Wheat growth grade assessment method, device, equipment and medium

Abstract

The present application discloses a wheat growth grade assessment method, apparatus, device, and medium, relating to the field of computer technology. The method comprises: processing a reflectance image of a wheat study area using a target extraction model to obtain wheat distribution results in the wheat study area, determining a first normalized vegetation index (NDI) for the current season and the mean of reconstructed vegetation indices for each historical period corresponding to the current season; determining a wheat growth assessment benchmark for the wheat study area in the current season based on the mean of the reconstructed vegetation indices and the mean of the first normalized vegetation indices; constructing a growth score matrix for the wheat monitoring area based on a reconstructed discontinuity list obtained by reconstructing an initial natural discontinuity list for the wheat monitoring area using the wheat growth assessment benchmark; and determining the wheat growth grade for the wheat monitoring area using the NDI and a growth uniformity score matrix for the wheat monitoring area. This reduces the complexity of wheat growth grade assessment and improves accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of remote sensing image processing and agricultural monitoring, and in particular to a method, device, equipment and medium for evaluating the growth grade of wheat. Background Art

[0002] Rapid and accurate acquisition of farm crop growth information is the prerequisite and foundation for achieving agricultural informatization and intelligence, and also the basis for efficient management and precise application of fertilizers, water, and pesticides. Using remote sensing imagery to accurately rate crop growth on farms helps farm managers promptly understand crop growth status, health status, and environmental conditions. This precise monitoring provides a more intuitive understanding of crop distribution on farms, as well as their growth status compared to the current season and historical periods. This provides a basis for decision-making regarding irrigation, fertilization, and pesticide application, ultimately enabling precision agricultural management.

[0003] Currently, the most common and practical method for evaluating crop growth is direct monitoring. This involves using remote sensing data to obtain parameters (such as the Normalized Difference Vegetation Index) and then correlating them with crop growth to identify relationships. This method requires a theoretical foundation and ground-based measurement points to establish a growth rating model. Furthermore, the modeling process must be repeated each time, making it complex and difficult to implement in production.

[0004] In summary, how to reduce the complexity of wheat growth grade assessment and improve the accuracy of growth grade assessment is a problem to be solved in this field. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a method, device, equipment and medium for wheat growth grade assessment, which reduces the complexity of wheat growth grade assessment and improves the accuracy of growth grade assessment. The specific scheme is as follows:

[0006] In a first aspect, the present application discloses a method for assessing wheat growth grade, comprising:

[0007] Processing the reflectance image of the wheat study area using the target extraction model to obtain a wheat distribution result in the wheat study area, and determining a first normalized vegetation index of the current season and a second normalized vegetation index of each historical period corresponding to the current season using the wheat distribution result and the reflectance image of the wheat study area;

[0008] Reconstructing the mean of the second normalized difference vegetation index to obtain a reconstructed vegetation index mean, and determining a wheat growth evaluation benchmark for the wheat research area in the current season based on the reconstructed vegetation index mean and the mean of the first normalized difference vegetation index;

[0009] Reconstructing an initial natural breakpoint list of a wheat monitoring area using the wheat growth evaluation benchmark to obtain a reconstructed breakpoint list, and constructing a growth score matrix of the wheat monitoring area based on the reconstructed breakpoint list;

[0010] A growth uniformity score matrix of the wheat monitoring area is obtained, and the growth grade of the wheat in the wheat monitoring area is determined using the growth score matrix and the growth uniformity score matrix.

[0011] Optionally, the process of processing the reflectance image of the wheat study area using the target extraction model to obtain the wheat distribution result in the wheat study area includes:

[0012] The reflectance image of the wheat study area is processed using the target extraction model to obtain the initial wheat distribution result in the wheat study area;

[0013] The initial wheat distribution result in the wheat study area is corrected to obtain the wheat distribution result in the wheat study area; wherein the correction processing includes removing broken spots and filling holes.

[0014] Optionally, before processing the reflectance image of the wheat study area using the target extraction model to obtain the wheat distribution result in the wheat study area, the method further includes:

[0015] Determining a wheat monitoring area and expanding the wheat monitoring area to obtain a wheat study area;

[0016] Based on the wheat sowing time and the wheat harvesting time of the wheat research area, remote sensing images of the current season and the historical periods corresponding to the current season of the wheat research area are collected respectively;

[0017] The remote sensing image is preprocessed to obtain a reflectance image of the wheat research area; wherein the preprocessing includes radiation calibration, atmospheric correction, geometric correction, data fusion, clipping and splicing processing.

[0018] Optionally, before processing the reflectance image of the wheat study area using the target extraction model to obtain the wheat distribution result in the wheat study area, the method further includes:

[0019] Extracting a green period reflectance image from the reflectance image of the wheat study area, and creating a training sample using the vector boundary of the wheat monitoring area and the green period reflectance image;

[0020] The initial extraction model is trained using the training samples to obtain a target extraction model; wherein the initial extraction model is an initial support vector machine.

[0021] Optionally, reconstructing the mean of the second normalized vegetation index to obtain a reconstructed vegetation index mean includes:

[0022] Calculating the vegetation index mean of the second normalized difference vegetation index based on a preset confidence level to obtain a mean of the second normalized difference vegetation index; wherein the mean of the second normalized difference vegetation index is expressed in an annual cumulative daily form;

[0023] According to the preset normal growth curve of wheat, the mean of the second normalized vegetation index is reconstructed using the Savitzky-Golay filter fitting method to obtain the reconstructed vegetation index mean.

[0024] Optionally, obtaining the growth uniformity score matrix of the wheat monitoring area includes:

[0025] Extracting the reflectance image of the wheat monitoring area from the reflectance image of the wheat research area, obtaining the normalized vegetation index image of the wheat monitoring area based on the reflectance image of the wheat monitoring area, and then calculating the pixel standard deviation of the normalized vegetation index image of the wheat monitoring area;

[0026] Obtain a list of standard deviation breakpoints of the pixel standard deviation, and use the list of standard deviation breakpoints to score the pixel standard deviation to obtain a growth uniformity score matrix for the wheat monitoring area.

[0027] Optionally, the determining the wheat growth grade of the wheat monitoring area using the growth score matrix and the growth uniformity score matrix includes:

[0028] Determining a first weight of the growth score matrix and a second weight of the growth uniformity score matrix;

[0029] Determining the wheat growth condition of the wheat monitoring area using the growth condition score matrix, the growth uniformity score matrix, the first weight, and the second weight;

[0030] The growth condition of the wheat in the wheat monitoring area is evaluated to obtain the growth condition grade of the wheat in the wheat monitoring area.

[0031] In a second aspect, the present application discloses a wheat growth grade assessment device, comprising:

[0032] a vegetation index determination module, configured to process the reflectance image of the wheat study area using a target extraction model to obtain a wheat distribution result in the wheat study area, and determine a first normalized vegetation index of the current season and second normalized vegetation indices of each historical period corresponding to the current season using the wheat distribution result and the reflectance image of the wheat study area;

[0033] an evaluation benchmark determination module, configured to reconstruct the mean of the second normalized difference vegetation index to obtain a reconstructed vegetation index mean, and determine a wheat growth evaluation benchmark for the wheat research area in the current season based on the reconstructed vegetation index mean and the mean of the first normalized difference vegetation index;

[0034] A scoring matrix construction module is used to reconstruct the initial natural breakpoint list of the wheat monitoring area using the wheat growth evaluation benchmark to obtain a reconstructed breakpoint list, and construct a growth score matrix for the wheat monitoring area based on the reconstructed breakpoint list;

[0035] The growth grade determination module is used to obtain the growth uniformity score matrix of the wheat monitoring area, and use the growth score matrix and the growth uniformity score matrix to determine the wheat growth grade of the wheat monitoring area.

[0036] In a third aspect, the present application discloses an electronic device, comprising:

[0037] Memory, used to store computer programs;

[0038] A processor is used to execute the computer program to implement the steps of the aforementioned disclosed method for assessing wheat growth grade.

[0039] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the steps of the aforementioned method for assessing wheat growth grade are implemented.

[0040] The beneficial effects of the present application are as follows: the present application uses a target extraction model to process the reflectance image of the wheat study area to obtain the wheat distribution result in the wheat study area, and uses the wheat distribution result and the reflectance image of the wheat study area to determine the first normalized vegetation index of the current season and the second normalized vegetation index of each historical period corresponding to the current season; the mean of the second normalized vegetation index is reconstructed to obtain the mean of the reconstructed vegetation index, and the wheat growth evaluation benchmark of the wheat study area in the current season is determined based on the mean of the reconstructed vegetation index and the mean of the first normalized vegetation index; the initial natural break point list of the wheat monitoring area is reconstructed using the wheat growth evaluation benchmark to obtain a reconstructed break point list, and a growth score matrix of the wheat monitoring area is constructed based on the reconstructed break point list; the growth uniformity score matrix of the wheat monitoring area is obtained, and the growth grade of the wheat monitoring area is determined using the growth score matrix and the growth uniformity score matrix. It can be seen from this that, on the one hand, the present application only needs to pre-build a target extraction model once, and then the target extraction model can be directly used to obtain the wheat distribution results of the wheat study area, thereby reducing the complexity of the wheat growth grade; on the other hand, the present application needs to determine the wheat growth evaluation benchmark based on the normalized vegetation index of the current season and each historical period corresponding to the current season, and the average of the normalized vegetation index of the current season. That is to say, the present application uses the historical period comparison method and the season period wheat comparison method to obtain the wheat growth evaluation benchmark. In this way, the obtained wheat growth evaluation benchmark is more comprehensive to ensure that the growth score matrix of the wheat monitoring area is more reliable and reasonable. Furthermore, when determining the wheat growth grade of the wheat monitoring area, the present application not only considers the growth score matrix of the wheat monitoring area, but also needs to consider the growth uniformity score matrix that can reflect the wheat growth quality of the wheat monitoring area. Therefore, the wheat growth grade obtained subsequently is more accurate, reliable and in line with reality. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without any creative work.

[0042] Figure 1 This is a flow chart of a wheat growth grade assessment method disclosed in this application;

[0043] Figure 2 This is a flow chart of a specific wheat growth grade assessment method disclosed in this application;

[0044] Figure 3 This is a flow chart of another specific wheat growth grade assessment method disclosed in this application;

[0045] Figure 4 This is a schematic structural diagram of a wheat growth grade assessment device disclosed in this application;

[0046] Figure 5 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0048] Currently, the most common and practical method for evaluating crop growth is direct monitoring. This involves using remote sensing data to obtain parameters (such as the Normalized Difference Vegetation Index) and then correlating them with crop growth to identify relationships. This method requires a theoretical foundation and ground-based measurement points to establish a growth rating model. Furthermore, the modeling process must be repeated each time, making it complex and difficult to implement in production.

[0049] To this end, this application provides a wheat growth grade assessment scheme to reduce the complexity of wheat growth grade assessment and improve the accuracy of growth grade assessment.

[0050] See also Figure 1 As shown, the embodiment of the present application discloses a method for evaluating the growth grade of wheat, comprising:

[0051] Step S11: Use the target extraction model to process the reflectance image of the wheat study area to obtain the wheat distribution result in the wheat study area, and use the wheat distribution result and the reflectance image of the wheat study area to determine the first normalized vegetation index of the current season and the second normalized vegetation index of each historical period corresponding to the current season.

[0052] In this embodiment, before using the target extraction model to process the reflectance image of the wheat study area to obtain the wheat distribution result in the wheat study area, it also includes: determining the wheat monitoring area and expanding the wheat monitoring area to obtain the wheat study area; based on the wheat sowing time and the wheat harvesting time of the wheat study area, respectively collecting the remote sensing images of the current season of the wheat study area and the historical periods corresponding to the current season; preprocessing the remote sensing images to obtain the reflectance image of the wheat study area; wherein the preprocessing includes radiation calibration, atmospheric correction, geometric correction, data fusion, clipping and splicing processing. Determine the monitoring area and expand the monitoring area to obtain the study area, for example, its range is the town where the monitoring area is located or 10 kilometers around the monitoring area, that is, the study area contains the monitoring area; based on the wheat sowing time and wheat harvesting time of the wheat study area, obtain the remote sensing images of the current season and the remote sensing images of the historical period corresponding to the current season respectively. The remote sensing images can be Sentinel-2 (Sentinel-2) images, and preprocess these remote sensing images to obtain the reflectance image of the wheat study area, wherein the preprocessing may include radiation calibration, atmospheric correction, geometric correction, data fusion, clipping and splicing processing.

[0053] In this embodiment, before using the target extraction model to process the reflectance image of the wheat study area to obtain the wheat distribution result in the wheat study area, it also includes: extracting the green period reflectance image from the reflectance image of the wheat study area, and using the vector boundary of the wheat monitoring area and the green period reflectance image to create a training sample; using the training sample to train the initial extraction model to obtain the target extraction model; wherein, the initial extraction model is an initial support vector machine. The reflectivity image of the wheat study area includes reflectivity images of wheat in various growth cycles. In order to better obtain the wheat distribution results later, the selected period is the greening period of wheat. That is to say, the greening period reflectivity image is extracted from the reflectivity image of the wheat study area, and the vector boundary of the wheat monitoring area and the greening period reflectivity image are used to produce sample data for wheat identification, that is, training samples. That is to say, the training samples include two types of training samples, one type is wheat, and the other type is other elements. Other elements include hardened surface, houses, water systems, shrubs, woods, open space, roads, etc. Then, the training samples are used to train the initial extraction model to obtain the target extraction model. The extraction model is, for example, a support vector machine (SVM).

[0054] In this embodiment, the reflectance image of the wheat study area is processed using the target extraction model to obtain the wheat distribution result in the wheat study area, including: using the target extraction model to process the reflectance image of the wheat study area to obtain the initial wheat distribution result in the wheat study area; correcting the initial wheat distribution result in the wheat study area to obtain the wheat distribution result in the wheat study area; wherein the correction processing includes debris removal and hole filling. The reflectance image of the wheat study area is input into the target extraction model, and the target extraction model performs corresponding processing on it to obtain the initial wheat distribution result in the corresponding wheat study area, that is, the area in the wheat study area where wheat is planted. The initial wheat distribution result also needs to be corrected by debris removal and hole filling to obtain a more accurate wheat distribution result in the wheat study area.

[0055] The wheat distribution results and the reflectance image of the wheat study area were used to determine the first normalized difference vegetation index (NDVI) of the current season and the second normalized difference vegetation index of each historical period corresponding to the current season. The calculation formula of the normalized difference vegetation index is as follows:

[0056] NDVI = (Nir - Red) / (Nir + Red);

[0057] Where Nir represents the reflectivity of the near-infrared band, which corresponds to the B4 band of the reflectivity image; Red represents the reflectivity of the infrared band, which corresponds to the B3 band of the reflectivity image.

[0058] Step S12: reconstruct the mean of the second normalized vegetation index to obtain the mean of the reconstructed vegetation index, and determine the wheat growth evaluation benchmark of the wheat research area in the current season based on the mean of the reconstructed vegetation index and the mean of the first normalized vegetation index.

[0059] Calculate the mean of the second normalized vegetation index, reconstruct the time series index mean according to the change law of wheat growth, and obtain the mean of the reconstructed vegetation index. The process of determining the wheat growth evaluation benchmark in the wheat study area is as follows:

[0060] 1) Calculate the histogram of the first normalized difference vegetation index of the image in the current season, set a 90% confidence level, and calculate the mean of the first normalized difference vegetation index in the study area in the current season, which is recorded as NDVIday-c;

[0061] 2) Determine the mean NDVIday-h of each reconstructed vegetation index for each historical period, compare NDVIday-c and NDVIday-h, and use the higher value as the starting standard for calculating the excellent grade of wheat, and the lower value as the starting standard for calculating the good grade of wheat. It can be understood that this method is a historical comparison method, that is, the wheat of each historical period in the same historical time period as the current season is compared.

[0062] Step S13: reconstructing the initial natural breakpoint list of the wheat monitoring area using the wheat growth evaluation benchmark to obtain a reconstructed breakpoint list, and constructing a growth score matrix of the wheat monitoring area based on the reconstructed breakpoint list.

[0063] The specific process of reconstructing the discontinuity list using the wheat growth evaluation benchmark is as follows: first, construct the initial natural discontinuity list [J1, J2, J3, J4, J5] of the wheat monitoring area, and then use the mean of the first normalized vegetation index NDVIday-c and the mean of the reconstructed vegetation index NDVIday-h to replace the corresponding discontinuity points in the initial natural discontinuity list to obtain the reconstructed discontinuity list, for example, the reconstructed discontinuity list is [J1, J2, J3, NDVIday-c, NDVIday-h]. Based on the reconstructed discontinuity list, the wheat growth in the monitoring area is divided, and the growth rating score matrix NDVI is produced. score .

[0064] Step S14: obtaining a growth uniformity score matrix of the wheat monitoring area, and determining the wheat growth grade of the wheat monitoring area using the growth score matrix and the growth uniformity score matrix.

[0065] In this embodiment, the method of determining the wheat growth grade of the wheat monitoring area using the growth score matrix and the growth uniformity score matrix includes: determining the first weight of the growth score matrix and the second weight of the growth uniformity score matrix; determining the wheat growth in the wheat monitoring area using the growth score matrix, the growth uniformity score matrix, the first weight, and the second weight; and evaluating the growth grade of the wheat in the wheat monitoring area to obtain the wheat growth grade in the wheat monitoring area. Determine the growth rating score matrix NDVI score The first weight K1 and the growth uniformity score matrix STD score The second weight K2, for example, K1, K2 are both 0.5, wherein the wheat growth in the wheat monitoring area is determined score The calculation formula is as follows:

[0066] Growth score =K1×NDVI score+K2×STD score ;

[0067] The growth of wheat in the wheat monitoring area is evaluated to obtain the growth grade of wheat in the wheat monitoring area. The specific growth grade evaluation example is as follows:

[0068] 1) When Growth score When ≤40, the wheat growth grade is poor;

[0069] 2) 40<Growth score ≤60: wheat growth grade is medium;

[0070] 3) 60<Growth score ≤80: Wheat growth grade is good;

[0071] 4) 80<Growth score ≤100: Wheat growth grade is excellent.

[0072] The beneficial effects of the present application are as follows: the present application uses a target extraction model to process the reflectance image of the wheat study area to obtain the wheat distribution result in the wheat study area, and uses the wheat distribution result and the reflectance image of the wheat study area to determine the first normalized vegetation index of the current season and the second normalized vegetation index of each historical period corresponding to the current season; the mean of the second normalized vegetation index is reconstructed to obtain the mean of the reconstructed vegetation index, and the wheat growth evaluation benchmark of the wheat study area in the current season is determined based on the mean of the reconstructed vegetation index and the mean of the first normalized vegetation index; the initial natural break point list of the wheat monitoring area is reconstructed using the wheat growth evaluation benchmark to obtain a reconstructed break point list, and a growth score matrix of the wheat monitoring area is constructed based on the reconstructed break point list; the growth uniformity score matrix of the wheat monitoring area is obtained, and the growth grade of the wheat monitoring area is determined using the growth score matrix and the growth uniformity score matrix. It can be seen from this that, on the one hand, the present application only needs to pre-build a target extraction model once, and then the target extraction model can be directly used to obtain the wheat distribution results of the wheat study area, thereby reducing the complexity of the wheat growth grade; on the other hand, the present application needs to determine the wheat growth evaluation benchmark based on the normalized vegetation index of the current season and each historical period corresponding to the current season, and the average of the normalized vegetation index of the current season. That is to say, the present application uses the historical period comparison method and the season period wheat comparison method to obtain the wheat growth evaluation benchmark. In this way, the obtained wheat growth evaluation benchmark is more comprehensive to ensure that the growth score matrix of the wheat monitoring area is more reliable and reasonable. Furthermore, when determining the wheat growth grade of the wheat monitoring area, the present application not only considers the growth score matrix of the wheat monitoring area, but also needs to consider the growth uniformity score matrix that can reflect the wheat growth quality of the wheat monitoring area. Therefore, the wheat growth grade obtained subsequently is more accurate, reliable and in line with reality.

[0073] See also Figure 2 As shown, the embodiment of the present application discloses a specific method for evaluating the growth grade of wheat, comprising:

[0074] Step S21: Use the target extraction model to process the reflectance image of the wheat study area to obtain the wheat distribution result in the wheat study area, and use the wheat distribution result and the reflectance image of the wheat study area to determine the first normalized vegetation index of the current season and the second normalized vegetation index of each historical period corresponding to the current season.

[0075] Step S22: performing histogram statistics on the second normalized vegetation index based on a preset confidence level to obtain a mean value of the second normalized vegetation index; wherein the mean value of the second normalized vegetation index is expressed in an annual daily form.

[0076] In this embodiment, the vegetation index of each period is statistically analyzed by histogram, and the histogram distribution is obtained. The confidence level is preset to 90%, and the mean value of the vegetation index is statistically analyzed, which is recorded as NDVI. day-year , day represents the annual accumulation day of index statistics, year represents the historical year, that is, the mean of the second normalized vegetation index is calculated in the form of annual accumulation day, and the time series mean of the second normalized vegetation index NDVI is calculated day-mean The formula is as follows:

[0077] NDVI day-mean =(NDVI day-year1 +NDVI day-year2 +...+NDVI day-yearn ) / (yearn-year1+1).

[0078] Step S23: reconstructing the mean of the second normalized vegetation index according to a preset normal wheat growth curve and using a Savitzky-Golay filter fitting method to obtain a reconstructed vegetation index mean.

[0079] The mean of the second normalized vegetation index was reconstructed using the Savizky-Golay filter fitting method with an n×s filter window, for example, a window width n of 5 and a step size s of 1. Data fitting was performed with reference to the preset normal wheat growth curve for comparison and judgment. Specifically, the reconstructed mean vegetation index should follow a trend of first rising, then falling, then regenerating and then falling again. Specifically, between the seedling and tillering stages, the reconstructed mean vegetation index showed a slow upward trend, reaching its first peak during the tillering stage. Between the tillering and greening stages, the reconstructed mean vegetation index showed a slow downward and stable trend, tending to stabilize during the wintering stage. Between the greening stage and the booting and flowering stages, the reconstructed mean vegetation index showed an upward trend, reaching its second peak during the booting and flowering stages. After the flowering and booting stages, the reconstructed mean vegetation index showed a downward trend, tending to stabilize during the maturity stage.

[0080] Step S24: determining a wheat growth evaluation benchmark for the wheat research area in the current season based on the mean value of the reconstructed vegetation index and the mean value of the first normalized vegetation index.

[0081] Step S25: reconstructing the initial natural breakpoint list of the wheat monitoring area using the wheat growth evaluation benchmark to obtain a reconstructed breakpoint list, and constructing a growth score matrix of the wheat monitoring area based on the reconstructed breakpoint list.

[0082] Step S26: Obtain the growth uniformity score matrix of the wheat monitoring area, and use the growth score matrix and the growth uniformity score matrix to determine the wheat growth grade of the wheat monitoring area.

[0083] It can be seen that this application expresses the mean of the second normalized vegetation index in the form of annual accumulation days, making it more consistent with the wheat growth conditions. In this way, a more reasonable mean of the reconstructed vegetation index can be reconstructed to make it more consistent with reality, providing strong guarantees for the subsequent determination of the wheat growth evaluation benchmark in the wheat research area and the determination of the wheat growth grade in the wheat monitoring area, and obtaining a more accurate wheat growth grade in the wheat monitoring area.

[0084] See also Figure 3 As shown, the embodiment of the present application discloses another specific method for assessing the growth grade of wheat, comprising:

[0085] Step S31: Use the target extraction model to process the reflectance image of the wheat study area to obtain the wheat distribution result in the wheat study area, and use the wheat distribution result and the reflectance image of the wheat study area to determine the first normalized vegetation index of the current season and the second normalized vegetation index of each historical period corresponding to the current season.

[0086] Step S32: reconstruct the mean of the second normalized vegetation index to obtain the mean of the reconstructed vegetation index, and determine the wheat growth evaluation benchmark of the wheat research area in the current season based on the mean of the reconstructed vegetation index and the mean of the first normalized vegetation index.

[0087] Step S33: reconstructing the initial natural breakpoint list of the wheat monitoring area using the wheat growth evaluation benchmark to obtain a reconstructed breakpoint list, and constructing a growth score matrix of the wheat monitoring area based on the reconstructed breakpoint list.

[0088] Step S34: extracting the reflectance image of the wheat monitoring area from the reflectance image of the wheat study area, and obtaining the normalized vegetation index image of the wheat monitoring area based on the reflectance image of the wheat monitoring area, and then calculating the pixel standard deviation of the normalized vegetation index image of the wheat monitoring area.

[0089] In this embodiment, a window of a preset size is set to calculate the pixel standard deviation of the normalized vegetation index image of the wheat monitoring area. For example, a 3×3 window is set, and the window step size S is 1.

[0090] Step S35: obtaining a list of standard deviation breakpoints of the pixel standard deviation, and using the list of standard deviation breakpoints to score the pixel standard deviation to obtain a growth uniformity score matrix for the wheat monitoring area.

[0091] Using the Jenks classification method, the pixel standard deviation is divided into four levels, and a list of standard deviation discontinuities for each level is obtained [jstd1, jstd2, jstd3, jstd4, jstd5]. The pixel standard deviation is scored with reference to the list of standard deviation discontinuities, that is, the uniformity of the normalized vegetation index in the wheat monitoring area is scored. The smaller the standard deviation, the more uniform the local growth. The specific scoring can be shown as follows:

[0092] 1) First-level standard deviation: jstd1≤std<jstd2, replace the standard deviation with 100;

[0093] 2) Secondary standard deviation: jstd2≤std<jstd3, replace the standard deviation with 80;

[0094] 3) Level 3 standard deviation: jstd3≤std<jstd4, replace the standard deviation with 60;

[0095] 4) Four-level standard deviation: jstd4≤std≤jstd5, replace the standard deviation with 40.

[0096] Step S36: Determine the wheat growth grade of the wheat monitoring area using the growth score matrix and the growth uniformity score matrix.

[0097] It can be seen that growth uniformity is an important indicator for evaluating the consistency of local crop growth. It is of great significance for optimizing management measures, adjusting fertilization and pesticide application, etc. It is one of the important indicators for evaluating the quality of crop growth. Therefore, this application also introduces a growth uniformity scoring matrix to obtain a more practical wheat growth grade in the wheat monitoring area.

[0098] See also Figure 4 As shown, the embodiment of the present application discloses a wheat growth grade assessment device, comprising:

[0099] The vegetation index determination module 11 is configured to process the reflectance image of the wheat study area using the target extraction model to obtain a wheat distribution result in the wheat study area, and determine a first normalized vegetation index of the current season and second normalized vegetation indexes of each historical period corresponding to the current season using the wheat distribution result and the reflectance image of the wheat study area;

[0100] An evaluation benchmark determination module 12 is configured to reconstruct the mean of the second normalized difference vegetation index to obtain a reconstructed vegetation index mean, and determine a wheat growth evaluation benchmark for the wheat study area in the current season based on the reconstructed vegetation index mean and the mean of the first normalized difference vegetation index;

[0101] A scoring matrix construction module 13 is used to reconstruct the initial natural breakpoint list of the wheat monitoring area using the wheat growth evaluation benchmark to obtain a reconstructed breakpoint list, and construct a growth score matrix of the wheat monitoring area based on the reconstructed breakpoint list;

[0102] The growth grade determination module 14 is used to obtain the growth uniformity score matrix of the wheat monitoring area, and determine the wheat growth grade of the wheat monitoring area using the growth score matrix and the growth uniformity score matrix.

