CN107492068A - Object video conversion real-time processing method, device and computing device - Google Patents
Object video conversion real-time processing method, device and computing device Download PDFInfo
- Publication number
- CN107492068A CN107492068A CN201710927355.9A CN201710927355A CN107492068A CN 107492068 A CN107492068 A CN 107492068A CN 201710927355 A CN201710927355 A CN 201710927355A CN 107492068 A CN107492068 A CN 107492068A
- Authority
- CN
- China
- Prior art keywords
- curve
- image
- processing
- coordinate system
- video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000006243 chemical reaction Methods 0.000 title claims abstract description 26
- 238000003672 processing method Methods 0.000 title claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 111
- 238000000034 method Methods 0.000 claims abstract description 66
- 230000008569 process Effects 0.000 claims description 40
- 238000004891 communication Methods 0.000 claims description 17
- 238000013507 mapping Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 10
- 230000006399 behavior Effects 0.000 claims 1
- 230000009466 transformation Effects 0.000 abstract description 38
- 230000000694 effects Effects 0.000 abstract description 26
- 239000000284 extract Substances 0.000 description 7
- 230000008859 change Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000012937 correction Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000026676 system process Effects 0.000 description 3
- 241000406668 Loxodonta cyclotis Species 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000009415 formwork Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/2628—Alteration of picture size, shape, position or orientation, e.g. zooming, rotation, rolling, perspective, translation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of object video conversion real-time processing method and device, method to include：The current frame image for including source object is obtained from video；Obtain the target image for including destination object；The first key message of source object is extracted from current frame image, the second key message of destination object is extracted from target image；Coordinate system is established, is fitted the crucial curve for handling the crucial curve and destination object that obtain source object in a coordinate system respectively according to the first key message and the second key message；According to the crucial curve of the crucial curve and destination object of source object, amplitude adjustment curve is calculated；Curve is adjusted according to amplitude to be adjusted current frame image, obtains the image after present frame processing；Image after present frame is handled covers the video data after former current frame image is handled；Video data after display processing, the image after present frame processing after conversion is more naturally, object transformation treatment effect is more fine, and video display effect is more preferably.
Description
Technical field
The present invention relates to image processing field, and in particular to a kind of object video conversion real-time processing method, device, calculating
Equipment and computer-readable storage medium.
Background technology
With the development of science and technology, the technology of image capture device also increasingly improves.Regarded using what image capture device was recorded
Frequency also becomes apparent from, resolution ratio, display effect also greatly improve.But the video of existing recording is only dull recorded material sheet
Body, the increasing individual requirement that user proposes can not be met.Prior art can be manual by user after recorded video
It is further again to video to be handled, to meet the individual requirement of user.But so processing needs user to have higher figure
As treatment technology, and the cost user more time is needed in processing, handle cumbersome, technical sophistication.
Therefore, it is necessary to which a kind of object video converts real-time processing method, to meet the individual requirement of user in real time.
The content of the invention
In view of the above problems, it is proposed that the present invention so as to provide one kind overcome above mentioned problem or at least in part solve on
State object video conversion real-time processing method, device, computing device and the computer-readable storage medium of problem.
According to an aspect of the invention, there is provided a kind of object video conversion real-time processing method, it includes：
Real-time image acquisition collecting device is captured and/or the video recorded in include source object current frame image；
Or the current frame image that source object is included in currently played video is obtained in real time；
Obtain the target image for including destination object；
The first key message of source object is extracted from current frame image, and target pair is extracted from target image
The second key message of elephant；
Coordinate system is established, is fitted handles in a coordinate system respectively according to the first key message and the second key message
To the crucial curve of the crucial curve and destination object of source object；
According to the crucial curve of the crucial curve and destination object of source object, amplitude adjustment curve is calculated；
Curve is adjusted according to amplitude to be adjusted current frame image, obtains the image after present frame processing；
Image after present frame is handled covers the video data after former current frame image is handled；
Video data after display processing.
Alternatively, the first key message includes the positional information of at least one first key point, and the second key message includes
The positional information of at least one second key point.
Alternatively, coordinate system is established to further comprise：Establish polar coordinate system；
It is fitted processing in a coordinate system respectively according to the first key message and the second key message and obtains source object
The crucial curve of crucial curve and destination object further comprises：
The positional information of the central point of source object is extracted in current frame image, using the mapping of the central point of source object as
The limit of polar coordinate system, will at least one according to the relative position between at least one first key point and the central point of source object
Individual first key point is mapped in polar coordinate system, is fitted according to the mapping result of at least one first key point in polar coordinate system
Processing obtains the crucial curve of source object；
The positional information of the central point of destination object is extracted in the target image, and the central point of destination object is mapped and made
It is near according to the relative position between at least one second key point and the central point of destination object for the limit of polar coordinate system
Few second key point is mapped in polar coordinate system, according to the mapping result of at least one second key point in polar coordinate system
Process of fitting treatment obtains the crucial curve of destination object.
Alternatively, one is entered according to the crucial curve of the crucial curve and destination object of source object, calculating amplitude adjustment curve
Step includes：
According to the polar diameter of any point on the crucial curve of source object, and there is with the point destination object of identical polar angle
Crucial curve on point polar diameter, calculate corresponding with polar angle regulation coefficient, obtain between polar angle and regulation coefficient
The amplitude adjustment curve of relation.
Alternatively, before polar coordinate system is established, method also includes：
According to the positional information of the central point of source object, place is corrected to the positional information of at least one first key point
Reason；And the positional information of the central point according to destination object, the positional information of at least one second key point is corrected
Processing.
Alternatively, the video data after display processing further comprises：By the video data real-time display after processing；
Method also includes：Video data after processing is uploaded to Cloud Server.
Alternatively, the video data after processing is uploaded into Cloud Server to further comprise：
Video data after processing is uploaded to cloud video platform server, so that cloud video platform server is in cloud video
Platform is shown video data.
Alternatively, the video data after processing is uploaded into Cloud Server to further comprise：
Video data after processing is uploaded to cloud direct broadcast server, so that cloud direct broadcast server pushes away video data in real time
Give viewing subscription client.
Alternatively, the video data after processing is uploaded into Cloud Server to further comprise：
Video data after processing is uploaded to cloud public number server, so that cloud public number server pushes away video data
Give public number concern client.
