CN109409275A - The recognition methods of target object and device, the determination method for being administered information - Google Patents
The recognition methods of target object and device, the determination method for being administered information Download PDFInfo
- Publication number
- CN109409275A CN109409275A CN201811217962.7A CN201811217962A CN109409275A CN 109409275 A CN109409275 A CN 109409275A CN 201811217962 A CN201811217962 A CN 201811217962A CN 109409275 A CN109409275 A CN 109409275A
- Authority
- CN
- China
- Prior art keywords
- target object
- target area
- type
- information
- target
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 241000196324 Embryophyta Species 0.000 claims abstract description 66
- 239000003814 drug Substances 0.000 claims abstract description 52
- 229940079593 drug Drugs 0.000 claims abstract description 35
- 238000012549 training Methods 0.000 claims abstract description 24
- 238000005507 spraying Methods 0.000 claims abstract description 23
- 239000002917 insecticide Substances 0.000 claims abstract description 19
- 239000007921 spray Substances 0.000 claims description 27
- 230000000875 corresponding effect Effects 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 16
- 238000004519 manufacturing process Methods 0.000 claims description 6
- 230000002596 correlated effect Effects 0.000 claims description 3
- 238000012806 monitoring device Methods 0.000 claims description 3
- 239000000575 pesticide Substances 0.000 abstract description 29
- 238000009333 weeding Methods 0.000 abstract description 10
- 230000000694 effects Effects 0.000 abstract description 5
- 239000002699 waste material Substances 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 12
- 230000002363 herbicidal effect Effects 0.000 description 6
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 244000025254 Cannabis sativa Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009313 farming Methods 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64D—EQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENT OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
- B64D1/00—Dropping, ejecting, releasing, or receiving articles, liquids, or the like, in flight
- B64D1/16—Dropping or releasing powdered, liquid, or gaseous matter, e.g. for fire-fighting
- B64D1/18—Dropping or releasing powdered, liquid, or gaseous matter, e.g. for fire-fighting by spraying, e.g. insecticides
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Pest Control & Pesticides (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Catching Or Destruction (AREA)
Abstract
This application discloses a kind of recognition methods of target object and devices, the determination method for being administered information.Wherein, this method comprises: obtaining the image of target area;Image based on the image recognition model identification object region that training obtains, obtains at least one target object in the density information of target area;Density information according at least one target object in target area determines the type of at least one target object, wherein type is for reflecting target object to the influence degree of crops in target area.Weed species and weeding control effect cannot be identified during present application addresses spraying insecticide using automatic drug spraying equipment, cause the waste of pesticide, the lower technical problem of weeding ratio.
Description
Technical field
This application involves reading intelligent agriculture fields, recognition methods and device, application in particular to a kind of target object
The determination method of information.
Background technique
In the prior art, peasant household to crops spray insecticide weeding when, can taking human as judging weed species and weed density,
So that it is determined that medicine types and drug dose are sprayed insecticide.And using automatic drug spraying equipment during spraying insecticide, one
As can ignore the density of weeds and the type of weeds, cannot select suitable dose pesticide and for weed species it is targeted
Selection pesticide type, cause the waste of pesticide, herbicidal effect is poor.
For above-mentioned problem, currently no effective solution has been proposed.
Summary of the invention
The embodiment of the present application provides recognition methods and the device, the determination method for being administered information of a kind of target object, with
It at least solves to identify weed species and weeding control effect during spraying insecticide using automatic drug spraying equipment, causes agriculture
The waste of medicine, the lower technical problem of weeding ratio.
According to the one aspect of the embodiment of the present application, a kind of recognition methods of target object is provided, comprising: obtain target
The image in region;Image based on the image recognition model identification object region that training obtains, obtains at least one target object
Density information in target area;Density information according at least one target object in target area determines at least one target
The type of object, wherein type is for reflecting target object to the influence degree of crops in target area.
Optionally, in the image of the image recognition model identification object region obtained based on training, at least one mesh is obtained
Marking density information of the object in target area includes: that image is input to preset model to analyze, and obtains at least one target
Density information of the object in target area, wherein preset model is obtained by multi-group data training, every in multi-group data
Group data include: the image information of target area, the density information for identifying at least one of image information target object
Label.
Optionally, the density information according at least one target object in target area determines at least one target object
Type comprises determining that value range belonging to density information;Determine type corresponding with value range;Using preset function model
Density information is analyzed, type is obtained, wherein preset function model is used to describe the yield damage of weed density and crops
Relationship between mistake rate.
Optionally, preset function model determines in the following manner: S=(d+c)/(a+b (d+c)), wherein S is for anti-
Production loss rate is reflected, d indicates that density information, a and b are the regression coefficient of function curve, and c is to be administered information according to history to determine
's.
Optionally, c is determined in the following manner: determining the yield of the corresponding crops of history application information;According to yield
Determine digital value corresponding with the yield of crops, wherein the number value and the yield of crops are positively correlated.
According to the another aspect of the embodiment of the present application, a kind of determination method for being administered information is additionally provided, comprising: obtain mesh
Mark the image in region;Image based on the image recognition model identification object region that training obtains, obtains at least one target pair
As the density information in target area;Density information according at least one target object in target area determines at least one mesh
Mark the type of object, wherein type is for reflecting target object to the influence degree of crops in target area;Believed based on density
Breath and type determine the application information at least one target object, wherein application information includes at least one of: drug class
Type and drug dose.
Optionally, the application information at least one target object is determined based on density information and type, comprising: based on close
Degree information determines the dosage of drug corresponding to medicine types;At least one target object is determined based on density information and/or type
Corresponding medicine types.
Optionally, the above method further include: the sprinkling path of spray drug operation equipment is determined based on density information and type;Its
In, it determines that the sprinkling path of spray drug operation equipment includes at least one of based on density information and type: first spraying target pair
As the big place target area of density, first the small place target area of sprinkling target object density, to the target object of a type
It sprays insecticide again to another target object after the completion of spraying insecticide.
According to the embodiment of the present application in another aspect, providing a kind of plant protection system, comprising: measuring device, for obtaining
The image of target area;Monitoring device, the image of the image recognition model identification object region for being obtained based on training, is obtained
Density information of at least one target object in target area;Density information according at least one target object in target area
Determine the type of at least one target object, wherein the type is for reflecting target object to the shadow of crops in target area
The degree of sound;Determine the application information at least one target object based on density information and type, wherein application information include with
It is at least one lower: medicine types and drug dose;Application information is sent to spray drug operation equipment;Spray drug operation equipment, is used for
Spray drug operation is carried out to target area according to application information.
According to the embodiment of the present application in another aspect, providing a kind of identification device of target object, which includes: to obtain
Modulus block, for obtaining the image of target area;Identification module, the image recognition model for being obtained based on training identify target
The image in region obtains at least one target object in the density information of target area;Determining module, for according at least one
Density information of the target object in target area determines the type of at least one target object, wherein the type is for reflecting mesh
Object is marked to the influence degree of crops in target area.
According to the one aspect of the embodiment of the present application, a kind of storage medium is provided, which is characterized in that storage medium includes
The program of storage, wherein equipment where control storage medium executes the recognition methods of above-mentioned target object in program operation.
According to the one aspect of the embodiment of the present application, a kind of processor is provided, which is characterized in that processor is for running
Program, wherein program executes the recognition methods of above-mentioned target object when running.
In the embodiment of the present application, using the image for obtaining target area;The image recognition model obtained based on training is known
The image of other target area obtains at least one target object in the density information of target area;According at least one target pair
As the density information in target area determines the type of at least one target object, wherein type is for reflecting target object pair
The mode of the influence degree of crops in target area, by identifying the density information of target object, further according to the density of identification
Information determines the type of target object, then determines spraying control method according to the density information of target object and type, reaches
The purpose of the feature of multi-faceted acquisition target object determines miscellaneous to realize through multi-faceted acquisition target object feature
The distributed intelligence and type of grass, select the pesticide of suitable dose and targetedly select the class of pesticide for weed species
Type improves the utilization rate of pesticide, improves the technical effect of weeding ratio, and then solves and spray agriculture using automatic drug spraying equipment
Weed species and weeding control effect cannot be identified during medicine, causes the waste of pesticide, and the lower technology of weeding ratio is asked
Topic.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present application, constitutes part of this application, this Shen
Illustrative embodiments and their description please are not constituted an undue limitation on the present application for explaining the application.In the accompanying drawings:
Fig. 1 is the flow chart according to a kind of recognition methods of target object of the embodiment of the present application;
Fig. 2 is the flow chart according to a kind of determination method of application information of the embodiment of the present application;
Fig. 3 is the structure chart according to a kind of plant protection system of the embodiment of the present application;
Fig. 4 is the structure chart according to a kind of identification device of target object of the embodiment of the present application.
Specific embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
The embodiment of the application a part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people
Member's every other embodiment obtained without making creative work, all should belong to the model of the application protection
It encloses.
It should be noted that the description and claims of this application and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to embodiments herein described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
According to the embodiment of the present application, the embodiment of a kind of spraying control method of unmanned plane is provided, it should be noted that
Step shown in the flowchart of the accompanying drawings can execute in a computer system such as a set of computer executable instructions, and
It, in some cases, can be to be different from sequence execution institute herein and although logical order is shown in flow charts
The step of showing or describing.
Fig. 1 is according to a kind of flow chart of the recognition methods of target object of the embodiment of the present application, as shown in Figure 1, the party
Method includes the following steps:
Step S102 obtains the image of target area.
In some optional embodiments of the application, target area is the growth district of crops, can be by removable
Dynamic high-definition image acquisition device obtains the high-definition image of crop growing region, and optionally, high-definition image acquisition device can also
To be mounted on unmanned plane, the image information in crop growth area is acquired.
Step S104, the image based on the image recognition model identification object region that training obtains, obtains at least one mesh
Object is marked in the density information of target area.
According to an optional embodiment of the application, step S104 is realized by the following method: image being input to pre-
If model is analyzed, at least one target object is obtained in the density information of target area, wherein preset model is by more
Group data training obtains, and every group of data in multi-group data include: the image information of target area, for identifying image letter
The label of at least one of the breath density information of target object.
In some optional embodiments of the application, by mass data, training obtains above-mentioned preset model in advance
Machine learning model, wherein the including but not limited to image of target area is used in the data of training machine learning model, it can
Characterize the characteristic information of the density of different type weeds.
Step S106, the density information according at least one target object in target area determine at least one target object
Type, wherein type is for reflecting target object to the influence degree of crops in target area.
Weeds and crops in farmland are very prominent to the competition of the limited resources such as moisture, nutrient, space and sunlight
, the competition of weeds and crops is exactly crop yield loss to the directly harm of crops, and the life of different type weeds
Long density is different, also just different to the extent of damage of crops, therefore weeds can be determined to crops by the density of weeds
The extent of damage, and then determine according to the extent of damage of the weeds to crops the type of farming.
According to an optional embodiment of the application, step S106 includes at least one of following methods: determining density
Value range belonging to information;Determine type corresponding with value range;Density information is divided using preset function model
Analysis, obtains type, wherein preset function model is used to describe the relationship between weed density and the production loss rate of crops.
In some optional embodiments of the application, pair of weed density and weed species can be prestored in the database
It should be related to, the density section of the density information of weeds be determined according to the evaluation criterion of preset weed density, such as will be miscellaneous
Careless density is that every square meter 1-10 is set as the first density rating, and every square meter 10-20 is set as the second density rating, every square meter
20 and 20 or more are set as third density rating, wherein the corresponding relationship of weed density and weed species are as follows: the first density
Grade corresponds to first kind weeds, and wherein first kind weeds are slight, the second density rating pair to the influence degree of crops
Second Type weeds are answered, wherein Second Type weeds are moderate to the influence degree of crops, and third density rating corresponds to third
Type weeds, wherein third type weeds are severe to the influence degree of crops, through the above steps, according to preset
The evaluation criterion of density information determines density rating, and the class of weeds is determined further according to the corresponding relationship of density rating and weed species
Type determines weeds to the influence degree of crops.
In some optional embodiments of the application, damage of the weeds to crops can also be calculated by preset formula
Degree, calculation method are as follows:
In some optional embodiments of the application, preset function model determines in the following manner: S=(d+c)/(a
+ b (d+c)), wherein S is for reflecting production loss rate, and d indicates that density information, a and b are the regression coefficient of function curve, and c is
It is determined according to history application information.
According to an optional embodiment of the application, c is determined in the following manner: determining that history application information is corresponding
The yield of crops;Digital value corresponding with the yield of crops is determined according to yield, wherein the number value and crops
Yield be positively correlated.
A and b is the regression coefficient of function curve, indicates that independent variable d influences the parameter of size on dependent variable S, to set in advance
Fixed two threshold values, c are determined by history application information, for example the dosage that history is sprayed insecticide respectively corresponds a c1 value, history spray
The type for spilling pesticide respectively corresponds a c2 value, goes the value of 5 c1 to average, the value of 5 c2 is averaged, then according to two
A average value seeks weighted average, obtains the value of c.In a, the value of b, c can calculate the value of S according to the value of d after determining, and
It is by formula S=(d+c)/(a+b (d+c)) it can be seen that being proportional between production loss rate S and weed density information, i.e., miscellaneous
Careless density is bigger, and crop yield loss late is higher.
In some optional embodiments of the application, since big for weed growth density and weed growth density is small
The dosage of the pesticide of region sprinkling is different, region spray small to weed density again after the completion of region sprinkling first big to weed density
It spills, or region sprinkling first small to weed density again sprays weed density the earth region, can spray to avoid unmanned plane
The unit fountain height that frequent switching is sprayed insecticide during pesticide can be improved the efficiency that unmanned plane is sprayed insecticide.Similarly
Due to the type difference for the pesticide that the type difference for weeds is sprayed, to a kind of pesticide spraying after the completion again to another type of
Pesticide spraying, can frequent switching is sprayed insecticide during spraying insecticide to avoid unmanned plane type the problem of, same energy
Enough improve the efficiency that unmanned plane is sprayed insecticide.
Fig. 2 is according to a kind of flow chart of the determination method of application information of the embodiment of the present application, as shown in Fig. 2, the party
Method the following steps are included:
Step S202 obtains the image of target area.
Step S204, the image based on the image recognition model identification object region that training obtains, obtains at least one mesh
Object is marked in the density information of target area.
Step S206, the density information according at least one target object in target area determine at least one target object
Type, wherein the type is for reflecting target object to the influence degree of crops in target area.
Step S208 determines the application information at least one target object based on density information and type, wherein application
Information includes at least one of: medicine types and drug dose.
According to an optional embodiment of the application, step S208 includes: to determine medicine types institute based on density information
The dosage of corresponding drug;The corresponding medicine types of at least one target object are determined based on density information and/or type.
In some optional embodiments of the application, spray insecticide in the big crop growing region of weed growth density
Dosage it is big, can cause to avoid the crop growing region big in weed growth density because of the pesticide underdosage of sprinkling
The halfway problem of weeding;In the small crop growing region of weed growth density, dosage of spraying insecticide is small, can be to avoid miscellaneous
The small crop growing region of careless stand density, because of the waste pesticide that the pesticide dosage of sprinkling excessively generates, and can be to soil
The problem of polluting.
According to the type of determining weeds can determine different types of weeds to the extent of damage of crops, for example,
It is severe to the influence degrees of crops that third class weeds, which are mentioned above, during the second class weeds are to the influence degree of crops
Degree, first kind weeds are slight to the influence degree of crops, therefore when being directed to different types of weeds, are targetedly selected
The type for selecting the pesticide of sprinkling can choose the strong pesticide of herbicidal performance such as third class weeds, for the second class weeds
It can choose the pesticide of herbicidal performance slightly almost, since herbicidal performance is strong and weak different, there is also differences for the price of pesticide itself
Not, different types of pesticide is selected to the influence degree of crops according to the density information of weeds or weeds, it is raw to crops
It is long to influence the strong pesticide of big weeds selection price high herbicidal performance, small weeds selection price is influenced slightly on crop growth
The pesticide of low spot can make pesticide spraying operation reach higher cost performance under the premise of preferable herbicidal effect.
The sprinkling side of pesticide is determined according to the method sprayed insecticide that the density of the weeds of identification and the type of weeds determine
After method, by above-mentioned pesticide spraying method send spray drug operation equipment, spray drug operation equipment include but is not limited to unmanned plane, ground without
The intelligent control devices such as people's vehicle.
According to an optional embodiment of the application, the recognition methods of above-mentioned target object further include: believed based on density
Breath and type determine the sprinkling path of spray drug operation equipment;Wherein, spray drug operation equipment is determined based on density information and type
Spraying path includes at least one of: first spraying that the big place target area of target object density, first sprinkling target object is close
Again to the sprinkling agriculture of another target object after the completion of spending small place target area, spraying insecticide to the target object of a type
Medicine.
Through the above steps, by identifying the density information of target object, target is determined further according to the density information of identification
Then the type of object determines spraying control method according to the density information of target object and type, reached multi-faceted acquisition
The purpose of the feature of target object determines the distributed intelligence of weeds to realize through multi-faceted acquisition target object feature
And type, it selects the pesticide of suitable dose and targetedly selects the type of pesticide for weed species, improve agriculture
The utilization rate of medicine improves the technical effect of weeding ratio.
Fig. 3 is according to a kind of structure chart of plant protection system of the embodiment of the present application, as shown in figure 3, the system includes:
Measuring device 30, for obtaining the image of target area.
Monitoring device 32 is connect with measuring device 30, and the image recognition model for being obtained based on training identifies target area
The image in domain obtains at least one target object in the density information of target area;According at least one target object in target
The density information in region determines the type of at least one target object, wherein the type is for reflecting target object to target area
The influence degree of crops in domain;The application information at least one target object is determined based on density information and type, wherein
Being administered information includes at least one of: medicine types and drug dose;Application information is sent to spray drug operation equipment 34.
Spray drug operation equipment 34 is communicated to connect with detection device 32, for spraying according to application information to target area
Medicine operation.
It should be noted that the preferred embodiment of embodiment illustrated in fig. 3 may refer to Fig. 1 to embodiment illustrated in fig. 2
Associated description, details are not described herein again.
Fig. 4 is according to a kind of structure chart of the identification device of target object of the embodiment of the present application, as shown in figure 4, the dress
It sets and includes:
Module 40 is obtained, for obtaining the image of target area.
Identification module 42, the image of the image recognition model identification object region for being obtained based on training, is obtained at least
A kind of density information of target object in target area.
Determining module 44 determines at least one mesh for the density information according at least one target object in target area
Mark the type of object, wherein the type is for reflecting target object to the influence degree of crops in target area.
It should be noted that the preferred embodiment of embodiment illustrated in fig. 4 may refer to Fig. 1 to embodiment illustrated in fig. 2
Associated description, details are not described herein again.
The embodiment of the present application additionally provides a kind of storage medium, and storage medium includes the program of storage, wherein in program
Equipment where controlling storage medium when operation executes the recognition methods of above-mentioned target object.
Above-mentioned storage medium is used to store the program for executing following functions: obtaining the image of target area;Based on trained
The image of the image recognition model identification object region arrived obtains at least one target object in the density information of target area;
Density information according at least one target object in target area determines the type of at least one target object, wherein type
For reflecting target object to the influence degree of crops in target area;Or
Obtain the image of target area;Image based on the image recognition model identification object region that training obtains, obtains
Density information of at least one target object in target area;Density information according at least one target object in target area
Determine the type of at least one target object, wherein type is for reflecting influence of the target object to crops in target area
Degree;The application information at least one target object is determined based on density information and type, wherein application information includes following
At least one: medicine types and drug dose.
The embodiment of the present application additionally provides a kind of processor, and processor is for running program, wherein program is held when running
The recognition methods of the above-mentioned target object of row.
Above-mentioned processor is used to execute the program for realizing following functions: obtaining the image of target area;It is obtained based on training
Image recognition model identification object region image, obtain at least one target object in the density information of target area;According to
Density information according at least one target object in target area determines the type of at least one target object, wherein type is used
In reflection target object to the influence degree of crops in target area;Or
Obtain the image of target area;Image based on the image recognition model identification object region that training obtains, obtains
Density information of at least one target object in target area;Density information according at least one target object in target area
Determine the type of at least one target object, wherein type is for reflecting influence of the target object to crops in target area
Degree;The application information at least one target object is determined based on density information and type, wherein application information includes following
At least one: medicine types and drug dose.
Above-mentioned the embodiment of the present application serial number is for illustration only, does not represent the advantages or disadvantages of the embodiments.
In above-described embodiment of the application, all emphasizes particularly on different fields to the description of each embodiment, do not have in some embodiment
The part of detailed description, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed technology contents can pass through others
Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, such as the division of the unit, Ke Yiwei
A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of unit or module
It connects, can be electrical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
On unit.It can some or all of the units may be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can for personal computer, server or network equipment etc.) execute each embodiment the method for the application whole or
Part steps.And storage medium above-mentioned includes: that USB flash disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic or disk etc. be various to can store program code
Medium.
The above is only the preferred embodiment of the application, it is noted that for the ordinary skill people of the art
For member, under the premise of not departing from the application principle, several improvements and modifications can also be made, these improvements and modifications are also answered
It is considered as the protection scope of the application.
Claims (12)
1. a kind of recognition methods of target object, which is characterized in that the described method includes:
Obtain the image of target area;
Based on the image for training obtained image recognition model to identify the target area, at least one target object is obtained in institute
State the density information of target area;
Density information according at least one target object in the target area determines at least one target object
Type, wherein the type is for reflecting the target object to the influence degree of crops in the target area.
2. the method according to claim 1, wherein identifying the mesh based on the image recognition model that training obtains
The image in region is marked, obtaining at least one target object in the density information of the target area includes:
Described image is input to preset model to analyze, obtains at least one target object in the target area
Density information, wherein the preset model is obtained by multi-group data training, and every group of data in the multi-group data are equal
It include: the label of the image information of target area, density information for identifying at least one of image information target object.
3. the method according to claim 1, wherein according at least one target object in the target area
The density information in domain determines that the type of at least one target object includes at least one of:
Determine value range belonging to the density information;Determine type corresponding with the value range;
The density information is analyzed using preset function model, obtains the type, wherein the preset function model
For describing the relationship between weed density and the production loss rate of the crops.
4. according to the method described in claim 3, it is characterized in that, the preset function model determines in the following manner:
S=(d+c)/(a+b (d+c)), wherein S is for reflecting the production loss rate, and d indicates the density information, and a and b are
The regression coefficient of function curve, c are to be administered what information determined according to history.
5. according to the method described in claim 4, it is characterized in that, c is determined in the following manner:
Determine the yield of the corresponding crops of history application information;It is corresponding with the yield of the crops according to yield determination
Digital value, wherein the yield of the number value and the crops is positively correlated.
6. a kind of determination method for being administered information, which is characterized in that the described method includes:
Obtain the image of target area;
Based on the image for training obtained image recognition model to identify the target area, at least one target object is obtained in institute
State the density information of target area;
Density information according at least one target object in the target area determines at least one target object
Type, wherein the type is for reflecting the target object to the influence degree of crops in the target area;
The application information at least one target object is determined based on the density information and type, wherein the application
Information includes at least one of: medicine types and drug dose.
7. according to the method described in claim 6, it is characterized in that, based on the density information and type determine to it is described at least
A kind of application information of target object, comprising:
The dosage of drug corresponding to the medicine types is determined based on the density information;
The corresponding medicine types of at least one target object are determined based on the density information and/or the type.
8. according to the method described in claim 6, it is characterized in that, the method also includes:
The sprinkling path of spray drug operation equipment is determined based on the density information and type;Wherein, based on the density information and
Type determines that the sprinkling path of the spray drug operation equipment includes at least one of:
It first sprays the big place target area of the target object density, first spray the small place target of the target object density
Region again sprays insecticide to another target object after the completion of spraying insecticide to the target object of a type type.
9. a kind of plant protection system, which is characterized in that the system comprises:
Measuring device, for obtaining the image of target area;
Monitoring device, the image recognition model for being obtained based on training are identified the image of the target area, obtain at least one
Density information of the kind target object in the target area;According at least one target object in the close of the target area
Degree information determines the type of at least one target object, wherein the type is for reflecting the target object to described
The influence degree of crops in target area;It is determined based on the density information and type at least one target object
It is administered information, wherein the application information includes at least one of: medicine types and drug dose;By the application information
It is sent to spray drug operation equipment;
The spray drug operation equipment, for carrying out spray drug operation to the target area according to the application information.
10. a kind of identification device of target object, which is characterized in that described device includes:
Module is obtained, for obtaining the image of target area;
Identification module, the image recognition model for being obtained based on training are identified the image of the target area, obtain at least one
Density information of the kind target object in the target area;
Determining module, it is described at least for the density information determination according at least one target object in the target area
A kind of type of target object, wherein the type is for reflecting the target object to crops in the target area
Influence degree.
11. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein run in described program
When control the storage medium where equipment perform claim require any one of 1 to 8 described in target object recognition methods.
12. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Benefit require any one of 1 to 8 described in target object recognition methods.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811217962.7A CN109409275B (en) | 2018-10-18 | 2018-10-18 | Target object identification method and device, and drug delivery information determination method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811217962.7A CN109409275B (en) | 2018-10-18 | 2018-10-18 | Target object identification method and device, and drug delivery information determination method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109409275A true CN109409275A (en) | 2019-03-01 |
CN109409275B CN109409275B (en) | 2021-06-15 |
Family
ID=65467721
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811217962.7A Active CN109409275B (en) | 2018-10-18 | 2018-10-18 | Target object identification method and device, and drug delivery information determination method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109409275B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110221598A (en) * | 2019-04-19 | 2019-09-10 | 广州极飞科技有限公司 | Job control method and device |
CN111027380A (en) * | 2019-11-05 | 2020-04-17 | 北京海益同展信息科技有限公司 | Spray head control method and device, computer equipment and storage medium |
CN112136637A (en) * | 2020-09-27 | 2020-12-29 | 安阳工学院 | Self-adaptive spraying method of cotton defoliant |
CN112407283A (en) * | 2020-11-24 | 2021-02-26 | 广东技术师范大学 | Unmanned aerial vehicle spraying operation method and device based on multi-level cooperation |
CN112700347A (en) * | 2020-12-31 | 2021-04-23 | 广州极飞科技有限公司 | Method and device for generating crop height growth curve and storage medium |
CN112733582A (en) * | 2019-10-28 | 2021-04-30 | 广州极飞科技有限公司 | Crop yield determination method and device and nonvolatile storage medium |
CN113011220A (en) * | 2019-12-19 | 2021-06-22 | 广州极飞科技股份有限公司 | Spike number identification method and device, storage medium and processor |
WO2022127406A1 (en) * | 2020-12-15 | 2022-06-23 | 广州极飞科技股份有限公司 | Method and apparatus for determining operation dose, unmanned device, and storage medium |
CN114758223A (en) * | 2022-03-08 | 2022-07-15 | 深圳市五谷网络科技有限公司 | Pesticide use monitoring and early warning method and device, terminal equipment and storage medium |
CN116912701A (en) * | 2023-09-14 | 2023-10-20 | 潍坊现代农业山东省实验室 | Weed identification method and device and weed spraying method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2004005625A1 (en) * | 2002-07-05 | 2004-01-15 | G AND G NöVÉNYVÉDELMI ÉS KERESKEDELMI | Weeding procedure for a railway vehicle |
CN1945601A (en) * | 2005-10-08 | 2007-04-11 | 中国农业机械化科学研究院 | Method for automatic identifying weeds in field and medicine spraying device |
CN102172233A (en) * | 2011-03-04 | 2011-09-07 | 江苏大学 | Method for carrying out real-time identification and targeted spraying on cotton field weeds |
CN108304796A (en) * | 2018-01-29 | 2018-07-20 | 深圳春沐源控股有限公司 | A kind of intelligence weeds alarming method for power and system |
CN108519775A (en) * | 2017-10-30 | 2018-09-11 | 北京博鹰通航科技有限公司 | A kind of UAV system and its control method precisely sprayed |
-
2018
- 2018-10-18 CN CN201811217962.7A patent/CN109409275B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2004005625A1 (en) * | 2002-07-05 | 2004-01-15 | G AND G NöVÉNYVÉDELMI ÉS KERESKEDELMI | Weeding procedure for a railway vehicle |
CN1945601A (en) * | 2005-10-08 | 2007-04-11 | 中国农业机械化科学研究院 | Method for automatic identifying weeds in field and medicine spraying device |
CN102172233A (en) * | 2011-03-04 | 2011-09-07 | 江苏大学 | Method for carrying out real-time identification and targeted spraying on cotton field weeds |
CN108519775A (en) * | 2017-10-30 | 2018-09-11 | 北京博鹰通航科技有限公司 | A kind of UAV system and its control method precisely sprayed |
CN108304796A (en) * | 2018-01-29 | 2018-07-20 | 深圳春沐源控股有限公司 | A kind of intelligence weeds alarming method for power and system |
Non-Patent Citations (1)
Title |
---|
赵浩宇 等: "四川省烟田杂草种类及群落特征", 《烟草科技》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110221598A (en) * | 2019-04-19 | 2019-09-10 | 广州极飞科技有限公司 | Job control method and device |
CN112733582A (en) * | 2019-10-28 | 2021-04-30 | 广州极飞科技有限公司 | Crop yield determination method and device and nonvolatile storage medium |
CN111027380A (en) * | 2019-11-05 | 2020-04-17 | 北京海益同展信息科技有限公司 | Spray head control method and device, computer equipment and storage medium |
CN113011220A (en) * | 2019-12-19 | 2021-06-22 | 广州极飞科技股份有限公司 | Spike number identification method and device, storage medium and processor |
CN112136637A (en) * | 2020-09-27 | 2020-12-29 | 安阳工学院 | Self-adaptive spraying method of cotton defoliant |
CN112407283A (en) * | 2020-11-24 | 2021-02-26 | 广东技术师范大学 | Unmanned aerial vehicle spraying operation method and device based on multi-level cooperation |
WO2022127406A1 (en) * | 2020-12-15 | 2022-06-23 | 广州极飞科技股份有限公司 | Method and apparatus for determining operation dose, unmanned device, and storage medium |
CN112700347A (en) * | 2020-12-31 | 2021-04-23 | 广州极飞科技有限公司 | Method and device for generating crop height growth curve and storage medium |
CN114758223A (en) * | 2022-03-08 | 2022-07-15 | 深圳市五谷网络科技有限公司 | Pesticide use monitoring and early warning method and device, terminal equipment and storage medium |
CN116912701A (en) * | 2023-09-14 | 2023-10-20 | 潍坊现代农业山东省实验室 | Weed identification method and device and weed spraying method |
Also Published As
Publication number | Publication date |
---|---|
CN109409275B (en) | 2021-06-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109409275A (en) | The recognition methods of target object and device, the determination method for being administered information | |
Berk et al. | Development of alternative plant protection product application techniques in orchards, based on measurement sensing systems: A review | |
Bennett et al. | Farm‐level economic performance of genetically modified cotton in Maharashtra, India | |
CN109446958B (en) | Method, device and system for determining pesticide application effect | |
CN109197278A (en) | Determination method and device, the determination method of herbal sprinkling strategy of Job Policies | |
Pontikakos et al. | Pest management control of olive fruit fly (Bactrocera oleae) based on a location-aware agro-environmental system | |
Carrasco et al. | Towards the integration of spread and economic impacts of biological invasions in a landscape of learning and imitating agents | |
Guixé et al. | Appropriateness of Special Protection Areas for wide‐ranging species: the importance of scale and protecting foraging, not just nesting habitats | |
CN105389737A (en) | Decision and control system of pesticide spraying | |
Peck et al. | Integrated and organic fruit production systems for ‘Liberty’apple in the Northeast United States: a systems-based evaluation | |
CN109496622A (en) | The recognition methods of pest and device, the determination method, the plant protection system that are administered information | |
CN109197275A (en) | The recognition methods of weeds type and device, the determination method for being administered information | |
CN109197273A (en) | Determination method and device, the determination method of spraying time of pest activity period | |
CN109711272A (en) | Crops intelligent management method, system, electronic equipment and storage medium | |
Mahaffee et al. | Responding to an introduced pathogen: Podosphaera macularis (hop powdery mildew) in the Pacific Northwest | |
CN115631061A (en) | Intelligent digital agriculture method, system and medium based on shared agricultural machinery | |
CN110688989B (en) | Intelligent agriculture monitoring management system and method based on ecological environment protection | |
Whitehouse | IPM of mirids in Australian cotton: why and when pest managers spray for mirids | |
Horne et al. | When will integrated pest management strategies be adopted? Example of the development and implementation of integrated pest management strategies in cropping systems in Victoria | |
Jørgensen et al. | Problems with disseminating information on disease control in wheat and barley to farmers | |
CN109197276A (en) | The harvesting method of the determination method and device of agricultural product grade, agricultural product | |
Miller | Patch spraying: future role of electronics in limiting pesticide use | |
Sciarretta et al. | Spatial clustering and associations of two savannah tsetse species, Glossina morsitans submorsitans and Glossina pallidipes (Diptera: Glossinidae), for guiding interventions in an adaptive cattle health management framework | |
CN114651283A (en) | Seedling emergence by search function | |
Gerhards | Site-specific weed control |
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 | ||
CB02 | Change of applicant information |
Address after: 510000 Block C, 115 Gaopu Road, Tianhe District, Guangzhou City, Guangdong Province Applicant after: XAG Co., Ltd. Address before: 510000, No. 1, Cheng Cheng Road, Gaotang Software Park, Guangzhou, Guangdong, Tianhe District, 3A01 Applicant before: Guangzhou Xaircraft Technology Co.,Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |