Method and system for monitoring growth vigor of crops through images

Abstract

The invention relates to the technical field of crop growth monitoring, in particular to a method and system for monitoring crop growth through images, and the method comprises the following steps: deploying an unmanned aerial vehicle, flying over a target paddy field, collecting image data, transmitting the image data to a ground station in real time through data transmission, and generating a preliminary image data set; and cutting and correcting the initial image data set. According to the invention, the unmanned aerial vehicle is used for image acquisition, the problem that the visual angle of a fixed ground camera is limited is avoided, and the data hysteresis is reduced through real-time data transmission, so that the monitoring is more timely. In the image data cutting and correcting process, angle deviation and background noise are eliminated, and the leaf area index calculation accuracy is improved. Through introduction of time sequence analysis, dynamic monitoring of crop growth trend is realized, growth evaluation is no longer limited to a single time point, historical data comparison is formed, and the prediction capability of the growth state is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of crop growth monitoring, and in particular to a method and system for monitoring crop growth through images. Background Art

[0002] The field of crop growth monitoring technology involves the use of a variety of sensing and data analysis methods to conduct real-time or periodic assessments of crop growth status, health status, and growth trends. The method of monitoring crop growth through images belongs to the field of crop growth monitoring technology, which mainly uses image data to analyze and evaluate crop growth status.

[0003] However, in the existing technology, the image data is not cropped and geometrically corrected, and the background information is complex, which can easily interfere with the calculation of the leaf area index and affect the accuracy of monitoring. Crop growth assessment usually relies on single-point image data without data comparison, which makes it difficult to accurately judge the growth trend and affects the reliability of agricultural management decisions. Therefore, improvements are needed. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a method and system for monitoring crop growth through images.

[0005] In order to achieve the above object, the present invention adopts the following technical solution, a method for monitoring crop growth through images, comprising the following steps: Deploy a drone to fly over a target rice field to collect image data, and send the image data to a ground station in real time through data transmission to generate a preliminary image data set; crop and correct the preliminary image data set to generate a processed image data set; Based on the processed image data set, the rice leaf area index in the image is identified and measured, the health status and growth stage of the crop are identified, and the original LAI data is generated; the original LAI data is analyzed in time series, the crop growth trend is determined by comparative analysis, and the time series analysis results are generated; Based on the time series analysis results, soil moisture and meteorological data are combined, and the soil moisture and meteorological data are combined with the time series analysis results to generate comprehensive monitoring data; the growth status of rice is evaluated using the comprehensive monitoring data, environmental factors affecting crop growth are analyzed, and crop growth evaluation results are generated; Based on the crop growth assessment results, the effectiveness of the current irrigation and fertilization plans is evaluated, whether agricultural management measures need to be adjusted is determined, and management adjustment recommendations are generated.

[0006] Preferably, the steps of acquiring the preliminary image data set are: Deploy a drone to fly over the target rice field, collect image data of the rice field through the camera, adjust the camera angle and focal length to cover the entire field surface, and obtain real-time collected rice field images; Based on the rice field images collected in real time, the data are sent to a ground station in real time via wireless transmission to obtain a preliminary image data set.

[0007] Preferably, the steps of acquiring the processed image data set are: Based on the preliminary image data set, edge transition areas are determined by pixel gradients, isolated noise points are eliminated, boundary ranges are adjusted according to shape features of the target crop area, redundant background areas are removed, and image data after boundary adjustment is obtained; Based on the image data after the boundary adjustment, lens distortion parameters including radial distortion and tangential distortion are calculated, and pixel offset caused by the correction is restored by image interpolation to generate distortion-corrected image data; Based on the distortion-corrected image data, color channel normalization processing is performed, and at the same time, histogram equalization is performed to adjust the brightness distribution to obtain a processed image data set.

[0008] Preferably, the steps of obtaining the original LAI data are: Based on the processed image data set, RGB channel separation is performed, pixel values ​​of the red channel, the green channel and the blue channel are extracted, and the channel data of the rice leaf region is obtained; Based on the rice leaf area channel data, the rice leaf area index is calculated using the following formula: and ; in, is the rice leaf area index, is a variable ratio vegetation index based on drone images. is the green channel digital value, is the digital value of the red channel, is the digital value of the blue channel; Based on the rice leaf area index, leaf color and texture features are extracted, spectral variation trends during the growth cycle are compared, crop health status and growth stage are identified, and original LAI data are obtained.

[0009] Preferably, the steps of obtaining the time series analysis results are: Based on the original LAI data, a time series matrix is ​​constructed, the rice leaf area index at each observation time point is extracted, the rice leaf area index change range between adjacent time points is calculated, the data missing area is filled by interpolation, and the time series smoothing process is performed to obtain the time series LAI data; Based on the time series LAI data, the crop growth trend index is calculated using the following formula: ; in, is the crop growth trend index, For the Rice leaf area index at each time point, is the rice leaf area index at the previous time point, For the The leaf density corresponding to each time point is is the rice canopy height, is the color change rate of rice leaves, is the influence factor of color change on trend index, is the number of data points in the time series; Based on the crop growth trend index, the change pattern of the crop growth trend index in the time dimension is analyzed, the trend characteristics of growth, stability or decline are extracted, and the time series analysis result is obtained.

[0010] Preferably, the steps of acquiring the comprehensive monitoring data are: Based on the time series analysis results, crop growth trend data is extracted, soil moisture measurement data and meteorological observation data are called, soil moisture change rate, air humidity change amplitude, temperature gradient and precipitation accumulation are calculated, and an environmental parameter set is obtained; Based on the environmental parameter set, the comprehensive monitoring index is calculated using the following formula: ; in, is a comprehensive monitoring index. Represent the real-time measurement values ​​of soil moisture content, air humidity and temperature respectively. are the time series smoothing values ​​of the corresponding parameters, Represent the fluctuation range of each environmental factor, represent the changing rates of soil moisture, air humidity and temperature respectively. Factors affecting environmental change; Based on the comprehensive monitoring index, the impact of environmental factors on crop growth trends is analyzed, the correlation between environmental variables and crop growth status is extracted, and comprehensive monitoring data is obtained.

[0011] Preferably, the steps for obtaining the crop growth assessment results are: Based on the comprehensive monitoring data, the growth adaptability score is calculated using the following formula: ; in, is the growth adaptability score, is the rice leaf area index, is the photosynthetic capacity index of crops, is the soil temperature, is the air humidity, is the cumulative impact value of meteorological factors, is the soil moisture change rate; Based on the growth adaptability score, the growth status of rice in the current environment is analyzed to obtain a crop growth assessment result.

[0012] Preferably, the steps of obtaining the management adjustment suggestion are: Based on the crop growth assessment results, soil moisture content, soil nitrogen, phosphorus and potassium content, chlorophyll index, precipitation and temperature are extracted to obtain basic agricultural management data; Based on the basic agricultural management data, the management adjustment index is calculated using the following formula: ; in, To manage the adjustment index, Respectively represent the current nitrogen, phosphorus and potassium concentrations in the soil. The amount of irrigation water supplied, is the total precipitation, is the chlorophyll index, is the crop leaf temperature; Based on the management adjustment index, the adaptability of rice to current irrigation and fertilization is analyzed, and whether agricultural management measures need to be adjusted is evaluated to obtain management adjustment recommendations.

[0013] The present invention provides a system, comprising: The data acquisition module deploys drones to fly over the target rice fields, collects image data, and sends them to the ground station in real time to generate a preliminary image data set; The image processing module crops and corrects the preliminary image data set to generate a processed image data set; The LAI calculation module, based on the processed image dataset, identifies and measures the rice leaf area index in the image, identifies the health status and growth stage of the crop, and generates raw LAI data; The data analysis module performs time series analysis on the original LAI data, determines the crop growth trend through comparative analysis, and generates time series analysis results; The agricultural management recommendation module is based on the results of time series analysis, combined with soil moisture and meteorological data. It combines soil moisture and meteorological data with the results of time series analysis to generate comprehensive monitoring data, uses the comprehensive monitoring data to evaluate the growth status of rice, analyzes the environmental factors affecting crop growth, and generates crop growth assessment results. Based on the crop growth assessment results, it evaluates the effectiveness of the current irrigation and fertilization plans, determines whether agricultural management measures need to be adjusted, and generates management adjustment recommendations.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, the use of unmanned aerial vehicles for image acquisition avoids the problem of limited viewing angle of fixed ground cameras, and reduces data lag through real-time data transmission, making monitoring more timely. In the process of image data clipping and correction, angle deviation and background noise are eliminated, and the accuracy of leaf area index calculation is improved. The introduction of time series analysis realizes the dynamic monitoring of crop growth trends, so that growth assessment is no longer limited to a single time point, but forms historical data comparison, which improves the prediction ability of growth status. The integration of environmental factors enhances the adaptability of the monitoring system to external influences, so that key factors such as meteorological changes and soil moisture dynamics can be quantified and directly act on crop growth assessment, avoiding the limitations of single crop appearance feature analysis. Based on comprehensive data analysis, the impact of current agricultural management measures on crop growth is evaluated, so that operations such as irrigation and fertilization can be dynamically adjusted according to the real-time needs of crops, optimize resource allocation, and improve the scientificity and execution efficiency of agricultural management. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the steps of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] See also Figure 1 The present invention provides a technical solution, a method for monitoring crop growth through images, comprising the following steps: Deploy UAVs to fly over the target rice fields to collect image data, and send the image data to the ground station in real time through data transmission to generate a preliminary image data set; crop and correct the preliminary image data set to generate a processed image data set; Based on the processed image dataset, the rice leaf area index in the image is identified and measured to identify the health status and growth stage of the crop and generate the original LAI data. The original LAI data is analyzed in time series to determine the crop growth trend through comparative analysis and generate the time series analysis results. Based on the results of time series analysis, soil moisture and meteorological data are combined with the results of time series analysis to generate comprehensive monitoring data; the comprehensive monitoring data are used to evaluate the growth status of rice, analyze the environmental factors that affect crop growth, and generate crop growth assessment results; Based on the crop growth assessment results, evaluate the effectiveness of the current irrigation and fertilization plans, determine whether agricultural management measures need to be adjusted, and generate management adjustment recommendations.

[0018] The steps to obtain the preliminary image dataset are: Deploy a drone to fly over the target rice field, collect image data of the rice field through the camera, adjust the camera angle and focal length to cover the entire field surface, and obtain real-time collected rice field images; Based on the real-time collected rice field images, the data are sent to the ground station in real time via wireless transmission to obtain a preliminary image data set.

[0019] Specifically, based on the target rice field area distribution data and geographic coordinate information collected in the early stage, the initial flight altitude range of the UAV is first set between 20 meters and 50 meters. This range is determined based on the statistical results of early surveying and mapping combined with experience. For example, when the area of ​​a single rice field exceeds 1 hectare, a flight altitude of more than 35 meters is used, and a calculation example is used to set the threshold H. If the collected farmland area S is 1.2 hectares, H can be set to 20 + (S-1.0) × 15, where S is measured in hectares and H is measured in meters. When H exceeds 50 meters or is less than 20 meters, it is judged as over-limit and triggers an alert. Then, the flight corridor is planned according to the established route and the horizontal spacing is guaranteed to be between 15 meters and 25 meters. The threshold is set based on experience. The camera pitch angle is adjusted between 45 and 75 degrees. If the speed of the drone exceeds the pre-defined upper limit of 5 meters per second during flight, the speed is adjusted. The speed upper limit is set by the statistical data of the field size. For example, a low-speed flight of 2 meters per second can be used in a field with an area of ​​less than 0.5 hectares. The positioning coordinates, flight altitude, camera focal length and inclination value during the flight are recorded and compared with the farmland coordinates. If it is detected that the flight range exceeds the geographic reference boundary, it is regarded as an invalid segment. All flight and camera adjustment operations are executed according to the pre-planned configuration strategy and registered after each change. Finally, the shooting results after all segments are covered are associated with the corresponding coordinate information to obtain real-time collected rice field images.

[0020] Based on the real-time collected rice field images, the image data of each captured frame is matched and recorded with the previously registered flight timestamp. For the wireless transmission part, a signal strength threshold is first set according to the signal coverage range of the ground station around the farmland. For example, when the received signal strength is lower than -75 dBm, it is judged as unstable transmission. It is necessary to rescan the surrounding available frequency bands or adjust the drone attitude to send the image again after the flight. If the signal strength is higher than -75 dBm and is always in the range of -60 dBm to -70 dBm, it is considered to be in the valid data range. All image data will be transmitted to the ground station after transmission. Time and location tags are attached, and the metadata of each frame of image is proofread to prevent duplication or omission. When image data loss within a certain period of time is detected, the flight altitude, camera angle and focal length of the lost period are marked together for manual comparison to see if there are any recording errors. All validly transmitted data are then numbered and sorted and checked with the corresponding geographic coordinate reference table. If the check result shows that the deviation exceeds the threshold of 0.5 degrees set based on previous testing experience, this part of the data is marked as suspicious and retained in the exception list. Finally, the confirmed valid image data is classified and sorted to obtain a preliminary image data set.

[0021] The steps to obtain the processed image dataset are: Based on the preliminary image data set, the edge transition area is determined by pixel gradient, and isolated noise points are eliminated. The boundary range is adjusted according to the shape characteristics of the target crop area, and the redundant background area is removed to obtain the image data after boundary adjustment. Based on the image data after boundary adjustment, the lens distortion parameters, including radial distortion and tangential distortion, are calculated, and the pixel offset caused by the correction is restored by image interpolation to generate the image data after distortion correction; Based on the distortion-corrected image data, color channel normalization is performed, and histogram equalization is performed to adjust the brightness distribution to obtain the processed image data set.

[0022] Specifically, based on the preliminary image data set obtained above, we first perform adjacent difference operations on the grayscale values ​​of each pixel and calculate the gradient size. For continuous pixel gradients greater than the threshold value calculated based on the statistical sample mean of previous years plus the correction coefficient k, When , it can be determined that there is a significant transition boundary in the region, where The setting method can be referred to , represents the average gradient value of the same type of images in previous years. k can be taken as 1.2 as an example. If the pixel gradient value in a certain area is generally less than Then it is classified as a non-transition area, and then the isolated noise points are cleaned up, for example, it is determined that the brightness fluctuation of the local pixel in the 3×3 neighborhood is less than the threshold determined empirically. If the noise point appears in all five frames of continuous images, it will be deleted after confirmation. Then, the detected edges will be fitted and compared according to the shape features of the target crop area recorded in advance, such as approximate rectangles or irregular multi-borders. If the fitting degree deviation exceeds a comparison coefficient obtained from the reference example, The gradient of the deviated part is recalculated and the ownership is confirmed again. Finally, the background partitions that do not conform to the shape of the target crop are listed as redundant areas and deleted. After checking each suspicious area one by one, the remaining areas that conform to the shape characteristics are retained and registered, and finally the image data with boundary adjustment is obtained.

[0023] Based on the image data after boundary adjustment obtained above, first read the known coordinate points and corresponding pixel positions in the reference calibration information, and convert the radial distortion coefficient and tangential distortion coefficient As the parameters to be estimated, the initial values ​​of these parameters can be obtained from the experimental data of the same type of lens in previous years and iteratively estimated by the least squares method. For each corresponding point, the coordinate difference before and after distortion is calculated and a residual vector is generated. When the residual is higher than the threshold given in an empirical way, When the fit is insufficient, it means that the coefficients need to be corrected again. It can be given by the average residual obtained from the calibration experiment in previous years plus a correction amount. For example, if the average residual in previous years is 0.2 pixels and the correction amount is 0.05, then In the iterative process, the coefficients are dynamically adjusted according to the changes in the residual distribution after each iteration. When the residual curve is lower than The pixel coordinates are then restored by interpolation, and the corrected coordinates are redistributed by bilinear or cubic interpolation to finally generate the distortion-corrected image data.

[0024] Based on the distortion-corrected image data obtained above, the red channel, green channel, and blue channel in the image are first extracted and the maximum and minimum pixel values ​​are calculated for each channel, which are then mapped to a range of 0 to 255 to unify the relative intensity of each channel. Then, a balanced threshold is given based on the distribution of brightness extremes recorded in the shooting environment in previous years. For example, the threshold is set to 128 to represent the median brightness, and the pixel histogram of each channel is normalized and compared with Compare, to less than The pixel segments are stretched to balance the brightness distribution. It is regarded as a segment with too high brightness and its pixel density is compressed accordingly. The value 30 is calculated from the statistical results of high-brightness areas in previous years. After the normalization of each channel and the brightness distribution adjustment are completed, the three-channel data are recombined to finally obtain the processed image data set.

[0025] The steps to obtain the original LAI data are: Based on the processed image data set, RGB channel separation is performed to extract the pixel values ​​of the red channel, green channel and blue channel to obtain the channel data of the rice leaf area; Based on the rice leaf area channel data, the rice leaf area index is calculated using the following formula: and ; in, is the rice leaf area index, is a variable ratio vegetation index based on drone images. is the green channel digital value, is the digital value of the red channel, is the digital value of the blue channel; Based on the rice leaf area index, the leaf color and texture characteristics are extracted, the spectral change trends during the growth cycle are compared, the crop health status and growth stage are identified, and the original LAI data is obtained.

[0026] Specifically, based on the processed image data set obtained above, the color component corresponding to each pixel is first read and numbered, and a one-to-one correspondence is established between the number and the pixel position information. The RGB value range is obtained by comparing the calibration data of the same model of shooting equipment in previous years, so as to identify the distribution of normal pixels in the range of 0 to 255. Then, according to the historical monitoring records of the illumination in the actual farmland shooting environment, a brightness threshold for distinguishing dark and bright areas is set. For example, we analyze the samples of all-weather images taken in previous years with sunshine duration of not less than 10 hours and find that the mean value of brightness distribution is about 130. Then we select As the adjustment interval, The range is 100 to 160. For pixel segments below this range, it is necessary to check whether the area is located in the shadow coverage position during extraction as the dark area. The shape contour can be used as a reference again and compared with the rice row spacing pattern recorded in the calibration information of previous years. If the row spacing characteristics do not match, it is regarded as an invalid pixel and cleaned up. Pixel segments above 160 are marked as bright areas and their corresponding red, green, and blue components are registered. The red component of each pixel is counted during the cleaning process. , Green component and blue component If it is found that the proportion of a certain component continues to deviate from the pre-set 15% and other components soar abnormally, it is listed as a suspicious noise point and its performance in adjacent frame images is checked again. If multiple frames are continuously abnormal, this pixel component is marked as abnormal. The normal pixel values ​​that have been identified by the brightness area are finally summarized and classified as rice leaf area channel data.

[0027] The benefit of the formula is that it combines the differences in the red channel, green channel, and blue channel to quantify the color characteristics of the leaves as a variable ratio vegetation index, and amplifies the sensitivity to small color differences in exponential form, thereby more accurately mapping the actual distribution of rice leaf area in subsequent analysis.

[0028] The steps to obtain the parameters are: The digital value of the green channel usually ranges from 0 to 255. It is extracted through the green component histogram of each pixel in the image taken by the drone. If the green value of some pixels deviates greatly from the usual statistical range, it is necessary to check whether there are strong reflective points or noise areas. Then, the correction coefficient is formed by comparing it with the actual measured color card to obtain the final For example, 10,000 green pixel values ​​are collected in the same plot and recorded as , compare the average of these pixel values ​​with the green channel average of the standard card. If the difference is 12, linearly correct the shooting result to align it with the standard reference, and use the corrected pixel green value as The official record of the results.

[0029] The steps to obtain the parameters are: Indicates the digital value of the red channel, ranging from 0 to 255. The acquisition method is the same as Similarly, we first read the red component pixel by pixel and filter out the high-brightness saturated area, and obtain the correction coefficient by comparing it with the calibration plate with known RGB values ​​in the field. Then, the uniformly corrected red channel value is recorded as For example, 200 frames are continuously shot in a farmland in Henan Province, and 5,000 valid red pixel values ​​are extracted from each frame, resulting in a total of 1 million records. The average value of these records is compared with the red average value of the standard calibration plate. If the difference is 8, the red component of each pixel is increased by the corresponding correction amount of 8 during correction, and the corrected value is finally obtained. .

[0030] The steps to obtain the parameters are: The digital value representing the blue channel is also in the range of 0 to 255. It is obtained by counting the blue component of the captured image pixel by pixel. For the phenomenon that the sky reflection is too strong and the local area is over-brightened, it is necessary to list those extremely high values ​​separately according to the actual situation and then calibrate them. Then, error correction is performed under the guidance of the visible light standard color card and finally recorded as For example, a sample area records about 800,000 blue pixel values ​​during the whole day of shooting, and compares its average with the reference card. If the average difference is 15, it is necessary to subtract 15 from the entire shooting data and update it as .

[0031] The steps for obtaining the 1.4527 coefficient are as follows: 1.4527 is a value obtained by fitting after large-scale field measurements. By measuring the leaf coverage of different plants in the same plot throughout the season and performing regression analysis with the calculated UAV-basedVARI_{RGB}, several sample points can be expanded on the coordinate axis and the least squares method can be used to fit an exponential curve. The intercept part fits a stable value of about 1.45. In order to obtain similar results in different regions, this 1.45 is environmentally corrected to obtain 1.4527. For example, in a concentrated experiment, 1000 groups of labeled leaf area indices and their corresponding UAV-basedVARI_{RGB} values ​​were counted, and they were segmented and fitted and averaged to obtain about 1.45. When compared with 50 other groups of data in the same region, a deviation of 0.0027 was generated, and the deviation was finally accumulated to determine 1.4527.

[0032] The steps to obtain the 7.8932 coefficient are as follows: 7.8932 is the amplification coefficient of the exponential part in the same regression process. Its acquisition method is similar to 1.4527. First, the leaf area index of all samples is segmented with UAV-basedVARI_{RGB}, and then the exponential form is selected. To fit, we get After fine analysis of the local area, a correction of 0.0032 is added to form a final value of 7.8932. For example, in the fitting results of the same plot, the distribution of most samples indicates It is between 7.8 and 8.0. After merging statistics and averaging, the value stabilizes at around 7.89. Combined with the lighting conditions during the actual shooting period, a second comparison is performed to obtain 7.8932.

[0033] Calculation process: First calculate , if a pixel is extracted ,but:

[0034] Substituting this result into the LAI formula:

[0035] The result shows that the leaf area index corresponding to this pixel area is about 2.2569. If the LAI values ​​of different pixels are counted as a whole, the average LAI value of a field can be obtained. When the average value is between 1 and 3, it can be regarded as a relatively stable interval for mid-term growth of rice. If it exceeds 5, it means that the leaf coverage is extremely high, and it is necessary to judge whether there is excessive canopy in combination with the actual planting density. If it is less than 0.5, it indicates that the leaf coverage is limited, and it should be checked whether it is in the early stage of rice or there are missing plants when shooting.

[0036] Based on the rice leaf area index obtained above, first read the LAI value recorded at each location and match it with the corresponding spectral information of samples at different growth stages. In order to identify the leaf color, it is necessary to extract the reflection curves of the three major categories of red, green and yellow in the visible light range. Compare with the spectral distribution patterns of the greening period, jointing period and heading period in the previous years' shooting library. If it is found that the color characteristics of a certain pixel between 600nm and 700nm account for a high proportion, it will be classified into the reddish to orange-red area, and combined with the texture direction to determine whether it has the characteristics of curling or complete flatness. When the texture direction is continuous and striped, it means that the leaf is in a normal growth mode, and when the texture direction is scattered and local broken lines appear, it is recorded as a possible damaged area. Then record these texture data for comparison with the spectral information. Compare with leaf samples with multiple growth stages and known health evaluation, the part with the largest difference in the current leaf texture distribution can be graded. For example, when setting a texture difference threshold When setting the texture difference threshold, we need to first calculate the average value of various texture features based on samples from previous years, and then weight it by a fluctuation coefficient. When the comparison result shows a deviation greater than 0.15, it is marked as abnormal. If the spectral color gradually shifts from green to yellow-brown and the texture difference increases significantly during multiple growth cycles, it can be inferred that it has entered the late maturity or pathological stage. The growth status of this period is divided into stages and the color spectrum is compared. Finally, after all leaf data are processed, an overall growth status identification conclusion can be formed to obtain the original LAI data.

[0037] The steps to obtain the time series analysis results are: Based on the original LAI data, a time series matrix was constructed to extract the rice leaf area index at each observation time point, and the change range of the rice leaf area index between adjacent time points was calculated. The missing data areas were filled by interpolation, and the time series smoothing was performed to obtain the time series LAI data. Based on the time series LAI data, the crop growth trend index is calculated using the following formula: ; in, is the crop growth trend index, For the Rice leaf area index at each time point, is the rice leaf area index at the previous time point, For the The leaf density corresponding to each time point is is the rice canopy height, is the color change rate of rice leaves, is the influence factor of color change on trend index, is the number of data points in the time series; Based on the crop growth trend index, the change pattern of the crop growth trend index in the time dimension is analyzed, the trend characteristics of growth, stability or decline are extracted, and the time series analysis results are obtained.

[0038] Specifically, based on the original LAI data obtained above, the rice leaf area index corresponding to each observation time point is first summarized and mapped to a time axis. All records are arranged in a matrix in chronological order and the records with obvious errors are compared with the rice growth curves established in previous years. If the deviation exceeds the threshold set after the previous sample comparison, For example, the rice LAI comparison mean of previous years plus or minus 0.8 is used as the benchmark judgment range. When any record exceeds the mean by 1.6, it is considered to be too large. Then these records with large deviations are placed in the list to be checked and combined with manual inspection to see if there are any collection anomalies or data missing. For observation periods that are confirmed to be completely missing, they are supplemented by interpolation. For example, when there are 3 days of data completely missing in a 30-day observation sequence, the LAI values ​​before and after the missing data are extracted and recorded as and , divide the intermediate period into equidistant steps by linear interpolation and insert the intermediate LAI value daily, and then use a smoothing coefficient empirically selected in the range of 0.2 to 0.3 to complete the weighted average. If the smoothing coefficient is set to 0.25, weighted operations on adjacent items are performed on the interpolated sequence in turn. After eliminating the anomalies, the continuity of the overall data in the time dimension is continuously checked. After all interpolation and smoothing processing are completed, a LAI time series with no omissions and low noise is statistically calculated to obtain the time series LAI data.

[0039] The benefit of the formula is that it couples the change in rice leaf area index between adjacent time points with leaf density, canopy height and color change rate, so that the growth trend not only reflects the increase or decrease in the index value, but also reflects the fluctuations caused by the amplitude of leaf morphology and color changes, thereby more accurately reflecting the overall growth dynamics of rice.

[0040] The steps to obtain are: Representative in the Rice leaf area index measured at different time points.

[0041] The steps to obtain , which is the absolute difference of LAI between adjacent time points, are to sort them in chronological order and subtract the LAI of two consecutive observations, and take their absolute values. If the difference exceeds the set upper threshold It is necessary to confirm whether there is a very significant increase or data anomaly. It can be determined by the average maximum change of samples in previous years. For example, if a historical record with 500 periods shows that the maximum change of LAI in a single day is 2.0, then It is set to 2.0 and new observation data are checked. Once the difference exceeds 2.0, it must be listed as a suspicious point. The corresponding difference is calculated at each time point and then summarized into a difference sequence, which is then linked with FSj for calculation.

[0042] The steps to obtain are: Indicates The leaf density corresponding to each time point can be measured by reading the number of leaves per unit area in the captured image, which generally fluctuates between 500 and 800 plants per square meter, and the indicator must be corrected based on the plant spacing. The monitoring method is to measure the number of plants through visual identification or on-site measurement in a fixed sample plot. If the seedlings are sparse in some areas, the actual FSj will be lower. To quantify this value, multiple 1-meter square grids are selected in an area for statistics, and the total number of leaves is recorded and divided by the number of grids to obtain the average number of leaves. This average value is then recorded as the basic amount of FSj. If the actual measurement in a certain place shows that the average number of leaves is 650, then FSj=650 is directly set.

[0043] The steps to obtain FSj are as follows: This square root term means amplifying the ratio of leaf density to LAIj+1. The ratio of FSj to LAIj+1 can be between 0 and hundreds. If FSj is too large, the ratio will be significantly increased. To ensure numerical stability, 1 is often added to the denominator, and then the square root is used to reduce excessive discreteness. FSj and LAIj+1 are both derived from previous measurements and calculations. Direct division and square root addition are then performed. For example, at observation time point j, FSj=600, LAIj=2.2, then the internal ratio is , add 1 and take the square root to get Approximately equal to 13.73.

[0044] The steps to obtain are: Indicates The rice canopy height at each time point is generally in the range of 10 cm to 120 cm. The measurement method usually involves randomly selecting representative locations in the field and measuring with a ruler. When the observed value deviates significantly, it needs to be verified again in combination with the plant height records of previous years. After recording all the height values, they are sorted by time point. If the height of a certain point is greater than the maximum height in previous years, it is checked whether it is a measurement error. Finally, the confirmed value is set as For example, the height is about 25 cm on the 20th day after transplanting, about 55 cm on the 40th day, and about 85 cm on the 60th day. This can be serialized and recorded as Etc., and put it into the denominator for summary operation.

[0045] The steps to obtain are: It represents the rate of change of rice leaf color. It is quantified by analyzing the degree to which the leaf color system in adjacent time periods evolves toward yellowish or brownish color. Usually, the main band position of the leaf color is extracted in the captured image and compared with the band position at the previous time point. The change in nm level is converted into a ratio of 0 to 1. If the color is yellowish, the band peak will move to a longer wavelength. If the shift is 6nm, the value is divided by an average visible light wavelength span, such as 300nm from 400nm to 700nm, and 0.02 is obtained as a color shift rate. If there is a larger fluctuation in the subsequent time period, the ratio will be increased accordingly. Finally, all leaf color change rates are marked as in a time series. , if the color peak position is 560nm in the jth period and 558nm in the j1th period, then the color shift of 2nm is calculated to be 0.0067 for 300nm, which is recorded as .

[0046] The steps to obtain are: The influence factor of color change on the trend index needs to be regressed by observing the different degrees of influence of the leaves changing from green to yellow in multiple experiments. Statistically, the FDj of each period is compared with the actual growth trend of the crop to obtain a group of samples, and then the least squares method is used to fit the trend index. The value of is usually between 0.5 and 2.0. For example, in a certain place, multiple batches of rice were tested and confirmed It is most consistent with the growth conditions observed in the field, so As a fixed value for subsequent calculations.

[0047] The steps for obtaining M are as follows: m is the number of data points in the time series, which comes directly from the observation frequency and duration set during the observation process. For example, if the observation is made every other day for 30 days, 15 time points will be obtained, or if the observation is made twice a day for 14 days, 28 time points will be obtained. Here, m only needs to be consistent with the actual observation frequency. For example, if a field is observed once a day for 60 consecutive days, then m=60.

[0048] Calculation process: In the records of m=5 time points, first substitute LAI and FSj, FHj, FDj of each period into the numerator and denominator, and set , , , , ,make , substituting it into the numerator:

[0049] in It is defined that the value at the end of the previous period can be recorded as 1.0, and calculated item by item: j=1 item: ; j=2 items: ; j=3 items: ; j=4 items: ; j=5 items: ; Numerator Total: ; Denominator:

[0050] Calculate in sequence: j=1 item: ; j=2 items: ; j=3 items: ; j=4 items: ; j=5 items: ; Denominator Total: ; Divide the numerator by the denominator:

[0051] The results show that under the values ​​of these five observation periods, the crop growth trend index T is approximately 0.42. The larger the value, the more significant the growth change. When T is greater than 3, it often corresponds to a high-speed growth stage, and when T is lower than 1, it indicates that the growth change is relatively mild.

[0052] Based on the crop growth trend index obtained above, all observation points are listed in chronological order and the index values ​​of each period are sorted. The multiple index distribution intervals summarized in the statistical data of previous years are compared. If the index value is found to be below 1 or above 4, the corresponding period is marked as likely to fluctuate significantly. The overall time dimension can be divided into three stages: early, middle and late according to the observation frequency. The index distribution of each stage is classified and counted to see whether it maintains continuous growth in the interval of 1 to 2 or presents stage stability in the interval of 3 to 4. The trend trajectory of the index over time is analyzed in combination with the additional parameters of leaf density and canopy height. If the index rises sharply in some periods of the middle period and exceeds the threshold of 3.5 set in the actual measurement comparison of previous years in this area, the period is marked as a rapid change period. A more detailed time interval analysis is performed for these rapid change periods and compared with the measured value of the color change rate. When the index is below 1 for many consecutive days, it is recorded as a recession mode and included in the special attention list. Finally, the corresponding growth, stability or recession characteristics are extracted according to the distribution form of the index values ​​of all periods on the time axis to obtain the time series analysis results.

[0053] The steps for obtaining comprehensive monitoring data are as follows: Based on the results of time series analysis, crop growth trend data is extracted, soil moisture measurement data and meteorological observation data are called, the soil moisture change rate, air humidity change amplitude, temperature gradient and precipitation accumulation are calculated, and the environmental parameter set is obtained; Based on the environmental parameter set, the comprehensive monitoring index is calculated using the following formula:

[0054] in, is a comprehensive monitoring index. Represent the real-time measurement values ​​of soil moisture content, air humidity and temperature respectively. are the time series smoothing values ​​of the corresponding parameters, Represent the fluctuation range of each environmental factor, represent the changing rates of soil moisture, air humidity and temperature respectively. Factors affecting environmental change; Based on the comprehensive monitoring index, the impact of environmental factors on crop growth trends is analyzed, the correlation between environmental variables and crop growth status is extracted, and comprehensive monitoring data is obtained.

[0055] Specifically, based on the time series analysis results obtained above, crop growth trend data are first extracted and matched to corresponding observation time periods one by one. After obtaining the trend data, the recorded soil moisture measurement information and local meteorological observation information are referenced, and the soil moisture values ​​sampled multiple times recently are numbered by day and compared with the historical humidity average of the same season. When the difference between the single-day measurement data and the average of previous years exceeds the humidity fluctuation threshold of 2 percentage points obtained through continuous field measurements, it is marked as a significant change, and the soil moisture change rate during this period is recorded. At the same time, the air humidity measurement value is calibrated with the established relative humidity reference range. If the deviation range is greater than the 3% upper and lower floating limit obtained through cumulative statistics in previous years, it is recorded as a significant fluctuation. The amplitude of the air humidity change during this period is recorded, and then the temperature observation content is analyzed. The difference between the highest and lowest temperatures is calculated hourly and regarded as the daily temperature gradient. When the temperature gradient difference is greater than the upper limit of 5°C of the daily average difference obtained from local summer observations in the past three years, it is additionally recorded as extreme temperature gradient data. The precipitation is superimposed by accumulating all rainfall periods on the day. When the cumulative amount exceeds the precipitation statistical interval of 40 mm provided by the hydrological department after continuous observation for many years, it is marked as medium to high-level precipitation. All recorded soil moisture change rates, air humidity change amplitudes, temperature gradients and precipitation accumulations are arranged in time series and corresponded one by one with crop growth trend data. The changes in each time period are comprehensively compared with the differences between similar periods in previous years. When it is confirmed that there are no obvious abnormal errors in the records, the values ​​of the four environmental factors are unified to form an environmental parameter set.

[0056] The benefit of the formula is that it combines the difference between the real-time measurement and smoothed value of soil moisture content, air humidity and temperature in a dynamic environment, and multiplies the numerator by an additional quantification term for the fluctuation amplitude. At the same time, it is linked to the rate of change through the exponential correction factor in the denominator, thereby more comprehensively evaluating the impact of the environment on crop growth trends.

[0057] The steps to obtain the parameters are: It indicates the real-time measurement value of soil moisture content, which is generally between 0% and 50%. During monitoring, a probe measuring point with a depth of about 10 cm is dug in the field, and the soil moisture content is recorded every 6 hours. When it is found that a single measurement result is significantly higher than the dryness and humidity limit value of 45% determined through years of actual measurement, it is necessary to recalibrate. The final confirmed measurement data is recorded as For example, the soil moisture content of a certain place in the last four days is 40%, 42%, 47% and 46% respectively. The values ​​measured on each day can be summarized in their respective time periods and then called into the formula calculation.

[0058] The steps to obtain the parameters are: It represents the real-time measurement value of air humidity. Common values ​​are between 20% and 100%. The humidity recording device deployed at a height of 2 meters above the farmland collects data once an hour. If multiple readings exceeding 80% are observed continuously, it is necessary to compare with the regional reference data. After confirming that the sampling value has not drifted, it is recorded as , and correspond to the humidity distribution range observed in the past. If the humidity recorded in multiple hours of a certain day is between 60% and 70%, the measured value of this period can be regarded as meeting the local common level. Finally, the humidity measurement value of the day is used for the formula input of the corresponding period. For example, on the first day, 65% was monitored at 8:00, 70% at 14:00, and 68% at 20:00 were monitored. Finally, it was recorded as a group. sequence.

[0059] The steps to obtain the parameters are: It indicates the real-time measurement of temperature in degrees Celsius. It may fluctuate greatly in the range of 0℃ to 40℃. The monitoring method is to obtain temperature records at the same height of the field weather station and track them hour by hour. When the temperature reading of the day differs from the multi-year average temperature by more than 6℃, it will be marked in the record for additional attention. It will then be officially registered after it is confirmed to be correct in subsequent statistics. For example, in a summer monitoring, the highest temperature can reach 35℃ and the lowest temperature is 25℃. After recording at multiple times throughout the day, several All numerical values ​​are put into the corresponding time period in the formula.

[0060] The steps to obtain the parameters are: The time series smoothing value of soil moisture content is represented by arranging the soil moisture data measured over multiple days into a column and unifying a relatively stable curve using the moving average method or exponential smoothing method. The specific operation is to select a moving window length of 3 days and calculate the mean of soil moisture in each window, and then arrange all the means to form a new sequence recorded as When looking back and finding that the humidity changes in a certain period of time are quite different, the weighted moving average method can be used to suppress the sudden increase in data. For example, the humidity measured in a period of 5 days is 40%, 39%, 44%, 43%, and 41%. The average of the adjacent 3 days is used as the smooth output to obtain approximately 40.3%, 42%, 42.6%, etc., thus forming Continuous values.

[0061] The steps to obtain the parameters are: Represents the time series smoothed value of air humidity, according to and A similar approach is used to make a weighted average of the air humidity recorded multiple times a day, amortize the errors of the extremely fluctuating hourly measurements, and then output the smoothed result and record it as , the range can be between 20% and 100%. If the humidity in a certain section changes dramatically, the length of the smoothing window can be shortened to ensure that the overall trend is accurately reflected. For example, the humidity in a certain area is 65% during the day, 80% at night, and 85% in the early morning. Then, the moving average is used to output smooth results such as 72%, 78%, etc., and finally concatenated into Used for subsequent formula calculations.

[0062] The steps to obtain the parameters are: The time series smoothing value of temperature is represented by marking individual observations that are too high or too low as noise in multiple temperature records monitored daily, and then calculating the mean in the form of a moving window and stringing them into a smooth sequence. If the temperature is collected once an hour in the summer, 24 data will be obtained. The mean of these data will be output as a moving window of 6 hours, and 4 smoother temperature values ​​will be obtained. When they are continuously aggregated for multiple days, a set of If the temperature is only 18℃ at night on a certain day and is above 25℃ in most other periods, you need to check the fluctuations when calculating the mean value and confirm that the actual measurement is correct before writing it. .

[0063] The steps to obtain the parameters are: Indicates the fluctuation range of soil moisture content. The change in moisture content is measured by analyzing the soil moisture range at multiple times of the day. If the difference between the maximum and minimum values ​​exceeds the 5% upper and lower thresholds accumulated over many years, it is classified as a large fluctuation. When recording, the difference is entered into the formula as the fluctuation range. If the soil moisture measured during the day changes from 36% to 42%, the fluctuation range can be determined as 6%. After combining the local threshold test to confirm that it is within the safe range, 6% is recorded as .

[0064] The steps to obtain the parameters are: Indicates the fluctuation range of air humidity. The range is confirmed by comparing the difference between the highest humidity and the lowest humidity within a day or several days. If the difference exceeds the previous experience threshold of 15%, it is considered to have a significant fluctuation and the difference is recorded as In terms of calculation, the maximum and minimum differences can be found in multiple observation periods every day, and then the thresholds can be compared after accumulation or average. If the sum of the highest and lowest differences in air humidity within three days is 45%, and the average difference is 15%, then it is marked .

[0065] The steps to obtain the parameters are: Indicates the fluctuation range of temperature. This range is obtained by recording the difference between the highest and lowest temperatures in a day. If the span is close to 10℃ for many consecutive days, it means that the fluctuation is large. When compared with the local statistical average of 9℃ over the years, it can be regarded as a high fluctuation and registered. If the highest temperature of 35℃ and the lowest temperature of 25℃ on the day have a difference of 10℃, 10 is recorded as .

[0066] The steps to obtain the parameters are: It represents the rate of change of soil moisture. The value is obtained by dividing the difference of soil moisture in the adjacent observation periods by the time interval. The change rate of each adjacent period is sorted and regarded as a sequence. If the soil moisture rises from 30% to 32% day by day, 2% is divided by 24 hours to get about 0.083% per hour. The daily average change rate is obtained by averaging the rates obtained from multiple consecutive observations and is checked again when it exceeds the past statistical interval. The final confirmed result can be recorded in the range of 0.01% per hour to 1% per hour. .

[0067] The steps to obtain the parameters are: It indicates the rate of change of air humidity. It is obtained by differentiating the humidity measurement records at the hourly level or shorter time granularity. When the value goes up or down significantly, it means that the humidity is changing rapidly. If it rises from 50% to 60% within 2 hours, the change is 10%, which is 5% per hour. If a similar trend occurs for two consecutive days, the average change rate of the day is set to 5% per hour and marked in the database. The final result is The numerical value is used in the denominator of the formula.

[0068] The steps to obtain the parameters are: It represents the rate of change of temperature. It is obtained by measuring the temperature difference between multiple observation periods and dividing it by the time interval. For example, if the temperature is 20℃ in the early morning and 30℃ at noon, it changes by 10℃ in 4 hours, with a rate of 2.5℃ per hour. Then check whether there is a temperature drop of the same magnitude during the night period. The average or peak value of the data of all periods can be used to derive a daily average rate of change, which is recorded as When it is detected that the value exceeds the statistical extreme value of the control area of ​​8℃ per hour for many consecutive days, it will be manually reviewed and finally recorded in the formula as .

[0069] The steps to obtain the parameters are: It represents the influencing factor of environmental change. It is obtained by comprehensive comparison and statistics of the influence of changes in soil moisture, air humidity and temperature on crop growth collected from multiple places. The general range is 0.5 to 2.0. The specific method is to collect the actual measured change rate and crop growth indicators in different farmland experiments, perform linear or nonlinear regression on the two, and extract the best fitting point to determine , when found When the error is the smallest, this value is fixed for subsequent unified use. For example, 30 fields in a certain area are compared, and the coupling degree between the color change rate and the environmental rate is calculated. It is found that The highest degree of agreement with field observations is confirmed. .

[0070] Calculation process: Select a scenario and specify , , , , plug these values ​​into the formula:

[0071] Then add the above three items together:

[0072] Finally, take the square root:

[0073] The results show that the comprehensive environmental monitoring index is about 4.4938 at this time. When the value exceeds 5, it will be related to large fluctuations in dryness and humidity and high temperature environment. When the value is lower than 1, it indicates that the environmental factors are basically stable.

[0074] Based on the comprehensive monitoring index obtained above, the index values ​​of multiple observation periods are first arranged and classified according to date and time period. Then, the crop growth trend data observed in the same period are read and directly compared with the corresponding index values. When the index is found to be in the 2 to 3 interval of the historical statistics in this area, the crop growth trend data in the farmland can be compared to see whether it is also in a state of stable growth. If the index is in the 4 to 5 interval, check whether the soil moisture content in the observation period greatly exceeds the 3% threshold of the daily average change obtained in the previous statistics, and whether the air humidity or temperature measurement value deviates significantly from the average of previous years by more than 5%. When it is confirmed that these external environments do fluctuate significantly, the corresponding relationship between the environmental parameters and the crop growth trend of the period is recorded, and then the time series curves are established one by one for comparative observation, and the fluctuations of the index and the changes in crop LAI are superimposed. For some continuous periods, the high index is combined with the high leaf area index increase to check whether it conforms to the linear trend of historical statistics. If it is observed that the index has increased significantly but the leaf area index increase is not large, the period is added to the subdivision list for subsequent in-depth review. Finally, the index of all periods is compared with the crop growth status one by one and written into the result comparison table to obtain comprehensive monitoring data.

[0075] The steps to obtain crop growth assessment results are: Based on the comprehensive monitoring data, the growth adaptability score is calculated using the following formula:

[0076] in, is the growth adaptability score, is the rice leaf area index, is the photosynthetic capacity index of crops, is the soil temperature, is the air humidity, is the cumulative impact value of meteorological factors, is the soil moisture change rate; Based on the growth adaptability score, the growth status of rice in the current environment is analyzed to obtain the crop growth assessment results.

[0077] Specifically, the formula is beneficial in that it comprehensively considers the relationship between the rice leaf area index, crop photosynthetic capacity index, soil temperature, air humidity, and the cumulative impact value of meteorological factors and the soil moisture change rate. It uses the numerator to measure the gap between crop physiological indicators and the external temperature and humidity, and then corrects it through the cumulative impact value and humidity change rate in the denominator. This allows the calculation results to more precisely quantify the degree of rice growth adaptability under different environments and different growth conditions.

[0078] The steps to obtain the LAI parameters are as follows: LAI represents the rice leaf area index, which has been obtained previously. The steps to obtain the P parameter are: P stands for the crop photosynthetic capacity index, which is generally used to describe the level of rice's absorption and conversion of sunlight energy. This index can range from 0 to 2 and is obtained by combining an actual field photometer with a plant physiological meter. The specific steps are to record the correlation between light intensity and leaf photosynthetic rate during the noon period of rice, and then convert the average maximum net photosynthetic rate calculated from multiple samples into a P score. In a certain place, 30 representative rice plants can be selected in the middle of the growth period, and the photosynthetic rate can be recorded and the average value calculated within the 3 hours of the strongest sunlight. For example, the net photosynthetic rate per hour is measured to be 25 micromoles of carbon dioxide per square meter second, and after comparing it with the average rate measured in previous years, it is concluded that P is about 1.7.

[0079] The steps to obtain the T parameter are: T represents soil temperature in degrees Celsius, which is generally obtained from a probe 5 to 10 cm below the soil surface. During the monitoring process, temperature sensors are placed in the field and the values ​​are recorded at hourly or half-hourly intervals. To ensure accuracy, the sensors need to be calibrated periodically and the temperatures collected at multiple points are weighted averaged. The soil temperature in a certain area can be monitored at 6 a.m., 12 noon, and 6 p.m., for example, after measuring 24°C, 28°C, and 26°C, an average value is weighted and finally registered as T=25°C. When there is extreme weather that may cause the value to exceed the local historical average by ±5°C, this part of the data must be recalibrated before it can be officially recorded as T.

[0080] The steps to obtain the YH parameters are: YH represents air humidity, and its dimension is usually between 0 and 1. It uses decimal form to represent relative humidity, and can also be expressed as a percentage value between 20% and 100%. The specific quantification method is to collect data through a humidity sensor installed about 2 meters above the ground, and then regularly compare it with the comparison table provided by the National Meteorological Observatory to eliminate sensor offset. Field monitoring can record relative humidity multiple times a day, and then combine it into a weighted average as a representative of YH. If the humidity recorded in a day is 70%, 80%, and 76%, the average value can be set to 0.75 (i.e. 75%), and it can be recorded in the formula to form the input item of YH=0.75.

[0081] The steps to obtain the YS parameters are: YS represents the cumulative impact value of meteorological factors, which is used to reflect the cumulative impact of meteorological changes on crop growth over a long period of time. This value usually has no fixed upper limit and is accumulated through experimental statistics or continuous observation. The specific acquisition is to first integrate the meteorological data of crops over a period of time, including the number of extreme temperatures, the duration of excessive humidity, precipitation, and abnormal sunshine periods, and assign an impact score to each meteorological event, and then add up the scores of multiple events to get YS. In a certain area, during a one-month observation period, the maximum daily temperature exceeding 35°C can be regarded as an impact event with 2 points, the relative humidity below 40% can be counted as 3 points, and the extreme rainstorm can be counted as 1 point, etc. The total score is added up and recorded as YS. If the final cumulative score is 2.0, substitute YS=2.0 into the formula.

[0082] The steps to obtain the YD parameters are: YD represents the rate of change of soil moisture, which can measure the dynamic degree of soil moisture change over time. The field practice is to first collect soil moisture values ​​on an hourly basis in a fixed monitoring area, define the ratio of the difference between adjacent time periods to the time interval as the instantaneous rate of change, and then take the average value for one or several observation days to obtain the representative value of YD. In a certain place, it takes 6 hours to monitor that the soil moisture rises from 30% to 32% within 24 hours. The difference of 2% divided by 6 hours equals 0.33% per hour. After multiple observations, the average is taken to form 0.4% per hour, which is then converted to 0.004, that is, 0.4% is substituted into the formula. At this time, YD=0.004.

[0083] Calculation process: Now select an example and let .

[0084] First calculate the numerator:

[0085] Next, calculate the denominator:

[0086] Divide the numerator by the denominator:

[0087] The results show that the growth adaptability score is close to 6, which means that under the conditions of soil temperature of 25°C, air humidity of 0.8 and LAI = 3.2, the rice growth and environmental matching degree is in the upper-middle range. Usually, a score greater than 8 indicates extremely high adaptability, while a score lower than 2 may indicate growth restriction and require additional inspection.

[0088] Based on the growth adaptability score obtained above, first record the environmental conditions and rice monitoring data corresponding to the score at different time nodes one by one, and form a comparison table by sorting out the soil temperature, air humidity and LAI values ​​of all monitoring periods, and add information such as the photosynthetic capacity index P and the cumulative impact value of meteorological factors YS to the comparison table. Then, arrange the scores of each day or hour in a continuous observation period and check whether there are large fluctuations. Combined with the soil moisture change rate YD, jointly evaluate the source of the score change. When the continuous curve of the score is lower than the empirical threshold 2 in some time periods, it is necessary to check again whether the air humidity in the period deviates significantly from the daily average of 60% obtained by many years of observation in this area, and check whether the soil temperature is within the range of 5% and above. If the temperature exceeds the range of 15℃ to 35℃ established according to local statistics, if there is a significant deviation, record this period as a potential unfavorable growth range and mark the actual situation accordingly, such as rainfall and water depth in the field, and then observe whether the score rebounds in the following days. If the score continues to exceed 8, it means that the environment and photosynthetic conditions are highly consistent. Record it in the high fitness segment and compare it with the actual growth performance of the crop. When all time periods are matched, perform time series statistics on these score partitions, and output the division results including medium, low and high intervals, which provide basic support for subsequent targeted judgment of rice growth status. Finally, in the summary stage, compare all partitions and trends one by one and check them with the latest field observations in the farmland to obtain the crop growth assessment results.

[0089] The steps to obtain management adjustment suggestions are: Based on the results of crop growth assessment, soil moisture content, soil nitrogen, phosphorus and potassium content, chlorophyll index, precipitation and temperature are extracted to obtain basic data for agricultural management; Based on the basic agricultural management data, the management adjustment index is calculated using the following formula:

[0090] in, To manage the adjustment index, Respectively represent the current nitrogen, phosphorus and potassium concentrations in the soil. The amount of irrigation water supplied, is the total precipitation, is the chlorophyll index, is the crop leaf temperature; Based on the management adjustment index, the adaptability of rice to current irrigation and fertilization is analyzed, and the need to adjust agricultural management measures is evaluated to obtain management adjustment recommendations.

[0091] Specifically, the formula is useful in that it integrates the key factors such as the concentrations of nitrogen, phosphorus and potassium in the soil, irrigation water supply, total precipitation, chlorophyll index and crop leaf temperature, and introduces nonlinear effects on chlorophyll and leaf temperature in the denominator, which can more intuitively reflect the balance between fertilizer and water supply and the physiological state of crops.

[0092] The steps to obtain the parameters are: The concentration value representing the soil nitrogen content is generally expressed in milligrams per kilogram of soil (mg / kg) or as a percentage. To ensure accuracy, several sampling points are randomly selected from different plots and soil samples are obtained within the 0 to 20 cm tillage layer. The contents of ammonium nitrogen, nitrate nitrogen, etc. are tested and summed using laboratory chemical analysis methods. If a certain area wishes to quantify the total amount of nitrogen, 200 grams of soil can be taken from each of the 10 sampling points in one day, totaling 2 kilograms, and then the nitrogen content can be measured using methods such as distillation, alkali addition, and colorimetric determination. If it is found that the nitrogen content per kilogram of soil is between 120 mg and 300 mg, the value is compiled into an average value and recorded as If the nitrogen content of the soil is 200 mg / kg in one operation, mg / kg is incorporated into the formula.

[0093] The steps to obtain the parameters are: Indicates soil phosphorus concentration, mostly in terms of available phosphorus (Olsen-P or fast-acting phosphorus), in mg / kg. The detection process is usually to collect soil from the field plough layer, extract it with sodium bicarbonate, and then use a spectrophotometer to measure the phosphorus concentration in the extract, and finally convert it back to soil content to form If the average available phosphorus content in the plough layer of a region is around 20 mg / kg, and in areas with high phosphorus fertilizer application, it may reach 40 to 50 mg / kg, a unified laboratory test is required after sampling. If the average value of three tests is 30 mg / kg, then Substitute mg / kg into the formula.

[0094] The steps to obtain the parameters are: Indicates the soil potassium concentration, usually presented as available potassium, and the unit can also be mg / kg. When obtaining, the soil sample needs to be dried and sieved, extracted with ammonium acetate solution, and then measured with a flame photometer. If the available potassium test results of the topsoil in a certain area show a range of 50 to 150 mg / kg, the representative mean or weighted result can be recorded as For example, after sampling and analyzing a piece of soil at multiple points, the average value of the available potassium content is 80 mg / kg, which can be marked as .

[0095] The steps to obtain the parameters are: It indicates the amount of irrigation water supplied, usually recorded in tons per hectare or cubic meters per hectare. When obtaining it, the actual amount of water injected into the field by the irrigation channel is first counted, or it is directly read by the flow meter installed at the irrigation outlet, and then converted into the irrigation duration and field area. If a region injects a total of 50 tons of water into 1 hectare of rice fields in a week, it can be recorded as Tons / hectare.

[0096] The steps to obtain the parameters are: Represents the total amount of precipitation, usually recorded in millimeters or cubic meters per hectare. It can be monitored using rain gauges or automatic weather observation instruments, and official weather stations and field rain gauges are cross-referenced and registered as daily cumulative values. The precipitation over several days or a week is combined into a total. If the total depth of precipitation recorded over three days is 30 mm, it means that about 300 cubic meters of rain have been input per hectare. If this value is recorded as Millimeters.

[0097] The steps to obtain the parameters are: Represents the chlorophyll index, which is used to reflect the chlorophyll content level in crop leaves. The value can range from 0 to 100, or it can be expressed as a relative value. The specific way to obtain it is to use a handheld chlorophyll meter (SPAD meter) or a multispectral drone to shoot in the field, extract the spectral reflectance characteristics in the leaf area and convert it into a chlorophyll index. If 10 representative plants are selected in a rice field, 3 leaves of each plant are measured and averaged, and then a set of data is obtained through instrument recording, if the average reading reaches 45, the value can be compared with the instrument calibration table to obtain the chlorophyll index. .

[0098] The steps to obtain the parameters are: Indicates the temperature of crop leaves in degrees Celsius, usually obtained with the help of an infrared temperature gun or thermal imager. To reflect the temperature distribution of the main leaf surface of the crop, the temperature of the top and middle and lower leaves of several rice plants can be collected during sunny hours, and then the multiple measurement results can be unified and averaged. If the top leaf temperature is about 28°C and the middle and lower leaf temperature is about 26°C on a certain day, and the combined temperature is 27°C after multiple measurements in one day, then it can be When it is detected that the plant temperature is significantly higher than the local historical range, it is necessary to check whether drought or poor ventilation occurs before recording the final temperature value.

[0099] Calculation process: make mg / kg, mg / kg, mg / kg, Tons / hectare, mm, , , unify the units and make reasonable conversions before entering the formula:

[0100] molecular:

[0101] Denominator:

[0102] overall:

[0103] The results show that when the soil nitrogen, phosphorus and potassium content is within the above range and the irrigation water, precipitation, chlorophyll index and leaf temperature are maintained at the corresponding levels, the management adjustment index can reach about 60,000. If the value is too large, it is necessary to determine the impact of nitrogen, phosphorus and potassium concentrations, irrigation volume or precipitation on overall management. Usually, in order to enhance the interpretability, it is necessary to combine the actual farmland area or adjust the unit dimension so that the value has a reference significance that is closer to the growers' operating habits.

[0104] Based on the management adjustment index obtained earlier, the actual measured nitrogen, phosphorus and potassium concentrations of each rice field, as well as the irrigation amount, precipitation in recent days and leaf temperature records are first summarized, and the chlorophyll index is used as an additional reference item to check whether it matches the planting process. If it is found that the leaf temperature in a certain period of time obviously exceeds the highest critical value of 35°C obtained from local statistics for many years, the soil moisture in the soil moisture monitoring results is compared to see whether it is lower than the reference humidity range of 25% to 40%. If high leaf temperature and low soil moisture are met at the same time, it may cause an imbalance in the transpiration rate. Therefore, the management adjustment index and chlorophyll readings of the period are recorded as related parameters, and then the fertilization and irrigation arrangements in the short term are compared to see whether they are obviously too little, and whether the supplementary amount of nitrogen, phosphorus and potassium is far lower than the average range of 30 to 50 grams per mu per week in previous years. This information is combined with the recent cumulative precipitation value. It is necessary to combine the nitrogen, phosphorus and potassium concentration records to observe whether the lack of nitrogen leads to the stagnation of crop growth, or whether the phosphorus and potassium concentrations have already exceeded the regional average and unnecessary excessive fertilization is still caused. Then, from the perspective of temperature and humidity, it is checked whether the leaf temperature continues to rise or the chlorophyll index is difficult to increase. After confirming the actual situation, fine-tune the fertilizer and water management details. For example, the irrigation amount can be increased by 5% to 10% or the time period for nitrogen fertilizer application can be adjusted, and the application time point can be close to the concentrated precipitation period to penetrate the soil more evenly. Finally, after comparing the index calculations of multiple observation periods with the field observation information, the irrigation and fertilization are evaluated in combination with the changes before and after, and the conclusion on whether to adjust the agricultural management measures is output to obtain management adjustment suggestions.

[0105] The present invention provides a system, comprising: The data acquisition module deploys drones to fly over the target rice fields, collects image data, and sends them to the ground station in real time to generate a preliminary image data set; The image processing module crops and corrects the preliminary image data set to generate a processed image data set; The LAI calculation module, based on the processed image dataset, identifies and measures the rice leaf area index in the image, identifies the health status and growth stage of the crop, and generates raw LAI data; The data analysis module performs time series analysis on the original LAI data, determines the crop growth trend through comparative analysis, and generates time series analysis results; The agricultural management recommendation module is based on the results of time series analysis, combined with soil moisture and meteorological data. It combines soil moisture and meteorological data with the results of time series analysis to generate comprehensive monitoring data, uses the comprehensive monitoring data to evaluate the growth status of rice, analyzes the environmental factors affecting crop growth, and generates crop growth assessment results. Based on the crop growth assessment results, it evaluates the effectiveness of the current irrigation and fertilization plans, determines whether agricultural management measures need to be adjusted, and generates management adjustment recommendations.

[0106] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for monitoring crop growth through images, characterized in that: The following steps are involved: Deploy a drone to fly over a target rice field to collect image data, and send the image data to a ground station in real time through data transmission to generate a preliminary image data set; crop and correct the preliminary image data set to generate a processed image data set; Based on the processed image data set, the rice leaf area index in the image is identified and measured, the health status and growth stage of the crop are identified, and the original LAI data is generated; the original LAI data is analyzed in time series, the crop growth trend is determined by comparative analysis, and the time series analysis results are generated; Based on the time series analysis results, soil moisture and meteorological data are combined, and the soil moisture and meteorological data are combined with the time series analysis results to generate comprehensive monitoring data; the growth status of rice is evaluated using the comprehensive monitoring data, environmental factors affecting crop growth are analyzed, and crop growth evaluation results are generated; Based on the crop growth assessment results, the effectiveness of the current irrigation and fertilization plans is evaluated, whether agricultural management measures need to be adjusted is determined, and management adjustment recommendations are generated.

2. The method for monitoring crop growth through images according to claim 1, characterized in that: The steps for obtaining the preliminary image data set are: Deploy a drone to fly over the target rice field, collect image data of the rice field through the camera, adjust the camera angle and focal length to cover the entire field surface, and obtain real-time collected rice field images; Based on the rice field images collected in real time, the data are sent to a ground station in real time via wireless transmission to obtain a preliminary image data set.

3. The method for monitoring crop growth through images according to claim 1, characterized in that: The steps for obtaining the processed image data set are: Based on the preliminary image data set, edge transition areas are determined by pixel gradients, isolated noise points are eliminated, boundary ranges are adjusted according to shape features of the target crop area, redundant background areas are removed, and image data after boundary adjustment is obtained; Based on the image data after the boundary adjustment, lens distortion parameters including radial distortion and tangential distortion are calculated, and pixel offset caused by the correction is restored by image interpolation to generate distortion-corrected image data; Based on the distortion-corrected image data, color channel normalization processing is performed, and at the same time, histogram equalization is performed to adjust the brightness distribution to obtain a processed image data set.

4. The method for monitoring crop growth through images according to claim 1, characterized in that: The steps for obtaining the original LAI data are: Based on the processed image data set, RGB channel separation is performed, pixel values ​​of the red channel, the green channel and the blue channel are extracted, and the channel data of the rice leaf region is obtained; Based on the rice leaf area channel data, the rice leaf area index is calculated using the following formula: and ; in, is the rice leaf area index, is a variable ratio vegetation index based on drone images. is the green channel digital value, is the digital value of the red channel, is the digital value of the blue channel; Based on the rice leaf area index, leaf color and texture features are extracted, spectral variation trends during the growth cycle are compared, crop health status and growth stage are identified, and original LAI data are obtained.

5. The method for monitoring crop growth through images according to claim 1, characterized in that: The steps for obtaining the time series analysis results are: Based on the original LAI data, a time series matrix is ​​constructed, the rice leaf area index at each observation time point is extracted, the rice leaf area index change range between adjacent time points is calculated, the data missing area is filled by interpolation, and the time series smoothing process is performed to obtain the time series LAI data; Based on the time series LAI data, the crop growth trend index is calculated using the following formula: ； in, is the crop growth trend index, For the Rice leaf area index at each time point, is the rice leaf area index at the previous time point, For the The leaf density corresponding to each time point is is the rice canopy height, is the color change rate of rice leaves, is the influence factor of color change on trend index, is the number of data points in the time series; Based on the crop growth trend index, the change pattern of the crop growth trend index in the time dimension is analyzed, the trend characteristics of growth, stability or decline are extracted, and the time series analysis result is obtained.

6. The method for monitoring crop growth through images according to claim 1, characterized in that: The steps for obtaining the comprehensive monitoring data are as follows: Based on the time series analysis results, crop growth trend data is extracted, soil moisture measurement data and meteorological observation data are called, soil moisture change rate, air humidity change amplitude, temperature gradient and precipitation accumulation are calculated, and an environmental parameter set is obtained; Based on the environmental parameter set, the comprehensive monitoring index is calculated using the following formula: ； in, is a comprehensive monitoring index. Represent the real-time measurement values ​​of soil moisture content, air humidity and temperature respectively. are the time series smoothing values ​​of the corresponding parameters, Represent the fluctuation range of each environmental factor, represent the changing rates of soil moisture, air humidity and temperature respectively. The factors affecting environmental changes; Based on the comprehensive monitoring index, the impact of environmental factors on crop growth trends is analyzed, the correlation between environmental variables and crop growth status is extracted, and comprehensive monitoring data is obtained.

7. The method for monitoring crop growth through images according to claim 1, characterized in that: The steps for obtaining the crop growth assessment result are: Based on the comprehensive monitoring data, the growth adaptability score is calculated using the following formula: ； in, is the growth adaptability score, is the rice leaf area index, is the crop photosynthetic capacity index, is the soil temperature, is the air humidity, is the cumulative impact value of meteorological factors, is the soil moisture change rate; Based on the growth adaptability score, the growth status of rice in the current environment is analyzed to obtain a crop growth assessment result.

8. The method for monitoring crop growth through images according to claim 1, characterized in that: The steps for obtaining the management adjustment suggestion are: Based on the crop growth assessment results, soil moisture content, soil nitrogen, phosphorus and potassium content, chlorophyll index, precipitation and temperature are extracted to obtain basic agricultural management data; Based on the basic agricultural management data, the management adjustment index is calculated using the following formula: ； in, To manage the adjustment index, Respectively represent the current nitrogen, phosphorus and potassium concentrations in the soil. The amount of irrigation water supplied, is the total precipitation, is the chlorophyll index, is the crop leaf temperature; Based on the management adjustment index, the adaptability of rice to current irrigation and fertilization is analyzed, and whether agricultural management measures need to be adjusted is evaluated to obtain management adjustment recommendations.

9. The system for monitoring crop growth through images according to any one of claims 1 to 8, characterized in that: include: The data acquisition module deploys drones to fly over the target rice fields, collects image data, and sends them to the ground station in real time to generate a preliminary image data set; The image processing module crops and corrects the preliminary image data set to generate a processed image data set; The LAI calculation module, based on the processed image dataset, identifies and measures the rice leaf area index in the image, identifies the health status and growth stage of the crop, and generates raw LAI data; The data analysis module performs time series analysis on the original LAI data, determines the crop growth trend through comparative analysis, and generates time series analysis results; The agricultural management recommendation module is based on the results of time series analysis, combined with soil moisture and meteorological data. It combines soil moisture and meteorological data with the results of time series analysis to generate comprehensive monitoring data, uses the comprehensive monitoring data to evaluate the growth status of rice, analyzes the environmental factors affecting crop growth, and generates crop growth assessment results. Based on the crop growth assessment results, it evaluates the effectiveness of the current irrigation and fertilization plans, determines whether agricultural management measures need to be adjusted, and generates management adjustment recommendations.

Images