CN108711192A - A kind of method for processing video frequency and device - Google Patents
A kind of method for processing video frequency and device Download PDFInfo
- Publication number
- CN108711192A CN108711192A CN201810316980.4A CN201810316980A CN108711192A CN 108711192 A CN108711192 A CN 108711192A CN 201810316980 A CN201810316980 A CN 201810316980A CN 108711192 A CN108711192 A CN 108711192A
- Authority
- CN
- China
- Prior art keywords
- special efficacy
- efficacy model
- dimensional special
- face
- dimensional
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
Abstract
The invention discloses a kind of method for processing video frequency, device, electronic equipment and computer readable storage mediums.This method includes：Obtain the video for including two or more target objects of video collector acquisition；In response to the operation of the three-dimensional special efficacy model of load, corresponding three-dimensional special efficacy model is loaded respectively for each target object in video, establishes and preserve the correspondence of each target object and each three-dimensional special efficacy model；When detecting target object generation action variation, according to correspondence, the corresponding action variation of the corresponding three-dimensional special efficacy model progress of driving and target object.Pass through the technical program, after the three-dimensional special efficacy model of each target object load in being embodied as video, each target object can also respectively drive corresponding three-dimensional special efficacy model and carry out action variation, meet the higher and higher video process demand of user, the interest for increasing video processing, enhances the usage experience of user.
Description
Technical field
The present invention relates to field of computer technology, and in particular to a kind of method for processing video frequency, device, electronic equipment and calculating
Machine readable storage medium storing program for executing.
Background technology
Nowadays, simply take pictures either record video operation cannot meet the needs of users in image or regard
The processing mode that various special efficacys have become image popular at present or video is added in frequency, for example, user upon taking a picture, is
Face adds three-dimensional special efficacy model etc..But it is based on the prior art, it is the three-dimensional special efficacy model of face load to be also only, or
When there are multiple faces in image or video, identical or different three-dimensional special efficacy model, such image are loaded for multiple faces
Or video processing mode increasingly cannot be satisfied the higher demand of user, reduce the use of user known to user
Experience.
Invention content
In view of the above problems, it is proposed that the present invention overcoming the above problem in order to provide one kind or solves at least partly
State method for processing video frequency, device, electronic equipment and the computer readable storage medium of problem.
According to an aspect of the invention, there is provided a kind of method for processing video frequency, wherein this method includes：
Obtain the video for including two or more target objects of video collector acquisition；
In response to the operation of the three-dimensional special efficacy model of load, corresponding three-dimensional is loaded respectively for each target object in the video
The correspondence of each target object and each three-dimensional special efficacy model is established and preserved to special efficacy model；
When detecting the target object generation action variation, according to the correspondence, driving and the target pair
As the corresponding three-dimensional special efficacy model carries out corresponding action variation.
Optionally, the correspondence of each target object and each three-dimensional special efficacy model includes：
Each corresponding fisrt feature information of target object and the corresponding second feature of each three-dimensional special efficacy model
One-to-one relationship between information.
Optionally, this method further comprises：
When meeting the first preset condition, the corresponding fisrt feature information of each target object is re-established and preserves,
And one-to-one relationship between the corresponding second feature information of each three-dimensional special efficacy model.
Optionally, this method further comprises：
It is that the respective objects object in the video replaces three-dimensional special efficacy model when meeting the second preset condition.
Optionally, the three-dimensional special efficacy model of respective objects object replacement in the video includes：
According to the type of the three-dimensional special efficacy model before replacement, the type of the three-dimensional special efficacy model after replacing is determined, from determination
Type in randomly select three-dimensional special efficacy model, or three-dimensional spy is selected from determining type according to second preset condition
Imitate model；
And/or
The three-dimensional special efficacy model after replacing directly is determined according to second preset condition.
Optionally, the three-dimensional special efficacy model is that three-dimensional sprouts face special efficacy model；Described is each target object in the video
Loading corresponding three-dimensional special efficacy model respectively includes：
Face special efficacy model, which is sprouted, with the three-dimensional replaces corresponding target object.
Optionally, this method further comprises：
Corresponding instruction image is generated according to each target object；
Each instruction image is added to the designated position of the corresponding video image.
Optionally, the target object is face.
According to another aspect of the present invention, a kind of video process apparatus is provided, wherein the device includes：
Acquiring unit is suitable for obtaining the video for including two or more target objects of video collector acquisition；
Correspondence relationship establishing unit is adapted for loading the operation of three-dimensional special efficacy model, is each target in the video
Object loads corresponding three-dimensional special efficacy model respectively, establishes and preserve the corresponding pass of each target object and each three-dimensional special efficacy model
System；
Driving unit, suitable for when detecting the target object generation action variation, according to the correspondence, driving
The corresponding action variation of corresponding with the target object three-dimensional special efficacy model progresss.
Optionally, the correspondence relationship establishing unit is adapted to set up and preserves corresponding first spy of each target object
One-to-one relationship between reference breath and the corresponding second feature information of each three-dimensional special efficacy model.
Optionally,
The correspondence relationship establishing unit is suitable for when meeting the first preset condition, re-establishes and preserve each target pair
As being corresponded between corresponding fisrt feature information and the corresponding second feature information of each three-dimensional special efficacy model
Relationship.
Optionally, which further comprises：
Unit is replaced, is suitable for when meeting the second preset condition, is that the respective objects object in the video replaces three-dimensional
Special efficacy model.
Optionally, the replacement unit is suitable for the type according to the three-dimensional special efficacy model before replacement, determines three after replacing
The type for tieing up special efficacy model, randomly selects three-dimensional special efficacy model, or according to second preset condition from determining type
Three-dimensional special efficacy model is selected from determining type；And/or the three-dimensional after replacing directly is determined according to second preset condition
Special efficacy model.
Optionally, the three-dimensional special efficacy model is that three-dimensional sprouts face special efficacy model；
The correspondence relationship establishing unit replaces corresponding target object suitable for sprouting face special efficacy model with the three-dimensional.
Optionally, which further comprises：
Indicating unit is suitable for generating corresponding instruction image according to each target object；Each instruction image is added to correspondence
The video image designated position.
Optionally, the target object is face.
According to another aspect of the invention, a kind of electronic equipment is provided, wherein the electronic equipment includes：
Processor；And
It is arranged to the memory of storage computer executable instructions, the executable instruction makes the place when executed
Device is managed to execute according to method above-mentioned.
In accordance with a further aspect of the present invention, a kind of computer readable storage medium is provided, wherein described computer-readable
The one or more programs of storage medium storage, one or more of programs when being executed by a processor, realize method above-mentioned.
According to the technique and scheme of the present invention, obtain video collector acquisition includes two or more target objects
Video；In response to the operation of the three-dimensional special efficacy model of load, corresponding three-dimensional special efficacy mould is loaded respectively for each target object in video
The correspondence of each target object and each three-dimensional special efficacy model is established and preserved to type；Become when detecting that target object generation acts
When change, according to correspondence, the corresponding action variation of the corresponding three-dimensional special efficacy model progress of driving and target object.By this skill
Art scheme, after the three-dimensional special efficacy model of each target object load in being embodied as video, each target object can also drive respectively
Dynamic corresponding three-dimensional special efficacy model carries out action variation, meets the higher and higher video process demand of user, increases video processing
Interest, enhance the usage experience of user.
Above description is only the general introduction of technical solution of the present invention, in order to better understand the technical means of the present invention,
And can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, below the special specific implementation mode for lifting the present invention.
Description of the drawings
By reading the detailed description of hereafter preferred embodiment, various other advantages and benefit are common for this field
Technical staff will become clear.Attached drawing only for the purpose of illustrating preferred embodiments, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings：
Fig. 1 shows the flow diagram of method for processing video frequency according to an embodiment of the invention；
Fig. 2 shows the structural schematic diagrams of video process apparatus according to an embodiment of the invention；
Fig. 3 shows the structural schematic diagram of electronic equipment according to an embodiment of the invention；
Fig. 4 shows the structural schematic diagram of computer readable storage medium according to an embodiment of the invention.
Specific implementation mode
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
Fig. 1 shows the flow diagram of method for processing video frequency according to an embodiment of the invention.As shown in Figure 1, should
Method includes：
Step S110 obtains the video for including two or more target objects of video collector acquisition.
In the present embodiment, after the video for getting video collector acquisition, include in video two or two are identified
A above target object.Recongnition of objects method in the prior art may be used in recognition methods, does not do herein in detail
It introduces.Preferably, goal object is face, therefore, to better illustrate the invention, embodiment below
In illustrated by taking face as an example.
Step S120 loads correspondence respectively in response to the operation of the three-dimensional special efficacy model of load for each target object in video
Three-dimensional special efficacy model, establish and preserve the correspondence of each target object and each three-dimensional special efficacy model.
When user is intended for the load three-dimensional special efficacy model of the face in video, can be operated accordingly, for example, triggering
The control of the three-dimensional special efficacy model of load provided in interface.Because in the present embodiment, in video comprising there are two or two with
On face can be followed successively by each three-dimensional special efficacy model of face load when user selects the three-dimensional special efficacy model of load.For example,
Include three faces in video：Face 1, face 2 and face 3 first choose face 1, so in the three-dimensional special efficacy model of load
Three-dimensional special efficacy model 1 is selected afterwards, then three-dimensional special efficacy model 1 will be loaded on face 1；Then face 2 is chosen, selects three
Special efficacy model 2 is tieed up, then three-dimensional special efficacy model 2 will be loaded on face 2；Face 3 is being chosen, three-dimensional special efficacy model is selected
3, then three-dimensional special efficacy model 3 will be loaded on face 3.For another example, user is by the way of dragging, by three-dimensional special efficacy model
1 choose after drag on face 1, three-dimensional special efficacy model 1 will be loaded on face 1；Three-dimensional special efficacy model 2 is chosen into rear dragging
It moves on face 2, three-dimensional special efficacy model 2 will be loaded on face 2；Face 3 is dragged to after three-dimensional special efficacy model 3 is chosen
On, three-dimensional special efficacy model 3 will be loaded on face 3.In this way, the correspondence of each face and three-dimensional special efficacy model has been built
It stands, i.e. 1 corresponding three-dimensional special efficacy model 1 of face, 2 corresponding three-dimensional special efficacy model 2 of face, 3 corresponding three-dimensional special efficacy model 3 of face, protects
Deposit the correspondence of each face and each three-dimensional special efficacy model.
Step S130, when detecting target object generation action variation, according to correspondence, driving and target object pair
The three-dimensional special efficacy model answered carries out corresponding action variation.
In the present embodiment, to be accomplished that the corresponding three-dimensional special efficacy model of each face driving carries out action variation, once
Detect that face changes, it is determined that corresponding action variation occurs for the corresponding three-dimensional special efficacy model of face, for example, in people
The three-dimensional special efficacy model of load deer head on the face, when the mouth of face opens, the mouth of driving deer head opens, when the eyes of face are closed
When, determine that the eyes of deer head are closed.
On the basis of previous example, when the action for detecting that face 1 is opened one's mouth, face 2 is laughed dynamic
Make, the action that face 3 is closed one's eyes, then according to correspondence, the action for driving three-dimensional special efficacy model 1 to open one's mouth, driving
The action that three-dimensional special efficacy model 2 is laughed, the action for driving three-dimensional special efficacy model 3 to close one's eyes.And then realize different people
The respective three-dimensional special efficacy model of face control.
In the present embodiment, the mode of detection face facial muscle may be used in detection face generation action variation, then
The action of the facial muscle of face is applied on the bone of corresponding three-dimensional special efficacy model, three-dimensional special efficacy model is driven to realize
It is acted accordingly.
As it can be seen that through this embodiment, after the three-dimensional special efficacy model of each target object load in being embodied as video, each mesh
Mark object can also respectively drive corresponding three-dimensional special efficacy model and carry out action variation, and then realize each target object in video
Interaction is converted into the interactive effect of model, meets the higher and higher video process demand of user, increases the entertaining of video processing
Property, enhance the usage experience of user.
In one embodiment of the invention, the corresponding pass of each target object in step S120 and each three-dimensional special efficacy model
System includes：Each corresponding fisrt feature information of target object and the corresponding second feature of each three-dimensional special efficacy model
One-to-one relationship between information.
In practical applications, the video that video collector acquires in real time can be handled, when for each one in video
After the three-dimensional special efficacy model of face load, it is possible that the case where one of face is removed except video collector camera lens, this is just
Can cause the removal camera lens face load three-dimensional special efficacy model become in camera lens there are still face three-dimensional special efficacy mould
There is the case where three-dimensional special efficacy model is acted according to other human face actions in type, when the removal camera lens face again
It is secondary when appearing in camera lens, former corresponding three-dimensional special efficacy model may would not be corresponding again, i.e., the face can not drive this again
Three-dimensional special efficacy model, this different face for deviating from the present invention drive the original intention of different three-dimensional special efficacy models.
In order to ensure the one-to-one relationship of three-dimensional special efficacy model and face so that face appears in mirror again after removing camera lens
When head, which still can accordingly be acted according to the face, in the present embodiment, established and protected
Deposit be the corresponding fisrt feature information of each face and the corresponding second feature information of each three-dimensional special efficacy model it
Between one-to-one relationship.I.e. here correspondence is the correspondence of characteristic information, can be each key point letter in face
Breath, and each key point information of corresponding three-dimensional special efficacy model, for example, fisrt feature information is the canthus, nose, the corners of the mouth of face
Etc. key points characteristic information；Then second feature information is also the spy of the key points such as canthus, nose, the corners of the mouth of three-dimensional special efficacy model
Reference ceases.In this way, in video, after face 1 removes camera lens because in the characteristic information and correspondence of face 2 with three-dimensional
1 corresponding characteristic information of special efficacy model is not consistent, then can not drive three-dimensional special efficacy model 1, when again face 1 appears in camera lens
When, face 1 and the correspondence of three-dimensional feature model 1 still exist, then can be according to the action drives three-dimensional special efficacy model 1 of face 1.
Further, method shown in FIG. 1 further comprises：When meeting the first preset condition, re-establishes and preserve
Between each corresponding fisrt feature information of target object and the corresponding second feature information of each three-dimensional special efficacy model
One-to-one relationship.
In the present embodiment, being exchanged with each other for the three-dimensional special efficacy model of each face in video may be implemented.Here meet
First preset condition, can be detect that face carries out preset action (as mutually get rid of head), and/or, the exchange control provided
It is triggered, and/or, preset voice is detected by speech recognition, etc..It realizes the exchange of three-dimensional special efficacy model, also just anticipates
Taste, and the human face action of three-dimensional special efficacy model foundation is driven also to be exchanged, so, in order to realize pair of basis newly after exchange
It should be related to the driving for carrying out three-dimensional special efficacy model, be to need to re-establish and preserve each face to correspond to respectively in the present embodiment
Fisrt feature information and the corresponding second feature information of each three-dimensional special efficacy model between one-to-one relationship.
For example, establishing and the correspondence preserved is：The second of the 1 corresponding three-dimensional special efficacy model 1 of fisrt feature of face 1 is special
3 corresponding three-dimensional of fisrt feature of the second feature 2 ', face 3 of levying the 2 corresponding three-dimensional special efficacy model 2 of fisrt feature of 1 ', face 2 is special
Imitate the second feature 3 ' of model 3.When meeting the first preset condition, correspondence is re-established, then correspondence becomes：Face
The second feature 2 ' of 11 corresponding three-dimensional special efficacy model 2 of fisrt feature, 2 corresponding three-dimensional special efficacy model 3 of the fisrt feature of face 2
The second feature 1 ' of second feature 3 ', 3 corresponding three-dimensional special efficacy model 1 of the fisrt feature of face 3.
Further, in step S130 when detecting target object generation action variation, according to correspondence,
The corresponding action of the corresponding three-dimensional special efficacy model progress of driving and the target object, which changes, includes：
When detecting target object generation action variation, according to the correspondence re-established and after preserving, driving with
The corresponding three-dimensional special efficacy model of target object carries out corresponding action variation.
On the basis of above-mentioned example, moved accordingly according to the new corresponding three-dimensional special efficacy model of correspondence driving
Work changes, and is：It is carried out acting variation accordingly according to the action drives three-dimensional special efficacy model 2 of face 1, according to the action of face 2
Driving three-dimensional special efficacy model 3 carries out acting variation accordingly, is carried out accordingly according to the action drives three-dimensional special efficacy model 1 of face 3
Action variation.
In one embodiment of the invention, method shown in FIG. 1 further comprises：When meeting the second preset condition,
Three-dimensional special efficacy model is replaced for the respective objects object in video.
In the present embodiment, realization is to replace the three-dimensional special efficacy model loaded.Here the second preset condition of satisfaction
Can be detect that face carries out preset action, and/or, the replacement control provided is triggered, and/or, pass through speech recognition
Detect the default voice for replacing three-dimensional special efficacy model, etc..After replacing three-dimensional special efficacy model, driven according to human face action to realize
Three-dimensional special efficacy model after dynamic replacement, it is also necessary to the corresponding pass of each three-dimensional special efficacy model after establishing and preserve each face and replacing
System.
Specifically, the above-mentioned three-dimensional special efficacy model of respective objects object replacement in video includes：Before replacement
The type of three-dimensional special efficacy model determines the type of the three-dimensional special efficacy model after replacing, three-dimensional is randomly selected from determining type
Special efficacy model, or three-dimensional special efficacy model is selected from determining type according to the second preset condition；And/or directly according to
Two preset conditions determine the three-dimensional special efficacy model after replacing.
In the present embodiment, it can be selected according to the type of the three-dimensional special efficacy model loaded, after type determines,
It can be randomly choosed, alternatively, user specifies a three-dimensional special efficacy model to replace from determining type.For example, more
Three-dimensional special efficacy model before changing is deer head, it is determined that the type of three-dimensional special efficacy model is animal head threedimensional model, then from determination
Animal head threedimensional model in randomly select a head of the horse, alternatively, to user show animal head 3 d model library, so as to
Family therefrom select one as replace after three-dimensional special efficacy model.
In the present embodiment, the three-dimensional special efficacy model after replacement can also be user directly from three-dimensional special efficacy model library into
Row selection is specified.
It should be noted that when occurring that two or more faces in video, can be replaced respectively, more
Mode when above-mentioned load three-dimensional special efficacy model may be used in the mode changed.It is of course also possible to be only one of those or it is several
A face is replaced, under the special scenes, it is desirable that the face needed replacing carries out corresponding deliberate action, for example, face 1
Three-dimensional special efficacy model is needed replacing, then the action that face 1 is shaken the head is face 1 after detecting that face 1 carries out the action
Three-dimensional special efficacy model is replaced, then face 2 need not be replaced just without the preset action.
In one embodiment of the invention, three-dimensional special efficacy model shown in FIG. 1 is that three-dimensional sprouts face special efficacy model；Then that is walked
It is that each target object loads corresponding three-dimensional special efficacy model and includes respectively in video in rapid S120：Face special efficacy model is sprouted with three-dimensional
Replace corresponding target object.
Here it is to cover face that three-dimensional, which sprouts face special efficacy model, so when being loaded, sprouts face special efficacy with three-dimensional
Model replaces corresponding face, to realize that three-dimensional sprouts the load of face special efficacy model.
Further, method shown in FIG. 1 further comprises：Corresponding instruction image is generated according to each target object；It will
Each instruction image is added to the designated position of corresponding video image.
In the present embodiment, because after three-dimensional is sprouted the load of face special efficacy model, face is completely covered, when face is into action
When making, although can according to the action drives of face, three-dimensional special efficacy model is acted accordingly accordingly, the use of viewing
Family can not direct feel to the three-dimensional special efficacy model be to be acted according to the action of face.So in the present embodiment, when
When three-dimensional sprouts face special efficacy model and blocks face completely, corresponding instruction image, finger here are generated according to each face in video
Include face in diagram picture, indicates that the human face action in image is synchronous with human face action in video；Then by the instruction image
It is added to corresponding position, for example, the beside of corresponding three-dimensional special efficacy model.In this way, be the image of face in instruction image,
After facial image acts, it indicates that the face in image also has action, and three-dimensional special efficacy model can also carry out accordingly
Action, in this way, even if three-dimensional special efficacy model can be shown if sheltering from the action of face face in indicating image, so as to
Family, which can intuitively experience the three-dimensional special efficacy model, to be acted according to the action of face, and the use of user is further enhanced
Experience.
In one example, include that the face 1 in left side and corresponding three-dimensional sprout face special efficacy model 1, right side in video
Face 2 and corresponding three-dimensional sprout face special efficacy model 2.Instruction image 1 is generated according to face 1, instruction image is generated according to face 2
2, it will indicate that the instruction addition of image 2 in the three-dimensional upper left corner for sprouting face special efficacy model 1, is sprouted face special efficacy mould by the addition of image 1 in three-dimensional
The upper right corner of type 3.
Fig. 2 shows the structural schematic diagrams of video process apparatus according to an embodiment of the invention.As shown in Fig. 2, should
Video process apparatus 200 includes：
Acquiring unit 210 is suitable for obtaining the video for including two or more target objects of video collector acquisition.
In the present embodiment, after the video for getting video collector acquisition, include in video two or two are identified
A above target object.Recongnition of objects method in the prior art may be used in recognition methods, does not do herein in detail
It introduces.Preferably, goal object is face, therefore, to better illustrate the invention, embodiment below
In illustrated by taking face as an example.
Correspondence relationship establishing unit 220 is adapted for loading the operation of three-dimensional special efficacy model, is each target pair in video
As loading corresponding three-dimensional special efficacy model respectively, the correspondence of each target object and each three-dimensional special efficacy model is established and preserved.
When user is intended for the load three-dimensional special efficacy model of the face in video, can be operated accordingly, for example, triggering
The control of the three-dimensional special efficacy model of load provided in interface.Because in the present embodiment, in video comprising there are two or two with
On face can be followed successively by each three-dimensional special efficacy model of face load when user selects the three-dimensional special efficacy model of load.For example,
Include three faces in video：Face 1, face 2 and face 3 first choose face 1, so in the three-dimensional special efficacy model of load
Three-dimensional special efficacy model 1 is selected afterwards, then three-dimensional special efficacy model 1 will be loaded on face 1；Then face 2 is chosen, selects three
Special efficacy model 2 is tieed up, then three-dimensional special efficacy model 2 will be loaded on face 2；Face 3 is being chosen, three-dimensional special efficacy model is selected
3, then three-dimensional special efficacy model 3 will be loaded on face 3.For another example, user is by the way of dragging, by three-dimensional special efficacy model
1 choose after drag on face 1, three-dimensional special efficacy model 1 will be loaded on face 1；Three-dimensional special efficacy model 2 is chosen into rear dragging
It moves on face 2, three-dimensional special efficacy model 2 will be loaded on face 2；Face 3 is dragged to after three-dimensional special efficacy model 3 is chosen
On, three-dimensional special efficacy model 3 will be loaded on face 3.In this way, the correspondence of each face and three-dimensional special efficacy model has been built
It stands, i.e. 1 corresponding three-dimensional special efficacy model 1 of face, 2 corresponding three-dimensional special efficacy model 2 of face, 3 corresponding three-dimensional special efficacy model 3 of face, protects
Deposit the correspondence of each face and each three-dimensional special efficacy model.
Driving unit 230, suitable for when detecting target object generation action variation, according to correspondence, driving and mesh
It marks the corresponding three-dimensional special efficacy model of object and carries out corresponding action variation.
In the present embodiment, to be accomplished that the corresponding three-dimensional special efficacy model of each face driving carries out action variation, once
Detect that face changes, it is determined that corresponding action variation occurs for the corresponding three-dimensional special efficacy model of face, for example, in people
The three-dimensional special efficacy model of load deer head on the face, when the mouth of face opens, the mouth of driving deer head opens, when the eyes of face are closed
When, determine that the eyes of deer head are closed.
On the basis of previous example, when the action for detecting that face 1 is opened one's mouth, face 2 is laughed dynamic
Make, the action that face 3 is closed one's eyes, then according to correspondence, the action for driving three-dimensional special efficacy model 1 to open one's mouth, driving
The action that three-dimensional special efficacy model 2 is laughed, the action for driving three-dimensional special efficacy model 3 to close one's eyes.And then realize different people
The respective three-dimensional special efficacy model of face control.
In the present embodiment, the mode of detection face facial muscle may be used in detection face generation action variation, then
The action of the facial muscle of face is applied on the bone of corresponding three-dimensional special efficacy model, three-dimensional special efficacy model is driven to realize
It is acted accordingly.
As it can be seen that through this embodiment, after the three-dimensional special efficacy model of each target object load in being embodied as video, each mesh
Mark object can also respectively drive corresponding three-dimensional special efficacy model and carry out action variation, and then realize each target object in video
Interaction is converted into the interactive effect of model, meets the higher and higher video process demand of user, increases the entertaining of video processing
Property, enhance the usage experience of user.
In one embodiment of the invention, correspondence relationship establishing unit 220 are adapted to set up and preserve each target object point
One-to-one correspondence between not corresponding fisrt feature information and the corresponding second feature information of each three-dimensional special efficacy model closes
System.
In practical applications, the video that video collector acquires in real time can be handled, when for each one in video
After the three-dimensional special efficacy model of face load, it is possible that the case where one of face is removed except video collector camera lens, this is just
Can cause the removal camera lens face load three-dimensional special efficacy model become in camera lens there are still face three-dimensional special efficacy mould
There is the case where three-dimensional special efficacy model is acted according to other human face actions in type, when the removal camera lens face again
It is secondary when appearing in camera lens, former corresponding three-dimensional special efficacy model may would not be corresponding again, i.e., the face can not drive this again
Three-dimensional special efficacy model, this different face for deviating from the present invention drive the original intention of different three-dimensional special efficacy models.