According to another aspect of the present invention, there is provided a kind of object video converts real-time processing device, and it includes：
First acquisition module, suitable for including source captured by real-time image acquisition collecting device and/or in the video recorded
The current frame image of object；Or the current frame image that source object is included in currently played video is obtained in real time；
Second acquisition module, suitable for obtaining the target image for including destination object；
Extraction module, suitable for extracting the first key message of source object from current frame image, and from target image
In extract the second key message of destination object；
Establishment of coordinate system module, is adapted to set up coordinate system；
Process of fitting treatment module, suitable for being fitted in a coordinate system respectively according to the first key message and the second key message
Processing obtains the crucial curve of the crucial curve and destination object of source object；
Computing module, suitable for the crucial curve of crucial curve and destination object according to source object, it is bent to calculate amplitude adjustment
Line；
Adjusting module, current frame image is adjusted suitable for adjusting curve according to amplitude, after obtaining present frame processing
Image；
Overlay module, the video data after former two field picture is handled is covered suitable for the image after present frame is handled；
Display module, suitable for the video data after display processing.
Alternatively, the first key message includes the positional information of at least one first key point, and the second key message includes
The positional information of at least one second key point.
Alternatively, establishment of coordinate system module is further adapted for：Establish polar coordinate system；
Process of fitting treatment module is further adapted for：The positional information of the central point of source object is extracted in current frame image,
Limit using the central point mapping of source object as polar coordinate system, according at least one first key point and the central point of source object
Between relative position, at least one first key point is mapped in polar coordinate system, according at least one first key point
Mapping result process of fitting treatment in polar coordinate system obtains the crucial curve of source object；
The positional information of the central point of destination object is extracted in the target image, and the central point of destination object is mapped and made
It is near according to the relative position between at least one second key point and the central point of destination object for the limit of polar coordinate system
Few second key point is mapped in polar coordinate system, according to the mapping result of at least one second key point in polar coordinate system
Process of fitting treatment obtains the crucial curve of destination object.
Alternatively, computing module is further adapted for：According to the polar diameter of any point on the crucial curve of source object, Yi Jiyu
The point has the polar diameter of the point on the crucial curve of the destination object of identical polar angle, calculates regulation coefficient corresponding with polar angle, obtains
Curve is adjusted to the amplitude on the relation between polar angle and regulation coefficient.
Alternatively, device also includes：Correction process module, suitable for the positional information of the central point according to source object, to extremely
The positional information of few first key point is corrected processing；And the positional information of the central point according to destination object, it is right
The positional information of at least one second key point is corrected processing.
Alternatively, display module is further adapted for：By the video data real-time display after processing；
Device also includes：Uploading module, suitable for the video data after processing is uploaded into Cloud Server.
Alternatively, uploading module is further adapted for：Video data after processing is uploaded to cloud video platform server, with
For cloud video platform server video data is shown in cloud video platform.
Alternatively, uploading module is further adapted for：Video data after processing is uploaded to cloud direct broadcast server, for cloud
Direct broadcast server gives video data real time propelling movement to viewing subscription client.
Alternatively, uploading module is further adapted for：Video data after processing is uploaded to cloud public number server, for
Video data is pushed to public number concern client by cloud public number server.
According to another aspect of the invention, there is provided a kind of computing device, including：Processor, memory, communication interface and
Communication bus, processor, memory and communication interface complete mutual communication by communication bus；
Memory is used to deposit an at least executable instruction, and executable instruction makes the above-mentioned object video conversion of computing device
Operated corresponding to real-time processing method.
In accordance with a further aspect of the present invention, there is provided a kind of computer-readable storage medium, be stored with least one in storage medium
Executable instruction, executable instruction make computing device operation as corresponding to above-mentioned object video conversion real-time processing method.
According to scheme provided by the invention, real-time image acquisition collecting device is captured and/or the video recorded in wrap
Current frame image containing source object；Or the current frame image that source object is included in currently played video is obtained in real time, obtain
The target image for including destination object is taken, extracts the first key message of source object from current frame image, and from target
The second key message of destination object is extracted in image, according to the first key message and the second key message respectively in coordinate system
In be fitted the crucial curve that processing obtains the crucial curve and destination object of source object, according to the crucial curve of source object and
The crucial curve of destination object, calculates amplitude adjustment curve, and adjust curve according to amplitude is adjusted to current frame image, can
Realization keeps smooth transformation during object transformation, so as to after object transformation processing terminates, ensure the frame in video
Image more naturally, and the object transformation processing effect it is more fine, beautified two field picture display effect, overcome existing skill
The edge phenomenon creasy of the two field picture occurred in art after object transformation, and make two field picture internal distortions without naturally asking
Topic.And do not need user to carry out extra process to the video of recording, user time is saved, can be handled with real-time display to user
Video data afterwards, facilitates user to check display effect.User's technical merit is not limited simultaneously, facilitates public use.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of specification, and in order to allow above and other objects of the present invention, feature and advantage can
Become apparent, below especially exemplified by the embodiment of the present invention.
Brief description of the drawings
By reading the detailed description of hereafter preferred embodiment, it is various other the advantages of and benefit it is common for this area
Technical staff will be clear understanding.Accompanying drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And in whole accompanying drawing, identical part is denoted by the same reference numerals.In the accompanying drawings：
Fig. 1 shows the schematic flow sheet of object video conversion real-time processing method according to an embodiment of the invention；
Fig. 2 shows the flow signal of object video conversion real-time processing method in accordance with another embodiment of the present invention
Figure；
Fig. 3 shows the shape of face figure of source object；
Fig. 4 shows the shape of face figure of destination object；
Fig. 5 shows the structural representation of object video conversion real-time processing device according to an embodiment of the invention；
Fig. 6 shows the structural representation of object video conversion real-time processing device in accordance with another embodiment of the present invention
Figure；
Fig. 7 shows a kind of structural representation of computing device according to an embodiment of the invention.
Embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in accompanying drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
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.
Object can be any objects such as face in image, animal in the present invention, enter in embodiment by taking face as an example
Row explanation, but face is not limited only to, for example, it is also possible to for carrying out conversion process to whole human body in image.
Fig. 1 shows the schematic flow sheet of object video conversion real-time processing method according to an embodiment of the invention.
As shown in figure 1, this method comprises the following steps：
Step S100, real-time image acquisition collecting device is captured and/or the video recorded in working as comprising source object
Prior image frame；Or the current frame image that source object is included in currently played video is obtained in real time.
Image capture device illustrates by taking mobile terminal as an example in the present embodiment.Get mobile terminal camera in real time
Current frame image when current frame image in recorded video or shooting video.Due to the present invention to source object at
Reason, therefore only obtain the current frame image comprising source object during acquisition current frame image.Except real-time image acquisition collecting device institute
Outside shooting and/or the video recorded, the present frame figure that source object is included in currently played video can also be obtained in real time
Picture.Wherein, source object can be face, can also be cute pet etc. certainly, and those skilled in the art can select according to being actually needed
Fixed process object is used as source object.
Step S101, obtain the target image for including destination object.
Destination object define the standard of wanting to reach comprising the target image of destination object can be according to
Selected operation of the family to image in photograph album determines, for example, storing the image of user star of interest, user in photograph album
An image can therefrom be selected, can also be user upload or from network download.Wish its shape of face being transformed into user A
Exemplified by certain star B shape of face, user A face is source object, and the face of the star B is destination object.
Step S102, extracts the first key message of source object from current frame image, and is carried from target image
Take out the second key message of destination object.
For convenience of object transformation processing, it is necessary to extract the first key message of source object from current frame image, and
The second key message of destination object is extracted from target image, for example, when needing to enter line translation to shape of face, extraction
The first key message mainly include face's outline information of source object, such as the tail of the eye, chin；The crucial letter of the second of extraction
The main face's outline information for including destination object of breath, such as the tail of the eye, chin.Object can be improved using key message to become
The processing speed and efficiency changed, meanwhile, key message is easy to extract, and extracts accurately, when carrying out object transformation processing more
It is convenient.
Step S103, establishes coordinate system, is carried out in a coordinate system respectively according to the first key message and the second key message
Process of fitting treatment obtains the crucial curve of the crucial curve and destination object of source object.
In embodiments of the present invention, process of fitting treatment is exactly that a series of first key message in plane is smooth with one
Curve is connected, and a series of second key message in plane is connected with a smooth curve.With face
Exemplified by, it is fitted processing in a coordinate system according to the first key message and obtains the crucial curve of source object similar to source object
Face contour；It is fitted processing in a coordinate system according to the second key message and obtains the crucial curve of destination object and is similar to mesh
The face contour of object is marked, is merely illustrative of here, without any restriction effect.
Step S104, according to the crucial curve of the crucial curve and destination object of source object, calculate amplitude adjustment curve.
Although having obtained the crucial curve of the crucial curve and destination object of source object in step s 103, the present invention is real
It is not simply to adjust the crucial curve of source object to the crucial curve of destination object to apply example, if simply simply by source
The crucial curve of object is adjusted to the crucial curve of destination object, is easy for object transformation back edge phenomenon creasy occur,
But also image internal distortions can be made without naturally, therefore, obtaining the key song of the crucial curve and destination object of source object
After line, it is also necessary to according to the crucial curve of the crucial curve and destination object of source object, amplitude adjustment curve is calculated, to utilize
The amplitude being calculated adjusts curve to be adjusted to current frame image.
Step S105, curve is adjusted according to amplitude current frame image is adjusted, obtain the image after present frame processing.
After amplitude adjustment curve is calculated, curve can be adjusted according to amplitude and current frame image is adjusted, this
In be that all pixels point of current frame image is all adjusted, so as to keep smooth during object transformation, overcome pair
As the edge occurred after conversion phenomenon creasy, and make image internal distortions without it is natural the problem of.
Step S106, the image after present frame is handled cover the video data after former current frame image is handled.
Image after being handled using present frame directly overrides former current frame image, the video after directly can be processed
Data.Meanwhile the user of recording can also be immediately seen the image after present frame processing.
Step S107, the video data after display processing.
After video data after being handled, it can be shown in real time, after user can directly be seen that processing
Video data display effect.
The method provided according to the above embodiment of the present invention, real-time image acquisition collecting device is captured and/or is recorded
Video in include the current frame image of source object；Or working as comprising source object in currently played video is obtained in real time
Prior image frame, the target image for including destination object is obtained, the first key message of source object is extracted from current frame image,
And the second key message of destination object is extracted from target image, according to the first key message and the second key message point
The crucial curve that processing obtains the crucial curve and destination object of source object is not fitted in a coordinate system, according to source object
The crucial curve of crucial curve and destination object, calculates amplitude adjustment curve, and adjust curve according to amplitude enters to current frame image
Row adjustment, can realize and smooth transformation is kept during object transformation, so as to after object transformation processing terminates, ensure
Two field picture in video more naturally, and the object transformation processing effect it is more fine, beautified two field picture display effect, gram
Taken the edge phenomenon creasy of the two field picture occurred after object transformation in the prior art, and make two field picture internal distortions and
The problem of unnatural.And do not need user to carry out extra process to the video of recording, and user time is saved, can be with real-time display
Video data after being handled to user, facilitates user to check display effect.User's technical merit is not limited simultaneously, it is convenient big
Crowd uses.
Object transformation real-time processing method will be illustrated by taking the shape of face for converting face as an example below：
Fig. 2 shows the flow signal of object video conversion real-time processing method in accordance with another embodiment of the present invention
Figure.As shown in Fig. 2 this method comprises the following steps：
Step S200, real-time image acquisition collecting device is captured and/or the video recorded in working as comprising source object
Prior image frame；Or the current frame image that source object is included in currently played video is obtained in real time.
Step S201, obtain the target image for including destination object.
Destination object define the standard of wanting to reach comprising the target image of destination object can be according to
Selected operation of the family to image in photograph album determines, for example, storing the image of user star of interest, user in photograph album
An image can therefrom be selected, can also be user upload or from network download.Wish its shape of face being transformed into user A
Exemplified by certain star B shape of face, user A face is source object, and the face of the star B is destination object.
Step S202, extracts the first key message of source object from current frame image, and is carried from target image
Take out the second key message of destination object.
Wherein, the first key message includes the positional information of at least one first key point, and the positional information indicates
Position of one key point in face；Second key message includes the positional information of at least one second key point, position letter
Breath indicates position of second key point in face.
Specifically, source object can be identified from current frame image：User A face part, is therefrom extracted at least
The positional information of one the first key point, the positional information of P1 as shown in Figure 3 point-P8 points；Mesh is identified from target image
Mark object：Star B face part, therefrom extract the positional information of at least one first key point, P1 as shown in Figure 4
The positional information of point-P8 points, is merely just schematically illustrated, without any restriction effect.
Step S203, according to the positional information of the central point of source object, to the positional information of at least one first key point
It is corrected processing.
In embodiments of the present invention, the current frame image comprising source object is probably the side face image of Zhang Yuan's object, or
Person is the image that a process zooms in or out processing, for this kind of image, if without any processing directly carry out object change
Change processing, it is easy to cause object transformation to handle inaccurate, cause object transformation effect poor, therefore, from current frame image
In extract the first key message of source object and postpone, can be according to the positional information of the central point of source object, at least one
The positional information of first key point is corrected processing, continues here so that shape of face converts as an example, and the central point of source object can select
Do the midpoint of two, by least one first key point along source object central point expansion and it is symmetrical, then carry out image
Scaling processing so that face changes to the size position of a standard of comparison, is easy to subsequent object conversion process.
Step S204, according to the positional information of the central point of destination object, the position of at least one second key point is believed
Breath is corrected processing.
In embodiments of the present invention, the target image comprising destination object is probably the side face image of a destination object,
Either a process zooms in or out the image of processing, for this kind of image, if without any processing directly use it to
Carry out object transformation processing, it is easy to cause object transformation handle it is inaccurate, cause object transformation effect poor, therefore, from
The second key message that destination object is extracted in target image postpones, and can be believed according to the position of the central point of destination object
Breath, is corrected processing to the positional information of at least one second key point, continues here so that shape of face converts as an example, destination object
Central point can select and do the midpoint of two, central point of at least one second key point along destination object is deployed and symmetrically divided
Cloth, then carry out image scaling processing so that face changes to the size position of a standard of comparison, is easy to subsequent object to convert
Processing.
Step S205, establishes polar coordinate system, and the positional information of the central point of source object is extracted in current frame image, will
The central point of source object maps the limit as polar coordinate system, according to the central point of at least one first key point and source object it
Between relative position, at least one first key point is mapped in polar coordinate system, according to reflecting at least one first key point
Penetrate result process of fitting treatment in polar coordinate system and obtain the crucial curve of source object.
So that shape of face converts as an example, the midpoint that people is two can be considered the central point of source object in current frame image, in present frame
The positional information of the central point of source object is extracted in image, the people midpoint of two is mapped into the limit as polar coordinate system, built
Vertical polar coordinate system, in order to fit the crucial curve of source object exactly, and embodies under polar coordinate system as far as possible
The shape of face of source object, it is thus necessary to determine that the relative position between at least one first key point and central point, including angle and distance,
Then, according to the relative position between at least one first key point and the central point of source object by least one first key point
It is mapped in polar coordinate system, according to the mapping result of at least one first key point, process of fitting treatment obtains source pair in polar coordinate system
The crucial curve of elephant, in embodiments of the present invention, process of fitting treatment are exactly a series of at least one first key point in plane
Connected with a smooth curve.Specifically, after coordinate system is established, can be entered using least square curve fitting method
Row process of fitting treatment, so that the shape of face of source object is square face as an example, after extraction obtains the first key message, according to the first crucial letter
Breath is fitted processing in a coordinate system using least square curve fitting method, obtains face's foreign steamer with the square face of source object
The crucial curve of wide approximate source object, as shown in figure 3, being merely illustrative of here, without any restriction effect.
Step S206, the positional information of the central point of destination object is extracted in the target image, by destination object
Heart point maps the limit as polar coordinate system, according to relative between at least one second key point and the central point of destination object
Position, at least one second key point is mapped in polar coordinate system, existed according to the mapping result of at least one second key point
Process of fitting treatment obtains the crucial curve of destination object in polar coordinate system.
So that shape of face converts as an example, the midpoint that people is two can be considered the central point of destination object in target image, in target figure
The positional information of the central point of destination object is extracted as in, the people midpoint of two is mapped into the limit as polar coordinate system, built
Vertical polar coordinate system, in order to fit the crucial curve of destination object exactly, and as far as possible in polar coordinate system lower body
The shape of face of existing destination object, it is thus necessary to determine that the relative position between at least one second key point and central point, including angle and
Distance, then, according to the relative position between at least one second key point and the central point of destination object by least one
Two key points are mapped in polar coordinate system, according to the mapping result of at least one second key point in polar coordinate system process of fitting treatment
The crucial curve of destination object is obtained, in embodiments of the present invention, process of fitting treatment is exactly a series of at least one in plane
Second key point is connected with a smooth curve.Specifically, after coordinate system is established, least square curve can be utilized
Fitting process is handled to be fitted, so that the shape of face of destination object is heart-shaped face as an example, after extraction obtains the first key message, and root
Processing is fitted in a coordinate system using least square curve fitting method according to the first key message, obtains the heart with destination object
The crucial curve of the approximate destination object of face's outline of shape face, as shown in figure 4, be merely illustrative of here, without appointing
What restriction effect.
Step S207, there is identical polar angle according to the polar diameter of any point on the crucial curve of source object, and with the point
Destination object crucial curve on point polar diameter, calculate corresponding with polar angle regulation coefficient, obtain on polar angle with adjusting
The amplitude adjustment curve of relation between coefficient.
Although having obtained the crucial curve of the crucial curve and destination object of source object in step S206, the present invention is real
It is not simply to adjust the crucial curve of source object to the crucial curve of destination object to apply example, if simply simply by source
The crucial curve of object is adjusted to the crucial curve of destination object, is easy for object transformation back edge phenomenon creasy occur,
But also image internal distortions can be made without naturally, therefore, obtaining the key song of the crucial curve and destination object of source object
After line, it is also necessary to according to the crucial curve of the crucial curve and destination object of source object, amplitude adjustment curve is calculated, to utilize
The amplitude being calculated adjusts curve to be adjusted to current frame image.
Specifically, any point on the crucial curve of source object is chosen, determines the polar diameter of the point, and finds and has with the point
Point on the crucial curve of the destination object of identical polar angle, the polar diameter of the point on the crucial curve of destination object is determined, according to source
The polar diameter of point on the crucial curve of object and the polar diameter of the point on the crucial curve of destination object calculate regulation coefficient, so as to
Curve is adjusted to the amplitude on the relation between polar angle and regulation coefficient.
Step S208, curve is adjusted according to amplitude current frame image is adjusted, obtain the image after present frame processing.
After amplitude adjustment curve is calculated, curve can be adjusted according to amplitude and current frame image is adjusted, this
In be that all pixels point of current frame image is all adjusted, so as to keep smooth during object transformation, overcome pair
As the edge occurred after conversion phenomenon creasy, and make image internal distortions without it is natural the problem of.
The object video conversion real-time processing method of the present invention can be also used for entering human body line translation, and central point can select
Navel position is selected, specifically transform process method no longer describes in detail here.
Step S209, the image after present frame is handled cover the video data after former current frame image is handled.
Image after being handled using present frame directly overrides former current frame image, the video after directly can be processed
Data.Meanwhile the user of recording can also be immediately seen the image after present frame processing.
Step S210, the video data after display processing.
After video data after being handled, it can be shown in real time, after user can directly be seen that processing
Video data display effect.
Step S211, the video data after processing is uploaded to Cloud Server.
Video data after processing can be directly uploaded to Cloud Server, specifically, can be by the video counts after processing
According to be uploaded to one or more cloud video platform server, such as iqiyi.com, youku.com, fast video cloud video platform server,
So that cloud video platform server is shown video data in cloud video platform.Or can also be by the video data after processing
Cloud direct broadcast server is uploaded to, can be straight by cloud when the user for having live viewing end is watched into cloud direct broadcast server
Broadcast server and give video data real time propelling movement to viewing subscription client.Or the video data after processing can also be uploaded to
Cloud public number server, when there is user to pay close attention to the public number, video data is pushed to public number by cloud public number server
Pay close attention to client；Further, cloud public number server can also be accustomed to according to the viewing of the user of concern public number, and push meets
The video data of user's custom pays close attention to client to public number.
The method provided according to the above embodiment of the present invention, real-time image acquisition collecting device is captured and/or is recorded
Video in include the current frame image of source object；Or working as comprising source object in currently played video is obtained in real time
Prior image frame, obtain the target image for including destination object, the first key point to extracting source object from current frame image
Positional information be corrected processing, and the second key point positional information to extracting destination object from target image is entered
Row correction process, subsequent object conversion process can be made more accurate, improve object transformation effect, according to the first key message
It is fitted the key that processing obtains the crucial curve and destination object of source object in a coordinate system respectively with the second key message
Curve, according to the crucial curve of the crucial curve and destination object of source object, amplitude adjustment curve is calculated, is adjusted according to amplitude bent
Line is adjusted to current frame image, can realize and smooth transformation is kept during object transformation, so as to become in object
Change after processing terminates, ensure two field picture in video more naturally, and object transformation processing effect it is more fine, beautification
Two field picture display effect, the edge phenomenon creasy of the two field picture occurred after object transformation in the prior art is overcome, and
Make two field picture internal distortions without it is natural the problem of.The present invention is not limited to user's technical merit, it is not necessary to which user is to image
Extra process is carried out, user time is saved, the image after being handled with Real-time Feedback, facilitates user to check.
Fig. 5 shows the structural representation of object video conversion real-time processing device according to an embodiment of the invention.
As shown in figure 5, the device includes：First acquisition module 500, the second acquisition module 501, extraction module 502, establishment of coordinate system mould
Block 503, process of fitting treatment module 504, computing module 505, adjusting module 506, overlay module 507 and display module 508.
First acquisition module 500, suitable for being included captured by real-time image acquisition collecting device and/or in the video recorded
The current frame image of source object；Or the current frame image that source object is included in currently played video is obtained in real time.
Second acquisition module 501, suitable for obtaining the target image for including destination object.
Extraction module 502, suitable for extracting the first key message of source object from current frame image, and from target figure
The second key message of destination object is extracted as in.
Establishment of coordinate system module 503, is adapted to set up coordinate system.
Process of fitting treatment module 504, suitable for being carried out in a coordinate system respectively according to the first key message and the second key message
Process of fitting treatment obtains the crucial curve of the crucial curve and destination object of source object.
Computing module 505, suitable for the crucial curve of crucial curve and destination object according to source object, calculate amplitude adjustment
Curve.
Adjusting module 506, current frame image is adjusted suitable for adjusting curve according to amplitude, after obtaining present frame processing
Image.
Overlay module 507, the video data after former two field picture is handled is covered suitable for the image after present frame is handled.
Display module 508, suitable for the video data after display processing.
The device provided according to the above embodiment of the present invention, real-time image acquisition collecting device is captured and/or is recorded
Video in include the current frame image of source object；Or working as comprising source object in currently played video is obtained in real time
Prior image frame, the target image for including destination object is obtained, the first key message of source object is extracted from current frame image,
And the second key message of destination object is extracted from target image, according to the first key message and the second key message point
The crucial curve that processing obtains the crucial curve and destination object of source object is not fitted in a coordinate system, according to source object
The crucial curve of crucial curve and destination object, calculates amplitude adjustment curve, and adjust curve according to amplitude enters to current frame image
Row adjustment, can realize and smooth transformation is kept during object transformation, so as to after object transformation processing terminates, ensure
Two field picture in video more naturally, and the object transformation processing effect it is more fine, beautified two field picture display effect, gram
Taken the edge phenomenon creasy of the two field picture occurred after object transformation in the prior art, and make two field picture internal distortions and
The problem of unnatural.
Fig. 6 shows the structural representation of object video conversion real-time processing device in accordance with another embodiment of the present invention
Figure.As shown in fig. 6, the device includes：First acquisition module 600, the second acquisition module 601, extraction module 602, coordinate system are built
Formwork erection block 603, process of fitting treatment module 604, computing module 605, adjusting module 606, overlay module 607 and display module 608.
