CN107948522A - Camera chooses method, apparatus, terminal and the storage medium of shooting personage's head portrait - Google Patents
Camera chooses method, apparatus, terminal and the storage medium of shooting personage's head portrait Download PDFInfo
- Publication number
- CN107948522A CN107948522A CN201711261941.0A CN201711261941A CN107948522A CN 107948522 A CN107948522 A CN 107948522A CN 201711261941 A CN201711261941 A CN 201711261941A CN 107948522 A CN107948522 A CN 107948522A
- Authority
- CN
- China
- Prior art keywords
- personage
- head portrait
- camera
- captured
- moment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 210000003128 head Anatomy 0.000 claims description 282
- 230000003287 optical effect Effects 0.000 claims description 8
- 230000015654 memory Effects 0.000 description 14
- 238000013519 translation Methods 0.000 description 7
- 230000000007 visual effect Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012790 confirmation Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 239000007787 solid Substances 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Exposure Control For Cameras (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses a kind of method that camera chooses shooting personage's head portrait, device, terminal and storage medium, when definite camera current shooting pattern is single screening-mode, obtain pictorial information of the camera at every one scan moment, by in the corresponding pixel number of personage's head portrait in all pictorial informations, personage's head portrait of pixel number maximum is as first personage's head portrait to be captured, so that it is more accurate to choose the personage's head portrait obtained, when carrying out shooting photo applied to camera, video carries out Video chat using camera, during the scene of online network direct broadcasting, camera can choose correct reference object all the time, so that the end-user experience including the camera is more preferable.
Description
Technical field
The present embodiments relate to camera technical field, more particularly to a kind of camera to choose the side of shooting personage's head portrait
Method, device, terminal and storage medium.
Background technology
With the rise of mobile Internet, the terminal such as smart mobile phone, tablet has been typically equipped with camera.
Shot using camera, Video chat or when carrying out live, which people in camera view on earth
Thing head portrait or which personage's head portrait are the target person head portraits needed, and existing image pickup method does not have good method from camera
Distinguished in one or more personage's head portraits in the visual field.
The content of the invention
The present invention provides method, apparatus, terminal and the storage medium that a kind of camera chooses shooting personage's head portrait, to solve
Existing camera is difficult to correct the problem of choosing shooting personage's head portrait from the shooting visual field.
In a first aspect, an embodiment of the present invention provides a kind of method that camera chooses shooting personage's head portrait, including：
If the current shooting pattern for confirming camera is single screening-mode, the camera is controlled in its scanning range
It is interior, shoot per the pictorial information in one scan moment camera view；
Calculate the corresponding pixel number of each personage's head portrait in the pictorial information；
Using personage's head portrait of pixel number maximum as first personage's head portrait to be captured.
Second aspect, the embodiment of the present invention additionally provide the device that a kind of camera chooses shooting personage's head portrait, including：
First scan module, if the current shooting pattern for confirming camera is single screening-mode, controls the camera
In its scanning range, shoot per the pictorial information in one scan moment camera view；Pixel computing module, described in calculating
The corresponding pixel number of each personage's head portrait in pictorial information；
First reference object determining module, for using personage's head portrait of pixel number maximum as the first personage to be captured
Head portrait.
The third aspect, the embodiment of the present invention additionally provide a kind of terminal, and the terminal includes：
One or more processors；
Storage device, for storing one or more programs；
Camera, for shooting picture；
Motor module, for controlling camera scanning or mobile；
When one or more of programs are performed by one or more of processors so that one or more of processing
Device realizes above-mentioned selection shooting personage's head portrait method.
Fourth aspect, the embodiment of the present invention additionally provides a kind of storage medium for including computer executable instructions, described
Computer executable instructions shoot personage's head portrait method when being performed by computer processor for performing above-mentioned selection.
A kind of method that the present invention chooses shooting personage's head portrait by providing camera, when definite camera current shooting mould
When formula is single screening-mode, pictorial information of the camera at every one scan moment is obtained, by personage's head in all pictorial informations
As in corresponding pixel number, personage's head portrait of pixel number maximum is as first personage's head portrait to be captured so that choose
Personage's head portrait of acquisition is more accurate, when applied to camera carry out shooting photo, video or utilize camera carry out video
Chat, online network direct broadcasting scene when, camera can choose correct reference object all the time so that including the camera
End-user experience is more preferable.
Brief description of the drawings
Fig. 1 is the step flow chart that a kind of camera of the embodiment of the present invention one chooses the method for shooting personage's head portrait；
Fig. 2 is the step flow chart that a kind of camera of the embodiment of the present invention two chooses the method for shooting personage's head portrait；
Fig. 3 is the structure diagram that a kind of camera of the embodiment of the present invention three chooses the device of shooting personage's head portrait；
Fig. 4 is a kind of structure diagram of terminal for the embodiment of the present invention four.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that in order to just
It illustrate only part related to the present invention rather than entire infrastructure in description, attached drawing.
Embodiment one
Fig. 1 is the step flow for the method that a kind of camera that the embodiment of the present invention one provides chooses shooting personage's head portrait
Figure, the present embodiment be applicable to using camera carry out shooting photo, video or using camera carry out Video chat, online
The situation of network direct broadcasting, this method can be performed by terminals such as the mobile phone with camera, tablets, can specifically be included as follows
Step：
If step 101, the current shooting pattern of confirmation camera are single screening-mode, the camera is controlled to be swept at it
In the range of retouching, shoot per the pictorial information in one scan moment camera view.
Specifically, the screening-mode of camera can include single screening-mode and more people's screening-modes, single shooting mould
Formula refers to pattern of the camera using personage's head portrait as reference object, and more people's screening-modes refer to camera by multiple personages
Pattern of the head portrait as reference object.
Camera is mounted in the terminals such as mobile phone, tablet, and the camera of the installation on these terminals can be pacified
Motor control in terminal and be scanned, wherein, scanning can be divided into translation scan and rotation sweep, and translation scan
Can be including translation scan, from top to bottom translation scan, rotation sweep can rotate from left to right including camera from left to right
Scanning, from top to bottom rotation sweep, i.e., can be complete in the position in camera translation scan to any one position, camera
Into rotation sweep, therefore, the scanning range of camera includes the horizontal sweep scope and rotational scan range of camera.
When camera starts scanning, camera be according to certain scanning sequency (such as first left-to-right translation scan, and
And rotation sweep is completed at each position, then carry out upper and lower translation scanning) and sweep speed swept in its scanning range
Retouch, scanning sequency therein is that technical staff is set in advance in terminal, and user can voluntarily select scanning sequency, work as scanning
After order determines, each scanning moment corresponds to the position that is presently in of a camera and when the rotating angle of preceding camera
Degree, is to be rotated to control by motor accordingly, due to camera scanning, each scanning moment also corresponds to the rotating step of motor
Several, i.e., motor rotates the corresponding rotation step number from original state, and camera also from initial position and angle, is moved and rotated to
The scanning moment corresponding camera position and rotation angle.
In embodiments of the present invention, terminal can first determine whether the current shooting pattern of camera, if confirming camera
Current shooting pattern be single screening-mode, camera can be controlled in its scanning range, shoot and take the photograph per the one scan moment
As the pictorial information in the head visual field, to filter out target person in personage's head portrait in the pictorial information out of camera view
Head portrait.
Step 102, calculate the corresponding pixel number of each personage's head portrait in the pictorial information.
In embodiments of the present invention, shoot per after the pictorial information in one scan moment camera view, people can be passed through
Face identification technology identifies personage's head portrait in pictorial information, then calculates the corresponding pixel number of each personage's head portrait.
Step 103, using personage's head portrait of pixel number maximum as first personage's head portrait to be captured.
In general, in a pictures, personage's head portrait of pixel number maximum is considered as apart from camera focal length
Nearest personage's head portrait, therefore, in embodiments of the present invention, after obtaining the corresponding pixel number of each personage's head portrait, by picture
Personage's head portrait of vegetarian refreshments number maximum makees the personage head portrait nearest apart from camera focus as first personage's head portrait to be captured
For first personage's head portrait to be captured, the accuracy rate that target person head portrait is selected in multiple personage's head portraits is improved, and it is this
Selection mode is more in line with user demand.
In one preferred embodiment of the invention, the pixel number sometimes selected in all pictorial informations is maximum
Personage's head portrait be not the personage's head portrait to be captured for best suiting user demand, should this is because inscribed in different scanning
This is personage's head portrait of pixel number maximum, since different scanning moment shooting angle is different, other and personage's head portrait phase
Close personage's head portrait becomes personage's head portrait of pixel number maximum, causes to occur judging inaccuracy, in order to tackle this feelings
Condition, step 103 can include following sub-step：
S11, calculate the camera focus and each personage's head portrait eyes line and the angle of horizontal direction, as personage
Head portrait deviation angle.
In embodiments of the present invention, shoot per the one scan moment pictorial information after, can calculate camera focus with
Each personage's head portrait eyes line and the angle of horizontal direction in pictorial information, as each personage's head portrait deviation angle, calculating should
After personage's head portrait deviation angle, which is used as the foundation that personage's head portrait deviates horizontal direction.
The weighted value of S12, each personage's head portrait of the pixel acquiring size based on each personage's head portrait.
In embodiments of the present invention, can in order to calculate the degree of personage's head portrait overall offset horizontal direction in pictorial information
With the weighted value of each personage's head portrait of pixel acquiring size based on each personage's head portrait, such as pixel can be set big
Personage's head portrait, its weighted value is big, so that the personage's head portrait finally chosen meets the accuracy higher of user demand.Preferably,
Weighted value that can be directly using the pixel size of each personage's head portrait as each personage's head portrait.
S13, according to personage's head portrait deviation angle, each personage's head portrait weighted value calculates weighted deviation angle.
In embodiments of the present invention, after determining each personage's head portrait deviation angle, and after corresponding personage's head portrait weighted value,
Weighted deviation angle can be calculated according to default weighting algorithm, feelings are deviated to react personage's head portrait in pictorial information on the whole
Condition.
S14, make the camera optical axis and horizontal direction angle and the weighted deviation angle immediate scanning moment
For the targeted scans moment.
In embodiments of the present invention, after calculating weighted deviation angle, moment camera optical axis and level will can each be scanned
The angle in direction most connects camera optical axis and horizontal direction angle and the weighted deviation angle compared with weighted deviation angle
The near scanning moment as the targeted scans moment, the people of selected pixels point maximum from the pictorial information captured by the object time
Thing head portrait.
S15, in the pictorial information at targeted scans moment, personage's head portrait of pixel number maximum is waited to clap as first
Take the photograph personage's head portrait.
In embodiments of the present invention, after determining the targeted scans moment, in the pictorial information at targeted scans moment, by pixel
Personage's head portrait of point number maximum is as first personage's head portrait to be captured, so that personage's head portrait of pixel number maximum is made
For first personage's head portrait to be captured when, combine personage's head portrait overall offset situation in pictorial information so that the first of selection is treated
Shooting personage's head portrait meets user demand most possibly.
The step of embodiment of the present invention is by above-mentioned steps 101-103, when definite camera current shooting pattern is for one
During screening-mode, pictorial information of the camera at every one scan moment is obtained, personage's head portrait in all pictorial informations is corresponding
In pixel number, personage's head portrait of pixel number maximum is as first personage's head portrait to be captured so that chooses the people of acquisition
Thing head portrait is more accurate, when carrying out shooting photo, video applied to camera or carry out Video chat, online using camera
During the scene of network direct broadcasting, camera can choose correct reference object all the time so that the terminal user including the camera
Experience is more preferable.
On the basis of above-mentioned steps 101-103, in one preferred embodiment of the invention, the choosing of the embodiment of the present invention
Taking the method for shooting personage's head portrait can also include：
Step 104, the record corresponding motor rotation step number per the one scan moment.
In embodiments of the present invention, as it was noted above, each scanning moment also corresponds to the rotating step number of motor, therefore,
Corresponding motor rotation step number of every one scan moment can be recorded.
Step 105, control motor rotate to, and the pictorial information belonging to personage's head portrait of pixel number maximum is corresponding to be swept
Retouch the motor rotation step number corresponding to the moment.
In embodiments of the present invention, after have recorded corresponding motor of every one scan moment rotation step number, electricity can be controlled
Machine rotates to, the motor rotation corresponding to the corresponding scanning moment of the pictorial information belonging to personage's head portrait of pixel number maximum
Step number so that camera returns to, the pictorial information belonging to personage's head portrait of pixel number maximum it is corresponding scanning the moment when
The position of camera and rotation angle so that camera is in a preferable camera site and rotation angle.
Step 106, the control camera only shoot described first personage's head portrait to be captured.
In embodiments of the present invention, when camera returns to, the picture belonging to personage's head portrait of pixel number maximum is believed
When ceasing the corresponding scanning moment after the position of camera and rotation angle, camera can be controlled only to shoot this first to be captured
Personage's head portrait, such as can focus so that only first personage's head portrait to be captured, or may be used also in camera view
To focus so that there was only first personage's head portrait to be captured in camera view, to other regions in camera view
Carry out background blurring.
Step 107, the adjustment camera so that first personage's head portrait to be captured is in the center of camera view
Position.
In embodiments of the present invention, after control only shoots first personage's head portrait to be captured, camera can also be adjusted, obtains institute
The center that first personage's head portrait to be captured is in camera view is stated, improves shooting effect.
In one preferred embodiment of the invention, step 107 can specifically include following sub-step：
S21, the control camera movement, shoot the picture of first personage's head portrait to be captured.
As described in step 105 above, since camera has been returned to, belonging to personage's head portrait of pixel number maximum
The position of camera and rotation angle during pictorial information corresponding scanning moment, at this time camera preferable clapped in one
Act as regent and put and shooting angle, still, do not ensure that personage's head portrait of camera shooting is in the centre bit of camera view
Put, therefore, in embodiments of the present invention, it is also necessary to control the camera to move, described first is shot in moving process and is treated
Shoot the picture of personage's head portrait.
S22, when in the picture of described first personage's head portrait to be captured, the profile of first personage's head portrait to be captured it is several
When what center is overlapped with the geometric center of the camera view, the camera is controlled to stop movement.
In embodiments of the present invention, during picture is shot in camera moving process, as the first personage to be captured
When the geometric center of the profile of head portrait is overlapped with the geometric center of the camera view, it is believed that at first personage's head portrait to be captured
In the center of picture, camera is controlled to stop movement at this time, so as to ensure that personage's head image information of camera shooting
Center in picture.
Embodiment two
In the inventive solutions, it is single shooting that above-mentioned steps 101-107, which is directed to camera screening-mode,
The situation of pattern, in embodiment two, when the screening-mode of camera is more people's screening-modes, with reference to Fig. 2, Fig. 2 is this hair
A kind of camera that bright embodiment two provides chooses the step flow chart of the method for shooting personage's head portrait, then technical side of the invention
Case may include steps of：
Step 201, judge the current screening-mode of camera.
Specifically, the screening-mode of camera can include single screening-mode and more people's screening-modes, single shooting mould
Formula refers to pattern of the camera using personage's head portrait as reference object, and more people's screening-modes refer to camera by multiple personages
Pattern of the head portrait as reference object, the screening-mode of camera is that technical staff pre-sets in the configuration information of camera
's.
In embodiments of the present invention, terminal can judge the current bat of camera by reading the configuration information of camera
Pattern is taken the photograph, judges the means not limited to this of the current screening-mode of camera certainly, various methods of the prior art are all can
Capable.
If step 202, the current shooting pattern of confirmation camera are single screening-mode, the camera is controlled to be swept at it
In the range of retouching, shoot per the pictorial information in one scan moment camera view.
Step 203, calculate the corresponding pixel number of each personage's head portrait in the pictorial information.
Step 204, using personage's head portrait of pixel number maximum as first personage's head portrait to be captured.Above-mentioned steps 202-
204 with reference to step 101-103, and details are not described herein for the embodiment of the present invention.
If step 205, the current shooting pattern of confirmation camera are more people's screening-modes, the camera is controlled to be swept at it
In the range of retouching, shoot per the pictorial information in one scan moment camera view.
In embodiments of the present invention, can be with if the current shooting pattern that terminal confirms camera is more people's screening-modes
Camera is controlled in its scanning range, shoots the pictorial information in per one scan moment camera view, so as to from camera
Target person head portrait is filtered out in personage's head portrait in pictorial information in the visual field.
Step 206, the number for calculating personage's head portrait in the pictorial information.
In embodiments of the present invention, shoot per after the pictorial information in one scan moment camera view, people can be passed through
Face identification technology identifies personage's head portrait in pictorial information, then calculates the number of personage's head portrait in pictorial information.
It should be noted that may in the scanning range of camera, have some personage's head portraits in pictorial information not
Completely, in step 206 number of personage's head portrait be complete personage's head portrait number, the personage's head portrait not photographed completely is then
Do not count.
Step 207, using personage's head portrait in the largest number of pictorial informations of personage's head portrait as the second personage to be captured
Head portrait.
In general, under the identical facilities of camera, the number for the personage's head portrait that can be accommodated in camera view is most
Big value is certain, therefore, in camera scanning range, it is believed that personage's head portrait in the pictorial information captured by camera
When most, all persons' head portrait in the pictorial information is personage's head portrait of the desired shooting of user.
The embodiment of the present invention, can identify the largest number of pictorial informations of personage's head portrait from all pictorial informations, and
Using personage's head portrait in the pictorial information as second personage's head portrait to be captured, the accuracy that personage's head portrait is chosen is improved.
In one preferred embodiment of the invention, the personage's head portrait number sometimes selected in all pictorial informations is most
More personage's head portraits is not the personage's head portrait to be captured for best suiting user demand, this is because being inscribed in different scanning, is taken the photograph
As the number of personage's head portrait in the head visual field be it is different, may some scanning moment, camera can photograph most
Personage's head portrait, but at the scanning moment, may too consider personage's head portrait number, and shooting angle is ignored, the scanning moment
Under personage's head portrait be not user demand personage's head portrait to be captured, in order to tackle this case, step 207 can include such as
Lower sub-step：
S31, calculate the camera focus and each personage's head portrait eyes line and the angle of horizontal direction, as personage
Head portrait deviation angle.
The weighted value of S32, each personage's head portrait of the pixel acquiring size based on each personage's head portrait.
S33, according to personage's head portrait deviation angle, each personage's head portrait weighted value calculates weighted deviation angle.
S34, make the camera optical axis and horizontal direction angle and the weighted deviation angle immediate scanning moment
For the targeted scans moment.
Above-mentioned steps S31-S34 is referred to step S11-S14, and details are not described herein for the embodiment of the present invention
S35, in the pictorial information at targeted scans moment, by the personage in the largest number of pictorial informations of personage's head portrait
Head portrait is as second personage's head portrait to be captured.
In embodiments of the present invention, after determining the targeted scans moment, in the pictorial information at targeted scans moment, by personage
Personage's head portrait in the largest number of pictorial informations of head portrait is as second personage's head portrait to be captured, so that personage's head portrait
When personage's head portrait in the largest number of pictorial informations is as second personage's head portrait to be captured, personage's head in pictorial information is combined
As overall offset situation so that second personage's head portrait to be captured of selection meets user demand most possibly.
It is similar with above-mentioned steps 104-107, in embodiments of the present invention, in the case where camera is in more people's screening-modes,
In a preferred embodiment of the present invention, the method for selection shooting personage's head portrait of the embodiment of the present invention can also include：
Step 208, the record corresponding motor rotation step number per the one scan moment.
In embodiments of the present invention, as it was noted above, each scanning moment also corresponds to the rotating step number of motor, therefore,
Corresponding motor rotation step number of every one scan moment can be recorded.
Step 209, control motor rotate to, and the corresponding scanning moment institute of the largest number of pictorial informations of personage's head portrait is right
The motor rotation step number answered.
In embodiments of the present invention, after have recorded corresponding motor of every one scan moment rotation step number, electricity can be controlled
Machine rotates to, the motor rotation step number corresponding to the largest number of pictorial informations corresponding scanning moment of personage's head portrait so that
Camera returns to, the position of camera and the anglec of rotation during the largest number of pictorial informations of personage's head portrait corresponding scanning moment
Degree so that camera is in a preferable camera site and rotation angle.
Step 210, the control camera only shoot described second personage's head portrait to be captured.
In embodiments of the present invention, when camera returns to, the largest number of pictorial informations of personage's head portrait are corresponding to be swept
When retouching the moment after the position of camera and rotation angle, camera can be controlled only to shoot second personage's head portrait to be captured,
Such as it can focus so that only second personage's head portrait to be captured, or be also possible that and adjust Jiao in camera view
Away from so that there was only second personage's head portrait to be captured in camera view, background is carried out to other regions in camera view
Virtualization.
Step 211, the adjustment camera so that second personage's head portrait to be captured is in the center of camera view
Position.
In embodiments of the present invention, after control only shoots second personage's head portrait to be captured, camera can also be adjusted, obtains institute
The center that second personage's head portrait to be captured is in camera view is stated, improves shooting effect.
In one preferred embodiment of the invention, step 211 can specifically include following sub-step：
S41, the control camera movement, shoot the picture of second personage's head portrait to be captured.
As described in step 209 above, since camera has been returned to, the largest number of pictorial informations pair of personage's head portrait
Answer scanning the moment when camera position and rotation angle, at this time camera be in a preferable camera site and bat
Angle is taken the photograph, still, does not ensure that personage's head portrait of camera shooting is in the center of camera view, therefore,
In the embodiment of the present invention, it is also necessary to control the camera to move, described second personage's head to be captured is shot in moving process
The picture of picture.
S42, when in the picture of described second personage's head portrait to be captured, the general outline of second personage's head portrait to be captured
Geometric center when being overlapped with the geometric center of the camera view, control the camera to stop movement.
Specifically, the general outline of second personage's head portrait to be captured can be that those skilled in the art are according to each personage
Head portrait profile, the general outline for containing each personage's head portrait fitted by mathematical method, for example, it is assumed that everyone
Thing head portrait is by the use of an ellipse as its profile, then general outline can be the union of all elliptic contours, on the basis of the union
The general outline of structure is oval, and as just a kind of example, those skilled in the art, can use the method for above-mentioned ellipse fitting
Existing various approximating methods establish the general outline of second personage's head portrait to be captured.
In embodiments of the present invention, during picture is shot in camera moving process, as the second personage to be captured
When the geometric center of the general outline of head portrait is overlapped with the geometric center of the camera view, it is believed that second personage's head to be captured
Center as being in picture, controls camera to stop movement at this time, so as to ensure that personage's head portrait of camera shooting
Information is in the center of picture.
Embodiment three
Fig. 3 is the structure diagram for the device that a kind of camera provided by Embodiment 2 of the present invention chooses shooting personage's head portrait,
The device can specifically include：
First scan module 301, if the current shooting pattern for confirming camera is single screening-mode, controls the shooting
Head is shot per the pictorial information in one scan moment camera view in its scanning range；
Pixel computing module 302, calculates the corresponding pixel number of each personage's head portrait in the pictorial information；
First reference object determining module 303, for personage's head portrait of pixel number maximum is to be captured as first
Personage's head portrait.
In one preferred embodiment of the invention, the first reference object determining module 303 can include：
First deviation angle calculating sub module, for calculating the camera focus and each personage's head portrait eyes line and water
Square to angle, as personage's head portrait deviation angle；
First weighted value acquisition submodule, for each personage's head portrait of pixel acquiring size based on each personage's head portrait
Weighted value；
First weighted deviation angle calculating sub module, for according to personage's head portrait deviation angle, each personage's head portrait weight
Value calculates weighted deviation angle；
First object scans moment determination sub-module, for the camera optical axis and horizontal direction angle to be added with described
The deviation angle immediate scanning moment is weighed as the targeted scans moment；
First personage's head portrait determination sub-module to be captured, in the pictorial information at targeted scans moment, by pixel
Personage's head portrait of number maximum is as first personage's head portrait to be captured.
In one preferred embodiment of the invention, which can also include：
First motor rotates logging modle, for recording corresponding motor rotation step number of every one scan moment；
First motor control module, for controlling motor to rotate to, the figure belonging to personage's head portrait of pixel number maximum
Motor rotation step number corresponding to the piece information corresponding scanning moment；
First taking module, for controlling the camera only to shoot described first personage's head portrait to be captured；
First adjustment module, for adjusting the camera so that first personage's head portrait to be captured is in camera
The center in the visual field.
In one preferred embodiment of the invention, the first adjustment module can include：
First control submodule, for controlling the camera to move, shoots the figure of first personage's head portrait to be captured
Piece；
First submodule placed in the middle, for when in the picture of described first personage's head portrait to be captured, first people to be captured
When the geometric center of the profile of thing head portrait is overlapped with the geometric center of the camera view, the camera is controlled to stop moving
It is dynamic.
In one preferred embodiment of the invention, which can also include：
Second scan module, if for confirming that the current shooting pattern of camera is more people's screening-modes, takes the photograph described in control
Picture head is shot per the pictorial information in one scan moment camera view in its scanning range；
Personage's head portrait computing module, for calculating the number of personage's head portrait in the pictorial information；
Second reference object determining module, makees for personage's head portrait in the largest number of pictorial informations by personage's head portrait
For second personage's head portrait to be captured.
In one preferred embodiment of the invention, the second reference object determining module can include：
Second deviation angle calculating sub module, for calculating the camera focus and each personage's head portrait eyes line and water
Square to angle, as personage's head portrait deviation angle；
Second weighted value acquisition submodule, for each personage's head portrait of pixel acquiring size based on each personage's head portrait
Weighted value；
Second weighted deviation angle calculating sub module, for according to personage's head portrait deviation angle, each personage's head portrait weight
Value calculates weighted deviation angle；
Second targeted scans moment determination sub-module, for the camera optical axis and horizontal direction angle to be added with described
The deviation angle immediate scanning moment is weighed as the targeted scans moment；
Second personage's head portrait determination sub-module to be captured, in the pictorial information at targeted scans moment, by personage's head
Personage's head portrait in the largest number of pictorial informations of picture is as second personage's head portrait to be captured.
In one preferred embodiment of the invention, which can also include：
Second motor rotates logging modle, for recording corresponding motor rotation step number of every one scan moment；
Second motor control module, for controlling motor to rotate to, the largest number of pictorial informations of personage's head portrait correspond to
Scanning the moment corresponding to motor rotation step number；
Second taking module, for controlling the camera only to shoot described second personage's head portrait to be captured；
Second adjustment module, for adjusting the camera so that second personage's head portrait to be captured is in camera
The center in the visual field.
In one preferred embodiment of the invention, second adjustment module can include：
Second control submodule, for controlling the camera to move, shoots the figure of second personage's head portrait to be captured
Piece；
Second submodule placed in the middle, for when in the picture of described second personage's head portrait to be captured, second people to be captured
When the geometric center of the general outline of thing head portrait is overlapped with the geometric center of the camera view, the camera is controlled to stop
It is mobile.
The device that the camera that the embodiment of the present invention is provided chooses shooting personage's head portrait can perform any implementation of the invention
The method that the camera that example is provided chooses shooting personage's head portrait, possesses the corresponding function module of execution method and beneficial effect.
Example IV
Fig. 4 is a kind of structure diagram for terminal that the embodiment of the present invention four provides, as shown in figure 4, the terminal includes place
Manage device 40, memory 41, input unit 42 and output device 43；The quantity of processor 40 can be one or more in terminal,
In Fig. 4 by taking a processor 40 as an example；Processor 40, memory 41, input unit 42 and output device 43 in terminal can be with
Connected by bus or other modes, in Fig. 4 exemplified by being connected by bus.
Memory 41 is used as a kind of computer-readable recording medium, and journey is can perform available for storage software program, computer
Sequence and module, as the camera in the embodiment of the present invention chooses the corresponding programmed instruction/module of method of shooting personage's head portrait
(for example, first scan module 201,202 and first reference object determining module 203 of pixel computing module in device).Place
Reason device 40 is stored in software program, instruction and module in memory 41 by operation, so as to perform the various functions of terminal
Using and data processing, that is, realize the method that above-mentioned camera chooses shooting personage's head portrait.
Memory 41 can mainly include storing program area and storage data field, wherein, storing program area can store operation system
Application program needed for system, at least one function；Storage data field can be stored uses created data etc. according to terminal.This
Outside, memory 41 can include high-speed random access memory, can also include nonvolatile memory, for example, at least a magnetic
Disk storage device, flush memory device or other non-volatile solid state memory parts.In some instances, memory 41 can be further
Including network connection to terminal can be passed through relative to the remotely located memory of processor 40, these remote memories.It is above-mentioned
The example of network includes but not limited to internet, intranet, LAN, mobile radio communication and combinations thereof.
Input unit 42 can be used for the numeral or character information for receiving input, and produce with the user setting of terminal and
The related key signals input of function control.Output device 43 may include the display devices such as display screen.
Embodiment five
The embodiment of the present invention five also provides a kind of storage medium for including computer executable instructions, and the computer can be held
A kind of method that row instruction chooses shooting personage's head portrait when being performed by computer processor for performing camera, this method bag
Include：
If the current shooting pattern for confirming camera is single screening-mode, the camera is controlled in its scanning range
It is interior, shoot per the pictorial information in one scan moment camera view；Each personage's head portrait in the pictorial information is calculated to correspond to
Pixel number；
Using personage's head portrait of pixel number maximum as first personage's head portrait to be captured.
Certainly, a kind of storage medium for including computer executable instructions that the embodiment of the present invention is provided, its computer
The method operation that executable instruction is not limited to the described above, can also carry out the camera choosing that any embodiment of the present invention is provided
Take the relevant operation in the method for shooting personage's head portrait.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but the former is more in many cases
Good embodiment.Based on such understanding, what technical scheme substantially in other words contributed the prior art
Part can be embodied in the form of software product, which can be stored in computer-readable recording medium
In, floppy disk, read-only storage (Read-Only Memory, ROM), random access memory (Random such as computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are with so that a computer is set
Standby (can be personal computer, server, or network equipment etc.) performs the method described in each embodiment of the present invention.
It is worth noting that, in the embodiment of the device of above-mentioned selection shooting personage's head portrait, included unit and
Module is simply divided according to function logic, but is not limited to above-mentioned division, as long as corresponding function can be realized
；In addition, the specific name of each functional unit is also only to facilitate mutually distinguish, the protection being not intended to limit the invention
Scope.
Note that it above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious changes,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although being carried out by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
It can include other more equivalent embodiments, and the scope of the present invention is determined by scope of the appended claims.
Claims (10)
1. a kind of method that camera chooses shooting personage's head portrait, it is characterised in that including：
If the current shooting pattern for confirming camera is single screening-mode, the camera is controlled in its scanning range, is clapped
Take the photograph the pictorial information in every one scan moment camera view；
Calculate the corresponding pixel number of each personage's head portrait in the pictorial information；
Using personage's head portrait of pixel number maximum as first personage's head portrait to be captured.
2. according to the method described in claim 1, it is characterized in that, personage's head portrait using pixel number maximum is as
One personage's head portrait to be captured, specifically includes：
The camera focus and each personage's head portrait eyes line and the angle of horizontal direction are calculated, is deviated as personage's head portrait
Angle；
The weighted value of each personage's head portrait of pixel acquiring size based on each personage's head portrait；
According to personage's head portrait deviation angle, each personage's head portrait weighted value calculates weighted deviation angle；
The camera optical axis and horizontal direction angle and the weighted deviation angle immediate scanning moment are swept as target
Retouch the moment；
In the pictorial information at targeted scans moment, using personage's head portrait of pixel number maximum as first personage's head to be captured
Picture.
3. method according to claim 1 or 2, it is characterised in that the method further includes：
Record corresponding motor rotation step number per the one scan moment；
Control motor rotates to, corresponding to the corresponding scanning moment of the pictorial information belonging to personage's head portrait of pixel number maximum
Motor rotation step number；
The camera is controlled only to shoot described first personage's head portrait to be captured；
Adjust the camera so that first personage's head portrait to be captured is in the center of camera view.
4. according to the method described in claim 3, it is characterized in that, the adjustment camera so that described first waits to clap
The center that personage's head portrait is in camera view is taken the photograph, is specifically included：
Control the camera to move, shoot the picture of first personage's head portrait to be captured；
When in the picture of described first personage's head portrait to be captured, the geometric center of the profile of first personage's head portrait to be captured with
When the geometric center of the camera view overlaps, the camera is controlled to stop movement.
5. according to the method described in claim 1, it is characterized in that, the method further includes：
If the current shooting pattern for confirming camera is more people's screening-modes, the camera is controlled in its scanning range, is clapped
Take the photograph the pictorial information in every one scan moment camera view；
Calculate the number of personage's head portrait in the pictorial information；
Using personage's head portrait in the largest number of pictorial informations of personage's head portrait as second personage's head portrait to be captured.
6. according to the method described in claim 5, it is characterized in that, in the largest number of pictorial informations by personage's head portrait
Personage's head portrait as second personage's head portrait to be captured, specifically include：
The camera focus and each personage's head portrait eyes line and the angle of horizontal direction are calculated, is deviated as personage's head portrait
Angle；
The weighted value of each personage's head portrait of pixel acquiring size based on each personage's head portrait；
According to personage's head portrait deviation angle, each personage's head portrait weighted value calculates weighted deviation angle；
The camera optical axis and horizontal direction angle and the weighted deviation angle immediate scanning moment are swept as target
Retouch the moment；
In the pictorial information at targeted scans moment, using personage's head portrait in the largest number of pictorial informations of personage's head portrait as
Second personage's head portrait to be captured.
7. the method according to claim 5 or 6, it is characterised in that the method further includes：
Record corresponding motor rotation step number per the one scan moment；
Control motor rotates to, the motor rotation corresponding to the largest number of pictorial informations corresponding scanning moment of personage's head portrait
Step number；
The camera is controlled only to shoot described second personage's head portrait to be captured；
Adjust the camera so that second personage's head portrait to be captured is in the center of camera view.
8. a kind of camera chooses the device of shooting personage's head portrait, it is characterised in that including：
First scan module, if the current shooting pattern for confirming camera is single screening-mode, controls the camera at it
In scanning range, shoot per the pictorial information in one scan moment camera view；Pixel computing module, calculates the picture
The corresponding pixel number of each personage's head portrait in information；
First reference object determining module, for using personage's head portrait of pixel number maximum as first personage's head to be captured
Picture.
9. a kind of terminal, it is characterised in that the terminal includes：
One or more processors；
Storage device, for storing one or more programs；
Camera, for shooting picture；
Motor module, for controlling camera scanning or mobile；
When one or more of programs are performed by one or more of processors so that one or more of processors are real
Now selection shooting personage's head portrait method as described in any in claim 1-7.
10. a kind of storage medium for including computer executable instructions, the computer executable instructions are by computer disposal
When device performs personage's head portrait method is shot for performing the selection as described in any in claim 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711261941.0A CN107948522B (en) | 2017-12-04 | 2017-12-04 | Method, device, terminal and storage medium for selecting shot person head portrait by camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711261941.0A CN107948522B (en) | 2017-12-04 | 2017-12-04 | Method, device, terminal and storage medium for selecting shot person head portrait by camera |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107948522A true CN107948522A (en) | 2018-04-20 |
| CN107948522B CN107948522B (en) | 2020-06-26 |
Family
ID=61947564
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711261941.0A Active CN107948522B (en) | 2017-12-04 | 2017-12-04 | Method, device, terminal and storage medium for selecting shot person head portrait by camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107948522B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1823298A (en) * | 2003-07-15 | 2006-08-23 | 欧姆龙株式会社 | Object decision device and imaging device |
| US20070086648A1 (en) * | 2005-10-17 | 2007-04-19 | Fujifilm Corporation | Target-image search apparatus, digital camera and methods of controlling same |
| CN1967566A (en) * | 2005-11-14 | 2007-05-23 | 索尼株式会社 | Image processing apparatus and method |
| CN101472071A (en) * | 2007-12-25 | 2009-07-01 | 奥林巴斯映像株式会社 | Image pickup apparatus and focus detection apparatus |
| CN104883498A (en) * | 2015-04-30 | 2015-09-02 | 广东欧珀移动通信有限公司 | Shooting method based on rotary camera, and terminal |
| CN106101448A (en) * | 2016-08-08 | 2016-11-09 | 北京奇虎科技有限公司 | A kind of photographic method based on terminal and device |
| CN106303029A (en) * | 2016-08-15 | 2017-01-04 | 广东欧珀移动通信有限公司 | The method of controlling rotation of a kind of picture, device and mobile terminal |
-
2017
- 2017-12-04 CN CN201711261941.0A patent/CN107948522B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1823298A (en) * | 2003-07-15 | 2006-08-23 | 欧姆龙株式会社 | Object decision device and imaging device |
| US20070086648A1 (en) * | 2005-10-17 | 2007-04-19 | Fujifilm Corporation | Target-image search apparatus, digital camera and methods of controlling same |
| CN1967566A (en) * | 2005-11-14 | 2007-05-23 | 索尼株式会社 | Image processing apparatus and method |
| CN101472071A (en) * | 2007-12-25 | 2009-07-01 | 奥林巴斯映像株式会社 | Image pickup apparatus and focus detection apparatus |
| CN104883498A (en) * | 2015-04-30 | 2015-09-02 | 广东欧珀移动通信有限公司 | Shooting method based on rotary camera, and terminal |
| CN106101448A (en) * | 2016-08-08 | 2016-11-09 | 北京奇虎科技有限公司 | A kind of photographic method based on terminal and device |
| CN106303029A (en) * | 2016-08-15 | 2017-01-04 | 广东欧珀移动通信有限公司 | The method of controlling rotation of a kind of picture, device and mobile terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107948522B (en) | 2020-06-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8059917B2 (en) | 3-D modeling | |
| CN104898832B (en) | Intelligent terminal-based 3D real-time glasses try-on method | |
| CN107770452B (en) | Photographing method, terminal and related medium product | |
| CN110266952A (en) | Image processing method, device, electronic equipment and storage medium | |
| CN105718887A (en) | Shooting method and shooting system capable of realizing dynamic capturing of human faces based on mobile terminal | |
| US9838616B2 (en) | Image processing method and electronic apparatus | |
| CN112702521B (en) | Image shooting method and device, electronic equipment and computer readable storage medium | |
| CN106250839B (en) | A kind of iris image perspective correction method, apparatus and mobile terminal | |
| CN107404615B (en) | Image recording method and electronic equipment | |
| CN110177210B (en) | Photographing method and related device | |
| CN111756996A (en) | Video processing method, video processing apparatus, electronic device, and computer-readable storage medium | |
| WO2021168804A1 (en) | Image processing method, image processing apparatus and image processing system | |
| CN110225243A (en) | Filming control method, device, storage medium and mobile terminal based on Folding screen | |
| CN111093022A (en) | Image shooting method, device, terminal and computer storage medium | |
| CN109361850B (en) | Image processing method, image processing device, terminal equipment and storage medium | |
| CN113810627B (en) | Video processing method, device, mobile terminal and readable storage medium | |
| JP2019106604A (en) | Imaging apparatus, method for controlling imaging apparatus, and program | |
| CN104902172A (en) | Determination method of shooting position and shooting terminal | |
| CN107948522A (en) | Camera chooses method, apparatus, terminal and the storage medium of shooting personage's head portrait | |
| JP2003289938A (en) | Cosmetic compact | |
| CN112204945A (en) | Image processing method, image processing apparatus, image capturing device, movable platform, and storage medium | |
| CN109389367A (en) | Staff attendance method, apparatus and storage medium | |
| CN112991175B (en) | Panoramic picture generation method and device based on single PTZ camera | |
| CN110930303A (en) | Panorama forming method and system | |
| WO2021237627A1 (en) | Image processing method and terminal device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231122 Address after: Room 1102, 11/F, Building (1), No. 6, Yunpu 4th Road, Huangpu District, Guangzhou City, Guangdong Province, 510530 Patentee after: Guangzhou Xibeisi Intelligent Technology Co.,Ltd. Address before: 510530 No. 6, Yunpu Fourth Road, Yunpu Industrial Park, Huangpu District, Guangzhou City, Guangdong Province Patentee before: Guangzhou Shiyuan Electronic Technology Company Limited Patentee before: Guangzhou Shirui Electronic Technology Company Limited. |