CN118124838A - Seedling condition and pest and disease damage early warning patrol unmanned aerial vehicle and method - Google Patents
Seedling condition and pest and disease damage early warning patrol unmanned aerial vehicle and method Download PDFInfo
- Publication number
- CN118124838A CN118124838A CN202410558189.XA CN202410558189A CN118124838A CN 118124838 A CN118124838 A CN 118124838A CN 202410558189 A CN202410558189 A CN 202410558189A CN 118124838 A CN118124838 A CN 118124838A
- Authority
- CN
- China
- Prior art keywords
- pesticide
- data
- pest
- insect pests
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 241000607479 Yersinia pestis Species 0.000 title claims abstract description 193
- 201000010099 disease Diseases 0.000 title claims abstract description 136
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 136
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000006378 damage Effects 0.000 title claims abstract description 26
- 239000000575 pesticide Substances 0.000 claims abstract description 140
- 241000238631 Hexapoda Species 0.000 claims abstract description 117
- 238000012545 processing Methods 0.000 claims abstract description 46
- 238000005507 spraying Methods 0.000 claims abstract description 44
- 230000008569 process Effects 0.000 claims abstract description 19
- 238000012544 monitoring process Methods 0.000 claims abstract description 10
- 230000007613 environmental effect Effects 0.000 claims description 43
- 238000012549 training Methods 0.000 claims description 20
- 238000012360 testing method Methods 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000009826 distribution Methods 0.000 claims description 12
- 230000000007 visual effect Effects 0.000 claims description 12
- 239000002917 insecticide Substances 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 4
- 238000013461 design Methods 0.000 claims description 3
- 208000015181 infectious disease Diseases 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims description 3
- 238000009434 installation Methods 0.000 description 5
- 230000000361 pesticidal effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000000749 insecticidal effect Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 230000002147 killing effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000007921 spray Substances 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 235000013601 eggs Nutrition 0.000 description 1
- 235000011389 fruit/vegetable juice Nutrition 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000024241 parasitism Effects 0.000 description 1
- 230000008654 plant damage Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Landscapes
- Catching Or Destruction (AREA)
Abstract
The invention relates to the technical field of pest and disease damage monitoring, and in particular discloses a seedling condition and pest and disease damage early warning patrol unmanned aerial vehicle and a method, wherein the unmanned aerial vehicle comprises a base, a camera module arranged at the top of the base, and further comprises: the data acquisition module and the data processing module arranged at the top of the camera module shoot through farmlands of a plurality of areas in the flight process of the unmanned aerial vehicle, thereby acquiring the information of the positions, the areas, the insect pest degrees and the like of the areas where the insect pests occur, then judging the insect pest conditions in each area of the farmlands according to the information, if judging that the insect pest conditions are serious, sending out an alarm to prompt an administrator, and installing the pesticide sprayer on the unmanned aerial vehicle for pesticide spraying operation.
Description
Technical Field
The invention relates to the technical field of pest and disease damage monitoring, in particular to a seedling condition and pest and disease damage early warning patrol unmanned aerial vehicle and a method.
Background
The plant diseases and insect pests are called as diseases and insect pests, and often cause adverse effects on agriculture, forestry, animal husbandry and the like, wherein the insect pests are plant damage phenomena caused by various harmful insects, and the insects bite, absorb plant juice, eggs, larva parasitism and the like through a mouth gag, so that the plants are subjected to leaf withering, incomplete, damaged and the like, and the crops cannot meet market demands, so that the market value of the crops is reduced.
In order not to influence the growth and development of crops, during the growth process of the crops, firstly, pests are isolated by physical means, such as using an isolation net, so as to prevent the invasion of the pests, and professional personnel are arranged to carry out inspection, so that problems can be found and treated in time by identifying the observation and analysis of the appearance of the crops, and farmers or professionals can take measures in time to control the spread and influence of the pests;
However, although the use of the isolation net to isolate the pests and the cooperation of manual inspection is an effective method, a lot of time and human resources are required, especially for large-scale farmlands or forests, in addition, human factors may cause inconsistency and subjectivity of inspection, thereby affecting the reliability of detection results, and when diseases and pests exist in farmlands, unmanned aerial vehicles are usually used for spraying pesticides to kill the pests, but the unmanned aerial vehicles are influenced by environmental factors in the process of spraying pesticides, thereby causing loss of pesticides and further causing reduction of insecticidal effects.
Disclosure of Invention
The invention aims to provide a seedling condition and pest and disease damage early warning patrol unmanned aerial vehicle and a method, which solve the following technical problems:
how to accurately evaluate the pest and disease conditions and realize accurate pesticide dosage.
The aim of the invention can be achieved by the following technical scheme:
a seedling condition and pest and disease damage early warning patrol unmanned aerial vehicle and method comprises a base and a camera module arranged at the top of the base;
Characterized by further comprising: the camera module comprises a data acquisition module and a data processing module arranged at the top of the camera module, wherein the data processing module comprises a processor installation shell;
The data acquisition module sends the acquired environmental information data to the data processing module, and the data processing module adjusts the spraying metering of the insecticide according to the environmental information data;
The power module is arranged above the data processing module shell and used for driving the unmanned aerial vehicle to fly;
The power module is arranged above the power module and used for providing power for the unmanned aerial vehicle;
and the top cover is arranged above the data acquisition module and is used for improving the signal of the unmanned aerial vehicle.
Further, the camera module includes:
The camera bracket is arranged at the top of the base;
The high-definition camera and the infrared camera are fixedly connected to the outer wall of the camera bracket;
The data processing module further comprises:
A data processor and a processor support;
the processor support is fixedly connected inside the processor mounting shell;
the data processor is fixedly connected to the top of the processor bracket;
The processor mounting shell is fixedly connected to the top of the camera bracket,
The power module includes:
the mounting frame is arranged at the top of the processor mounting shell;
The first propeller and the second propeller are fixedly connected in the mounting frame;
the first propeller and the second propeller output shafts are fixedly connected with the motor.
Further, the power module includes:
The power supply shell is arranged at the top of the mounting frame;
the power supply installation seats are fixedly connected in the power supply shell;
The battery packs are respectively arranged in the power supply installation seats;
The data acquisition module comprises:
the connecting shell is arranged at the top of the power supply shell;
The data acquisition bracket is fixedly connected in the connecting shell;
the satellite positioning module and the environment information acquisition module are arranged at the top of the data acquisition bracket;
The top cover comprises:
The cover body is fixedly connected to the top of the connecting shell;
The module connecting strip is fixedly connected to the bottom of the cover body;
And the signal antenna is arranged at the bottom of the module connecting strip.
Further, a method for early warning and patrol of seedling and plant diseases and insect pests is characterized in that patrol is performed by the early warning and patrol unmanned aerial vehicle for seedling and plant diseases and insect pests according to any one of claims 1 to 3, and the method comprises the following steps:
S1: training and test data preparation: starting the patrol unmanned aerial vehicle, collecting picture information through a high-definition camera or an infrared camera, and resolving the gesture;
s2: and (3) intelligent analysis of pest and disease damage areas: quantifying the extent of infection by measuring parameters such as area, number and distribution of the affected area;
S3: automatic processing: and after the identified pest and disease areas are intelligently analyzed, an alarm is sent, visual data are sent to background farmland management personnel, and a pesticide spraying instruction is automatically sent according to the pest and disease extent.
If the overall risk degree of the plant diseases and insect pests is greater than the preset risk degree of the plant diseases and insect pests, judging that the plant diseases and insect pests exist, then carrying out intelligent analysis on the data of the plant diseases and insect pests and uploading the data, sending an alarm to prompt an administrator by a data processing module, sending a pesticide spraying instruction, and then automatically controlling pesticide dosage according to the risk degree of the plant diseases and insect pests.
Further, the process of intelligent analysis of the pest and disease damage area in S2 includes:
The method comprises the steps of collecting parameters such as the area, the number and the distribution of an infected area through a camera module, calculating the risk of diseases and insect pests in the area according to collected data, and calculating the overall risk of the diseases and insect pests through identifying the characteristics such as the types and the influences of the diseases and insect pests, so as to generate a visual data report.
Further, the process of intelligent analysis of the pest and disease damage area in the step S2 further comprises the following steps of;
comparing the overall risk degree of the plant diseases and insect pests with a preset plant diseases and insect pests risk degree threshold;
if the overall risk degree of the plant diseases and insect pests is smaller than the preset plant diseases and insect pests risk degree, judging that the plant diseases and insect pests are not present;
If the overall risk degree of the plant diseases and insect pests is greater than the preset risk degree of the plant diseases and insect pests, judging that the plant diseases and insect pests exist, then carrying out intelligent analysis on the data of the plant diseases and insect pests and uploading the data, sending an alarm to prompt an administrator by a data processing module, sending a pesticide spraying instruction, and then automatically controlling pesticide dosage according to the risk degree of the plant diseases and insect pests.
Further, the automatic processing in S3 includes:
the environmental information of the infected area is acquired through an environmental information acquisition module in the data acquisition module, wherein the environmental information comprises air humidity, air temperature and air speed, and then the pesticide loss coefficient of the unmanned aerial vehicle when spraying the pesticide is calculated according to the acquired environmental information, so that a visual data report is generated.
Further, the automatic processing in S3 further includes;
Comparing the pesticide loss coefficient with a preset loss coefficient threshold value:
if the loss coefficient of the pesticide is smaller than a preset loss coefficient threshold value, judging that the pesticide is not influenced by environmental factors when being sprayed, and not needing to adjust the dosage of the pesticide;
If the loss coefficient of the pesticide is larger than a preset loss coefficient threshold value, the pesticide is judged to be influenced by environmental factors when spraying the pesticide, and the dosage of the pesticide needs to be adjusted.
Further, the automatic processing in S3 further includes:
When the pesticide is judged to be influenced by environmental factors when being sprayed;
The loss amount of the pesticide when spraying the pesticide is calculated according to the loss coefficient of the pesticide by the data processor, and the adjusted pesticide dosage is calculated according to the loss amount of the pesticide when spraying the pesticide.
Further, the gesture resolving process in S1 includes:
s11: the method comprises the steps of disclosing a disease and pest data set on a download network and collecting farmland disease and pest pictures, wherein the total number of the two types of images is N;
s12: and (3) data marking: labeling the acquired pest and disease damage area dataset by using labeling software LabelImg;
s13: and (3) data processing: dividing the marked data sample into a training set, a verification set and a test set according to the ratio of 8:1:1;
s14: and (3) network structure design: adopting YOLOV algorithm, taking the data sample as an input layer, and then passing through a series of convolution layers for extracting the characteristics in the image;
s15: model training: model training is carried out on the training set, image data are input into a model, a loss function is calculated, and then model parameters are updated by using a back propagation algorithm;
s16: model deployment: the model is deployed into the actual environment and integrated into an application, website or other system for real-time pest monitoring.
The invention has the beneficial effects that:
(1) According to the invention, the unmanned aerial vehicle shoots in farmlands of a plurality of areas in the flying process, so that the information of the positions, the areas, the insect pest degrees and the like of the areas where insect pests occur is obtained, then the insect pest conditions in each area in the farmland are judged according to the information, if the insect pest conditions are judged to be serious, an alarm is sent to prompt an administrator, and the pesticide sprayer is arranged on the unmanned aerial vehicle to spray pesticide.
(2) According to the invention, the environment information near the position of the pest and disease damage area is collected through the data acquisition module in the unmanned aerial vehicle, the adjusted pesticide dosage is calculated and obtained, the data processing unit can transmit the information to the background farmland manager, the background farmland manager can kill pests in the polluted area only by spraying the pesticide dosage according to the adjusted pesticide dosage through the unmanned aerial vehicle, the adjusted pesticide dosage can be accurately calculated through the arrangement, the situation that the pesticide effect is affected due to insufficient pesticide dosage can be avoided, the situation that the damage is caused to crops due to excessive pesticide dosage due to the fact that the adjusted pesticide dosage is determined empirically can be avoided, and good growth of crops and trees is ensured.
(3) The invention uses the overall risk degree of the plant diseases and insect pests in all areasRespectively and preset pest risk threshold/>The comparison can be carried out, and the condition of the plant diseases and insect pests in the area can be judged according to the overall risk degree of the plant diseases and insect pests in the area, so that the condition of the plant diseases and insect pests in a large-scale farmland or forest can be monitored in real time, the pesticide spraying and insect killing treatment can be carried out for the first time when the farmland or forest is subjected to serious plant diseases and insect pests, and the growth and development effects of crops and trees are improved.
(4) The invention builds a common crop disease and pest monitoring model, then carries out model training on a training set, inputs image data into the model and calculates a loss function, then uses a back propagation algorithm to update model parameters, uses a verification set to verify the model, monitors the performance of the model and adjusts super parameters to prevent over fitting, finally carries out testing through a testing set, and after the testing is completed, deploys the model into an actual environment, integrates the model into an application program, a website or other systems, so as to carry out real-time disease and pest monitoring.
Drawings
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is an overall block diagram of a patrol unmanned aerial vehicle in the present invention;
FIG. 2 is a block diagram of a camera module according to the present invention;
FIG. 3 is an exploded view of the structure of the data processing module of the present invention;
FIG. 4 is an exploded view of the power module of the present invention;
FIG. 5 is an exploded view of the structure of the power module of the present invention;
FIG. 6 is a block diagram of a data acquisition module of the present invention;
FIG. 7 is a block diagram of the top cover of the present invention;
FIG. 8 is a flow chart of the judgment of insect pest in the present invention;
FIG. 9 is a flow chart of a method of early warning patrol of seedling conditions and pests in the present invention;
fig. 10 is a flow chart of pose resolution in the present invention.
Reference numerals: 100. a base; 200. a camera module; 210. high definition camera; 220. a camera bracket; 230. an infrared camera; 300. a data processing module; 310. a data processor; 320. a processor support; 330. a processor mounting shell; 400. a power module; 410. a mounting frame; 420. a first propeller; 430. a second propeller; 440. a motor; 500. a power module; 510. a power supply housing; 520. a power supply mounting base; 530. a battery pack; 600. a data acquisition module; 610. a connection housing; 620. a satellite positioning module; 630. a data acquisition bracket; 640. an environmental information acquisition module; 650. a signal antenna; 700. a top cover; 710. a cover body; 720. module connecting strips.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-10, in one embodiment, the present application provides a seedling and pest early warning patrol unmanned aerial vehicle and method, comprising a base 100, a camera module 200 disposed on top of the base 100;
Characterized by further comprising: a data acquisition module 600 and a data processing module 300 disposed on top of the camera module 200, the data processing module 300 including a processor mounting case 330;
the data acquisition module 600 sends the acquired environmental information data to the data processing module, and the data processing module adjusts the spraying metering of the insecticide according to the environmental information data;
the power module 400 is arranged above the data processing module 300 shell and is used for driving the unmanned aerial vehicle to fly;
the power module 500 is arranged above the power module 400 and is used for providing power for the unmanned aerial vehicle;
the top cover 700 is arranged above the data acquisition module 600 and is used for improving the signal of the unmanned aerial vehicle;
According to the technical scheme, when a large-scale farmland or forest is inspected, a power supply module 500 is used for providing power for the unmanned aerial vehicle, the unmanned aerial vehicle is driven to fly through a power module 400, the data processing module 300 arranged in the unmanned aerial vehicle firstly divides the farmland into a plurality of areas in the flying process, the camera module 200 is used for shooting the farmland in the plurality of areas, so that information such as the positions, the areas and the insect pest degrees of the areas where insect pests occur is obtained, then the insect pest conditions in the areas in the farmland are judged according to the information, if the insect pest conditions are judged to be serious, an alarm is sent to prompt an administrator, and insecticide is installed on the unmanned aerial vehicle, and the unmanned aerial vehicle is used for spraying the insecticide;
The unmanned aerial vehicle can gather the environmental information of disease and pest area position through data acquisition module 600 afterwards, later calculate the pesticide loss coefficient of unmanned aerial vehicle when spraying the insecticide according to the environmental information who gathers, and adjust the dose of insecticide, through so setting up, can easily realize the operation of patrol to extensive farmland or forest, and can not lead to the inconsistency and the subjectivity of patrolling and examining because of artificial factor, the accuracy of testing result has been improved, and through calculating the pesticide loss coefficient, not only can avoid the pesticide dosage not enough to lead to influencing the circumstances of insecticidal effect to appear, and can avoid artifical experience to confirm the dosage, lead to the dosage to the condition that the excessive production harm to crops appears.
Referring to fig. 2, 3 and 4, the camera module 200 includes:
a camera bracket 220 disposed on top of the base 100;
The high-definition camera 210 and the infrared camera 230 are fixedly connected to the outer wall of the camera bracket 220;
The data processing module 300 further comprises:
A data processor 310 and a processor support 320;
the processor support 320 is fixedly connected inside the processor mounting case 330;
The data processor 310 is fixedly connected to the top of the processor support 320;
The processor mounting housing 330 is fixedly attached to the top of the camera bracket 220,
The power module 400 includes:
a mounting frame 410 provided on top of the processor mounting case 330;
The first propeller 420 and the second propeller 430 are fixedly connected in the mounting frame 410;
the output shafts of the first propeller 420 and the second propeller 430 are fixedly connected with a motor 440;
Through the above technical scheme, when the large-scale farmland or forest is patrolled and examined, first screw 420 and second screw 430 are driven to rotate synchronously through motor 440, at this moment, first screw 420 and second screw 430 can provide power for unmanned aerial vehicle, make unmanned aerial vehicle can remove in large-scale farmland or forest, in this process, camera support 220 outside high definition digtal camera 210 can take the image to farmland or forest, if at night, can take the image through infrared camera 230, thereby obtain the regional position of taking place the insect pest, the area, insect pest degree, afterwards data processor 310 can judge information such as insect pest situation in each region in this farmland according to this information, if judge that the insect pest condition is comparatively serious, send alarm suggestion administrator, and install insecticide sprayer on unmanned aerial vehicle and spout the medicine operation, through so setting up, can realize the patrol operation to large-scale farmland or forest, and can not lead to the inconsistency and the subjective nature of patrolling because of the artificial factor, the accuracy of detection result has been improved.
Referring to fig. 5, 6 and 7, the power module 500 includes:
A power source housing 510 provided on top of the mounting frame 410;
the power supply installation seats 520 are arranged in a plurality of groups, and the power supply installation seats 520 are fixedly connected in the power supply shell 510;
a plurality of battery packs 530 respectively disposed in the plurality of power supply mounting seats 520;
the data acquisition module 600 includes:
a connection case 610 disposed at the top of the power supply case 510;
The data acquisition bracket 630, the data acquisition bracket 630 is fixedly connected in the connection shell 610;
the satellite positioning module 620 and the environmental information acquisition module 640 are arranged on the top of the data acquisition bracket 630;
the canopy 700 includes:
the cover 710 fixedly connected to the top of the connection case 610;
The module connecting strip 720 is fixedly connected to the bottom of the cover 710;
a signal antenna 650 disposed at the bottom of the module connecting bar 720;
Through the above technical scheme, when judging that a certain pest situation is more serious, can send out the warning suggestion administrator and spout the medicine automatically, unmanned aerial vehicle's environmental information near emergence pest area position is collected through data acquisition module 600 this moment, afterwards calculate unmanned aerial vehicle's pesticide loss coefficient when spraying insecticide according to the environmental information who gathers, and adjust the dose of insecticide, through so setting up, not only can avoid the insufficient circumstances that leads to influencing the insecticidal effect of pesticide dosage to appear, and can avoid the manual work to confirm the dosage by experience, the circumstances that leads to the excessive production harm to crops of dosage appear, and signal antenna 650 can improve unmanned aerial vehicle's signal, guarantee that its transmission data can not appear losing the condition, and then guarantee its accuracy of gathering information.
Referring to fig. 9, a method for early warning and patrol of seedling conditions and diseases and insect pests is characterized in that the unmanned aerial vehicle for early warning and patrol of seedlings and diseases and insect pests in any one of claims 1-3 is used for patrol, and the method comprises:
S1: training and test data preparation: starting the patrol unmanned aerial vehicle, collecting picture information through a high-definition camera or an infrared camera, and resolving the gesture;
s2: and (3) intelligent analysis of pest and disease damage areas: quantifying the extent of infection by measuring parameters such as area, number and distribution of the affected area;
s3: automatic processing: after the identified pest and disease areas are intelligently analyzed, an alarm is sent, visual data are sent to background farmland management personnel, and a pesticide spraying instruction is automatically sent according to the pest and disease extent;
According to the technical scheme, when a large-scale farmland or forest is patrolled, a patrol unmanned aerial vehicle is started, picture information is acquired through a high-definition camera or an infrared camera, gesture calculation is performed, the positions and the degrees of diseases and insect pests in an output image are calculated through the gestures, a model is deployed into an actual environment and integrated into an application program, a website or other systems to monitor the diseases and insect pests in real time, the infected degrees are quantified through measuring parameters such as the area, the number and the distribution of an infected area, the risk of the diseases and insect pests in the area is calculated according to the acquired data, and the overall risk of the diseases and insect pests is calculated and judged through identifying the characteristics such as the types and the influences of the diseases and insect pests, so that a visual data report is generated;
The whole risk degree of the plant diseases and insect pests in the identified plant diseases and insect pests area is then intelligently analyzed, if the whole risk degree of the plant diseases and insect pests is higher, an alarm is sent, visual data are sent to a background farmland manager, and a pesticide spraying instruction is sent according to the plant diseases and insect pests risk degree, in the process, environmental information of an infected area is collected through an environmental information collection module 640 in a data collection module 600, the pesticide loss coefficient of the unmanned aerial vehicle when pesticide is sprayed is then calculated according to the collected environmental information, the adjusted pesticide dosage is calculated according to the pesticide loss when pesticide is sprayed, then the farmland manager adjusts the pesticide dosage according to the data, the pesticide is installed on the unmanned aerial vehicle, pesticide spraying is carried out through the unmanned aerial vehicle, a visual data report is generated, and through the arrangement, the pesticide spraying efficiency can be improved, and the situation that the pesticide effect is affected due to the fact that the pesticide adding quantity is insufficient can be avoided.
The process of intelligent analysis of the pest and disease damage area in the S2 comprises the following steps:
The method comprises the steps of collecting parameters such as the area, the number and the distribution of an infected area through a camera module 200, calculating the risk of diseases and insect pests in the area according to collected data, and calculating the overall risk of the diseases and insect pests through identifying the characteristics such as the types and the influences of the diseases and insect pests, so as to generate a visual data report;
Through the above technical scheme, when a large-scale farmland or forest is inspected, firstly, the camera module 200 collects the area, the number, the distribution and other parameters of the infected area, and calculates the overall risk of the plant diseases and insect pests by identifying the characteristics of the plant diseases and insect pests, the influence and the like;
The formula can be used Calculating to obtain the overall risk degree/>, of the plant diseases and insect pests in the a-th area；
Obviously, when the larger the pest area monitored in the a-th area, the larger the number of pests and the larger the distribution area of pests, the overall risk of the pests in the a-th areaThe larger the area, the more serious the pest problem in the area, otherwise, if the smaller the monitored pest area in the a-th area, the smaller the number of pests and the smaller the distribution area of pests, the overall risk degree/>, of the pests in the a-th areaThe smaller the plant diseases and insect pests in the area are, the smaller the plant diseases and insect pests in the area are or the plant diseases and insect pests are not existed, by the arrangement, the unmanned aerial vehicle monitors the area, the number and the distribution range of the plant diseases and insect pests in the area in real time, the condition of the plant diseases and insect pests in the area can be primarily judged, the method is convenient and rapid, the patrol operation of a large-scale farmland or forest can be easily realized, the inconsistency and subjectivity of patrol can not be caused by artificial factors, and the accuracy of the detection result is improved;
wherein a is any monitoring area, For the area of pest detected in the a-th zone,/>Is the total area of the a-th region,/>For the number of pests detected in zone a; /(I)For the pest distribution area monitored in zone a,/>For the pest type influence function, the pest type influence function can be set according to the overall risk degree influence test data of different pests on the pests in a fitting way,/>For pest type, X1 and X2 are weight coefficients, which can be set according to empirical fit.
Referring to fig. 8, the process of intelligent analysis of the pest and disease damage area in S2 further includes;
comparing the overall risk degree of the plant diseases and insect pests with a preset plant diseases and insect pests risk degree threshold;
if the overall risk degree of the plant diseases and insect pests is smaller than the preset plant diseases and insect pests risk degree, judging that the plant diseases and insect pests are not present;
If the overall risk of the plant diseases and insect pests is greater than the preset risk of the plant diseases and insect pests, judging that the plant diseases and insect pests exist, then intelligently analyzing and uploading data of the plant diseases and insect pests, sending an alarm to prompt an administrator by the data processing module 300, sending a pesticide spraying instruction, and then automatically controlling pesticide dosage according to the risk of the plant diseases and insect pests;
through the technical scheme, the overall risk degree of the plant diseases and insect pests in all areas is achieved Respectively and preset pest risk threshold/>Comparing;
If any one of Judging that the overall risk of the plant diseases and insect pests in the area is high, indicating that the plant diseases and insect pests in the area are relatively serious, then intelligently analyzing and uploading the data of the plant diseases and insect pests, then sending an alarm by the data processing module 300 to prompt an administrator, sending a pesticide spraying instruction, and then automatically controlling the pesticide dosage according to the risk of the plant diseases and insect pests;
If all are All are(s)The method has the advantages that the condition of the diseases and insect pests in the area can be judged according to the overall risk degree of the diseases and insect pests in the area, so that the real-time monitoring of the condition of the diseases and insect pests in a large scale farmland or forest is realized, the first time of pesticide spraying and insect killing treatment when the farmland or forest is subjected to serious diseases and insect pests is ensured, and the effects of crops and tree growth are improved.
The automatic processing procedure in S3 includes:
Collecting environmental information of an infected area through an environmental information collecting module 640 in the data collecting module 600, wherein the environmental information comprises air humidity, air temperature and air speed, and then calculating a pesticide loss coefficient of the unmanned aerial vehicle when spraying pesticide according to the collected environmental information to generate a visual data report;
In the above technical solution, when it is determined that the overall risk of the pest in the a-th area is high, it is indicated that the pest situation in the a-th area is relatively serious, then the data processing module 300 will send an alarm to prompt the administrator to send a pesticide spraying instruction, in this process, the environmental information of the infected area needs to be collected by the environmental information collection module 640 in the data collection module 600 in the unmanned aerial vehicle, and the pesticide loss coefficient of the unmanned aerial vehicle when spraying the pesticide is calculated according to the collected environmental information;
The formula can be used Calculating to obtain the loss coefficient/>；
Obviously, when the humidity and the wind speed in the a-th area with high overall risk degree of plant diseases and insect pests are higher and the temperature influence function is larger, the greater the pesticide loss coefficient of the unmanned aerial vehicle is, the greater the pesticide loss coefficient is, when pesticide spraying operation is carried out in the environment, the greater the loss amount of the pesticide can appear, through the arrangement, when pesticide spraying operation is carried out, the adding amount of the pesticide can be adjusted according to the loss amount through the data processing module 300, and the situation that the pesticide effect is influenced due to insufficient adding amount of the pesticide when pesticide spraying operation is carried out is avoided, so that the pesticide effect is improved.
Wherein,To define a function, if/>Then/>If/>Then/>，/>For the humidity monitored in zone a,/>For a preset humidity threshold in the a-th zone,/>For the wind speed monitored in zone a,For a preset wind speed threshold in the a-th zone,/>A temperature influence function which can be set by fitting the loss measurement results of the pesticide sprayed at different temperatures,/>Is the value of the ambient temperature,/>For/>The standard value of (2) can be set according to empirical fitting.
The automatic processing process in the step S3 further comprises the following steps of;
Comparing the pesticide loss coefficient with a preset loss coefficient threshold value:
if the loss coefficient of the pesticide is smaller than a preset loss coefficient threshold value, judging that the pesticide is not influenced by environmental factors when being sprayed, and not needing to adjust the dosage of the pesticide;
If the loss coefficient of the pesticide is larger than a preset loss coefficient threshold value, judging that the pesticide is influenced by environmental factors when spraying the pesticide, and adjusting the dosage of the pesticide;
through the technical scheme, when pesticide spraying operation is carried out, firstly, the pesticide loss coefficient in the a-th area with high overall risk of plant diseases and insect pests is calculated With a preset loss coefficient threshold/>Comparing;
If it is Judging that the pesticide spraying operation is influenced by environmental factors, and adjusting the dosage of the pesticide;
otherwise, judging that the pesticide is not influenced by environmental factors when spraying, and not needing to adjust the pesticide dosage;
By the judging method, whether the dosage of the pesticide needs to be complemented or not can be judged according to the pesticide loss coefficient in the a-th area with high overall risk degree of the plant diseases and insect pests, and the situation that the insecticidal effect is affected due to insufficient pesticide adding amount is avoided, so that the pest killing effect is improved.
The automatic processing in S3 further includes:
When the pesticide is judged to be influenced by environmental factors when being sprayed;
Calculating, by the data processor 310, a loss amount of the pesticide when spraying the pesticide according to the pesticide loss coefficient, and calculating an adjusted pesticide dosage according to the loss amount of the pesticide when spraying the pesticide;
According to the technical scheme, when the influence of environmental factors is judged when pesticide is sprayed, firstly, the loss amount of the pesticide when the pesticide is sprayed is calculated by the data processor 310 according to the loss coefficient of the pesticide, and the adjusted pesticide dosage is calculated according to the loss amount of the pesticide when the pesticide is sprayed;
The formula can be used Calculating the dosage/>, after loss of the pesticide；
And pass through the formulaCalculating to obtain the adjusted pesticide dosage/>；
After the adjusted pesticide dosage is calculated and obtained, the data processing unit transmits the information to a background farmland manager, the background farmland manager only needs to allocate according to the adjusted pesticide dosage and spray the pesticide dosage on an unmanned aerial vehicle, and pests in a polluted area can be killed, by the arrangement, the adjusted pesticide dosage can be accurately calculated, then the farmland manager can adjust the pesticide dosage according to the data, the pesticide is installed on the unmanned aerial vehicle, pesticide spraying is carried out through the unmanned aerial vehicle, the situation that the pesticide effect is affected due to insufficient pesticide dosage can be avoided, the situation that the damage to crops is caused due to excessive pesticide dosage due to the fact that the adjusted pesticide dosage is determined empirically can be avoided, and good growth of crops and trees is ensured;
Wherein P is the preset dosage of pesticide, Is obtained according to the influence test of the overall risk of the plant and the insect pest on the dosage of the pesticideThe effect function of the loss coefficient of the pesticide can be obtained according to empirical fitting.
Referring to fig. 10, the gesture resolving process in S1 includes:
s11: the method comprises the steps of disclosing a disease and pest data set on a download network and collecting farmland disease and pest pictures, wherein the total number of the two types of images is N;
s12: and (3) data marking: labeling the acquired pest and disease damage area dataset by using labeling software LabelImg;
s13: and (3) data processing: dividing the marked data sample into a training set, a verification set and a test set according to the ratio of 8:1:1;
s14: and (3) network structure design: adopting YOLOV algorithm, taking the data sample as an input layer, and then passing through a series of convolution layers for extracting the characteristics in the image;
s15: model training: model training is carried out on the training set, image data are input into a model, a loss function is calculated, and then model parameters are updated by using a back propagation algorithm;
S16: model deployment: deploying the model into an actual environment, and integrating the model into an application program, a website or other systems to monitor the plant diseases and insect pests in real time;
in the process of gesture calculation, firstly, the acquired pest and disease area data set is marked by using marking software LabelImg, wherein the marking information is a rectangular frame (marking frame) surrounding the pest and disease area and the score of the marking frame, and the label form is as follows Wherein/>Score representing annotation box,/>When the marking frame contains the pest and disease damage area, the marking frame is equal to 0 or 1When the labeling frame does not contain a pest and disease damage area/>；/>,/>Representing the coordinates of the starting point of the lower left corner of the target frame,, />The width and the height of a target frame are represented, the marked data are converted into a model XML format, and then marked data samples are divided into a training set, a verification set and a test set according to the ratio of 8:1:1;
Then adopting YOLOV algorithm, taking the data sample as an input layer, then passing through a series of convolution layers for extracting features in the image, wherein each convolution layer comprises convolution operation, reLU activation function and average pooling operation, the deep convolution layer is used for further extracting higher-level features so as to better represent the defects in the image, the extracted feature map is restored to the original image size through the pairing of the transposed convolution layer and the convolution layer, the up-sampling and restoration of the image are realized, jump connection is introduced to help solve the gradient vanishing problem, the performance and stability of the network are improved, the features extracted by the convolution layer are mapped to the layers of the output category (diseases and insect pests or normal), and the positions and the degrees of the diseases and insect pests in the image are output;
Then training the model on a training set, inputting image data into the model and calculating a loss function, then updating model parameters by using a back propagation algorithm, verifying the model by using a verification set, monitoring the performance of the model and adjusting the parameters to prevent over fitting, and finally testing by a testing set;
after the test is completed, the model is deployed into an actual environment and integrated into an application program, a website or other systems for real-time pest and disease monitoring.
The foregoing describes one embodiment of the present invention in detail, but the description is only a preferred embodiment of the present invention and should not be construed as limiting the scope of the invention. All equivalent changes and modifications within the scope of the present invention are intended to be covered by the present invention.
Claims (10)
1. The seedling condition and pest and disease damage early warning patrol unmanned aerial vehicle comprises a base (100) and a camera module (200) arranged at the top of the base (100);
Characterized by further comprising: a data acquisition module (600) and a data processing module (300) disposed on top of the camera module (200), the data processing module (300) comprising a processor mounting shell (330);
the data acquisition module (600) sends the acquired environmental information data to the data processing module, and the data processing module adjusts the spraying metering of the insecticide according to the environmental information data;
The power module (400) is arranged above the shell of the data processing module (300) and is used for driving the unmanned aerial vehicle to fly;
The power module (500) is arranged above the power module (400) and is used for providing power for the unmanned aerial vehicle;
and the top cover (700) is arranged above the data acquisition module (600) and is used for improving the signal of the unmanned aerial vehicle.
2. A seedling and pest warning patrol drone according to claim 1, wherein said camera module (200) comprises:
the camera bracket (220) is arranged at the top of the base (100);
The high-definition camera (210) and the infrared camera (230) are fixedly connected to the outer wall of the camera bracket (220);
the data processing module (300) further comprises:
A data processor (310) and a processor support (320);
the processor support (320) is fixedly connected inside the processor mounting shell (330);
The data processor (310) is fixedly connected to the top of the processor bracket (320);
the processor mounting shell (330) is fixedly connected to the top of the camera bracket (220),
The power module (400) includes:
a mounting bracket (410) disposed on top of the processor mounting housing (330);
the first propeller (420) and the second propeller (430), wherein the first propeller (420) and the second propeller (430) are fixedly connected in the mounting frame (410);
the output shafts of the first propeller (420) and the second propeller (430) are fixedly connected with a motor (440).
3. The seedling and pest warning patrol drone according to claim 1, wherein said power module (500) comprises:
a power supply housing (510) disposed on top of the mounting frame (410);
The power supply comprises a plurality of groups of power supply mounting seats (520), wherein the power supply mounting seats (520) are fixedly connected in a power supply shell (510);
A plurality of groups of battery packs (530) respectively arranged in the plurality of groups of power supply mounting seats (520);
The data acquisition module (600) comprises:
a connection housing (610) disposed on top of the power supply housing (510);
The data acquisition support (630), the data acquisition support (630) is fixedly connected in the connection shell (610);
The satellite positioning module (620) and the environment information acquisition module (640) are arranged at the top of the data acquisition bracket (630);
The canopy (700) includes:
the cover body (710) is fixedly connected to the top of the connecting shell (610);
The module connecting strip (720) is fixedly connected to the bottom of the cover body (710);
And the signal antenna (650) is arranged at the bottom of the module connecting strip (720).
4. A method for early warning patrol of seedling conditions and plant diseases and insect pests, characterized in that patrol is performed by the early warning patrol unmanned aerial vehicle for seedling conditions and plant diseases and insect pests according to any one of claims 1 to 3, the method comprising:
S1: training and test data preparation: starting the patrol unmanned aerial vehicle, collecting picture information through a high-definition camera or an infrared camera, and resolving the gesture;
s2: and (3) intelligent analysis of pest and disease damage areas: quantifying the extent of infection by measuring parameters such as area, number and distribution of the affected area;
S3: automatic processing: and after the identified pest and disease areas are intelligently analyzed, an alarm is sent, visual data are sent to background farmland management personnel, and a pesticide spraying instruction is automatically sent according to the pest and disease extent.
5. The method for early warning patrol of seedling conditions and diseases and insect pests according to claim 4, wherein the process of intelligent analysis of the disease and insect pest area in S2 comprises:
Parameters such as the area, the number and the distribution of the infected areas are acquired through the camera module (200), the risk degree of the diseases and insect pests in the areas is calculated according to the acquired data, and the overall risk degree of the diseases and insect pests is calculated by identifying the characteristics such as the types and the influences of the diseases and insect pests, so that a visual data report is generated.
6. The method for early warning patrol of seedling conditions and diseases and insect pests according to claim 4, wherein the process of intelligent analysis of the disease and insect pest area in S2 further comprises;
comparing the overall risk degree of the plant diseases and insect pests with a preset plant diseases and insect pests risk degree threshold;
if the overall risk degree of the plant diseases and insect pests is smaller than the preset plant diseases and insect pests risk degree, judging that the plant diseases and insect pests are not present;
If the overall risk degree of the plant diseases and insect pests is greater than the preset plant diseases and insect pests risk degree, judging that the plant diseases and insect pests exist, then performing intelligent analysis on the data of the plant diseases and insect pests and uploading the data, sending an alarm by the data processing module (300) to prompt an administrator, sending a pesticide spraying instruction, and then automatically controlling the pesticide dosage according to the plant diseases and insect pests risk degree.
7. The method of claim 4, wherein the automatic processing in S3 comprises:
Environmental information of an infected area is acquired through an environmental information acquisition module (640) in the data acquisition module (600), wherein the environmental information comprises air humidity, air temperature and air speed, and then the pesticide loss coefficient of the unmanned aerial vehicle when spraying pesticide is calculated according to the acquired environmental information, so that a visual data report is generated.
8. The method for early warning patrol of a seedling and pest according to claim 4, wherein the automatic processing in S3 further comprises;
Comparing the pesticide loss coefficient with a preset loss coefficient threshold value:
if the loss coefficient of the pesticide is smaller than a preset loss coefficient threshold value, judging that the pesticide is not influenced by environmental factors when being sprayed, and not needing to adjust the dosage of the pesticide;
If the loss coefficient of the pesticide is larger than a preset loss coefficient threshold value, the pesticide is judged to be influenced by environmental factors when spraying the pesticide, and the dosage of the pesticide needs to be adjusted.
9. The method of claim 4, wherein the automatic processing in S3 further comprises:
When the pesticide is judged to be influenced by environmental factors when being sprayed;
The amount of pesticide lost when spraying the pesticide is calculated by the data processor (310) based on the pesticide loss coefficient, and the adjusted pesticide dosage is calculated based on the amount of pesticide lost when spraying the pesticide.
10. The method for early warning patrol of seedling conditions and diseases and insect pests according to claim 4, wherein the gesture resolving process in S1 comprises:
s11: the method comprises the steps of disclosing a disease and pest data set on a download network and collecting farmland disease and pest pictures, wherein the total number of the two types of images is N;
s12: and (3) data marking: labeling the acquired pest and disease damage area dataset by using labeling software LabelImg;
s13: and (3) data processing: dividing the marked data sample into a training set, a verification set and a test set according to the ratio of 8:1:1;
s14: and (3) network structure design: adopting YOLOV algorithm, taking the data sample as an input layer, and then passing through a series of convolution layers for extracting the characteristics in the image;
s15: model training: model training is carried out on the training set, image data are input into a model, a loss function is calculated, and then model parameters are updated by using a back propagation algorithm;
s16: model deployment: the model is deployed into the actual environment and integrated into an application, website or other system for real-time pest monitoring.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410558189.XA CN118124838B (en) | 2024-05-08 | 2024-05-08 | Seedling condition and pest and disease damage early warning patrol unmanned aerial vehicle and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410558189.XA CN118124838B (en) | 2024-05-08 | 2024-05-08 | Seedling condition and pest and disease damage early warning patrol unmanned aerial vehicle and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118124838A true CN118124838A (en) | 2024-06-04 |
| CN118124838B CN118124838B (en) | 2024-07-16 |
Family
ID=91244319
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410558189.XA Active CN118124838B (en) | 2024-05-08 | 2024-05-08 | Seedling condition and pest and disease damage early warning patrol unmanned aerial vehicle and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118124838B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109122633A (en) * | 2018-06-25 | 2019-01-04 | 华南农业大学 | The accurate variable-rate spraying device of the plant protection drone of Decision of Neural Network and control method |
| KR20190080060A (en) * | 2017-12-28 | 2019-07-08 | 이호동 | Forest pest suspect tree selection system using unmanned aircraft |
| CN111339921A (en) * | 2020-02-24 | 2020-06-26 | 南京邮电大学 | Insect disease detection unmanned aerial vehicle based on lightweight convolutional neural network and detection method |
| CN111770881A (en) * | 2017-10-05 | 2020-10-13 | 欧弗沃克斯有限公司 | Remotely controllable aviation ordnance |
| KR102192635B1 (en) * | 2019-11-29 | 2020-12-18 | 박상원 | Drone for pest control and pest control system using the same |
| CN112565310A (en) * | 2019-09-09 | 2021-03-26 | 云南天质弘耕科技有限公司 | Intelligent plant protection system based on artificial neural network |
| US20210209352A1 (en) * | 2019-12-26 | 2021-07-08 | Bernard Fryshman | Insect and other small object image recognition and instant active response with enhanced application and utility |
| US20220354073A1 (en) * | 2019-12-09 | 2022-11-10 | Valmont Industries, Inc. | Pest and disease management system for use with a crop irrigation system |
| CN116158421A (en) * | 2023-03-01 | 2023-05-26 | 新疆农业大学 | Crop pest control pesticide spraying method, system, storage medium, equipment and application |
| CN116686814A (en) * | 2023-07-27 | 2023-09-05 | 山西农业大学 | Pesticide application control method, system and medium for plant protection unmanned aerial vehicle |
| CN117456358A (en) * | 2023-10-25 | 2024-01-26 | 陕西科技大学 | Method for detecting plant diseases and insect pests based on YOLOv5 neural network |
-
2024
- 2024-05-08 CN CN202410558189.XA patent/CN118124838B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111770881A (en) * | 2017-10-05 | 2020-10-13 | 欧弗沃克斯有限公司 | Remotely controllable aviation ordnance |
| KR20190080060A (en) * | 2017-12-28 | 2019-07-08 | 이호동 | Forest pest suspect tree selection system using unmanned aircraft |
| CN109122633A (en) * | 2018-06-25 | 2019-01-04 | 华南农业大学 | The accurate variable-rate spraying device of the plant protection drone of Decision of Neural Network and control method |
| CN112565310A (en) * | 2019-09-09 | 2021-03-26 | 云南天质弘耕科技有限公司 | Intelligent plant protection system based on artificial neural network |
| KR102192635B1 (en) * | 2019-11-29 | 2020-12-18 | 박상원 | Drone for pest control and pest control system using the same |
| US20220354073A1 (en) * | 2019-12-09 | 2022-11-10 | Valmont Industries, Inc. | Pest and disease management system for use with a crop irrigation system |
| US20210209352A1 (en) * | 2019-12-26 | 2021-07-08 | Bernard Fryshman | Insect and other small object image recognition and instant active response with enhanced application and utility |
| CN111339921A (en) * | 2020-02-24 | 2020-06-26 | 南京邮电大学 | Insect disease detection unmanned aerial vehicle based on lightweight convolutional neural network and detection method |
| CN116158421A (en) * | 2023-03-01 | 2023-05-26 | 新疆农业大学 | Crop pest control pesticide spraying method, system, storage medium, equipment and application |
| CN116686814A (en) * | 2023-07-27 | 2023-09-05 | 山西农业大学 | Pesticide application control method, system and medium for plant protection unmanned aerial vehicle |
| CN117456358A (en) * | 2023-10-25 | 2024-01-26 | 陕西科技大学 | Method for detecting plant diseases and insect pests based on YOLOv5 neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118124838B (en) | 2024-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112911931B (en) | Imaging device for detecting arthropods and system for detecting arthropods | |
| US20220107298A1 (en) | Systems and methods for crop health monitoring, assessment and prediction | |
| CN111582055A (en) | Aerial pesticide application route generation method and system for unmanned aerial vehicle | |
| TWI708546B (en) | Liquid spraying method of drone system and artificial intelligence image processing technology | |
| WO2014037936A1 (en) | System for automatic trapping and counting of flying insects | |
| WO2008063751A2 (en) | Apparatus and systems for using semiochemical compositions for insect pest control | |
| CN111225854A (en) | Unmanned plane | |
| CN106097119A (en) | Harvester, server and information gathering, push, obtain and sending method | |
| KR102091033B1 (en) | Method for conjecturing agricultural produce using Smart drone system | |
| CN108366526A (en) | Simplify the system and method for forestry literature by the priority of automated biological characteristic | |
| CN111045467B (en) | Intelligent agricultural machine control method based on Internet of things | |
| EP3522704A1 (en) | Identification of beneficial insects and/or pollutants in a field for crop plants | |
| CN110263624A (en) | A kind of agricultural insect pest's monitoring and managing method based on 5G technology | |
| EP3516580B1 (en) | Control of harmful organisms | |
| CN107883927A (en) | Quadrotor plant growth inspection system | |
| CN118124838B (en) | Seedling condition and pest and disease damage early warning patrol unmanned aerial vehicle and method | |
| CN114819568A (en) | Method and system for determining farm insect pest searching and killing scheme based on machine learning | |
| US20240016136A1 (en) | Method and system for monitoring and controlling the presence of at least one type of insect in agricultural crops | |
| AU2021103499A4 (en) | An automated plantation health monitoring system and a method thereof | |
| CN115756037A (en) | Greenhouse vegetable management and control method and system | |
| CN113361377A (en) | Plant growth control model construction method, electronic device and storage medium | |
| Vaheed | Chapter-4 Drone technology-for Smart Agriculture | |
| WO2023247209A1 (en) | Apparatus and method for measuring insect activity | |
| WO2023144293A1 (en) | Plant disease detection at onset stage | |
| WO2022049580A1 (en) | Methods for artificial pollination and apparatus for doing the same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |