Crop disease and pest monitoring and early warning method and system based on machine vision

Abstract

The invention provides a crop disease and pest monitoring and early warning method and system based on machine vision, and the method comprises the steps: obtaining crop information based on a current region, and the crop information comprises at least one of crop sowing time, crop position and crop variety; determining growth information of crops based on the crop information; determining preset personnel information of the current area based on the current area, the crop information and the growth information; determining a first difference value based on the preset personnel information and the actual personnel information; determining a first risk based on the first difference value and a first threshold value; and determining an early warning instruction based on the first risk.

Description

Technical Field

[0001] The present application relates to the field of early warning technology, and in particular to a method and system for monitoring and early warning of crop diseases and insect pests based on machine vision. Background Art

[0002] Crop pests and diseases are important issues in agricultural production, which have a significant impact on crop growth and yield. Traditional pest and disease monitoring methods usually rely on manual inspection, which is inefficient and limited by subjective judgment. With the development of computer vision technology, monitoring systems based on machine vision can provide more efficient and accurate monitoring methods. However, monitoring systems in existing technologies often lack the ability to provide timely warnings, making it difficult to achieve automated warnings.

[0003] Therefore, it is hoped to provide a crop disease and pest monitoring and early warning method and system based on machine vision, which can detect and predict the losses caused by pests and diseases by automatically processing real-time crop images, issue early warning notifications in a timely manner, determine whether the monitoring instructions need to be reset, and automatically reset the monitoring instructions. This can improve work efficiency, increase monitoring efforts, and automatically reduce the increase in pest and disease risks due to improper operation, thereby effectively improving the timeliness and accuracy of pest and disease control. Summary of the invention

[0004] The present application provides a crop disease and pest monitoring and early warning method based on machine vision, the method comprising: obtaining crop information based on a current area, the crop information comprising at least one of crop sowing time, crop location, and crop variety; determining crop growth information based on the crop information; determining preset personnel information of the current area based on the current area, the crop information, and the growth information; determining a first difference based on the preset personnel information and actual personnel information; determining a first risk based on the first difference and a first threshold; and determining an early warning instruction based on the first risk.

[0005] The present application proposes a machine vision-based crop disease and insect pest monitoring and early warning system, which includes: a crop information acquisition module, used to acquire crop information based on a current area, the crop information including at least one of crop sowing time, crop location, and crop variety; a growth information acquisition module, used to determine crop growth information based on the crop information; a preset personnel acquisition module, used to determine preset personnel information of the current area based on the current area, the crop information, and the growth information; a first difference module, used to determine a first difference based on the preset personnel information and actual personnel information; a first risk module, used to determine a first risk based on the first difference and a first threshold; and a warning instruction acquisition module, used to determine a warning instruction based on the first risk.

[0006] The present application provides a crop disease and pest monitoring and early warning device based on machine vision, the device comprising a processor and a memory; the memory is used to store instructions, and is characterized in that when the instructions are executed by the processor, the device causes the device to implement a crop disease and pest monitoring and early warning method based on machine vision as described in any one of the above.

[0007] The present application provides a computer-readable storage medium, characterized in that the storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer runs the crop disease and pest monitoring and early warning method based on machine vision as described in any one of the above. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 It is a schematic diagram of an application scenario of a crop disease and insect pest monitoring and early warning system based on machine vision according to some embodiments of this specification;

[0009] Figure 2 is a module schematic diagram of a crop disease and insect pest monitoring and early warning system based on machine vision according to some embodiments of this specification;

[0010] Figure 3 This is an exemplary flow chart of a crop disease and insect pest monitoring and early warning method based on machine vision as shown in some embodiments of this specification. DETAILED DESCRIPTION

[0011] The preferred embodiments of the present application are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application and are not used to limit the present application.

[0012] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0013] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0014] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0015] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0016] Figure 1 Schematic diagram of an application scenario of a crop pest monitoring and early warning system based on machine vision according to some embodiments of this specification. Figure 1 As shown, the scene 100 involved in the crop disease and insect pest monitoring and early warning system based on machine vision may include a processor 110 , a user terminal 120 , a storage device 130 , a network 140 , and a crop area 150 .

[0017] In some embodiments, the processor 110 may be used to process information and / or data related to the scene 100. For example, the processor 110 may obtain a network spectrum based on the data. In some embodiments, the processor 110 may be local or remote. For example, the processor 110 may access information and / or data stored in the storage device 130 or the user terminal 120 via the network 140. For another example, the processor 110 may be directly connected to the storage device 130 or the user terminal 120 to access the stored information and / or data.

[0018] The user terminal 120 may be a device used by a user. The user terminal 120 may be used to view the operation status, instruction information, etc. of the crop pest and disease monitoring and early warning system based on machine vision.

[0019] The storage device 130 can be used to store data and / or instructions related to machine vision-based crop pest monitoring and early warning. In some embodiments, the storage device 130 can store data obtained / retrieved from the user terminal 120. In some embodiments, the storage device 130 can store data and / or instructions that the processor 110 uses to execute or use to complete the exemplary methods described in this application. The storage device 130 can be implemented on a cloud platform. In some embodiments, the storage device 130 can be used to store historical data, for example, information and historical behavior of inspection personnel and / or operators.

[0020] In some embodiments, the storage device 130 may be connected to the network 140 to communicate with one or more components of the scene 100 (e.g., the processor 110, the user terminal 120). One or more components of the scene 100 may access data or instructions stored in the storage device 130 via the network 140. In some embodiments, the storage device 130 may be directly connected to or communicate with one or more components of the scene 100 (e.g., the processor 110, the concentrator 120, the user terminal 120). In some embodiments, the storage device 130 may be part of the processor 110. In some embodiments, the storage device 130 may be a separate memory. The storage device 140 may store historical data, such as historical work data, user feature data, etc. The storage device 140 may also store machine learning models, etc.

[0021] Network 140 may facilitate the exchange of information and / or data. In some embodiments, one or more components of scene 100 (eg, processor 110, user terminal 120) may send information and / or data to other components of scene 100 via network 140.

[0022] The crop area 150 may include a plurality of crop types, and a plurality of imaging devices may be included in the crop area 150 for acquiring crop information.

[0023] Figure 2 It is a module schematic diagram of a crop disease and insect pest monitoring and early warning system based on machine vision according to some embodiments of this specification.

[0024] like Figure 2 As shown, the machine vision-based crop disease and pest monitoring and early warning system 200 may include a crop information acquisition module 210, a growth information acquisition module 220, a preset personnel acquisition module 230, a first difference module 240, a first risk module 250, and an early warning instruction acquisition module 260.

[0025] The crop information acquisition module 210 is used to acquire crop information based on the current area, where the crop information includes at least one of crop sowing time, crop location, and crop variety.

[0026] The growth information acquisition module 220 is used to determine the growth information of the crop based on the crop information.

[0027] In some embodiments, the growth information acquisition module 220 includes: a first acquisition module, used to acquire a first image of the current crop at a first time point, and determine a first growth stage at the first time point based on the first image and the crop sowing time; an ideal module, used to acquire an ideal image of the current crop at a second time point based on the first image, the second time point being later than the first time point; a comparison module, used to compare the second image at the second time point with the ideal image, and determine delay information based on the comparison result; and a growth stage module, used to determine the growth stage based on the delay information.

[0028] The preset personnel acquisition module 230 is used to determine the preset personnel information of the current area based on the current area, crop information, and growth information.

[0029] The first difference module 240 is used to determine a first difference based on preset personnel information and actual personnel information.

[0030] The first risk module 250 is configured to determine a first risk based on the first difference and a first threshold.

[0031] The warning instruction acquisition module 260 is used to determine a warning instruction based on the first risk.

[0032] In some embodiments, the early warning instruction includes a judgment instruction that triggers whether the monitoring instruction needs to be reset, and the early warning instruction acquisition module 260 includes: a second acquisition module, used to obtain preset monitoring instructions; a third acquisition module, used to obtain crop information of the current area based on the preset monitoring instructions; a first pest score determination module, used to predict the first pest damage score of the current area at a third time point based on crop information and growth information; an adverse behavior module, used to determine adverse behavior information that may occur in the future based on historical data; a second pest score determination module, used to determine the second pest damage score at a third time point based on the adverse behavior information; a reset module, used to determine the reset monitoring instruction when the first pest damage score and / or the second pest damage score meet the preset conditions.

[0033] In some embodiments, the reset module includes: a preset interval module, used to obtain a preset time interval based on a preset time point; a reset interval module, used to determine the reset time interval by the following formula:

[0034]

[0035] Wherein, T is the reset time interval, τ1 is the preset time interval, S2 may refer to the current crop maturity period, S1 may refer to the current crop start period, S may refer to the current crop growth stage, and α is the adjustment coefficient corresponding to the first difference; the monitoring instruction module is used to determine the reset monitoring instruction based on the reset time interval and the current crop growth stage.

[0036] Figure 3 300 is an exemplary flow chart of a crop pest monitoring and early warning method based on machine vision according to some embodiments of this specification. Process 300 can be executed by a processor. Figure 3 As shown, process 300 may include the following steps:

[0037] Step 310, obtaining crop information based on the current area, the crop information including at least one of crop sowing time, crop location, and crop variety.

[0038] In some embodiments, the crop information may include crop images of the current area. Image data of the crop may be obtained by using an imaging device such as a camera set in the current area, such as a drone. The crop location may be the location of the current area. The crop sowing time and crop variety may be obtained through a storage device of the crop pest monitoring and early warning system.

[0039] Step 320, determining crop growth information based on the crop information.

[0040] The growth information may include the growth stage of the crop. The growth stage may include the seed stage, the emergence stage, the vegetative growth stage, the flowering stage, the fruiting stage, the maturity stage, etc. The growth stage may also be the early stage, the middle stage, and the late stage. For example, the early stage of the emergence stage.

[0041] In some embodiments, the growth stage of a crop can be obtained by:

[0042] S11, acquiring a first image of the current crop at a first time point, and determining a first growth stage at the first time point based on the first image and the sowing time of the crop.

[0043] The first image may refer to a crop image at a first time point. The first image may be acquired by connecting to a storage device or an imaging device in the current area.

[0044] The first time point may refer to a time point in the past, and the first time point may be a specific number of days after sowing or a seedling emergence stage.

[0045] The first growth stage may refer to a growth stage at a first time point. In some embodiments, the first growth stage of the crop at the first time point is determined based on the first image and the crop sowing time. For example, image analysis is used to determine whether the crop has sprouted or is in a fruiting stage.

[0046] S12, acquiring an ideal image of the current crop at a second time point based on the first image, where the second time point is later than the first time point.

[0047] In some embodiments, the second time point may be the current time point.

[0048] The ideal image may be an image of the growth of the crop at a second time point under an ideal condition.

[0049] In some embodiments, the ideal image is determined by an image model based on the first image, the first time point, the second time point, and the weather information between the first time point and the second time point. The weather information between the first time point and the second time point can be obtained from a third-party platform (e.g., a weather website) through a network.

[0050] The image model may be a machine learning model, such as a graph neural network model. The input of the image model may include a first image, a first time point, a second time point, and weather information between the first time point and the second time point, and the output may include an ideal image at the second time point.

[0051] The image model can be obtained through the first historical training sample and the first label training. For example, the first historical training sample is input into the initial image model, and a loss function is established based on the first label and the output result of the initial image model, and the parameters of the initial image model are updated. When the loss function of the initial image model meets the preset conditions, the model training is completed, wherein the preset conditions may be that the loss function converges, the number of iterations reaches a threshold, etc.

[0052] In some embodiments, the first historical training sample can be obtained from historical data without encountering pests, and can include a historical first image, a historical first time point, a historical second time point, and historical weather information between the historical first time point and the historical second time point. The training sample can be obtained based on historical data. The first label of the first historical training sample can be a historical crop image. The first label can be manually labeled.

[0053] The first time point and the second time point may both be preset time points for obtaining crop information. The preset time point may be a time point for obtaining crop information, and may be preset according to a key time of a growth stage of the crop.

[0054] S13, comparing the second image at the second time point with the ideal image, and determining delay information based on the comparison result.

[0055] The second image may refer to a crop image at a second time point. The second image may be acquired by connecting to a storage device or an imaging device in the current area.

[0056] In some embodiments, the second image and the ideal image at the second time point are standardized to ensure the accuracy of image comparison, which may include resizing, illumination correction, and noise removal; further, a convolutional neural network (CNN) is used to extract the second features and the ideal features of the second image and the ideal image; the similarity between the second image and the ideal image is determined based on the second features and the ideal features by an image similarity algorithm (such as structural similarity (SSIM) or mean square error (MSE)). The higher the similarity, the closer the actual growth state is to the ideal state. Finally, based on the similarity calculation result, the growth delay is determined. For example, the delay time is inferred using a similarity score and a set threshold.

[0057] Delay information refers to the time difference between the actual growth of crops and the ideal state calculated by comparing the actual image with the expected or ideal image. Delay information can help determine the gap between the actual situation and the ideal state, thereby estimating the degree of lag in the current state.

[0058] S14, determining a growth stage based on the delay information.

[0059] Based on the delay information, the second image determines the current growth stage of the crop.

[0060] In some cases, the method of judging the growth stage based solely on the crop image at the second time point may result in inaccurate judgments. For example, due to too many crops, the growth stage of each crop cannot be unified, or due to weather, pests, etc., which may cause growth delays, the growth stage of crops in the current area cannot be accurately judged based solely on the second image. For example, by comparing the second image with the ideal image, the delay information shows that the crop growth lags by 7 days. Under ideal conditions, the crop may be in the early growth stage at the second time point, rather than the middle stage under ideal conditions.

[0061] By improving the accuracy of growth stage judgment, the accuracy of later pest information judgment can be further improved.

[0062] Step 330, determining preset personnel information of the current area based on the current area, crop information, and growth information.

[0063] The preset personnel may refer to the personnel who are pre-set to be responsible for crop management in a certain area. The preset personnel may include inspection personnel and / or operating personnel.

[0064] Due to different growth stages, the steps required are also different. The operator can determine based on the growth stage.

[0065] Preset personnel information may refer to information related to preset personnel. The preset personnel information is obtained through the storage device of the crop pest and disease monitoring and early warning system. The preset personnel information may include at least one of the preset personnel's name, preset work content and time, corresponding professional score, and efficiency score. The professional score may refer to the professional level of each work content. The higher the score, the higher the professional level of the work content. The efficiency score can be set manually and scored based on the historical work data of the manager. The higher the efficiency score, the higher the completion of the preset work content by the preset personnel, and the better the prevention effect of pests. In some embodiments, the preset personnel information of the current area is determined by a preset relationship based on the current area, crop information, and growth information. For example, the preset relationship may include the scores of the inspection personnel and / or the operators in the corresponding preset content. In some embodiments, the preset score may correspond to a number.

[0066] Step 340: Determine a first difference based on the preset personnel information and the actual personnel information.

[0067] The actual personnel may refer to the personnel who actually perform the operation. The actual personnel information may refer to the information related to the actual personnel. The actual personnel information may be determined by an imaging device. The actual personnel information may include at least one of the name of the actual personnel, the actual work content and time, the corresponding professional score, and the efficiency score. The actual personnel and the actual work content completed may be determined by the imaging device. Each item in the actual personnel information may correspond to a score.

[0068] The first difference value represents the difference between the preset personnel information and the actual personnel information, for example, by subtracting the number corresponding to the preset personnel information from the number corresponding to the actual personnel information. The first difference value can be represented by a number, and the larger the first difference value, the greater the difference between the preset personnel information and the actual personnel information. In some embodiments, the first difference value can correspond to the adjustment coefficient, and the larger the first difference value, the smaller the corresponding adjustment coefficient.

[0069] Since the preset personnel may not have higher professional scores and efficiency scores than the actual personnel, the first difference is a positive value.

[0070] The first difference may be a difference accumulated at each growth stage or a difference at each growth stage. For example, the first difference may include the sum of the differences at each stage of the seed stage, the seedling stage, and the vegetative growth stage.

[0071] Step 350: determining a first risk based on the first difference and a first threshold.

[0072] The first threshold value may be a set difference standard, which is used to determine whether there is a first risk. The first threshold value may be set manually. When the first difference value is lower than the first threshold value, it is determined to be a first risk.

[0073] The first risk may refer to the risk of pests and diseases caused by existing human operations.

[0074] When the first difference is a difference between each growth stage, the first difference between each growth stage and the corresponding first threshold value may be compared respectively.

[0075] When the first difference is lower than the first threshold, improper crop management may be caused by human factors, thereby increasing the risk of pests and diseases at a future time point. For example, due to inexperienced workers in the process of spraying pesticides or inadequate monitoring of the spraying of pesticides, the probability of pests occurring in the future time period will increase.

[0076] Step 360: Determine a warning instruction based on the first risk.

[0077] The early warning instruction may include a judgment instruction for triggering whether a monitoring instruction needs to be reset.

[0078] In some cases, temporary changes in personnel or operations may increase the threat value of pests and diseases. Through some embodiments of this specification, it is possible to determine the first risk caused by the above changes and further determine whether it is necessary to reset the monitoring instructions and strengthen the monitoring efforts.

[0079] In some cases, since the first difference is lower than the first threshold, that is, the crop management is improper, in order to reduce the risk of pests, it may be necessary to reset the monitoring instruction based on the preset monitoring instruction to further increase the intensity of monitoring. The preset monitoring instruction includes a preset time point for obtaining crop information. The preset time interval can be obtained based on the preset time point.

[0080] In some embodiments, determining the early warning monitoring instruction may include the following steps:

[0081] Step S21, obtaining a preset monitoring instruction.

[0082] Preset monitoring instructions can be obtained through the crop pest and disease monitoring and early warning system.

[0083] Step S22, obtaining crop information of the current area based on the preset monitoring instructions.

[0084] Step S23: predicting the first pest damage score of the current area at a third time point based on the crop information and the growth information.

[0085] In some embodiments, the points of interest observed in the acquired crop image may be determined based on the growth information. The points of interest may include a key observation area of ​​the crop in the current area, and a key observation part on one of the crops in the key observation area.

[0086] Due to different growth stages and crops, the pests that may occur and the parts where the pests occur are different. For example, wheat in the seedling stage may be more susceptible to aphids or wheat mites, while in the jointing and maturity stages, it may face pests such as wheat head blight or wheat leaf rollers. For another example, wheat borers mainly harm wheat seeds and newly emerged plants, biting seeds or seedlings, resulting in poor germination or plant death, and wheat ear flies mainly harm wheat ears.

[0087] By segmenting the points of interest in crop images, the accuracy of determining the pest damage score can be improved.

[0088] In some embodiments, the first pest damage score is determined by a first damage model. The first damage model may be a machine learning model. The input of the first damage model is crop information, growth information, and the first difference, and the output is the first pest damage score. The higher the first pest damage score, the greater the impact of the first difference between the existing preset personnel information and the actual personnel information on the crops at the third time point, that is, it may cause an increase in the loss of pests and diseases at the third time point.

[0089] Step S24, determining possible adverse behavior information in the future based on historical data.

[0090] Adverse behavior may include behavior that is not conducive to crop growth, such as reducing the number of spraying times and dosage, replacing personnel with poor performance, etc. Adverse behavior information may refer to information related to the adverse behavior, such as the probability of occurrence of the adverse behavior, and the growth stage of the crop corresponding to the occurrence of the adverse behavior.

[0091] In some embodiments, the adverse behavior that may occur in the current area before the third time point is determined based on the preset personnel information. In some embodiments, the preset personnel can be determined based on the preset personnel information, and the preset personnel information and the preset personnel's historical behavior can be used to construct a time series sequence, and the probability of the adverse behavior that may occur can be predicted based on the time series sequence through a machine learning model.

[0092] Step S25, determining a second pest damage score at a third time point based on the adverse behavior information.

[0093] In some embodiments, the second insect pest damage score is determined based on the adverse behavior information and the behavior-damage control value that occurs by a preset value. The higher the second damage score, the more serious the damage to the insect pests caused by the adverse behavior that may occur at the third time point.

[0094] Step S26: When the first pest damage score and / or the second pest damage score meets a preset condition, a reset monitoring instruction is determined.

[0095] In some embodiments, the preset conditions may include a second threshold and a third threshold. When the first pest damage score is higher than the second threshold, and / or the second pest damage score is higher than the third threshold, based on the second difference between the first pest damage score and the second threshold, and / or the third difference between the second pest damage score and the third threshold, a reset monitoring instruction is determined through a preset score-frequency correspondence table, including the time point and number of reset time points.

[0096] Through image recognition algorithms, the system can automatically identify and classify pests and diseases, and by increasing the division of points of interest in the image, it can reduce human errors and improve the ability to prevent pests and diseases.

[0097] In some embodiments, the reset monitoring instruction may further include:

[0098] Step S31, obtaining a preset time interval based on a preset time point.

[0099] Step S32, determining the reset time interval by formula (1).

[0100]

[0101] Wherein, T is the reset time interval, τ1 is the preset time interval, S2 may refer to the current crop maturity period, S1 may refer to the current crop start period, S may refer to the current crop growth stage, and α is the adjustment coefficient corresponding to the first difference.

[0102] When S is close to S1, Close to 0; when S is close to S2, Close to 1. The reset time point can be determined based on the reset time interval. S1, S2, S can be represented by numbers, and the higher the number, the closer to maturity.

[0103] As a dynamic adjustment factor, when S is close to S1 and the current crop is in the early growth stage, It is close to 1, which makes the reset time interval close to the preset time interval. This is because in the early stage, there are relatively few human activities and the preset time interval can meet the monitoring needs.

[0104] In some embodiments, since the growth stage can also be early, middle and late, the reset time interval in each growth stage can be determined based on formula (1). S2 can refer to the late stage of the current crop growth stage, and S1 can refer to the early stage of the current crop growth stage.

[0105] In step S33, a reset monitoring instruction is determined based on the reset time interval and the current growth stage of the crop.

[0106] In some embodiments of the present specification, the determination of whether a monitoring instruction needs to be reset and the automatic resetting of the monitoring instruction can improve work efficiency.

[0107] Through automated monitoring and early warning systems, accurate risk assessment and monitoring instruction adjustments can optimize resource allocation, reduce unnecessary expenses, and provide early warning of pests and diseases based on scientific data, so as to provide reasonable and effective prevention and control plans as early as possible.

[0108] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other beneficial effects that may be obtained.

[0109] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0110] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0111] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some embodiments currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0112] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0113] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0114] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0115] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A crop pest monitoring and early warning method based on machine vision, characterized in that: The method comprises: Acquire crop information based on the current area, the crop information including at least one of crop sowing time, crop location, and crop variety; determining growth information of the crop based on the crop information; Determine preset personnel information of the current area based on the current area, the crop information, and the growth information; Determine a first difference based on the preset personnel information and the actual personnel information; determining a first risk based on the first difference and a first threshold; A warning instruction is determined based on the first risk.

2. The method according to claim 1, characterized in that The growth information includes a growth stage, and determining the growth information of the crop based on the crop information includes: Acquire a first image of the current crop at a first time point, and determine a first growth stage at the first time point based on the first image and a sowing time of the crop; acquiring an ideal image of the current crop at a second time point based on the first image, the second time point being later than the first time point; comparing the second image at the second time point with the ideal image, and determining delay information based on the comparison result; A growth stage is determined based on the delay information.

3. The method according to claim 1, characterized in that The early warning instruction includes a judgment instruction for triggering whether a monitoring instruction needs to be reset, and the determination of the early warning instruction includes: Get preset monitoring instructions; Acquiring crop information of the current area based on the preset monitoring instruction; Based on the crop information and the growth information, predicting a first insect pest damage score of the current area at a third time point; Determine possible adverse action information in the future based on historical data; determining a second pest damage score at a third time point based on the adverse behavior information; When the first pest damage score and / or the second pest damage score meets a preset condition, a reset monitoring instruction is determined.

4. The method according to claim 3, characterized in that The determining of resetting the monitoring instruction comprises: Get the preset time interval based on the preset time point: The reset time interval is determined by the following formula, Wherein, T is the reset time interval, τ1 is the preset time interval, S2 may refer to the current crop maturity period, S1 may refer to the current crop start period, S may refer to the current crop growth stage, and α is the adjustment coefficient corresponding to the first difference; A reset monitoring instruction is determined based on the reset time interval and the current crop growth stage.

5. A crop pest monitoring and early warning system based on machine vision, characterized in that: The system comprises: A crop information acquisition module, used to acquire crop information based on the current area, wherein the crop information includes at least one of crop sowing time, crop location, and crop variety; A growth information acquisition module, used to determine the growth information of the crop based on the crop information; A preset personnel acquisition module, used to determine preset personnel information of the current area based on the current area, the crop information, and the growth information; A first difference module, configured to determine a first difference based on the preset personnel information and the actual personnel information; A first risk module, configured to determine a first risk based on the first difference and a first threshold; A warning instruction acquisition module is used to determine a warning instruction based on the first risk.

6. The system according to claim 5, characterized in that The growth information includes a growth stage, and the growth information acquisition module includes: A first acquisition module, configured to acquire a first image of the current crop at a first time point, and determine a first growth stage at the first time point based on the first image and a sowing time of the crop; An ideal module, configured to obtain an ideal image of the current crop at a second time point based on the first image, the second time point being later than the first time point; a comparison module, configured to compare the second image at the second time point with the ideal image, and determine delay information based on the comparison result; A growth phase module is used to determine a growth phase based on the delay information.

7. The system according to claim 5, characterized in that The early warning instruction includes a judgment instruction for triggering whether a monitoring instruction needs to be reset, and the early warning instruction acquisition module includes: A second acquisition module is used to acquire preset monitoring instructions; A third acquisition module, configured to acquire the crop information of the current area based on the preset monitoring instruction; A first pest score determination module, configured to predict a first pest damage score of the current area at a third time point based on the crop information and growth information; An adverse action module, used to determine possible adverse action information in the future based on historical data; A second pest score determination module, for determining a second pest damage score at a third time point based on the adverse behavior information; The reset module is used to determine a reset monitoring instruction when the first pest damage score and / or the second pest damage score meets a preset condition.

8. The system according to claim 7, characterized in that The reset module comprises: The preset interval module is used to obtain the preset time interval based on the preset time point: A reset interval module is used to determine the reset time interval by the following formula: Wherein, T is the reset time interval, τ1 is the preset time interval, S2 may refer to the current crop maturity period, S1 may refer to the current crop start period, S may refer to the current crop growth stage, and α is the adjustment coefficient corresponding to the first difference; The monitoring instruction module is used to determine a reset monitoring instruction based on the reset time interval and the current growth stage of the crop.

9. A crop pest monitoring and early warning device based on machine vision, the device comprising a processor and a memory; the memory is used to store instructions, characterized in that: When the instruction is executed by the processor, the device implements the crop disease and insect pest monitoring and early warning method based on machine vision as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer runs the crop disease and insect pest monitoring and early warning method based on machine vision as described in any one of claims 1 to 4.

Images