A forestry monitoring point data intelligent processing system

Abstract

This invention relates to the field of monitoring data processing technology, and more particularly to an intelligent data processing system for forestry monitoring points, comprising: a monitoring acquisition module for acquiring first monitoring information, second monitoring information, third monitoring information, forest area information, and collection date of a forestry pest monitoring point; a first monitoring module for analyzing a first hazard parameter based on the first monitoring information; a monitoring data construction module for constructing a monitoring grayscale image based on the third monitoring information, the first monitoring information, the forest area information, and the collection date; a second monitoring module for analyzing a second hazard parameter based on the second and third monitoring information; a comprehensive monitoring module for analyzing pest parameters based on the monitoring grayscale image, and also for analyzing pest severity levels based on the pest parameters; and a severity level output module for outputting the pest severity level. This invention achieves intelligent monitoring and processing of monitoring point data.

Description

Technical Field

[0001] This invention relates to the field of monitoring data processing technology, and in particular to an intelligent data processing system for forestry monitoring points. Background Technology

[0002] With the rapid development of IoT, big data, and AI technologies, monitoring data is experiencing explosive growth, placing higher demands on real-time data processing, accurate analysis, and intelligent decision-making. Monitoring data processing technology, through intelligent, networked, and big data methods, enables the rapid processing, effective analysis, and intelligent application of massive amounts of monitoring data, providing a scientific basis for decision-making in environmental protection, resource optimization, and energy management.

[0003] Chinese Patent Publication No. CN113111207A discloses a pest control and detection information system and its implementation method, including a backend server, a user terminal, and an insect-catching device; the user terminal, the backend server, and the insect-catching device are interconnected; wherein, the insect-catching device includes a support column, a solar panel, a first fixing rod, an insect trap, a control device, and a camera. This invention, through the above method and structure, achieves pest monitoring in a given area by matching insect photos sent by the user terminal, insect-catching images obtained by the insect-catching device, and a preset insect information database. This allows ordinary pedestrians or tourists to take photos of pests and upload them. While this invention monitors pests in each area by capturing images of insects caught in each area, it does not achieve comprehensive analysis of data from the collection points, the surrounding environment, and the monitoring area, resulting in low efficiency and inaccurate pest data analysis. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent data processing system for forestry monitoring points to solve at least one of the problems existing in the prior art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A forestry monitoring point data intelligent processing system includes:

[0007] The monitoring and acquisition module is used to acquire the first monitoring information, second monitoring information, third monitoring information, forest area information, and collection date of forest pest monitoring points;

[0008] The first monitoring module is used to analyze the type of monitored object based on the first monitoring image and the first preset monitoring image, and also to analyze the first hazard parameter based on the first monitoring information and the type of monitored object;

[0009] The monitoring data construction module is used to analyze the coordinates of monitoring points based on the third monitoring information, to analyze the quantitative change relationship based on the first and third monitoring information, and to construct a monitoring grayscale image based on the monitoring point coordinates, forest area information, quantitative change relationship and collection date.

[0010] The second monitoring module is used to analyze the second hazard parameter based on the second monitoring information and the third monitoring information;

[0011] The integrated monitoring module is used to analyze pest and disease parameters based on the monitored grayscale images, adjust the analysis process of pest and disease parameters based on the first hazard parameter and the second hazard parameter, and analyze the pest and disease level based on the pest and disease parameters.

[0012] The rating output module is used to output the rating of pests and diseases.

[0013] Furthermore, the first monitoring module includes a pest analysis unit, which is used to calculate a first hazard parameter based on the type and hazard level of the monitored organism using a first hazard parameter analysis formula. The first hazard parameter analysis formula for the pest analysis unit is as follows:

[0014] ,

[0015] Where A(i) represents the first hazard parameter, i represents the monitoring point number, i∈{1,2,3,4,5}, when i=1, it represents the central monitoring point, and when i>1, it represents the non-central monitoring point.

[0016] Furthermore, the monitoring data construction module includes a coordinate analysis unit, which is used to analyze the coordinates of the monitoring points based on the third monitoring information: when 0 ≤ θ(i) < 90, the coordinate analysis unit analyzes the coordinates of the monitoring points and sets x(i) = S(i) × sinθ(i) and y(i) = S(i) × cosθ(i); when 90 ≤ θ(i) < 180, the coordinate analysis unit analyzes the coordinates of the monitoring points and sets x(i) = S(i) × sinθ(i) and y(i) = S(i) × -cosθ(i); when 180 ≤ θ(i) < 270, ... The coordinate analysis unit analyzes the coordinates of the monitoring point and sets x(i) = S(i) × -sinθ(i) and y(i) = S(i) × -cosθ(i). When 270 ≤ θ(i) < 360, the coordinate analysis unit analyzes the coordinates of the monitoring point and sets x(i) = S(i) × -sinθ(i) and y(i) = S(i) × cosθ(i). Wherein, θ(i) represents the relative angle, S(i) represents the relative distance, x(i) represents the abscissa of the monitoring point, y(i) represents the ordinate of the monitoring point, and (x(i), y(i)) represents the trap coordinate point.

[0017] Furthermore, the monitoring data construction module also includes a relationship analysis unit, which is used to calculate the quantitative change relationship based on the number of monitoring targets and third-party monitoring information using a quantitative relationship analysis formula. The quantitative relationship analysis formula for the relationship analysis unit is as follows:

[0018] Q(i) = [N(i) - N(1)] / S(i);

[0019] Where Q(i) represents the quantity change relationship, N(i) represents the number of monitoring targets, and N(1) represents the number of monitoring targets at the central monitoring point.