First acquisition module 600, suitable for being included captured by real-time image acquisition collecting device and/or in the video recorded
The current frame image of source object；Or the current frame image that source object is included in currently played video is obtained in real time.
Second acquisition module 601, suitable for obtaining the target image for including destination object.
Extraction module 602, suitable for extracting the first key message of source object from current frame image, and from target figure
The second key message of destination object is extracted as in.
Wherein, the first key message includes the positional information of at least one first key point, and the second key message includes extremely
The positional information of few second key point.
Correction process module 609, suitable for the positional information of the central point according to source object, at least one first key point
Positional information be corrected processing；And the positional information of the central point according to destination object, it is crucial at least one second
The positional information of point is corrected processing.
Establishment of coordinate system module 603, is adapted to set up polar coordinate system.
Process of fitting treatment module 604, the positional information of the central point suitable for extracting source object in current frame image, by source
The central point of object maps the limit as polar coordinate system, according between at least one first key point and the central point of source object
Relative position, at least one first key point is mapped in polar coordinate system, according to the mapping of at least one first key point
As a result process of fitting treatment obtains the crucial curve of source object in polar coordinate system；And destination object is extracted in the target image
Central point positional information, the limit using the mapping of the central point of destination object as polar coordinate system, according at least one second
Relative position between key point and the central point of destination object, at least one second key point is mapped in polar coordinate system,
According to the mapping result of at least one second key point, process of fitting treatment obtains the crucial curve of destination object in polar coordinate system.
Computing module 605, there is phase suitable for the polar diameter of any point on the crucial curve according to source object, and with the point
With the polar diameter of the point on the crucial curve of the destination object of polar angle, regulation coefficient corresponding with polar angle is calculated, is obtained on polar angle
The amplitude adjustment curve of relation between regulation coefficient.
Adjusting module 606, current frame image is adjusted suitable for adjusting curve according to amplitude, after obtaining present frame processing
Image.
Overlay module 607, the video data after former two field picture is handled is covered suitable for the image after present frame is handled；
Display module 608, suitable for the video data after display processing.
Display module 608 handled after video data after, it can be shown in real time, user can be direct
See the display effect of the video data after processing.
Uploading module 610, suitable for the video data after processing is uploaded into Cloud Server.
Video data after processing can be directly uploaded to Cloud Server by uploading module 610, specifically, uploading module
610 can be uploaded to the video data after processing the cloud video platform server of one or more, such as iqiyi.com, youku.com, fast
The cloud video platform server such as video, so that cloud video platform server is shown video data in cloud video platform.Or
Video data after processing can also be uploaded to cloud direct broadcast server by uploading module 610, when the user for having live viewing end enters
When entering cloud direct broadcast server and being watched, can by cloud direct broadcast server by video data real time propelling movement to viewing user client
End.Or the video data after processing can also be uploaded to cloud public number server by uploading module 610, it is somebody's turn to do when there is user's concern
During public number, video data is pushed to public number concern client by cloud public number server；Further, cloud public number service
Device can also be accustomed to according to the viewing of the user of concern public number, and the video data that push meets user's custom is paid close attention to public number
Client.
The device provided according to the above embodiment of the present invention, real-time image acquisition collecting device is captured and/or is recorded
Video in include the current frame image of source object；Or working as comprising source object in currently played video is obtained in real time
Prior image frame, obtain the target image for including destination object, the first key point to extracting source object from current frame image
Positional information be corrected processing, and the second key point positional information to extracting destination object from target image is entered
Row correction process, subsequent object conversion process can be made more accurate, improve object transformation effect, according to the first key message
It is fitted the key that processing obtains the crucial curve and destination object of source object in a coordinate system respectively with the second key message
Curve, according to the crucial curve of the crucial curve and destination object of source object, amplitude adjustment curve is calculated, is adjusted according to amplitude bent
Line is adjusted to current frame image, can realize and smooth transformation is kept during object transformation, so as to become in object
Change after processing terminates, ensure two field picture in video more naturally, and object transformation processing effect it is more fine, beautification
Two field picture display effect, the edge phenomenon creasy of the two field picture occurred after object transformation in the prior art is overcome, and
Make two field picture internal distortions without it is natural the problem of.The present invention is not limited to user's technical merit, it is not necessary to which user is to image
Extra process is carried out, user time is saved, the image after being handled with Real-time Feedback, facilitates user to check.
Present invention also provides a kind of nonvolatile computer storage media, the computer-readable storage medium is stored with least
One executable instruction, the image capture device data that the computer executable instructions can perform in above-mentioned any means embodiment are real
When processing method.
Fig. 7 shows a kind of structural representation of computing device according to an embodiment of the invention, of the invention specific real
Specific implementation of the example not to computing device is applied to limit.
As shown in fig. 7, the computing device can include：Processor (processor) 702, communication interface
(Communications Interface) 704, memory (memory) 706 and communication bus 708.
Wherein：
Processor 702, communication interface 704 and memory 706 complete mutual communication by communication bus 708.
Communication interface 704, for being communicated with the network element of miscellaneous equipment such as client or other servers etc..
Processor 702, for configuration processor 710, it can specifically perform above-mentioned image capture device generating date side
Correlation step in method embodiment.
Specifically, program 710 can include program code, and the program code includes computer-managed instruction.
Processor 702 is probably central processor CPU, or specific integrated circuit ASIC (Application
Specific Integrated Circuit), or it is arranged to implement the integrated electricity of one or more of the embodiment of the present invention
Road.The one or more processors that computing device includes, can be same type of processor, such as one or more CPU；Also may be used
To be different types of processor, such as one or more CPU and one or more ASIC.
Memory 706, for depositing program 710.Memory 706 may include high-speed RAM memory, it is also possible to also include
Nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.
Program 710 specifically can be used for causing processor 702 to perform the method in Fig. 1 and embodiment illustrated in fig. 2.
Algorithm and display be not inherently related to any certain computer, virtual system or miscellaneous equipment provided herein.
Various general-purpose systems can also be used together with teaching based on this.As described above, required by constructing this kind of system
Structure be obvious.In addition, the present invention is not also directed to any certain programmed language.It should be understood that it 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 specification that this place provides, 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 in the case of these no details.In some instances, known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it will be appreciated that in order to simplify the disclosure and help to understand one or more of each inventive aspect,
Above in the description to the 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：I.e. required guarantor
The application claims of shield features more more than the feature being expressly recited in each claim.It is more precisely, such as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following embodiment are expressly incorporated in the embodiment, wherein each claim is in itself
Separate embodiments all as the present invention.
