CN104683692B - A kind of continuous shooting method and device - Google Patents

A kind of continuous shooting method and device Download PDF

Info

Publication number
CN104683692B
CN104683692B CN201510058180.3A CN201510058180A CN104683692B CN 104683692 B CN104683692 B CN 104683692B CN 201510058180 A CN201510058180 A CN 201510058180A CN 104683692 B CN104683692 B CN 104683692B
Authority
CN
China
Prior art keywords
image frames
image
continuous shooting
reference picture
face
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.)
Expired - Fee Related
Application number
CN201510058180.3A
Other languages
Chinese (zh)
Other versions
CN104683692A (en
Inventor
吴鸿儒
张弓
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Oppo Mobile Telecommunications Corp Ltd
Original Assignee
Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong Oppo Mobile Telecommunications Corp Ltd filed Critical Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority to CN201510058180.3A priority Critical patent/CN104683692B/en
Priority to CN201710877073.2A priority patent/CN107483834B/en
Publication of CN104683692A publication Critical patent/CN104683692A/en
Application granted granted Critical
Publication of CN104683692B publication Critical patent/CN104683692B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/61Control of cameras or camera modules based on recognised objects
    • H04N23/611Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161Detection; Localisation; Normalisation
    • G06V40/166Detection; Localisation; Normalisation using acquisition arrangements
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168Feature extraction; Face representation
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/95Computational photography systems, e.g. light-field imaging systems
    • H04N23/951Computational photography systems, e.g. light-field imaging systems by using two or more images to influence resolution, frame rate or aspect ratio

Abstract

The embodiment of the invention discloses a kind of continuous shooting method and device, wherein the continuous shooting method includes:Continuous shooting enabled instruction is received, the start image frame containing face-image of camera collection is obtained, using the start image frame is as reference picture and stores;Obtain the acquired image frames containing face-image of the camera collection;Detect the difference value of the face characteristic information in the acquired image frames and the face characteristic information of the reference picture;The step of when the difference value are more than or equal to threshold value, the acquired image frames being set to reference picture and stored, and perform the acquired image frames containing face-image for obtaining the camera collection.Terminal resource can be saved using the present invention, the degree of accuracy that useful picture frame is captured during continuous shooting is improved.

Description

A kind of continuous shooting method and device
Technical field
The present invention relates to field of terminal, more particularly to a kind of continuous shooting method and device.
Background technology
With continuing to develop for terminal technology, the integrated function of terminal is more and more, and being increasingly becoming can not in people's life Or a scarce part.Wherein, GIF (Graphic Interchange Format, the graphic interchange format) dynamics that terminal is provided Chart-pattern has interest very much, deep to be liked by users.The principle of this GIF Dynamic Graphs is:Stored in a gif file Multiple image, reads the multiple image data being stored in a gif file by width and shows and be a kind of simplest so as to constitute Animation.User generally captures the picture frame with continuous action or expression using burst mode and is used as in actual use The raw data of GIF Dynamic Graphs synthesis, in the prior art, burst mode are typically to be made using Fixed Time Interval acquired image frames For continuous shooting image, in order that the image that must be captured has continuity, the Fixed Time Interval sets shorter, but user do express one's feelings or The speed of action does not often catch up with camera and carries out the speed of continuous shooting, thus can grab during continuous shooting some it is fuzzy or Person moves express one's feelings during unwanted picture frame, waste terminal storage resource.
The content of the invention
The embodiments of the invention provide a kind of continuous shooting method and device, the storage resource of terminal can be saved, continuous shooting mistake is improved The degree of accuracy of useful picture frame is captured in journey.
The embodiments of the invention provide a kind of continuous shooting method, the continuous shooting method includes:
Continuous shooting enabled instruction is received, the start image frame containing face-image of camera collection is obtained, by the starting Picture frame is as reference picture and stores;
Obtain the acquired image frames containing face-image of the camera collection;
Detect the difference of the face characteristic information in the acquired image frames and the face characteristic information of the reference picture Value;
When the difference value is more than or equal to threshold value, the acquired image frames are set to reference picture and stored, are held The step of row obtains the acquired image frames containing face-image of the camera collection.
Accordingly, the embodiments of the invention provide a kind of continuous shooting device, described device includes:
Picture frame acquiring unit, for receiving continuous shooting enabled instruction, obtains the rising containing face-image of camera collection Beginning picture frame;
Reference image setting unit, for using the start image frame is as reference picture and stores;
Described image frame acquiring unit, is additionally operable to obtain the collection image containing face-image of the camera collection Frame;
Facial features localization unit, for detecting the face characteristic information in the acquired image frames and the reference picture Face characteristic information difference value;
The reference image setting unit, is additionally operable to, when the difference value is more than or equal to threshold value, the collection be schemed As frame is set to reference picture and stores.
The embodiment of the present invention, can receive continuous shooting enabled instruction, obtain the starting figure containing face-image of camera collection As frame, using the start image frame is as reference picture and stores;The camera collection can also be obtained contains face-image Acquired image frames;Detect the face characteristic information in the acquired image frames and the face characteristic information of the reference picture Difference value;And then when the difference value is more than threshold value, the acquired image frames are set to reference picture and stored, execution is obtained The step of taking the acquired image frames containing face-image of the camera collection, can save the storage resource of terminal, the company of raising The degree of accuracy of useful picture frame is captured during bat, Consumer's Experience is improved.
Brief description of the drawings
Technical scheme, is used required in being described below to embodiment in order to illustrate the embodiments of the present invention more clearly Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the present invention, general for this area For logical technical staff, on the premise of not paying creative work, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of continuous shooting method schematic flow sheet provided in an embodiment of the present invention;
Fig. 2 is another continuous shooting method schematic flow sheet provided in an embodiment of the present invention;
Fig. 3 is a kind of continuous shooting apparatus structure schematic diagram provided in an embodiment of the present invention;
Fig. 4 is picture frame acquiring unit structural representation provided in an embodiment of the present invention;
Fig. 5 is facial features localization cellular construction schematic diagram provided in an embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete Site preparation is described, it is clear that described embodiment is a part of embodiment of the invention, rather than whole embodiments.Based on this hair Embodiment in bright, the every other implementation that those of ordinary skill in the art are obtained under the premise of creative work is not made Example, belongs to the scope of protection of the invention.
In the specific implementation, the terminal mentioned in the embodiment of the present invention includes but is not limited to:Smart mobile phone (such as Android Mobile phone, IOS mobile phones), tablet personal computer, notebook computer, palm PC, the electronic equipment such as digital camera.Institute of the embodiment of the present invention The method of description is performed by one group of code being stored in terminal memory, and the code is implemented in based on von Neumann system In computer system.
A kind of continuous shooting method and device provided in an embodiment of the present invention are specifically described below in conjunction with Fig. 1 to Fig. 5.
It is a kind of continuous shooting method schematic flow sheet provided in an embodiment of the present invention, continuous shooting method as depicted referring to Fig. 1 It may include following steps:
S101, receives continuous shooting enabled instruction, obtains the start image frame containing face-image of camera collection, will be described Start image frame is as reference picture and stores.
In the specific implementation, can start camera first and select burst mode in the setting menu of terminal, camera enters Enter and auto-focusing just carried out after viewfinder mode, user inputted when getting out posture photographing instruction be just considered as input continuous shooting start refer to Order, wherein, the input of photographing instruction has various ways, can be that user clicks on camera button triggering or terminal is being prolonged When exposal model under, terminal is triggered when delay of taking pictures is reached.Continuous shooting method in the present embodiment, its main application scenarios Include the continuous shooting image of character face's image for collection, therefore terminal, when receiving continuous shooting instruction, camera collection is containing facial The start image frame of image, using the start image frame is as reference picture and stores, is used as photographed during continuous shooting One image.
S102, obtains the acquired image frames containing face-image of the camera collection.
In step S101, the start image frame that camera is collected is as after reference picture, and camera continues to find a view And auto-focusing is carried out, to gather the acquired image frames containing face-image, wait other images during continuous shooting to be captured.
Face characteristic information and the face characteristic information of the reference picture in S103, the detection acquired image frames Difference value.
In the specific implementation, this step can be based on face recognition technology, pedestrian is entered to acquired image frames and reference picture first Face detection (judge whether face-image in complicated background and split it from background) is included with obtaining it Face-image, then the face-image included in acquired image frames and reference picture is sampled to carry out face characteristic letter Breath is extracted, and then detects the difference of the face characteristic information in the acquired image frames and the face characteristic information of the reference picture Different value.The method of Face datection includes but is not limited to:The regular method of reference template method, face, sample learning method, complexion model method or Sub-face of feature method etc..The extraction of face characteristic information is generally included:Feature vector method and face line template.Wherein, recognition of face Feature vector method refer to:Determine the image surface face profile such as eye iris, the wing of nose, corners of the mouth the attribute such as size, position, distance, Then the geometric feature (Euclidean distance, curvature, angle) or algebraic characteristic amount (square of each characteristic point in image surface face profile are calculated Battle array characteristic vector) to describe the facial characteristics of picture frame septum reset image.