[0020] Further, the image construction unit uses the coordinates in the monitored grayscale image that have the same horizontal and vertical coordinates as the monitoring point coordinates as the trap coordinates, and uses the coordinates in the monitored grayscale image that are not trap coordinates as the construction coordinates. The grayscale value of the trap coordinates is set to L(x(i),y(i)), and the grayscale value of the construction coordinates is set to L(x,y), where:

[0021] ,

[0022] ,

[0023] Where u represents the grayscale construction parameter, i max This represents the maximum value of the monitoring point number, which is equal to the number of monitoring points. (x,y) represents the coordinates of the constructed coordinate point.

[0024] Furthermore, the monitoring data construction module also includes a tree analysis unit, which adjusts the analysis process of the grayscale values ​​of the constructed coordinate points according to the number of trees: when M(k)≥M(k-1), the tree analysis unit determines that the number of trees is stable and does not adjust the analysis process of the grayscale values ​​of the constructed coordinate points; when M(k)<M(k-1), the tree analysis unit determines that the number of trees has decreased and adjusts the analysis process of the grayscale values ​​of the constructed coordinate points. The adjusted grayscale value of the constructed coordinate points is L1(x,y), and L1(x,y)=L(x,y)×log M(k-1) M(k); where M(k) represents the number of trees in the current analysis period, M(k-1) represents the number of trees in the previous analysis period, and k represents the analysis period number, k∈N. + ;

[0025] The monitoring data construction module also includes a data acquisition and analysis unit, which optimizes the adjustment process of the grayscale values ​​of the constructed coordinate points based on the acquisition date. The optimized grayscale value of the constructed coordinate points is L2(x,y), and L2(x,y) = L1(x,y) × T(i) × i max / ∑T(i), where T(i) represents the number of days between the collection date of each monitoring point in the current analysis period and its previous collection date.

[0026] Furthermore, the second monitoring module compares the second monitoring image with the preset leaf outline and extracts the leaf region based on the comparison result: when Z≥α, the second monitoring module extracts the region corresponding to the preset leaf outline in the second monitoring image as the leaf region; when Z<α, the second monitoring module does not analyze the leaf region; where Z represents the similarity between the second monitoring image and the preset leaf outline, α represents the similarity threshold, and 0.8≤α<1;

[0027] The second monitoring module calculates the average gray value of the leaf area by taking the gray value of the leaf area, which is denoted as R=∑L(X,Y) / NL, where R represents the average gray value of the leaf area, L(X,Y) represents the gray value of the leaf area, (X,Y) represents the pixel coordinates of the leaf area, and NL represents the number of pixels in the leaf area.

[0028] The second monitoring module analyzes the second hazard parameter based on the gray value of the leaf area and the average gray value of the leaf area: when L(X,Y)<R×β, the second monitoring module extracts the currently analyzed pixel as the missing pixel and counts the number of missing pixels as the number of missing pixels; when L(X,Y)≥R×β, the second monitoring module does not analyze the missing pixels.

[0029] The second monitoring module calculates the second hazard parameter based on the number of defects and the number of pixels in the leaf area, setting B=NR / NL;

[0030] Where β represents the defect threshold, B represents the second hazard parameter, and NR represents the number of defects.

[0031] Furthermore, the integrated monitoring module includes a pest and disease analysis unit, which analyzes pest and disease parameters based on the monitored grayscale image. The pest and disease analysis unit counts the number of coordinate points in the monitored grayscale image that satisfy L(x,y)=0 as the number of outliers, and calculates the pest and disease parameters based on the number of outliers using the pest and disease parameter analysis formula. The pest and disease analysis unit includes the following pest and disease parameter analysis formula:

[0032] ,

[0033] Where D represents the pest and disease parameters, N1 represents the number of pixels in the monitored grayscale image, N2 represents the number of outliers, H(i) represents the tree height, and NH represents the number of trees.

[0034] Furthermore, the integrated monitoring module also includes a first hazard analysis unit, which is used to adjust the analysis process of pest and disease parameters according to the first hazard parameter: when A(i)>P(3) / 2, the first hazard analysis unit determines that the first hazard parameter does not meet the threshold, adjusts the analysis process of pest and disease parameters, and the adjusted pest and disease parameter is D1, which is set as D1=D×log A(i) P(3); When A(i)≤P(3) / 2, the first hazard analysis unit determines that the first hazard parameter meets the threshold and does not adjust the analysis process of the pest and disease parameter;

[0035] The integrated monitoring module also includes a second hazard analysis unit, which optimizes the adjustment process of pest and disease parameters based on the second hazard parameter: when B≥b, the second hazard analysis unit determines that the second hazard parameter does not meet the threshold, optimizes the adjustment process of pest and disease parameters, and the optimized pest and disease parameter is D2, which is set as D2=D1×e. B When B < b, the second hazard analysis unit determines that the second hazard parameter meets the threshold and does not optimize the adjustment process of the pest and disease parameters.

[0036] Where b represents the leaf erosion threshold.

[0037] Furthermore, the integrated monitoring module also includes a level analysis unit for analyzing the level of pests and diseases based on pest and disease parameters: when D≤d1, the level analysis unit determines the level of pests and diseases to be normal; when d1<D≤d2, the level analysis unit determines the level of pests and diseases to be low risk; when D>d2, the level analysis unit determines the level of pests and diseases to be high risk; where d1 represents the first pest and disease level threshold and d2 represents the second pest and disease level threshold.

