CN109068118A - Double parallax range methods of adjustment for taking the photograph mould group, device and double take the photograph mould group - Google Patents
Double parallax range methods of adjustment for taking the photograph mould group, device and double take the photograph mould group Download PDFInfo
- Publication number
- CN109068118A CN109068118A CN201811060659.0A CN201811060659A CN109068118A CN 109068118 A CN109068118 A CN 109068118A CN 201811060659 A CN201811060659 A CN 201811060659A CN 109068118 A CN109068118 A CN 109068118A
- Authority
- CN
- China
- Prior art keywords
- mould group
- double
- image
- photograph
- taking
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/67—Focus control based on electronic image sensor signals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Studio Devices (AREA)
Abstract
The present invention provides a kind of double parallax range methods of adjustment for taking the photograph mould group, device and it is double take the photograph mould group, be related to technical field of image processing, this method is applied to that parallax range is adjustable double to take the photograph mould group；This method comprises: obtaining targets preview image；Scene in targets preview image is identified, current scene information is obtained；Double target baseline distances for taking the photograph mould group are determined according to current scene information；Double current basic line distances for taking the photograph mould group are adjusted to target baseline distance.The present invention can adjust parallax range according to photographed scene and accordingly, help to promote shooting effect, better meet user demand.
Description
Technical field
The present invention relates to technical field of image processing, more particularly, to a kind of double parallax range methods of adjustment for taking the photograph mould group,
Device and double take the photograph mould group.
Background technique
The effect of taking pictures of gradually promotion with people to requirement of taking pictures, single camera mould group has been unable to satisfy demand, double
Camera module (referred to as double to take the photograph mould group) is come into being, and be can use dual camera and is generated stereoscopic vision, obtains the scape of image
It is deep, background blurring, 3D scanning, auxiliary focusing etc. are carried out using depth of view information, and can use the two different figures in left and right
As carrying out image co-registration, higher resolution ratio and better color are obtained with expectation.Because double mould groups of taking the photograph are with good effect of taking pictures
Fruit, more and more the electronic equipments with camera function start to be taken the photograph mould group using double and clapped by camera, mobile phone, ipad etc.
According to, and realize it is double take the photograph U.S. face, it is double take the photograph night scene, it is double take the photograph virtualization etc. based on it is double take the photograph mould group realization camera functions.
Under normal conditions, double scene depth of field that mould group measures and double parallax ranges for taking the photograph mould group taken the photograph are (that is, two camera shootings
The distance between head) it is related, parallax range is bigger, and it is double to take the photograph that the range that mould group can be measured that is remoter, it can measure
The scene depth of field is deeper.Existing double parallax ranges for taking the photograph mould group are mostly fixed and smaller, and the scene depth of field measured is usually relatively close,
Overlayable field depth is smaller, it is difficult to be suitable for different scenes, cause shooting effect bad, be unable to satisfy user demand.
Summary of the invention
In view of this, the purpose of the present invention is to provide a kind of double parallax range methods of adjustment for taking the photograph mould group, device and double
Mould group is taken the photograph, parallax range can be adjusted according to photographed scene and accordingly, helps to promote shooting effect, bettering meet user needs
It asks.
To achieve the goals above, technical solution used in the embodiment of the present invention is as follows:
In a first aspect, the embodiment of the invention provides a kind of double parallax range methods of adjustment for taking the photograph mould group, the method is answered
Mould group is taken the photograph for parallax range adjustable pair；The described method includes: obtaining targets preview image；To in the targets preview image
Scene identified, obtain current scene information；Double target bases for taking the photograph mould group are determined according to the current scene information
Linear distance；Double current basic line distances for taking the photograph mould group are adjusted to the target baseline distance.
Further, the step of scene in the targets preview image identifies, obtains current scene information,
It include: that the targets preview image is input to scene Recognition model；Wherein, the scene Recognition model is a kind of neural network
Model；The scene information that the scene Recognition model exports is determined as current scene information.
Further, it is described according to the current scene information determine double target baseline for taking the photograph mould group apart from the step of,
Include: the parallax range table searched and pre-established, determines parallax range corresponding with the current scene information；Wherein, described
Record has the corresponding relationship of scene information and parallax range in parallax range table；The parallax range found is determined as institute
State double target baseline distances for taking the photograph mould group.
Further, it is described by double current basic line distances for taking the photograph mould group adjust to the target baseline apart from the step of,
It include: to send adjustment instruction to double drive motors for taking the photograph mould group, so that the drive motor drives described pair to take the photograph mould group
Two cameras are mobile, and double current basic line distances for taking the photograph mould group are adjusted to the target baseline distance；Wherein, the tune
The target baseline distance is carried in whole instruction.
Further, the method also includes: when double current basic line distances for taking the photograph mould group are adjusted to the target baseline
Apart from when, execute photographing operation, current capture image to obtain.
Further, the execution candid photograph operation, to obtain current the step of capturing image, comprising: enable described pair to take the photograph mould group
The first camera acquisition first capture image, enable double second camera acquisition second for taking the photograph mould group capture image；It is based on
Described first, which captures image and described second, captures image, synthesizes current candid photograph image.
Further, described to capture image and the second candid photograph image based on described first, it generates and currently captures image
Step, comprising: capture image and described second based on described first and capture image, calculated by image depth algorithm to be synthesized
The current depth of view information for capturing image；Image and described second is captured according to the depth of view information being calculated, described first
Image is captured, current candid photograph image is synthesized.
Second aspect, the embodiment of the present invention also provide a kind of double parallax range adjustment devices for taking the photograph mould group, and described device is answered
Mould group is taken the photograph for parallax range adjustable pair；Described device includes: that preview image obtains module, for obtaining targets preview figure
Picture；Scene Recognition module obtains current scene information for identifying to the scene in the targets preview image；Baseline
Apart from determining module, for determining double target baseline distances for taking the photograph mould group according to the current scene information；Parallax range
Module is adjusted, for adjusting double current basic line distances for taking the photograph mould group to the target baseline distance.
The third aspect, the embodiment of the invention provides a kind of pair to take the photograph mould group, and double parallax ranges for taking the photograph mould group are adjustable, and
Double take the photograph in mould group is arranged just like the adjustment device of parallax range described in second aspect.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage medium, the computer-readable storage
Computer program is stored on medium, the computer program is executed when being run by processor described in above-mentioned any one of first aspect
Method the step of.
The embodiment of the invention provides a kind of double parallax range methods of adjustment for taking the photograph mould group, device and double take the photograph mould group, application
Mould group is taken the photograph in parallax range adjustable pair, the scene in the targets preview image of acquisition can be identified, obtain working as front court
Scape information, and target baseline distance is determined according to current scene information, thus by double current basic line distances for taking the photograph mould group adjust to
The target baseline distance.This mode provided in this embodiment can identify the scene in preview image, and take the photograph mould group for double
Current basic line distance adjust to target baseline distance corresponding with the scene.It is this that baseline is accordingly adjusted according to photographed scene
The mode of distance helps to promote shooting effect, betters meet user demand.
Other feature and advantage of the embodiment of the present invention will illustrate in the following description, alternatively, Partial Feature and excellent
Point can deduce from specification or unambiguously determine, or the above-mentioned technology by implementing the embodiment of the present invention can obtain
Know.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 shows the structural schematic diagram of a kind of electronic equipment provided by the embodiment of the present invention；
Fig. 2 shows the double parallax range method of adjustment flow charts for taking the photograph mould group of one kind provided by the embodiment of the present invention；
Fig. 3 shows a kind of image depth algorithm principle figure provided by the embodiment of the present invention；
Fig. 4 shows another kind parallax range method of adjustment flow chart provided by the embodiment of the present invention；
Fig. 5 shows the structural frames of the double parallax range adjustment devices for taking the photograph mould group of one kind provided by the embodiment of the present invention
Figure.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing to the present invention
Technical solution be clearly and completely described, it is clear that described embodiments are some of the embodiments of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall within the protection scope of the present invention.
The parallax ranges for taking the photograph mould group in view of in the prior art pair are fixed mostly and smaller, the scene depth of field measured
Usually relatively close, overlayable field depth is smaller, it is difficult to be suitable for different scenes, cause shooting effect bad, be unable to satisfy use
Family demand.To improve this problem, a kind of double parallax range methods of adjustment for taking the photograph mould group provided in an embodiment of the present invention, device and double
Mould group is taken the photograph, which can be applied to shooting technology, realize using corresponding software and hardware, carry out below to the embodiment of the present invention
It is discussed in detail.
Embodiment one:
Firstly, describing referring to Fig.1 for realizing double parallax range methods of adjustment for taking the photograph mould group of the embodiment of the present invention, dress
It sets and double exemplary electronic devices 100 for taking the photograph mould group.
The structural schematic diagram of a kind of electronic equipment as shown in Figure 1, electronic equipment 100 include one or more processors
102, one or more storage units 104, input unit 106, output unit 108 and it is double take the photograph mould group 110, these components pass through
The interconnection of bindiny mechanism's (not shown) of bus system 112 and/or other forms.It should be noted that electronic equipment 100 shown in FIG. 1
Component and structure be it is illustrative, and not restrictive, as needed, the electronic equipment also can have other assemblies
And structure.
The processor 102 can use digital signal processor (DSP), field programmable gate array (FPGA), can compile
At least one of journey logic array (PLA) example, in hardware realizes that the processor 102 can be central processing unit
(CPU) or one or more of the processing unit of other forms with data-handling capacity and/or instruction execution capability
Combination, and can control other components in the electronic equipment 100 to execute desired function.
The storage unit 104 may include one or more computer program products, and the computer program product can
To include various forms of computer readable storage mediums, such as volatile memory and/or nonvolatile memory.It is described easy
The property lost memory for example may include random access memory (RAM) and/or cache memory (cache) etc..It is described non-
Volatile memory for example may include read-only memory (ROM), hard disk, flash memory etc..In the computer readable storage medium
On can store one or more computer program instructions, processor 102 can run described program instruction, to realize hereafter institute
The client functionality (realized by processor) in the embodiment of the present invention stated and/or other desired functions.In the meter
Can also store various application programs and various data in calculation machine readable storage medium storing program for executing, for example, the application program use and/or
The various data etc. generated.
The input unit 106 can be the device that user is used to input instruction, and may include keyboard, mouse, wheat
One or more of gram wind and touch screen etc..
The output unit 108 can export various information (for example, image or sound) to external (for example, user), and
It and may include one or more of display, loudspeaker etc..
Described pair is taken the photograph mould group 110 and can shoot the desired image of user (such as photo, video etc.), specifically may include two
Camera, two cameras can acquire image respectively.Captured image is stored in the storage unit 104 by double mould groups of taking the photograph
For the use of other components.
Illustratively, for realizing double parallax range methods of adjustment for taking the photograph mould group according to an embodiment of the present invention, device and
Double exemplary electronic devices for taking the photograph mould group may be implemented as the intelligent terminals such as camera, smart phone, tablet computer.
Embodiment two:
A kind of double parallax range methods of adjustment for taking the photograph mould group are present embodiments provided, it is adjustable that this method is applied to parallax range
Double take the photograph mould group；Specifically, this pair, which takes the photograph mould group, can be used as independent individual, it also can be used as image acquisition component and be configured at such as phase
It is double to take the photograph two cameras that mould group includes and may be the same or different on the electronic equipments such as machine, smart phone.Institute referring to fig. 2
The double parallax range method of adjustment flow charts for taking the photograph mould group of the one kind shown, this method comprises:
Step S202 obtains targets preview image.
In one embodiment, present preview image can be obtained when receiving the photographing instruction of user；It will be current
Preview image is determined as targets preview image.User can (equipment entity key or touch screen be virtually pressed by triggering shoot button
Key) and to it is double take the photograph mould group issue photographing instruction, it is double take the photograph mould group by user the preview graph collected at the time of triggering shoot button
As being determined as targets preview image.
Step S204 identifies the scene in targets preview image, obtains current scene information.
Such as, the scene in targets preview image can be identified with scene Recognition algorithm, determines scene type, obtains
Current scene information.Scene type may include numerous reality scenes such as square, building, portrait, pet, no longer arrange one by one herein
It lifts.
Step S206 determines double target baseline distances for taking the photograph mould group according to current scene information.
In the specific implementation, the parallax range table pre-established can be first looked for, determination is corresponding with current scene information
Parallax range (and can be described as double take the photograph parallax range)；Wherein, record has scene information and parallax range in parallax range table
Corresponding relationship；Then the parallax range found is determined as double target baseline distances for taking the photograph mould group.
It is understood that different photographed scenes be corresponding with it is different it is double take the photograph parallax range, such as: square, building are big
Scene scene needs biggish pair to take the photograph parallax range, to cover the farther depth of field；The scenes such as portrait, pet need lesser double
Parallax range is taken the photograph, portrait or pet are focused with emphasis.
The target baseline distance determined above by parallax range table is double recommendation parallax ranges for taking the photograph mould group, is found
Target baseline distance can be double parallax ranges taking the photograph mould group default and selecting.In practical applications, user can also be according to reality
The target baseline distance of demand and sets itself current scene, details are not described herein.
Step S208 adjusts double current basic line distances for taking the photograph mould group to target baseline distance.
Specifically, adjustment instruction can be sent to double drive motors for taking the photograph mould group, so that drive motor driving is double to take the photograph mould group
Two cameras it is mobile, double current basic line distances for taking the photograph mould group are adjusted to target baseline distance；Wherein, it is taken in adjustment instruction
With target baseline distance.
Above-mentioned double parallax range methods of adjustment for taking the photograph mould group provided in an embodiment of the present invention, it is adjustable to be applied to parallax range
It is double to take the photograph mould group, the scene in the targets preview image of acquisition can be identified, obtain current scene information, and according to current
Scene information determines target baseline distance, to adjusting double current basic line distances for taking the photograph mould group to the target baseline distance.
This mode provided in this embodiment can identify the scene in preview image, and double current basic line distances for taking the photograph mould group are adjusted
Whole extremely target baseline distance corresponding with the scene.This mode that parallax range is accordingly adjusted according to photographed scene, helps
In promoting shooting effect, user demand is better meet.
When identifying to the scene in targets preview image, nerual network technique realization can be used, when it is implemented,
Targets preview image can be input to scene Recognition model；Wherein, scene Recognition model is a kind of neural network model；Then
The scene information that scene Recognition model exports is determined as current scene information.
Scene Recognition model mainly has following mode classification when identifying to image scene:
Mode classification one: object-based scene classification.Specifically, the mode classification is using object as recognition unit, according to
The special object occurred in scene distinguishes different scenes；By identifying to objects such as personage, pet, buildings, come area
Divide different scenes.Scene Recognition model can be using neural networks such as AlexNet, VGG-Net, GoogLeNet, ResNet
Structure is realized.
Mode classification two: the scene classification based on region.Specifically, the mode classification selects to calculate by object candidate area
Method generates a series of candidate target regions, then extracts candidate target region feature by deep neural network, and special with these
Sign is classified.Scene Recognition model can be realized using neural network structures such as RCNN.
Mode classification three: the scene classification based on context.Specifically, the mode classification passes through identification global object, and
Small object set or accurate zone boundary in non-scene, to identify scene type.This mode can reduce part and make an uproar
Influence of the sound to scene classification.Scene Recognition model can be realized using the neural network structure based on Gist feature extraction.
Three kinds of mode classifications are only simply listed above, but are not construed as limiting, it in practical applications, can be according to need
It wants and flexibly uses one of mode classification or a variety of.
Further, the scene Recognition model that can identify image scene is usually to obtain by training in advance, to
To scene identification model, it specifically can refer to following steps:
(1) all kinds of scene images of preset quantity are acquired.Wherein, the amount of images of acquisition is generally large enough, and such as 100,000
It opens scene image (being only for example signal), to cover various types of other scene as much as possible.
(2) it carries out scene to the scene image of acquisition precisely to mark, the tool such as presented to each scene image according to it
Body scene and accordingly attach the labels such as building, square, portrait, pet.
(3) training set, verifying collection and test set will be divided by a certain percentage by the scene image of mark.
(4) initial model built is trained using training set, while using verifying collection in training process
Between result verified (real-time adjusting training parameter), when training precision and verifying precision all reach certain threshold value when, stop instruction
Practice, obtain it is trained after scene Recognition model.Such as back-propagation algorithm realization can be used in specific training method, when training essence
Degree reaches the first given threshold, when verifying precision reaches the second given threshold, determine current model it is exportable meet it is desired
Recognition result also relatively accurately can carry out scene Recognition to scene image.
(5) the scene Recognition model obtained after above-mentioned training is tested using test set, to measure the scene Recognition
The recognition effect of model.
It can be to the scene Recognition model that the scene in image is accurately identified by the above-mentioned means, can be obtained.
Identified to the scene in targets preview image, and by double current basic line distances for taking the photograph mould group adjust to this
After the corresponding target baseline distance of scene, double mould groups of taking the photograph can execute photographing operation, to obtain current candid photograph image.It is specific and
Speech enables double the first camera acquisitions first for taking the photograph mould group capture image, and double second camera acquisitions second for taking the photograph mould group is enabled to capture
Image；Image and second is captured based on first and captures image, synthesizes current candid photograph image.Specifically, image co-registration can be used
Technology captures image and second for first and captures image progress fusion treatment.Application image integration technology can extract first respectively
The channel information of image and the channel information of the second candid photograph image are captured, then melts the corresponding channel information of two images
Conjunction processing synthesizes current candid photograph image.This mode can integrate the image information of different camera acquisitions, effectively improve figure
As the utilization rate of information, the current candid photograph image formed through two image co-registrations generally comprises richer information content, can be compared with
For complete display characterize photographic subjects.
In the current candid photograph image of synthesis, image and second can be captured based on first and capture image, pass through image depth
Algorithm calculates the depth of view information of current candid photograph image to be synthesized；Then according to be calculated depth of view information, the first candid photograph figure
Picture and second captures image, synthesizes current candid photograph image.Such as, it can be captured first to first by above-mentioned image fusion technology
Image and the second candid photograph image carry out synthesis processing, combine the depth of view information being calculated in the synthesis process, formation is currently grabbed
Clap image.Current candid photograph image in the present embodiment be based not only on the first candid photograph image and second capture image channel information into
Row fusion has also embodied the depth of view information being calculated by the first candid photograph image and the second candid photograph image.Wherein, depth of view information
The distance range that imaging can be understood in space is described, that is, subject is made to generate the closest approach of relatively clear image extremely
The distance in farthest point, and can be regarded as the spatial depth that subject is capable of blur-free imaging.Typically, in field depth indoor setting
The clarity of object image is not fully consistent, wherein the clarity highest in focus, remaining image definition is with it and coke
The distance decline in direct ratio of point.By calculating the current depth of view information for capturing image, image and the are captured in conjunction with first
Two capture the image information of image, can merge to be formed with depth of view information and two images using above-mentioned image fusion technology
Channel fuse information current candid photograph image, this currently captures image being capable of depth of view information obtained by calculation preferably body
Reveal the subject that the first candid photograph image and the second candid photograph image are presented jointly.
For ease of understanding, a kind of image depth algorithm principle figure as shown in connection with fig. 3, further illustrates the meter of depth of view information
Calculation mode.Fig. 3, which is illustrated, double takes the photograph left image and right image that two cameras of mould group acquire respectively；Wherein, left image is
Image is captured for aforementioned first, right image is aforementioned second candid photograph image.Left images illustrate a little 1, point 2 and point 3,
In, point 1 indicates certain imaging of point on the image being taken on material object；Point 2 indicates the position of optical axis on the image；Point 3 indicates
Image (sensor) sensor position namely camera position.Between point 3 in point 3 in left image and right image
Distance as the distance between two cameras, that is, baseline distance B.Point 4 in Fig. 3 indicates certain point being taken on material object, P
(xc, yc, zc) it is certain the point coordinate being taken on material object.In addition, a little 1 coordinate in left image is also illustrated in Fig. 3 respectively
For (Xleft, Y), the coordinate in right image is (Xright, Y).Specific depth of field calculating process is as follows:
According to the following formula:
Wherein, f indicates focal length.
It can deduce:
Wherein, Disparity=Xleft-Xright, characterize XleftWith XrightBetween difference.
Wherein, Xleft、Xright, Y, B and f be all known quantity, so as to be derived by xc, ycAnd zcSpecific value,
In, zcThe depth of field for certain point being as taken on material object.By the above-mentioned means, each of on double scene images for taking the photograph the acquisition of mould group
Point can all calculate the corresponding depth of field, so that full frame depth of view information can be obtained.
A kind of image depth algorithm is only schematically illustrated above, is not construed as limiting, it in practical applications, can be with
Realize that details are not described herein using other image depth algorithms.
Based on aforementioned parallax range method of adjustment, for ease of understanding, the present embodiment further provides a kind of parallax range
The concrete application example of method of adjustment.Specifically, another parallax range method of adjustment flow chart shown in Figure 4, packet
Include following steps:
Step S402 opens double parallax range adjustable functions for taking the photograph mould group.
Step S404, load is double to take the photograph parallax range look-up table.
Step S406, camera open preview video stream, acquire preview data frame.Wherein, preview data frame is preview
Image.
Step S408 judges whether to take pictures.If so, step S410 is executed, if not, executing step S422；
Step S410 obtains the preview data frame for moment of taking pictures.The preview data frame of the moment of taking pictures is preceding aim
Preview image.
The preview data frame for moment of taking pictures is input to scene Recognition model by step S412, carries out field to preview data frame
Scape identification, obtains the scene information of current scene.
Step S414, according to scene information, from it is double take the photograph in parallax range look-up table to search be suitable for the double of current scene and take the photograph
Parallax range d.
Double parallax range d that take the photograph are sent to double drive motor units for taking the photograph baseline, drive motor unit driving by step S416
Dual camera is mobile, to adjust the parallax range between dual camera.
Step S418, dual camera the first image of synchronous crawl and the second image.
First image and the second image are input to image depth algorithm, calculate the full frame of current scene by step S420
Depth of view information, and current candid photograph image is synthesized according to full frame depth of view information, or full frame depth of view information is applied to three
Tie up application task.Such as, three-dimensional applications task can be background blurring task, task of focusing again, scratch figure task, 3-D image
Reconstruction tasks etc..It is understood that the image capture devices such as camera, mobile phone can provide the user with difference using depth of view information
Function.By taking focusing task again as an example, when camera provides focus function again, the focusing that can be issued according to user refers to
It enables and (such as, detects that user's finger touches the position in image display interfaces) and determine that user wants the focus position focused again
It sets, then the current focus for capturing image of adjustment, and the current depth of field for capturing other regions in image is adjusted according to depth of view information,
Picture stereovision is presented according to user demand so that currently capturing image.The above is only exemplary illustrations, are not limited herein,
In practical application, the three-dimensional applications task that any need is applied to depth of view information all may be used.It is synthesized according to full frame depth of view information
It is current when capturing image, it may be implemented double to take the photograph the effects of taking pictures such as virtualization.Wherein, due to depth that dual camera can measure
Range is related with parallax range, and parallax range is smaller namely parallax is smaller, is more suitable for clapping close shot, and parallax range is bigger, parallax
It is bigger, it is more suitable for clapping distant view, is based on this, when parallax range is smaller, is advantageously implemented the virtualization application of close shot depth, can highlights close
Scape, and distant view is blurred；When parallax range is larger, it is advantageously implemented the virtualization application of distant view depth, can highlight distant view, and by close shot
Virtualization.Certainly, the above is only being illustrated for parallax range to the influence of the depth of field, in practical applications, depth of field size is also
The combined influence that will receive many factors such as aperture, focal length, object distance, herein without repeating.
Step S422 judges whether to exit.If not, executing step S408；If so, terminating.
In conclusion the above-mentioned double parallax range methods of adjustment for taking the photograph mould group provided through this embodiment, can be based on people
Work intellectual technology identifies present filming scene, to take the photograph parallax range, Neng Goudong according to current scene dynamic adjustment is double
The acquisition of state is taken pictures the depth of field (such as, close shot depth, distant view depth, dynamic depth etc.) of scene, by covering far and near field depth, with
It is only capable of acquisition close shot in the prior art to compare deeply, can effectively promote shooting effect, and be preferably applied for such as three-dimensional reconstruction
Etc. in many three-dimensional applications tasks, the application space of the three-dimensional applications of the electronic equipment with camera function is enriched, further
Extend double a possibility that taking the photograph application.
Embodiment three:
Corresponding to aforementioned double parallax range methods of adjustment for taking the photograph mould group, the present embodiment proposes a kind of double baselines for taking the photograph mould group
Distance adjusting system, the device are applied to parallax range adjustable pair and take the photograph mould group；The double bases for taking the photograph mould group of one kind shown in Figure 5
Linear distance adjusts the structural block diagram of device, which includes:
Preview image obtains module 502, for obtaining targets preview image；
Scene Recognition module 504 obtains current scene information for identifying to the scene in targets preview image；
Parallax range determining module 506, for determining double target baseline distances for taking the photograph mould group according to current scene information；
Parallax range adjusts module 508, for adjusting double current basic line distances for taking the photograph mould group to target baseline distance.
Above-mentioned double parallax range adjustment devices for taking the photograph mould group provided in an embodiment of the present invention, it is adjustable to be applied to parallax range
It is double to take the photograph mould group, the scene in the targets preview image of acquisition can be identified, obtain current scene information, and according to current
Scene information determines target baseline distance, to adjusting double current basic line distances for taking the photograph mould group to the target baseline distance.
This device provided in this embodiment can identify the scene in preview image, and double current basic line distances for taking the photograph mould group are adjusted
Whole extremely target baseline distance corresponding with the scene.This device that parallax range is accordingly adjusted according to photographed scene, helps
In promoting shooting effect, user demand is better meet.
In one embodiment, above-mentioned preview image obtains module 502 and is used for: when the photographing instruction for receiving user
When, obtain present preview image；Present preview image is determined as targets preview image.
In one embodiment, above-mentioned scene Recognition module 504 is used for: targets preview image is input to scene Recognition
Model；Wherein, scene Recognition model is a kind of neural network model；The scene information that scene Recognition model exports is determined as working as
Preceding scene information.
In one embodiment, above-mentioned parallax range determining module 506 is used for: searching the parallax range pre-established
Table determines parallax range corresponding with current scene information；Wherein, record has scene information and parallax range in parallax range table
Corresponding relationship；The parallax range found is determined as double target baseline distances for taking the photograph mould group.
In one embodiment, above-mentioned parallax range adjustment module 508 is used for: being sent to double drive motors for taking the photograph mould group
Adjustment instruction adjusts double current basic line distances for taking the photograph mould group so that double two cameras for taking the photograph mould group of drive motor driving are mobile
It is whole to target baseline distance；Wherein, target baseline distance is carried in adjustment instruction.
Further, above-mentioned apparatus further include: photo module, for adjusting when double current basic line distances for taking the photograph mould group to target
When parallax range, photographing operation is executed, to obtain current candid photograph image.
In one embodiment, above-mentioned photo module is used for: double the first camera acquisitions first for taking the photograph mould group being enabled to capture
Image enables double second camera acquisitions second for taking the photograph mould group capture image；Image and second is captured based on first and captures image, is closed
Image is captured at current.The photo module is further used for: capturing image and second based on first and captures image, passes through image scape
Deep algorithm calculates the depth of view information of current candid photograph image to be synthesized；Image is captured according to the depth of view information being calculated, first
Image is captured with second, synthesizes current candid photograph image.
The technical effect of device provided by the present embodiment, realization principle and generation is identical with previous embodiment, for letter
It describes, Installation practice part does not refer to place, can refer to corresponding contents in preceding method embodiment.
Example IV:
Mould group is taken the photograph the embodiment of the invention also provides a kind of double, the parallax range that this pair takes the photograph mould group is adjustable, and double takes the photograph mould group
Upper setting adjusts device just like the parallax range that previous embodiment provides.
It is apparent to those skilled in the art that for convenience and simplicity of description, the double of foregoing description take the photograph
The specific work process of mould group, can be with reference to the corresponding process in previous embodiment, and details are not described herein.
Further, the present embodiment additionally provides a kind of computer readable storage medium, on the computer readable storage medium
It is stored with computer program, it is double provided by execution preceding method embodiment when which is run by processor to take the photograph mould group
Parallax range method of adjustment the step of.
Double parallax range method of adjustment, device and double computers for taking the photograph mould group for taking the photograph mould group provided by the embodiment of the present invention
Program product, the computer readable storage medium including storing program code, the instruction that said program code includes can be used for
Previous methods method as described in the examples is executed, specific implementation can be found in embodiment of the method, and details are not described herein.
In addition, in the description of the embodiment of the present invention unless specifically defined or limited otherwise, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected；It can
To be mechanical connection, it is also possible to be electrically connected；It can be directly connected, can also can be indirectly connected through an intermediary
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood at this with concrete condition
Concrete meaning in invention.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
In the description of the present invention, it should be noted that term " center ", "upper", "lower", "left", "right", "vertical",
The orientation or positional relationship of the instructions such as "horizontal", "inner", "outside" be based on the orientation or positional relationship shown in the drawings, merely to
Convenient for description the present invention and simplify description, rather than the device or element of indication or suggestion meaning must have a particular orientation,
It is constructed and operated in a specific orientation, therefore is not considered as limiting the invention.In addition, term " first ", " second ",
" third " is used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention, should all cover in protection of the invention
Within the scope of.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (10)
1. a kind of double parallax range methods of adjustment for taking the photograph mould group, which is characterized in that it is adjustable that the method is applied to parallax range
It is double to take the photograph mould group；The described method includes:
Obtain targets preview image；
Scene in the targets preview image is identified, current scene information is obtained；
Double target baseline distances for taking the photograph mould group are determined according to the current scene information；
Double current basic line distances for taking the photograph mould group are adjusted to the target baseline distance.
2. the method according to claim 1, wherein the scene in the targets preview image is known
Not, the step of obtaining current scene information, comprising:
The targets preview image is input to scene Recognition model；Wherein, the scene Recognition model is a kind of neural network
Model；
The scene information that the scene Recognition model exports is determined as current scene information.
3. the method according to claim 1, wherein described determine that described pair is taken the photograph according to the current scene information
The target baseline of mould group apart from the step of, comprising:
The parallax range table pre-established is searched, determines parallax range corresponding with the current scene information；Wherein, the base
Record has the corresponding relationship of scene information and parallax range in linear distance table；
The parallax range found is determined as double target baseline distances for taking the photograph mould group.
4. the method according to claim 1, wherein described by double current basic line distance adjustment for taking the photograph mould group
To the target baseline apart from the step of, comprising:
Adjustment instruction is sent to double drive motors for taking the photograph mould group, so that the drive motor drives described pair to take the photograph the two of mould group
A camera is mobile, and double current basic line distances for taking the photograph mould group are adjusted to the target baseline distance；Wherein, the adjustment
The target baseline distance is carried in instruction.
5. method according to any one of claims 1 to 4, which is characterized in that the method also includes:
When double current basic line distances for taking the photograph mould group adjust to the target baseline apart from when, photographing operation is executed, to obtain
It is current to capture image.
6. according to the method described in claim 5, it is characterized in that, operation is captured in the execution, to obtain current candid photograph image
The step of, comprising:
It enables double the first camera acquisitions first for taking the photograph mould group capture image, enables double second camera acquisitions for taking the photograph mould group
Second captures image；
Image and described second is captured based on described first and captures image, synthesizes current candid photograph image.
7. according to the method described in claim 6, it is characterized in that, described grabbed based on the first candid photograph image and described second
Image is clapped, current the step of capturing image is synthesized, comprising:
Image and described second is captured based on described first and captures image, is calculated and to be synthesized is currently grabbed by image depth algorithm
Clap the depth of view information of image；
Image and described second is captured according to the depth of view information being calculated, described first and captures image, and synthesis is currently grabbed
Clap image.
8. a kind of double parallax range adjustment devices for taking the photograph mould group, which is characterized in that it is adjustable that described device is applied to parallax range
It is double to take the photograph mould group；Described device includes:
Preview image obtains module, for obtaining targets preview image；
Scene Recognition module obtains current scene information for identifying to the scene in the targets preview image；
Parallax range determining module, for determining double target baseline distances for taking the photograph mould group according to the current scene information；
Parallax range adjusts module, for adjusting double current basic line distances for taking the photograph mould group to the target baseline distance.
9. a kind of pair is taken the photograph mould group, which is characterized in that double parallax ranges for taking the photograph mould group are adjustable, and double take the photograph in mould group is arranged
There is parallax range adjustment device as claimed in claim 8.
10. a kind of computer readable storage medium, computer program, feature are stored on the computer readable storage medium
The step of being, the described in any item methods of the claims 1 to 7 executed when the computer program is run by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811060659.0A CN109068118B (en) | 2018-09-11 | 2018-09-11 | Baseline distance adjusting method and device of double-camera module and double-camera module |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811060659.0A CN109068118B (en) | 2018-09-11 | 2018-09-11 | Baseline distance adjusting method and device of double-camera module and double-camera module |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109068118A true CN109068118A (en) | 2018-12-21 |
| CN109068118B CN109068118B (en) | 2020-11-27 |
Family
ID=64761375
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811060659.0A Active CN109068118B (en) | 2018-09-11 | 2018-09-11 | Baseline distance adjusting method and device of double-camera module and double-camera module |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109068118B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112804458A (en) * | 2021-01-11 | 2021-05-14 | 广东小天才科技有限公司 | Shooting view finding method and device, terminal equipment and storage medium |
| CN113362381A (en) * | 2020-03-03 | 2021-09-07 | RealMe重庆移动通信有限公司 | Image processing method and device, readable medium and communication terminal |
| CN114666483A (en) * | 2022-04-06 | 2022-06-24 | Oppo广东移动通信有限公司 | Electronic device and shooting method thereof |
| CN114942009A (en) * | 2022-06-20 | 2022-08-26 | 山东信通电子股份有限公司 | Hidden danger early warning method, device, equipment and medium based on power transmission line |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101276138A (en) * | 2008-04-30 | 2008-10-01 | 北京工业大学 | Binocular stereoscopic camera with self-adjusting base length |
| CN103292710A (en) * | 2013-05-27 | 2013-09-11 | 华南理工大学 | Distance measuring method applying binocular visual parallax error distance-measuring principle |
| CN104982034A (en) * | 2013-03-15 | 2015-10-14 | 英特尔公司 | Adaptive depth sensing |
| CN105940674A (en) * | 2014-12-31 | 2016-09-14 | 深圳市大疆创新科技有限公司 | System and method for adjusting baseline of imaging system with microlens array |
| CN107801017A (en) * | 2017-10-30 | 2018-03-13 | 北京都是科技有限公司 | A kind of more mesh 3D video cameras and its 3D rendering modeling method |
| CN107820020A (en) * | 2017-12-06 | 2018-03-20 | 广东欧珀移动通信有限公司 | Method of adjustment, device, storage medium and the mobile terminal of acquisition parameters |
| CN108615243A (en) * | 2017-01-25 | 2018-10-02 | 北京三星通信技术研究有限公司 | The determination method, apparatus and system of three-dimensional multimedia messages |
-
2018
- 2018-09-11 CN CN201811060659.0A patent/CN109068118B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101276138A (en) * | 2008-04-30 | 2008-10-01 | 北京工业大学 | Binocular stereoscopic camera with self-adjusting base length |
| CN104982034A (en) * | 2013-03-15 | 2015-10-14 | 英特尔公司 | Adaptive depth sensing |
| CN103292710A (en) * | 2013-05-27 | 2013-09-11 | 华南理工大学 | Distance measuring method applying binocular visual parallax error distance-measuring principle |
| CN105940674A (en) * | 2014-12-31 | 2016-09-14 | 深圳市大疆创新科技有限公司 | System and method for adjusting baseline of imaging system with microlens array |
| CN108615243A (en) * | 2017-01-25 | 2018-10-02 | 北京三星通信技术研究有限公司 | The determination method, apparatus and system of three-dimensional multimedia messages |
| CN107801017A (en) * | 2017-10-30 | 2018-03-13 | 北京都是科技有限公司 | A kind of more mesh 3D video cameras and its 3D rendering modeling method |
| CN107820020A (en) * | 2017-12-06 | 2018-03-20 | 广东欧珀移动通信有限公司 | Method of adjustment, device, storage medium and the mobile terminal of acquisition parameters |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113362381A (en) * | 2020-03-03 | 2021-09-07 | RealMe重庆移动通信有限公司 | Image processing method and device, readable medium and communication terminal |
| CN112804458A (en) * | 2021-01-11 | 2021-05-14 | 广东小天才科技有限公司 | Shooting view finding method and device, terminal equipment and storage medium |
| CN114666483A (en) * | 2022-04-06 | 2022-06-24 | Oppo广东移动通信有限公司 | Electronic device and shooting method thereof |
| CN114942009A (en) * | 2022-06-20 | 2022-08-26 | 山东信通电子股份有限公司 | Hidden danger early warning method, device, equipment and medium based on power transmission line |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109068118B (en) | 2020-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10455141B2 (en) | Auto-focus method and apparatus and electronic device | |
| CN107087107B (en) | Image processing apparatus and method based on dual camera | |
| US9185388B2 (en) | Methods, systems, and computer program products for creating three-dimensional video sequences | |
| US20220012495A1 (en) | Visual feature tagging in multi-view interactive digital media representations | |
| CN107113415B (en) | The method and apparatus for obtaining and merging for more technology depth maps | |
| US9813607B2 (en) | Method and apparatus for image capture targeting | |
| CN109068118A (en) | Double parallax range methods of adjustment for taking the photograph mould group, device and double take the photograph mould group | |
| CN102843509B (en) | Image processing device and image processing method | |
| CN102308590B (en) | Three-dimensional image output device and three-dimensional image output method | |
| US9036072B2 (en) | Image processing apparatus and image processing method | |
| CN104243800B (en) | Control device and storage medium | |
| JP2011166264A (en) | Image processing apparatus, imaging device and image processing method, and program | |
| JP2016516369A (en) | Photo output method and apparatus | |
| CN104902182B (en) | A kind of method and apparatus for realizing continuous auto-focusing | |
| US9324158B2 (en) | Image processing device for performing image processing on moving image | |
| US20120013783A1 (en) | Photgraphing support system, photographing support method, server photographing apparatus, and program | |
| CN102739958A (en) | Imaging processing apparatus, image processing method, and program | |
| CN106791456A (en) | A kind of photographic method and electronic equipment | |
| KR20150091064A (en) | Method and system for capturing a 3d image using single camera | |
| CN104155839B (en) | System and method for providing 3 d image | |
| US8908012B2 (en) | Electronic device and method for creating three-dimensional image | |
| CN102984447A (en) | Photographic system and method for generating photos | |
| CN109961422A (en) | The determination of the contrast value of digital picture | |
| Chen | Capturing fast motion with consumer grade unsynchronized rolling-shutter cameras | |
| US11659135B2 (en) | Slow or fast motion video using depth information |
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 |