Crop Change Detection Method, Device and Equipment

Abstract

The present application discloses a method, device and equipment for crop change detection, which relates to the technical field of crop detection. By using the normalized correlation between co-polarization channels of crops to eliminate the intensity information of co-polarization channels, the true changes during the growth process of crops can be captured more accurately. The method includes: after acquiring co-polarization synthetic aperture radar data, constructing a polarization covariance matrix according to the image data of crops on co-polarization channels; calculating the normalized correlation between co-polarization channels of crops according to the polarization covariance matrix; calculating the polarization correlation distance between different time points of crops according to the normalized correlation between co-polarization channels of crops; and determining the first change amount feature during the growth process of crops according to the polarization correlation distance between different time points of crops, where the first change amount feature at least includes the change amplitude of the growth process of crops.

Description

Technical Field

[0001] This application relates to the technical field of crop detection, and particularly to a method, device and equipment for crop change detection. Background Art

[0002] In the rapidly changing era of globalization, the production status of crops directly affects the national economic development. With the help of satellite remote sensing technology, large-scale and high-precision monitoring of crop production status has become an important means to improve crop yields and optimize resource utilization. Among various remote sensing technologies, polarimetric synthetic aperture radar has significant advantages in the application of crop change detection due to its all-weather and all-time observation capabilities and high sensitivity to the physical characteristics of targets, providing reliable data support for precision agriculture and long-term dynamic monitoring of crops.

[0003] In the related art, for the crop change detection technology based on polarimetric synthetic aperture radar, more information about target characteristics can be obtained by simultaneously transmitting and receiving radar waves of multiple polarization states. Usually, the polarimetric covariance matrix is used for analysis to more comprehensively express target characteristics. Here, the polarimetric covariance matrix is composed of the intensities of different polarization channels and the correlation information between channels, but the intensity is easily affected by environmental factors and cannot accurately reflect the true changes of crops. Summary of the Invention

[0004] In view of this, this application provides a method, device and equipment for crop change detection, mainly aiming to solve the problem that the intensity in the existing polarimetric covariance matrix is easily affected by environmental factors and cannot accurately reflect the true changes of crops.

[0005] According to the first aspect of this application, a method for crop change detection is provided, including:

[0006] After obtaining the co-polarimetric synthetic aperture radar data, constructing a polarimetric covariance matrix according to the image data of the crop on the co-polarization channel;

[0007] Calculating the normalized correlation between the co-polarization channels of the crop according to the polarimetric covariance matrix;

[0008] Calculating the polarimetric correlation distance between different time points of the crop according to the normalized correlation between the co-polarization channels of the crop;

[0009] Determining the first change amount feature in the crop growth process according to the polarimetric correlation distance between different time points of the crop, where the first change amount feature at least includes the change amplitude of the crop growth process.

[0010] Further, the calculating the normalized correlation between the co-polarization channels of the crop according to the polarimetric covariance matrix includes:

[0011] Extract the intensity after filtering in the co-polarization channels and the correlation between different polarization channels respectively according to the polarization covariance matrix;

[0012] Calculate the normalized correlation between the co-polarization channels of the crops according to the intensity after filtering in the co-polarization channels and the correlation between different polarization channels.

[0013] Further, calculating the polarization correlation distance between different time points of the crops according to the normalized correlation between the co-polarization channels of the crops includes:

[0014] Perform coordinate transformation on the normalized correlation between the co-polarization channels of the crops so that the correlation is transformed from the polar coordinate system to the Cartesian coordinate system;

[0015] Calculate the polarization correlation distance between different time points of the crops in the Cartesian coordinate system.

[0016] Further, after calculating the normalized correlation between the co-polarization channels of the crops according to the polarization covariance matrix, the method further includes:

[0017] Calculate the polarization correlation distance of the crops on at least one standard scattering mechanism according to the normalized correlation between the co-polarization channels of the crops;

[0018] Establish a polarization state vector of the crops at different time points according to the polarization correlation distance of the crops on at least one standard scattering mechanism, and the polarization state vector is used to represent the characteristics of the crops on at least one standard scattering mechanism;

[0019] Determine the second change quantity characteristics in the growth process of the crops according to the difference between the polarization state vectors of the crops at different time points, and the second change quantity characteristics at least include the change type, change direction and change amplitude of the crops in the growth process on at least one standard scattering mechanism.

[0020] Further, before calculating the polarization correlation distance of the crops on at least one standard scattering mechanism according to the normalized correlation between the co-polarization channels of the crops, the method further includes:

[0021] Pre-define the polarization correlation of at least one standard scattering mechanism, and the polarization correlation of at least one standard scattering mechanism includes at least one of the polarization correlation of volume scattering, the polarization correlation of surface scattering and the polarization correlation of secondary scattering.

[0022] Further, calculating the polarization correlation distance of the crop on at least one standard scattering mechanism according to the normalized correlation between the co-polarization channels of the crop includes:

[0023] Performing coordinate transformation on the normalized correlation between the co-polarization channels of the crop and the polarization correlation of at least one standard scattering mechanism, so that the correlation is transformed from the polar coordinate system to the Cartesian coordinate system;

[0024] In the Cartesian coordinate system, calculate the distance between the normalized correlation between the co-polarization channels of the crop and the polarization correlation of the at least one standard scattering mechanism respectively, to obtain the polarization correlation distance of the crop on at least one standard scattering mechanism.

[0025] Further, establishing the polarization state vector of the crop at different time points according to the polarization correlation distance of the crop on at least one standard scattering mechanism includes:

[0026] Determining the weight proportion of the crop on at least one standard scattering mechanism according to the polarization correlation distance of the crop on at least one standard scattering mechanism;

[0027] Establishing the polarization state vector of the crop at different time points according to the weight proportion of the crop on at least one standard scattering mechanism.

[0028] According to the second aspect of the present application, there is provided a crop change detection device, including:

[0029] A construction unit, configured to construct a polarization covariance matrix according to the image data of the crop on the co-polarization channel after acquiring the co-polarization synthetic aperture radar data;

[0030] A first calculation unit, configured to calculate the normalized correlation between the co-polarization channels of the crop according to the polarization covariance matrix;

[0031] A second calculation unit, configured to calculate the polarization correlation distance between different time points of the crop according to the normalized correlation between the co-polarization channels of the crop;

[0032] A first determination unit, configured to determine the first change amount feature in the growth process of the crop according to the polarization correlation distance between different time points of the crop, and the first change amount feature at least includes the change amplitude in the growth process of the crop.