[0038] The beneficial effects of this invention are as follows: By acquiring the first monitoring information, second monitoring information, third monitoring information, forest area information, and collection date through the monitoring acquisition module, the accuracy of information acquisition is improved, thereby increasing the system's analysis efficiency and accuracy of the first monitoring information. Through the analysis of the first monitoring information by the first monitoring module, a first hazard parameter is derived, which represents the hazard level relationship of the monitored objects at each monitoring point, thus improving the system's analysis efficiency and accuracy of the first monitoring information. Through the analysis of the third monitoring information, first monitoring information, forest area information, and collection date by the monitoring data construction module, a monitoring grayscale image is constructed, establishing the relationship between each piece of information and converting it into an image format, making data change analysis more intuitive and ensuring the integrity of the system's data analysis, thereby improving the system's analysis of the first monitoring information. To improve the efficiency and accuracy of the analysis of the first monitoring information, the second monitoring module analyzes the second and third monitoring information to determine the second hazard parameter, which represents the degree of leaf damage caused by pests in the vicinity of the monitoring point. This increases the diversity of system analysis, thereby improving the efficiency and accuracy of the system's analysis of the first monitoring information. The comprehensive monitoring module analyzes the monitoring grayscale image, the first hazard parameter, and the second hazard parameter to determine the pest and disease parameters, which represent the pest and disease situation in the forest area. This allows for the determination of the pest and disease level, further improving the efficiency and accuracy of the system's analysis of the first monitoring information. Finally, the level output module outputs the pest and disease level, improving the accuracy of the system's output, thus enhancing the efficiency and accuracy of the system's analysis of the first monitoring information. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention, 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 the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a schematic diagram of the intelligent data processing system for forestry monitoring points in this embodiment.

[0041] Figure 2 This is a schematic diagram of the structure of the first monitoring module in this embodiment.

[0042] Figure 3 This is a schematic diagram of the monitoring data construction module in this embodiment.

[0043] Figure 4This is a schematic diagram of the integrated monitoring module in this embodiment. Detailed Implementation

[0044] To more clearly illustrate the present invention, the following description, in conjunction with preferred embodiments and accompanying drawings, further explains the invention. Similar components in the drawings are indicated by the same reference numerals. Those skilled in the art should understand that the specific description below is illustrative rather than restrictive and should not be construed as limiting the scope of protection of the present invention.

[0045] It should be noted that although the terms first, second, third, etc., may be used in the embodiments of this application for description, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of this application, first can also be referred to as second, and similarly, second can also be referred to as first.

[0046] Please see Figure 1 As shown, this is a forestry monitoring point data intelligent processing system according to this embodiment, including:

[0047] The monitoring and acquisition module is used to acquire first monitoring information, second monitoring information, third monitoring information, forest area information, and collection date of forest pest monitoring points. The monitoring points are pest trapping points set up within the forest area. The first monitoring information includes the number of monitored targets and a first monitoring image. The second monitoring information refers to the tree information monitored by the monitoring point, including tree height and a second monitoring image. The third monitoring information refers to the information of the monitoring points, including the number of monitoring points, monitoring point type, and monitoring point location. The first monitoring information is the information of pests captured by the forest pest monitoring points. The tree height is the average height of trees within a 2-meter radius of the forest pest monitoring point. The second monitoring image is an image of tree leaves within a 2-meter radius of the forest pest monitoring point. The forest area information includes the number of trees and the forest area area. The forest pest monitoring point is the location within the forest area where insect traps are set. The monitoring point type includes central monitoring points and non-central monitoring points. The number of central monitoring points should meet certain requirements. One monitoring point is set up, and its location should be centrally located within the forest area. The location of the monitoring point includes relative angle and relative distance. The location of the monitoring point is the relative position between the non-central monitoring point and the central monitoring point. The relative angle is the angle between the non-central monitoring point and the central monitoring point in the north-clockwise direction. The relative distance is the distance between the non-central monitoring point and the central monitoring point. The collection date is the date of acquisition of the first monitoring information and the second monitoring information. The first monitoring information is acquired by the user through interactive uploading of captured pests from the forest pest monitoring point. The second monitoring information is acquired and uploaded through infrared sensors and cameras installed at the forest pest monitoring point. The third monitoring information and forest area information are acquired through user interactive input. The collection date is acquired by importing system running data. In this embodiment, the number of monitoring points is set to 5, including 1 central monitoring point and 4 non-central monitoring points. The non-central monitoring points are distributed in the northwest, northeast, southwest and southeast directions of the central monitoring point, with 1 in each direction.

[0048] The first monitoring module is used to analyze the type of monitored object based on the first monitoring image and the first preset monitoring image, and also to analyze the first hazard parameter based on the first monitoring information and the type of monitored object. The first monitoring module is connected to the monitoring acquisition module.

[0049] Please see Figure 2 As shown, the first monitoring module is equipped with:

[0050] The tiered planning unit is used to plan the hazard level of monitored objects. The hazard level of monitored objects represents the degree of hazard corresponding to each preset type of monitored object, thereby improving the diversity of system analysis.

[0051] The grading planning unit plans the hazard level of the monitored species according to the preset monitored species. The hazard level of the monitored species for trunk pests is set as g1, the hazard level of the monitored species for twig pests is set as g2, and the hazard level of the monitored species for leaf pests is set as g3. Here, P(p) represents the hazard level of the monitored species, and p represents the preset monitored species. When p=1, it means that the preset monitored species is trunk pest, P(1)=g1; when p=2, it means that the preset monitored species is twig pest, P(2)=g2; when p=3, it means that the preset monitored species is leaf pest. For pests, P(3)=g3. In this embodiment, the setting of the hazard level of the monitored object is not specifically limited. Those skilled in the art can set it freely. The setting of the hazard level of the monitored object should satisfy g1<g2<g3 and g1+g2≥g3. The optimal value of the hazard level of the monitored object is: g1=2, g2=3, g3=5. Through the analysis of the preset monitored object types by the level planning unit, the hazard level of the monitored object is analyzed, and the hazard level of different monitored objects is divided, thereby improving the system's analysis efficiency of the first monitoring information and improving the accuracy of the first monitoring information analysis.

[0052] Specifically, in this embodiment, the types of monitored pests are pre-defined as stem pests, branch pests, and leaf pests. Stem pests include longhorn beetles, jewel beetles, and tree beetles, while branch pests include leaf rollers, aphids, and psyllids. Leaf pests include tussock moths, bamboo locusts, and sawflies.

[0053] Please continue reading. Figure 2 As shown, the first monitoring module is equipped with:

[0054] The pest identification unit is used to analyze the types of monitored objects and to identify and classify the biological species in the monitoring images. The pest identification unit is connected to the hierarchical planning unit.

[0055] The pest identification unit matches the first monitoring image with a first preset monitoring image, and analyzes the species of the monitored organisms based on the matching results, wherein:

[0056] When the first monitoring image is successfully matched with the first preset monitoring image, the pest identification unit will take the preset monitoring species corresponding to the successfully matched first preset monitoring image as the monitoring species.

[0057] When the first monitoring image fails to match the first preset monitoring image, the pest identification unit does not analyze the species of the monitored object. The pest identification unit analyzes the first monitoring image and the first preset monitoring image to identify the species of the monitored object, ensuring the accuracy of the first monitoring image identification analyzed by the system, thereby improving the system's efficiency in analyzing the first monitoring information and improving the accuracy of the first monitoring information analysis.

[0058] Specifically, in this embodiment, the pest identification unit outputs the first monitoring image that fails to match. The user can identify the species of the first monitoring image that fails to match and upload the first monitoring image identified by the user as the first preset monitoring image to increase the data in the system sample database.

[0059] Please continue reading. Figure 2 As shown, the first monitoring module includes:

[0060] The pest analysis unit is used to analyze the first hazard parameter, which represents the relationship between the hazard levels of the monitored objects at each monitoring point, thereby achieving a unified analysis of the hazard levels of the monitored objects. The pest analysis unit is connected to the pest identification unit.

[0061] The pest analysis unit calculates the first hazard parameter based on the type and hazard level of the monitored organism using a first hazard parameter analysis formula. The pest analysis unit has the following first hazard parameter analysis formula:

[0062] ,

[0063] Where A(i) represents the first hazard parameter, i represents the monitoring point number, i∈{1,2,3,4,5}, when i=1, it represents the central monitoring point, when i>1, it represents the non-central monitoring point, when i=2, it represents the non-central monitoring point located northeast of the central monitoring point, when i=3, it represents the non-central monitoring point located southeast of the central monitoring point, when i=4, it represents the non-central monitoring point located southwest of the central monitoring point, when i=5, it represents the non-central monitoring point located northwest of the central monitoring point, F(i,j) represents the type of monitored object, and j represents the number of monitored targets. max The maximum value of the number of monitored targets is equal to the number of monitored targets. Through the analysis of the number of monitored targets, the hazard level of the monitored objects, and the types of monitored objects by the pest analysis unit, the first hazard parameter is analyzed to realize the comprehensive analysis of the monitored objects by the system, thereby improving the system's analysis efficiency of the first monitoring information and improving the accuracy of the first monitoring information analysis.

[0064] Please continue reading. Figure 1 As shown, the intelligent data processing system for forestry monitoring points also includes:

[0065] The monitoring data construction module is used to analyze the coordinates of monitoring points based on the third monitoring information, analyze the quantitative change relationship based on the first and third monitoring information, and construct a monitoring grayscale image based on the monitoring point coordinates, forest area information, quantitative change relationship and collection date. The monitoring data construction module is connected to the monitoring acquisition module.

[0066] Please see Figure 3As shown, the monitoring data construction module includes:

[0067] The coordinate analysis unit is used to analyze the coordinates of the monitoring points, and uses the coordinates of the monitoring points to represent the position of each monitoring point in the grayscale image, thereby realizing the analysis of the position of the monitoring points;

[0068] The coordinate analysis unit analyzes the coordinates of the monitoring point based on the third monitoring information: when 0 ≤ θ(i) < 90, the coordinate analysis unit analyzes the coordinates of the monitoring point and sets x(i) = S(i) × sinθ(i) and y(i) = S(i) × cosθ(i); when 90 ≤ θ(i) < 180, the coordinate analysis unit analyzes the coordinates of the monitoring point and sets x(i) = S(i) × sinθ(i) and y(i) = S(i) × -cosθ(i); when 180 ≤ θ(i) < 270, the coordinate analysis unit analyzes the coordinates of the monitoring point and sets x(i) = S(i) × -sinθ(i) and y(i) = S(i) × -cosθ(i). When 270 ≤ θ(i) < 360, the coordinate analysis unit analyzes the coordinates of the monitoring point, setting x(i) = S(i) × -sinθ(i) and y(i) = S(i) × cosθ(i); where θ(i) represents the relative angle, S(i) represents the relative distance, x(i) represents the abscissa of the monitoring point, y(i) represents the ordinate of the monitoring point, and (x(i), y(i)) represents the trap coordinate point; through the analysis of the third monitoring information by the coordinate analysis unit, the coordinates of the monitoring point are analyzed to ensure the accuracy of the system's analysis data, thereby improving the system's analysis efficiency of the first monitoring information and improving the accuracy of the first monitoring information analysis.

[0069] Please continue reading. Figure 3 As shown, the monitoring data construction module includes:

[0070] The relationship analysis unit is used to analyze the quantitative change relationship, and to express the fluctuation relationship between the pest data at each monitoring point and the pest data at the central monitoring point.

[0071] The relationship analysis unit calculates the quantity change relationship based on the number of monitored targets and third-party monitoring information using a quantitative relationship analysis formula. The quantitative relationship analysis formula for the relationship analysis unit is as follows:

[0072] Q(i) = [N(i) - N(1)] / S(i);

[0073] Wherein, Q(i) represents the quantity change relationship, N(i) represents the number of monitoring targets, and N(1) represents the number of monitoring targets at the central monitoring point; by analyzing the first monitoring information and the third monitoring information through the relationship analysis unit, the quantity change relationship can be analyzed, the fluctuation of monitoring data can be analyzed, the diversity of system analysis can be increased, thereby improving the system's analysis efficiency of the first monitoring information and improving the accuracy of the first monitoring information analysis.

[0074] Please continue reading. Figure 3 As shown, the monitoring data construction module includes:

[0075] An image construction unit is used to construct a monitoring grayscale image to graphically represent the relationships between the analyzed data. The image construction unit is connected to the relationship analysis unit.

[0076] The image construction unit constructs a monitoring grayscale image based on the monitoring point coordinates, forest area information, and quantity change relationship. The number of pixels in the monitoring grayscale image is the same as the size of the forest area. The center point of the monitoring grayscale image is set as the position of the center monitoring point. A plane rectangular coordinate system is established with the center monitoring point as the origin. The x-axis points in the direction of due north, and the y-axis points in the direction of due east. The coordinate points represent the position of each pixel in the monitoring grayscale image.

[0077] The image construction unit uses the coordinates in the monitored grayscale image that have the same x-coordinate and y-coordinate as the monitoring point coordinates as the trap coordinates, and uses the coordinates in the monitored grayscale image that are not trap coordinates as the construction coordinates. The grayscale value of the trap coordinates is set to L(x(i),y(i)), and the grayscale value of the construction coordinates is set to L(x,y), where:

[0078] ,

[0079] ,

[0080] Where u represents the grayscale construction parameter, 100≤u≤150, i maxThe maximum value of the monitoring point number is equal to the number of monitoring points. (x,y) represents the coordinates of the constructed coordinate point. When L(x(i),y(i)) < 0 or L(x,y) < 0, the grayscale value of the trapping coordinate point that meets the condition is set to L(x(i),y(i)) = 0, and the grayscale value of the constructed coordinate point that meets the condition is set to L(x,y) = 0. Through the analysis of the relationship between the monitoring point coordinates, forest area and quantity changes by the image construction unit, a monitoring grayscale image is generated, the relationship between various information is constructed and converted into image form, making the data change analysis more intuitive, ensuring the integrity of the system analysis data, thereby improving the system's analysis efficiency of the first monitoring information and improving the accuracy of the first monitoring information analysis. It is understood that this embodiment does not specifically limit the value of the grayscale construction parameter. Those skilled in the art can set it freely, as long as it meets the analysis of the grayscale value of the trapping coordinate point. The optimal value of the grayscale construction parameter is: u = 125.

[0081] Please continue reading. Figure 3 As shown, the monitoring data construction module includes:

[0082] The tree analysis unit is used to adjust the construction process of the monitoring grayscale image so that the grayscale value of the constructed coordinate point is related to the change in the number of trees. The tree analysis unit is connected to the image construction unit.

[0083] The tree analysis unit adjusts the analysis process of the grayscale value of the constructed coordinate point according to the number of trees: when M(k)≥M(k-1), the tree analysis unit determines that the number of trees is stable and does not adjust the analysis process of the grayscale value of the constructed coordinate point; when M(k)<M(k-1), the tree analysis unit determines that the number of trees has decreased and adjusts the analysis process of the grayscale value of the constructed coordinate point. The adjusted grayscale value of the constructed coordinate point is L1(x,y), and L1(x,y) is set to L(x,y)×log M(k-1) M(k); where M(k) represents the number of trees in the current analysis period, M(k-1) represents the number of trees in the previous analysis period, and k represents the analysis period number, k∈N. + The tree analysis unit analyzes the number of trees to adjust the analysis process of grayscale values ​​of the constructed coordinate points, thereby adjusting the construction process of the grayscale image. This allows for the increase of grayscale values ​​of the constructed coordinate points when trees are severely damaged by pests and diseases and die, making the image data more obvious. This improves the system's efficiency in analyzing the first monitoring information and enhances the accuracy of the first monitoring information analysis.

[0084] Please continue reading. Figure 3 As shown, the monitoring data construction module includes:

[0085] The acquisition and analysis unit is used to optimize the adjustment process of the monitored grayscale image, so that the grayscale value of the constructed coordinate point is related to the acquisition interval;

[0086] The data acquisition and analysis unit optimizes the adjustment process of the grayscale values ​​of the constructed coordinate points based on the acquisition date. The optimized grayscale value of the constructed coordinate points is L2(x,y), and L2(x,y) = L1(x,y) × T(i) × i max / ∑T(i), where T(i) represents the number of days between the collection date of each monitoring point in the current analysis period and its previous collection date; the collection and analysis unit analyzes the collection date to optimize the adjustment process of the grayscale value of the constructed coordinate point, thereby optimizing the construction process of the monitoring grayscale image, increasing the diversity of system analysis, and thus improving the system's analysis efficiency and accuracy of the first monitoring information; the collection and analysis unit is connected to the tree analysis unit.

[0087] Please continue reading. Figure 1 As shown, the intelligent data processing system for forestry monitoring points also includes:

[0088] The second monitoring module is used to establish a Cartesian coordinate system by taking the lower left corner pixel of the second monitoring image as the origin of the coordinate system and the two sides adjacent to the origin as the x-axis and y-axis. The x-axis increases from left to right and the y-axis increases from bottom to top. The coordinate points represent the position of each pixel in the second monitoring image.

[0089] The second monitoring module compares the second monitoring image with the preset leaf outline and extracts the leaf region based on the comparison result: when Z≥α, the second monitoring module extracts the region corresponding to the preset leaf outline in the second monitoring image as the leaf region; when Z<α, the second monitoring module does not analyze the leaf region; where Z represents the similarity between the second monitoring image and the preset leaf outline, and α represents the similarity threshold, 0.8≤α<1;

[0090] When calculating the similarity between the second monitoring image and the preset leaf outline, the second monitoring module performs binarization processing on the second monitoring image to remove areas in the second monitoring image that differ significantly from the leaf color, and calculates the curvature of the second monitoring image after binarization. The curvature of the second monitoring image after binarization processing is compared with the curvature of the preset leaf outline to calculate the similarity between the second monitoring image and the preset leaf outline.

[0091] The second monitoring module calculates the average gray value of the leaf area by taking the gray value of the leaf area, which is denoted as R=∑L(X,Y) / NL, where R represents the average gray value of the leaf area, L(X,Y) represents the gray value of the leaf area, (X,Y) represents the pixel coordinates of the leaf area, and NL represents the number of pixels in the leaf area.

[0092] The second monitoring module analyzes the second hazard parameter based on the grayscale value of the leaf area and the average grayscale value of the leaf area: when L(X,Y)<R×β, the second monitoring module extracts the currently analyzed pixel as the missing pixel and counts the number of missing pixels as the number of missing pixels; when L(X,Y)≥R×β, the second monitoring module does not analyze the missing pixels; the second monitoring module calculates the second hazard parameter based on the number of missing pixels and the number of pixels in the leaf area, setting B=NR / NL; where β represents the missing threshold, 0.3≤β≤0.7, B represents the second hazard parameter, and NR represents the number of missing pixels. It is understood that this embodiment does not specifically limit the setting of the similarity threshold, which can be freely set by those skilled in the art, as long as it satisfies the extraction of the leaf region. The optimal value of the similarity threshold is α=0.8. This embodiment does not specifically limit the calculation method of the similarity between the second monitoring image and the preset leaf outline, which can be freely set by those skilled in the art. For example, it can also be set to extract the gray value features and morphological features of the second monitoring image based on the gray value of the second monitoring image, and compare the extracted gray value features and morphological features with the gray value features and morphological features of the preset leaf outline to calculate the similarity between the second monitoring image and the preset leaf outline. This embodiment does not specifically limit the value of the incompleteness threshold, which can be freely set by those skilled in the art, as long as it satisfies the analysis of the second hazard parameter. The optimal value of the incompleteness threshold is β=0.4. The second monitoring module is connected to the monitoring acquisition module.

[0093] Please continue reading. Figure 1 As shown, the intelligent data processing system for forestry monitoring points also includes:

[0094] The integrated monitoring module is used to analyze pest and disease parameters based on the monitored grayscale images, adjust the analysis process of pest and disease parameters based on the first hazard parameter, optimize the adjustment process of pest and disease parameters based on the second hazard parameter, and analyze the pest and disease level based on the pest and disease parameters. The integrated monitoring module is connected to the first monitoring module, the monitoring data construction module, and the second monitoring module.

[0095] Please see Figure 4 As shown, the integrated monitoring module includes:

[0096] The pest and disease analysis unit is used to analyze pest and disease parameters and to represent the pest and disease situation in the forest area.

[0097] The pest and disease analysis unit analyzes pest and disease parameters based on the monitored grayscale images. The unit counts the number of coordinate points in the grayscale images that satisfy L(x,y)=0 as the number of outliers, and calculates the pest and disease parameters based on the number of outliers using the pest and disease parameter analysis formula. The pest and disease analysis unit has the following pest and disease parameter analysis formula:

[0098] ,

[0099] Wherein, D represents the pest and disease parameters, N1 represents the number of pixels in the monitored grayscale image, N2 represents the number of outliers, H(i) represents the tree height, and NH represents the number of trees; by analyzing the monitored grayscale image through the pest and disease analysis unit, the pest and disease parameters are analyzed, and the pest and disease situation in the forest area is comprehensively analyzed, thereby improving the system's efficiency in analyzing the first monitoring information and improving the accuracy of the first monitoring information analysis.

[0100] Please continue reading. Figure 4 As shown, the integrated monitoring module includes:

[0101] The first hazard analysis unit is used to adjust the analysis process of pest and disease parameters so that the adjusted pest and disease parameters are related to the hazard level of the monitored object. The first hazard analysis unit is connected to the pest and disease analysis unit.

[0102] The first hazard analysis unit adjusts the analysis process of the pest and disease parameters based on the first hazard parameter: when A(i)>P(3) / 2, the first hazard analysis unit determines that the first hazard parameter does not meet the threshold, and adjusts the analysis process of the pest and disease parameters. The adjusted pest and disease parameters are D1, and D1 is set as D×log A(i) P(3); When A(i)≤P(3) / 2, the first hazard analysis unit determines that the first hazard parameter meets the threshold and does not adjust the analysis process of the pest and disease parameter; through the analysis of the first hazard parameter by the first hazard analysis unit, the analysis process of the pest and disease parameter is adjusted. When the data in the hazard level of the monitored object is biased towards the hazard level of the monitored object of leaf pests, the pest and disease parameter is increased, thereby improving the system's analysis efficiency of the first monitoring information and improving the accuracy of the analysis of the first monitoring information.

[0103] Please continue reading. Figure 4 As shown, the integrated monitoring module includes:

[0104] The second hazard analysis unit is used to optimize the adjustment process of pest and disease parameters, so that the optimized pest and disease parameters are related to the second hazard parameters. The second hazard analysis unit is connected to the first hazard analysis unit.

[0105] The second hazard analysis unit optimizes the adjustment process of the pest and disease parameters based on the second hazard parameter: when B ≥ b, the second hazard analysis unit determines that the second hazard parameter does not meet the threshold, optimizes the adjustment process of the pest and disease parameters, and the optimized pest and disease parameter is D2, which is set as D2 = D1 × e. B When B < b, the second hazard analysis unit determines that the second hazard parameter meets the threshold and does not optimize the adjustment process of the pest and disease parameters; where b represents the leaf erosion threshold, 0.1 ≤ b ≤ 0.2. Specifically, in this embodiment, the second hazard analysis unit analyzes the second hazard parameter to optimize the adjustment process of the pest and disease parameters. When the second hazard parameter is large, the pest and disease parameters are increased, thereby improving the system's analysis efficiency of the first monitoring information and improving the accuracy of the first monitoring information analysis. It is understood that this embodiment does not specifically limit the value of the leaf erosion threshold. Those skilled in the art can freely set it, as long as it meets the optimization of the pest and disease parameters. The optimal value of the leaf erosion threshold is: b = 0.1.

[0106] Please continue reading. Figure 4 As shown, the integrated monitoring module includes:

[0107] The grade analysis unit is used to analyze the grade of pests and diseases, and realizes the analysis of the grade of pests and diseases in the forest area. The grade analysis unit is connected to the second hazard analysis unit.

[0108] The grading analysis unit analyzes the pest and disease level based on pest and disease parameters: when D ≤ d1, the grading analysis unit determines the pest and disease level to be normal; when d1 < D ≤ d2, the grading analysis unit determines the pest and disease level to be low risk; when D > d2, the grading analysis unit determines the pest and disease level to be high risk; where d1 represents the first pest and disease level threshold, 0.7 ≤ d1 < 1, and d2 represents the second pest and disease level threshold, 1 ≤ d2 ≤ 1.2. It is understood that this embodiment does not specifically limit the value of the pest and disease level threshold; those skilled in the art can freely set it, as long as it meets the early warning requirements for pests and diseases. The optimal values ​​for the pest and disease parameter thresholds are: d1 = 0.8, d2 = 1.1.

[0109] Please continue reading. Figure 1 As shown, the intelligent data processing system for forestry monitoring points also includes:

[0110] The grade output module is used to output pest and disease parameters, and the grade output module is connected to the integrated monitoring module.

[0111] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the implementation of the present invention. For those skilled in the art, other variations or modifications can be made based on the above description. It is impossible to exhaustively list all the implementation methods here. All obvious variations or modifications derived from the technical solutions of the present invention are still within the protection scope of the present invention.

Claims

1. A forestry monitoring point data intelligent processing system, characterized in that, include: The monitoring and acquisition module is used to acquire the first monitoring information, second monitoring information, third monitoring information, forest area information, and collection date of forest pest monitoring points; The first monitoring module is used to analyze the type of monitored object based on the first monitoring image and the first preset monitoring image, and also to analyze the first hazard parameter based on the first monitoring information and the type of monitored object; The monitoring data construction module is used to analyze the coordinates of monitoring points based on the third monitoring information, to analyze the quantitative change relationship based on the first and third monitoring information, and to construct a monitoring grayscale image based on the monitoring point coordinates, forest area information, quantitative change relationship and collection date. The second monitoring module is used to analyze the second hazard parameter based on the second monitoring information and the third monitoring information; The integrated monitoring module is used to analyze pest and disease parameters based on the monitored grayscale images, adjust the analysis process of pest and disease parameters based on the first hazard parameter and the second hazard parameter, and analyze the pest and disease level based on the pest and disease parameters. The rating output module is used to output the rating of pests and diseases. The first monitoring module is equipped with a pest analysis unit, which is used to calculate the first hazard parameter A(i) based on the type and hazard level of the monitored organism. , Where A(i) represents the first hazard parameter, i represents the monitoring point number, i=1 represents the central monitoring point, i>1 represents the non-central monitoring point, F(i,j) represents the type of monitored object, and j represents the number of monitored targets. max The maximum value of the number of monitored targets is equal to the number of monitored targets. P(p) represents the hazard level of the preset monitored species, where p represents the preset monitored species, and P[F(i,j)] represents the hazard level of the monitored species currently being analyzed. The monitoring data construction module also includes an image construction unit, which is used to take the coordinates points in the monitoring grayscale image that have the same horizontal and vertical coordinates as the monitoring point coordinates as the trap coordinates, and take the coordinates points in the monitoring grayscale image that are not trap coordinates as the construction coordinates, and set the grayscale value of the trap coordinates to L(x(i),y(i)), and set the grayscale value of the construction coordinates to L(x,y), where: ， u represents the grayscale construction parameter, 100≤u≤150, i max The maximum value of the monitoring point number is equal to the number of monitoring points. (x,y) represents the coordinates of the constructed coordinate point. When L(x(i),y(i))<0 or L(x,y)<0, the gray value of the trap coordinate point that meets the condition is set to L(x(i),y(i))=0, and the gray value of the constructed coordinate point that meets the condition is set to L(x,y)=0. Q(i) represents the quantity change relationship, and N(i) represents the number of monitoring targets. The monitoring data construction module also includes a tree analysis unit, which compares the number of trees M(k) with the number of trees M(k-1) in the previous analysis period. When the number of trees decreases, the analysis process of the grayscale value of the constructed coordinate point is adjusted. The adjusted grayscale value of the constructed coordinate point is L1(x,y), where L1(x,y) = L(x,y) × log M(k-1) M(k); where M(k) represents the number of trees in the current analysis period, k represents the analysis period number, and k∈N + ; The monitoring data construction module is also equipped with a data acquisition and analysis unit, which is used to optimize the adjustment process of the gray value of the constructed coordinate point according to the acquisition date. The optimized gray value of the constructed coordinate point is L2(x,y). The integrated monitoring module includes a pest and disease analysis unit, which analyzes pest and disease parameters based on the monitored grayscale images. This unit counts the number of coordinate points in the grayscale images that satisfy L(x,y)=0 as the number of outliers N2, and calculates the pest and disease parameter D based on the number of outliers. D represents the pest and disease parameters, N1 represents the number of pixels in the monitored grayscale image, N2 represents the number of outliers, H(i) represents the tree height, and NH represents the number of trees. The integrated monitoring module also includes a first hazard analysis unit, which is used to adjust the analysis process of pest and disease parameters based on the first hazard parameter A(i). When the first hazard parameter does not meet the threshold, the analysis process of pest and disease parameters is adjusted, and the adjusted pest and disease parameters are D1, where D1 = D × log A(i) P(3), P(3) represents the hazard level of the monitored species for leaf pests; The integrated monitoring module also includes a second hazard analysis unit, which compares the second hazard parameter B with the leaf erosion threshold b. When the second hazard parameter does not meet the threshold, the adjustment process of the pest and disease parameters is optimized. The optimized pest and disease parameter is D2, where D2 = D1 × e B .

2. The intelligent data processing system for forestry monitoring points according to claim 1, characterized in that, The monitoring data construction module is equipped with a coordinate analysis unit, which is used to analyze the capture coordinate points (x(i), y(i)) based on the relative distance S(i) and the relative angle θ(i).

3. The intelligent data processing system for forestry monitoring points according to claim 2, characterized in that, The monitoring data construction module also includes a relationship analysis unit, which is used to calculate the quantitative change relationship based on the number of monitoring targets and third-party monitoring information using a quantitative relationship analysis formula. The quantitative relationship analysis formula of the relationship analysis unit is as follows: Q(i) = [N(i) - N(1)] / S(i); Where N(1) represents the number of monitoring targets at the central monitoring point.

4. The intelligent data processing system for forestry monitoring points according to claim 3, characterized in that, The second monitoring module compares the similarity Z between the second monitoring image and the preset leaf outline with the similarity threshold α, and extracts the leaf region based on the comparison result; The second monitoring module calculates the average gray value R of the leaf area based on the gray value of the leaf area; The second monitoring module analyzes the second hazard parameter based on the gray value of the leaf area and the average gray value R of the leaf area: when L(X,Y)<R×β, the second monitoring module extracts the currently analyzed pixel as the missing pixel and counts the number of missing pixels as the number of missing pixels; when L(X,Y)≥R×β, the second monitoring module does not analyze the missing pixels, where β represents the missing threshold, L(X,Y) represents the gray value of the leaf area, and (X,Y) represents the pixel coordinates of the leaf area. The second monitoring module calculates the second hazard parameter B based on the number of defects and the number of pixels in the leaf area. The second hazard parameter is the ratio of the number of defects to the number of pixels in the leaf area.

5. The intelligent data processing system for forestry monitoring points according to claim 4, characterized in that, The integrated monitoring module also includes a level analysis unit, which compares the pest parameter D with the pest level thresholds d1 and d2, and determines the pest level based on the comparison results. The pest level includes normal, low risk, and high risk.

Images