[0103] The beneficial effects of the present application are as follows: the present application uses a target extraction model to process the reflectance image of the wheat study area to obtain the wheat distribution result in the wheat study area, and uses the wheat distribution result and the reflectance image of the wheat study area to determine the first normalized vegetation index of the current season and the second normalized vegetation index of each historical period corresponding to the current season; the mean of the second normalized vegetation index is reconstructed to obtain the mean of the reconstructed vegetation index, and the wheat growth evaluation benchmark of the wheat study area in the current season is determined based on the mean of the reconstructed vegetation index and the mean of the first normalized vegetation index; the initial natural break point list of the wheat monitoring area is reconstructed using the wheat growth evaluation benchmark to obtain a reconstructed break point list, and a growth score matrix of the wheat monitoring area is constructed based on the reconstructed break point list; the growth uniformity score matrix of the wheat monitoring area is obtained, and the growth grade of the wheat monitoring area is determined using the growth score matrix and the growth uniformity score matrix. It can be seen from this that, on the one hand, the present application only needs to pre-build a target extraction model once, and then the target extraction model can be directly used to obtain the wheat distribution results of the wheat study area, thereby reducing the complexity of the wheat growth grade; on the other hand, the present application needs to determine the wheat growth evaluation benchmark based on the normalized vegetation index of the current season and each historical period corresponding to the current season, and the average of the normalized vegetation index of the current season. That is to say, the present application uses the historical period comparison method and the same period comparison method to obtain the wheat growth evaluation benchmark. In this way, the obtained wheat growth evaluation benchmark is more comprehensive to ensure that the growth score matrix of the wheat monitoring area is more reliable and reasonable. Furthermore, when determining the wheat growth grade of the wheat monitoring area, the present application not only considers the growth score matrix of the wheat monitoring area, but also needs to consider the growth uniformity score matrix that can reflect the wheat growth quality of the wheat monitoring area. Therefore, the wheat growth grade obtained subsequently is more accurate, reliable, and in line with reality.

[0104] Furthermore, an embodiment of the present application also provides an electronic device. Figure 5 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram should not be considered as any limitation to the scope of application of the present application.

[0105] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Specifically, the device may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps of the wheat growth grade assessment method performed by the electronic device as disclosed in any of the aforementioned embodiments.

[0106] In this embodiment, the power supply 23 is used to provide operating voltage for various hardware devices on the electronic device; the communication interface 24 can create a data transmission channel between the electronic device and external devices. The communication protocol it follows is any communication protocol that can be applied to the technical solution of this application and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world. Its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0107] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0108] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or CD, etc. The resources stored thereon include an operating system 221, a computer program 222 and data 223, etc. The storage method can be temporary storage or permanent storage.

[0109] Among them, the operating system 221 is used to manage and control the various hardware devices and computer programs 222 on the electronic device to enable the processor 21 to calculate and process the massive data 223 in the memory 22. It can be Windows, Unix, Linux, etc. In addition to including computer programs that can be used to complete the wheat growth grade assessment method performed by the electronic device disclosed in any of the aforementioned embodiments, the computer program 222 can further include computer programs that can be used to complete other specific tasks. In addition to including data transmitted by external devices received by the electronic device, the data 223 can also include data collected by its own input and output interface 25.

[0110] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when executed by a processor, the computer program implements the aforementioned method for assessing wheat growth grade. The specific steps of this method can be found in the corresponding contents disclosed in the aforementioned embodiments and will not be repeated here.

[0111] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. Reference can be made to the descriptions of the identical or similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and the relevant parts can be referred to the descriptions of the methods.

[0112] Professionals may further appreciate that the units and algorithmic steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application. The steps of the method or algorithm described in conjunction with the embodiments disclosed herein can be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in random access memory (RAM), memory, read-only memory (ROM), electrically programmable EPROM (Erasable Programmable Read Only Memory), electrically erasable programmable EEPROM (Electrically Erasable Programmable read only memory), registers, hard disk, removable disk, CD-ROM (CoMP23022377act Disc Read-Only Memory), or any other form of storage medium known in the technical field.

[0113] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0114] The above is a detailed introduction to the wheat growth grade assessment method, device, equipment and medium provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for evaluating wheat growth grade, characterized in that: include: Processing the reflectance image of the wheat study area using the target extraction model to obtain a wheat distribution result in the wheat study area, and determining a first normalized vegetation index of the current season and a second normalized vegetation index of each historical period corresponding to the current season using the wheat distribution result and the reflectance image of the wheat study area; Reconstructing the mean of the second normalized difference vegetation index to obtain a reconstructed vegetation index mean, and determining a wheat growth evaluation benchmark for the wheat research area in the current season based on the reconstructed vegetation index mean and the mean of the first normalized difference vegetation index; Reconstructing an initial natural breakpoint list of a wheat monitoring area using the wheat growth evaluation benchmark to obtain a reconstructed breakpoint list, and constructing a growth score matrix of the wheat monitoring area based on the reconstructed breakpoint list; Obtaining a growth uniformity score matrix for the wheat monitoring area, and determining the wheat growth grade of the wheat monitoring area using the growth score matrix and the growth uniformity score matrix; The step of obtaining the growth uniformity score matrix of the wheat monitoring area is as follows: include: Among them, the reflectivity image of the wheat monitoring area is extracted from the reflectivity image of the wheat research area, and the normalized vegetation index image of the wheat monitoring area is obtained based on the reflectivity image of the wheat monitoring area, and then the pixel standard deviation of the normalized vegetation index image of the wheat monitoring area is calculated; the standard deviation discontinuity point list of the pixel standard deviation is obtained, and the pixel standard deviation is scored using the standard deviation discontinuity point list to obtain the growth uniformity score matrix of the wheat monitoring area.

2. The wheat growth grade assessment method according to claim 1, wherein The process of processing the reflectance image of the wheat study area using the target extraction model to obtain the wheat distribution result in the wheat study area includes: The reflectance image of the wheat study area is processed using the target extraction model to obtain the initial wheat distribution result in the wheat study area; The initial wheat distribution result in the wheat study area is corrected to obtain the wheat distribution result in the wheat study area; wherein the correction processing includes removing broken spots and filling holes.

3. The wheat growth grade assessment method according to claim 1, wherein Before the reflectance image of the wheat study area is processed by the target extraction model to obtain the wheat distribution result in the wheat study area, the method further includes: Determining a wheat monitoring area and expanding the wheat monitoring area to obtain a wheat study area; Based on the wheat sowing time and wheat harvesting time of the wheat research area, remote sensing images of the current season and each historical period corresponding to the current season of the wheat research area are collected respectively; The remote sensing image is preprocessed to obtain a reflectance image of the wheat research area; wherein the preprocessing includes radiation calibration, atmospheric correction, geometric correction, data fusion, clipping and splicing processing.

4. The wheat growth grade assessment method according to claim 3, wherein: Before the reflectance image of the wheat study area is processed by the target extraction model to obtain the wheat distribution result in the wheat study area, the method further includes: Extracting a green period reflectance image from the reflectance image of the wheat study area, and creating a training sample using the vector boundary of the wheat monitoring area and the green period reflectance image; The initial extraction model is trained using the training samples to obtain a target extraction model; wherein the initial extraction model is an initial support vector machine.

5. The wheat growth grade assessment method according to any one of claims 1 to 4, characterized in that: The reconstructing the mean of the second normalized vegetation index to obtain a reconstructed vegetation index mean includes: Calculating the mean of the second normalized difference vegetation index based on a preset confidence level to obtain a mean of the second normalized difference vegetation index; wherein the mean of the second normalized difference vegetation index is expressed in an annual cumulative daily form; According to the preset normal growth curve of wheat, the mean of the second normalized vegetation index is reconstructed using the Savitzky-Golay filter fitting method to obtain the reconstructed vegetation index mean.

6. The wheat growth grade assessment method according to claim 1, wherein: The method of determining the wheat growth grade of the wheat monitoring area by using the growth score matrix and the growth uniformity score matrix includes: Determining a first weight of the growth score matrix and a second weight of the growth uniformity score matrix; Determining the wheat growth condition of the wheat monitoring area using the growth condition score matrix, the growth uniformity score matrix, the first weight, and the second weight; The growth condition of the wheat in the wheat monitoring area is evaluated to obtain the growth condition grade of the wheat in the wheat monitoring area.

7. A wheat growth grade assessment device, characterized in that: include: a vegetation index determination module, configured to process the reflectance image of the wheat study area using a target extraction model to obtain a wheat distribution result in the wheat study area, and determine a first normalized vegetation index of the current season and second normalized vegetation indices of each historical period corresponding to the current season using the wheat distribution result and the reflectance image of the wheat study area; an evaluation benchmark determination module, configured to reconstruct the mean of the second normalized difference vegetation index to obtain a reconstructed vegetation index mean, and determine a wheat growth evaluation benchmark for the wheat research area in the current season based on the reconstructed vegetation index mean and the mean of the first normalized difference vegetation index; A scoring matrix construction module is used to reconstruct the initial natural breakpoint list of the wheat monitoring area using the wheat growth evaluation benchmark to obtain a reconstructed breakpoint list, and construct a growth score matrix for the wheat monitoring area based on the reconstructed breakpoint list; A growth grade determination module is used to obtain a growth uniformity score matrix of the wheat monitoring area, and determine the wheat growth grade of the wheat monitoring area using the growth score matrix and the growth uniformity score matrix; Wherein, the growth grade determination module is specifically used to: The reflectance image of the wheat monitoring area is extracted from the reflectance image of the wheat research area, and the normalized vegetation index image of the wheat monitoring area is obtained based on the reflectance image of the wheat monitoring area. Then, the pixel standard deviation of the normalized vegetation index image of the wheat monitoring area is calculated; a list of standard deviation discontinuity points of the pixel standard deviation is obtained, and the pixel standard deviation is scored using the standard deviation discontinuity point list to obtain a growth uniformity score matrix of the wheat monitoring area.

8. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor is used to execute the computer program to implement the steps of the wheat growth grade assessment method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that Used to store computer programs; wherein, when the computer program is executed by a processor, the steps of the wheat growth grade assessment method according to any one of claims 1 to 6 are implemented.

Images