Method and system for monitoring the growth of dryland oats based on unmanned aerial vehicle hyperspectral remote sensing

Abstract

The application provides a dry oat growth monitoring method and system based on unmanned aerial vehicle hyperspectral remote sensing, relates to the technical field of dry oat growth monitoring, and comprises the following steps: adopting radiation correction to process the preprocessed image, calculating the reflectivity of each image pixel under different spectral band conditions by referring to the absolute radiation brightness and known reflectivity of a reference plate, obtaining the average reflectivity of a unit grid at different spectral bands, adopting linear product to construct a growth score index, adopting K-means clustering method to cluster the growth score index of each grid unit, outputting the clustering situation of the growth of dry oat in the grid unit, setting a judgment threshold according to the clustering situation of the growth of dry oat, and realizing growth classification. The reference plate is introduced to calibrate the reflectivity, the pixel-level absolute reflectivity is calculated through a radiation transmission equation, and the influence of illumination condition change is eliminated; the K-means clustering is adopted to automatically divide the growth grades, and the threshold can be adaptively generated based on data distribution.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of dry oat growth monitoring, in particular to a dry oat growth monitoring method and system based on unmanned aerial vehicle hyperspectral remote sensing. BACKGROUND

[0002] Traditional dry oat growth monitoring methods usually rely on manual surveying or low-resolution remote sensing images, which have limitations in time efficiency and spatial resolution, and cannot accurately reflect the growth status of crops in time, leading to the inability of farmers to make timely agricultural management decisions. With the rapid development of unmanned aerial vehicle technology, hyperspectral remote sensing technology provides a new solution for crop monitoring. By obtaining high-resolution spectral images, the growth status of crops and their environmental stress response can be more accurately evaluated.

[0003] In the prior art, a crop is photographed by sub-regions using an unmanned aerial vehicle

[0004] , different sub-regions of remote sensing images are obtained, all remote sensing images are spliced to form a whole crop remote sensing image, and the growth distribution state information of the crop is obtained by analyzing the whole crop remote sensing image to determine the crop growth demand information of different sub-regions. However, this method does not consider the influence of soil bare area on vegetation, does not consider the emissivity of vegetation under different spectral conditions, and does not reflect the growth trend of crops by multiple index indicators, and does not set corresponding thresholds to divide the growth of crops. Therefore, there is an urgent need for a dry oat growth monitoring method based on unmanned aerial vehicle remote sensing.

[0005] The above information disclosed in the background section is only used to enhance the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0006] The purpose of the present application is to provide a dry oat growth monitoring method and system based on unmanned aerial vehicle hyperspectral remote sensing to solve the problems raised in the background.

[0007] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0008] The dry oat growth monitoring method based on unmanned aerial vehicle hyperspectral remote sensing comprises the following specific steps:

[0009] S1: The boundary of the target monitoring dry oat planting area is calibrated, the planting area is divided into several identical rectangular grid units according to the calibrated boundary, and the spectral image of each grid unit is obtained by using an unmanned aerial vehicle to obtain the spectral image, and the spectral image is preprocessed;

[0010] S2: screening the reflectance bands of the pretreated spectral image, for each grid cell, obtaining the reflectance mean value of all pixels under different bands respectively, obtaining the average reflectance data of the grid cell under different bands, classifying all grid cells with the set band threshold, and marking the grid cell as soil bare area or vegetation covered area;

[0011] S3: dynamically calculating the adaptive parameters of the soil background according to the spectral images of all grid cells marked as soil bare area, using the multi-spectral coupling to construct the vegetation spectral index and the water stress index as the index for monitoring the growth of the dry oat, and correcting the vegetation spectral index and the water stress index of the grid corresponding to the vegetation covered area through the adaptive parameters of the soil background;

[0012] S4: based on the corrected vegetation spectral index and the water stress index of each grid cell of the vegetation covered area, using linear product to construct the growth score index, and generating the growth score index corrected by the adaptive parameters of the soil background;

[0013] S5: using K-means clustering method to cluster the growth score index of each grid cell of the vegetation covered area, outputting the clustering situation of the growth of the dry oat of the grid cell of the vegetation covered area, setting a judgment threshold according to the clustering situation of the growth of the dry oat, and realizing the growth classification.

[0014] Further, the spectral image includes reflectance spectral information of a plurality of pixel points, the spectral information includes a corresponding relationship between wavelength and reflectance value, and the method for pretreating the spectral image is:

[0015] For each pixel point in the spectral image of each grid cell, the reflectance spectral curve of the pixel point is extracted, the reflectance values of a plurality of bands before and after each band in the spectral curve of the pixel point are taken based on a set window length, the average value of the reflectance in the window is taken as the smoothing output value of the current band, the original reflectance value is replaced with the smoothing output value, and the pretreatment of the reflectance spectral curve of each pixel point is completed.

[0016] Further, the screened reflectance bands are four bands of 、 、 and For each pretreated spectral image, for the screened reflectance bands, all pixels in the spectral image are traversed, the reflectance values of all pixels under each screened band are collected, and the collected reflectance values of all pixels are averaged to obtain the average reflectance of the spectral image under the band.

[0017] For each spectral image corresponding to each grid cell, the average reflectivity calculation of the four target bands is sequentially completed, and the average reflectivity of each grid cell in 、 、 and four bands is obtained;

[0018] The average reflectivity of each grid cell in four bands is converted into absolute radiance, and the formula is:

[0019] ;

[0020] Wherein, represents the average reflectivity of the th grid cell in the band, and respectively represent the gain coefficient and the bias term of the band reflectivity, represents the absolute radiance of the th grid cell in the band, represents the wavelength value of the screened band;

[0021] The average reflectivity data of the grid cell in different bands is obtained by referring to the absolute radiance of the reference plate combined with the average reflectivity of each grid cell in four bands, and the formula is:

[0022] ;

[0023] Wherein, the th grid cell in the band average reflectivity data, and respectively represent the radiance and the calibrated reflectivity of the reference plate in the band, and the average reflectivity data corresponding to each grid cell includes the average reflectivity data in 、 、 and four bands.

[0024] Further, the lower limit threshold of the reflectivity of the near-infrared spectrum of the vegetation and the upper limit threshold of the reflectivity of the red spectrum are set, and the whole planting area is classified by the set threshold, the reflectivity image in the threshold interval is identified as the soil bare area, and the reflectivity image outside the threshold interval is identified as the vegetation covered area.

[0025] For each grid cell, its in average reflectance data in the wave band, respectively set lower limit threshold of reflectance in the wave band and upper limit threshold of reflectance in the wave band, according to the following classification rule:

[0026] when the average reflectance of the grid cell in the wave band is higher than or equal to the set lower limit threshold of reflectance, and the average reflectance of the grid cell in the wave band is lower than or equal to the set upper limit threshold of reflectance, mark the grid cell as a vegetation cover area; otherwise, mark the grid cell as a soil bare area;

[0027] By sequentially performing the above determination on all grid cells, the classification of soil bare area and vegetation cover area is realized.

[0028] Further, according to the spectral images of all grid cells marked as soil bare area, the adaptive parameters of soil background are dynamically calculated, and the specific steps are:

[0029] For all grid cells that have been marked as soil bare area, collect the spectral images corresponding to each grid cell, including the average reflectance data in , , and four wave bands;

[0030] For all grid cells of soil bare area, respectively, the average reflectance values in each wave band are counted to form a spectral feature set of soil bare area;

[0031] On the basis of the spectral feature set of soil bare area, the adaptive parameters of soil background are calculated by statistical analysis method, and the adaptive parameters include the mean and standard deviation of soil average reflectance in each wave band, and the specific steps are:

[0032] For each wave band, calculate the mean of the average reflectance of all grid cells of soil bare area as the adaptive mean parameter of soil background in the wave band;

[0033] For each target wave band, calculate the standard deviation of the average reflectance of all grid cells of soil bare area as the adaptive dispersion parameter of soil background in the wave band.

[0034] Further, based on the average reflectance of the grid cell, the multi-spectral coupling is used to construct vegetation spectral index and water stress index for the grid cell marked as vegetation cover area as the index for monitoring the growth of dry oat, and the specific steps are:

[0035] ; ​​

[0036] ;

[0037] wherein, represents the vegetation spectral index of the th grid cell; represents the water stress index of the th grid cell; represents the number of grid indices of the whole planting area; represents the average reflectance of the th grid cell under the wave band ; represents the average reflectance of the th grid cell under the wave band ; represents the average reflectance of the th grid cell under the wave band .

[0038] Further, the vegetation spectral index and the water stress index corresponding to the grid of the vegetation coverage area are corrected by the adaptive parameter of the soil background, and the specific steps are as follows:

[0039] For the grid cell of the vegetation coverage area , the corrected value of the reflectance under the wave band is:

[0040] ;

[0041] wherein, represents the average reflectance after correction under the wave band ; represents the mean value of the soil reflectance under the wave band ; represents the standard deviation of the soil reflectance under the wave band ;

[0042] Based on the average reflectance of each wave band after correction, the vegetation spectral index and the water stress index after correction of the adaptive parameter of the soil background are generated, and the specific steps are as follows:

[0043] ;

[0044] ;

[0045] wherein, represents the corrected vegetation spectral index of the th grid cell; represents the average reflectance after correction under the wave band ; represents the wave band average reflectivity after correction; a corrected moisture stress index representing the th grid cell;

[0046] for the th grid cell, a vigor score index of each grid cell is constructed based on the corrected vegetation spectral index and the moisture stress index:

[0047] ;

[0048] a vigor score index representing the th grid cell; an inhibition intensity of moisture stress on the vigor score is determined based on expert scoring.

[0049] Further, K-means clustering is used to cluster the vigor score index of each grid point, and the vigor classification of the drought-grown oats in the entire wheat field is output, specifically:

[0050] Three initial cluster center values are randomly selected as the starting centers of each category. For the vigor score index of each grid cell in a vegetation coverage area, the distance to each cluster center is calculated, and it is assigned to the category to which the nearest cluster center belongs.

[0051] For the vigor score index of all grid cells assigned to the category in each category, the mean value is calculated as the new cluster center.

[0052] Based on the updated cluster center, the distance between the vigor score index of each grid cell in a vegetation coverage area and the updated cluster center is repeatedly calculated, and it is assigned to the category to which the nearest cluster center belongs until the cluster center no longer changes, and the clustering is completed.

[0053] Further, according to the clustering of the vigor of the drought-grown oats, a judgment threshold is set to realize the vigor classification, specifically:

[0054] All the vigor score indexes are finally divided into clusters, and the cluster center corresponding to each cluster is , and arranged in ascending order as:

[0055] ;

[0056] wherein, , respectively represent the smallest, medium and largest center values of the vigor score index cluster;

[0057] The division points of the vigor are calculated respectively:

[0058] ;

[0059] ;

[0060] wherein, represents the demarcation value between weak growth potential and normal growth potential; represents the demarcation value between normal growth potential and strong growth potential;

[0061] when is less than or equal to , the dry oat is judged as the weak growth potential case; when is greater than and less than or equal to , the dry oat is judged as the normal growth potential case; when is greater than , the dry oat is judged as the strong growth potential case.

[0062] The application further provides a dry oat growth potential monitoring system based on unmanned aerial vehicle hyperspectral remote sensing, which is used for executing the monitoring method, and comprises:

[0063] A data acquisition module is configured to demarcate the boundary of a target monitoring dry oat planting area, divide the planting area into a plurality of same rectangular grid units according to the demarcated boundary, and acquire spectral images of each grid unit by using an unmanned aerial vehicle to pre-process the spectral images.

[0064] A grid processing module is configured to filter the reflectivity bands of the pre-processed spectral images, acquire the reflectivity mean value of all pixels under different bands for each grid unit, obtain the average reflectivity data of the grid unit under different bands, and classify all grid units by using a set band threshold to mark the grid units as soil bare areas or vegetation covered areas.

[0065] An index construction module is configured to dynamically calculate adaptive parameters of a soil background according to the spectral images of all grid units marked as soil bare areas, construct a vegetation spectral index and a water stress index by using multi-spectral coupling for the grid units marked as vegetation covered areas as indexes for monitoring the growth potential of dry oat, and correct the vegetation spectral index and the water stress index corresponding to the grid of the vegetation covered area by using the adaptive parameters of the soil background.

[0066] A growth potential scoring module is configured to construct a growth potential scoring index by using linear product based on the corrected vegetation spectral index and the water stress index of each grid unit of the vegetation covered area, and generate the growth potential scoring index corrected by the adaptive parameters of the soil background.

[0067] The longness classification module is used for adopting K-means clustering method to cluster the longness score index of the grid unit of each vegetation coverage area, outputting the clustering condition of the longness of the dry oat of the grid unit of the vegetation coverage area, setting a judgment threshold according to the clustering condition of the longness of the dry oat, and realizing longness classification.

[0068] Compared with the prior art, the present application has the following beneficial effects:

[0069] The present application solves the problem of insufficient adaptability of traditional static threshold to complex farmland environment by dynamically compensating the soil background interference in the vegetation spectral index based on the adaptive parameters of the soil bare area brightness index; the longness score index is constructed by the linear product of the vegetation spectral index and the water stress index, which synchronously represents the vegetation coverage and the water stress degree, overcoming the limitations of single index analysis; the K-means clustering is combined with the adaptive score threshold to realize the local adaptive division of the longness grade, compared with the global threshold classification method, the classification accuracy is improved, and the robustness is significantly enhanced, especially in the sparse vegetation area; the corrected vegetation index and the water stress index are coupled by linear product to construct the composite longness score index, which breaks through the limitation of traditional method of single dependence on vegetation coverage, and can synchronously reflect the crop biomass and drought resistance, providing multi-dimensional basis for precise longness evaluation. BRIEF DESCRIPTION OF DRAWINGS

[0070] Figure 1 It is a whole method flowchart of the present application;

[0071] Figure 2 It is a change relation graph of the longness score index and the corrected vegetation spectral index;

[0072] Figure 3 It is a change relation graph of the longness score index and the corrected water stress index;

[0073] Figure 4 It is a whole system structure block diagram of the present application. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application is further described in detail below in combination with specific embodiments.

[0075] It should be noted that, unless otherwise defined, technical terms or scientific terms used in the present application shall be understood as having the usual meaning as understood by a person with ordinary skill in the art to which the present application pertains. The terms "first", "second", and similar terms used in the present application do not indicate any order, number, or importance, but are only used to distinguish different components. The terms "include", "contain", and similar terms mean that the elements or objects before the terms encompass the elements or objects listed after the terms and their equivalents, and do not exclude other elements or objects. The terms "connect" or "connected" and similar terms are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms "upper", "lower", "left", "right", and the like are only used to indicate relative positional relationships, which can change accordingly when the absolute positions of the described objects change.

[0076] Embodiments:

[0077] Referring to Figures 1-3 The present application provides a technical solution:

[0078] The method for monitoring the growth of dryland oats based on unmanned aerial vehicle hyperspectral remote sensing includes the following specific steps:

[0079] S1: The boundary of the target monitoring dryland oat planting area is demarcated, the planting area is divided into a plurality of identical rectangular grid units according to the demarcated boundary, and an unmanned aerial vehicle is used to obtain spectral images of each grid unit and pre-process the spectral images.

[0080] When demarcating the boundary of the target monitoring dryland oat planting area, first, a high-precision GPS device and an unmanned aerial vehicle are used to obtain high-resolution remote sensing images of the area, then remote sensing image processing software is used to analyze the images, an edge detection algorithm is used to identify the contour of the oat planting area and demarcate the boundary, and after demarcation, GIS software is used to divide the planting area into a plurality of rectangular grid units of the same size, so as to ensure that each grid unit can uniformly cover the entire planting area and facilitate the unmanned aerial vehicle to obtain spectral image data in each grid in the future. Such division will provide a standardized spatial framework for subsequent spectral analysis and crop growth monitoring.

[0081] The spectral image includes reflection spectral information of a plurality of pixel points, and the spectral information includes a corresponding relationship between wavelength and reflectivity value. The method for pre-processing the spectral image is:

[0082] For each pixel point in the spectral image of each grid cell, the reflectance spectrum curve of the pixel point is extracted, and for each waveband in the spectrum curve of the pixel point, the reflectance values of several wavebands before and after the current waveband are taken, the average value of the reflectance values in the window is taken as the smoothing output value of the current waveband, and the original reflectance value is replaced with the smoothing output value, thereby completing the preprocessing of the reflectance spectrum curve of each pixel point.

[0083] The spectral data is often affected by environmental factors, sensor noise and other factors during the acquisition process, resulting in fluctuations in the reflectance values. By setting a window to smooth the reflectance values of each waveband, the random noise can be effectively reduced, thereby improving the signal-to-noise ratio of the data; using the smoothing output value to replace the original reflectance value can help eliminate the inconsistency caused by fluctuations in a small range at different wavelengths, making the spectral curve smoother and more coherent; through the average value in the window, important features or trends in the spectral curve can be better highlighted, such as vegetation index or soil characteristics. This smoothing process can help analysts more easily identify and extract features related to important information such as crop health, soil characteristics, etc.; in subsequent classification and analysis, the smoothed spectral data can provide more accurate information, which helps to improve the recognition accuracy of different categories such as vegetation coverage and soil exposure.

[0084] S2: screening the reflectance wavebands of the preprocessed spectral image, for each grid cell, obtaining the reflectance mean values of all pixels at different wavebands, obtaining the average reflectance data of the grid cell at different wavebands, classifying all grid cells with a set waveband threshold, and marking the grid cells as soil exposure or vegetation coverage;

[0085] The screened reflectance wavebands are , , and four wavebands, for each preprocessed spectral image, for the screened reflectance wavebands, traversing all pixels in the spectral image, collecting the reflectance values of all pixels at each screened waveband, and averaging all collected pixel reflectance values to obtain the average reflectance of the spectral image at the waveband.

[0086] The reason for screening the reflectance wavebands , , and is that these wavebands can effectively reflect the spectral characteristics of vegetation and soil, and have strong distinguishing ability. The waveband is in the visible light range, mainly used to obtain the green reflectance characteristics of vegetation, which helps to evaluate the health status of vegetation; The wave band is in the near-infrared region, which can effectively distinguish the growth of vegetation, and the reflectivity of vegetation shows obvious changes in this wave band; The wave band is used to identify the water content and soil characteristics, and can provide information about soil humidity and vegetation water stress. The wave band is used to obtain the blue light reflection characteristics, and can analyze the photosynthetic activity of plants; the reflectivity data of the above wave bands can help to accurately classify the grid unit as a soil bare area or a vegetation covered area, thereby supporting subsequent agricultural monitoring and management decisions.

[0087] For each spectral image corresponding to each grid unit, the average reflectivity of four target wave bands is calculated in turn, and the reflectivity mean of each grid unit in , , and four wave bands is obtained;

[0088] The reflectivity mean of each grid unit in four wave bands is converted into absolute radiance, and the formula is:

[0089]

[0090] wherein, represents the reflectivity mean of the th grid unit in the th wave band, and represent the gain coefficient and the bias term of the th wave band reflectivity, represents the absolute radiance of the th grid unit in the th wave band, represents the wavelength value of the selected wave band;

[0091] The purpose of converting the reflectivity mean of each grid unit in four wave bands into absolute radiance is to realize the consistency and comparability of data under different conditions, and the absolute radiance can more accurately represent the real radiation characteristics of the object, which is convenient for subsequent analysis and comparison; in the formula , represents the reflectivity mean of the th grid unit in the th wave band; represents the gain coefficient of the th wave band reflectivity, which is a linear proportional coefficient for converting the reflectivity value into radiance brightness, represents the ​The bias term for band reflectance corrects for background noise and other ineffective signals in the system. Using the above formula, reflectance under the same band can be consistently converted to absolute radiance, better supporting subsequent remote sensing analysis and applications.

[0092] The average reflectance data of each grid cell in different bands is obtained by combining the absolute radiance of the reference plate with the average reflectance of each grid cell across four bands, according to the formula:

[0093] ;

[0094] in, No. Each grid cell in Average reflectance data in the band, and They represent The radiance and calibrated reflectance of the reference plate in the specified band, and the average reflectance data for each grid cell are included in... , , and Average reflectance data for four bands.

[0095] The purpose of the above formula is to perform radiometric calibration using the absolute radiance of the reference plate, thereby improving the accuracy and consistency of reflectance data for each grid cell across different spectral bands. By ratioing the radiance of the grid cell to the reference value, measurement errors caused by environmental changes, sensor characteristics, and other factors can be corrected, thus standardizing the reflectance data of each grid cell into a relatively consistent form. This ensures comparability between different spectral bands and different geographical regions, thereby enhancing the reliability of subsequent analysis and classification.

[0096] Near-infrared settings for vegetation The lower limit threshold of spectral reflectance and red light The upper limit threshold of spectral reflectance is used to classify the entire planting area. Images with reflectance within the threshold range are identified as bare soil areas, while images with reflectance outside the threshold range are identified as vegetation-covered areas.

[0097] For each grid cell, obtain its position in... bands and Average reflectance data under each band, respectively set Lower limit threshold of reflectivity for the band and The upper limit threshold for reflectivity in a band is determined according to the following classification rules:

[0098] When the grid cell The average reflectivity of the band is higher than or equal to the set lower limit threshold for reflectivity, and When the average reflectivity of the wave band is lower than or equal to the set upper threshold of reflectivity, the grid cell is marked as a vegetation cover area; otherwise, the grid cell is marked as a soil bare area;

[0099] Through the above determination on all grid cells in turn, the classification of the soil bare area and the vegetation cover area is realized.

[0100] In the above process, the vegetation cover area has a higher reflectivity in the near-infrared wave band due to the influence of leaf structure and biochemical composition, and a lower reflectivity in the red light wave band. The soil bare area has a lower reflectivity in the near-infrared wave band and a relatively higher reflectivity in the red light wave band.

[0101] Therefore, by setting the lower threshold of reflectivity in the near-infrared wave band and the upper threshold of reflectivity in the red light wave band, the vegetation cover area and the soil bare area can be effectively distinguished: when the near-infrared reflectivity of the grid cell is higher than the threshold and the red light reflectivity is lower than the threshold, it indicates that the area is mainly covered by vegetation; otherwise, it indicates that the area is a soil bare area.

[0102] S3: According to the spectral images of all grid cells marked as soil bare areas, the adaptive parameters of the soil background are dynamically calculated, and the spectral index of vegetation and the water stress index are used as indicators for monitoring the growth of drought-resistant oats by coupling multiple spectra, and the spectral index of vegetation and the water stress index corresponding to the grid of the vegetation cover area are corrected by the adaptive parameters of the soil background;

[0103] According to the spectral images of all grid cells marked as soil bare areas, the adaptive parameters of the soil background are dynamically calculated, and the spectral index of vegetation and the water stress index are used as indicators for monitoring the growth of drought-resistant oats by coupling multiple spectra, and the spectral index of vegetation and the water stress index corresponding to the grid of the vegetation cover area are corrected by the adaptive parameters of the soil background;

[0104] For all grid cells marked as soil bare areas, the spectral images corresponding to each grid cell are collected, including the average reflectivity data in the four wave bands of , , and ;

[0105] For all grid cells of the soil bare area, the average reflectivity values in each wave band are counted respectively to form a spectral feature set of the soil bare area;

[0106] On the basis of the spectral feature set of the soil bare area, the adaptive parameters of the soil background are calculated by statistical analysis method, and the adaptive parameters include the mean and standard deviation of the average reflectivity of the soil in each wave band, and the specific steps are as follows:

[0107] ​For each waveband, the mean value of the average reflectance of the grid cells of all soil bare areas is calculated as the soil background adaptive mean parameter under the waveband;

[0108] For each target waveband, the standard deviation of the average reflectance of the grid cells of all soil bare areas is calculated as the soil background adaptive dispersion parameter under the waveband.

[0109] Based on the average reflectance of the grid cells, the multispectral coupling is adopted for the cell grids marked as vegetation coverage areas to construct vegetation spectral index and water stress index as the indicators for monitoring the growth of dry oat, specifically:

[0110] ;

[0111] ;

[0112] wherein, represents the vegetation spectral index of the i-th grid cell; represents the water stress index of the i-th grid cell; represents the grid index number of the whole planting area; represents the average reflectance of the i-th grid cell under the waveband j; represents the average reflectance of the i-th grid cell under the waveband j; represents the average reflectance of the i-th grid cell under the waveband j. The vegetation spectral index and the water stress index of the grid corresponding to the vegetation coverage area are corrected through the adaptive parameters of the soil background, and the specific steps are as follows: For the grid cell of the vegetation coverage area, , the corrected value of the reflectance under the waveband j is:

[0113] wherein, represents the corrected average reflectance under the waveband j;

[0114] represents the mean value of the soil reflectance under the waveband j; represents the standard deviation of the soil reflectance under the waveband j;

[0115] ;

[0116]

[0117] ​​​​​​​​​​​​Based on the corrected average reflectance of each band, adaptive parameter-corrected vegetation spectral index and water stress index for soil background are generated. The specific steps are as follows:

[0118] ;

[0119] ;

[0120] in, Indicates the first Corrected vegetation spectral index for each grid cell; Indicates band Average reflectance after downcorrection; Indicates band Average reflectance after downcorrection; Indicates the first Corrected water stress index for each grid cell;

[0121] In the above formula, since The band falls within the near-infrared spectral range, where healthy vegetation tissue exhibits high reflectivity. The band corresponds to the red light spectrum, which is strongly absorbed by vegetation chlorophyll. Among them, high near-infrared reflectivity reflects the integrity of vegetation cell structure and biomass, while strong infrared absorption can characterize chlorophyll content and photosynthetic efficiency. By subtracting the mean soil reflectivity and standardizing, reflection interference from bare soil or sparse vegetation areas is eliminated, enhancing the purity of vegetation signals.

[0122] The band is located in the shortwave infrared range and is highly sensitive to vegetation moisture content, while The near-infrared band is less affected by water and reflects the stability of vegetation structure; the ratio of the two can quantify the degree of water stress. When water is deficient, the cellular structure of vegetation is damaged, and the reflectivity of the short-wave infrared spectrum increases significantly. The near-infrared band serves as a stable near-infrared reflectance reference, eliminating interference from changes in vegetation cover. Standardization eliminates the background influence of soil moisture differences on the reflectance of the two bands, making the index more accurately reflect the internal moisture status of vegetation.

[0123] S4: Based on the vegetation spectral index and water stress index corrected by the grid unit of each vegetation cover area, a growth score index is constructed by linear product, and an adaptive parameter-corrected growth score index for soil background is generated.

[0124] For the For each grid cell, a growth score index is constructed based on the corrected vegetation spectral index and water stress index:

[0125] ;

[0126] represents the longness score index of the th grid unit; represents the inhibition intensity of water stress on the longness score, determined based on expert scoring.

[0127] Dependent variable represents the longness score index of the th grid unit, reflecting the comprehensive health degree of vegetation under the growth state and water stress conditions, obtained by ratio normalization of the corrected vegetation spectral index water stress index ; the inhibition weight of water stress on the longness is adjusted by to adapt to the drought resistance characteristics of different regions or crops; characterizes the vegetation coverage density and photosynthetic activity, and positively correlated; the higher the vegetation coverage, i.e. , the closer the longness score index to 1, indicating that the improvement of vegetation coverage contributes positively to the longness score; is located in the denominator and multiplied by , and the increase of its value will make the denominator increase, i.e. the more serious the water stress, the stronger the inhibition of the denominator term on ; the greater the negative impact of water stress on the longness score.

[0128] In the above embodiments, 10 groups of longness score indexes are respectively selected to change the data of the corrected vegetation spectral index and the water stress index, as shown in Tables 1 and 2:

[0129] Table 1: Change relationship table of longness score index and corrected vegetation spectral index

[0130]

[0131] From Table 1, it can be seen that under the condition that the corrected water stress index is unchanged and , with the increase of the corrected vegetation spectral index, the longness score index increases accordingly.

[0132] Table 2: Change relationship table of longness score index and corrected water stress index

[0133]

[0134] From Table 2, it can be seen that under the condition that the corrected vegetation spectral index is unchanged and In the case of the corrected moisture stress index, it can be seen that the growth score index decreases as the corrected moisture stress index increases.

[0135] S5: The K-means clustering method is used to cluster the growth score index of the grid cells of each vegetation coverage area, and the clustering of the growth of the dry oat in the vegetation coverage area is output. According to the clustering of the growth of the dry oat, a judgment threshold is set to realize growth classification.

[0136] The K-means clustering method is used to cluster the growth score index of each grid point, and the growth classification of the dry oat in the entire wheat field is output. Specifically,

[0137] Randomly select three initial cluster center values as the starting centers of each category. For the growth score index of each grid cell in the vegetation coverage area, calculate the distance between the growth score index and each cluster center, and assign it to the category to which the nearest cluster center belongs.

[0138] For the growth score index of all grid cells assigned to the category in each category, calculate the mean value as the new cluster center.

[0139] Based on the updated cluster center, repeat the calculation of the distance between the growth score index of each grid cell in the vegetation coverage area and the updated cluster center, and assign it to the category to which the nearest cluster center belongs until the cluster center no longer changes, and complete the clustering.

[0140] According to the clustering of the growth of the dry oat, a judgment threshold is set to realize growth classification. Specifically,

[0141] Set the final all growth score indexes to be divided into clusters, and the cluster center corresponding to each cluster is , and arranged in ascending order:

[0142] ;

[0143] Among them, , respectively represent the minimum, medium and maximum center values of the growth score index clustering;

[0144] The growth score index is calculated respectively:

[0145] ;

[0146] ;

[0147] Among them, represents the weak growth and normal growth demarcation value; A boundary value between normal growth vigor and strong growth vigor is represented;

[0148] When is less than or equal to , the dry oat is determined as weak growth vigor; when is greater than and less than or equal to , the dry oat is determined as normal growth vigor; when is greater than , the dry oat is determined as strong growth vigor.

[0149] Referring to Figure 4 , the application further provides a dry oat growth vigor monitoring system based on unmanned aerial vehicle hyperspectral remote sensing, which is used for executing the monitoring method and comprises:

[0150] A data acquisition module is configured to demarcate the boundary of a target monitoring dry oat planting area, divide the planting area into a plurality of same rectangular grid units according to the demarcated boundary, and acquire spectral images of each grid unit by using an unmanned aerial vehicle to pre-process the spectral images.

[0151] A grid processing module is configured to filter the reflectivity bands of the pre-processed spectral images, acquire the reflectivity mean value of all pixels under different bands for each grid unit, obtain the average reflectivity data of the grid unit under different bands, classify all grid units by using a set band threshold, and mark the grid unit as a soil bare area or a vegetation coverage area.

[0152] An index construction module is configured to dynamically calculate adaptive parameters of a soil background according to the spectral images of all grid units marked as the soil bare area, construct a vegetation spectral index and a water stress index by using multi-spectral coupling for the grid units marked as the vegetation coverage area as indexes for monitoring the growth vigor of the dry oat, and correct the vegetation spectral index and the water stress index of the grid corresponding to the vegetation coverage area by using the adaptive parameters of the soil background.

[0153] A growth vigor scoring module is configured to construct a growth vigor scoring index by using linear product based on the corrected vegetation spectral index and the water stress index of each grid unit of the vegetation coverage area, and generate the growth vigor scoring index corrected by the adaptive parameters of the soil background.

[0154] A growth vigor classification module is configured to cluster the growth vigor scoring index of each grid unit of the vegetation coverage area by using a K-means clustering method, output the clustering condition of the growth vigor of the dry oat of the grid unit of the vegetation coverage area, set a judgment threshold according to the clustering condition of the growth vigor of the dry oat, and realize growth vigor classification.

[0155] The above formulas are all dimensionless values calculated, the formula is obtained by collecting a large amount of data to simulate the most recent real situation, and the preset parameters in the formula are set by a person skilled in the art according to the actual situation.

[0156] The above embodiments can be implemented wholly or partially by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented wholly or partially in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solutions.

[0157] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, which can be located in one place or distributed on multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiments according to actual needs.

[0158] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A method for monitoring the growth of dryland oats based on UAV hyperspectral remote sensing, characterized by the following steps: include: S1: The boundary of the target monitoring dryland oat planting area is marked. The planting area is divided into several identical rectangular grid units according to the marked boundary. The UAV is used to acquire the spectral image of each grid unit and preprocess the spectral image. S2: Filter the reflectance bands of the preprocessed spectral image. For each grid cell, obtain the average reflectance of all pixels in different bands to obtain the average reflectance data of the grid cell in different bands. Classify all grid cells according to the set band threshold and mark the grid cells as bare soil areas or vegetation-covered areas. S3: Based on the spectral images of all grid cells marked as bare soil areas, dynamically calculate the adaptive parameters of the soil background. For grid cells marked as vegetated areas, construct vegetation spectral indices and water stress indices using multispectral coupling as indicators for monitoring the growth of dryland oats. Correct the vegetation spectral indices and water stress indices corresponding to the grid cells in the vegetated areas using the adaptive parameters of the soil background. S4: Based on the vegetation spectral index and water stress index corrected by the grid cells of each vegetation cover area, a growth score index is constructed by linear multiplication, and an adaptive parameter-corrected growth score index for soil background is generated. S5: K-means clustering is used to cluster the growth score index of each grid unit in the vegetation coverage area, and the clustering of the growth of dryland oats in the grid units of the vegetation coverage area is output. Based on the clustering of the growth of dryland oats, a judgment threshold is set to achieve growth classification. Based on the spectral images of all grid cells marked as bare soil areas, adaptive parameters of the soil background are dynamically calculated. The specific steps are as follows: For all grid cells marked as bare soil areas, collect the spectral image corresponding to each grid cell, including... , , and Average reflectance data for four spectral bands; For all grid cells in the exposed soil area, the average reflectance values ​​under each band are statistically analyzed to form a set of spectral characteristics of the exposed soil area; Based on the spectral feature set of exposed soil areas, adaptive parameters of the soil background are calculated using statistical analysis methods. These adaptive parameters include the mean and standard deviation of the average soil reflectance in each band. The specific steps are as follows: For each band, the mean of the average reflectance of all grid cells in the exposed soil area is calculated and used as the adaptive mean parameter of the soil background in that band. For each target band, the standard deviation of the average reflectance of the grid cells in all exposed soil areas is calculated and used as the adaptive dispersion parameter of the soil background in that band. The vegetation spectral index and water stress index corresponding to the grid of the vegetation cover area are corrected by adaptive parameters of soil background. The specific steps are as follows: For grid units in vegetated areas For bands reflectivity The corrected value is: in, Indicates band The corrected average reflectance; Indicates band The mean soil reflectance; Indicates band The standard deviation of soil reflectance; Based on the corrected average reflectance of each band, adaptive parameter-corrected vegetation spectral index and water stress index for soil background are generated. The specific steps are as follows: in, Indicates the first Corrected vegetation spectral index for each grid cell; Indicates band Average reflectance after downcorrection; Indicates band Average reflectance after downcorrection; Indicates the first The corrected water stress index for each grid cell; For the For each grid cell, a growth score index is constructed based on the corrected vegetation spectral index and water stress index: Indicates the first Growth score index of each grid cell; The score indicates the inhibitory effect of water stress on growth, determined based on expert scoring.

2. The method for monitoring the growth of dryland oats based on UAV hyperspectral remote sensing according to claim 1, characterized in that, The spectral image includes reflectance spectral information of multiple pixels. The spectral information includes the correspondence between wavelength and reflectance values. The method for preprocessing the spectral image is as follows: For each pixel in the spectral image of each grid cell, the reflectance spectral curve of that pixel is extracted. Based on the set window length, for each band in the spectral curve of that pixel, the reflectance values ​​of several bands before and after it are taken. The average reflectance within the window is used as the smoothed output value of the current band. The original reflectance value is replaced with the smoothed output value to complete the preprocessing of the reflectance spectral curve of each pixel.

3. The method for monitoring the growth of dryland oats based on UAV hyperspectral remote sensing according to claim 1, characterized in that, The selected reflectance bands are respectively , , and For each preprocessed spectral image, for the reflectance band of the selected wave, all pixels in the spectral image are traversed, the reflectance values ​​of all pixels in each selected wave are collected, and the average of all collected pixel reflectance values ​​is calculated to obtain the average reflectance of the spectral image in that wave band. For the spectral image corresponding to each grid cell, the average reflectance of the four target bands is calculated sequentially to obtain the average reflectance of each grid cell in the four target bands. , , and Average reflectance across four bands; The average reflectance of each grid cell across the four bands is converted to absolute radiance using the following formula: in, Indicates the first Each grid cell in Mean reflectance in the band, and They represent Gain coefficient and bias term for band reflectivity, Indicates the first Each grid cell in Absolute radiance in the band, This indicates the wavelength value of the selected band; The average reflectance data of each grid cell in different bands is obtained by combining the absolute radiance of the reference plate with the average reflectance of each grid cell across four bands, according to the formula: in, No. Each grid cell in Average reflectance data in the band, and They represent The radiance and calibrated reflectance of the reference plate in the specified band, and the average reflectance data for each grid cell are included in... , , and Average reflectance data for four bands.

4. The method for monitoring the growth of dryland oats based on UAV hyperspectral remote sensing according to claim 1, characterized in that, Near-infrared settings for vegetation The lower limit threshold of spectral reflectance and red light The upper limit threshold of spectral reflectance is used to classify the entire planting area based on the set threshold. Images with reflectance within the threshold range are identified as bare soil areas, while images with reflectance outside the threshold range are identified as vegetation-covered areas. For each grid cell, obtain its position in... bands and Average reflectance data under each band, respectively set Lower limit threshold of reflectivity for the band and The upper limit threshold for reflectivity in a band is determined according to the following classification rules: When the grid cell The average reflectivity of the band is higher than or equal to the set lower limit threshold for reflectivity, and When the average reflectance of a band is lower than or equal to the set upper limit threshold for reflectance, the grid cell is marked as a vegetation-covered area; otherwise, the grid cell is marked as a bare soil area. By performing the above-mentioned judgment on all grid cells in sequence, the classification of bare soil areas and vegetation-covered areas can be achieved.

5. The method for monitoring the growth of dryland oats based on UAV hyperspectral remote sensing according to claim 3, characterized in that, Based on the average reflectance of grid cells, multispectral coupling was used to construct vegetation spectral indices and water stress indices for grid cells marked as vegetation-covered areas, serving as indicators for monitoring the growth of dryland oats. Specifically: in, Indicates the first Vegetation spectral index of each grid cell; Indicates the first Moisture stress index of each grid cell; This represents the number of grid indices for the entire planting area; Indicates band The next Average reflectance of each grid cell; Indicates band The next Average reflectance of each grid cell; Indicates band The next Average reflectance of each grid cell.

6. The method for monitoring the growth of dryland oats based on UAV hyperspectral remote sensing according to claim 1, characterized in that, The K-means clustering method is used to cluster the growth score index of each grid point, and the growth classification of dryland oats in the entire wheat field is output. Specifically: Three initial cluster center values ​​are randomly selected as the starting centers for each category. For the growth score index of each grid cell in the vegetation cover area, the distance between it and each cluster center is calculated, and it is assigned to the category of the nearest cluster center. For each category, calculate the mean of the growth score index of all grid cells assigned to that category, and use it as the new cluster center; Based on the updated cluster centers, the distance between each grid cell in the vegetation cover area and the updated cluster centers is calculated repeatedly according to the growth score index of each grid cell. The cells are then assigned to the category of the nearest cluster center until the cluster centers no longer change, thus completing the clustering process.

7. The method for monitoring the growth of dryland oats based on UAV hyperspectral remote sensing according to claim 1, characterized in that, The method of setting a judgment threshold based on the clustering of dryland oat growth to achieve growth classification is as follows: Ultimately, all growth score indices were divided into: The clusters are obtained by sorting them in ascending order based on their cluster centers: in, , These represent the smallest, medium, and largest cluster centers of the growth score index, respectively. Calculate the dividing point of growth separately: in, This indicates the dividing line between weak and normal growth. This indicates the dividing line between normal and vigorous growth. when Less than or equal to At that time, it was determined that the dryland oats were in a weak growth condition; when Greater than and less than or equal to At that time, it was determined that the dryland oats were growing normally; when Greater than At that time, it was determined that the dryland oats were growing vigorously.

8. A system for monitoring the growth of dryland oats based on UAV hyperspectral remote sensing, characterized in that: The monitoring system is used to perform the monitoring method according to any one of claims 1-7, including: The data acquisition module is used to mark the boundaries of the target monitoring dryland oat planting area. Based on the marked boundaries, the planting area is divided into several identical rectangular grid units. The UAV is used to acquire the spectral images of each grid unit and preprocess the spectral images. The grid processing module is used to filter the reflectance bands of the preprocessed spectral image. For each grid cell, the average reflectance of all pixels in different bands is obtained to obtain the average reflectance data of the grid cell in different bands. All grid cells are classified according to the set band threshold and marked as bare soil area or vegetation cover area. The index construction module is used to dynamically calculate the adaptive parameters of the soil background based on the spectral images of all grid cells marked as bare soil areas. For grid cells marked as vegetated areas, multispectral coupling is used to construct vegetation spectral indices and water stress indices as indicators for monitoring the growth of dryland oats. The adaptive parameters of the soil background are used to correct the vegetation spectral indices and water stress indices corresponding to the grid cells in the vegetated areas. The growth scoring module is used to construct a growth scoring index based on the vegetation spectral index and water stress index corrected by the grid cells of each vegetation cover area, and to generate a growth scoring index after adaptive parameter correction of the soil background. The growth classification module is used to cluster the growth score index of each grid unit in the vegetation coverage area using the K-means clustering method, outputting the clustering status of dryland oats in the grid units of the vegetation coverage area, and setting a judgment threshold based on the clustering status of dryland oats to achieve growth classification.

Images