CN108696699A - A kind of method and apparatus of video processing - Google Patents

A kind of method and apparatus of video processing Download PDF

Info

Publication number
CN108696699A
CN108696699A CN201810316940.XA CN201810316940A CN108696699A CN 108696699 A CN108696699 A CN 108696699A CN 201810316940 A CN201810316940 A CN 201810316940A CN 108696699 A CN108696699 A CN 108696699A
Authority
CN
China
Prior art keywords
special efficacy
dimensional special
specified
model
efficacy model
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
Application number
CN201810316940.XA
Other languages
Chinese (zh)
Inventor
徐毅刚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guang Heng Hengyu (beijing) Technology Co Ltd
Original Assignee
Guang Heng Hengyu (beijing) Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guang Heng Hengyu (beijing) Technology Co Ltd filed Critical Guang Heng Hengyu (beijing) Technology Co Ltd
Priority to CN201810316940.XA priority Critical patent/CN108696699A/en
Publication of CN108696699A publication Critical patent/CN108696699A/en
Pending legal-status Critical Current

Links

Classifications

    • 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
    • H04N5/2621—Cameras specially adapted for the electronic generation of special effects during image pickup, e.g. digital cameras, camcorders, video cameras having integrated special effects capability
    • 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
    • H04N5/265—Mixing

Abstract

The invention discloses method, apparatus, electronic equipment and the computer readable storage mediums of a kind of processing of video.This method includes:Obtain the video of video collector acquisition, the specified target in the acquired video of identification;When identifying multiple specified targets from video, multiple and different three-dimensional special efficacy models is chosen from three-dimensional special efficacy model library;Multiple and different three-dimensional special efficacy models of selection are loaded into respectively in the multiple specified targets identified.By the technical program, when having multiple specified targets in video, it can be that multiple specified targets load different three-dimensional special efficacy models respectively, meet the needs of users, increase the interest of video processing, enhance the usage experience of user.

Description

A kind of method and apparatus of video processing
Technical field
The present invention relates to field of computer technology, and in particular to a kind of method, apparatus, electronic equipment and the meter of video processing Calculation 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 etc..But when having multiple people in image or video, it is generally the case that can only all be not added with special efficacy or Identical special efficacy is loaded, the demand of user is cannot be satisfied, reduces the usage experience of user.
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, apparatus, electronic equipment and the computer readable storage medium of the video processing of problem.
According to an aspect of the invention, there is provided a kind of method of video processing, wherein this method includes:
Obtain the video of video collector acquisition, the specified target in the acquired video of identification;
When identifying multiple specified targets from the video, multiple and different three are chosen from three-dimensional special efficacy model library Tie up special efficacy model;
Multiple and different three-dimensional special efficacy models of selection are loaded into respectively in the multiple specified targets identified.
Optionally, described to choose multiple three-dimensional special efficacy models from three-dimensional special efficacy model library and include:
The specified attribute of each specified target identified is obtained respectively;
It is chosen from three-dimensional special efficacy model library and the matched three-dimensional special efficacy model of the specified attribute of each specified target obtained;
Described multiple and different three-dimensional special efficacy models of selection are loaded into respectively in the multiple specified targets identified is wrapped It includes:
According to the specified attribute for each specified target of acquisition identified, by multiple and different three-dimensional special efficacy models of selection It is loaded into respectively in corresponding specified target.
Optionally, the specified attribute of the specified target includes:
The gender of specified target and/or age.
Optionally, this method further comprises:
The selection control of three-dimensional special efficacy model is provided;
It is described to choose multiple and different three-dimensional special efficacy models from three-dimensional special efficacy model library and include:
In response to the selection operation to three-dimensional special efficacy model, corresponding three-dimensional special efficacy is selected from three-dimensional special efficacy model library Model.
Optionally, described that multiple and different three-dimensional special efficacy models of selection are loaded into the multiple specified mesh identified respectively Put on including:
Show the multiple and different three-dimensional special efficacy models selected;
In response to the drag operation to the three-dimensional special efficacy model selected, determine each three-dimensional special efficacy model with identify it is each The correspondence of specified target;
According to the correspondence, multiple and different three-dimensional special efficacy models of selection are loaded into corresponding specified mesh respectively It puts on.
Optionally, this method further comprises:
When meeting preset condition, the specified category of the three-dimensional special efficacy model in the specified target in the video is converted Property.
Optionally, the preset condition that meets includes:
The specified target recognized in acquired image has carried out preset attitudes vibration;
And/or
The changed changing value of light recognized in acquired image is more than the first preset value;
And/or
It recognizes the background environment in acquired image and preset variation has occurred.
Optionally, the specified attribute of the three-dimensional special efficacy model includes below one or more:
The textures texture of the three-dimensional special efficacy model;
The color of the three-dimensional special efficacy model;
The skeletal structure of the three-dimensional special efficacy model.
According to another aspect of the present invention, a kind of device of video processing is provided, wherein the device includes:
Recognition unit is suitable for obtaining the video of video collector acquisition, the specified target in the acquired video of identification;
Model selection unit, suitable for when identifying multiple specified targets from the video, from three-dimensional special efficacy model library It is middle to choose multiple and different three-dimensional special efficacy models;
Model loading unit, suitable for by choose multiple and different three-dimensional special efficacy models be loaded into respectively identify it is multiple In specified target.
Optionally,
The model selection unit, suitable for obtaining the specified attribute of each specified target identified respectively;From three-dimensional special efficacy It is chosen in model library and the matched three-dimensional special efficacy model of the specified attribute of each specified target obtained;
The model loading unit, suitable for the specified attribute according to each specified target identified of acquisition, by selection Multiple and different three-dimensional special efficacy models are loaded into respectively in corresponding specified target.
Optionally, the specified attribute of the specified target includes:
The gender of specified target and/or age.
Optionally,
The model selection unit is adapted to provide for the selection control of three-dimensional special efficacy model;In response to three-dimensional special efficacy model Selection operation, corresponding three-dimensional special efficacy model is selected from three-dimensional special efficacy model library.
Optionally,
The model loading unit, suitable for showing the multiple and different three-dimensional special efficacy models selected;In response to choosing The drag operation of the three-dimensional special efficacy model gone out determines the correspondence of each three-dimensional special efficacy model and each specified target identified; According to the correspondence, multiple and different three-dimensional special efficacy models of selection are loaded into respectively in corresponding specified target.
Optionally, which further comprises:
Attribute transformation unit, suitable for when meeting preset condition, converting described three in the specified target in the video Tie up the specified attribute of special efficacy model.
Optionally, the preset condition that meets includes:
The specified target recognized in acquired image has carried out preset attitudes vibration;
And/or
The changed changing value of light recognized in acquired image is more than the first preset value;
And/or
It recognizes the background environment in acquired image and preset variation has occurred.
Optionally, the specified attribute of the three-dimensional special efficacy model includes below one or more:
The textures texture of the three-dimensional special efficacy model;
The color of the three-dimensional special efficacy model;
The skeletal structure of the three-dimensional special efficacy model.
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, the video of video collector acquisition, the finger in the acquired video of identification are obtained It sets the goal;When identifying multiple specified targets from video, it is special that multiple and different three-dimensionals is chosen from three-dimensional special efficacy model library Imitate model;Multiple and different three-dimensional special efficacy models of selection are loaded into respectively in the multiple specified targets identified.Pass through this Technical solution can be that multiple specified targets load different three-dimensional special efficacy moulds respectively when having multiple specified targets in video Type is met the needs of users, and is increased the interest of video processing, is enhanced 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 the method for video processing according to an embodiment of the invention;
Fig. 2 shows the structural schematic diagrams of the device of video according to an embodiment of the invention processing;
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 the method for video processing according to an embodiment of the invention.As shown in Figure 1, This method includes:
Step S110 obtains the video of video collector acquisition, the specified target in the acquired video of identification.
In the present embodiment, specified target can be the certain objects or artificiality in face, animal, plant, nature Etc., identify that the specified target in video may be used the existing corresponding recognizer for specifying target and be identified, such as Machine learning model.In practical applications, user can carry out the selection of specified target according to demand, for example, in display interface The selection control of target is specified in middle display, and when user selects one of control, specified mesh accordingly is just identified from video Mark just identifies face for example, when user selects face control from video.
Step S120, when identifying multiple specified targets from video, chosen from three-dimensional special efficacy model library it is multiple not Same three-dimensional special efficacy model.
When identifying a specified target from video, existing technology may be used and specify target load corresponding this Three-dimensional special efficacy model.In the present embodiment, it is when identifying multiple specified targets from video, in order to more to what is identified A specified target loads different three-dimensional special efficacy models, and it is special that corresponding multiple and different three-dimensional is chosen from three-dimensional special efficacy model library Imitate model.
Multiple and different three-dimensional special efficacy models of selection are loaded into the multiple specified targets identified by step S130 respectively On.
For example, specified target is face, three faces are identified from video, then just choose three from three-dimensional special efficacy model A different three-dimensional special efficacy model is deer head threedimensional model, Santa Claus's head threedimensional model and magic cap three-dimensional mould respectively These three three-dimensional special efficacy models are then loaded into three people identified on the face by type respectively, and e.g., face 1 loads the three-dimensional mould of deer head Type, face 2 load Santa Claus's head threedimensional model, face 3 loads magic cap threedimensional model.
It should be noted that special efficacy model here is three-dimensional special efficacy model, and after being loaded into specified target, Ke Yisui The change of posture, angle of specified target etc. and change the posture of its own, angle etc..
As it can be seen that can be that multiple specified targets load respectively when having multiple specified targets in video through this embodiment Different three-dimensional special efficacy models, meets the needs of users, and increases the interest of video processing, enhances the usage experience of user.
In one embodiment of the invention, multiple three-dimensional special efficacys are chosen from three-dimensional special efficacy model library in step S120 Model includes:The specified attribute of each specified target identified is obtained respectively;It is chosen from three-dimensional special efficacy model library and acquisition The matched three-dimensional special efficacy model of specified attribute of each specified target.
Being loaded into multiple and different three-dimensional special efficacy models of selection respectively in step S130 is identified multiple specified Include in target:According to the specified attribute for each specified target of acquisition identified, by multiple and different three-dimensional special efficacys of selection Model is loaded into respectively in corresponding specified target.
The attribute of each specified target is not consistent, and in the present embodiment, is chosen in being lost from three-dimensional special efficacy model Three-dimensional special efficacy model is matched with the specified attribute of each specified target, in this manner it is possible to so that the three-dimensional special efficacy mould selected The attribute of type and specified target matches, and further increases the usage experience of user.In the present embodiment, each specified target is obtained Specified attribute, can be by specifying the specified attribute recognizer of target to realize that each specified attribute recognizer can be advance It is obtained by machine learning.
After selecting three-dimensional special efficacy model matched with the specified attribute of each specified target, will choose three are needed Special efficacy model is corresponding is loaded into specified target for dimension.For example, the specified target 1 got, specified target 2, specified target 3 Specified attribute is attribute 1, attribute 2 and attribute 3 respectively, and the corresponding matched three-dimensional special efficacy model of selection is model 1, model 2 and mould Type 3, wherein model 1 corresponds to attribute 1, model 2 corresponds to attribute 3, model 3 corresponds to attribute 2, then in load, model 1 is added It carries and specifies in target 1, model 2 is loaded into specified target 3, and model 3 is loaded into specified target 2.
Specifically, the specified attribute of above-mentioned specified target includes:The gender of specified target and/or age.
In the present embodiment, it is face to specify target, and gender and/or the age of the face can be obtained by face, that When choosing three-dimensional special efficacy model from three-dimensional special efficacy model library, chosen according to the gender of specified target and/age.
For example, identifying two faces in video, the gender of the face 1 of acquisition is man, and the age is 38;The face of acquisition 2 gender is female, and the age is 8.Then when choosing three-dimensional special efficacy model, according to the attribute of the face of acquisition, it can obtain and people The corresponding three-dimensional special efficacy model of face 1 is Santa Claus's three-dimensional special efficacy model, fawn three-dimensional special efficacy model corresponding with face 2. When load because Santa Claus's three-dimensional special efficacy Model Matching be man, 38 years old, then by Santa Claus's three-dimensional special efficacy model load Onto face 1;Fawn three-dimensional special efficacy Model Matching be female, 8 years old, then fawn three-dimensional special efficacy model is loaded on face 2.
In one embodiment of the invention, method shown in FIG. 1 further comprises:The selection of three-dimensional special efficacy model is provided Control.
Then multiple and different three-dimensional special efficacy model of being chosen from three-dimensional special efficacy model library in step S120 includes:In response to Selection operation to three-dimensional special efficacy model selects corresponding three-dimensional special efficacy model from three-dimensional special efficacy model library.
In the above-described embodiment, it is according to the selection for specifying the specified attribute of target to carry out three-dimensional special efficacy model.In order to The usage experience of user is further increased, in the present embodiment, user can voluntarily select three-dimensional special efficacy model, specifically be to provide Each three-dimensional special efficacy model in three-dimensional special efficacy model library is included in interface, for user by the selection control of three-dimensional special efficacy model It is chosen, according to the selection operation of user, therefrom selects corresponding three-dimensional special efficacy model, the three-dimensional that then will be selected again Special efficacy model is loaded into specified target.
For example, user clicks the selection control for choosing control and three-dimensional special efficacy model 2 for having chosen three-dimensional special efficacy model 1, Three-dimensional special efficacy model 1 and three-dimensional special efficacy model 2, the three-dimensional that then will be selected again are so just chosen from three-dimensional special efficacy model library Special efficacy model is loaded into respectively in specified target 1 and specified target 2.
It, can also basis when the selection operation according to user can be loaded at random after selecting three-dimensional special efficacy model The correspondence that user specifies loads.Further, multiple and different three-dimensional special efficacy moulds by selection in step S130 Type is loaded into respectively in the multiple specified targets identified:Show the multiple and different three-dimensional special efficacy models selected;It rings Ying Yu determines each three-dimensional special efficacy model and each specified target identified to the drag operation of the three-dimensional special efficacy model selected Correspondence;According to correspondence, multiple and different three-dimensional special efficacy models of selection are loaded into corresponding specified target respectively On.
In the present embodiment, after user is according to the three-dimensional special efficacy model for choosing control selection needs, it is possible to specify identification The correspondence of the specified target gone out and three-dimensional special efficacy model, needs user to carry out correspondence by way of dragging herein Determination.In one example, three-dimensional special efficacy model 1, three-dimensional special efficacy model 2 and three-dimensional are selected according to the selection operation of user Special efficacy model 3, and include user's long-press in interface by three-dimensional special efficacy model 1, three-dimensional special efficacy model 2 and three-dimensional special efficacy model 3 Three-dimensional special efficacy model 1, and three-dimensional special efficacy model 1 is drawn at the specified target 3 identified, it is determined that three-dimensional special efficacy model 1 Corresponding specified target 3;User's long-press three-dimensional special efficacy model 2, and three-dimensional special efficacy model 2 is drawn to the specified target 2 identified Place, it is determined that three-dimensional special efficacy model 2, which corresponds to, specifies target 2;User's long-press three-dimensional special efficacy model 3, and three-dimensional special efficacy model 3 is dragged It drags to the specified target 1 identified, it is determined that three-dimensional special efficacy model 3, which corresponds to, specifies target 1.It, will be three-dimensional special when so loading Effect model 1 is loaded onto in specified target 3, three-dimensional special efficacy model 2 is loaded onto in specified target 2, loads three-dimensional special efficacy model 3 To specified target 1.
In one embodiment of the invention, method shown in FIG. 1 further comprises:When meeting preset condition, transformation The specified attribute of three-dimensional special efficacy model in specified target in video.
In practical applications, after user is image or the upper special efficacy of video load, if it is desired to the special efficacy loaded is replaced, Special efficacy can only be reselected and reloaded, be easy to influence loading velocity, especially in the case where special effects data is larger, special efficacy The rate of replacement is low, can not complete the timely replacement of special efficacy, and reduce user uses experience.
In the present embodiment, when user needs replacing the three-dimensional special efficacy model loaded, default item accordingly can be triggered Part, such as change posture, preset condition is triggered, and changes the specified of the specified three-dimensional special efficacy model being loaded into specified target Attribute reaches the requirement that user replaces three-dimensional special efficacy model to change the bandwagon effect of specified three-dimensional special efficacy model, but at this It is not that the specified three-dimensional special efficacy model that will load is more sliding for another three-dimensional special efficacy model in embodiment, only to referring to Determine attribute to be converted, the data content that transformation specified attribute is rendered, be needed than replacing entire three-dimensional special efficacy model The data content loaded will lack, so, for the replacement of more three-dimensional special efficacy model, it is possible to reduce the data of load Content improves and replaces speed, meets the needs of user replaces special efficacy model.
Here the specified attribute of the three-dimensional special efficacy model in the specified target in transformation video can be in video The specified attribute of three-dimensional special efficacy model in multiple specified targets is converted.
As it can be seen that through this embodiment, when carrying out special effect transforming, transformation be three-dimensional special efficacy model specified attribute, and Non- is to replace three-dimensional special efficacy model, can also reach the bandwagon effect for replacing the three-dimensional special efficacy model loaded, meet user's The replacement demand of special efficacy model, and the data content of load is reduced, the rate of special efficacy model replacement is improved, special efficacy model is completed Timely replacement, increase video processing interest, improve the usage experience of user.
In one embodiment of invention, the above-mentioned preset condition that meets includes:Recognize the finger in acquired image It sets the goal and has carried out preset attitudes vibration;And/or the changed changing value of light recognized in acquired image is big In the first preset value;And/or preset variation has occurred in the background environment recognized in acquired image.
When user wants to replace the three-dimensional special efficacy model loaded, corresponding preset condition can be triggered, for example, carrying out pre- If attitudes vibration, such as people lift hand, do certain gestures, grimace, opening one's mouth/shutting up, close one eye action variation;Again Such as, when the outdoor environment for becoming carrying blue sky and white cloud from indoor environment.Above-mentioned each preset condition can be used alone, and also may be used To be used in combination.Through this embodiment, user can carry out the replacement of three-dimensional special efficacy model according to the demand of oneself, that is, carry out pre- If attitudes vibration;In order to adapt to different light or environment, auto-changing can also be carried out, increases the three-dimensional special efficacy mould of the load The diversity of type further increases the usage experience of user.
For example, in specified target be the three-dimensional special efficacy model of deer head just, when the attitudes vibration that specified target is shaken the head, The color of the three-dimensional special efficacy model of deer head on video middle finger being set the goal becomes white from Current Yellow.
Specifically, the above-mentioned changed changing value of the light recognized in acquired image is more than the first preset value Including:The gray value for obtaining each pixel of acquired image, calculates being averaged for all pixels point of acquired image Gray value;When the changed changing value of the average gray value of calculating is more than the first preset value, it is determined that recognize and acquired Image in light change.
Picture gray scale and luminous intensity have proportional relation, i.e. the most direct embodiment of the variation of light in image is the picture of image On the gray value of vegetarian refreshments.In the present embodiment, image is judged by the variation of the average gray value of the pixel of acquisition image Light variation.For example, the first preset value is 100, the average gray value of the pixel in the video of acquisition is from 50 variations 170, then changing value is 120, is more than the first preset value 100, then it is assumed that be to meet preset condition.
In one embodiment of the invention, the specified attribute of above-mentioned three-dimensional special efficacy model includes below a kind of or more Kind:The textures texture of three-dimensional special efficacy model;The color of three-dimensional special efficacy model;The skeletal structure of three-dimensional special efficacy model.
In the present embodiment, after meeting preset condition, the note figure texture of specified three-dimensional special efficacy model is converted; And/or color is changed;And/or skeletal structure is changed.
For example, when the environment in video changes to the outdoor environment with blue sky and white cloud from interior, three can will be specified The note figure texture variations for tieing up special efficacy model are the white alternate texture of the indigo plant close with blue sky and white cloud.
Some has corresponding skeletal structure in three-dimensional special efficacy model, can change three-dimensional by the change of skeletal structure The form of special efficacy model, in the present embodiment, after meeting preset condition, thus it is possible to vary the category of the skeletal structure of three-dimensional special efficacy model Property is converted.For example, changing the nose skeletal structure in head portrait threedimensional model, with the tall and straight degree etc. for changing nose.
In one embodiment of the invention, the specified attribute of above-mentioned specified three-dimensional special efficacy model includes specified three-dimensional spy Imitate the color of model.
The color of the specified three-dimensional special efficacy model in specified target in above-mentioned transformation video includes:What acquisition was acquired Background color in image;It is the color consistent with the background color of acquisition by the colour switching of specified three-dimensional special efficacy model, or The colour switching of specified three-dimensional special efficacy model is the color opposite with the background color of acquisition by person;Wherein, with the background of acquisition The opposite color of color refers to being more than the color of the second preset value with the color difference of background color.
In the present embodiment, when meeting preset condition, the color of the three-dimensional special efficacy model in specified target can be become To be consistent with background color, to reach the bandwagon effect of chameleon;It can also make the color and background face of three-dimensional special efficacy model The comparison of color is stronger.For example, the background color obtained is green, then the color of specified three-dimensional special efficacy model can be become red The color of specified three-dimensional special efficacy model is also become green by color, the latter.
In one embodiment of the invention, the specified attribute of above-mentioned specified three-dimensional special efficacy model includes specified three-dimensional spy Imitate the skeletal structure of model.
The skeletal structure of the specified three-dimensional special efficacy model in specified target in above-mentioned transformation video includes:Three will be specified The bony segment structure of dimension special efficacy model is transformed to the second skeletal structure from the first skeletal structure.
In the skeletal structure variation for carrying out specified three-dimensional special efficacy model, whole transformation can be carried out, for example, specified three Dimension special efficacy model is the chimera three-dimensional special efficacy model of docility, after meeting preset condition, changes the bone of chimera as a result, being transformed to roar The chimera three-dimensional special efficacy model of heavy breathing.
In the present embodiment, the transformation that can be achieved on the bony segment structure to specified three-dimensional special efficacy model, by the portion Skeletal structure is divided to be transformed to the second skeletal structure from the first skeletal structure.
Preferably, when the preset condition of satisfaction refers to that the part to set the goal is blocked, by specified three-dimensional special efficacy model Bony segment structure is transformed to the second skeletal structure from the first skeletal structure:By specified three-dimensional special efficacy model and specified target The corresponding bony segment structure in the part that is blocked be transformed to the second skeletal structure from the first skeletal structure.
In the present embodiment, the variation for carrying out skeletal structure can be carried out the moment being blocked in specified target, also may be used To be the moment progress for the state for becoming not being blocked from the state being blocked in specified target.
In one example, specified target is face, and the three-dimensional special efficacy model of load is simple eye little Huang people's three-dimensional special efficacy mould Type becomes smaller the skeletal structure of the eyes of simple eye little Huang people's three-dimensional special efficacy model, i.e. eye when the moment that the eyes of face are blocked Eyeball becomes smaller, and gravity treatment renders eye portion, and after the eyes of face become the state not being blocked, what user saw is then than original The small simple eye little Huang people's three-dimensional special efficacy model display effect of the eyes of beginning;Or when face eyes from be blocked to not by The skeletal structure of the eyes of simple eye little Huang people's three-dimensional special efficacy model is become two eyes by the moment blocked from an eyes, and Gravity treatment renders eye portion, and what user saw is then the bandwagon effect of eyes little Huang people's three-dimensional special efficacy model.
It should be noted that the difference of the preset condition met, converted also it is different (the different specified attribute of transformation or The different transform effects of the same specified attribute of person), specific transformation rule can be set in advance in configuration file.
Fig. 2 shows the structural schematic diagrams of the device of video according to an embodiment of the invention processing.As shown in Fig. 2, The video processing device 200 include:
Recognition unit 210 is suitable for obtaining the video of video collector acquisition, the specified mesh in the acquired video of identification Mark.
In the present embodiment, specified target can be the certain objects or artificiality in face, animal, plant, nature Etc., identify that the specified target in video may be used the existing corresponding recognizer for specifying target and be identified, such as Machine learning model.In practical applications, user can carry out the selection of specified target according to demand, for example, in display interface The selection control of target is specified in middle display, and when user selects one of control, specified mesh accordingly is just identified from video Mark just identifies face for example, when user selects face control from video.
Model selection unit 220, suitable for when identifying multiple specified targets from video, from three-dimensional special efficacy model library Choose multiple and different three-dimensional special efficacy models.
When identifying a specified target from video, existing technology may be used and specify target load corresponding this Three-dimensional special efficacy model.In the present embodiment, it is when identifying multiple specified targets from video, in order to more to what is identified A specified target loads different three-dimensional special efficacy models, and it is special that corresponding multiple and different three-dimensional is chosen from three-dimensional special efficacy model library Imitate model.
Model loading unit 230 is identified suitable for being loaded into the multiple and different three-dimensional special efficacy models chosen respectively In multiple specified targets.
For example, specified target is face, three faces are identified from video, then just choose three from three-dimensional special efficacy model A different three-dimensional special efficacy model is deer head threedimensional model, Santa Claus's head threedimensional model and magic cap three-dimensional mould respectively These three three-dimensional special efficacy models are then loaded into three people identified on the face by type respectively, and e.g., face 1 loads the three-dimensional mould of deer head Type, face 2 load Santa Claus's head threedimensional model, face 3 loads magic cap threedimensional model.
It should be noted that special efficacy model here is three-dimensional special efficacy model, and after being loaded into specified target, Ke Yisui The change of posture, angle of specified target etc. and change the posture of its own, angle etc..
As it can be seen that can be that multiple specified targets load respectively when having multiple specified targets in video through this embodiment Different three-dimensional special efficacy models, meets the needs of users, and increases the interest of video processing, enhances the usage experience of user.
In one embodiment of the invention, model selection unit 220, suitable for obtaining each specified target identified respectively Specified attribute;It is chosen from three-dimensional special efficacy model library and the matched three-dimensional special efficacy mould of the specified attribute of each specified target obtained Type.
Then model loading unit 230, suitable for the specified attribute according to each specified target identified of acquisition, by selection Multiple and different three-dimensional special efficacy models are loaded into respectively in corresponding specified target.
The attribute of each specified target is not consistent, and in the present embodiment, is chosen in being lost from three-dimensional special efficacy model Three-dimensional special efficacy model is matched with the specified attribute of each specified target, in this manner it is possible to so that the three-dimensional special efficacy mould selected The attribute of type and specified target matches, and further increases the usage experience of user.In the present embodiment, each specified target is obtained Specified attribute, can be by specifying the specified attribute recognizer of target to realize that each specified attribute recognizer can be advance It is obtained by machine learning.
After selecting three-dimensional special efficacy model matched with the specified attribute of each specified target, will choose three are needed Special efficacy model is corresponding is loaded into specified target for dimension.For example, the specified target 1 got, specified target 2, specified target 3 Specified attribute is attribute 1, attribute 2 and attribute 3 respectively, and the corresponding matched three-dimensional special efficacy model of selection is model 1, model 2 and mould Type 3, wherein model 1 corresponds to attribute 1, model 2 corresponds to attribute 3, model 3 corresponds to attribute 2, then in load, model 1 is added It carries and specifies in target 1, model 2 is loaded into specified target 3, and model 3 is loaded into specified target 2.
Specifically, the specified attribute of above-mentioned specified target includes:The gender of specified target and/or age.
In the present embodiment, it is face to specify target, and gender and/or the age of the face can be obtained by face, that When choosing three-dimensional special efficacy model from three-dimensional special efficacy model library, chosen according to the gender of specified target and/age.
For example, identifying two faces in video, the gender of the face 1 of acquisition is man, and the age is 38;The face of acquisition 2 gender is female, and the age is 8.Then when choosing three-dimensional special efficacy model, according to the attribute of the face of acquisition, it can obtain and people The corresponding three-dimensional special efficacy model of face 1 is Santa Claus's three-dimensional special efficacy model, fawn three-dimensional special efficacy model corresponding with face 2. When load because Santa Claus's three-dimensional special efficacy Model Matching be man, 38 years old, then by Santa Claus's three-dimensional special efficacy model load Onto face 1;Fawn three-dimensional special efficacy Model Matching be female, 8 years old, then fawn three-dimensional special efficacy model is loaded on face 2.
In one embodiment of the invention, model selection unit 220 is adapted to provide for the selection control of three-dimensional special efficacy model Part;In response to the selection operation to three-dimensional special efficacy model, corresponding three-dimensional special efficacy model is selected from three-dimensional special efficacy model library.
In the above-described embodiment, it is according to the selection for specifying the specified attribute of target to carry out three-dimensional special efficacy model.In order to The usage experience of user is further increased, in the present embodiment, user can voluntarily select three-dimensional special efficacy model, specifically be to provide Each three-dimensional special efficacy model in three-dimensional special efficacy model library is included in interface, for user by the selection control of three-dimensional special efficacy model It is chosen, according to the selection operation of user, therefrom selects corresponding three-dimensional special efficacy model, the three-dimensional that then will be selected again Special efficacy model is loaded into specified target.
For example, user clicks the selection control for choosing control and three-dimensional special efficacy model 2 for having chosen three-dimensional special efficacy model 1, Three-dimensional special efficacy model 1 and three-dimensional special efficacy model 2, the three-dimensional that then will be selected again are so just chosen from three-dimensional special efficacy model library Special efficacy model is loaded into respectively in specified target 1 and specified target 2.
It, can also basis when the selection operation according to user can be loaded at random after selecting three-dimensional special efficacy model The correspondence that user specifies loads.Further, model loading unit 230 selects multiple and different suitable for display Three-dimensional special efficacy model;In response to the drag operation to the three-dimensional special efficacy model selected, determines each three-dimensional special efficacy model and know The correspondence for each specified target not gone out;According to correspondence, multiple and different three-dimensional special efficacy models of selection are added respectively It is downloaded in corresponding specified target.
In the present embodiment, after user is according to the three-dimensional special efficacy model for choosing control selection needs, it is possible to specify identification The correspondence of the specified target gone out and three-dimensional special efficacy model, needs user to carry out correspondence by way of dragging herein Determination.In one example, three-dimensional special efficacy model 1, three-dimensional special efficacy model 2 and three-dimensional are selected according to the selection operation of user Special efficacy model 3, and include user's long-press in interface by three-dimensional special efficacy model 1, three-dimensional special efficacy model 2 and three-dimensional special efficacy model 3 Three-dimensional special efficacy model 1, and three-dimensional special efficacy model 1 is drawn at the specified target 3 identified, it is determined that three-dimensional special efficacy model 1 Corresponding specified target 3;User's long-press three-dimensional special efficacy model 2, and three-dimensional special efficacy model 2 is drawn to the specified target 2 identified Place, it is determined that three-dimensional special efficacy model 2, which corresponds to, specifies target 2;User's long-press three-dimensional special efficacy model 3, and three-dimensional special efficacy model 3 is dragged It drags to the specified target 1 identified, it is determined that three-dimensional special efficacy model 3, which corresponds to, specifies target 1.It, will be three-dimensional special when so loading Effect model 1 is loaded onto in specified target 3, three-dimensional special efficacy model 2 is loaded onto in specified target 2, loads three-dimensional special efficacy model 3 To specified target 1.
In one embodiment of the invention, device shown in Fig. 2 further comprises:
Attribute transformation unit, suitable for when meeting preset condition, converting the three-dimensional special efficacy mould in the specified target in video The specified attribute of type.
In practical applications, after user is image or the upper special efficacy of video load, if it is desired to the special efficacy loaded is replaced, Special efficacy can only be reselected and reloaded, be easy to influence loading velocity, especially in the case where special effects data is larger, special efficacy The rate of replacement is low, can not complete the timely replacement of special efficacy, and reduce user uses experience.
In the present embodiment, when user needs replacing the three-dimensional special efficacy model loaded, default item accordingly can be triggered Part, such as change posture, preset condition is triggered, and changes the specified of the specified three-dimensional special efficacy model being loaded into specified target Attribute reaches the requirement that user replaces three-dimensional special efficacy model to change the bandwagon effect of specified three-dimensional special efficacy model, but at this It is not that the specified three-dimensional special efficacy model that will load is more sliding for another three-dimensional special efficacy model in embodiment, only to referring to Determine attribute to be converted, the data content that transformation specified attribute is rendered, be needed than replacing entire three-dimensional special efficacy model The data content loaded will lack, so, for the replacement of more three-dimensional special efficacy model, it is possible to reduce the data of load Content improves and replaces speed, meets the needs of user replaces special efficacy model.
Here the specified attribute of the three-dimensional special efficacy model in the specified target in transformation video can be in video The specified attribute of three-dimensional special efficacy model in multiple specified targets is converted.
As it can be seen that through this embodiment, when carrying out special effect transforming, transformation be three-dimensional special efficacy model specified attribute, and Non- is to replace three-dimensional special efficacy model, can also reach the bandwagon effect for replacing the three-dimensional special efficacy model loaded, meet user's The replacement demand of special efficacy model, and the data content of load is reduced, the rate of special efficacy model replacement is improved, special efficacy model is completed Timely replacement, increase video processing interest, improve the usage experience of user.
In one embodiment of the invention, the above-mentioned preset condition that meets includes:It recognizes in acquired image Specified target has carried out preset attitudes vibration;And/or recognize the changed changing value of light in acquired image More than the first preset value;And/or preset variation has occurred in the background environment recognized in acquired image.
When user wants to replace the three-dimensional special efficacy model loaded, corresponding preset condition can be triggered, for example, carrying out pre- If attitudes vibration, such as people lift hand, do certain gestures, grimace, opening one's mouth/shutting up, close one eye action variation;Again Such as, when the outdoor environment for becoming carrying blue sky and white cloud from indoor environment.Above-mentioned each preset condition can be used alone, and also may be used To be used in combination.Through this embodiment, user can carry out the replacement of three-dimensional special efficacy model according to the demand of oneself, that is, carry out pre- If attitudes vibration;In order to adapt to different light or environment, auto-changing can also be carried out, increases the three-dimensional special efficacy mould of the load The diversity of type further increases the usage experience of user.
For example, in specified target be the three-dimensional special efficacy model of deer head just, when the attitudes vibration that specified target is shaken the head, The color of the three-dimensional special efficacy model of deer head on video middle finger being set the goal becomes white from Current Yellow.
Specifically, above-mentioned attribute transformation unit is suitable for obtaining the gray value of each pixel of acquired image, meter Calculate the average gray value of all pixels point of acquired image;When the changed changing value of the average gray value of calculating is more than When the first preset value, it is determined that the light recognized in acquired image changes.
Picture gray scale and luminous intensity have proportional relation, i.e. the most direct embodiment of the variation of light in image is the picture of image On the gray value of vegetarian refreshments.In the present embodiment, image is judged by the variation of the average gray value of the pixel of acquisition image Light variation.For example, the first preset value is 100, the average gray value of the pixel in the video of acquisition is from 50 variations 170, then changing value is 120, is more than the first preset value 100, then it is assumed that be to meet preset condition.
In one embodiment of the invention, the specified attribute of above-mentioned three-dimensional special efficacy model includes below a kind of or more Kind:The textures texture of three-dimensional special efficacy model;The color of three-dimensional special efficacy model;The skeletal structure of three-dimensional special efficacy model.
In the present embodiment, after meeting preset condition, the note figure texture of specified three-dimensional special efficacy model is converted; And/or color is changed;And/or skeletal structure is changed.
For example, when the environment in video changes to the outdoor environment with blue sky and white cloud from interior, three can will be specified The note figure texture variations for tieing up special efficacy model are the white alternate texture of the indigo plant close with blue sky and white cloud.
Some has corresponding skeletal structure in three-dimensional special efficacy model, can change three-dimensional by the change of skeletal structure The form of special efficacy model, in the present embodiment, after meeting preset condition, thus it is possible to vary the category of the skeletal structure of three-dimensional special efficacy model Property is converted.For example, changing the nose skeletal structure in head portrait threedimensional model, with the tall and straight degree etc. for changing nose.
In one embodiment of the invention, the specified attribute of above-mentioned specified three-dimensional special efficacy model includes specified three-dimensional spy Imitate the color of model.
Above-mentioned attribute transformation unit is suitable for obtaining the background color in acquired image;By specified three-dimensional special efficacy mould The colour switching of type is the color consistent with the background color of acquisition, alternatively, being by the colour switching of specified three-dimensional special efficacy model The color opposite with the background color of acquisition;Wherein, the color opposite with the background color of acquisition refers to the face with background color Value of chromatism is more than the color of the second preset value.
In the present embodiment, when meeting preset condition, the color of the three-dimensional special efficacy model in specified target can be become To be consistent with background color, to reach the bandwagon effect of chameleon;It can also make the color and background face of three-dimensional special efficacy model The comparison of color is stronger.For example, the background color obtained is green, then the color of specified three-dimensional special efficacy model can be become red The color of specified three-dimensional special efficacy model is also become green by color, the latter.
In one embodiment of the invention, the specified attribute of above-mentioned specified three-dimensional special efficacy model includes specified three-dimensional spy Imitate the skeletal structure of model.
Above-mentioned attribute transformation unit is suitable for the bony segment structure of specified three-dimensional special efficacy model from the first skeletal structure It is transformed to the second skeletal structure.
In the skeletal structure variation for carrying out specified three-dimensional special efficacy model, whole transformation can be carried out, for example, specified three Dimension special efficacy model is the chimera three-dimensional special efficacy model of docility, after meeting preset condition, changes the bone of chimera as a result, being transformed to roar The chimera three-dimensional special efficacy model of heavy breathing.
In the present embodiment, the transformation that can be achieved on the bony segment structure to specified three-dimensional special efficacy model, by the portion Skeletal structure is divided to be transformed to the second skeletal structure from the first skeletal structure.
Preferably, above-mentioned attribute transformation unit, suitable for referring to that the part to set the goal is blocked when the preset condition met When, specified three-dimensional special efficacy model bony segment structure corresponding with the part that is blocked of specified target is become from the first skeletal structure It is changed to the second skeletal structure.
In the present embodiment, the variation for carrying out skeletal structure can be carried out the moment being blocked in specified target, also may be used To be the moment progress for the state for becoming not being blocked from the state being blocked in specified target.
In one example, specified target is face, and the three-dimensional special efficacy model of load is simple eye little Huang people's three-dimensional special efficacy mould Type becomes smaller the skeletal structure of the eyes of simple eye little Huang people's three-dimensional special efficacy model, i.e. eye when the moment that the eyes of face are blocked Eyeball becomes smaller, and gravity treatment renders eye portion, and after the eyes of face become the state not being blocked, what user saw is then than original The small simple eye little Huang people's three-dimensional special efficacy model display effect of the eyes of beginning;Or when face eyes from be blocked to not by The skeletal structure of the eyes of simple eye little Huang people's three-dimensional special efficacy model is become two eyes by the moment blocked from an eyes, and Gravity treatment renders eye portion, and what user saw is then the bandwagon effect of eyes little Huang people's three-dimensional special efficacy model.
It should be noted that the difference of the preset condition met, converted also it is different (the different specified attribute of transformation or The different transform effects of the same specified attribute of person), specific transformation rule can be set in advance in configuration file.
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 that the video according to figure 1 and its each embodiment is handled
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 The method of video processing 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 The method for applying the video processing 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.
In conclusion according to the technique and scheme of the present invention, obtaining the video of video collector acquisition, identify that is acquired regards Specified target in frequency;When identifying multiple specified targets from video, chosen from three-dimensional special efficacy model library multiple and different Three-dimensional special efficacy model;Multiple and different three-dimensional special efficacy models of selection are loaded into the multiple specified targets identified respectively On.Can be that multiple specified targets load different three respectively when having multiple specified targets in video by the technical program Special efficacy model is tieed up, is met the needs of users, increases the interest of video processing, 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 that device, the electronics of video processing according to the ... of the embodiment of the present invention are set The some or all functions of some or all components in standby and computer readable storage medium.The present invention can also realize It is some or all equipment or program of device for executing method as described herein (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 There are one or multiple signals form.Such signal can be downloaded from internet website and be obtained, or in carrier signal Upper offer, or provide 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 methods of video processing, wherein this method includes:
Obtain the video of video collector acquisition, the specified target in the acquired video of identification;
When identifying multiple specified targets from the video, multiple and different three are chosen from three-dimensional special efficacy model library Tie up special efficacy model;
Multiple and different three-dimensional special efficacy models of selection are loaded into respectively in the multiple specified targets identified.
A2, the method as described in A1, wherein described that multiple three-dimensional special efficacy model packets are chosen from three-dimensional special efficacy model library It includes:
The specified attribute of each specified target identified is obtained respectively;
It is chosen from three-dimensional special efficacy model library and the matched three-dimensional special efficacy model of the specified attribute of each specified target obtained;
Described multiple and different three-dimensional special efficacy models of selection are loaded into respectively in the multiple specified targets identified is wrapped It includes:
According to the specified attribute for each specified target of acquisition identified, by multiple and different three-dimensional special efficacy models of selection It is loaded into respectively in corresponding specified target.
A3, the method as described in A2, wherein the specified attribute of the specified target includes:
The gender of specified target and/or age.
A4, the method as described in A1, wherein this method further comprises:
The selection control of three-dimensional special efficacy model is provided;
It is described to choose multiple and different three-dimensional special efficacy models from three-dimensional special efficacy model library and include:
In response to the selection operation to three-dimensional special efficacy model, corresponding three-dimensional special efficacy is selected from three-dimensional special efficacy model library Model.
A5, the method as described in A4, wherein described that multiple and different three-dimensional special efficacy models of selection are loaded into knowledge respectively Include in the multiple specified targets not gone out:
Show the multiple and different three-dimensional special efficacy models selected;
In response to the drag operation to the three-dimensional special efficacy model selected, determine each three-dimensional special efficacy model with identify it is each The correspondence of specified target;
According to the correspondence, multiple and different three-dimensional special efficacy models of selection are loaded into corresponding specified mesh respectively It puts on.
A6, the method as described in A1, wherein this method further comprises:
When meeting preset condition, the specified category of the three-dimensional special efficacy model in the specified target in the video is converted Property.
A7, the method as described in A6, wherein the preset condition that meets includes:
The specified target recognized in acquired image has carried out preset attitudes vibration;
And/or
The changed changing value of light recognized in acquired image is more than the first preset value;
And/or
It recognizes the background environment in acquired image and preset variation has occurred.
A8, the method as described in A6, wherein the specified attribute of the three-dimensional special efficacy model includes below a kind of or more Kind:
The textures texture of the three-dimensional special efficacy model;
The color of the three-dimensional special efficacy model;
The skeletal structure of the three-dimensional special efficacy model.
The invention also discloses B9, a kind of devices of video processing, wherein the device includes:
Recognition unit is suitable for obtaining the video of video collector acquisition, the specified target in the acquired video of identification;
Model selection unit, suitable for when identifying multiple specified targets from the video, from three-dimensional special efficacy model library It is middle to choose multiple and different three-dimensional special efficacy models;
Model loading unit, suitable for by choose multiple and different three-dimensional special efficacy models be loaded into respectively identify it is multiple In specified target.
B10, the device as described in B9, wherein
The model selection unit, suitable for obtaining the specified attribute of each specified target identified respectively;From three-dimensional special efficacy It is chosen in model library and the matched three-dimensional special efficacy model of the specified attribute of each specified target obtained;
The model loading unit, suitable for the specified attribute according to each specified target identified of acquisition, by selection Multiple and different three-dimensional special efficacy models are loaded into respectively in corresponding specified target.
B11, the device as described in B10, wherein the specified attribute of the specified target includes:
The gender of specified target and/or age.
B12, the device as described in B9, wherein
The model selection unit is adapted to provide for the selection control of three-dimensional special efficacy model;In response to three-dimensional special efficacy model Selection operation, corresponding three-dimensional special efficacy model is selected from three-dimensional special efficacy model library.
B13, the device as described in B12, wherein
The model loading unit, suitable for showing the multiple and different three-dimensional special efficacy models selected;In response to choosing The drag operation of the three-dimensional special efficacy model gone out determines the correspondence of each three-dimensional special efficacy model and each specified target identified; According to the correspondence, multiple and different three-dimensional special efficacy models of selection are loaded into respectively in corresponding specified target.
B14, the device as described in B9, wherein the device further comprises:
Attribute transformation unit, suitable for when meeting preset condition, converting described three in the specified target in the video Tie up the specified attribute of special efficacy model.
B15, the device as described in B14, wherein the preset condition that meets includes:
The specified target recognized in acquired image has carried out preset attitudes vibration;
And/or
The changed changing value of light recognized in acquired image is more than the first preset value;
And/or
It recognizes the background environment in acquired image and preset variation has occurred.
B16, the device as described in B14, wherein the specified attribute of the three-dimensional special efficacy model includes below a kind of or more Kind:
The textures texture of the three-dimensional special efficacy model;
The color of the three-dimensional special efficacy model;
The skeletal structure of the three-dimensional special efficacy model.
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 a kind of 18, computer readable storage mediums, wherein the computer readable storage medium is deposited 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 of video processing, wherein this method includes:
Obtain the video of video collector acquisition, the specified target in the acquired video of identification;
When identifying multiple specified targets from the video, it is special that multiple and different three-dimensionals is chosen from three-dimensional special efficacy model library Imitate model;
Multiple and different three-dimensional special efficacy models of selection are loaded into respectively in the multiple specified targets identified.
2. the method for claim 1, wherein described choose multiple three-dimensional special efficacy model packets from three-dimensional special efficacy model library It includes:
The specified attribute of each specified target identified is obtained respectively;
It is chosen from three-dimensional special efficacy model library and the matched three-dimensional special efficacy model of the specified attribute of each specified target obtained;
Described multiple and different three-dimensional special efficacy models of selection are loaded into respectively in the multiple specified targets identified include:
According to the specified attribute for each specified target of acquisition identified, multiple and different three-dimensional special efficacy models of selection are distinguished It is loaded into corresponding specified target.
3. method as claimed in claim 2, wherein the specified attribute of the specified target includes:
The gender of specified target and/or age.
4. the method for claim 1, wherein this method further comprises:
The selection control of three-dimensional special efficacy model is provided;
It is described to choose multiple and different three-dimensional special efficacy models from three-dimensional special efficacy model library and include:
In response to the selection operation to three-dimensional special efficacy model, corresponding three-dimensional special efficacy mould is selected from three-dimensional special efficacy model library Type.
5. method as claimed in claim 4, wherein described to be loaded into multiple and different three-dimensional special efficacy models of selection respectively Include in the multiple specified targets identified:
Show the multiple and different three-dimensional special efficacy models selected;
In response to the drag operation to the three-dimensional special efficacy model selected, determines each three-dimensional special efficacy model and identify each specified The correspondence of target;
According to the correspondence, multiple and different three-dimensional special efficacy models of selection are loaded into corresponding specified target respectively On.
6. the method for claim 1, wherein this method further comprises:
When meeting preset condition, the specified attribute of the three-dimensional special efficacy model in the specified target in the video is converted.
7. method as claimed in claim 6, wherein the preset condition that meets includes:
The specified target recognized in acquired image has carried out preset attitudes vibration;
And/or
The changed changing value of light recognized in acquired image is more than the first preset value;
And/or
It recognizes the background environment in acquired image and preset variation has occurred.
8. a kind of device of video processing, wherein the device includes:
Recognition unit is suitable for obtaining the video of video collector acquisition, the specified target in the acquired video of identification;
Model selection unit, suitable for when identifying multiple specified targets from the video, being selected from three-dimensional special efficacy model library Take multiple and different three-dimensional special efficacy models;
Model loading unit, suitable for the multiple and different three-dimensional special efficacy models chosen are loaded into respectively identify it is multiple specified In target.
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.
CN201810316940.XA 2018-04-10 2018-04-10 A kind of method and apparatus of video processing Pending CN108696699A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810316940.XA CN108696699A (en) 2018-04-10 2018-04-10 A kind of method and apparatus of video processing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810316940.XA CN108696699A (en) 2018-04-10 2018-04-10 A kind of method and apparatus of video processing

Publications (1)

Publication Number Publication Date
CN108696699A true CN108696699A (en) 2018-10-23

Family

ID=63844936

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810316940.XA Pending CN108696699A (en) 2018-04-10 2018-04-10 A kind of method and apparatus of video processing

Country Status (1)

Country Link
CN (1) CN108696699A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109729284A (en) * 2018-12-17 2019-05-07 惠州Tcl移动通信有限公司 Image processing method, intelligent terminal and the storage device of intelligent terminal
CN111627086A (en) * 2020-06-03 2020-09-04 上海商汤智能科技有限公司 Head portrait display method and device, computer equipment and storage medium
CN111667588A (en) * 2020-06-12 2020-09-15 上海商汤智能科技有限公司 Person image processing method, person image processing device, AR device and storage medium
WO2021196890A1 (en) * 2020-04-02 2021-10-07 腾讯科技（深圳）有限公司 Method and device for multimedia processing, electronic device, and storage medium
WO2022007627A1 (en) * 2020-07-10 2022-01-13 北京字节跳动网络技术有限公司 Method and apparatus for implementing image special effect, and electronic device and storage medium

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103702100A (en) * 2013-12-17 2014-04-02 Tcl商用信息科技（惠州）股份有限公司 3D (three-dimensional) display method and 3D display system for scenario
CN103824269A (en) * 2012-11-16 2014-05-28 广州三星通信技术研究有限公司 Face special-effect processing method and system
US20140218371A1 (en) * 2012-12-17 2014-08-07 Yangzhou Du Facial movement based avatar animation
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
CN105678826A (en) * 2014-11-19 2016-06-15 珠海金山办公软件有限公司 Method and system for realizing multi-object animation
CN107071580A (en) * 2017-03-20 2017-08-18 北京潘达互娱科技有限公司 Data processing method and device
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
CN107369200A (en) * 2017-07-04 2017-11-21 福建星网视易信息系统有限公司 A kind of 3D scene special effects processing method and storage device
CN107592474A (en) * 2017-09-14 2018-01-16 光锐恒宇（北京）科技有限公司 A kind of image processing method and device
CN107633541A (en) * 2017-09-14 2018-01-26 光锐恒宇（北京）科技有限公司 The generation method and device of a kind of image special effect
CN107679497A (en) * 2017-10-11 2018-02-09 齐鲁工业大学 Video face textures effect processing method and generation system

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103824269A (en) * 2012-11-16 2014-05-28 广州三星通信技术研究有限公司 Face special-effect processing method and system
US20140218371A1 (en) * 2012-12-17 2014-08-07 Yangzhou Du Facial movement based avatar animation
CN103702100A (en) * 2013-12-17 2014-04-02 Tcl商用信息科技（惠州）股份有限公司 3D (three-dimensional) display method and 3D display system for scenario
CN105678826A (en) * 2014-11-19 2016-06-15 珠海金山办公软件有限公司 Method and system for realizing multi-object animation
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
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
CN107071580A (en) * 2017-03-20 2017-08-18 北京潘达互娱科技有限公司 Data processing method and device
CN107369200A (en) * 2017-07-04 2017-11-21 福建星网视易信息系统有限公司 A kind of 3D scene special effects processing method and storage device
CN107592474A (en) * 2017-09-14 2018-01-16 光锐恒宇（北京）科技有限公司 A kind of image processing method and device
CN107633541A (en) * 2017-09-14 2018-01-26 光锐恒宇（北京）科技有限公司 The generation method and device of a kind of image special effect
CN107679497A (en) * 2017-10-11 2018-02-09 齐鲁工业大学 Video face textures effect processing method and generation system

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109729284A (en) * 2018-12-17 2019-05-07 惠州Tcl移动通信有限公司 Image processing method, intelligent terminal and the storage device of intelligent terminal
WO2021196890A1 (en) * 2020-04-02 2021-10-07 腾讯科技（深圳）有限公司 Method and device for multimedia processing, electronic device, and storage medium
CN111627086A (en) * 2020-06-03 2020-09-04 上海商汤智能科技有限公司 Head portrait display method and device, computer equipment and storage medium
CN111667588A (en) * 2020-06-12 2020-09-15 上海商汤智能科技有限公司 Person image processing method, person image processing device, AR device and storage medium
WO2022007627A1 (en) * 2020-07-10 2022-01-13 北京字节跳动网络技术有限公司 Method and apparatus for implementing image special effect, and electronic device and storage medium

Similar Documents

Publication Publication Date Title
CN108696699A (en) A kind of method and apparatus of video processing
US20220301269A1 (en) Utilizing topological maps for augmented or virtual reality
US8843585B1 (en) Methods and apparatus for generating a unique virtual item
US11263821B1 (en) Generating augmented reality prerenderings using template images
CN106548179A (en) The detection method of object and dress ornament key point, device and electronic equipment
CN107633541A (en) The generation method and device of a kind of image special effect
CN108495058A (en) Image processing method, device and computer readable storage medium
CN108648139A (en) A kind of image processing method and device
US10534443B2 (en) Method and system for generating a synthetic database of postures and gestures
CN108537725A (en) A kind of method for processing video frequency and device
CN108648284A (en) A kind of method and apparatus of video processing
CN108711192A (en) A kind of method for processing video frequency and device
CN109191545A (en) A kind of method and device making caricature
CN107633480A (en) A kind of image processing method and device
CN108470362A (en) A kind of method and apparatus for realizing video toning
CN114119154A (en) Virtual makeup method and device
CN114119935A (en) Image processing method and device
Collomosse Supervised genetic search for parameter selection in painterly rendering
KR20240047881A (en) Electronic apparatus that provides a drawing guide and method for controlling thereof

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20181023