CN107933921A - Aircraft and its sprinkling Route Generation and execution method, apparatus, control terminal - Google Patents
Aircraft and its sprinkling Route Generation and execution method, apparatus, control terminal Download PDFInfo
- Publication number
- CN107933921A CN107933921A CN201711033665.2A CN201711033665A CN107933921A CN 107933921 A CN107933921 A CN 107933921A CN 201711033665 A CN201711033665 A CN 201711033665A CN 107933921 A CN107933921 A CN 107933921A
- Authority
- CN
- China
- Prior art keywords
- aircraft
- information
- route
- characteristic information
- characteristic
- 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 52
- 238000005507 spraying Methods 0.000 claims abstract description 88
- 239000007921 spray Substances 0.000 claims description 51
- 238000012545 processing Methods 0.000 claims description 2
- 238000013507 mapping Methods 0.000 abstract description 10
- 235000013399 edible fruits Nutrition 0.000 description 31
- 241000196324 Embryophyta Species 0.000 description 8
- 238000013135 deep learning Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 6
- 239000013558 reference substance Substances 0.000 description 6
- 238000000926 separation method Methods 0.000 description 6
- 241000209094 Oryza Species 0.000 description 5
- 235000007164 Oryza sativa Nutrition 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 235000009566 rice Nutrition 0.000 description 5
- 230000000750 progressive effect Effects 0.000 description 4
- 240000001923 Thevetia neriifolia Species 0.000 description 3
- 241000209140 Triticum Species 0.000 description 3
- 235000021307 Triticum Nutrition 0.000 description 3
- 238000010521 absorption reaction Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 235000015097 nutrients Nutrition 0.000 description 3
- 239000000575 pesticide Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 241000607479 Yersinia pestis Species 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Classifications
-
- 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
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
- B64U2101/00—UAVs specially adapted for particular uses or applications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
- B64U2201/00—UAVs characterised by their flight controls
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pest Control & Pesticides (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Processing Or Creating Images (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The present invention provides a kind of aircraft sprinkling route generation method, includes the following steps：The image information of target area is obtained, the three-dimensional map of cloud data is included according to described image information architecture；The characteristic information of the positional information of all objects and each object in the target area is determined according to the three-dimensional map；According to the positional information of all objects and characteristic information generation aircraft sprinkling route, to indicate that the aircraft implements spraying operation.This method reduces mapping time and reduces sprinkling reconnaissance survey cost, improve efficiency of the aircraft in plant protection operation to solve the problems, such as that spraying operation reconnaissance survey is of high cost in the prior art.The present invention also provides corresponding aircraft sprinkling Route Generation device and control terminal.In addition, the present invention also provides corresponding aircraft and its sprinkling route to perform method and apparatus.
Description
Technical field
The present invention relates to vehicle technology field, more particularly to a kind of aircraft and its sprinkling route generation method and dress
Put, and corresponding aircraft sprinkling route performs method and apparatus, correspondingly provides a kind of control terminal in addition.
Background technology
With the development of science and technology, aircraft such as unmanned plane etc. is obtained in various fields such as agricultural, military, industry field
Wide spectrum.As unmanned plane is flying the maturation of anti-plant protection field application, the plant protection operation demand of industrial crops is increasing,
And to realize and carry out pesticide spraying operation to industrial crops if tree etc. automatically using unmanned plane, then need to obtain in operation area
The data messages such as the geographical locations of all crops, height, central point longitude and latitude, in order to generate operation course line.In the prior art,
The acquisition of above-mentioned data usually require operator carry plotting board around farmland row take a round mapping obtain, i.e., manually survey and draw
Mode, and manually survey and draw link and expend very much time and manpower, manually survey and draw inefficiency and cost is higher, therefore spray and make
The efficiency of industry can not be guaranteed, and the economic benefit is not high.
The content of the invention
Based on the above problem, the present invention provides a kind of aircraft and its sprinkling route generation method and device, Yi Jixiang
The aircraft sprinkling route answered performs method and apparatus, a kind of control terminal is correspondingly provided in addition, to solve the prior art
The problem of middle spraying operation reconnaissance survey inefficiency is of high cost, reduces mapping time and reduces sprinkling reconnaissance survey cost, carry
Efficiency of the high aircraft in plant protection operation.
To achieve these goals, the present invention provides following technical scheme：
The present invention provides a kind of aircraft sprinkling route generation method, it includes the following steps：Obtain the figure of target area
Picture information, the three-dimensional map of cloud data is included according to described image information architecture；The mesh is determined according to the three-dimensional map
Mark the positional information of all objects and the characteristic information of each object in region；According to the positional information of all objects and spy
Reference breath generation aircraft sprinkling route, to indicate that the aircraft implements spraying operation.
It is preferred that it is described according to the three-dimensional map determine all objects in the target area positional information and
Before the step of characteristic information of each object, further include：Generate to determine the knowledge of object positional information and characteristic information
Other engine.
Specifically, the step of generation is to determine the identification engine of object positional information and characteristic information, specifically
Including：The multi-group data in relation to object positional information and characteristic information is obtained, generation includes the target area of multiple objects
Model；According to the target area model target multiple characteristic points associated with the characteristic information of each object；According to all
The positional information of object multigroup number corresponding with the matching relationship of the cloud data and the characteristic information of all objects
According to the matching relationship with all characteristic points to determine and generate the identification engine.
Further, the corresponding multi-group data of the characteristic information of all objects and all features are determined by interative computation
The matching relationship of point.
Specifically, it is described that the positional information of all objects and each is determined in the target area according to the three-dimensional map
The step of characteristic information of object, specifically include：The identification engine determines the position of each object according to the cloud data
Confidence ceases；It is described identification engine determine with the associated multiple characteristic points of each object, according to the corresponding feature of different target thing
Point determines the characteristic information of each object.
Specifically, it is described that aircraft sprinkling route is generated to indicate according to the positional information and characteristic information of all objects
The aircraft was implemented in the step of spraying operation, including：Determine aircraft in each target according to the characteristic information of each object
Spraying operation information at thing.
It is preferred that the spraying operation information includes flight time, fountain height and the sprinkling aircraft at each object
Scope.
It is preferred that height above sea level of the positional information of the object residing for including object central point longitude and latitude and object
Degree.
It is preferred that the characteristic information of the object includes relative altitude, the floor space of object and the mesh of object
Mark effective spraying range of thing.
Alternatively, calculated using RCNN (Regions with Convolutional Neural Network Features)
Method, Fast-RCNN algorithms or the generation of Faster-RCNN algorithms are drawn to the identification of definite object positional information and characteristic information
Hold up.
Correspondingly, the present invention provides a kind of aircraft sprinkling Route Generation device, it includes：Message processing module, is used for
The image information of target area is obtained, and the three-dimensional map of cloud data is included according to described image information architecture；Information identifies
Module, for generating identification engine and making the identification engine to determine own in the target area according to the three-dimensional map
The characteristic information of the positional information of object and each object；Route Generation module, for being believed according to the position of all objects
Breath and characteristic information generation aircraft sprinkling route, to indicate that the aircraft implements spraying operation.
Specifically, in described information identification module, including：Engine generation module is identified, for generating to definite target
The identification engine of object location information and characteristic information.
Specifically, in the identification engine generation module, including：Model generation unit, for obtaining related object position
Confidence ceases and the multi-group data of characteristic information, generation include the target area model of multiple objects；Target unit, for basis
The target area model target multiple characteristic points associated with the characteristic information of each object；Execution unit, according to all
The positional information of object multigroup number corresponding with the matching relationship of the cloud data and the characteristic information of all objects
According to the matching relationship with all characteristic points to determine and generate the identification engine.
Further, the corresponding multi-group data of the characteristic information of all objects and all features are determined by interative computation
The matching relationship of point.
Specifically, in the identification engine, specifically include：The clear and definite unit of positional information, for according to the cloud data
Determine the positional information of each object；The clear and definite unit of characteristic information, for determine with the associated multiple characteristic points of each object,
The characteristic information of each object is determined according to the corresponding characteristic point of different target thing.
Specifically, in the Route Generation module, including：Task configuration module, for being believed according to the feature of each object
Breath determines spraying operation information of the aircraft at each object.
It is preferred that the spraying operation information includes flight time, fountain height and the sprinkling aircraft at each object
Scope.
It is preferred that height above sea level of the positional information of the object residing for including object central point longitude and latitude and object
Degree.
It is preferred that the characteristic information of the object includes relative altitude, the floor space of object and the mesh of object
Mark effective spraying range of thing.
Alternatively, generated using RCNN algorithms, Fast-RCNN algorithms or Faster-RCNN algorithms to determine object
The identification engine of positional information and characteristic information.
Correspondingly, the present invention also provides a kind of aircraft sprinkling route to perform method, includes the following steps：Receive sprinkling road
Line related information, the sprinkling route related information are used to limit the route that the aircraft implements spraying operation；Described in startup
Aircraft, implements spraying operation according to the sprinkling route related information.
Specifically, the flight that the associated information of spraying operation includes aircraft at each object is implemented with the aircraft
Time, fountain height and spraying range.
Specifically, the sprinkling route related information includes the positional information of object and the characteristic information of object.
Further specifically, the positional information of the object is included residing for object central point longitude and latitude and object
Height above sea level.
Further specifically, the characteristic information of the object includes the relative altitude of object, the occupation of land face of object
Effective spraying range of product and object.
Correspondingly, the present invention also provides a kind of aircraft to spray route executive device, including：Information receiving module, is used for
Sprinkling route related information is received, the sprinkling route related information is used to limit the road that the aircraft implements spraying operation
Line；Starting module, for starting the aircraft, implements spraying operation according to the sprinkling route related information.
Correspondingly, the present invention also provides a kind of control terminal, it is characterised in that including：One or more processors；Storage
Device；One or more application program, wherein one or more of application programs are stored in the memory and are configured
To be performed by one or more of processors, one or more of programs are configured to：Perform any of the above-described technical side
The step of aircraft described in case sprays route generation method.
Correspondingly, the present invention also provides a kind of aircraft, it includes：One or more processors；Memory；One or more
A application program, wherein one or more of application programs are stored in the memory and are configured as by one
Or multiple processors perform, one or more of programs are configured to：Perform the flight described in any of the above-described technical solution
The step of device sprinkling route performs method.
Compared with prior art, the solution of the present invention has the advantages that：
The aircraft sprinkling route generation method of the present invention, device and control system, pass through the target area that gets
Image information builds three-dimensional map, and cloud data is included in the three-dimensional map, i.e., the position letter of all objects in target area
Breath；Therefore, believed according to the feature that image information and cloud data are the positional information and each object that can determine that all objects
Breath；Finally, aircraft sprinkling route can accordingly be generated according to the positional information of all objects and characteristic information, consequently facilitating flying
Row device completes spraying operation.Whole process is greatly enhanced without manually surveying and drawing object positional information and characteristic information
The work efficiency of mapping object positional information and characteristic information, while reduce mapping cost, improve aircraft implementation
The efficiency of spraying operation.
The identification engine can be according in the image information and corresponding three-dimensional map identification object region got
All objects, and can determine the positional information and characteristic information of each object, therefore for different target areas, only
Image information corresponding with different target region need to be obtained, you can contribute to generation sprinkling route.
The positional information of the object determines that the positional information of object is usual by the cloud data in three-dimensional map
The information of position correspondence where finger object, such as longitude of object position, latitude, height above sea level, for fixed
Object for, these positional informations are invariable.The characteristic information of object is then by identifying that engine is identified
To determine, the characteristic information of object is often referred to effective spray of the relative altitude of object, the floor space of object, object
The information such as scope are spilt, for example, for trees, its characteristic information generally comprises the height of trees, tree crown radius, tree crown border
Etc. information.Therefore, by determining the positional information of each object, then according to the positional information of object aircraft can be planned in mesh
Mark each point sprayed in region on route, each corresponding object of point；And by determining the characteristic information of each object,
It then can determine that duration, fountain height corresponding to each object, sprinkling corresponding to each object of the aircraft in each point stop
Scope etc., so as to be conducive to balance the spraying operation of aircraft.
The aircraft sprinkling route of the present invention performs method and apparatus, implements spray for limiting the aircraft by receiving
The sprinkling route related information of the route of operation is spilt, and spraying operation is implemented according to the related information, aircraft sprinkling can be improved
The efficiency of operation.
The additional aspect of the present invention and advantage will be set forth in part in the description, these will become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Substantially and it is readily appreciated that, wherein：
Fig. 1 is the flow diagram that the aircraft of the present invention sprays a kind of exemplary embodiments of route generation method；
Fig. 2 is one kind typical case's implementation for the method that identification engine is generated in the aircraft sprinkling route generation method of the present invention
The flow diagram of example；
Fig. 3 is that the aircraft of the present invention sprays the positional information and characteristic information that object is determined in route generation method
A kind of flow diagram of exemplary embodiments；
Fig. 4 is the functional block diagram that the aircraft of the present invention sprays a kind of exemplary embodiments of Route Generation device；
Fig. 5 is that the aircraft of the present invention sprays a kind of exemplary embodiments that engine generation module is identified in Route Generation device
Functional block diagram；
Fig. 6 is the principle frame that the aircraft of the present invention sprays a kind of exemplary embodiments that engine is identified in Route Generation device
Figure；
The aircraft that Fig. 7 is the present invention sprays the flow diagram that route performs a kind of exemplary embodiments of method；
Fig. 8 is the functional block diagram that the aircraft of the present invention sprays a kind of exemplary embodiments of route executive device.
Embodiment
The embodiment of the present invention is described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or has the function of same or like element.Below with reference to attached
The embodiment of figure description is exemplary, and is only used for explaining the present invention, and is not construed as limiting the claims.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singulative " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that what is used in the specification of the present invention arranges
Diction " comprising " refer to there are the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
One or more other features, integer, step, operation, element, component and/or their groups.It should be understood that when we claim member
Part is " connected " or during " coupled " to another element, it can be directly connected or coupled to other elements, or there may also be
Intermediary element.In addition, " connection " used herein or " coupling " can include wireless connection or wireless coupling.It is used herein to arrange
Taking leave "and/or" includes whole or any cell and all combinations of one or more associated list items.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific terminology), there is the meaning identical with the general understanding of the those of ordinary skill in fields of the present invention.Should also
Understand, those terms such as defined in the general dictionary, it should be understood that have with the context of the prior art
The consistent meaning of meaning, and unless by specific definitions as here, idealization or the implication of overly formal otherwise will not be used
To explain.
Aircraft typically refers to be manufactured by the mankind, can fly away from ground, in the air flight and by people come the machine of flight that controls
Tool flying object, such as space shuttle, helicopter, unmanned plane, wherein, unmanned plane is used widely in various fields.Nobody
Machine is a kind of small aircraft based on wireless remotecontrol or itself programme-control, its with it is small, cost is relatively low,
The advantages that easy to control, be commonly used for take photo by plane photography, plant protection operation, environmental monitoring, military surveillance, disaster inspection, anti-terrorism lifesaving
Deng field, conventional aircraft can be overcome the shortcomings of as present in pilot steering aircraft carries out aerial work, and reduces making
Cost and maintenance cost, while also improve delivery security.
In plant protection operation field, unmanned plane is commonly used in carrying out pesticide spraying to there are the plants such as the trees of disease pest and weed
Operation, improves the efficiency of plant protection operation.Generally use manual control unmanned plane carries out spraying operation and unmanned plane automated execution
Spraying operation two ways, it is clear that with respect to for the former, the latter is greatly improved work efficiency, precision also higher.It is necessary
Ground, will realize and such as fruit tree carry out pesticide spraying operation, it is necessary to obtain the institute in operation area to industrial crops using unmanned plane
There are the data messages such as the geographical location of crop, height, central point longitude and latitude, in order to generate spraying operation course line.And existing
In technology, these data usually require manually to be surveyed and drawn and obtained, and manually survey and draw link and expend very much time and manpower, survey
It is higher to plot this, the raising of plant protection operation efficiency is extremely limited.
Referring to Fig. 1, the present invention provides a kind of aircraft to spray route generation method, include the following steps：
Step S11：The image information of target area is obtained, the three-dimensional of cloud data is included according to described image information architecture
Map.
For implementing spraying operation using aircraft, the target area is the region of spraying operation to be performed, such as
Farmland, hillside etc., kind is implanted with crops if tree, rice, flowers etc. in the region.Described image information includes being used for target
Picture that region is recorded, image data etc., the image information of target area can be by being exclusively used in shooting high definition map, geography
The unmanned plane of mapping is shot, and the background system of the unmanned plane of the type can generate three-dimensional point cloud.Point cloud generally refers to wrap
Point set containing coordinate information, correspondingly, the cloud data included in three-dimensional map represent the coordinate of all the points in point set
Information, including longitude, latitude, height above sea level etc..Object in diverse location, its coordinate information are fixed and unique.For example,
For planting in the trees on hillside, the longitude, latitude between the trees in same height above sea level are different, in same
Height above sea level, latitude between the trees of longitude is different, and the height above sea level, longitude difference between the trees in Same Latitude are, it is necessary to illustrate
, to distinguish these differences and require unmanned plane to possess very high accuracy.The tool of all objects is included in three-dimensional map
Shape and corresponding data message, rather than object is simplified to a coordinate points, consequently facilitating to each in subsequent step
Object is recognized and distinguished, it is preferable that the central point for usually choosing object represents object in target area coordinates system
In coordinate points.The selection rule of object central point can be provided according to different needs, for example, can be with the weight of object
The heart can also be shared as its central point, or using the geometric center of object as object central point with all objects
Characteristic body is as object central point.In same target area coordinates system, all objects are required for following same rule really
The central point of fixed each object, to reduce Systematic Errors.
Certainly, in addition to cloud data, the fixed reference substance of target area selection can also be directed to, and using the reference substance as
Benchmark builds the space coordinates of target area, due to choosing point on the basis of fixed reference thing, and each object in target area
Relative position with reference substance is fixed, therefore may determine therefrom that specific position of each object in the space coordinates
Put.
Step S12：The positional information of all objects and each mesh in the target area are determined according to the three-dimensional map
Mark the characteristic information of thing.
The positional information of object corresponds to above-mentioned coordinate information, i.e. cloud data.Cloud data is included in three-dimensional map
In, it is therefore desirable to the three-dimensional map is obtained, cloud data therein could be parsed and presented.
The characteristic information of object includes but not limited to the relative altitude of object, the floor space of object and object
Effective spraying range.With reference to specific example in order to understand, for example, when the object is fruit tree, its relative altitude refers to
Be fruit tree vertex relative to the height on ground, the maximum that unmanned plane flies at the fruit tree position can be set by the index
Highly；The floor space of fruit tree is not only limited to the floor area that its tree root occupies, and also the tree crown including fruit tree is maximum transversal
The frontal projected area of area, i.e. tree crown on the ground, can determine the size of its frontal projected area by determining the border of tree crown,
Generally it is also contemplated that the orthographic projection of tree crown on the ground is rounded, therefore it can determine tree crown on the ground by measuring tree crown radius
Frontal projected area, spray area of the unmanned plane at the fruit tree position can determine that by the index；Effective sprinkling model of fruit tree
Enclose, refer to need the position for implementing spraying operation on fruit tree, generally also can efficient absorption nutrient, the position of moisture, such as
Fruit tree tree root, leaf etc., fountain height of the unmanned plane at the fruit tree position is can determine that by the index.When the object is agriculture
During field crop (such as rice, wheat), then it needs to be determined that area (floor space for corresponding to object), the different croplands in farmland
Between the spacing distance effective spraying range of object (correspond to) etc..For different crops, it is necessary to clear and definite feature
Information is not quite similar, and the characteristic information is also not limited to the relative altitude of object, the floor space of object and mesh
Effective spraying range of thing etc. is marked, specifically needs to determine with reference to different crops.
Step S13：According to the positional information of all objects and characteristic information generation aircraft sprinkling route, to indicate
State aircraft and implement spraying operation.
It can determine that aircraft sprays each point on route, Mei Gedian in the target area according to the positional information of object
A corresponding object, sprinkling route can be constructed by connecting these points.
By determining the characteristic information of each object, then spraying operation information of the aircraft at each object is can determine that,
The spraying operation information includes but not limited to the duration that aircraft stops in each object position, corresponding to each target
The fountain height of thing, corresponding to spraying range of each object etc. so that be conducive to balance aircraft spraying operation.
, it is necessary to generate identification engine before above-mentioned steps S12, the identification engine has the ability of deep learning, energy
It is enough according to the three-dimensional map and with the associated data message of three-dimensional map and determine the positional information and characteristic information of object,
For example, the identification engine can determine that the coordinate of different target thing, the object included according to three-dimensional map according to cloud data
Shape and relevant data message can determine that the characteristic information of object, the occupation of land of relative altitude, object such as object
Area etc..
Alternatively, RCNN algorithms (Regions with Convolutional Neural Network can be passed through
Features), any one in Fast-RCNN algorithms or Faster-RCNN algorithms generates described identification engine, above-mentioned three kinds
Algorithm is all mainly to carry out target detection using deep learning, and three kinds of algorithms are relation progressive successively, and every kind of algorithm is all preceding
It is improved and optimizes on the basis of a kind of algorithm, therefore the effect of three kinds of algorithms is also in progressive relationship successively.
Referring to Fig. 2, in RCNN algorithms, Fast-RCNN algorithms or Faster-RCNN algorithms any one algorithm base
On plinth, following steps need to be completed by generating the identification engine：
Step S01：The multi-group data in relation to object positional information and characteristic information is obtained, generation includes multiple objects
Target area model.
Target area includes substantial amounts of object, therefore some objects can be chosen from object, and obtains object
Positional information and characteristic information.The positional information of object can determine that the characteristic information of object then leads to by cloud data
Manually mark is crossed to be determined.As it was noted above, the positional information of object includes longitude, latitude, the height above sea level residing for object
Height etc., the characteristic information of object include effective sprinkling of the relative altitude of object, the floor space of object, object
Scope etc., for example, it is necessary to mark the distance on trees vertex and ground, tree crown border, tree crown radius etc. for trees.Really
Set the goal the positional information of thing, and after the characteristic information by manually marking definite object, is correspondingly formed data table related, after
And target area model can be generated on the basis of the tables of data.
Certainly, the target area model can also be used the related data in other regions and generate, which has and mesh
The similar feature in region is marked, and can determine that the positional information and characteristic information of respective objects thing in the region.For example, the region
Geographical environment it is identical or close with the geographical environment of target area, the crops in crops and target area in the region
With same or similar shape, the crops in crops and target area in the region have same or similar distribution
Rule, etc..
Step S02：According to the target area model target multiple features associated with the characteristic information of each object
Point.
Whether in the model of target area, or in actual target area, object all cannot be only with single
Coordinate points represent, otherwise can not be successfully implementation spraying operation.The characteristic information of different target thing is not quite similar, therefore to survey on the spot
Amount is undesirable to determine that the way of the characteristic information of each object is spent human and material resources very much.In consideration of it, determining object
On the basis of shape, multiple characteristic points are chosen according to object shape and carry out target, then pass through the position between different characteristic point
Relation and distance are put to determine the characteristic information of object.For example, for trees, first chosen in the model of target area
One object, and some characteristic points are chosen on the object by mark, such as the separation on the vertex of trees, trees and ground
Any opposite 2 points of (separation is usually located on tree root axle center), tree crown bottom margin, to form multigroup corresponding data.
Specifically, the separation with reference to the vertex of trees and trees and ground can determine that the trees are relatively high in the model of target area
Degree, with reference to any 2 points of opposite tree crown radiuses that can determine that in the model of target area of tree crown bottom margin, so that it is determined that target
The floor space of trees in regional model.Obviously, on this basis, and in the big of target area model and realistic objective region
Under the conditions of small scale is known, it may be determined that the relative altitude of trees, floor space etc. in realistic objective region.
Step S03：According to the matching relationship and all targets of the positional information of all objects and the cloud data
The corresponding multi-group data of characteristic information of thing and the matching relationship of all characteristic points are to determine and generate the identification engine.
Since the positional information of object is corresponded with cloud data, as long as cloud data is determined, you can
Determine the positional information of each object.
For the matching relationship of the characteristic point on the corresponding multi-group data of object characteristic information and object, in order to
Make matching relationship more accurate, it is necessary to reduce error, cause object and reality in the model of target area to the full extent
Respective objects thing in object module is consistent.Therefore, target area model can be continued to optimize using interative computation, in short
It, after the matching relationship for often determining the object in a model and the object in realistic objective region, then carries out further
Matching, until error is reduced in the range of permission.
Similarly, the positional information of each object can also be carried out excellent with the matching relationship with cloud data by interative computation
Change.
After above-mentioned series of steps, the identification engine can be generated, on the basis of trained, the identification is drawn
Hold up with the ability for carrying out deep learning, after the three-dimensional map is obtained, the identification engine can be according to the specific of object
Shape determines according to these characteristic points the characteristic information of object to the multiple characteristic points of its target, therefore without to described three
The object tieed up in map carries out artificial target, improves operational efficiency.As it was noted above, the identification engine can be according to described three
Tie up map and determine the positional information and characteristic information of each object in target area.
Referring to Fig. 3, specifically, it is described to identify that the step of engine determines object positional information and characteristic information is included such as
Lower specific steps：
Step S121：The identification engine determines the positional information of each object according to the cloud data.
By description above, in the model of target area, the positional information of object is matched with cloud data, described
Identify that engine can determine specific location of each object in target area coordinates system according to cloud data.
Step S122：It is described identification engine determine with the associated multiple characteristic points of each object, according to different target thing
Corresponding characteristic point determines the characteristic information of each object.
Difference lies in the purpose of step S03 is by determining that object characteristic information is corresponding to this step with step S03
Multi-group data and the matching relationship of characteristic point and generate the identification engine, its data used, information etc. are from target area
Obtain, and step S122 is by identifying engine, and in the corresponding multi-group data of object characteristic information and Feature Points Matching
What relation carried out under conditions of having built up, its data used is that the image information of foundation target area is built dimensionally
Figure., can be according to the object characteristic information having built up since the identification engine has the ability for carrying out deep learning
On the basis of corresponding multi-group data and Feature Points Matching relation, the target in pair target area similar to target area model
Thing is identified, so that it is determined that its characteristic information.
In conclusion the aircraft sprinkling route generation method of the present invention, is believed by the image of the target area got
Breath builds three-dimensional map, includes cloud data in the three-dimensional map, i.e., the positional information of all objects in target area；Cause
This, is the characteristic information for the positional information and each object that can determine that all objects according to image information and cloud data；Most
Afterwards, aircraft sprinkling route can accordingly be generated according to the positional information of all objects and characteristic information, consequently facilitating aircraft
Complete spraying operation.Whole process drastically increases survey without manually surveying and drawing object positional information and characteristic information
The work efficiency of object positional information and characteristic information is painted, reduces mapping cost, aircraft is improved and implements spraying operation
Efficiency.
Correspondingly, the present invention also provides a kind of control terminal, it includes：One or more processors；Memory；One or
Multiple application programs, wherein one or more of application programs are stored in the memory and are configured as by described one
A or multiple processors perform, and one or more of programs are configured to：Perform and fly described in any of the above-described technical solution
Row device sprays the step of route generation method.Therefore the control terminal has the excellent of aircraft sprinkling route generation method
Point, therefore do not repeat.
Referring to Fig. 4, correspondingly, the present invention also provides a kind of aircraft to spray Route Generation device, it is included at information
Module 11, information identification module 12 and Route Generation module 13 are managed, specifically：
Described information processing module 11, for obtaining the image information of target area, according to described image information architecture bag
Three-dimensional map containing cloud data.
For implementing spraying operation using aircraft, the target area is the region of spraying operation to be performed, such as
Farmland, hillside etc., kind is implanted with crops if tree, rice, flowers etc. in the region.Described image information includes being used for target
Picture that region is recorded, image data etc., the image information of target area can be by being exclusively used in shooting high definition map, geography
The unmanned plane of mapping is shot, and the background system of the unmanned plane of the type can generate three-dimensional point cloud.Point cloud generally refers to wrap
Point set containing coordinate information, correspondingly, the cloud data included in three-dimensional map represent the coordinate of all the points in point set
Information, including longitude, latitude, height above sea level etc..Object in diverse location, its coordinate information are fixed and unique.For example,
For planting in the trees on hillside, the longitude, latitude between the trees in same height above sea level are different, in same
Height above sea level, latitude between the trees of longitude is different, and the height above sea level, longitude difference between the trees in Same Latitude are, it is necessary to illustrate
, to distinguish these differences and require unmanned plane to possess very high accuracy.The tool of all objects is included in three-dimensional map
Shape and corresponding data message, rather than object is simplified to a coordinate points, consequently facilitating to each in subsequent step
Object is recognized and distinguished, it is preferable that the central point for usually choosing object represents object in target area coordinates system
In coordinate points.The selection rule of object central point can be provided according to different needs, for example, can be with the weight of object
The heart can also be shared as its central point, or using the geometric center of object as object central point with all objects
Characteristic body is as object central point.In same target area coordinates system, all objects are required for following same rule really
The central point of fixed each object, to reduce Systematic Errors.
Certainly, in addition to cloud data, the fixed reference substance of target area selection can also be directed to, and using the reference substance as
Benchmark builds the space coordinates of target area, due to choosing point on the basis of fixed reference thing, and each object in target area
Relative position with reference substance is fixed, therefore may determine therefrom that specific position of each object in the space coordinates
Put.
Described information identification module 12, for generating identification engine and making the identification engine can be according to the three-dimensional map
Determine the characteristic information of the positional information of all objects and each object in the target area.
The positional information of object corresponds to above-mentioned coordinate information, i.e. cloud data.Cloud data is included in three-dimensional map
In, it is therefore desirable to the three-dimensional map is obtained, cloud data therein could be parsed and presented.
The characteristic information of object includes but not limited to the relative altitude of object, the floor space of object and object
Effective spraying range.With reference to specific example in order to understand, for example, when the object is fruit tree, its relative altitude refers to
Be fruit tree vertex relative to the height on ground, the maximum that unmanned plane flies at the fruit tree position can be set by the index
Highly；The floor space of fruit tree is not only limited to the floor area that its tree root occupies, and also the tree crown including fruit tree is maximum transversal
The frontal projected area of area, i.e. tree crown on the ground, can determine the size of its frontal projected area by determining the border of tree crown,
Generally it is also contemplated that the orthographic projection of tree crown on the ground is rounded, therefore it can determine tree crown on the ground by measuring tree crown radius
Frontal projected area, spray area of the unmanned plane at the fruit tree position can determine that by the index；Effective sprinkling model of fruit tree
Enclose, refer to need the position for implementing spraying operation on fruit tree, generally also can efficient absorption nutrient, the position of moisture, such as
Fruit tree tree root, leaf etc., fountain height of the unmanned plane at the fruit tree position is can determine that by the index.When the object is agriculture
During field crop (such as rice, wheat), then it needs to be determined that area (floor space for corresponding to object), the different croplands in farmland
Between the spacing distance effective spraying range of object (correspond to) etc..For different crops, it is necessary to clear and definite feature
Information is not quite similar, and the characteristic information is also not limited to the relative altitude of object, the floor space of object and mesh
Effective spraying range of thing etc. is marked, specifically needs to determine with reference to different crops.
The Route Generation module 13, for the positional information according to all objects and characteristic information generation aircraft spray
Route is spilt, to indicate that the aircraft implements spraying operation.
It can determine that aircraft sprays each point on route, Mei Gedian in the target area according to the positional information of object
A corresponding object, sprinkling route can be constructed by connecting these points.
The Route Generation module 13 includes task configuration module (not shown, similarly hereinafter), is determining the feature of each object
After information, the task configuration module can determine that spraying operation information of the aircraft at each object, the spraying operation letter
Breath includes but not limited to duration, the fountain height, right corresponding to each object that aircraft is stopped in each object position
Should be in spraying range of each object etc., so as to be conducive to balance the spraying operation of aircraft.
The identification engine has the ability of deep learning, can be according to the three-dimensional map and associated with three-dimensional map
The positional information and characteristic information of data message and definite object, for example, the identification engine can determine that according to cloud data
The coordinate of different target thing, the object shape and relevant data message included according to three-dimensional map can determine that object
The relative altitude of characteristic information, such as object, the floor space of object.
The identification engine is generated, needs to include identifying that engine generation module (is not schemed in described information identification module 12
Show).Alternatively, for the identification engine generation module, RCNN algorithms, Fast-RCNN algorithms or Faster- can be passed through
Any one in RCNN algorithms generates the identification engine, and above-mentioned three kinds of algorithms are all mainly to carry out target using deep learning
Detection, three kinds of algorithms are relation progressive successively, and every kind of algorithm is all improved and optimizes on the basis of former algorithm, because
The effect of this three kinds of algorithms is also in progressive relationship successively.
Referring to Fig. 5, in RCNN algorithms, Fast-RCNN algorithms or Faster-RCNN algorithms any one algorithm base
On plinth, the identification engine generation module need to include model generation unit 101, target unit 102 and execution unit 103, specifically
Ground：
The model generation unit 101, it is raw for obtaining the multi-group data in relation to object positional information and characteristic information
Into the target area model comprising multiple objects.
Target area includes substantial amounts of object, therefore some objects can be chosen from object, and obtains object
Positional information and characteristic information.The positional information of object can determine that the characteristic information of object then leads to by cloud data
Manually mark is crossed to be determined.As it was noted above, the positional information of object includes longitude, latitude, the height above sea level residing for object
Height etc., the characteristic information of object include effective sprinkling of the relative altitude of object, the floor space of object, object
Scope etc., for example, it is necessary to mark the distance on trees vertex and ground, tree crown border, tree crown radius etc. for trees.Really
Set the goal the positional information of thing, and after the characteristic information by manually marking definite object, is correspondingly formed data table related, after
And target area model can be generated on the basis of the tables of data.
Certainly, the target area model can also be used the related data in other regions and generate, which has and mesh
The similar feature in region is marked, and can determine that the positional information and characteristic information of respective objects thing in the region.For example, the region
Geographical environment it is identical or close with the geographical environment of target area, the crops in crops and target area in the region
With same or similar shape, the crops in crops and target area in the region have same or similar distribution
Rule, etc..
The target unit 102, for related to the characteristic information of each object according to the target area model target
Multiple characteristic points of connection.
Whether in the model of target area, or in actual target area, object all cannot be only with single
Coordinate points represent, otherwise can not be successfully implementation spraying operation.The characteristic information of different target thing is not quite similar, therefore to survey on the spot
Amount is undesirable to determine that the way of the characteristic information of each object is spent human and material resources very much.In consideration of it, determining object
On the basis of shape, multiple characteristic points are chosen according to object shape and carry out target, then pass through the position between different characteristic point
Relation and distance are put to determine the characteristic information of object.For example, for trees, first chosen in the model of target area
One object, and some characteristic points are chosen on the object by mark, such as the separation on the vertex of trees, trees and ground
Any opposite 2 points of (separation is usually located on tree root axle center), tree crown bottom margin, form corresponding multi-group data.Tool
Body, it can determine that the trees are relatively high in the model of target area with reference to the separation of the vertex of trees and trees and ground
Degree, with reference to any 2 points of opposite tree crown radiuses that can determine that in the model of target area of tree crown bottom margin, so that it is determined that target
The floor space of trees in regional model.Obviously, on this basis, and in the big of target area model and realistic objective region
Under the conditions of small scale is known, it may be determined that the relative altitude of trees, floor space etc. in realistic objective region.
The execution unit 103, for the positional information according to all objects and the matching relationship of the cloud data
And the matching relationship of the corresponding multi-group data of characteristic information of all objects and all characteristic points is described to determine and generate
Identify engine.
Since the positional information of object is corresponded with cloud data, as long as cloud data is determined, you can
Determine the positional information of each object.
For the matching relationship of the characteristic point on the corresponding multi-group data of object characteristic information and object, in order to
Make matching relationship more accurate, it is necessary to reduce error, cause object and reality in the model of target area to the full extent
Respective objects thing in object module is consistent.Therefore, target area model can be continued to optimize using interative computation, in short
It, after the matching relationship for often determining the object in a model and the object in realistic objective region, then carries out further
Matching, until error is reduced in the range of permission.
Similarly, the positional information of each object can also be carried out excellent with the matching relationship with cloud data by interative computation
Change.
On the basis of trained, the identification engine has the ability for carrying out deep learning, is obtaining the three-dimensional
After map, the identification engine can be according to the concrete shape of object to the multiple characteristic points of its target, and according to these characteristic points
Determine the characteristic information of object, therefore without carrying out artificial target to the object in the three-dimensional map, improve operation effect
Rate.As it was noted above, the identification engine can determine the position letter of each object in target area according to the three-dimensional map
Breath and characteristic information.
Referring to Fig. 6, specifically, the identification engine includes the clear and definite unit 121 of positional information, the clear and definite unit of characteristic information
122, specifically：
The clear and definite unit 121 of positional information, for determining the positional information of each object according to the cloud data.
By description above, in the model of target area, the positional information of object is matched with cloud data, described
Identify that engine can determine specific location of each object in target area coordinates system according to cloud data.
The clear and definite unit 122 of characteristic information, for the definite and associated multiple characteristic points of each object, according to difference
The corresponding characteristic point of object determines the characteristic information of each object.
It is with 103 difference of execution unit, the purpose of the execution unit 103 is by determining that object is special
Reference ceases the matching relationship of corresponding multi-group data and characteristic point and generates the identification engine, its data used, information etc.
Obtained from target area, and the clear and definite unit 122 of the characteristic information, it is to believe by identifying engine, and in object characteristic
Cease what is carried out under conditions of corresponding multi-group data has built up with Feature Points Matching relation, its data used is according to target
The three-dimensional map of the image information structure in region., can root since the identification engine has the ability for carrying out deep learning
According to the corresponding multi-group data of object characteristic information that has built up with the basis of Feature Points Matching relation, pair and target area
Object in the similar target area of model is identified, so that it is determined that its characteristic information.
In conclusion the aircraft sprinkling Route Generation device of the present invention, is believed by the image of the target area got
Breath builds three-dimensional map, includes cloud data in the three-dimensional map, i.e., the positional information of all objects in target area；Cause
This, is the characteristic information for the positional information and each object that can determine that all objects according to image information and cloud data；Most
Afterwards, aircraft sprinkling route can accordingly be generated according to the positional information of all objects and characteristic information, consequently facilitating aircraft
Complete spraying operation.Whole process reduces mapping cost without manually surveying and drawing object positional information and characteristic information,
And the work efficiency of mapping object positional information and characteristic information is drastically increased, so as to also improve aircraft implementation
The efficiency of spraying operation.
Referring to Fig. 7, correspondingly, present invention also offers a kind of aircraft sprinkling route to perform method, it includes as follows
Step：
Step S21：Sprinkling route related information is received, the sprinkling route related information is used to limit the aircraft reality
Apply the route of spraying operation.
The sprinkling route related information includes but not limited to the characteristic information of the positional information and object of object.Institute
State sprinkling route related information generally to detect by external device (ED) to obtain, the aircraft need to only receive these letters from external device (ED)
Breath, then performs spraying operation according to these information.
Specifically, the positional information of object includes longitude, latitude, height above sea level of object position etc., passes through
Corresponding coordinate system is established to can determine that.
The characteristic information of object includes but not limited to the relative altitude of object, the floor space of object and object
Effective spraying range.With reference to specific example in order to understand, for example, when the object is fruit tree, its relative altitude refers to
Be fruit tree vertex relative to the height on ground, the maximum that unmanned plane flies at the fruit tree position can be set by the index
Highly；The floor space of fruit tree is not only limited to the floor area that its tree root occupies, and also the tree crown including fruit tree is maximum transversal
The frontal projected area of area, i.e. tree crown on the ground, can determine the size of its frontal projected area by determining the border of tree crown,
Generally it is also contemplated that the orthographic projection of tree crown on the ground is rounded, therefore it can determine tree crown on the ground by measuring tree crown radius
Frontal projected area, spray area of the unmanned plane at the fruit tree position can determine that by the index；Effective sprinkling model of fruit tree
Enclose, refer to need the position for implementing spraying operation on fruit tree, generally also can efficient absorption nutrient, the position of moisture, such as
Fruit tree tree root, leaf etc., fountain height of the unmanned plane at the fruit tree position is can determine that by the index.When the object is agriculture
During field crop (such as rice, wheat), then it needs to be determined that area (floor space for corresponding to object), the different croplands in farmland
Between the spacing distance effective spraying range of object (correspond to) etc..For different crops, it is necessary to clear and definite feature
Information is not quite similar, and the characteristic information is also not limited to the relative altitude of object, the floor space of object and mesh
Effective spraying range of thing etc. is marked, specifically needs to determine with reference to different crops.
Step S22：Start the aircraft, implement spraying operation according to the sprinkling route related information.
In general, implementing the associated information of spraying operation with the aircraft includes but not limited to aircraft in each object
Flight time at place, fountain height and spraying range etc., so as to be conducive to balance the spraying operation of aircraft.
Referring to Fig. 8, the present invention also provides a kind of aircraft to spray route executive device, it includes information receiving module 21
With starting module 22, specifically：
Described information receiving module 21, sprays route related information for receiving, and the sprinkling route related information is used for
Limit the route that the aircraft implements spraying operation.
The starting module 22, for starting the aircraft, implements sprinkling according to the sprinkling route related information and makees
Industry.
The aircraft sprinkling route executive device is corresponding with aircraft sprinkling route execution method, therefore does not go to live in the household of one's in-laws on getting married
State.
The aircraft sprinkling route of the present invention performs method and apparatus, implements spray for limiting the aircraft by receiving
The sprinkling route related information of the route of operation is spilt, and spraying operation is implemented according to the related information, aircraft sprinkling can be improved
The efficiency of operation.
In addition, present invention also offers a kind of aircraft, it includes：One or more processors；Memory；One or more
A application program, wherein one or more of application programs are stored in the memory and are configured as by one
Or multiple processors perform, one or more of programs are configured to：Perform the aircraft sprinkling route and perform method
The step of.Therefore the flying instrument has the advantages of aircraft sprinkling route performs method, therefore does not repeat.
It is often necessary to which the aircraft sprinkling route executive device is combined with aircraft sprinkling Route Generation device, change
Yan Zhi, sprays Route Generation device by the aircraft and sprays route to generate aircraft, and is sprayed by the aircraft
Route execution side device implements spraying operation on the basis of the aircraft sprays route.
The above is only some embodiments of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (28)
1. a kind of aircraft sprays route generation method, it is characterised in that includes the following steps：
The image information of target area is obtained, the three-dimensional map of cloud data is included according to described image information architecture；
The positional information of all objects and the feature of each object letter in the target area are determined according to the three-dimensional map
Breath；
According to the positional information of all objects and characteristic information generation aircraft sprinkling route, to indicate that the aircraft is implemented
Spraying operation.
2. aircraft according to claim 1 sprays route generation method, it is characterised in that described according to the three-dimensional
Before map determines the step of characteristic information of the positional information of all objects and each object in the target area, also wrap
Include：
Generate to determine the identification engine of object positional information and characteristic information.
3. aircraft according to claim 2 sprays route generation method, it is characterised in that the generation is to definite mesh
The step of identification engine of mark object location information and characteristic information, specifically include：
The multi-group data in relation to object positional information and characteristic information is obtained, generation includes the target area mould of multiple objects
Type；
According to the target area model target multiple characteristic points associated with the characteristic information of each object；
According to the positional information of all objects and the matching relationship of the cloud data and the characteristic information of all objects
The matching relationship of corresponding multi-group data and all characteristic points is to determine and generate the identification engine.
4. aircraft according to claim 3 sprays route generation method, it is characterised in that determines institute by interative computation
There are the corresponding multi-group data of characteristic information of object and the matching relationship of all characteristic points.
5. aircraft according to claim 3 sprays route generation method, it is characterised in that described in the basis dimensionally
Figure determines the step of characteristic information of the positional information of all objects and each object in the target area, specifically includes：
The identification engine determines the positional information of each object according to the cloud data；
It is described identification engine determine with the associated multiple characteristic points of each object, it is true according to the corresponding characteristic point of different target thing
The characteristic information of fixed each object.
6. aircraft according to claim 1 sprays route generation method, it is characterised in that described according to all objects
Positional information and characteristic information generation aircraft sprinkling route to indicate in the step of aircraft implements spraying operation, bag
Include：
Spraying operation information of the aircraft at each object is determined according to the characteristic information of each object.
7. aircraft according to claim 6 sprays route generation method, it is characterised in that the spraying operation packet
Include flight time, fountain height and spraying range of the aircraft at each object.
8. aircraft according to claim 1 sprays route generation method, it is characterised in that the position letter of the object
Breath includes object central point longitude and latitude and the height above sea level residing for object.
9. aircraft according to claim 1 sprays route generation method, it is characterised in that the feature letter of the object
Breath includes effective spraying range of the relative altitude of object, the floor space of object and object.
10. aircraft according to claim 3 sprays route generation method, it is characterised in that using RCNN algorithms,
Fast-RCNN algorithms or the generation of Faster-RCNN algorithms are to definite object positional information and the identification engine of characteristic information.
11. a kind of aircraft sprays Route Generation device, it is characterised in that including：
Message processing module, point cloud number is included for obtaining the image information of target area, and according to described image information architecture
According to three-dimensional map；
Information identification module, for generating identification engine and making the identification engine to determine the mesh according to the three-dimensional map
Mark the positional information of all objects and the characteristic information of each object in region；
Route Generation module, sprays route for the positional information according to all objects and characteristic information generation aircraft, with
Indicate that the aircraft implements spraying operation.
12. aircraft according to claim 11 sprays Route Generation device, it is characterised in that described information identification module
In, including：
Engine generation module is identified, for generating the identification engine to definite object positional information and characteristic information.
13. aircraft according to claim 12 sprays Route Generation device, it is characterised in that the identification engine generation
In module, specifically include：
Model generation unit, for obtaining the multi-group data in relation to object positional information and characteristic information, generation is comprising multiple
The target area model of object；
Target unit, for according to the target area model target multiple features associated with the characteristic information of each object
Point；
Execution unit, according to the matching relationship and all objects of the positional information of all objects and the cloud data
The matching relationship of the corresponding multi-group data of characteristic information and all characteristic points is to determine and generate the identification engine.
14. aircraft according to claim 13 sprays Route Generation device, it is characterised in that is determined by interative computation
The corresponding multi-group data of characteristic information of all objects and the matching relationship of all characteristic points.
15. aircraft according to claim 13 sprays Route Generation device, it is characterised in that in the identification engine,
Specifically include：
The clear and definite unit of positional information, for determining the positional information of each object according to the cloud data；
The clear and definite unit of characteristic information, for the definite and associated multiple characteristic points of each object, corresponds to according to different target thing
Characteristic point determine the characteristic information of each object.
16. aircraft according to claim 11 sprays Route Generation device, it is characterised in that the Route Generation module
In, including：
Task configuration module, for determining that spraying operation of the aircraft at each object is believed according to the characteristic information of each object
Breath.
17. aircraft according to claim 16 sprays Route Generation device, it is characterised in that the spraying operation information
Including aircraft flight time, fountain height and spraying range at each object.
18. aircraft according to claim 11 sprays Route Generation device, it is characterised in that the position of the object
Height above sea level of the information residing for including object central point longitude and latitude and object.
19. aircraft according to claim 11 sprays Route Generation device, it is characterised in that the feature of the object
Effective spraying range of relative altitude of the information including object, the floor space of object and object.
20. aircraft according to claim 13 sprays Route Generation device, it is characterised in that using RCNN algorithms,
Fast-RCNN algorithms or the generation of Faster-RCNN algorithms are to definite object positional information and the identification engine of characteristic information.
21. a kind of aircraft sprinkling route performs method, it is characterised in that includes the following steps：
Sprinkling route related information is received, the sprinkling route related information is used to limit the aircraft implementation spraying operation
Route；
Start the aircraft, implement spraying operation according to the sprinkling route related information.
22. aircraft sprinkling route according to claim 21 performs method, it is characterised in that implements with the aircraft
The associated information of spraying operation includes flight time, fountain height and the spraying range aircraft at each object.
23. aircraft sprinkling route according to claim 21 performs method, it is characterised in that the sprinkling route association
Information includes the positional information of object and the characteristic information of object.
24. aircraft sprinkling route according to claim 23 performs method, it is characterised in that the position of the object
Height above sea level of the information residing for including object central point longitude and latitude and object.
25. aircraft sprinkling route according to claim 23 performs method, it is characterised in that the feature of the object
Effective spraying range of relative altitude of the information including object, the floor space of object and object.
26. a kind of aircraft sprays route executive device, it is characterised in that including：
Information receiving module, sprays route related information for receiving, and the sprinkling route related information is used to limit described fly
Row device implements the route of spraying operation；
Starting module, for starting the aircraft, implements spraying operation according to the sprinkling route related information.
A kind of 27. control terminal, it is characterised in that including：
One or more processors；
Memory；
One or more application program, wherein one or more of application programs are stored in the memory and are configured
To be performed by one or more of processors, one or more of programs are configured to：Perform according to claim 1-10
The step of aircraft described in middle any one sprays route generation method.
A kind of 28. aircraft, it is characterised in that including：
One or more processors；
Memory；
One or more application program, wherein one or more of application programs are stored in the memory and are configured
To be performed by one or more of processors, one or more of programs are configured to：Perform according to claim 21-25
The step of aircraft sprinkling route described in middle any one performs method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711033665.2A CN107933921B (en) | 2017-10-30 | 2017-10-30 | Aircraft, spraying route generation and execution method and device thereof, and control terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711033665.2A CN107933921B (en) | 2017-10-30 | 2017-10-30 | Aircraft, spraying route generation and execution method and device thereof, and control terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107933921A true CN107933921A (en) | 2018-04-20 |
| CN107933921B CN107933921B (en) | 2020-11-17 |
Family
ID=61936678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711033665.2A Active CN107933921B (en) | 2017-10-30 | 2017-10-30 | Aircraft, spraying route generation and execution method and device thereof, and control terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107933921B (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108803657A (en) * | 2018-06-13 | 2018-11-13 | 仲恺农业工程学院 | A kind of unmanned plane plant protection monitoring system and method for manipulating automatically |
| CN108812599A (en) * | 2018-06-13 | 2018-11-16 | 仲恺农业工程学院 | A kind of unmanned plane plant protection monitoring system and method for manual manipulation |
| CN109271862A (en) * | 2018-08-15 | 2019-01-25 | 广州极飞科技有限公司 | Sprinkling control method and terminal, mobile device based on mobile device |
| CN109445457A (en) * | 2018-10-18 | 2019-03-08 | 广州极飞科技有限公司 | Determination method, the control method and device of unmanned vehicle of distributed intelligence |
| CN109507967A (en) * | 2018-11-30 | 2019-03-22 | 广州极飞科技有限公司 | Job control method and device |
| CN109699620A (en) * | 2019-01-15 | 2019-05-03 | 广州极飞科技有限公司 | Liquid infusion method, control device and perfusion machine |
| CN109784626A (en) * | 2018-12-10 | 2019-05-21 | 北京云无忧大数据科技有限公司 | For the method and apparatus of plant protection, storage medium and electronic equipment |
| CN109857141A (en) * | 2019-03-13 | 2019-06-07 | 商丘中原无人机科技有限公司 | Plant protection drone spray method and system |
| CN110770791A (en) * | 2018-11-22 | 2020-02-07 | 深圳市大疆创新科技有限公司 | Image boundary acquisition method and device based on point cloud map and aircraft |
| CN110799983A (en) * | 2018-11-22 | 2020-02-14 | 深圳市大疆创新科技有限公司 | Map generation method, map generation equipment, aircraft and storage medium |
| CN110832425A (en) * | 2018-10-31 | 2020-02-21 | 深圳市大疆创新科技有限公司 | Control method and device, surveying and mapping unmanned aerial vehicle and spraying unmanned aerial vehicle |
| WO2020103108A1 (en) * | 2018-11-22 | 2020-05-28 | 深圳市大疆创新科技有限公司 | Semantic generation method and device, drone and storage medium |
| WO2020107354A1 (en) * | 2018-11-29 | 2020-06-04 | 深圳市大疆创新科技有限公司 | Control method and device |
| CN111625016A (en) * | 2019-02-28 | 2020-09-04 | 深圳市翔农创新科技有限公司 | Plant protection unmanned aerial vehicle operation optimization method, device and system and readable storage medium |
| CN111750857A (en) * | 2019-10-24 | 2020-10-09 | 广州极飞科技有限公司 | Route generation method, route generation device, terminal and storage medium |
| CN111984028A (en) * | 2019-05-23 | 2020-11-24 | 广州极飞科技有限公司 | Method, device and equipment for adjusting spraying amount in plant protection and storage medium |
| WO2021081896A1 (en) * | 2019-10-31 | 2021-05-06 | 深圳市大疆创新科技有限公司 | Operation planning method, system, and device for spraying unmanned aerial vehicle |
| CN112799416A (en) * | 2019-10-24 | 2021-05-14 | 广州极飞科技股份有限公司 | Airline generation method, apparatus and system, unmanned aerial vehicle system, and storage medium |
| WO2021120660A1 (en) * | 2019-12-19 | 2021-06-24 | 广州极飞科技有限公司 | Spraying system and control method for spraying system |
| CN113498499A (en) * | 2020-10-28 | 2021-10-12 | 深圳市大疆创新科技有限公司 | Operation control method and device, unmanned aerial vehicle and computer readable storage medium |
| WO2021237462A1 (en) * | 2020-05-26 | 2021-12-02 | 深圳市大疆创新科技有限公司 | Altitude limting method and apparatus for unmanned aerial vehicle, unmanned aerial vehicle, and storage medium |
| WO2021237957A1 (en) * | 2020-05-29 | 2021-12-02 | 广州极飞科技有限公司 | Spraying operation control method and apparatus, carrying device, and storage medium |
| CN113741490A (en) * | 2020-05-29 | 2021-12-03 | 广州极飞科技股份有限公司 | Inspection method, inspection device, aircraft and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8855405B2 (en) * | 2003-04-30 | 2014-10-07 | Deere & Company | System and method for detecting and analyzing features in an agricultural field for vehicle guidance |
| CN104615146A (en) * | 2015-02-05 | 2015-05-13 | 广州快飞计算机科技有限公司 | Unmanned aerial vehicle spraying operation automatic navigation method without need of external navigation signal |
| CN105373616A (en) * | 2015-11-26 | 2016-03-02 | 杨珊珊 | Manufacture method and manufacture device of electronic map |
| CN106647742A (en) * | 2016-10-31 | 2017-05-10 | 纳恩博（北京）科技有限公司 | Moving path planning method and device |
| CN106780735A (en) * | 2016-12-29 | 2017-05-31 | 深圳先进技术研究院 | A kind of semantic map constructing method, device and a kind of robot |
| CN107272726A (en) * | 2017-08-11 | 2017-10-20 | 上海拓攻机器人有限公司 | Operating area based on unmanned plane plant protection operation determines method and device |
-
2017
- 2017-10-30 CN CN201711033665.2A patent/CN107933921B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8855405B2 (en) * | 2003-04-30 | 2014-10-07 | Deere & Company | System and method for detecting and analyzing features in an agricultural field for vehicle guidance |
| CN104615146A (en) * | 2015-02-05 | 2015-05-13 | 广州快飞计算机科技有限公司 | Unmanned aerial vehicle spraying operation automatic navigation method without need of external navigation signal |
| CN105373616A (en) * | 2015-11-26 | 2016-03-02 | 杨珊珊 | Manufacture method and manufacture device of electronic map |
| CN106647742A (en) * | 2016-10-31 | 2017-05-10 | 纳恩博（北京）科技有限公司 | Moving path planning method and device |
| CN106780735A (en) * | 2016-12-29 | 2017-05-31 | 深圳先进技术研究院 | A kind of semantic map constructing method, device and a kind of robot |
| CN107272726A (en) * | 2017-08-11 | 2017-10-20 | 上海拓攻机器人有限公司 | Operating area based on unmanned plane plant protection operation determines method and device |
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108812599B (en) * | 2018-06-13 | 2021-08-27 | 仲恺农业工程学院 | Unmanned aerial vehicle plant protection monitoring system and method for manual control |
| CN108812599A (en) * | 2018-06-13 | 2018-11-16 | 仲恺农业工程学院 | A kind of unmanned plane plant protection monitoring system and method for manual manipulation |
| CN108803657A (en) * | 2018-06-13 | 2018-11-13 | 仲恺农业工程学院 | A kind of unmanned plane plant protection monitoring system and method for manipulating automatically |
| WO2019237412A1 (en) * | 2018-06-13 | 2019-12-19 | 仲恺农业工程学院 | Monitoring system and method for automatically operated unmanned aerial vehicle for plant protection |
| CN109271862A (en) * | 2018-08-15 | 2019-01-25 | 广州极飞科技有限公司 | Sprinkling control method and terminal, mobile device based on mobile device |
| EP3859479A4 (en) * | 2018-10-18 | 2021-11-24 | Guangzhou Xaircraft Technology Co., Ltd | Method for determining distribution information, and control method and device for unmanned aerial vehicle |
| CN109445457B (en) * | 2018-10-18 | 2021-05-14 | 广州极飞科技股份有限公司 | Method for determining distribution information, and method and device for controlling unmanned aerial vehicle |
| JP2022502794A (en) * | 2018-10-18 | 2022-01-11 | 広州極飛科技股▲ふん▼有限公司Guangzhou Xaircraft Technology Co., Ltd. | Distribution information determination method, unmanned aircraft control method and equipment |
| CN109445457A (en) * | 2018-10-18 | 2019-03-08 | 广州极飞科技有限公司 | Determination method, the control method and device of unmanned vehicle of distributed intelligence |
| AU2019362430B2 (en) * | 2018-10-18 | 2022-09-08 | Guangzhou Xaircraft Technology Co., Ltd. | Method for determining distribution information, and control method and device for unmanned aerial vehicle |
| CN110832425B (en) * | 2018-10-31 | 2021-10-01 | 深圳市大疆创新科技有限公司 | Control method and device, surveying and mapping unmanned aerial vehicle and spraying unmanned aerial vehicle |
| CN113848973A (en) * | 2018-10-31 | 2021-12-28 | 深圳市大疆创新科技有限公司 | Control method and device, surveying and mapping unmanned aerial vehicle and spraying unmanned aerial vehicle |
| CN110832425A (en) * | 2018-10-31 | 2020-02-21 | 深圳市大疆创新科技有限公司 | Control method and device, surveying and mapping unmanned aerial vehicle and spraying unmanned aerial vehicle |
| WO2020087384A1 (en) * | 2018-10-31 | 2020-05-07 | 深圳市大疆创新科技有限公司 | Control method, apparatus, surveying and mapping unmanned aerial vehicle, and spraying unmanned aerial vehicle |
| WO2020103108A1 (en) * | 2018-11-22 | 2020-05-28 | 深圳市大疆创新科技有限公司 | Semantic generation method and device, drone and storage medium |
| WO2020103109A1 (en) * | 2018-11-22 | 2020-05-28 | 深圳市大疆创新科技有限公司 | Map generation method and device, drone and storage medium |
| CN110770791A (en) * | 2018-11-22 | 2020-02-07 | 深圳市大疆创新科技有限公司 | Image boundary acquisition method and device based on point cloud map and aircraft |
| CN110799983A (en) * | 2018-11-22 | 2020-02-14 | 深圳市大疆创新科技有限公司 | Map generation method, map generation equipment, aircraft and storage medium |
| WO2020107354A1 (en) * | 2018-11-29 | 2020-06-04 | 深圳市大疆创新科技有限公司 | Control method and device |
| CN111279284B (en) * | 2018-11-29 | 2024-05-17 | 深圳市大疆创新科技有限公司 | Control method and apparatus |
| CN111279284A (en) * | 2018-11-29 | 2020-06-12 | 深圳市大疆创新科技有限公司 | Control method and apparatus |
| CN109507967A (en) * | 2018-11-30 | 2019-03-22 | 广州极飞科技有限公司 | Job control method and device |
| CN109784626A (en) * | 2018-12-10 | 2019-05-21 | 北京云无忧大数据科技有限公司 | For the method and apparatus of plant protection, storage medium and electronic equipment |
| CN109699620B (en) * | 2019-01-15 | 2021-10-08 | 广州极飞科技股份有限公司 | Liquid infusion method, control device and drug infusion machine |
| CN109699620A (en) * | 2019-01-15 | 2019-05-03 | 广州极飞科技有限公司 | Liquid infusion method, control device and perfusion machine |
| CN111625016A (en) * | 2019-02-28 | 2020-09-04 | 深圳市翔农创新科技有限公司 | Plant protection unmanned aerial vehicle operation optimization method, device and system and readable storage medium |
| CN109857141A (en) * | 2019-03-13 | 2019-06-07 | 商丘中原无人机科技有限公司 | Plant protection drone spray method and system |
| CN109857141B (en) * | 2019-03-13 | 2022-06-03 | 商丘中原无人机科技有限公司 | Plant protection unmanned aerial vehicle spraying method and system |
| CN111984028B (en) * | 2019-05-23 | 2023-11-17 | 广州极飞科技股份有限公司 | Method, device, equipment and storage medium for adjusting spraying dosage in plant protection |
| CN111984028A (en) * | 2019-05-23 | 2020-11-24 | 广州极飞科技有限公司 | Method, device and equipment for adjusting spraying amount in plant protection and storage medium |
| CN112799416B (en) * | 2019-10-24 | 2024-04-12 | 广州极飞科技股份有限公司 | Route generation method, equipment and system, unmanned operation system and storage medium |
| CN112799416A (en) * | 2019-10-24 | 2021-05-14 | 广州极飞科技股份有限公司 | Airline generation method, apparatus and system, unmanned aerial vehicle system, and storage medium |
| CN111750857B (en) * | 2019-10-24 | 2021-12-28 | 广州极飞科技股份有限公司 | Route generation method, route generation device, terminal and storage medium |
| CN111750857A (en) * | 2019-10-24 | 2020-10-09 | 广州极飞科技有限公司 | Route generation method, route generation device, terminal and storage medium |
| WO2021081896A1 (en) * | 2019-10-31 | 2021-05-06 | 深圳市大疆创新科技有限公司 | Operation planning method, system, and device for spraying unmanned aerial vehicle |
| WO2021120660A1 (en) * | 2019-12-19 | 2021-06-24 | 广州极飞科技有限公司 | Spraying system and control method for spraying system |
| WO2021237462A1 (en) * | 2020-05-26 | 2021-12-02 | 深圳市大疆创新科技有限公司 | Altitude limting method and apparatus for unmanned aerial vehicle, unmanned aerial vehicle, and storage medium |
| CN113741490A (en) * | 2020-05-29 | 2021-12-03 | 广州极飞科技股份有限公司 | Inspection method, inspection device, aircraft and storage medium |
| WO2021237957A1 (en) * | 2020-05-29 | 2021-12-02 | 广州极飞科技有限公司 | Spraying operation control method and apparatus, carrying device, and storage medium |
| CN113498499A (en) * | 2020-10-28 | 2021-10-12 | 深圳市大疆创新科技有限公司 | Operation control method and device, unmanned aerial vehicle and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107933921B (en) | 2020-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107933921A (en) | Aircraft and its sprinkling Route Generation and execution method, apparatus, control terminal | |
| KR102229095B1 (en) | UAV operation method and device | |
| Martinez-Guanter et al. | Spray and economics assessment of a UAV-based ultra-low-volume application in olive and citrus orchards | |
| US11526997B2 (en) | Targeting agricultural objects to apply units of treatment autonomously | |
| US12004443B2 (en) | Payload selection to treat multiple plant objects having different attributes | |
| Dos Santos et al. | Towards a reliable robot for steep slope vineyards monitoring | |
| Stefas et al. | Vision-based monitoring of orchards with UAVs | |
| US11812681B2 (en) | Precision treatment of agricultural objects on a moving platform | |
| US11465162B2 (en) | Obscurant emission to assist image formation to automate agricultural management and treatment | |
| US20230083872A1 (en) | Pixel projectile delivery system to replicate an image on a surface using pixel projectiles | |
| US20210185942A1 (en) | Managing stages of growth of a crop with micro-precision via an agricultural treatment delivery system | |
| US20210186006A1 (en) | Autonomous agricultural treatment delivery | |
| US11653590B2 (en) | Calibration of systems to deliver agricultural projectiles | |
| Uche et al. | UAV for agrochemical application: a review | |
| Yadav et al. | Computer Vision for Volunteer Cotton Detection in a Corn Field with UAS Remote Sensing Imagery and Spot Spray Applications | |
| CN114137473A (en) | Unmanned aerial vehicle positioning method capable of covering signal of agricultural and forestry robot | |
| CN112167212A (en) | Unmanned aerial vehicle pesticide spraying control system and method | |
| WO2019237412A1 (en) | Monitoring system and method for automatically operated unmanned aerial vehicle for plant protection | |
| Kalaiselvi et al. | Harvesting Efficiency: The Rise of Drone Technology in Modern Agriculture | |
| KR20190011171A (en) | Agricultural nesting apparatus and agricultural nesting method | |
| KR20190011155A (en) | Agricultural nesting apparatus and agricultural nesting method | |
| Bochtis et al. | Unmanned Aerial Systems in Agriculture: Eyes Above Fields | |
| CN112262356A (en) | Unmanned aerial vehicle spraying control method, unmanned aerial vehicle and storage medium | |
| Huang | UAV Applications in Agriculture | |
| CN114302339A (en) | Augmented Lagrange method capable of covering robot signal for positioning 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 510000 Block C, 115 Gaopu Road, Tianhe District, Guangzhou City, Guangdong Province Patentee after: Guangzhou Jifei Technology Co.,Ltd. Address before: 510032 Si Cheng Road No. 1, Tianhe District Gaotang Software Park, Guangzhou, Guangdong Province, 3A01 Patentee before: Guangzhou Xaircraft Technology Co.,Ltd. |