Those skilled in the art, which are appreciated that, to be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more equipment different from the embodiment.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.In addition at least some in such feature and/or process or unit exclude each other, it can use any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, summary and accompanying 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, summary and accompanying drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generation
Replace.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included some features rather than further 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 realized with hardware, or to be run on one or more processor
Software module realize, or realized with combinations thereof.It will be understood by those of skill in the art that it can use in practice
Microprocessor or digital signal processor (DSP) set to realize that object video conversion according to embodiments of the present invention is handled in real time
The some or all functions of some or all parts in standby.The present invention is also implemented as described here for performing
Method some or all equipment or program of device (for example, computer program and computer program product).This
The program of the realization present invention of sample can store on a computer-readable medium, or can have one or more signal
Form.Such signal can be downloaded from internet website and obtained, and either be provided or with any other on carrier signal
Form provides.
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 symbol 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 some different elements and being come by means of properly programmed computer real
It is existing.In if the unit claim of equipment for drying is listed, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and run after fame
Claim.
Claims (10)
1. a kind of object video converts real-time processing method, it includes：
Real-time image acquisition collecting device is captured and/or the video recorded in include source object current frame image；Or
The current frame image that source object is included in currently played video is obtained in real time；
Obtain the target image for including destination object；
The first key message of the source object is extracted from the current frame image, and is extracted from the target image
Go out the second key message of the destination object；
Coordinate system is established, is intended respectively in the coordinate system according to first key message and second key message
Conjunction handles to obtain the crucial curve of the crucial curve and destination object of source object；
According to the crucial curve of the crucial curve and destination object of source object, amplitude adjustment curve is calculated；
Curve is adjusted according to the amplitude to be adjusted the current frame image, obtains the image after present frame processing；
Image after present frame is handled covers the video data after former current frame image is handled；
Show the video data after the processing.
2. according to the method for claim 1, wherein, first key message includes the position of at least one first key point
Confidence ceases, and second key message includes the positional information of at least one second key point.
3. method according to claim 1 or 2, wherein, the coordinate system of establishing further comprises：Establish polar coordinate system；
It is described that processing is fitted in the coordinate system according to first key message and second key message respectively
The crucial curve for obtaining the crucial curve and destination object of source object further comprises：
The positional information of the central point of the source object is extracted in current frame image, the central point of the source object is mapped
As the limit of polar coordinate system, according to the relative position between at least one first key point and the central point of the source object
Put, at least one first key point is mapped in the polar coordinate system, according at least one first key point
Mapping result process of fitting treatment in the polar coordinate system obtains the crucial curve of source object；
The positional information of the central point of the destination object is extracted in the target image, and the central point of the destination object is reflected
The limit as polar coordinate system is penetrated, according to the phase between at least one second key point and the central point of the destination object
To position, at least one second key point is mapped in the polar coordinate system, it is crucial according to described at least one second
The mapping result of point process of fitting treatment in the polar coordinate system obtains the crucial curve of destination object.
4. according to the method described in claim any one of 1-3, wherein, the crucial curve and destination object according to source object
Crucial curve, calculating amplitude adjustment curve further comprise：
According to the polar diameter of any point on the crucial curve of source object, and there is with the point pass of the destination object of identical polar angle
The polar diameter of point on key curve, regulation coefficient corresponding with polar angle is calculated, is obtained on the relation between polar angle and regulation coefficient
Amplitude adjustment curve.
5. according to the method described in claim any one of 1-4, wherein, before polar coordinate system is established, methods described also includes：
According to the positional information of the central point of the source object, school is carried out to the positional information of at least one first key point
Positive processing；And the positional information of the central point according to the destination object, to the position of at least one second key point
Information is corrected processing.
6. according to the method any one of claim 1-5, wherein, the video data after the display processing further wraps
Include：By the video data real-time display after processing；
Methods described also includes：Video data after processing is uploaded to Cloud Server.
7. according to the method described in claim any one of 1-6, wherein, the video data by after processing is uploaded to cloud clothes
Business device further comprises：
Video data after processing is uploaded to cloud video platform server, so that cloud video platform server is in cloud video platform
It is shown video data.
8. a kind of object video converts real-time processing device, it includes：
First acquisition module, suitable for including source object captured by real-time image acquisition collecting device and/or in the video recorded
Current frame image；Or the current frame image that source object is included in currently played video is obtained in real time；
Second acquisition module, suitable for obtaining the target image for including destination object；
Extraction module, suitable for extracting the first key message of the source object from the current frame image, and from described
The second key message of the destination object is extracted in target image；
Establishment of coordinate system module, is adapted to set up coordinate system；
Process of fitting treatment module, suitable for according to first key message and second key message respectively in the coordinate system
It is fitted the crucial curve that processing obtains the crucial curve and destination object of source object；
Computing module, suitable for the crucial curve of crucial curve and destination object according to source object, calculate amplitude adjustment curve；
Adjusting module, the current frame image is adjusted suitable for adjusting curve according to the amplitude, obtains present frame processing
Image afterwards；
Overlay module, the video data after former two field picture is handled is covered suitable for the image after present frame is handled；
Display module, suitable for the video data after the display processing.
9. a kind of computing device, including：Processor, memory, communication interface and communication bus, the processor, the storage
Device and the communication interface complete mutual communication by the communication bus；
The memory is used to deposit an at least executable instruction, and the executable instruction makes the computing device such as right will
Ask the object video any one of 1-7 to convert corresponding to real-time processing method to operate.
10. a kind of computer-readable storage medium, an at least executable instruction, the executable instruction are stored with the storage medium
Make behaviour corresponding to object video conversion real-time processing method of the computing device as any one of claim 1-7
Make.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710927355.9A CN107492068B (en) | 2017-09-28 | 2017-09-28 | Video object transformation real-time processing method and device and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710927355.9A CN107492068B (en) | 2017-09-28 | 2017-09-28 | Video object transformation real-time processing method and device and computing equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107492068A true CN107492068A (en) | 2017-12-19 |
| CN107492068B CN107492068B (en) | 2020-08-04 |
Family
ID=60653764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710927355.9A Active CN107492068B (en) | 2017-09-28 | 2017-09-28 | Video object transformation real-time processing method and device and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107492068B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107993217A (en) * | 2017-12-22 | 2018-05-04 | 北京奇虎科技有限公司 | Video data real-time processing method and device, computing device |
| CN112001851A (en) * | 2019-05-27 | 2020-11-27 | 腾讯科技（深圳）有限公司 | Image processing method, image processing device, computer equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103079016A (en) * | 2013-01-24 | 2013-05-01 | 上海斐讯数据通信技术有限公司 | Photographed face transformation method and intelligent terminal |
| CN103337085A (en) * | 2013-06-17 | 2013-10-02 | 大连理工大学 | Efficient portrait face distortion method |
| CN103413268A (en) * | 2013-08-06 | 2013-11-27 | 厦门美图移动科技有限公司 | Photographing method capable of automatically optimizing facial form |
| CN103503025A (en) * | 2011-02-25 | 2014-01-08 | 弗劳恩霍夫应用研究促进协会 | Determining model parameters based on transforming a model of an object |
| CN105096377A (en) * | 2014-05-14 | 2015-11-25 | 华为技术有限公司 | Image processing method and apparatus |
| CN105184249A (en) * | 2015-08-28 | 2015-12-23 | 百度在线网络技术（北京）有限公司 | Method and device for processing face image |
| CN105374055A (en) * | 2014-08-20 | 2016-03-02 | 腾讯科技（深圳）有限公司 | Image processing method and device |
| CN105869153A (en) * | 2016-03-24 | 2016-08-17 | 西安交通大学 | Non-rigid face image registering method integrated with related block information |
| US20170116705A1 (en) * | 2015-10-22 | 2017-04-27 | Korea Institute Of Science And Technology | Method for automatic facial impression transformation, recording medium and device for performing the method |
-
2017
- 2017-09-28 CN CN201710927355.9A patent/CN107492068B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103503025A (en) * | 2011-02-25 | 2014-01-08 | 弗劳恩霍夫应用研究促进协会 | Determining model parameters based on transforming a model of an object |
| CN103079016A (en) * | 2013-01-24 | 2013-05-01 | 上海斐讯数据通信技术有限公司 | Photographed face transformation method and intelligent terminal |
| CN103337085A (en) * | 2013-06-17 | 2013-10-02 | 大连理工大学 | Efficient portrait face distortion method |
| CN103413268A (en) * | 2013-08-06 | 2013-11-27 | 厦门美图移动科技有限公司 | Photographing method capable of automatically optimizing facial form |
| CN105096377A (en) * | 2014-05-14 | 2015-11-25 | 华为技术有限公司 | Image processing method and apparatus |
| CN105374055A (en) * | 2014-08-20 | 2016-03-02 | 腾讯科技（深圳）有限公司 | Image processing method and device |
| CN105184249A (en) * | 2015-08-28 | 2015-12-23 | 百度在线网络技术（北京）有限公司 | Method and device for processing face image |
| US20170116705A1 (en) * | 2015-10-22 | 2017-04-27 | Korea Institute Of Science And Technology | Method for automatic facial impression transformation, recording medium and device for performing the method |
| CN105869153A (en) * | 2016-03-24 | 2016-08-17 | 西安交通大学 | Non-rigid face image registering method integrated with related block information |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107993217A (en) * | 2017-12-22 | 2018-05-04 | 北京奇虎科技有限公司 | Video data real-time processing method and device, computing device |
| CN107993217B (en) * | 2017-12-22 | 2021-04-09 | 北京奇虎科技有限公司 | Video data real-time processing method and device and computing equipment |
| CN112001851A (en) * | 2019-05-27 | 2020-11-27 | 腾讯科技（深圳）有限公司 | Image processing method, image processing device, computer equipment and storage medium |
| CN112001851B (en) * | 2019-05-27 | 2023-08-04 | 腾讯科技（深圳）有限公司 | Image processing method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107492068B (en) | 2020-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10846836B2 (en) | View synthesis using deep convolutional neural networks | |
| CN107820027A (en) | Video personage dresss up method, apparatus, computing device and computer-readable storage medium | |
| CN107507155A (en) | Video segmentation result edge optimization real-time processing method, device and computing device | |
| CN107483892A (en) | Video data real-time processing method and device, computing device | |
| CN107734207A (en) | Object video transform process method, device and computing device | |
| CN107277391B (en) | Image conversion network processing method, server, computing device and storage medium | |
| CN107277615B (en) | Live broadcast stylization processing method and device, computing device and storage medium | |
| US10403001B2 (en) | Producing three-dimensional representation based on images of an object | |
| CN107808373A (en) | Sample image synthetic method, device and computing device based on posture | |
| CN108109161B (en) | Video data real-time processing method and device based on self-adaptive threshold segmentation | |
| CN107613360A (en) | Video data real-time processing method and device, computing device | |
| CN112991358A (en) | Method for generating style image, method, device, equipment and medium for training model | |
| CN107644423B (en) | Scene segmentation-based video data real-time processing method and device and computing equipment | |
| CN107767326A (en) | Objects in images transform process method, device and computing device | |
| CN107492068A (en) | Object video conversion real-time processing method, device and computing device | |
| CN107766803B (en) | Video character decorating method and device based on scene segmentation and computing equipment | |
| CN103745429A (en) | Method for rapidly realizing eye image processing | |
| KR101388965B1 (en) | Method for transforming drawing from digital picture | |
| CN115546379A (en) | Data processing method and device and computer equipment | |
| CN107566853A (en) | Realize the video data real-time processing method and device, computing device of scene rendering | |
| WO2022142908A1 (en) | Three-dimensional model generation method, xr device and storage medium | |
| CN107563962A (en) | Video data real-time processing method and device, computing device | |
| CN108171716A (en) | Video personage based on the segmentation of adaptive tracing frame dresss up method and device | |
| CN112528978A (en) | Face key point detection method and device, electronic equipment and storage medium | |
| CN107767391A (en) | Landscape image processing method, device, computing device and computer-readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |