CN108702448A - Unmanned plane image-pickup method and unmanned plane - Google Patents
Unmanned plane image-pickup method and unmanned plane Download PDFInfo
- Publication number
- CN108702448A CN108702448A CN201780010140.9A CN201780010140A CN108702448A CN 108702448 A CN108702448 A CN 108702448A CN 201780010140 A CN201780010140 A CN 201780010140A CN 108702448 A CN108702448 A CN 108702448A
- Authority
- CN
- China
- Prior art keywords
- reference object
- target reference
- image
- present image
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 74
- 230000008859 change Effects 0.000 claims description 45
- 238000004458 analytical method Methods 0.000 claims description 23
- 238000005259 measurement Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 8
- 230000000694 effects Effects 0.000 description 26
- 238000010586 diagram Methods 0.000 description 21
- 239000000203 mixture Substances 0.000 description 20
- 238000003384 imaging method Methods 0.000 description 9
- 230000001133 acceleration Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 6
- 238000013527 convolutional neural network Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005183 dynamical system Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000059 patterning Methods 0.000 description 2
- 238000004801 process automation Methods 0.000 description 2
- 230000003416 augmentation Effects 0.000 description 1
- 230000003139 buffering effect Effects 0.000 description 1
- 238000000701 chemical imaging Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000005304 joining Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000009987 spinning Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/64—Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Studio Devices (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the present application provides a kind of unmanned plane image-pickup method and unmanned plane, wherein this method includes:Reception is taken off instruction;It obtains target reference object and preserves the feature of the target reference object;According to target reference object described in the signature tracking of the target reference object, present image is obtained;Wherein, the present image includes target reference object;Analyze position of the target reference object in the present image, if position of the target reference object in the present image meets Image Acquisition condition, then acquire image, realize that unmanned plane is taken pictures the automation of process, it is manually operated without user, it provides diversified selection to the user, promotes user experience.
Description
This patent document disclosure includes material protected by copyright.The copyright is all for copyright holder.Copyright
Owner do not oppose the patent document in the presence of anyone replicates the proce's-verbal of Patent&Trademark Office and archives or this specially
Profit discloses.
Technical field
This application involves unmanned plane field more particularly to unmanned plane image-pickup method unmanned planes.
Background technology
In unmanned plane application, occur a series of self-timer unmanned plane on the market, it is small around fast taking pictures and recording
Video is shared for sending out the social softwares such as circle of friends, microblogging.But the shooting process of unmanned plane all compares in the prior art
It is cumbersome, it is necessary first to which that user's control is taken off, then the position progress of unmanned plane is adjusted by remote controler or application program
Then composition could take pictures, if the dissatisfied effect of taking pictures of user after having clapped, need to continue to operate aircraft to other positions
It sets, composition is taken pictures again.Such process automation degree of taking pictures is not high, and user needs to input many operations, and aircraft can not
Diversified selection is provided.
Invention content
In view of this, this application provides a kind of unmanned plane image-pickup method and unmanned plane, the bat of unmanned plane can be made
According to process automation, it is manually operated without user, provides diversified selection to the user.
The embodiment of the present application first aspect provides a kind of unmanned plane image-pickup method, including:
Reception is taken off instruction;
It obtains target reference object and preserves the feature of the target reference object;
According to target reference object described in the signature tracking of the target reference object, present image is obtained;Wherein, described
Present image includes target reference object;
Position of the target reference object in the present image is analyzed, if the target reference object is worked as described
Position in preceding image meets Image Acquisition condition, then acquires image.
The embodiment of the present application second aspect provides a kind of unmanned plane, including:
Memory, for storing unmanned plane image acquisition procedure;
Processor, for calling the unmanned plane image acquisition procedure in the memory and executing:
Reception is taken off instruction;
It obtains target reference object and preserves the feature of the target reference object;
According to target reference object described in the signature tracking of the target reference object, present image is obtained;Wherein, described
Present image includes target reference object;
Position of the target reference object in the present image is analyzed, if the target reference object is worked as described
Position in preceding image meets Image Acquisition condition, then acquires image.
The embodiment of the present application third aspect provides a kind of computer readable storage medium, is stored thereon with computer journey
Sequence, the computer program execute the unmanned plane Image Acquisition side of the embodiment of the present application first aspect offer when being executed by processor
Method.
Unmanned plane image-pickup method unmanned plane provided by the embodiments of the present application, by receiving instruction of taking off;Obtain target
Reference object and the feature for preserving the target reference object;It is clapped according to target described in the signature tracking of the target reference object
Object is taken the photograph, present image is obtained;Wherein, the present image includes target reference object;The target reference object is analyzed to exist
Position in the present image, if position of the target reference object in the present image meets Image Acquisition item
Part, then acquire image, and whether automatically track target reference object is simultaneously full according to the position judgment of target reference object in the picture
The condition taken pictures enough realizes unmanned plane and takes pictures the automation of process, promotes user experience.
Description of the drawings
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, below will be to institute in embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the present invention
Example, for those of ordinary skill in the art, without creative efforts, can also obtain according to these attached drawings
Obtain other attached drawings.
Fig. 1 is a kind of structure chart of unmanned plane provided by the embodiments of the present application;
Fig. 2 is a kind of unmanned plane image-pickup method flow diagram provided by the embodiments of the present application;
Fig. 3 is a kind of unmanned plane takeoff method flow diagram provided by the embodiments of the present application;
Fig. 4 is another unmanned plane takeoff method flow diagram provided by the embodiments of the present application;
Fig. 5 is a kind of unmanned plane image-pickup method flow diagram that another embodiment of the application provides;
Fig. 6 is the distance between unmanned plane provided by the embodiments of the present application and target reference object schematic diagram;
Fig. 7 is adjustment provided by the embodiments of the present application apart from effect diagram;
Fig. 8 is adjustment course angle effect diagram provided by the embodiments of the present application;
Fig. 9 is adjustment pitch angle effect diagram provided by the embodiments of the present application;
Figure 10 is overlapping image schematic diagram provided by the embodiments of the present application;
Figure 11 is image split-joint method flow diagram provided by the embodiments of the present application;
Relative position schematic diagrames of the Figure 12 between unmanned plane provided by the embodiments of the present application and target reference object;
Figure 13 is a kind of unmanned plane structural schematic diagram provided by the embodiments of the present application;
Figure 14 is a kind of command reception module structural schematic diagram provided by the embodiments of the present application;
Figure 15 is another command reception module structural schematic diagram provided by the embodiments of the present application;
Figure 16 is a kind of analysis acquisition module structural schematic diagram provided by the embodiments of the present application;
Figure 17 is a kind of unmanned plane structural schematic diagram that another embodiment of the application provides;
Figure 18 is a kind of unmanned plane structural schematic diagram that another embodiment of the application provides;
Figure 19 is a kind of unmanned plane structural schematic diagram that another embodiment of the application provides;
Figure 20 is a kind of unmanned plane structural schematic diagram that another embodiment of the application provides.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, to applying for that it is clear, complete that the technical solution in bright embodiment carries out
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
The embodiment of the present application provides a kind of unmanned plane, and Fig. 1 is a kind of structure chart of unmanned plane provided in an embodiment of the present invention.
As shown in Figure 1, the unmanned plane in the present embodiment, may include:
Fuselage 110;
Dynamical system 120 on fuselage, for providing flying power;
Holder 130 and imaging device 140, imaging device 140 are equipped on by holder 130 on the fuselage 110 of unmanned plane.
Imaging device 140 is used to carry out image or video capture, including but not limited to multispectral imaging in the flight course of unmanned plane
Instrument, hyperspectral imager, Visible Light Camera and infrared camera etc., holder 130 are spinning transmission and stability augmentation system, and horizontal stage electric machine is logical
The rotational angle of toning turn over moving axis compensates the shooting angle of imaging device 140, and passes through and buffering appropriate is arranged
Mechanism prevents or reduces the shake of imaging device 140.
Next unmanned plane image-pickup method provided by the embodiments of the present application is introduced in conjunction with Fig. 2-12.
Referring initially to Fig. 2.Fig. 2 is unmanned plane image-pickup method flow diagram provided by the embodiments of the present application.Such as
Shown in Fig. 2, unmanned plane image-pickup method at least may include following steps:
S201:Reception is taken off instruction.
Specifically, instruction of taking off can be that user passes through the instruction of taking off with the matched control terminal input of unmanned plane.Its
In, the mode for inputting instruction of taking off can be that user inputs instruction of taking off by the control-rod in control terminal, can also be use
The button that takes off on the control panel that family passes through control terminal inputs instruction of taking off, and can also be and inputs phonetic order by user
Instruction of taking off is inputted, can also be and input instruction of taking off by way of losing face, can also be and inputted by way of throwing and flying
Fly instruction.
Specifically, the method that instruction of taking off is inputted by way of losing face includes at least following steps, such as Fig. 3 institutes
Show:
S2011:Receive the instruction that triggering is taken off.
Specifically, it can be the power button on user's double-click or long-press unmanned plane to trigger the instruction taken off, and triggered
Winged instruction can also be user's double-click or long-press and the power button etc. in the matched control terminal of unmanned plane.
S2013:Search for target image.
Specifically, after receiving the instruction that triggering is taken off, holder 130 controls imaging device 140 and searches for mesh in picture
Logo image.Imaging device 140 specifically can be controlled by the course angle or pitch angle for changing holder 130 and search for mesh in picture
Logo image.
S2015:When target image is matched with pre-set image, unmanned plane is made to generate lift.
Specifically, pre-set image can be the image that user is pre-stored in the memory of unmanned plane, which can be with
It is the face image of user or other images.Target image is searched in picture when imaging device 140 to protect in advance with user
When the pre-set image matching deposited, the dynamical system 120 for controlling unmanned plane generates lift.
Specifically, when the similarity of target image and pre-set image is more than certain threshold value, it is believed that be the target image
It is matched with pre-set image.Wherein, which for example can be 80%, 90%, 95%, 100% etc..
In addition, the method for inputting instruction of taking off by way of throwing and flying includes at least following steps, as shown in Figure 4:
S2017:Detect the variation of the Inertial Measurement Unit data of unmanned plane.
Specifically, user holds unmanned plane and dishes out outward, and the inertia that unmanned plane detects unmanned plane during movement is surveyed
Measure the variation of cell data.Inertial Measurement Unit (Inertial measurement unit, IMU) contain three it is uniaxial
Accelerometer and three uniaxial gyroscopes, accelerometer detection object found the acceleration letter of three axis in carrier coordinate system unification and independence
Number, and angular velocity signal of the gyroscope detection carrier relative to navigational coordinate system, measure the angular speed of object in three dimensions
And acceleration, and calculate with this posture of object.In a kind of concrete implementation mode, IMU is in for measuring unmanned plane
The level inclination and acceleration generated when current flight position.
S2019:If the variation of Inertial Measurement Unit data meets the first preset condition, unmanned plane is made to generate lift.
Specifically, the first preset condition can be that the level inclination of unmanned plane is no more than the first range, and acceleration is more than
Second range.Wherein, level inclination is no more than the first range and is used to determine whether unmanned plane is to keep flat to throw upwards, the first range
Such as can be spent from -30 to 30 degree of interval range.Acceleration is for determining whether unmanned plane is tossed control, the second model
Enclose for example can be from -0.6g to -1.2g (wherein g be acceleration of gravity) interval range.
In certain specifically realization method, IMU, which can be also used for detecting other, can reflect that unmanned plane was spilled over flies
Row parameter, the first preset condition also can also be the range about other flight parameters, and the first range and the second range can also
It is other rational ranges, is not limited herein.
S203:It obtains target reference object and preserves the feature of target reference object.
Specifically, target reference object can be the reference object of user's manual setting, can also be that unmanned plane is taking off
During the reference object in the picture that searches, determine the feature that target reference object is extracted after reference object,
In, the algorithm for extracting feature can be convolutional neural networks (Convolutional Neural Network, CNN) scheduling algorithm.
It is appreciated that the sequencing of S201 and S203 does not limit herein.Can be will after unmanned plane takes off
Reference object in picture can also be user elder generation manual setting target reference object before take-off as target reference object,
Unmanned plane is controlled again to take off.
S205:According to the signature tracking target reference object of target reference object, present image is obtained.
Specifically, unmanned plane passes through the signature tracking of the target reference object of the preservation target reference object.Present image
Including target reference object, i.e., the current picture that is arrived by 140 preview of imaging device.
S207:Position of the target reference object in present image is analyzed, if target reference object is in present image
Position meets Image Acquisition condition, then acquires image.
Specifically, unmanned plane can automatically analyze position of the target reference object in present image, when target shooting pair
Image is then acquired when meeting Image Acquisition condition as the position in present image.
Specifically, unmanned plane can obtain present image, and current image date is uploaded to server, server according to
Position of the data analysis target reference object that unmanned plane uploads in present image, when target reference object is in present image
Position when meeting Image Acquisition condition, server sends image capture instruction to unmanned plane, and unmanned plane is receiving server
After the image capture instruction of transmission, image is acquired.
Wherein, Image Acquisition condition can be determined according to mode of composition.Different mode of composition Image Acquisition conditions is different,
The image finally collected may include multiple images under a variety of modes of composition, this application provides a variety of modes of composition,
Refer to the description of subsequent embodiment.
In another realization method, judge that position of the target reference object in present image meets Image Acquisition
After condition, further determine whether that receive the image capture instruction that user sends out acquires if receiving image capture instruction
Image.
Wherein, image capture instruction can be some specific gesture instruction or phonetic order that user sends out, and accuse
Know that no aircraft can start to take pictures, pose before taking pictures convenient for user, obtains more ideal photo.The gesture instruction
Or phonetic order is pre-stored in the storage device of unmanned plane.It is appreciated that image capture instruction sends out mode
It is not limited to the gesture instruction or phonetic order that user sends out, there can also be other realization sides in actual use
Formula is not limited herein.
In addition, after judging that position of the target reference object in present image meets Image Acquisition condition, Yong Hufa
Go out before image capture instruction, unmanned plane can also issue the user with signal, inform that user currently meets Image Acquisition condition, allow
User can be promptly and accurately send out image capture instruction.Wherein, what unmanned plane issued the user with meets the letter of Image Acquisition condition
It number can be to be sent out by some signal lamp on unmanned plane, such as can be by making the signal lamp be lighted with specific frequency
To send out signal.Certainly, the main body for sending out signal is not limited to signal lamp, the mode for the signal that signal lamp is sent out be also not necessarily limited to be
The frequency lighted can also have other realization methods, not be limited herein in actual use.
The embodiment of the present application is taken off by control unmanned plane and obtains target reference object, and target reference object is tracked, point
It analyses whether position of the target reference object in present image meets Image Acquisition condition, image is acquired if meeting condition.It is real
Existing unmanned plane is taken pictures the automation of process, is manually operated without user, is provided diversified selection to the user, promotes user's body
It tests.
In another embodiment, present image further includes background image.After S205, before S207, such as Fig. 5 institutes
Show, unmanned plane image-pickup method can also include:
S206:Change position of the target reference object in present image.
Specifically, can be existed to change target reference object by changing the distance between unmanned plane and target reference object
Position in present image.Wherein, the distance between unmanned plane and target reference object include horizontal distance and vertical range.Tool
Body is as shown in Figure 6.Specifically, the vertical range h between unmanned plane and target reference object can be from the inertial navigation of unmanned plane
System inertia navigation system (Inertial Navigation System, INS) obtains, between unmanned plane and target reference object
Horizontal distance s can be obtained according to h and θ, s=h*tan θ, wherein θ can also be obtained according to the INS of unmanned plane the angle letter
Breath.
Specifically, can also worked as to change target reference object by the course angle and/or pitch angle for changing unmanned plane
Position in preceding image, or change mesh by changing course angle and/or the pitch angle of the holder 130 being mounted on unmanned plane
Mark position of the reference object in present image.
Change target reference object it should be noted that different patterning schemes can correspond to different modes and scheme currently
Position as in.Each patterning scheme can correspond to various ways and change target reference object in present image
Position.
In one possible implementation, target can be changed by adjusting with the distance between target reference object
Position of the reference object in present image.Specifically, the distance between unmanned plane and target reference object include horizontal distance
And vertical range.By adjusting the vertical range between target reference object, the effect of final collected picture can be adjusted
Fruit.Such as when smaller with the vertical range of target reference object, the effect for facing upward bat can be built, when with target reference object
Between vertical range when gradually increasing, the flat effect clapped and taken a crane shot can be built.User, which can pre-set, to be wanted to obtain
Shooting effect, unmanned plane during taking pictures auto composition to meet the needs of user setting.It can also be unmanned plane certainly
Picture under the dynamic various effects of shooting meets the diversified demand of user for selection by the user.It is adjusting and target shooting pair
After vertical range as between, the horizontal distance between target reference object is further adjusted.It adjusts and target shooting pair
Horizontal distance as between can change the ratio of target reference object and current image, such as when horizontal distance is closer, can
With collect user half body shine, when horizontal distance farther out when, can collect user whole body shine.As shown in Figure 7.
When being patterned according to classical mode of composition, such as it can be three points in a kind of concrete implementation mode
Composition method, nine grids composition method, position that can be by adjusting target reference object in present image, by target reference object
It is placed in entertaining center;Wherein, three parts are divided by current picture is horizontal and vertical, the infall of lines is entertaining center.
In addition, in concrete implementation, it can also be according to other classical mode of composition such as diagonal line composition methods or gold spiral shell
Rotation composition method etc. is patterned.
Further, in the realization method of another possibility, when meeting the with the distance between target reference object
After two preset conditions, i.e., after having adjusted at a distance between target reference object, unmanned plane or holder can also be changed again
130 course angle and/or pitch angle, to adjust position of the target reference object in present image.Wherein, the second preset condition
Can be the distance between the target reference object determined according to the pre-set shooting effect that goes for of user, second
Preset condition can also be that the various shooting effects that are obtained automatically according to unmanned plane determine between target reference object away from
From.Such as left and right position of the target reference object in current image can be changed when adjusting course angle, as shown in figure 8, working as
Upper and lower position etc. of the target reference object in current image can be changed when adjusting pitch angle, as shown in Figure 9.Likewise, with
Family can with it is pre-set it is final go for effect of taking pictures, unmanned plane during taking pictures auto composition to meet user setting
Demand.It can also be that unmanned plane automatically snaps the picture under various effects, for selection by the user, meet the diversified need of user
It asks.
In addition, in the realization method of another possibility, when position of the target reference object in present image meets
Image Acquisition condition then acquires at least two images;Wherein, the coincidence factor between adjacent two images is located in preset range;
If judging, position of the target reference object in present image meets Image Acquisition condition, after acquiring at least two images,
Splice above-mentioned at least two images.As shown in Figure 10.The part that image 1 is overlapped with image 2 is overlapping region, which accounts for
The ratio of whole image is coincidence factor.
Specifically, the preset range of the coincidence factor between the two images that are connected for example can be 20% to 30%.
Specifically, after adjusting at a distance between target reference object (including horizontal distance and vertical range), lead to
Course angle is overregulated to obtain multiple image, and the coincidence factor between adjacent two images can be controlled by the size of course angle
System.After obtaining several and meeting the image of coincidence factor, the matching of characteristic point is carried out in the overlapping region of these adjacent images,
Then it carries out bundle adjustment (Bundle Adjustment, BA) to optimize so that the relative position between image is more accurate, so
Compensation is exposed to image afterwards, finds splicing line, finally by deformation process, be projected as an image can to it is above-mentioned several
Image is spliced.Specific joining method is as shown in figure 11.The shooting angle of unmanned plane can be expanded using the stitching algorithm,
It provides a kind of broader shooting visual angle to the user, while overcoming the slow technology of taking pictures of panorama in the prior art and asking
Topic, provides a kind of more quick panorama photographic method.
In another embodiment, after S205, before S207, unmanned plane image-pickup method can also include:
S206:Change position of the target reference object in present image.
Specifically, unmanned plane can have the function of intelligent Background Recognition and partitioning algorithm, and background can be made full use of special
Property is patterned.
In one possible implementation, it can be shot with target by identifying background image by changing unmanned plane
Relative distance between object changes position of the target reference object in present image.I.e. unmanned plane is centered around target shooting
The different direction of data collection.Different background photo can be obtained.It is specific as shown in figure 12.
It, can also be by the background image of identification present image, according to Background in alternatively possible realization method
As adjustment the distance between unmanned plane and target reference object, to change position of the target reference object in present image;
Wherein, the distance between unmanned plane and target reference object include horizontal distance and vertical range.It is specific as shown in Figure 6.
For example, when it is seashore to identify the background image of present image, can be shot by adjusting unmanned plane and target
Horizontal distance and vertical range adjustment between object are patterned so that background is open enough.Specifically, unmanned plane and target
Vertical range between reference object should be one meter more slightly higher than the whole height of target reference object, unmanned plane and target shooting pair
Horizontal distance as between should be about 45 meters.
In alternatively possible realization method, can also by identify present image background, according to background adjustment with
The distance between target reference object;Wherein, distance includes horizontal distance and vertical range.When between target reference object
After distance meets the second preset condition, existed to change target reference object by the course angle and/or pitch angle that change unmanned plane
Position in present image, or changed by changing course angle and/or the pitch angle of the holder 130 being mounted on unmanned plane
Position of the target reference object in present image.Wherein, the second preset condition can be mentioned according in a upper embodiment
The distance between the target reference object that the pre-set shooting effect gone for of user determines, the second preset condition is also
Can be the various shooting effects obtained automatically according to the unmanned plane mentioned in a upper embodiment determine with target reference object
The distance between.When needing to obtain a variety of shooting effects, can be determined under various shooting effects respectively and target shooting pair
As the distance between after, then change course angle and/or the pitch angle of unmanned plane to change target reference object in present image
Position for selection by the user, meet the diversified demand of user to obtain the picture under various effects.
For example, when it is the main body in scenic spot to identify the background image of present image, i.e., there is shooting outstanding in background
When object, then need by changing course angle and pitch angle is patterned so that main body landscape is in picture center, and people is in side
Side, with sight spot object of giving prominence to the key points.
In alternatively possible realization method, can also by identify present image background, according to background adjustment with
The distance between target reference object;Wherein, distance includes horizontal distance and vertical range.When between target reference object
After distance meets the second preset condition, according to the relative position of background adjustment and target reference object, i.e. unmanned plane is centered around mesh
Mark the different direction around reference object.After the relative position between target reference object meets third preset condition, lead to
The course angle for changing unmanned plane and/or pitch angle are crossed to change position of the target reference object in present image, or is passed through
Change course angle and/or the pitch angle for the holder 130 being mounted on unmanned plane to change target reference object in present image
Position.Wherein, the second preset condition can be gone for according to the user mentioned in a upper embodiment is pre-set
The distance between the target reference object that shooting effect determines, the second preset condition can also be to be carried according in a upper embodiment
To the distance between the target reference object that determines of the various shooting effects that obtain automatically of unmanned plane.Third preset condition can
It is pre- to meet user with the different background images obtained by relative position of the change unmanned plane between target reference object
The requirement being first arranged, such as user can pre-enter the corresponding orientation in multiple camera sites, and third preset condition can also be
The relative position between target reference object determined according to the various shooting backgrounds that unmanned plane obtains automatically.It is a variety of when needing
, can be respectively after the distance between determining the various reference objects with target when shooting effect, then adjust and target reference object
Between relative position, finally adjust course angle and/or pitch angle again change present image background image and target shooting
Position of the object in present image for selection by the user, meets the diversified need of user to obtain the picture under various effects
It asks.
For example, during taking pictures, unmanned plane can follow target reference object always, so target reference object one is scheduled on
In picture, then according to background, first changes the distance between target reference object and be patterned, it is if it is big scape, then separate
Some can then be slightly closer to if it is close shot.Then change the relative position between target reference object again, by background
In bright spot characteristic be adjusted in picture.Finally, by judging whether there is emphasis reference object around target reference object, such as
Fruit has, and the key object is placed on picture center by course angle and/or pitch angle, by target reference object if not
It is placed on center, is patterned.
It, can also be by searching for being more than first threshold with present image similarity in alternatively possible realization method
Contrast images;Obtain the acquisition parameters of contrast images;Wherein, acquisition parameters include with the target reference object in contrast images it
Between distance, course angle and pitch angle, distance include horizontal distance and vertical range;It is adjusted according to the acquisition parameters of contrast images
Position of the target reference object in present image.Wherein, first threshold is such as can be 80%, 85%, 90%.When with work as
When preceding image similarity is more than the image more than one of first threshold, the highest image of similarity can be chosen and schemed as a comparison
Picture.
Specifically, it directly can summarize the best photo of each scene from network, then use CNN algorithms to picture field
Scape is learnt, and training pattern is stored in unmanned plane.When triggering unmanned plane auto composition is taken pictures, it can directly pass through CNN
Algorithm find out with the most similar contrast images of present image, then copy the mode of composition in the contrast images to be patterned, adopt
The length that each professional photographer can be integrated in this way, takes nice picture.
Specifically, the position according to the reference object in contrast images in contrast images can obtain the bat of contrast images
Take the photograph parameter, including with the distance between reference object, course angle and pitch angle.Nothing is adjusted further according to the acquisition parameters of contrast images
The distance between man-machine and target reference object, course angle and pitch angle.To obtain mode of composition similar with contrast images,
Obtain preferably shooting effect.
The embodiment of the present application provides a kind of unmanned plane image-pickup method, can be taken off and be obtained by controlling unmanned plane
Target reference object, tracks target reference object, and whether position of the analysis target reference object in present image meets image
Acquisition condition acquires image if meeting condition.Realize that unmanned plane is taken pictures the automation of process, is manually operated without user.Into
One step, the embodiment of the present application also provides a variety of unmanned plane auto composition modes, can obtain the figure under various shooting effects
Piece, user provide diversified selection, promote user experience.
The unmanned plane image-pickup method of above-described embodiment description, the embodiment of the present application also accordingly carry in order to better understand
A kind of unmanned plane is supplied.As shown in figure 13, unmanned plane 30 at least may include:Command reception module 310 obtains preserving module
320, acquisition module 330 and analysis acquisition module 340 are tracked;Wherein:
Command reception module 310 is for receiving instruction of taking off.
Preserving module 320 is obtained, for obtaining target reference object and preserving the feature of target reference object.
Acquisition module 330 is tracked for the signature tracking target reference object according to target reference object, obtains current figure
Picture;Wherein, present image includes target reference object.
Analysis acquisition module 340 is for analyzing position of the target reference object in present image, if target reference object
Position in present image meets Image Acquisition condition, then acquires image.
In an alternative embodiment, as shown in figure 14, command reception module 310 includes:First detection unit 3110,
First takes off unit 3120;Wherein:
After first detection unit 3110 is used to detect the instruction that triggering is taken off, target image is searched for.
First takes off unit 3120 for when target image is matched with pre-set image, making unmanned plane 30 generate lift.
In an alternative embodiment, as shown in figure 15, command reception module 310 includes:Second detection unit 3130,
Second takes off unit 3140;Wherein:
Second detection unit 3130 is used to detect the variation of the Inertial Measurement Unit data of unmanned plane 30;
If second take off unit 3140 for Inertial Measurement Unit data variation meet the first preset condition, make unmanned plane
30 generate lift.
In an alternative embodiment, as shown in figure 16, analysis acquisition module 340 includes:Analytical judgment unit 3410,
Collecting unit 3420;Wherein:
Unit 3410 is analyzed and determined for analyzing position of the target reference object in present image, if target reference object
Position in present image meets Image Acquisition condition, then judges whether to receive image capture instruction;
If collecting unit 3420 acquires figure for analyzing and determining that unit 3410 is judged to receive image capture instruction
Picture.
In an alternative embodiment, unmanned plane 30 further includes position change module 350, as shown in figure 17, is used for
With tracking acquisition module 330 according to the signature tracking target reference object of target reference object, after obtaining present image, analysis
Acquisition module 340 analyzes position of the target reference object in present image, if position of the target reference object in present image
It sets and meets Image Acquisition condition, then before acquiring image, change position of the target reference object in present image.
In an alternative embodiment, position change module 350 is specifically used between adjustment and target reference object
Distance;Wherein, distance includes horizontal distance and vertical range;By being shot with the distance between target reference object change target
Position of the object in present image.
In an alternative embodiment, position change module 350 is specifically used between adjustment and target reference object
Distance;Wherein, distance includes horizontal distance and vertical range;When meeting the second default item with the distance between target reference object
After part, course angle and/or pitch angle are adjusted;Change target reference object in present image by course angle and/or pitch angle
Position.
In an alternative embodiment, analysis acquisition module 340 is schemed specifically for analysis target reference object currently
Position as in acquires at least two width figures if position of the target reference object in present image meets Image Acquisition condition
Picture;Wherein, the coincidence factor between adjacent two images is located in preset range.
Unmanned plane 30 further includes image mosaic module 360, as shown in figure 18, for being acquired extremely in analysis acquisition module 340
After few two images, splicing at least two images.
In an alternative embodiment, present image further includes background image.Unmanned plane 30 further includes position change mould
Block 350, as shown in figure 17, for tracking acquisition module 330 according to the shooting pair of the signature tracking target of target reference object
As after obtaining present image, analysis acquisition module 340 analyzes position of the target reference object in present image, if target
Position of the reference object in present image meets Image Acquisition condition, then before acquiring image, changes target reference object and exist
Position in present image.It analyzes acquisition module 340 and is specifically used for position of the analysis target reference object in present image, if
Judge that position of the target reference object in the present image meets image according to the background image of the present image
Acquisition condition then acquires image.
In an alternative embodiment, position change module 350 is specifically used for adjustment and the target reference object
Relative position.
In an alternative embodiment, position change module 350 is specifically used for the background image of identification present image, root
According to the distance between background image adjustment and target reference object;Wherein, distance includes horizontal distance and vertical range.
In an alternative embodiment, position change module 350 is specifically used for the background of identification present image, according to the back of the body
Scape adjusts the distance between target reference object;Wherein, distance includes horizontal distance and vertical range;When with target shooting pair
As the distance between meet the second preset condition after, adjust course angle and/or pitch angle.
In an alternative embodiment, position change module 350 is specifically used for the background of identification present image, according to the back of the body
Scape adjusts the distance between target reference object;Wherein, distance includes horizontal distance and vertical range;When with target shooting pair
As the distance between meet the second preset condition after, according to background adjustment and the relative position of target reference object;When with target
After relative position between reference object meets third preset condition, course angle and/or pitch angle are adjusted.
In an alternative embodiment, unmanned plane 30 in addition to include command reception module 310, obtain preserving module 320,
It tracks except acquisition module 330 and analysis acquisition module 340, further includes searching module 370, parameter acquisition module 380, adjustment mould
Block 390, as shown in figure 19, wherein:
Searching module 370 is used to search the contrast images with present image similarity more than first threshold.
Parameter acquisition module 380 is used to obtain the acquisition parameters of contrast images;Wherein, acquisition parameters include and contrast images
In the distance between target reference object, course angle and pitch angle;Distance includes horizontal distance and vertical range.
Module 390 is adjusted to be used to adjust position of the target reference object in present image according to the acquisition parameters of contrast images
It sets.
In the embodiment of the present application, the specific implementation of the modules of unmanned plane can refer to phase in above-mentioned each embodiment of the method
The description held inside the Pass.
The embodiment of the present application can be taken off by controlling unmanned plane and obtain target reference object, tracking target shooting pair
As whether position of the analysis target reference object in present image meets Image Acquisition condition, the acquisition figure if meeting condition
Picture.Realize that unmanned plane is taken pictures the automation of process, is manually operated without user.Further, the embodiment of the present application also provides
A variety of unmanned plane auto composition modes can obtain the picture under various shooting effects, and user provides diversified selection, is promoted
User experience.
Figure 20 is referred to again, and Figure 20 is the structural schematic diagram of another unmanned plane provided by the embodiments of the present application.Such as Figure 20
Shown, unmanned plane 40 at least may include:Memory 410, processor 420, by total between memory 410 and processor 420
Line 430 is connected.
Memory 410 is for storing unmanned plane image acquisition procedure;
Processor 420, for calling the unmanned plane image acquisition procedure in memory 410 and executing:
Reception is taken off instruction;It obtains target reference object and preserves the feature of target reference object;It is clapped according to the target
The signature tracking target reference object of object is taken the photograph, present image is obtained;Wherein, present image includes target reference object;Analysis
Position of the target reference object in present image, if position of the target reference object in present image meets Image Acquisition item
Part then acquires image.
In one optionally embodiment, processor 420 receives instruction of taking off and includes:Detect the instruction that triggering is taken off
Afterwards, target image is searched for;When target image is matched with pre-set image, unmanned plane is made to generate lift.
In one optionally embodiment, processor 420 receives instruction of taking off and includes:Detect the inertia measurement list of unmanned plane
The variation of metadata;If the variation of Inertial Measurement Unit data meets the first preset condition, unmanned plane is made to generate lift.
In one optionally embodiment, if position of the target reference object in present image meets Image Acquisition item
Part, processor 420 acquire image and include:If position of the target reference object in present image meets Image Acquisition condition,
Judge whether to receive image capture instruction;If receiving image capture instruction, image is acquired.
In one optionally embodiment, according to the signature tracking target reference object of target reference object, obtain current
After image, position of the analysis target reference object in present image, if position of the target reference object in present image
Meet Image Acquisition condition, then before acquiring image, processor 420 is additionally operable to:Change target reference object in present image
Position.
In one optionally embodiment, processor 420 changes position of the target reference object in present image and includes:
The distance between adjustment and target reference object;Wherein, distance includes horizontal distance and vertical range;By with target shooting pair
As the distance between change position of the target reference object in present image.
In one optionally embodiment, processor 420 changes position of the target reference object in present image and includes:
The distance between adjustment and target reference object;Wherein, distance includes horizontal distance and vertical range;When with target reference object
The distance between meet the second preset condition after, adjust course angle and/or pitch angle;Changed by course angle and/or pitch angle
Position of the target reference object in present image.
In one optionally embodiment, if position of the target reference object in present image meets Image Acquisition item
Part, processor 420 acquire image and include:If position of the target reference object in present image meets Image Acquisition condition,
Acquisition at least two images;Wherein, the coincidence factor between adjacent two images is located in preset range;If judging target shooting pair
As the position in present image meets Image Acquisition condition, then after acquiring at least two images, processor 420 is additionally operable to:
Splicing at least two images.
In one optionally embodiment, present image further includes background image.According to the spy of the target reference object
Sign tracks the target reference object, after obtaining present image, position of the analysis target reference object in present image, if
Position of the target reference object in present image meets Image Acquisition condition, then before acquiring image, processor 420 is also used
In:Change position of the target reference object in present image;If position of the target reference object in present image meets figure
As acquisition condition, processor 420 acquires image and includes:If judging that target reference object is being worked as according to the background image of present image
Position in preceding image meets Image Acquisition condition, then acquires image.
In one optionally embodiment, processor 420 changes position of the target reference object in present image and includes:
The relative position of adjustment and target reference object.
In one optionally embodiment, processor 420 changes position of the target reference object in present image and includes:
The background image for identifying present image, according to the distance between background image adjustment and target reference object;Wherein, distance includes
Horizontal distance and vertical range.
In one optionally embodiment, processor 420 changes position of the target reference object in present image and includes:
The background for identifying present image, according to the distance between background adjustment and the target reference object;Wherein, distance includes level
Distance and vertical range;After meeting the second preset condition with the distance between target reference object, adjusts course angle and/or bow
The elevation angle.
In one optionally embodiment, processor 420 changes position of the target reference object in present image and includes:
The background for identifying institute's present image, according to the distance between institute's background adjustment and target reference object;Wherein, distance includes level
Distance and vertical range;After meeting the second preset condition with the distance between target reference object, according to background adjustment and mesh
Mark the relative position of reference object;After the relative position between target reference object meets third preset condition, adjustment boat
To angle and/or pitch angle.
In one optionally embodiment, according to the signature tracking target reference object of target reference object, obtain current
After image, position of the analysis target reference object in present image, if position of the target reference object in present image
Meet Image Acquisition condition, then before acquiring image, processor 420 is additionally operable to:It is more than first to search with present image similarity
The contrast images of threshold value;Obtain the acquisition parameters of contrast images;Wherein, acquisition parameters include being shot with the target in contrast images
The distance between object, course angle and pitch angle;Distance includes horizontal distance and vertical range;Joined according to the shooting of contrast images
Position of the number adjustment target reference object in present image.
The embodiment of the present application can be taken off by controlling unmanned plane and obtain target reference object, tracking target shooting pair
As whether position of the analysis target reference object in present image meets Image Acquisition condition, the acquisition figure if meeting condition
Picture.Realize that unmanned plane is taken pictures the automation of process, is manually operated without user.Further, the embodiment of the present application also provides
A variety of unmanned plane auto composition modes can obtain the picture under various shooting effects, and user provides diversified selection, is promoted
User experience.
One of ordinary skill in the art will appreciate that realizing all or part of flow in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a computer read/write memory medium
In, the program is when being executed, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
The above disclosure is only the preferred embodiments of the present invention, cannot limit the right model of the present invention with this certainly
It encloses, therefore equivalent changes made in accordance with the claims of the present invention, is still within the scope of the present invention.
Claims (29)
1. a kind of unmanned plane image-pickup method, which is characterized in that including:
Reception is taken off instruction;
It obtains target reference object and preserves the feature of the target reference object;
According to target reference object described in the signature tracking of the target reference object, present image is obtained;Wherein, described current
Image includes target reference object;
Position of the target reference object in the present image is analyzed, if the target reference object is in the current figure
Position as in meets Image Acquisition condition, then acquires image.
2. the method as described in claim 1, which is characterized in that the reception instruction of taking off includes:
After detecting the instruction that triggering is taken off, target image is searched for;
When the target image is matched with pre-set image, the unmanned plane is made to generate lift.
3. the method as described in claim 1, which is characterized in that the reception instruction of taking off includes:
Detect the variation of the Inertial Measurement Unit data of the unmanned plane;
If the variation of the Inertial Measurement Unit data meets the first preset condition, the unmanned plane is made to generate lift.
4. the method as described in claim 1, which is characterized in that if the target reference object is in the present image
Position meet Image Acquisition condition, then acquiring image includes:
If position of the target reference object in the present image meets Image Acquisition condition, judge whether to receive
Image capture instruction;
If receiving image capture instruction, image is acquired.
5. method as described in claim 1 or 4, which is characterized in that the signature tracking according to the target reference object
The target reference object, after obtaining present image, the analysis target reference object is in the present image
Position, if position of the target reference object in the present image meets Image Acquisition condition, before acquiring image,
The method further includes:Change position of the target reference object in the present image.
6. method as claimed in claim 5, which is characterized in that described to change the target reference object in the present image
In position include:
The distance between adjustment and the target reference object;Wherein, the distance includes horizontal distance and vertical range;
By changing position of the target reference object in the present image with the distance between the target reference object
It sets.
7. method as claimed in claim 5, which is characterized in that described to change the target reference object in the present image
In position include:
The distance between adjustment and the target reference object;Wherein, the distance includes horizontal distance and vertical range;
After meeting the second preset condition with the distance between the target reference object, course angle and/or pitch angle are adjusted;
Change position of the target reference object in the present image by the course angle and/or pitch angle.
8. the method for claim 7, which is characterized in that if the target reference object is in the present image
Position meet Image Acquisition condition, then acquiring image includes:
If position of the target reference object in the present image meets Image Acquisition condition, at least two width figures are acquired
Picture;Wherein, the coincidence factor between adjacent two images is located in preset range;
If the position for judging the target reference object in the present image meets Image Acquisition condition, acquire to
After few two images, the method further includes:At least two images described in splicing.
9. method as described in claim 1 or 4, which is characterized in that the present image further includes background image;
Target reference object described in the signature tracking according to the target reference object, it is described after obtaining present image
Position of the target reference object in the present image is analyzed, if the target reference object is in the present image
Position meet Image Acquisition condition, then before acquiring image, the method further includes:Change the target reference object in institute
State the position in present image;
If position of the target reference object in the present image meets Image Acquisition condition, image packet is acquired
It includes:If judging that position of the target reference object in the present image meets according to the background image of the present image
Image Acquisition condition, then acquire image.
10. method as claimed in claim 9, which is characterized in that described to change the target reference object in the current figure
Position as in includes:The relative position of adjustment and the target reference object.
11. method as claimed in claim 9, which is characterized in that described to change the target reference object in the current figure
Position as in includes:
The background image for identifying the present image, according to the background image adjustment the target reference object between away from
From;Wherein, the distance includes horizontal distance and vertical range.
12. method as claimed in claim 9, which is characterized in that described to change the target reference object in the current figure
Position as in includes:
The background for identifying the present image, according to the distance between background adjustment and the target reference object;Wherein,
The distance includes horizontal distance and vertical range;
After meeting the second preset condition with the distance between the target reference object, course angle and/or pitch angle are adjusted.
13. method as claimed in claim 9, which is characterized in that described to change the target reference object in the current figure
Position as in includes:
The background for identifying the present image, according to the distance between background adjustment and the target reference object;Wherein,
The distance includes horizontal distance and vertical range;
After meeting the second preset condition with the distance between the target reference object, according to background adjustment and the mesh
Mark the relative position of reference object;
After the relative position between the target reference object meets third preset condition, course angle and/or pitching are adjusted
Angle.
14. method as described in claim 1 or 4, which is characterized in that the signature tracking according to the target reference object
The target reference object, after obtaining present image, the analysis target reference object is in the present image
Position, if position of the target reference object in the present image meets Image Acquisition condition, before acquiring image,
The method further includes:
Search the contrast images more than first threshold with the present image similarity;
Obtain the acquisition parameters of the contrast images;Wherein, the acquisition parameters include being clapped with the target in the contrast images
Take the photograph the distance between object, course angle and pitch angle;The distance includes horizontal distance and vertical range;
Position of the target reference object in the present image is adjusted according to the acquisition parameters of the contrast images.
15. a kind of unmanned plane, which is characterized in that including:
Memory, for storing unmanned plane image acquisition procedure;
Processor, for calling the unmanned plane image acquisition procedure in the memory and executing:
Reception is taken off instruction;
It obtains target reference object and preserves the feature of the target reference object;
According to target reference object described in the signature tracking of the target reference object, present image is obtained;Wherein, described current
Image includes target reference object;
Position of the target reference object in the present image is analyzed, if the target reference object is in the current figure
Position as in meets Image Acquisition condition, then acquires image.
16. unmanned plane as claimed in claim 15, which is characterized in that the processor receives instruction of taking off and includes:
After detecting the instruction that triggering is taken off, target image is searched for;
When the target image is matched with pre-set image, the unmanned plane is made to generate lift.
17. unmanned plane as claimed in claim 15, which is characterized in that the processor receives instruction of taking off and includes:
Detect the variation of the Inertial Measurement Unit data of the unmanned plane;
If the variation of the Inertial Measurement Unit data meets the first preset condition, the unmanned plane is made to generate lift.
18. unmanned plane as claimed in claim 15, which is characterized in that if the processor target reference object is described
Position in present image meets Image Acquisition condition, then acquires image and include:
If position of the target reference object in the present image meets Image Acquisition condition, judge whether to receive
Image capture instruction;
If receiving image capture instruction, image is acquired.
19. the unmanned plane as described in claim 15 or 18, which is characterized in that the feature according to the target reference object
The target reference object is tracked, after obtaining present image, the analysis target reference object is in the present image
In position acquire image if position of the target reference object in the present image meets Image Acquisition condition
Before, the processor is additionally operable to:Change position of the target reference object in the present image.
20. unmanned plane as claimed in claim 19, which is characterized in that the processor changes the target reference object in institute
The position stated in present image includes:
The distance between adjustment and the target reference object;Wherein, the distance includes horizontal distance and vertical range;
By changing position of the target reference object in the present image with the distance between the target reference object
It sets.
21. unmanned plane as claimed in claim 19, which is characterized in that the processor changes the target reference object in institute
The position stated in present image includes:
The distance between adjustment and the target reference object;Wherein, the distance includes horizontal distance and vertical range;
After meeting the second preset condition with the distance between the target reference object, course angle and/or pitch angle are adjusted;
Change position of the target reference object in the present image by the course angle and/or pitch angle.
22. unmanned plane as claimed in claim 21, which is characterized in that if the processor executes the target reference object and exists
Position in the present image meets Image Acquisition condition, then acquires image and include:
If position of the target reference object in the present image meets Image Acquisition condition, at least two width figures are acquired
Picture;Wherein, the coincidence factor between adjacent two images is located in preset range;
If the position for judging the target reference object in the present image meets Image Acquisition condition, acquire to
After few two images, the processor is additionally operable to:At least two images described in splicing.
23. the unmanned plane as described in claim 15 or 18, which is characterized in that the present image further includes background image;
Target reference object described in the signature tracking according to the target reference object, it is described after obtaining present image
Position of the target reference object in the present image is analyzed, if the target reference object is in the present image
Position meet Image Acquisition condition, then before acquiring image, the processor is additionally operable to:Change the target reference object to exist
Position in the present image;
If the processor executes the target reference object, the position in the present image meets Image Acquisition condition,
Acquiring image includes:If judging the target reference object in the present image according to the background image of the present image
Position meet Image Acquisition condition, then acquire image.
24. unmanned plane as claimed in claim 23, which is characterized in that the processor changes the target reference object in institute
The position stated in present image includes:The relative position of adjustment and the target reference object.
25. unmanned plane as claimed in claim 23, which is characterized in that the processor changes the target reference object in institute
The position stated in present image includes:
The background image for identifying the present image, according to the background image adjustment the target reference object between away from
From;Wherein, the distance includes horizontal distance and vertical range.
26. unmanned plane as claimed in claim 23, which is characterized in that the processor changes the target reference object in institute
The position stated in present image includes:
The background for identifying the present image, according to the distance between background adjustment and the target reference object;Wherein,
The distance includes horizontal distance and vertical range;
After meeting the second preset condition with the distance between the target reference object, course angle and/or pitch angle are adjusted.
27. unmanned plane as claimed in claim 23, which is characterized in that the processor changes the target reference object in institute
The position stated in present image includes:
The background for identifying the present image, according to the distance between background adjustment and the target reference object;Wherein,
The distance includes horizontal distance and vertical range;
After meeting the second preset condition with the distance between the target reference object, according to background adjustment and the mesh
Mark the relative position of reference object;
After the relative position between the target reference object meets third preset condition, course angle and/or pitching are adjusted
Angle.
28. the unmanned plane as described in claim 15 or 18, which is characterized in that the feature according to the target reference object
The target reference object is tracked, after obtaining present image, the analysis target reference object is in the present image
In position acquire image if position of the target reference object in the present image meets Image Acquisition condition
Before, the processor is additionally operable to:
Search the contrast images more than first threshold with the present image similarity;
Obtain the acquisition parameters of the contrast images;Wherein, the acquisition parameters include being clapped with the target in the contrast images
Take the photograph the distance between object, course angle and pitch angle;The distance includes horizontal distance and vertical range;
Position of the target reference object in the present image is adjusted according to the acquisition parameters of the contrast images.
29. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
Such as claim 1-14 any one of them unmanned plane image-pickup methods are executed when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110304772.4A CN113038016B (en) | 2017-09-27 | 2017-09-27 | Unmanned aerial vehicle image acquisition method and unmanned aerial vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2017/103624 WO2019061063A1 (en) | 2017-09-27 | 2017-09-27 | Image collection method for unmanned aerial vehicle, and unmanned aerial vehicle |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110304772.4A Division CN113038016B (en) | 2017-09-27 | 2017-09-27 | Unmanned aerial vehicle image acquisition method and unmanned aerial vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108702448A true CN108702448A (en) | 2018-10-23 |
| CN108702448B CN108702448B (en) | 2021-04-09 |
Family
ID=63843843
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201780010140.9A Active CN108702448B (en) | 2017-09-27 | 2017-09-27 | Unmanned aerial vehicle image acquisition method, unmanned aerial vehicle and computer readable storage medium |
| CN202110304772.4A Active CN113038016B (en) | 2017-09-27 | 2017-09-27 | Unmanned aerial vehicle image acquisition method and unmanned aerial vehicle |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110304772.4A Active CN113038016B (en) | 2017-09-27 | 2017-09-27 | Unmanned aerial vehicle image acquisition method and unmanned aerial vehicle |
Country Status (2)
| Country | Link |
|---|---|
| CN (2) | CN108702448B (en) |
| WO (1) | WO2019061063A1 (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109709982A (en) * | 2018-12-29 | 2019-05-03 | 东南大学 | A kind of unmanned plane determines high control system and method |
| CN109741271A (en) * | 2018-12-14 | 2019-05-10 | 陕西高速公路工程试验检测有限公司 | A kind of detection method and system |
| CN110132049A (en) * | 2019-06-11 | 2019-08-16 | 南京森林警察学院 | A kind of automatic aiming formula sniper rifle based on unmanned aerial vehicle platform |
| CN110426970A (en) * | 2019-06-25 | 2019-11-08 | 西安爱生无人机技术有限公司 | A kind of unmanned plane camera system and its control method |
| CN110971824A (en) * | 2019-12-04 | 2020-04-07 | 深圳市凯达尔科技实业有限公司 | Unmanned aerial vehicle shooting control method |
| CN111445455A (en) * | 2020-03-26 | 2020-07-24 | 北京润科通用技术有限公司 | Image acquisition method and device |
| CN111709949A (en) * | 2020-08-19 | 2020-09-25 | 武汉精测电子集团股份有限公司 | Outdoor display screen detection and repair method, device, equipment and storage medium |
| CN113129468A (en) * | 2021-04-06 | 2021-07-16 | 深圳市艾赛克科技有限公司 | Underground pipe gallery inspection method based on unmanned aerial vehicle |
| CN113906360A (en) * | 2020-08-07 | 2022-01-07 | 深圳市大疆创新科技有限公司 | Control method and device for movable platform and computer readable storage medium |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110989649B (en) * | 2019-12-26 | 2023-07-25 | 中国航空工业集团公司沈阳飞机设计研究所 | Flight action control device for high-maneuver fixed-wing unmanned aerial vehicle and training method |
| CN111737604B (en) * | 2020-06-24 | 2023-07-21 | 中国银行股份有限公司 | Target object searching method and device |
| CN113747071B (en) * | 2021-09-10 | 2023-10-24 | 深圳市道通智能航空技术股份有限公司 | Unmanned aerial vehicle shooting method and device, unmanned aerial vehicle and storage medium |
| CN114040107B (en) * | 2021-11-19 | 2024-04-16 | 智己汽车科技有限公司 | Intelligent automobile image shooting system, intelligent automobile image shooting method, intelligent automobile image shooting vehicle and intelligent automobile image shooting medium |
| CN114285996B (en) * | 2021-12-23 | 2023-08-22 | 中国人民解放军海军航空大学 | Ground target coverage shooting method and system |
| CN116027798B (en) * | 2022-09-30 | 2023-11-17 | 三峡大学 | Unmanned aerial vehicle power inspection system and method based on image correction |
| CN116929306B (en) * | 2023-07-20 | 2024-04-19 | 深圳赛尔智控科技有限公司 | Data acquisition method, device, equipment and computer readable storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101415076A (en) * | 2007-10-17 | 2009-04-22 | 索尼株式会社 | Composition determining apparatus, composition determining method, and program |
| CN106331508A (en) * | 2016-10-19 | 2017-01-11 | 深圳市道通智能航空技术有限公司 | Composition shooting method and device |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017038891A1 (en) * | 2015-09-04 | 2017-03-09 | Ｎｅｃソリューションイノベータ株式会社 | Flight control device, flight control method, and computer-readable recording medium |
| WO2017060782A1 (en) * | 2015-10-07 | 2017-04-13 | Lee Hoi Hung Herbert | Flying apparatus with multiple sensors and gesture-based operation |
| CN105549614B (en) * | 2015-12-17 | 2018-06-05 | 北京猎鹰无人机科技有限公司 | Unmanned plane target tracking |
| CN106354157B (en) * | 2016-11-28 | 2019-05-14 | 中山市昌源模型有限公司 | A kind of unmanned plane autonomous flight system |
| CN106909172A (en) * | 2017-03-06 | 2017-06-30 | 重庆零度智控智能科技有限公司 | Around tracking, device and unmanned plane |
| CN107102647A (en) * | 2017-03-30 | 2017-08-29 | 中国人民解放军海军航空工程学院青岛校区 | Unmanned plane target tracking and controlling method based on image |
| CN107016367B (en) * | 2017-04-06 | 2021-02-26 | 北京精英路通科技有限公司 | Tracking control method and tracking control system |
| CN106991413A (en) * | 2017-05-04 | 2017-07-28 | 上海耐相智能科技有限公司 | A kind of unmanned plane |
-
2017
- 2017-09-27 WO PCT/CN2017/103624 patent/WO2019061063A1/en active Application Filing
- 2017-09-27 CN CN201780010140.9A patent/CN108702448B/en active Active
- 2017-09-27 CN CN202110304772.4A patent/CN113038016B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101415076A (en) * | 2007-10-17 | 2009-04-22 | 索尼株式会社 | Composition determining apparatus, composition determining method, and program |
| CN106331508A (en) * | 2016-10-19 | 2017-01-11 | 深圳市道通智能航空技术有限公司 | Composition shooting method and device |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109741271A (en) * | 2018-12-14 | 2019-05-10 | 陕西高速公路工程试验检测有限公司 | A kind of detection method and system |
| CN109741271B (en) * | 2018-12-14 | 2021-11-19 | 陕西高速公路工程试验检测有限公司 | Detection method and system |
| CN109709982A (en) * | 2018-12-29 | 2019-05-03 | 东南大学 | A kind of unmanned plane determines high control system and method |
| CN110132049A (en) * | 2019-06-11 | 2019-08-16 | 南京森林警察学院 | A kind of automatic aiming formula sniper rifle based on unmanned aerial vehicle platform |
| CN110426970A (en) * | 2019-06-25 | 2019-11-08 | 西安爱生无人机技术有限公司 | A kind of unmanned plane camera system and its control method |
| CN110426970B (en) * | 2019-06-25 | 2021-05-25 | 西安爱生无人机技术有限公司 | Unmanned aerial vehicle photographing system and control method thereof |
| CN110971824A (en) * | 2019-12-04 | 2020-04-07 | 深圳市凯达尔科技实业有限公司 | Unmanned aerial vehicle shooting control method |
| CN111445455A (en) * | 2020-03-26 | 2020-07-24 | 北京润科通用技术有限公司 | Image acquisition method and device |
| CN111445455B (en) * | 2020-03-26 | 2023-04-07 | 北京润科通用技术有限公司 | Image acquisition method and device |
| CN113906360A (en) * | 2020-08-07 | 2022-01-07 | 深圳市大疆创新科技有限公司 | Control method and device for movable platform and computer readable storage medium |
| CN111709949A (en) * | 2020-08-19 | 2020-09-25 | 武汉精测电子集团股份有限公司 | Outdoor display screen detection and repair method, device, equipment and storage medium |
| CN113129468A (en) * | 2021-04-06 | 2021-07-16 | 深圳市艾赛克科技有限公司 | Underground pipe gallery inspection method based on unmanned aerial vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108702448B (en) | 2021-04-09 |
| CN113038016B (en) | 2023-05-19 |
| WO2019061063A1 (en) | 2019-04-04 |
| CN113038016A (en) | 2021-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108702448A (en) | Unmanned plane image-pickup method and unmanned plane | |
| CN107087427B (en) | Control method, device and the equipment and aircraft of aircraft | |
| US10674062B2 (en) | Control method for photographing using unmanned aerial vehicle, photographing method using unmanned aerial vehicle, mobile terminal, and unmanned aerial vehicle | |
| CN105391939B (en) | Unmanned plane filming control method and device, unmanned plane image pickup method and unmanned plane | |
| CN107690305B (en) | Generating images from video | |
| CN110494360A (en) | For providing the autonomous system and method photographed and image | |
| CN106331508A (en) | Composition shooting method and device | |
| CN105045279A (en) | System and method for automatically generating panorama photographs through aerial photography of unmanned aerial aircraft | |
| CN105955308A (en) | Aircraft control method and device | |
| CN107197153B (en) | Shooting method and shooting device for photo | |
| CN107765709A (en) | The method and device of self-timer is realized based on aircraft | |
| CN108377328A (en) | A kind of helicopter makes an inspection tour the target image pickup method and device of operation | |
| US20240179398A1 (en) | Method, control apparatus and control system for controlling an image capture of movable device | |
| CN112771576A (en) | Position information acquisition method, device and storage medium | |
| CN108702456A (en) | A kind of focusing method, equipment and readable storage medium storing program for executing | |
| WO2018198281A1 (en) | Information processing apparatus, aerial-photographing path generation method, aerial-photographing path generation system, program, and recording medium | |
| CN113875222A (en) | Shooting control method and device, unmanned aerial vehicle and computer readable storage medium | |
| JP2015056152A (en) | Display control device and method for controlling display control device | |
| KR102402949B1 (en) | Acquisition method of image information with improved precision | |
| CN114659499B (en) | Smart city 3D map model photography establishment method based on unmanned aerial vehicle technology | |
| CN110392891A (en) | Mobile's detection device, control device, moving body, movable body detecting method and program | |
| JP2020085918A (en) | Determination device, imaging device, imaging system, moving body, determination method and program | |
| WO2022077297A1 (en) | Data processing method, apparatus and device, and storage medium | |
| JP2005286379A (en) | Photographing support system and photographing support method | |
| JP2021012612A (en) | Information processor, information processing system, and control method and program for same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |