Rice identification method based on growth early stage short time sequence SAR image

Abstract

The invention relates to a rice identification method based on a growth early-stage short time sequence SAR image, and the method comprises the steps: obtaining rice growth early-stage time sequence SAR data in a target region, and carrying out the preprocessing of the rice growth early-stage time sequence SAR data, so as to obtain standard early-stage SAR data; collecting target historical SAR data of rice growth in the target area, calculating a water body backscattering value and a vegetation backscattering value of the target area according to the target historical SAR data, and calculating a rice discrimination index of the target area based on the water body backscattering value, the vegetation backscattering value and the standard early SAR data; and segmenting the rice discrimination index by using a preset SSSI threshold to obtain an index segmentation result, extracting a rice planting range in the target area according to the index segmentation result, and identifying the rice earliest identification period of the target area through the rice planting range. Therefore, the problems that an existing rice early-stage extraction method depends on priori knowledge, and the regional popularization ability is poor are solved.

Description

Technical Field

[0001] The present application relates to the technical field of radar remote sensing image processing, and in particular to a rice recognition method based on short-time series SAR images in the early growth stage. Background Art

[0002] Traditional field survey methods for monitoring rice-growing areas require a lot of manpower and material resources, making it difficult to conduct large-scale monitoring. Remote sensing images have the characteristics of high efficiency, wide coverage, and low consumption of manpower and material resources, making it possible to monitor crops over a large area and over a long period of time. However, optical remote sensing is easily affected by weather such as clouds and rain, making it difficult to obtain complete and continuous observation data, and the spectral sensitivity gradually saturates as vegetation grows, which makes the optical remote sensing method have certain limitations in monitoring rice-growing areas.

[0003] Synthetic Aperture Radar (SAR) is a remote sensing system that actively emits electromagnetic waves. It is not affected by weather and has all-day and all-weather observation capabilities. SAR is sensitive to the structural characteristics and dielectric properties of crops, which makes up for the limitations of optical remote sensing and makes it possible to monitor rice-growing areas using time-series SAR images. At the same time, early determination of the rice planting range is beneficial to agriculture and land management and the formulation and adjustment of national food policies. Therefore, the use of short-time series SAR images in the early stage of crop growth to extract rice-growing areas has important research significance and application value.

[0004] At present, the crop identification methods using time-series SAR images in the early stage of crop growth are mainly divided into feature threshold method, curve feature similarity method, classification-based machine learning and deep learning methods. Among them, the feature threshold method needs to rely on prior knowledge to determine the phase suitable for threshold detection, which is difficult to apply to early crop identification in different regions; the curve feature similarity method is a relatively automated crop identification method, but it still relies on prior knowledge to collect a certain amount of representative samples to construct a standard curve and determine the time range of the standard curve; classification-based machine learning and deep learning methods rely more on prior knowledge and require a large number of training samples, so their regional promotion ability (or generalization ability) is weak.

[0005] In summary, the existing early rice extraction methods rely heavily on prior knowledge and have weak regional promotion capabilities, which needs to be urgently addressed. Summary of the invention

[0006] The present application provides a rice recognition method based on short-time series SAR images in the early growth stage, so as to solve the problems that the existing early rice extraction methods are more dependent on prior knowledge and have weak regional promotion capabilities.

[0007] The first aspect of the present application provides a rice identification method based on short-time series SAR images in the early growth stage, comprising the following steps: acquiring time-series SAR data of rice growth in the target area, and preprocessing the time-series SAR data of rice growth in the early growth stage to obtain standard early SAR data; collecting target historical SAR data of rice growth in the target area, and calculating water backscatter values ​​and vegetation backscatter values ​​of the target area based on the target historical SAR data, and calculating a rice discrimination index of the target area based on the water backscatter values, the vegetation backscatter values ​​and the standard early SAR data; segmenting the rice discrimination index using a preset SSSI threshold to obtain an index segmentation result, and extracting the rice planting range in the target area based on the index segmentation result, and identifying the earliest rice identification period of the target area through the rice planting range.

[0008] Optionally, in one embodiment of the present application, after obtaining the rice planting range within the target area according to the index segmentation result, it also includes: obtaining ground monitoring data of the target area, and performing accuracy assessment on the rice planting range through the ground monitoring data to obtain an accuracy assessment result; correcting the rice discrimination index according to the accuracy assessment result to identify a new rice planting range within the target area based on the corrected rice discrimination index.

[0009] Optionally, in one embodiment of the present application, the acquiring of early rice growth time-series SAR data in the target area and preprocessing of the early rice growth time-series SAR data to obtain standard early SAR data include: performing orbit correction processing on the early time-series SAR data based on a preset target orbit vector state file of SAR data to obtain orbit-corrected SAR data; performing a radiation calibration operation on the orbit-corrected SAR data to generate radiation-calibrated SAR data; performing a geometric calibration operation on the radiation-calibrated SAR data according to a preset range Doppler equation and a digital elevation model to obtain geometrically-calibrated SAR data; and performing coherent speckle filtering on the geometrically-calibrated SAR data to obtain the standard early SAR data.

[0010] Optionally, in one embodiment of the present application, the water backscatter value and the vegetation backscatter value of the target area are calculated according to the target historical SAR data, and the rice discrimination index of the target area is calculated based on the water backscatter value, the vegetation backscatter value and the standard early SAR data, including: calculating the water backscatter value and the vegetation backscatter value based on the target historical SAR data and a preset land use and surface cover data set; obtaining a field time-series backscatter curve of the target crop in the target area, and determining the field The method comprises the following steps: obtaining the minimum value of the time series backscatter curve and the water body similarity of the water body backscatter value; obtaining the maximum value after the minimum value on the field time series backscatter curve, and determining the vegetation similarity between the maximum value and the vegetation backscatter value; obtaining the field time series backscatter dynamic range of the target crop, and determining the rice field scattering similarity between the field time series backscattering dynamic range and the rice field based on the water body backscatter value and the vegetation backscatter value; calculating the rice discrimination index based on the water body similarity, the vegetation similarity and the rice field scattering similarity.

[0011] Optionally, in one embodiment of the present application, the mathematical expression of the rice discrimination index is:

[0012] SSSI=f(p1)*f(p2)*f(p1,p2)

[0013] Among them, SSSI represents the rice discrimination index; p1 represents the minimum value of the field time series backscattering curve; p2 represents the maximum value after the minimum value on the field time series backscattering curve; f(p1) represents the water body similarity; f(p2) represents the vegetation similarity; f(p1, p2) represents the rice field scattering similarity.

[0014] The second aspect of the present application provides a rice identification device based on short-time SAR images in the early growth stage, including: a preprocessing module, used to obtain time-series SAR data of rice growth in the target area, and preprocess the time-series SAR data of rice growth in the early growth stage to obtain standard early SAR data; an acquisition module, used to acquire target historical SAR data of rice growth in the target area, and calculate the water body backscatter value and vegetation backscatter value of the target area based on the target historical SAR data, and calculate the rice discrimination index of the target area based on the water body backscatter value, the vegetation backscatter value and the standard early SAR data; an identification module, used to segment the rice discrimination index using a preset SSSI threshold to obtain an index segmentation result, and extract the rice planting range in the target area according to the index segmentation result, and identify the earliest rice identification period of the target area through the rice planting range.

[0015] Optionally, in one embodiment of the present application, it also includes: an evaluation module, used to obtain ground monitoring data of the target area after obtaining the rice planting range in the target area according to the index segmentation result, and perform accuracy evaluation on the rice planting range through the ground monitoring data to obtain an accuracy evaluation result; a correction module, used to correct the rice discrimination index according to the accuracy evaluation result, so as to identify a new rice planting range in the target area based on the corrected rice discrimination index.

[0016] Optionally, in one embodiment of the present application, the preprocessing module includes: an orbit correction unit, used to perform orbit correction processing on the early time series SAR data based on a preset target orbit vector state file of the SAR data to obtain orbit correction SAR data; a radiation calibration unit, used to perform a radiation calibration operation on the orbit correction SAR data to generate radiation calibration SAR data; a geometric calibration unit, used to perform a geometric calibration operation on the radiation calibration SAR data according to a preset range Doppler equation and a digital elevation model to obtain geometric calibration SAR data; a filtering unit, used to perform coherent speckle filtering on the geometric calibration SAR data to obtain the standard early SAR data.

[0017] Optionally, in one embodiment of the present application, the acquisition module includes: a first calculation unit, used to calculate the water body backscatter value and the vegetation backscatter value based on the target historical SAR data and a preset land use and surface cover data set; an acquisition unit, used to obtain the field time-series backscatter curve of the target crop in the target area, and determine the minimum value of the field time-series backscatter curve and the water body similarity of the water body backscatter value; a first determination unit, used to obtain the maximum value after the minimum value on the field time-series backscatter curve, and determine the maximum value and the vegetation similarity of the vegetation backscatter value; a second determination unit, used to obtain the field time-series backscatter dynamic range of the target crop, and determine the field time-series backscatter dynamic range and the rice field scattering similarity of the rice field based on the water body backscatter value and the vegetation backscatter value; a second calculation unit, used to calculate the rice discrimination index based on the water body similarity, the vegetation similarity and the rice field scattering similarity.

[0018] Optionally, in one embodiment of the present application, the mathematical expression of the rice discrimination index is:

[0019] SSSI=f(p1)*f(p2)*f(p1,p2)

[0020] Among them, SSSI represents the rice discrimination index; p1 represents the minimum value of the field time series backscattering curve; p2 represents the maximum value after the minimum value on the field time series backscattering curve; f(p1) represents the water body similarity; f(p2) represents the vegetation similarity; f(p1, p2) represents the rice field scattering similarity.

[0021] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the rice identification method based on short-time series SAR images in the early growth stage as described in the above embodiment.

[0022] A fourth aspect of the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above rice identification method based on short-time series SAR images in the early growth stage.

[0023] The fifth aspect of the present application provides a computer program product, including a computer program, which is executed to implement the above-mentioned rice identification method based on short-time series SAR images in the early growth stage.

[0024] Therefore, the embodiments of the present application have the following beneficial effects:

[0025] The embodiment of the present application can obtain the early time-series SAR data of rice growth in the target area, and pre-process the early time-series SAR data of rice growth to obtain standard early SAR data; collect the target historical SAR data of rice growth in the target area, and calculate the water body backscatter value and vegetation backscatter value of the target area according to the target historical SAR data, and calculate the rice discrimination index of the target area based on the water body backscatter value, the vegetation backscatter value and the standard early SAR data; use the preset SSSI threshold to segment the rice discrimination index to obtain the index segmentation result, and extract the rice planting range in the target area according to the index segmentation result, and identify the earliest rice identification period of the target area through the rice planting range. The present application completes the extraction of rice planting areas by using SAR images from the rice planting period to the tillering period, thereby reducing the degree of dependence on prior knowledge, and has a wide range of adaptability, and can be used for the extraction of a wide range of rice planting areas. Therefore, the existing early rice extraction method is more dependent on prior knowledge and has weak regional promotion capabilities.

[0026] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0028] Figure 1 A flowchart of a rice identification method based on short-time series SAR images in the early growth stage provided according to an embodiment of the present application;

[0029] Figure 2 A schematic diagram of the execution logic of a rice recognition method based on short-time series SAR images in the early growth stage provided in one embodiment of the present application;

[0030] Figure 3 A schematic diagram of early characteristics of rice provided for one embodiment of the present application;

[0031] Figure 4 A schematic diagram of a change in parameters in SSSI with time-sequential image length provided by an embodiment of the present application;

[0032] Figure 5 A schematic diagram of a change in the length of a SSSI time-series image provided by an embodiment of the present application;

[0033] Figure 6 A schematic diagram of a Sigmod function provided for an embodiment of the present application;

[0034] Figure 7 This is an example diagram of a rice identification device based on short-time series SAR images in the early growth stage according to an embodiment of the present application;

[0035] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0036] Among them, 10 is a rice identification device based on short-time SAR images in the early growth stage; 100 is a preprocessing module, 200 is an acquisition module, 300 is an identification module; 801 is a memory, 802 is a processor, and 803 is a communication interface. DETAILED DESCRIPTION

[0037] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0038] The following describes the rice recognition method based on the short-time series SAR image of the early growth stage of the embodiment of the present application with reference to the accompanying drawings. In view of the problems mentioned in the above background technology, the present application provides a rice recognition method based on the short-time series SAR image of the early growth stage, in which the early time series SAR data of rice growth in the target area is obtained, and the early time series SAR data of rice growth is preprocessed to obtain standard early SAR data; the target historical SAR data of rice growth in the target area is collected, and the water body backscatter value and the vegetation backscatter value of the target area are calculated according to the target historical SAR data, and the rice discrimination index of the target area is calculated based on the water body backscatter value, the vegetation backscatter value and the standard early SAR data; the rice discrimination index is segmented by using the preset SSSI threshold to obtain the index segmentation result, and the rice planting range in the target area is extracted according to the index segmentation result, and the earliest rice recognition period of the target area is identified by the rice planting range. The present application completes the extraction of the rice planting area by using SAR images from the rice planting period to the tillering period, thereby reducing the degree of dependence on prior knowledge, and has a wide range of adaptability, and can be used for the extraction of a large range of rice planting areas. This solves the problems that the existing early rice extraction methods are more dependent on prior knowledge and have weak regional promotion capabilities.

[0039] Specifically, Figure 1 A flowchart of a rice identification method based on short-time series SAR images in the early growth stage provided in an embodiment of the present application.

[0040] like Figure 1 As shown, the rice recognition method based on short-time SAR images in the early growth stage includes the following steps:

[0041] In step S101, the time-series SAR data of the early growth stage of rice in the target area is acquired, and the time-series SAR data of the early growth stage of rice is preprocessed to obtain standard early SAR data.

[0042] The embodiments of the present application can firstly obtain the time-series SAR data (i.e., time-series SAR images) of the early stage of rice growth in the target area, and perform pre-processing operations such as orbit correction, radiation calibration, geometric correction, registration, and coherent speckle filtering on the time-series SAR images, so as to obtain standard early SAR data.

[0043] Optionally, in one embodiment of the present application, early time-series SAR data of rice growth in a target area is acquired, and the early time-series SAR data of rice growth is preprocessed to obtain standard early SAR data, including: based on a preset target orbit vector state file of SAR data, orbit correction processing is performed on the early time-series SAR data to obtain orbit-corrected SAR data; a radiation calibration operation is performed on the orbit-corrected SAR data to generate radiation-calibrated SAR data; a geometric calibration operation is performed on the radiation-calibrated SAR data according to a preset range Doppler equation and a digital elevation model to obtain geometrically calibrated SAR data; and coherent speckle filtering is performed on the geometrically calibrated SAR data to obtain standard early SAR data.

[0044] In the actual implementation process, the embodiment of the present application can perform pre-processing operations such as orbit correction, radiation calibration, geometric correction, registration and coherent speckle filtering on the time-series SAR images in sequence.

[0045] Specifically, the embodiments of the present application can first update the satellite orbit status information in the data header file by obtaining the precise orbit vector status file (i.e., the target orbit vector status file) from the European Space Agency to achieve orbit correction and obtain orbit-corrected SAR data; secondly, the embodiments of the present application can use the calibration constants obtained in advance through calibration to calculate the backscattering coefficients of the objects in the SAR image to complete the radiation calibration and obtain the radiation-calibrated SAR data; thereafter, the embodiments of the present application can use the range Doppler equation and the digital elevation model to perform geometric calibration to obtain accurate coordinate information, thereby obtaining geometrically calibrated SAR data; finally, the embodiments of the present application can use a refined Lee filter to perform filtering operations, which has a small amount of calculation, a good filtering effect, and can better maintain details such as points, lines, and edges.

[0046] Therefore, the embodiment of the present application sequentially performs orbit correction, radiation calibration, geometric correction, registration, speckle filtering and other pre-processing operations on the time-series SAR images, thereby providing a reliable data basis for the subsequent calculation of the rice discrimination index.

[0047] In step S102, target historical SAR data of rice growth in the target area is collected, and the water backscatter value and vegetation backscatter value of the target area are calculated based on the target historical SAR data, and the rice discrimination index of the target area is calculated based on the water backscatter value, the vegetation backscatter value and the standard early SAR data.

[0048] Furthermore, the embodiments of the present application can collect the target historical SAR data of rice growth in the target area, and calculate the two regional adaptive parameters of the water backscatter value (i.e., the backscatter value of the local water body) and the vegetation backscatter value (i.e., the backscatter value of the local vegetation) in the target area; thereafter, the embodiments of the present application can use the short-time series SAR images of the early stage of rice growth (i.e., the standard early SAR data) to perform rice discrimination index, such as Figure 2 As shown, the calculation of SSSI (3-Sigmoid Index) composed of three Sigmoidal components.

[0049] Optionally, in one embodiment of the present application, water backscatter values ​​and vegetation backscatter values ​​of the target area are calculated according to the target historical SAR data, and the rice discrimination index of the target area is calculated based on the water backscatter values, the vegetation backscatter values ​​and the standard early SAR data, including: calculating the water backscatter values ​​and the vegetation backscatter values ​​based on the target historical SAR data and the preset land use and surface cover data set; obtaining the field time series backscatter curve of the target crop in the target area, and determining the minimum value of the field time series backscatter curve and the water body similarity of the water body backscatter value; obtaining the maximum value after the minimum value on the field time series backscatter curve, and determining the vegetation similarity between the maximum value and the vegetation backscatter value; obtaining the field time series backscatter dynamic range of the target crop, and determining the field time series backscatter dynamic range and the rice field scattering similarity of the rice field based on the water backscatter value and the vegetation backscatter value; calculating the rice discrimination index based on the water body similarity, the vegetation similarity and the rice field scattering similarity.

[0050] In an embodiment of the present application, SSSI includes two regional adaptive parameters, namely, the calculation of local water body and vegetation baseline values ​​(i.e., water body backscatter value and vegetation backscatter value), v is the vegetation backscatter value, and w is the water body backscatter value, so as to adapt to the differences in geographical and climatic backgrounds between different study areas; in the actual implementation process, the calculation of v and w values ​​requires some understanding of the local water body and vegetation coverage.

[0051] In the specific implementation process, the embodiments of the present application can use a set of global near-real-time 10m resolution land use and surface cover datasets named "DynamicWorld", which generates land use and land cover at the corresponding time for each Sentinel-2 image, and to a certain extent avoids the influence of non-permanent water bodies and non-permanent vegetation on the calculation of v and w values; at the same time, in order to enable the embodiments of the present application to be applied to the early extraction of rice in the current season, the embodiments of the present application can use all phase SAR images of the year before the experimental year (i.e., the target historical SAR data) and the corresponding land use and surface cover data to calculate the v and w values.

[0052] In addition, the SSSI function in the embodiments of the present application includes three sub-functions, namely f(p1), f(p2), and f(p1, p2), which describe the scattering curve characteristics of rice on SAR images. For example, Figure 3 as shown, the backscattering is relatively low in the rice planting area, approaching the backscattering level of water bodies. As the rice grows rapidly, the rice biomass increases, and the SAR backscattering also increases rapidly, approaching the backscattering level of local vegetation. Therefore, a rice discrimination index is constructed based on this characteristic.

[0053] Specifically, in SSSI, the function f(p1) measures the water similarity (Characteristic 1) between the minimum value on the time-series backscattering curve of a given field block (i.e., the early time-series curve of rice) and the backscattering intensity of the local water body. Generally, when the p1 value is lower than the w value, it indicates that the backscattering intensity of this field block at this time is very low, and it can almost be confirmed as the backscattering of the water body. At this time, the value of the function is set to 1. When the p1 value is higher than the v value, it indicates that the backscattering intensity of this field block at this time is very high, and it is almost impossible for this field block to be a water body. At this time, the value of the function is set to 0. When w < p1 < v, the embodiments of the present application can use the Sigmoid function to enhance the ability of the function to distinguish rice from other crops, so that the values of f(p1) are evenly distributed at both ends of 0.5, and the f(p1) function values corresponding to smaller p1 values are closer to 1, and the f(p1) function values corresponding to larger p1 values are closer to 0, as shown in the following formula:

[0054]

[0055] Secondly, f(p2) quantifies the vegetation similarity (Characteristic 2) between the new high value on the backscattering curve of a given crop field block (i.e., the early time-series curve of rice) brought about by crop growth and the backscattering intensity v of the local vegetation, as shown in Equation (2), that is, the degree of satisfaction of the early curve with "Characteristic 2". The values of f(p2) are also evenly distributed at both ends of 0.5, and the f(p2) function values corresponding to smaller p2 values are closer to 0, and the f(p2) function values corresponding to larger p2 values are closer to 1.

[0056]

[0057] f(p1, p2) measures the paddy field scattering similarity (Characteristic 3) between the backscattering dynamic range p2 - p1 of a given crop field and the paddy field v - w; where p1 is the value of the lowest point on the backscattering curve of the field block, and p2 is the value of the highest point after the lowest point p1 on the backscattering curve of the field block, as Figure 4As shown; similarly, the embodiment of the present application can use the Sigmoid function to adjust the value of f(p1, p2) between 0 and 1 to measure the degree of satisfaction of the current curve for "Feature 3", and the higher the function value, the higher the degree of satisfaction with the feature, as shown in the following formula:

[0058]

[0059] Afterwards, the embodiment of the present application can calculate the rice discrimination index SSSI according to the water body similarity, vegetation similarity and rice field scattering similarity, thereby providing guidance and basis for obtaining the rice planting range.

[0060] Optionally, in one embodiment of the present application, the mathematical expression of the rice discrimination index is:

[0061] SSSI=f(p1)*f(p2)*f(p1,p2)

[0062] Among them, SSSI represents the rice discrimination index; p1 represents the minimum value of the field time series backscattering curve; p2 represents the maximum value after the minimum value on the field time series backscattering curve; f(p1) represents the water body similarity; f(p2) represents the vegetation similarity; f(p1,p2) represents the rice field scattering similarity.

[0063] It should be noted that the early curve of the rice field should satisfy the above three characteristics at the same time. Therefore, the SSSI in the embodiment of the present application can be designed as a multiplication combination of three Sigmoid functions, as shown in the following formula:

[0064] SSSI=f(p1)*f(p2)*f(p1,p2) (4)

[0065] Among them, SSSI represents the rice discrimination index; p1 represents the minimum value of the field time series backscattering curve; p2 represents the maximum value after the minimum value on the field time series backscattering curve; f(p1) represents the water body similarity; f(p2) represents the vegetation similarity; f(p1,p2) represents the rice field scattering similarity.

[0066] It is understandable that as the number of available time-series SAR images increases, the time-series curve becomes longer, the positions of p1 and p2 will also change in time, and the value of the Sigmoid function will also change. Figure 5 The blue curve in the middle is the rice VH backscatter value, and the red curve is a schematic diagram of the change of SSSI with the length of the sequential image. Figure 5 It can be seen that the SSSI value is distributed between 0 and 1, and can quickly capture the scattering characteristics of rice when facing the rice scattering curve.

[0067] In step S103, the rice discrimination index is segmented using a preset SSSI threshold to obtain an index segmentation result, and the rice planting range in the target area is extracted according to the index segmentation result, and the earliest rice identification period in the target area is identified through the rice planting range.

[0068] Furthermore, in the embodiment of the present application, the Sigmoid function distribution is concentrated at both ends with 0.5 as the boundary, and the Sigmoid function has the characteristic that the range distribution remains unchanged after multiple multiplications, such as Figure 6 As shown, the embodiment of the present application can use 0.5 as a threshold to segment the SSSI result (i.e., rice discrimination index). The area with an SSSI value greater than 0.5 is the rice planting range, and the earliest rice identification period in the target area is identified by the rice planting range.

[0069] Therefore, in view of the problems existing in the existing early rice extraction methods, such as reliance on prior knowledge and weak regional promotion capabilities, the embodiment of the present application constructs a comprehensive index for distinguishing rice fields by utilizing the characteristics of rapid changes in backscattering intensity on time-series SAR images in the early growth stage of rice, and proposes an unsupervised extraction method for rice-growing areas using short-time-series SAR images in the early growth stage of rice, thereby overcoming the current method's reliance on labeled data and being applicable to different climatic zones.

[0070] Optionally, in one embodiment of the present application, after obtaining the rice planting range within the target area according to the index segmentation result, it also includes: obtaining ground monitoring data of the target area, and performing accuracy assessment on the rice planting range through the ground monitoring data to obtain an accuracy assessment result; correcting the rice discrimination index according to the accuracy assessment result to identify the new rice planting range within the target area based on the corrected rice discrimination index.

[0071] In addition, after obtaining the rice planting range in the target area according to the index segmentation result, the embodiment of the present application can also obtain ground monitoring data of the target area, and use the ground monitoring data to perform accuracy assessment on the rice planting range to obtain an accuracy assessment result, and then correct the rice discrimination index according to the accuracy assessment result to re-identify the new rice planting range in the target area and improve the reliability of rice planting range identification.

[0072] Therefore, the embodiment of the present application mines short-time series SAR images in the early stage of rice growth, completes the extraction of rice planting areas in the tillering stage of rice based only on SAR images, and can be applied to different climate zones.

[0073] According to the rice recognition method based on short-time SAR images in the early growth stage proposed in the embodiment of the present application, by acquiring time-series SAR data of rice growth in the target area, and preprocessing the time-series SAR data of rice growth in the early growth stage to obtain standard early SAR data; collecting target historical SAR data of rice growth in the target area, and calculating the water body backscatter value and vegetation backscatter value of the target area based on the target historical SAR data, and calculating the rice discrimination index of the target area based on the water body backscatter value, vegetation backscatter value and standard early SAR data; using a preset SSSI threshold to segment the rice discrimination index to obtain an index segmentation result, and extracting the rice planting range in the target area according to the index segmentation result, and identifying the earliest rice recognition period of the target area through the rice planting range. The present application completes the extraction of rice planting areas by using SAR images from the rice planting period to the tillering period, thereby reducing the degree of dependence on prior knowledge, and has a wide range of adaptability, and can be used for the extraction of a large range of rice planting areas.

[0074] Next, a rice identification device based on short-time series SAR images in the early growth stage proposed in accordance with an embodiment of the present application is described with reference to the accompanying drawings.

[0075] Figure 7 Schematic diagram of a rice identification device based on short-time series SAR images in the early growth stage according to an embodiment of the present application.

[0076] like Figure 7 As shown, the rice identification device 10 based on short-time series SAR images in the early growth stage includes: a preprocessing module 100 , a collection module 200 and an identification module 300 .

[0077] The preprocessing module 100 is used to obtain the time-series SAR data of the early growth period of rice in the target area, and preprocess the time-series SAR data of the early growth period of rice to obtain standard early SAR data.

[0078] The acquisition module 200 is used to collect the target historical SAR data of rice growth in the target area, and calculate the water backscatter value and vegetation backscatter value of the target area based on the target historical SAR data, and calculate the rice discrimination index of the target area based on the water backscatter value, the vegetation backscatter value and the standard early SAR data.

[0079] The identification module 300 is used to segment the rice discrimination index using a preset SSSI threshold to obtain an index segmentation result, extract the rice planting range in the target area according to the index segmentation result, and identify the earliest rice identification period in the target area through the rice planting range.

[0080] Optionally, in one embodiment of the present application, the rice identification device 10 based on short-time series SAR images in the early growth stage of the present application embodiment further includes: an evaluation module and a correction module.

[0081] Among them, the evaluation module is used to obtain the ground monitoring data of the target area after obtaining the rice planting range in the target area according to the index segmentation result, and to perform accuracy evaluation on the rice planting range through the ground monitoring data to obtain an accuracy evaluation result.

[0082] The correction module is used to correct the rice discrimination index according to the accuracy evaluation result, so as to identify the new rice planting range in the target area based on the corrected rice discrimination index.

[0083] Optionally, in one embodiment of the present application, the preprocessing module 100 includes: a track correction unit, a radiation calibration unit, a geometric calibration unit and a filtering unit.

[0084] The orbit correction unit is used to perform orbit correction processing on the early time series SAR data based on the preset target orbit vector state file of the SAR data to obtain orbit corrected SAR data.

[0085] The radiation calibration unit is used to perform a radiation calibration operation on the orbit correction SAR data to generate radiation calibration SAR data.

[0086] The geometric calibration unit is used to perform geometric calibration operation on the radiation calibration SAR data according to the preset range Doppler equation and digital elevation model to obtain geometric calibration SAR data.

[0087] The filtering unit is used for performing speckle filtering on the geometrically calibrated SAR data to obtain standard early SAR data.

[0088] Optionally, in one embodiment of the present application, the acquisition module 200 includes: a first calculation unit, an acquisition unit, a first determination unit, a second determination unit and a second calculation unit.

[0089] Wherein, the first calculation unit is used to calculate the water body backscatter value and the vegetation backscatter value based on the target historical SAR data and the preset land use and surface cover data set.

[0090] The acquisition unit is used to acquire the field time-series backscatter curve of the target crop in the target area, and determine the minimum value of the field time-series backscatter curve and the water body similarity of the water body backscatter value.

[0091] The first determination unit is used to obtain the maximum value after the minimum value on the field time series backscatter curve, and determine the vegetation similarity between the maximum value and the vegetation backscatter value.

[0092] The second determination unit is used to obtain the field time-series backscattering dynamic range of the target crop, and determine the field time-series backscattering dynamic range and the rice field scattering similarity of the rice field based on the water body backscattering value and the vegetation backscattering value.

[0093] The second calculation unit is used to calculate the rice discrimination index based on the water body similarity, the vegetation similarity and the rice field scattering similarity.

[0094] Optionally, in one embodiment of the present application, the mathematical expression of the rice discrimination index is:

[0095] SSSI=f(p1)*f(p2)*f(p1,p2)

[0096] Among them, SSSI represents the rice discrimination index; p1 represents the minimum value of the field time series backscattering curve; p2 represents the maximum value after the minimum value on the field time series backscattering curve; f(p1) represents the water body similarity; f(p2) represents the vegetation similarity; f(p1,p2) represents the rice field scattering similarity.

[0097] It should be noted that the above explanation of the rice identification method embodiment based on short-time series SAR images in the early growth stage is also applicable to the rice identification device based on short-time series SAR images in the early growth stage of this embodiment, which will not be repeated here.

[0098] According to the rice identification device based on the short-time series SAR image of the early growth stage proposed in the embodiment of the present application, it includes a preprocessing module for acquiring the time series SAR data of the early growth stage of rice in the target area, and preprocessing the time series SAR data of the early growth stage of rice to obtain standard early SAR data; an acquisition module for acquiring the target historical SAR data of rice growth in the target area, and calculating the water body backscatter value and vegetation backscatter value of the target area based on the target historical SAR data, and calculating the rice discrimination index of the target area based on the water body backscatter value, the vegetation backscatter value and the standard early SAR data; an identification module for segmenting the rice discrimination index using a preset SSSI threshold to obtain an index segmentation result, and extracting the rice planting range in the target area according to the index segmentation result, and identifying the earliest rice identification period of the target area through the rice planting range. The present application completes the extraction of the rice planting area by using SAR images from the rice planting period to the tillering period, thereby reducing the degree of dependence on prior knowledge, and has a wide range of adaptability, and can be used for the extraction of a large range of rice planting areas.

[0099] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0100] A memory 801 , a processor 802 , and a computer program stored in the memory 801 and executable on the processor 802 .

[0101] When the processor 802 executes the program, the rice recognition method based on the short-time series SAR image in the early growth stage provided in the above embodiment is implemented.

[0102] Furthermore, the electronic device further comprises:

[0103] The communication interface 803 is used for communication between the memory 801 and the processor 802 .

[0104] The memory 801 is used to store computer programs that can be executed on the processor 802 .

[0105] The memory 801 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0106] If the memory 801, the processor 802 and the communication interface 803 are implemented independently, the communication interface 803, the memory 801 and the processor 802 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0107] Optionally, in a specific implementation, if the memory 801, the processor 802 and the communication interface 803 are integrated on a chip, the memory 801, the processor 802 and the communication interface 803 can communicate with each other through an internal interface.

[0108] The processor 802 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0109] The embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned rice identification method based on short-time series SAR images in the early growth stage.

[0110] The embodiment of the present application also provides a computer program product, including a computer program, which, when executed, is used to implement the above-mentioned rice identification method based on short-time series SAR images in the early growth stage.

[0111] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0112] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0113] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0114] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0115] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0116] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0117] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0118] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A rice recognition method based on short-time SAR images in the early growth stage, characterized in that: The following steps are involved: Acquiring early rice growth time-series SAR data in a target area, and preprocessing the early rice growth time-series SAR data to obtain standard early SAR data; Collecting target historical SAR data of rice growth in the target area, and calculating a water body backscatter value and a vegetation backscatter value of the target area according to the target historical SAR data, and calculating a rice discrimination index of the target area based on the water body backscatter value, the vegetation backscatter value and the standard early SAR data; The rice discrimination index is segmented using a preset SSSI threshold to obtain an index segmentation result, and the rice planting range in the target area is extracted according to the index segmentation result, and the earliest rice identification period in the target area is identified through the rice planting range.

2. The method according to claim 1, characterized in that After obtaining the rice planting range in the target area according to the index segmentation result, the method further includes: Acquiring ground monitoring data of the target area, and performing precision assessment on the rice planting range based on the ground monitoring data to obtain a precision assessment result; The rice discrimination index is corrected according to the accuracy evaluation result, so as to identify a new rice planting range in the target area based on the corrected rice discrimination index.

3. The method according to claim 2, characterized in that The step of acquiring the early rice growth time-series SAR data in the target area and preprocessing the early rice growth time-series SAR data to obtain standard early SAR data includes: Based on a preset target orbit vector state file of SAR data, performing orbit correction processing on the early time series SAR data to obtain orbit correction SAR data; performing a radiometric calibration operation on the orbit-corrected SAR data to generate radiometrically calibrated SAR data; Performing a geometric calibration operation on the radiation calibration SAR data according to a preset range Doppler equation and a digital elevation model to obtain geometric calibration SAR data; The geometrically calibrated SAR data is subjected to speckle filtering to obtain the standard early SAR data.

4. The method according to claim 3, characterized in that The step of calculating the water backscatter value and the vegetation backscatter value of the target area according to the target historical SAR data, and calculating the rice discrimination index of the target area based on the water backscatter value, the vegetation backscatter value and the standard early SAR data, comprises: Calculating the water body backscatter value and the vegetation backscatter value based on the target historical SAR data and a preset land use and surface cover data set; Acquire a field time-series backscatter curve of a target crop in the target area, and determine a minimum value of the field time-series backscatter curve and a water body similarity of the water body backscatter value; Obtaining a maximum value after the minimum value on the field time series backscatter curve, and determining a vegetation similarity between the maximum value and the vegetation backscatter value; Acquire the field time-series backscattering dynamic range of the target crop, and determine the field time-series backscattering dynamic range and the paddy field scattering similarity of the paddy field based on the water body backscattering value and the vegetation backscattering value; The rice discrimination index is calculated based on the water body similarity, the vegetation similarity and the rice field scattering similarity.

5. The method according to claim 4, characterized in that The mathematical expression of the rice discrimination index is: SSSI=f(p1)*f(p2)*f(p1,p2) Among them, SSSI represents the rice discrimination index; p1 represents the minimum value of the field time series backscattering curve; p2 represents the maximum value after the minimum value on the field time series backscattering curve; f(p1) represents the water body similarity; f(p2) represents the vegetation similarity; f(p1, p2) represents the rice field scattering similarity.

6. A rice identification device based on short-time SAR images in the early growth stage, characterized in that: include: A preprocessing module is used to obtain time-series SAR data of early rice growth in a target area, and preprocess the time-series SAR data of early rice growth to obtain standard early SAR data; A collection module, used for collecting target historical SAR data of rice growth in the target area, and calculating the water body backscatter value and the vegetation backscatter value of the target area according to the target historical SAR data, and calculating the rice discrimination index of the target area based on the water body backscatter value, the vegetation backscatter value and the standard early SAR data; The identification module is used to segment the rice discrimination index using a preset SSSI threshold to obtain an index segmentation result, extract the rice planting range in the target area according to the index segmentation result, and identify the earliest rice identification period in the target area through the rice planting range.

7. The method according to claim 6, characterized in that The preprocessing module comprises: An orbit correction unit, configured to perform orbit correction processing on the early time series SAR data based on a preset target orbit vector state file of the SAR data to obtain orbit correction SAR data; A radiation calibration unit, used for performing a radiation calibration operation on the orbit correction SAR data to generate radiation calibration SAR data; A geometric calibration unit, used for performing a geometric calibration operation on the radiation calibration SAR data according to a preset range Doppler equation and a digital elevation model to obtain geometric calibration SAR data; A filtering unit is used to perform speckle filtering on the geometrically calibrated SAR data to obtain the standard early SAR data.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the rice recognition method based on short-time series SAR images in the early growth stage as described in any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the rice recognition method based on short-time series SAR images in the early growth stage as described in any one of claims 1 to 5.

10. A computer program product, comprising a computer program, characterized in that The computer program is executed to implement the rice recognition method based on short-time series SAR images in the early growth stage as described in any one of claims 1 to 5.

Images