[0033] Further, the first calculation unit is specifically configured to:

[0034] Extract the intensity after filtering of the co-polarization channel and the correlation of different polarization channels respectively according to the polarization covariance matrix;

[0035] Calculate the normalized correlation between the co-polarization channels of the crops based on the intensity after filtering in the co-polarization channels and the correlation between different polarization channels.

[0036] Further, the second calculation unit is specifically configured to:

[0037] Perform coordinate transformation on the normalized correlation between the co-polarization channels of the crops, so that the correlation is transformed from the polar coordinate system to the Cartesian coordinate system;

[0038] Calculate the polarization correlation distance between different time points of the crops in the Cartesian coordinate system.

[0039] Further, the device further includes:

[0040] A third calculation unit, configured to calculate the polarization correlation distance of the crops on at least one standard scattering mechanism according to the normalized correlation between the co-polarization channels of the crops after calculating the normalized correlation between the co-polarization channels of the crops according to the polarization covariance matrix;

[0041] A building unit, configured to build a polarization state vector of the crops at different time points according to the polarization correlation distance of the crops on at least one standard scattering mechanism, where the polarization state vector is used to represent the characteristics of the crops on at least one standard scattering mechanism;

[0042] A second determination unit, configured to determine the second change amount characteristic in the growth process of the crops according to the difference between the polarization state vectors of the crops at different time points, where the second change amount characteristic at least includes the change type, change direction, and change amplitude of the growth process of the crops on at least one standard scattering mechanism.

[0043] Further, the device further includes:

[0044] A definition unit, configured to pre-define the polarization correlation of at least one standard scattering mechanism before calculating the polarization correlation distance of the crops on at least one standard scattering mechanism according to the normalized correlation between the co-polarization channels of the crops, where the polarization correlation of the at least one standard scattering mechanism includes at least one of the polarization correlation of volume scattering, the polarization correlation of surface scattering, and the polarization correlation of secondary scattering.

[0045] Further, the third calculation unit is specifically configured to:

[0046] Perform coordinate transformation on the normalized correlation between the co-polarization channels of the crops and the polarization correlation of at least one standard scattering mechanism, so that the correlation is transformed from the polar coordinate system to the Cartesian coordinate system;

[0047] Under the Cartesian coordinate system, calculate the distance between the normalized correlation between the same polarization channels of the crop and the polarization correlation of the at least one standard scattering mechanism respectively, so as to obtain the polarization correlation distance of the crop on the at least one standard scattering mechanism.

[0048] Further, the establishing unit is specifically configured to:

[0049] Determine the weight ratio of the crop on the at least one standard scattering mechanism according to the polarization correlation distance of the crop on the at least one standard scattering mechanism;

[0050] Establish a polarization state vector of the crop at different time points according to the weight ratio of the crop on the at least one standard scattering mechanism.

[0051] According to the third aspect of the present application, there is provided a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the method described in the first aspect are implemented.

[0052] According to the fourth aspect of the present application, there is provided a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0053] By means of the above technical solution, compared with the current prior art method of using the polarization covariance matrix to detect crop changes, after obtaining the same polarization synthetic aperture radar data in the present application, a polarization covariance matrix is constructed according to the image data of the crop on the same polarization channels; according to the polarization covariance matrix, calculate the normalized correlation between the same polarization channels of the crop; according to the normalized correlation between the same polarization channels of the crop, calculate the polarization correlation distance between different time points of the crop; according to the polarization correlation distance between different time points of the crop, determine the first change amount feature in the crop growth process, and the first change amount feature at least includes the change amplitude of the crop growth process. The whole process calculates the normalized correlation between the same polarization channels of the crop on the basis of the polarization covariance matrix, eliminates the intensity of the same polarization channels through the normalized correlation between the same polarization channels of the crop, can effectively avoid the influence of environmental factors on the intensity, and further detects the change amount feature of the crop through the polarization correlation distance between different time points of the crop, and can more accurately capture the real changes in the crop growth process.

[0054] The above description is only an overview of the technical solution of the present application. In order to better understand the technical means of the present application, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the specific embodiments of the present application are hereinafter given. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation to the present application. In the drawings:

[0056] Figure 1 is a schematic flowchart of a method for detecting crop changes in an embodiment of the present application;

[0057] Figure 2 is Figure 1 a schematic flowchart of a specific implementation manner of step 102 in;

[0058] Figure 3 is Figure 1 a schematic flowchart of a specific implementation manner of step 103 in;

[0059] Figure 4 is a schematic flowchart of a method for detecting crop changes in another embodiment of the present application;

[0060] Figure 5 is Figure 4 a schematic flowchart of a specific implementation manner of step 402 in;

[0061] Figure 6 is Figure 4 a schematic flowchart of a specific implementation manner of step 403 in;

[0062] Figure 7 is the average polarization correlation of barley at different time points in this embodiment

[0063] Figure 8 is the polarization correlation distance of barley on different standard scattering mechanisms in this embodiment;

[0064] Figure 9 is the change in the scattering state corresponding to barley at different time points in this embodiment;

[0065] Figure 10 is the overall change amount of barley between any two time points in this embodiment;

[0066] Figure 11 is the overall change amount of barley between any two time points represented by a change matrix of geometric distance in this embodiment;

[0067] Figure 12It is the overall change amount of barley between any two time points represented by the change matrix of Wishart distance in this embodiment;

[0068] Figure 13 It is the change direction and change amount of barley corresponding to the second scattering in this embodiment;

[0069] Figure 14 It is the change direction and change amount of barley corresponding to the volume scattering in this embodiment;

[0070] Figure 15 It is the change direction and change amount of barley corresponding to the surface scattering in this embodiment;

[0071] Figure 16 It is the structural schematic diagram of the crop change detection device in an embodiment of this application;

[0072] Figure 17 It is the device structural schematic diagram of a computer device provided by an embodiment of the present invention. Detailed implementation manners

[0073] Now, the content of the present invention will be discussed with reference to several exemplary embodiments. It should be understood that discussing these embodiments is only to enable those of ordinary skill in the art to better understand and thus implement the content of the present invention, rather than implying any limitation to the scope of the present invention.

[0074] As used herein, the term "including" and its variants are to be construed as open-ended terms meaning "including but not limited to". The term "based on" is to be construed as "at least partially based on". The term "one embodiment" and "an embodiment" are to be construed as "at least one embodiment". The term "another embodiment" is to be construed as "at least one other embodiment".

[0075] In the scenario of crop change detection, based on the crop change detection technology of polarimetric synthetic aperture radar, more information about the target characteristics can be obtained by simultaneously transmitting and receiving radar waves of multiple polarization states. Usually, the polarization covariance matrix is used for analysis to more comprehensively express the target characteristics. Here, the polarization covariance matrix is composed of the intensities of different polarization channels and the correlation information between channels, but the intensity is easily affected by environmental factors and cannot accurately reflect the real changes of crops.

[0076] To solve this problem, this embodiment provides a crop change detection method, as Figure 1 shown, including the following steps:

[0077] 101. After obtaining the co-polarized synthetic aperture radar data, construct a polarization covariance matrix according to the image data of the crop on the co-polarized channel.

[0078] Polarimetric synthetic aperture radar systems usually transmit and receive electromagnetic waves in different polarization channels. For example, the horizontal polarization channel H and the vertical polarization channel V. For a full-polarization system, there may be four channels: HH, HV, VH, and VV.

[0079] In this embodiment, the co-polarization channels refer to the same polarization channels for transmission and reception, including two channels: HH and VV. Correspondingly, the image data of the crops in the co-polarization channels includes the image data of the HH channel and the image data of the VV channel. Correspondingly, the polarization covariance matrix is 2×2 and is used to describe the statistical relationship between the HH channel and the VV channel.

[0080] The elements of the polarization covariance matrix can be constructed from the image data of the crops corresponding to each pixel in the HH channel and the VV channel. Here, the image data is usually complex and includes amplitude and phase information; then, the covariance matrix elements of each pixel are calculated through conjugate multiplication and spatial averaging. For example, for the window around the pixel, the average value of the conjugate multiplication of the image data of all pixels in the HH channel and the VV channel within the window is calculated, and thus the covariance matrix is constructed. It should be noted that since the noise of a single element data is relatively large and cannot be accurately estimated, the covariance matrix needs to estimate the average value, and usually, temporal averaging or spatial averaging is required to reduce the noise. Here, spatial averaging can be performed on the area around each pixel point to estimate the statistic.

[0081] Exemplarily, on the basis of obtaining the image data of the HH channel and the image data of the VV channel , calculating the elements in the polarization covariance matrix of each pixel includes , , , . Correspondingly, the constructed polarization covariance matrix is shown in the following formula:

[0082] ;

[0083] where is the polarization covariance matrix, is the spatial averaging operation, is the Hermitian transpose. Correspondingly, the element in the polarization covariance matrix represents the intensity after filtering of the HH channel, represents the intensity after filtering of the VV channel, and represent the correlation between the HH channel and the VV channel.

[0084] 102. Calculate the normalized correlation between the co-polarization channels of the crops according to the polarization covariance matrix.

[0085] In this embodiment, in the polarization covariance matrix, the diagonal elements respectively represent the intensities after filtering of the HH channel and the VV channel, and the off-diagonal elements are the correlations between the HH channel and the VV channel. For the correlation between the same polarization channels of crops after normalization, it can be measured by the complex correlation coefficient, which is a complex number, but in practical applications, its magnitude and phase are usually concerned. For the specific calculation process of the correlation between the same polarization channels of crops after normalization, refer to the following formula:

[0086] ;

[0087] where, is the normalized complex coherence between the HH and VV channels, is the magnitude value of the coherence, and its value range is from 0 to 1, is the phase value of the coherence, and its value range is from -180 degrees to 180 degrees.

[0088] It should be noted that the elements in the polarization covariance matrix are complex numbers, including magnitude and phase information.

[0089] In practical application scenarios, the correlation between the same polarization channels of the same crop may be different at different growth stages. By analyzing the correlation between the same polarization channels of crops after normalization, it can help with crop phenology recognition or change detection. For example, the magnitude of the same polarization correlation of barley is between 0.7 and 0.9 in the early growth stage, with a relatively high correlation, and between 0.3 and 0.5 in the middle growth stage, with a medium correlation. The phase of the same polarization correlation of barley is around 0 degrees in the early growth stage and 90 degrees - 180 degrees in the middle growth stage.

[0090] 103. Calculate the polarization correlation distance between crops at different time points according to the correlation between the same polarization channels of the crops after normalization.

[0091] It can be understood that the correlation between the same polarization channels of crops after normalization reflects the correlation between different polarization channels at the same time point, usually in the form of a complex number, including magnitude and phase. In order to obtain the differences between the polarization characteristics of crops at different time points, the correlations of crops at different time points can be compared, and the polarization correlation distance between crops at different time points can be calculated, so as to evaluate the changes of crops over time.

[0092] Specifically, according to the correlation between co-polarization channels of crops after normalization, the correlation at each time point can be used as a feature vector, and then the distance between the feature vectors at different time points can be calculated to obtain the polarization correlation distance between crops at different time points. For example, assuming that at time points t1 and t2, the correlation coefficients ρ1 and ρ2 of HH and VV are calculated respectively, and the distance between the corresponding time points is |ρ1 - ρ2|. Here, the Euclidean distance can be used to calculate the distance between the feature vectors at different time points.

[0093] 104. Determine the first change amount feature in the growth process of the crop according to the polarization correlation distance between the crops at different time points.

[0094] Among them, the first change amount feature at least includes the change amplitude in the growth process of the crop. A large change amplitude indicates a significant change in the overall scattering mechanism of the crop, and a small change amplitude indicates a weak change in the overall scattering mechanism of the crop.

[0095] For the change amplitude, it can directly reflect the distance of polarization correlation between different time points. The larger the distance, the greater the change amplitude. In order to more accurately evaluate the change amplitude, the relative difference can also be calculated, that is, the ratio of the difference to the initial polarization correlation distance, which can eliminate the influence of the absolute distance difference under different crops or different measurement conditions and more intuitively reflect the relative degree of change.

[0096] As an implementation method, the time can be taken as the horizontal axis and the polarization correlation distance as the vertical axis, and the data can be curve-fitted. The rate of change of the polarization correlation distance with time can be reflected by the slope of the fitted curve. The larger the absolute value of the slope, the greater the change amplitude. By comparing the slopes of the fitted curves in different stages, the dynamic change of the change amplitude in the growth process of the crop can be determined to judge whether it is a rapid growth stage or a slow growth stage.

[0097] As another implementation method, the standard deviation of the change in the polarization correlation distance at multiple measurement points within the same time interval can be calculated; a larger standard deviation indicates that the change amplitude of the crop growth in this time period varies greatly among different samples, which may be due to the uneven growth of the crops in the farmland or the influence of local environmental factors; a smaller standard deviation indicates that the growth change amplitude is relatively consistent.

[0098] The crop change detection method provided by the embodiments of the present application, compared with the current existing technology that uses the polarization covariance matrix to detect crop changes, after obtaining the co-polarized synthetic aperture radar data, constructs a polarization covariance matrix according to the image data of the crops on the co-polarized channels; calculates the normalized correlation between the co-polarized channels of the crops according to the polarization covariance matrix; calculates the polarization correlation distance between different time points of the crops according to the normalized correlation between the co-polarized channels of the crops; determines the first change quantity feature in the growth process of the crops according to the polarization correlation distance between different time points of the crops, and the first change quantity feature at least includes the change amplitude in the growth process of the crops. The whole process calculates the normalized correlation between the co-polarized channels of the crops based on the polarization covariance matrix, eliminates the intensity of the co-polarized channels through the normalized correlation between the co-polarized channels of the crops, can effectively avoid the influence of environmental factors on the intensity, and further detects the change quantity feature of the crops through the polarization correlation distance between different time points of the crops, and can more accurately capture the real changes in the growth process of the crops.

[0099] Considering that the polarization covariance matrix contains the scattering information of the target on the HH and VV channels, it is necessary to extract the elements related to the co-polarized channels from the polarization covariance matrix. In the above embodiment, specifically, as Figure 2 shown, step 102 includes the following steps:

[0100] 201. Respectively extract the intensity after filtering of the co-polarized channels and the correlation of different polarized channels according to the polarization covariance matrix.

[0101] 202. Calculate the normalized correlation between the co-polarized channels of the crops according to the intensity after filtering of the co-polarized channels and the correlation of different polarized channels.

[0102] In this embodiment, for the co-polarized channels, that is, the horizontal polarization and vertical polarization channels, the intensity after filtering of the co-polarized channels extracted from the polarization covariance matrix includes the intensity after filtering of the HH channel and the intensity after filtering of the VV channel, and the average power of the scattering signals of the HH channel and the VV channel can be reflected through the intensity after filtering. The correlation of different polarized channels extracted from the polarization covariance matrix includes the correlation between the HH channel and the VV channel, and the degree of association between the scattering signals of the HH channel and the VV channel can be reflected through the correlation.

[0103] To specifically calculate the normalized correlation between the co-polarization channels of crops, according to the calculation principle of the correlation coefficient in statistics, use the formula for calculating the normalized correlation between the co-polarization channels of crops. Take the correlation between the HH channel and the VV channel as the numerator, multiply the intensity after filtering the HH channel and the intensity after filtering the VV channel and take the square root as the denominator, and finally divide the numerator by the denominator to obtain the normalized correlation between the co-polarization channels of crops.

[0104] It can be understood that the correlation includes the correlation amplitude and the correlation phase. Among them, the value range of the correlation amplitude is between 0 and 1. The closer the correlation amplitude is to 1, it indicates that the correlation between the HH channel and the VV channel is stronger, meaning that the scattering characteristics of the crops under these two polarization channels are more similar; the closer the correlation amplitude is to 0, it indicates that there is almost no correlation between the two. The value range of the correlation phase is from -180 degrees to 180 degrees. When the correlation phase is close to 0 degrees, it means that the crops are close to the surface scattering mechanism or the volume scattering mechanism. When the correlation phase is close to ±180 degrees, it means that the crops are close to the double scattering mechanism.

[0105] In the above embodiment, specifically, as Figure 3 shown, step 103 includes the following steps:

[0106] 301. Perform coordinate transformation on the normalized correlation between the co-polarization channels of the crops so that the correlation is transformed from the polar coordinate system to the Cartesian coordinate system.

[0107] 302. Calculate the polarization correlation distance between different time points of the crops in the Cartesian coordinate system.

[0108] In this embodiment, the polar coordinate system uses the radius and angle to represent the position of a point, and the Cartesian coordinate system uses the x and y coordinates. Coordinate transformation requires converting the amplitude and phase (polar coordinates) to the real part and imaginary part (Cartesian), or converting the correlation parameters represented in a certain polar coordinate form to the parameters in the rectangular coordinate system.

[0109] Specifically, the normalized correlation between the co-polarization channels of the crops is represented in polar coordinates as follows:

[0110] ;

[0111] Among them, is the amplitude, representing the coherence intensity between the HH channel and the VV channel, with a range of 0 - 1, and φ is the phase, reflecting the interference phase difference between the two channels and containing information on terrain, deformation, or scattering mechanism differences.

[0112] Correspondingly, during the process of converting the correlation from polar coordinates to the Cartesian coordinate system, the complex coherence Decomposed into real and imaginary parts, it can be expressed in the following form:

[0113] ;

[0114] It can be understood that through coordinate transformation, the normalized correlation between crops in the co-polarization channels can be more intuitively analyzed and processed in the Cartesian coordinate system. For example, operations such as distance calculation on the correlation can provide a more convenient mathematical basis for further studying the scattering characteristics and growth status of crops, etc.

[0115] Furthermore, in the Cartesian coordinate system, assuming that the polarization correlation between crops at the first time point is ( ), and the polarization correlation between crops at the second time point is ( ). Correspondingly, calculating the polarization correlation distance between crops at the first time point and the second time point can be expressed in the following form:

[0116] ;

[0117] In the above embodiment, further, as Figure 4 shown, after step 103, the method further includes the following steps:

[0118] 401. Calculate the polarization correlation distance of the crop on at least one standard scattering mechanism according to the normalized correlation between the crops in the co-polarization channels.

[0119] 402. Establish the polarization state vectors of the crops at different time points according to the polarization correlation distances of the crops on at least one standard scattering mechanism.

[0120] 403. Determine the second change quantity characteristics of the crops during the growth process according to the differences between the polarization state vectors of the crops at different time points.

