CN105872448A - Display method and device of video images in video calls - Google Patents

Display method and device of video images in video calls Download PDF

Info

Publication number
CN105872448A
CN105872448A CN201610378309.3A CN201610378309A CN105872448A CN 105872448 A CN105872448 A CN 105872448A CN 201610378309 A CN201610378309 A CN 201610378309A CN 105872448 A CN105872448 A CN 105872448A
Authority
CN
China
Prior art keywords
video image
described
video
background
image
Prior art date
Application number
CN201610378309.3A
Other languages
Chinese (zh)
Inventor
张磊
Original Assignee
宇龙计算机通信科技(深圳)有限公司
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 宇龙计算机通信科技(深圳)有限公司 filed Critical 宇龙计算机通信科技(深圳)有限公司
Priority to CN201610378309.3A priority Critical patent/CN105872448A/en
Publication of CN105872448A publication Critical patent/CN105872448A/en

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00Television systems
    • H04N7/14Systems for two-way working
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00Details of television systems
    • H04N5/222Studio circuitry; Studio devices; Studio equipment ; Cameras comprising an electronic image sensor, e.g. digital cameras, video cameras, TV cameras, video cameras, camcorders, webcams, camera modules for embedding in other devices, e.g. mobile phones, computers or vehicles
    • H04N5/225Television cameras ; Cameras comprising an electronic image sensor, e.g. digital cameras, video cameras, camcorders, webcams, camera modules specially adapted for being embedded in other devices, e.g. mobile phones, computers or vehicles
    • H04N5/232Devices for controlling television cameras, e.g. remote control ; Control of cameras comprising an electronic image sensor
    • H04N5/23229Devices for controlling television cameras, e.g. remote control ; Control of cameras comprising an electronic image sensor comprising further processing of the captured image without influencing the image pickup process
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00Television systems
    • H04N7/14Systems for two-way working
    • H04N7/141Systems for two-way working between two video terminals, e.g. videophone

Abstract

The invention discloses a display method and device of video images in video calls. The method is applied to a first terminal. Both the first terminal and a second terminal have the video call function. The method comprises the following steps that in the video call process of the first terminal and the second terminal, as for each frame of a captured first video image based on real scenes, the foreground portion of the first video image recognized according to preset recognition rules; the foreground portion of the first video image and a predetermined target pseudo background are subjected to image fusion processing, and a second video image corresponding to the first video image is obtained; the second video image is sent to the second terminal, so that the second terminal shows the second video image to a second user. By applying the technical scheme, the entertainment of video calls is enhanced, and user experience is improved.

Description

Video image methods of exhibiting and device in a kind of video calling

Technical field

The present invention relates to video call technology field, particularly relate to video in a kind of video calling Image presentation method and device.

Background technology

Along with mobile communication technology and the fast development of Internet technology, video call technology also by Gradually grow up.Video calling, it is possible to achieve aspectant phase between the user of various location Exchange and conmmunication mutually.

In video call process, two parties is it can be seen that true field residing for the other user Scape.In actual applications, the demand of user is diversified, and some users are for certain purpose Consider, as protected individual privacy, or amusement etc., may be not intended to show certainly to the other user The real scene at own place.In this case, user can only be by not using the video of terminal Call function avoids showing the real scene at oneself place to the other side, makes user lack and it He user carries out the enjoyment of video calling, and Consumer's Experience is poor.

Summary of the invention

It is an object of the invention to provide video image methods of exhibiting and device in a kind of video calling, To be not desired in the case of other users show the real scene at self place user, it is also possible to Carry out video calling, promote Consumer's Experience.

Video image methods of exhibiting in a kind of video calling, is applied to first terminal, and described first Terminal and the second terminal are respectively provided with video call function, and described method includes:

Carrying out in video call process with described second terminal, for each frame base captured In the first video image of real scene, it is performed both by following steps:

According to default recognition rule, identify the foreground part in this first video image;

Foreground part in this first video image is carried out with predetermined target puppet background Image co-registration processes, it is thus achieved that second video image corresponding with this first video image;

This second video image is sent to described second terminal, so that described second terminal is to Two users show this second video image.

In a kind of detailed description of the invention of the present invention, determine that described target is pseudo-by following steps Background:

Receive the first user selection instruction for the pseudo-background in default pseudo-background resources bank;

Selection instruction according to described first user, determines target puppet background.

In a kind of detailed description of the invention of the present invention, described determine target puppet background after, Described method also includes:

Receive the described first user instruction for previewing to described target puppet background;

According to described instruction for previewing, catch the of real scene based on described first user place Three video images;

For each frame the 3rd video image captured, according to described recognition rule, identifying should Foreground part in 3rd video image, by the foreground part in the 3rd video image with described Target puppet background carries out image co-registration process, it is thus achieved that fourth corresponding with the 3rd video image regards Frequently image, shows described first user by the 4th video image output.

In a kind of detailed description of the invention of the present invention, in this first video image of described identification Foreground part after, described by the foreground part in this first video image with predetermined Before target puppet background carries out image co-registration process, described method also includes:

Determine in the foreground part in this first video image and former frame the first video image The display size relation of foreground part;

According to the display size relation determined, the display adjusting described target puppet background is big Little.

In a kind of detailed description of the invention of the present invention, described target puppet background is dynamic background, Described foreground part in this first video image and predetermined target puppet background are carried out figure Picture fusion treatment, including:

According to default corresponding relation, determine that the described target corresponding with this first video image is pseudo- The target video frame of background;

With described target video frame, the foreground part in this first video image is carried out image melt Conjunction processes.

In a kind of detailed description of the invention of the present invention, at described acquisition and this first video image After the second corresponding video image, described method also includes:

This second video image is only shown to described first user;

Or,

Show this first video image and this second video image to described first user simultaneously.

In a kind of detailed description of the invention of the present invention, described method also includes:

While showing this second video image to described first user, export show this The moment of two video images, the playing duration of described target puppet background.

Video image exhibiting device in a kind of video calling, is applied to first terminal, and described first Terminal and the second terminal are respectively provided with video call function, and described device includes:

Foreground part identification module, for carrying out video call process with described second terminal In, for each frame captured the first video image based on real scene, according to default Recognition rule, identifies the foreground part in this first video image;

Video image obtains module, for described foreground part identification module is recognized this Foreground part in one video image and predetermined target puppet background are carried out at image co-registration Reason, it is thus achieved that second video image corresponding with this first video image;

Video image sending module, for by described video image obtain module obtain this second Video image is sent to described second terminal, so that described second terminal shows this to the second user Second video image.

In a kind of detailed description of the invention of the present invention, described device also includes that target puppet background is true Cover half block, for determining described target puppet background by following steps:

Receive the first user selection instruction for the pseudo-background in default pseudo-background resources bank;

Selection instruction according to described first user, determines target puppet background.

In a kind of detailed description of the invention of the present invention, described device also includes that target puppet background is pre- Look at module, be used for:

Described determine target puppet background after, receive described first user and described target puppet carried on the back The instruction for previewing of scape;

According to described instruction for previewing, catch the of real scene based on described first user place Three video images;

For each frame the 3rd video image captured, according to described recognition rule, identifying should Foreground part in 3rd video image, by the foreground part in the 3rd video image with described Target puppet background carries out image co-registration process, it is thus achieved that fourth corresponding with the 3rd video image regards Frequently image, shows described first user by the 4th video image output.

In a kind of detailed description of the invention of the present invention, described device also includes showing that size adjusts Module, is used for:

After foreground part in this first video image of described identification, described this first is regarded Frequently the foreground part in image and predetermined target puppet background carry out image co-registration and process it Before, before determining in the foreground part in this first video image and former frame the first video image The display size relation of scape part;

According to the display size relation determined, the display adjusting described target puppet background is big Little.

In a kind of detailed description of the invention of the present invention, described target puppet background is dynamic background, Described video image obtains module, specifically for:

According to default corresponding relation, determine that the described target corresponding with this first video image is pseudo- The target video frame of background;

With described target video frame, the foreground part in this first video image is carried out image melt Conjunction processes.

In a kind of detailed description of the invention of the present invention, described device also includes display module, uses In:

After the second video image that described acquisition is corresponding with this first video image, to described First user only shows this second video image;Or,

Show this first video image and this second video image to described first user simultaneously.

In a kind of detailed description of the invention of the present invention, described device also includes that playing duration is shown Module, is used for:

While showing this second video image to described first user, export show this The moment of two video images, the playing duration of described target puppet background.

The technical scheme that the application embodiment of the present invention is provided, first terminal can predefine mesh The pseudo-background of mark, so carries out in video call process at first terminal and the second terminal, and first eventually End, for each frame captured the first video image based on real scene, can identify this Foreground part in first video image, and this foreground part and target puppet background are carried out image Fusion treatment, it is thus achieved that the second video image, and the second video image is sent to the second terminal, Such second terminal display is to second video image of the second user and comprises target puppet background Video image, it is achieved that be not desired to show to the second user the true field at self place at first user In the case of scape, first user also is able to carry out the purpose of video calling with the second user, strengthens Video calling recreational, improves Consumer's Experience.

Accompanying drawing explanation

For the clearer explanation embodiment of the present invention or the technical scheme of prior art, below will The accompanying drawing used required in embodiment or description of the prior art is briefly described, aobvious and easy Insight, the accompanying drawing in describing below is only some embodiments of the present invention, general for this area From the point of view of logical technical staff, on the premise of not paying creative work, it is also possible to attached according to these Figure obtains other accompanying drawing.

Fig. 1 is the enforcement of video image methods of exhibiting in a kind of video calling in the embodiment of the present invention Flow chart;

Fig. 2 is the structure of video image exhibiting device in a kind of video calling in the embodiment of the present invention Schematic diagram.

Detailed description of the invention

In order to make those skilled in the art be more fully understood that the present invention program, below in conjunction with the accompanying drawings The present invention is described in further detail with detailed description of the invention.Obviously, described enforcement Example is only a part of embodiment of the present invention rather than whole embodiments.Based in the present invention Embodiment, those of ordinary skill in the art are obtained under not making creative work premise Every other embodiment, broadly fall into the scope of protection of the invention.

Embodiments provide video image methods of exhibiting in a kind of video calling.The method It is applied to first terminal.First terminal and the second terminal can carry out video calling, as passed through 3G Network carries out video calling, or by LTE (Long Term Evolution, Long Term Evolution) Network carries out video calling, or carries out video calling by internet.It is to say, first Terminal and the second terminal are respectively provided with video call function.

In embodiments of the present invention, use the user of first terminal to be first user, use the The user of two terminals is the second user.It is not desired to show oneself institute to the second user at first user Real scene in the case of, first terminal can be according to the corresponding instruction of first user, really Set the goal pseudo-background.So, first terminal is carrying out in video call process with the second terminal, The technical scheme that the embodiment of the present invention can be applied to be provided carries out true and false background replacement, and will bag The second video image containing target puppet background is sent to the second terminal, and the second terminal is by such Two video images show the second user.So, the video image that the second user sees is bag Video image containing target puppet background.

In embodiments of the present invention, first terminal and the second terminal carry out in video call process, Can catch the first video image based on real scene, continuous print multiframe the first video image is i.e. May make up a video.For each frame captured the first video image based on real scene, First terminal all can perform the operation of step shown in Fig. 1.

Shown in Figure 1, by video figure in a kind of video calling that the embodiment of the present invention is provided As the implementing procedure figure of methods of exhibiting, the method may comprise steps of:

S110: according to default recognition rule, identify the foreground part in this first video image.

First terminal, after setting up video calling with the second terminal, can trigger internal or external Camera catches the first video image based on first user place real scene.For capturing Each frame the first video image, first terminal can according to default recognition rule, identify should Foreground part in first video image.Certainly, in this first video image, except foreground portion Part exceptionally is the background parts of this first video image.

In embodiments of the present invention, for the recognition rule of the foreground part in video image, can To be set as the case may be and to adjust.Such as, special if video image exists face Levy, then face is defined as the foreground part of this video image.

S120: by the foreground part in this first video image and predetermined target puppet background Carry out image co-registration process, it is thus achieved that second video image corresponding with this first video image.

In embodiments of the present invention, it may be predetermined that puppet to be used in video call process Background, this puppet background is target puppet background.

In a kind of detailed description of the invention of the present invention, can determine that target is pseudo-by following steps Background:

Step one: receive the first user choosing for the pseudo-background in default pseudo-background resources bank Select instruction;

Step 2: instruct according to the selection of first user, determine target puppet background.

For ease of describing, above-mentioned two step is combined and illustrates.

In embodiments of the present invention, a pseudo-background resources bank, this puppet background can be obtained ahead of time Resources bank can comprise multiple pseudo-background.

In actual applications, pseudo-background resources bank can be stored in first terminal, is used by first Family creates, or first terminal communicates with server, obtains from server.When first When user has the demand of camouflage video image background, can be in the pseudo-background money of first terminal storage Source selects in storehouse, and sends for the pseudo-background in pseudo-background resources bank to first terminal Select instruction.After first terminal receives this selection instruction, instruct according to this selection, can be true Set the goal pseudo-background.Will user select pseudo-background be defined as target puppet background.

For saving terminal storage resource, pseudo-background resources bank can also store in the server.When When first user has the demand of camouflage video image background, first terminal can be set up with server Communication connection, first user passes through first terminal login service device, the puppet stored in the server Background resources bank selects, and sends for the puppet in pseudo-background resources bank to first terminal The selection instruction of background.First terminal according to this selection instruct after, can be from server under Carry the pseudo-background that first user selects, and this puppet background is defined as target puppet background.

Pseudo-background resources bank can comprise the pseudo-background that technical staff sets, it is also possible to comprise use The self-defining pseudo-background in family.In actual applications, first user can be with self-defined pseudo-background.? In self-defined pseudo-context process, first user need to be by the video of oneself recording or the photo of shooting Being sent to first terminal, video or photo that first user can be sent by first terminal are carried out Respective handling, or by this video or photo upload to server, server carry out corresponding position Reason, as complied with default frame per second, resolution ratio etc., regarding after then first terminal will process Frequency or photo are as in pseudo-context update to pseudo-background resources bank.

In actual applications, first user can carry out the choosing of pseudo-background before video calling Select, it is also possible in video call process, carry out the selection of pseudo-background.

If first user carried out the selection of pseudo-background, then first terminal root before video calling Instruct according to the selection of first user, after determining target puppet background, can be at ensuing video Call is applied this target puppet background, it is also possible to only should in ensuing first time video calling By this target puppet background.Or, before applying this target puppet background in carrying out video calling, Show information to first user, be confirmed whether to apply this target puppet background.

If first user carries out the selection of pseudo-background, then first terminal in video call process Selection instruction according to first user, after determining target puppet background, can lead at current video This target puppet background is applied during words, or by before this target puppet background replacement current time Determined by target puppet background.

Identify the foreground part of the first video image in step S110, by this foreground part with Target puppet background carries out image co-registration process, it is possible to obtain corresponding with this first video image Two video images.

Concrete, after identifying the foreground part of the first video image, this prospect can be extracted Part, is embedded into this foreground part in target puppet background by image co-registration treatment technology, obtains Obtain the second video image.So, it is thus achieved that foreground part and first video of the second video image The foreground part of image is identical, and the background parts of the second video image is target puppet background.

Or, after identifying the foreground part of the first video image, the background of the first video image Part namely identified, target puppet background can be replaced the background portion of this first video image Point, it is thus achieved that the second video image.So, it is thus achieved that the foreground part of the second video image be still The foreground part of the first video image, the background parts of the second video image is target puppet background.

In embodiments of the present invention, target puppet background can be static background, it is also possible to be dynamic Background.

When target puppet background is static background, for each frame the first video image captured After carrying out true and false background replacement, the background parts of each frame the second video image obtained is phase With, it is this static background.

When target puppet background is dynamic background, for each frame the first video image captured When carrying out the replacement of true and false background, the background parts of each frame the second video image obtained is not With, for the different video frame of this dynamic background.

In a kind of detailed description of the invention of the present invention, it is the feelings of dynamic background in target puppet background Under condition, the foreground part in this first video image is carried out with predetermined target puppet background Image co-registration processes, and specifically can be carried out by following steps:

First step: according to default corresponding relation, determines corresponding with this first video image The target video frame of target puppet background;

Second step: the foreground part in this first video image is carried out with target video frame Image co-registration processes.

For ease of describing, above-mentioned two step is combined and illustrates.

Being dynamic background in target puppet background, during such as video, this target puppet background is by multiple videos Frame is constituted.For each frame the first video image captured, can be according to default corresponding pass System, determines the target video frame of the target puppet background corresponding with this first video image.Such as, If this first video image is the first frame, then with this first video image corresponding target video frame It is the first frame frame of video of target puppet background.

After determining the target video frame of the target puppet background corresponding with this first video image, can So that the foreground part of this first video image and this target video frame are carried out image co-registration process.

As such, it is possible to obtain second video image corresponding with this first video image, this is second years old The foreground part of video image is identical with the foreground part of this first video image, this second video The background parts of image is this target video frame.

S130: this second video image is sent to the second terminal, so that the second terminal is to second User shows this second video image.

In step S120, for each frame the first video image captured, all can obtain and be somebody's turn to do The second video image that first video image is corresponding.This second video image is sent to second eventually End, the second terminal can show this second video image to the second user.From the second user perspective For, multiple continuous print the second video images can be presented as video, and what it was seen is bag Contain the video of pseudo-background.

The technical scheme that the application embodiment of the present invention is provided, first terminal can predefine mesh The pseudo-background of mark, so carries out in video call process at first terminal and the second terminal, and first eventually End, for each frame captured the first video image based on real scene, can identify this Foreground part in first video image, and this foreground part and target puppet background are carried out image Fusion treatment, it is thus achieved that the second video image, and the second video image is sent to the second terminal, Such second terminal display is to second video image of the second user and comprises target puppet background Video image, it is achieved that be not desired to show to the second user the true field at self place at first user In the case of scape, first user also is able to carry out the purpose of video calling with the second user, strengthens Video calling recreational, improves Consumer's Experience.

In one embodiment of the invention, after determining target puppet background, the method also may be used To comprise the following steps:

Step one: receive the first user instruction for previewing to target puppet background;

Step 2: according to instruction for previewing, catch the of real scene based on first user place Three video images;

Step 3: for each frame the 3rd video image captured, according to recognition rule, know Foreground part in not the 3rd video image, by the foreground part in the 3rd video image with Target puppet background carries out image co-registration process, it is thus achieved that fourth corresponding with the 3rd video image regards Frequently image, shows first user by the 4th video image output.

For ease of describing, above three step is combined and illustrates.

It is understood that when first user selects for the pseudo-background in pseudo-background resources bank Selecting, after first terminal determines target puppet background, first user can check this by preview mode The camouflage effectiveness of target puppet background, if be unsatisfied with camouflage effectiveness, can reselect puppet again Background, this way it is possible to avoid first user in video call process because camouflage effectiveness difference and The situation causing call awkward occurs.

When first user has the demand to target puppet BACKGROUNDA preview, can send to first terminal Corresponding instruction for previewing, concrete, first terminal can be that first user provides preview button, When first user clicks on this preview button, i.e. can be considered and have issued for target to first terminal The instruction for previewing of pseudo-background.

First terminal receives the first user instruction for previewing to target puppet background, refers to according to this preview Order, can catch real scene based on first user place by internal or external camera 3rd video image.For each frame the 3rd video image captured, first terminal can root According to above-mentioned recognition rule, identify the foreground part of the 3rd video image, regard the 3rd Frequently the foreground part of image and target puppet background carry out image co-registration process, it is thus achieved that regard with the 3rd Frequently the 4th video image that image is corresponding, and the 4th video image output is showed the first use Family.

Foreground part is identified, carries out the detailed description of the invention of image co-registration process etc., can With reference to the explanation to Fig. 1 illustrated embodiment, not repeat them here.

So, first user can view the camouflage effectiveness of target puppet background, according to camouflage effect Really, it is determined whether reselect pseudo-background.

In one embodiment of the invention, after step silo, before step S120, The method can also comprise the following steps:

First step: determine that the foreground part in this first video image regards with former frame first Frequently the display size relation of the foreground part in image;

Second step: according to the display size relation determined, adjust target puppet background Display size.

For ease of describing, above-mentioned two step is combined and illustrates.

It is understood that first user use first terminal is in carrying out video call process, Will not transfixion always, it may adjust instant the internal or external of first terminal that adjust and take the photograph As head and the distance of self.In this case, each frame first that first terminal captures regards Frequently the display size of the foreground part in image can change.From the point of view of first user angle, should Foreground part may zoom in or out.First terminal is for each frame the first video image, all Before may determine that in the foreground part in this first video image and former frame the first video image The display size relation of scape part, and according to the display size relation determined, permissible Adjust the display size of target puppet background, so can ensure that the vivid effect of pseudo-background.

Such as, for a certain frame the first video image captured, if this first video image In foreground part compared with the foreground part in former frame the first video image, be exaggerated 50%, Then show that the internal or external camera of first terminal and the distance of first user further, at this In the case of Zhong, according to this display size relation, can be by big for the display of target puppet background Little amplification 50%.

In one embodiment of the invention, first terminal is obtaining and this first video image pair After the second video image answered, it is also possible to show this second video image to first user, or Person, shows this first video image and this second video image to first user simultaneously.

In actual applications, what first terminal was shown on self screen can be only, and this first regards Frequently image, it is also possible to be only this second video image, it is also possible to subregion is same on self screen Time show this first video image and this second video image, so that first user is seen in real time Examine true and false background.

First terminal, while showing this second video image to first user, exports and is showing The moment of this second video image, the playing duration of target puppet background.So, user is permissible Recognize the playing duration of target puppet background in real time, can actively terminate before broadcasting terminates with The video calling of the second user, it is to avoid target puppet background loop is play or shows real scene Situation occurs.

Application above method embodiment, the embodiment of the present invention additionally provides in a kind of video calling Video image exhibiting device.It is equal that this device is applied to first terminal, first terminal and the second terminal There is video call function.

Shown in Figure 2, for video image in a kind of video calling that the embodiment of the present invention provides The structural representation of exhibiting device, this device can include with lower module:

Foreground part identification module 210, for carrying out in video call process with the second terminal, For each frame captured the first video image based on real scene, according to default identification Rule, identifies the foreground part in this first video image;

Video image obtains module 220, for recognized by foreground part identification module 210 Foreground part in this first video image and predetermined target puppet background carry out image co-registration Process, it is thus achieved that second video image corresponding with this first video image;

Video image sending module 230, should for what video image obtained module 220 obtains Second video image is sent to the second terminal so that the second terminal to the second user show this second Video image.

The device that the application embodiment of the present invention is provided, it is pseudo-that first terminal can predefine target Background, so carries out in video call process at first terminal and the second terminal, first terminal pin First video image based on real scene to each frame captured, can identify this first Foreground part in video image, and this foreground part and target puppet background are carried out image co-registration Process, it is thus achieved that the second video image, and the second video image is sent to the second terminal, so Second terminal display is the video comprising target puppet background to second video image of the second user Image, it is achieved that be not desired to show to the second user the real scene at self place at first user In the case of, first user also is able to carry out the purpose of video calling with the second user, enhances and regards It is recreational that frequency is conversed, and improves Consumer's Experience.

In one embodiment of the invention, this device can also include that target puppet background determines mould Block, for determining target puppet background by following steps:

Receive the first user selection instruction for the pseudo-background in default pseudo-background resources bank;

Selection instruction according to first user, determines target puppet background.

In one embodiment of the invention, this device can also include target puppet BACKGROUNDA preview mould Block, is used for:

After determining target puppet background, receive first user and the preview of target puppet background is referred to Order;

According to instruction for previewing, catch the 3rd video figure of real scene based on first user place Picture;

For each frame the 3rd video image captured, according to recognition rule, identify the 3rd Foreground part in video image, carries on the back the foreground part in the 3rd video image with target puppet Scape carries out image co-registration process, it is thus achieved that fourth video image corresponding with the 3rd video image, 4th video image output is showed first user.

In a kind of detailed description of the invention of the present invention, pseudo-background resources bank comprises first user Self-defining pseudo-background.

In one embodiment of the invention, this device can also include showing that size adjusts mould Block, is used for:

After foreground part in identifying this first video image, by this first video image Foreground part and predetermined target puppet background carry out image co-registration process before, determine this Foreground part in first video image is aobvious with the foreground part in former frame the first video image Show size relation;

According to the display size relation determined, adjust the display size of target puppet background.

In one embodiment of the invention, target puppet background is dynamic background, and video image obtains Module 220, can be specifically for:

According to default corresponding relation, determine the target puppet background corresponding with this first video image Target video frame;

Foreground part in this first video image and target video frame are carried out at image co-registration Reason.

In one embodiment of the invention, this device can also include display module, is used for:

After obtaining second video image corresponding with this first video image, to first user Only show this second video image;Or,

Show this first video image and this second video image to first user simultaneously.

In one embodiment of the invention, this device can also include that playing duration shows mould Block, is used for:

While showing this second video image to first user, export and showing that this second regards Frequently the moment of image, the playing duration of target puppet background.

In this specification, each embodiment uses the mode gone forward one by one to describe, and each embodiment emphasis is said Bright is all the difference with other embodiments, same or similar part between each embodiment See mutually.For device disclosed in embodiment, disclosed in itself and embodiment Method is corresponding, so describe is fairly simple, relevant part sees method part and illustrates.

Professional further appreciates that, describes in conjunction with the embodiments described herein The unit of each example and algorithm steps, it is possible to electronic hardware, computer software or the two Be implemented in combination in, in order to clearly demonstrate the interchangeability of hardware and software, in described above In generally described composition and the step of each example according to function.These functions are actually Perform with hardware or software mode, depend on application-specific and the design constraint of technical scheme Condition.Each specifically should being used for can be used different methods to realize institute by professional and technical personnel The function described, but this realization is it is not considered that beyond the scope of this invention.

The method described in conjunction with the embodiments described herein or the step of algorithm can be direct Implement with hardware, the software module of processor execution, or the combination of the two.Software module Random access memory (RAM), internal memory, read-only storage (ROM), electrically programmable can be placed in ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM, Or in any other form of storage medium well known in technical field.

Above to video image methods of exhibiting and dress in a kind of video calling provided by the present invention Put and be described in detail.Specific case used herein is to the principle of the present invention and embodiment party Formula is set forth, the explanation of above example be only intended to help to understand the method for the present invention and Its core concept.It should be pointed out that, for those skilled in the art, not On the premise of departing from the principle of the invention, it is also possible to the present invention is carried out some improvement and modification, this A little improvement and modification also fall in the protection domain of the claims in the present invention.

Claims (14)

1. video image methods of exhibiting in a video calling, it is characterised in that be applied to One terminal, described first terminal and the second terminal are respectively provided with video call function, described method bag Include:
Carrying out in video call process with described second terminal, for each frame base captured In the first video image of real scene, it is performed both by following steps:
According to default recognition rule, identify the foreground part in this first video image;
Foreground part in this first video image is carried out with predetermined target puppet background Image co-registration processes, it is thus achieved that second video image corresponding with this first video image;
This second video image is sent to described second terminal, so that described second terminal is to Two users show this second video image.
Method the most according to claim 1, it is characterised in that true by following steps Fixed described target puppet background:
Receive the first user selection instruction for the pseudo-background in default pseudo-background resources bank;
Selection instruction according to described first user, determines target puppet background.
Method the most according to claim 2, it is characterised in that determine target described After pseudo-background, described method also includes:
Receive the described first user instruction for previewing to described target puppet background;
According to described instruction for previewing, catch the of real scene based on described first user place Three video images;
For each frame the 3rd video image captured, according to described recognition rule, identifying should Foreground part in 3rd video image, by the foreground part in the 3rd video image with described Target puppet background carries out image co-registration process, it is thus achieved that fourth corresponding with the 3rd video image regards Frequently image, shows described first user by the 4th video image output.
Method the most according to claim 1, it is characterised in that described identification this After foreground part in one video image, described by the foreground part in this first video image Before carrying out image co-registration process with predetermined target puppet background, described method also includes:
Determine in the foreground part in this first video image and former frame the first video image The display size relation of foreground part;
According to the display size relation determined, the display adjusting described target puppet background is big Little.
5. according to the method described in any one of Claims 1-4, it is characterised in that described Target puppet background is dynamic background, described by the foreground part in this first video image with in advance The target puppet background determined carries out image co-registration process, including:
According to default corresponding relation, determine that the described target corresponding with this first video image is pseudo- The target video frame of background;
With described target video frame, the foreground part in this first video image is carried out image melt Conjunction processes.
Method the most according to claim 5, it is characterised in that described acquisition with should After the second video image that first video image is corresponding, described method also includes:
This second video image is only shown to described first user;
Or,
Show this first video image and this second video image to described first user simultaneously.
Method the most according to claim 6, it is characterised in that described method also includes:
While showing this second video image to described first user, export show this The moment of two video images, the playing duration of described target puppet background.
8. video image exhibiting device in a video calling, it is characterised in that be applied to One terminal, described first terminal and the second terminal are respectively provided with video call function, described device bag Include:
Foreground part identification module, for carrying out video call process with described second terminal In, for each frame captured the first video image based on real scene, according to default Recognition rule, identifies the foreground part in this first video image;
Video image obtains module, for described foreground part identification module is recognized this Foreground part in one video image and predetermined target puppet background are carried out at image co-registration Reason, it is thus achieved that second video image corresponding with this first video image;
Video image sending module, for by described video image obtain module obtain this second Video image is sent to described second terminal, so that described second terminal shows this to the second user Second video image.
Device the most according to claim 8, it is characterised in that described device also includes Target puppet background determination module, for determining described target puppet background by following steps:
Receive the first user selection instruction for the pseudo-background in default pseudo-background resources bank;
Selection instruction according to described first user, determines target puppet background.
Device the most according to claim 9, it is characterised in that described device also includes Target puppet BACKGROUNDA preview module, is used for:
Described determine target puppet background after, receive described first user and described target puppet carried on the back The instruction for previewing of scape;
According to described instruction for previewing, catch the of real scene based on described first user place Three video images;
For each frame the 3rd video image captured, according to described recognition rule, identifying should Foreground part in 3rd video image, by the foreground part in the 3rd video image with described Target puppet background carries out image co-registration process, it is thus achieved that fourth corresponding with the 3rd video image regards Frequently image, shows described first user by the 4th video image output.
11. devices according to claim 8, it is characterised in that described device also includes Display size adjusting module, is used for:
After foreground part in this first video image of described identification, described this first is regarded Frequently the foreground part in image and predetermined target puppet background carry out image co-registration and process it Before, before determining in the foreground part in this first video image and former frame the first video image The display size relation of scape part;
According to the display size relation determined, the display adjusting described target puppet background is big Little.
12. according to Claim 8 to the device described in 11 any one, it is characterised in that described Target puppet background is dynamic background, and described video image obtains module, specifically for:
According to default corresponding relation, determine that the described target corresponding with this first video image is pseudo- The target video frame of background;
With described target video frame, the foreground part in this first video image is carried out image melt Conjunction processes.
13. devices according to claim 12, it is characterised in that described device also wraps Include display module, be used for:
After the second video image that described acquisition is corresponding with this first video image, to described First user only shows this second video image;Or,
Show this first video image and this second video image to described first user simultaneously.
14. devices according to claim 13, it is characterised in that described device also wraps Include playing duration display module, be used for:
While showing this second video image to described first user, export show this The moment of two video images, the playing duration of described target puppet background.
CN201610378309.3A 2016-05-31 2016-05-31 Display method and device of video images in video calls CN105872448A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610378309.3A CN105872448A (en) 2016-05-31 2016-05-31 Display method and device of video images in video calls

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610378309.3A CN105872448A (en) 2016-05-31 2016-05-31 Display method and device of video images in video calls
PCT/CN2016/107936 WO2017206456A1 (en) 2016-05-31 2016-11-30 Method and apparatus for presenting video image in video call

Publications (1)

Publication Number Publication Date
CN105872448A true CN105872448A (en) 2016-08-17

Family

ID=56643138

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610378309.3A CN105872448A (en) 2016-05-31 2016-05-31 Display method and device of video images in video calls

Country Status (2)

Country Link
CN (1) CN105872448A (en)
WO (1) WO2017206456A1 (en)

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106254784A (en) * 2016-09-29 2016-12-21 宇龙计算机通信科技(深圳)有限公司 A kind of method and device of Video processing
CN106878588A (en) * 2017-02-27 2017-06-20 努比亚技术有限公司 A kind of video background blurs terminal and method
CN106954034A (en) * 2017-03-28 2017-07-14 宇龙计算机通信科技(深圳)有限公司 A kind of image processing method and device
CN107317990A (en) * 2017-06-27 2017-11-03 宇龙计算机通信科技(深圳)有限公司 Video call method, device, user terminal and computer-readable recording medium
WO2017206456A1 (en) * 2016-05-31 2017-12-07 宇龙计算机通信科技(深圳)有限公司 Method and apparatus for presenting video image in video call
CN107592490A (en) * 2017-09-11 2018-01-16 广东欧珀移动通信有限公司 Video background replacement method, device and mobile terminal
CN107610076A (en) * 2017-09-11 2018-01-19 广东欧珀移动通信有限公司 Image processing method and device, electronic installation and computer-readable recording medium
CN107610077A (en) * 2017-09-11 2018-01-19 广东欧珀移动通信有限公司 Image processing method and device, electronic installation and computer-readable recording medium
CN107623832A (en) * 2017-09-11 2018-01-23 广东欧珀移动通信有限公司 Video background replacement method, device and mobile terminal
CN107644440A (en) * 2017-09-11 2018-01-30 广东欧珀移动通信有限公司 Image processing method and device, electronic installation and computer-readable recording medium
CN107959790A (en) * 2017-11-15 2018-04-24 维沃移动通信有限公司 A kind of image capturing method, device and mobile terminal
CN108010037A (en) * 2017-11-29 2018-05-08 腾讯科技(深圳)有限公司 Image processing method, device and storage medium
CN108737765A (en) * 2018-08-02 2018-11-02 广东小天才科技有限公司 A kind of video calling processing method, device, terminal device and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050140802A1 (en) * 2003-12-27 2005-06-30 Samsung Electronics Co., Ltd. Method for synthesizing photographed image with background scene in appratus having a camera
CN101309389A (en) * 2008-06-19 2008-11-19 深圳华为通信技术有限公司 Method, apparatus and terminal synthesizing visual images
CN101610421A (en) * 2008-06-17 2009-12-23 深圳华为通信技术有限公司 Video communication method, video communication device and video communication system
CN101677386A (en) * 2008-08-01 2010-03-24 中兴通讯股份有限公司 System capable of selecting real-time virtual call background and video call method
CN101946500A (en) * 2007-12-17 2011-01-12 斯坦·考塞瑞德 Real time video inclusion system
EP2556425A1 (en) * 2010-04-07 2013-02-13 Apple Inc. Device, method, and graphical user interface for managing folders

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8265392B2 (en) * 2006-02-07 2012-09-11 Qualcomm Incorporated Inter-mode region-of-interest video object segmentation
TWI376930B (en) * 2006-09-04 2012-11-11 Via Tech Inc Scenario simulation system and method for a multimedia device
CN101193261B (en) * 2007-03-28 2010-07-21 腾讯科技(深圳)有限公司 Video communication system and method
CN102387311A (en) * 2010-09-02 2012-03-21 Tcl集团股份有限公司 Device for synthesizing video images and method for synthesizing video images
CN102098381A (en) * 2010-12-29 2011-06-15 上海华勤通讯技术有限公司 Backgrounded conversation realizing method for mobile phone
CN103607554B (en) * 2013-10-21 2017-10-20 易视腾科技股份有限公司 It is a kind of based on full-automatic face without the image synthesizing method being stitched into
CN105872448A (en) * 2016-05-31 2016-08-17 宇龙计算机通信科技(深圳)有限公司 Display method and device of video images in video calls

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050140802A1 (en) * 2003-12-27 2005-06-30 Samsung Electronics Co., Ltd. Method for synthesizing photographed image with background scene in appratus having a camera
CN101946500A (en) * 2007-12-17 2011-01-12 斯坦·考塞瑞德 Real time video inclusion system
CN101610421A (en) * 2008-06-17 2009-12-23 深圳华为通信技术有限公司 Video communication method, video communication device and video communication system
CN101309389A (en) * 2008-06-19 2008-11-19 深圳华为通信技术有限公司 Method, apparatus and terminal synthesizing visual images
CN101677386A (en) * 2008-08-01 2010-03-24 中兴通讯股份有限公司 System capable of selecting real-time virtual call background and video call method
EP2556425A1 (en) * 2010-04-07 2013-02-13 Apple Inc. Device, method, and graphical user interface for managing folders

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017206456A1 (en) * 2016-05-31 2017-12-07 宇龙计算机通信科技(深圳)有限公司 Method and apparatus for presenting video image in video call
CN106254784A (en) * 2016-09-29 2016-12-21 宇龙计算机通信科技(深圳)有限公司 A kind of method and device of Video processing
CN106878588A (en) * 2017-02-27 2017-06-20 努比亚技术有限公司 A kind of video background blurs terminal and method
CN106954034A (en) * 2017-03-28 2017-07-14 宇龙计算机通信科技(深圳)有限公司 A kind of image processing method and device
CN107317990A (en) * 2017-06-27 2017-11-03 宇龙计算机通信科技(深圳)有限公司 Video call method, device, user terminal and computer-readable recording medium
CN107610076A (en) * 2017-09-11 2018-01-19 广东欧珀移动通信有限公司 Image processing method and device, electronic installation and computer-readable recording medium
CN107592490A (en) * 2017-09-11 2018-01-16 广东欧珀移动通信有限公司 Video background replacement method, device and mobile terminal
CN107610077A (en) * 2017-09-11 2018-01-19 广东欧珀移动通信有限公司 Image processing method and device, electronic installation and computer-readable recording medium
CN107623832A (en) * 2017-09-11 2018-01-23 广东欧珀移动通信有限公司 Video background replacement method, device and mobile terminal
CN107644440A (en) * 2017-09-11 2018-01-30 广东欧珀移动通信有限公司 Image processing method and device, electronic installation and computer-readable recording medium
CN107959790A (en) * 2017-11-15 2018-04-24 维沃移动通信有限公司 A kind of image capturing method, device and mobile terminal
CN108010037A (en) * 2017-11-29 2018-05-08 腾讯科技(深圳)有限公司 Image processing method, device and storage medium
CN108737765A (en) * 2018-08-02 2018-11-02 广东小天才科技有限公司 A kind of video calling processing method, device, terminal device and storage medium

Also Published As

Publication number Publication date
WO2017206456A1 (en) 2017-12-07

Similar Documents

Publication Publication Date Title
CN105122794B (en) Camera occlusion detection
TWI462566B (en) Switching cameras during a video conference of a multi-camera mobile device
US9332194B2 (en) Imaging apparatus for obtaining a user-intended image when orientation of the imaging apparatus changes in applying a special effect that changes the image quality in a set direction
US9615012B2 (en) Using a second camera to adjust settings of first camera
US20120069143A1 (en) Object tracking and highlighting in stereoscopic images
US8866943B2 (en) Video camera providing a composite video sequence
KR100565269B1 (en) Method for taking a photograph by mobile terminal with camera function
US9172888B2 (en) Determining exposure times using split paxels
US8964060B2 (en) Determining an image capture payload burst structure based on a metering image capture sweep
US20170085770A1 (en) Mobile terminal photographing method and mobile terminal
KR101864059B1 (en) Mobile terminal and shooting method thereof
CN103024165B (en) Method and device for automatically setting shooting mode
US20130120602A1 (en) Taking Photos With Multiple Cameras
CN103037164A (en) Imaging apparatus, imaging system, and imaging method
CN103297697A (en) Method and device for displaying template pictures during photographing
JP2004201191A (en) Image processing and transmitting system, cellular phone, and method and program for image processing and transmission
CN103220490A (en) Special effect implementation method in video communication and video user terminal
KR20150099302A (en) Electronic device and control method of the same
US20130120592A1 (en) Method for wireless sharing of images
US9253340B2 (en) Wireless camera with image sharing prioritization
CN102685306B (en) Method and mobile terminal for switching image collecting units
CN102209195A (en) Imaging apparatus, image processing apparatus,image processing method, and program
US9066017B2 (en) Viewfinder display based on metering images
US10341630B2 (en) Creating time lapse video in real-time
CN104125395A (en) Method and device for realizing automatic shooting

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination