CN108700892A - A kind of path method of adjustment and unmanned plane - Google Patents
A kind of path method of adjustment and unmanned plane Download PDFInfo
- Publication number
- CN108700892A CN108700892A CN201780009908.0A CN201780009908A CN108700892A CN 108700892 A CN108700892 A CN 108700892A CN 201780009908 A CN201780009908 A CN 201780009908A CN 108700892 A CN108700892 A CN 108700892A
- Authority
- CN
- China
- Prior art keywords
- image
- return voyage
- path
- making
- unmanned plane
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 239000003550 marker Substances 0.000 claims abstract description 67
- 230000005055 memory storage Effects 0.000 claims description 3
- 230000036544 posture Effects 0.000 description 27
- 238000010586 diagram Methods 0.000 description 12
- 230000000007 visual effect Effects 0.000 description 5
- 230000033001 locomotion Effects 0.000 description 4
- 238000006073 displacement reaction Methods 0.000 description 3
- 235000013399 edible fruits Nutrition 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000005259 measurement Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000007921 spray Substances 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000010006 flight Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- 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)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Navigation (AREA)
Abstract
A kind of path method of adjustment and unmanned plane, this method include:When losing positioning signal, path of making a return voyage is determined according to the location information recorded;When making a return voyage according to path of making a return voyage, the image that makes a return voyage is acquired at first position;The image that will make a return voyage carries out matching treatment with the tag image in image data base, and determines target marker image according to the result of matching treatment;According to the image that makes a return voyage, target marker image and the location information for determining with the associated posture information of target marker image first position;Flight path is adjusted according to the location information of first position and path of making a return voyage, can automatically and accurately be maked a return voyage when unmanned plane loses positioning signal.
Description
Technical field
The present invention relates to electronic technology field more particularly to a kind of path method of adjustment and unmanned planes.
Background technology
With the continuous development of electronic technology, unmanned plane has also obtained developing on a large scale very much.
Currently, most of unmanned plane is all by positioning system (such as global positioning system (Global Positioning
System, GPS), Beidou satellite navigation system (BeiDou Navigation Satellite System, BDS) etc.) realize
Positioning, when losing positioning signal, operator can manually control the unmanned plane to make a return voyage.
However, aforesaid operations person manually controls the mode maked a return voyage, operating procedure is very complicated, and is wanted to the profession of operator
It asks higher, for non-professional operator, the case where being susceptible to operation error, causes during making a return voyage, unmanned plane holds
Easily there is the problem of falling, breaking, causes unnecessary loss.
Invention content
The embodiment of the invention discloses a kind of path method of adjustment and unmanned planes, and unmanned plane may be implemented in no positioning signal
When automatic precisely make a return voyage.
First aspect of the embodiment of the present invention discloses a kind of path method of adjustment, including:When losing positioning signal, according to
The location information of record determines path of making a return voyage;
When making a return voyage according to the path of making a return voyage, the image that makes a return voyage is acquired at first position;
The image that makes a return voyage is subjected to matching treatment with the tag image in image data base, and according to the knot of matching treatment
Fruit determines target marker image;
According to the image that makes a return voyage, the target marker image and with the associated posture information of the target marker image
Determine the location information of the first position;
Flight path is adjusted according to the location information of the first position and the path of making a return voyage.
Wherein, the unmanned plane is specifically included when making a return voyage according to the path of making a return voyage:
It is maked a return voyage according to the path of making a return voyage using vision module;Wherein, which includes visual odometry (Visual
Odometery, VO)
Second aspect of the embodiment of the present invention discloses a kind of unmanned plane, including:Memory and processor;
The memory, for storing program instruction;
The processor, the program instruction for executing memory storage are used for when program instruction is performed:
When losing positioning signal, path of making a return voyage is determined according to the location information recorded;
When making a return voyage according to the path of making a return voyage, the image that makes a return voyage is acquired at first position;
The image that makes a return voyage is subjected to matching treatment with the tag image in image data base, and according to the knot of matching treatment
Fruit determines target marker image;
According to the image that makes a return voyage, the target marker image and with the associated posture information of the target marker image
Determine the location information of the first position;
Flight path is adjusted according to the location information of the first position and the path of making a return voyage.
In embodiments of the present invention, unmanned plane can determine path of making a return voyage, and according to institute when losing positioning signal
When stating path of making a return voyage and making a return voyage, at first position acquisition make a return voyage image, target marker image will be matched, according to the figure that makes a return voyage
Picture, the target marker image and the location information that the first position is determined with the associated posture information of the target marker image,
Flight path is adjusted according to the location information of the first position and the path of making a return voyage, can automatically be returned when losing positioning signal
Boat is met to a certain extent to unmanned plane automation, intelligent demand.
Description of the drawings
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to needed in the embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without having to pay creative labor, others are can also be obtained according to these attached drawings
Attached drawing.
Fig. 1 is a kind of scene schematic diagram for path adjustment provided in an embodiment of the present invention;
Fig. 2 is a kind of flow diagram of path method of adjustment provided in an embodiment of the present invention;
Fig. 3 is the flow diagram of another path method of adjustment provided in an embodiment of the present invention;
Fig. 4 is another scene schematic diagram for path adjustment provided in an embodiment of the present invention;
Fig. 5 is a kind of structural schematic diagram of unmanned plane provided in an embodiment of the present invention;
Fig. 6 is a kind of structural schematic diagram of system provided in an embodiment of the present invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes.
Most of unmanned planes realize positioning using positioning system (such as GPS system, BDS systems etc.), but fixed
Position system is it sometimes appear that failure, causes positioning signal to be lost.In this case, following two sides may be used in unmanned plane
Formula:
First way is when positioning signal is lost, which just stops in the position original place of lossing signal, with etc.
Person to be operated finds.However, once unmanned plane has run out far distance (such as 3km, 5km etc.), operator just needs
The position of unmanned plane stopping is taken a long time to reach, convenience is relatively low.In addition, by taking unmanned plane as an example, unmanned plane itself
Value is very high, the equipment for adding UAV flight, even more very worthy, if unmanned plane is tight in the position original place of lossing signal
It crashes accidentally when urgent drop, it will cause huge loss.
The second way is when positioning signal is lost, and operator manually controls the unmanned plane and makes a return voyage.However, manually
It controls to the professional more demanding of operator, for non-professional operator, manual operation step is very complicated, and operates
It is difficult.For example, by taking unmanned plane is agriculture unmanned plane as an example, the operator of agriculture unmanned plane is usually common peasant household, behaviour
It is typically not capable of professional requirement as level, and agriculture unmanned plane is frequently in low latitude (such as 5 meters, 10 meters etc.) operation again, once
Misoperation, the very easy crash of unmanned plane, leads to huge loss.
Therefore, how to ensure that unmanned plane can automatically, accurately make a return voyage when losing positioning signal, become one urgently
It solves the problems, such as.
In order to solve technical problem set out above, an embodiment of the present invention provides a kind of path methods of adjustment.It please refers to
Fig. 1, for a kind of scene schematic diagram for path adjustment provided in an embodiment of the present invention.As shown in Figure 1, black line is unmanned plane
Guidance path, unmanned plane moves ahead from takeoff point A, and according to the guidance path of black line planning, during forward, this nobody
Machine can record a series of location information and acquire the tag image at the location information, and by the location information with it is corresponding
Tag image be stored in image data base, wherein circle shown in FIG. 1 indicate the unmanned plane record flight point, the flight
Point corresponds to location information.
In one embodiment, which can be the location information recorded by positioning system.For example, should
The positioning got can be recorded as the location information by unmanned plane by GPS positioning system.
In one embodiment, which, can be from the flight point of record when losing GPS point B loss GPS signals
Select the point that makes a return voyage (Fig. 1 is indicated with black circles).Specifically, it can be a little to be located at the flight point to make a return voyage on path that this, which makes a return voyage,
That is, the subset for the flight point that can be a little record that makes a return voyage.
In one embodiment, which can determine multiple flights in takeoff point A between losing GPS point B
Point, each flight point can be associated with corresponding GPS signal, corresponding tag image and corresponding Inertial Measurement Unit
(IMU) posture information, wherein above-mentioned associated information is only illustrated, and non exhaustive, a flight point can also be associated with it is multiple its
His information.
In one embodiment, the unmanned plane can be selected from multiple flight points it is multiple make a return voyage a little, and will be multiple
Make a return voyage a line, obtains path of making a return voyage, in Fig. 1, the path of making a return voyage be represented by the dotted line (wherein, with guidance path intersection
It is not shown in Fig. 1).
Wherein, the unmanned plane determination make a return voyage path when, the strategy of polygonal approximation may be used, such as RDP algorithms
(RamerDouglas Peuckeralgorithm) etc., the present invention is not intended to be limited in any this.
In one embodiment, which can utilize VO to acquire the image that makes a return voyage, and estimate the position currently reached in real time
It sets, and determines the flight point in preset range in the position (such as in 1 meter, in 3 meters etc.).
In one embodiment, which estimates and currently reaches near the point C that makes a return voyage that (position being actually reached is with
One position indicates), so that it may to acquire the image n that makes a return voyage at the first position, and the image n that makes a return voyage is related to the point C that makes a return voyage
The tag image c of connection and in the corresponding mark of flight point of (such as in 1 meter, in 3 meters etc.) of making a return voyage in point C preset ranges
Remember image (the tag image c for the point C that makes a return voyage and the tag image in point C preset ranges of making a return voyage are indicated with intersection m herein) into
Row matching treatment.
In one embodiment, which can determine according to the matching result of intersection m and the image n that makes a return voyage
Tag image c in intersection m matched with the image m that makes a return voyage (wherein, make a return voyage point C and flight point C be the same point, tag image c is
The correspondence picture of flight point C), which can obtain the corresponding GPS signals of flight point C, and corresponding tag image is (i.e.
Tag image c) and corresponding IMU posture informations.
In one embodiment, which can be according to the corresponding GPS signals of flight point C, corresponding tag image
(i.e. tag image c) and corresponding IMU posture informations, and the image n that makes a return voyage taken in first position are returned with this is shot
Corresponding IMU posture informations when chart is as n determine that the first position distance is maked a return voyage the deviation of point C.
In one embodiment, which can fly to next the making a return voyage a little for the point C that makes a return voyage according to the deviation adjusting
Flight path.For example, the location information expression of first position can be to just in 0.5 meter of point C front-lefts of making a return voyage, the so unmanned plane
Right is advanced 0.5 meter, is maked a return voyage with returning on the point C that makes a return voyage, alternatively, the unmanned plane can also be according to current location information meter
It calculates distance to make a return voyage the distance value of point D, the point d that makes a return voyage then is arrived according to distance value flight, is returned according to the path of making a return voyage with continuation
Boat.
In one embodiment, which can also make a return voyage this corresponding depth maps of image n and tag image c
Depth map, the position orientation relation (camera pose) for obtaining tag image c between the image n that makes a return voyage, which can wrap
Include rotation and displacement.
In one embodiment, which can obtain the posture of the corresponding IMU of tag image c using IMU units
And the corresponding IMU postures of the image n that makes a return voyage, and the position orientation relation that tag image c is calculated between the image n that makes a return voyage.
In one embodiment, if the position orientation relation being calculated by above two mode matches, this nobody
Machine can determine that the determination process of tag image c is correct, and the corresponding location informations of tag image c can be used to indicate that first
The location information of position.
In one embodiment, for the unmanned plane when making a return voyage according to the path of making a return voyage, the flight of the unmanned plane is high
Degree is less than preset height.The preset height can be less than 30 meters.Alternatively, the preset height can be less than 20 meters.Alternatively, this is preset
Height can be less than 10 meters.
In order to better illustrate, the present processes embodiment is described below.
Referring to Fig. 2, being a kind of flow diagram of path method of adjustment provided in an embodiment of the present invention.In the present embodiment
Described path method of adjustment, including:
When S201, loss positioning signal, path of making a return voyage is determined according to the location information recorded.
It should be noted that the executive agent of the embodiment of the present invention can be unmanned plane, which can refer to nobody
Drive aircraft.
In some feasible embodiments, which can be technical grade unmanned plane, such as agricultural spray unmanned plane
Deng, further, the agricultural spray unmanned plane can be low-latitude flying (such as flying height be less than 30m or flying height
It is less than 10m etc. less than 20m or flying height) when, execute the method that the embodiment of the present invention is provided.
It should be noted that the locating module (such as GPS module etc.) that the positioning signal can be the unmanned plane obtains
Signal can be used for recording the location information of the unmanned plane.
Specifically, the location information of the unmanned plane may include location information, such as GPS information etc..
It should be noted that when locating module breaks down or energizes insufficient, which may lose positioning signal,
When losing positioning signal, the location information which can record according to locating module, to determine path of making a return voyage.
In one embodiment, when the loss positioning signal, according to recorded location information determination make a return voyage path it
Before, further include:Generate described image database, described image database include multiple tag images and with the tag image
Associated posture information.
It should be noted that the tag image can refer to corresponding to the image of location information shooting, for marking nobody
The position that machine flew.For example, the unmanned plane during flying is to position a, and a shoots tag image a, the tag image in the position
A may be used for identifying position a.
It should be noted that the posture information, may include location information and posture information.
Wherein, which may include the rotation (Rotation) and displacement when shooting the tag image
(Translation)。
In one embodiment, the generation image data base, including:It is flown according to positioning signal in the unmanned plane
When, tag image when record-setting flight and with the associated posture information of tag image when the flight;According to the flight
When tag image and generate image data base with the associated posture information of tag image when the flight.
For example, which can fly when not losing positioning signal according to the instruction of positioning signal, and
In flight course, (such as 1 minute, 10 minutes etc.) or real-time record once make a return voyage a little at regular intervals, and recording should
The location information to make a return voyage a little, and call photographic device shot mark image and the records photographing label at information in the position
Above-mentioned tag image, location information, posture information are finally stored in image data base by posture information when image.
In one embodiment, the path of making a return voyage refers to:The path of the unmanned plane planning.
In some feasible embodiments, unmanned plane can be believed according to the position recorded in a flash before positioning signal is lost
Location information when breath and unmanned plane set out preferentially selects rectilinear flight, and is returned for this by the more path maked a return voyage a little
Bit path.
In some feasible embodiments, unmanned plane can also be according to the position recorded in a flash before loss positioning signal
Location information when information and unmanned plane set out, using the straightway determined by two location informations as the road of making a return voyage
Diameter.
In the specific implementation, polygonal approximation strategy may be used in the unmanned plane, the path of making a return voyage is determined such as RDP algorithms,
Certainly, aforesaid way is only illustrated, and non exhaustive, including but not limited to above-mentioned optional mode.
S202, when making a return voyage according to the path of making a return voyage, at first position acquisition make a return voyage image.
In one embodiment, when making a return voyage according to the path of making a return voyage, the flying height of the unmanned plane is less than preset
Highly.The preset height can be 30 meters, or 20 meters, the embodiment of the present invention is not intended to be limited in any this.
In some feasible embodiments, which can be less than 20 meters.For example, 19 meters, 13 meters, 10 meters, 5
Rice etc..
In some feasible embodiments, which can acquire the image that makes a return voyage using visual odometry.Alternatively, should
Unmanned plane can also acquire the image that makes a return voyage using other modes.
It is maked a return voyage according to path of making a return voyage it should be noted that unmanned plane may be implemented by VO, but VO is generally concerned with local time
Between on movement (such as movement between two moment), when VO samples the time with certain interval, so that it may estimation fortune
Movement of the animal body within each time interval, due to factors such as this estimation affected by noise, brightness of image, flying heights,
The evaluated error of previous time is may result in, can be added on the movement of following time, drift (Drift) phenomenon is caused,
VO is set not fully to make a return voyage according to the path of making a return voyage, there are certain errors with the path of making a return voyage.
In one embodiment, the path of making a return voyage includes multiple location informations to make a return voyage a little;The first position be with
The distance maked a return voyage a little is less than the point of preset distance.
It should be noted that the preset distance can be 1 meter, 5 meters, the arbitrary preset distances such as 10 meters, the present invention is to this
It is not intended to be limited in any.
Wherein, which can be the position that aerocraft real reaches, and the first position can deviate this and return
Bit path.
It should also be noted that, this makes a return voyage path include it is multiple make a return voyage a little, to include making a return voyage a little for 1, the unmanned plane
Flight to make a return voyage a little 1 when, can estimate arrived and make a return voyage a little near 1, but actual capabilities with make a return voyage a little 1 position presence partially
Difference, the deviation can be within the preset distances.
S203, the tag image in make a return voyage image and the image data base carries out to matching treatment, and according to matching at
The result of reason determines target marker image.
It should be noted that the target marker image can be and the image that the makes a return voyage tag image the most matched.
For example, the unmanned plane determine flight to make a return voyage a little 1 position when, can choose this make a return voyage a little 1 preset away from
From in range multiple tag images (such as centered on 1 position that this makes a return voyage, with pre-determined distance ranging from area coverage into
Row is chosen), and multiple tag image and the image that makes a return voyage are subjected to matching treatment, determine target marker image.
In one embodiment, described that the image that makes a return voyage is subjected to matching treatment with the tag image recorded, including:
Matching treatment is carried out according to the image similarity to make a return voyage between image and the tag image recorded.
For example, which can extract the image of characteristics of image and each tag image in the image that makes a return voyage
Feature, if the similarity of the characteristics of image of one of tag image a reach preset condition (such as similarity 80% and with
On), so that it may to determine tag image a as target marker image.
S204, according to described in make a return voyage image, the target marker image and with the associated position of the target marker image
Appearance information determines the location information of the first position.
For example, which can be determined as the first position by the location information corresponding to the target marker image
Location information.
Again for example, which image and can also believe with the associated pose of target marker image according to making a return voyage
Breath, determines the diversity factor of the make a return voyage image and the target marker image, and this first can be all calculated according to the difference
It sets and the deviation of the target marker image, according to the corresponding location information of the target marker image and the first position and the mesh
The deviation for marking tag image, can determine the location information of the first position.
S205, flight path is adjusted according to the location information and the path of making a return voyage of the first position.
In one embodiment, the flight path refers to:The path of the unmanned plane practical flight.
In some feasible embodiments, which, which can determine to make a return voyage, a little 1 and makes a return voyage a little 2, and calculates
Make a return voyage a little 1 and a little the distance between 2 value D that makes a return voyage, and when making a return voyage according to path of making a return voyage, which can utilize VO determinations fly
Row to make a return voyage a little 1 position it is neighbouring (but actual capabilities can and make a return voyage a little 1 position there are deviation, the position that is actually reached is with the
One position indicates), so that it may the image that makes a return voyage is acquired at first position with basis, and this is maked a return voyage what image was concentrated with image data
Tag image matched come, determine target marker image, then according to the image that makes a return voyage, the target marker image and
With the associated posture information of the target marker image, determine the location information of the first position (such as positioned at a little 1 position of making a return voyage
5 meters of front-left at).
In some feasible embodiments, which can calculate this according to the location information of the first position
First position and make a return voyage a little the distance between 2 and orientation, and can based on the distance and the orientation adjustment flight path, with
Convenient for that can fly to a little position where 2 of making a return voyage.
In some feasible embodiments, which can also calculate according to the location information of the first position
It the first position and makes a return voyage a little the distance between 1 and orientation, and flight path can be adjusted first and returned in order to reach
Position where destination 1, may then continue with flight, in order to reach the position at a little 2 places of making a return voyage.
In one embodiment, the unmanned plane can also detect the positioning when making a return voyage according to the path of making a return voyage
Signal;If detecting the positioning signal, maked a return voyage according to the positioning signal and the path of making a return voyage.
In the specific implementation, unmanned plane can be with preset two offline mode, a kind of can be the pattern flown by positioning signal
1, one is the pattern 2 by visual flight, the pattern of the visual flight is the pattern for needing to acquire tag image.When pattern 1
When failure, unmanned plane can automatically switch to pattern 2, and when the pattern 1 restores normal condition, (i.e. unmanned plane can detect
The state of positioning signal), unmanned plane can slave pattern 2 switch back into pattern 1, and according to positioning signal and can determine
Path of making a return voyage is maked a return voyage.
As it can be seen that in embodiments of the present invention, unmanned plane can determine path of making a return voyage when losing positioning signal, and
When making a return voyage according to the path of making a return voyage, the image that makes a return voyage is acquired at first position, target marker image will be matched, according to described
It makes a return voyage image, the target marker image and the position that the first position is determined with the associated posture information of the target marker image
Information adjusts flight path according to the location information of the first position and the path of making a return voyage, can be when losing positioning signal, energy
It enough makes a return voyage automatically, and the deviation between adjustment practical flight path and path of making a return voyage, certain journey can be implemented during making a return voyage
It is met on degree to unmanned plane automation, intelligent demand.
Referring to Fig. 3, for the flow diagram of another path method of adjustment provided in an embodiment of the present invention.The present embodiment
Described in method, including:
When S301, loss positioning signal, path of making a return voyage is determined according to the location information recorded.
S302, when making a return voyage according to the path of making a return voyage, at first position acquisition make a return voyage image.
It should be noted that the specific implementation of S301 steps and S302 steps shown in the embodiment of the present invention can join
According to the S201 steps and S202 steps of preceding method embodiment, therefore not to repeat here.
S303, determine described in make a return voyage the description information of image.
The description information of image it should be noted that this makes a return voyage can refer to the information based on the description generation to image,
Specifically, the description information may include picture material brief introduction in making a return voyage image, classifying content etc., the embodiment of the present invention pair
This is not intended to be limited in any.
In some feasible embodiments, the unmanned plane can by bag of words (bag of words model,
BOW model) determine the description information.
In one embodiment, which can extract the corresponding characteristics of image of the image that makes a return voyage, and determine the figure that makes a return voyage
Then descriptor as corresponding to corresponding characteristics of image generates description information according to the descriptor.
It should be noted the corresponding descriptor of the characteristics of image, can be the words of description to the characteristics of image, it should
Words of description can be used for describing the classification of the characteristics of image, feature etc..
In some feasible embodiments, unsupervised machine learning (unsupervised ML) may be used in unmanned plane
In cluster (clustering) each characteristics of image is sorted out to obtain corresponding descriptor (feature
descriptors)。
In one embodiment, described that description information is generated according to the descriptor, including:Determine that the descriptor corresponds to
Weighted value;Description information is generated according to the descriptor and the corresponding weighted value of the descriptor.
It should be noted that the corresponding weighted value of the descriptor can be determined according to the significance level of descriptor.Tool
Body, which can be according to accounting range of the picture material represented by descriptor in whole image, entirely scheming
Representativeness etc. as in determines.
In some feasible embodiments, which can use K-Means++ algorithms (to can guarantee that classification is uniform
Mean algorithm), and can indicate the description information with tree structure, and term frequency-inverse document frequency (term may be used
Frequency-inverse document frequency, tf-idf) weighted value of each descriptor is set.
Further, which can be the structure of K fork trees.
In order to better illustrate, referring to Fig. 4, for another scene for path adjustment provided in an embodiment of the present invention
Schematic diagram, in Fig. 4, solid black lines indicate search characteristics of image when path, circle indicate path on node (namely description
Symbol).
Specifically, the unmanned plane can will make a return voyage, image is as root node, and can extract the image in the image that makes a return voyage
Feature determines the corresponding descriptor of each characteristics of image, and determines the corresponding classification number of plies of each descriptor, by returning layer by layer
Class obtains first layer classification, and the second layer is sorted out, until kth layer is sorted out, wherein and it can be that last layer is sorted out that kth layer, which is sorted out,
Kth layer classification includes the descriptor corresponding to the picture material of descriptor, that is, image of leaf node itself, into one
Step, the unmanned plane can assign weighted value to each node, so that it may to establish tree structure shown in Fig. 4, entire tree-like knot
The content that structure indicates can be as the description information of the image.
For example, as shown in figure 4, the unmanned plane can will make a return voyage, as root node, which can determine image a
The characteristics of image of the image a that makes a return voyage.Root node is the image a that makes a return voyage, and can be divided into 3 layers of classification (k=3).During first layer is sorted out
Each descriptor (being indicated with circle) can be each corresponding to a weighted value, and each descriptor during the second layer is sorted out can be each
From a weighted value is corresponded to, each descriptor during third layer is sorted out can be each corresponding to a weighted value, wherein third
Descriptor during layer is sorted out can be leaf node descriptor, and the content that entire tree structure shown in Fig. 4 indicates can conduct
The description information of the image a that makes a return voyage.
The each tag image recorded in the description information and image data base of image of making a return voyage described in S304, basis is closed
The description information of connection carries out similarity-rough set.
In one embodiment, the associated description information of each tag image is recorded, including:Extract each tag image pair
The characteristics of image answered, and determine the corresponding descriptor of described image feature;Description information is generated according to the descriptor.
In one embodiment, described that description information is generated according to the descriptor, including:Determine that the descriptor corresponds to
Weighted value;Description information is generated according to the descriptor and the corresponding weighted value of the descriptor.
It should be noted that unmanned plane can will make a return voyage, image utilizes identical processing mode with each tag image,
To determine corresponding description information, and weighted value is arranged to each descriptor.Specifically, the unmanned plane is according to the corresponding figure of image
Determine description information as feature and the mode of weighted value be set, can the aforementioned S303 steps of parameter and Fig. 4 corresponding description
Part, therefore not to repeat here.
In some feasible embodiments, which can make a return voyage this tree structure that image is determined, with
And the tree structure that each tag image is determined is compared, and determines the similarity of the tree structure of the two.
S305, target marker image is determined according to comparison result.
In some feasible embodiments, the unmanned plane can with if it is determined that the image that makes a return voyage tree structure and mark to be selected
Remember image tree structure similarity reach default similarity condition (such as similarity 90% and its more than), then the nothing
It is man-machine to determine that the tag image to be selected is target marker image.
For example, the tree structure of image and the tree structure phase of tag image f if comparison result expression is maked a return voyage
Like degree 99%, then the unmanned plane can determine that tag image f is target marker image.
In one embodiment, described that target marker image is determined according to comparison result, including:It is true according to comparison result
Make the first tag image;By the corresponding depth map of first tag image, depth map corresponding with the image that makes a return voyage is compared
Compared with;If comparison result matches between two width depth maps, using first tag image as target marker image.
In some feasible embodiments, which can obtain the first tag image using binocular vision system
The depth map of depth map and the image that makes a return voyage.
In one embodiment, described by the corresponding depth map of first tag image, depth corresponding with the image that makes a return voyage
Degree figure is compared, including:According to the corresponding depth map of first tag image and the corresponding depth of the image that makes a return voyage
Figure, obtains the relative pose information between two width depth maps;According to first tag image and the image that makes a return voyage, obtain
Relative rotational relationship between two images;The relative rotational relationship is compared with the relative pose information.
It should be noted that photographic device is when shooting above-mentioned two amplitude deepness image, it is possible due to shooting the difference of posture
Cause the depth information of the image content of two amplitude deepness images that there is difference, the difference of the depth information can be used as the two width figure
The relative rotational relationship of picture.
It should also be noted that, the relative pose information between first tag image and the image that makes a return voyage, Ke Yishi
Position when shooting the first tag image and posture, make a return voyage with shooting image when position and posture between difference.
For example, which can obtain two amplitude deepness image by binocular vision system, and solve two width depth
Spend relative pose information (including location information and the posture information, specifically, the location information may include rotation between image
Turn, which may include displacement).The unmanned plane can also obtain make a return voyage image and the first mark by Inertial Measurement Unit
Remember the relative rotational relationship of image, and the relative rotational relationship is matched with the relative pose information, if matched,
Then it can determine the location information of the first position according to the corresponding location information of the first tag image.
S306, according to described in make a return voyage image, the target marker image and with the associated position of the target marker image
Appearance information determines the location information of the first position.
S307, determine that the first position is the distance value to make a return voyage a little with the target in the path of making a return voyage.
It should be noted that it can refer to a little the point nearest apart from the first position that the target, which is maked a return voyage, alternatively, the target is returned
After destination can also be the unmanned plane according to path arrival first position of making a return voyage, it should which the next of arrival is maked a return voyage a little.
For example, the unmanned plane can according to make a return voyage a little 1 to make a return voyage a little 2 path of making a return voyage make a return voyage, make a return voyage a little 1 in arrival
(physical location may deviate this and make a return voyage a little 1, and physical location is indicated with first position) afterwards, it may be determined that arrival makes a return voyage a little 1, and leads to
The mode for crossing make a return voyage image and marker image match determines the accurate location of the first position, and determines the first position and return
The distance between destination 1 (i.e. target is maked a return voyage a little) value.
Again for example, the unmanned plane can also by way of make a return voyage image and marker image match, determine this
After the accurate location of one position, the first position is further determined that and a little the distance between 2 (i.e. target is maked a return voyage a little) value of making a return voyage.
S308, flight path is adjusted according to the distance value, so that the unmanned plane during flying makes a return voyage a little to the target.
It should be noted that the unmanned plane can correct current flight path according to the distance value, so that the unmanned plane
It may return to and make a return voyage on path, and according to the path flight of making a return voyage.
As it can be seen that in embodiments of the present invention, which can determine path of making a return voyage when losing positioning signal, and
When making a return voyage according to path of making a return voyage, acquisition is maked a return voyage image, determines the description information of the image that makes a return voyage, and by the description for the image that makes a return voyage
The description information of information and each tag image carries out similarity-rough set, and target marker image is determined according to comparison result, and
The position letter that the first position is determined according to the target marker image finally determines that the first position is maked a return voyage with target at a distance from a little
Value adjusts flight path according to the distance value, can pass through the side of make a return voyage image and marker image match during making a return voyage
Formula constantly corrects the position of unmanned plane, so that the unmanned plane can make a return voyage according to this, path is maked a return voyage, and realizes unmanned plane without fixed
Automatic precisely the making a return voyage when signal of position.
Referring to Fig. 5, being a kind of structural schematic diagram of unmanned plane provided in an embodiment of the present invention.Described in the present embodiment
Unmanned plane, including:Memory 501 and processor 502;
The memory 501, for storing program instruction;
The processor 502, the program instruction for executing memory storage are used when program instruction is performed
In:
When losing positioning signal, path of making a return voyage is determined according to the location information recorded;
When making a return voyage according to the path of making a return voyage, the image that makes a return voyage is acquired at first position;
The image that makes a return voyage is subjected to matching treatment with the tag image in image data base, and according to the knot of matching treatment
Fruit determines target marker image;
According to the image that makes a return voyage, the target marker image and with the associated posture information of the target marker image
Determine the location information of the first position;
Flight path is adjusted according to the location information of the first position and the path of making a return voyage.
In one embodiment, it is true according to the location information recorded when the processor 502 is used to lose positioning signal
Surely it makes a return voyage before path, is additionally operable to:
Described image database is generated, described image database includes multiple tag images and closed with the tag image
The posture information of connection.
In one embodiment, when the processor 502 generates image data base, it is specifically used for:
When the unmanned plane is according to positioning signal flight, tag image when record-setting flight and with when the flight
The associated posture information of tag image;
It tag image when according to the flight and is generated with the associated posture information of tag image when the flight
Image data base.
In one embodiment, the path of making a return voyage includes multiple location informations to make a return voyage a little;
The first position is to be less than the point of preset distance at a distance from a little with described make a return voyage.
In one embodiment, the path of making a return voyage refers to:The path of the unmanned plane planning;
The flight path refers to:The path of the unmanned plane practical flight.
In one embodiment, location information and the make a return voyage path of the processor 502 according to the first position
When adjusting flight path, it is specifically used for:
Determine that the first position is the distance value to make a return voyage a little with the target in the path of making a return voyage;
Flight path is adjusted according to the distance value, so that the unmanned plane during flying makes a return voyage a little to the target.
In one embodiment, the processor 502 by the tag image in make a return voyage image and the image data base into
Row matching treatment, and when determining target marker image according to the result of matching treatment, be specifically used for:
It makes a return voyage described in determination the description information of image;
It is associated according to each tag image recorded in the description information and image data base of the image that makes a return voyage
Description information carries out similarity-rough set;
Target marker image is determined according to comparison result, wherein the associated description information of the target marker image and institute
The description information for stating the image that makes a return voyage meets default similarity condition.
In one embodiment, it is specific to use when the processor 502 records each tag image associated description information
In:
The corresponding characteristics of image of each tag image is extracted, and determines the corresponding descriptor of described image feature;
Description information is generated according to the descriptor.
In one embodiment, when the processor 502 generates description information according to the descriptor, it is specifically used for:
Determine the corresponding weighted value of the descriptor;
Description information is generated according to the descriptor and the corresponding weighted value of the descriptor.
In one embodiment, it is specific to use when the processor 502 determines target marker image according to comparison result
In:
The first tag image is determined according to comparison result;
By the corresponding depth map of first tag image, depth map corresponding with the image that makes a return voyage is compared;
If comparison result matches between two width depth maps, using first tag image as target label figure
Picture.
In one embodiment, the processor 502 is by the corresponding depth map of first tag image, with the image that makes a return voyage
When corresponding depth map is compared, it is specifically used for:
According to the corresponding depth map of first tag image and the corresponding depth map of the image that makes a return voyage, two width are obtained
Relative pose information between depth map;
According to first tag image and the image that makes a return voyage, the relative rotational relationship between two images is obtained;
The relative rotational relationship is compared with the relative pose information.
In one embodiment, the processor 502 matches the image that makes a return voyage with the tag image recorded
When processing, it is specifically used for:
Matching treatment is carried out according to the image similarity to make a return voyage between image and the tag image recorded.
In one embodiment, the processor 502 is additionally operable to:
When making a return voyage according to the path of making a return voyage, the positioning signal is detected;
If detecting the positioning signal, maked a return voyage according to the positioning signal and the path of making a return voyage.
In one embodiment, the processor 502 is additionally operable to:
When making a return voyage according to the path of making a return voyage, the flying height of the unmanned plane is less than preset height.
In one embodiment, the preset height is less than 20 meters.
The embodiment of the present invention provides a kind of system.Fig. 6 is a kind of structural schematic diagram of system provided in an embodiment of the present invention.
As shown in fig. 6, the system includes:Photographic device 601 and unmanned plane 602.
Wherein, which is unmanned plane 602 disclosed in the embodiments of the present invention, and principle and realization method are equal
Similar to the above embodiments, details are not described herein again.
Wherein, which can be arranged on the unmanned plane 562, and marker bit is used for for being shot in flight
The tag image set and the image that makes a return voyage.
Specifically, photographic device 60 can be equipped on by holder or other carrying equipments in the main body of unmanned plane.Camera shooting dress
It sets for carrying out image or video capture, including but not limited to multi-spectral imager, EO-1 hyperion in the flight course of unmanned plane
Imager, Visible Light Camera and infrared camera, VO etc., and the photographic device can be one or more than one.Specifically,
Unmanned plane can be in flight, and real-time control photographic device shoots image.
Wherein, unmanned plane 602 can determine path of making a return voyage when losing positioning signal according to the location information recorded,
When making a return voyage according to the path of making a return voyage, at first position acquisition make a return voyage image, will this make a return voyage image in image data base
Tag image carries out matching treatment, and determines target marker image according to the result of matching treatment, according to the image that makes a return voyage, is somebody's turn to do
Target marker image and the location information that the first position is determined with the associated posture information of the target marker image, according to this
The location information of first position and the path adjustment flight path that makes a return voyage.
It should be noted that the unmanned plane 602 can be used for executing path method of adjustment shown in preceding method embodiment,
Specific implementation process can refer to this method embodiment, and therefore not to repeat here.
It should be noted that for each embodiment of the method above-mentioned, for simple description, therefore it is all expressed as to a system
The combination of actions of row, but those skilled in the art should understand that, the present invention is not limited by the described action sequence, because
For according to the present invention, certain some step can be performed in other orders or simultaneously.Secondly, those skilled in the art also should
Know, embodiment described in this description belongs to preferred embodiment, involved action and module not necessarily this hair
Necessary to bright.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium may include:Flash disk, read-only memory (Read-Only Memory, ROM), random access device (Random Access
Memory, RAM), disk or CD etc..
It is provided for the embodiments of the invention a kind of path method of adjustment above and unmanned plane is described in detail, herein
In apply specific case principle and implementation of the present invention are described, the explanation of above example is only intended to sides
Assistant solves the method and its core concept of the present invention;Meanwhile for those of ordinary skill in the art, think of according to the present invention
Think, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification should not be construed as pair
The limitation of the present invention.
Claims (30)
1. a kind of path method of adjustment, which is characterized in that it is applied to unmanned plane, the method includes:
When losing positioning signal, path of making a return voyage is determined according to the location information recorded;
When making a return voyage according to the path of making a return voyage, the image that makes a return voyage is acquired at first position;
The image that makes a return voyage is subjected to matching treatment with the tag image in image data base, and true according to the result of matching treatment
Make target marker image;
It is determined according to the image that makes a return voyage, the target marker image and with the associated posture information of the target marker image
The location information of the first position;
Flight path is adjusted according to the location information of the first position and the path of making a return voyage.
2. according to the method described in claim 1, it is characterized in that, when the loss positioning signal, according to the position recorded
Information determination is maked a return voyage before path, further includes:
Described image database is generated, described image database includes multiple tag images and associated with the tag image
Posture information.
3. according to the method described in claim 2, it is characterized in that, the generation image data base, including:
When the unmanned plane is according to positioning signal flight, tag image when record-setting flight and with the label when flight
The associated posture information of image;
Tag image when according to the flight and generate image with the associated posture information of tag image when the flight
Database.
4. according to claim 1-3 any one of them methods, which is characterized in that the path of making a return voyage includes multiple makes a return voyage a little
Location information;
The first position is to be less than the point of preset distance at a distance from a little with described make a return voyage.
5. according to the method described in claim 4, it is characterized in that, the path of making a return voyage refers to:The road of the unmanned plane planning
Diameter;
The flight path refers to:The path of the unmanned plane practical flight.
6. according to the method described in claim 1, it is characterized in that, the location information according to the first position and described
Make a return voyage path adjustment flight path, including:
Determine that the first position is the distance value to make a return voyage a little with the target in the path of making a return voyage;
Flight path is adjusted according to the distance value, so that the unmanned plane during flying makes a return voyage a little to the target.
7. according to the method described in claim 1, it is characterized in that, described by image and the mark in image data base of making a return voyage
Remember that image carries out matching treatment, and target marker image is determined according to the result of matching treatment, including:
It makes a return voyage described in determination the description information of image;
According to the associated description of each tag image recorded in the description information and image data base of the image that makes a return voyage
Information carries out similarity-rough set;
Target marker image is determined according to comparison result, wherein the associated description information of the target marker image is returned with described
The description information of chart picture, which meets, presets similarity condition.
8. the method according to the description of claim 7 is characterized in that record the associated description information of each tag image, including:
The corresponding characteristics of image of each tag image is extracted, and determines the corresponding descriptor of described image feature;
Description information is generated according to the descriptor.
9. according to the method described in claim 8, it is characterized in that, it is described according to the descriptor generate description information, including:
Determine the corresponding weighted value of the descriptor;
Description information is generated according to the descriptor and the corresponding weighted value of the descriptor.
10. the method according to the description of claim 7 is characterized in that described determine target marker image according to comparison result,
Including:
The first tag image is determined according to comparison result;
By the corresponding depth map of first tag image, depth map corresponding with the image that makes a return voyage is compared;
If comparison result matches between two width depth maps, using first tag image as target marker image.
11. according to the method described in claim 10, it is characterized in that, described by the corresponding depth of first tag image
Figure, depth map corresponding with the image that makes a return voyage are compared, including:
According to the corresponding depth map of first tag image and the corresponding depth map of the image that makes a return voyage, two width depth are obtained
Relative pose information between figure;
According to first tag image and the image that makes a return voyage, the relative rotational relationship between two images is obtained;
The relative rotational relationship is compared with the relative pose information.
12. according to claim 1-11 any one of them methods, which is characterized in that it is described by it is described make a return voyage image with recorded
Tag image carry out matching treatment, including:
Matching treatment is carried out according to the image similarity to make a return voyage between image and the tag image recorded.
13. according to the method for claim 12, which is characterized in that the method further includes:
When making a return voyage according to the path of making a return voyage, the positioning signal is detected;
If detecting the positioning signal, maked a return voyage according to the positioning signal and the path of making a return voyage.
14. according to the method described in claim 1-11, which is characterized in that the unmanned plane makes a return voyage according to the path of making a return voyage
When, the flying height of the unmanned plane is less than preset height.
15. according to the method described in claim 1-11, which is characterized in that the preset height is less than 20 meters.
16. a kind of unmanned plane, which is characterized in that including:Memory and processor;
The memory, for storing program instruction;
The processor, the program instruction for executing memory storage are used for when program instruction is performed:
When losing positioning signal, path of making a return voyage is determined according to the location information recorded;
When making a return voyage according to the path of making a return voyage, the image that makes a return voyage is acquired at first position;
The image that makes a return voyage is subjected to matching treatment with the tag image in image data base, and true according to the result of matching treatment
Make target marker image;
It is determined according to the image that makes a return voyage, the target marker image and with the associated posture information of the target marker image
The location information of the first position;
Flight path is adjusted according to the location information of the first position and the path of making a return voyage.
17. unmanned plane according to claim 16, which is characterized in that when the processor is used to lose positioning signal, root
Before determining path of making a return voyage according to the location information recorded, it is additionally operable to:
Described image database is generated, described image database includes multiple tag images and associated with the tag image
Posture information.
18. unmanned plane according to claim 17, which is characterized in that when the processor generates image data base, specifically
For:
When the unmanned plane is according to positioning signal flight, tag image when record-setting flight and with the label when flight
The associated posture information of image;
Tag image when according to the flight and generate image with the associated posture information of tag image when the flight
Database.
19. according to claim 16-18 any one of them unmanned planes, which is characterized in that the path of making a return voyage includes multiple returns
The location information of destination;
The first position is to be less than the point of preset distance at a distance from a little with described make a return voyage.
20. unmanned plane according to claim 19, which is characterized in that the path of making a return voyage refers to:The unmanned plane planning
Path;
The flight path refers to:The path of the unmanned plane practical flight.
21. the unmanned plane according to claim 19 or 20, which is characterized in that the processor is according to the first position
When location information and the path of making a return voyage adjust flight path, it is specifically used for:
Determine that the first position is the distance value to make a return voyage a little with the target in the path of making a return voyage;
Flight path is adjusted according to the distance value, so that the unmanned plane during flying makes a return voyage a little to the target.
22. unmanned plane according to claim 16, which is characterized in that the processor is by image and the picture number of making a return voyage
It is specific to use when carrying out matching treatment according to the tag image in library, and target marker image is determined according to the result of matching treatment
In:
It makes a return voyage described in determination the description information of image;
According to the associated description of each tag image recorded in the description information and image data base of the image that makes a return voyage
Information carries out similarity-rough set;
Target marker image is determined according to comparison result, wherein the associated description information of the target marker image is returned with described
The description information of chart picture, which meets, presets similarity condition.
23. unmanned plane according to claim 22, which is characterized in that it is associated that the processor records each tag image
When description information, it is specifically used for:
The corresponding characteristics of image of each tag image is extracted, and determines the corresponding descriptor of described image feature;
Description information is generated according to the descriptor.
24. unmanned plane according to claim 23, which is characterized in that the processor is generated according to the descriptor and described
When information, it is specifically used for:
Determine the corresponding weighted value of the descriptor;
Description information is generated according to the descriptor and the corresponding weighted value of the descriptor.
25. unmanned plane according to claim 22, which is characterized in that the processor determines target according to comparison result
When tag image, it is specifically used for:
The first tag image is determined according to comparison result;
By the corresponding depth map of first tag image, depth map corresponding with the image that makes a return voyage is compared;
If comparison result matches between two width depth maps, using first tag image as target marker image.
26. unmanned plane according to claim 25, which is characterized in that the processor corresponds to first tag image
Depth map be specifically used for when depth map corresponding with the image that makes a return voyage is compared:
According to the corresponding depth map of first tag image and the corresponding depth map of the image that makes a return voyage, two width depth are obtained
Relative pose information between figure;
According to first tag image and the image that makes a return voyage, the relative rotational relationship between two images is obtained;
The relative rotational relationship is compared with the relative pose information.
27. according to claim 16-26 any one of them unmanned planes, which is characterized in that the processor is by the figure that makes a return voyage
When as carrying out matching treatment with the tag image recorded, it is specifically used for:
Matching treatment is carried out according to the image similarity to make a return voyage between image and the tag image recorded.
28. unmanned plane according to claim 27, which is characterized in that the processor is additionally operable to:
When making a return voyage according to the path of making a return voyage, the positioning signal is detected;
If detecting the positioning signal, maked a return voyage according to the positioning signal and the path of making a return voyage.
29. according to the unmanned plane described in claim 16-26, which is characterized in that the processor is additionally operable to:
When making a return voyage according to the path of making a return voyage, the flying height of the unmanned plane is less than preset height.
30. according to the unmanned plane described in claim 16-26, which is characterized in that the preset height is less than 20 meters.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2017/103808 WO2019061111A1 (en) | 2017-09-27 | 2017-09-27 | Path adjustment method and unmanned aerial vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108700892A true CN108700892A (en) | 2018-10-23 |
Family
ID=63843838
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201780009908.0A Pending CN108700892A (en) | 2017-09-27 | 2017-09-27 | A kind of path method of adjustment and unmanned plane |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108700892A (en) |
| WO (1) | WO2019061111A1 (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111352434A (en) * | 2018-12-20 | 2020-06-30 | 波音公司 | Apparatus and method for supporting an aircraft approaching an airport runway at an airport |
| CN111367266A (en) * | 2020-03-12 | 2020-07-03 | 北京三快在线科技有限公司 | Unmanned equipment route adjusting method and device and unmanned equipment system |
| WO2021078167A1 (en) * | 2019-10-21 | 2021-04-29 | 深圳市道通智能航空技术有限公司 | Aerial vehicle return control method and apparatus, aerial vehicle, and storage medium |
| CN112783208A (en) * | 2020-12-31 | 2021-05-11 | 广州极飞科技股份有限公司 | Unmanned equipment return control method and device and unmanned equipment |
| WO2022016534A1 (en) * | 2020-07-24 | 2022-01-27 | 深圳市大疆创新科技有限公司 | Flight control method of unmanned aerial vehicle and unmanned aerial vehicle |
| CN113985910A (en) * | 2021-09-09 | 2022-01-28 | 常州希米智能科技有限公司 | Unmanned aerial vehicle control method and system combining mobile network and satellite positioning |
| CN115409437A (en) * | 2022-11-03 | 2022-11-29 | 成都沃飞天驭科技有限公司 | Low-altitude flight emergency processing method and device, aircraft and storage medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114442672A (en) * | 2022-02-16 | 2022-05-06 | 中国电子科技集团公司第五十四研究所 | Full-autonomous cruising method of unmanned aerial vehicle |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN106027896A (en) * | 2016-06-20 | 2016-10-12 | 零度智控（北京）智能科技有限公司 | Video photographing control device and method, and unmanned aerial vehicle |
| JP6020872B1 (en) * | 2016-06-24 | 2016-11-02 | 株式会社アドインテ | Analysis system and analysis method |
| CN106774402A (en) * | 2016-12-28 | 2017-05-31 | 湖南省道通科技有限公司 | The method and device positioned to unmanned plane |
| CN106774404A (en) * | 2016-12-29 | 2017-05-31 | 哈密创动科技有限公司 | The control method of making a return voyage of unmanned plane, device and unmanned plane |
| CN106873619A (en) * | 2017-01-23 | 2017-06-20 | 上海交通大学 | A kind of processing method in unmanned plane during flying path |
| CN107077153A (en) * | 2017-01-22 | 2017-08-18 | 深圳市大疆创新科技有限公司 | Control method, control system and the movable fixture of movable fixture |
| CN107065925A (en) * | 2017-04-01 | 2017-08-18 | 成都通甲优博科技有限责任公司 | A kind of unmanned plane makes a return voyage method and device |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105302043B (en) * | 2015-11-17 | 2019-02-22 | 重庆国飞通用航空设备制造有限公司 | A kind of method of controlling security of unmanned plane |
| US20170233071A1 (en) * | 2016-02-15 | 2017-08-17 | Skyyfish, LLC | System and Method for Return-Home Command in Manual Flight Control |
| CN105867181A (en) * | 2016-04-01 | 2016-08-17 | 腾讯科技（深圳）有限公司 | Control method and apparatus of unmanned aerial vehicle |
| CN105786018B (en) * | 2016-04-19 | 2018-10-02 | 清远市巨劲科技有限公司 | A kind of unmanned plane automatic make a return voyage laser orientation system, unmanned plane |
| CN105955291B (en) * | 2016-04-29 | 2021-04-27 | 深圳市哈博森科技有限公司 | Unmanned aerial vehicle flight route track recording and automatic flight control mode |
| CN106352872B (en) * | 2016-09-14 | 2019-11-08 | 北京理工大学 | A kind of unmanned plane autonomous navigation system and its air navigation aid |
| CN106527481A (en) * | 2016-12-06 | 2017-03-22 | 重庆零度智控智能科技有限公司 | Unmanned aerial vehicle flight control method, device and unmanned aerial vehicle |
-
2017
- 2017-09-27 CN CN201780009908.0A patent/CN108700892A/en active Pending
- 2017-09-27 WO PCT/CN2017/103808 patent/WO2019061111A1/en active Application Filing
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN106027896A (en) * | 2016-06-20 | 2016-10-12 | 零度智控（北京）智能科技有限公司 | Video photographing control device and method, and unmanned aerial vehicle |
| JP6020872B1 (en) * | 2016-06-24 | 2016-11-02 | 株式会社アドインテ | Analysis system and analysis method |
| CN106774402A (en) * | 2016-12-28 | 2017-05-31 | 湖南省道通科技有限公司 | The method and device positioned to unmanned plane |
| CN106774404A (en) * | 2016-12-29 | 2017-05-31 | 哈密创动科技有限公司 | The control method of making a return voyage of unmanned plane, device and unmanned plane |
| CN107077153A (en) * | 2017-01-22 | 2017-08-18 | 深圳市大疆创新科技有限公司 | Control method, control system and the movable fixture of movable fixture |
| CN106873619A (en) * | 2017-01-23 | 2017-06-20 | 上海交通大学 | A kind of processing method in unmanned plane during flying path |
| CN107065925A (en) * | 2017-04-01 | 2017-08-18 | 成都通甲优博科技有限责任公司 | A kind of unmanned plane makes a return voyage method and device |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111352434A (en) * | 2018-12-20 | 2020-06-30 | 波音公司 | Apparatus and method for supporting an aircraft approaching an airport runway at an airport |
| CN111352434B (en) * | 2018-12-20 | 2023-11-28 | 波音公司 | Device and method for supporting aircraft approaching airport runway of airport |
| WO2021078167A1 (en) * | 2019-10-21 | 2021-04-29 | 深圳市道通智能航空技术有限公司 | Aerial vehicle return control method and apparatus, aerial vehicle, and storage medium |
| CN111367266A (en) * | 2020-03-12 | 2020-07-03 | 北京三快在线科技有限公司 | Unmanned equipment route adjusting method and device and unmanned equipment system |
| WO2022016534A1 (en) * | 2020-07-24 | 2022-01-27 | 深圳市大疆创新科技有限公司 | Flight control method of unmanned aerial vehicle and unmanned aerial vehicle |
| CN112783208A (en) * | 2020-12-31 | 2021-05-11 | 广州极飞科技股份有限公司 | Unmanned equipment return control method and device and unmanned equipment |
| CN113985910A (en) * | 2021-09-09 | 2022-01-28 | 常州希米智能科技有限公司 | Unmanned aerial vehicle control method and system combining mobile network and satellite positioning |
| CN113985910B (en) * | 2021-09-09 | 2023-07-18 | 常州希米智能科技有限公司 | Unmanned aerial vehicle control method and system combining mobile network and satellite positioning |
| CN115409437A (en) * | 2022-11-03 | 2022-11-29 | 成都沃飞天驭科技有限公司 | Low-altitude flight emergency processing method and device, aircraft and storage medium |
| CN115409437B (en) * | 2022-11-03 | 2023-03-24 | 成都沃飞天驭科技有限公司 | Low-altitude flight emergency processing method and device, aircraft and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019061111A1 (en) | 2019-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108700892A (en) | A kind of path method of adjustment and unmanned plane | |
| Cesetti et al. | A vision-based guidance system for UAV navigation and safe landing using natural landmarks | |
| CN106989746A (en) | Air navigation aid and guider | |
| EP2818957A1 (en) | System and method for UAV landing | |
| CN110136199A (en) | A kind of vehicle location based on camera, the method and apparatus for building figure | |
| CN108303103A (en) | The determination method and apparatus in target track | |
| CN108700890A (en) | Unmanned plane makes a return voyage control method, unmanned plane and machine readable storage medium | |
| CN109791414A (en) | The method and system that view-based access control model lands | |
| CN109084786A (en) | A kind of processing method of map datum | |
| CN115861860B (en) | Target tracking and positioning method and system for unmanned aerial vehicle | |
| CN111812978B (en) | Cooperative SLAM method and system for multiple unmanned aerial vehicles | |
| US10935938B1 (en) | Learning from operator data for practical autonomy | |
| US9892340B2 (en) | Method for classifying objects in an imaging surveillance system | |
| Pluckter et al. | Precision UAV landing in unstructured environments | |
| CN117036989A (en) | Miniature unmanned aerial vehicle target recognition and tracking control method based on computer vision | |
| Ching et al. | Ultra-wideband localization and deep-learning-based plant monitoring using micro air vehicles | |
| CN112130577A (en) | Path planning method and device for unmanned flight equipment, unmanned flight equipment and storage medium | |
| CN109283942A (en) | For controlling the flying method and device that unmanned plane is tracked | |
| CN109283933A (en) | The control method and device that unmanned plane follows | |
| CN109472258A (en) | Tracking and device | |
| CN109240319A (en) | The method and device followed for controlling unmanned plane | |
| CN112487889A (en) | Unmanned aerial vehicle ground detection method and system based on deep neural network | |
| Shen et al. | A benchmark for vision-based multi-UAV multi-object tracking | |
| CN109240318A (en) | For controlling the method and device of unmanned plane during flying | |
| CN109901589A (en) | Mobile robot control method and apparatus |
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 |