[0121] In this embodiment, at least one standard scattering mechanism includes volume scattering, surface scattering, and second-order scattering. Correspondingly, the polarization correlation distance of the crop on at least one standard scattering mechanism can be expressed as the distance between the correlation of different standard scattering mechanisms and the co-polarization correlation. For example, the distance between the correlation of volume scattering and the co-polarization correlation, and the distance between the correlation of second-order scattering and the co-polarization correlation.

[0122] Specifically, before calculating the polarization correlation distance of the crop on at least one standard scattering mechanism, the polarization correlation of at least one standard scattering mechanism can be predefined. Here, the polarization correlation of at least one standard scattering mechanism includes at least one of the polarization correlation of volume scattering, the polarization correlation of surface scattering, and the polarization correlation of second-order scattering. Correspondingly, the polarization correlation of volume scattering can be expressed as , the polarization correlation of surface scattering can be expressed as , the polarization correlation of secondary scattering can be expressed as .

[0123] Specifically, in the above embodiment, as Figure 5 shown, step 402 includes the following steps:

[0124] 501. Perform coordinate transformation on the correlation between the same polarization channels of the crop after normalization and the polarization correlations of at least one standard scattering mechanism, so that the correlation is transformed from the polar coordinate system to the Cartesian coordinate system.

[0125] 502. In the Cartesian coordinate system, calculate the distances between the correlation between the same polarization channels of the crop after normalization and the polarization correlations of the at least one standard scattering mechanism respectively, to obtain the polarization correlation distances of the crop on at least one standard scattering mechanism.

[0126] In this embodiment, the correlation between the same polarization channels of the crop after normalization is transformed from the polar coordinate system to the Cartesian coordinate system. Referring to the content of step 302 above, after the correlation is transformed from the polar coordinate to the Cartesian coordinate system, the correlation can be expressed as . Correspondingly, after the polarization correlations of at least one standard scattering mechanism are transformed from the polar coordinate system to the Cartesian coordinate system, the polarization correlation of volume scattering is expressed as , the polarization correlation of surface scattering is expressed as , the polarization correlation of secondary scattering is expressed as .

[0127] Correspondingly, calculating the distance between the polarization correlation of volume scattering and the co-polarization correlation can be expressed in the following form:

[0128] ;

[0129] Correspondingly, calculating the distance between the polarization correlation of surface scattering and the co-polarization correlation can be expressed in the following form:

[0130] ;

[0131] Correspondingly, calculating the distance between the polarization correlation of secondary scattering and the co-polarization correlation can be expressed in the following form:

[0132] ;

[0133] It can be understood that the polarization correlation distances of the crop on at least one standard scattering mechanism are used to measure the degree of difference between the scattering characteristics of the crop and at least one standard scattering mechanism, and can reflect the type characteristics and change situations of the crop scattering mechanism.

[0134] Specifically, the polarization correlation distance of the above-mentioned crops on at least one standard scattering mechanism can be used to determine the dominant component of the crop scattering mechanism. If the polarization correlation distance with surface scattering is small, it indicates that the crops are close to the standard surface scattering mechanism. If the polarization correlation distance with volume scattering is small, it indicates that the crop scattering mechanism conforms to the standard scattering mechanism with strong depolarization such as volume scattering.

[0135] Furthermore, in the standard scattering mechanism, the polarization correlation distance of the crops on at least one standard scattering mechanism represents the difference of the crops on the standard scattering mechanism. The smaller the difference, the greater the co-occurrence of this mechanism. Here, the reciprocal of the polarization correlation distance can be used as the weight to emphasize the similarity between the crops and different standard scattering mechanisms. In this way, the smaller the distance, the higher the similarity, and the greater the weight naturally.

[0136] Specifically, the polarization correlation distance of the crops on at least one standard scattering mechanism can be converted into a weight, and the weight is further normalized. The weight of the scattering mechanism after normalization is used to establish the polarization state vector of the crops at different time points. Here, normalization is to make the sum of all weights equal to 1, and the corresponding polarization state vector can represent a probability distribution or proportion. In this way, the characteristics of the crops on at least one standard scattering mechanism can be represented by the polarization vector state, and each component corresponds to a different standard scattering mechanism. For example, if at least one standard scattering mechanism includes: volume scattering, surface scattering, and secondary scattering, the corresponding polarization vector state has three components, and each component corresponds to the normalized weight of a standard scattering mechanism. In this way, the polarization state vector can comprehensively reflect the performance of the crops on different standard scattering mechanisms, especially the characteristics on at least one standard scattering mechanism.

[0137] Specifically, in the above embodiment, as Figure 6 shown, step 403 includes the following steps:

[0138] 601. Determine the weight ratio of the crops on at least one standard scattering mechanism according to the polarization correlation distance of the crops on at least one standard scattering mechanism.

[0139] 602. Establish the polarization state vector of the crops at different time points according to the weight ratio of the crops on at least one standard scattering mechanism.

[0140] Correspondingly, according to the distance between the polarization correlation of volume scattering and the co-polarization correlation, the weight of volume scattering can be expressed in the following form:

[0141] ;

[0142] Correspondingly, according to the distance between the polarization correlation and the co-polarization correlation of surface scattering, the weight of surface scattering can be expressed in the following form:

[0143] ;

[0144] Correspondingly, according to the distance between the polarization correlation and the co-polarization correlation of double scattering, the weight of double scattering can be expressed in the following form:

[0145] ;

[0146] The process of further normalizing the weights requires summing up the weights, which can be expressed in the following form:

[0147] ;

[0148] Correspondingly, using the weights of the scattering mechanisms after normalization to establish the polarization state vectors of the crops at different time points can be expressed in the following form:

[0149] ;

[0150] Among them, corresponds to the normalized weight of volume scattering, corresponds to the normalized weight of surface scattering, corresponds to the normalized weight of double scattering.

[0151] In the actual application scenario, assuming that the normalized weights of the crops corresponding to the three standard scattering mechanisms are 0.21, 0.78, and 0.01 respectively, the corresponding polarization state vectors are: = . This polarization state vector indicates that 78% of the scattering characteristics of the crops are close to volume scattering (possibly growing vegetation), and 21% are close to surface scattering (possibly soil exposure).

[0152] Furthermore, set and to represent two different time points, and calculate the difference between the polarization state vectors of the crops at different time points, which can be expressed in the following form:

[0153] ;

[0154] In this embodiment, calculating the difference between the polarization state vectors of the crops at different time points may require comparing the changes in the scattering mechanism composition of the same crop area at different time points. For example, in the early stage, it may be mainly surface scattering. As the crop grows, double scattering increases, and there may be more volume scattering in the mature stage.

[0155] Specifically, the second variation feature at least includes the variation type, variation direction, and variation amplitude of the crop growth process on at least one standard scattering mechanism. The variation type refers to which scattering mechanism changes. For example, surface scattering, second-order scattering, or volume scattering. The variation direction may indicate whether a certain scattering mechanism increases or decreases. The variation amplitude is the magnitude of the variation value. Suppose at time point t1, surface scattering accounts for 40%, volume scattering 50%, and second-order scattering 10%; at time point t2, surface scattering is 20%, volume scattering 60%, and second-order scattering 20%. The second variation feature includes: surface scattering decreases by 20% (negative direction), volume scattering increases by 10% (positive), second-order scattering increases by 10% (positive). The variation type and variation direction are mainly that surface scattering decreases, and second-order scattering and volume scattering increase, with the variation amplitudes being 20%, 10%, and 10% respectively.

[0156] For the variation type, the distance of the co-polarization correlation with respect to the polarization correlation points of different standard scattering mechanisms represents the contribution of the corresponding scattering mechanism of the crop. For example, in the early growth stage, the crop may be mainly dominated by volume-surface scattering, and as it grows, it may gradually change to be dominated by second-order scattering or other volume scattering mechanisms. By comparing the polarization correlation distances of the crop at different time points, the variation trend of the scattering mechanism can be judged, and thus the transition of the crop growth stage can be determined. For example, the transition from the vegetative growth stage to the reproductive growth stage.

[0157] Specifically, the growth stage of the crop can be roughly determined by the dominant scattering mechanism. Volume scattering mainly describes the scattering effect generated after the increase in the leaf coverage of the crop canopy. Second-order scattering shows significant changes during the jointing and rapid growth stages of the crop. In contrast, the signal of surface scattering mainly comes from the ground surface and is more obvious in the early and mature stages of the crop.

[0158] For the variation direction, if the component of volume scattering in the polarization state vector difference of the crop at different time points is positive, it indicates that the structure of the crop becomes more complex, which may reflect an increase in the density of the vegetation canopy. A positive component of second-order scattering usually means that the stems of the crop begin to grow taller. A positive component of surface scattering indicates an enhancement of the ground surface signal, which usually corresponds to the bare land state before sowing or the farmland after harvesting. When the crop coverage is low, this scattering mechanism dominates. In addition, if the variation direction of a certain scattering feature is negative, it means that the contribution of this scattering mechanism decreases relatively, which may be due to crop structure adjustment or growth stage transition.

[0159] It can be understood that the polarization correlation distance of different scattering mechanisms is the quantification of the polarization state vector difference, and the polarization state vector can reflect the main direction and intensity of crop scattering. By comparing the polarization state vectors at different time points, if the value of a certain scattering state is negative, it indicates that the scattering feature of the crop decreases, which may mean that the growth posture or structure of the crop has changed.

[0160] In an actual application scenario, 11 image data of barley corresponding to different time points on the co-polarization channel are collected in advance. During the acquisition of the image data, the barley has experienced different growth stages. First, it enters the tillering stage on April 19th, and then starts stem growth on May 3rd. On May 24th, the plants begin to head, and then enter the flowering stage on June 7th. On June 13th, the fruits start to develop, until they enter the maturity stage on July 5th, and finally are harvested on July 26th.

[0161] During the process of specifically detecting changes in barley, by preprocessing the images, the average polarization correlation of barley on different dates can be obtained. See Figure 7 As shown, where the amplitude is represented by the radius of the unit circle and the phase is represented by the angle. From Figure 7 it can be seen that at different time points, the positions of the polarization correlations on the unit circle are different. This indicates that the polarization complex coherence is sensitive to the growth of barley. Then mark the positions of different standard scattering mechanisms on the unit circle. See Figure 8 As shown, where the secondary scattering is represented by square dots, the volume scattering is represented by star dots, and the surface scattering is represented by triangular dots. Combining the distances between the average polarization correlation (round dots) and the standard scattering mechanisms, the scattering states of barley at different time points are determined. See Figure 9 As shown, from Figure 9 it can be seen that in the early to middle stages of barley growth, secondary scattering is dominant, and then it gradually changes to volume scattering dominance. After harvesting, surface scattering becomes the dominant scattering mechanism.

[0162] Furthermore, by calculating the average polarization coherence distance between any two time points, the overall change amount of barley can be extracted. This process is shown in Figure 10 As shown, the change amount calculated between any two time points can be represented by a positive geometric distance and is represented by the upper triangular part of the matrix. This process is shown in Figure 11 As shown. Compared with the Wishart distance including intensity, this process is shown in Figure 12 , the coherence distance proposed in this embodiment can capture the changes of the crops themselves more accurately without being affected by environmental factors. For example, during the growth of barley, the Wishart distance between the 0511 time point and the 0515 time point is relatively large, but in fact, the changes in the crops between these two time points are very small and they are still in the same growth stage.

[0163] Furthermore, according to the scattering states of barley at different time points, a change detection matrix of barley is determined. Figure 13 is the change direction and change amplitude corresponding to the secondary scattering of barley. Figure 14 is the change direction and change amplitude corresponding to the volume scattering of barley.Figure 15 For the change direction and change amplitude of the surface scattering of barley. Among them, the upper triangle indicates an increase, and the lower triangle indicates a decrease. Combining Figures 13 - 15 It can be seen that during the middle growth stage of barley, the secondary scattering gradually decreases, and the volume scattering gradually increases; while at the end of the barley growth stage and the harvesting stage, the surface scattering becomes the main growth component. For the convenience of analysis, the change detection matrices of these three different standard scattering mechanisms can be further synthesized by RGB to form a color change detection matrix.

[0164] Furthermore, as Figures 1 - 6 a specific implementation of the method, an embodiment of the present application provides a crop change detection device, as Figure 16 shown, the device includes: a construction unit 71, a first calculation unit 72, a second calculation unit 73, and a first determination unit 74.

[0165] The construction unit 71 is configured to construct a polarization covariance matrix according to the image data of the crop on the co-polarization channel after acquiring the co-polarization synthetic aperture radar data;

[0166] The first calculation unit 72 is configured to calculate the normalized correlation between the co-polarization channels of the crop according to the polarization covariance matrix;

[0167] The second calculation unit 73 is configured to calculate the polarization correlation distance between different time points of the crop according to the normalized correlation between the co-polarization channels of the crop;

[0168] The first determination unit 74 is configured to determine the first change amount feature in the growth process of the crop according to the polarization correlation distance between different time points of the crop, and the first change amount feature at least includes the change amplitude in the growth process of the crop.

[0169] The crop change detection device provided by the embodiments of the present invention, compared with the prior art method of using the polarization covariance matrix to detect crop changes, after acquiring the co-polarized synthetic aperture radar data, constructs a polarization covariance matrix based on the image data of the crops in the co-polarized channel; calculates the normalized correlation between the co-polarized channels of the crops according to the polarization covariance matrix; calculates the polarization correlation distance between different time points of the crops according to the normalized correlation between the co-polarized channels of the crops; determines the first change amount feature in the crop growth process according to the polarization correlation distance between different time points of the crops, and the first change amount feature at least includes the change amplitude in the crop growth process. The whole process calculates the normalized correlation between the co-polarized channels of the crops based on the polarization covariance matrix, eliminates the intensity of the co-polarized channels through the normalized correlation between the co-polarized channels of the crops, can effectively avoid the influence of environmental factors on the intensity, and further detects the change amount feature of the crops through the polarization correlation distance between different time points of the crops, and can more accurately capture the real changes in the crop growth process.

[0170] In a specific application scenario, the first calculation unit is specifically configured to:

[0171] Extract the intensity after filtering the co-polarized channels and the correlation between different polarized channels respectively according to the polarization covariance matrix;

[0172] Calculate the normalized correlation between the co-polarized channels of the crops according to the intensity after filtering the co-polarized channels and the correlation between different polarized channels.

[0173] In a specific application scenario, the second calculation unit is specifically configured to:

[0174] Perform coordinate transformation on the normalized correlation between the co-polarized channels of the crops so that the correlation is transformed from the polar coordinate system to the Cartesian coordinate system;

[0175] Calculate the polarization correlation distance between different time points of the crops in the Cartesian coordinate system.

[0176] In a specific application scenario, the device further includes:

[0177] A third calculation unit, configured to calculate the polarization correlation distance of the crops on at least one standard scattering mechanism according to the normalized correlation between the co-polarized channels of the crops after calculating the normalized correlation between the co-polarized channels of the crops according to the polarization covariance matrix;

[0178] A building unit, configured to establish polarization state vectors of the crop at different time points according to the polarization correlation distance of the crop on at least one standard scattering mechanism, where the polarization state vectors are used to represent the characteristics of the crop on at least one standard scattering mechanism;

[0179] A second determination unit, configured to determine a second change amount characteristic during the growth process of the crop according to the difference between the polarization state vectors of the crop at different time points, where the second change amount characteristic at least includes a change type, a change direction, and a change amplitude of the crop growth process on at least one standard scattering mechanism.

[0180] In a specific application scenario, the device further includes:

[0181] A definition unit, configured to pre-define the polarization correlation of at least one standard scattering mechanism before calculating the polarization correlation distance of the crop on at least one standard scattering mechanism according to the normalized correlation between the same polarization channels of the crop, where the polarization correlation of the at least one standard scattering mechanism includes at least one of the polarization correlation of volume scattering, the polarization correlation of surface scattering, and the polarization correlation of secondary scattering.

[0182] In a specific application scenario, the third calculation unit is specifically configured to:

[0183] Perform coordinate transformation on the normalized correlation between the same polarization channels of the crop and the polarization correlation of at least one standard scattering mechanism, so that the correlation is transformed from a polar coordinate system to a Cartesian coordinate system;

[0184] Under the Cartesian coordinate system, calculate the distance between the normalized correlation between the same polarization channels of the crop and the polarization correlation of the at least one standard scattering mechanism respectively, to obtain the polarization correlation distance of the crop on at least one standard scattering mechanism.

[0185] In a specific application scenario, the building unit is specifically configured to:

[0186] Determine the weight ratio of the crop on at least one standard scattering mechanism according to the polarization correlation distance of the crop on at least one standard scattering mechanism;

[0187] Establish polarization state vectors of the crop at different time points according to the weight ratio of the crop on at least one standard scattering mechanism.

[0188] It should be noted that for other corresponding descriptions of each functional unit involved in a crop change detection device provided in this embodiment, reference can be made to the corresponding description in Figures 1 - 6 and details are not described herein again.

[0189] Based on the above method as Figures 1 - 6 shown, correspondingly, an embodiment of the present application further provides a storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the above method for detecting crop changes as Figures 1 - 6 shown.

[0190] Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various implementation scenarios of the present application.

[0191] Based on the above method as Figures 1 - 6 shown, and Figure 16 the virtual device embodiment shown, in order to achieve the above object, an embodiment of the present application further provides an entity device for detecting crop changes, which can specifically be a computer, a smart phone, a tablet computer, a smart watch, a server, or a network device, etc. The entity device includes a storage medium and a processor; the storage medium is used for storing a computer program; the processor is used for executing the computer program to implement the method for detecting crop changes as Figures 1 - 6 shown.

[0192] Optionally, the entity device may further include a user interface, a network interface, a camera, a radio frequency (RF) circuit, sensors, an audio circuit, a WI-FI module, etc. The user interface may include a display screen (Display), an input unit such as a keyboard (Keyboard), etc. Optionally, the user interface may further include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.

[0193] In an exemplary embodiment, referring to Figure 17 , the above entity device includes a communication bus, a processor, a memory, and a communication interface, and may further include an input / output interface and a display device. Among them, each functional unit can complete mutual communication through the bus. The memory stores a computer program, and the processor is used for executing the program stored on the memory to execute the method for detecting crop changes in the above embodiment.

[0194] Those skilled in the art can understand that the structure of an entity device for detecting crop changes provided in this embodiment does not constitute a limitation on the entity device, and it may include more or fewer components, or combine certain components, or have different component arrangements.

[0195] The storage medium may further include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the physical device for the above-mentioned crop change detection, and supports the operation of the information processing program and other software and / or programs. The network communication module is used to implement the communication between the components inside the storage medium, as well as the communication between other hardware and software in the information processing physical device.

[0196] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform, or can also be implemented by hardware. By applying the technical solution of the present application, compared with the current existing methods, the present application calculates the normalized correlation between the co-polarization channels of crops based on the polarization covariance matrix, and eliminates the intensity of the co-polarization channels through the normalized correlation between the co-polarization channels of crops, which can effectively avoid the influence of environmental factors on the intensity. Further, the change amount characteristics of crops are detected by the polarization correlation distance between different time points of crops, and the real changes during the growth process of crops can be captured more accurately.

[0197] Those skilled in the art can understand that the drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the drawings are not necessarily essential for implementing the present application. Those skilled in the art can understand that the modules in the device in the implementation scenario can be distributed in the device in the implementation scenario according to the description of the implementation scenario, or can be correspondingly changed and located in one or more devices different from the present implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.

[0198] The above serial numbers of the present application are only for description and do not represent the advantages or disadvantages of the implementation scenarios. The above-disclosed are only several specific implementation scenarios of the present application. However, the present application is not limited thereto, and any changes that can be thought of by those skilled in the art should fall within the protection scope of the present application.

Claims

1. A method for detecting crop changes, characterized in that, Including: After obtaining the co-polarized synthetic aperture radar data, constructing a polarization covariance matrix based on the image data of the crops in the co-polarized channels; Calculating the normalized correlation between the co-polarized channels of the crops according to the polarization covariance matrix; Calculating the polarization correlation distance between different time points of the crops according to the normalized correlation between the co-polarized channels of the crops; Determining the first change quantity feature in the growth process of the crops according to the polarization correlation distance between different time points of the crops, where the first change quantity feature at least includes the change amplitude in the growth process of the crops; After calculating the normalized correlation between the co-polarized channels of the crops according to the polarization covariance matrix, calculating the polarization correlation distance of the crops on at least one standard scattering mechanism according to the normalized correlation between the co-polarized channels of the crops, where the polarization correlation distance of the crops on at least one standard scattering mechanism is the distance between the correlations of different standard scattering mechanisms and the co-polarization correlation; establishing a polarization state vector of the crops at different time points according to the polarization correlation distance of the crops on at least one standard scattering mechanism, where the polarization state vector is used to represent the characteristics of the crops on at least one standard scattering mechanism; determining the second change quantity feature in the growth process of the crops according to the difference between the polarization state vectors of the crops at different time points, where the second change quantity feature at least includes the change type, change direction, and change amplitude of the growth process of the crops on at least one standard scattering mechanism.

2. The method according to claim 1, wherein The calculating the normalized correlation between the co-polarized channels of the crops according to the polarization covariance matrix includes: Respectively extracting the intensity after filtering of the co-polarized channels and the correlation of different polarization channels according to the polarization covariance matrix; Calculating the normalized correlation between the co-polarized channels of the crops according to the intensity after filtering of the co-polarized channels and the correlation of different polarization channels.

3. The method according to claim 1, characterized in that, The calculating the polarization correlation distance between different time points of the crops according to the normalized correlation between the co-polarized channels of the crops includes: Performing coordinate transformation on the normalized correlation between the co-polarized channels of the crops so that the correlation is transformed from the polar coordinate system to the Cartesian coordinate system; Calculating the polarization correlation distance between different time points of the crops in the Cartesian coordinate system.

4. The method according to claim 1, wherein Before calculating the polarization correlation distance of the crops on at least one standard scattering mechanism according to the normalized correlation between the co-polarized channels of the crops, the method further includes: Pre-defining the polarization correlation of at least one standard scattering mechanism, where the polarization correlation of at least one standard scattering mechanism includes at least one of the polarization correlation of volume scattering, the polarization correlation of surface scattering, and the polarization correlation of double scattering.

5. The method according to claim 1, wherein The calculating the polarization correlation distance of the crops on at least one standard scattering mechanism according to the normalized correlation between the co-polarized channels of the crops includes: Perform coordinate transformation on the correlation between the crops after normalization between the co-polarization channels and the polarization correlation of at least one standard scattering mechanism, so that the correlation is transformed from the polar coordinate system to the Cartesian coordinate system; Under the Cartesian coordinate system, calculate the distance between the correlation between the crops after normalization between the co-polarization channels and the polarization correlation of the at least one standard scattering mechanism respectively, to obtain the polarization correlation distance of the crops on at least one standard scattering mechanism.

6. The method according to claim 1, characterized in that, Establish the polarization state vectors of the crops at different time points according to the polarization correlation distance of the crops on at least one standard scattering mechanism, including: Determine the weight ratio of the crops on at least one standard scattering mechanism according to the polarization correlation distance of the crops on at least one standard scattering mechanism; Establish the polarization state vectors of the crops at different time points according to the weight ratio of the crops on at least one standard scattering mechanism.

7. A crop change detection device, characterized in that, Including: A construction unit, configured to construct a polarization covariance matrix according to the image data of the crops on the co-polarization channels after acquiring the co-polarization synthetic aperture radar data; A first calculation unit, configured to calculate the correlation between the crops after normalization between the co-polarization channels according to the polarization covariance matrix; A second calculation unit, configured to calculate the polarization correlation distance between different time points of the crops according to the correlation between the crops after normalization between the co-polarization channels; A first determination unit, configured to determine the first change amount feature in the growth process of the crops according to the polarization correlation distance between different time points of the crops, where the first change amount feature at least includes the change amplitude of the growth process of the crops; A third calculation unit, configured to calculate the polarization correlation distance of the crops on at least one standard scattering mechanism according to the correlation between the crops after normalization between the co-polarization channels after calculating the correlation between the crops after normalization between the co-polarization channels according to the polarization covariance matrix, where the polarization correlation distance of the crops on at least one standard scattering mechanism is the distance between the correlation of different standard scattering mechanisms and the co-polarization correlation; A construction unit, configured to establish the polarization state vectors of the crops at different time points according to the polarization correlation distance of the crops on at least one standard scattering mechanism, where the polarization state vectors are used to represent the characteristics of the crops on at least one standard scattering mechanism; A second determination unit, configured to determine the second change amount feature in the growth process of the crops according to the difference between the polarization state vectors of the crops at different time points, where the second change amount feature at least includes the change type, change direction and change amplitude of the growth process of the crops on at least one standard scattering mechanism.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the crop change detection method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the crop change detection method according to any one of claims 1 to 6 are implemented.

Images