In the present embodiment, can obtain acquired image frames and reference picture septum reset image face feature point (such as corners of the mouth, The wing of nose, canthus, eye exterior feature, nose, brows, eyebrow tail) coordinate information in picture frame, it is then each in detection acquired image frames respectively Face feature point and the coordinate difference of each corresponding face feature point in reference picture, are schemed with the face judged in acquired image frames Seem no espressiove or change in location, the change of such as the distance between brows can determine whether whether face has the table knitted one's brows The change of the distance between feelings, nose and canthus can determine whether the expression for whether having wrinkle nose in face.
For example, the threshold value for setting the transverse and longitudinal coordinate difference value of corners of the mouth characteristic point A points and B points in face characteristic is 0.5, right Acquired image frames and reference picture are done after Face datection and face characteristic information extraction, obtain corners of the mouth A points and B in acquired image frames Point coordinate be respectively (0.5,1.5) and (2.5,1.5), in reference picture the coordinate of corners of the mouth A points and B points be respectively (1,1) and The transverse and longitudinal coordinate difference value of A points and B points is respectively 0.5 in (2,1), therefore detectable acquired image frames and reference picture, Equal to default threshold value, step S104 is now performed, the acquired image frames are set to reference picture and stored.Wherein, mouth The difference of the abscissa of angle A points and B points can represent the length of face, and the difference of the ordinate of corners of the mouth A points and B points can represent the corners of the mouth Difference in height, it is known that relative to the face of reference picture septum reset image, the face length in acquired image frames septum reset image It increased and the corners of the mouth has raised up, therefore can determine whether, relative to the face in reference picture septum reset image, to gather image Face in frame, which has, is changed into smile's state, is espressiove change relative to the face-image in reference picture acquired image frames.
The acquired image frames, when the difference value is more than or equal to threshold value, is set to reference picture and deposited by S104 Storage, the step of performing the acquired image frames containing face-image for obtaining the camera collection.
The present embodiment is after the acquired image frames are set to reference picture and store, if being gathered needed for this continuous shooting Image and do not complete and can transfer circulation and perform step S102~S104 until completing this continuous shooting.
In another alternative embodiment, perform by the acquired image frames be set to reference picture and storing step it Afterwards, methods described also includes:Judge whether the quantity as reference picture and the picture frame stored is more than or equal to first Threshold value, if so, terminating continuous shooting;Otherwise, the acquired image frames containing face-image for obtaining the camera collection are performed The step of.
In the specific implementation, the image shot needed for this continuous shooting can be specified while camera selection burst mode is started Quantity is as first threshold, and usual terminal provides 4 continuous shootings, 6 continuous shootings, 8 continuous shootings or the selection of 16 burst mode options for user, also Can selection burst mode after shooting image needed for self-defined continuous shooting quantity.Terminal often shoots a figure during continuous shooting Picture, just judges whether the image captured by this continuous shooting reaches default first threshold, if so, then terminating this continuous shooting;If it is not, Execution step S102~S104 is continued cycling through until completing this continuous shooting.
In another alternative embodiment, after reception continuous shooting enabled instruction step is performed, methods described also includes:Obtain The initial time stamp of the continuous shooting enabled instruction.
Accordingly, the step of acquired image frames containing face-image of the acquisition camera collection also include: Current time stamp is obtained, continuous shooting duration is calculated according to the current time stamp and the initial time stamp, when judging the continuous shooting It is long whether to be more than or equal to Second Threshold, if so, terminating continuous shooting;Otherwise, containing for the acquisition camera collection is performed The step of acquired image frames of face-image.
When in the specific implementation, burst mode can selected in advance, continuous shooting duration needed for this continuous shooting is set to be used as the Two threshold values, after terminal receives reception continuous shooting enabled instruction, start timing, terminal often shoots a figure during continuous shooting Picture, just judges whether this continuous shooting duration reaches default Second Threshold, if so, then terminating this continuous shooting;If it is not, continuing cycling through Step S102~S104 is performed until this continuous shooting duration reaches predetermined threshold value so as to complete this continuous shooting.
In another alternative embodiment, perform the acquired image frames are set to reference picture and the step of store it Afterwards, methods described also includes:Dynamic Graph generation instruction is received, is obtained as reference picture and stored picture frame, according to institute State as reference picture and stored picture frame generation Dynamic Graph.
In the specific implementation, after this continuous shooting terminates, terminal can shoot this continuous shooting directly or according to user's request Image making turn into GIF Dynamic Graphs, improve burst mode interest.
In another alternative embodiment, step S102 may include step:
11) multiple cache image frames containing face-image of the camera collection, are obtained;
12) the focusing evaluation of estimate of each cache image frame in multiple described cache image frames, is calculated;
13) the maximum cache image frame of focusing evaluation of estimate in multiple described cache image frames, is chosen as the collection to scheme As frame.
After terminal obtains first continuous shooting image, terminal gathers multiple cachings containing face-image by camera Picture frame, and the focusing evaluation of estimate of focusing area in every picture frame is calculated simultaneously, wherein focusing evaluation of estimate is focusing area Definition reference value (such as sharpness value), then the maximum cache image frame of selection focusing evaluation of estimate is used as collection image therefrom Frame, can obtain relatively that clearly acquired image frames are to increase the definition of continuous shooting image, with certain stabilization effect.
The embodiment of the present invention, can receive continuous shooting enabled instruction, obtain the starting figure containing face-image of camera collection As frame, using the start image frame is as reference picture and stores;The camera collection can also be obtained contains face-image Acquired image frames;Detect the face characteristic information in the acquired image frames and the face characteristic information of the reference picture Difference value;And then when the difference value is more than threshold value, the acquired image frames are set to reference picture and stored, execution is obtained The step of taking the acquired image frames containing face-image of the camera collection, can save the storage resource of terminal, the company of raising The degree of accuracy of useful picture frame is captured during bat, Consumer's Experience is improved.
It is another continuous shooting method schematic flow sheet provided in an embodiment of the present invention, continuous shooting side as depicted referring to Fig. 2 Method may include following steps:
S201, receives continuous shooting enabled instruction, obtains the start image frame containing face-image of camera collection, will be described Start image frame is as reference picture and stores.
S202, obtains the acquired image frames containing face-image of the camera collection.
S203, obtains the coordinate value of face characteristic in the acquired image frames and the reference picture respectively.
In the specific implementation, this step can be based on face recognition technology, pedestrian is entered to acquired image frames and reference picture first Face detection (judge whether face-image in complicated background and split it from background) is included with obtaining it Face-image, then the face-image included in acquired image frames and reference picture is sampled to obtain human face characteristic point Coordinate value.
S204, judges the coordinate value of the coordinate value of face characteristic and face characteristic in the acquired image frames in reference picture Between difference whether be more than or equal to threshold value.
If the difference in reference picture in the coordinate value and acquired image frames of face characteristic between the coordinate value of face characteristic Step S205 is continued executing with more than or equal to threshold value.For example, setting the transverse and longitudinal of corners of the mouth characteristic point A points and B points in face characteristic to sit The threshold value for marking difference value is 0.5, after acquired image frames and reference picture are done with Face datection and face characteristic information extraction, is obtained Into acquired image frames, the coordinate of corners of the mouth A points and B points is respectively corners of the mouth A points in (0.5,1.5) and (2.5,1.5), reference picture Coordinate with B points is respectively the horizontal stroke of A points and B points in (1,1) and (2,1), therefore detectable acquired image frames and reference picture Ordinate difference value is equal to default threshold value for respectively 0.5, now performs step S205.Optionally, if people in reference picture Difference in the coordinate value and acquired image frames of face feature between the coordinate value of face characteristic is less than threshold value, then performs step S202。
The acquired image frames are set to reference picture and stored by S205.
S206, judges whether the quantity as reference picture and the picture frame stored is more than or equal to first threshold.
The image shot needed for this continuous shooting can be specified while camera selection burst mode is started by implementing Quantity is as first threshold, and usual terminal provides 4 continuous shootings, 6 continuous shootings, 8 continuous shootings or the selection of 16 burst mode options for user, also Can selection burst mode after shooting image needed for self-defined continuous shooting quantity.Terminal often shoots a figure during continuous shooting Picture, just judges whether the image captured by this continuous shooting reaches default first threshold, if so, then terminating this continuous shooting;If it is not, Then step S202~S206 is performed until completing this continuous shooting.
S207, terminates continuous shooting.
The embodiment of the present invention, can obtain the starting containing face-image of camera collection when receiving continuous shooting enabled instruction Picture frame, using the start image frame is as reference picture and stores, can also obtain the camera collection containing face figure The acquired image frames of picture, so obtain respectively in the acquired image frames and the reference picture coordinate value of face characteristic and Judge that the difference in reference picture in the coordinate value of face characteristic and the acquired image frames between the coordinate value of face characteristic is big When threshold value, the acquired image frames are set to reference picture and stored, then judge described as reference picture And whether the quantity of the picture frame stored is more than or equal to first threshold, and in its judged result to terminate this continuous shooting when being, It can save the storage resource of terminal, improve the degree of accuracy that useful picture frame is captured during continuous shooting, improve Consumer's Experience.
Referring to Fig. 3, a kind of continuous shooting apparatus structure schematic diagram provided in an embodiment of the present invention, continuous shooting device as depicted is extremely It can include less:Picture frame acquiring unit 301, reference image setting unit 302 and facial features localization unit 303.
Picture frame acquiring unit 301, for receiving continuous shooting enabled instruction, obtain camera collection containing face-image Start image frame.
In the specific implementation, can start camera first and select burst mode in the setting menu of terminal, camera enters Enter and auto-focusing just carried out after viewfinder mode, user inputted when getting out posture photographing instruction be just considered as input continuous shooting start refer to Order, wherein, the input of photographing instruction has various ways, can be that user clicks on camera button triggering or terminal is being prolonged When exposal model under, the delay of taking pictures of terminal is triggered when reaching.Continuous shooting method in the present embodiment, its main application scenarios Include the continuous shooting image of character face's image for collection, therefore picture frame acquiring unit 301 is when receiving continuous shooting and instructing, picture frame Acquiring unit 301 gathers the start image frame containing face-image by camera, and reference image setting unit 302 described will rise Beginning picture frame is as reference picture and stores, and is used as first image photographed during continuous shooting.
Reference image setting unit 302, for using the start image frame is as reference picture and stores.
Described image frame acquiring unit 301, is additionally operable to obtain the collection figure containing face-image of the camera collection As frame.
Reference image setting unit 302 is using the start image frame as after reference picture, and camera, which continues to find a view, goes forward side by side Row auto-focusing, to gather the acquired image frames containing face-image, waits other images during continuous shooting to be captured.
Facial features localization unit 303, for detecting the face characteristic information in the acquired image frames and the reference The difference value of the face characteristic information of image.
In the specific implementation, facial features localization unit 303 can be based on face recognition technology, first to acquired image frames and ginseng Examine image and carry out Face datection (judge whether face-image in complicated background and split it from background) To obtain the face-image that it is included, then the face-image included in acquired image frames and reference picture is sampled to enter Pedestrian's face feature information extraction, and then detect the face characteristic information in the acquired image frames and the face of the reference picture The difference value of characteristic information.The method of Face datection includes but is not limited to:The regular method of reference template method, face, sample learning method, Complexion model method or sub-face of feature method etc..The extraction of face characteristic information is generally included:Feature vector method and face line template.Its In, the feature vector method of recognition of face refers to:Determine the image surface face profile such as eye iris, the wing of nose, corners of the mouth size, position, The attributes such as distance, the geometric feature (Euclidean distance, curvature, angle) or algebraically for then calculating each characteristic point in face profile is special Facial characteristics of the amount of levying (matrix character vector) to describe picture frame septum reset image.
In the present embodiment, can obtain acquired image frames and reference picture septum reset image face feature point (such as corners of the mouth, The wing of nose, canthus, eye exterior feature, nose, brows, eyebrow tail) coordinate information in picture frame, it is then each in detection acquired image frames respectively Face feature point and the coordinate difference of each corresponding face feature point in reference picture, are schemed with the face judged in acquired image frames Seem no espressiove or change in location, the change of such as the distance between brows can determine whether whether face has the table knitted one's brows The change of the distance between feelings, nose and canthus can determine whether the expression for whether having wrinkle nose in face.
For example, the threshold value for setting the transverse and longitudinal coordinate difference value of corners of the mouth characteristic point A points and B points in face characteristic is 0.5, right Acquired image frames and reference picture are done after Face datection and face characteristic information extraction, obtain corners of the mouth A points and B in acquired image frames Point coordinate be respectively (0.5,1.5) and (2.5,1.5), in reference picture the coordinate of corners of the mouth A points and B points be respectively (1,1) and The transverse and longitudinal coordinate difference value of A points and B points is respectively 0.5 in (2,1), therefore detectable acquired image frames and reference picture, Equal to default threshold value, the acquired image frames are set to reference picture and stored by the reference image setting unit 302.Its In, the difference of the abscissa of corners of the mouth A points and B points can represent the length of face, and the difference of the ordinate of corners of the mouth A points and B points can represent institute State the difference in height of the corners of the mouth, it is known that relative to the face of reference picture septum reset image, the mouth in acquired image frames septum reset image Ba Changdu increased and the corners of the mouth has raised up, therefore can determine whether, relative to the face in reference picture septum reset image, to adopt Face in collection picture frame, which has, is changed into smile's state, is that espressiove becomes relative to the face-image in reference picture acquired image frames Change.
The reference image setting unit 302, is additionally operable to when the difference value is more than or equal to threshold value, by the collection Picture frame is set to reference picture and stored.
The acquired image frames are set to reference picture in the reference image setting unit 302 and stored by the present embodiment Afterwards, if this continuous shooting needed for collection image and do not complete can continue through described image frame acquiring unit 301, the reference Image setting unit 302 and the facial features localization unit 303 complete the collection of continuous shooting image until this continuous shooting terminates.
In another alternative embodiment, the continuous shooting device also includes:Amount of images judging unit 304, for the ginseng Examine image setting unit by the acquired image frames be set to reference picture and store after, judge it is described as reference picture simultaneously Whether the quantity of the picture frame of storage is more than or equal to first threshold, if so, terminating continuous shooting;Otherwise, described image frame obtains single Member 301 obtains the acquired image frames containing face-image of the camera collection.
In the specific implementation, the image shot needed for this continuous shooting can be specified while camera selection burst mode is started Quantity is as first threshold, and usual terminal provides 4 continuous shootings, 6 continuous shootings, 8 continuous shootings or the selection of 16 burst mode options for user, also Can selection burst mode after shooting image needed for self-defined continuous shooting quantity.An image is often shot during continuous shooting, is schemed Whether the image as captured by quantity judging unit 304 just judges this continuous shooting reaches default first threshold, if so, then terminating This continuous shooting;If it is not, described image frame acquiring unit 301 is continued through, the reference image setting unit 302 and the face Characteristic detection unit 303 shoots continuous shooting image until completing this continuous shooting.
In another alternative embodiment, the continuous shooting device also includes:Timestamp acquiring unit 305, for described image Frame acquiring unit is received after continuous shooting enabled instruction, obtains the initial time stamp of the continuous shooting enabled instruction.
The timestamp acquiring unit 305, is additionally operable to obtain current time stamp.
Accordingly, the continuous shooting device also includes:Continuous shooting duration judging unit 306, for according to the current time stamp Continuous shooting duration is calculated with the initial time stamp, judges whether the continuous shooting duration is more than or equal to Second Threshold, if so, terminating Continuous shooting;Otherwise, described image frame acquiring unit 301 obtains the acquired image frames containing face-image of the camera collection.
When in the specific implementation, burst mode can selected in advance, continuous shooting duration needed for this continuous shooting is set to be used as the Two threshold values, after terminal receives reception continuous shooting enabled instruction, timestamp acquiring unit 305 obtains continuous shooting initial time, opens Beginning timing, often shoots an image during continuous shooting, and timestamp acquiring unit 305 obtains current time to calculate during continuous shooting Long, continuous shooting duration judging unit 306 just judges whether this continuous shooting duration reaches default Second Threshold, if so, then terminating this Secondary continuous shooting;If it is not, continuing through described image frame acquiring unit 301, the reference image setting unit 302, the face are special Levy detection unit 303 and shoot continuous shooting image until this continuous shooting duration reaches predetermined threshold value so as to complete this continuous shooting.
In another alternative embodiment, the continuous shooting device also includes:Dynamic Graph synthesis unit 307, for the reference The acquired image frames are set to after reference picture and storage by image setting unit, are received Dynamic Graph generation instruction, are obtained As reference picture and stored picture frame, according to described as reference picture and stored picture frame generates Dynamic Graph.
After continuous shooting terminates, what Dynamic Graph synthesis unit 307 can shoot this continuous shooting directly or according to user's request Image making turns into GIF Dynamic Graphs, improves the interest of burst mode.
Referring to Fig. 4, picture frame acquiring unit structural representation provided in an embodiment of the present invention, picture frame as depicted is obtained Unit 301 is taken to include:Cache image frame obtains subelement 3101, and focusing evaluation of estimate computation subunit 3102 gathers image Frame chooses subelement 3103.
Cache image frame obtains subelement 3101, and multiple containing face-image for obtaining the camera collection are delayed Deposit picture frame.
Evaluation of estimate of focusing computation subunit 3102, pair for calculating each cache image frame in multiple described cache image frames Burnt evaluation of estimate.
Acquired image frames choose subelement 3103, for choosing focusing evaluation of estimate maximum in multiple described cache image frames Cache image frame is used as the acquired image frames.
After first continuous shooting image is obtained, cache image frame obtains subelement 3101 and contains face by camera collection Multiple cache image frames of portion's image, focusing evaluation of estimate computation subunit 3102 calculates focusing area in every cache image frame Focusing evaluation of estimate, wherein focusing evaluation of estimate is the definition reference value (such as sharpness value) of focusing area, then acquired image frames are selected Take subelement 3103 to select to focus the maximum cache image frame of evaluation of estimate therefrom as acquired image frames, can obtain relatively clear Clear acquired image frames are to increase the definition of continuous shooting image, with certain stabilization effect.
Referring to Fig. 5, facial features localization cellular construction schematic diagram provided in an embodiment of the present invention, face as depicted is special Levying detection unit 303 can include:Face characteristic obtains subelement 3301 and face characteristic judgment sub-unit 3303.
Face characteristic obtains subelement 3301, the coordinate value for obtaining face characteristic in the acquired image frames.
In the specific implementation, face characteristic, which obtains subelement 3301, can be based on face recognition technology, first to acquired image frames Face datection (judge whether face-image in complicated background and split it from background) is carried out to obtain Its face-image included, is then sampled to obtain face to the face-image included in acquired image frames and reference picture The coordinate value of characteristic point.
The face characteristic obtains subelement 3301, is additionally operable to obtain the coordinate value of face characteristic in the reference picture.
Face characteristic judgment sub-unit 3302, for judging that the coordinate value of face characteristic is adopted with described in the reference picture Collect whether the difference in picture frame between the coordinate value of face characteristic is more than threshold value, if so, the reference image setting unit 302 The acquired image frames are set to reference picture and stored;If it is not, described image frame acquiring unit 301 obtains the camera The acquired image frames containing face-image of collection.
For example, the threshold value for setting the transverse and longitudinal coordinate difference value of corners of the mouth characteristic point A points and B points in face characteristic is 0.5, face Feature obtain subelement 3301 obtain acquired image frames in corners of the mouth A points and B points coordinate be respectively (0.5,1.5) and (2.5, 1.5), the coordinate of corners of the mouth A points and B points is respectively (1,1) and (2,1) in reference picture, therefore face characteristic judgment sub-unit The transverse and longitudinal coordinate difference value of A points and B points is respectively 0.5 in 3302 detectable acquired image frames and reference picture, equal to pre- If threshold value, now reference image setting unit 302 acquired image frames are set to reference picture and stored.
A kind of continuous shooting method and device disclosed in the embodiment of the present invention are described in detail above, it is above disclosed Only present pre-ferred embodiments, can not limit the interest field of the present invention with this certainly, therefore according to right of the present invention It is required that the equivalent variations made, still belong to the scope that the present invention is covered.

Claims (10)

1. a kind of continuous shooting method, it is characterised in that including:
Continuous shooting enabled instruction is received, the start image frame containing face-image of camera collection is obtained, by the start image Frame is as reference picture and stores;
Obtain the acquired image frames containing face-image of the camera collection;
Detect the difference value of the face characteristic information in the acquired image frames and the face characteristic information of the reference picture;
When the difference value is more than or equal to threshold value, the acquired image frames are set to reference picture and stored, execution is obtained The step of taking the acquired image frames containing face-image of the camera collection;
Wherein, it is described that the acquired image frames are set to after reference picture and storage, in addition to:
Judge whether the quantity as reference picture and the picture frame stored is more than or equal to first threshold, if so, terminating Continuous shooting;Otherwise, the step of performing the acquired image frames containing face-image of the acquisition camera collection.
2. according to the method described in claim 1, it is characterised in that after the reception continuous shooting enabled instruction step, in addition to:
Obtain the initial time stamp of the continuous shooting enabled instruction;
The step of acquired image frames containing face-image of the acquisition camera collection, includes:
Current time stamp is obtained, continuous shooting duration is calculated according to the current time stamp and the initial time stamp, the company is judged Clap whether duration is more than or equal to Second Threshold, if so, terminating continuous shooting;Otherwise, the acquisition camera collection is performed The step of acquired image frames containing face-image.
3. according to the method described in claim 1, it is characterised in that described that the acquired image frames are set to reference picture simultaneously Also include after the step of storage:
Dynamic Graph generation instruction is received, obtains as reference picture and stored picture frame, reference picture is used as according to described And stored picture frame generation Dynamic Graph.
4. according to the method described in claim 1, it is characterised in that what the acquisition camera was gathered contains face-image Acquired image frames include:
Obtain multiple cache image frames containing face-image of the camera collection;
The focusing evaluation of estimate of each cache image frame in multiple described cache image frames is calculated, focusing evaluation of estimate is clear for focusing area Clear degree reference value;
Choose the maximum cache image frame of focusing evaluation of estimate in multiple described cache image frames and be used as the acquired image frames.
5. according to the method described in claim 1, it is characterised in that the detection acquired image frames and the reference picture The difference value of face characteristic information include:
Obtain the coordinate value of face characteristic in the acquired image frames;
Obtain the coordinate value of face characteristic in the reference picture;
Judge in the reference picture in the coordinate value of face characteristic and the acquired image frames between the coordinate value of face characteristic Difference whether be more than or equal to the threshold value, if so, perform the acquired image frames are set to reference picture and stored Step;If it is not, performing the acquired image frames step containing face-image for obtaining the camera collection.
6. a kind of continuous shooting device, it is characterised in that including:
Picture frame acquiring unit, for receiving continuous shooting enabled instruction, obtains the starting figure containing face-image of camera collection As frame;
Reference image setting unit, for using the start image frame is as reference picture and stores;
Described image frame acquiring unit, is additionally operable to obtain the acquired image frames containing face-image of the camera collection;
Facial features localization unit, the people for detecting the face characteristic information in the acquired image frames and the reference picture The difference value of face characteristic information;
The reference image setting unit, is additionally operable to when the difference value is more than or equal to threshold value, by the acquired image frames It is set to reference picture and stores;
Wherein, described device also includes:
The acquired image frames are set to reference picture simultaneously by amount of images judging unit for the reference image setting unit After storage, judge whether the quantity as reference picture and the picture frame stored is more than or equal to first threshold, if so, Terminate continuous shooting;Otherwise, described image frame acquiring unit obtains the acquired image frames containing face-image of the camera collection.
7. device according to claim 6, it is characterised in that described device also includes:
Timestamp acquiring unit, after the reception continuous shooting enabled instruction of described image frame acquiring unit, obtains the continuous shooting and opens The initial time stamp of dynamic instruction;
The timestamp acquiring unit, is additionally operable to obtain current time stamp;
Continuous shooting duration judging unit, for calculating continuous shooting duration according to the current time stamp and the initial time stamp, judges Whether the continuous shooting duration is more than or equal to Second Threshold, if so, terminating continuous shooting;Otherwise, described image frame acquiring unit is obtained The acquired image frames containing face-image of the camera collection.
8. device according to claim 6, it is characterised in that described device also includes:
The acquired image frames are set to reference picture for the reference image setting unit and deposited by Dynamic Graph synthesis unit After storage, Dynamic Graph generation instruction is received, is obtained as reference picture and stored picture frame, according to described as with reference to figure Picture and stored picture frame generation Dynamic Graph.
9. device according to claim 6, it is characterised in that described image frame acquiring unit includes:
Cache image frame obtains subelement, multiple cache images containing face-image for obtaining the camera collection Frame;
Focusing evaluation of estimate computation subunit, the focusing evaluation for calculating each cache image frame in multiple described cache image frames Value, focusing evaluation of estimate is the definition reference value of focusing area;
Acquired image frames choose subelement, for choosing the maximum cache image of focusing evaluation of estimate in multiple described cache image frames Frame is used as the acquired image frames.
10. device according to claim 6, it is characterised in that the facial features localization unit includes:
Face characteristic obtains subelement, the coordinate value for obtaining face characteristic in the acquired image frames;
The face characteristic obtains subelement, is additionally operable to obtain the coordinate value of face characteristic in the reference picture;
Face characteristic judgment sub-unit, for judging the coordinate value of face characteristic and the acquired image frames in the reference picture Whether the difference between the coordinate value of middle face characteristic is more than or equal to the threshold value, if so, the reference image setting unit The acquired image frames are set to reference picture and stored;Adopted if it is not, described image frame acquiring unit obtains the camera The acquired image frames containing face-image of collection.
CN201510058180.3A 2015-02-04 2015-02-04 A kind of continuous shooting method and device Expired - Fee Related CN104683692B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201510058180.3A CN104683692B (en) 2015-02-04 2015-02-04 A kind of continuous shooting method and device
CN201710877073.2A CN107483834B (en) 2015-02-04 2015-02-04 Image processing method, continuous shooting method and device and related medium product

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510058180.3A CN104683692B (en) 2015-02-04 2015-02-04 A kind of continuous shooting method and device

Related Child Applications (1)

Application Number Title Priority Date Filing Date
CN201710877073.2A Division CN107483834B (en) 2015-02-04 2015-02-04 Image processing method, continuous shooting method and device and related medium product

Publications (2)

Publication Number Publication Date
CN104683692A CN104683692A (en) 2015-06-03
CN104683692B true CN104683692B (en) 2017-10-17

Family

ID=53318197

Family Applications (2)

Application Number Title Priority Date Filing Date
CN201710877073.2A Expired - Fee Related CN107483834B (en) 2015-02-04 2015-02-04 Image processing method, continuous shooting method and device and related medium product
CN201510058180.3A Expired - Fee Related CN104683692B (en) 2015-02-04 2015-02-04 A kind of continuous shooting method and device

Family Applications Before (1)

Application Number Title Priority Date Filing Date
CN201710877073.2A Expired - Fee Related CN107483834B (en) 2015-02-04 2015-02-04 Image processing method, continuous shooting method and device and related medium product

Country Status (1)

Country Link
CN (2) CN107483834B (en)

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105323483B (en) * 2015-10-27 2018-06-29 广东欧珀移动通信有限公司 GIF picture shootings and playback method and GIF picture shootings and play system
CN105554373A (en) * 2015-11-20 2016-05-04 宇龙计算机通信科技(深圳)有限公司 Photographing processing method and device and terminal
CN106303235A (en) * 2016-08-11 2017-01-04 广东小天才科技有限公司 Take pictures processing method and processing device
CN106303234A (en) * 2016-08-11 2017-01-04 广东小天才科技有限公司 Take pictures processing method and processing device
CN107240143A (en) * 2017-05-09 2017-10-10 北京小米移动软件有限公司 Bag generation method of expressing one's feelings and device
CN107368777A (en) * 2017-06-02 2017-11-21 广州视源电子科技股份有限公司 A kind of smile motion detection method and device and vivo identification method and system
US11191341B2 (en) * 2018-01-11 2021-12-07 Casio Computer Co., Ltd. Notification device, notification method, and storage medium having program stored therein
CN108401110B (en) * 2018-03-18 2020-09-08 Oppo广东移动通信有限公司 Image acquisition method and device, storage medium and electronic equipment
CN109389086B (en) * 2018-10-09 2021-03-05 北京科技大学 Method and system for detecting unmanned aerial vehicle image target
CN109447006A (en) * 2018-11-01 2019-03-08 北京旷视科技有限公司 Image processing method, device, equipment and storage medium
CN109659006B (en) * 2018-12-10 2021-03-23 深圳先进技术研究院 Facial muscle training method and device and electronic equipment
WO2020155052A1 (en) * 2019-01-31 2020-08-06 华为技术有限公司 Method for selecting images based on continuous shooting and electronic device
CN110769150A (en) * 2019-09-23 2020-02-07 珠海格力电器股份有限公司 Photographing method, device, terminal and computer readable medium
TWI777126B (en) * 2020-01-22 2022-09-11 中國醫藥大學 Method of facial characteristic angle measurement and device thereof
CN111669504B (en) * 2020-06-29 2021-11-05 维沃移动通信有限公司 Image shooting method and device and electronic equipment
CN113239220A (en) * 2021-05-26 2021-08-10 Oppo广东移动通信有限公司 Image recommendation method and device, terminal and readable storage medium
CN114245017A (en) * 2021-12-21 2022-03-25 维沃移动通信有限公司 Shooting method and device and electronic equipment

