on mapping irrigated land using microwave remote sensing. In addition, since irrigated land is relatively discrete in spatial distribution and varies in size, it is more difficult to map irrigated land based on satellite microwave remote sensing data.

[0004] Common irrigated land mapping methods based on remote sensing technology include: Based on optical multi-band classification method, for example, using Landsat data and the aid of water conservancy facilities distribution data to identify irrigated areas, or using time series MODIS (Moderate resolution imagingspectroradiometer) data and decision tree method to generate surface classification map and irrigated land distribution map.

[0005] Based on the vegetation index method, for example, the time signal difference of vegetation indices such as Normalized Differential Vegetation Index (NDVI), Normalized Differential Water Index (NDWI) and Green Vegetation Index (GVI) is used to classify irrigated land and dry land.

[0006] Radar-based methods: For example, using radar data such as TerraSAR-X and Sentinel-1, combined with neural networks, deep learning and other methods, the model is trained through data, and then the trained model is used to map irrigated land.

[0007] Existing methods use multi-band information from optical images or vegetation indices calculated from different bands to identify irrigated land, which is easily affected by clouds and fog. Radar-based methods have all-day and all-weather observation capabilities, but usually require the combination of machine learning methods such as neural networks and random forests, and require a large amount of measured data to train the model, which is not conducive to the promotion of the method. In addition, most methods for identifying irrigated land using radar data are based on the analysis of radar backscattering rather than directly analyzing changes in soil moisture. Because radar backscattering is affected by multiple factors such as soil moisture, vegetation, and surface roughness, it will introduce certain errors to the results. Summary of the invention

[0008] The present application proposes a method and device for remote sensing identification of irrigated land, which solves the problem of errors introduced by remote sensing technology in identifying irrigated land due to the influence of climate and environment.

[0009] In a first aspect, the present application embodiment provides a method for remote sensing identification of irrigated land, comprising the following steps: Invert the soil moisture of the target date based on the backscatter value of the pixel point; Obtaining the average value of soil moisture within a set range around the pixel point; The difference between the soil moisture of the pixel point and the average value is obtained, and it is determined that irrigation occurs at the pixel point where the difference is greater than a first set threshold. In one embodiment, the method further comprises the following steps: The standard deviation of the difference of the pixel points within the whole year is calculated, and the pixel points whose standard deviation is greater than a second set threshold are determined to be irrigated land.

[0010] In one embodiment, inverting soil moisture on a target date includes the following steps: Determine the ratio of the backscatter difference of the pixel point on the target date to its maximum value; The soil moisture of the pixel is determined based on the relationship that the ratio of the backscatter difference to its maximum value is equal to the ratio of the soil moisture difference to its maximum value.

[0011] In one embodiment, inverting soil moisture on a target date includes the following steps: The maximum value of the backscatter difference is determined based on the relationship curve between the NDVI, the maximum value of the backscatter difference and the NDVI on the target date; Determine the ratio of the backscatter difference value to the maximum value according to the backscatter difference value of the pixel point on the target date and the maximum value; The soil moisture of the pixel is determined based on the relationship that the ratio of the backscatter difference to its maximum value is equal to the ratio of the soil moisture difference to its maximum value.

[0012] In one embodiment, determining the ratio of the backscatter difference value of the target date pixel point to its maximum value includes the following steps: Obtain satellite data, and for each pixel point, first determine the date of the minimum backscatter value of the pixel point in a year, and then determine the backscatter difference value of the pixel point on other dates, wherein the backscatter difference value is the difference between the backscatter value of the other dates and the backscatter value of the date; Generate a scatter plot between the difference and the NDVI of the corresponding date; Fitting and generating a relationship curve between the maximum value of the difference and NDVI; The maximum value of the backscatter difference is determined based on the NDVI on the target date and the relationship curve.

[0013] In one embodiment, determining the soil moisture of the pixel point according to the relationship that the ratio of the backscatter difference to its maximum value is equal to the ratio of the soil moisture difference to its maximum value comprises the following steps: Determine the ratio of the backscatter difference value of the pixel point to the maximum value according to the backscatter difference value of the pixel point on the target date and the maximum value of the backscatter difference value corresponding to the NDVI of the pixel point on the target date; According to the maximum and minimum values ​​of soil moisture at the pixel point, the maximum value of the soil moisture difference is obtained; The soil moisture difference of the pixel point is determined based on the relationship that the ratio of the backscatter difference to its maximum value is equal to the ratio of the soil moisture difference to its maximum value.

[0014] In one embodiment, the fitting generates a relationship curve between the maximum value of the difference and the NDVI, further comprising the following steps: For each NDVI value in the scatter plot, the maximum value of the backscatter difference corresponding to the NDVI value in the scatter plot is taken, and a relationship curve between the maximum value of the backscatter difference and the NDVI is generated by fitting.

[0015] In some embodiments, for each NDVI value in the scatter plot, when the maximum backscatter difference value corresponding to the NDVI value in the scatter plot is taken, According to a set ratio, a number of scattered points with large backscattering differences corresponding to NDVI values ​​are excluded, and / or a number of scattered points with NDVI values ​​greater than any set value are excluded.

[0016] In a second aspect, the present application proposes a remote sensing identification device for irrigated land, which is used to implement the method described in any embodiment of the first aspect of the present application, including: An inversion module is used to invert the soil moisture of the target date based on the backscatter value of the pixel point; an acquisition module, used to acquire an average value of soil moisture within a set range around the pixel point, and a difference between the soil moisture at the pixel point and the average value, The determination module is used to determine that irrigation occurs at the pixel point where the difference is greater than a first set threshold. In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any embodiment of the first aspect of the present application.

[0017] In a fourth aspect, an embodiment of the present application proposes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described in any embodiment of the first aspect of the present application is implemented.

[0018] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: This application proposes a method for identifying irrigated land by combining radar data and optical data. This application first obtains soil moisture information of the area to be detected, then compares the soil moisture of each pixel with the average soil moisture of its surrounding pixels, separates the effects of irrigation and rainfall on soil moisture, and thus realizes the identification of irrigated land. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 A flowchart of an irrigated land remote sensing identification method embodiment proposed in the present application; Figure 2 This is an embodiment of the soil moisture inversion process of the embodiment of the present application; Figure 3 It is a distribution diagram between backscatter difference and NDVI; Figure 4 is an embodiment of curve fitting; Figure 5 (a)-(b) shows the schematic diagram of the spatial distribution of soil moisture in the area to be tested; Figure 6 (a)-(b) shows the spatial distribution of average soil moisture within 3 km around the pixel point in the detection area; Figure 7 (a)-(b) shows the spatial distribution of the difference between the pixel point in the detection area and the average soil moisture of the surrounding 3 km; Figure 8 (a)-(b) shows the time variation of the average soil moisture of the pixel point in the detection area and its surrounding 3 km; Fig. 9It represents the standard deviation of the annual change of the difference between the pixel point in the detection area and the average soil moisture of the surrounding 3 kilometers; Fig.10 Indicates the classification result of the area to be tested; Fig.11 This is an embodiment of the irrigated land remote sensing identification device of the present application embodiment; Fig.12 This is an electronic device embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0021] This application uses a simple soil moisture inversion method to obtain soil moisture, and uses the time-varying information of the difference between the average soil moisture of a pixel point and its surrounding range (e.g., 3 kilometers) to extract irrigated land. When other soil moisture inversion methods are used, and the range is set different from 3 kilometers, and other statistical information such as replacing the standard deviation of time variation used in this article with the mean value is replaced, it all falls within the scope of protection of this application.

[0022] The key technical point of this application is to use two simple statistical indicators of soil moisture time changes to realize the identification of irrigated land. For example, first use the change detection method to realize the inversion of soil moisture, which can more accurately reflect the change information of soil moisture. Then use the difference between the soil moisture at the pixel point and the average soil moisture of the surrounding 3 kilometers to distinguish between irrigation and precipitation, which are two phenomena that increase soil moisture. Finally, use the time change information of the difference, and statistically analyze its standard deviation to accurately identify the spatial distribution of irrigated land.

[0023] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0024] Figure 1 This is a flowchart of an embodiment of a method for remote sensing identification of irrigated land proposed in an embodiment of the present application. In a first aspect, an embodiment of the present application proposes a method for remote sensing identification of irrigated land, comprising the following steps: Step 110: Invert the soil moisture on the target date based on the backscatter value of the pixel point.

[0025] In one embodiment, inverting soil moisture on a target date includes the following steps: Step 111, determine the ratio of the backscatter difference value of the pixel point on the target date to its maximum value, specifically, for example: first, determine the maximum value of the backscatter difference value based on the NDVI of the target date, the maximum value of the backscatter difference value and the relationship curve between the NDVI; secondly, determine the ratio of the backscatter difference value to its maximum value based on the backscatter difference value of the pixel point on the target date and the maximum value.

[0026] The optimized relationship curve formula proposed in this application is: (1) in, is the maximum value of the backscatter difference.

[0027] Step 112: determine the soil moisture of the pixel point based on the relationship that the ratio of the backscatter difference to its maximum value is equal to the ratio of the soil moisture difference to its maximum value.

[0028] (2) (3) (4) in, is the backscatter difference, is the soil moisture difference, is the maximum soil moisture difference, For pixel i Soil moisture of the day, is the minimum soil moisture content, is the maximum value of soil moisture. Those skilled in the art will understand that according to formulas (1) to (4), when other variables are known, the value of the pixel point can be calculated. i Soil moisture of the day.

[0029] because Indicates the maximum backscatter difference under the corresponding NDVI. It can be calculated based on the NDVI and fitting curve of each pixel on a specific date. f(NDVI) Solve, for example, in this application, it is assumed that the minimum value of soil moisture at all pixels is 0.03 cm 3 / cm 3 , the maximum difference in soil moisture is 0.25 cm 3 / cm 3 When the soil moisture solution method is applied to other areas, the two empirical values ​​can be adjusted according to actual conditions.

[0030] The specific solution process for soil moisture at each pixel is: a. Using the NDVI of the corresponding date and the fitted quadratic curve f(NDVI) Solution ; b. Using the maximum and minimum values ​​of soil moisture, solve In this study area, it is 0.22 cm 3 / cm 3 ; c. Use the i Sky backscatter and Solution , and then use the solved , Substitute into formula (2) and solve ,use and Solving for soil moisture .

[0031] Step 120: Obtain an average value of soil moisture within a set range around the pixel point.

[0032] Step 130: Obtain the difference between the soil moisture of the pixel point and the average value, and determine that irrigation occurs at the pixel point where the difference is greater than a first set threshold. For example, if the set range is 3 kilometers, the difference between the soil moisture of each pixel and the average soil moisture within a 3-kilometer range around the pixel is obtained. When the difference is positive, it means that irrigation has occurred at the pixel; when the difference does not change much, it means that no irrigation has occurred; when the difference is negative, it means that precipitation or irrigation has occurred in other surrounding areas, but no irrigation has occurred at the pixel.

[0033] Step 140, calculating the standard deviation of the difference of the pixel points within the whole year, and determining that the pixel points whose standard deviation is greater than a second set threshold are irrigated land.

[0034] Calculate the annual When the standard deviation of the pixel is large, it means that irrigation occurs frequently, and the pixel is irrigated land.

[0035] (5) in The soil moisture at this pixel point is It represents the average soil moisture within 3 kilometers around the pixel. represents the set of the difference between the two soil moisture values ​​of the pixel point throughout the year, and std represents the standard deviation operation. When it is greater than the threshold, it is irrigated land; when When it is less than the threshold, it is dry land.

[0036] Figure 2 This is an embodiment of the soil moisture inversion process of the embodiment of the present application. To implement steps 111-112 of the above embodiment, in one embodiment, determining the ratio of the backscatter difference of the pixel point on the target date to its maximum value includes steps 210-240: Step 210: Acquire satellite data and perform data preprocessing.

[0037] For example, using the high-resolution radar and optical image data provided by Sentinel-1 and Sentinel-2, we can invert soil moisture, separate the effects of irrigation and rainfall on soil moisture, and identify irrigated land. The specific steps are as follows: 1. Download the radar data of Sentinel-1 (A / B), and then perform preprocessing such as noise removal, radiation calibration, terrain correction, and incident angle normalization to obtain radar image data covering the area to be detected (resolution of 10 m). 2. Download the optical data of Sentinel-2, remove the cloud from the original data, and then perform filtering and interpolation operations to supplement the missing data after cloud removal, and then calculate the Normalized Difference Vegetation Index (NDVI, with a resolution of 10 m) of the area to be detected.

[0038] Step 220, for each pixel point, first determine the date of the minimum backscatter value of the pixel point in a year, and then determine the backscatter difference of the pixel point on other dates, where the backscatter difference is the difference between the backscatter value of the other dates and the backscatter value of the date.

[0039] In order to invert soil moisture, the minimum backscatter value of each pixel in a year is determined, and the minimum backscatter value corresponds to the date with the lowest soil moisture content. Then the difference between the backscatter value of the point on other dates and the backscatter value of this date is solved.

[0040] (6) in, Indicates i Backscatter of the sky, represents the backscatter on the date with the lowest soil moisture content, Represents the backscatter difference.

[0041] Step 230: Generate a scatter plot between the difference and the NDVI of the corresponding date, and generate a relationship curve between the maximum value of the difference and the NDVI by fitting.

[0042] First, solve the backscatter difference corresponding to all dates for all pixels, and draw a scatter plot between the backscatter difference and the NDVI of the corresponding date. If the NDVI date does not correspond to the backscatter date, the NDVI before and after the missing date is supplemented to the date when the backscatter is obtained. The top point of the scatter plot represents the maximum backscatter difference under each NDVI, which represents the maximum value of soil moisture change. Figure 3 .

[0043] In one embodiment, for each NDVI value in the scatter plot, the maximum value of the backscatter difference corresponding to the NDVI value in the scatter plot is taken, and a relationship curve between the maximum value of the backscatter difference and the NDVI is generated by fitting.

[0044] In some embodiments, for each NDVI value in the scatter plot, when taking the maximum value of the backscatter difference corresponding to the NDVI value in the scatter plot, several scatter points with large backscatter differences corresponding to the NDVI values ​​are excluded according to a set ratio, and / or several scatter points with NDVI values ​​greater than any set value are excluded.

[0045] Step 240: Determine the maximum value of the backscatter difference according to the NDVI on the target date and the relationship curve.

[0046] In one embodiment, in order to implement the step 112 of determining the soil moisture of the pixel point according to the relationship that the ratio of the backscatter difference to its maximum value is equal to the ratio of the soil moisture difference to its maximum value, the method further includes steps 250-270: Step 250: Determine the ratio of the backscatter difference value of the pixel point to the maximum value based on the backscatter difference value of the pixel point on the target date and the maximum value of the backscatter difference value corresponding to the NDVI of the pixel point on the target date.

[0047] Step 260: Obtain the maximum value of the soil moisture difference according to the maximum value and the minimum value of the soil moisture at the pixel point.

[0048] Step 270: Determine the soil moisture difference value at the pixel point according to the relationship that the ratio of the backscatter difference value to its maximum value is equal to the ratio of the soil moisture difference value to its maximum value.

[0049] Figure 3 This is a schematic diagram of the distribution between backscatter difference and NDVI. It represents the maximum backscatter difference under the corresponding NDVI. The maximum value of all scatter differences can be represented by fitting the quadratic curve f(NDVI), where m and n represent the row and column numbers of the pixel points.

[0050] Figure 4The gray dots are the scatter plots of the backscatter differences of all pixels on all dates and the NDVI of the corresponding dates. The black curve is the curve fitted using the top point of the scatter plot (black dots: in order to reduce the influence of noise points on the final fitting curve, the top 5‰ points are not involved in the fitting) f(NDVI) . use f(NDVI) And the corresponding NDVI , which can be solved with this NDVI The maximum backscatter difference value corresponding to the value Among them, due to NDVI The points after >0.8 account for a very small proportion, so they are not involved in the calculation when solving the fitting curve. The final fitting curve is, for example, formula (1).

[0051] Figure 5 (a)-(b) is a schematic diagram of the spatial distribution of soil moisture in the area to be tested. Using the above-mentioned soil moisture inversion method, the first step of this application obtained a total of 31 scenes of soil moisture results in 2020. Figure 5 shows 2 scenes selected from the 31 scenes of soil moisture results, with dates of June 9, 2020 (a) and September 1, 2020 (b). It can be seen from Figure 5 (a)-(b) that the spatial distribution of soil moisture is different on different dates. Locations with higher soil moisture may be caused by precipitation or irrigation. Figure 6 (a)-(b) is the spatial distribution of average soil moisture within 3 kilometers around the pixel points in the area to be tested, and the dates are consistent with Figure 5 (a)-(b).

[0052] Figure 7 (a)-(b) shows the spatial distribution of the difference between the pixel point in the detection area (Figure 5 (a)-(b)) and the average soil moisture of the surrounding 3 kilometers (Figure 6 (a)-(b)). In order to distinguish the increase in soil moisture caused by precipitation or irrigation, the present application solves the difference between the soil moisture of each pixel point and the average soil moisture of the surrounding 3 kilometers. Figure 7 (a)-(b) shows the location where the soil moisture of the pixel point is greater than the average soil moisture of the surrounding 3 kilometers. When the soil moisture of the pixel point is greater than the average soil moisture of the surrounding area, it means that irrigation has occurred at the pixel point. It can be seen from Figure 7 (a)-(b) that irrigation has obviously occurred in some areas.

[0053] Figure 8 (a)-(b) shows the time variation of the average soil moisture of the pixel point in the detection area and its surrounding 3 km. In order to make full use of the time series information of soil moisture throughout the year, this application first analyzes the soil moisture of irrigated land and dry land (θ represents the soil moisture of the pixel point; The average soil moisture within 3 km around the pixel point) changes over time. Figure 8 (a)-(b) includes the changes of two types of soil moisture and rainfall over time. It can be seen from Figure 8 (a)-(b) that the soil moisture of the pixel point of the irrigated land is significantly greater than the average soil moisture within 3 km around it, and the fluctuation is more obvious, while the band difference of the two types of soil moisture in the dry land is not obvious.

[0054] Therefore, based on the above analysis, this application uses the difference in the volatility of the two types of soil moisture in the time series to identify irrigated land and dry land. The volatility difference can be measured by the standard deviation of the time series data. Fig. 9 It is the standard deviation of the annual change of the difference between the pixel point in the detection area and the average soil moisture of the surrounding 3 kilometers. As can be seen from the figure, the standard deviation of the difference between the two soil moisture in the irrigated area is significantly greater than that in the dry land.

[0055] Fig.10 Indicates the classification result of the area to be detected. This application uses 0.05 as the screening threshold. When the standard deviation is greater than 0.05, the area to be detected is identified as irrigated land. The final classification result, gray is irrigated land, and black is dry land.

[0056] Fig.11 This is an embodiment of the irrigated land remote sensing identification device of the present application. The present application proposes an irrigated land remote sensing identification device, which is used to implement the method described in any embodiment of the present application, and includes an inversion module 310, an acquisition module 320 and a determination module 330.

[0057] The inversion module is used to invert the soil moisture of the target date according to the backscatter value of the pixel point; The acquisition module is used to acquire an average value of soil moisture within a set range around the pixel point and a difference between the soil moisture at the pixel point and the average value.

[0058] In one embodiment, the lake area module includes a first acquisition unit, which is used to obtain the average value of soil moisture within a set range around the pixel point, the difference between the soil moisture of the pixel point and the average value. The determination module is used to determine that irrigation occurs at the pixel point where the difference is greater than a first set threshold. In one embodiment, the determination module includes a first determination unit, and the first determination unit is used to determine that irrigation occurs at a pixel point where the difference is greater than a first set threshold.

[0059] In one embodiment, the determination module includes a second determination unit, which is used to calculate the standard deviation of the difference of the pixel points within the whole year, and determine that the pixel points whose standard deviation is greater than a second set threshold are irrigated land.

[0060] In one embodiment, the inversion module inverts the soil moisture on the target date, further comprising a third determination unit and a fourth determination unit: The third determination unit is used to determine the ratio of the backscatter difference value of the pixel point on the target date to its maximum value; The fourth determination unit determines the soil moisture of the pixel point according to the relationship that the ratio of the backscatter difference to its maximum value is equal to the ratio of the soil moisture difference to its maximum value.

[0061] In one embodiment, the inversion module inverts the soil moisture on the target date, further comprising a fifth determination unit, a sixth determination unit and a seventh determination unit: The fifth determining unit is used to determine the maximum value of the backscatter difference according to the NDVI on the target date, the maximum value of the backscatter difference and the relationship curve between the NDVI; The sixth determining unit is used to determine the ratio of the backscatter difference value to the maximum value according to the backscatter difference value of the pixel point on the target date and the maximum value; The seventh determination unit is used to determine the soil moisture of the pixel point according to the relationship that the ratio of the backscatter difference to its maximum value is equal to the ratio of the soil moisture difference to its maximum value.

[0062] In one embodiment, in order to determine the ratio of the backscatter difference value of the target date pixel point to its maximum value, the acquisition module further includes a second acquisition unit, a first generation unit and a second generation unit.

[0063] The second acquisition unit is used to acquire satellite data, and for each pixel point, first determine the date of the minimum backscatter value of the pixel point in a year, and then determine the backscatter difference of other dates of the pixel point, where the backscatter difference is the difference between the backscatter value of the other dates and the backscatter value of the date; The first generating unit is used to generate a scatter plot between the difference and the NDVI of the corresponding date; The second generating unit is used for fitting and generating a relationship curve between the maximum value of the difference and the NDVI; The fifth determination unit realizes the function of determining the maximum value of the backscatter difference according to the NDVI on the target date and the relationship curve.

[0064] In one embodiment, the seventh determination unit determines the soil moisture of the pixel point based on the relationship that the ratio of the backscattering difference to its maximum value is equal to the ratio of the soil moisture difference to its maximum value, and further includes a backscattering ratio unit, a soil moisture difference maximum value unit and a soil moisture difference unit.

[0065] The backscatter ratio unit is used to determine the ratio of the backscatter difference value of the pixel point to the maximum value according to the backscatter difference value of the pixel point on the target date and the maximum value of the backscatter difference value corresponding to the NDVI of the pixel point on the target date; The soil moisture difference maximum value unit is used to obtain the maximum value of the soil moisture difference according to the maximum value and the minimum value of the soil moisture at the pixel point; The soil moisture difference unit is configured to determine the soil moisture difference of the pixel point according to the relationship that the ratio of the backscatter difference to its maximum value is equal to the ratio of the soil moisture difference to its maximum value.

[0066] In one embodiment, the second generating unit fits and generates a relationship curve between the maximum value of the difference and the NDVI, and is further used to: For each NDVI value in the scatter plot, the maximum value of the backscatter difference corresponding to the NDVI value in the scatter plot is taken, and a relationship curve between the maximum value of the backscatter difference and the NDVI is generated by fitting.

[0067] In some embodiments, for each NDVI value in the scatter plot, when taking the maximum value of the backscatter difference corresponding to the NDVI value in the scatter plot, several scatter points with large backscatter difference corresponding to the NDVI value are excluded according to a set ratio, and / or several scatter points with NDVI values ​​greater than any set value are excluded.

[0068] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt 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 codes.

[0069] Therefore, the present application also proposes a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in any embodiment of the present application is implemented.

[0070] Furthermore, the present application also proposes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present application when executing the computer program.

[0071] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0072] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0073] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0074] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory. The memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0075] Fig.12It is a structural diagram of an electronic device provided in an embodiment of the present application. The electronic device 600 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiment of the present application. It includes: one or more processors 620; a storage device 610, which is used to store one or more programs. When the one or more programs are run by the one or more processors 620, the one or more processors 620 implement the irrigated land remote sensing identification method provided in the embodiment of the present application. The method includes all or part of the functions of the steps 110~130 and 210~270 of the embodiment, which will not be repeated here.

[0076] The electronic device 600 further includes an input device 630 and an output device 640; the processor 620, storage device 610, input device 630 and output device 640 in the electronic device can be connected via a bus or other means, and the figure takes the connection via a bus 650 as an example.

[0077] The storage device 610, as a computer-readable storage medium, can be used to store software programs, computer executable programs, and module units, such as program instructions corresponding to the irrigated land remote sensing identification method in the embodiment of the present application. The storage device 610 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the storage device 610 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the storage device 610 may further include a memory remotely arranged relative to the processor 620, and these remote memories may be connected via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0078] The input device 630 may be used to receive input numbers, character information or voice information, and generate key signal input related to user settings and function control of the electronic device. The output device 640 may include electronic devices such as a display screen and a speaker.

[0079] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0080] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A remote sensing identification method for irrigated land, characterized in that: The following steps are involved: Invert the soil moisture of the target date based on the backscatter value of the pixel point; Obtaining the average value of soil moisture within a set range around the pixel point; The difference between the soil moisture of the pixel point and the average value is obtained, and it is determined that irrigation occurs at the pixel point where the difference is greater than a first set threshold.

2. A remote sensing identification method for irrigated land according to claim 1, characterized in that: The standard deviation of the difference of the pixel points within the whole year is calculated, and the pixel points whose standard deviation is greater than a second set threshold are determined to be irrigated land.

3. The remote sensing identification method of irrigated land according to claim 1, characterized in that: The soil moisture of the target date is retrieved, including the following steps: Determine the ratio of the backscatter difference of the pixel point on the target date to its maximum value; The soil moisture of the pixel is determined based on the relationship that the ratio of the backscatter difference to its maximum value is equal to the ratio of the soil moisture difference to its maximum value.

4. The remote sensing identification method of irrigated land according to claim 1, characterized in that: The soil moisture of the target date is retrieved, including the following steps: The maximum value of the backscatter difference is determined based on the relationship curve between the NDVI, the maximum value of the backscatter difference and the NDVI on the target date; Determine the ratio of the backscatter difference value to the maximum value according to the backscatter difference value of the pixel point on the target date and the maximum value; The soil moisture of the pixel is determined based on the relationship that the ratio of the backscatter difference to its maximum value is equal to the ratio of the soil moisture difference to its maximum value.

5. The remote sensing identification method for irrigated land according to claim 3, characterized in that: Determining the ratio of the backscatter difference value of the target date pixel point to its maximum value includes the following steps: Obtain satellite data, and for each pixel point, first determine the date of the minimum backscatter value of the pixel point in a year, and then determine the backscatter difference value of the pixel point on other dates, wherein the backscatter difference value is the difference between the backscatter value of the other dates and the backscatter value of the date; Generate a scatter plot between the difference and the NDVI of the corresponding date; Fitting and generating a relationship curve between the maximum value of the difference and NDVI; The maximum value of the backscatter difference is determined based on the NDVI on the target date and the relationship curve.

6. The remote sensing identification method of irrigated land according to claim 1, characterized in that: Determining the soil moisture of the pixel point according to the relationship that the ratio of the backscatter difference to its maximum value is equal to the ratio of the soil moisture difference to its maximum value comprises the following steps: Determine the ratio of the backscatter difference value of the pixel point to the maximum value according to the backscatter difference value of the pixel point on the target date and the maximum value of the backscatter difference value corresponding to the NDVI of the pixel point on the target date; According to the maximum and minimum values ​​of soil moisture at the pixel point, the maximum value of the soil moisture difference is obtained; The soil moisture difference of the pixel point is determined based on the relationship that the ratio of the backscatter difference to its maximum value is equal to the ratio of the soil moisture difference to its maximum value.

7. The remote sensing identification method of irrigated land according to claim 5, characterized in that: The fitting generates a relationship curve between the maximum value of the difference and the NDVI, further comprising the following steps: For each NDVI value in the scatter plot, the maximum value of the backscatter difference corresponding to the NDVI value in the scatter plot is taken, and a relationship curve between the maximum value of the backscatter difference and the NDVI is generated by fitting.

8. The remote sensing identification method for irrigated land according to claim 1, characterized in that: For each NDVI value in the scatter plot, when the maximum backscatter difference value corresponding to the NDVI value in the scatter plot is taken, According to a set ratio, a number of scattered points with large backscattering differences corresponding to NDVI values ​​are excluded, and / or a number of scattered points with NDVI values ​​greater than any set value are excluded.

9. A remote sensing identification device for irrigated land, used to implement the method described in any one of claims 1 to 8, characterized in that: include: An inversion module is used to invert the soil moisture of the target date based on the backscatter value of the pixel point; an acquisition module, used to acquire an average value of soil moisture within a set range around the pixel point, and a difference between the soil moisture at the pixel point and the average value, The determination module is used to determine that irrigation occurs at the pixel point where the difference is greater than a first set threshold.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

11. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

Images