Forest pest monitoring method and system based on remote sensing technology
Through remote sensing technology, the overlay and grid division of forest pest distribution data is carried out, and combined with the monitoring of drone remote sensing devices, the problems of insufficient forest pest monitoring accuracy and low resource utilization are solved, and more accurate pest monitoring and resources are achieved optimization.
Patent Information
- Application Number
- CN202410465101.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-18
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-04-18
AI Technical Summary
The existing forest pest monitoring technology has problems such as insufficient monitoring accuracy and low resource utilization, and it is impossible to finely divide forest areas, resulting in inaccurate pest monitoring results and unreasonable resource allocation.
The forest pest monitoring method based on remote sensing technology is adopted to obtain historical pest distribution data of the target forest through interactive access, superimpose scatter plots, divide grid fields, and monitor and constrained configuration based on the collection of drone remote sensing devices to optimize resource configuration and Improve monitoring accuracy.
The accuracy of forest pest monitoring and resource allocation efficiency are improved, and the accurate reflection of pest distribution and reasonable resource allocation are ensured.
Smart Images

Figure CN118279744B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to forestry science-related fields, and in particular to a forest pest monitoring method and system based on remote sensing technology. Background Art
[0002] Forest pest and disease monitoring is to conduct regular and systematic observation and investigation of pests and diseases in the forest to timely discover and prevent their occurrence. Pest and disease monitoring is very necessary because pests and diseases can threaten forest health, leading to tree death, ecological balance destruction and other problems. In traditional methods, pest and disease monitoring usually relies on manual inspections and ground observations. Since it is impossible to make fine divisions of forest areas, the monitoring results of pests and diseases are not accurate enough, and it is impossible to reasonably allocate monitoring resources according to the distribution of pests and diseases, resulting in waste of resources or insufficient monitoring in certain areas.
[0003] Among the current related technologies, forest pest and disease monitoring has technical problems such as insufficient monitoring accuracy and low resource utilization. Summary of the invention
[0004] This application provides a forest pest and disease monitoring method and system based on remote sensing technology. It adopts technical means such as dividing the target forest into multiple grid areas, marking the pest and disease degree of each grid area, and configuring monitoring constraints on a collection of unmanned aerial vehicle remote sensing devices, thereby achieving the technical effect of improving monitoring accuracy and optimizing resource allocation.
[0005] This application provides a forest pest monitoring method based on remote sensing technology, including:
[0006] Interactively obtain P historical pest distribution data of the target forest within the historical window, wherein the P historical pest distribution data include P historical pest distribution scatter plots, each of which has a plurality of scattered points, and each of the plurality of scattered points has a plurality of distribution position identifiers and a plurality of pest severity identifiers;
[0007] Superimposing multiple scattered points in the P historical pest distribution scatter plots according to the same coordinate system to obtain a mixed historical pest distribution scatter plot, wherein the mixed historical pest distribution scatter plot has multiple mixed scattered points, and the multiple mixed scattered points have multiple mixed distribution position identifiers and multiple mixed pest severity identifiers;
[0008] Divide the mixed historical pest distribution scatter diagram into grid areas according to the multiple mixed distribution position identifiers and the multiple mixed pest and disease degree identifiers of the multiple mixed scattered points to obtain K grid areas, wherein the K grid areas have K area pest and disease degree identifiers;
[0009] Based on the K grid areas and the K area pest and disease degree identifiers, a monitoring constraint configuration is performed on the UAV remote sensing device set to obtain a remote sensing monitoring control scheme, wherein the UAV remote sensing device set includes a first UAV remote sensing device equipped with a hyperspectrometer and a second UAV remote sensing device equipped with a multispectrometer;
[0010] The UAV remote sensing device assembly performs pest and disease monitoring on the target forest according to the remote sensing monitoring and control scheme.
[0011] In a possible implementation, the mixed historical pest distribution scatter diagram is divided into grid areas according to the multiple mixed distribution position identifiers and the multiple mixed pest severity identifiers of the multiple mixed scattered points to obtain K grid areas, and the following processing is performed:
[0012] Using the multiple mixed pest and disease severity identifiers as the mountain heights of the multiple mixed distribution locations, performing mountain simulation on the mixed historical pest and disease distribution scatter diagram to obtain a simulated mountain;
[0013] Taking the mixed distribution position corresponding to the minimum mountain height as the water injection starting point, injecting water into the simulated mountain, calculating the mountain height difference between the first mixed distribution position submerged after the water level rises and the water injection starting point, judging whether the mountain height difference meets the preset height difference threshold, and if so, generating a first dividing ridge line at the first mixed distribution position submerged after the water level rises, wherein the first dividing ridge line rises as the water level rises;
[0014] If not, continue to inject water into the simulated mountain until the water surface covers the mixed distribution position corresponding to the maximum mountain height, and divide the mixed historical pest distribution scatter diagram into initial grid areas according to multiple segmentation ridge lines on the water surface to obtain multiple initial grid areas;
[0015] A fusion analysis is performed according to the area sizes of the multiple initial grid areas to obtain the K grid areas.
[0016] In a possible implementation, a fusion analysis is performed according to the area sizes of the multiple initial grid areas to obtain the K grid areas, and the following processing is performed:
[0017] Extracting the coverage area interval of the set of UAV remote sensing devices;
[0018] Determine whether the areas of the multiple initial grid areas meet the minimum value of the coverage area interval, and if not, add them into the initial grid area to be fused;
[0019] According to the positional relationship between the multiple initial grid areas, the initial grid areas to be fused are subjected to nearest neighbor fusion to obtain the K grid areas.
[0020] In a possible implementation, the following processing is performed:
[0021] Traversing multiple mixed pest and disease identifications corresponding to multiple mixed scattered points in the K grid areas to perform fluctuation analysis to obtain K fluctuation factors;
[0022] When the K fluctuation factors are less than the preset fluctuation factor threshold, the average of the multiple mixed pest and disease identifications corresponding to the multiple mixed scattered points in the K grid areas is used as the pest and disease degree identification of the K areas;
[0023] When the K fluctuation factors are greater than or equal to the preset fluctuation factor threshold, the mixed pest and disease identifications whose number is in the top m among the multiple mixed pest and disease identifications corresponding to the multiple mixed scattered points in the K grid areas are averaged, and the calculation result is used as the pest and disease degree identification of the K areas.
[0024] In a possible implementation, based on the K grid areas and the K area pest and disease degree identifiers, a monitoring constraint configuration is performed on the UAV remote sensing device set to obtain a remote sensing monitoring control scheme, and the following processing is performed:
[0025] According to the preset pest and disease degree reference value, the pest and disease degree identifications of the K fields are classified into two categories to obtain a first grid field set and a second grid field set, wherein the preset pest and disease degree reference value is the median of the pest and disease degree identifications of the K fields;
[0026] Using the first UAV remote sensing device and the second UAV remote sensing device to perform remote sensing monitoring on the first grid area set and the second grid area set according to preset flight rules, respectively, to obtain a first time window and a second time window;
[0027] The first time window and the second time window are superimposed to obtain an initial time window.
[0028] In a possible implementation, the following processing is performed:
[0029] Performing multiple bidirectional adjustments on the preset pest and disease degree reference value according to a preset step length to obtain multiple adjusted pest and disease degree reference values, wherein the preset step length is a preset pest and disease degree mark size for a single adjustment;
[0030] Dividing the K grid areas multiple times based on the multiple adjusted pest and disease severity reference values to obtain multiple division schemes;
[0031] Counting multiple time windows of the multiple partitioning schemes;
[0032] The division scheme corresponding to the minimum value in the multiple time windows is used as the remote sensing monitoring control scheme.
[0033] In a possible implementation, the first UAV remote sensing device and the second UAV remote sensing device are used to perform remote sensing monitoring on the first grid area set and the second grid area set according to preset flight rules, and a first time window and a second time window are obtained, and the following processing is performed:
[0034] According to a preset flight rule, a first monitoring path and a second monitoring path are generated according to the first grid area set and the second grid area set respectively, wherein the preset flight rule is to reach the end monitoring point in a straight line round trip from the starting monitoring point;
[0035] Extracting a first flight speed and a second flight speed of the first UAV remote sensing device and the second UAV remote sensing device;
[0036] Dividing the first monitoring path by the first flight speed to generate the first time window;
[0037] The second monitoring path is multiplied by the second flight speed to generate the second time window.
[0038] This application also provides a forest pest monitoring system based on remote sensing technology, including:
[0039] A historical pest distribution data acquisition module, wherein the historical pest distribution data acquisition module is used to interactively acquire P historical pest distribution data of the target forest within a historical window, wherein the P historical pest distribution data include P historical pest distribution scatter plots, each of which has a plurality of scatter points, and each of the plurality of scatter points has a plurality of distribution position identifiers and a plurality of pest severity identifiers;
[0040] A mixed historical pest distribution scatter plot acquisition module, the mixed historical pest distribution scatter plot acquisition module is used to superimpose multiple scattered points in the P historical pest distribution scatter plots according to the same coordinate system to obtain a mixed historical pest distribution scatter plot, wherein the mixed historical pest distribution scatter plot has multiple mixed scattered points, and the multiple mixed scattered points have multiple mixed distribution position identifiers and multiple mixed pest degree identifiers;
[0041] A grid domain division module, the grid domain division module is used to divide the mixed historical pest distribution scatter diagram into grid domains according to the multiple mixed distribution position identifiers and the multiple mixed pest and disease degree identifiers of the multiple mixed scattered points, to obtain K grid domains, wherein the K grid domains have K domain pest and disease degree identifiers;
[0042] A remote sensing monitoring and control scheme acquisition module, the remote sensing monitoring and control scheme acquisition module is used to perform monitoring constraint configuration on the UAV remote sensing device set based on the K grid areas and the K area pest and disease degree identifiers to obtain a remote sensing monitoring and control scheme, wherein the UAV remote sensing device set includes a first UAV remote sensing device equipped with a hyperspectrometer and a second UAV remote sensing device equipped with a multi-spectrometer;
[0043] A pest monitoring module is used by the UAV remote sensing device assembly to perform pest monitoring on the target forest according to the remote sensing monitoring control scheme.
[0044] It is intended to acquire P historical pest distribution data of the target forest within the historical window through the interactive acquisition of the forest pest monitoring method and system based on remote sensing technology proposed in the present application, wherein the P historical pest distribution data include P historical pest distribution scatter plots, each of which has multiple scattered points, each of which has multiple distribution position identifiers and multiple pest severity identifiers, and then superimpose the multiple scattered points in the P historical pest distribution scatter plots according to the same coordinate system to obtain a mixed historical pest distribution scatter plot, wherein the mixed historical pest distribution scatter plot has multiple mixed scattered points, each of which has multiple mixed distribution position identifiers and multiple mixed pest severity identifiers, and then according to the multiple mixed scattered points in the P historical pest distribution scatter plots, the mixed historical pest distribution scatter plot has multiple mixed scattered points, each of which has multiple mixed distribution position identifiers and multiple mixed pest severity identifiers. The mixed historical pest and disease distribution scatter map is divided into grid areas based on multiple mixed distribution positions of mixed scatter points and multiple mixed pest and disease degree identifiers to obtain K grid areas, wherein the K grid areas have K area pest and disease degree identifiers, and then the UAV remote sensing device set is monitored and constrained based on the K grid areas and the K area pest and disease degree identifiers to obtain a remote sensing monitoring and control scheme, wherein the UAV remote sensing device set includes a first UAV remote sensing device equipped with a hyperspectral instrument and a second UAV remote sensing device equipped with a multi-spectrometer. Finally, the UAV remote sensing device set monitors pests and diseases on the target forest according to the remote sensing monitoring and control scheme, thereby achieving the technical effect of improving monitoring accuracy and optimizing resource allocation. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.
[0046] Figure 1 A schematic diagram of a forest pest monitoring method based on remote sensing technology provided in an embodiment of the present application;
[0047] Figure 2 A schematic diagram of the structure of a forest pest and disease monitoring system based on remote sensing technology provided in an embodiment of the present application.
[0048] Explanation of the accompanying reference numerals: historical pest and disease distribution data acquisition module 10, mixed historical pest and disease distribution scatter plot acquisition module 20, grid area division module 30, remote sensing monitoring and control scheme acquisition module 40, pest and disease monitoring module 50. DETAILED DESCRIPTION
[0049] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.
[0050] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.
[0051] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.
[0052] The present application embodiment provides a forest pest monitoring method based on remote sensing technology, such as Figure 1 As shown, the method includes:
[0053] Step S100, interactively obtain P historical pest distribution data of the target forest within the historical window, wherein the P historical pest distribution data include P historical pest distribution scatter plots, each of the historical pest distribution scatter plots has a plurality of scatter points, and the plurality of scatter points respectively have a plurality of distribution position identifiers and a plurality of pest severity identifiers. Specifically, a historical window is determined, and the historical window is a historical time window representing the time range for collecting pest distribution data on the target forest. After the historical window is determined, interaction is performed with the forest management department, pest monitoring agency or related database, and the pest distribution data of the target forest within the historical window is obtained through a data interaction interface or a data sharing platform, wherein P represents the number of times pest distribution data are collected on the target forest within the historical window, and the P historical pest distribution data are presented in the form of scatter points. P historical pest distribution scatter plots are generated by sorting, and each historical pest distribution scatter plot contains multiple scatter points, and each scatter point has a distribution position identifier and a pest severity identifier, wherein the distribution position identifier is used to identify the specific position of each scatter point in the target forest, which can be represented by latitude and longitude, coordinate system, etc.; the pest severity identifier is used to represent the degree of pests and diseases in the area represented by each scatter point, which can be measured by indicators such as the frequency, type, and severity of pests and diseases.
[0054] Step S200, superimposing multiple scatter points in the P historical pest and disease distribution scatter plots according to the same coordinate system to obtain a mixed historical pest and disease distribution scatter plot, wherein the mixed historical pest and disease distribution scatter plot has multiple mixed scatter points, and the multiple mixed scatter points have multiple mixed distribution position identifiers and multiple mixed pest and disease degree identifiers. Specifically, an overlay coordinate system is determined, and the overlay coordinate system is used as the basis for overlaying all historical pest distribution scatter plots. The overlay coordinate system can be a geographic coordinate system, a projection coordinate system, etc. Before overlaying, the data of each historical pest distribution scatter plot is preprocessed, including coordinate conversion, data format unification, etc. Through preprocessing, different historical pest distribution scatter plots are aligned in the same coordinate system, and the preprocessed P historical pest distribution scatter plots are overlaid according to the overlay coordinate system. After the overlay is completed, a mixed historical pest distribution scatter plot containing multiple mixed scatter points is obtained. For each mixed scatter point, a mixed distribution position identifier and a mixed pest degree identifier are assigned. The mixed distribution position identifier is determined based on the coordinate position after overlay, and the mixed pest degree identifier is obtained by statistical analysis based on the pest degree identifiers of the overlaid scatter points. For example, it can be determined by calculating the average value, the maximum value or the weighted average value.
[0055] Step S300, dividing the mixed historical pest distribution scatter diagram into grid areas according to the multiple mixed distribution position identifiers and the multiple mixed pest and disease degree identifiers of the multiple mixed scatter points, to obtain K grid areas, wherein the K grid areas have K area pest and disease degree identifiers. Specifically, based on the mixed distribution position identification and mixed pest and disease degree identification of the mixed scattered points, a grid domain division standard is formulated. For example, the division standard can be based on the size and shape of the grid and the threshold value of the pest and disease degree in the grid. According to the determined division standard, the mixed historical pest and disease distribution scatter map is divided into grid domains. In the division process, it is ensured that the mixed scattered points in each grid domain have a certain similarity or continuity in distribution position and pest and disease degree. For each divided grid domain, a domain pest and disease degree identification is calculated and assigned according to the pest and disease degree identification of the mixed scattered points inside it. The domain pest and disease degree identification can be the average, maximum, minimum or weighted average of the pest and disease degrees of all mixed scattered points in the grid domain. After the above steps, K grid domains are obtained, and each grid domain has a corresponding pest and disease degree identification.
[0056] In a possible implementation, step S300 further includes step S310, using the multiple mixed pest and disease degree identifiers as the mountain heights of the multiple mixed distribution positions, performing mountain simulation on the mixed historical pest and disease distribution scatter plot to obtain a simulated mountain. Specifically, the mixed pest and disease degree identifier of each mixed scattered point is used as the height value in the simulated mountain. The higher the mixed pest and disease degree, the larger the corresponding height value. Based on the converted height value, a three-dimensional simulated mountain model is constructed, in which the height of each point is determined by its corresponding mixed pest and disease degree. Step S320, using the mixed distribution position corresponding to the minimum mountain height as the water injection starting point, injecting water into the simulated mountain, calculating the mountain height difference between the first mixed distribution position submerged after the water level rises and the water injection starting point, and judging whether the mountain height difference meets the preset height difference threshold. If so, generating a first dividing ridge line at the first mixed distribution position submerged after the water level rises, wherein the first dividing ridge line rises as the water level rises. Specifically, find the point with the minimum height (i.e., mixed pest and disease degree) in the simulated mountain as the starting point of water injection, start from the starting point of water injection, simulate the process of injecting water into the mountain, as the water level rises, you will encounter terrains of different heights, when the water level rises and submerges the first mixed distribution position, calculate the difference in mountain height between this position and the starting point of water injection, if the calculated mountain height difference meets the preset height difference threshold, it means that the change in the degree of pest and disease in this area has reached a certain degree, and it is necessary to generate a split ridge line here, and generate the first split ridge line at the position that meets the height difference threshold. Step S330, if not, continue to inject water into the simulated mountain until the water surface submerges the mixed distribution position corresponding to the maximum mountain height, and divide the mixed historical pest and disease distribution scatter diagram into initial grid areas according to the multiple split ridge lines on the water surface, and obtain multiple initial grid areas. Specifically, if the calculated mountain height difference does not meet the preset height difference threshold, it means that the pest degree in the current area has changed little and is not enough to form a segmentation ridge line. At this time, continue to inject water into the simulated mountain. As the water level continues to rise, segmentation ridge lines will be generated at multiple mixed distribution positions. When the water surface finally passes the highest point of the simulated mountain (i.e., the position with the largest mixed pest degree), stop injecting water. According to the multiple segmentation ridge lines formed on the water surface, the mixed historical pest distribution scatter plot is initially divided into grid areas to obtain multiple initial grid areas. Step S340, according to the area size of the multiple initial grid areas, a fusion analysis is performed to obtain the K grid areas. Specifically, the area, shape, pest degree distribution and other factors of the initial grid area are analyzed. According to the analysis results, the adjacent initial grid areas with similar pest degree distribution are fused to form the final K grid areas. By fusion analysis of the initial grid areas, overly fragmented or irregular grid areas are eliminated, making the final grid area more reasonable and scientific.This implementation method comprehensively considers the spatial distribution and changes of mixed pest and disease severity through a terrain analysis method that simulates water injection. Compared with simple grid division or distance-based division methods, this method is more flexible and adaptable, and can more accurately reflect the actual distribution of pests and diseases in the forest, thereby facilitating the formulation of targeted UAV remote sensing monitoring strategies, achieving the technical effect of providing more accurate data support for the formulation of remote sensing monitoring strategies.
[0057] In a possible implementation, step S340 further includes step S341, extracting the coverage area interval of the drone remote sensing device set. Specifically, the technical parameters of each drone in the drone remote sensing device set, including the maximum flight altitude, camera resolution, lens angle, etc., are collected, and based on the technical parameters of the drone, the ground area that each drone can cover in a flight mission is calculated, and the coverage area of all drones is combined to determine a coverage area interval, which represents the minimum and maximum area that the drone remote sensing device set can monitor. Step S342, judging whether the area of the multiple initial grid fields meets the minimum value of the coverage area interval, if not, adding them to the initial grid field to be fused. Specifically, the area of each initial grid field is compared with the minimum value of the coverage area interval determined in step S341. If the area of a certain initial grid field is less than the minimum value of the coverage area interval, it means that the initial grid field is too small and is not suitable as a monitoring unit alone. At this time, it is added to the list of initial grid fields to be fused. Step S343, according to the positional relationship between the multiple initial grid areas, the initial grid areas to be fused are subjected to nearest neighbor fusion to obtain the K grid areas. Specifically, according to the positional relationship between the initial grid areas, the spatial distance between the initial grid areas is calculated to determine which initial grid areas are adjacent. For the initial grid areas to be fused, they are merged with the initial grid areas of their neighbors according to the similarity of the mixed pest and disease degree, the continuity of the geographical location and other factors. Through continuous nearest neighbor fusion operations, K grid areas are finally obtained. Through the nearest neighbor fusion operation, the initial grid areas that are too small are eliminated to form grid areas with moderate area and reasonable shape. This implementation method ensures the rationality and effectiveness of the final grid area by screening and merging the initial grid areas according to the actual coverage capability of the UAV remote sensing device, avoids the waste of resources caused by monitoring too small grid areas, and achieves the technical effect of reducing unnecessary flight missions and improving the efficiency of UAV remote sensing monitoring.
[0058] In a possible implementation, step S300 further includes step S350, traversing multiple mixed pest and disease identifications corresponding to multiple mixed scattered points in the K grid areas for fluctuation analysis to obtain K fluctuation factors. Specifically, for each grid area, traverse all the mixed scattered points therein, which represent the pest and disease conditions at different positions in the grid area, extract the corresponding mixed pest and disease identification from each mixed scattered point, and the mixed pest and disease identification reflects the severity or type of the pest and disease. By calculating the standard deviation, coefficient of variation or other relevant statistical indicators, the mixed pest and disease identification in each grid area is subjected to fluctuation analysis, and the fluctuation analysis is performed to measure the discrete degree or variation range of the mixed pest and disease identification in the grid area. According to the result of the fluctuation analysis, a fluctuation factor is calculated for each grid area, and the fluctuation factor reflects the fluctuation degree of the mixed pest and disease identification in the grid area. If the fluctuation factor is small, it means that the mixed pest and disease identification in the grid area is relatively stable and the pest and disease conditions are relatively consistent; if the fluctuation factor is large, it means that there are large differences in the mixed pest and disease identification in the grid area, and the pest and disease conditions are relatively complex. Step S360, when the K fluctuation factors are less than the preset fluctuation factor threshold, the mean of the multiple mixed pest and disease identifications corresponding to the multiple mixed scattered points in the K grid areas is used as the pest and disease degree identification of the K areas. Specifically, check whether the fluctuation factor of the current grid area is less than the preset fluctuation factor threshold. If the fluctuation factor is less than the preset fluctuation factor threshold, it means that the mixed pest and disease identification in the current grid area is relatively stable. At this time, the mean of the mixed pest and disease identifications corresponding to all mixed scattered points in the current grid area is calculated, and this mean is used as the area pest and disease degree identification of the grid area. The area pest and disease degree identification represents the average level or overall situation of pests and diseases in the grid area. Step S370, when the K fluctuation factors are greater than or equal to the preset fluctuation factor threshold, the mixed pest and disease identifications whose number is in the first m positions among the multiple mixed pest and disease identifications corresponding to the multiple mixed scattered points in the K grid areas are averaged, and the calculation result is used as the pest and disease degree identification of the K areas. Specifically, check whether the fluctuation factor of the current grid area is greater than or equal to the preset fluctuation factor threshold. If the fluctuation factor is greater than or equal to the preset fluctuation factor threshold, it means that there are large differences in the mixed pest and disease identification in the current grid area. At this time, select the mixed scattered points whose mixed pest and disease identification numbers are in the top m in the current grid area, calculate the mean of these m mixed pest and disease identifications, and use the mean calculation result as the field pest and disease degree identification of the grid area. In the case of a large fluctuation factor, using the mean of the mixed pest and disease identification numbers in the top m as the field pest and disease degree identification better reflects the main characteristics of pests and diseases in the grid area.This implementation method determines the pest and disease severity identification of the field by conducting fluctuation analysis and using different calculation methods according to different fluctuation factors, thereby achieving the technical effect of more accurately reflecting the actual situation of pests and diseases in each grid area.
[0059] Step S400, based on the K grid areas and the pest and disease degree identifications of the K areas, monitoring constraints are configured for the UAV remote sensing device set to obtain a remote sensing monitoring control plan, wherein the UAV remote sensing device set includes a first UAV remote sensing device equipped with a hyperspectral instrument and a second UAV remote sensing device equipped with a multi-spectral instrument. Specifically, according to the geographical location, size, shape and pest and disease degree identification of each grid area, the characteristics of the grid area are analyzed, including the distribution, severity and possible influencing factors of pests and diseases, and based on the characteristics of the grid area, the monitoring requirements of each grid area are determined. For example, for grid areas with more serious pests and diseases, more frequent monitoring and higher-precision data are required; for grid areas with lighter or stable pests and diseases, the monitoring frequency and data accuracy requirements can be relatively low. According to the monitoring needs, the UAV remote sensing device set is configured, wherein the UAV remote sensing device set includes a first UAV remote sensing device equipped with a hyperspectrometer and a second UAV remote sensing device equipped with a multispectrometer. The hyperspectrometer can provide more detailed spectral information for more accurate identification and analysis of pests and diseases; the multispectrometer can provide image data of multiple bands for monitoring vegetation health and growth conditions, etc. According to the monitoring needs of different grid areas, the appropriate UAV remote sensing device is determined for configuration. According to the distribution and size of the grid area, the flight plan of the UAV is formulated, including determining the flight route, flight altitude, flight speed and other parameters to ensure that the UAV can cover all target forest areas that need to be monitored and obtain the required remote sensing data, and set the data processing and analysis process of the remote sensing data, including data preprocessing, feature extraction, classification and recognition and other steps. Based on the results of the above steps, the final remote sensing monitoring and control plan is generated. The remote sensing monitoring and control plan includes the configuration information of the UAV, flight plan, data processing and analysis process and other contents.
[0060] In a possible implementation, step S400 further includes step S410, wherein the K field pest and disease degree identifiers are binary classified according to a preset pest and disease degree reference value to obtain a first grid field set and a second grid field set, wherein the preset pest and disease degree reference value is the median of the K field pest and disease degree identifiers. Specifically, the median of the K field pest and disease degree identifiers is calculated as the preset pest and disease degree reference value, and the preset pest and disease degree reference value reflects the overall level of the field pest and disease degree identifiers. The K field pest and disease degree identifiers are compared with the preset pest and disease degree reference value, and the grid fields whose field pest and disease degree identifiers are greater than or equal to the preset pest and disease degree reference value are classified into the first grid field set, representing areas with relatively serious pests and diseases; the grid fields whose field pest and disease degree identifiers are less than the preset pest and disease degree reference value are classified into the second grid field set, representing areas with relatively light or stable pests and diseases. Through binary classification, the target forest is divided into two sets with different pest and disease severity. Step S420, using the first UAV remote sensing device and the second UAV remote sensing device to perform remote sensing monitoring on the first grid area set and the second grid area set according to the preset flight rules, respectively, to obtain a first time window and a second time window. Specifically, the preset flight rules include parameters such as flight altitude, speed, and route. The first UAV remote sensing device is used to perform simulated remote sensing monitoring on the first grid area set according to the preset flight rules, and the first time window is obtained according to the start time and end time of the remote sensing monitoring. The second UAV remote sensing device is used to perform simulated remote sensing monitoring on the second grid area set according to the preset flight rules, and the second time window is obtained according to the start time and end time of the remote sensing monitoring. Step S430, superimposing the first time window and the second time window to obtain an initial time window. Specifically, the first time window and the second time window are superimposed, that is, the two time periods are merged into one continuous time period to obtain the initial time window. This implementation method classifies grid areas with different degrees of pest and disease severity and uses different types of drone remote sensing devices to monitor them. It can obtain pest and disease information of the target forest more efficiently and accurately, achieving a technical effect of balancing monitoring efficiency and accuracy.
[0061] In a possible implementation, step S400 further includes step S440, performing multiple bidirectional adjustments on the preset pest and disease degree reference value according to a preset step size to obtain multiple adjusted pest and disease degree reference values, wherein the preset step size is a preset pest and disease degree identification size for a single adjustment. Specifically, the preset step size is a fixed value that is increased or decreased each time the preset pest and disease degree reference value is adjusted, and is used to control the amplitude and frequency of the adjustment, starting from the original preset pest and disease degree reference value, and adjusting upward and downward according to the preset step size, respectively, to obtain a series of adjusted pest and disease degree reference values that are higher and lower than the original preset pest and disease degree reference value. Step S450, multiple divisions are performed on the K grid areas based on the multiple adjusted pest and disease degree reference values to obtain multiple division schemes. Specifically, for each adjusted pest and disease degree reference value, it is applied to the division of K grid areas, and the field pest and disease degree identifier is compared with the adjusted pest and disease degree reference value, so as to divide the grid area into two groups (severe pests and diseases and relatively light pests and diseases). Through the above steps, multiple division schemes based on different adjusted pest and disease degree reference values are obtained. Step S460, multiple time windows of the multiple division schemes are counted. Specifically, for each division scheme, the process of remote sensing monitoring of two groups of grid areas by the drone according to the preset flight rules is simulated, and the total time required to complete each division scheme, that is, the time window, is calculated according to the simulated monitoring process. Step S470, the division scheme corresponding to the minimum value in the multiple time windows is used as the remote sensing monitoring control scheme. Specifically, the time windows corresponding to all division schemes are compared, and the minimum value is found, and the division scheme corresponding to the minimum value of the time window is determined as the final remote sensing monitoring control scheme. This implementation method not only analyzes the impact of the severity of pests and diseases on the monitoring path and time, but also finds a division scheme that can complete the monitoring task in the shortest time by optimizing the preset pest and disease benchmark value, thereby achieving the technical effect of improving the efficiency of UAV remote sensing monitoring.
[0062] In a possible implementation, step S420 further includes step S421, generating a first monitoring path and a second monitoring path according to the first grid area set and the second grid area set respectively according to the preset flight rules, wherein the preset flight rules are to reach the end monitoring point in a straight line round trip from the starting monitoring point. Specifically, based on the geographical distribution of the target forest, the location of the take-off and landing points of the drone, and flight safety, etc., the starting monitoring point and the end monitoring point of the drone are determined, and the first grid area set and the second grid area set are analyzed, including the shape, size, location, and severity of pests and diseases. Starting from the starting monitoring point, according to the distribution of each grid area, the drone is planned to fly straight to each grid area for monitoring, and then fly straight back to the starting point or a nearby point, and the cycle is repeated until all grid areas are covered to generate the first monitoring path and the second monitoring path. Step S422, extracting the first flight speed and the second flight speed of the first drone remote sensing device and the second drone remote sensing device. Specifically, the instructions or technical documents of the first UAV remote sensing device and the second UAV remote sensing device are consulted to obtain the flight speed parameters, and the flight speed of the UAV is selected or adjusted according to the specific requirements of the monitoring task (such as data accuracy, monitoring range, etc.). For example, in areas where higher data accuracy is required, a slower flight speed can be selected; in areas where rapid coverage is required, a faster flight speed can be selected. Step S423, the first monitoring path is divided by the first flight speed to generate the first time window; step S424, the second monitoring path is divided by the second flight speed to generate the second time window. Specifically, according to the first monitoring path generated in step S421, the total length of the first monitoring path is calculated using geographic information system (GIS) software or related tools, and the length of the first monitoring path is divided by the first flight speed of the first UAV remote sensing device to obtain the time required to complete the first monitoring path, which is the first time window. The process of generating the second time window is similar to that of generating the first time window. This implementation method achieves the technical effect of providing reliable data support for subsequent task scheduling and data analysis by accurately calculating and generating the time window for UAV remote sensing monitoring.
[0063] Step S500, the UAV remote sensing device set performs pest and disease monitoring on the target forest according to the remote sensing monitoring and control scheme. Specifically, according to the remote sensing monitoring and control scheme, the UAV is started to fly, and the hyperspectral instrument and multi-spectral instrument carried by the UAV perform remote sensing monitoring of the target forest, obtain real-time data, process and analyze the obtained data, and generate a pest and disease monitoring report. The embodiment of the present application adopts technical means such as dividing the target forest into multiple grid areas, marking the degree of pest and disease in each grid area, and configuring monitoring constraints for the UAV remote sensing device set, so as to achieve the technical effect of improving monitoring accuracy and optimizing resource allocation.
[0064] In the above, refer to Figure 1 The forest pest monitoring method based on remote sensing technology according to an embodiment of the present invention is described in detail. Figure 2 A forest pest monitoring system based on remote sensing technology according to an embodiment of the present invention is described.
[0065] The forest pest monitoring system based on remote sensing technology according to the embodiment of the present invention is used to solve the technical problems of insufficient monitoring accuracy and low resource utilization in the existing forest pest monitoring, so as to achieve the technical effect of improving monitoring accuracy and optimizing resource allocation. The forest pest monitoring system based on remote sensing technology includes: a historical pest distribution data acquisition module 10, a mixed historical pest distribution scatter plot acquisition module 20, a grid domain division module 30, a remote sensing monitoring control scheme acquisition module 40, and a pest monitoring module 50.
[0066] The historical pest distribution data acquisition module 10 is used to interactively acquire P historical pest distribution data of the target forest within the historical window, wherein the P historical pest distribution data include P historical pest distribution scatter plots, each of which has a plurality of scattered points, and each of the plurality of scattered points has a plurality of distribution position identifiers and a plurality of pest severity identifiers;
[0067] The mixed historical pest distribution scatter plot acquisition module 20 is used to superimpose multiple scattered points in the P historical pest distribution scatter plots according to the same coordinate system to obtain a mixed historical pest distribution scatter plot, wherein the mixed historical pest distribution scatter plot has multiple mixed scattered points, and the multiple mixed scattered points have multiple mixed distribution position identifiers and multiple mixed pest degree identifiers;
[0068] The grid domain division module 30 is used to divide the mixed historical pest distribution scatter diagram into grid domains according to the multiple mixed distribution position identifiers and the multiple mixed pest and disease degree identifiers of the multiple mixed scattered points, and obtain K grid domains, wherein the K grid domains have K domain pest and disease degree identifiers;
[0069] The remote sensing monitoring control scheme acquisition module 40 is used to perform monitoring constraint configuration on the UAV remote sensing device set based on the K grid areas and the K area pest and disease degree identifiers to obtain a remote sensing monitoring control scheme, wherein the UAV remote sensing device set includes a first UAV remote sensing device equipped with a hyperspectrometer and a second UAV remote sensing device equipped with a multispectrometer;
[0070] The pest monitoring module 50 is used by the UAV remote sensing device assembly to perform pest monitoring on the target forest according to the remote sensing monitoring control scheme.
[0071] The specific configuration of the grid domain division module 30 will be described in detail below. As described above, the mixed historical pest distribution scatter diagram is grid-divided according to the multiple mixed distribution position identifiers and the multiple mixed pest and disease degree identifiers of the multiple mixed scattered points to obtain K grid domains. The grid domain division module 30 may further include: a mountain simulation unit for performing mountain simulation on the mixed historical pest and disease distribution scatter diagram using the multiple mixed pest and disease degree identifiers as the mountain heights of the multiple mixed distribution positions to obtain a simulated mountain; a first segmentation ridge line generation unit for using the mixed distribution position corresponding to the minimum mountain height as the water injection starting point to inject water into the simulated mountain, and calculating the first mixed distribution position submerged after the water level rises and the The height difference of the mountain at the starting point of water injection is used to determine whether the height difference of the mountain meets the preset height difference threshold. If so, a first dividing ridge line is generated at the first mixed distribution position submerged after the water level rises, wherein the first dividing ridge line rises as the water level rises; the initial grid area division unit is used to, if not, continue to inject water into the simulated mountain until the water surface submerges the mixed distribution position corresponding to the maximum mountain height, and perform initial grid area division on the mixed historical pest and disease distribution scatter diagram according to multiple dividing ridge lines on the water surface to obtain multiple initial grid areas; the fusion analysis unit is used to perform fusion analysis according to the area sizes of the multiple initial grid areas to obtain the K grid areas.
[0072] Among them, a fusion analysis is performed according to the area sizes of the multiple initial grid areas to obtain the K grid areas, and the fusion analysis unit may further include: a coverage area interval extraction subunit is used to extract the coverage area interval of the set of unmanned aerial vehicle remote sensing devices; a judgment subunit is used to judge whether the areas of the multiple initial grid areas meet the minimum value of the coverage area interval, if not, then add them into the initial grid area to be fused; a neighbor fusion subunit is used to perform neighbor fusion on the initial grid area to be fused according to the positional relationship between the multiple initial grid areas to obtain the K grid areas.
[0073] Among them, the grid field division module 30 may further include: a fluctuation analysis unit for traversing the multiple mixed pest and disease identifications corresponding to the multiple mixed scattered points in the K grid fields to perform fluctuation analysis and obtain K fluctuation factors; a mean calculation unit for, when the K fluctuation factors are less than a preset fluctuation factor threshold, using the mean of the multiple mixed pest and disease identifications corresponding to the multiple mixed scattered points in the K grid fields as the K field pest and disease degree identification, and when the K fluctuation factors are greater than or equal to the preset fluctuation factor threshold, performing mean calculation on the mixed pest and disease identifications whose number is in the top m among the multiple mixed pest and disease identifications corresponding to the multiple mixed scattered points in the K grid fields, and using the calculation result as the K field pest and disease degree identification.
[0074] The specific configuration of the remote sensing monitoring and control scheme acquisition module 40 will be described in detail below. As described above, based on the K grid areas and the K area pest and disease degree identifications, the monitoring constraint configuration of the UAV remote sensing device set is performed to obtain the remote sensing monitoring and control scheme. The remote sensing monitoring and control scheme acquisition module 40 may further include: a binary classification unit is used to binary classify the K area pest and disease degree identifications according to a preset pest and disease degree reference value to obtain a first grid area set and a second grid area set, wherein the preset pest and disease degree reference value is the median of the K area pest and disease degree identifications; a remote sensing monitoring unit is used to perform remote sensing monitoring on the first grid area set and the second grid area set using the first UAV remote sensing device and the second UAV remote sensing device respectively according to preset flight rules to obtain a first time window and a second time window; a time window superposition unit is used to superimpose the first time window and the second time window to obtain an initial time window.
[0075] Among them, the remote sensing monitoring and control scheme acquisition module 40 may further include: a bidirectional adjustment unit for performing multiple bidirectional adjustments on the preset pest and disease degree benchmark value according to a preset step size to obtain multiple adjusted pest and disease degree benchmark values, wherein the preset step size is a preset single-adjustment pest and disease degree identification size; a division unit for performing multiple divisions on the K grid areas based on the multiple adjusted pest and disease degree benchmark values to obtain multiple division schemes; a time window statistics unit for counting multiple time windows of the multiple division schemes; and a remote sensing monitoring and control scheme acquisition unit for using the division scheme corresponding to the minimum value in the multiple time windows as the remote sensing monitoring and control scheme.
[0076] Among them, the first grid area set and the second grid area set are remotely sensed and monitored by the first UAV remote sensing device and the second UAV remote sensing device respectively according to the preset flight rules to obtain the first time window and the second time window. The remote sensing monitoring unit may further include: a monitoring path generation subunit is used to generate the first monitoring path and the second monitoring path according to the first grid area set and the second grid area set respectively according to the preset flight rules, wherein the preset flight rules are to reach the ending monitoring point in a straight line from the starting monitoring point; the flight speed extraction subunit is used to extract the first flight speed and the second flight speed of the first UAV remote sensing device and the second UAV remote sensing device; the time window generation subunit is used to compare the first monitoring path with the first flight speed to generate the first time window, and compare the second monitoring path with the second flight speed to generate the second time window.
[0077] The forest pest monitoring system based on remote sensing technology provided by the embodiment of the present invention can execute the forest pest monitoring method based on remote sensing technology provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0078] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.
[0079] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
Claims
1. A forest pest monitoring method based on remote sensing technology, characterized in that: The method comprises: Interactively obtain P historical pest distribution data of the target forest within the historical window, wherein the P historical pest distribution data include P historical pest distribution scatter plots, each of which has a plurality of scattered points, and each of the plurality of scattered points has a plurality of distribution position identifiers and a plurality of pest severity identifiers; Superimposing multiple scattered points in the P historical pest distribution scatter plots according to the same coordinate system to obtain a mixed historical pest distribution scatter plot, wherein the mixed historical pest distribution scatter plot has multiple mixed scattered points, and the multiple mixed scattered points have multiple mixed distribution position identifiers and multiple mixed pest severity identifiers; Divide the mixed historical pest distribution scatter diagram into grid areas according to the multiple mixed distribution position identifiers and the multiple mixed pest and disease degree identifiers of the multiple mixed scattered points to obtain K grid areas, wherein the K grid areas have K area pest and disease degree identifiers; Based on the K grid areas and the K area pest and disease degree identifiers, a monitoring constraint configuration is performed on the UAV remote sensing device set to obtain a remote sensing monitoring control scheme, wherein the UAV remote sensing device set includes a first UAV remote sensing device equipped with a hyperspectrometer and a second UAV remote sensing device equipped with a multispectrometer; The drone remote sensing device assembly performs pest and disease monitoring on the target forest according to the remote sensing monitoring and control scheme; Wherein, based on the K grid areas and the K area pest and disease degree identifications, the remote sensing monitoring control scheme is obtained by performing monitoring constraint configuration on the UAV remote sensing device set, including: According to the preset pest and disease degree reference value, the pest and disease degree identifications of the K fields are classified into two categories to obtain a first grid field set and a second grid field set, wherein the preset pest and disease degree reference value is the median of the pest and disease degree identifications of the K fields; Using the first UAV remote sensing device and the second UAV remote sensing device to perform remote sensing monitoring on the first grid area set and the second grid area set according to preset flight rules, respectively, to obtain a first time window and a second time window; The first time window and the second time window are superimposed to obtain an initial time window.
2. The forest pest monitoring method based on remote sensing technology according to claim 1, characterized in that: The mixed historical pest distribution scatter diagram is divided into grid areas according to the multiple mixed distribution position identifiers and the multiple mixed pest severity identifiers of the multiple mixed scattered points to obtain K grid areas, the method comprising: Using the multiple mixed pest and disease severity identifiers as the mountain heights of the multiple mixed distribution locations, performing mountain simulation on the mixed historical pest and disease distribution scatter diagram to obtain a simulated mountain; Taking the mixed distribution position corresponding to the minimum mountain height as the water injection starting point, injecting water into the simulated mountain, calculating the mountain height difference between the first mixed distribution position submerged after the water level rises and the water injection starting point, judging whether the mountain height difference meets the preset height difference threshold, and if so, generating a first dividing ridge line at the first mixed distribution position submerged after the water level rises, wherein the first dividing ridge line rises as the water level rises; If not, continue to inject water into the simulated mountain until the water surface covers the mixed distribution position corresponding to the maximum mountain height, and divide the mixed historical pest distribution scatter diagram into initial grid areas according to multiple segmentation ridge lines on the water surface to obtain multiple initial grid areas; A fusion analysis is performed according to the area sizes of the multiple initial grid areas to obtain the K grid areas.
3. The forest pest monitoring method based on remote sensing technology as claimed in claim 2, characterized in that: Performing fusion analysis according to the area sizes of the multiple initial grid areas to obtain the K grid areas, the method includes: Extracting the coverage area interval of the set of UAV remote sensing devices; Determine whether the areas of the multiple initial grid areas meet the minimum value of the coverage area interval, and if not, add them into the initial grid area to be fused; According to the positional relationship between the multiple initial grid areas, the initial grid areas to be fused are subjected to nearest neighbor fusion to obtain the K grid areas.
4. The forest pest monitoring method based on remote sensing technology as claimed in claim 3, characterized in that: The method comprises: Traversing multiple mixed pest and disease identifications corresponding to multiple mixed scattered points in the K grid areas to perform fluctuation analysis to obtain K fluctuation factors; When the K fluctuation factors are less than the preset fluctuation factor threshold, the average of the multiple mixed pest and disease identifications corresponding to the multiple mixed scattered points in the K grid areas is used as the pest and disease degree identification of the K areas; When the K fluctuation factors are greater than or equal to the preset fluctuation factor threshold, the mixed pest and disease identifications whose number is in the top m among the multiple mixed pest and disease identifications corresponding to the multiple mixed scattered points in the K grid areas are averaged, and the calculation result is used as the pest and disease degree identification of the K areas.
5. The forest pest monitoring method based on remote sensing technology according to claim 1, characterized in that: The method comprises: Performing multiple bidirectional adjustments on the preset pest and disease degree reference value according to a preset step length to obtain multiple adjusted pest and disease degree reference values, wherein the preset step length is a preset pest and disease degree mark size for a single adjustment; Dividing the K grid areas multiple times based on the multiple adjusted pest and disease severity reference values to obtain multiple division schemes; Counting multiple time windows of the multiple partitioning schemes; The division scheme corresponding to the minimum value in the multiple time windows is used as the remote sensing monitoring control scheme.
6. The forest pest monitoring method based on remote sensing technology according to claim 1, characterized in that: The first unmanned aerial vehicle remote sensing device and the second unmanned aerial vehicle remote sensing device are used to perform remote sensing monitoring on the first grid area set and the second grid area set according to preset flight rules to obtain a first time window and a second time window, and the method includes: According to a preset flight rule, a first monitoring path and a second monitoring path are generated according to the first grid area set and the second grid area set respectively, wherein the preset flight rule is to reach the end monitoring point in a straight line round trip from the starting monitoring point; Extracting a first flight speed and a second flight speed of the first UAV remote sensing device and the second UAV remote sensing device; Dividing the first monitoring path by the first flight speed to generate the first time window; The second monitoring path is multiplied by the second flight speed to generate the second time window.
7. The forest pest monitoring system based on remote sensing technology is characterized by: The system is used to implement the forest pest monitoring method based on remote sensing technology according to any one of claims 1 to 6, and the system comprises: A historical pest distribution data acquisition module, wherein the historical pest distribution data acquisition module is used to interactively acquire P historical pest distribution data of the target forest within a historical window, wherein the P historical pest distribution data include P historical pest distribution scatter plots, each of which has a plurality of scatter points, and each of the plurality of scatter points has a plurality of distribution position identifiers and a plurality of pest severity identifiers; A mixed historical pest distribution scatter plot acquisition module, the mixed historical pest distribution scatter plot acquisition module is used to superimpose multiple scattered points in the P historical pest distribution scatter plots according to the same coordinate system to obtain a mixed historical pest distribution scatter plot, wherein the mixed historical pest distribution scatter plot has multiple mixed scattered points, and the multiple mixed scattered points have multiple mixed distribution position identifiers and multiple mixed pest degree identifiers; A grid domain division module, the grid domain division module is used to divide the mixed historical pest distribution scatter diagram into grid domains according to the multiple mixed distribution position identifiers and the multiple mixed pest and disease degree identifiers of the multiple mixed scattered points, to obtain K grid domains, wherein the K grid domains have K domain pest and disease degree identifiers; A remote sensing monitoring and control scheme acquisition module, the remote sensing monitoring and control scheme acquisition module is used to perform monitoring constraint configuration on the UAV remote sensing device set based on the K grid areas and the K area pest and disease degree identifiers to obtain a remote sensing monitoring and control scheme, wherein the UAV remote sensing device set includes a first UAV remote sensing device equipped with a hyperspectrometer and a second UAV remote sensing device equipped with a multi-spectrometer; A pest monitoring module is used by the UAV remote sensing device assembly to perform pest monitoring on the target forest according to the remote sensing monitoring control scheme.