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005275916A (en) * 2004-03-25 2005-10-06 Toyota Motor Corp Image recognition device and image recognition method
JP2005323227A (en) * 2004-05-11 2005-11-17 Fuji Photo Film Co Ltd Device, method, and program for picking up image
CN1731859A (en) * 2005-09-09 2006-02-08 北京中星微电子有限公司 Video compression method and video system using the method
FR2875322A1 (en) * 2004-09-14 2006-03-17 Atmel Grenoble Soc Par Actions Person`s face locating method for e.g. identifying person, involves detecting eyes in digital image produced by performing point to point subtraction between reference image taken before or after eye blink and image taken during blink
CN101290539A (en) * 2008-06-12 2008-10-22 北京中星微电子有限公司 Electronic equipment usage situation judgement method and system
JP2009081636A (en) * 2007-09-26 2009-04-16 Casio Comput Co Ltd Image recording apparatus and photographing method
WO2010070820A1 (en) * 2008-12-17 2010-06-24 パナソニック株式会社 Image communication device and image communication method
DE102009049528A1 (en) * 2009-10-15 2011-04-21 Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. Method for detecting facial movement e.g. facial expression, of face in image sequence, involves calculating difference between positions of reference points in respective images, and detecting movement of face based on difference
CN102208107A (en) * 2010-03-30 2011-10-05 索尼公司 Image processing device, image processing method, and program
CN103020580A (en) * 2011-09-23 2013-04-03 无锡中星微电子有限公司 Rapid human face detection method

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101354899B1 (en) * 2007-08-29 2014-01-27 삼성전자주식회사 Method for photographing panorama picture
KR101398475B1 (en) * 2007-11-21 2014-05-26 삼성전자주식회사 Apparatus for processing digital image and method for controlling thereof
JP5247356B2 (en) * 2008-10-29 2013-07-24 キヤノン株式会社 Information processing apparatus and control method thereof
CN103856617A (en) * 2012-12-03 2014-06-11 联想(北京)有限公司 Photographing method and user terminal
CN103903213B (en) * 2012-12-24 2018-04-27 联想(北京)有限公司 A kind of image pickup method and electronic equipment
CN103152524B (en) * 2013-03-05 2016-04-06 东莞宇龙通信科技有限公司 Camera arrangement and continuous shooting method thereof
TWI496109B (en) * 2013-07-12 2015-08-11 Vivotek Inc Image processor and image merging method thereof
CN103491299B (en) * 2013-09-17 2016-10-05 宇龙计算机通信科技(深圳)有限公司 One is taken pictures treating method and apparatus
CN104185981A (en) * 2013-10-23 2014-12-03 华为终端有限公司 Method and terminal selecting image from continuous captured image
CN103685948A (en) * 2013-12-04 2014-03-26 乐视致新电子科技(天津)有限公司 Shooting method and device

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005275916A (en) * 2004-03-25 2005-10-06 Toyota Motor Corp Image recognition device and image recognition method
JP2005323227A (en) * 2004-05-11 2005-11-17 Fuji Photo Film Co Ltd Device, method, and program for picking up image
FR2875322A1 (en) * 2004-09-14 2006-03-17 Atmel Grenoble Soc Par Actions Person`s face locating method for e.g. identifying person, involves detecting eyes in digital image produced by performing point to point subtraction between reference image taken before or after eye blink and image taken during blink
CN1731859A (en) * 2005-09-09 2006-02-08 北京中星微电子有限公司 Video compression method and video system using the method
JP2009081636A (en) * 2007-09-26 2009-04-16 Casio Comput Co Ltd Image recording apparatus and photographing method
CN101290539A (en) * 2008-06-12 2008-10-22 北京中星微电子有限公司 Electronic equipment usage situation judgement method and system
WO2010070820A1 (en) * 2008-12-17 2010-06-24 パナソニック株式会社 Image communication device and image communication method
DE102009049528A1 (en) * 2009-10-15 2011-04-21 Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. Method for detecting facial movement e.g. facial expression, of face in image sequence, involves calculating difference between positions of reference points in respective images, and detecting movement of face based on difference
CN102208107A (en) * 2010-03-30 2011-10-05 索尼公司 Image processing device, image processing method, and program
CN103020580A (en) * 2011-09-23 2013-04-03 无锡中星微电子有限公司 Rapid human face detection method

Also Published As

Publication number Publication date
CN104683692A (en) 2015-06-03
CN107483834B (en) 2020-01-14
CN107483834A (en) 2017-12-15

Similar Documents

Publication Publication Date Title
CN104683692B (en) A kind of continuous shooting method and device
CN104754218B (en) A kind of Intelligent photographing method and terminal
CN104519263A (en) Method for acquiring image and electronic device
CN103685940A (en) Method for recognizing shot photos by facial expressions
CN102946516A (en) Mobile terminal and method for detecting blink action and realizing autodyne by mobile terminal
CN108307120B (en) Image shooting method and device and electronic terminal
CN106331497B (en) A kind of image processing method and terminal
CN105227855B (en) A kind of image processing method and terminal
CN104219444B (en) The processing method and processing device of video capture
EP3518522B1 (en) Image capturing method and device
CN106372627A (en) Automatic photographing method and device based on face image recognition and electronic device
CN104883505A (en) Electronic equipment and photographing control method therefor
CN106648344A (en) Screen content adjustment method and equipment
CN107909539A (en) Image background weakening method, terminal and computer-readable recording medium
CN104506765A (en) Mobile terminal and focusing method based on touch gesture of mobile terminal
CN109961403B (en) Photo adjusting method and device, storage medium and electronic equipment
CN107835373A (en) A kind of mobile terminal and its take pictures beautification method and system
CN103873755B (en) Jump portrait system and method
CN108600628B (en) Image capturing method and device, terminal and readable medium
CN104683680A (en) A method, device and mobile terminal for automatically taking a picture
CN107357424B (en) Gesture operation recognition method and device and computer readable storage medium
CN115862081A (en) Image acquisition method, device, equipment and computer readable storage medium
CN112188108A (en) Photographing method, terminal, and computer-readable storage medium
CN104539842A (en) Intelligent photographing method and photographing device
CN107920210A (en) Image capturing method, device and terminal

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CP01 Change in the name or title of a patent holder

Address after: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18

Patentee after: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd.

Address before: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18

Patentee before: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd.

CP01 Change in the name or title of a patent holder
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20171017

CF01 Termination of patent right due to non-payment of annual fee