CN108881668A - Video increases steady method, apparatus, system and computer-readable medium - Google Patents
Video increases steady method, apparatus, system and computer-readable medium Download PDFInfo
- Publication number
- CN108881668A CN108881668A CN201710408761.4A CN201710408761A CN108881668A CN 108881668 A CN108881668 A CN 108881668A CN 201710408761 A CN201710408761 A CN 201710408761A CN 108881668 A CN108881668 A CN 108881668A
- Authority
- CN
- China
- Prior art keywords
- video
- video flowing
- steady
- shooting
- mesh point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/14—Picture signal circuitry for video frequency region
- H04N5/21—Circuitry for suppressing or minimising disturbance, e.g. moiré or halo
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/14—Picture signal circuitry for video frequency region
- H04N5/144—Movement detection
- H04N5/145—Movement estimation
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of videos to increase steady method, apparatus, system and computer-readable medium, and the video increases steady method and includes:For the video stream calculation through shooting for being increased the steady information flow of increasing surely compensated to the video flowing;And increase steady information flow to the video flowing implementation deformation operation through shooting, to obtain the video flowing after increasing surely based on described.Video according to an embodiment of the present invention increases steady method, apparatus, system and computer-readable medium and extracts the corresponding steady information flow of increasing from the video flowing through shooting, and the video flowing through shooting is carried out to increase steady compensation based on the steady information flow of the increasing, video can be carried out online to increase surely, and operand and delay will not be dramatically increased, it is conducive to upgrading and deployment.
Description
Technical field
The present invention relates to field of artificial intelligence, relates more specifically to a kind of video and increase steady method, apparatus, system and meter
Calculation machine readable medium.
Background technique
Currently, having become a kind of important video source using the video that various mobile devices are independently shot.Mobile device
User's video (such as mobile phone from shoot the video) for often independently shooting it uploading onto the server is shared with other people, Huo Zhechuan
The client of other users is sent to so that other users are checked.The rise of various webcast websites is derived from this.
Due to various reasons, such as the amateur shooting technical ability of photographer or unfavorable shooting condition etc., this self-timer regard
The viewing experience of frequency may be bad, needs to carry out video and increases surely.It is limited by computing capability and requirement of real-time, traditional is offline
Video increase steady method and be difficult to apply.Simultaneously as shoot the video certainly middle prospect (people) and the depth disparity of background it is very big, be based only on
The method of three axis rotation (such as gravitometer or gyroscope), which is unable to get, satisfactorily increases steady result.
Summary of the invention
The present invention is proposed to solve the above-mentioned problems.According to an aspect of the present invention, a kind of steady method of video increasing is provided,
The video increases steady method:It is steady to be used to increase the video flowing increasing surely compensated for the video stream calculation through shooting
Information flow;And increase steady information flow to the video flowing implementation deformation operation through shooting, after obtaining increasing surely based on described
Video flowing.
In one embodiment of the invention, the calculating for increasing steady information flow includes:To the video flowing through shooting
Consecutive frame carry out estimation, to obtain the motion information between the consecutive frame;And it is calculated based on the motion information
Make the compensating parameter of the content smooth motion in the video flowing through shooting, the compensating parameter of each frame constitutes the steady letter of the increasing
Breath stream.
In one embodiment of the invention, the estimation includes:Foreground detection is carried out, foreground area is obtained;?
Several mesh points are set on the image of the foreground area;And it calculates described between the consecutive frame through the video flowing shot
The motion information of mesh point on the image of foreground area, using as the motion information between the consecutive frame.
In one embodiment of the invention, the progress foreground detection obtains foreground area and includes:Face datection is carried out,
Human face region is obtained as the foreground area.
In one embodiment of the invention, the deformation operation includes:For each of the video flowing through shooting
Frame:Position after the compensation of the mesh point is calculated based on the compensating parameter;And the mesh point is deformed to the compensation
Position afterwards.
In one embodiment of the invention, the steady method of the video increasing further includes:For in the foreground area extremely
A few mesh point uses the motion information for the mesh point being located at around each of at least one mesh point mesh point
Low-pass filtering on airspace is carried out to respective grid points.
In one embodiment of the invention, implement at any one of the calculating for increasing steady information flow in the following:It claps
Take the photograph the client of video flowing, the server of transfer video flowing and the client for checking video flowing.
In one embodiment of the invention, the deformation operation transfer video flowing server or check video flowing
Implement in client.
In one embodiment of the invention, the steady method of the video increasing is applied to video living transmission system, and the side
Method further includes:Video flowing real-time perfoming after described increase surely is shown.
According to a further aspect of the invention, a kind of video tranquilizer is provided, the video tranquilizer includes:Calculate mould
Block, for being used to increase the video flowing the steady information flow of increasing surely compensated for the video stream calculation through shooting;And become
Shape module, for increasing steady information flow to the video flowing implementation deformation operation through shooting, after obtaining increasing surely based on described
Video flowing.
In one embodiment of the invention, the computing module further comprises:Motion estimation module, for described
The consecutive frame of video flowing through shooting carries out estimation, to obtain the motion information between the consecutive frame;And movement is flat
Sliding formwork block, for calculating the compensation ginseng for making the content smooth motion in the video flowing through shooting based on the motion information
Number, the compensating parameter of each frame constitute the steady information flow of increasing.
In one embodiment of the invention, the motion estimation module is further used for:Foreground detection is carried out, before obtaining
Scene area;Several mesh points are set on the image of the foreground area;And calculate the adjacent of the video flowing through shooting
The motion information of mesh point between frame on the image of the foreground area, using as the motion information between the consecutive frame.
In one embodiment of the invention, the progress foreground detection obtains foreground area and includes:Face datection is carried out,
Human face region is obtained as the foreground area.
In one embodiment of the invention, the deformation module is further used for:For the video flowing through shooting
Each frame:Position after the compensation of the mesh point is calculated based on the compensating parameter;And the mesh point is deformed to institute
State position after compensating.
In one embodiment of the invention, the video tranquilizer further includes:Airspace filter module, for for institute
At least one mesh point in foreground area is stated, using around each of at least one mesh point mesh point
The motion information of mesh point carries out the low-pass filtering on airspace to respective grid points.
In one embodiment of the invention, it is realized at any one of the computing module in the following:Shoot video flowing
Client, transfer video flowing server and check the client of video flowing.
In one embodiment of the invention, the deformation module transfer video flowing server or check video flowing
It is realized in client.
In one embodiment of the invention, the video tranquilizer is applied to video living transmission system, and the dress
It sets and further includes:Display module, for showing the video flowing real-time perfoming after described increase surely.
According to a further aspect of the present invention, a kind of video stability augmentation system is provided, the video stability augmentation system includes storage dress
It sets and processor, is stored with the computer program run by the processor on the storage device, the computer program exists
Video described in any of the above embodiments is executed when being run by the processor increases steady method.
Another aspect according to the present invention provides a kind of computer-readable medium, stores on the computer-readable medium
There is computer program, the computer program executes video described in any of the above embodiments at runtime and increases steady method.
Video according to an embodiment of the present invention increases steady method, apparatus, system and computer-readable medium from the view through shooting
The corresponding steady information flow of increasing is extracted in frequency stream, and the video flowing through shooting is carried out to increase steady compensation based on the steady information flow of the increasing,
Video can be carried out online to increase surely, and will not dramatically increase operand and delay, be conducive to upgrading and deployment.
Detailed description of the invention
The embodiment of the present invention is described in more detail in conjunction with the accompanying drawings, the above and other purposes of the present invention,
Feature and advantage will be apparent.Attached drawing is used to provide to further understand the embodiment of the present invention, and constitutes explanation
A part of book, is used to explain the present invention together with the embodiment of the present invention, is not construed as limiting the invention.In the accompanying drawings,
Identical reference label typically represents same parts or step.
Fig. 1 shows the exemplary electronic device for increasing steady method and apparatus for realizing video according to an embodiment of the present invention and shows
Meaning property block diagram;
Fig. 2 shows the schematic flow charts that video according to an embodiment of the present invention increases steady method;
Fig. 3 shows the schematic block diagram of video tranquilizer according to an embodiment of the present invention;And
Fig. 4 shows the schematic block diagram of video stability augmentation system according to an embodiment of the present invention.
Specific embodiment
In order to enable the object, technical solutions and advantages of the present invention become apparent, root is described in detail below with reference to accompanying drawings
According to example embodiments of the present invention.Obviously, described embodiment is only a part of the embodiments of the present invention, rather than this hair
Bright whole embodiments, it should be appreciated that the present invention is not limited by example embodiment described herein.Based on described in the present invention
The embodiment of the present invention, those skilled in the art's obtained all other embodiment in the case where not making the creative labor
It should all fall under the scope of the present invention.
Firstly, the video to describe for realizing the embodiment of the present invention increases steady method, apparatus, system and calculating referring to Fig.1
The exemplary electronic device 100 of machine readable medium.
As shown in Figure 1, electronic equipment 100 include one or more processors 102, it is one or more storage device 104, defeated
Enter device 106, output device 108 and imaging sensor 110, these components pass through bus system 112 and/or other forms
The interconnection of bindiny mechanism's (not shown).It should be noted that the component and structure of electronic equipment 100 shown in FIG. 1 are only exemplary, and
Unrestricted, as needed, the electronic equipment also can have other assemblies and structure.
The processor 102 can be central processing unit (CPU) or have data-handling capacity and/or instruction execution
The processing unit of the other forms of ability, and the other components that can control in the electronic equipment 100 are desired to execute
Function.
The storage device 104 may include one or more computer program products, and the computer program product can
To include various forms of computer readable storage mediums, such as volatile memory and/or nonvolatile memory.It is described easy
The property lost memory for example may include random access memory (RAM) and/or cache memory (cache) etc..It is described non-
Volatile memory for example may include read-only memory (ROM), hard disk, flash memory etc..In the computer readable storage medium
On can store one or more computer program instructions, processor 102 can run described program instruction, to realize hereafter institute
The client functionality (realized by processor) in the embodiment of the present invention stated and/or other desired functions.In the meter
Can also store various application programs and various data in calculation machine readable storage medium storing program for executing, for example, the application program use and/or
The various data etc. generated.
The input unit 106 can be the device that user is used to input instruction, and may include keyboard, mouse, wheat
One or more of gram wind and touch screen etc..
The output device 108 can export various information (such as image or sound) to external (such as user), and
It may include one or more of display, loudspeaker etc..
Described image sensor 110 can be shot the desired image of user (such as photo, video etc.), and will be captured
Image be stored in the storage device 104 for other components use.
Illustratively, increase steady method, apparatus, system and computer-readable for realizing video according to an embodiment of the present invention
The exemplary electronic device of medium may be implemented as smart phone, tablet computer etc..
In the following, will describe video according to an embodiment of the present invention with reference to Fig. 2 increases steady method 200.
In step S210, surely believe for the video stream calculation through shooting for being increased the increasing surely compensated to the video flowing
Breath stream.
In one embodiment, the video flowing through shooting for example can be autonomous using mobile device for the user of mobile device
The video of shooting, such as the interested video of user, shooting the video certainly etc. for live streaming.
In one embodiment, it after user is using mobile device shooting video, can directly be set in the movement of the user
Standby place, for being increased the steady information flow of increasing surely compensated to the video flowing, is then based on this for the video stream calculation through shooting
Increase steady information flow video flowing is carried out to increase steady compensation, so that after the user can watch increasing surely in the mobile device of oneself
Video flowing, or share or send to other users viewing.In this embodiment, shooting mobile device of video flowing itself can be with
Implement video according to an embodiment of the present invention alone and increase steady method, convenient for upgrading deployment.
It in another embodiment, can be directly in the movement of the user after user is using mobile device shooting video
Then should for the video stream calculation through shooting for being increased the steady information flow of increasing surely compensated to the video flowing at equipment
Video flowing and the steady information flow of increasing being calculated, which arrive, wishes to check that another equipment of the video flowing (such as also sets to move
It is standby), the steady information flow of the increasing is based on by another equipment, video flowing is carried out to increase steady compensation, so that the user of another equipment can be with
Video flowing after viewing increases surely in the equipment of oneself.In this embodiment, shoot video flowing mobile device can with it is another
Equipment cooperates together to be implemented video according to an embodiment of the present invention and increases steady method so that related calculation amount be distributed to it is different
Equipment (client), be conducive to realize that video increases using the limited computing capability of mobile device it is steady, do not dramatically increase calculation amount and
Delay.
It In yet another embodiment, can be directly in the movement of the user after user is using mobile device shooting video
Then should for the video stream calculation through shooting for being increased the steady information flow of increasing surely compensated to the video flowing at equipment
Video flowing and the steady information flow of the increasing being calculated are based on the steady information flow pair of the increasing by the transfer server to transfer server
Video flowing carries out increasing steady compensation, and by the video stream after increasing surely to target device (such as being also mobile device), so that
The user of the target device can watch the video flowing after increasing surely in the equipment of oneself.In this embodiment, it is passed for transfer
It send the transfer server of video flowing to share part to calculate, cooperation is implemented according to the present invention together with the equipment for checking video flowing
The video of embodiment increases steady method, can utilize well the computing capability of server, while also utilizing mobile device end
Computing capability is also able to achieve efficient, convenient and fast video and increases surely.
It in a further embodiment, can be directly by captured video after user is using mobile device shooting video
It is streamed to another equipment (such as being also mobile device) for wishing to check the video flowing, which can be for through shooting
Video stream calculation for being increased the steady information flow of increasing surely compensated to the video flowing, be then based on the steady information flow of the increasing to view
Frequency stream carries out increasing steady compensation, so that the user of another equipment can watch the video flowing after increasing surely in the equipment of oneself.
In this embodiment, check that the mobile device of video flowing itself implements alone video according to an embodiment of the present invention and increases steady method,
Convenient for upgrading deployment.
Above-described embodiment may be implemented online video and increase surely, take into account the requirement of computing capability and real-time.
In other embodiments, it can also implement to increase the calculating of steady information flow simultaneously at transfer server and increase steady mend
It repays, the equipment for shooting video flowing only sends the video flowing of shooting, and the equipment for checking video flowing only receives the video flowing after increasing surely.
In one embodiment, the calculating for increasing steady information flow may include:To the consecutive frame of the video flowing through shooting
Estimation is carried out, to obtain the motion information between the consecutive frame;And the warp is made based on motion information calculating
The compensating parameter of content smooth motion in the video flowing of shooting, the compensating parameter of each frame constitute the steady information flow of increasing.Base
In the compensating parameter of each frame of video flowing, each frame of video flowing can be carried out increasing steady compensation, increase the related behaviour surely compensated
Work will be described in the step S220 being described below.
In one embodiment, increasing estimation included in the calculating of steady information flow may include:For through shooting
Video flowing each frame carry out foreground detection, obtain foreground area;Several grids are set on the image of the foreground area
Point;And calculate the movement letter of the mesh point between the consecutive frame through the video flowing shot on the image of the foreground area
Breath, using as the motion information between the consecutive frame.The motion information calculated between consecutive frame by mesh point can be with base
Preferable estimation is realized in less calculation amount, so that can realize the present invention in the limited mobile terminal of computing capability
Method.It illustratively, can optical flow algorithm --- Lucas Kanade algorithm etc. obtains based on one of computer vision
The motion information of mesh point between adjacent video frames.In other examples, it can also be obtained using other suitable methods adjacent
Motion information between video frame.
Further, the foreground detection can be Face datection, and described in the obtained human face region of Face datection is used as
Foreground area.In the shooting the video certainly of various network direct broadcastings, people's (face) is foreground area.It, can for this from shooting the video
To detect the human face region in the video, and several mesh points are set on the image of human face region, calculate people between consecutive frame
The motion information of mesh point on the image in face region, using as the motion information between consecutive frame, for from the increasing that shoots the video
The calculating of steady information flow, for obtaining shooting the video after increasing surely certainly.
It in one embodiment, can be at least one mesh point in the foreground area (such as human face region)
Using the motion information for the mesh point being located at around each of at least one mesh point mesh point to respective grid points
Carry out the low-pass filtering on airspace.Based on this, it can prevent from increasing surely influencing main body and (such as shoot the video certainly for what is be broadcast live etc.
Personage) movement presentation, it is ensured that main body because increase it is steady due to mistake deformation does not occur, further improve video increasing of the invention
The performance of steady method.
Based on the obtained motion information of estimation, the content smooth motion made in the video flowing through shooting can be calculated
Compensating parameter.In one embodiment, the method for calculating compensating parameter can be:Use index discount (Exponential
Discount method) calculates present frame and then negates with respect to the offset of reference frame (such as former frame), and being formulated can
Think:
C [i]=- (p × D [i]+p2×D[i-1]+p3×D[i-2]+…)
Wherein, C [i] indicates the compensating parameter of the i-th frame, and D [i] indicates the movement between estimated the i-th frame and former frame
Information, p are index used in index discount method.In other embodiments, other suitable method meters can also be used
Calculate compensating parameter.
Based on the compensating parameter as each frame for increasing steady information flow, the video flowing through shooting can be carried out increasing steady benefit
It repays, as described in the following step.
In step S220, increase steady information flow to the video flowing implementation deformation operation through shooting, to obtain based on described
Video flowing after increasing surely.
In one embodiment, can in the client (such as another equipment described in aforementioned exemplary) for checking video flowing or
Based on steady information flow implementation is increased, to the deformation operation through shooting video flowing, (i.e. increasing is steady as elucidated before is mended on person's transfer server
It repays).It can both make the client (mobile device as described in aforementioned exemplary) for shooting video flowing too many without transmission in this way
Data volume (such as only transmit the video flowing of shooting, or transmission video flowing and increase steady information flow), and to check video flowing
Client can use its limited computing capability viewed by deformation operation increase it is steady after video flowing, raising checks body
It tests, implements simultaneously because step S210 and step S220 can be distributed in different equipment, each equipment can be made to play its meter
Calculation ability is dispersed data processing amount, is improved efficiency, and can handle in real time close to realizing.It is of course also possible to not use distributed place
Reason, and implement video of the invention on the same device and increase steady method.
In one embodiment, can be used (such as check the client of video flowing) it is used for the opening of embedded system
Shape library (OpenGL ES) is implemented to the deformation operation through shooting video flowing and plays deformed video flowing (after increasing surely
Video flowing).In other examples, the deformation through shooting video flowing can also be grasped using other suitable methods or execution of instrument
Make.
In one embodiment, based on it is described increase steady information flow deformation operation is implemented to the video flowing through shooting can be with
Including:Compensating parameter based on each frame being calculated calculate after the content augmentation in video flowing should position (referred to as mend
Repay rear position), then content is moved to position after compensating, to realize the video flowing after increasing video rheological behavior surely.
Specifically, in example above-mentioned, due to being set in the foreground region image of each frame of the video flowing through shooting
Several mesh points have been set, and have calculated the motion information of the mesh point between consecutive frame on the image of the foreground area.It is based on
This, the deformation operation of step S220 may include:For each frame of the video flowing through shooting:Grid is calculated based on compensating parameter
Position after the compensation of point;And by mesh point be deformed to compensation after position.For example, each small grid can be become using projection
It changes (Projective Transformation) and is deformed to position after compensation, to be shown to viewer.Deformation based on mesh point
It is steady that operation can realize that reliable video increases in the case where less calculation amount.
Based on above description, video according to an embodiment of the present invention increases steady method and extracts phase from the video flowing through shooting
It is corresponding to increase steady information flow, and the video flowing through shooting is carried out to increase steady compensation based on the steady information flow of the increasing, it can carry out online
Video increases surely, and will not dramatically increase operand and delay, is conducive to upgrading and deployment.
In one embodiment, video according to an embodiment of the present invention, which increases steady method, can be applied to video living transmission system,
And video according to an embodiment of the present invention, which increases steady method, to be included the following steps:By the video flowing real-time perfoming after increasing surely
Display.Video flowing after real-time display increases surely can be further improved user experience.
Illustratively, video according to an embodiment of the present invention increase steady method can be in setting with memory and processor
It is realized in standby, device or system.
Illustratively, video according to an embodiment of the present invention increases steady method and can be deployed at personal terminal, such as intelligently
Phone, tablet computer, personal computer etc..Alternatively, video according to an embodiment of the present invention increases steady method and can also be deployed in
Server end (or cloud).Alternatively, video according to an embodiment of the present invention increases steady method can also be deployed in service with being distributed
At device end (or cloud) and personal terminal.Alternatively, video according to an embodiment of the present invention, which increases steady method, can also be distributed ground portion
Administration is at different personal terminal.
Video according to an embodiment of the present invention is described above exemplarily increases illustrative steps stream included by steady method
Journey.
The video tranquilizer of another aspect of the present invention offer is described below with reference to Fig. 3.Fig. 3 shows real according to the present invention
Apply the schematic block diagram of the video tranquilizer 300 of example.
As shown in figure 3, video tranquilizer 300 according to an embodiment of the present invention includes computing module 310 and deformation module
320.The modules can execute each step/function for increasing steady method above in conjunction with the video of Fig. 2 description respectively.Below
Only the major function of each unit of video tranquilizer 300 is described, and omits the detail content having been described above.
Computing module 310 is used for for the video stream calculation through shooting for being increased the increasing surely compensated to the video flowing
Steady information flow.Deformation module 320 is used to implement deformation operation to the video flowing through shooting based on the steady information flow of increasing, with
Obtain the video flowing after increasing surely.Computing module 310 and deformation module 320 can processing in electronic equipment as shown in Figure 1
The program instruction that stores in 102 Running storage device 104 of device is realized.
In one embodiment, the video flowing through shooting for example can be autonomous using mobile device for the user of mobile device
The video of shooting, such as the interested video of user, shooting the video certainly etc. for live streaming.Video according to an embodiment of the present invention
Tranquilizer 300 can realize at the mobile device of the shooting video flowing, can also not be to shoot the movement of video flowing to set
(such as checking at the equipment of video flowing) is realized at standby another equipment, can also partially (such as computing module 310) shoot
It is realized at the mobile device of video flowing, another part (such as deformation module 320) be not the mobile device for shooting video flowing
(such as checking at the equipment of video flowing) is realized at another equipment.In other embodiments, video according to an embodiment of the present invention
The whole (i.e. both computing module 310 and deformation module 320) or part (i.e. computing module 310 and distorted pattern of tranquilizer 300
320 one of both of block) it also may be implemented (to pass video flowing from the client of shooting video flowing in the server of transfer video flowing
The transfer server used when being sent to the client for checking video flowing) in.
In one embodiment, computing module 310 may further include motion estimation module and motion smoothing module (
It is not shown in FIG. 3).Wherein, motion estimation module is used to carry out estimation to the consecutive frame of the video flowing through shooting,
To obtain the motion information between the consecutive frame.Motion smoothing module is used to make based on motion information calculating described through clapping
The compensating parameter of content smooth motion in the video flowing taken the photograph, the compensating parameter of each frame constitute the steady information flow of increasing.It is based on
The compensating parameter of each frame of video flowing, deformation module 320 can carry out each frame of video flowing increasing steady compensation (i.e. deformation behaviour
Make).
In one embodiment, motion estimation module can be further used for:For each frame of the video flowing through shooting
Foreground detection is carried out, foreground area is obtained;Several mesh points are set on the image of the foreground area;And calculate the warp
The motion information of mesh point between the consecutive frame of the video flowing of shooting on the image of the foreground area, using as described adjacent
Motion information between frame.The motion information between consecutive frame is calculated by mesh point can be realized based on less calculation amount
Preferable estimation, so that can realize motion estimation module of the invention in the limited mobile terminal of computing capability.Show
Example property, motion estimation module can be based on one of computer vision optical flow algorithm --- Lucas Kanade algorithm etc.
To the motion information of mesh point between adjacent video frames.In other examples, motion estimation module can also be suitable using other
Method obtain the motion information between adjacent video frames.
Further, the foreground detection can be Face datection, and described in the obtained human face region of Face datection is used as
Foreground area.In the shooting the video certainly of various network direct broadcastings, people's (face) is foreground area.For this from shooting the video, transport
Dynamic estimation module can detecte the human face region in the video, and several mesh points are arranged on the image of human face region, calculate
The motion information of mesh point between consecutive frame on the image of human face region, using as the motion information between consecutive frame, with
In the calculating for increasing steady information flow that shoots the video certainly, for obtaining shooting the video after increasing surely certainly.
In one embodiment, video tranquilizer 300 according to an embodiment of the present invention can also include airspace filter mould
Block (not shown in FIG. 3).Airspace filter module can be used for in the foreground area (such as human face region) at least
One mesh point uses the motion information pair for the mesh point being located at around each of at least one mesh point mesh point
Respective grid points carry out the low-pass filtering on airspace.Based on this, it can prevent from increasing surely influencing main body (such as being broadcast live etc.
Personage from shooting the video) movement presentation, it is ensured that main body because increase it is steady due to mistake do not occur deform, further improve video
Increase steady performance.
Based on the obtained motion information of motion estimation module, motion smoothing module, which can calculate, makes the video flowing through shooting
In content smooth motion compensating parameter.In one embodiment, the method that motion smoothing module calculates compensating parameter can be with
For:Present frame is calculated with respect to reference frame (such as former frame) using the method for index discount (Exponential Discount)
Then offset negates, being formulated to be:
C [i]=- (p × D [i]+p2×D[i-1]+p3×D[i-2]+…)
Wherein, C [i] indicates the compensating parameter of the i-th frame, and D [i] indicates the movement between estimated the i-th frame and former frame
Information, p are index used in index discount method.In other embodiments, motion smoothing module can also use other
Suitable method calculates compensating parameter.
Based on the compensating parameter as each frame for increasing steady information flow, deformation module 320 can be to the video flowing through shooting
Deformation operation is carried out to realize and increase steady compensation.
In one embodiment, the open graphic library (OpenGL for embedded system can be used in deformation module 320
ES) implement to the deformation operation through shooting video flowing and play deformed video flowing (video flowing after increasing surely).At other
In example, deformation module 320 can also be using other suitable methods or execution of instrument to the deformation operation through shooting video flowing.
In one embodiment, deformation module 320 increases steady information flow to the video flowing implementation through shooting based on described
Deformation operation may include:Compensating parameter based on each frame being calculated calculates after the content augmentation in video flowing should be
Position (referred to as compensate after position), content is then moved to position after compensation, thus realize video rheological behavior is increased it is steady
Video flowing afterwards.
Specifically, in example above-mentioned, since motion estimation module is in the prospect of each frame of the video flowing through shooting
It is provided with several mesh points on the image in region, and calculates mesh point between consecutive frame on the image of the foreground area
Motion information.Based on this, the deformation operation of deformation module 320 may include:For each frame of the video flowing through shooting:It is based on
Position after the compensation of compensating parameter calculating mesh point;And by mesh point be deformed to compensation after position.For example, deformation module 320
Each small grid can be deformed to position after compensating using projective transformation (Projective Transformation), with
It is shown to viewer.
Based on above description, video tranquilizer according to an embodiment of the present invention extracts phase from the video flowing through shooting
It is corresponding to increase steady information flow, and the video flowing through shooting is carried out to increase steady compensation based on the steady information flow of the increasing, it can carry out online
Video increases surely, and will not dramatically increase operand and delay, is conducive to upgrading and deployment.
In one embodiment, video tranquilizer according to an embodiment of the present invention can be applied to video living transmission system,
And video tranquilizer according to an embodiment of the present invention can also include display module (not shown in FIG. 3), the display mould
Block can show the video flowing real-time perfoming after increasing surely, to further increase user experience.
Fig. 4 shows the schematic block diagram of video stability augmentation system 400 according to an embodiment of the present invention.Video stability augmentation system
400 include storage device 410 and processor 420.
Wherein, storage device 410 stores the corresponding step increased in steady method for realizing video according to an embodiment of the present invention
Rapid program code.Program code of the processor 420 for being stored in Running storage device 410, it is real according to the present invention to execute
The video for applying example increases the corresponding steps of steady method, and for realizing the phase in video tranquilizer according to an embodiment of the present invention
Answer module.In addition, video stability augmentation system 400 can also include image collecting device (not shown in FIG. 4), can be used for clapping
Take the photograph video flowing.Certainly, image collecting device is not required, and can directly receive the video flowing from other equipment shooting.
In one embodiment, when said program code is run by processor 420 video stability augmentation system 400 is executed
Following steps:For the video stream calculation through shooting for being increased the steady information flow of increasing surely compensated to the video flowing;And
Increase steady information flow to the video flowing implementation deformation operation through shooting, to obtain the video flowing after increasing surely based on described.
In one embodiment, when said program code is run by processor 420 video stability augmentation system 400 is executed
The calculating of the steady information flow of increasing include:Estimation is carried out to the consecutive frame of the video flowing through shooting, to obtain the phase
Motion information between adjacent frame;And transport the content in the video flowing through shooting smoothly based on motion information calculating
Dynamic compensating parameter, the compensating parameter of each frame constitute the steady information flow of increasing.
In one embodiment, when said program code is run by processor 420 video stability augmentation system 400 is executed
Estimation include:Foreground detection is carried out, foreground area is obtained;Several grids are set on the image of the foreground area
Point;And calculate the movement letter of the mesh point between the consecutive frame through the video flowing shot on the image of the foreground area
Breath, using as the motion information between the consecutive frame.
In one embodiment, when said program code is run by processor 420 video stability augmentation system 400 is executed
The carry out foreground detection obtain foreground area and include:Face datection is carried out, obtains human face region as the foreground area.
In one embodiment, when said program code is run by processor 420 video stability augmentation system 400 is executed
Deformation operation include:For each frame of the video flowing through shooting:The mesh point is calculated based on the compensating parameter
Compensation after position;And the mesh point is deformed to position after the compensation.
In one embodiment, hold video stability augmentation system 400 when said program code is run by processor 420
Row following steps:For at least one mesh point in the foreground area, using at least one described mesh point
The motion information of mesh point around each mesh point carries out the low-pass filtering on airspace to respective grid points.
In one embodiment, when said program code is run by processor 420 video stability augmentation system 400 is executed
The steady information flow of increasing calculating any one in the following at implement:Shoot the service of the client, transfer video flowing of video flowing
Device and the client for checking video flowing.
In one embodiment, when said program code is run by processor 420 video stability augmentation system 400 is executed
Deformation operation transfer video flowing server or check video flowing client on implement.
In one embodiment, video stability augmentation system 400 is applied to video living transmission system, and is located in said program code
Reason device 420 also makes video stability augmentation system 400 execute following steps when running:Video flowing real-time perfoming after described increase surely is shown
Show.
In addition, according to embodiments of the present invention, additionally providing a kind of storage medium, storing program on said storage
Instruction increases steady method for executing the video of the embodiment of the present invention when described program instruction is run by computer or processor
Corresponding steps, and for realizing the corresponding module in video tranquilizer according to an embodiment of the present invention.The storage medium
It such as may include the storage card of smart phone, the storage unit of tablet computer, the hard disk of personal computer, read-only memory
(ROM), Erasable Programmable Read Only Memory EPROM (EPROM), portable compact disc read-only memory (CD-ROM), USB storage,
Or any combination of above-mentioned storage medium.The computer readable storage medium can be one or more computer-readable deposit
Any combination of storage media, such as a computer readable storage medium include to increase steady information for the video stream calculation through shooting
The computer-readable program code of stream, another computer readable storage medium include based on the steady information flow of increasing to through shooting
The computer-readable program code of video flowing implementation deformation operation.
In one embodiment, the computer program instructions may be implemented real according to the present invention when being run by computer
Each functional module of the video tranquilizer of example is applied, and/or video according to an embodiment of the present invention can be executed and increased surely
Method.
In one embodiment, the computer program instructions make computer or place when being run by computer or processor
It manages device and executes following steps:For the video stream calculation through shooting for being increased the steady information of increasing surely compensated to the video flowing
Stream;And increase steady information flow to the video flowing implementation deformation operation through shooting, to obtain the video after increasing surely based on described
Stream.
In one embodiment, the computer program instructions make computer or place when being run by computer or processor
Managing the calculating for increasing steady information flow that device executes includes:Estimation is carried out to the consecutive frame of the video flowing through shooting, with
Motion information between the consecutive frame;And made in the video flowing through shooting based on motion information calculating
Hold the compensating parameter of smooth motion, the compensating parameter of each frame constitutes the steady information flow of increasing.
In one embodiment, the computer program instructions make computer or place when being run by computer or processor
Managing the estimation that device executes includes:Foreground detection is carried out, foreground area is obtained;If being arranged on the image of the foreground area
Dry mesh point;And the mesh point between the calculating consecutive frame through the video flowing shot on the image of the foreground area
Motion information, using as the motion information between the consecutive frame.
In one embodiment, the computer program instructions make computer or place when being run by computer or processor
The carry out foreground detection that reason device executes obtains foreground area and includes:Face datection is carried out, is obtained described in human face region conduct
Foreground area.
In one embodiment, the computer program instructions make computer or place when being run by computer or processor
Managing the deformation operation that device executes includes:For each frame of the video flowing through shooting:Institute is calculated based on the compensating parameter
State position after the compensation of mesh point;And the mesh point is deformed to position after the compensation.
In one embodiment, the computer program instructions also make when being run by computer or processor computer or
Processor executes following steps:For at least one mesh point in the foreground area, using positioned at least one described net
The motion information of mesh point around each of lattice point mesh point carries out the low-pass filtering on airspace to respective grid points.
In one embodiment, the computer program instructions make computer or place when being run by computer or processor
It manages and implements at any one of the calculating for the steady information flow of increasing that device executes in the following:Shoot client, the transfer video of video flowing
The server of stream and the client for checking video flowing.
In one embodiment, the computer program instructions make computer or place when being run by computer or processor
Reason device execute deformation operation transfer video flowing server or check video flowing client on implement.
In one embodiment, the storage medium application is in video living transmission system, and the computer program instructions
Computer or processor is also set to execute following steps when being run by computer or processor:Video flowing after described increase surely is real
Shi Jinhang is shown.
Video according to an embodiment of the present invention increases steady method, apparatus, system and storage medium from the video flowing through shooting
It is middle to extract the corresponding steady information flow of increasing, and the video flowing through shooting is carried out to increase steady compensation based on the steady information flow of the increasing, it can
The online video that carries out increases surely, and will not dramatically increase operand and delay, is conducive to upgrading and deployment.
Although describing example embodiment by reference to attached drawing here, it should be understood that above example embodiment are only exemplary
, and be not intended to limit the scope of the invention to this.Those of ordinary skill in the art can carry out various changes wherein
And modification, it is made without departing from the scope of the present invention and spiritual.All such changes and modifications are intended to be included in appended claims
Within required the scope of the present invention.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In several embodiments provided herein, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, apparatus embodiments described above are merely indicative, for example, the division of the unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied
Another equipment is closed or is desirably integrated into, or some features can be ignored or not executed.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be practiced 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 specification.
Similarly, it should be understood that in order to simplify the present invention and help to understand one or more of the various inventive aspects,
To in the description of exemplary embodiment of the present invention, each feature of the invention be grouped together into sometimes single embodiment, figure,
Or in descriptions thereof.However, the method for the invention should not be construed to reflect following intention:It is i.e. claimed
The present invention claims features more more than feature expressly recited in each claim.More precisely, such as corresponding power
As sharp claim reflects, inventive point is that the spy of all features less than some disclosed single embodiment can be used
Sign is to solve corresponding technical problem.Therefore, it then follows thus claims of specific embodiment are expressly incorporated in this specific
Embodiment, wherein each, the claims themselves are regarded as separate embodiments of the invention.
It will be understood to those skilled in the art that any combination pair can be used other than mutually exclusive between feature
All features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed any method
Or all process or units of equipment are combined.Unless expressly stated otherwise, this specification (is wanted including adjoint right
Ask, make a summary and attached drawing) disclosed in each feature can be replaced with an alternative feature that provides the same, equivalent, or similar purpose.
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 mean it is of the invention
Within the scope of and form different embodiments.For example, in detail in the claims, embodiment claimed it is one of any
Can in any combination mode come using.
Various component embodiments of the invention can be implemented in hardware, or to run on one or more processors
Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice
Microprocessor or digital signal processor (DSP) realize some moulds in article analytical equipment according to an embodiment of the present invention
The some or all functions of block.The present invention is also implemented as a part or complete for executing method as described herein
The program of device (for example, computer program and computer program product) in portion.It is such to realize that program of the invention can store
On a computer-readable medium, it or may be in the form of one or more signals.Such signal can be from internet
Downloading obtains on website, is perhaps provided on the carrier signal or is provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability
Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between parentheses 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" located in front of the 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 through the same hardware branch
To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame
Claim.
The above description is merely a specific embodiment or to the explanation of specific embodiment, protection of the invention
Range is not limited thereto, and anyone skilled in the art in the technical scope disclosed by the present invention, can be easily
Expect change or replacement, should be covered by the protection scope of the present invention.Protection scope of the present invention should be with claim
Subject to protection scope.
Claims (20)
1. a kind of video increases steady method, which is characterized in that the video increases steady method and includes:
For the video stream calculation through shooting for being increased the steady information flow of increasing surely compensated to the video flowing;And
Increase steady information flow to the video flowing implementation deformation operation through shooting, to obtain the video flowing after increasing surely based on described.
2. video according to claim 1 increases steady method, which is characterized in that the calculating for increasing steady information flow includes:
Estimation is carried out to the consecutive frame of the video flowing through shooting, to obtain the motion information between the consecutive frame;
And
The compensating parameter for making the content smooth motion in the video flowing through shooting, each frame are calculated based on the motion information
Compensating parameter constitute and described increase steady information flow.
3. video according to claim 2 increases steady method, which is characterized in that the estimation includes:
Foreground detection is carried out, foreground area is obtained;
Several mesh points are set on the image of the foreground area;And
The motion information of the mesh point between the consecutive frame through the video flowing shot on the image of the foreground area is calculated,
Using as the motion information between the consecutive frame.
4. video according to claim 3 increases steady method, which is characterized in that the carry out foreground detection obtains foreground zone
Domain, including:
Face datection is carried out, obtains human face region as the foreground area.
5. video according to claim 3 increases steady method, which is characterized in that the deformation operation includes:For the warp
Each frame of the video flowing of shooting:
Position after the compensation of the mesh point is calculated based on the compensating parameter;And
The mesh point is deformed to position after the compensation.
6. video according to claim 3 increases steady method, which is characterized in that the video increases steady method and further includes:
For at least one mesh point in the foreground area, using positioned at each of at least one mesh point net
The motion information of mesh point around lattice point carries out the low-pass filtering on airspace to respective grid points.
7. video described in any one of -6 increases steady method according to claim 1, which is characterized in that the steady information flow of increasing
It calculates and implements at any one in the following:It shoots the client of video flowing, the server of transfer video flowing and checks video
The client of stream.
8. video described in any one of -6 increases steady method according to claim 1, which is characterized in that the deformation operation is in
Turn the server of video flowing or check in the client of video flowing to implement.
9. video according to claim 1 to 6 increases steady method, which is characterized in that the video increases steady method and answers
For video living transmission system, and the method also includes:
Video flowing real-time perfoming after described increase surely is shown.
10. a kind of video tranquilizer, which is characterized in that the video tranquilizer includes:
Computing module, for being used to increase the video flowing the steady information of increasing surely compensated for the video stream calculation through shooting
Stream;And
Deformation module, for increasing steady information flow to the video flowing implementation deformation operation through shooting, to be increased based on described
Video flowing after steady.
11. video tranquilizer according to claim 10, which is characterized in that the computing module further comprises:
Motion estimation module carries out estimation for the consecutive frame to the video flowing through shooting, described adjacent to obtain
Motion information between frame;And
Motion smoothing module, for calculating the content smooth motion made in the video flowing through shooting based on the motion information
Compensating parameter, the compensating parameter of each frame, which is constituted, described increases steady information flow.
12. video tranquilizer according to claim 11, which is characterized in that the motion estimation module is further used
In:
Foreground detection is carried out, foreground area is obtained;
Several mesh points are set on the image of the foreground area;And
The motion information of the mesh point between the consecutive frame through the video flowing shot on the image of the foreground area is calculated,
Using as the motion information between the consecutive frame.
13. video tranquilizer according to claim 12, which is characterized in that the carry out foreground detection obtains prospect
Region, including:
Face datection is carried out, obtains human face region as the foreground area.
14. video tranquilizer according to claim 12, which is characterized in that the deformation module is further used for:Needle
To each frame of the video flowing through shooting:
Position after the compensation of the mesh point is calculated based on the compensating parameter;And
The mesh point is deformed to position after the compensation.
15. video tranquilizer according to claim 12, which is characterized in that the video tranquilizer further includes:
Airspace filter module, for at least one mesh point in the foreground area, using be located at it is described at least one
The motion information of mesh point around each of mesh point mesh point carries out the low-pass filtering on airspace to respective grid points.
16. video tranquilizer described in any one of 0-15 according to claim 1, which is characterized in that the computing module
It is realized at any one in the following:It shoots the client of video flowing, the server of transfer video flowing and checks video flowing
Client.
17. video tranquilizer described in any one of 0-15 according to claim 1, which is characterized in that the deformation module
Transfer video flowing server or check video flowing client on realize.
18. video tranquilizer described in any one of 0-15 according to claim 1, which is characterized in that the video increases steady
Device is applied to video living transmission system, and described device further includes:
Display module, for showing the video flowing real-time perfoming after described increase surely.
19. a kind of video stability augmentation system, which is characterized in that the video stability augmentation system includes storage device and processor, described
The computer program run by the processor is stored on storage device, the computer program is run by the processor
Video of the Shi Zhihang as described in any one of claim 1-9 increases steady method.
20. a kind of computer-readable medium, which is characterized in that be stored with computer program, institute on the computer-readable medium
It states the video that computer program is executed at runtime as described in any one of claim 1-9 and increases steady method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710408761.4A CN108881668A (en) | 2017-06-02 | 2017-06-02 | Video increases steady method, apparatus, system and computer-readable medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710408761.4A CN108881668A (en) | 2017-06-02 | 2017-06-02 | Video increases steady method, apparatus, system and computer-readable medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108881668A true CN108881668A (en) | 2018-11-23 |
Family
ID=64321081
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710408761.4A Pending CN108881668A (en) | 2017-06-02 | 2017-06-02 | Video increases steady method, apparatus, system and computer-readable medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108881668A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110490075A (en) * | 2019-07-17 | 2019-11-22 | 阿里巴巴集团控股有限公司 | Obtain the method, apparatus and computer-readable medium of stabilizer frame |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060244836A1 (en) * | 2005-04-28 | 2006-11-02 | Texas Instruments Incorporated | Motion stabilization |
US7649549B2 (en) * | 2004-09-27 | 2010-01-19 | Texas Instruments Incorporated | Motion stabilization in video frames using motion vectors and reliability blocks |
CN103426182A (en) * | 2013-07-09 | 2013-12-04 | 西安电子科技大学 | Electronic image stabilization method based on visual attention mechanism |
CN105323420A (en) * | 2014-07-29 | 2016-02-10 | 腾讯科技(深圳)有限公司 | Video image processing method and apparatus |
US20160140695A1 (en) * | 2013-07-23 | 2016-05-19 | Lu Yuan | Adaptive path smoothing for video stabilization |
CN106101535A (en) * | 2016-06-21 | 2016-11-09 | 北京理工大学 | A kind of based on local and the video stabilizing method of mass motion disparity compensation |
-
2017
- 2017-06-02 CN CN201710408761.4A patent/CN108881668A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7649549B2 (en) * | 2004-09-27 | 2010-01-19 | Texas Instruments Incorporated | Motion stabilization in video frames using motion vectors and reliability blocks |
US20060244836A1 (en) * | 2005-04-28 | 2006-11-02 | Texas Instruments Incorporated | Motion stabilization |
CN103426182A (en) * | 2013-07-09 | 2013-12-04 | 西安电子科技大学 | Electronic image stabilization method based on visual attention mechanism |
US20160140695A1 (en) * | 2013-07-23 | 2016-05-19 | Lu Yuan | Adaptive path smoothing for video stabilization |
CN105323420A (en) * | 2014-07-29 | 2016-02-10 | 腾讯科技(深圳)有限公司 | Video image processing method and apparatus |
CN106101535A (en) * | 2016-06-21 | 2016-11-09 | 北京理工大学 | A kind of based on local and the video stabilizing method of mass motion disparity compensation |
Non-Patent Citations (1)
Title |
---|
谢璐 等: "《基于视频稳像和视角变换的公交客流计数方法》", 《计算机应用》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110490075A (en) * | 2019-07-17 | 2019-11-22 | 阿里巴巴集团控股有限公司 | Obtain the method, apparatus and computer-readable medium of stabilizer frame |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11250485B2 (en) | Filtering digital images stored on a blockchain database | |
CN107079141B (en) | Image mosaic for 3 D video | |
US11417130B2 (en) | System and method for facilitating graphic-recognition training of a recognition model | |
CN110809175B (en) | Video recommendation method and device | |
CN108875539B (en) | Expression matching method, device and system and storage medium | |
CN107479699A (en) | Virtual reality exchange method, apparatus and system | |
CN109089038B (en) | Augmented reality shooting method and device, electronic equipment and storage medium | |
CN108875535A (en) | image detecting method, device and system and storage medium | |
CN108876804A (en) | It scratches as model training and image are scratched as methods, devices and systems and storage medium | |
CN109743584B (en) | Panoramic video synthesis method, server, terminal device and storage medium | |
CN108776917B (en) | Synchronous processing method and device for virtual three-dimensional space | |
US20170361158A1 (en) | Analyzing Team Game Play Interactions Using Gaze Data | |
US20180048860A1 (en) | Method and system for measuring quality of video call | |
WO2017092432A1 (en) | Method, device, and system for virtual reality interaction | |
CN109561257A (en) | Picture focusing method, device, terminal and corresponding storage medium | |
CN108765084B (en) | Synchronous processing method and device for virtual three-dimensional space | |
CN108876428A (en) | The calculation method and device of advertisement delivery effect under line | |
US11161029B2 (en) | Sport training on augmented/virtual reality devices by measuring hand-eye coordination-based measurements | |
CN108421240A (en) | Court barrage system based on AR | |
US10296786B2 (en) | Detecting hand-eye coordination in real time by combining camera eye tracking and wearable sensing | |
CN108174227A (en) | Display methods, device and the storage medium of virtual objects | |
US11042778B2 (en) | Generating realistic organ x-ray angiography (XA) images for deep learning consumption | |
CN110363814A (en) | A kind of method for processing video frequency, device, electronic device and storage medium | |
JP2020150519A (en) | Attention degree calculating device, attention degree calculating method and attention degree calculating program | |
CN108881668A (en) | Video increases steady method, apparatus, system and computer-readable 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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181123 |