CN109446959A - Partitioning method and device, the sprinkling control method of drug of target area - Google Patents
Partitioning method and device, the sprinkling control method of drug of target area Download PDFInfo
- Publication number
- CN109446959A CN109446959A CN201811217976.9A CN201811217976A CN109446959A CN 109446959 A CN109446959 A CN 109446959A CN 201811217976 A CN201811217976 A CN 201811217976A CN 109446959 A CN109446959 A CN 109446959A
- Authority
- CN
- China
- Prior art keywords
- target area
- image
- sprinkling
- density
- region
- 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
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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Catching Or Destruction (AREA)
Abstract
This application discloses a kind of partitioning method and devices of target area.Wherein, this method comprises: obtaining the image of target area；Image based on the image recognition model identification object region that training obtains, obtains the density information of at least one of target area target object；Target area is divided according to the density information of at least one target object, obtains at least one connected region.The technical issues of present application addresses as when carrying out pesticide spraying operation using to not only being damaged to the plant not by cordyceps sinensis disaster caused by the sprinkling of entire plant growth area coverage, can also cause to waste, will also result in pollution to soil to pesticide.
Description
Technical field
This application involves reading intelligent agriculture fields, in particular to a kind of partitioning method and device of target area.
Background technique
At this stage, unmanned plane is widely used in reading intelligent agriculture field, is being sprayed at present using unmanned plane to plant
All it is to be sprayed by the way of traversal when pesticide operation, is usually all uniformly to be sprayed to the entire growth district of plant, in use
The method for stating pesticide spraying can not only damage the plant not by cordyceps sinensis disaster, can also cause to waste to pesticide, right
Soil will also result in pollution, and pesticide residue is also than more serious.
For above-mentioned problem, currently no effective solution has been proposed.
Summary of the invention
The embodiment of the present application provides a kind of partitioning method and device of target area, at least to solve due to carrying out pesticide
Not only the plant not by cordyceps sinensis disaster is made using to caused by the sprinkling of entire plant growth area coverage when spraying operation
At damage, the technical issues of also causing to waste, will also result in pollution to soil to pesticide.
According to the one aspect of the embodiment of the present application, a kind of division methods of target area are 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 in target area
The density information of middle target object；Target area is divided according to the density information of at least one target object, obtain to
A few connected region.
Optionally, it in the image of the image recognition model identification object region obtained based on training, obtains in target area
Before the density information of at least one target object, the above method further include: obtain image recognition model, the step include: by
It is marked according to sample image of the density rating to magnanimity；Multiple sample images that density rating is marked are clustered, are obtained
Take the corresponding density rating of different types of sample image；Sample is carried out based on the corresponding density rating of different types of sample image
This training generates image recognition model.
Optionally, the image of the image recognition model identification object region obtained based on training, is obtained in target area extremely
The density information of few a kind of target object, comprising: the image of target area is input to image recognition model, is marked in image
The density information of different location；Based on the density information of different location in image, the density information of different zones in image is obtained.
Optionally, target area is divided according at least one target object density information, obtains at least one company
Logical region, comprising: the density information based at least one target object, division obtain at least one density section；According to difference
Density section image is divided, obtain the corresponding connected region in each density section in image.
Optionally, in the image of the image recognition model identification object region obtained based on training, target area is obtained
After the density information of at least one target object, the above method further include: the image of target area is divided into multiple specific items
Mark region；The maximum value and average value of the pesticide spraying amount in multiple sub-goal regions are determined according to density information；To including weeds
Sub-goal region carry out pesticide spraying, wherein pesticide spraying amount be pesticide spraying amount maximum value or average value.
Optionally, density information include: the distribution density information of weeds in target area, in target area pest distribution
Density information.
According to the another aspect of the embodiment of the present application, a kind of sprinkling control method of drug is additionally provided, comprising: receive spray
Spill strategy, wherein the sprinkling strategy is to determine according to following manner: at least one target object is close in foundation target area
Degree information divides target area, obtains at least one connected region；Density information according to connected region determines sprinkling
Strategy；Herbal sprinkling is carried out to target area according to sprinkling policy control.
According to the embodiment of the present application in another aspect, additionally providing the sprinkling control method of another drug, comprising: obtain
The image of target area；Image based on the image recognition model identification object region that training obtains, obtains in target area extremely
A kind of density information of few target object；Target area is divided according to the density information of at least one target object, is obtained
To at least one connected region；According to the density information for dividing at least one obtained connected region, the sprinkling plan of drug is determined
Slightly.
Optionally, above-mentioned sprinkling strategy includes: sprinkling path；The sprinkling path is determined by least one following mode:
It is successively traversed according to the location information of different connected regions and is sprayed, successively traversed according to the size information of different connected regions
It is sprayed, sprinkling path is determined according to the agriculture evil degree of different connected regions, is true according to the agriculture evil type of different connected regions
Surely it sprays path, determine sprinkling path according to the priority of different connected regions.
Optionally, it is sprayed according to the priority of different connected regions, comprising: to the identical connection of multiple density informations
When region is sprayed, the traverse path of the identical connected region of multiple density informations is connected using shortest path, is pressed
The identical connected region of multiple density informations is sprayed according to the path after connection, wherein different density informations is corresponding not
Same priority.
Optionally, above-mentioned sprinkling strategy further includes at least one of: determining the herbal sprinkling of at least one connected region
Amount；Herbal sprinkling amount is adjusted in the intersection of different connected regions；Region except at least one connected region and at least one
The spray head of sprinkling drug is opened or closed to the intersection of a connected region.
According to the embodiment of the present application in another aspect, additionally providing a kind of dividing device of target area, comprising: obtain mould
Block, for obtaining the image of target area；Identification module, the image recognition model identification object region for being obtained based on training
Image, obtain the density information of at least one of target area target object；Division unit, for according at least one target
The density information of object divides target area, obtains at least one connected region.
According to the embodiment of the present application in another aspect, additionally providing a kind of herbal sprinkling system, comprising: image collector
It sets, for obtaining the image of target area；Processor is connect with image collecting device, and the image for being obtained based on training is known
The image of other model identification object region, obtains the density information of at least one of target area target object；According at least one
The density information of kind target object divides target area, obtains at least one connected region；According to divide obtain to
A few connected region, determines the sprinkling strategy of drug；Unmanned plane, for spraying drug to target area according to sprinkling strategy.
According to the embodiment of the present application in another aspect, additionally providing a kind of storage medium, storage medium includes the journey of storage
Sequence, wherein equipment when program is run where control storage medium execute more than target area division methods and drug
Spray control method.
According to the embodiment of the present application in another aspect, additionally providing a kind of processor, processor is used to run program,
In, the division methods of target area when program is run more than execution and the sprinkling control method of drug.
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 the density information of at least one target object of target area；According at least one target pair
The density information of elephant divides target area, obtains the mode of at least one connected region, passes through machine learning model pair
The figure in plant growth region is identified that plant growth region division is multiple connections by the density information obtained according to identification
Region controls the sprinkling of pesticide according to the connected region after division, thus realize avoid pesticide waste, reduce pesticide residue,
It is planted when improving the technical effect of pesticide spraying operation effectiveness, and then solving due to carrying out pesticide spraying operation using to entire
Not only the plant not by cordyceps sinensis disaster is damaged caused by the traversal sprinkling of object growth district, can also cause wave to pesticide
The technical issues of taking, pollution will also result in soil.
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 division methods of target area of the embodiment of the present application；
Fig. 2 is the flow chart according to a kind of method of acquisition image recognition model of the embodiment of the present application；
Fig. 3 is the flow chart according to the division methods of another target area of the embodiment of the present application；
Fig. 4 a is the schematic diagram according to a kind of weed density line of the embodiment of the present application；
Fig. 4 b is the schematic diagram according to a kind of target area grid division of the embodiment of the present application；
Fig. 5 is the flow chart according to a kind of sprinkling control method of drug of the embodiment of the present application；
Fig. 6 is the flow chart according to the sprinkling control method of another drug of the embodiment of the present application；
Fig. 7 is the structure chart according to a kind of dividing device of target area of the embodiment of the present application；
Fig. 8 is the structure chart according to a kind of herbal sprinkling system 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, a kind of embodiment of the method for controlling pesticide spraying is provided, it should be noted that attached
The step of process of figure illustrates can execute in a computer system such as a set of computer executable instructions, though also,
So logical order is shown in flow charts, but in some cases, it can be to be different from shown by sequence execution herein
Or the step of description.
Fig. 1 is according to a kind of flow chart of the division methods of target area 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, the image for obtaining plant growth region is specifically using with positioning
The equipment acquisition of device, such as the mapping unmanned plane of RTK (Real-time Kinematic, abbreviation RTK) high accuracy positioning；
Or support the Mobile photographic device (camera, mobile phone) etc. of high accuracy positioning.Plant growth area can be determined by position mapping
The more specific location information in domain.
Step S104, the image based on the image recognition model identification object region that training obtains, obtains in target area
The density information of at least one target object；
In some optional embodiments of the application, before carrying out step S104, the above method further includes acquisition figure
As identification model, Fig. 2 is according to a kind of flow chart of the method for acquisition image recognition model of the embodiment of the present application, such as Fig. 2 institute
Show, method includes the following steps:
Step S202 is marked according to sample image of the density rating to magnanimity.
Step S204 clusters multiple sample images that density rating is marked, obtains different types of sample graph
As corresponding density rating.
Step S206 carries out sample training based on the corresponding density rating of different types of sample image, generates image and know
Other model.
According to an optional embodiment of the application, density information includes: the distribution density letter of weeds in target area
The distribution density information of pest in breath, target area.
Artificial intelligence recognizer is specifically to carry out density rating label to a large amount of pictures first, to label in step S204
Multiple sample images of density rating are clustered, and are obtained the corresponding density rating of different types of sample image and are referred to and pass through
Multiple sample images are clustered, the corresponding sample image of weed density grade and the corresponding figure of pest density grade are obtained
Picture.Then the corresponding sample image of weed density grade and the corresponding image of pest density grade are trained, obtain image
Identification model.
According to an optional embodiment of the application, step S104 is realized by following steps: by the figure of target area
As being input to image recognition model, the density information of different location in image is marked；Density based on different location in image
Information obtains the density information of different zones in image.
The image in the plant growth region that will acquire is input to trained image recognition model and is identified, identifies figure
The density rating of different location as in, determines plant growth area according to the density rating of the different location in the image identified
The density rating of domain different location.
Fig. 3 is according to the flow chart of the division methods of another target area of the embodiment of the present application, as shown in figure 3, should
Method includes:
The image of target area is divided into multiple sub-goal regions by step S302.
Step S304 determines the maximum value and average value of the pesticide spraying amount in multiple sub-goal regions according to density information.
Step S306 carries out pesticide spraying to the sub-goal region comprising weeds, and wherein pesticide spraying amount is above-mentioned pesticide
The maximum value or average value of fountain height.
It is multiple grids by plant growth region division, only to containing in some optional embodiments of the application
The grid of weeds carries out path planning, such as can be sprayed according to the round-trip course line of unmanned plane, then determines the sprinkling of pesticide
Amount determines the maximum fountain height for the pesticide for needing to spray in the grid divided by the density information for the weeds identified, and
Mean value computation is carried out to weed density in each grid, to determine the average sprinkling for the pesticide for needing to spray in the grid divided
Amount.Path planning only is carried out to the grid containing weeds when carrying out pesticide spraying using unmanned plane, and only to containing miscellaneous
The grid of grass is sprayed, and can be sprayed according to the maximum fountain height for the pesticide for needing to spray in grid, can also be according to grid
The average fountain height sprinkling of the middle pesticide for needing to spray.
Step S106 divides target area according to the density information of at least one target object, obtains at least one
A connected region.
According to an optional embodiment of the application, step S106 is realized by the following method: based at least one mesh
The density information of object is marked, division obtains at least one density section；Image is divided according to different density sections, is obtained
The corresponding connected region in each density section into image.
The above method is illustrated by taking the density information according to weeds as an example below: being 0 by the weed density recognized
Region do not demarcate, by weed density be every square metre 1-5 be demarcated as the first connected region, by weed density be every square metre
6-10 is demarcated as the second connected region, and so on determine multiple connected regions, the pesticide of different connected region sprinklings
Dosage is different.
Fig. 4 a is according to a kind of schematic diagram of weed density line of the embodiment of the present application, as shown in fig. 4 a, according to acquisition
The weed density of target area can determine the isodensity line chart of weeds, and the identical region of weed density is connected, and generate
Connected region can be generated according to the isopycnic of division in isopycnic schematic diagram, according to the connected region of generation to weeds into
Row pesticide spraying operation.
It can be generated according to the connected region determined only in there are the regions of cordyceps sinensis evil to carry out route planning, example
The connected region that can be first such as 1 to density carries out flight course planning then operation, and the careful degree of operation can for 1 the first connected region
Flight course planning then operation is carried out to the second connected region that density is 2 to continue to change operation dosage.
The boundary line for changing discharge rate, location information and boundary when operating equipment can also be formed according to the connected region determined
When the location information in face is overlapped, change operation dosage, guarantees that aggrieved more region job amount is big, the workload in aggrieved few region
It is small, or when guarantee fallen leaves, the high region sprinkling dosage of leaves density is big, and the sprinkling dosage in the small region of leaves density is big.
Fig. 4 b be according to a kind of schematic diagram of target area grid division of the embodiment of the present application, as shown in Figure 4 b, according to
The weed density of the target area of acquisition can carry out grid division to target area, such as will recognize no crop smothering, i.e. crop smothering
The region that density is 0 is not demarcated, and the raster data that crop smothering density is every square metre 1-5 is labeled as 1, is demarcated as the first connection
The raster data that crop smothering density is every square metre 6-10 is labeled as 2, is demarcated as the second connected region by region, and so on
The raster data for determining all grids forms multiple connected regions, and different connected regions is using different workload (sprinklings
Amount).
It can be generated according to the connected region determined only in there are the regions of cordyceps sinensis evil to carry out route planning, example
The connected region that can be first such as 1 to raster data carries out flight course planning then operation, the first connected region that the careful degree of operation is 1
Domain can continue to change the second connected region progress flight course planning then operation that operation dosage is 2 to raster data.
The boundary line for changing discharge rate, location information and boundary when operating equipment can also be formed according to the connected region determined
When the location information in face is overlapped, change operation dosage, guarantees that aggrieved more region job amount is big, the workload in aggrieved few region
It is small, or when guarantee fallen leaves, the high region sprinkling dosage of leaves density is big, and the sprinkling dosage in the small region of leaves density is big.
Through the above steps, it may be implemented to avoid pesticide waste, reduce pesticide residue, improve pesticide spraying operation effectiveness
Technical effect.
Fig. 5 is according to a kind of flow chart of the sprinkling control method of drug of the embodiment of the present application, as shown in figure 5, the party
Method the following steps are included:
Step S502 receives sprinkling strategy, wherein the sprinkling strategy is to determine according to following manner: according to target area
The density information of at least one target object divides target area in domain, obtains at least one connected region；According to even
The density information in logical region determines sprinkling strategy.
Step S504 carries out herbal sprinkling to target area according to sprinkling policy control.
It should be noted that the preferred embodiment of embodiment illustrated in fig. 5 may refer to the phase of Fig. 1 to embodiment illustrated in fig. 2
Description is closed, details are not described herein again.
Fig. 6 is according to the flow chart of the sprinkling control method of another drug of the embodiment of the present application, as shown in fig. 6, should
Method the following steps are included:
Step S602 obtains the image of target area.
Step S604, the image based on the image recognition model identification object region that training obtains, obtains in target area
The density information of at least one target object.
Step S606 divides target area according to the density information of at least one target object, obtains at least one
A connected region.
Step S608 determines the sprinkling strategy of drug according to the density information for dividing at least one obtained connected region.
In some optional embodiments of the application, the sprinkling strategy in step S508 includes sprinkling path；The sprinkling
Path passes through at least one following mode and determines: successively traversed according to the location information of different connected regions sprayed, according to
The size information of different connected regions, which successively traverses, to be sprayed, determines sprinkling road according to the agriculture evil degree of different connected regions
Diameter determines sprinkling path according to the agriculture evil type of different connected regions, determines sprinkling road according to the priority of different connected regions
Diameter.
Planning that the sprinkling path of pesticide includes any one in following methods according to connected region: according to connected region
Location information planning path, for example traversed and path planning carried out to the second connected region again after the first connected region, successively
Analogize, the advantage of doing so is that not having to continually switch unit pesticide spraying amount；It can also be according to the size information of connected region
Path planning is carried out, for example carries out pesticide spraying operation from big to small according to the area of connected region；According to different connected regions
Agriculture evil degree sprayed, such as first spray the more serious connected region of Pest organism disaster；According in different connected regions
The type of weeds or pest is sprayed.
According to an optional embodiment of the application, sprayed according to the priority of different connected regions, to more
When the identical connected region of a density information is sprayed, using shortest path by the identical connected region of multiple density informations
Traverse path connects, and sprays according to the path after connection to the identical connected region of multiple density informations.
For example it is spraying insecticide in plant growth region comprising the identical connected region of multiple weed density grades
When spraying path planning, the identical connected region of multiple weed density grades can be connected by a shortest path,
It can once complete to improve pesticide to the pesticide spraying operation of the identical connected region of above-mentioned multiple weed density grades in this way
The efficiency of spraying operation.
In some optional embodiments of the application, the sprinkling strategy in step S508 further includes at least one of:
Determine the pesticide spraying amount of at least one connected region；Pesticide spraying amount is adjusted in the intersection of different connected regions；At least
The spray head sprayed insecticide is opened or closed to the intersection in region and at least one connected region except one connected region.
Unit pesticide spraying since the weeds of different connected regions or the density of pest are different, in different zones
Amount is also different, after planning sprinkling path, when carrying out pesticide spraying, changes pesticide spray in the intersection of different connected regions
The amount of spilling, for example it is adjusted to the second fountain height in the intersection that the first connected region enters the second connected region, in the second connected region
The intersection that domain enters third connecting region is adjusted to third fountain height.It is adjusted through the above steps for different connected regions
Pesticide spraying amount, being not only able to save pesticide can also avoid multipair being not subject to weeds or pest because spraying insecticide
Plant damage.
Region and at least one company according to an optional embodiment of the application, except at least one connected region
The spray head sprayed insecticide is opened or closed to the intersection in logical region.Such as the first connected region is entered in the region that density is 0
Domain intersection opens the spray head sprayed insecticide, and closes sprinkling entering the region intersection that density is 0 from the first connected region
The spray head of pesticide.
It should be noted that preferred embodiment of the step S602 into step S604 may refer to shown in Fig. 1 and Fig. 2 in fact
The associated description of example is applied, details are not described herein again.
Fig. 7 is according to a kind of structure chart of the dividing device of target area of the embodiment of the present application, as shown in fig. 7, the dress
It sets and includes:
Module 70 is obtained, for obtaining the image of target area.
Identification module 72, the image of the image recognition model identification object region for being obtained based on training, obtains target
The density information of at least one of region target object.
Division module 74 is obtained for dividing target area according to the density information of at least one target object
At least one connected region.
It should be noted that the embodiment of the preferred embodiment of embodiment illustrated in fig. 7 may refer to shown in Fig. 1 to Fig. 2 in fact
The associated description of example is applied, details are not described herein again.
Fig. 8 is according to a kind of structure chart of herbal sprinkling system of the embodiment of the present application, as shown in figure 8, the system includes:
Image collecting device 80, for obtaining the image of target area.
Processor 82 is connect with image collecting device 70, and the image recognition model for being obtained based on training identifies target
The image in region obtains the density information of at least one of target area target object；According to the close of at least one target object
Degree information divides target area, obtains at least one connected region；Foundation divides at least one obtained connected region,
Determine the sprinkling strategy of drug.
Unmanned plane 84, for spraying drug to target area according to sprinkling strategy.
It should be noted that the embodiment of the preferred embodiment of embodiment illustrated in fig. 8 may refer to shown in Fig. 1 to Fig. 2 in fact
The associated description of example is applied, details are not described herein again.
The embodiment of the present application also provides a kind of storage medium, storage medium includes the program of storage, wherein is transported in program
The division methods of target area where controlling storage medium when row more than equipment execution and the sprinkling control method of drug.
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 the density information of at least one target object of target area；
Target area is divided according to the density information of at least one target object, obtains at least one connected region.And/or
Receive sprinkling strategy, wherein the sprinkling strategy is to determine according to following manner: according in target area at least one
The density information of a target object divides target area, obtains at least one connected region；According to the close of connected region
It spends information and determines sprinkling strategy；Herbal sprinkling is carried out to target area according to sprinkling policy control.
Image based on the image recognition model identification object region that training obtains, obtains at least one mesh of target area
Mark the density information of object；Target area is divided according to the density information of at least one target object, obtains at least one
A connected region；According to the density information for dividing at least one obtained connected region, the sprinkling strategy of drug is determined.
The embodiment of the present application also provides a kind of processor, processor is for running program, wherein holds in program operation
The division methods of target area more than row and the sprinkling control method of drug.
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 the density information of at least one target object of target area；It presses
Target area is divided according to the density information of at least one target object, obtains at least one connected region.
And/or
Receive sprinkling strategy, wherein the sprinkling strategy is to determine according to following manner: according in target area at least one
The density information of a target object divides target area, obtains at least one connected region；According to the close of connected region
It spends information and determines sprinkling strategy；Herbal sprinkling is carried out to target area according to sprinkling policy control.
Image based on the image recognition model identification object region that training obtains, obtains at least one mesh of target area
Mark the density information of object；Target area is divided according to the density information of at least one target object, obtains at least one
A connected region；According to the density information for dividing at least one obtained connected region, the sprinkling strategy of drug is determined.
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 (15)
1. a kind of division methods of target area characterized by comprising
Obtain the image of target area；
Based on the image for training obtained image recognition model to identify the target area, obtain at least one in the target area
The density information of kind target object；
The target area is divided according to the density information of at least one target object, obtains at least one connection
Region.
2. the method according to claim 1, wherein described in being identified in the image recognition model obtained based on training
The image of target area, before obtaining the density information of at least one of target area target object, the method is also wrapped
It includes:
Described image identification model is obtained, which includes:
It is marked according to sample image of the density rating to magnanimity；
Multiple sample images that density rating is marked are clustered, corresponding density of different types of sample image etc. is obtained
Grade；
Sample training is carried out based on the corresponding density rating of different types of sample image, generates described image identification model.
3. according to the method described in claim 2, it is characterized in that, identifying the mesh based on the image recognition model that training obtains
The image for marking region, obtains the density information of at least one of target area target object, comprising:
The image of the target area is input to described image identification model, marks the density of different location in described image
Information；
Based on the density information of different location in described image, the density information of different zones in described image is obtained.
4. according to the method described in claim 3, it is characterized in that, the density information according at least one target object will
The target area is divided, at least one connected region is obtained, comprising:
Based on the density information of at least one target object, division obtains at least one density section；
Described image is divided according to different density sections, obtains the corresponding connection in each density section in described image
Region.
5. the method according to claim 1, wherein described in being identified in the image recognition model obtained based on training
The image of target area, after obtaining the density information of at least one of target area target object, the method is also wrapped
It includes:
The image of the target area is divided into multiple sub-goal regions；
The maximum value and average value of the pesticide spraying amount in the multiple sub-goal region are determined according to the density information；
To comprising weeds the sub-goal region carry out pesticide spraying, wherein pesticide spraying amount be the pesticide spraying amount most
Big value or average value.
6. method as claimed in any of claims 1 to 5, which is characterized in that the density information includes: the mesh
Mark the distribution density information of weeds in region, in the target area pest distribution density information.
7. a kind of sprinkling control method of drug characterized by comprising
Receive sprinkling strategy, wherein the sprinkling strategy is to determine according to following manner: according at least one mesh in target area
The density information of mark object divides the target area, obtains at least one connected region；According to the connected region
Density information determine sprinkling strategy；
Herbal sprinkling is carried out to the target area according to the sprinkling policy control.
8. a kind of sprinkling control method of drug characterized by comprising
Obtain the image of target area；
Based on the image for training obtained image recognition model to identify the target area, obtain at least one in the target area
The density information of kind target object；
The target area is divided according to the density information of at least one target object, obtains at least one connection
Region；
According to the density information for dividing at least one obtained connected region, the sprinkling strategy of drug is determined.
9. according to the method described in claim 8, it is characterized in that, the sprinkling strategy includes:
Spray path；The sprinkling path passes through at least one following mode and determines: according to different connected regions location information according to
Secondary traversal is sprayed, successively traverses and sprayed, according to different connected regions according to the size information of different connected regions
Agriculture evil degree determines sprinkling path, determines sprinkling path, according to different connected regions according to the agriculture evil type of different connected regions
Priority determine sprinkling path.
10. according to the method described in claim 9, it is characterized in that, being sprayed according to the priority of different connected regions, packet
It includes:
When being sprayed to the identical connected region of multiple density informations, using shortest path by multiple density informations
The traverse path of identical connected region connects, according to the path after connection to the identical connection of multiple density informations
It is sprayed in region, wherein different density informations corresponds to different priority.
11. according to the method described in claim 8, it is characterized in that, the sprinkling strategy further includes at least one of:
Determine the herbal sprinkling amount of at least one connected region；
The herbal sprinkling amount is adjusted in the intersection of different connected regions；
The intersection in region and at least one connected region except at least one described connected region is opened or is closed
Close the spray head of sprinkling drug.
12. a kind of dividing device of target area characterized by comprising
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 the mesh
Mark the density information of at least one of region target object；
Division module is obtained for dividing the target area according to the density information of at least one target object
To at least one connected region.
13. a kind of herbal sprinkling system characterized by comprising
Image collecting device, for obtaining the image of target area；
Processor is connect with described image acquisition device, and the image recognition model for being obtained based on training identifies the target
The image in region obtains the density information of at least one of target area target object；According at least one target
The density information of object divides the target area, obtains at least one connected region；It is obtained at least according to dividing
One connected region determines the sprinkling strategy of drug；
Unmanned plane, for spraying drug to the target area according to the sprinkling strategy.
14. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein described program right of execution
Benefit require any one of 1 to 6 described in target area division methods and the medicine described in any one of claim 7 to 11
The sprinkling control method of object.
15. 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 6 described in target area division methods and the medicine described in any one of claim 7 to 11
The sprinkling control method of object.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811217976.9A CN109446959B (en) | 2018-10-18 | 2018-10-18 | Target area dividing method and device and medicine spraying control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811217976.9A CN109446959B (en) | 2018-10-18 | 2018-10-18 | Target area dividing method and device and medicine spraying control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109446959A true CN109446959A (en) | 2019-03-08 |
| CN109446959B CN109446959B (en) | 2021-10-08 |
Family
ID=65547450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811217976.9A Active CN109446959B (en) | 2018-10-18 | 2018-10-18 | Target area dividing method and device and medicine spraying control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109446959B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111123992A (en) * | 2019-12-30 | 2020-05-08 | 江苏省血吸虫病防治研究所 | Method for detecting ampullaria gigas and controlling dosage by using unmanned aerial vehicle |
| CN111209824A (en) * | 2019-12-30 | 2020-05-29 | 江苏省血吸虫病防治研究所 | Method for monitoring ampullaria gigas by using unmanned aerial vehicle |
| CN112136637A (en) * | 2020-09-27 | 2020-12-29 | 安阳工学院 | Self-adaptive spraying method of cotton defoliant |
| CN112425328A (en) * | 2020-11-23 | 2021-03-02 | 广州极飞科技有限公司 | Multi-material spreading control method and device, terminal equipment, unmanned equipment and medium |
| WO2021051278A1 (en) * | 2019-09-17 | 2021-03-25 | 深圳市大疆创新科技有限公司 | Earth surface feature identification method and device, unmanned aerial vehicle, and computer readable storage medium |
| CN112948371A (en) * | 2019-12-10 | 2021-06-11 | 广州极飞科技股份有限公司 | Data processing method, data processing device, storage medium and processor |
| CN113179826A (en) * | 2021-04-30 | 2021-07-30 | 梁世军 | Application technology of pesticide on water surface |
| CN114521384A (en) * | 2022-02-15 | 2022-05-24 | 深圳市杉川机器人有限公司 | Mowing method and system of intelligent mower |
| CN115151949A (en) * | 2022-06-02 | 2022-10-04 | 深圳市正浩创新科技股份有限公司 | Target object collecting method, device and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739569A (en) * | 2009-12-17 | 2010-06-16 | 北京中星微电子有限公司 | Crowd density estimation method, device and monitoring system |
| US20150206004A1 (en) * | 2014-01-20 | 2015-07-23 | Ricoh Company, Ltd. | Object tracking method and device |
| CN106585992A (en) * | 2016-12-15 | 2017-04-26 | 上海土是宝农业科技有限公司 | Method and system for intelligent identification and accurate pesticide spraying using unmanned aerial vehicles |
| CN106912331A (en) * | 2017-03-02 | 2017-07-04 | 深圳春沐源农业科技有限公司 | A kind of spray method and pesticide spraying system for crop pests |
| US20170229523A1 (en) * | 2014-08-06 | 2017-08-10 | Beijing Zhigu Rui Tuo Tech Co., Ltd | Image acquisition control methods and apparatuses, and image acquisition devices |
| US20180184637A1 (en) * | 2017-01-03 | 2018-07-05 | International Business Machines Corporation | System, method and computer program product for locust swarm amelioration |
| 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 |
-
2018
- 2018-10-18 CN CN201811217976.9A patent/CN109446959B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739569A (en) * | 2009-12-17 | 2010-06-16 | 北京中星微电子有限公司 | Crowd density estimation method, device and monitoring system |
| US20150206004A1 (en) * | 2014-01-20 | 2015-07-23 | Ricoh Company, Ltd. | Object tracking method and device |
| US20170229523A1 (en) * | 2014-08-06 | 2017-08-10 | Beijing Zhigu Rui Tuo Tech Co., Ltd | Image acquisition control methods and apparatuses, and image acquisition devices |
| CN106585992A (en) * | 2016-12-15 | 2017-04-26 | 上海土是宝农业科技有限公司 | Method and system for intelligent identification and accurate pesticide spraying using unmanned aerial vehicles |
| US20180184637A1 (en) * | 2017-01-03 | 2018-07-05 | International Business Machines Corporation | System, method and computer program product for locust swarm amelioration |
| CN106912331A (en) * | 2017-03-02 | 2017-07-04 | 深圳春沐源农业科技有限公司 | A kind of spray method and pesticide spraying system for crop pests |
| 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 |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021051278A1 (en) * | 2019-09-17 | 2021-03-25 | 深圳市大疆创新科技有限公司 | Earth surface feature identification method and device, unmanned aerial vehicle, and computer readable storage medium |
| CN112948371A (en) * | 2019-12-10 | 2021-06-11 | 广州极飞科技股份有限公司 | Data processing method, data processing device, storage medium and processor |
| CN111123992A (en) * | 2019-12-30 | 2020-05-08 | 江苏省血吸虫病防治研究所 | Method for detecting ampullaria gigas and controlling dosage by using unmanned aerial vehicle |
| CN111209824A (en) * | 2019-12-30 | 2020-05-29 | 江苏省血吸虫病防治研究所 | Method for monitoring ampullaria gigas by using unmanned aerial vehicle |
| CN112136637A (en) * | 2020-09-27 | 2020-12-29 | 安阳工学院 | Self-adaptive spraying method of cotton defoliant |
| CN112425328A (en) * | 2020-11-23 | 2021-03-02 | 广州极飞科技有限公司 | Multi-material spreading control method and device, terminal equipment, unmanned equipment and medium |
| CN113179826A (en) * | 2021-04-30 | 2021-07-30 | 梁世军 | Application technology of pesticide on water surface |
| CN114521384A (en) * | 2022-02-15 | 2022-05-24 | 深圳市杉川机器人有限公司 | Mowing method and system of intelligent mower |
| CN114521384B (en) * | 2022-02-15 | 2023-02-03 | 深圳市杉川机器人有限公司 | Mowing method and system of intelligent mower |
| CN115151949A (en) * | 2022-06-02 | 2022-10-04 | 深圳市正浩创新科技股份有限公司 | Target object collecting method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109446959B (en) | 2021-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109446959A (en) | Partitioning method and device, the sprinkling control method of drug of target area | |
| CN109197278A (en) | Determination method and device, the determination method of herbal sprinkling strategy of Job Policies | |
| CN110297483B (en) | Method and device for obtaining boundary of area to be operated and operation route planning method | |
| CN104615146B (en) | Unmanned aerial vehicle spraying operation automatic navigation method without need of external navigation signal | |
| CN105173085B (en) | Unmanned plane variable farm chemical applying automatic control system and method | |
| WO2020078396A1 (en) | Method for determining distribution information, and control method and device for unmanned aerial vehicle | |
| CN109409275B (en) | Target object identification method and device, and drug delivery information determination method | |
| CN109446958B (en) | Method, device and system for determining pesticide application effect | |
| CN109409170B (en) | Insect pest identification method and device for crops | |
| CN111582055A (en) | Aerial pesticide application route generation method and system for unmanned aerial vehicle | |
| CN109886192A (en) | A kind of ecological environment intelligent monitor system | |
| CN1628513A (en) | Method for employing agricultural chemicals to target accurately | |
| CN110399908A (en) | Classification method and device based on event mode camera, storage medium, electronic device | |
| CN110188661B (en) | Boundary identification method and device | |
| CN114545833B (en) | Intelligent interactive processing system of facility agriculture based on internet of things | |
| CN114463308A (en) | Visual detection method, device and processing equipment for visual angle photovoltaic module of unmanned aerial vehicle | |
| CN102646312B (en) | Forest smoke-fire monitoring and recognizing method suitable for distributed type parallel processing | |
| CN114511627A (en) | Target fruit positioning and dividing method and system | |
| CN109197275A (en) | The recognition methods of weeds type and device, the determination method for being administered information | |
| CN113349188A (en) | Lawn and forage grass precise weeding method based on cloud weeding spectrum | |
| Marra et al. | Terrain classification using texture for the ALV | |
| US20210084885A1 (en) | Apparatus for spray management | |
| CN109492541A (en) | Determination method and device, plant protection method, the plant protection system of target object type | |
| CN114651283A (en) | Seedling emergence by search function | |
| CN115316172B (en) | Nano pesticide application method and system based on plant protection unmanned aerial vehicle |
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: Guangzhou Jifei Technology 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 |