Walnut tree state monitoring method and system

Abstract

The invention provides a walnut tree state monitoring method and system, and belongs to the technical field of tree monitoring, and the method comprises the steps: determining the initial monitoring result of the state of a walnut tree based on the state parameter of the walnut tree; determining a monitoring image of the walnut tree based on the first state parameter of the walnut tree in response to the initial monitoring result of the walnut tree state as an abnormal state; the first state parameter is a parameter affected by diseases and insect pests; and determining a target monitoring result of the walnut tree state based on the monitoring image of the walnut tree. According to the walnut tree state monitoring method and system provided by the invention, the reliability and timeliness of walnut tree state monitoring can be improved.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of tree monitoring, and more specifically, relates to a method and system for monitoring the state of walnut trees. Background Art

[0002] As an important cash crop, the growth state of walnut trees directly affects the fruit yield and quality. Therefore, accurately monitoring the state of walnut trees is crucial for ensuring walnut yield and quality. Traditional monitoring of walnut tree state mainly relies on manual experience. Growers roughly judge the health condition by visually observing the appearance of walnut trees, such as leaf color, fruit condition, etc. However, it is difficult to detect early subtle lesions by this method, which is likely to lead to the spread of pests and diseases. Therefore, there is an urgent need for a reliable and timely method for monitoring the state of walnut trees. Summary of the Invention

[0003] The purpose of the present disclosure is to provide a method and system for monitoring the state of walnut trees to improve the reliability and timeliness of walnut tree state monitoring.

[0004] In the first aspect of the embodiments of the present disclosure, a method for monitoring the state of walnut trees is provided, including: Determining an initial monitoring result of the state of the walnut tree based on the state parameters of the walnut tree; In response to the initial monitoring result of the state of the walnut tree being an abnormal state, determining a monitoring image of the walnut tree based on the first state parameter of the walnut tree; the first state parameter is a parameter that will be affected by pests and diseases; Determining a target monitoring result of the state of the walnut tree based on the monitoring image of the walnut tree.

[0005] In the second aspect of the embodiments of the present disclosure, a system for monitoring the state of walnut trees is provided, including: An initial monitoring module for determining an initial monitoring result of the state of the walnut tree based on the state parameters of the walnut tree; A monitoring image determination module for determining a monitoring image of the walnut tree based on the first state parameter of the walnut tree in response to the initial monitoring result of the state of the walnut tree being an abnormal state; the first state parameter is a parameter that will be affected by pests and diseases; A target monitoring module for determining a target monitoring result of the state of the walnut tree based on the monitoring image of the walnut tree.

[0006] In the third aspect of the embodiments of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned method for monitoring the state of walnut trees are implemented.

[0007] In the fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned walnut tree status monitoring method are implemented.

[0008] The beneficial effects of the walnut tree status monitoring method and system provided by the embodiments of the present disclosure are as follows: By initially monitoring the status parameters of the walnut tree, the present disclosure can quickly capture the abnormal conditions of the walnut tree, providing strong support for subsequent precise monitoring. Secondly, when an abnormal status is detected, the present disclosure can specifically obtain the monitoring image of the walnut tree based on the first status parameters that may be affected by pests and diseases. The present disclosure not only improves the pertinence of monitoring, but also effectively avoids waste of resources, making the monitoring work more efficient and timely. Finally, by further analyzing the monitoring image, the target monitoring result of the walnut tree status can be obtained, which not only helps to timely detect and handle the pest and disease problems of the walnut tree, but also effectively improves the yield and quality of the walnut tree. Therefore, the present disclosure can monitor the status of the walnut tree timely and reliably. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present disclosure. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0010] Figure 1 It is a schematic flowchart of a walnut tree status monitoring method provided by an embodiment of the present disclosure; Figure 2 It is a structural block diagram of a walnut tree status monitoring system provided by an embodiment of the present disclosure; Figure 3 It is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0011] In the following description, specific details such as specific system structures and technologies are proposed for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present disclosure. However, those skilled in the art should clearly understand that the present disclosure can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present disclosure.

[0012] In order to make the purpose, technical solution, and advantages of the present disclosure clearer, the following will be described through specific embodiments with reference to the drawings.

[0013] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a walnut tree status monitoring method provided by an embodiment of the present disclosure. The method includes: S101: Determine an initial monitoring result of the walnut tree status based on the status parameters of the walnut tree.

[0014] In this embodiment, the status parameters of the walnut tree are various data that can reflect the growth, health, etc. of the walnut tree. For example, tree height, new shoot length, leaf size, fruit size, water content of the trunk, and chlorophyll content, etc. The walnut tree status refers to the growth or health status during the growth period of the walnut tree, which can be divided into a normal state and an abnormal state. The normal state indicates that the walnut tree grows well without obvious pests, diseases, or growth obstacles; the abnormal state indicates that the walnut tree may be invaded by pests and diseases, so further monitoring is required to determine whether there are pests and diseases. The initial monitoring result is an initial judgment conclusion about the walnut tree status obtained by analyzing and processing the status parameters of the walnut tree, that is, the normal state or the abnormal state, providing a basis for whether further monitoring is needed.

[0015] The status parameters of the walnut tree can be collected by setting multiple types of sensors for various status parameters of the walnut tree. After that, the status parameters can be compared and analyzed with a preset normal range or standard value. If all the status parameter values are within the normal range, it is determined that the initial monitoring result of the walnut tree status is the normal state; if at least one of the status parameter values exceeds the normal range, it is determined that the initial monitoring result of the walnut tree status is the abnormal state, and further monitoring is required to determine whether there are pests and diseases.

[0016] Specifically, the status parameters of the walnut tree include physiological parameters and growth parameters; Determining an initial monitoring result of the walnut tree status based on the status parameters of the walnut tree includes: Determine a first suspicion degree based on the physiological parameters of the walnut tree; Determine a second suspicion degree based on the growth parameters of the walnut tree; Perform a weighted calculation on the first suspicion degree and the second suspicion degree to determine the pest and disease suspicion degree; Determine an initial monitoring result of the walnut tree status based on the pest and disease suspicion degree.

[0017] In this embodiment, the physiological parameters are indicators that can reflect the physiological activity status of the walnut tree, including but not limited to the photosynthetic rate of the leaves, chlorophyll content, and water content of the trunk. The growth parameters are indicators that can reflect the growth and development status of the walnut tree, including but not limited to tree height, new shoot length, branch thickness, and fruit size.

[0018] The first suspicion degree is the numerical value of the possibility that the walnut tree has pests and diseases obtained by analyzing the physiological parameters of the walnut tree. The higher this numerical value, the greater the possibility that the walnut tree has pests and diseases based on the physiological parameters. The second suspicion degree is the numerical value of the possibility that the walnut tree has pests and diseases obtained by analyzing the growth parameters of the walnut tree, which is similar to the first suspicion degree. The pest and disease suspicion degree is an overall numerical value obtained by comprehensively considering the physiological parameters and growth parameters and performing weighted calculations on the first suspicion degree and the second suspicion degree, and is used to represent the comprehensive possibility that the walnut tree has pests and diseases.

[0019] Specifically, determining the first suspicion degree based on the physiological parameters of the walnut tree includes: Determining multiple standard physiological parameters based on the growth period of the walnut tree; Calculating the first matching degree between the physiological parameters of the walnut tree and each standard physiological parameter; Determining the first suspicion degree based on the first matching degree.

[0020] In this embodiment, the growth period of the walnut tree refers to the growth and development stages of the walnut tree from germination, flowering, fruiting to leaf-falling dormancy, etc. The standard physiological parameters are the standards of various physiological parameters in the normal growth state at different growth periods of the walnut tree, such as the normal chlorophyll content in the germination period, the normal photosynthetic rate in the flowering period, etc.

[0021] The first matching degree is the degree of closeness between the actually measured physiological parameters of the walnut tree and the standard physiological parameters of the corresponding growth period. The first suspicion degree is the suspicious degree of the walnut tree having pests and diseases determined based on the matching degree between the physiological parameters of the walnut tree and the standard physiological parameters. Among them, the higher the first matching degree, the closer the physiological state of the walnut tree is to normal, and the lower the first suspicion degree; on the contrary, the lower the first matching degree, the higher the first suspicion degree, and the greater the possibility that the walnut tree has pests and diseases.

[0022] The calculation formula for the first matching degree is:

[0023] Where is the th first matching degree, is the th physiological parameter, is the th standard physiological parameter, , is the total number of physiological parameters.

[0024] When multiple first matching degrees are determined through the calculation formula of the first matching degree, the multiple first matching degrees can be added up to calculate and determine the first suspicion degree.

[0025] Specifically, determining the second suspicion degree based on the growth parameters of the walnut tree includes: Determine multiple standard growth parameters based on the growth period of walnut trees; Calculate the second matching degree between the growth parameters of walnut trees and each standard growth parameter; Determine the second suspicion degree based on the second matching degree.

[0026] In this embodiment, the standard growth parameters are the numerical values of various growth indexes under normal growth conditions measured during each growth period of walnut trees. For example, in the budding period, the normal initial growth length range of new shoots; in the fruit swelling period, the daily growth diameter change range of fruits, etc.

[0027] The second matching degree is used to measure the degree of conformity between the actually measured growth parameters of walnut trees and the standard growth parameters corresponding to the growth period. The lower this value, the more the actual growth parameters deviate from the standard values. The second suspicion degree is the degree of possibility that the walnut tree is affected by diseases and pests evaluated according to the matching situation between the growth parameters of the walnut tree and the standard growth parameters. The higher the second suspicion degree, the greater the possibility of abnormal growth of the walnut tree.

[0028] The calculation formula for the second matching degree is:

[0029] Among them, is the th second matching degree, is the th growth parameter, is the th standard growth parameter, , is the total number of growth parameters.

[0030] The denominator part is for normalizing the difference so that growth parameters of different magnitudes can calculate the matching degree on a unified scale.

[0031] When determining multiple second matching degrees through the calculation formula of the second matching degree, the multiple second matching degrees can be summed up to determine the second suspicion degree.

[0032] The calculation formula for the disease and pest suspicion degree is:

[0033] Among them, is the disease and pest suspicion degree, is the weight coefficient of the first matching degree, is the weight coefficient of the second matching degree, , , 。When the growth period of the walnut tree is in the initial stage, even if there are pests and diseases, the change in growth parameters is small, but the tree's physiology has been affected. At this time, 。The above two weight coefficients can be set according to experience.

[0034] Specifically, the initial monitoring result of the walnut tree status based on the pest and disease suspicion degree includes: If the pest and disease suspicion degree is greater than or equal to the first suspicion degree threshold, the initial monitoring result of the walnut tree status is an abnormal status; If the pest and disease suspicion degree is less than the first suspicion degree threshold, the initial monitoring result of the walnut tree status is a normal status.

[0035] In this embodiment, the first suspicion degree threshold is a preset boundary value, which can be set according to experience and is used to judge whether there may be pests and diseases on the walnut tree, serving as a standard to distinguish the normal status and abnormal status of the walnut tree. Compare the pest and disease suspicion degree calculated in the above steps with the preset first suspicion degree threshold, and determine the initial monitoring result of the walnut tree status according to the comparison result. If the pest and disease suspicion degree is greater than or equal to the first suspicion degree threshold, it indicates that there may be pests and diseases on the walnut tree, and its initial monitoring result is determined as an abnormal status; if the pest and disease suspicion degree is less than the first suspicion degree threshold, it is considered that there are no obvious signs of pests and diseases on the walnut tree, and its initial monitoring result is determined as a normal status.

[0036] S102: In response to the initial monitoring result of the walnut tree status being an abnormal status, determine the monitoring image of the walnut tree based on the first status parameter of the walnut tree; the first status parameter is a parameter that will be affected by pests and diseases.

[0037] In this embodiment, the monitoring image of the walnut tree is the monitoring image of the specific part of the walnut tree determined according to the first status parameter of the walnut tree, which can improve the efficiency of subsequent pest and disease determination. For example, the monitoring image of the walnut tree can be a leaf image, a fruit image, a tree tip image, or a tree trunk image, etc.

[0038] Specifically, according to step S101, it can be determined whether the initial monitoring result of the walnut tree status is a normal status or an abnormal status. If the initial monitoring result is an abnormal status, then further analyze the first status parameter of the walnut tree, and determine the target monitoring part of the walnut tree according to the abnormal value of the first status parameter of the walnut tree, so as to collect the corresponding image as the monitoring image of the walnut tree, providing a basis for subsequent judgment of whether there are pests and diseases and the type of pests and diseases.

[0039] Exemplarily, if after analyzing the first state parameter, it is found that the fruit moisture content is less than the preset moisture threshold, the monitoring image of the walnut tree is a fruit image; if after analyzing the first state parameter, it is found that the chlorophyll content is less than the preset chlorophyll content threshold, the monitoring image of the walnut tree is a leaf image; if after analyzing the first state parameter, it is found that the growth rate of the tree top is less than the preset growth rate threshold, the monitoring image of the walnut tree is a tree top image. The above preset thresholds are all empirically set according to the values of normal and healthy walnut trees.

[0040] S103: Determine the target monitoring result of the walnut tree state based on the monitoring image of the walnut tree.

[0041] In this embodiment, the monitoring image of the walnut tree is an image corresponding to the specific monitoring part of the walnut tree obtained by analyzing the first state parameter that will be affected by diseases and pests. Then, in this embodiment, the monitoring image of the walnut tree is preprocessed, features are extracted, and the features extracted are analyzed to obtain the target monitoring result of the walnut tree state.

[0042] The target monitoring result of the walnut tree state is whether it is affected by diseases and pests. When the monitoring image of the walnut tree is analyzed and relevant features of diseases and pests are found, the target monitoring result is that the walnut tree is affected by diseases and pests and the types of diseases and pests.

[0043] It can be concluded from the above that the present disclosure can quickly capture the abnormal conditions of the walnut tree through the initial monitoring of the state parameters of the walnut tree, providing strong support for subsequent precise monitoring. Secondly, when an abnormal state is detected, the present disclosure can specifically obtain the monitoring image of the walnut tree based on the first state parameter that may be affected by diseases and pests. The present disclosure not only improves the pertinence of monitoring, but also effectively avoids waste of resources, making the monitoring work more efficient and timely. Finally, by further analyzing the monitoring image, the target monitoring result of the walnut tree state can be obtained, which not only helps to timely discover and handle the diseases and pests problems of the walnut tree, but also effectively improves the yield and quality of the walnut tree. Therefore, the present disclosure can monitor the state of the walnut tree timely and reliably.

[0044] In an embodiment of the present disclosure, determining the monitoring image of the walnut tree based on the first state parameter of the walnut tree includes: Determine a plurality of standard state parameters based on the growth period of the walnut tree; the first state parameter includes a plurality of actual parameters of the growth period of the walnut tree, and each standard state parameter corresponds to a monitoring part of the walnut tree; Determine the target similarity based on each actual parameter and each standard physiological parameter; Determine the monitoring part of the walnut tree based on the target similarity; Collect monitoring images of the walnut tree based on the monitored parts of the walnut tree.

[0045] In this embodiment, the first state parameter is a parameter that can be affected by pests and diseases, and can reflect that the walnut tree may be invaded by pests and diseases. The first state parameter is a parameter obtained by actual measurement of the walnut tree during its growth period. The above parameters reflect the current actual growth and physiological conditions of the walnut tree, including various growth parameters (such as tree height, new shoot length, fruit size, etc.) and physiological parameters (such as photosynthetic rate, chlorophyll content, enzyme activity, etc.).

[0046] The standard state parameter is an important reference standard for judging whether the walnut tree is healthy, and each standard state parameter corresponds to a specific monitored part of the walnut tree. For example, a certain standard chlorophyll content corresponds to the leaf part, and a certain standard trunk sap flow rate corresponds to the trunk part, etc.

[0047] The target similarity is a quantitative index used to measure the similarity between the actual parameters of the walnut tree and the standard state parameters. In this embodiment, the target similarity can be calculated by the cosine similarity, and the proximity of the actual state of each part of the walnut tree to the normal state can be judged.

[0048] The monitored part is a specific position on the walnut tree body that needs to be monitored key points, such as leaves, branches, fruits, roots, etc. According to the calculation result of the target similarity, determine which parts may be abnormal, so as to be the acquisition object of the monitoring image.

[0049] The monitoring image is an image obtained by photographing the determined monitored parts of the walnut tree through an image acquisition device. These images are used to further analyze the state of the walnut tree and judge whether there are problems such as pests and diseases and abnormal growth.

[0050] Specifically, the steps of this embodiment can be as follows: First, this embodiment accurately judges the growth period of the walnut tree, which can be determined by monitoring the appearance characteristics of the tree body (such as whether it is flowering, the fruit development stage, etc.) and collecting planting records. After determining the growth period, obtain a series of standard state parameters corresponding to this growth period from the pre-established database. For example, when it is determined that the walnut tree is in the fruit swelling period, the standard growth rate of the fruit, the standard photosynthetic rate of the leaves, the standard diameter growth value of the trunk, etc. in this stage are retrieved from the database, and at the same time, clarify the monitored parts corresponding to each standard parameter, such as the fruit growth rate corresponding to the fruit part, the photosynthetic rate corresponding to the leaf part, etc.

[0051] Secondly, measure the actual parameters of the walnut tree to obtain the actual values of each in the first state parameter. Then compare each actual parameter with the corresponding standard state parameter, and the target similarity between them can be calculated by algorithms such as the cosine similarity algorithm or the Euclidean distance algorithm.

[0052] Then, based on the calculated target similarity, a similarity threshold is set. If the target similarity between the actual parameters and the standard parameters corresponding to a certain monitored part is lower than the threshold, it indicates that there may be an abnormality in this part, and it is determined as the part that needs to be monitored key.

[0053] Finally, an image acquisition device (such as a camera, a camera device carried by a drone, etc.) is used to take pictures of the determined monitored parts to obtain monitoring images.

[0054] It can be concluded from the above that in this embodiment, by accurately matching the standards of the growth stages of walnut trees with the actual state parameters, the parts with possible pests, diseases or growth abnormalities of walnut trees are effectively identified. This embodiment not only improves the accuracy and efficiency of monitoring, but also reduces unnecessary image acquisition and saves resources.

[0055] In an embodiment of the present disclosure, determining a target monitoring result of the state of a walnut tree based on an image of the walnut tree includes: Preprocessing the image of the walnut tree to obtain a target walnut tree image; Extracting pest and disease characteristics from the target walnut tree image to obtain a feature vector; Based on the target support vector machine model, classifying the feature vector to determine the pest and disease types of the walnut tree, and the pest and disease types of the walnut tree are the target monitoring results of the state of the walnut tree.

[0056] In this embodiment, the target walnut tree image is an image obtained after performing image enhancement processing on the image of the walnut tree.

[0057] Specifically, preprocessing the image of the walnut tree to obtain a target walnut tree image includes: Determining the standard deviation of pixel values of the image of the walnut tree; In response to the standard deviation of pixel values being greater than or equal to the first standard deviation threshold, performing noise reduction processing on the image of the walnut tree to obtain a target walnut tree image; In response to the standard deviation of pixel values being less than the first standard deviation threshold, directly using the image of the walnut tree as the target walnut tree image.

[0058] In this embodiment, the standard deviation of pixel values is used to measure the degree of dispersion of pixel values in the image and can estimate the noise level. The larger the standard deviation of pixel values, the greater the difference between pixel values and the more noise exists in the image. The first standard deviation threshold is a preset reference value used as a standard for determining whether the walnut tree image needs to be subjected to noise reduction processing.

[0059] When the calculated standard deviation of pixel values is greater than or equal to a pre-set first standard deviation threshold, it indicates that there is more noise in the image, and appropriate noise reduction algorithms such as Gaussian filtering, median filtering, etc. need to be used to process the image to obtain a target walnut tree image with less noise.

[0060] If the calculated standard deviation of pixel values is less than the first standard deviation threshold, it means that the noise level in the image is low, and no noise reduction processing is required. The original walnut tree image can be directly used as the target walnut tree image for subsequent analysis.

[0061] Extract information from the target walnut tree image that can characterize the presence and type of pests and diseases, and quantify and organize the above-extracted pest and disease characteristics to form an ordered set of data as the input to the target support vector machine model. For example, in this embodiment, through methods such as edge detection and color segmentation, features such as disease spots and insect holes on the leaves are identified, and then these features are quantified, such as the size, shape, and color distribution of the disease spots, and the number and location of the insect holes, etc., and converted into a set of numerical values to form a feature vector.

[0062] The target support vector machine model is a trained support vector machine model that has learned the association between a large number of historical pest and disease feature vectors and pest and disease types. The target support vector machine model is used to classify the input feature vector to determine the pest and disease type of the walnut tree.

[0063] From the above, it can be concluded that this embodiment can accurately and quickly determine the pest and disease type of the walnut tree, that is, the target monitoring result of the walnut tree state, which not only improves the accuracy of pest and disease identification, but also greatly shortens the monitoring period, providing strong support for the timely prevention and control of the walnut tree.

[0064] In an embodiment of the present disclosure, the target support vector machine includes an objective function; A walnut tree state monitoring method further includes: Determine the initial penalty parameter of the objective function; In response to the prediction accuracy requirement being greater than or equal to the first accuracy threshold, control the initial penalty parameter to increase by the first step size to obtain the target penalty parameter; In response to the prediction accuracy requirement being less than the first accuracy threshold, control the initial penalty parameter to decrease by the second step size to obtain the target penalty parameter.

[0065] In this embodiment, the target support vector machine is a supervised machine learning algorithm that can be used for classification tasks. By finding an optimal hyperplane to separate data points of different classes, the interval between different classes is maximized. In the target support vector machine, the objective function is used to measure the performance of the model, which can maximize the interval or minimize the combination of classification error and model complexity.

[0066] The penalty parameter is used to control the degree of penalty for misclassified samples by the support vector machine. A larger penalty parameter means a stricter penalty for misclassification, and the model will tend to reduce the misclassified points in the training data; a smaller penalty parameter allows the model to have more misclassified points, which can improve the generalization ability of the model, but may reduce the classification accuracy.

[0067] The prediction accuracy requirement refers to the requirement for the accuracy of the prediction results of the support vector machine model in the walnut tree status monitoring task. The first accuracy threshold is a preset reference value used to judge the level of the prediction accuracy requirement to determine how to adjust the penalty parameter. The first step size is the fixed step size used to increase the initial penalty parameter when the prediction accuracy requirement is high. The second step size is the fixed step size used to decrease the initial penalty parameter when the prediction accuracy requirement is low. Among them, the first accuracy threshold, the first step size, and the second step size can all be set according to experience.

[0068] Specifically, if the requirement for the model prediction accuracy is high, reaching or exceeding the preset first accuracy threshold, then increase the value of the initial penalty parameter according to the set first step size. The parameter value obtained after adjustment is the target penalty parameter, which is used for subsequent model training or prediction. When the prediction accuracy requirement is low, less than the first accuracy threshold, then decrease the value of the initial penalty parameter according to the set second step size. The finally obtained parameter value is the target penalty parameter, so as to adjust the complexity of the model to make it more in line with the generalization ability requirement under the lower accuracy requirement.

[0069] It can be concluded from the above that the present embodiment introduces the objective function of the target support vector machine and the dynamic adjustment mechanism of its penalty parameter, which significantly improves the flexibility and accuracy of monitoring. According to the actual demand of the prediction accuracy, the penalty parameter of the objective function is intelligently adjusted to ensure that while meeting the accuracy requirement, the model performance is optimized. By precisely controlling the increase and decrease step sizes of the penalty parameter, this method effectively balances the complexity and generalization ability of the model on the premise of ensuring the prediction accuracy.

[0070] In an embodiment of the present disclosure, a walnut tree status monitoring method further includes: In response to the initial monitoring result of the walnut tree status being the normal state, predicting based on the second state parameter of the walnut tree to obtain the predicted state parameter of the walnut tree; the second state parameter is data related to the growth trend of the walnut tree.

[0071] In this embodiment, the second state parameter of the walnut tree may include growth data and fruit-bearing data.

[0072] When the initial monitoring result of the walnut tree's state is the normal state, it indicates that the walnut tree is growing healthily. Based on the time series analysis model, the growth data and result data of the walnut tree can be predicted to determine the growth trend of the walnut tree, realizing the intelligent prediction of the growth trend of the walnut tree and providing a scientific basis for walnut planting. Among them, the time series analysis model can be a trained long short-term memory network model, which can mine the variation law of state parameters over time.

[0073] The growth data can include the germination rate, the branch formation rate, the medium and short branch rate, etc.; the result data can include the fruit setting rate, the fruit weight, the yield per plant, etc. For example, according to the germination rate data and the environmental data, the future germination rate can be predicted; according to the fruit setting rate data and the environmental data during the flowering period, the future fruit setting rate can be predicted; according to the yield data and the environmental data during the fruit development period, the future yield can be predicted.

[0074] Specifically, in this embodiment, by continuously collecting the current state parameters and using the time series analysis model to learn and simulate the above rules, the future state of the walnut tree can be estimated in advance, providing forward-looking information for the long-term management and maintenance of the walnut tree, so as to take measures in advance to ensure its continuous healthy growth.

[0075] Corresponding to a walnut tree state monitoring method in the above embodiment, Figure 2 is a structural block diagram of a walnut tree state monitoring system provided by an embodiment of the present disclosure. For the sake of illustration, only the parts related to the embodiments of the present disclosure are shown. Refer to Figure 2 This walnut tree state monitoring system 20 includes: an initial monitoring module 21, a monitoring image determination module 22, and a target monitoring module 23.

[0076] Among them, the initial monitoring module 21 is used to determine the initial monitoring result of the walnut tree state based on the state parameters of the walnut tree; The monitoring image determination module 22 is used to determine the monitoring image of the walnut tree based on the first state parameters of the walnut tree in response to the initial monitoring result of the walnut tree state being an abnormal state; the first state parameters are the parameters affected by diseases and pests; The target monitoring module 23 is used to determine the target monitoring result of the walnut tree state based on the monitoring image of the walnut tree.

[0077] In an embodiment of the present disclosure, the state parameters of the walnut tree include physiological parameters and growth parameters; The initial monitoring module 21 is specifically used to determine the first suspicion degree based on the physiological parameters of the walnut tree; Determine the second suspicion degree based on the growth parameters of the walnut tree; Perform weighted calculation on the first suspicion degree and the second suspicion degree to determine the disease and pest suspicion degree; Determine the initial monitoring result of the walnut tree state based on the disease and pest suspicion degree.

[0078] In one embodiment of the present disclosure, the initial monitoring module 21 is further specifically configured to: if the pest and disease suspicion degree is greater than or equal to the first suspicion degree threshold, the initial monitoring result of the walnut tree state is an abnormal state; if the pest and disease suspicion degree is less than the first suspicion degree threshold, the initial monitoring result of the walnut tree state is a normal state.

[0079] In one embodiment of the present disclosure, the monitoring image determination module 22 is specifically configured to determine a plurality of standard state parameters based on the growth period of the walnut tree; the first state parameter includes a plurality of actual parameters of the growth period of the walnut tree, and each standard state parameter corresponds to a monitoring part of the walnut tree; determine the target similarity based on each actual parameter and each standard state parameter; determine the monitoring part of the walnut tree based on the target similarity; collect the monitoring image of the walnut tree based on the monitoring part of the walnut tree.

[0080] In one embodiment of the present disclosure, the target monitoring module 23 is specifically configured to preprocess the image of the walnut tree to obtain a target walnut tree image; extract pest and disease features from the target walnut tree image to obtain a feature vector; classify the feature vector based on the target support vector machine model to determine the pest and disease type of the walnut tree, and the pest and disease type of the walnut tree is the target monitoring result of the walnut tree state.

[0081] In one embodiment of the present disclosure, the target support vector machine includes an objective function; A walnut tree state monitoring system 20 further includes: a parameter adjustment module, configured to determine an initial penalty parameter of the objective function; in response to the prediction accuracy requirement being greater than or equal to the first accuracy threshold, control the initial penalty parameter to increase by a first step length to obtain a target penalty parameter; in response to the prediction accuracy requirement being less than the first accuracy threshold, control the initial penalty parameter to decrease by a second step length to obtain a target penalty parameter.

[0082] In one embodiment of the present disclosure, a walnut tree state monitoring system 20 further includes: a growth trend prediction module, configured to, in response to the initial monitoring result of the walnut tree state being a normal state, perform a prediction based on the second state parameter of the walnut tree to obtain a predicted state parameter of the walnut tree; the second state parameter is data related to the growth trend of the walnut tree.

[0083] See Figure 3 , Figure 3 is a schematic block diagram of an electronic device provided in an embodiment of the present disclosure. As Figure 3The electronic device 300 in the present embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The above-mentioned processors 301, input devices 302, output devices 303, and memories 304 communicate with each other through a communication bus 305. The memory 304 is used to store a computer program, and the computer program includes program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. Among them, the processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above system embodiments, for example Figure 2 the functions of the initial monitoring module 21, the monitoring image determination module 22, and the target monitoring module 23 shown.

[0084] It should be understood that in the embodiments of the present disclosure, the so-called processor 301 may be a central processing unit (CPU), and this processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0085] The input device 302 may include a touchpad, a fingerprint acquisition sensor (for acquiring the fingerprint information and the direction information of the fingerprint of the user), a microphone, etc., and the output device 303 may include a display (such as an LCD), a speaker, etc.

[0086] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A part of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0087] In specific implementation, the processors 301, input devices 302, and output devices 303 described in the embodiments of the present disclosure may implement the implementation manners described in the first embodiment and the second embodiment of a walnut tree status monitoring method provided by the embodiments of the present disclosure, and may also implement the implementation manner of the electronic device described in the embodiments of the present disclosure, which will not be elaborated here.

[0088] In another embodiment of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, all or part of the processes in the methods of the above embodiments are implemented. It can also be completed by instructing relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0089] The computer-readable storage medium can be the internal storage unit of the electronic device in any of the foregoing embodiments, such as the hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk equipped on the electronic device, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the computer-readable storage medium can also include both the internal storage unit and the external storage device of the electronic device. The computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store the data that has been output or will be output.

[0090] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0091] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described electronic devices and units can refer to the corresponding processes in the foregoing method embodiments and will not be described in detail here.

[0092] In several embodiments provided by this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed couplings or direct couplings or communication connections to each other can be indirect couplings or communication connections through some interfaces or units, and can also be electrical, mechanical or other forms of connection.

[0093] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present disclosure.

[0094] In addition, each functional unit in various embodiments of the present disclosure can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0095] The above is only the specific implementation manner of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present disclosure can easily think of various equivalent modifications or replacements, and these modifications or replacements should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A method for monitoring the state of a walnut tree, characterized in that Including: Determining an initial monitoring result of the walnut tree status based on the status parameters of the walnut tree; In response to the initial monitoring result of the walnut tree status being an abnormal status, determining a monitoring image of the walnut tree based on the first status parameter of the walnut tree; the first status parameter is a parameter that will be affected by pests and diseases; Determining a target monitoring result of the walnut tree status based on the monitoring image of the walnut tree.

2. The walnut tree status monitoring method according to claim 1, wherein The status parameters of the walnut tree include physiological parameters and growth parameters; The determining of the initial monitoring result of the walnut tree status based on the status parameters of the walnut tree includes: Determining a first suspicion degree based on the physiological parameters of the walnut tree; Determining a second suspicion degree based on the growth parameters of the walnut tree; Performing weighted calculation on the first suspicion degree and the second suspicion degree to determine a pest and disease suspicion degree; Determining the initial monitoring result of the walnut tree status based on the pest and disease suspicion degree.

3. The method for monitoring the state of a walnut tree according to claim 2, wherein The determining of the initial monitoring result of the walnut tree status based on the pest and disease suspicion degree includes: If the pest and disease suspicion degree is greater than or equal to a first suspicion degree threshold, the initial monitoring result of the walnut tree status is an abnormal status; If the pest and disease suspicion degree is less than the first suspicion degree threshold, the initial monitoring result of the walnut tree status is a normal status.

4. The walnut tree state monitoring method according to claim 1, characterized in that, The determining of the monitoring image of the walnut tree based on the first status parameter of the walnut tree includes: Determining a plurality of standard status parameters based on the growth period of the walnut tree; the first status parameter includes a plurality of actual parameters of the growth period of the walnut tree, and each standard status parameter corresponds to a monitoring part of the walnut tree; Determining a target similarity based on each actual parameter and each standard status parameter; Determining the monitoring part of the walnut tree based on the target similarity; Collecting a monitoring image of the walnut tree based on the monitoring part of the walnut tree.

5. The walnut tree state monitoring method according to claim 1, wherein, The determining of the target monitoring result of the walnut tree status based on the image of the walnut tree includes: Performing preprocessing on the image of the walnut tree to obtain a target walnut tree image; Performing pest and disease feature extraction on the target walnut tree image to obtain a feature vector; Classifying the feature vector based on a target support vector machine model to determine the pest and disease type of the walnut tree, and the pest and disease type of the walnut tree is the target monitoring result of the walnut tree status.

6. The walnut tree status monitoring method according to claim 5, characterized in that, The target support vector machine includes an objective function; The method for monitoring the status of a walnut tree further includes: Determining an initial penalty parameter of the objective function; In response to the prediction accuracy requirement being greater than or equal to a first accuracy threshold, controlling the initial penalty parameter to increase by a first step length to obtain a target penalty parameter; In response to the prediction accuracy requirement being less than the first accuracy threshold, controlling the initial penalty parameter to decrease by a second step length to obtain a target penalty parameter.

7. The state monitoring method of a walnut tree according to claim 1, characterized in that It further includes: In response to the initial monitoring result of the walnut tree status being a normal status, predicting based on the second status parameter of the walnut tree to obtain a predicted status parameter of the walnut tree; the second status parameter is data related to the growth trend of the walnut tree.

8. A walnut tree status monitoring system, characterized in that, Including: An initial monitoring module, configured to determine an initial monitoring result of the walnut tree status based on the status parameters of the walnut tree; A monitoring image determination module, configured to determine a monitoring image of the walnut tree based on a first state parameter of the walnut tree in response to an initial monitoring result of the state of the walnut tree being an abnormal state; the first state parameter is a parameter that will be affected by pests and diseases. A target monitoring module, configured to determine a target monitoring result of the state of the walnut tree based on the monitoring image of the walnut tree.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images