CN106127201A - A kind of unmanned plane landing method of view-based access control model positioning landing end - Google Patents
A kind of unmanned plane landing method of view-based access control model positioning landing end Download PDFInfo
- Publication number
- CN106127201A CN106127201A CN201610454292.5A CN201610454292A CN106127201A CN 106127201 A CN106127201 A CN 106127201A CN 201610454292 A CN201610454292 A CN 201610454292A CN 106127201 A CN106127201 A CN 106127201A
- Authority
- CN
- China
- Prior art keywords
- marker
- unmanned plane
- airport
- aircraft gate
- landing
- 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 24
- 239000003550 marker Substances 0.000 claims abstract description 166
- 239000011159 matrix material Substances 0.000 claims description 24
- 238000013461 design Methods 0.000 claims description 11
- 239000000284 extract Substances 0.000 claims description 10
- 230000035558 fertility Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 abstract description 3
- 238000013459 approach Methods 0.000 description 5
- 231100000572 poisoning Toxicity 0.000 description 3
- 230000000607 poisoning effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000003628 erosive effect Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 241001050985 Disco Species 0.000 description 1
- 241000287531 Psittacidae Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 229910002056 binary alloy Inorganic materials 0.000 description 1
- 210000005252 bulbus oculi Anatomy 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/245—Aligning, centring, orientation detection or correction of the image by locating a pattern; Special marks for positioning
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses the unmanned plane landing method of a kind of view-based access control model positioning landing end; the unmanned plane airport used in the method is made up of multiple aircraft gate Marker; unmanned plane obtains the Marker in visual range by vision module and verifies the ID of each Marker in visual range, thus estimates the accurate land of self-position.The unmanned plane airport that the present invention provides can be that multiple different unmanned plane provides landing service, also unit stopping platform can be provided at roof, all kinds of small-sized platform of balcony lamp, unified framework can be achieved at low cost full autonomous flight landing in whole unmanned plane is dispatched, and has good promotion prospect.
Description
Technical field
The present invention relates to unmanned aerial vehicle (UAV) control technical field, be specifically related to the unmanned plane of a kind of view-based access control model positioning landing end
Landing method.
Background technology
In recent years, MAV due to the features such as little, lightweight, the good concealment of its volume be widely used in shooting,
Monitor, investigate, follow the trail of, the every field such as mapping, and open the epoch of unmanned air vehicle technique blast.And it is micro-during dynamic tracing shooting
Chain-wales (such as vehicle top) reclaims shooting equipment, express delivery industry fixed point delivers the new demand that the civilian unmanned planes such as article use, all
The automatic landing technology of MAV is proposed new challenge.
International consumer electronics product exhibition (International Consumer Electronics in 2016
Show, is called for short CES) on, the novel unmanned plane of the exhibitions of well-known unmanned plane company such as big boundary, zero degree, hundred million boats is all automatic by unmanned plane
Landing as required skill, the novel unmanned plane Disco that wherein Parrot company releases proposes the super simplification nothing of " key is gone home "
It is countless that man-machine automatic landing operation inhales eyeball especially.
Owing to the accuracy class of GPS still cannot meet the requirement of unmanned plane high accuracy landing, had significant by design
The trend that the landing place of feature reaches precision approach is more and more obvious.Increase income and fly to control PixHawk and illustrate a kind of based on red
Outer landing mark, it is other accurately that unmanned plane can carry out Centimeter Level by lift-launch corresponding infrared photography landing module booting self
Landing.Amazon also show its scheme utilizing significant landing plate to deliver goods to the customers to user's unmanned plane.
But more than landing place is the most only an airplane design, it is impossible to land multi-aircraft, and unmanned plane is only simultaneously
Have when arriving in scope the least above ground, landing field and self could be carried out relative localization.
Summary of the invention
For above-mentioned problems of the prior art, it is an object of the invention to, it is provided that a kind of view-based access control model location fall
Fall the unmanned plane landing method of end, utilizes the Airborne Camera on unmanned plane to process the Airport Images photographed, intends adopting
With identification thing multiple, that identify with ID at many levels, establish one and can accommodate the large-scale of hundreds and thousands of unmanned plane landing demand
Unmanned plane airport, this method cost is extremely low simultaneously, it is adaptable to unmanned planes single, multiple landing uses.
In order to realize above-mentioned task, the present invention by the following technical solutions:
The unmanned plane landing method of a kind of view-based access control model positioning landing end, comprises the following steps:
Step one, sets up unmanned plane airport
Step S10, arranges aircraft gate Marker, and the design rule of aircraft gate Marker is:
Aircraft gate Marker is all the square structure being made up of N*N grid spaces；At each aircraft gate Marker
In, in the grid spaces of outmost turns, at least 2/3 is filled to black, and remaining grid spaces is black or white；
Step S11, arranges nested Marker, the design of nested Marker and aircraft gate Marker in the Marker of aircraft gate
Rule is identical, and except for the difference that the specification of nested Marker is little compared with Marker, and nested Marker has plurality of specifications, is distributed in and stops
The inside of seat in the plane Marker；
Step S12, sets up unmanned plane airport, and airport is the square structure being made up of N*N grid spaces, and airport is
Grid spaces, outer ring is black, and remaining region is white；It is distributed in order or disorderly in the white portion on airport
Multiple described aircraft gate Marker, the most overlapping between the Marker of aircraft gate；
Step 2, the descent of unmanned plane
Step S20, unmanned plane receive landing instruction, landing instruction comprise all unmanned plane airports GPS position information,
The positional information of aircraft gate Marker, the unmanned plane airport ID of the required landing of unmanned plane, unmanned plane in each unmanned plane airport
The ID of the aircraft gate Marker of required landing；
Step S21, utilizes the GPS position information on unmanned plane airport to be guided above airport by unmanned plane, treats that unmanned plane arrives
After reaching above airport, gather the image on airport with fixing speed limit trailing edge, and each two field picture collected is walked
The process of rapid S210 to S213:
Step S210, rim detection and contours extract
The image of collection is converted into gray-scale map, utilizes Canny operator to obtain the marginal distribution figure of binaryzation, utilize corruption
Erosion, expansion algorithm carry out noise and filter, and then extract the profile information of image, and profile information is all aircraft gates in comprising airport
Marker and the profile on airport；
Step S211, screens unmanned plane airport
Two categories below profile is filtered in profile information:
The first kind: area is less than the profile of 2/3 unmanned plane airport area；
Equations of The Second Kind: the profile of internal loss of fecundity profile；
After filtering above two class profiles, choose the outside unmanned plane airport for convex quadrangle as candidate airport；
Step S212, is mapped to candidate airport in square region, utilizes k-means algorithm the pixel on candidate airport to be divided
For black and white two class, thus obtain the binary image on candidate airport；Utilize binary image to encode, obtain a N*N's
Two values matrix, for two values matrix, first determines whether whether the outmost turns of two values matrix is complete zero, if non-full zero, abandons；So
After two values matrix is converted to unsigned int except the binary coding of outmost turns；
Step S213, carries out code value calculating according to the unsigned int on each candidate airport, obtains each candidate's machine
ID, landing instruction ID and the unmanned plane on candidate airport received needs the unmanned plane airport ID landed to carry out
Join, select the ID candidate airport that the match is successful as treating landing station；
Step S22, after landing station finds, the image stopping collecting unmanned plane carries out step S210's to S213
Processing, now unmanned plane during flying is to the top treating landing station；
Step S23, unmanned plane arrives after above landing station, treats landing station with fixing speed limit trailing edge collection
Image, and each two field picture collected is carried out following process:
Step S230, is converted into gray-scale map by the image of collection, utilizes Canny operator to obtain the marginal distribution of binaryzation
Figure, utilizes burn into expansion algorithm to carry out noise and filters, then extract the profile information of image；
Step S231, screens aircraft gate Marker
Two categories below profile is filtered in profile information:
The first kind: the area profile less than 2/3 aircraft gate Marker；
Equations of The Second Kind: the profile of internal loss of fecundity profile；
After filtering above two class profiles, choose the outside aircraft gate Marker for convex quadrangle as candidate aircraft gate
Marker；
Step S232, is mapped to candidate aircraft gate Marker in square region, utilizes k-means algorithm candidate to be shut down
The pixel of position Marker is divided into black and white two class, thus obtains the binary image of candidate aircraft gate Marker；Utilize binary picture
As encoding, obtain the two values matrix of a N*N, for two values matrix, first determine whether that whether the outmost turns of two values matrix is
Complete zero, if non-full zero, abandon；Then two values matrix is converted to unsigned int except the binary coding of outmost turns；
Step S233, carries out code value calculating according to the unsigned int of each candidate aircraft gate Marker, obtains each
The ID of individual candidate aircraft gate Marker, needs fall in landing ID and the unmanned plane of candidate aircraft gate Marker received instruction
The ID of the candidate aircraft gate Marker fallen mates, and selects the ID Marker aircraft gate to be landed, candidate aircraft gate that the match is successful
Marker；
Step S24, unmanned plane flies to aircraft gate to be landed according to the positional information of aircraft gate Marker to be landed
Marker lands behind top position.
Further, satellite Marker, satellite Marker and aircraft gate it are additionally provided with in described aircraft gate Marker
The design rule of Marker is identical, and except for the difference that the area of satellite Marker is less than the grid spaces area of nesting Marker
1/3.
The present invention compared with prior art has a techniques below feature:
1. the landing method that the present invention provides, unmanned plane determines shutdown orientation according to ID value in descent, and keeps
Constant, do not affected by extraneous factor.
2. the unmanned plane airport that the present invention provides, owing to each unmanned plane can utilize all marks that whole airport provides
Knowledge information, to self poisoning, therefore just can give self poisoning in several meters even distance of hundreds of meters, the least yardstick
Marker can be that unmanned plane landing end provides millimetre-sized positioning precision.Rely on the precise location information of whole process, unmanned
Machine can drop to target aircraft gate efficiently, safely, accurately；
3. the unmanned plane airport that the present invention provides can be that multiple different unmanned plane provides landing service, and unified framework can
It is achieved at low cost full autonomous flight landing in whole unmanned plane is dispatched, there is good promotion prospect.
Accompanying drawing explanation
Fig. 1 is the structural representation of aircraft gate Marker；
Fig. 2 is the flow chart of unmanned plane descent；
Fig. 3 is the structural representation on a unmanned plane airport；
Detailed description of the invention
Deferring to technique scheme, as shown in drawings, the present invention provides the unmanned of a kind of view-based access control model positioning landing end
Machine landing method, comprises the following steps:
Step one: set up unmanned plane airport
The unmanned plane airport of the present invention is made up of, often multiple Marker (may be used without other and have significant terrestrial reference)
Individual aircraft gate Marker has the feature having distinctness, and can carry out binary coding by light and shade striped, is encoded by deciphering
Its id information can be obtained；Unmanned plane obtains the aircraft gate Marker in the visual field by onboard image equipment, is compiled by binary system
Yardage is calculated the ID of each aircraft gate Marker and verifies, by being fitted calculating with the three-dimensional point under corresponding global coordinate system
Pose, thus estimate self-position well, to carry out precision approach.
Aircraft gate Marker is all the square structure being made up of N*N (N is integer) individual identical grid spaces；?
In the Marker of each aircraft gate, in the grid spaces of outmost turns, at least 2/3 is filled to black (or being stuffed entirely with as black),
So grid spaces of guarantee outmost turns is black, and this is the important symbol of aircraft gate Marker；Remaining grid spaces
For black or white, this is to ensure that the feature of nesting；Aircraft gate Marker mentioned in this programme and unmanned plane
Airport is in the middle of a plane, and all only has black and white, in order to image procossing.Whole airport nested multiple solely
Vertical aircraft gate, each aircraft gate Marker may be incorporated for guiding a frame unmanned plane to stop thereon, and aircraft gate Marker is
Square structure, is considered as being combined into by each grid spaces of N*N.
Except aircraft gate Marker, it is additionally provided with nested Marker therein, for end auxiliary landing, it is ensured that landing
Precision and stability；
Step S11, arranges nested Marker, the design of nested Marker and aircraft gate Marker in the Marker of aircraft gate
Rule is identical, and rule here is identical refers to that nested Marker is also the square structure being made up of N*N grid spaces, and
2/3 black is the most at least filled in the grid spaces of its outer ring, and remaining grid spaces is black or white；Except for the difference that nested
The specification of Marker is little compared with Marker, and the ID value of each nested Marker and corresponding aircraft gate Marker differs；
Nested Marker has plurality of specifications, in the case of the coding rule ensureing original aircraft gate Marker is immovable, is distributed in and stops
The inside of seat in the plane Marker；Here plurality of specifications refers to that nested Marker's is in different size, i.e. the length of side is different, and often
Individual nested black Marker within, white portion distribution are also different, and the ID of the most each nesting Marker is different.
Nested Marker is distributed in the Marker of aircraft gate.
Preferably, satellite Marker, satellite Marker and aircraft gate can also be set inside the Marker of aircraft gate
The design rule of Marker is identical (scaled down version of aircraft gate Marker can also be regarded as), the except for the difference that face of satellite Marker
The 1/3 of the long-pending grid spaces area less than nesting Marker, in order to avoid having influence on nested Marker to play its effect.Its master
Act on is to avoid unmanned plane to be affected deviation aircraft gate by pneumatic in descent；Satellite Marker is preferably distributed in aircraft gate
The inner ring position of Marker.When satellite Marker is distributed in the Marker of aircraft gate, satellite Marker can partly or entirely with
The outmost turns (black circle) of aircraft gate Marker is overlapping, as shown in Figure 1；Black on nested Marker and aircraft gate Marker
When there is overlap in region, the edge of nested Marker lap leaves white space, in order to calculates and distinguishes.
Sum it up, aircraft gate Marker, nested Marker, satellite Marker are the same is all by the grid spaces structure of N*N
Becoming, and outmost turns is or at least 2/3 fills black, difference is that their ID, area are different, its Satellite Marker
Area minimum, the area of nested Marker takes second place.
Step S12, sets up unmanned plane airport, as it is shown on figure 3, airport is the square knot being made up of N*N grid spaces
Structure, the outmost turns grid spaces on airport is black, and remaining region is white；Orderly or nothing in the white portion on airport
Multiple described aircraft gate Marker is distributed to sequence, and (aircraft gate Marker and unmanned plane airport must be configured into two can identified
Dimension code mark thing so that unmanned plane can be in whole place inner position), the most overlapping between the Marker of aircraft gate, but aircraft gate
Marker can part the most overlapping with the black box region of airport outmost turns, and the edge of lap leave white space so that
In differentiation.Different aircraft gate Marker in airport towards can be identical, it is also possible to different, by actual demand design distribution.
The distribution of aircraft gate Marker directly affects the ID value on airport, and the ID on airport is the important symbol identifying airport.
Unmanned plane airport can be spaced apart multiple in same bulk zone, for parking of extensive unmanned plane.
Step 2: the descent of unmanned plane
Step S20, unmanned plane receives the landing instruction of ground control centre (or controlling equipment), and landing instruction comprises institute
Have aircraft gate Marker in the GPS position information on unmanned plane airport, each unmanned plane airport positional information (ID value, relative to
The coordinate etc. on unmanned plane airport), the unmanned plane airport ID of the required landing of unmanned plane, the aircraft gate of the required landing of unmanned plane
The ID of Marker；
This programme utilizes GPS secondarily position, because GPS is affected relatively big by weather, residing region, lead
The precision causing GPS in varied situations is variant, it is impossible to meet the demand of unmanned plane precision approach.To this end, it is the most sharp in this programme
With GPS, unmanned plane is carried out the guiding of approximate location, when the vision facilities of unmanned plane can shoot and resolve the unmanned plane on ground
After Airport Images, unmanned plane precision approach can be guided by Quick Response Code mark.
Step S21, utilizes the GPS position information on unmanned plane airport by (concrete height root above unmanned plane guiding to airport
Depending on the internal reference of camera and airport dimensions, the generally size on 15 times of airports), after unmanned plane arrives at the airport top, with solid
Fixed speed limit trailing edge gathers the image on airport, and each two field picture collected carries out the place of step S210 to S213
Reason:
Step S210, rim detection and contours extract
The image of collection is converted into gray-scale map, utilizes Canny operator to obtain the marginal distribution figure of binaryzation, utilize corruption
Erosion, expansion algorithm carry out noise and filter, and then extract the profile information of image, and profile information is all aircraft gates in comprising airport
Marker and the profile on airport；
Step S211, screens unmanned plane airport
Two categories below profile is filtered in profile information:
The first kind: area is less than the profile of 2/3 unmanned plane airport area, because this profile size does not meets unmanned plane machine
The area of field, may be other objects of ground, need to filter；(unmanned plane is obtained its place by self-contained ultrasonic equipment
Highly, according to this height and the area of image that photographs, calculate corresponding three-dimensional of image according to camera model
Area)
Equations of The Second Kind: the profile of internal loss of fecundity profile；Here the profile being aircraft gate Marker from profile, due to one
Necessarily comprise aircraft gate Marker inside correct unmanned plane airport, therefore when some contoured interior does not has sub-profile, say
This profile bright is not airport.
After filtering above two class profiles, choose the outside unmanned plane airport (profile) for convex quadrangle as candidate airport；
Owing in a panel region, unmanned plane airport may have multiple, the candidate airport therefore screened has been likely to multiple；
Step S212, is mapped to candidate airport in square region that (image that Airborne Camera photographs may produce abnormal
Becoming, mapping is to reduce the shape of image of its original), utilize k-means algorithm that the pixel on candidate airport is divided into black and white
Two classes (when the black area of each square is more than the 2/3 of this square area, are then divided into black, white is also such), from
And obtain the binary image on candidate airport；Utilize binary image to encode, obtain the two values matrix of a N*N, for
Two values matrix, first determines whether whether the outmost turns of two values matrix is complete zero, if non-full zero, abandons；Then two values matrix is removed
The binary coding of outmost turns (i.e. (N-2) * (N-2) region of the inside) is converted to unsigned int；
Step S213, carries out code value calculating according to the unsigned int on each candidate airport, owing to there are four courts on airport
To, the most respectively calculate four towards code value and choose 4 towards middle code value minima as ID；Thus obtain each and wait
Select the ID on airport, landing instruction ID and the unmanned plane on candidate airport received needs the unmanned plane airport ID of landing to carry out
Coupling, selects the ID candidate airport that the match is successful as treating landing station；
Step S22, after landing station finds, the image stopping collecting unmanned plane carries out step S210's to S213
Processing, now unmanned plane is according to treating the current height of the landing station positional information on ground, unmanned plane and unmanned plane collection
The image information on airport, determine the position treating landing station relative to unmanned plane, then adjust self attitude and fly to treating
The top of landing station；
After unmanned plane arrives above aircraft gate, aircraft gate Marker will be capable of identify that and to self poisoning, now unmanned
Machine adjustable Yaw direction (rotating around Y-direction, i.e. yaw angle) also finally drops to relevant position, and detailed process is as follows:
Step S23, unmanned plane arrives after above landing station, treats landing station with fixing speed limit trailing edge collection
Image, and each two field picture collected is carried out following process:
Step S230, is converted into gray-scale map by the image of collection, utilizes Canny operator to obtain the marginal distribution of binaryzation
Figure, utilizes burn into expansion algorithm to carry out noise and filters, then extract the profile information of image；
Step S231, screens aircraft gate Marker
Two categories below profile is filtered in profile information:
The first kind: the area profile less than 2/3 aircraft gate Marker；
Equations of The Second Kind: the profile of internal loss of fecundity profile；
After filtering above two class profiles, choose the outside aircraft gate Marker for convex quadrangle as candidate aircraft gate
Marker；(principle of the process that filters here is with as before)
Step S232, is mapped to candidate aircraft gate Marker in square region, utilizes k-means algorithm candidate to be shut down
The pixel of position Marker is divided into black and white two class, thus obtains the binary image of candidate aircraft gate Marker；Utilize binary picture
As encoding, obtain the two values matrix of a N*N, for two values matrix, first determine whether that whether the outmost turns of two values matrix is
Complete zero, if non-full zero, abandon；Then two values matrix is converted to unsigned int except the binary coding of outmost turns；
Step S233, carries out code value calculating according to the unsigned int of each candidate aircraft gate Marker, obtains each
The ID of individual candidate aircraft gate Marker, needs fall in landing ID and the unmanned plane of candidate aircraft gate Marker received instruction
The ID of the candidate aircraft gate Marker fallen mates, and selects the ID Marker aircraft gate to be landed, candidate aircraft gate that the match is successful
Marker；
Step S24, unmanned plane flies to aircraft gate to be landed according to the positional information of aircraft gate Marker to be landed
Marker lands behind top position.
During precision approach, unmanned plane carries out landing and calculating the real-time pose of unmanned plane with middling speed, extracts landing
The coordinate that 4 angle points of aircraft gate Marker are corresponding, and corresponding with image slices vegetarian refreshments.Combining camera internal reference, utilizes the PnP algorithm can
Obtain the attitude of camera.Relative position relation according to unmanned plane Yu camera can be derived by UAV position and orientation.
When unmanned plane drops to certain position, aircraft gate Marker can not be presented in camera plane completely,
Now, nested Marker works, and now unmanned plane has only to according to the ID in step S210-S213 (or S230-S233)
Analytical algorithm, carrying out that the ID of nested Marker mates can (the nested Marker in the Marker of this aircraft gate).Now unmanned plane
Reduce speed now decline, is easy for being affected by wind during declining, and when unmanned plane is blown off level point, unmanned plane passes through
To the ID of the satellite Marker photographed to resolve its offset direction and to be modified.
Claims (2)
1. the unmanned plane landing method of a view-based access control model positioning landing end, it is characterised in that comprise the following steps:
Step one, sets up unmanned plane airport
Step S10, arranges aircraft gate Marker, and the design rule of aircraft gate Marker is:
Aircraft gate Marker is all the square structure being made up of N*N grid spaces；In the Marker of each aircraft gate,
In the grid spaces of outer ring, at least 2/3 is filled to black, and remaining grid spaces is black or white；
Step S11, arranges nested Marker, the design rule of nested Marker and aircraft gate Marker in the Marker of aircraft gate
Identical, except for the difference that the specification of nested Marker is little compared with Marker, and nested Marker has plurality of specifications, is distributed in aircraft gate
The inside of Marker；
Step S12, sets up unmanned plane airport, and airport is the square structure being made up of N*N grid spaces, the outmost turns on airport
Grid spaces is black, and remaining region is white；It is distributed multiple in the white portion on airport in order or disorderly
Described aircraft gate Marker, the most overlapping between the Marker of aircraft gate；
Step 2, the descent of unmanned plane
Step S20, unmanned plane receives landing instruction, and landing instruction comprises the GPS position information on all unmanned plane airports, each
In unmanned plane airport needed for the positional information of aircraft gate Marker, the unmanned plane airport ID of the required landing of unmanned plane, unmanned plane
The ID of aircraft gate Marker to be landed；
Step S21, utilizes the GPS position information on unmanned plane airport to be guided above airport by unmanned plane, treats that unmanned plane arrives machine
After above Chang, gather the image on airport with fixing speed limit trailing edge, and each two field picture collected is carried out step
The process of S210 to S213:
Step S210, rim detection and contours extract
The image of collection is converted into gray-scale map, utilizes Canny operator to obtain the marginal distribution figure of binaryzation, utilize burn into swollen
Swollen algorithm carries out noise and filters, and then extracts the profile information of image, and profile information is all aircraft gate Marker in comprising airport
And the profile on airport；
Step S211, screens unmanned plane airport
Two categories below profile is filtered in profile information:
The first kind: area is less than the profile of 2/3 unmanned plane airport area；
Equations of The Second Kind: the profile of internal loss of fecundity profile；
After filtering above two class profiles, choose the outside unmanned plane airport for convex quadrangle as candidate airport；
Step S212, is mapped to candidate airport in square region, utilizes k-means algorithm to be divided into black by the pixel on candidate airport
White two classes, thus obtain the binary image on candidate airport；Utilize binary image to encode, obtain the two-value of a N*N
Matrix, for two values matrix, first determines whether whether the outmost turns of two values matrix is complete zero, if non-full zero, abandons；Then will
Two values matrix is converted to unsigned int except the binary coding of outmost turns；
Step S213, carries out code value calculating according to the unsigned int on each candidate airport, obtains each candidate airport
ID, needs the unmanned plane airport ID of landing to mate in the landing instruction received with unmanned plane by the ID on candidate airport, choosing
Select the ID candidate airport that the match is successful as treating landing station；
Step S22, after landing station finds, the image stopping collecting unmanned plane carries out the place of step S210 to S213
Reason, now unmanned plane during flying is to the top treating landing station；
Step S23, unmanned plane arrives after above landing station, treats the figure of landing station with fixing speed limit trailing edge collection
Picture, and each two field picture collected is carried out following process:
Step S230, is converted into gray-scale map by the image of collection, utilizes Canny operator to obtain the marginal distribution figure of binaryzation, profit
Carry out noise with burn into expansion algorithm to filter, then extract the profile information of image；
Step S231, screens aircraft gate Marker
Two categories below profile is filtered in profile information:
The first kind: the area profile less than 2/3 aircraft gate Marker；
Equations of The Second Kind: the profile of internal loss of fecundity profile；
After filtering above two class profiles, choose the outside aircraft gate Marker for convex quadrangle as candidate aircraft gate Marker；
Step S232, is mapped to candidate aircraft gate Marker in square region, utilizes k-means algorithm by candidate aircraft gate
The pixel of Marker is divided into black and white two class, thus obtains the binary image of candidate aircraft gate Marker；Utilize binary image
Encode, obtain the two values matrix of a N*N, for two values matrix, first determine whether whether the outmost turns of two values matrix is complete
Zero, if non-full zero, abandon；Then two values matrix is converted to unsigned int except the binary coding of outmost turns；
Step S233, carries out code value calculating according to the unsigned int of each candidate aircraft gate Marker, obtains each and waits
Select the ID of aircraft gate Marker, landing instruction ID and the unmanned plane of candidate aircraft gate Marker received needs landing
The ID of candidate aircraft gate Marker mates, and selecting the ID candidate aircraft gate Marker that the match is successful is aircraft gate to be landed
Marker；
Step S24, unmanned plane flies to aircraft gate Marker to be landed according to the positional information of aircraft gate Marker to be landed
Orientation postpones lands.
2. the unmanned plane landing method of described view-based access control model positioning landing end as claimed in claim 1, it is characterised in that
The design rule phase of satellite Marker, satellite Marker and aircraft gate Marker it is additionally provided with in described aircraft gate Marker
With, except for the difference that the area of satellite Marker less than nesting Marker grid spaces area 1/3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610454292.5A CN106127201B (en) | 2016-06-21 | 2016-06-21 | A kind of unmanned plane landing method of view-based access control model positioning landing end |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610454292.5A CN106127201B (en) | 2016-06-21 | 2016-06-21 | A kind of unmanned plane landing method of view-based access control model positioning landing end |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106127201A true CN106127201A (en) | 2016-11-16 |
| CN106127201B CN106127201B (en) | 2019-02-15 |
Family
ID=57471368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610454292.5A Active CN106127201B (en) | 2016-06-21 | 2016-06-21 | A kind of unmanned plane landing method of view-based access control model positioning landing end |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106127201B (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106527487A (en) * | 2016-12-23 | 2017-03-22 | 北京理工大学 | Autonomous precision landing system of unmanned aerial vehicle on motion platform and landing method |
| CN107066981A (en) * | 2017-04-20 | 2017-08-18 | 上海博历机械科技有限公司 | For the visual rating scale terrestrial reference positioning identification system of SUAV Autonomous landing |
| CN107450590A (en) * | 2017-08-07 | 2017-12-08 | 深圳市科卫泰实业发展有限公司 | A kind of unmanned plane auxiliary landing method |
| CN107578236A (en) * | 2017-10-20 | 2018-01-12 | 天津航佳机场设备科技有限公司 | A kind of bridge based on aircraft number carries equipment metering settlement management system and management method |
| CN108121360A (en) * | 2017-12-19 | 2018-06-05 | 歌尔科技有限公司 | A kind of unmanned plane position control method and freight transport system |
| CN109739257A (en) * | 2018-12-21 | 2019-05-10 | 中科院合肥技术创新工程院 | Merge the patrol unmanned machine closing method and system of satellite navigation and visual perception |
| JP2019077446A (en) * | 2017-03-06 | 2019-05-23 | 株式会社Ｓｐｉｒａｌ | Control system for flight vehicle, and marking portion |
| CN109823552A (en) * | 2019-02-14 | 2019-05-31 | 深圳市多翼创新科技有限公司 | The unmanned plane precision approach method of view-based access control model, storage medium, apparatus and system |
| CN109901620A (en) * | 2019-04-01 | 2019-06-18 | 西安因诺航空科技有限公司 | A kind of multiple UAVs cooperative system and formation method |
| CN110221625A (en) * | 2019-05-27 | 2019-09-10 | 北京交通大学 | The Autonomous landing guidance method of unmanned plane exact position |
| CN110989674A (en) * | 2019-12-16 | 2020-04-10 | 西安因诺航空科技有限公司 | Unmanned aerial vehicle visual guidance landing method based on Aruco label |
| WO2020211812A1 (en) * | 2019-04-19 | 2020-10-22 | 深圳市道通智能航空技术有限公司 | Aircraft landing method and apparatus |
| CN112198894A (en) * | 2020-07-31 | 2021-01-08 | 北京理工大学 | Autonomous moving landing guidance method and system for rotor unmanned aerial vehicle |
| CN113377118A (en) * | 2021-07-14 | 2021-09-10 | 中国计量大学 | Multi-stage accurate landing method for unmanned aerial vehicle hangar based on vision |
| CN113597591A (en) * | 2019-03-21 | 2021-11-02 | Wing航空有限责任公司 | Geographic reference for unmanned aerial vehicle navigation |
| CN113655806A (en) * | 2021-07-01 | 2021-11-16 | 中国人民解放军战略支援部队信息工程大学 | Unmanned aerial vehicle group auxiliary landing method |
| CN114815905A (en) * | 2022-06-29 | 2022-07-29 | 中国航空工业集团公司沈阳飞机设计研究所 | Multi-machine continuous landing guide control method and device |
| CN114935946A (en) * | 2022-07-21 | 2022-08-23 | 浙江这里飞科技有限公司 | Unmanned aerial vehicle landing method and device |
| WO2022261901A1 (en) * | 2021-06-17 | 2022-12-22 | 深圳市大疆创新科技有限公司 | Unmanned aerial vehicle landing control method and apparatus, unmanned aerial vehicle, system, and storage medium |
| WO2023274321A1 (en) * | 2021-07-02 | 2023-01-05 | 北京三快在线科技有限公司 | Beacon, beacon generation method, beacon generation apparatus, and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103226356A (en) * | 2013-02-27 | 2013-07-31 | 广东工业大学 | Image-processing-based unmanned plane accurate position landing method |
| CN104166854A (en) * | 2014-08-03 | 2014-11-26 | 浙江大学 | Vision grading landmark locating and identifying method for autonomous landing of small unmanned aerial vehicle |
| WO2015108588A3 (en) * | 2013-10-21 | 2015-10-08 | Kespry, Inc. | Systems and methods for unmanned aerial vehicle landing |
| US20160122038A1 (en) * | 2014-02-25 | 2016-05-05 | Singularity University | Optically assisted landing of autonomous unmanned aircraft |
| CN105676873A (en) * | 2016-03-08 | 2016-06-15 | 览意科技（上海）有限公司 | Automatic landing method and control system of unmanned aerial vehicle |
-
2016
- 2016-06-21 CN CN201610454292.5A patent/CN106127201B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103226356A (en) * | 2013-02-27 | 2013-07-31 | 广东工业大学 | Image-processing-based unmanned plane accurate position landing method |
| WO2015108588A3 (en) * | 2013-10-21 | 2015-10-08 | Kespry, Inc. | Systems and methods for unmanned aerial vehicle landing |
| US20160122038A1 (en) * | 2014-02-25 | 2016-05-05 | Singularity University | Optically assisted landing of autonomous unmanned aircraft |
| CN104166854A (en) * | 2014-08-03 | 2014-11-26 | 浙江大学 | Vision grading landmark locating and identifying method for autonomous landing of small unmanned aerial vehicle |
| CN105676873A (en) * | 2016-03-08 | 2016-06-15 | 览意科技（上海）有限公司 | Automatic landing method and control system of unmanned aerial vehicle |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106527487A (en) * | 2016-12-23 | 2017-03-22 | 北京理工大学 | Autonomous precision landing system of unmanned aerial vehicle on motion platform and landing method |
| JP2019077446A (en) * | 2017-03-06 | 2019-05-23 | 株式会社Ｓｐｉｒａｌ | Control system for flight vehicle, and marking portion |
| CN107066981A (en) * | 2017-04-20 | 2017-08-18 | 上海博历机械科技有限公司 | For the visual rating scale terrestrial reference positioning identification system of SUAV Autonomous landing |
| CN107450590A (en) * | 2017-08-07 | 2017-12-08 | 深圳市科卫泰实业发展有限公司 | A kind of unmanned plane auxiliary landing method |
| CN107578236A (en) * | 2017-10-20 | 2018-01-12 | 天津航佳机场设备科技有限公司 | A kind of bridge based on aircraft number carries equipment metering settlement management system and management method |
| CN108121360A (en) * | 2017-12-19 | 2018-06-05 | 歌尔科技有限公司 | A kind of unmanned plane position control method and freight transport system |
| CN108121360B (en) * | 2017-12-19 | 2023-07-21 | 歌尔科技有限公司 | Unmanned aerial vehicle positioning control method and freight system |
| CN109739257A (en) * | 2018-12-21 | 2019-05-10 | 中科院合肥技术创新工程院 | Merge the patrol unmanned machine closing method and system of satellite navigation and visual perception |
| CN109823552A (en) * | 2019-02-14 | 2019-05-31 | 深圳市多翼创新科技有限公司 | The unmanned plane precision approach method of view-based access control model, storage medium, apparatus and system |
| CN113597591B (en) * | 2019-03-21 | 2024-05-10 | Wing航空有限责任公司 | Geographic benchmarking for unmanned aerial vehicle navigation |
| CN113597591A (en) * | 2019-03-21 | 2021-11-02 | Wing航空有限责任公司 | Geographic reference for unmanned aerial vehicle navigation |
| CN109901620A (en) * | 2019-04-01 | 2019-06-18 | 西安因诺航空科技有限公司 | A kind of multiple UAVs cooperative system and formation method |
| WO2020211812A1 (en) * | 2019-04-19 | 2020-10-22 | 深圳市道通智能航空技术有限公司 | Aircraft landing method and apparatus |
| CN110221625A (en) * | 2019-05-27 | 2019-09-10 | 北京交通大学 | The Autonomous landing guidance method of unmanned plane exact position |
| CN110221625B (en) * | 2019-05-27 | 2021-08-03 | 北京交通大学 | Autonomous landing guiding method for precise position of unmanned aerial vehicle |
| CN110989674A (en) * | 2019-12-16 | 2020-04-10 | 西安因诺航空科技有限公司 | Unmanned aerial vehicle visual guidance landing method based on Aruco label |
| CN110989674B (en) * | 2019-12-16 | 2023-03-31 | 西安因诺航空科技有限公司 | Unmanned aerial vehicle visual guidance landing method based on ArUco label |
| CN112198894A (en) * | 2020-07-31 | 2021-01-08 | 北京理工大学 | Autonomous moving landing guidance method and system for rotor unmanned aerial vehicle |
| WO2022261901A1 (en) * | 2021-06-17 | 2022-12-22 | 深圳市大疆创新科技有限公司 | Unmanned aerial vehicle landing control method and apparatus, unmanned aerial vehicle, system, and storage medium |
| CN113655806A (en) * | 2021-07-01 | 2021-11-16 | 中国人民解放军战略支援部队信息工程大学 | Unmanned aerial vehicle group auxiliary landing method |
| CN113655806B (en) * | 2021-07-01 | 2023-08-08 | 中国人民解放军战略支援部队信息工程大学 | Unmanned aerial vehicle group auxiliary landing method |
| WO2023274321A1 (en) * | 2021-07-02 | 2023-01-05 | 北京三快在线科技有限公司 | Beacon, beacon generation method, beacon generation apparatus, and device |
| CN113377118A (en) * | 2021-07-14 | 2021-09-10 | 中国计量大学 | Multi-stage accurate landing method for unmanned aerial vehicle hangar based on vision |
| CN114815905B (en) * | 2022-06-29 | 2022-09-20 | 中国航空工业集团公司沈阳飞机设计研究所 | Multi-machine continuous landing guide control method and device |
| CN114815905A (en) * | 2022-06-29 | 2022-07-29 | 中国航空工业集团公司沈阳飞机设计研究所 | Multi-machine continuous landing guide control method and device |
| CN114935946A (en) * | 2022-07-21 | 2022-08-23 | 浙江这里飞科技有限公司 | Unmanned aerial vehicle landing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106127201B (en) | 2019-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106127201B (en) | A kind of unmanned plane landing method of view-based access control model positioning landing end | |
| US11693428B2 (en) | Methods and system for autonomous landing | |
| US11454988B2 (en) | Systems and methods for automated landing of a drone | |
| CN107544550B (en) | Unmanned aerial vehicle automatic landing method based on visual guidance | |
| US6952632B2 (en) | Method of guiding an aircraft in the final approach phase and a corresponding system | |
| Kalinov et al. | High-precision uav localization system for landing on a mobile collaborative robot based on an ir marker pattern recognition | |
| Marut et al. | ArUco markers pose estimation in UAV landing aid system | |
| CN106054929A (en) | Unmanned plane automatic landing guiding method based on optical flow | |
| CN106054931A (en) | Unmanned aerial vehicle fixed-point flight control system based on visual positioning | |
| Li et al. | Toward automated power line corridor monitoring using advanced aircraft control and multisource feature fusion | |
| CN105644785A (en) | Unmanned aerial vehicle landing method based on optical flow method and horizon line detection | |
| CN109885086A (en) | A kind of unmanned plane vertical landing method based on the guidance of multiple polygonal shape mark | |
| CN104091369A (en) | Unmanned aerial vehicle remote-sensing image building three-dimensional damage detection method | |
| CN109460046B (en) | Unmanned aerial vehicle natural landmark identification and autonomous landing method | |
| Zarandy et al. | A novel algorithm for distant aircraft detection | |
| CN109613926A (en) | Multi-rotor unmanned aerial vehicle land automatically it is High Precision Automatic identification drop zone method | |
| Oszust et al. | A vision-based method for supporting autonomous aircraft landing | |
| Minghui et al. | Deep learning enabled localization for UAV autolanding | |
| CN114689030A (en) | Unmanned aerial vehicle auxiliary positioning method and system based on airborne vision | |
| US11816863B2 (en) | Method and device for assisting the driving of an aircraft moving on the ground | |
| Kim et al. | Fusing lidar data and aerial imagery with perspective correction for precise localization in urban canyons | |
| CN106128170A (en) | A kind of aircraft berth intelligent indicating system | |
| Pan et al. | BRISK based target localization for fixed-wing UAV's vision-based autonomous landing | |
| US20220397676A1 (en) | Aircraft identification | |
| US20220406040A1 (en) | Method and device for generating learning data for an artificial intelligence machine for aircraft landing assistance |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A landing method of UAV Based on vision positioning landing terminal Effective date of registration: 20200729 Granted publication date: 20190215 Pledgee: Xi'an innovation financing Company limited by guarantee Pledgor: XI'AN INNNO AVIATION TECHNOLOGY Co.,Ltd. Registration number: Y2020990000846 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20211028 Granted publication date: 20190215 Pledgee: Xi'an innovation financing Company limited by guarantee Pledgor: XI'AN INNNO AVIATION TECHNOLOGY Co.,Ltd. Registration number: Y2020990000846 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A landing method of UAV Based on visual positioning landing end Effective date of registration: 20211124 Granted publication date: 20190215 Pledgee: Xi'an innovation financing Company limited by guarantee Pledgor: XI'AN INNNO AVIATION TECHNOLOGY Co.,Ltd. Registration number: Y2021610000357 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20221115 Granted publication date: 20190215 Pledgee: Xi'an innovation financing Company limited by guarantee Pledgor: XI'AN INNNO AVIATION TECHNOLOGY Co.,Ltd. Registration number: Y2021610000357 |