CN106131411A - A kind of method and apparatus shooting image - Google Patents
A kind of method and apparatus shooting image Download PDFInfo
- Publication number
- CN106131411A CN106131411A CN201610555364.5A CN201610555364A CN106131411A CN 106131411 A CN106131411 A CN 106131411A CN 201610555364 A CN201610555364 A CN 201610555364A CN 106131411 A CN106131411 A CN 106131411A
- Authority
- CN
- China
- Prior art keywords
- image
- scene
- picking
- scene image
- sub
- 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
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
- H04N23/64—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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
-
- 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
- H04N23/667—Camera operation mode switching, e.g. between still and video, sport and normal or high- and low-resolution modes
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Studio Devices (AREA)
Abstract
The present invention relates to electronic technology field, particularly relate to a kind of method and apparatus shooting image.The method and apparatus of the shooting image that the embodiment of the present invention provides, for realizing auto composition and carrying out the technique effect shot.The method of described shooting image includes: controls image picking-up apparatus and shoots scene, to obtain the scene image of described scene；At least one element is extracted from described scene image；According to default composition rule, the object element at least one element described is patterned；Control described image picking-up apparatus and shoot image according to described composition.
Description
Technical field
The present invention relates to electronic technology field, particularly relate to a kind of method and apparatus shooting image.
Background technology
In recent years, unmanned plane, and the intelligent robot possessing shoot function occurs gradually in the visual field of people.Unmanned
Machine and possess the appearance of robot (hereinafter referred to as the two for " robot ") of shoot function so that user need not in person go one
The a little inconvenient or place that is beyond one's reach shoots, such as volcano, or overhead, city etc..So, robot makes to clap
Take the photograph convenient.
But, although robot can substitute for user and in person goes shooting, but with what angle shot and how composition, still
So need to rely on the control of user.So, there is the technical problem that can not automatically snap in robot of the prior art.
Summary of the invention
Embodiments provide a kind of method and apparatus shooting image, be used for realizing auto composition and shooting
Technique effect.
First aspect, the invention provides a kind of method shooting image, including:
Control image picking-up apparatus scene to be shot, to obtain the scene image of described scene；
At least one element is extracted from described scene image；
According to default composition rule, the object element at least one element described is patterned；
Control described image picking-up apparatus and shoot image according to described composition.
Optionally, control image picking-up apparatus and scene is shot, to obtain the scene image of described scene, including:
The many groups part scene image shot according to described image picking-up apparatus, the multiple backup scenario images of corresponding structure,
Wherein, part scene image described in each group is for building a described backup scenario image；
The mobile element in described scene is determined based on the plurality of backup scenario image；
Remove the mobile element in each described backup scenario image；
According to the plurality of backup scenario image after the described mobile element of removal, it is thus achieved that described scene image.
Optionally, from described scene image, extract at least one element, including:
Described scene image is divided into multiple sub-scene image；
Each sub-scene image is carried out element extraction, to obtain at least one element described.
Optionally, each sub-scene image is being carried out element extraction, after obtaining at least one element described, also wrapping
Include:
Sub-scene image according to each element place and described each element are in the sub-scene image at described place
Position, determine described each element position in described scene.
Optionally, before the object element at least one element described is patterned, also include:
The preview image shot according to described image picking-up apparatus, identifies human body and face from described scene；
Obtain described human body position in described scene.
Optionally, according to default composition rule, the object element at least one element described is patterned, including:
Determine from least one element described and meet pre-conditioned described object element；
According to described human body position in described scene, default facial orientation, described object element and described mesh
The position of mark element, is patterned according to described default rule.
Optionally, at the many groups part scene image shot according to described image picking-up apparatus, corresponding structure is multiple standby
Before scene image, also include:
Control described image picking-up apparatus and start cycle rotation from the predeterminated position of described scene；
In the rotary course in each cycle, the some of described scene is shot, to obtain portion described in a group
Divide scene image.
Second aspect, the invention provides a kind of device shooting image, including:
First control module, is used for controlling image picking-up apparatus and shoots scene, to obtain the scene of described scene
Image；
First extraction module, for extracting at least one element from described scene image；
First composition module, for according to default composition rule, is carried out the object element at least one element described
Composition；
Second control module, is used for controlling described image picking-up apparatus and shoots image according to described composition.
Optionally, described first control module is for the many groups part scene graph shot according to described image picking-up apparatus
Picture, the multiple backup scenario images of corresponding structure, wherein, part scene image described in each group is for building a described alternate aerodrome
Scape image；The mobile element in described scene is determined based on the plurality of backup scenario image；Remove each described alternate aerodrome
Mobile element in scape image；According to the plurality of backup scenario image after the described mobile element of removal, it is thus achieved that described scene
Image.
Optionally, described first extraction module for being divided into multiple sub-scene image by described scene image；To each
Sub-scene image carries out element extraction, to obtain at least one element described.
Optionally, described device also includes that first determines module, for each sub-scene image is being carried out element extraction,
After obtaining at least one element described, sub-scene image and described each element according to each element place are described
Position in the sub-scene image at place, determines described each element position in described scene.
Optionally, described device also includes identification module, for entering the object element at least one element described
Before row composition, the preview image shot according to described image picking-up apparatus, identifies human body and face from described scene；Obtain
Obtain described human body position in described scene.
Optionally, described first composition module meets pre-conditioned institute for determining from least one element described
State object element；According to described human body position in described scene, default facial orientation, described object element and described
The position of object element, is patterned according to described default rule.
Optionally, described device also includes the 3rd control module, for shooting many according to described image picking-up apparatus
Group part scene image, before the multiple backup scenario images of corresponding structure, controls described image picking-up apparatus from described scene
Predeterminated position starts cycle rotation；
Packet taking module, in the rotary course in each cycle, shoots the some of described scene,
To obtain part scene image described in a group.
Beneficial effects of the present invention is as follows:
In embodiments of the present invention, first control image picking-up apparatus scene is shot, it is thus achieved that scene image, then
At least one element is extracted, the most automatically according to default composition rule, at least one element from scene image
Object element is patterned, and the final image picking-up apparatus that controls shoots image according to composition.Visible, due to according to default composition method
Then it is automatically performed composition and shoots so that the image picking-up apparatus in the embodiment of the present invention can be independent of the automatic structure of user
Figure, so, solve the technical problem that in prior art, robot can not automatically snap, it is achieved that auto composition the skill shot
Art effect.
Accompanying drawing explanation
Fig. 1 is the method flow diagram of the shooting image of the embodiment of the present invention；
Fig. 2 a-Fig. 2 c is one group of part scene image schematic diagram in the embodiment of the present invention；
Fig. 3 is the backup scenario image schematic diagram built by the part scene image shown in Fig. 2 a-Fig. 2 c；
Fig. 4 is a shooting image schematic diagram in the embodiment of the present invention；
Fig. 5 is a scene image schematic diagram in the embodiment of the present invention；
Fig. 6 is an object element and the position view of shooting vision facilities in the embodiment of the present invention；
Fig. 7 is the object element in Fig. 6 and the postrotational position view of image picking-up apparatus；
Fig. 8 is that image picking-up apparatus is at the image schematic diagram captured by the position shown in Fig. 7；
Fig. 9 is another object element and the position view of shooting vision facilities in the embodiment of the present invention；
Figure 10 is that image picking-up apparatus is at the image schematic diagram captured by the position shown in Fig. 9；
Figure 11 is the apparatus structure schematic diagram of the shooting image in the embodiment of the present invention.
Detailed description of the invention
Embodiments provide a kind of method and apparatus shooting image, be used for realizing auto composition and shooting
Technique effect.
In order to solve above-mentioned technical problem, in embodiments of the present invention, first control image picking-up apparatus scene is carried out
Shooting, it is thus achieved that scene image, then extracts at least one element from scene image, the most automatically according to default composition method
Then, being patterned the object element at least one element, the final image picking-up apparatus that controls shoots image according to composition.Can
See, owing to being automatically performed composition according to default composition rule and shooting so that the image taking in the embodiment of the present invention sets
For being independent of user's auto composition, so, solve the technical problem that in prior art, robot can not automatically snap, real
Auto composition the technique effect shot are showed.
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
The a part of embodiment of the present invention rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under not making creative work premise, broadly falls into the scope of protection of the invention.
It addition, the terms "and/or", a kind of incidence relation describing affiliated partner, expression can exist
Three kinds of relations, such as, A and/or B, can represent: individualism A, there is A and B, individualism B these three situation simultaneously.Separately
Outward, character "/" herein, typically represent the forward-backward correlation relation to liking a kind of "or".
The method of the shooting image in the embodiment of the present invention is applied to image picking-up apparatus, such as unmanned plane, robot, flat
Weighing apparatus car etc. has the equipment of image taking and locomotive function.Refer to Fig. 1, for the embodiment of the present invention shoots the method stream of image
Cheng Tu, the method includes:
S101: control image picking-up apparatus and scene is shot, to obtain the scene image of described scene；
S102: extract at least one element from described scene image；
S103: according to default composition rule, the object element at least one element described is patterned；
S104: control described image picking-up apparatus and shoot image according to described composition.
Specifically, in S101, first control image picking-up apparatus and scene is shot, and then obtain scene graph
Picture.In embodiments of the present invention, S101 can realize to be achieved by mode:
The many groups part scene image shot according to described image picking-up apparatus, the multiple backup scenario images of corresponding structure,
Wherein, part scene image described in each group is for building a described backup scenario image；
The mobile element in described scene is determined based on the plurality of backup scenario image；
Remove the mobile element in each described backup scenario image；
According to the plurality of backup scenario image after the described mobile element of removal, it is thus achieved that described scene image.
Specifically, each group of part scene image is for building a backup scenario image.Backup scenario image is for using
Image in structure scene image.Often group part scene image includes multiple images, and every image is to clap with different angles
Take the photograph the image that a part for scene obtains.All include owing to often organizing part scene image with a different angles photographed scene part
Image, therefore, each group of part scene image can construct a complete scene image, i.e. backup scenario image.
When utilizing one group of part scene image to build a corresponding backup scenario image, determine according to shooting time
The splicing order of part scene image.For example, one of which part scene image includes such as Fig. 2 a, Fig. 2 b and Fig. 2 c institute
Three images shown.According to the information of three images, the time of shooting image shown in Fig. 2 a is 00:01, shown in shooting Fig. 2 b
Time of image be 00:02, the time of shooting image shown in Fig. 2 c is 00:03, it is thus determined that the splicing order of this group depends on
Secondary for Fig. 2 a, Fig. 2 b with Fig. 2 c.
Then, according to splicing order, multiple image mosaic in this group are become a backup scenario image.Implementing
During, if adjacent two images have repeating part, then delete the repeating part in any one, then spell with adjacent image
Connect.For continuing to use example above, it is assumed that in Fig. 2 a, dotted line is to repeat with dotted line in right part and Fig. 2 b with left part
, in Fig. 2 b, solid line is to repeat with right part and Fig. 2 c dotted line with left part.Delete Fig. 2 b dotted line with left part and
After Fig. 2 c dotted line is with left part, Fig. 2 a, Fig. 2 b and Fig. 2 c are stitched together, the final backup scenario obtained as shown in Figure 3
Image.
Owing to the mobile element in scene is typically instability, and there is interference, so utilizing often group part scene
After image configuration goes out multiple backup scenario image, determine the mobile element in scene based on multiple backup scenario images, and from
Each backup scenario image is removed mobile element.Wherein, the element in the embodiment of the present invention refers to object correspondence in scene
Image, such as automobile, house, mountain, teacup, desk etc..
Specifically, relatively multiple backup scenario images, if the position that identity element is in each backup scenario image
Unanimously, then it represents that the object that this element is corresponding is not moved in the scene, then this element is static element；Whereas if with
One element position in each backup scenario image is not quite identical, then it represents that the object that this element is corresponding occurs in the scene
Movement, then this element is mobile element.So, by contrast, the mobile unit that in scene, position is moved has been determined that out
Element.And then, from each backup scenario image, remove mobile element.
It follows that after owing to removing mobile element, mobile element does not just have image in region originally, accordingly, it would be desirable to
The image obtaining this region from other backup scenario images supplements.Backup scenario image after supplemental image formed complete and
Static image, it is possible to as scene image.
In embodiments of the present invention, many group part scene images can be to control image picking-up apparatus by user to clap voluntarily
Taking the photograph, such as on balance car or remote control balance car rotates subscriber station, often rotates to an angle, the camera collection of balance car
One part scene image.Or, many group part scene images can also shoot for image picking-up apparatus, voluntarily specifically at root
According to many groups part scene image of image picking-up apparatus shooting, before the multiple backup scenario images of corresponding structure, perform following step
Rapid:
Control described image picking-up apparatus and start cycle rotation from the predeterminated position of described scene；
In the rotary course in each cycle, the some of described scene is shot, to obtain portion described in a group
Divide scene image.
Specifically, predeterminated position can be the center of the optional position in scene, for example, scene, or scene
In the highest position etc. of level height, the present invention is not particularly limited.Control image picking-up apparatus and offer week from predeterminated position
Phase property rotates, and interval photographed scene in the rotation in each cycle.Every rotating 360 degrees, taken by this rotating 360 degrees
Multiple part scene images, as one group of part scene image.
It can be continuous print between swing circle.In other words, upper cycle rotation immediately begins to next cycle after terminating
Rotate.Or, can also be discontinuous between swing circle.In other words, a upper cycle rotates and terminates rear capture apparatus time-out
A period of time, start the rotation in next cycle the most again.During implementing, ordinary skill people of the art
Member can be the most continuous according to actual selection swing circle, and the setting of time out when discontinuous, and the present invention does not do to be had
Body limits.
It addition, first aspect, in the rotation of different cycles, shooting angle that every part scene image is spaced can phase
Together can also be different.Such as in the rotation in a upper cycle, image picking-up apparatus often rotates one part scene graph of 30 degree of shootings
Picture, and in the rotation in next cycle, the most often rotate one part scene image of 35 degree of shootings；Or, the rotation in each cycle
In, image picking-up apparatus all rotates one part scene image of 30 degree of shootings.Second aspect, in the rotation of different cycles, claps
Take the photograph focus can be the same or different.Such as in the rotation in a upper cycle, image picking-up apparatus shoots with the focus of 3 meters,
And in the rotation in next cycle, then shoot with the focus of 7 meters；Or, in the rotation in each cycle, image picking-up apparatus
All shoot with the focus of 10 meters.
During implementing, in order to the scene image that makes finally to obtain no matter distance is the clearest, it is preferred that should adjust
Whole focus carries out the shooting in multiple cycle.Certainly, those skilled in the art can set according to actual
Putting, the present invention is not particularly limited.
After obtaining scene image, it follows that in S102, extract at least one element from scene image.Wherein, exist
In the embodiment of the present invention, extract at least one element and specifically include:
Described scene image is divided into multiple sub-scene image；
Each sub-scene image is carried out element extraction, to obtain at least one element described.
Specifically, first scene image is divided into multiple sub-scene image.During implementing, can be according to
Even partition method, it is also possible to according to repeated segmentation method, or split according to other split-runs, the present invention is not particularly limited.Its
In, even partition method refers to scene image is divided into equal-sized multiple sub-scene image equably.Repeated segmentation method, be
Refer to according to same ratio repeated segmentation scene image.It is the most proportionally 1/2 to carry out repeated segmentation.First by scene image decile
Part 1 and two parts of part 2 are become to carry out element extraction.Part 1 is divided into the 1.1st part and the 1.2nd the most again
Part, is divided into the 2.1st part by part 2 and the 2.2nd part carries out element extraction.Then, then by the 1.1st part it is divided into
1.1.1 part and 1.1.2 part, be divided into 1.2.1 part and 1.2.2 part, by the 2.1st by the 1.2nd part
Grade and be divided into 2.1.1 part and 2.1.2 part, the 2.2nd part is divided into 2.2.1 part and 2.2.2 part is entered
Row element extracts ... the rest may be inferred.
In embodiments of the present invention, in image picking-up apparatus, storage has element database.Element database contains multiple element, example
Such as elements such as automobile, house, mountain, teacup, desk, lake, hotel, the Forbidden City, the Hall of Supreme Harmony, the Monument to the People's Heroes and each
The feature of element.Certainly, user uses for convenience, improves the accuracy of element extraction, during implementing, it is also possible to
Allow user to import elemental characteristic voluntarily, and networking updates element database etc. automatically.
According to the elemental characteristic in element database, each sub-scene image is carried out characteristic matching.If at sub-scene image
The element that middle existence elemental characteristic a certain with element database mates, then by this element extraction out, and determine and extracted feature
This certain element of coupling.
It addition, it should be appreciated by one skilled in the art that above-mentioned scene image is divided into many height
Scene image, can be to be divided into multiple independent image by actual for scene image, it is also possible to for splitting in logic, i.e.
Actually not segmentation, but in different images region, perform element extraction respectively.
Further, each sub-scene image is being carried out element extraction, it is thus achieved that after at least one element, also include:
Sub-scene image according to each element place and described each element are in the sub-scene image at described place
Position, determine described each element position in described scene.
Specifically, in order to realize auto composition, in addition it is also necessary to determine each element position in the scene.Concrete next
Say, extract element time, it is thus achieved that this element coordinate (A1, A2) in the sub-scene image in place, then, in conjunction with place subfield
Scape image coordinate range [X1n, X2n] in overall scenario image and [Y1n, Y2n], calculate this element position in the scene
It is set to (A1+X1n, A2+Y1n).Wherein, A1 represents arbitrary element abscissa in the sub-scene image in place, and then this is any for A1
Element vertical coordinate in the sub-scene image in place.[X1n, X2n] represents that this arbitrary element place subfield scape is sat at scene image
Abscissa scope occupied in mark system, and the origin coordinates that X1n is occupied abscissa scope, X1n is then occupied horizontal seat
The termination coordinate of mark scope.Similarly, [Y1n, Y2n] represents this arbitrary element place subfield scape institute in scene image coordinate system
The vertical coordinate scope occupied, and the origin coordinates that Y1n is occupied vertical coordinate scope, Y2n is then occupied vertical coordinate scope
Terminate coordinate.
As an example it is assumed that extracting an element from the second sub-scene image is teacup, and teacup is at the second subfield scape
Coordinate in image is (3,4).It addition, the abscissa scope of the second sub-scene image is [60,90], vertical coordinate scope be [0,
300], therefore, teacup coordinate in scene image is just (3+60,4+0), i.e. (63,4).
It follows that perform S102, at least one element is patterned, and S104, control image picking-up apparatus shooting
Image.Specifically, when being patterned, can be patterned according to the composition rule such as three way classification, Fibonacci method.Citing
For, it is assumed that the element extracted is tower and lake, according to Fibonacci method composition principle, determines the gold that tower is placed in image
At cut-point, lake then occupies the Golden area distinction of 2/3 in image.And, calculating and to shoot by this composition, image is clapped
Take the photograph equipment and with what angle shot.And then, control the position that image picking-up apparatus moves to shoot according to above-mentioned composition
And angle, shoot image.Assume that the image that photographs is as shown in Figure 4.
In another embodiment, owing to scene there may be people, and also need to be with artificial core when shooting, therefore,
Before S103, may further comprise:
The preview image shot according to described image picking-up apparatus, identifies human body and face from described scene；
Obtain described human body position in described scene.
Specifically, before shooting, image picking-up apparatus starts preview shooting, it is thus achieved that preview image.Then, exist
In preview image, according to Generic face model, identify from preview image face and face current towards.And, according to
General human body model, identifies human body from preview image.After identifying human body, the most again by human body position in the scene
Put and read out.
Further, in conjunction with above-mentioned embodiment, in another embodiment, S103 specifically can be real by following process
Existing:
Determine from least one element described and meet pre-conditioned described object element；
According to described human body position in described scene, default facial orientation, described object element and described mesh
The position of mark element, is patterned according to described default rule.
Specifically, in embodiments of the present invention, pre-conditioned can have multiple, and then determines from least one element
Go out to meet pre-conditioned object element and also have multiple implementation.Below, just describe in detail to the most several.
The first:
Meet the group element that pre-conditioned object element is distance human body minimum.In the first implementation, carry
After taking out at least one element, according to each element position in the scene, carry out cluster calculation, thus by close together many
Individual element is divided into a group element.Then, the distance of every group element and human body is calculated.It follows that compare every group element and people
The distance of body, is defined as object element by the group element that distance is minimum.
For example, refer to Fig. 5, be a scene image schematic diagram.Small circle in Fig. 5 represents the element extracted,
The position of each small circle is exactly the position in scene image of each element.Square expression human body position in Fig. 5.
Through cluster calculation, determine three groups of small circles that in 3 group elements, i.e. Fig. 5, dotted line surrounds.By calculating, the 1st group element distance
The distance of human body is L1, and the distance of the 2nd group element distance human body is L2, and the distance of the 3rd group element distance human body is L3.Relatively
L1, L2 and L3, obtain L1 ＞ L3 ＞ L2.Accordingly, it is determined that 3 elements in the 2nd group element are object element.
The second:
Meeting pre-conditioned object element is N number of element that definition is the highest.N is positive integer, and the concrete value of N by
Those skilled in the art select, and the present invention is not particularly limited.
In the second implementation, after extracting at least one element, except needs, to obtain at least one element on the scene
Position in scape, in addition it is also necessary to obtain the definition of each element.Then, to all elements extracted, according to definition by height
It is ranked up to low.And then, sequence is defined as object element at the element of top N.
The third:
Meeting pre-conditioned object element is N number of element that color saturation is the highest.N is positive integer, and specifically the taking of N
Value is selected by those skilled in the art, and the present invention is not particularly limited.
In the third implementation, after extracting at least one element, except needs, to obtain at least one element on the scene
Position in scape, in addition it is also necessary to obtain the saturation of each element.Then, to all elements extracted, according to saturation by height
It is ranked up to low.And then, sequence is defined as object element at the element of top N.
4th kind:
Meeting pre-conditioned object element is the element chosen by user.Specifically, in the 4th kind of implementation,
After extracting at least one element, the element extracted is shown by image picking-up apparatus on the display unit, and controls every
Individual element is in treats selected state.User observes each element, according to oneself need choose one or more element.Image is clapped
Equipment of taking the photograph obtains the element chosen, using the element chosen as object element.
During implementing, those skilled in the art can according to actual selection above-mentioned four kinds
Any one in implementation or other implementations, the present invention is not particularly limited.
After determining object element, it follows that according to human body position in the scene, default facial orientation, object element
And the position of object element, it is patterned according to default rule.
Facial orientation such as front, side or the back side preset, can be configured as required.According to default face
Towards, determining and to shoot default facial orientation, image picking-up apparatus needs how to move.Such as, image picking-up apparatus is worked as
Anteposition is in the frontal of face, and the facial orientation preset is side, it is thus determined that image picking-up apparatus needs around human body
90 degree clockwise or counterclockwise.It addition, also need to human body as core, according to composition rule, object element is carried out structure
Figure.Such as, composition rule is three way classification, then human body should be placed in the region of the centre 1/3 of picture, be placed in by object element
The region of lower 1/3.Or, composition rule is Fibonacci method, then human body should be placed in golden section point, and object element is also placed in
The position of golden section point.During implementing, auto composition is suitable with the priority determining how mobile image picking-up apparatus
Sequence can arbitrarily set.
As an example it is assumed that object element is the Cocos nucifera L. in Fig. 6, the circle in Fig. 6 represents the position of human body of user, and
Arrow in circle then represent face towards.It is patterned according to Fibonacci method, determines and face and Cocos nucifera L. are placed in
In golden section point.Meanwhile, the position of square expression image picking-up apparatus in Fig. 6.The facial orientation preset is side, due to this
Time image picking-up apparatus in the face of the front of face, it is therefore desirable to around human body counterclockwise 90-degree rotation.And then, image taking
Equipment 90-degree rotation, to the position shown in Fig. 7, shoots image as shown in Figure 8 according to composition.
Again as an example it is assumed that the element extracted is the sun, mountain and automobile, according to the default bar that distance human body is nearest
Part, determines that object element is the automobile in Fig. 9.Circle in Fig. 9 represents the position of human body of user, the then table of the arrow in circle
Let others have a look at face towards.Be patterned according to three way classification, determine human body in the region of central authorities 1/3, automobile is also placed in central authorities 1/3
In region.Meanwhile, the position of square expression image picking-up apparatus in Fig. 6.The facial orientation preset is front, due to now image
Capture apparatus, in the face of the front of face, therefore need not adjust camera site.And then, image picking-up apparatus is shot according to composition
Image as shown in Figure 10.
Based on the same inventive concept of method with above-mentioned shooting image, the embodiment of the present invention additionally provides a kind of shooting image
Device, as shown in figure 11, including:
First control module 101, is used for controlling image picking-up apparatus and shoots scene, to obtain the field of described scene
Scape image；
First extraction module 102, for extracting at least one element from described scene image；
First composition module 103, for according to default composition rule, enters the object element at least one element described
Row composition；
Second control module 104, is used for controlling described image picking-up apparatus and shoots image according to described composition.
Optionally, described first control module 101 is for the many groups part scene shot according to described image picking-up apparatus
Image, the multiple backup scenario images of corresponding structure, wherein, part scene image described in each group is described standby for building one
Scene image；The mobile element in described scene is determined based on the plurality of backup scenario image；Remove each described standby
Mobile element in scene image；According to the plurality of backup scenario image after the described mobile element of removal, it is thus achieved that described field
Scape image.
Optionally, described first extraction module 102 for being divided into multiple sub-scene image by described scene image；To often
Individual sub-scene image carries out element extraction, to obtain at least one element described.
Optionally, described device also includes that first determines module, for each sub-scene image is being carried out element extraction,
After obtaining at least one element described, sub-scene image and described each element according to each element place are described
Position in the sub-scene image at place, determines described each element position in described scene.
Optionally, described device also includes identification module, for entering the object element at least one element described
Before row composition, the preview image shot according to described image picking-up apparatus, identifies human body and face from described scene；Obtain
Obtain described human body position in described scene.
Optionally, described first composition module 103 for determine from least one element described meet pre-conditioned
Described object element；According to described human body position in described scene, default facial orientation, described object element and
The position of described object element, is patterned according to described default rule.
Optionally, described device also includes the 3rd control module, for shooting many according to described image picking-up apparatus
Group part scene image, before the multiple backup scenario images of corresponding structure, controls described image picking-up apparatus from described scene
Predeterminated position starts cycle rotation；
Packet taking module, in the rotary course in each cycle, shoots the some of described scene,
To obtain part scene image described in a group.
Beneficial effects of the present invention is as follows:
In embodiments of the present invention, first control image picking-up apparatus scene is shot, it is thus achieved that scene image, then
At least one element is extracted, the most automatically according to default composition rule, at least one element from scene image
Object element is patterned, and the final image picking-up apparatus that controls shoots image according to composition.Visible, due to according to default composition method
Then it is automatically performed composition and shoots so that the image picking-up apparatus in the embodiment of the present invention can be independent of the automatic structure of user
Figure, so, solve the technical problem that in prior art, robot can not automatically snap, it is achieved that auto composition the skill shot
Art effect.
Obviously, those skilled in the art can carry out various change and the modification essence without deviating from the present invention to the present invention
God and scope.So, if these amendments of the present invention and modification belong to the scope of the claims in the present invention and equivalent technologies thereof
Within, then the present invention is also intended to comprise these change and modification.
Claims (14)
1. the method shooting image, it is characterised in that including:
Control image picking-up apparatus scene to be shot, to obtain the scene image of described scene；
At least one element is extracted from described scene image；
According to default composition rule, the object element at least one element described is patterned；
Control described image picking-up apparatus and shoot image according to described composition.
2. the method shooting image as claimed in claim 1, it is characterised in that control image picking-up apparatus and scene is clapped
Take the photograph, to obtain the scene image of described scene, including:
The many groups part scene image shot according to described image picking-up apparatus, the multiple backup scenario images of corresponding structure, wherein,
Part scene image described in each group is for building a described backup scenario image；
The mobile element in described scene is determined based on the plurality of backup scenario image；
Remove the mobile element in each described backup scenario image；
According to the plurality of backup scenario image after the described mobile element of removal, it is thus achieved that described scene image.
3. the method shooting image as claimed in claim 2, it is characterised in that extract at least from described scene image
Individual element, including:
Described scene image is divided into multiple sub-scene image；
Each sub-scene image is carried out element extraction, to obtain at least one element described.
4. the method shooting image as claimed in claim 3, it is characterised in that carry each sub-scene image is carried out element
Take, after obtaining at least one element described, also include:
Sub-scene image according to each element place and described each element position in the sub-scene image at described place
Put, determine described each element position in described scene.
5. the method shooting image as claimed in claim 4, it is characterised in that to the target at least one element described
Before element is patterned, also include:
The preview image shot according to described image picking-up apparatus, identifies human body and face from described scene；
Obtain described human body position in described scene.
6. the as claimed in claim 5 method shooting image, it is characterised in that according to default composition rule, to described at least
Object element in one element is patterned, including:
Determine from least one element described and meet pre-conditioned described object element；
According to described human body position in described scene, default facial orientation, described object element and described target element
The position of element, is patterned according to described default rule.
7. the method shooting image as claimed in claim 2, it is characterised in that shoot according to described image picking-up apparatus
Many group part scene images, before the multiple backup scenario images of corresponding structure, also include:
Control described image picking-up apparatus and start cycle rotation from the predeterminated position of described scene；
In the rotary course in each cycle, the some of described scene is shot, to obtain part field described in a group
Scape image.
8. the device shooting image, it is characterised in that including:
First control module, is used for controlling image picking-up apparatus and shoots scene, to obtain the scene image of described scene；
First extraction module, for extracting at least one element from described scene image；
First composition module, for according to default composition rule, is patterned the object element at least one element described；
Second control module, is used for controlling described image picking-up apparatus and shoots image according to described composition.
9. device as claimed in claim 8, it is characterised in that described first control module is for setting according to described image taking
Many groups part scene image of standby shooting, the multiple backup scenario images of corresponding structure, wherein, part scene image described in each group
For building a described backup scenario image；The mobile unit in described scene is determined based on the plurality of backup scenario image
Element；Remove the mobile element in each described backup scenario image；The plurality of standby according to remove after described mobile element
Scene image, it is thus achieved that described scene image.
10. device as claimed in claim 9, it is characterised in that described first extraction module is for dividing described scene image
It is slit into multiple sub-scene image；Each sub-scene image is carried out element extraction, to obtain at least one element described.
11. devices as claimed in claim 10, it is characterised in that described device also includes that first determines module, for right
Each sub-scene image carries out element extraction, after obtaining at least one element described, according to the subfield at each element place
Scape image and described each element position in the sub-scene image at described place, determine that described each element is in described field
Position in scape.
12. devices as claimed in claim 11, it is characterised in that described device also includes identification module, for described
Before object element at least one element is patterned, the preview image shot according to described image picking-up apparatus, from institute
State and scene identifies human body and face；Obtain described human body position in described scene.
13. devices as claimed in claim 12, it is characterised in that described first composition module is for from least one unit described
Element is determined and meets pre-conditioned described object element；According to described human body position in described scene, default people
Face, towards, described object element and the position of described object element, is patterned according to described default rule.
14. devices as claimed in claim 9, it is characterised in that described device also includes the 3rd control module, in basis
Many groups part scene image of described image picking-up apparatus shooting, before the multiple backup scenario images of corresponding structure, controls described
Image picking-up apparatus starts cycle rotation from the predeterminated position of described scene；
Packet taking module, in the rotary course in each cycle, shoots the some of described scene, to obtain
Part scene image described in obtaining one group.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610555364.5A CN106131411B (en) | 2016-07-14 | 2016-07-14 | A kind of method and apparatus shooting image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610555364.5A CN106131411B (en) | 2016-07-14 | 2016-07-14 | A kind of method and apparatus shooting image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106131411A true CN106131411A (en) | 2016-11-16 |
| CN106131411B CN106131411B (en) | 2019-04-02 |
Family
ID=57283310
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610555364.5A Active CN106131411B (en) | 2016-07-14 | 2016-07-14 | A kind of method and apparatus shooting image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106131411B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107357312A (en) * | 2017-07-28 | 2017-11-17 | 上海瞬动科技有限公司合肥分公司 | A kind of UAV Intelligent flight control method based on target pattern |
| CN107705307A (en) * | 2017-11-09 | 2018-02-16 | 睿魔智能科技（东莞）有限公司 | A kind of shooting patterning process and system based on deep learning |
| CN107888822A (en) * | 2017-10-27 | 2018-04-06 | 珠海市魅族科技有限公司 | Image pickup method, device, terminal and readable storage medium storing program for executing |
| CN108234867A (en) * | 2017-12-21 | 2018-06-29 | 维沃移动通信有限公司 | Image processing method and mobile terminal |
| CN108289169A (en) * | 2018-01-09 | 2018-07-17 | 北京小米移动软件有限公司 | Image pickup method, device, electronic equipment and storage medium |
| WO2018133305A1 (en) * | 2017-01-19 | 2018-07-26 | 华为技术有限公司 | Method and device for image processing |
| CN108366203A (en) * | 2018-03-01 | 2018-08-03 | 北京金山安全软件有限公司 | Composition method, composition device, electronic equipment and storage medium |
| WO2018214401A1 (en) * | 2017-05-26 | 2018-11-29 | 深圳市大疆创新科技有限公司 | Mobile platform, flying object, support apparatus, portable terminal, method for assisting in photography, program and recording medium |
| CN110826564A (en) * | 2019-11-01 | 2020-02-21 | 山东浪潮人工智能研究院有限公司 | A method and system for semantic segmentation of small objects in complex scene images |
| CN110830712A (en) * | 2019-09-16 | 2020-02-21 | 幻想动力(上海)文化传播有限公司 | Autonomous photographing system and method |
| CN111432114A (en) * | 2019-12-31 | 2020-07-17 | 武汉星巡智能科技有限公司 | Grading method, device and equipment based on shooting composition and storage medium |
| WO2021056442A1 (en) * | 2019-09-27 | 2021-04-01 | 深圳市大疆创新科技有限公司 | Composition method and system for photographing device, and storage medium |
| WO2022188151A1 (en) * | 2021-03-12 | 2022-09-15 | 深圳市大疆创新科技有限公司 | Image photographing method, control apparatus, movable platform, and computer storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7756322B2 (en) * | 2003-08-18 | 2010-07-13 | Honda Motor Co., Ltd. | Picture taking mobile robot |
| CN104243787A (en) * | 2013-06-06 | 2014-12-24 | 华为技术有限公司 | Photographing method and equipment, and photo management method |
| CN104717413A (en) * | 2013-12-12 | 2015-06-17 | 北京三星通信技术研究有限公司 | Shooting assistance method and equipment |
| CN105052123A (en) * | 2013-03-27 | 2015-11-11 | 奥林巴斯株式会社 | Image pickup device, composition assist device, composition assist method, and composition assist program |
| CN105100728A (en) * | 2015-08-18 | 2015-11-25 | 零度智控（北京）智能科技有限公司 | Unmanned aerial vehicle video tracking shooting system and method |
| CN105512643A (en) * | 2016-01-06 | 2016-04-20 | 北京二郎神科技有限公司 | Image acquisition method and device |
| CN105991925A (en) * | 2015-03-06 | 2016-10-05 | 联想(北京)有限公司 | Scene composition indicating method and indicating device |
-
2016
- 2016-07-14 CN CN201610555364.5A patent/CN106131411B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7756322B2 (en) * | 2003-08-18 | 2010-07-13 | Honda Motor Co., Ltd. | Picture taking mobile robot |
| CN105052123A (en) * | 2013-03-27 | 2015-11-11 | 奥林巴斯株式会社 | Image pickup device, composition assist device, composition assist method, and composition assist program |
| CN104243787A (en) * | 2013-06-06 | 2014-12-24 | 华为技术有限公司 | Photographing method and equipment, and photo management method |
| CN104717413A (en) * | 2013-12-12 | 2015-06-17 | 北京三星通信技术研究有限公司 | Shooting assistance method and equipment |
| CN105991925A (en) * | 2015-03-06 | 2016-10-05 | 联想(北京)有限公司 | Scene composition indicating method and indicating device |
| CN105100728A (en) * | 2015-08-18 | 2015-11-25 | 零度智控（北京）智能科技有限公司 | Unmanned aerial vehicle video tracking shooting system and method |
| CN105512643A (en) * | 2016-01-06 | 2016-04-20 | 北京二郎神科技有限公司 | Image acquisition method and device |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109479087B (en) * | 2017-01-19 | 2020-11-17 | 华为技术有限公司 | Image processing method and device |
| WO2018133305A1 (en) * | 2017-01-19 | 2018-07-26 | 华为技术有限公司 | Method and device for image processing |
| CN109479087A (en) * | 2017-01-19 | 2019-03-15 | 华为技术有限公司 | Method and device for image processing |
| WO2018214401A1 (en) * | 2017-05-26 | 2018-11-29 | 深圳市大疆创新科技有限公司 | Mobile platform, flying object, support apparatus, portable terminal, method for assisting in photography, program and recording medium |
| CN109863745A (en) * | 2017-05-26 | 2019-06-07 | 深圳市大疆创新科技有限公司 | Mobile platform, flying body support device, portable terminal, camera shooting householder method, program and recording medium |
| CN107357312A (en) * | 2017-07-28 | 2017-11-17 | 上海瞬动科技有限公司合肥分公司 | A kind of UAV Intelligent flight control method based on target pattern |
| CN107888822A (en) * | 2017-10-27 | 2018-04-06 | 珠海市魅族科技有限公司 | Image pickup method, device, terminal and readable storage medium storing program for executing |
| CN107705307A (en) * | 2017-11-09 | 2018-02-16 | 睿魔智能科技（东莞）有限公司 | A kind of shooting patterning process and system based on deep learning |
| CN107705307B (en) * | 2017-11-09 | 2021-01-01 | 睿魔智能科技（东莞）有限公司 | Shooting composition method and system based on deep learning |
| CN108234867A (en) * | 2017-12-21 | 2018-06-29 | 维沃移动通信有限公司 | Image processing method and mobile terminal |
| CN108289169A (en) * | 2018-01-09 | 2018-07-17 | 北京小米移动软件有限公司 | Image pickup method, device, electronic equipment and storage medium |
| CN108366203B (en) * | 2018-03-01 | 2020-10-13 | 北京金山安全软件有限公司 | Composition method, composition device, electronic equipment and storage medium |
| CN108366203A (en) * | 2018-03-01 | 2018-08-03 | 北京金山安全软件有限公司 | Composition method, composition device, electronic equipment and storage medium |
| CN110830712A (en) * | 2019-09-16 | 2020-02-21 | 幻想动力(上海)文化传播有限公司 | Autonomous photographing system and method |
| WO2021056442A1 (en) * | 2019-09-27 | 2021-04-01 | 深圳市大疆创新科技有限公司 | Composition method and system for photographing device, and storage medium |
| CN110826564A (en) * | 2019-11-01 | 2020-02-21 | 山东浪潮人工智能研究院有限公司 | A method and system for semantic segmentation of small objects in complex scene images |
| CN111432114A (en) * | 2019-12-31 | 2020-07-17 | 武汉星巡智能科技有限公司 | Grading method, device and equipment based on shooting composition and storage medium |
| CN111432114B (en) * | 2019-12-31 | 2021-08-24 | 宁波星巡智能科技有限公司 | Grading method, device and equipment based on shooting composition and storage medium |
| WO2022188151A1 (en) * | 2021-03-12 | 2022-09-15 | 深圳市大疆创新科技有限公司 | Image photographing method, control apparatus, movable platform, and computer storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106131411B (en) | 2019-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106131411A (en) | A kind of method and apparatus shooting image | |
| CN103297697A (en) | Method and device for displaying template pictures during photographing | |
| CN106843460B (en) | Multiple target position capture positioning system and method based on multi-cam | |
| CN110545378B (en) | Intelligent recognition shooting system and method for multi-person scene | |
| CN111935393A (en) | Shooting method, shooting device, electronic equipment and storage medium | |
| CN109889708A (en) | Dual aperture zoom digital camera with automatically adjustable telephoto field of view | |
| CN107925753A (en) | The method and system of 3D rendering seizure is carried out using dynamic camera | |
| WO2019041276A1 (en) | Image processing method, and unmanned aerial vehicle and system | |
| CN106131418A (en) | A kind of composition control method, device and photographing device | |
| CN106851094A (en) | A kind of information processing method and device | |
| CN106586011A (en) | Aligning method of aerial shooting unmanned aerial vehicle and aerial shooting unmanned aerial vehicle thereof | |
| CN106101575B (en) | Augmented reality photo generation method and device and mobile terminal | |
| CN106780629A (en) | A kind of three-dimensional panorama data acquisition, modeling method | |
| CN113240615B (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| CN104767975A (en) | Method for achieving interactive panoramic video stream map | |
| CN109948423B (en) | Unmanned aerial vehicle travel accompanying service method applying face and posture recognition and unmanned aerial vehicle | |
| CN104883506A (en) | Self-service shooting method based on face identification technology | |
| CN101872243A (en) | System and method for realizing 360-degree panoramic play following real space direction | |
| CN109769326A (en) | A method, device and equipment for chasing light | |
| CN117170504B (en) | Method, system and storage medium for viewing with person in virtual character interaction scene | |
| CN108629828A (en) | Scene rendering transition method in the moving process of three-dimensional large scene | |
| CN107995481A (en) | The display methods and device of a kind of mixed reality | |
| CN108259787B (en) | Panoramic video switching device and method | |
| CN110830712A (en) | Autonomous photographing system and method | |
| CN104474710A (en) | System and method for tracking group users in large-scale scenes on basis of Kinect networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |