CN106131411B - A kind of method and apparatus shooting image - Google Patents
A kind of method and apparatus shooting image Download PDFInfo
- Publication number
- CN106131411B CN106131411B CN201610555364.5A CN201610555364A CN106131411B CN 106131411 B CN106131411 B CN 106131411B CN 201610555364 A CN201610555364 A CN 201610555364A CN 106131411 B CN106131411 B CN 106131411B
- Authority
- CN
- China
- Prior art keywords
- image
- scene
- sub
- shooting
- scene image
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 239000000203 mixture Substances 0.000 claims abstract description 57
- 238000000605 extraction Methods 0.000 claims description 22
- 230000001815 facial effect Effects 0.000 claims description 11
- 239000000284 extract Substances 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 9
- 230000011218 segmentation Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000010276 construction Methods 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
- 230000008676 import Effects 0.000 description 1
- 230000003137 locomotive effect Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- CCEKAJIANROZEO-UHFFFAOYSA-N sulfluramid Chemical group CCNS(=O)(=O)C(F)(F)C(F)(F)C(F)(F)C(F)(F)C(F)(F)C(F)(F)C(F)(F)C(F)(F)F CCEKAJIANROZEO-UHFFFAOYSA-N 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000000153 supplemental effect 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
- H04N23/64—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; CALCULATING OR 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 more particularly to a kind of method and apparatus for shooting image.The method and apparatus of shooting image provided in an embodiment of the present invention, for realizing auto composition and the technical effect that is shot.The method of the shooting image includes: that control image picking-up apparatus shoots scene, to obtain the scene image of the scene;At least one element is extracted from the scene image;According to default composition rule, the object element at least one described element is patterned;It controls described image capture apparatus and shoots image according to the composition.
Description
Technical field
The present invention relates to electronic technology field more particularly to a kind of method and apparatus for shooting image.
Background technique
In recent years, unmanned plane, and the intelligent robot for having shooting function occur gradually in the visual field of people.Nobody
The appearance of machine and the robot for having shooting function (hereinafter referred to as the two is " robot "), so that user does not need to go one in person
Place that is a little inconvenient or being unable to reach is shot, such as volcano or city overhead etc..So robot to clap
It takes the photograph more convenient.
However, although robot can replace user and go to shoot in person, with what angle shot and how composition, still
So need to rely on the control of user.So there is technical issues that cannot for robot in the prior art.
Summary of the invention
The embodiment of the invention provides a kind of method and apparatus for shooting image, for realizing auto composition and are shot
Technical effect.
In a first aspect, the present invention provides a kind of methods for shooting image, comprising:
Control image picking-up apparatus shoots scene, to obtain the scene image of the scene;
At least one element is extracted from the scene image;
According to default composition rule, the object element at least one described element is patterned;
It controls described image capture apparatus and shoots image according to the composition.
Optionally, control image picking-up apparatus shoots scene, to obtain the scene image of the scene, comprising:
It is corresponding to construct multiple backup scenario images according to the multiple groups part scene image that described image capture apparatus is shot,
Wherein, part scene image described in each group is for constructing a backup scenario image;
The mobile element in the scene is determined based on the multiple backup scenario image;
Remove the mobile element in each backup scenario image;
According to the multiple backup scenario image after the removal mobile element, the scene image is obtained.
Optionally, at least one element is extracted from the scene image, comprising:
The scene image is divided into multiple sub-scene images;
Element extraction is carried out to each sub-scene image, to obtain at least one described element.
Optionally, element extraction is being carried out to each sub-scene image, after obtaining at least one described element, also wrapped
It includes:
Sub-scene image and each element where each element is in the sub-scene image at the place
Position, determine position of each element in the scene.
Optionally, before being patterned to the object element at least one described element, further includes:
According to the preview image that described image capture apparatus is shot, human body and face are identified from the scene;
Obtain position of the human body in the scene.
Optionally, according to default composition rule, the object element at least one described element is patterned, comprising:
The object element for meeting preset condition is determined from least one described element;
According to position of the human body in the scene, preset facial orientation, the object element and the mesh
The position for marking element, is patterned according to the default rule.
Optionally, in the multiple groups part scene image shot according to described image capture apparatus, corresponding building is multiple spare
Before scene image, further includes:
Control the period rotation since the predeterminated position of the scene of described image capture apparatus;
In the rotary course in each period, the multiple portions of the scene are shot, with portion described in one group of acquisition
Divide scene image.
Second aspect, the present invention provides a kind of devices for shooting image, comprising:
First control module shoots scene for controlling image picking-up apparatus, to obtain the scene of the scene
Image;
First extraction module, for extracting at least one element from the scene image;
First composition module, for being carried out to the object element at least one described element according to default composition rule
Composition;
Second control module shoots image according to the composition for controlling described image capture apparatus.
Optionally, first control module is used for the multiple groups part scene figure shot according to described image capture apparatus
Picture, it is corresponding to construct multiple backup scenario images, wherein part scene image described in each group is for constructing an alternate aerodrome
Scape image;The mobile element in the scene is determined based on the multiple backup scenario image;Remove each alternate aerodrome
Mobile element in scape image;According to the multiple backup scenario image after the removal mobile element, the scene is obtained
Image.
Optionally, first extraction module is used to the scene image being divided into multiple sub-scene images;To each
Sub-scene image carries out element extraction, to obtain at least one described element.
Optionally, described device further includes the first determining module, for carrying out element extraction to each sub-scene image,
After obtaining at least one described element, the sub-scene image and each element where each element are described
Position in the sub-scene image at place determines position of each element in the scene.
Optionally, described device further includes identification module, for the object element at least one described element into
Before row composition, according to the preview image that described image capture apparatus is shot, human body and face are identified from the scene;It obtains
Obtain position of the human body in the scene.
Optionally, the first composition module is used to determine the institute for meeting preset condition from least one described element
State object element;According to position of the human body in the scene, preset facial orientation, the object element and described
The position of object element is patterned according to the default rule.
Optionally, described device further includes third control module, for shot according to described image capture apparatus it is more
Group part scene image corresponds to before constructing multiple backup scenario images, controls described image capture apparatus from the scene
Predeterminated position starts period rotation;
It is grouped shooting module, for being shot to the multiple portions of the scene in the rotary course in each period,
With part scene image described in one group of acquisition.
Beneficial effects of the present invention are as follows:
In embodiments of the present invention, control image picking-up apparatus first shoots scene, obtains scene image, then
At least one element is extracted from scene image, further automatically according to default composition rule, at least one element
Object element is patterned, and the final image picking-up apparatus that controls is according to composition shooting image.As it can be seen that due to according to default composition method
It is then automatically performed composition and is shot, the image picking-up apparatus in the embodiment of the present invention is allowed not depend on the automatic structure of user
Figure, so, solve the technical issues of robot cannot automatically snap in the prior art, the skill for realizing auto composition and shooting
Art effect.
Detailed description of the invention
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 of the building of the part scene image as 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 the position view of an object element and shooting vision facilities in the embodiment of the present invention;
Fig. 7 is the object element and the postrotational position view of image picking-up apparatus in Fig. 6;
Fig. 8 is image schematic diagram captured by image picking-up apparatus position shown in Fig. 7;
Fig. 9 is the position view of another object element and shooting vision facilities in the embodiment of the present invention;
Figure 10 is image schematic diagram captured by image picking-up apparatus position shown in Fig. 9;
Figure 11 is the apparatus structure schematic diagram of the shooting image in the embodiment of the present invention.
Specific embodiment
The embodiment of the invention provides a kind of method and apparatus for shooting image, for realizing auto composition and are shot
Technical effect.
In order to solve the above-mentioned technical problem, in embodiments of the present invention, control image picking-up apparatus carries out scene first
Shooting obtains scene image, at least one element is then extracted from scene image, further automatically according to default composition method
Then, the object element at least one element is patterned, the final image picking-up apparatus that controls is according to composition shooting image.It can
See, due to being automatically performed composition according to default composition rule and being shot, so that the image taking in the embodiment of the present invention is set
It is standby not depend on user's auto composition, so, solve the technical issues of robot cannot automatically snap in the prior art, it is real
The technical effect for having showed auto composition and having shot.
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
In addition, the terms "and/or", only a kind of incidence relation for describing affiliated partner, indicates may exist
Three kinds of relationships, for example, A and/or B, can indicate: individualism A exists simultaneously A and B, these three situations of individualism B.Separately
Outside, character "/" herein typicallys represent the relationship that forward-backward correlation object is a kind of "or".
The method of shooting image in the embodiment of the present invention is applied to image picking-up apparatus, such as unmanned plane, robot, flat
Weigh the equipment with image taking and locomotive function such as vehicle.Referring to FIG. 1, to shoot the method stream of image in the embodiment of the present invention
Cheng Tu, this method comprises:
S101: control image picking-up apparatus shoots scene, to obtain the scene image of the scene;
S102: at least one element is extracted from the scene image;
S103: according to default composition rule, the object element at least one described element is patterned;
S104: control described image capture apparatus shoots image according to the composition.
Specifically, in S101, control image picking-up apparatus first shoots scene, and then obtains scene figure
Picture.In embodiments of the present invention, S101 can be achieved by the following procedure mode and realize:
It is corresponding to construct multiple backup scenario images according to the multiple groups part scene image that described image capture apparatus is shot,
Wherein, part scene image described in each group is for constructing a backup scenario image;
The mobile element in the scene is determined based on the multiple backup scenario image;
Remove the mobile element in each backup scenario image;
According to the multiple backup scenario image after the removal mobile element, the scene image is obtained.
Specifically, each group of part scene image is for constructing a backup scenario image.Backup scenario image is to use
In the image of construction scene image.It include multiple images in every group of part scene image, and every image is to be clapped with different angle
Take the photograph the image that a part of scene obtains.Since every group of part scene image all includes with different angle photographed scene a part
Image, therefore, each group of part scene image can construct a complete scene image, i.e. backup scenario image.
When constructing a corresponding backup scenario image using one group of part scene image, determined according to shooting time
The splicing sequence of part scene image.For example, wherein including such as Fig. 2 a, Fig. 2 b and Fig. 2 c institute in one group of part scene image
Three images shown.According to the information of three images, the time of image shown in shooting figure 2a is 00:01, shown in shooting figure 2b
Time of image be 00:02, the time of image shown in shooting figure 2c is 00:03, it is thus determined that the splicing sequence of the group according to
Secondary is Fig. 2 a, Fig. 2 b and Fig. 2 c.
Then, according to splicing sequence, by multiple image mosaics in the group at a backup scenario image.It is implementing
In the process, if adjacent two images have repeating part, the repeating part in any one is deleted, then spell with adjacent image
It connects.It continues to use for example above, it is assumed that dotted line is to repeat with left part with dotted line in right part and Fig. 2 b in Fig. 2 a
, solid line is duplicate with left part with right part and Fig. 2 c dotted line in Fig. 2 b.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, backup scenario as shown in Figure 3 is finally obtained
Image.
Since the mobile element in scene is usually unstable, and there is interference, so utilizing every group of part scene
After image configuration goes out multiple backup scenario images, the mobile element in scene is determined based on multiple backup scenario images, and from
Mobile element is removed in each backup scenario image.Wherein, the element in the embodiment of the present invention refers to that object is corresponding in scene
Image, such as automobile, house, mountain, teacup, desk etc..
Specifically, more multiple backup scenario images, if position of the identity element in each backup scenario image
Unanimously, then it represents that the corresponding object of the element does not move in the scene, then the element is static element;, whereas if same
Position of one element in each backup scenario image is not quite identical, then it represents that the corresponding object of the element occurs in the scene
Movement, then the element is mobile element.So, by comparison, determined that out that mobile mobile member occurs for position in scene
Element.In turn, mobile element is removed from each backup scenario image.
Next, after due to removal mobile element, mobile element script region just without image, therefore, it is necessary to
The image in the region is obtained from other backup scenario images to supplement.Backup scenario image after supplemental image formed it is complete and
Static image can be used as scene image.
In embodiments of the present invention, multiple groups part scene image can be voluntarily to be clapped by user's control image picking-up apparatus
It takes the photograph, such as subscriber station is on balance car or remote control balance car rotates, and often rotates by a certain angle, the camera acquisition of balance car
One part scene image.Alternatively, multiple groups part scene image may be that image picking-up apparatus is voluntarily shot, specifically in root
It according to the multiple groups part scene image that image picking-up apparatus is shot, corresponds to before constructing multiple backup scenario images, executes following step
It is rapid:
Control the period rotation since the predeterminated position of the scene of described image capture apparatus;
In the rotary course in each period, the multiple portions of the scene are shot, with portion described in one group of acquisition
Divide scene image.
Specifically, predeterminated position can be any position in scene, for example, center of scene or scene
In the highest position of level height etc., the present invention is not particularly limited.It controls image picking-up apparatus and opens up week from predeterminated position
The rotation of phase property, and the interval photographed scene in the rotation in each period.It is often rotated by 360 °, this is rotated by 360 ° taken
Multiple part scene images, as one group of part scene image.
It can be continuous between swing circle.In other words, next period is immediately begun to after upper period rotation
Rotation.Alternatively, between swing circle or discontinuous.In other words, capture apparatus suspends after upper period rotation
For a period of time, then start the rotation in next period again.During specific implementation, ordinary skill people of the art
Member can whether continuous according to actual selection swing circle, and when discontinuous time out setting, the present invention, which is not done, to be had
Body limitation.
In addition, in a first aspect, the angle that every part scene image of shooting is spaced can phase in the rotation of different cycles
It is same to can also be different.Such as in the rotation in a upper period, every rotation 30 degree of shootings, the one part scene figure of image picking-up apparatus
Picture, and in the rotation in next period, then every rotation 35 degree of shootings, one part scene image;Alternatively, the rotation in each period
In, image picking-up apparatus rotates 30 degree of shootings, one part scene image.Second aspect is clapped in the rotation of different cycles
Taking the photograph focus can be the same or different.Such as in the rotation in a upper period, image picking-up apparatus is shot with 3 meters of focus,
And in the rotation in next period, then it is shot with 7 meters of focus;Alternatively, in the rotation in each period, image picking-up apparatus
Shot with 10 meters of focus.
During specific implementation, in order to which the no matter far and near clear of the scene image finally obtained made, preferably, should adjust
Whole focus carries out the shooting in multiple periods.Certainly, those skilled in the art can be according to actually setting
It sets, the present invention is not particularly limited.
After obtaining scene image, next, extracting at least one element from scene image in S102.Wherein, exist
In the embodiment of the present invention, extracts at least one element and specifically includes:
The scene image is divided into multiple sub-scene images;
Element extraction is carried out to each sub-scene image, to obtain at least one described element.
Specifically, scene image is divided into multiple sub-scene images first.It, can be according to during specific implementation
Even partition method can also be divided according to repeated segmentation method, or according to other split plot designs, and the present invention is not particularly limited.Its
In, even partition method, which refers to, is equably divided into scene image equal-sized multiple sub-scene images.Repeated segmentation method is
Refer to according to same ratio repeated segmentation scene image.Such as repeated segmentation proportionally is carried out for 1/2.First by scene image equal part
Element extraction is carried out at two parts of part 1 and part 2.Then part 1 is divided into the 1.1st part and the 1.2nd again
Part 2 is divided into the 2.1st part and the 2.2nd part and carries out element extraction by part.Then, then by the 1.1st part it is divided into
1.2nd part is divided into the part 1.2.1 and the part 1.2.2, by the 2.1st by the part 1.1.1 and the part 1.1.2
Point be divided into the part 2.1.1 and the part 2.1.2, by the 2.2nd part be divided into the part 2.2.1 and the part 2.2.2 into
Row element extracts ..., and the rest may be inferred.
In embodiments of the present invention, element database is stored in image picking-up apparatus.Multiple elements, example are contained in element database
Such as automobile, house, mountain, teacup, desk, lake, hotel, the Forbidden City, the Hall of Supreme Harmony, Monument to the People's Heroes element, and it is each
The feature of element.Certainly, in order to facilitate user's use, the accuracy of element extraction is improved, it, can be with during specific implementation
User is allowed voluntarily to import elemental characteristic, and automatic networking updates element database etc..
According to the elemental characteristic in element database, characteristic matching is carried out to each sub-scene image.If in sub-scene image
It is middle to exist with the matched element of elemental characteristic a certain in element database, then the element extraction is come out, and feature has been extracted in determination
The matched a certain element.
In addition, it should be appreciated by one skilled in the art that above-mentioned be divided into multiple sons for scene image
Scene image can be and scene image is physically actually divided into multiple independent images, or divides in logic, i.e.,
Actually there is no segmentations, but execute element extraction respectively in different images region.
Further, element extraction is being carried out to each sub-scene image, after obtaining at least one element, further includes:
Sub-scene image and each element where each element is in the sub-scene image at the place
Position, determine position of each element in the scene.
Specifically, in order to realizing auto composition, it is also necessary to determine the position of each element in the scene.It is specific next
Say, extract element when, coordinate (A1, A2) of the element in the sub-scene image of place is obtained, then, in conjunction with place subfield
Coordinate range [X1n, X2n] and [Y1n, Y2n] of the scape image in overall scenario image, calculate the position of the element in the scene
It is set to (A1+X1n, A2+Y1n).Wherein, A1 indicates abscissa of the arbitrary element in the sub-scene image of place, and then this is any by A1
Ordinate of the element in the sub-scene image of place.Sub-scene where [X1n, X2n] indicates the arbitrary element is sat in scene image
Occupied abscissa range in mark system, and X1n is the origin coordinates of occupied abscissa range, X1n is then occupied horizontal seat
Mark the terminating coordinates of range.Similarly, sub-scene institute in scene image coordinate system where [Y1n, Y2n] indicates the arbitrary element
The ordinate range occupied, and Y1n is the origin coordinates of occupied ordinate range, Y2n is then occupied ordinate range
Terminating coordinates.
As an example it is assumed that extracting an element from the second sub-scene image is teacup, and teacup is in the second sub-scene
Coordinate in image is (3,4).In addition, the abscissa range of the second sub-scene image be [60,90], ordinate range be [0,
300], therefore, coordinate of the teacup in scene image is just (3+60,4+0), i.e. (63,4).
Next, executing S102, at least one element is patterned and S104, control image picking-up apparatus are shot
Image.Specifically, it when being patterned, can be patterned according to the compositions such as trichotomy, Fibonacci method rule.Citing
For, it is assumed that the element extracted is tower and lake, according to Fibonacci method composition principle, the determining gold that tower is placed in image
At cut-point, and lake then occupies in image 2/3 Golden area distinction.And calculate and to be shot by this composition, image is clapped
Take the photograph equipment and with what angle shot.In turn, control image picking-up apparatus is moved to the position that can be shot according to above-mentioned composition
And angle, shoot image.Assuming that the image taken is as shown in Figure 4.
In another embodiment, since there may be people in scene, and when shooting need to also taking human as core, therefore,
Before S103, it may further comprise:
According to the preview image that described image capture apparatus is shot, human body and face are identified from the scene;
Obtain position of the human body in the scene.
Specifically, before being shot, image picking-up apparatus starts preview shooting, obtains preview image.Then, exist
In preview image, according to Generic face model, face and the current direction of face are identified from preview image.And according to
General human body model, identifies human body from preview image.After identifying human body, the further position by human body in the scene again
It sets and reads out.
Further, in conjunction with above embodiment, in another embodiment, S103 specifically can be real by following process
It is existing:
The object element for meeting preset condition is determined from least one described element;
According to position of the human body in the scene, preset facial orientation, the object element and the mesh
The position for marking element, is patterned according to the default rule.
Specifically, in embodiments of the present invention, preset condition can there are many, and then from least one element determine
Meeting the object element of preset condition out, also there are many implementations.In the following, just describing in detail to wherein several.
The first:
The object element for meeting preset condition is apart from the smallest one group of element of human body.In the first implementation, it mentions
After taking out at least one element, according to the position of each element in the scene, cluster calculation is carried out, thus more by what is be closer
A element is divided into one group of element.Then, every group of element is calculated at a distance from human body.Next, more every group of element and people
The distance of body will be determined as object element apart from the smallest one group of element.
For example, referring to FIG. 5, being a scene image schematic diagram.Small circle in Fig. 5 indicates the element extracted,
The position of each small circle is exactly the position in scene image of each element.Rectangular expression human body position in Fig. 5.
By cluster calculation, 3 groups of elements are determined, i.e. three groups of small circles that dotted line surrounds in Fig. 5.By calculating, the 1st group of element distance
The distance of human body is L1, and the 2nd group of distance of the element apart from human body is L2, and the 3rd group of distance of the element apart from human body is L3.Compare
L1, L2 and L3 obtain L1 > L3 > L2.Accordingly, it is determined that 3 elements in the 2nd group of element are object element.
Second:
The object element for meeting preset condition is the highest N number of element of clarity.N is positive integer, and the specific value of N by
Those skilled in the art's selection, the present invention are not particularly limited.
In the second implementation, on the scene in addition to needing to obtain at least one element after extracting at least one element
Position in scape, it is also necessary to obtain the clarity of each element.Then, to all elements extracted, according to clarity by height
It is ranked up to low.In turn, the element by sequence in top N is determined as object element.
The third:
The object element for meeting preset condition is the highest N number of element of color saturation.N is positive integer, and the specific of N takes
Value is selected by those skilled in the art, and the present invention is not particularly limited.
It is on the scene in addition to needing to obtain at least one element after extracting at least one element in the third implementation
Position in scape, it is also necessary to obtain the saturation degree of each element.Then, to all elements extracted, according to saturation degree by height
It is ranked up to low.In turn, the element by sequence in top N is determined as object element.
4th kind:
The object element for meeting preset condition is the element chosen by user.Specifically, in the 4th kind of implementation,
After extracting at least one element, image picking-up apparatus on the display unit shows the element extracted, and controls every
A element is in selected state.User observes each element, chooses one or more elements according to their own needs.Image is clapped
It takes the photograph equipment and obtains the element chosen, using the element chosen as object element.
During specific implementation, those skilled in the art can be above-mentioned four kinds according to actual selection
Any one in implementation or other implementations, the present invention is not particularly limited.
After determining object element, next, according to human body position in the scene, preset facial orientation, object element
And the position of object element, it is patterned according to default rule.
Preset facial orientation such as front, side or the back side, can according to need and be configured.According to preset face
Direction, determination will shoot preset facial orientation, and image picking-up apparatus needs how to move.For example, image picking-up apparatus is worked as
Anteposition is in the positive direction of face, and preset facial orientation is side, it is thus determined that image picking-up apparatus is needed around human body
90 degree clockwise or counterclockwise.In addition, it is also necessary to using human body as core, structure be carried out to object element according to composition rule
Figure.For example, composition rule is trichotomy, then human body should be placed in the region of the centre 1/3 of picture, object element is placed in
Lower 1/3 region.Alternatively, composition rule is Fibonacci method, then human body should be placed in golden section point, object element is also placed in
The position of golden section point.During specific implementation, auto composition and the successive suitable of mobile image capture apparatus is determined how
Sequence can arbitrarily be set.
As an example it is assumed that object element is the coco in Fig. 6, the circle in Fig. 6 indicates the position of human body of user, and
Arrow in circle then indicates the direction of face.It is patterned according to Fibonacci method, face and coco are placed in by determination
In golden section point.Meanwhile the rectangular position for indicating image picking-up apparatus in Fig. 6.Preset facial orientation is side, due to this
When image picking-up apparatus face face front, it is therefore desirable to rotate counterclockwise 90 degree around human body.In turn, image taking
Equipment is rotated by 90 °, until shooting image as shown in Figure 8 according to composition behind position shown in Fig. 7.
Again as an example it is assumed that the element extracted is the sun, mountain and automobile, according to the default item nearest apart from human body
Part determines that object element is the automobile in Fig. 9.Circle in Fig. 9 indicates the position of human body of user, and the then table of the arrow in circle
It lets others have a look at the direction of face.It is patterned according to trichotomy, determines human body in the region in center 1/3, automobile is also placed in center 1/3
In region.Meanwhile the rectangular position for indicating image picking-up apparatus in Fig. 6.Preset facial orientation is front, due to image at this time
Capture apparatus faces the front of face, therefore does not need adjustment camera site.In turn, 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 invention also provides a kind of shooting images
Device, as shown in figure 11, comprising:
First control module 101, shoots scene for controlling image picking-up apparatus, to obtain the field of the scene
Scape image;
First extraction module 102, for extracting at least one element from the scene image;
First composition module 103, for according to default composition rule, to the object element at least one described element into
Row composition;
Second control module 104 shoots image according to the composition for controlling described image capture apparatus.
Optionally, first control module 101 is used for the multiple groups part scene shot according to described image capture apparatus
Image, it is corresponding to construct multiple backup scenario images, wherein part scene image described in each group is described spare for constructing one
Scene image;The mobile element in the scene is determined based on the multiple backup scenario image;It removes each described spare
Mobile element in scene image;According to the multiple backup scenario image after the removal mobile element, the field is obtained
Scape image.
Optionally, first extraction module 102 is used to the scene image being divided into multiple sub-scene images;To every
A sub- scene image carries out element extraction, to obtain at least one described element.
Optionally, described device further includes the first determining module, for carrying out element extraction to each sub-scene image,
After obtaining at least one described element, the sub-scene image and each element where each element are described
Position in the sub-scene image at place determines position of each element in the scene.
Optionally, described device further includes identification module, for the object element at least one described element into
Before row composition, according to the preview image that described image capture apparatus is shot, human body and face are identified from the scene;It obtains
Obtain position of the human body in the scene.
Optionally, the first composition module 103 from least one described element for determining to meet preset condition
The object element;According to position of the human body in the scene, preset facial orientation, the object element and
The position of the object element is patterned according to the default rule.
Optionally, described device further includes third control module, for shot according to described image capture apparatus it is more
Group part scene image corresponds to before constructing multiple backup scenario images, controls described image capture apparatus from the scene
Predeterminated position starts period rotation;
It is grouped shooting module, for being shot to the multiple portions of the scene in the rotary course in each period,
With part scene image described in one group of acquisition.
Beneficial effects of the present invention are as follows:
In embodiments of the present invention, control image picking-up apparatus first shoots scene, obtains scene image, then
At least one element is extracted from scene image, further automatically according to default composition rule, at least one element
Object element is patterned, and the final image picking-up apparatus that controls is according to composition shooting image.As it can be seen that due to according to default composition method
It is then automatically performed composition and is shot, the image picking-up apparatus in the embodiment of the present invention is allowed not depend on the automatic structure of user
Figure, so, solve the technical issues of robot cannot automatically snap in the prior art, the skill for realizing auto composition and shooting
Art effect.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (12)
1. a kind of method for shooting image characterized by comprising
Control image picking-up apparatus shoots scene, to obtain the scene image of the scene;
At least one element is extracted from the scene image;
According to default composition rule, the object element at least one described element is patterned;
It controls described image capture apparatus and shoots image according to the composition;
Wherein, control image picking-up apparatus shoots scene, to obtain the scene image of the scene, comprising:
It include multiple figures in every group of part scene image according to the multiple groups part scene image that described image capture apparatus is shot
Picture, and every image is the image obtained with a part of different angle photographed scene, it is corresponding to construct multiple backup scenario images,
Wherein, part scene image described in each group is for constructing a backup scenario image;
The mobile element in the scene is determined based on the multiple backup scenario image;
Remove the mobile element in each backup scenario image;
According to the multiple backup scenario image after the removal mobile element, the scene image is obtained.
2. the method for shooting image as described in claim 1, which is characterized in that extract at least one from the scene image
A element, comprising:
The scene image is divided into multiple sub-scene images;
Element extraction is carried out to each sub-scene image, to obtain at least one described element.
3. the method for shooting image as claimed in claim 2, which is characterized in that mentioned carrying out element to each sub-scene image
It takes, after at least one described element of acquisition, further includes:
The position of sub-scene image and each element in the sub-scene image at the place where each element
It sets, determines position of each element in the scene.
4. the method for shooting image as claimed in claim 3, which is characterized in that the target at least one described element
Before element is patterned, further includes:
According to the preview image that described image capture apparatus is shot, human body and face are identified from the scene;
Obtain position of the human body in the scene.
5. the method for shooting image as claimed in claim 4, which is characterized in that according to default composition rule, to it is described at least
Object element in one element is patterned, comprising:
The object element for meeting preset condition is determined from least one described element;
According to position of the human body in the scene, preset facial orientation, the object element and the target element
The position of element, is patterned according to the default rule.
6. the method for shooting image as described in claim 1, which is characterized in that is shot according to described image capture apparatus
Multiple groups part scene image corresponds to before constructing multiple backup scenario images, further includes:
Control the period rotation since the predeterminated position of the scene of described image capture apparatus;
In the rotary course in each period, the multiple portions of the scene are shot, with part field described in one group of acquisition
Scape image.
7. a kind of device for shooting image characterized by comprising
First control module shoots scene for controlling image picking-up apparatus, to obtain the scene image of the scene;
First extraction module, for extracting at least one element from the scene image;
First composition module, for being patterned to the object element at least one described element according to default composition rule;
Second control module shoots image according to the composition for controlling described image capture apparatus;
Wherein, first control module is used for the multiple groups part scene image shot according to described image capture apparatus, each
Group part scene image can construct a complete scene image, corresponding to construct multiple backup scenario images, wherein each
The group part scene image is for constructing a backup scenario image;It is determined based on the multiple backup scenario image
Mobile element in the scene;Remove the mobile element in each backup scenario image;It is described mobile first according to removing
The multiple backup scenario image after element, obtains the scene image.
8. device as claimed in claim 7, which is characterized in that first extraction module is for dividing the scene image
At multiple sub-scene images;Element extraction is carried out to each sub-scene image, to obtain at least one described element.
9. device as claimed in claim 8, which is characterized in that described device further includes the first determining module, for every
A sub- scene image carries out element extraction, the sub-scene after obtaining at least one described element, where each element
The position of image and each element in the sub-scene image at the place determines each element in the scene
In position.
10. device as claimed in claim 9, which is characterized in that described device further includes identification module, for it is described extremely
Before object element in a few element is patterned, according to the preview image that described image capture apparatus is shot, from described
Human body and face are identified in scene;Obtain position of the human body in the scene.
11. device as claimed in claim 10, which is characterized in that the first composition module is used for from least one described member
The object element for meeting preset condition is determined in element;According to position of the human body in the scene, preset people
The position of face direction, the object element and the object element, is patterned according to the default rule.
12. device as claimed in claim 7, which is characterized in that described device further includes third control module, in basis
The multiple groups part scene image of described image capture apparatus shooting corresponds to before constructing multiple backup scenario images, described in control
Image picking-up apparatus period since the predeterminated position of the scene rotates;
It is grouped shooting module, for being shot in the rotary course in each period to the multiple portions of the 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 CN106131411A (en) | 2016-11-16 |
CN106131411B true 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) |
Families Citing this family (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018133305A1 (en) * | 2017-01-19 | 2018-07-26 | 华为技术有限公司 | Method and device for image processing |
JP6875196B2 (en) * | 2017-05-26 | 2021-05-19 | エスゼット ディージェイアイ テクノロジー カンパニー リミテッドSz Dji Technology Co.,Ltd | Mobile platforms, flying objects, support devices, mobile terminals, imaging assist methods, programs, and recording media |
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 |
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 |
CN108234867B (en) * | 2017-12-21 | 2020-06-30 | 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 |
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 |
CN112154655A (en) * | 2019-09-27 | 2020-12-29 | 深圳市大疆创新科技有限公司 | Composition method, system and storage medium for camera device |
CN110826564A (en) * | 2019-11-01 | 2020-02-21 | 山东浪潮人工智能研究院有限公司 | Small target semantic segmentation method and system in complex scene image |
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 |
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 |
Also Published As
Publication number | Publication date |
---|---|
CN106131411A (en) | 2016-11-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106131411B (en) | A kind of method and apparatus shooting image | |
US11070725B2 (en) | Image processing method, and unmanned aerial vehicle and system | |
CN106657923B (en) | Scene switching type shared viewing system based on position | |
CN107925753A (en) | The method and system of 3D rendering seizure is carried out using dynamic camera | |
CN104079802B (en) | Aviation or the shadow removal method and apparatus of satellite photo | |
US9756277B2 (en) | System for filming a video movie | |
CN105991915A (en) | Shooting method and apparatus, and terminal | |
CN101363962A (en) | Method for providing output image in either cylindrical mode or perspective mode | |
CN107065409A (en) | Trend projection arrangement and its method of work | |
CN106586011A (en) | Aligning method of aerial shooting unmanned aerial vehicle and aerial shooting unmanned aerial vehicle thereof | |
CN107027014A (en) | A kind of intelligent optical projection system of trend and its method | |
CN110879979B (en) | Augmented reality system based on mobile terminal | |
US20210112194A1 (en) | Method and device for taking group photo | |
CN113240615B (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
WO2022242395A1 (en) | Image processing method and apparatus, electronic device and computer-readable storage medium | |
CN107005648B (en) | Method, control device and control system for controlling unmanned aerial vehicle shooting | |
CN104883506A (en) | Self-service shooting method based on face identification technology | |
CN102368137A (en) | Embedded calibrating stereoscopic vision system | |
CN109769326A (en) | One kind is followed spot method, device and equipment | |
CN106101575A (en) | Generation method, device and the mobile terminal of a kind of augmented reality photo | |
CN109002059A (en) | A kind of multi-rotor unmanned aerial vehicle object real-time tracking camera system and method | |
CN113450253A (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
CN104168407A (en) | Panorama photographing method | |
CN106204743A (en) | Control method, device and the mobile terminal of a kind of augmented reality function | |
CN107544547A (en) | A kind of unmanned plane Full-automatic single person shines image pickup method |
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 |