Crop growth state monitoring system based on multispectral remote sensing

Abstract

This application relates to the field of agricultural planting technology and discloses a crop growth status monitoring system based on multispectral remote sensing. The system includes a region planning module, which divides the target area into sub-regions according to different crop planting types; a data acquisition module, which uses a multispectral drone to perform low-altitude scanning of crops to acquire multispectral data; and a data analysis module, which analyzes the crop growth status based on the multispectral data and the different region division methods. By dividing the target area into different regions, a data acquisition path is planned for the multispectral drone, and the drone's position is acquired in real time during data acquisition. The system determines whether the multispectral drone has deviated from the acquisition area based on its real-time position.

Description

Technical Field

[0001] This application relates to the field of agricultural planting technology, specifically a crop growth status monitoring system based on multispectral remote sensing. Background Technology

[0002] Crop growth status monitoring refers to monitoring crops after planting to obtain their growth status, understand and manage the distribution and growth status of crops in farmland, which is of great significance for optimizing agricultural production layout and improving resource utilization efficiency.

[0003] Traditional crop growth monitoring relies on manual surveys and sampling statistics. Manual surveys involve professionals visiting and recording crop distribution, which, while providing accurate data, is time-consuming, labor-intensive, and costly. Sampling statistics, on the other hand, involve conducting detailed surveys of selected plots to extrapolate the overall layout, which is prone to significant errors and lacks timeliness. Furthermore, sampling statistics cannot provide a comprehensive understanding of crop growth within the planting area, making it difficult to promptly assess crop growth conditions.

[0004] To address these shortcomings, this invention proposes a crop growth status monitoring system based on multispectral remote sensing. Summary of the Invention

[0005] The purpose of this application is to provide a crop growth status monitoring system based on multispectral remote sensing to solve the problems mentioned in the background art.

[0006] The objective of this application can be achieved through the following technical solutions: A crop growth status monitoring system based on multispectral remote sensing includes the following modules: The regional planning module divides the target area into sub-regions according to different regional division methods based on the types of crops planted within the target area. The data acquisition module uses a multispectral drone to perform low-altitude scanning of crops and acquire multispectral data of the crops. The data analysis module analyzes the growth status of crops based on the multispectral data of the crops and different regional division methods; The monitoring report module generates corresponding crop growth status monitoring reports based on the growth status analysis results.

[0007] Preferably, the work content of the regional planning module is as follows: Obtain the types of plants within the target area; The target region is divided into sub-regions according to different partitioning methods, including: Divide the same type of crops into one region, divide the target region, and define the divided regions as sub-regions of the same type; The target area is divided according to the preset planting area range, and the divided areas are defined as planting sub-regions.

[0008] Preferably, the data acquisition module performs the following tasks: Based on the divided sub-regions of the same type and the planting sub-regions, a multispectral data acquisition path is planned for the multispectral UAV; Based on the sub-region ranges of the divided similar sub-regions and the planting sub-regions, the data acquisition area of ​​the multispectral UAV is defined; The acquisition position error distance of the multispectral UAV is obtained based on the set data acquisition area and sub-area range; The data acquisition path for the multispectral UAV is preset, the position of the multispectral UAV during data acquisition is obtained in real time, and it is determined whether the multispectral UAV is within the allowable acquisition position error distance. If the distance of the multispectral UAV exceeds the acquisition position error distance, the position of the multispectral UAV will be corrected, and the multispectral data before correction will be used as the reference multispectral data.

[0009] Preferably, the data analysis module performs the following tasks: The collected multispectral data are divided into different regions and labeled in the corresponding sub-regions of the same type and the planting sub-regions, and the reference multispectral data are also labeled accordingly. Obtain historical multispectral data of the same type of sub-region, and obtain the overall growth index of the same type of sub-region based on the historical multispectral data of the same type of sub-region and the currently collected multispectral data; Based on the division of similar sub-regions, the overall growth indices of multiple similar sub-regions are compared to obtain the deviation value of the target region; Based on the planting sub-region division, any one of the planting sub-regions is selected, and the selected planting sub-region is compared with other planting sub-regions of the same crop to obtain the same type of growth comparison index of the same type of crop.

[0010] Preferably, the process for obtaining the overall growth index of the same type of sub-region is as follows: Preprocess the currently acquired multispectral data and corresponding reference multispectral data of the same sub-region; Normalized vegetation values ​​are obtained from the current multispectral data, reference multispectral data, and historical multispectral data of the same type of sub-region, respectively. Using the normalized vegetation value of the reference multispectral data as a benchmark, the collected multispectral data is calibrated to obtain the normalized vegetation value feature sequence of the same sub-region after calibration. The calibrated current normalized vegetation value is compared with the historical normalized vegetation value to obtain the crop growth deviation characteristic value of each sampling point in the same sub-region. The overall growth index of the same sub-region is obtained by averaging the growth deviation characteristic values ​​of all points within the same sub-region by area weighting.

[0011] Preferably, the process for obtaining the deviation value of the target area is as follows: Obtain the overall growth index of all similar sub-regions within the target area; The average value of the overall growth index is calculated based on all overall growth indices. Calculate the relative deviation between the overall growth index and the average value of the overall growth index for each of the aforementioned sub-regions of the same type; The relative deviations of all similar sub-regions are summed by area weighting to obtain the overall deviation value of crop growth in the target region.

[0012] Preferably, the method for obtaining the comparative growth index of the same type of crops is as follows: Based on the normalized mean vegetation value of the multispectral data and the actual planting density of the planting sub-region, the single-region growth characteristic value of the planting sub-region is calculated, which is the product of the normalized mean vegetation value and the planting density. Filter out all planting sub-regions within the target area that grow the same type of crop, and obtain the planting area data of each planting sub-region; Calculate the weighted average of the single-region growth characteristic values ​​of all planting sub-regions of the same type of crops, and use it as a unified comparison benchmark value for the growth status of the same type of crops; For each planting sub-region of the same type of crop, the growth characteristic value of the single region is compared with the unified comparison benchmark value to obtain the single region comparison coefficient of the planting sub-region; The average value of the comparison coefficients of all single regions is calculated, which is the growth comparison index of the same type of crops.

[0013] Preferably, the monitoring report module performs the following tasks: A basic data pool for the report is established based on the overall growth index, deviation value, comparison index of similar growth, as well as multispectral raw data, calibration data and basic information of the target area; The overall growth index, deviation value, and growth ratio of the same type are compared with the preset evaluation thresholds of the index. A standardized monitoring report is generated based on the comparison results.

[0014] The beneficial effects of this application are: 1. This application divides the target area into different regions, plans data acquisition paths for multispectral drones, and acquires the drone's position in real time during data acquisition. Based on the real-time acquired position, it determines whether the drone has deviated from the acquisition area. Then, based on historical multispectral data, real-time acquired spectral data, planting density, and planting area, it calculates the overall growth index, deviation value, and similar growth comparison index. Based on the overall growth index, deviation value, similar growth comparison index, and preset thresholds, it comprehensively evaluates the growth status of crops, realizing regional balance analysis and horizontal comparison of similar crops, and achieving accurate analysis of crop growth status.

[0015] Of course, any product implementing this application does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a system module diagram of the crop growth status monitoring system based on multispectral remote sensing in this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] Please see Figure 1 As shown, this application is a crop growth status monitoring system based on multispectral remote sensing, including a regional planning module, a data acquisition module, a data analysis module, and a monitoring report module; The regional planning module is used to divide the target area into sub-regions according to different regional division methods based on the types of crops planted within the target area. Specifically, it first identifies the planting types of all crops within the target area through preliminary identification and on-site surveys, knowing the types of crops planted and their approximate distribution range. Based on this, two different sub-region division methods can be used to divide the target area. One method is homogeneous sub-region division, which divides areas planted with the same type of crop into independent sub-regions according to the principle of consistency in crop planting types. For example, if the target area simultaneously grows corn, wheat, and cotton... For crops, adjacent corn-growing areas are integrated into a single corn-type sub-region, wheat-growing areas into a single wheat-type sub-region, and cotton-growing areas into a single cotton-type sub-region. In this case, the target area is divided into three types of sub-regions. Another method of division is planting sub-region division, which involves setting a fixed planting area range in advance based on actual production needs such as agricultural production planning, plot boundaries, and irrigation areas. The target area is then divided according to this preset range. For example, the area of ​​each planting sub-region is preset to be 5 or 10 mu, and the field irrigation ditches and field ridges are used as natural boundaries to divide the target area into several independent planting sub-regions.

[0020] The data acquisition module is used to perform low-altitude scanning of crops using a multispectral UAV to acquire multispectral data of the crops. Specifically, based on the division of similar sub-regions and planting sub-regions, and considering the boundary ranges, topography, crop distribution density, and other actual conditions of the similar and planting sub-regions, a data acquisition area is set. The data acquisition area is not completely consistent with the defined sub-region ranges, but rather a region slightly larger than the boundary ranges of the similar and planting sub-regions is planned in the air. In this application, the data acquisition area is 10% larger than the boundaries of the corresponding similar and planting sub-regions. This setting aims to avoid interference from the UAV. Minor deviations in flight attitude and errors in sub-region boundary identification can lead to missed data collection of crops at the edges of sub-regions. Only when the UAV selects appropriate collection points within the slightly larger planned collection area can it effectively ensure that the collected multispectral data can completely cover the target sub-region, while improving the accuracy and completeness of the data. This ensures that the data can truly reflect the growth status of crops within the sub-region. After setting the data collection area, a scientific and reasonable multispectral data collection route should be planned for the multispectral UAV to ensure that the route can fully cover all sub-regions, while taking into account collection efficiency and data quality, and avoiding collection blind spots or repeated collection.

[0021] Subsequently, based on the range difference between the set data acquisition area and the corresponding sub-area, and combined with parameters such as the UAV's flight accuracy and the acquisition range of the multispectral sensor, the acquisition position error distance of the multispectral UAV is calculated and obtained. This determines the allowable position deviation range of the UAV during the acquisition process. The acquisition position error distance is determined by comprehensively considering the range difference between the data acquisition area and the sub-area, the UAV's flight accuracy, and the acquisition characteristics of the multispectral sensor. Specifically, the boundary offset between the planned data acquisition area, which is slightly larger than the sub-area, and the corresponding sub-area is first calculated. Then, combined with the flight positioning accuracy error of the multispectral UAV and the sensor acquisition viewing angle error, the maximum value of the boundary offset and the two device errors is taken as the final acquisition position error distance. This ensures that even if the UAV has a slight position deviation, it can still complete the acquisition within the data acquisition area, guaranteeing the accuracy and integrity of the multispectral data.

[0022] After the drone begins data collection, its GPS positioning information is acquired in real time. The drone's actual flight position is dynamically monitored and compared in real time with the preset data collection position error distance to determine if the drone is within the allowable data collection position error range and if it is collecting data within the planned data collection area. If the drone's actual position exceeds the preset data collection area, i.e., exceeds the allowable data collection position error distance, the module immediately issues a position correction command to control the drone to adjust its flight attitude and correct its flight path, ensuring it quickly returns to the planned data collection area to continue its data collection work. The specific process is as follows: Let the current actual position coordinates of the drone be... The center coordinates of the data acquisition area are The sampling location error distance is The drone's flight speed is ,but: The drone's position offset is calculated using the following formula: The drone's return angle is adjusted using the formula: The return flight time of the drone is calculated using the formula: ,in, For the safety offset threshold, ; Assume the center coordinates of the sampling area corresponding to a certain seed region The range is (1000m, 2000m), and the sampling location error distance is... Drone flight speed Safety offset threshold If the drone's current location If the distance is (1008m, 2006m), then: Because 10m > 5m, a correction command is triggered; Adjust the angle as follows: This means that the drone needs to adjust its flight direction to 216.87° and point it toward the center of the data collection area; The regression time is: That is, the drone travels at a speed of 10 m / s along... Directional flight s, and you can return to the safe range of the collection area, completing the precise return.

[0023] Multispectral data collected before the UAV position correction is saved separately and defined as reference multispectral data.

[0024] The data analysis module is used to analyze the growth status of crops based on the multispectral data and different regional division methods. Specifically, the collected multispectral data is first labeled into the corresponding sub-regions of the same type and the planting sub-region according to the two seed region types divided by the regional planning module. At the same time, the reference multispectral data obtained before the position correction is also labeled into the corresponding sub-regions. Then, for each sub-region of the same type, the historical multispectral data of the region is first obtained. Combined with the currently collected multispectral data and the corresponding reference multispectral data, the overall growth index of the sub-region of the same type is obtained. The overall growth index can objectively and comprehensively reflect the overall growth status of the same type of crops in the sub-region. The higher the overall growth index, the stronger the crop growth, and vice versa, it indicates abnormal growth.

[0025] The process of obtaining the overall growth index of similar sub-regions is as follows: Preprocess the currently collected multispectral data and corresponding reference multispectral data of the similar sub-regions; obtain the normalized vegetation values ​​from the current multispectral data, reference multispectral data, and historical multispectral data of the similar sub-regions respectively; calibrate the collected multispectral data using the normalized vegetation value of the reference multispectral data as a benchmark; obtain the characteristic sequence of the calibrated normalized vegetation values ​​of the similar sub-regions; compare the calibrated current normalized vegetation values ​​with the historical normalized vegetation values; and obtain the crop growth deviation characteristic value at each sampling point within the similar sub-regions. The overall growth index of the same sub-region is obtained by taking an area-weighted average of the growth deviation characteristic values ​​of all points within the same sub-region, using the formula: ; in, This represents the normalized vegetation value from the current multispectral data. To reference the normalized vegetation values ​​from multispectral data, These are normalized vegetation values ​​from historical multispectral data. The area weights are for sub-regions of the same type. This is the position error correction coefficient.

[0026] The Normalized Difference Vegetation Index (NDVI), representing crop growth, was selected. Using reference multispectral data before UAV position correction, the effective multispectral data collected after position correction was numerically calibrated to eliminate the acquisition error caused by UAV position drift. The calibrated current spectral feature data was then normalized and compared with the historical spectral feature data of the same sub-region. The degree of crop growth deviation at each sampling point was calculated. Combined with the spatial weight of each sampling point, the growth deviation values ​​of all points were weighted and fused to finally obtain an overall growth index that can objectively reflect the overall growth level of crops in the same sub-region.

[0027] When a multispectral UAV collects data, if its flight position exceeds a preset error distance, the system will correct the UAV's position. The multispectral data collected before position correction corresponds to the spectral information of crops at incorrect geographical locations and is not the true data of the target sub-region. Although the data collected after position correction matches the spatial position, it is affected by instantaneous position adjustments and brief sensor jitter, resulting in abrupt deviations in the values. Directly using the original collected data after correction will cause the spectral data to become disconnected from the growth status of the target crops due to spatial mismatch and numerical abrupt changes, failing to accurately reflect the growth situation of the sub-region. Therefore, it is necessary to use the reference multispectral data before correction for calibration to correct the error. The difference between the reference multispectral data and the collected data after correction represents the numerical deviation caused by the UAV's position error, which is a quantifiable system random error. The calibration process involves weighting this deviation according to a correction coefficient and superimposing or correcting it onto the original collected data. Mathematically, this is a reverse error compensation, reducing the deviation between the original observation value and the true value. After calibration, the numerical distribution of the data is closer to the true mathematical expectation of the spectral characteristics of the target sub-region, eliminating the numerical disturbance caused by the position error.

[0028] For example, in a specific sub-region of wheat, three sampling points are taken, and the correction coefficient is... The area weights are as follows: The original data for each sampling point are as follows: , Among them, the second and third sampling points did not experience any positional shift during the sampling process due to the multi-sensing drone. ; ; ; but, ; The overall growth index of this sub-region is 1.024.

[0029] After obtaining the overall growth index of all similar sub-regions, the overall deviation value of crop growth in the target area can be obtained. The process of obtaining the deviation value is as follows: obtain the overall growth index of all similar sub-regions within the target area; calculate the average of the overall growth index based on all the overall growth indices; calculate the relative deviation between the overall growth index of each similar sub-region and the average of the overall growth index; perform area-weighted summation on the relative deviations of all similar sub-regions to obtain the overall deviation value of crop growth in the target area, using the formula: Overall growth index average : ; Relative deviation of a single sub-region of the same type : ; Overall deviation value : ; in, For the first The overall growth index of similar sub-regions For the first Area weights for each sub-region of the same type.

[0030] For example, if there are 3 similar sub-regions within a certain area, , .

[0031] Overall growth index average for: ; Relative deviation of a single sub-region of the same type They are respectively: ; ; ; Overall deviation value for: =0.0211; In summary, the overall deviation value of the final target area is 0.0211. The smaller the overall deviation value, the more uniform the growth of each sub-region. Subsequently, based on the division of planting sub-regions, any one of the aforementioned planting sub-regions is selected. The selected planting sub-region is then compared with other planting sub-regions of the same crop to obtain the same type of growth comparison index for the same type of crop. The method for obtaining the same type of growth comparison index for the same type of crop is as follows: Based on the normalized mean vegetation value of the multispectral data and the actual planting density of the planting sub-region, the single-region growth characteristic value of the planting sub-region is calculated, which is the product of the normalized mean vegetation value and the planting density. All planting sub-regions with the same type of crops in the target area are selected, and the planting area data of each planting sub-region is obtained. Calculate the weighted average of the single-region growth characteristic values ​​of all planting sub-regions of the same type of crop, and use this as a unified comparison benchmark value for the growth status of the same type of crop. For each planting sub-region of the same type of crop, compare the single-region growth characteristic value with the unified comparison benchmark value to obtain the single-region comparison coefficient of the planting sub-region. Calculate the average of all single-region comparison coefficients, which is the same-type growth comparison index for the same type of crop, using the formula: ; in, It is a comparative index of the same type of growth of similar crops. This represents the total number of sub-regions within the target area where the same type of crop is grown. For the first Mean normalized vegetation values ​​from multispectral data of each planting sub-region For the first The actual planting density of each planting sub-region For the first The planting area of ​​each planting sub-region For the first Single-region growth characteristic values ​​of each planting sub-region It serves as a unified benchmark for comparing the growth status of crops of the same type.

[0032] For example, for the same crop, there are 3 planting sub-regions. The normalized mean vegetation value, planting density, and planting area of ​​the 3 planting sub-regions are as follows: , , The single-region growth characteristic values ​​are as follows: , .

[0033] The unified comparison benchmark value is: =0.7245; The contrast coefficient for each region is: , , .

[0034] Ultimately, the comparison index for similar growth types is: ≈0.988.

[0035] In summary, the similar growth comparison index of the three planting sub-regions for the same type of crop is: The growth comparison index of the same type is close to 1, indicating that the growth of this type of crop is relatively uniform in all planting sub-regions.

[0036] Overall growth index It is obtained by comparing the normalized vegetation value after calibration in the same sub-region with the vegetation index of the same period in history. It reflects the current overall growth and health of crops in a single sub-region of the same type. An index greater than 1 means that the crop growth is better than the level of the same period in history, equal to 1 means that it is basically the same as the same period in history, and less than 1 means that the growth is weaker than in previous years. It can intuitively reflect the overall growth quality of crops in the region.

[0037] The deviation value is calculated by weighting the relative deviation between the overall growth index of each sub-region and the regional weighted average. It is used to measure the balance of growth status among different sub-regions of the same crop within the target area. The smaller the value, the closer the crop growth of each sub-region is and the more uniform the growth distribution. The larger the value, the more significant the growth difference between regions, and the existence of local imbalances such as excessive or weak growth.

[0038] The same-type growth comparison index is a comprehensive comparison result constructed by combining the normalized vegetation value mean of planting sub-regions, planting density and area weight. It is used to evaluate the overall relative growth level of the same type of crop in different planting sub-regions. The closer the index is to 1, the more consistent the growth of this type of crop is in each planting management unit. A value significantly greater than 1 indicates that the overall growth level is generally better than the average benchmark of the same type. A value significantly less than 1 indicates that the overall growth is generally lower than the average level of the same type.

[0039] The monitoring report module is used to generate corresponding crop growth status monitoring reports based on the growth status analysis results. Specifically, it constructs a basic data pool for the report based on basic information such as the overall growth index, deviation value, comparison index of the same type of growth, multispectral raw acquisition data, reference calibration data, various sub-region division information, crop planting type, planting density, planting area, and historical monitoring data of the same period.

[0040] After completing the basic data integration, preset the thresholds for the overall growth index, deviation value, and comparison index of the same type of growth. Among them, the overall growth index threshold is: This indicates excellent crop growth, with robust development significantly exceeding historical levels for the same period. This indicates that the plant is growing well and its condition is better than in previous years. The growth is normal, basically the same as in the same period of history, 0.85≤ A value <0.95 indicates weak growth, with performance slightly worse than historical averages for the same period. A value <0.85 indicates abnormal growth, significant stunted growth, and stress or management problems. Based on multiple thresholds, crop growth is classified into excellent growth, normal growth, weak growth, and abnormal growth. This helps determine whether the current crop growth in the same sub-region is significantly improved, basically the same, or significantly insufficient compared to the same period in history. Furthermore, by combining the changes in normalized vegetation values ​​before and after calibration, the influence of UAV data collection errors on the indicator results is analyzed to ensure that the evaluation conclusions are not affected by data bias.

[0041] Deviation threshold: This indicates highly balanced growth, with each sub-region exhibiting essentially the same growth pattern. This indicates relatively even growth, with only slight differences. This indicates a slight imbalance, with differences in crop growth observed in certain plots. This indicates a moderate imbalance, with significant differences in growth between regions. This indicates a severe imbalance and significant regional growth differentiation, requiring key management. Based on multiple thresholds, it distinguishes between balanced, relatively balanced, slightly unbalanced, and significantly unbalanced growth levels, and identifies whether there are any local plots with abnormally prominent or severely lagging growth. It also associates the spatial location information of the corresponding sub-regions to provide a positioning basis for agricultural management.

[0042] Similar growth comparison index threshold: This indicates that the overall growth is excellent, generally better than the average level of similar types. This indicates that the overall growth is good, slightly above the average level of similar types. This indicates that the overall growth is normal and basically consistent with the average level of similar plants. This indicates that the overall growth is weak, generally slightly below the average level of similar plants. This indicates that the overall growth is poor, significantly lower than the average level of the same type. Based on multiple thresholds, the overall relative growth level of the same crop in different planting sub-regions is judged, and evaluation results such as overall better than the average level, basically the same, and overall weak are distinguished. At the same time, the differences in planting density are combined to analyze the differences in growth that may be caused by factors such as management measures, water and fertilizer conditions, and soil environment.

[0043] After completing the graded evaluation and preliminary analysis of the causes of all indicators, the report is structured according to the pre-set standardized report structure, which includes an overview of the target area, data collection instructions, core growth indicator analysis, regional growth balance evaluation, a summary of the growth of similar crops, abnormal area marking and management suggestions, etc. The indicator analysis section presents the specific index values, trends and spatial distribution characteristics of each sub-region and planting sub-region. The balance evaluation section focuses on explaining the regional growth differences reflected by the deviation values. Finally, a complete crop growth status monitoring report is formed that can be directly used for agricultural management decisions, planting effect evaluation and precision operation guidance.

[0044] The above description is merely an example and illustration of the concept of this application. Those skilled in the art can make various modifications or additions to the specific embodiments described or use similar methods to replace them, as long as they do not deviate from the inventive concept or exceed the scope defined in the claims, they should all fall within the protection scope of this application.

Claims

1. A crop growth status monitoring system based on multispectral remote sensing, characterized in that, Includes the following modules: The regional planning module divides the target area into sub-regions according to different regional division methods based on the types of crops planted within the target area. The data acquisition module uses a multispectral drone to perform low-altitude scanning of crops and acquire multispectral data of the crops. The data analysis module analyzes the growth status of crops based on the multispectral data of the crops and different regional division methods; The monitoring report module generates corresponding crop growth status monitoring reports based on the growth status analysis results.

2. The crop growth status monitoring system based on multispectral remote sensing according to claim 1, characterized in that, The work content of the regional planning module is as follows: Obtain the types of plants within the target area; The target region is divided into sub-regions according to different partitioning methods, including: Divide the same type of crops into one region, divide the target region into regions, and define the divided regions as sub-regions of the same type; The target area is divided according to the preset planting area range, and the divided areas are defined as planting sub-regions.

3. The crop growth status monitoring system based on multispectral remote sensing according to claim 1, characterized in that, The data acquisition module performs the following functions: Based on the divided sub-regions of the same type and the planting sub-regions, a multispectral data acquisition path is planned for the multispectral UAV; Based on the sub-region ranges of the divided similar sub-regions and the planting sub-regions, the data acquisition area of ​​the multispectral UAV is defined; The acquisition position error distance of the multispectral UAV is obtained based on the set data acquisition area and sub-area range; The data acquisition path for the multispectral UAV is preset, the position of the multispectral UAV during data acquisition is obtained in real time, and it is determined whether the multispectral UAV is within the allowable acquisition position error distance. If the distance of the multispectral UAV exceeds the acquisition position error distance, the position of the multispectral UAV will be corrected, and the multispectral data before correction will be used as the reference multispectral data.

4. The crop growth status monitoring system based on multispectral remote sensing according to claim 1, characterized in that, The data analysis module performs the following tasks: The collected multispectral data are divided into different regions and labeled in the corresponding sub-regions of the same type and the planting sub-regions, and the reference multispectral data are also labeled accordingly. Obtain historical multispectral data of the same type of sub-region, and obtain the overall growth index of the same type of sub-region based on the historical multispectral data of the same type of sub-region and the currently collected multispectral data; Based on the division of similar sub-regions, the overall growth indices of multiple similar sub-regions are compared to obtain the deviation value of the target region; Based on the planting sub-region division, any one of the planting sub-regions is selected, and the selected planting sub-region is compared with other planting sub-regions of the same crop to obtain the same type of growth comparison index of the same type of crop.

5. The crop growth status monitoring system based on multispectral remote sensing according to claim 4, characterized in that, The process for obtaining the overall growth index of the similar sub-regions is as follows: Preprocess the currently acquired multispectral data and corresponding reference multispectral data of the same sub-region; Normalized vegetation values ​​are obtained from the current multispectral data, reference multispectral data, and historical multispectral data of the same type of sub-region, respectively. Using the normalized vegetation value of the reference multispectral data as a benchmark, the collected multispectral data is calibrated to obtain the normalized vegetation value feature sequence of the same sub-region after calibration. The calibrated current normalized vegetation value is compared with the historical normalized vegetation value to obtain the crop growth deviation characteristic value of each sampling point in the same sub-region. The overall growth index of the same sub-region is obtained by averaging the growth deviation characteristic values ​​of all points within the same sub-region by area weighting.

6. The crop growth status monitoring system based on multispectral remote sensing according to claim 5, characterized in that, The process for obtaining the deviation value of the target area is as follows: Obtain the overall growth index of all similar sub-regions within the target area; The average value of the overall growth index is calculated based on all overall growth indices. Calculate the relative deviation between the overall growth index and the average value of the overall growth index for each of the aforementioned sub-regions of the same type; The relative deviations of all similar sub-regions are summed by area weighting to obtain the overall deviation value of crop growth in the target region.

7. The crop growth status monitoring system based on multispectral remote sensing according to claim 6, characterized in that, The method for obtaining the comparative growth index of the same type of crops is as follows: Based on the normalized mean vegetation value of the multispectral data and the actual planting density of the planting sub-region, the single-region growth characteristic value of the planting sub-region is calculated, which is the product of the normalized mean vegetation value and the planting density. Filter out all planting sub-regions within the target area that grow the same type of crop, and obtain the planting area data of each planting sub-region; Calculate the weighted average of the single-region growth characteristic values ​​of all planting sub-regions of the same type of crops, and use it as a unified comparison benchmark value for the growth status of the same type of crops; For each planting sub-region of the same type of crop, the growth characteristic value of the single region is compared with the unified comparison benchmark value to obtain the single region comparison coefficient of the planting sub-region; The average value of the comparison coefficients of all single regions is calculated, which is the growth comparison index of the same type of crops.

8. The crop growth status monitoring system based on multispectral remote sensing according to claim 1, characterized in that, The monitoring report module performs the following functions: A basic data pool for the report is established based on the overall growth index, deviation value, comparison index of similar growth, as well as multispectral raw data, calibration data and basic information of the target area; The overall growth index, deviation value, and growth ratio of the same type are compared with the preset evaluation thresholds of the index. A standardized monitoring report is generated based on the comparison results.

Images