CN106774402A - The method and device positioned to unmanned plane - Google Patents

The method and device positioned to unmanned plane Download PDF

Info

Publication number
CN106774402A
CN106774402A CN201611240082.2A CN201611240082A CN106774402A CN 106774402 A CN106774402 A CN 106774402A CN 201611240082 A CN201611240082 A CN 201611240082A CN 106774402 A CN106774402 A CN 106774402A
Authority
CN
China
Prior art keywords
unmanned plane
image
benchmark image
return voyage
characteristic point
Prior art date
Application number
CN201611240082.2A
Other languages
Chinese (zh)
Inventor
雷志辉
卞杰
卞一杰
杨凯斌
贾宁
Original Assignee
湖南省道通科技有限公司
深圳市道通智能航空技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 湖南省道通科技有限公司, 深圳市道通智能航空技术有限公司 filed Critical 湖南省道通科技有限公司
Priority to CN201611240082.2A priority Critical patent/CN106774402A/en
Publication of CN106774402A publication Critical patent/CN106774402A/en

Links

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/10Simultaneous control of position or course in three dimensions
    • G05D1/101Simultaneous control of position or course in three dimensions specially adapted for aircraft
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/10Simultaneous control of position or course in three dimensions
    • G05D1/101Simultaneous control of position or course in three dimensions specially adapted for aircraft
    • G05D1/102Simultaneous control of position or course in three dimensions specially adapted for aircraft specially adapted for vertical take-off of aircraft
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/08Control of attitude, i.e. control of roll, pitch, or yaw
    • G05D1/0808Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/12Target-seeking control

Abstract

A kind of method and device positioned to unmanned plane, wherein, methods described includes:During unmanned plane during flying, benchmark image is generated;Obtain the present image of current time collection;According to benchmark image and present image, the current location of unmanned plane is determined.There is certain relevance between benchmark image and present image, then, the current location of unmanned plane is can determine according to benchmark image and present image.Relative to resolution ratio fixed in the prior art, unmanned plane can be better achieved Dynamic Matching, reduce systematic error during making a return voyage, so as to improve the positioning precision maked a return voyage.

Description

The method and device positioned to unmanned plane
Technical field
The present invention relates to unmanned aerial vehicle (UAV) control field, and in particular to a kind of method and device positioned to unmanned plane.
Background technology
Unmanned plane take precautions against natural calamities recover, there is wide application in the field such as scientific investigation, and flight control system is unmanned plane Important component, UAV Intelligent and it is practical in play an important role.Generally, unmanned plane is in flight control system Gone under the control of system after the completion of the operation of destination, can automatically be maked a return voyage according to former road.
Positioning during in order to realize making a return voyage unmanned plane automatically, in the prior art, generally can be in the flight system of unmanned plane The map datum that third party provides is stored in system, then by positioner such as global positioning system (Global Position System, GPS) realize positioning and the navigation of unmanned plane.However, the resolution ratio and unmanned plane of the map datum of third party's offer Height apart from ground is relevant, and typically, the liftoff flying height of unmanned plane is higher, and resolution ratio is lower.Because unmanned plane exists Flying height in operation process can often change, and the resolution ratio difference for thus easily causing ground target is larger, matching Precision is low, result in positioning precision when making a return voyage poor.
Therefore, how to improve positioning precision as technical problem urgently to be resolved hurrily.
The content of the invention
The technical problem to be solved in the present invention is how to improve positioning precision.
Therefore, according in a first aspect, the embodiment of the invention discloses a kind of method positioned to unmanned plane, including:
During unmanned plane during flying, benchmark image is generated;Obtain the present image of current time collection;According to benchmark Image and present image, determine the current location of unmanned plane.
Alternatively, benchmark image is generated, including:During unmanned plane during flying, ground image is gathered;By ground image Spliced, obtained benchmark image.
Alternatively, during unmanned plane during flying, ground image is gathered, including:Flown to from original position in unmanned plane Make a return voyage during position, gather ground image.
Alternatively, before the present image of current time collection is obtained, the present embodiment is disclosed to be determined unmanned plane The method of position also includes:It is determined that making a return voyage.
Alternatively, before it is determined that making a return voyage, the disclosed method positioned to unmanned plane of the present embodiment also includes:Receive The instruction maked a return voyage for instruction that controller sends.
Alternatively, after generating the reference images, the disclosed method positioned to unmanned plane of the present embodiment also includes: Determine that unmanned plane flies to the reverse track of position of making a return voyage from original position.
Alternatively, it is determined that after reverse track, the disclosed method positioned to unmanned plane of the present embodiment also includes: Flown to original position from position of making a return voyage according to reverse track.
Alternatively, according to benchmark image and present image, the current location of unmanned plane is determined, including:To present image with Benchmark image is matched, and obtains unmanned plane in motion vector of the current time relative to benchmark image;It is true according to motion vector Unmanned plane is determined in location information of the current time relative to benchmark image;Wherein, location information includes at least one following:Nobody The course of the position of machine, the height of unmanned plane, the attitude of unmanned plane, the orientation of unmanned plane, the speed of unmanned plane and unmanned plane.
Alternatively, present image is matched with benchmark image, obtains unmanned plane at current time relative to reference map The motion vector of picture, including:Present image and benchmark image are carried out into scene matching aided navigation, obtain unmanned plane current time relative to The motion vector of benchmark image.
Alternatively, present image and benchmark image are carried out into scene matching aided navigation, obtains unmanned plane at current time relative to base The motion vector of quasi- image, including:The characteristic point of benchmark image is chosen, wherein, the characteristic point of selection is used as reference characteristic Point;It is determined that in present image with the characteristic point of reference characteristic Point matching, wherein, the characteristic point that obtains of matching is used as currently Characteristic point;Current signature point is matched with reference characteristic point, unmanned plane is obtained at current time relative to benchmark image Motion vector.
According to second aspect, the embodiment of the invention discloses a kind of device positioned to unmanned plane, including:
Base modules, for during unmanned plane during flying, generating benchmark image;Acquisition module, it is current for obtaining The present image of moment collection;Locating module, what benchmark image and acquisition module for being generated according to base modules were gathered works as Preceding image, determines the current location of unmanned plane.
Alternatively, base modules include:Sampling unit, for during unmanned plane during flying, gathering ground image;Spell Order unit, the ground image for sampling unit to be gathered is spliced, and obtains benchmark image.
Alternatively, during sampling unit in unmanned plane specifically for flying to position of making a return voyage from original position, locality Face image.
Alternatively, the disclosed device positioned to unmanned plane of the present embodiment also includes:Determining module, for determining to return Boat.
Optionally it is determined that module is additionally operable to receive the instruction maked a return voyage for instruction that controller sends.
Alternatively, the disclosed device positioned to unmanned plane of the present embodiment also includes:Track module, in benchmark After module generation benchmark image, determine that unmanned plane flies to the reverse track of position of making a return voyage from original position.
Alternatively, the disclosed device positioned to unmanned plane of the present embodiment also includes:Make a return voyage module, for according to rail Flown to original position from position of making a return voyage the reverse track that mark module determines.
Alternatively, locating module includes:Matching unit, for being matched with benchmark image to present image, obtains nothing It is man-machine in motion vector of the current time relative to benchmark image;Location information unit, for determining nobody according to motion vector Machine is in location information of the current time relative to benchmark image;Wherein, location information includes at least one following:The position of unmanned plane Put, the course of the attitude of the height of unmanned plane, unmanned plane, the orientation of unmanned plane, the speed of unmanned plane and unmanned plane.
Alternatively, matching unit obtains unmanned plane and exists specifically for present image and benchmark image are carried out into scene matching aided navigation Motion vector of the current time relative to benchmark image.
Alternatively, matching unit includes:Selection subelement, the characteristic point for choosing benchmark image, wherein, the spy of selection Levy and be a little used as reference characteristic point;Characteristic point determination subelement, for determine in present image with reference characteristic Point matching Characteristic point, wherein, the characteristic point that obtains of matching is used as current signature point;Vector subelement, for by current signature point Matched with reference characteristic point, obtained unmanned plane in motion vector of the current time relative to benchmark image.
Technical solution of the present invention, has the following advantages that:
The method and device positioned to unmanned plane provided in an embodiment of the present invention, it is raw during unmanned plane during flying Into benchmark image, benchmark image can the newest surface state of ground reflection, then, obtain the present image of current time collection, Collection is obtained during unmanned plane during flying due to benchmark image and present image, therefore, benchmark image and present image Between there is certain relevance, then, the current location of unmanned plane is can determine according to benchmark image and present image;This hair In the scheme of bright embodiment, benchmark image is generated during unmanned plane during flying, and present image is also unmanned plane during flying During collection acquire, therefore, the benchmark image of generation is produced during can dynamically compensating adaptation unmanned plane during flying Raw differences in resolution, relative to resolution ratio fixed in the prior art, unmanned plane can be better achieved dynamic during making a return voyage State is matched, and systematic error is reduced, so as to improve the positioning precision maked a return voyage.
As optional technical scheme, after generating the reference images, determine that unmanned plane flies to position of making a return voyage from original position The reverse track put so that unmanned plane, can be directly according to reverse track from returning when from position of making a return voyage to original position flight Boat position is flown to original position, reduces the planning amount of making a return voyage of flight path, improves the effect that flight path determines when making a return voyage Rate.Additionally, unmanned plane is in the case where no signal or communication failure is run into, by according to reverse track from making a return voyage position to Beginning position flight so that unmanned plane can smoothly be back to original position.
In addition, generally unmanned plane from original position to make a return voyage position flight when can cook up preferably for example cut-through Thing etc. goes to journey track, therefore so that during according to going to the reverse track of journey track from position of making a return voyage to original position flight, can Maked a return voyage with preferably track.
Brief description of the drawings
In order to illustrate more clearly of the specific embodiment of the invention or technical scheme of the prior art, below will be to specific The accompanying drawing to be used needed for implementation method or description of the prior art is briefly described, it should be apparent that, in describing below Accompanying drawing is some embodiments of the present invention, for those of ordinary skill in the art, before creative work is not paid Put, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of method flow diagram positioned to unmanned plane in the embodiment of the present invention;
Fig. 2 is that a kind of scene matching aided navigation obtains the method flow diagram of unmanned plane motion vector in the embodiment of the present invention;
Fig. 3 is a kind of apparatus structure schematic diagram positioned to unmanned plane in the embodiment of the present invention;
Fig. 4 is a kind of system structure diagram positioned to unmanned plane in the embodiment of the present invention.
Specific embodiment
Technical scheme is clearly and completely described below in conjunction with accompanying drawing, it is clear that described implementation Example is a part of embodiment of the invention, rather than whole embodiments.Based on the embodiment in the present invention, ordinary skill The every other embodiment that personnel are obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
In the description of the invention, it is necessary to explanation, term " " center ", " on ", D score, "left", "right", " vertical ", The orientation or position relationship of the instruction such as " level ", " interior ", " outward " be based on orientation shown in the drawings or position relationship, merely to Be easy to the description present invention and simplify describe, rather than indicate imply signified device or element must have specific orientation, With specific azimuth configuration and operation, therefore it is not considered as limiting the invention.Additionally, term " first ", " second ", " the 3rd " is only used for describing purpose, and it is not intended that instruction or hint relative importance, can not be interpreted as sequencing.
In the description of the invention, it is necessary to illustrate, unless otherwise clearly defined and limited, term " installation ", " phase Company ", " connection " should be interpreted broadly, for example, it may be being fixedly connected, or being detachably connected, or be integrally connected;Can Being to mechanically connect, or electrically connect;Can be joined directly together, it is also possible to be indirectly connected to by intermediary, can be with It is two connections of element internal, can is wireless connection, or wired connection.For one of ordinary skill in the art For, above-mentioned term concrete meaning in the present invention can be understood with concrete condition.
As long as additionally, technical characteristic involved in invention described below different embodiments non-structure each other Can just be combined with each other into conflict.
In order to improve the positioning precision of unmanned plane during flying, present embodiment discloses a kind of side positioned to unmanned plane Method, refer to Fig. 1, be the method flow diagram that this pair of unmanned plane is positioned, and the method that this pair of unmanned plane is positioned includes:
Step S101, during unmanned plane during flying, generates benchmark image.
In the present embodiment, ground image can be gathered after unmanned plane takes off since original position, by unmanned plane preceding The ground image gathered toward the moving process of destination is spliced, using spliced result as benchmark image.Allegedly Face image refer to unmanned plane in flight course to overlook the image of visual angle collection, the folder of the vertical view view directions and vertical direction Angle is less than 90 degree.Preferably, the vertical view view directions can straight down, in the case, be overlooked view directions and erect Nogata to angle be 0 degree.
Unmanned plane can store the benchmark image of generation, in case being subsequently continuing with the benchmark image..It is optional as one kind Mode, the benchmark image after generating the reference images, can also be sent to other unmanned planes, so as to other by unmanned plane Unmanned plane can also use the benchmark image.It should be noted that for same unmanned plane, because the items of unmanned plane are hard Part parameter will not change during unmanned plane during flying, so the benchmark image that unmanned plane itself is generated can be characterized The unmanned plane goes to journey track.It is so-called that to go to journey track refer to that unmanned plane flies to the flight path of destination locations from original position.
Step S102, obtains the present image of current time collection.
After benchmark image is generated, during unmanned plane during flying, the present image of current time collection can be obtained.
Step S103, according to benchmark image and present image, determines the current location of unmanned plane.
In the present embodiment, after benchmark image is obtained, present image and benchmark image can be compared, obtain current The difference of image and benchmark image, the motion vector of unmanned plane is can be evaluated whether according to the difference, thereby determines that the current of unmanned plane Position.
In an alternate embodiment of the invention, in step S101, the operation for generating benchmark image can include:In unmanned plane during flying During, gather ground image;Ground image is spliced, benchmark image is obtained.In a particular embodiment, can be by pre- If interval collection ground image, alleged predetermined interval can determine default time interval in time domain according to priori, or Default distance interval on person position.Alleged predetermined interval can be at equal intervals, or unequal interval.
In specific splicing, can be spliced using one-piece pattern, it would however also be possible to employ segmented model carries out image mosaic. Specifically, in splicing, overlapping region is usually there will be between adjacent two field picture, will can be had two before and after lap Two field picture is combined into a secondary large-scale seamless image.For with the adjacent two field pictures for overlapping, it is also possible to will a wherein two field picture Overlapping region directly cast out, the part being had more is spliced on another two field picture, is merged in seam region, so as to obtain Spliced map.
In the embodiment of the present invention, during unmanned plane flies to position of making a return voyage from original position, ground image is gathered.Institute Title original position refers to unmanned plane in the position for starting to take off;Alleged position of making a return voyage refers to start to start bit after unmanned plane takes off Put the position of return.Generally, make a return voyage the destination that position goes to for unmanned plane, but, in specific implementation process, position of making a return voyage Can also be unmanned plane received during destination of flying to make a return voyage instruction when where position.Position of making a return voyage can also be Unmanned plane runs into the position that special circumstances determine to need to make a return voyage during destination of flying to.Occur for example in flight course Not enough power supply, without emergency cases such as gps signal, unmanned plane failures, at this moment the flight control system in unmanned plane determines to make a return voyage.
Alternatively, before step S102 is performed, can also include:
Step S104, it is determined that making a return voyage.
Can be that unmanned plane actively determines to make a return voyage wherein in a kind of implementation method, for example unmanned plane is in flight course Running into special circumstances needs to make a return voyage, and not enough power supply occurs in flight course in such as unmanned plane, without gps signal, unmanned plane failure Etc. emergency case, the at this moment flight control system determination in unmanned plane is maked a return voyage.Fulfiled assignment after task destination is flown to, unmanned plane Can actively determine that needs make a return voyage.
Maked a return voyage in another implementation method, or by controller control unmanned plane.Specifically, unmanned plane is received The instruction maked a return voyage for instruction that controller sends.After unmanned plane receives the instruction, it is determined that making a return voyage.In the present embodiment, control Device can be unmanned plane dedicated remote control, or with the terminal being remotely controlled to unmanned plane, such as mobile terminal, calculate Machine, notebook etc..
In order to provide track reference of making a return voyage when making a return voyage to unmanned plane, alternatively, after step S101 is performed, also wrap Include:
Step S105, determines that unmanned plane flies to the reverse track of position of making a return voyage from original position.
In the present embodiment, for a unmanned plane, because every physical parameter of the unmanned plane is in flight course All do not change, therefore during position of making a return voyage is flown to from original position, the image of collection after splicing, Neng Gougen The flight path of unmanned plane is determined according to image attributes.In the present embodiment, original position is flown to from position of making a return voyage along journey track is gone to Form the reverse track that unmanned plane flies to position of making a return voyage from original position.When unmanned plane makes a return voyage, unmanned plane can be according to this Reverse track performs operation of making a return voyage.
Alternatively, step S103 can be specifically included:Present image is matched with benchmark image, unmanned plane is obtained and is existed Motion vector of the current time relative to benchmark image;Determine unmanned plane at current time relative to reference map according to motion vector The location information of picture.
In the present embodiment, location information includes at least one following:The position of unmanned plane, the height of unmanned plane, unmanned plane Attitude, the orientation of unmanned plane, the course of the speed of unmanned plane and unmanned plane.Wherein, the direction position of unmanned plane refers to aircraft In the present image and the relative angle of benchmark image of current time collection, the course of unmanned plane refers to that the actual of unmanned plane flies Line direction.When present image is matched with benchmark image, because the flight path of the process of making a return voyage is the inverse of journey track To track, therefore, motion vector of the unmanned plane current time relative to benchmark image can be obtained by the matching, by the fortune Dynamic vector can obtain the information such as position of the unmanned plane at current time in benchmark image, height, attitude and orientation, in It is, it may be determined that unmanned plane is in the position at current time.
In a particular embodiment, present image and benchmark image match obtain unmanned plane current time relative to During the motion vector of benchmark image, present image and benchmark image can be carried out scene matching aided navigation and obtain unmanned plane current time phase For the motion vector of benchmark image, specifically, Fig. 2 is refer to.Method shown in Fig. 2 includes:
Step S201, chooses the characteristic point of the benchmark image, and the characteristic point of the selection is used as reference characteristic point.
The point or building of easy identification can be chosen as reference characteristic point, such as the object edge point of texture-rich Deng.After reference characteristic point is selected, the mathematical way such as such as histogram of gradients, local random binary feature can be used to retouch State characteristic point.
Step S202, it is determined that the characteristic point obtained with the characteristic point of reference characteristic Point matching, the matching in present image It is used as current signature point.
In a particular embodiment, the pixel in present image can be described by identical mathematical description mode, is utilized Mathematical knowledge can determine the current signature point with reference characteristic Point matching in present image.
Step S203, current signature point is matched with reference characteristic point, obtain unmanned plane current time relative to The motion vector of benchmark image.
Current signature point and reference characteristic point can be carried out by affine Transform Model or projective transformation model Match somebody with somebody.Relevant affine Transform Model or projective transformation model are described as follows.
(1) for affine Transform Model, affine Transform Model can be set up by way of equation group, specifically, is led to The transformation model for crossing equation group foundation is as follows:
Wherein, on the basis of (x, y) in image reference characteristic point coordinate, (x', y') be present image in reference characteristic The coordinate of the characteristic point of Point matching, a, b, c, d, m and n are affine transformation parameter.In the present embodiment, when the characteristic point of matching is three When organizing not conllinear characteristic point, complete affine transformation parameter just can be calculated;When the characteristic point of matching is more than three groups, More accurate affine transformation parameter can be solved by least square solution.
In a particular embodiment, affine Transform Model can be set up by the form of matrix, specifically, is built by matrix Vertical transformation model is as follows:
Wherein, on the basis of (x, y) in image reference characteristic point coordinate, (x', y') be present image in reference characteristic The coordinate of the characteristic point of Point matching, a0, a1, a2, b0, b1 and b2 are affine transformation parameter.In the present embodiment, when the feature of matching When point is for three groups of not conllinear characteristic points, complete affine transformation parameter just can be calculated;When the characteristic point of matching is three groups During the above, more accurate affine transformation parameter can be solved by least square solution.
The affine transformation parameter being calculated according to affine Transform Model may be used to indicate that the motion vector of unmanned plane.
(2) for projective transformation model, projective transformation model can be set up by way of equation group, specifically, is led to Cross below equation and set up transformation model:
Wherein, on the basis of (x, y) in image reference characteristic point coordinate, (x', y') be present image in reference characteristic The coordinate of the characteristic point of Point matching, (w'x'w'y'w') and (wx wy w) is respectively the homogeneous coordinates of (x, y) and (x', y'),It is projective transform matrix, in a particular embodiment, transformation matrixCan split It is 4 parts, wherein,Linear transformation is represented, [a31 a32] is used to translate, [a13 a23]TProduce projective transformation, A33=1.
The projective transform matrix being calculated according to projective transformation model may be used to indicate that the motion vector of unmanned plane.
The present embodiment also discloses a kind of device positioned to unmanned plane, refer to Fig. 3, and the unmanned plane makes a return voyage positioning Device includes:Base modules 301, acquisition module 302 and locating module 303, wherein:
Base modules 301 are used to during unmanned plane during flying, generate benchmark image;Acquisition module 302 is used to obtain The present image of current time collection;Locating module 303 is used for the benchmark image and acquisition module generated according to base modules 301 The present image of 302 collections, determines the current location of unmanned plane.
In an alternate embodiment of the invention, base modules 301 include:Sampling unit, for during unmanned plane during flying, adopting Collection ground image;Concatenation unit, the ground image for sampling unit to be gathered is spliced, and obtains benchmark image.
In an alternate embodiment of the invention, sampling unit from original position specifically for flying to the process of position of making a return voyage in unmanned plane In, gather ground image.
In an alternate embodiment of the invention, also include:Determining module, for determining to make a return voyage.
In an alternate embodiment of the invention, determining module is additionally operable to receive the instruction maked a return voyage for instruction that controller sends.
In an alternate embodiment of the invention, also include:Track module, after generating benchmark image in base modules 301, really Determine the reverse track that unmanned plane flies to position of making a return voyage from original position.
In an alternate embodiment of the invention, also include:Make a return voyage module, for the reverse track that determines according to track module from making a return voyage Flown to original position position.
In an alternate embodiment of the invention, locating module includes:Matching unit, for being carried out to present image and benchmark image Match somebody with somebody, obtain unmanned plane in motion vector of the current time relative to benchmark image;Location information unit, for according to motion vector Determine unmanned plane in location information of the current time relative to benchmark image;Wherein, location information includes at least one following:Nothing The boat of man-machine position, the height of unmanned plane, the attitude of unmanned plane, the orientation of unmanned plane, the speed of unmanned plane and unmanned plane To.
In an alternate embodiment of the invention, matching unit is additionally operable to for present image and benchmark image to carry out scene matching aided navigation, obtains Unmanned plane is in motion vector of the current time relative to benchmark image.
In an alternate embodiment of the invention, matching unit includes:Selection subelement, the characteristic point for choosing benchmark image, its In, the characteristic point of selection is used as reference characteristic point;Characteristic point determination subelement, for determine in present image with benchmark The characteristic point of Feature Points Matching, wherein, the characteristic point that matching is obtained is used as current signature point;Vector subelement, for inciting somebody to action Current signature point is matched with reference characteristic point, obtains unmanned plane in motion vector of the current time relative to benchmark image.
The present embodiment also discloses a kind of unmanned plane, refer to Fig. 4.The unmanned plane includes:Fuselage 401, image collector 402 and processor (not shown) are put, wherein:
Fuselage 401 is used to carry all parts of unmanned plane, and such as battery, engine (motor), shooting are first-class;
Image collecting device 402 is arranged on fuselage 401, and image collecting device 402 is used to gather image.
It should be noted that in the present embodiment, image collecting device 402 can be video camera.Alternatively, IMAQ Device 402 can be used for panoramic shooting.For example, image collecting device 402 can include many mesh cameras, it is also possible to including panorama Camera, can also simultaneously include many mesh cameras and full-view camera, to gather image or video from multi-angle.
Processor is used to perform the method disclosed in embodiment illustrated in fig. 1.
The method and device positioned to unmanned plane that the present embodiment is provided, it is provided in an embodiment of the present invention to unmanned plane The method and device for being positioned, generates benchmark image during unmanned plane during flying, benchmark image can ground reflection it is newest Surface state, then, the present image of current time collection is obtained, because benchmark image and present image are winged in unmanned plane Collection is obtained during row, therefore, there is certain relevance between benchmark image and present image, then, according to benchmark Image and present image can determine the current location of unmanned plane;In the scheme of the embodiment of the present invention, benchmark image is at nobody Generated in machine flight course, and present image is also to gather during unmanned plane during flying to acquire, therefore, the base of generation Quasi- image can dynamically be compensated and adapt to produced differences in resolution during unmanned plane during flying, relative to fixing in the prior art Resolution ratio, unmanned plane can be better achieved Dynamic Matching, reduce systematic error, be maked a return voyage so as to improve during making a return voyage Positioning precision.
In an alternate embodiment of the invention, after generating the reference images, determine that unmanned plane flies to position of making a return voyage from original position Reverse track so that unmanned plane, can be directly according to reverse track from making a return voyage when from position of making a return voyage to original position flight Position is flown to original position, reduces the planning amount of making a return voyage of flight path, improves the efficiency that flight path determines when making a return voyage. Additionally, unmanned plane is in the case where no signal or communication failure is run into, by according to reverse track from position to starting of making a return voyage Fly position so that unmanned plane can smoothly be back to original position.
In addition, generally unmanned plane from original position to make a return voyage position flight when can cook up preferably for example cut-through Thing etc. goes to journey track, therefore so that during according to going to the reverse track of journey track from position of making a return voyage to original position flight, can Maked a return voyage with preferably track.
It should be understood by those skilled in the art that, embodiments of the invention can be provided as method, system or computer program Product.Therefore, the present invention can be using the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware Apply the form of example.And, the present invention can be used and wherein include the computer of computer usable program code at one or more The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) is produced The form of product.
The present invention is the flow with reference to method according to embodiments of the present invention, equipment (system) and computer program product Figure and/or block diagram are described.It should be understood that every first-class during flow chart and/or block diagram can be realized by computer program instructions The combination of flow and/or square frame in journey and/or square frame and flow chart and/or block diagram.These computer programs can be provided The processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce A raw machine so that produced for reality by the instruction of computer or the computing device of other programmable data processing devices The device of the function of being specified in present one flow of flow chart or multiple one square frame of flow and/or block diagram or multiple square frames.
These computer program instructions may be alternatively stored in can guide computer or other programmable data processing devices with spy In determining the computer-readable memory that mode works so that instruction of the storage in the computer-readable memory is produced and include finger Make the manufacture of device, the command device realize in one flow of flow chart or multiple one square frame of flow and/or block diagram or The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that in meter Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented treatment, so as in computer or The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one The step of function of being specified in individual square frame or multiple square frames.
Obviously, above-described embodiment is only intended to clearly illustrate example, and not to the restriction of implementation method.It is right For those of ordinary skill in the art, can also make on the basis of the above description other multi-forms change or Change.There is no need and unable to be exhaustive to all of implementation method.And the obvious change thus extended out or Among changing still in the protection domain of the invention.

Claims (20)

1. a kind of method positioned to unmanned plane, it is characterised in that including:
During unmanned plane during flying, benchmark image is generated;
Obtain the present image of current time collection;
According to the benchmark image and the present image, the current location of the unmanned plane is determined.
2. the method for claim 1, it is characterised in that the generation benchmark image, including:
During the unmanned plane during flying, ground image is gathered;
The ground image is spliced, the benchmark image is obtained.
3. method as claimed in claim 2, it is characterised in that during the unmanned plane during flying, gathers the ground Image, including:
During the unmanned plane flies to position of making a return voyage from original position, the ground image is gathered.
4. the method as described in any in claim 1-3, it is characterised in that obtain current time collection present image it Before, methods described also includes:
It is determined that making a return voyage.
5. method as claimed in claim 4, it is characterised in that before it is determined that making a return voyage, methods described also includes:
Receive the instruction maked a return voyage for instruction that controller sends.
6. the method as described in any in claim 1-5, it is characterised in that after the benchmark image is generated, the side Method also includes:
Determine that the unmanned plane flies to the reverse track of position of making a return voyage from original position.
7. method as claimed in claim 6, it is characterised in that it is determined that after the reverse track, methods described also includes:
Flown to the original position from the position of making a return voyage according to the reverse track.
8. the method as described in any one in claim 1-7, it is characterised in that described according to the benchmark image and described Present image, determines the current location of the unmanned plane, including:
The present image is matched with the benchmark image, the unmanned plane is obtained at the current time relative to institute State the motion vector of benchmark image;
Determine the unmanned plane in location information of the current time relative to the benchmark image according to the motion vector;
Wherein, the location information includes at least one following:
The position of the unmanned plane, the height of the unmanned plane, the attitude of the unmanned plane, the orientation of the unmanned plane, institute State the speed of unmanned plane and the course of the unmanned plane.
9. method as claimed in claim 8, it is characterised in that described to be carried out to the present image and the benchmark image Match somebody with somebody, obtain the unmanned plane in motion vector of the current time relative to the benchmark image, including:
The present image is carried out into scene matching aided navigation with the benchmark image, the unmanned plane is obtained relative at the current time In the motion vector of the benchmark image.
10. method as claimed in claim 9, it is characterised in that described that the present image is carried out with the benchmark image Scene matching aided navigation, obtains the unmanned plane in motion vector of the current time relative to the benchmark image, including:
The characteristic point of the benchmark image is chosen, wherein, the characteristic point of the selection is used as reference characteristic point;
It is determined that in the present image with the characteristic point of the reference characteristic Point matching, wherein, it is described to match the feature that obtains Point is used as current signature point;
The current signature point is matched with the reference characteristic point, the unmanned plane is obtained relative at the current time In the motion vector of the benchmark image.
A kind of 11. devices positioned to unmanned plane, it is characterised in that including:
Base modules, for during unmanned plane during flying, generating benchmark image;
Acquisition module, the present image for obtaining current time collection;
Locating module, for the present image that the benchmark image generated according to the base modules and the acquisition module are gathered, Determine the current location of the unmanned plane.
12. devices as claimed in claim 11, it is characterised in that the base modules include:
Sampling unit, for during the unmanned plane during flying, gathering ground image;
Concatenation unit, for the ground image that the sampling unit is gathered to be spliced, obtains the benchmark image.
13. devices as claimed in claim 12, it is characterised in that the sampling unit specifically in the unmanned plane from Beginning position fly to position of making a return voyage during, gather the ground image.
14. device as described in any in claim 11-13, it is characterised in that also include:
Determining module, for determining to make a return voyage.
15. devices as claimed in claim 14, it is characterised in that the determining module is additionally operable to receive the use that controller sends In the instruction that instruction is maked a return voyage.
16. device as described in any in claim 11-15, it is characterised in that also include:
Track module, after generating the benchmark image in base modules, determines that the unmanned plane flies to from original position Make a return voyage the reverse track of position.
17. devices as claimed in claim 16, it is characterised in that also include:
Make a return voyage module, the reverse track for determining according to the track module flies from the position of making a return voyage to the original position OK.
18. device as described in claim 11-17 any one, it is characterised in that the locating module includes:
Matching unit, for being matched with the benchmark image to the present image, obtains the unmanned plane and works as described Motion vector of the preceding moment relative to the benchmark image;
Location information unit, for determining the unmanned plane at the current time relative to the base according to the motion vector The location information of quasi- image;
Wherein, the location information includes at least one following:
The position of the unmanned plane, the height of the unmanned plane, the attitude of the unmanned plane, the orientation of the unmanned plane, institute State the speed of unmanned plane and the course of the unmanned plane.
19. devices as claimed in claim 18, it is characterised in that the matching unit specifically for by the present image with The benchmark image carries out scene matching aided navigation, obtains the unmanned plane in motion of the current time relative to the benchmark image Vector.
20. devices as claimed in claim 19, it is characterised in that the matching unit includes:
Selection subelement, the characteristic point for choosing the benchmark image, wherein, the characteristic point of the selection is used as benchmark Characteristic point;
Characteristic point determination subelement, for determining the characteristic point in the present image with the reference characteristic Point matching, its In, the characteristic point for obtaining that matches is used as current signature point;
Vector subelement, for the current signature point to be matched with the reference characteristic point, obtains the unmanned plane and exists Motion vector of the current time relative to the benchmark image.
CN201611240082.2A 2016-12-28 2016-12-28 The method and device positioned to unmanned plane CN106774402A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611240082.2A CN106774402A (en) 2016-12-28 2016-12-28 The method and device positioned to unmanned plane

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201611240082.2A CN106774402A (en) 2016-12-28 2016-12-28 The method and device positioned to unmanned plane
PCT/CN2017/072477 WO2018120350A1 (en) 2016-12-28 2017-01-24 Method and device for positioning unmanned aerial vehicle

Publications (1)

Publication Number Publication Date
CN106774402A true CN106774402A (en) 2017-05-31

Family

ID=58923493

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611240082.2A CN106774402A (en) 2016-12-28 2016-12-28 The method and device positioned to unmanned plane

Country Status (2)

Country Link
CN (1) CN106774402A (en)
WO (1) WO2018120350A1 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108700892A (en) * 2017-09-27 2018-10-23 深圳市大疆创新科技有限公司 A kind of path method of adjustment and unmanned plane
WO2019006772A1 (en) * 2017-07-06 2019-01-10 杨顺伟 Return flight method and device for unmanned aerial vehicle
CN110243357A (en) * 2018-03-07 2019-09-17 杭州海康机器人技术有限公司 A kind of unmanned plane localization method, device, unmanned plane and storage medium
WO2021056144A1 (en) * 2019-09-23 2021-04-01 深圳市大疆创新科技有限公司 Method and apparatus for controlling return of movable platform, and movable platform

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101046387A (en) * 2006-08-07 2007-10-03 南京航空航天大学 Scene matching method for raising navigation precision and simulating combined navigation system
CN103411609A (en) * 2013-07-18 2013-11-27 北京航天自动控制研究所 Online composition based aircraft return route programming method
CN104807456A (en) * 2015-04-29 2015-07-29 深圳市保千里电子有限公司 Method for automatic return flight without GPS (global positioning system) signal
CN104932515A (en) * 2015-04-24 2015-09-23 深圳市大疆创新科技有限公司 Automatic cruising method and cruising device
CN105487555A (en) * 2016-01-14 2016-04-13 浙江大华技术股份有限公司 Hovering positioning method and hovering positioning device of unmanned aerial vehicle
CN106204443A (en) * 2016-07-01 2016-12-07 成都通甲优博科技有限责任公司 A kind of panorama UAS based on the multiplexing of many mesh

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101046387A (en) * 2006-08-07 2007-10-03 南京航空航天大学 Scene matching method for raising navigation precision and simulating combined navigation system
CN103411609A (en) * 2013-07-18 2013-11-27 北京航天自动控制研究所 Online composition based aircraft return route programming method
CN104932515A (en) * 2015-04-24 2015-09-23 深圳市大疆创新科技有限公司 Automatic cruising method and cruising device
CN104807456A (en) * 2015-04-29 2015-07-29 深圳市保千里电子有限公司 Method for automatic return flight without GPS (global positioning system) signal
CN105487555A (en) * 2016-01-14 2016-04-13 浙江大华技术股份有限公司 Hovering positioning method and hovering positioning device of unmanned aerial vehicle
CN106204443A (en) * 2016-07-01 2016-12-07 成都通甲优博科技有限责任公司 A kind of panorama UAS based on the multiplexing of many mesh

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019006772A1 (en) * 2017-07-06 2019-01-10 杨顺伟 Return flight method and device for unmanned aerial vehicle
CN108700892A (en) * 2017-09-27 2018-10-23 深圳市大疆创新科技有限公司 A kind of path method of adjustment and unmanned plane
CN110243357A (en) * 2018-03-07 2019-09-17 杭州海康机器人技术有限公司 A kind of unmanned plane localization method, device, unmanned plane and storage medium
WO2021056144A1 (en) * 2019-09-23 2021-04-01 深圳市大疆创新科技有限公司 Method and apparatus for controlling return of movable platform, and movable platform

Also Published As

Publication number Publication date
WO2018120350A1 (en) 2018-07-05

Similar Documents

Publication Publication Date Title
US9641810B2 (en) Method for acquiring images from arbitrary perspectives with UAVs equipped with fixed imagers
CN106020237B (en) The multimachine operation flight course planning and its spraying operation method and system of plant protection drone
US8831877B2 (en) Automatic correction of trajectory data
US10210905B2 (en) Remote controlled object macro and autopilot system
CN103118230B (en) A kind of panorama acquisition, device and system
US8797400B2 (en) Apparatus and method for generating an overview image of a plurality of images using an accuracy information
US8902308B2 (en) Apparatus and method for generating an overview image of a plurality of images using a reference plane
CN102419178B (en) Mobile robot positioning system and method based on infrared road sign
CN205263655U (en) A system, Unmanned vehicles and ground satellite station for automatic generation panoramic photograph
CN103247075B (en) Based on the indoor environment three-dimensional rebuilding method of variation mechanism
US6064398A (en) Electro-optic vision systems
CN104637370B (en) A kind of method and system of Photogrammetry and Remote Sensing synthetic instruction
Zhang et al. Photogrammetric processing of low‐altitude images acquired by unpiloted aerial vehicles
US7916138B2 (en) Electro-optic vision systems
Strecha et al. Dynamic and scalable large scale image reconstruction
Udin et al. Assessment of photogrammetric mapping accuracy based on variation flying altitude using unmanned aerial vehicle
Alonso et al. Accurate global localization using visual odometry and digital maps on urban environments
KR100484941B1 (en) System for constructing and browsing geographic information using video data and method thereof
ES2391452T3 (en) Advanced 3D display system and method for mobile navigation units
CN103875024B (en) Systems and methods for navigating camera
US7363157B1 (en) Method and apparatus for performing wide area terrain mapping
US8437501B1 (en) Using image and laser constraints to obtain consistent and improved pose estimates in vehicle pose databases
CN102426019B (en) Unmanned aerial vehicle scene matching auxiliary navigation method and system
CN103809195A (en) Method and device for generating GPS trajectory curve
CN105627991B (en) A kind of unmanned plane image real time panoramic joining method and system

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
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20170531