Method, device, electronic device and storage medium used for rice mapping

Abstract

This disclosure provides a method, apparatus, electronic device, and storage medium for rice mapping. The method includes: acquiring farmland images within a preset time period, the farmland images including multiple farmland plots; determining the maximum normalized difference vegetation index and the maximum normalized difference water index for each farmland plot within the preset time period, and determining the target maximum backscattering intensity of local vegetation and the target minimum backscattering intensity of local water bodies; acquiring SAR time series data for each farmland plot within the preset time period; determining the local maximum backscattering intensity and the local minimum backscattering intensity for each farmland plot based on the SAR time series data; and determining the target rice mapping index for each farmland plot based on the local maximum backscattering intensity and the local minimum backscattering intensity, as well as the target maximum backscattering intensity of local vegetation and the target minimum backscattering intensity of local water bodies.

Description

Technical Field

[0001] This disclosure relates to the field of remote sensing data analysis technology, and more specifically, to a method, apparatus, electronic device, and storage medium for rice surveying. Background Technology

[0002] Timely and effective monitoring of rice cultivation is not only crucial for food security, but also for environmental issues related to water use and climate change.

[0003] With the development of remote sensing technology, two sources of remote sensing data—optical and synthetic aperture radar data—are widely used in large-scale and long-term rice mapping and monitoring. However, in practice, adverse weather conditions often limit optical observations, especially in tropical and subtropical regions, leading to inaccurate rice mapping.

[0004] Rice mapping methods in related technologies face several challenges. First, most require prior information on rice phenology to define the time window for extracting phenological characteristics, limiting their applicability in areas lacking such information. Second, classification and threshold-based methods require pre-training to ensure accuracy, making the performance of rice mapping highly dependent on the availability and reliability of training samples, leading to high costs for large-scale applications. Third, significant differences in planting systems, rice phenology, topography, or other factors can cause variations in SAR backscatter signal intensity, meaning models trained for local environments may not be suitable for other locations.

[0005] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] This disclosure provides a method, apparatus, electronic device, and storage medium for rice mapping. The target rice mapping index obtained by this method can effectively distinguish rice from other crops, can adaptively consider local conditions, and achieve robust mapping results in different regions.

[0007] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0008] This disclosure provides a method for rice mapping, comprising: acquiring farmland images within a preset time period, wherein the farmland images include multiple farmland plots; determining the maximum normalized difference vegetation index and the maximum normalized difference water index for each farmland plot within the preset time period; determining the target maximum backscattering intensity of local vegetation and the target minimum backscattering intensity of local water bodies based on the maximum normalized difference vegetation index and the maximum normalized difference water index for each farmland plot within the preset time period; acquiring synthetic aperture radar (SAR) time series data for each farmland plot within the preset time period; determining the local maximum backscattering intensity and the local minimum backscattering intensity for each farmland plot based on the SAR time series data; and determining a target rice mapping index for each farmland plot based on the local maximum backscattering intensity and the local minimum backscattering intensity, as well as the target maximum backscattering intensity of local vegetation and the target minimum backscattering intensity of local water bodies, wherein the target rice mapping index is used to characterize the probability of rice being planted in the farmland plot.

[0009] In an exemplary embodiment, the method further includes: if the rice surveying index of the cultivated land plot is greater than or equal to a preset threshold, then classifying the cultivated land plot as a rice plot; if the rice surveying index of the cultivated land plot is less than the preset threshold, then classifying the cultivated land plot as a non-rice plot.

[0010] In an exemplary embodiment, the preset threshold is greater than or equal to 0.5 and less than or equal to 0.7.

[0011] In an exemplary embodiment, determining the target maximum backscattering intensity of local vegetation and the target minimum backscattering intensity of local water body based on the maximum normalized difference vegetation index and the maximum normalized difference water index of each cultivated land plot within a preset time period includes: identifying at least one vegetation object and at least one temporary water body object from each cultivated land plot based on the maximum normalized difference vegetation index and the maximum normalized difference water index of each cultivated land plot within the preset time period; determining the target maximum backscattering intensity of the local vegetation based on the maximum backscattering intensity of the at least one vegetation object; and determining the target minimum backscattering intensity of the local water body based on the minimum backscattering intensity of the at least one temporary water body object.

[0012] In an exemplary embodiment, determining at least one vegetation object and at least one temporary water body object from each cultivated land plot based on the maximum normalized difference vegetation index and the maximum normalized difference water index within the preset time period includes: if the maximum normalized difference vegetation index of the cultivated land plot within the preset time period is greater than 0.4 and the maximum normalized difference water index is less than or equal to 0.3, then the cultivated land plot is determined as the vegetation object; if the maximum normalized difference vegetation index of the cultivated land plot within the preset time period is greater than 0.4 and the maximum normalized difference water index is greater than 0.3, then the cultivated land plot is determined as the temporary water body object.

[0013] In an exemplary embodiment, determining the target maximum backscattering intensity of the local vegetation based on the maximum backscattering intensity of the at least one vegetation object includes: determining the target maximum backscattering intensity of the local vegetation from the maximum backscattering intensity of the at least one vegetation object based on a first preset percentile; wherein, determining the target minimum backscattering intensity of the local water body based on the minimum backscattering intensity of the at least one temporary water body object includes: determining the target minimum backscattering intensity of the local water body from the minimum backscattering intensity of the at least one temporary water body object based on a second preset percentile.

[0014] In an exemplary embodiment, the first preset percentile is greater than or equal to 10 and less than or equal to 25; when the terrain corresponding to the cultivated land image is flat, the second preset percentile is greater than or equal to 5 and less than or equal to 25; when the terrain corresponding to the cultivated land image is non-flat, the second preset percentile is greater than or equal to 75 and less than or equal to 95.

[0015] In an exemplary embodiment, determining the target rice mapping index for each cultivated land plot based on its local maximum and minimum backscattering intensities, as well as the target maximum backscattering intensities of the local vegetation and the target minimum backscattering intensities of the local water body, includes: determining the difference between the local maximum and minimum backscattering intensities of the cultivated land plot as the backscattering distance of the cultivated land plot; determining the difference between the target maximum backscattering intensities of the local vegetation and the target minimum backscattering intensities of the local water body as the target depth; and determining the target rice mapping index based on the local maximum and minimum backscattering intensities of the local vegetation and the target minimum backscattering intensities of the local water body. A first rice mapping index is determined based on the backscattering distance of the cultivated land plot and the target depth; a second rice mapping index is determined based on the difference between the local minimum backscattering intensity of the cultivated land plot and the target minimum backscattering intensity of the local water body, as well as the target depth; a third rice mapping index is determined based on the difference between the target maximum backscattering intensity of the local vegetation and the local maximum backscattering intensity of the cultivated land plot, as well as the target depth; and the target rice mapping index for each cultivated land plot is determined based on the first rice mapping index, the second rice mapping index, and the third rice mapping index.

[0016] In an exemplary embodiment, the first rice mapping index is determined according to the following formula:

[0017]

[0018] Where f(D) represents the first rice mapping index, D represents the backscattering distance of the cultivated land plot, v represents the maximum backscattering intensity of the target of the local vegetation, and w represents the minimum backscattering intensity of the target of the local water body;

[0019] The second rice mapping index is determined according to the following formula:

[0020]

[0021] Where f(W) represents the second rice mapping index, and p1 represents the local minimum backscattering intensity of the cultivated land plot;

[0022] The third rice mapping index is determined according to the following formula:

[0023]

[0024] Where f(V) represents the third rice mapping index, and p2 represents the local maximum backscattering intensity of the cultivated land plot.

[0025] In an exemplary embodiment, the method further includes: generating a rice mapping map corresponding to the cultivated land image based on the target rice mapping index of each cultivated land plot.

[0026] This disclosure provides an apparatus for rice surveying, comprising: an acquisition module for acquiring farmland images within a preset time period, wherein the farmland images include multiple farmland plots; a determination module for determining the maximum normalized difference vegetation index and the maximum normalized difference water index for each farmland plot within the preset time period; the determination module is further configured to determine the target maximum backscattering intensity of local vegetation and the target minimum backscattering intensity of local water bodies based on the maximum normalized difference vegetation index and the maximum normalized difference water index for each farmland plot within the preset time period; the acquisition module is further configured to acquire data for each farmland plot within the preset time period... The synthetic aperture radar (SAR) time series data for each of the preset time periods; the determining module is further configured to determine the local maximum backscattering intensity and local minimum backscattering intensity of each cultivated land plot based on the SAR time series data; the determining module is further configured to determine the target rice mapping index of each cultivated land plot based on the local maximum backscattering intensity and local minimum backscattering intensity of each cultivated land plot, as well as the target maximum backscattering intensity of the local vegetation and the target minimum backscattering intensity of the local water body, wherein the target rice mapping index is used to characterize the probability of planting rice in the cultivated land plot.

[0027] This disclosure provides an electronic device, including: at least one processor; and a storage terminal device for storing at least one program, which, when executed by the at least one processor, causes the at least one processor to implement any of the above-described methods for rice surveying.

[0028] This disclosure provides a computer-readable storage medium storing a computer program thereon, characterized in that the computer program, when executed by a processor, implements any of the above-described methods for rice surveying.

[0029] This disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the method for rice surveying described above.

[0030] The method for rice mapping provided in this disclosure determines the maximum normalized difference vegetation index and the maximum normalized difference water index for each cultivated land plot within a preset time period based on cultivated land images within that time period. Based on these indices, it determines the target maximum backscattering intensity of local vegetation and the target minimum backscattering intensity of local water bodies. It also determines the local maximum and minimum backscattering intensities for each cultivated land plot based on SAR time series data. Finally, it determines the target rice mapping index for each cultivated land plot based on these local maximum and minimum backscattering intensities, as well as the target maximum and minimum backscattering intensities of the local vegetation and water bodies, thus characterizing the probability of rice cultivation in the cultivated land plot. The target rice mapping index obtained by this method can effectively distinguish rice from other crops, especially in heterogeneous agricultural areas where rice and other crops are intercropped, where its application effect is even better. Furthermore, this method does not require prior information, reference samples, or many predefined parameters, and is characterized by high automation, high flexibility, ease of application, and good robustness. It can support large-area rice mapping, and is particularly suitable for cloudy areas where optical remote sensing data is not frequently available. This method is independent of climatic conditions and has good applicability under different climatic conditions. It can adaptively consider local conditions and achieve robust mapping results in different regions. Moreover, the target rice mapping index obtained by this method is a continuous variable related to the probability or coverage of rice planting, which can provide more objective and flexible rice mapping than hard classification.

[0031] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0032] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0033] Figure 1 This is a flowchart illustrating a method for rice surveying according to an exemplary embodiment.

[0034] Figure 2 The diagram shows a Sentinel-2 cloudless image and a Sentinel-1 VH image near the rice transplanting period, corresponding to locations 1 to 5.

[0035] Figure 3A schematic diagram of the process for determining the values ​​of w and v is shown.

[0036] Figure 4 This is a schematic diagram of a Sentinel-1VH time series as shown in an example.

[0037] Figure 5 This is a schematic diagram showing the comparison of the separability of rice and other land cover using linear and sigmoid functions, respectively.

[0038] Figure 6 The diagram shows the ROC curves for locations 1 to 5 and a schematic diagram of the sensitivity analysis of the SPRMI binary classification threshold for locations 1 to 5.

[0039] Figure 7 The diagram shows the farmland images, SPRMI maps, rice mapping results, and reference maps corresponding to locations 1 to 5.

[0040] Figure 8 A schematic diagram showing the accuracy of rice surveying at locations 1 to 4 based on three methods is presented.

[0041] Figure 9 Histograms of SPRMI values, local minimum backscatter intensity at transplanting time, dynamic backscatter range, and transplanting date are shown for rice and non-rice validation samples.

[0042] Figure 10 A schematic diagram comparing the accuracy (F1 score) of rice mapping using the local adaptive parameter method with that using the uniform parameter method is shown.

[0043] Figure 11 The F1 scores for locations 1 through 5 are shown after selecting the V and W lines using different percentiles.

[0044] Figure 12 This is a block diagram illustrating an apparatus for rice surveying according to an exemplary embodiment.

[0045] Figure 13 This is a schematic diagram illustrating the structure of an electronic device suitable for implementing exemplary embodiments of the present disclosure, according to an exemplary embodiment. Detailed Implementation

[0046] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted.

[0047] The features, structures, or characteristics described in this disclosure can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more specific details omitted, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0048] The accompanying drawings are merely illustrative of this disclosure, and the same reference numerals in the drawings denote the same or similar parts, thus omitting repeated descriptions of them. Some block diagrams shown in the drawings do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in at least one hardware module or integrated circuit, or in different network and / or processor devices and / or microcontroller devices.

[0049] The flowchart shown in the accompanying drawings is merely illustrative and does not necessarily include all content and steps, nor does it require execution in the described order. For example, some steps may be broken down, while others may be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0050] Furthermore, in the description of this disclosure, the terms “a,” “one,” “the,” “the,” and “at least one” are used to indicate the presence of at least one element or component; the terms “comprising,” “including,” and “having” are used to indicate an open-ended inclusion and to mean that there may be other elements or components in addition to the listed elements or components; the terms “first,” “second,” and “third,” etc., are used only as labels and are not a limitation on the number of objects.

[0051] The following will describe in more detail the various steps of the method for rice mapping in the exemplary embodiments of this disclosure, with reference to the accompanying drawings and examples.

[0052] Figure 1 This is a flowchart illustrating a method for rice surveying according to an exemplary embodiment.

[0053] like Figure 1 As shown, the method provided in this disclosure embodiment may include the following steps.

[0054] In step S102, farmland images within a preset time period are acquired, wherein the farmland images include multiple farmland plots.

[0055] In this embodiment of the disclosure, multiple farmland images within a preset time period can be acquired for a target location. The preset time period can be, for example, 30 days, 90 days, 180 days, 365 days, etc. In the following examples, the preset time period of 365 days is used as an example for illustration, but this disclosure is not limited to this. The farmland images can be, for example, Sentinel-2 cloudless images.

[0056] For example, Sentinel-2 cloud-free images can be obtained for a single farmland object every day for 365 days.

[0057] In this embodiment of the disclosure, five locations are used as test sites (i.e., target sites). These five locations differ in the following aspects: 1) geographical and climatic conditions; 2) landscape complexity; and 3) planting systems. Location 1 is located in Glen County, California (122°0′–122°12′W, 39°26′–39°36′N); Locations 2 and 3 are both located in the Mississippi River basin, which is mainly agricultural; Locations 4 and 5 are located in the mountainous areas of Sichuan and Hunan provinces in China, respectively, which have unique small-scale farming characteristics.

[0058] In this embodiment of the disclosure, Sentinel-2 cloudless images and Sentinel-1 (Sentinel 1) VH images of each of locations 1 to 5 can be obtained over 365 days.

[0059] refer to Figure 2 The diagram shows a Sentinel-2 cloudless image (top row) and Sentinel-1 VH image (bottom row) near the rice transplanting period for locations 1 to 5.

[0060] The Sentinel-1 Ground Range Detected (GRD) images are calibration and orthorectification products provided by GEE (Google Earth Engine). Based on the Sentinel-1 VH images, SAR VH time series with a spatial resolution of 10m and a temporal resolution of 12 days can be generated (Table 1), used to calculate the local maximum and minimum backscattering intensities for each farmland plot. Sentinel-2 images (blue, green, red, and near-infrared bands) can be obtained from the GEE platform. Sentinel-2 cloud-free images, for example, images with a cloud cover of <10%, can be used to obtain the maximum normalized difference vegetation index (NDVI) and maximum normalized difference water index for each farmland plot within a preset time period.

[0061] Table 1. Sentinel-1 time series used in this disclosure.

[0062] Target location track Orbiter Data Frame Acquisition period Location 1 Ascend 137 124 January 5 – December 30, 2020 Location 2 Ascend 165 110 January 7 – December 20, 2020 Location 3 Ascend 165 110 January 7 – December 20, 2020 Location 4 Ascend 128 94 February 12 - December 21, 2017 Location 5 Ascend 84 80&85 January 7 - October 22, 2021

[0063] In this embodiment of the disclosure, after acquiring farmland images within a preset time period, each farmland image can be segmented to obtain multiple farmland plots corresponding to each farmland image. For example, the plot boundaries can be automatically extracted from Sentinel-2 cloudless imagery using the Canny operator, and then farmland plots can be generated using the watershed algorithm.

[0064] In step S104, the maximum normalized difference vegetation index (NDVI) and the maximum normalized difference water index (NDWI) of each cultivated land plot within a preset time period are determined.

[0065] In this embodiment of the disclosure, the maximum normalized difference vegetation index of the cultivated land plot within a preset time period can be determined as the maximum normalized difference vegetation index (hereinafter referred to as "NDVImax") and the maximum normalized difference water index (hereinafter referred to as "NDWImax") of the cultivated land plot.

[0066] For example, the annual maximum NDVI and annual maximum NDWI can be calculated based on all available Sentinel-2 images within a year to reduce the impact of cloud interference.

[0067] In step S106, the target maximum backscattering intensity of local vegetation and the target minimum backscattering intensity of local water body are determined based on the maximum normalized difference vegetation index and the maximum normalized difference water index of each cultivated land plot within a preset time period.

[0068] The maximum backscattering intensity of the target in the local vegetation is represented by v, and the minimum backscattering intensity of the target in the local water body is represented by w.

[0069] Taking a farmland plot as an example, the farmland plot can be classified according to NDVImax and NDWImax within a preset time period. The v value is determined according to the maximum backscattering intensity of the vegetation objects in each farmland plot, and the w value is determined according to the minimum backscattering intensity of the temporary water objects in each farmland plot.

[0070] In an exemplary embodiment, determining the target maximum backscattering intensity of local vegetation and the target minimum backscattering intensity of local water body based on the maximum normalized difference vegetation index and the maximum normalized difference water index of each cultivated land plot within a preset time period includes: identifying at least one vegetation object and at least one temporary water body object from each cultivated land plot based on the maximum normalized difference vegetation index and the maximum normalized difference water index of each cultivated land plot within a preset time period; determining the target maximum backscattering intensity of local vegetation based on the maximum backscattering intensity of at least one vegetation object; and determining the target minimum backscattering intensity of local water body based on the minimum backscattering intensity of at least one temporary water body object.

[0071] For example, thresholding methods can be used to select vegetation objects and temporary water bodies by applying NDVImax and NDWImax. In this case, rice paddies flooded during the irrigation period can be regarded as a type of temporary water body object.

[0072] In an exemplary embodiment, at least one vegetation object and at least one temporary water body object are determined from each cultivated land plot based on the maximum normalized difference vegetation index and the maximum normalized difference water index within a preset time period. This includes: if the maximum normalized difference vegetation index of the cultivated land plot within the preset time period is greater than 0.4 and the maximum normalized difference water index is less than or equal to 0.3, then the cultivated land plot is determined as a vegetation object; if the maximum normalized difference vegetation index of the cultivated land plot within the preset time period is greater than 0.4 and the maximum normalized difference water index is greater than 0.3, then the cultivated land plot is determined as a temporary water body object.

[0073] refer to Figure 3 Taking a plot of farmland as an example, if the NDVImax of the farmland plot is greater than 0.4 and the NDWImax is less than or equal to 0.3 within a preset time period, the farmland plot is identified as a vegetation object; if the NDVImax of the farmland plot is greater than 0.4 and the NDWImax is greater than 0.3 within a preset time period, the farmland plot is identified as a temporary water body object; if the NDVImax of the farmland plot is less than or equal to 0.3 within a preset time period, the farmland plot is identified as a permanent water body object (such as a lake).

[0074] After obtaining at least one vegetation object, the target maximum backscattering intensity (v value) of the local vegetation can be determined based on the annual maximum backscattering intensity of the at least one vegetation object; after obtaining at least one temporary water body object, the target minimum backscattering intensity (w value) of the local water body can be determined based on the minimum backscattering intensity of the at least one temporary water body object.

[0075] For example, each vegetation object corresponds to an annual maximum backscattering intensity, thus obtaining a set of annual maximum backscattering intensities. The largest maximum backscattering intensity in this set can be used as the v value, or a maximum backscattering intensity can be selected from this set using a preset percentile. Each temporary water body object corresponds to an annual minimum backscattering intensity, thus obtaining a set of annual minimum backscattering intensities. The smallest minimum backscattering intensity in this set can be used as the w value, or a maximum backscattering intensity can be selected from this set using a preset percentile.

[0076] In an exemplary embodiment, determining the target maximum backscattering intensity of local vegetation based on the maximum backscattering intensity of at least one vegetation object includes: determining the target maximum backscattering intensity of local vegetation from the maximum backscattering intensity of at least one vegetation object based on a first preset percentile; wherein, determining the target minimum backscattering intensity of local water body based on the minimum backscattering intensity of at least one temporary water body object includes: determining the target minimum backscattering intensity of local water body from the minimum backscattering intensity of at least one temporary water body object based on a second preset percentile.

[0077] For example, all values ​​in the set of maximum backscattering intensities corresponding to vegetation objects are arranged from smallest to largest, and a reasonable value is selected as the v value based on the first preset percentile; all values ​​in the set of minimum backscattering intensities corresponding to temporary water bodies are arranged from smallest to largest, and a reasonable value is selected as the w value based on the second preset percentile.

[0078] The first preset percentile and the second preset percentile can be the same or different; the first preset percentile and the second preset percentile can be set according to the terrain of the target location.

[0079] In an exemplary embodiment, the first preset percentile is greater than or equal to 10 and less than or equal to 25; when the terrain corresponding to the cultivated land image is flat, the second preset percentile is greater than or equal to 5 and less than or equal to 25; when the terrain corresponding to the cultivated land image is non-flat (e.g., hills, mountains), the second preset percentile is greater than or equal to 75 and less than or equal to 95.

[0080] Taking locations 1 to 5 as examples, the parameters w and v used for SPRMI (SAR-based Paddy Rice Mapping Index) calculations at these five test locations can be shown in Table 2.

[0081] Table 2. Parameters w and v used for SPRMI calculations at five test sites.

[0082]

[0083] Locations 1 to 3 are plains (i.e., flat terrain), while locations 4 and 5 are mountainous areas (i.e., non-flat terrain). The first preset percentile for locations 1 to 5 can be the 10th percentile, the second preset percentile for locations 1 to 3 can be the 75th percentile, and the second preset percentile for locations 4 to 5 can be the 25th percentile.

[0084] In step S108, the SAR (Synthetic Aperture Radar) time series data of each cultivated land plot within a preset time period are obtained.

[0085] Taking a plot of farmland as an example, the Sentinel-1VH time series data of the farmland plot within one year can be obtained. The Sentinel-1VH time series data can be generated based on the above Sentinel-1VH image.

[0086] Figure 4 This is a schematic diagram of a Sentinel-1VH time series as shown in an example.

[0087] refer to Figure 4 The horizontal axis represents the number of days in a year, and the vertical axis represents the Sentinel-1 backscattering intensity. After obtaining the time series data of the cultivated land plot within a preset time period, it can be filtered. The local maximum backscattering intensity p2 and local minimum backscattering intensity p2 of the cultivated land plot can be calculated using the filtered time series data.

[0088] Figure 4 The “V line” represents the maximum backscattering intensity of the target local vegetation, and the “W line” represents the minimum backscattering intensity of the target local water body. In this embodiment, an upper boundary is set to represent the maximum backscattering intensity v (i.e., the “V line”) of the target local vegetation and a lower boundary is set to represent the minimum backscattering intensity w (i.e., the “W line”) of the target local water body, thereby defining a vegetation-water body interval.

[0089] In step S110, the local maximum backscattering intensity and local minimum backscattering intensity of each cultivated land plot are determined based on SAR time series data.

[0090] Among them, SAR time series can capture signals of key rice growth stages and can be used for rice mapping in cloudy areas.

[0091] In this embodiment of the disclosure, the local maximum backscattering intensity p2 and local minimum backscattering intensity p1 of cultivated land plots in the Sentinel-1 VH time series can be used; for example, this can be achieved by finding inflection points in the Sentinel-1 time series curve (e.g., points where the curve gradient is 0). By assuming that the rice growth cycle is much longer than the rainfall event, points in the Sentinel-1 time series shorter than 40 days can be filtered out by linear interpolation (see...). Figure 4 The original and filtered Sentinel-1 time series are used to extract local maxima and minima and their backscattering intensities from the filtered Sentinel-1 time series.

[0092] In step S112, the target rice mapping index for each cultivated land plot is determined based on the local maximum and minimum backscattering intensities of each cultivated land plot, as well as the target maximum backscattering intensities of local vegetation and the target minimum backscattering intensities of local water bodies. The target rice mapping index is used to characterize the probability of planting rice in the cultivated land plot.

[0093] Taking a plot of arable land as an example, refer to Figure 4 Based on the local maximum backscattering intensity p2 and local minimum backscattering intensity p1 of the cultivated land plot, as well as the target maximum backscattering intensity (V value) of the local vegetation and the target minimum backscattering intensity (W value) of the local water body, the target rice mapping index is determined. The target rice mapping index can be a scalar between 0 and 1.

[0094] Specifically, rice is the only crop that requires a large amount of water during its growth stages. The backscattering mechanism of rice during its growth period is mainly influenced by soil moisture, plant cover, and height. During the irrigation period, due to the small size of the plants and sparse plant cover, the backscattering intensity is mainly affected by surface water. Therefore, the backscattering value at the transplanting stage is much lower than that of other unirrigated vegetation or crops. In contrast, the backscattering intensity of mature rice does not differ significantly from that of other vegetation.

[0095] Therefore, the characteristics of rice growth can be summarized as follows: the dynamic range of backscattering intensity is large throughout the entire growth cycle, which is greater than that of other crops (characteristic 1); the backscattering value during the irrigation period is low, close to that of water (characteristic 2); and the rice has high scattering characteristics during the growing season, which are similar to those of other vegetation (characteristic 3).

[0096] Therefore, in this embodiment of the disclosure, a first rice mapping index f(D), a second rice mapping index f(W), and a third rice mapping index f(V) are used to quantify three characteristics of rice cultivation throughout the entire cycle. A target rice mapping index can be determined based on these three indices. The first, second, third, and target rice mapping indices are all scalars ranging from 0 to 1. The first, second, and third rice mapping indices assess the likelihood of rice cultivation on cultivated land plots from three different characteristics, while the target rice mapping index is used to comprehensively assess the likelihood of rice cultivation on cultivated land plots.

[0097] In this embodiment of the disclosure, the first rice mapping index, the second rice mapping index, or the third rice mapping index can be used individually to assess the likelihood of planting rice on cultivated land plots, or the target rice mapping index can be used to comprehensively assess the likelihood of planting rice on cultivated land plots.

[0098] In an exemplary embodiment, the target rice mapping index for each cultivated land plot is determined based on its local maximum and minimum backscattering intensities, as well as the target maximum backscattering intensities of local vegetation and the target minimum backscattering intensities of local water bodies. This includes: determining the difference between the local maximum and minimum backscattering intensities of the cultivated land plot as the backscattering distance of the cultivated land plot; and determining the difference between the target maximum backscattering intensities of local vegetation and the target minimum backscattering intensities of local water bodies as the target depth. The first rice mapping index is determined based on the backscattering distance and target depth of the cultivated land plot; the second rice mapping index is determined based on the difference between the local minimum backscattering intensity of the cultivated land plot and the target minimum backscattering intensity of the local water body, as well as the target depth; the third rice mapping index is determined based on the difference between the target maximum backscattering intensity of the local vegetation and the local maximum backscattering intensity of the cultivated land plot, as well as the target depth; and the target rice mapping index for each cultivated land plot is determined based on the first, second, and third rice mapping indices.

[0099] In this embodiment of the disclosure, the first rice mapping index f(D) can be calculated by the ratio between the backscattering distance D (i.e., p2-p1) and the depth of the VW region (i.e., vw), that is, by a linear function: f(D) = D / (vw).

[0100] In an exemplary embodiment, the first rice mapping index can also be determined according to the following formula:

[0101]

[0102] Where f(D) represents the first rice mapping index, D represents the backscattering distance of the cultivated land plot, v represents the maximum backscattering intensity of the target of the local vegetation, and w represents the minimum backscattering intensity of the target of the local water body.

[0103] Formula (1) adjusts the value of D to 0-1 using the sigmoid function. Compared to adjusting the value of D to 0-1 using a linear function, the first rice mapping index f(D) obtained by formula (1) can amplify the difference between rice and other crops and better distinguish rice from other crops.

[0104] Figure 5 This is a schematic diagram showing the comparison of the separability of rice and other land cover using linear and sigmoid functions, respectively.

[0105] refer to Figure 5 (a) compares the separability of rice and other land cover using a linear function, and (b) compares the separability of rice and other land cover using the sigmoid function. It can be seen that the sigmoid function can better distinguish rice from other crops.

[0106] Because rice has a large dynamic range of backscattering intensity throughout its growth cycle, meaning that the dynamic range of backscattering intensity of rice throughout its growth cycle is greater than that of other crops, the First Rice Mapping Index can characterize the dynamic range of backscattering intensity of cultivated land plots. Therefore, rice can be distinguished from other crops through the First Rice Mapping Index.

[0107] The second rice mapping index f(W) can be determined according to the following formula:

[0108]

[0109] Where f(W) represents the second rice mapping index, and p1 represents the local minimum backscattering intensity of the cultivated land plot.

[0110] For the second rice mapping index f(W), the quadratic function of formula (2) is used to calculate the relative difference between the p1 and W lines. The probability of rice cultivation is represented by a value between 0 and 1, while the difference between rice and other land cover is amplified by squaring.

[0111] Because rice has a low backscattering value during the irrigation period, which is close to that of water, the second rice mapping index can characterize the degree of similarity between the local minimum backscattering intensity of cultivated land and the target minimum backscattering intensity of local water bodies. Therefore, rice can be distinguished from other crops through the second rice mapping index.

[0112] The third rice mapping index can be determined using the following formula:

[0113]

[0114] Where f(V) represents the third rice mapping index, and p2 represents the local maximum backscattering intensity of the cultivated land plot.

[0115] For the third rice mapping index f(V), the quadratic function of formula (3) is used to calculate the relative difference between the V line and p2. The probability of rice cultivation is represented by a value between 0 and 1, while the difference between rice and other land cover is amplified by squaring.

[0116] Because rice has high scattering characteristics during its growth period, the third rice mapping index can characterize the degree of similarity between the local maximum backscattering intensity of cultivated land plots and the target maximum backscattering intensity of local vegetation. Therefore, the third rice mapping index can be used to distinguish rice from other crops.

[0117] The target rice mapping index SPRMI can be determined using the following formula:

[0118] SPRMI=f(D)×f(W)×f(V) (4)

[0119] The first rice mapping index f(D), the second rice mapping index f(W), and the third rice mapping index f(V) all range from 0 to 1. Higher values ​​for these three parameters indicate a greater likelihood of rice cultivation. Furthermore, the target rice mapping index SPRMI, derived from these three indices, also ranges from 0 to 1, with a higher SPRMI indicating a greater likelihood of rice cultivation. Compared to using a single measurement, the combined use of these three measurements provides a more reliable estimate of the probability of rice cultivation.

[0120] In an exemplary embodiment, the method may further include: classifying the cultivated land plot as a rice plot if the rice survey index of the cultivated land plot is greater than or equal to a preset threshold; and classifying the cultivated land plot as a non-rice plot if the rice survey index of the cultivated land plot is less than the preset threshold.

[0121] In this embodiment of the disclosure, a preset threshold can be set, and the cultivated land plot can be classified into a rice plot or a non-rice plot based on the relationship between the preset threshold and the rice mapping index of the cultivated land plot.

[0122] In an exemplary embodiment, the preset threshold can be set to a value greater than or equal to 0.5 and less than or equal to 0.7. For example, the preset threshold can be set to 0.6.

[0123] In this embodiment of the disclosure, the threshold for distinguishing between rice and non-rice cover from SPRMI is relatively easy to determine because SPRMI effectively balances misclassification and omission errors and eliminates location differences.

[0124] Figure 6 The diagram shows the ROC curves for locations 1 to 5 and a schematic diagram of the sensitivity analysis of the SPRMI binary classification threshold for locations 1 to 5.

[0125] like Figure 6 (a) The Receiver Operating Characteristic (ROC) curve shows that the rice mapping index proposed in this disclosure is insensitive to location differences, i.e., it is not constrained by geographical location; the area under the ROC curve (AUC ROC) ranges from 0.92 to 0.98, indicating good separation between rice and non-rice crops. This threshold can be determined according to the user's needs, depending on whether the user is more concerned with misclassification error or omission error. Typically, UA increases with increasing threshold, while PA decreases with increasing threshold. Figure 6 As shown in (b), the test results from five locations indicate that by balancing UA and PA, any value of the preset threshold in the range of 0.5 to 0.7 can effectively distinguish between rice and non-rice, thereby generating an accurate rice map.

[0126] In an exemplary embodiment, the method may further include: generating a rice mapping map corresponding to the cultivated land image based on the target rice mapping index of each cultivated land plot.

[0127] Figure 7 The diagram shows the farmland images, SPRMI maps, rice mapping results, and reference maps corresponding to locations 1 to 5.

[0128] It can be seen that, Figure 7 (The second column) shows the SPRMI values ​​for five locations. It indicates the correlation between farmland plots with high SPRMI values ​​and irrigated areas in Sentinel-2. Figure 7 The dark areas in the first column of the image match very well. In rice cultivation practice, the land needs to be irrigated before transplanting. Furthermore, it can be seen that cultivated land plots with low SPRMI values ​​match the areas with natural vegetation and other land cover. Objects with moderate SPRMI values ​​are less frequent across all locations, indicating that SPRMI values ​​can effectively distinguish between rice and non-rice crops. Figure 7 The changes in SPRMI values ​​in paddy fields are also shown (e.g., the light to dark areas in the SPRMI plot), which may be caused by biophysical factors (e.g., different seeding densities) and environmental factors (e.g., irrigation).

[0129] A map showing the rice planting area at five locations based on SPRMI values ​​is shown below. Figure 7 (Third column) As shown. Rice maps for all locations were generated by classifying SPRMI images using a threshold of 0.6, but this disclosure is not limited thereto. A visual comparison was made between the SPRMI segmentation results for locations 1 to 3 and the rice maps in the reference, revealing that the classification maps for these three locations were consistent with the reference map ( Figure 7 The fourth column in the image shows high consistency. Location 1 shows the highest consistency, with rice cultivation dominating. In the two test locations, Locations 4 and 5, rice is mainly distributed in flat valleys in mountainous areas. The magnified areas of Locations 4 and 5 are the visual effect of overlaying the detected rice paddies onto the Sentinel-2 image, showing that rice paddies can be well distinguished from other land cover (such as roads in Location 4) even in complex terrain.

[0130] The method for rice mapping provided in this disclosure determines the maximum normalized difference vegetation index and the maximum normalized difference water index for each cultivated land plot within a preset time period based on cultivated land images within that time period. Based on these indices, it determines the target maximum backscattering intensity of local vegetation and the target minimum backscattering intensity of local water bodies. It also determines the local maximum and minimum backscattering intensities for each cultivated land plot based on SAR time series data. Finally, it determines the target rice mapping index for each cultivated land plot based on these local maximum and minimum backscattering intensities, as well as the target maximum and minimum backscattering intensities of the local vegetation and water bodies, thus characterizing the probability of rice cultivation in the cultivated land plot. The target rice mapping index obtained by this method can effectively distinguish rice from other crops, especially in heterogeneous agricultural areas where rice and other crops are intercropped, where its application effect is even better. Furthermore, this method does not require prior information, reference samples, or many predefined parameters, avoiding the collection of a large number of training samples. It features high automation, high flexibility, ease of application, and good robustness, supporting large-area rice mapping, and is particularly suitable for cloudy areas where optical remote sensing data is not frequently available. This method is independent of climatic conditions and has good applicability under different climatic conditions, adaptively considering local conditions and achieving robust mapping results in different regions. Moreover, the target rice mapping index obtained by this method is a continuous variable related to the probability or coverage of rice cultivation, providing more objective and flexible rice mapping than hard classification.

[0131] The accuracy of the target rice mapping indicators obtained through the embodiments of this disclosure will be explained below.

[0132] Validation sample sets from locations 1 to 5 were obtained to validate the target rice mapping indicators. The validation sample sets for locations 4 and 5 could be ground survey samples, such as 30 rice planting samples collected based on field observations at location 4. Ground data for location 5 could include 53 rice samples and 50 non-rice samples. Validation sample sets from locations 1 to 3 were collected from relevant websites providing farmland data for the test locations.

[0133] In this embodiment of the disclosure, producer's accuracy (PA), user's accuracy (UA), overall accuracy (OA), and F1 score are used to evaluate the accuracy of rice mapping; PA, UA, OA, and F1 can be determined by the following formula:

[0134]

[0135]

[0136]

[0137]

[0138] Where x R x represents the number of samples with actual rice coverage classified as rice. i* x represents the total number of samples classified as rice. *j This represents the number of samples with actual rice cover. Sd is the number of correctly classified samples, and n represents the total number of validation samples.

[0139] The target rice mapping indicators obtained through this embodiment were used to classify farmland images at locations 1 to 5. The accuracy of the classification results for locations 1 to 5 was then evaluated separately, and the results are shown in Table 3. It can be seen that the OA (Option Aspect Ratio) for locations 1 to 5 is greater than or equal to 0.88, and the PA (Proportional Aspect Ratio) is greater than or equal to 0.91. This indicates that the method has successfully identified most rice-covered objects at all locations. Unlike PA, UA reflects the method's ability to distinguish rice from other land cover. Except for location 2 (UA of 0.82), the UA for other locations reached 0.9. This may be because the rice-covered areas at location 2 are more complexly interbedded with other crops. Therefore, irrigation processes may affect plots near the rice paddies, making it difficult to distinguish rice from other nearby crops.

[0140] Table 3

[0141]

[0142] Table 4 compares the method proposed in this disclosure with two related rule-based rice mapping methods. The UA and PA of the three methods were compared at five study sites, revealing that the method proposed in this disclosure has a higher UA and a similar PA. Therefore, the method proposed in this disclosure can better balance the relationship between misclassification and omission errors. As shown in Table 4, at site 1, all three methods performed well, with PA and UA exceeding 0.9, indicating that these methods can be used for rice mapping in areas where rice is the main crop. At sites 2 and 3, the UA of the method proposed in this disclosure is significantly higher than that of the other two methods. Compared with the phenology-based decision tree method, the UA at sites 2 and 3 increased by 0.26 and 0.42, respectively. Compared with the ARM-SARFS method, the UA at site 3 increased by 0.40. This indicates that the method proposed in this disclosure can reduce classification confusion by amplifying the differences between rice and other land cover, which is the biggest challenge in rice mapping when rice is mixed with other crops (e.g., at sites 2 and 3).

[0143] Table 4. Evaluation results of rice user accuracy (UA) and producer accuracy (PA) using three different methods.

[0144]

[0145] Figure 8 A schematic diagram showing the accuracy of rice surveying at locations 1 to 4 based on three methods is presented.

[0146] refer to Figure 8 It can be seen that, taking into account the first rice mapping index f(D), the second rice mapping index f(W), and the third rice mapping index f(V), the results are significantly better than those obtained by using f(V) and f(W) or by using only f(V).

[0147] It should be noted that, Figure 8 In this context, “f(V)+f(W)+f(D)” means to consider f(D), f(W) and f(V) together, rather than simply adding f(D), f(W) and f(V); similarly, “f(V)+f(W)” means to consider f(W) and f(V) together, rather than simply adding f(W) and f(V) together.

[0148] Using only f(V), it is difficult to separate rice from other vegetation cover due to the similar volumetric scattering characteristics exhibited by rice to other vegetation cover. f(W) can reduce the error by filtering out vegetation cover without flooding signals (e.g., natural vegetation cover and maize), especially for locations 2 and 3. f(D) can further reduce the confusion between rice and other crops with a moist soil background. Therefore, the SPRMI index, which combines the three characteristics, effectively reduces the confusion between rice and other vegetation cover such as natural vegetation and various crops, thus achieving the highest F1 score for all test locations.

[0149] Figure 9 Histograms showing SPRMI values, local minimum backscatter intensity at transplanting time, dynamic backscatter range, and transplanting date for validation samples of rice (light bars) and non-rice (dark bars) are presented.

[0150] The method proposed in this disclosure can amplify the difference between rice and other land cover by nonlinearly rescaling the characteristics, which differs from existing methods for paddy field extraction using original characteristics.

[0151] Original characteristics include local minimum SAR backscatter intensity, dynamic backscatter range, and rice transplanting date, etc. See [link to relevant documentation]. Figure 9 Columns two through four show that these raw characteristics have some ability to distinguish between paddy fields and non-paddy fields, but it is difficult to find a suitable threshold to differentiate between paddy fields and other paddy fields. Furthermore, a threshold that has been effectively trained may not be applicable to different locations.

[0152] In the method proposed in this disclosure embodiment, SPRMI amplifies the difference in index values ​​between rice and non-rice cover; that is, the SPRMI value of rice fields is higher, close to 1, while the SPRMI value of all non-rice fields is lower, close to 0. This makes the intersection of rice and non-rice in the histogram of SPRMI values ​​smaller than the histograms of other original features. Figure 9 (First column). The small overlap in the histogram of SPRMI values ​​between paddy fields and non-paddy fields indicates that a uniform threshold for distinguishing paddy fields and non-paddy fields using this index can be easily determined for all locations.

[0153] Figure 10 A schematic diagram comparing the accuracy (F1 score) of rice mapping using the local adaptive parameter method with that using the uniform parameter method is shown.

[0154] The method proposed in this disclosure incorporates two regional adaptive parameters: an upper boundary "V-line" (v) and a lower boundary "W-line" (w), to accommodate differences in geographical and climatic backgrounds across different research locations. Comparing the method using local adaptive parameters in this disclosure with methods using uniform parameters in related technologies reveals a significant improvement in the F1 score. This is because SAR backscatter values ​​and their dynamic range vary depending on the location, terrain conditions, rice variety and planting, and the angle of incidence in different regions. Therefore, the method of collecting SPRMI parameters from samples surrounding the target rice paddy can eliminate locational differences.

[0155] Figure 11 The F1 scores for locations 1 through 5 are shown after selecting the V and W lines using different percentiles.

[0156] refer to Figure 11 The V and W lines correspond to v and w, respectively. These two parameters are determined automatically and adaptively based on Sentinel-2 images, which reduces the reliance on prior information found in other existing methods. These two parameters, v and w, can be determined using only the vegetation index and moisture index, which determine percentiles. The method proposed in this disclosure investigates the sensitivity of rice mapping accuracy to percentile selection, providing guidance for users to apply the proposed method in any other location.

[0157] Specifically, SPRMI is calculated by selecting different percentiles, namely the 5th, 10th, 25th, 50th, 75th, 90th, and 95th percentiles of the candidate backscattering intensity values, as the values ​​of v and w. Figure 11 The F1 scores for rice mapping at each location are shown for different combinations of v and w values. The results indicate that at location 1, where rice is the primary crop, mapping accuracy is insensitive to the percentiles of v and w. At the other four locations, the F1 score is more sensitive to w than to v. Figure 11 A wide range of v and w values ​​are displayed. The large range allows for obtaining the desired results at each location (e.g., F1 score > 0.8), indicating that users can easily select the appropriate percentile.

[0158] In this embodiment of the disclosure, it is recommended to select the 10th to 25th percentiles to determine the v value at any location because rice typically has relatively low backscattering compared to other vegetation and crops. For the w value, it is recommended to select the 5th to 25th percentiles for flat terrain (e.g., locations 1–3) and the 75th to 95th percentiles for hilly terrain (e.g., locations 4 and 5), because C-band backscattering is negatively correlated with water depth and hilly terrain is more likely to have deeper water surfaces during irrigation compared to paddy fields.

[0159] It should also be understood that the above is only to help those skilled in the art better understand the embodiments of this disclosure, and is not intended to limit the scope of the embodiments of this disclosure. Those skilled in the art can obviously make various equivalent modifications or changes based on the examples given above. For example, some steps in the above methods may be unnecessary, or new steps may be added, etc. Alternatively, any combination of any two or more of the above embodiments may be used. Such modifications, changes, or combinations also fall within the scope of the embodiments of this disclosure.

[0160] It should also be understood that the above description of the embodiments of this disclosure focuses on highlighting the differences between the various embodiments. Similarities or differences not mentioned can be referred to each other, and for the sake of brevity, they will not be repeated here.

[0161] It should also be understood that the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this disclosure.

[0162] It should also be understood that, in the various embodiments of this disclosure, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions between different embodiments are consistent and can be referenced by each other, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0163] The foregoing has detailed examples of methods for rice surveying provided in this disclosure. It is understood that, in order to achieve the above functions, the computer device includes corresponding hardware structures and / or software modules for performing each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this disclosure can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0164] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein. For details not disclosed in the apparatus embodiments of this disclosure, please refer to the embodiments of the method disclosed herein.

[0165] Figure 12 This is a block diagram illustrating an apparatus for rice surveying according to an exemplary embodiment.

[0166] like Figure 12 As shown, the apparatus 1200 for rice surveying may include an acquisition module 1202 and a determination module 1204.

[0167] The acquisition module 1202 is used to obtain farmland images within a preset time period, wherein the farmland images include multiple farmland plots; the determination module 1204 is used to determine the maximum normalized difference vegetation index and the maximum normalized difference water index for each farmland plot within the preset time period; the determination module 1204 is also used to determine the target maximum backscattering intensity of local vegetation and the target minimum backscattering intensity of local water bodies based on the maximum normalized difference vegetation index and the maximum normalized difference water index for each farmland plot within the preset time period; the acquisition module 1202 is also used to acquire images of each farmland plot within the preset time period. The determination module 1204 is further configured to determine the local maximum backscattering intensity and local minimum backscattering intensity of each cultivated land plot based on the SAR time series data; the determination module 1204 is further configured to determine the target rice mapping index of each cultivated land plot based on the local maximum backscattering intensity and local minimum backscattering intensity of each cultivated land plot, as well as the target maximum backscattering intensity of the local vegetation and the target minimum backscattering intensity of the local water body, wherein the target rice mapping index is used to characterize the probability of planting rice in the cultivated land plot.

[0168] In an exemplary embodiment, the apparatus further includes a classification module, configured to classify the cultivated land plot as a rice plot if the rice survey index of the cultivated land plot is greater than or equal to a preset threshold, and to classify the cultivated land plot as a non-rice plot if the rice survey index of the cultivated land plot is less than the preset threshold.

[0169] In an exemplary embodiment, the preset threshold is greater than or equal to 0.5 and less than or equal to 0.7.

[0170] In an exemplary embodiment, the determining module 1204 is further configured to determine at least one vegetation object and at least one temporary water body object from each cultivated land plot based on the normalized difference vegetation index and normalized difference water index of each cultivated land plot within the preset time period; determine the target maximum backscattering intensity of the local vegetation based on the maximum backscattering intensity of the at least one vegetation object; and determine the target minimum backscattering intensity of the local water body based on the minimum backscattering intensity of the at least one temporary water body object.

[0171] In an exemplary embodiment, the determining module 1204 is further configured to determine the cultivated land plot as the vegetation object if the maximum normalized difference vegetation index of the cultivated land plot is greater than 0.4 and the maximum normalized difference water index is less than or equal to 0.3 within the preset time period; and to determine the cultivated land plot as the temporary water body object if the maximum normalized difference vegetation index of the cultivated land plot is greater than 0.4 and the maximum normalized difference water index is greater than 0.3 within the preset time period.

[0172] In an exemplary embodiment, the determining module 1204 is further configured to determine the target maximum backscattering intensity of the local vegetation from the maximum backscattering intensity of the at least one vegetation object based on a first preset percentile; wherein, determining the target minimum backscattering intensity of the local water body based on the minimum backscattering intensity of the at least one temporary water body object includes: determining the target minimum backscattering intensity of the local water body from the minimum backscattering intensity of the at least one temporary water body object based on a second preset percentile.

[0173] In an exemplary embodiment, the first preset percentile is greater than or equal to 10 and less than or equal to 25; when the terrain corresponding to the cultivated land image is flat, the second preset percentile is greater than or equal to 5 and less than or equal to 25; when the terrain corresponding to the cultivated land image is non-flat, the second preset percentile is greater than or equal to 75 and less than or equal to 95.

[0174] In an exemplary embodiment, the determining module 1204 is further configured to determine the difference between the local maximum backscattering intensity and the local minimum backscattering intensity of the cultivated land plot as the backscattering distance of the cultivated land plot; determine the difference between the target maximum backscattering intensity of the local vegetation and the target minimum backscattering intensity of the local water body as the target depth; determine a first rice mapping index based on the backscattering distance of the cultivated land plot and the target depth; determine a second rice mapping index based on the difference between the local minimum backscattering intensity of the cultivated land plot and the target minimum backscattering intensity of the local water body, and the target depth; determine a third rice mapping index based on the difference between the target maximum backscattering intensity of the local vegetation and the local maximum backscattering intensity of the cultivated land plot, and the target depth; and determine the target rice mapping index for each cultivated land plot based on the first rice mapping index, the second rice mapping index, and the third rice mapping index.

[0175] In an exemplary embodiment, the first rice mapping index is determined according to the following formula:

[0176]

[0177] Where f(D) represents the first rice mapping index, D represents the backscattering distance of the cultivated land plot, v represents the maximum backscattering intensity of the target of the local vegetation, and w represents the minimum backscattering intensity of the target of the local water body;

[0178] The second rice mapping index is determined according to the following formula:

[0179]

[0180] Where f(W) represents the second rice mapping index, and p1 represents the local minimum backscattering intensity of the cultivated land plot;

[0181] The third rice mapping index is determined according to the following formula:

[0182]

[0183] Where f(V) represents the third rice mapping index, and p2 represents the local maximum backscattering intensity of the cultivated land plot.

[0184] In an exemplary embodiment, the apparatus further includes a generation module, configured to generate a rice mapping map corresponding to the cultivated land image based on the target rice mapping index of each cultivated land plot.

[0185] It should be noted that the block diagrams shown in the above figures are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor terminal devices and / or microcontroller terminal devices.

[0186] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0187] Figure 13 This is a schematic diagram illustrating the structure of an electronic device suitable for implementing exemplary embodiments of the present disclosure, according to an exemplary embodiment. It should be noted that... Figure 13 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0188] like Figure 13 As shown, the electronic device 1300 includes a central processing unit (CPU) 1301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1302 or a program loaded from a storage section 1308 into a random access memory (RAM) 1303. The RAM 1303 also stores various programs and data required for the operation of the system 1300. The CPU 1301, ROM 1302, and RAM 1303 are interconnected via a bus 1304. An input / output (I / O) interface 1305 is also connected to the bus 1304.

[0189] The following components are connected to I / O interface 1305: an input section 1306 including a keyboard, mouse, etc.; an output section 1307 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1308 including a hard disk, etc.; and a communication section 1309 including a network interface card such as a LAN card, modem, etc. The communication section 1309 performs communication processing via a network such as the Internet. A drive 1310 is also connected to I / O interface 1305 as needed. Removable media 1311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 1310 as needed so that computer programs read from them can be installed into storage section 1308 as needed.

[0190] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1309, and / or installed from removable medium 1311. When the computer program is executed by central processing unit (CPU) 1301, it performs the functions defined above in the system of this disclosure.

[0191] It should be noted that the computer-readable medium disclosed herein may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0192] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0193] The units described in the embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor can be described as including a sending unit, an acquisition unit, a determining unit, and a first processing unit. The names of these units do not necessarily limit the specific unit; for example, a sending unit can also be described as "a unit that sends an image acquisition request to a connected server."

[0194] In another aspect, this disclosure also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable storage medium carries one or more programs that, when executed by the electronic device, cause the electronic device to perform the methods described in the above embodiments. For example, the electronic device may perform... Figure 1 The steps shown.

[0195] According to one aspect of this disclosure, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in various optional implementations of the above embodiments.

[0196] It should be understood that any number of elements in the accompanying drawings is for illustrative purposes only and not for limitation, and any naming is for distinction only and has no limiting meaning.

[0197] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0198] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for rice surveying, characterized in that, include: Acquire farmland images within a preset time period, wherein the farmland images include multiple farmland plots; Determine the maximum normalized difference vegetation index and the maximum normalized difference water index for each cultivated land plot within the preset time period; Based on the maximum normalized difference vegetation index and the maximum normalized difference water index of each cultivated land plot within the preset time period, determine the target maximum backscattering intensity of local vegetation and the target minimum backscattering intensity of local water body. Acquire the synthetic aperture radar (SAR) time series data of each cultivated land plot within the preset time period. The local maximum and local minimum backscattering intensities of each cultivated land plot were determined based on the SAR time series data. Based on the local maximum and minimum backscattering intensities of each cultivated land plot, as well as the target maximum backscattering intensity of the local vegetation and the target minimum backscattering intensity of the local water body, the target rice mapping index for each cultivated land plot is determined, wherein the target rice mapping index is used to characterize the probability of planting rice in the cultivated land plot.

2. The method according to claim 1, characterized in that, Also includes: If the rice survey index of the cultivated land plot is greater than or equal to a preset threshold, the cultivated land plot will be classified as a rice plot. If the rice survey index of the cultivated land plot is less than the preset threshold, the cultivated land plot will be classified as a non-rice plot.

3. The method according to claim 2, characterized in that, The preset threshold is greater than or equal to 0.5 and less than or equal to 0.

7.

4. The method according to claim 1, characterized in that, Based on the maximum normalized difference vegetation index and the maximum normalized difference water index of each cultivated land plot within a preset time period, determine the target maximum backscattering intensity of local vegetation and the target minimum backscattering intensity of local water bodies, including: Based on the maximum normalized difference vegetation index and the maximum normalized difference water index of each cultivated land plot within the preset time period, at least one vegetation object and at least one temporary water body object are identified from each cultivated land plot. The target maximum backscattering intensity of the local vegetation is determined based on the maximum backscattering intensity of the at least one vegetation object. The target minimum backscattering intensity of the local water body is determined based on the minimum backscattering intensity of the at least one temporary water body object.

5. The method according to claim 4, characterized in that, Based on the maximum normalized difference vegetation index and the maximum normalized difference water index of each cultivated land plot within the preset time period, at least one vegetation object and at least one temporary water body object are identified from each cultivated land plot, including: If the maximum normalized difference vegetation index of the cultivated land plot is greater than 0.4 and the maximum normalized difference water index is less than or equal to 0.3 within the preset time period, then the cultivated land plot is identified as the vegetation object. If the maximum normalized difference vegetation index of the cultivated land plot is greater than 0.4 and the maximum normalized difference water index is greater than 0.3 within the preset time period, then the cultivated land plot is identified as the temporary water body object.

6. The method according to claim 4, characterized in that, Determining the target maximum backscattering intensity of the local vegetation based on the maximum backscattering intensity of the at least one vegetation object includes: The target maximum backscattering intensity of the local vegetation is determined from the maximum backscattering intensity of the at least one vegetation object based on a first preset percentile. Determining the target minimum backscattering intensity of the local water body based on the minimum backscattering intensity of the at least one temporary water body object includes: The target minimum backscattering intensity of the local water body is determined from the minimum backscattering intensity of the at least one temporary water body object based on a second preset percentile.

7. The method according to claim 6, characterized in that, The first preset percentile is greater than or equal to 10 and less than or equal to 25; When the terrain corresponding to the cultivated land image is flat, the second preset percentile is greater than or equal to 5 and less than or equal to 25. When the terrain corresponding to the cultivated land image is non-flat, the second preset percentile is greater than or equal to 75 and less than or equal to 95.

8. The method according to claim 1, characterized in that, Based on the local maximum and minimum backscattering intensities of each cultivated land plot, as well as the target maximum backscattering intensity of the local vegetation and the target minimum backscattering intensity of the local water body, the target rice mapping index for each cultivated land plot is determined, including: The difference between the local maximum backscattering intensity and the local minimum backscattering intensity of the cultivated land plot is determined as the backscattering distance of the cultivated land plot; The difference between the maximum backscattering intensity of the target in the local vegetation and the minimum backscattering intensity of the target in the local water body is determined as the target depth. The first rice mapping index is determined based on the backscattering distance of the cultivated land plot and the target depth; The second rice mapping index is determined based on the difference between the local minimum backscatter intensity of the cultivated land plot and the target minimum backscatter intensity of the local water body, as well as the target depth. The third rice mapping index is determined based on the difference between the target maximum backscattering intensity of the local vegetation and the local maximum backscattering intensity of the cultivated land plot, as well as the target depth. The target rice mapping index for each cultivated land plot is determined based on the first rice mapping index, the second rice mapping index, and the third rice mapping index.

9. The method according to claim 8, characterized in that, The first rice mapping index is determined according to the following formula: Where f(D) represents the first rice mapping index, D represents the backscattering distance of the cultivated land plot, v represents the maximum backscattering intensity of the target of the local vegetation, and w represents the minimum backscattering intensity of the target of the local water body; The second rice mapping index is determined according to the following formula: Where f(W) represents the second rice mapping index, and p1 represents the local minimum backscattering intensity of the cultivated land plot; The third rice mapping index is determined according to the following formula: Where f(V) represents the third rice mapping index, and p2 represents the local maximum backscattering intensity of the cultivated land plot.

10. The method according to any one of claims 1-9, characterized in that, Also includes: Based on the target rice mapping index for each cultivated land plot, a rice mapping map corresponding to the cultivated land image is generated.

11. A device for rice surveying, characterized in that, include: The acquisition module is used to obtain farmland images within a preset time period, wherein the farmland images include multiple farmland plots; The determination module is used to determine the maximum normalized difference vegetation index and the maximum normalized difference water index for each cultivated land plot within the preset time period. The determining module is also used to determine the target maximum backscattering intensity of local vegetation and the target minimum backscattering intensity of local water body based on the maximum normalized difference vegetation index and the maximum normalized difference water index of each cultivated land plot within the preset time period. The acquisition module is also used to acquire the synthetic aperture radar (SAR) time series data of each cultivated land plot within the preset time period. The determining module is also used to determine the local maximum backscattering intensity and local minimum backscattering intensity of each cultivated land plot based on the SAR time series data; The determining module is further configured to determine the target rice mapping index for each cultivated land plot based on the local maximum and minimum backscattering intensities of each cultivated land plot, as well as the target maximum backscattering intensities of the local vegetation and the target minimum backscattering intensities of the local water bodies, wherein the target rice mapping index is used to characterize the probability of planting rice in the cultivated land plot.

12. An electronic device, characterized in that, include: At least one processor; A storage device for storing at least one program, which, when executed by the at least one processor, causes the at least one processor to implement the method as described in any one of claims 1 to 9.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 9.

Images