Green pest control method, device, equipment and medium

Abstract

The invention relates to a pest green control method, device, equipment and medium, and belongs to the field of pest control. The method comprises the following steps: uniformly dividing a pest control area into pest control sub-areas, detecting a plant pest damage degree, establishing a pest damage evaluation model, and outputting a pest damage evaluation result; physical pest control measures are adopted for the pest control sub-regions outputting general pest evaluation, and physical and chemical pest control measures are adopted for the pest control sub-regions outputting serious pest evaluation; insect corpses trapped and killed by the pest physical control measures are collected and decomposed to obtain decomposed insect organic fertilizer; respectively predicting sub-region soil fertility of the pest control sub-regions and outputting sub-region fertility prediction information; and applying a decomposed insect organic fertilizer into the pest control sub-region outputting the soil depletion information. The insect pest degree can be rapidly and accurately detected, insect pest prevention and control measures are taken, the pesticide dosage is reduced, meanwhile, insect dead bodies are secondarily utilized as chemical fertilizer, and ecological circulation, energy conservation and emission reduction are facilitated.

Description

Technical Field

[0001] The present invention belongs to the technical field of pest control, and specifically relates to a green pest control method, device, equipment and medium. Background Art

[0002] The damage to crops by pests may lead to serious economic losses and food shortages. The global losses caused by pests are as high as hundreds of billions of dollars each year. Pests such as mosquitoes, locusts, mites, etc. have a significant negative impact on human life and production. With the advancement of science and technology, the field of pest control has developed rapidly, and excessive chemical control is prone to occur, leading to the abuse of pesticides, which is harmful to the environment, crops and humans. Insects killed by chemical control may also cause harm to the soil. At the same time, insects killed by physical control cannot be reused, resulting in a waste of resources. Summary of the invention

[0003] In order to solve the above problems existing in the prior art, the present invention provides a green pest control method, device, equipment and medium.

[0004] The purpose of the present invention can be achieved through the following technical solutions: A green pest control method, the implementation of which comprises the following steps: Evenly divide the pest control area into pest control sub-areas, detect the plant pest degree of the pest control sub-areas by random inspection method, establish a pest evaluation model, and output pest evaluation results, wherein the pest evaluation results include severe pest evaluation, general pest evaluation, and slight pest evaluation; The method of detecting the plant pest degree of the pest control sub-area by random inspection and establishing a pest evaluation model specifically includes: Randomly select plant leaves in the pest control sub-areas and obtain plant leaf images; Dividing the plant leaf image into a background area and a leaf area by an improved edge detection method; The leaf area is divided into a healthy area and an insect-damaged area by an improved edge detection method; Respectively obtaining the total area of ​​healthy areas and the total area of ​​pest-infested areas of each pest control sub-area, obtaining the plant pest degree and establishing the pest evaluation model, wherein the plant pest degree is the ratio of the total area of ​​the pest-infested areas to the total area of ​​the healthy areas; Preset an insect pest degree threshold, the insect pest degree threshold includes a first insect pest threshold and a second insect pest threshold, and obtain the insect pest evaluation result by comparing the plant insect pest degree and the insect pest degree threshold; Determining the plant pest degree, and when the plant pest degree is greater than or equal to the first pest threshold, outputting the severe pest evaluation; When the plant pest degree is greater than or equal to the second pest threshold and less than the first pest threshold, outputting the general pest evaluation; When the plant pest degree is less than the second pest threshold, outputting the slight pest evaluation; Take physical pest control measures for the pest control sub-areas that output the general pest evaluation, and take combined physical and chemical pest control measures for the pest control sub-areas that output the severe pest evaluation; Collecting the dead bodies of insects killed by the physical pest control measures and composting them to obtain composted insect organic fertilizer; Predicting the soil fertility of each pest control sub-region and outputting the sub-region fertility prediction information, wherein the sub-region fertility prediction information includes soil fertility information and soil barrenness information; The decomposed insect organic fertilizer is applied to the pest control sub-area that outputs the soil barrenness information.

[0005] Preferably, the physical pest control measures include insecticidal lamp trapping, pheromone trapping, and fully degradable yellow and blue board trapping, and the combined physical and chemical pest control measures are to add chemical pesticides to the physical pest control measures.

[0006] Preferably, the step of dividing the plant leaf image into a background area and a leaf area by improving the edge detection method comprises: filtering the plant leaf image by an adaptive median filter; The gradient amplitude and gradient angle of the plant leaf image are calculated by using the directional gradient values, wherein the directional gradient values ​​include horizontal gradient values, vertical gradient values, 45° gradient values, and 135° gradient values. The calculation formula of the gradient amplitude is: , where F is the gradient amplitude, F s is the horizontal gradient value, F c is the vertical gradient value, F 45 is the 45° gradient value, F 135 is a gradient value of 135°; the calculation formula of the gradient amplitude is: , where θ is the gradient amplitude; Performing non-maximum suppression on the gradient amplitude, retaining the local gradient maximum value, and determining the suspected edge of the plant leaf image according to the local gradient maximum value and the gradient amplitude angle; Further processing the suspected edge by using an optimal segmentation threshold to obtain a clear edge; The plant leaf image is divided into the background area and the leaf area according to the clear edge.

[0007] Preferably, further processing the suspected edge by using the optimal segmentation threshold to obtain a clear edge includes: Obtaining the grayscale level and pixel occurrence probability of the plant leaf image, selecting a background segmentation grayscale value within the grayscale level, and calculating the background probability of a pixel point of the plant leaf image appearing in the background area and the leaf probability of a pixel point appearing in the leaf area; Calculate the leaf average gray value, background average gray value and total average gray value according to the leaf probability and the background probability; Calculate the inter-class variance according to the leaf average gray value and the background average gray value; The maximum value of the inter-class variance is obtained according to the inter-class variance, and the segmentation threshold corresponding to the maximum value of the inter-class variance is the optimal segmentation threshold.

[0008] Preferably, the respectively predicting the soil fertility of the pest control sub-regions and outputting the sub-regional fertility prediction information comprises: Detecting the soil fertility of the sub-region at the current stage, obtaining fertility-related factors, and obtaining a prediction regression curve based on the fertility-related factors; Predicting the soil fertility of the sub-region according to the prediction regression curve to obtain a predicted value of the soil fertility of the sub-region; A fertility threshold is preset, and the sub-regional fertility prediction information is obtained by comparing the sub-regional soil fertility prediction value with the fertility threshold.

[0009] Preferably, the fertility-related factors include soil age, soil moisture availability, soil temperature, and soil moisture.

[0010] A green pest control device, used to implement the green pest control method described above, comprising a pest evaluation module, a pest control module, and a pest secondary utilization module; The pest evaluation module is used to evenly divide the pest control area into pest control sub-areas, detect the plant pest degree of the pest control sub-areas by random inspection method and establish a pest evaluation model, and output the pest evaluation result, which includes a serious pest evaluation, a general pest evaluation, and a slight pest evaluation. The random inspection method is used to detect the plant pest degree of the pest control sub-areas and establish a pest evaluation model, and specifically includes: Randomly select plant leaves in the pest control sub-areas and obtain plant leaf images; Dividing the plant leaf image into a background area and a leaf area by an improved edge detection method; The leaf area is divided into a healthy area and an insect-damaged area by an improved edge detection method; Respectively obtaining the total area of ​​healthy areas and the total area of ​​pest-infested areas of each pest control sub-area, obtaining the plant pest degree and establishing the pest evaluation model, wherein the plant pest degree is the ratio of the total area of ​​the pest-infested areas to the total area of ​​the healthy areas; Preset an insect pest degree threshold, the insect pest degree threshold includes a first insect pest threshold and a second insect pest threshold, and obtain the insect pest evaluation result by comparing the plant insect pest degree and the insect pest degree threshold; Determining the plant pest degree, and when the plant pest degree is greater than or equal to the first pest threshold, outputting the severe pest evaluation; When the plant pest degree is greater than or equal to the second pest threshold and less than the first pest threshold, outputting the general pest evaluation; When the plant pest degree is less than the second pest threshold, outputting the slight pest evaluation; The pest control module is used to take physical pest control measures for the pest control sub-region that outputs the general pest evaluation; and take physical and chemical combined pest control measures for the pest control sub-region that outputs the severe pest evaluation; The pest secondary utilization module is used to collect the insect corpses lured and killed by the pest physical control measures and decompose them to obtain decomposed insect organic fertilizer; predict the regional soil fertility of the pest control sub-region respectively and output the regional fertility prediction information, the regional fertility prediction information includes soil fertility information and soil barrenness information; and apply the decomposed insect organic fertilizer to the pest control sub-region where the soil barrenness information is output.

[0011] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the green pest control method described above is implemented when the processor executes the program.

[0012] A storage medium containing computer executable instructions, which are used to execute the above-mentioned green pest control method when executed by a computer processor.

[0013] The beneficial effects of the present invention are: (1) By dividing pest control sub-regions and testing the pest severity of each sub-region, the severity of plant diseases and pests in each region can be accurately evaluated and measures can be taken to adapt to local conditions. Physical control measures can be taken in areas with less pests to avoid the abuse of pesticides and other chemical drugs, which may cause damage to the environment and human body. (2) By composting insects killed by physical control measures into fertilizer and applying it to areas with low predicted fertility, insect carcasses can be reused, while saving fertilizer and achieving sustainable resource development; (3) By improving the edge detection method, the plant leaf image is divided into background area, healthy area and pest area. The division is more accurate and fast, which is conducive to timely response to pest threats in the later stage; (4) The gradient amplitude and gradient angle of the plant leaf image are calculated by using four directional gradient values: horizontal gradient value, vertical gradient value, 45° gradient value, and 135° gradient value. Compared with conventional methods, adding 45° gradient value and 135° gradient value makes it less likely to produce false edges when detecting higher concentration noise; (5) The suspected edge is further processed by the optimal segmentation threshold to obtain a clear edge. The operation is simple, which can avoid the deviation easily caused by manually setting the threshold, and improve the noise resistance and adaptability of the edge detection algorithm, thus obtaining a clearer edge image. (6) Predicting soil fertility through the prediction regression curve is a simple and fast method, which significantly improves work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0015] Figure 1 The present invention is a flowchart of the steps of a green pest control method. DETAILED DESCRIPTION

[0016] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0017] The working principle and use process of the present invention: See also Figure 1 , a green pest control method, comprising: S1: Evenly divide the pest control area into pest control sub-areas, detect the plant pest degree of the pest control sub-areas by random inspection method, establish a pest evaluation model, and output pest evaluation results, which include severe pest evaluation, general pest evaluation, and slight pest evaluation; S2: Take physical pest control measures for the pest control sub-area outputting the general pest evaluation, and the physical pest control measures include but are not limited to insecticidal lamp trapping, pheromone trapping, and fully degradable yellow / blue board trapping; take combined physical and chemical pest control measures for the pest control sub-area outputting the severe pest evaluation, and add chemical pesticides to the physical pest control measures; S3: collecting the dead bodies of insects killed by the physical pest control measures and composting them to obtain composted insect organic fertilizer; S4: respectively predicting the soil fertility of the pest control sub-regions and outputting the sub-regional fertility prediction information, wherein the sub-regional fertility prediction information includes soil fertility information and soil barrenness information; S5: applying the decomposed insect organic fertilizer to the pest control sub-area that outputs the soil barrenness information.

[0018] In this embodiment, the pest control area is evenly divided into pest control sub-areas, the plant pest degree of the pest control sub-areas is detected by random inspection method, and a pest evaluation model is established to output the pest evaluation result, which can be implemented in the following ways: S101: randomly selecting plant leaves in the pest control sub-areas and acquiring plant leaf images; S102: dividing the plant leaf image into a background area and a leaf area by improving the edge detection method, so that the division is more accurate and fast, which is conducive to timely responding to pest threats in the later stage; S103: dividing the leaf area into a healthy area and an insect-damaged area by using an improved edge detection method; S104: respectively obtaining the total area of ​​the healthy area and the total area of ​​the pest-infested area of ​​each pest control sub-area, obtaining the plant pest degree and establishing the pest evaluation model, wherein the plant pest degree is the ratio of the total area of ​​the pest-infested area to the total area of ​​the healthy area; S105: Preset an insect pest degree threshold, the insect pest degree threshold includes a first insect pest threshold and a second insect pest threshold, and obtain the insect pest evaluation result by comparing the plant insect pest degree with the insect pest degree threshold; Determining the plant pest degree, and when the plant pest degree is greater than or equal to the first pest threshold, outputting the severe pest evaluation; When the plant pest degree is greater than or equal to the second pest threshold and less than the first pest threshold, outputting the general pest evaluation; When the plant pest degree is less than the second pest threshold, the slight pest evaluation is output.

[0019] In this embodiment, the plant leaf image is divided into a background area and a leaf area by an improved edge detection method, which can be implemented in the following manner: S102-1: filtering the plant leaf image by using an adaptive median filter; S102-2: Calculate the gradient amplitude and gradient angle of the plant leaf image by using the directional gradient values, wherein the directional gradient values ​​include horizontal gradient values, vertical gradient values, 45° gradient values, and 135° gradient values. Compared with conventional methods, adding 45° gradient values ​​and 135° gradient values ​​makes it less likely to generate false edges when detecting higher concentration noise. The calculation formula of the gradient amplitude is: , where F is the gradient amplitude, F s is the horizontal gradient value, F c is the vertical gradient value, F 45 is the 45° gradient value, F135 is a gradient value of 135°; the calculation formula of the gradient amplitude is: , where θ is the gradient amplitude, F s is the horizontal gradient value, F c is the vertical gradient value; S102-3: performing non-maximum suppression on the gradient amplitude, retaining the local gradient maximum, and determining the suspected edge of the plant leaf image according to the local gradient maximum and the gradient amplitude angle; S102-4: further processing the suspected edge by using an optimal segmentation threshold to obtain a clear edge; The grayscale level and pixel occurrence probability of the plant leaf image are obtained. The pixel occurrence probability is the probability of a certain pixel appearing at a certain grayscale level. The background segmentation grayscale value is selected within the grayscale level. The background probability of the pixel point of the plant leaf image appearing in the background area and the leaf probability of appearing in the leaf area are calculated. The calculation formula of the leaf probability is: , where P1 is the leaf probability, k is the background segmentation gray value, P is the pixel occurrence probability, and L is the number of gray levels. The calculation formula for the background probability is: , where P2 is the background probability; The leaf average gray value, background average gray value and total average gray value are calculated according to the leaf probability and the background probability. The calculation formula of the leaf average gray value is: , where h1 is the average gray value of leaves, P1 is the leaf probability, k is the background segmentation gray value, P is the pixel occurrence probability, and L is the number of gray levels; the calculation formula for the background average gray value is: , where h2 is the background average gray value, P2 is the background probability; the calculation formula of the total average gray value is: , where h is the total average gray value; The inter-class variance is calculated based on the leaf average gray value and the background average gray value. The calculation formula is: ,in, is the inter-class variance, P1 is the leaf probability, h1 is the average leaf gray value, h is the total average gray value, P2 is the background probability, and h2 is the background average gray value; Acquire the maximum value of the inter-class variance according to the inter-class variance, and the segmentation threshold corresponding to the maximum value of the inter-class variance is the optimal segmentation threshold; S102-5: Divide the plant leaf image into the background area and the leaf area according to the clear edge.

[0020] In this embodiment, the leaf area is divided into a healthy area and an insect-infested area by improving the edge detection method, which can be implemented in the following manner: S103-1: filtering the leaf region by using an adaptive median filter; S103-2: Calculate the blade gradient amplitude and blade gradient angle of the blade area through the blade directional gradient values, wherein the blade directional gradient values ​​include the blade horizontal gradient value, the blade vertical gradient value, the blade 45° gradient value, and the blade 135° gradient value. The blade gradient amplitude is calculated as follows: , where F' is the blade gradient amplitude, F s ' is the horizontal gradient value of the blade, F c ' is the vertical gradient value of the blade, F 45 ' is the blade 45° gradient value, F 135 ' is the blade 135° gradient value; the calculation formula of the blade gradient angle is: , where θ' is the blade gradient angle, F s ' is the horizontal gradient value of the blade, F c ' is the vertical gradient value of the blade; S103-3: performing non-maximum suppression on the blade gradient amplitude, retaining the local maximum value of the blade gradient, and determining the boundary suspected edge of the blade region according to the local maximum value of the blade gradient and the blade gradient amplitude angle; S103-4: further processing the suspected boundary edge by using the optimal segmentation threshold to obtain a clear boundary edge, which is simple to operate and can avoid the deviation easily caused by manually setting the threshold, and improve the noise resistance and adaptability of the edge detection algorithm to obtain a clearer edge image; Obtain the leaf grayscale level and leaf pixel occurrence probability of the leaf area, select the pest segmentation grayscale value within all the leaf grayscale levels, and calculate the healthy probability of the pixel points of the leaf area appearing in the healthy area and the pest probability of appearing in the pest area. The calculation formula of the healthy probability is: , where P1' is the health probability, k' is the gray value of pest segmentation, P' is the probability of leaf pixel appearance, L' is the number of leaf gray levels, and the calculation formula of the pest probability is: , where P2' is the probability of pests; The healthy average gray value and the pest average gray value are calculated according to the healthy probability and the pest probability. The calculation formula of the healthy average gray value is: , where h1' is the average gray value of health, P1' is the health probability, k' is the gray value of pest segmentation, P' is the probability of leaf pixel occurrence, and L' is the number of leaf gray levels; the calculation formula for the average gray value of pests is: , where h2' is the average gray value of pests, and P2' is the probability of pests; The variance between pest classes is calculated based on the healthy average gray value and the pest average gray value. The calculation formula is: ,in, is the inter-class variance of pests, P1' is the health probability, h1' is the average gray value of health, h1 is the average gray value of leaves, P2' is the pest probability, h2' is the average gray value of pests; Obtaining the maximum value of the variance between pest classes according to the variance between pest classes, wherein the segmentation threshold corresponding to the maximum value of the variance between pest classes is the optimal segmentation threshold for demarcation; S103-5: Divide the leaf area into the healthy area and the pest area according to the clear demarcation edge.

[0021] In this embodiment, the soil fertility of each pest control sub-region is predicted and the regional fertility prediction information is output, which can be implemented in the following ways: S401: Detecting the soil fertility of the sub-region at the current stage, obtaining fertility-related factors, the fertility-related factors including soil service life, soil moisture effectiveness, soil temperature, and soil moisture, and obtaining a prediction regression curve according to the fertility-related factors, the prediction regression curve being a regression curve of the soil fertility of the sub-region and the fertility-related factors; S402: predicting the soil fertility of the sub-region according to the prediction regression curve to obtain a predicted value of the soil fertility of the sub-region, wherein the prediction means is simple and fast, and the work efficiency is significantly improved; S403: Preset a fertility threshold, and obtain the sub-regional fertility prediction information by comparing the sub-regional soil fertility prediction value with the fertility threshold; Determining the predicted value of soil fertility in each region, and when the predicted value of soil fertility in each region is greater than or equal to the fertility threshold, outputting the soil fertility information; When the sub-region soil fertility prediction value is less than the fertility threshold, the soil infertility information is output.

[0022] A green pest control device comprises a pest evaluation module, a pest control module and a pest secondary utilization module.

[0023] The pest evaluation module is used to evenly divide the pest control area into pest control sub-areas, detect the plant pest degree of the pest control sub-areas by random inspection method and establish a pest evaluation model, and output the pest evaluation result, which includes a serious pest evaluation, a general pest evaluation, and a slight pest evaluation. The random inspection method is used to detect the plant pest degree of the pest control sub-areas and establish a pest evaluation model, and specifically includes: Randomly select plant leaves in the pest control sub-areas and obtain plant leaf images; Dividing the plant leaf image into a background area and a leaf area by an improved edge detection method; The leaf area is divided into a healthy area and an insect-damaged area by an improved edge detection method; Respectively obtaining the total area of ​​healthy areas and the total area of ​​pest-infested areas of each pest control sub-area, obtaining the plant pest degree and establishing the pest evaluation model, wherein the plant pest degree is the ratio of the total area of ​​the pest-infested areas to the total area of ​​the healthy areas; Preset an insect pest degree threshold, the insect pest degree threshold includes a first insect pest threshold and a second insect pest threshold, and obtain the insect pest evaluation result by comparing the plant insect pest degree and the insect pest degree threshold; Determining the plant pest degree, and when the plant pest degree is greater than or equal to the first pest threshold, outputting the severe pest evaluation; When the plant pest degree is greater than or equal to the second pest threshold and less than the first pest threshold, outputting the general pest evaluation; When the plant pest degree is less than the second pest threshold, outputting the slight pest evaluation; The pest control module is used to take physical pest control measures for the pest control sub-region that outputs the general pest evaluation; and take physical and chemical combined pest control measures for the pest control sub-region that outputs the severe pest evaluation; The pest secondary utilization module is used to collect the insect corpses lured and killed by the pest physical control measures and decompose them to obtain decomposed insect organic fertilizer; predict the regional soil fertility of the pest control sub-region respectively and output the regional fertility prediction information, the regional fertility prediction information includes soil fertility information and soil barrenness information; and apply the decomposed insect organic fertilizer to the pest control sub-region where the soil barrenness information is output.

[0024] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0025] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0026] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0027] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A green pest control method, characterized in that: The implementation of the green pest control method comprises the following steps: Evenly divide the pest control area into pest control sub-areas, detect the plant pest degree of the pest control sub-areas by random inspection method, establish a pest evaluation model, and output pest evaluation results, wherein the pest evaluation results include severe pest evaluation, general pest evaluation, and slight pest evaluation; The method of detecting the plant pest degree of the pest control sub-area by random inspection and establishing a pest evaluation model specifically includes: Randomly select plant leaves in the pest control sub-areas and obtain plant leaf images; Dividing the plant leaf image into a background area and a leaf area by an improved edge detection method; The leaf area is divided into a healthy area and an insect-damaged area by an improved edge detection method; Respectively obtaining the total area of ​​healthy areas and the total area of ​​pest-infested areas of each pest control sub-area, obtaining the plant pest degree and establishing the pest evaluation model, wherein the plant pest degree is the ratio of the total area of ​​the pest-infested areas to the total area of ​​the healthy areas; Preset an insect pest degree threshold, the insect pest degree threshold includes a first insect pest threshold and a second insect pest threshold, and obtain the insect pest evaluation result by comparing the plant insect pest degree and the insect pest degree threshold; Determining the plant pest degree, and when the plant pest degree is greater than or equal to the first pest threshold, outputting the severe pest evaluation; When the plant pest degree is greater than or equal to the second pest threshold and less than the first pest threshold, outputting the general pest evaluation; When the plant pest degree is less than the second pest threshold, outputting the slight pest evaluation; Take physical pest control measures for the pest control sub-areas that output the general pest evaluation, and take combined physical and chemical pest control measures for the pest control sub-areas that output the severe pest evaluation; Collecting the dead bodies of insects killed by the physical pest control measures and composting them to obtain composted insect organic fertilizer; Predicting the soil fertility of each pest control sub-region and outputting the sub-region fertility prediction information, wherein the sub-region fertility prediction information includes soil fertility information and soil barrenness information; The decomposed insect organic fertilizer is applied to the pest control sub-area that outputs the soil barrenness information.

2. The green pest control method according to claim 1, characterized in that: The physical pest control measures include trapping with insecticidal lamps, trapping with pheromones, and trapping with fully degradable yellow and blue boards. The combined physical and chemical pest control measures are to add chemical pesticides to the physical pest control measures.

3. The green pest control method according to claim 1, characterized in that: The step of dividing the plant leaf image into a background area and a leaf area by improving the edge detection method comprises: filtering the plant leaf image by an adaptive median filter; The gradient amplitude and gradient angle of the plant leaf image are calculated by using the directional gradient values, wherein the directional gradient values ​​include horizontal gradient values, vertical gradient values, 45° gradient values, and 135° gradient values. The calculation formula of the gradient amplitude is: , where F is the gradient amplitude, F s is the horizontal gradient value, F c is the vertical gradient value, F 45 is the 45° gradient value, F 135 is a gradient value of 135°; the calculation formula of the gradient amplitude is: , where θ is the gradient amplitude; Performing non-maximum suppression on the gradient amplitude, retaining the local gradient maximum value, and determining the suspected edge of the plant leaf image according to the local gradient maximum value and the gradient amplitude angle; Further processing the suspected edge by using an optimal segmentation threshold to obtain a clear edge; The plant leaf image is divided into the background area and the leaf area according to the clear edge.

4. The green pest control method according to claim 3, characterized in that: The further processing of the suspected edge by the optimal segmentation threshold to obtain a clear edge comprises: Obtaining the grayscale level and pixel occurrence probability of the plant leaf image, selecting a background segmentation grayscale value within the grayscale level, and calculating the background probability of a pixel point of the plant leaf image appearing in the background area and the leaf probability of a pixel point appearing in the leaf area; Calculate the leaf average gray value, background average gray value and total average gray value according to the leaf probability and the background probability; Calculate the inter-class variance according to the leaf average gray value and the background average gray value; The maximum value of the inter-class variance is obtained according to the inter-class variance, and the segmentation threshold corresponding to the maximum value of the inter-class variance is the optimal segmentation threshold.

5. The green pest control method according to claim 1, characterized in that: The method of respectively predicting the soil fertility of the pest control sub-regions and outputting the regional fertility prediction information comprises: Detecting the soil fertility of the sub-region at the current stage, obtaining fertility-related factors, and obtaining a prediction regression curve based on the fertility-related factors; Predicting the soil fertility of the sub-region according to the prediction regression curve to obtain a predicted value of the soil fertility of the sub-region; A fertility threshold is preset, and the sub-regional fertility prediction information is obtained by comparing the sub-regional soil fertility prediction value with the fertility threshold.

6. The green pest control method according to claim 5, characterized in that: The fertility-related factors include soil age, soil water availability, soil temperature and soil moisture.

7. A green pest control device using the green pest control method according to claim 1, characterized in that: Including pest assessment module, pest control module, and pest secondary utilization module; The pest evaluation module is used to evenly divide the pest control area into pest control sub-areas, detect the plant pest degree of the pest control sub-areas by random inspection method and establish a pest evaluation model, and output the pest evaluation result, which includes a serious pest evaluation, a general pest evaluation, and a slight pest evaluation. The random inspection method is used to detect the plant pest degree of the pest control sub-areas and establish a pest evaluation model, and specifically includes: Randomly select plant leaves in the pest control sub-areas and obtain plant leaf images; Dividing the plant leaf image into a background area and a leaf area by an improved edge detection method; The leaf area is divided into a healthy area and an insect-damaged area by an improved edge detection method; Respectively obtaining the total area of ​​healthy areas and the total area of ​​pest-infested areas of each pest control sub-area, obtaining the plant pest degree and establishing the pest evaluation model, wherein the plant pest degree is the ratio of the total area of ​​the pest-infested areas to the total area of ​​the healthy areas; Preset an insect pest degree threshold, the insect pest degree threshold includes a first insect pest threshold and a second insect pest threshold, and obtain the insect pest evaluation result by comparing the plant insect pest degree and the insect pest degree threshold; Determining the plant pest degree, and when the plant pest degree is greater than or equal to the first pest threshold, outputting the severe pest evaluation; When the plant pest degree is greater than or equal to the second pest threshold and less than the first pest threshold, outputting the general pest evaluation; When the plant pest degree is less than the second pest threshold, outputting the slight pest evaluation; The pest control module is used to take physical pest control measures for the pest control sub-region that outputs the general pest evaluation; and take physical and chemical combined pest control measures for the pest control sub-region that outputs the severe pest evaluation; The pest secondary utilization module is used to collect the insect corpses lured and killed by the pest physical control measures and decompose them to obtain decomposed insect organic fertilizer; predict the regional soil fertility of the pest control sub-region respectively and output the regional fertility prediction information, the regional fertility prediction information includes soil fertility information and soil barrenness information; and apply the decomposed insect organic fertilizer to the pest control sub-region where the soil barrenness information is output.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the green pest control method as described in any one of claims 1 to 6 is implemented.

9. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the green pest control method as described in any one of claims 1 to 6 when executed by a computer processor.

Images