In order to ensure the one-to-one relationship of three-dimensional special efficacy model and face so that face appears in mirror again after removing camera lens
When head, which still can accordingly be acted according to the face, in the present embodiment, established and protected
Deposit be the corresponding fisrt feature information of each face and the corresponding second feature information of each three-dimensional special efficacy model it
Between one-to-one relationship.I.e. here correspondence is the correspondence of characteristic information, can be each key point letter in face
Breath, and each key point information of corresponding three-dimensional special efficacy model, for example, fisrt feature information is the canthus, nose, the corners of the mouth of face
Etc. key points characteristic information；Then second feature information is also the spy of the key points such as canthus, nose, the corners of the mouth of three-dimensional special efficacy model
Reference ceases.In this way, in video, after face 1 removes camera lens because in the characteristic information and correspondence of face 2 with three-dimensional
1 corresponding characteristic information of special efficacy model is not consistent, then can not drive three-dimensional special efficacy model 1, when again face 1 appears in camera lens
When, face 1 and the correspondence of three-dimensional feature model 1 still exist, then can be according to the action drives three-dimensional special efficacy model 1 of face 1.
Further, correspondence relationship establishing unit 220 are suitable for when meeting the first preset condition, re-establish and preserve
Between each corresponding fisrt feature information of target object and the corresponding second feature information of each three-dimensional special efficacy model
One-to-one relationship.
In the present embodiment, being exchanged with each other for the three-dimensional special efficacy model of each face in video may be implemented.Here meet
First preset condition, can be detect that face carries out preset action (as mutually get rid of head), and/or, the exchange control provided
It is triggered, and/or, preset voice is detected by speech recognition, etc..It realizes the exchange of three-dimensional special efficacy model, also just anticipates
Taste, and the human face action of three-dimensional special efficacy model foundation is driven also to be exchanged, so, in order to realize pair of basis newly after exchange
It should be related to the driving for carrying out three-dimensional special efficacy model, be to need to re-establish and preserve each face to correspond to respectively in the present embodiment
Fisrt feature information and the corresponding second feature information of each three-dimensional special efficacy model between one-to-one relationship.
For example, establishing and the correspondence preserved is：The second of the 1 corresponding three-dimensional special efficacy model 1 of fisrt feature of face 1 is special
3 corresponding three-dimensional of fisrt feature of the second feature 2 ', face 3 of levying the 2 corresponding three-dimensional special efficacy model 2 of fisrt feature of 1 ', face 2 is special
Imitate the second feature 3 ' of model 3.When meeting the first preset condition, correspondence is re-established, then correspondence becomes：Face
The second feature 2 ' of 11 corresponding three-dimensional special efficacy model 2 of fisrt feature, 2 corresponding three-dimensional special efficacy model 3 of the fisrt feature of face 2
The second feature 1 ' of second feature 3 ', 3 corresponding three-dimensional special efficacy model 1 of the fisrt feature of face 3.
Further, driving unit 230 is suitable for, when detecting target object generation action variation, according to re-establishing
And the correspondence after preserving, the corresponding action variation of the corresponding three-dimensional special efficacy model progress of driving and target object.
On the basis of above-mentioned example, moved accordingly according to the new corresponding three-dimensional special efficacy model of correspondence driving
Work changes, and is：It is carried out acting variation accordingly according to the action drives three-dimensional special efficacy model 2 of face 1, according to the action of face 2
Driving three-dimensional special efficacy model 3 carries out acting variation accordingly, is carried out accordingly according to the action drives three-dimensional special efficacy model 1 of face 3
Action variation.
In one embodiment of the invention, device shown in Fig. 2 further comprises：
Unit is replaced, is suitable for when meeting the second preset condition, is that the respective objects object in video replaces three-dimensional special efficacy
Model.
In the present embodiment, realization is to replace the three-dimensional special efficacy model loaded.Here the second preset condition of satisfaction
Can be detect that face carries out preset action, and/or, the replacement control provided is triggered, and/or, pass through speech recognition
Detect the default voice for replacing three-dimensional special efficacy model, etc..After replacing three-dimensional special efficacy model, driven according to human face action to realize
Three-dimensional special efficacy model after dynamic replacement, it is also necessary to the corresponding pass of each three-dimensional special efficacy model after establishing and preserve each face and replacing
System.
Specifically, above-mentioned replacement unit is suitable for the type according to the three-dimensional special efficacy model before replacement, determines after replacing
The type of three-dimensional special efficacy model, randomly selects three-dimensional special efficacy model from determining type, or according to the second preset condition from
Three-dimensional special efficacy model is selected in determining type；And/or the three-dimensional special efficacy mould after replacing directly is determined according to the second preset condition
Type.
In the present embodiment, it can be selected according to the type of the three-dimensional special efficacy model loaded, after type determines,
It can be randomly choosed, alternatively, user specifies a three-dimensional special efficacy model to replace from determining type.For example, more
Three-dimensional special efficacy model before changing is deer head, it is determined that the type of three-dimensional special efficacy model is animal head threedimensional model, then from determination
Animal head threedimensional model in randomly select a head of the horse, alternatively, to user show animal head 3 d model library, so as to
Family therefrom select one as replace after three-dimensional special efficacy model.
In the present embodiment, the three-dimensional special efficacy model after replacement can also be user directly from three-dimensional special efficacy model library into
Row selection is specified.
It should be noted that when occurring that two or more faces in video, can be replaced respectively, more
Mode when above-mentioned load three-dimensional special efficacy model may be used in the mode changed.It is of course also possible to be only one of those or it is several
A face is replaced, under the special scenes, it is desirable that the face needed replacing carries out corresponding deliberate action, for example, face 1
Three-dimensional special efficacy model is needed replacing, then the action that face 1 is shaken the head is face 1 after detecting that face 1 carries out the action
Three-dimensional special efficacy model is replaced, then face 2 need not be replaced just without the preset action.
In one embodiment of the invention, above-mentioned three-dimensional special efficacy model is that three-dimensional sprouts face special efficacy model.
Correspondence relationship establishing unit 220 replaces corresponding target object suitable for sprouting face special efficacy model with three-dimensional.
Here it is to cover face that three-dimensional, which sprouts face special efficacy model, so when being loaded, sprouts face special efficacy mould with three-dimensional
Type replaces corresponding face, to realize that three-dimensional sprouts the load of face special efficacy model.
Further, device shown in Fig. 2 further comprises：
Indicating unit is suitable for generating corresponding instruction image according to each target object；Each instruction image is added to correspondence
Video image designated position.
In the present embodiment, because after three-dimensional is sprouted the load of face special efficacy model, face is completely covered, when face is into action
When making, although can according to the action drives of face, three-dimensional special efficacy model is acted accordingly accordingly, the use of viewing
Family can not direct feel to the three-dimensional special efficacy model be to be acted according to the action of face.So in the present embodiment, when
When three-dimensional sprouts face special efficacy model and blocks face completely, corresponding instruction image, finger here are generated according to each face in video
Include face in diagram picture, indicates that the human face action in image is synchronous with human face action in video；Then by the instruction image
It is added to corresponding position, for example, the beside of corresponding three-dimensional special efficacy model.In this way, be the image of face in instruction image,
After facial image acts, it indicates that the face in image also has action, and three-dimensional special efficacy model can also carry out accordingly
Action, in this way, even if three-dimensional special efficacy model can be shown if sheltering from the action of face face in indicating image, so as to
Family, which can intuitively experience the three-dimensional special efficacy model, to be acted according to the action of face, and the use of user is further enhanced
Experience.
In one example, include that the face 1 in left side and corresponding three-dimensional sprout face special efficacy model 1, right side in video
Face 2 and corresponding three-dimensional sprout face special efficacy model 2.Instruction image 1 is generated according to face 1, instruction image is generated according to face 2
2, it will indicate that the instruction addition of image 2 in the three-dimensional upper left corner for sprouting face special efficacy model 1, is sprouted face special efficacy mould by the addition of image 1 in three-dimensional
The upper right corner of type 3.
The present invention also provides a kind of electronic equipment, wherein the electronic equipment includes：
Processor；And it is arranged to the memory of storage computer executable instructions, executable instruction is when executed
Processor is set to execute the method for processing video frequency according to figure 1 and its each embodiment.
Fig. 3 shows the structural schematic diagram of electronic equipment according to an embodiment of the invention.As shown in figure 3, the electronics
Equipment 300 includes：
Processor 310；And it is arranged to the memory 320 of storage computer executable instructions (program code), it is depositing
In reservoir 320, there are the memory space 330 of storage program code, the program code for executing steps of a method in accordance with the invention
330 are stored in memory space 330, and it is according to figure 1 and its each which when executed execute processor 310
Method for processing video frequency in embodiment.
Fig. 4 shows the structural schematic diagram of computer readable storage medium according to an embodiment of the invention.Such as Fig. 4 institutes
Show, the computer readable storage medium 400, stores one or more programs (program code) 410, one or more program (journeys
Sequence code) 410 when being executed by a processor, for executing steps of a method in accordance with the invention, i.e., shown in FIG. 1 and its each reality
Apply the method for processing video frequency in example.
It should be noted that each embodiment of electronic equipment shown in Fig. 3 and computer readable storage medium shown in Fig. 4
It is corresponding identical as each embodiment of method shown in FIG. 1, it has been described in detail above, details are not described herein.
Using face as target object, the present invention will be described for the various embodiments described above, it should be noted that face
It is a preferred example as target object, in the present invention, target object should not limit as face, can also be according to need
The other elements being limited in video are sought, for example, tree, animal etc., therefore, in the present invention, target object is not do specific limit
Fixed.
In conclusion according to the technique and scheme of the present invention, obtain video collector acquisition includes two or more
The video of target object；In response to the operation of the three-dimensional special efficacy model of load, loaded respectively for each target object in video corresponding
The correspondence of each target object and each three-dimensional special efficacy model is established and preserved to three-dimensional special efficacy model；When detecting target object
When generation action variation, according to correspondence, the corresponding action change of the corresponding three-dimensional special efficacy model progress of driving and target object
Change.By the technical program, after the three-dimensional special efficacy model of each target object load in being embodied as video, each target object is also
Corresponding three-dimensional special efficacy model can be respectively driven and carry out action variation, meet the higher and higher video process demand of user, increase
The interest for adding video to handle, enhances the usage experience of user.
It should be noted that：
Algorithm and display be not inherently related to any certain computer, virtual bench or miscellaneous equipment provided herein.
Various fexible units can also be used together with teaching based on this.As described above, it constructs required by this kind of device
Structure be obvious.In addition, the present invention is not also directed to any certain programmed language.It should be understood that can utilize various
Programming language realizes the content of invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention
Example can be put into practice without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of each inventive aspect,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention：It is i.e. required to protect
Shield the present invention claims the more features of feature than being expressly recited in each claim.More precisely, as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific implementation mode are expressly incorporated in the specific implementation mode, wherein each claim itself
All as a separate embodiment of the present invention.
Those skilled in the art, which are appreciated that, to carry out adaptively the module in the equipment in embodiment
Change and they are arranged in the one or more equipment different from the embodiment.It can be the module or list in embodiment
Member or component be combined into a module or unit or component, and can be divided into addition multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it may be used any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so to appoint
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification (including adjoint power
Profit requires, abstract and attached drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generation
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments means in of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
One of meaning mode can use in any combination.
The all parts embodiment of the present invention can be with hardware realization, or to run on one or more processors
Software module realize, or realized with combination thereof.It will be understood by those of skill in the art that can use in practice
Microprocessor or digital signal processor (DSP) realize video process apparatus according to the ... of the embodiment of the present invention, electronic equipment
With some or all functions of some or all components in computer readable storage medium.The present invention is also implemented as
For executing method as described herein some or all equipment or program of device (for example, computer program and
Computer program product).It is such to realize that the program of the present invention may be stored on the computer-readable medium, or can have
The form of one or more signal.Such signal can be downloaded from internet website and be obtained, or on carrier signal
It provides, or provides in any other forms.
For example, Fig. 3 shows the structural schematic diagram of electronic equipment according to an embodiment of the invention.The electronic equipment
300 conventionally comprise processor 310 and are arranged to the memory 320 of storage computer executable instructions (program code).It deposits
Reservoir 320 can be such as flash memory, EEPROM (electrically erasable programmable read-only memory), EPROM, hard disk or ROM etc
Electronic memory.Memory 320 has storage for executing any method and step in shown in FIG. 1 and each embodiment
The memory space 330 of program code 340.For example, the memory space 330 for program code may include being respectively used to realization
Each program code 340 of various steps in the method in face.These program codes can be from one or more computer journey
It reads or is written in sequence product in this one or more computer program product.These computer program products include all
Such as hard disk, the program code carrier of compact-disc (CD), storage card or floppy disk etc.Such computer program product is usually
Such as the computer readable storage medium 400 described in Fig. 4.The computer readable storage medium 400 can have the electronics with Fig. 3
Memory paragraph, the memory space etc. of 320 similar arrangement of memory in equipment.Program code can be pressed for example in a suitable form
Contracting.In general, storage unit is stored with the program code 410 for executing steps of a method in accordance with the invention, you can with by such as
The program code that 310 etc processor is read causes the electronic equipment to be held when these program codes are run by electronic equipment
Each step in row method described above.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference mark between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be by the same hardware branch
To embody.The use of word first, second, and third does not indicate that any sequence.These words can be explained and be run after fame
Claim.
The invention discloses A1, a kind of method for processing video frequency, wherein this method includes：
Obtain the video for including two or more target objects of video collector acquisition；
In response to the operation of the three-dimensional special efficacy model of load, corresponding three-dimensional is loaded respectively for each target object in the video
The correspondence of each target object and each three-dimensional special efficacy model is established and preserved to special efficacy model；
When detecting the target object generation action variation, according to the correspondence, driving and the target pair
As the corresponding three-dimensional special efficacy model carries out corresponding action variation.
A2, the method as described in A1, wherein the correspondence of each target object and each three-dimensional special efficacy model includes：
Each corresponding fisrt feature information of target object and the corresponding second feature of each three-dimensional special efficacy model
One-to-one relationship between information.
A3, the method as described in A2, wherein this method further comprises：
When meeting the first preset condition, the corresponding fisrt feature information of each target object is re-established and preserves,
And one-to-one relationship between the corresponding second feature information of each three-dimensional special efficacy model.
A4, the method as described in A1, wherein this method further comprises：
It is that the respective objects object in the video replaces three-dimensional special efficacy model when meeting the second preset condition.
A5, the method as described in A4, wherein the respective objects object in the video replaces three-dimensional special efficacy model
Including：
According to the type of the three-dimensional special efficacy model before replacement, the type of the three-dimensional special efficacy model after replacing is determined, from determination
Type in randomly select three-dimensional special efficacy model, or three-dimensional spy is selected from determining type according to second preset condition
Imitate model；
And/or
The three-dimensional special efficacy model after replacing directly is determined according to second preset condition.
A6, the method as described in A1, wherein the three-dimensional special efficacy model is that three-dimensional sprouts face special efficacy model；Described is described
Each target object loads corresponding three-dimensional special efficacy model and includes respectively in video：
Face special efficacy model, which is sprouted, with the three-dimensional replaces corresponding target object.
A7, the method as described in A6, wherein this method further comprises：
Corresponding instruction image is generated according to each target object；
Each instruction image is added to the designated position of the corresponding video image.
A8, the method as described in any one of A1-A7, wherein the target object is face.
The invention also discloses B9, a kind of video process apparatus, wherein the device includes：
Acquiring unit is suitable for obtaining the video for including two or more target objects of video collector acquisition；
Correspondence relationship establishing unit is adapted for loading the operation of three-dimensional special efficacy model, is each target in the video
Object loads corresponding three-dimensional special efficacy model respectively, establishes and preserve the corresponding pass of each target object and each three-dimensional special efficacy model
System；
Driving unit, suitable for when detecting the target object generation action variation, according to the correspondence, driving
The corresponding action variation of corresponding with the target object three-dimensional special efficacy model progresss.
B10, the device as described in B9, wherein the correspondence relationship establishing unit is adapted to set up and preserves each target object
One-to-one correspondence between corresponding fisrt feature information and the corresponding second feature information of each three-dimensional special efficacy model
Relationship.
B11, the device as described in B10, wherein
The correspondence relationship establishing unit is suitable for when meeting the first preset condition, re-establishes and preserve each target pair
As being corresponded between corresponding fisrt feature information and the corresponding second feature information of each three-dimensional special efficacy model
Relationship.
B12, the device as described in B9, wherein the device further comprises：
Unit is replaced, is suitable for when meeting the second preset condition, is that the respective objects object in the video replaces three-dimensional
Special efficacy model.
B13, the device as described in B12, wherein the replacement unit is suitable for according to the three-dimensional special efficacy model before replacement
Type determines the type of the three-dimensional special efficacy model after replacing, three-dimensional special efficacy model, Huo Zhegen is randomly selected from determining type
Three-dimensional special efficacy model is selected from determining type according to second preset condition；And/or directly according to the described second default item
Part determines the three-dimensional special efficacy model after replacing.
B14, the device as described in B9, wherein the three-dimensional special efficacy model is that three-dimensional sprouts face special efficacy model；
The correspondence relationship establishing unit replaces corresponding target object suitable for sprouting face special efficacy model with the three-dimensional.
B15, the device as described in B14, wherein the device further comprises：
Indicating unit is suitable for generating corresponding instruction image according to each target object；Each instruction image is added to correspondence
The video image designated position.
B16, the device as described in any one of B9-B15, wherein the target object is face.
The invention also discloses C17, a kind of electronic equipment, wherein the electronic equipment includes：
Processor；And
It is arranged to the memory of storage computer executable instructions, the executable instruction makes the place when executed
Manage method of the device execution according to any one of A1~A8.
The invention also discloses D18, a kind of computer readable storage mediums, wherein the computer readable storage medium
The one or more programs of storage, one or more of programs when being executed by a processor, are realized described in any one of A1~A8
Method.
Claims (10)
1. a kind of method for processing video frequency, wherein this method includes：
Obtain the video for including two or more target objects of video collector acquisition；
In response to the operation of the three-dimensional special efficacy model of load, corresponding three-dimensional special efficacy is loaded respectively for each target object in the video
The correspondence of each target object and each three-dimensional special efficacy model is established and preserved to model；
When detecting the target object generation action variation, according to the correspondence, driving and the target object pair
The three-dimensional special efficacy model answered carries out corresponding action variation.
2. the method for claim 1, wherein correspondence packet of each target object and each three-dimensional special efficacy model
It includes：
Each corresponding fisrt feature information of target object and the corresponding second feature information of each three-dimensional special efficacy model
Between one-to-one relationship.
3. method as claimed in claim 2, wherein this method further comprises：
When meeting the first preset condition, the corresponding fisrt feature information of each target object is re-established and preserves, and
One-to-one relationship between the corresponding second feature information of each three-dimensional special efficacy model.
4. the method for claim 1, wherein this method further comprises：
It is that the respective objects object in the video replaces three-dimensional special efficacy model when meeting the second preset condition.
5. method as claimed in claim 4, wherein the respective objects object in the video replaces three-dimensional special efficacy mould
Type includes：
According to the type of the three-dimensional special efficacy model before replacement, the type of the three-dimensional special efficacy model after replacing is determined, from determining class
Three-dimensional special efficacy model is randomly selected in type, or selects three-dimensional special efficacy mould from determining type according to second preset condition
Type；
And/or
The three-dimensional special efficacy model after replacing directly is determined according to second preset condition.
6. the method for claim 1, wherein the three-dimensional special efficacy model is that three-dimensional sprouts face special efficacy model；It is described for institute
It states each target object in video and loads corresponding three-dimensional special efficacy model respectively and include：
Face special efficacy model, which is sprouted, with the three-dimensional replaces corresponding target object.
7. method as claimed in claim 6, wherein this method further comprises：
Corresponding instruction image is generated according to each target object；
Each instruction image is added to the designated position of the corresponding video image.
8. a kind of video process apparatus, wherein the device includes：
Acquiring unit is suitable for obtaining the video for including two or more target objects of video collector acquisition；
Correspondence relationship establishing unit is adapted for loading the operation of three-dimensional special efficacy model, is each target object in the video
Corresponding three-dimensional special efficacy model is loaded respectively, establishes and preserve the correspondence of each target object and each three-dimensional special efficacy model；
Driving unit, suitable for when detecting target object generation action variation, according to the correspondence, driving and institute
It states the corresponding three-dimensional special efficacy model of target object and carries out corresponding action variation.
9. a kind of electronic equipment, wherein the electronic equipment includes：
Processor；And
It is arranged to the memory of storage computer executable instructions, the executable instruction makes the processor when executed
Execute method according to any one of claims 1 to 7.
10. a kind of computer readable storage medium, wherein the computer-readable recording medium storage one or more program,
One or more of programs when being executed by a processor, realize method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810316980.4A CN108711192A (en) | 2018-04-10 | 2018-04-10 | A kind of method for processing video frequency and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810316980.4A CN108711192A (en) | 2018-04-10 | 2018-04-10 | A kind of method for processing video frequency and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108711192A true CN108711192A (en) | 2018-10-26 |
Family
ID=63867172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810316980.4A Pending CN108711192A (en) | 2018-04-10 | 2018-04-10 | A kind of method for processing video frequency and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108711192A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111050203A (en) * | 2019-12-06 | 2020-04-21 | 腾讯科技（深圳）有限公司 | Video processing method and device, video processing equipment and storage medium |
| CN114666622A (en) * | 2022-04-02 | 2022-06-24 | 北京字跳网络技术有限公司 | Special effect video determination method and device, electronic equipment and storage medium |
| CN115278041A (en) * | 2021-04-29 | 2022-11-01 | 北京字跳网络技术有限公司 | Image processing method, image processing device, electronic equipment and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104394313A (en) * | 2014-10-27 | 2015-03-04 | 成都理想境界科技有限公司 | Special effect video generating method and device |
| CN104780458A (en) * | 2015-04-16 | 2015-07-15 | 美国掌赢信息科技有限公司 | Method and electronic equipment for loading effects in instant video |
| CN104780339A (en) * | 2015-04-16 | 2015-07-15 | 美国掌赢信息科技有限公司 | Method and electronic equipment for loading expression effect animation in instant video |
| US20160086304A1 (en) * | 2014-09-22 | 2016-03-24 | Ming Chuan University | Method for estimating a 3d vector angle from a 2d face image, method for creating face replacement database, and method for replacing face image |
| CN107067474A (en) * | 2017-03-07 | 2017-08-18 | 深圳市吉美文化科技有限公司 | A kind of augmented reality processing method and processing device |
| CN107635104A (en) * | 2017-08-11 | 2018-01-26 | 光锐恒宇（北京）科技有限公司 | A kind of method and apparatus of special display effect in the application |
-
2018
- 2018-04-10 CN CN201810316980.4A patent/CN108711192A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160086304A1 (en) * | 2014-09-22 | 2016-03-24 | Ming Chuan University | Method for estimating a 3d vector angle from a 2d face image, method for creating face replacement database, and method for replacing face image |
| CN104394313A (en) * | 2014-10-27 | 2015-03-04 | 成都理想境界科技有限公司 | Special effect video generating method and device |
| CN104780458A (en) * | 2015-04-16 | 2015-07-15 | 美国掌赢信息科技有限公司 | Method and electronic equipment for loading effects in instant video |
| CN104780339A (en) * | 2015-04-16 | 2015-07-15 | 美国掌赢信息科技有限公司 | Method and electronic equipment for loading expression effect animation in instant video |
| CN107067474A (en) * | 2017-03-07 | 2017-08-18 | 深圳市吉美文化科技有限公司 | A kind of augmented reality processing method and processing device |
| CN107635104A (en) * | 2017-08-11 | 2018-01-26 | 光锐恒宇（北京）科技有限公司 | A kind of method and apparatus of special display effect in the application |
Non-Patent Citations (1)
| Title |
|---|
| 车丹丹: "图像\视频特效制作的若干关键技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111050203A (en) * | 2019-12-06 | 2020-04-21 | 腾讯科技（深圳）有限公司 | Video processing method and device, video processing equipment and storage medium |
| CN111050203B (en) * | 2019-12-06 | 2022-06-14 | 腾讯科技（深圳）有限公司 | Video processing method and device, video processing equipment and storage medium |
| CN115278041A (en) * | 2021-04-29 | 2022-11-01 | 北京字跳网络技术有限公司 | Image processing method, image processing device, electronic equipment and readable storage medium |
| CN115278041B (en) * | 2021-04-29 | 2024-02-27 | 北京字跳网络技术有限公司 | Image processing method, device, electronic equipment and readable storage medium |
| CN114666622A (en) * | 2022-04-02 | 2022-06-24 | 北京字跳网络技术有限公司 | Special effect video determination method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108024083A (en) | Handle method, apparatus, electronic equipment and the computer-readable recording medium of video | |
| CN109670558A (en) | It is completed using the digital picture of deep learning | |
| CN107633541A (en) | The generation method and device of a kind of image special effect | |
| CN108711192A (en) | A kind of method for processing video frequency and device | |
| CN108012559A (en) | Automatic threedimensional model generation | |
| CN108401176A (en) | A kind of method and apparatus for realizing video personage mark | |
| CN107886032A (en) | Terminal device, smart mobile phone, authentication method and system based on face recognition | |
| CN108696699A (en) | A kind of method and apparatus of video processing | |
| CN110674341B (en) | Special effect processing method and device, electronic equipment and storage medium | |
| CN109829959B (en) | Facial analysis-based expression editing method and device | |
| CN108108268A (en) | Reboot process method and apparatus are exited in a kind of video record application | |
| CN108537725A (en) | A kind of method for processing video frequency and device | |
| CN107592474A (en) | A kind of image processing method and device | |
| CN108495058A (en) | Image processing method, device and computer readable storage medium | |
| CN108573516B (en) | It draws the generation method of this document, calculate equipment and computer storage medium | |
| US11402975B2 (en) | Apparatus and method for providing interactive content | |
| US20160121214A1 (en) | Character model animation using stored recordings of player movement interface data | |
| CN108040265A (en) | A kind of method and apparatus handled video | |
| CN108460104A (en) | A kind of method and apparatus for realizing content customization | |
| CN107633228A (en) | Video data handling procedure and device, computing device | |
| CN107730461A (en) | Image processing method, apparatus, device and medium | |
| CN106683193A (en) | Three-dimensional model design method and design device | |
| CN105975072A (en) | Method, device and system for identifying gesture movement | |
| US9480924B2 (en) | Rules based system for managing user selections in customizable objects | |
| CN108495184A (en) | A kind of method and apparatus for adding barrage for video |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181026 |
|
| RJ01 | Rejection of invention patent application after publication |