Method for determining buffer distance of plant protection unmanned aerial vehicle spraying based on pesticide damage detection limit and related equipment

Abstract

The application discloses a plant protection unmanned aerial vehicle spraying pesticide buffer distance determination method based on a pesticide damage detection limit and related equipment, and relates to the technical field of plant protection unmanned aerial vehicles. The application discloses a plant protection unmanned aerial vehicle spraying pesticide buffer distance determination method based on a pesticide damage detection limit and related equipment, and relates to the technical field of plant protection unmanned aerial vehicles. The application discloses a plant protection unmanned aerial vehicle spraying pesticide buffer distance determination method based on a pesticide damage detection limit and related equipment, and relates to the technical field of plant protection unmanned aerial vehicles. The application discloses a plant protection unmanned aerial vehicle spraying pesticide buffer distance determination method based on a pesticide damage detection limit and related equipment, and relates to the technical field of plant protection unmanned aerial vehicles. The application discloses a plant protection unmanned aerial vehicle spraying pesticide buffer distance determination method based on a pesticide damage detection limit and related equipment, and relates to the technical field of plant protection unmanned aerial vehicles. The application discloses a plant protection unmanned aerial vehicle spraying pesticide buffer distance determination method based on a pesticide damage detection limit and related equipment, and relates to the technical field of plant protection unmanned aerial vehicles. The application discloses a plant protection unmanned aerial vehicle spraying pesticide buffer distance determination method based on a pesticide damage detection limit and related equipment, and relates to the technical field of plant protection unmanned aerial vehicles. The application discloses a plant protection unmanned aerial vehicle spraying pesticide buffer distance determination method based on a pesticide damage detection limit and related equipment, and relates to the technical field of plant protection unmanned aerial vehicles. The application discloses a plant protection unmanned aerial vehicle spraying pesticide buffer distance determination method based on a pesticide damage detection limit and related equipment, and relates to the technical field of plant protection unmanned aerial vehicles. The application discloses a plant protection unmanned aerial vehicle spraying pesticide buffer distance determination method based on a pesticide damage detection limit and related equipment, and relates to the technical field of plant protection unmanned aerial vehicles. The application discloses a plant protection unmanned aerial vehicle spraying pesticide buffer distance determination method based on a pesticide damage detection limit and related equipment, and relates to the technical field of plant protection unmanned aerial vehicles. The application discloses a plant protection unmanned aerial vehicle spraying pesticide buffer distance determination method based on a pesticide damage detection limit and related equipment, and relates to the technical field of plant protection unmanned aerial vehicles. The application discloses a plant protection unmanned aerial vehicle spraying pesticide buffer distance determination method based on a pesticide damage detection limit and related equipment, and relates to the technical field of plant protection unmanned aerial vehicles. The application discloses a plant protection unmanned aerial vehicle spraying pesticide buffer distance determination method

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of agricultural plant protection technology, and in particular to a method and device for determining a buffer distance for spraying and applying pesticides by a plant protection unmanned aerial vehicle based on a pesticide damage detection limit. BACKGROUND

[0002] In the process of planting crops, in order to ensure the normal growth of crops, farmers will use pesticides, fungicides and herbicides to prevent and control pests and weeds. Among them, herbicides achieve the purpose of weeding and protecting seedlings through time difference, position difference, shape, physiology and biochemistry. Although herbicides have selectivity for crops (such as wheat) in the herbicide field, they pose a potential risk to other crops on adjacent fields or field ridges.

[0003] With the wide application of plant protection unmanned aerial vehicles, the problem of pesticide drift is becoming more and more serious. Due to the unreasonable use of herbicides in farmland, other crops planted in the surrounding area are often affected, leading to growth inhibition and yield reduction. Pesticide drift not only damages surrounding sensitive crops, but also poses a challenge to environmental protection, attracting people's high attention to its potential harm. Therefore, how to reasonably judge the adverse effects of pesticides on adjacent crops and set a reasonable buffer distance has become a problem to be solved. SUMMARY

[0004] In view of the above defects or deficiencies in the prior art, it is desirable to provide a method and device for determining a buffer distance for spraying and applying pesticides by a plant protection unmanned aerial vehicle based on a pesticide damage detection limit, which can reasonably set the buffer distance for spraying and applying pesticides by a plant protection unmanned aerial vehicle based on the accurate pesticide damage detection limit of the drift amount of adjacent crops, effectively reduce the impact of pesticides on adjacent fields on the basis of ensuring reasonable pesticide application to target fields, and improve the total yield of crops.

[0005] In a first aspect, the embodiments of the present application provide a method for determining a buffer distance for spraying and applying pesticides by a plant protection unmanned aerial vehicle based on a pesticide damage detection limit, comprising:

[0006] Selecting a plurality of downwind distances based on a reference position of a test flight of a plant protection unmanned aerial vehicle;

[0007] Placing a plurality of ground drift amount collection devices at each of the downwind distances along the flight direction of the plant protection unmanned aerial vehicle;

[0008] After the plant protection unmanned aerial vehicle flies based on different test parameters, collecting ground drift droplets collected by the ground drift amount collection devices;

[0009] Determining the ground drift amount corresponding to each of the downwind distances according to the ground drift amount collection devices, and generating a first mapping relationship between the downwind distances and the ground drift amounts;

[0010] construct a ground drift amount prediction model related to the distance from the downwind direction under different characteristic parameters;

[0011] obtain a second mapping relationship between the degree of pesticide damage to the sensitive crop plants in the adjacent land and the drift amount of the ground drift device at the corresponding position, and determine the drift amount pesticide damage detection limit of the sensitive crop plants;

[0012] According to the ground drift amount prediction model and the drift amount pesticide damage detection limit, determine the buffer distance required for the adjacent land sensitive crop plants to be harmless to the spraying task.

[0013] In some embodiments, the second mapping relationship between the degree of pesticide damage to the sensitive crop plants in the adjacent land and the drift amount of the ground drift device at the corresponding position comprises:

[0014] Place the sensitive crop plants in the adjacent land at different downwind distances, and place the ground drift device at the corresponding position of the plant to conduct pesticide damage test on the sensitive crop plants, and obtain the sensitive crop plants after the test and the ground drift amount at the corresponding position;

[0015] Extract all the leaves of the sensitive crop plants after the test and make leaf patterns;

[0016] Obtain the pesticide damage pixel features and leaf pixel features corresponding to the leaf patterns;

[0017] Determine the yellowing ratio of the sensitive crop plants after the test based on the pesticide damage pixel features and the leaf pixel features;

[0018] Based on the ground drift amount of the sensitive crop plants after the test and the yellowing ratio, generate a second mapping relationship between the degree of pesticide damage and the ground drift amount of the ground drift device at the corresponding position of the sensitive crop plants.

[0019] In some embodiments, the ground drift amount corresponding to each downwind distance is determined by the ground drift amount acquisition device, comprising:

[0020] For any downwind distance, the ground drift amount acquisition device uses deionized water to elute the pesticide solution collected in the ground drift amount acquisition device to obtain an eluate;

[0021] Measure and record the fluorescence value of the eluate using a fluorescence instrument; wherein the plant protection unmanned aerial vehicle spraying test uses ABF fluorescent tracer and the test pesticide solution of 0.1% of the tested pesticide;

[0022] Determine the ground drift amount corresponding to the downwind distance according to the fluorescence value.

[0023] In some embodiments, the ground drift amount corresponding to the downwind distance is determined by the following formula:

[0024]

[0025] wherein β dep is the drift amount per unit area of the droplets, in mL / cm 2 ; F cal is the relationship coefficient of the fluorescence value and the tracer concentration, in μg / L; V dil is the volume of the eluent, in mL; ρ smpl is the absorbance of the eluent; ρ blk is the fluorescence value of the blank plastic culture dish; ρ spray is the tracer concentration of the spray liquid, in g / L; A col is the area of the plastic culture dish, in cm 2 .

[0026] In some embodiments, the ground drift amount prediction model related to the downwind distance is constructed by comprising:

[0027] constructing an initial ANN artificial neural network model and GWO algorithm parameters;

[0028] taking the structural features of the initial ANN artificial neural network model as prey, calculating the position vector of the wolf pack; and calculating the fitness corresponding to the current wolf pack position vector based on the training set;

[0029] calculating the information of the three gray wolves with the optimal fitness, updating the position vectors thereof and the position vector of the wolf pack, and iteratively training the same;

[0030] when the termination condition is met, assigning the position vector of the wolf pack of the current iteration round to the ANN artificial neural network model to obtain the ground drift amount prediction model.

[0031] In some embodiments, the buffer distance required for the sensitive crop plants of the adjacent plots to be harmless to the spray application task to be performed is determined according to the ground drift amount prediction model and the drift amount phytotoxicity limit by comprising:

[0032] predicting the spray application task to be performed by using the ground drift amount prediction model to obtain the predicted ground drift amount of the spray application task to be performed at each downwind distance;

[0033] comparing the predicted ground drift amount of the spray application task to be performed at each downwind distance with the drift amount phytotoxicity limit to determine the downwind distance corresponding to the drift amount matching the drift amount phytotoxicity limit;

[0034] The preset downwind distance adjacent to and smaller than the downwind distance under the foundation is taken as the buffer distance.

[0035] In some embodiments, the phytotoxicity detection limit is 0-1% of the phytotoxicity degree.

[0036] In a second aspect, the embodiments of the present application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method described in the embodiments of the present application when executing the program.

[0037] In a third aspect, the embodiments of the present application provide a computer readable storage medium, having a computer program stored thereon, and the program is executable on a processor to implement the method described in the embodiments of the present application.

[0038] In a fourth aspect, the embodiments of the present application provide a computer program product, including a computer program, and the computer program is executable on a processor to implement the method described in the embodiments of the present application.

[0039] The method for determining the buffer distance of the plant protection unmanned aerial vehicle spraying application based on the phytotoxicity detection limit can obtain the drift phytotoxicity detection limit by using the second mapping relationship between the ground drift amount and the phytotoxicity degree constructed by the prior test, and can realize the accurate prediction of the ground drift amount at different downwind distances under different characteristic parameters by constructing the ground drift amount prediction model by the test, and further determine the buffer distance required for the adjacent land to be harmless to the spraying application task to be executed, thereby providing guidance for the safe spraying application of the plant protection unmanned aerial vehicle.

[0040] Additional aspects and advantages of the application will be set forth in part in the description that follows, and in part will become apparent to those skilled in the art upon examination of the following and / or can be learned by practice of the application. BRIEF DESCRIPTION OF DRAWINGS

[0041] Other features, objects, and advantages of the application will become more apparent from the following detailed description of non-limiting embodiments thereof, when read in conjunction with the accompanying drawings:

[0042] Figure 1 An implementation environment architecture diagram of a terminal interface recognition method provided by the embodiments of the present application is shown.

[0043] Figure 2 A structural schematic diagram of a computer system of an electronic device or a server suitable for implementing the embodiments of the present application is shown. DETAILED DESCRIPTION

[0044] The application will be described in further detail below with reference to the drawings and embodiments. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not intended to limit the scope of the application. In addition, it should be noted that only parts related to the application are shown in the drawings for ease of description.

[0045] It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict. The present application will be described in detail below with reference to the drawings and embodiments.

[0046] In order to further illustrate the technical solutions provided by the embodiments of the present application, the following will be described in detail in combination with the drawings and specific embodiments. Although the embodiments of the present application provide the method operation instruction steps as shown in the following embodiments or drawings, more or less operation instruction steps can be included in the method based on conventional or non-creative labor. The execution order of the steps is not limited to the execution order provided by the embodiments of the present application in the logical sense. The method can be executed in sequence or in parallel when actually processed or executed by the device, as shown in the embodiments or drawings.

[0047] Reference is made to Figure 1 , Figure 1 A flowchart of a method for determining a buffer distance of a plant protection unmanned aerial vehicle spraying according to an embodiment of the present application is shown. As shown in Figure 1 , the method comprises:

[0048] Step 101, based on the reference position of the plant protection unmanned aerial vehicle test flight, a plurality of downwind distances are selected.

[0049] It should be noted that the downwind distance is the distance from the position of the plant protection unmanned aerial vehicle downwind direction and the edge of the plant protection unmanned aerial vehicle spraying range. Optionally, the downwind distance can be determined according to the plant protection unmanned aerial vehicle spraying environment, such as the distance between adjacent two plots. Preferably, the downwind distance can be selected as 3m, 5m, 10m, 15m, 20m, 30m and 50m, which is not limited in the present application.

[0050] Step 102, at each downwind distance along the flight direction of the plant protection unmanned aerial vehicle, a plurality of ground drift amount collection devices are placed.

[0051] Among them, the ground drift amount collection device can be a collection container with a certain opening, such as a plastic culture dish.

[0052] Optionally, the ground drift amount collecting device can be placed continuously along the flight direction of the plant protection unmanned aerial vehicle, for example, it can be placed according to a preset interval along the flight distance, or it can be placed according to a preset number of placements to calculate the corresponding placement interval according to the flight distance. Preferably, the preset number of placements can be 9, that is, based on the flight distance of the plant protection unmanned aerial vehicle and the preset number of placements is 9, the placement interval is calculated, and then a plurality of ground drift amount collecting devices are placed at each point according to the placement interval.

[0053] Step 103, after the plant protection unmanned aerial vehicle implements flight based on different test parameters, the ground drift droplets collected by the ground drift amount collecting device are obtained.

[0054] That is, during the test, the plant protection unmanned aerial vehicle will implement multiple flights based on different test parameters, and after each flight, the ground drift droplets collected by the ground drift amount collecting device are collected to supplement the test data corresponding to the test flight.

[0055] In a feasible embodiment, the test parameters include but are not limited to flight height, flight speed, droplet size, average environmental wind speed, average temperature, average humidity, nozzle rotation speed and downwind distance.

[0056] Step 104, determining the ground drift amount corresponding to each downwind distance according to the ground drift amount collecting device, and generating a first mapping relationship between the downwind distance and the ground drift amount.

[0057] In a feasible embodiment, determining the ground drift amount corresponding to each downwind distance according to the ground drift amount collecting device, and generating a first mapping relationship between the downwind distance and the ground drift amount, includes: for the ground drift amount collecting device of any downwind distance, eluting the pesticide solution collected in the ground drift amount collecting device with deionized water to obtain an eluate, and using a fluorescence instrument to measure and record the fluorescence value of the eluate. Wherein, the plant protection unmanned aerial vehicle spray test adopts ABF fluorescent tracer and the test pesticide is 0.1%. The fluorescence value is used to determine the ground drift amount corresponding to the downwind distance.

[0058] Optionally, the ground drift amount corresponding to the downwind distance is determined by the following formula:

[0059]

[0060] Wherein, β dep is the drift amount of droplets per unit area, with units of mL / cm 2 ; F cal is the relationship coefficient of fluorescence value and tracer concentration, with units of μg / L; V dil is the volume of the eluate, with units of mL; ρ smpl is the absorbance of the eluate; ρblk is the fluorescence value of a blank plastic petri dish; p spray is the tracer concentration of the spray liquid, in g / L; A col is the area of the plastic petri dish, in cm 2 .

[0061] Step 105, constructing a ground drift amount prediction model related to the downwind distance under different characteristic parameters.

[0062] Specifically, the method comprises: obtaining historical test data of a plant protection unmanned aerial vehicle spraying test, preprocessing the historical test data to obtain preprocessed historical test data, performing correlation analysis on the preprocessed historical test data based on a random forest algorithm, determining at least one target characteristic parameter for spraying drift amount prediction, obtaining preprocessed test parameter data corresponding to the target characteristic parameter, and constructing a training set and a test set. Then, an initial ANN-GWO artificial neural network model is constructed, and the training set and the test set are used to train the initial ANN-GWO artificial neural network model to obtain a ground drift amount prediction model for spraying drift amount prediction.

[0063] It should be noted that preprocessing the historical test data can reduce the interference of false data and improve the reliability and accuracy of the data.

[0064] In the embodiments of the present application, preprocessing the historical test data comprises deleting missing values in the historical test data. Specifically, a group of historical test data having missing values is deleted, and preferably, a group of historical test data having missing values in the test parameter data corresponding to the candidate characteristic parameter is deleted.

[0065] Further, the historical test data after processing the missing values is normalized and standardized in the embodiments of the present application.

[0066] It should be noted that normalizing the historical test data can scale the test parameter data corresponding to a plurality of candidate characteristic parameters to a unified measurement range, such as [0, 1], so as to avoid abnormal weight influence in subsequent analysis caused by large differences between the test parameter data. In addition, standardizing the historical test data can make the processed data conform to the standard normal distribution, further improving the reliability and accuracy of the data in subsequent use.

[0067] Specifically, the following formula can be used for normalization:

[0068]

[0069] wherein, x i is the original historical test data to be normalized, is the normalized historical test data, the value range of which is [0, 1], x max is the maximum value in the original historical test data;

[0070] The standardization processing is performed by using the following formula:

[0071]

[0072] wherein μ is the mean value of the normalized historical test data, and σ is the standard deviation of the normalized historical test data, x standardized is the standardized historical test data, the standardized historical test data conforms to the standard normal distribution, the mean value is 0, and the standard deviation is 1.

[0073] It should be further noted that, when the historical test data is standardized, the test parameter data obtained after normalization for each candidate feature parameter can be standardized respectively, so as to improve the feature expression ability of each candidate feature parameter itself.

[0074] In addition, the random forest algorithm is an algorithm for judging the importance of features in the decision tree. Specifically, in the random forest algorithm, the Gini index is used to calculate the importance of each feature. The Gini index is an index for measuring the impurity or uncertainty of data.

[0075] Specifically, the Gini index is calculated by using the following formula:

[0076]

[0077] wherein p k represents the weight of the kth category.

[0078] Further, the random forest algorithm is used to perform correlation analysis based on the preprocessed historical test data, to determine at least one target feature parameter for predicting the spray drift amount, including: obtaining the Gini index difference value of each candidate feature parameter before and after the branch of the decision tree, using the Gini index difference value of each candidate feature parameter to determine the feature contribution amount of each candidate feature parameter, using the ratio of the feature contribution amount of each candidate feature parameter to the total sum of the feature contribution amounts of all candidate feature parameters to determine the contribution value of the candidate feature parameter, and taking at least one candidate feature parameter whose contribution value meets a preset condition as the target feature parameter.

[0079] For example, for the candidate feature parameter j, the Gini index change amount at the node m can be obtained by calculating the difference between the Gini index of the candidate feature parameter j before the branch of the node and the Gini index after the branch. Specifically, the following formula can be used to express,

[0080] VIM jm = GI m-GI l -GI r

[0081] wherein, VIM jm represents the Gini index variation value of the candidate feature parameter j on the node m, GI m represents the Gini index before the branch, GI l and GI r is the Gini index of the two new nodes generated after the branch of the node m.

[0082] Therefore, the feature contribution amount of the candidate feature parameter j in the decision tree i is:

[0083] VIM ij =∑ m∈M VIM jm

[0084] If there are n decision trees in the random forest, then the feature contribution amount of the candidate feature parameter j is:

[0085]

[0086] The contribution value of the candidate feature parameter j is the normalized value of the contribution amount of the candidate feature parameter j:

[0087]

[0088] wherein, VIM′ j represents the contribution amount of the feature j after normalization, represents the sum of the Gini index differences of all features.

[0089] It should be understood that the candidate feature parameter with a larger contribution value is considered to have a greater impact on the decision, therefore, by calculating the Gini index of each candidate feature parameter, the importance degree of the multiple candidate feature parameters in the historical test data can be analyzed, and then at least one candidate feature parameter with a higher importance degree is taken as the target feature parameter.

[0090] Optionally, the N candidate feature parameters with the highest contribution values are taken as the target feature parameters, or at least one candidate feature parameter with a contribution value ratio greater than 50% is taken as the target parameter.

[0091] Preferably, when the downwind distance of the candidate feature parameter meets the selection strategy of the target feature parameter, the downwind distance is directly taken as the target feature parameter, and when the downwind distance of the candidate feature parameter does not meet the selection strategy of the target feature parameter, the downwind distance is taken as the target feature parameter.

[0092] Further, the pre-processed test parameter data corresponding to the target characteristic parameter is acquired to construct a training set and a test set. Preferably, the pre-processed test parameter data corresponding to the target characteristic parameter can be divided into the training set and the test set according to a ratio of 8:2.

[0093] It should be noted that the GWO (Grey Wolf Optimizer) is to take the weights and biases of the neural network model as optimization variables, to perform global search and local development by simulating the hunting behavior of the grey wolf group, and to further find the optimal structure combination.

[0094] In the embodiments of the present application, the parameter combinations of different ANN artificial neural network models are randomly initialized in the exploration space by the GWO algorithm to train the ANN artificial neural network model, and the optimal solution is gradually approached by iteratively updating these solutions to determine the best ANN artificial neural network model structure for predicting the drift amount.

[0095] In the embodiments of the present application, the initial ANN artificial neural network model needs to be constructed according to the number of target characteristic parameters. The GWO algorithm parameters include the number of grey wolves and the maximum number of iterations, wherein the number of grey wolves is greater than or equal to 3.

[0096] Before optimization, all weights and biases of the initial ANN artificial neural network model need to be flattened into a one-dimensional vector and mapped to GWO:

[0097] D = (input_dim x hidden_dim) + hidden_dim + (hidden_dim x output_dim) + output_dim

[0098] Wherein, input_dim is the number of input target characteristic parameters, hidden_dim is the number of neurons in each layer, and output_dim is the number of output results.

[0099] Preferably, the initial position vector of the wolf group is randomly generated. Wherein, the position vector of each grey wolf in the wolf group corresponds to a set of parameters of the ANN artificial neural network model.

[0100] Further, the fitness of each grey wolf position vector in the wolf group is calculated.

[0101] It should be noted that the fitness is used to evaluate the difference between the predicted value generated by the ANN artificial neural network model corresponding to the current wolf group position vector based on the training set and the actual value corresponding to the training set. Wherein, the fitness can adopt the coefficient of determination R 2 , root mean square error RMSE, mean absolute error MAE, etc.

[0102] In the embodiment of the present application, since the target downwind distance needs to be predicted according to the target downwind distance in the subsequent model prediction, that is, the input of the downwind distance feature parameter is focused on, at least the focus on the downwind distance needs to be realized during the model training, while other target feature parameters are also considered.

[0103] Preferably, in the embodiment of the present application, the improved root mean square error is used to calculate the fitness of the current wolf position vector.

[0104] Specifically, the multi-objective optimization strategy is adopted in the present application, that is, the balanced solution is selected by the Pareto front to realize the simultaneous optimization of the model performance and the feature weight distribution. The fitness function is:

[0105]

[0106] Wherein, n is the training number, ω i is the feature weight, O i is the corresponding drift data in the training set, P i is the prediction result according to the test parameter data in the training set.

[0107] It should be noted that the optimization target of the fitness function is to minimize the model error (root mean square error RMSE) and maximize the uniformity of the feature weight, so as to ensure that the ANN artificial neural network model effectively considers the influence of other target feature parameters on the spray drift under the condition that the target downwind distance is sufficiently focused on, so as to ensure that the spray drift of the target downwind distance can be predicted by relying on the uniform weight of other target feature parameters.

[0108] In the embodiment of the present application, the preset maximum iteration number of GWO is used as the training termination condition. Then, the wolf position vector with the optimal fitness is assigned to the ANN artificial neural network model to obtain the ground drift prediction model. The ground drift prediction model has multiple input ends, which correspond to the number of target feature parameters.

[0109] Step 106, obtaining a second mapping relationship between the degree of phytotoxicity of the sensitive crop plant in the adjacent plot and the drift of the corresponding ground drift device, and determining the drift phytotoxicity detection limit of the sensitive crop plant.

[0110] It should be noted that the sensitive crop can be the plant type planted in the adjacent plot in the season, that is, the crop type to be planted or actually planted in the adjacent plot can be used as the sensitive crop to understand the real sensitive reaction of the crop plant to the pesticide liquid during the test.

[0111] In one feasible embodiment, the sensitive crop plants adjacent to the plot are placed at different downwind distances, and the ground drift devices are placed at the corresponding positions of the plants to conduct a phytotoxicity test on the sensitive crop plants, to obtain the post-test sensitive crop plants and the corresponding ground drift amounts at the positions; all the leaves of the post-test sensitive crop plants are picked and made into leaf patterns; the phytotoxicity pixel features and the leaf pixel features corresponding to the leaf images are obtained, the yellowing ratio corresponding to the post-test sensitive crop plants is determined based on the phytotoxicity pixel features and the leaf pixel features, and a second mapping relationship between the phytotoxicity degree and the ground drift amount of the ground drift device at the corresponding position of the sensitive crop is generated based on the ground drift amount and the yellowing ratio of the post-test sensitive crop plants.

[0112] Specifically, the post-test sensitive crop plants are placed in an undisturbed room for 7 days to allow the post-test sensitive crop plants to fully react after being treated. Then the leaves of the sensitive crop plants are picked and pasted on A4 paper to form leaf patterns. Each leaf can be made into a leaf pattern to improve the accuracy and reliability of subsequent image processing.

[0113] After obtaining the leaf patterns, image processing algorithms are used to process the leaf images to extract the phytotoxicity pixel features and the leaf pixel features from the leaf patterns. Specifically, each leaf image is segmented using an RGB threshold to obtain the phytotoxicity pixel features of the phytotoxicity part and the leaf pixel features of the non-phytotoxicity part. The phytotoxicity pixel features are the pixel feature regions corresponding to the yellow color in the RGB color value, including but not limited to various degrees of yellow pixel regions, and the leaf pixel features are the non-white regions in the leaf pattern, i.e., the regions on the entire A4 paper except the white paper are the leaf pixel feature regions.

[0114] Further, the yellowing ratio corresponding to the post-test sensitive crop plants is determined by calculating the proportion of the phytotoxicity pixel features in the leaf pixel features. Optionally, the complete leaf area can be calculated using the leaf pixel features, and then the yellowing ratio can be calculated using the number of phytotoxicity pixel features and the leaf area. The yellowing ratio is used as a quantitative analysis index of the phytotoxicity degree of the sensitive crop plants. Optionally, the yellowing ratio is directly proportional to the phytotoxicity degree. For example, the post-test sensitive crop plants with a yellowing ratio of 99.9-100% have a high phytotoxicity degree, and the post-test sensitive crop plants with a yellowing ratio of 0-1% have a low phytotoxicity degree.

[0115] The sensitive crop corresponding position ground drift device is eluted, and its corresponding ground drift amount is calculated. The average value of the drift amount corresponding to the post-test sensitive crop plants with a yellowing ratio of 0-1% is the drift amount phytotoxicity limit of the sensitive crop.

[0116] That is, the phytotoxicity limit is the phytotoxicity degree of 0-1%.

[0117] Step 107, according to the ground drift amount prediction model and the drift amount pesticide damage detection limit, determine the buffer distance required for the to-be-executed spray application task to be harmless to the adjacent plot sensitive crop plants.

[0118] In a feasible embodiment, the to-be-executed spray application task is predicted by using the ground drift amount prediction model, the predicted ground drift amount of the to-be-executed spray application task at each downwind distance is obtained, the predicted ground drift amount of the to-be-executed spray application task at each downwind distance is compared with the drift amount pesticide damage detection limit, the downwind distance under the basis corresponding to the drift amount pesticide damage detection limit matched with the drift amount is determined, and the preset downwind distance adjacent to and smaller than the downwind distance under the basis is taken as the buffer distance.

[0119] That is, after determining the corresponding parameters of the to-be-executed spray application task, the ground drift amount at each downwind distance under the parameter combination can be predicted, and then according to the ground drift amount prediction model and the drift amount pesticide damage detection limit, the pesticide damage degree corresponding to each ground drift amount is obtained, and the pesticide damage degree corresponding to each ground drift amount is compared with the pesticide damage degree corresponding to the pesticide damage detection limit, preferably, starting from the ground drift amount corresponding to the minimum downwind distance, the pesticide damage degree mapped by the ground drift amount corresponding to each downwind distance is compared with the pesticide damage degree of the drift amount pesticide damage detection limit. The first downwind distance smaller than the pesticide damage detection limit is taken as the buffer distance corresponding to the to-be-executed task.

[0120] Therefore, the plant protection unmanned aerial vehicle spray application buffer distance determination method based on pesticide damage detection limit provided by the embodiments of the present application can utilize the prior test to construct the second mapping relationship between the ground drift amount and the pesticide damage degree, and according to the test, the ground drift amount prediction model is constructed, the accurate prediction of the ground drift amount at different downwind distances under different characteristic parameters is realized, and then by comparing the ground drift amount at different downwind distances with the drift amount pesticide damage detection limit, the buffer distance required for the to-be-executed spray application task to be harmless to the adjacent plot is further determined, thereby providing guidance for the safe application of the plant protection unmanned aerial vehicle.

[0121] It should be noted that although the operations of the method of the present application are described in a specific order in the accompanying drawings, this does not require or imply that the operations must be performed in this specific order, or that all of the shown operations must be performed to achieve the desired results.

[0122] The following refers to Figure 2 , Figure 2 shows a structural schematic diagram of a computer system of an electronic device or a server suitable for realizing the embodiments of the present application,

[0123] As Figure 2As shown, the computer system includes a central processing unit (CPU) 201, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 202 or the program loaded from the storage part 208 to the random access memory (RAM) 203. Various programs and data required for the operation instructions of the system are also stored in the RAM 203. The CPU 201, ROM 202 and RAM 203 are connected to each other via a bus 204. An input / output (I / O) interface 205 is also connected to the bus 204.

[0124] The following components are connected to the I / O interface 205: an input section 206 including a keyboard, a mouse, and the like; an output section 207 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 208 including a hard disk; and a communication section 209 including a network interface card such as a LAN card or a modem. The communication section 209 performs communication processing via a network such as the Internet. A drive 210 is also connected to the I / O interface 205 as needed. A removable medium 211, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 210 as needed, so that computer programs read therefrom can be installed into the storage section 208 as needed.

[0125] In particular, according to the embodiment of the present application, the above reference flow chart Figure 2 The described process can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 209, and / or installed from a removable medium 211. When the computer program is executed by the central processing unit (CPU) 201, the above-mentioned functions defined in the system of the present application are executed.

[0126] It should be noted that the computer-readable medium shown in the application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or component. In this application, the computer-readable signal medium can include a data signal carried in a baseband or as a carrier wave part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take many forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium that can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or component. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0127] The flowcharts and block diagrams in the drawings illustrate the possible implementation architectures, functions and operation instructions of the systems, methods and computer program products according to various embodiments of the application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment or a part of code, which contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can also occur in different order from that noted in the drawings. For example, two connected blocks can actually be executed substantially in parallel, and sometimes in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operation instructions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0128] As another aspect, the present application also provides a computer readable storage medium, which can be included in the electronic device described in the above embodiments, or can exist separately without being assembled into the electronic device. The computer readable storage medium stores one or more programs, when the programs are used by one or more processors to execute the method for determining the buffer distance of the plant protection unmanned aerial vehicle spraying according to the pesticide damage detection limit.

[0129] The above description is merely the preferred embodiments of the present application and the explanation of the technical principles used. It should be understood by those skilled in the art that the disclosed scope of the present application is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by the combinations of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features can be replaced with the technical features disclosed in the present application (but not limited to) having similar functions to form the technical solutions.

Claims

1. A method for measuring the buffer distance of pesticide spraying by unmanned aerial vehicles for plant protection based on the detection limit of pesticide damage, characterized in that: include: Based on the reference position of the plant protection UAV test flight, multiple downwind distances were selected; Placing a plurality of ground drift collection devices at each downwind distance along the flight direction of the plant protection UAV; After the plant protection unmanned aircraft performs a flight based on different test parameters, obtaining ground drift droplets collected by the ground drift amount collection device; Determining the ground drift amount corresponding to each downwind distance according to the ground drift amount acquisition device, and generating a first mapping relationship between the downwind distance and the ground drift amount; Constructing a ground drift prediction model related to the downwind distance under different characteristic parameters; Obtaining a second mapping relationship between the degree of pesticide damage to sensitive crop plants in adjacent plots and the drift amount of the ground drift device at the corresponding position, and determining a pesticide damage detection limit corresponding to the drift amount of the sensitive crop plants; According to the ground drift amount prediction model and the drift amount pesticide damage detection limit, the buffer distance required for the spraying task to be performed to be harmless to sensitive crop plants in adjacent plots is determined.

2. The method for measuring the buffer distance of pesticide spraying by an unmanned aerial vehicle for plant protection based on the pesticide damage detection limit according to claim 1, wherein: The method of obtaining a second mapping relationship between the degree of pesticide damage to sensitive crop plants in adjacent plots and the drift amount of the ground drift device at the corresponding position includes: Placing sensitive crop plants in adjacent plots at different downwind distances, and placing ground drift devices at positions corresponding to the plants to conduct a pesticide damage test on the sensitive crop plants, and obtaining the ground drift amounts of the sensitive crop plants and the corresponding positions after the test; Picking all leaves of the sensitive crop plants after the test and making leaf patterns; Obtaining the pesticide damage pixel features and leaf pixel features corresponding to the leaf pattern; Determining the yellowing ratio of the sensitive crop plants after the test based on the pesticide-damaged pixel features and the leaf pixel features; Based on the ground drift amount corresponding to the sensitive crop plants after the test and the yellowing ratio, a second mapping relationship is generated between the degree of pesticide damage and the ground drift amount of the ground drift device at the corresponding position of the sensitive crop plants.

3. The method for measuring the buffer distance of pesticide spraying by an unmanned aerial vehicle for plant protection based on the pesticide damage detection limit according to claim 1, wherein: The determining of the ground drift amount corresponding to each downwind distance according to the ground drift amount collecting device includes: For the ground drift amount collection device at any of the downwind distances, eluting the collected liquid in the ground drift amount collection device with deionized water to obtain an eluate; The eluate is measured using a fluorescence meter and the fluorescence value is recorded; wherein the plant protection drone spraying test uses a test solution containing ABF fluorescent tracer and the test agent at 0.1%; The ground drift amount corresponding to the downwind distance is determined according to the fluorescence value.

4. The method for measuring the buffer distance of pesticide spraying by an unmanned aerial vehicle for plant protection based on the pesticide damage detection limit according to claim 3, wherein: The ground drift corresponding to the downwind distance is determined using the following formula: Among them, β dep is the droplet drift per unit area, in mL / cm 2 ; F cal is the coefficient of relationship between fluorescence value and tracer concentration, in μg / L; V dil is the volume of eluent added, in mL; ρ smpl is the absorbance of the eluent; ρ blk is the fluorescence value of the blank plastic culture dish; ρ spray is the tracer concentration of the spray solution, in g / L; A col is the area of ​​the plastic culture dish in cm 2 .

5. The method for measuring the buffer distance of pesticide spraying by an unmanned aerial vehicle for plant protection based on the pesticide damage detection limit according to claim 1, wherein: The constructing of a ground drift prediction model related to the downward distance includes: Construct the initial ANN artificial neural network model and GWO algorithm parameters; The structural features of the initial ANN artificial neural network model are used as prey to calculate the position vector of the wolf pack; and the fitness corresponding to the current wolf pack position vector is calculated based on the training set; Calculate the information of the three gray wolves with the best fitness and update their position vectors and the position vectors of the wolf pack to perform iterative training; When the termination condition is met, the position vector of the wolf pack in the current iteration round is assigned to the ANN artificial neural network model to obtain the ground drift amount prediction model.

6. The method for measuring the buffer distance of pesticide spraying by an unmanned aerial vehicle for plant protection based on the pesticide damage detection limit according to claim 1, characterized in that: The step of determining the buffer distance required for the spray application task to be performed to be harmless to sensitive crop plants in adjacent plots based on the ground drift amount prediction model and the drift amount pesticide damage detection limit includes: Using the ground drift amount prediction model to predict the spray application task to be executed, and obtaining the predicted ground drift amount of the spray application task to be executed at each downwind distance; Comparing the predicted ground drift amount of the spray application task to be executed at each downwind distance with the drift amount pesticide damage detection limit, and determining the downwind distance based on the drift amount corresponding to the drift amount pesticide damage detection limit; A preset downwind distance that is adjacent to the downwind distance under the foundation and smaller than the downwind distance under the foundation is used as the buffer distance.

7. The method for measuring the buffer distance of pesticide spraying by an unmanned aerial vehicle for plant protection based on the pesticide damage detection limit according to claim 6, wherein: The detection limit of the phytotoxicity is 0-1% of the phytotoxicity level.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for measuring the buffer distance of spraying pesticides by an unmanned aerial vehicle for plant protection based on the pesticide damage detection limit as described in any one of claims 1 to 7 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for measuring the buffer distance of spraying pesticides by an unmanned aerial vehicle for plant protection based on the pesticide damage detection limit as described in any one of claims 1 to 7 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for measuring the buffer distance of spraying pesticides by an unmanned aerial vehicle for plant protection based on the pesticide damage detection limit according to any one of claims 1 to 7 is implemented.

Images