WO2017206456A1 - Method and apparatus for presenting video image in video call - Google Patents

Abstract

Disclosed are a method and apparatus for presenting a video image in a video call. The method is applied to a first terminal, the first terminal and a second terminal both having a video call function, and comprises the following steps: during a video call with the second terminal, performing the following steps for a captured first video image, each frame of which is based on a real scenario: identifying a foreground part of the first video image according to a pre-set identification rule; performing image fusion on the foreground part of the first video image and a pre-determined target pseudo background, and obtaining a second video image corresponding to the first video image; and sending the second video image to the second terminal, so that the second terminal presents the second video image to a second user. With the application of the technical solution provided by the embodiments of the present invention, the entertainment of a video call is enhanced, and the user experience is improved.

Description

Video image display method and device in video call

This application claims priority to Chinese Patent Application No. 201610378309.3, entitled "A Video Image Display Method and Apparatus for Video Calls", which is filed on May 31, 2016, the entire contents of which are incorporated by reference. In this application.

Technical field

The present invention relates to the field of video call technologies, and in particular, to a video image display method and apparatus for video call.

Background technique

With the rapid development of mobile communication technology and Internet technology, video call technology has gradually developed. Video calls can enable face-to-face communication and communication between users at different locations.

During the video call, both users can see the real scene of the other party's user. In practical applications, the needs of users are diversified, and some users consider for a certain purpose, such as protecting personal privacy, or entertainment, and may not want to show the real scene of the user to the other party. In this case, the user can only avoid showing the real scene of the user by not using the video call function of the terminal, so that the user lacks the fun of making a video call with other users, and the user experience is poor.

Summary of the invention

An object of the present invention is to provide a video image display method and apparatus for a video call, so that a user can perform a video call and enhance the user experience if the user does not want to show other users the real scene.

A method for displaying a video image in a video call is applied to a first terminal, where the first terminal and the second terminal both have a video call function, and the method includes:

During a video call with the second terminal, the following steps are performed on the first video image based on the real scene for each captured frame:

Identifying a foreground portion of the first video image according to a preset identification rule;

Performing image fusion processing on the foreground portion in the first video image and the predetermined target pseudo background to obtain a second video image corresponding to the first video image;

Sending the second video image to the second terminal, so that the second terminal presents the second video image to the second user.

In a specific embodiment of the invention, the target pseudo background is determined by the following steps:

Receiving a selection instruction of the first user for a pseudo background in the preset pseudo background resource library;

A target pseudo background is determined according to the selection instruction of the first user.

In a specific implementation of the present invention, after the determining the target pseudo background, the method further includes:

Receiving a preview instruction of the first user to the target pseudo background;

And capturing, according to the preview instruction, a third video image based on a real scene where the first user is located;

Identifying, in the third video image of each frame, the foreground portion in the third video image according to the identification rule, and performing image fusion processing on the foreground portion in the third video image and the target pseudo background, And obtaining a fourth video image corresponding to the third video image, and displaying the fourth video image output to the first user.

In a specific embodiment of the present invention, after the identifying the foreground portion in the first video image, before performing the image fusion processing on the foreground portion in the first video image and the predetermined target pseudo background The method further includes:

Determining a display size ratio relationship between a foreground portion of the first video image and a foreground portion of the first video image of the previous frame;

Adjusting the display size of the target pseudo background according to the determined display size ratio relationship.

In a specific implementation of the present invention, the target pseudo background is a dynamic background, and the image fusion processing of the foreground portion in the first video image and the predetermined target pseudo background includes:

Determining, according to a preset correspondence, a target video frame of the target pseudo background corresponding to the first video image;

And performing image fusion processing on the foreground portion in the first video image and the target video frame.

In a specific implementation of the present invention, after the obtaining the second video image corresponding to the first video image, the method further includes:

Presenting only the second video image to the first user;

or,

The first video image and the second video image are simultaneously displayed to the first user.

In a specific embodiment of the present invention, the method further includes:

While displaying the second video image to the first user, outputting the played duration of the target pseudo background at the time of displaying the second video image.

A video call display device for video call is applied to a first terminal, where the first terminal and the second terminal both have a video call function, and the device includes:

a foreground part identification module, configured to identify, in a video call with the second terminal, a first video image based on a real scene for each captured frame, and identify the first video image according to a preset identification rule Part of the foreground;

a video image obtaining module, configured to perform image fusion processing on a foreground portion of the first video image identified by the foreground portion identification module and a predetermined target pseudo background, to obtain a second video corresponding to the first video image image;

The video image sending module is configured to send the second video image obtained by the video image obtaining module to the second terminal, so that the second terminal displays the second video image to the second user.

In a specific embodiment of the present invention, the apparatus further includes a target pseudo background determining module configured to determine the target pseudo background by the following steps:

Receiving a selection instruction of the first user for a pseudo background in the preset pseudo background resource library;

A target pseudo background is determined according to the selection instruction of the first user.

In a specific implementation manner of the present invention, the apparatus further includes a target pseudo background preview module, configured to:

Receiving, by the first user, a preview instruction of the target pseudo background after determining the target pseudo background;

And capturing, according to the preview instruction, a third video image based on a real scene where the first user is located;

Identifying, in the third video image of each frame, the foreground portion in the third video image according to the identification rule, and performing image fusion processing on the foreground portion in the third video image and the target pseudo background, And obtaining a fourth video image corresponding to the third video image, and displaying the fourth video image output to the first user.

In a specific implementation manner of the present invention, the device further includes a display size adjustment module, configured to:

Determining a foreground portion of the first video image after the recognizing the foreground portion in the first video image, and performing image fusion processing on the foreground portion in the first video image and the predetermined target pseudo background a proportional relationship with the display size of the foreground portion in the first video image of the previous frame;

Adjusting the display size of the target pseudo background according to the determined display size ratio relationship.

In a specific implementation of the present invention, the target pseudo background is a dynamic background, and the video image obtaining module is specifically configured as:

Determining, according to a preset correspondence, a target video frame of the target pseudo background corresponding to the first video image;

And performing image fusion processing on the foreground portion in the first video image and the target video frame.

In a specific embodiment of the present invention, the device further includes a display module, configured to:

After the obtaining the second video image corresponding to the first video image, displaying the second video image only to the first user; or

The first video image and the second video image are simultaneously displayed to the first user.

In a specific implementation manner of the present invention, the apparatus further includes a play duration display module, configured to:

While displaying the second video image to the first user, outputting the played duration of the target pseudo background at the time of displaying the second video image.

According to the technical solution provided by the embodiment of the present invention, the first terminal may determine the target pseudo background in advance, so that during the video call between the first terminal and the second terminal, the first terminal is based on the real scene for each frame captured. The first video image can identify the foreground portion of the first video image, and perform image fusion processing on the foreground portion and the target pseudo background to obtain a second video image, and send the second video image to the second terminal. In this way, the second video image displayed by the second terminal to the second user is a video image that includes the target pseudo background, so that the first user can also display the first user when the first user does not want to display the real scene of the second user. The purpose of making a video call with the second user enhances the entertainment of the video call and improves the user experience.

DRAWINGS

In order to more clearly illustrate the embodiments of the present invention or the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below. Obviously, the drawings in the following description are merely Some embodiments of the present invention may also be used to obtain other drawings based on these drawings without departing from the art.

1 is a flowchart of implementing a video image display method in a video call according to an embodiment of the present invention;

2 is a schematic structural diagram of a video image display device in a video call according to an embodiment of the present invention;

FIG. 3 is a schematic structural diagram of a video image display apparatus in a video call according to another embodiment of the present invention.

detailed description

The present invention will be further described in detail below in conjunction with the drawings and embodiments. It is apparent that the described embodiments are only a part of the embodiments of the invention, and not all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

Embodiments of the present invention provide a video image display method in a video call. The method is applied to the first terminal. The first terminal and the second terminal can perform a video call, such as a video call through a 3G network, a video call through an LTE (Long Term Evolution) network, or a video call over the Internet. That is to say, both the first terminal and the second terminal have a video call function.

In the embodiment of the present invention, the user who uses the first terminal is the first user, and the user who uses the second terminal is the second user. In a case where the first user does not want to show the second user the real scene in which he is located, the first terminal may determine the target pseudo background according to the corresponding instruction of the first user. In this way, during the video call with the second terminal, the first terminal may apply the technical solution provided by the embodiment of the present invention to perform the authentic background replacement, and send the second video image including the target pseudo background to the second terminal. The second terminal presents such a second video image to the second user. Thus, the video image seen by the second user is the video image containing the target pseudo background.

In the embodiment of the present invention, during the video call between the first terminal and the second terminal, the first video image based on the real scene may be captured, and the continuous multi-frame first video image may constitute a video. The first terminal can perform the operations of the steps shown in FIG. 1 for each frame captured based on the first video image of the real scene.

FIG. 1 is a flowchart of implementing a video image display method in a video call according to an embodiment of the present invention. The method may include the following steps:

S110: Identify a foreground part in the first video image according to a preset identification rule.

After the first terminal establishes a video call with the second terminal, the built-in or external camera can be triggered to capture the first video image based on the real scene of the first user. For each frame of the first video image captured, the first terminal may identify the foreground portion of the first video image according to a preset identification rule. Of course, in the first video image, the portion other than the foreground portion is the background portion of the first video image.

In the embodiment of the present invention, the identification rules of the foreground portion in the video image may be set and adjusted according to specific conditions. For example, if there is a face feature in the video image, the face is determined to be the foreground portion of the video image.

S120: Perform image fusion processing on the foreground portion in the first video image and the predetermined target pseudo background to obtain a second video image corresponding to the first video image.

In the embodiment of the present invention, a pseudo background to be used during a video call may be determined in advance, and the pseudo background is a target pseudo background.

In a specific embodiment of the present invention, the target pseudo background can be determined by the following steps:

Step 1: receiving a selection instruction of the first user for the pseudo background in the preset pseudo background resource library;

Step 2: Determine the target pseudo background according to the first user's selection instruction.

For the convenience of description, the above two steps are combined for explanation.

In the embodiment of the present invention, a pseudo background resource library may be obtained in advance, and the pseudo background resource library may include multiple pseudo backgrounds.

In an actual application, the pseudo background resource library may be stored in the first terminal, created by the first user, or the first terminal communicates with the server and obtained from the server. When the first user has the requirement of disguising the background of the video image, the selection may be made in the pseudo background resource library stored by the first terminal, and a selection instruction for the pseudo background in the pseudo background resource library is issued to the first terminal. After receiving the selection instruction, the first terminal may determine the target pseudo background according to the selection instruction. The pseudo background selected by the user is determined as the target pseudo background.

To save terminal storage resources, the pseudo background repository can also be stored in the server. When the first user has a need to disguise the background of the video image, the first terminal may establish a communication connection with the server, and the first user logs in to the server through the first terminal, selects in the pseudo background resource library stored in the server, and performs the first The terminal issues a selection instruction for a pseudo background in the pseudo background repository. After the first terminal receives the selection instruction, the pseudo background selected by the first user may be downloaded from the server, and the pseudo background is determined as the target pseudo background.

The pseudo background repository can contain pseudo backgrounds set by the technician, and can also contain user-defined pseudo backgrounds. In practical applications, the first user can customize the pseudo background. During the process of customizing the pseudo background, the first user needs to send the recorded video or the captured photo to the first terminal, and the first terminal may process the video or photo sent by the first user, or the video or photo. Uploaded to the server, the server performs corresponding processing, such as making it conform to the preset frame rate, resolution, etc., and then the first terminal updates the processed video or photo as a pseudo background to the pseudo background resource library.

In an actual application, the first user can select a pseudo background before the video call, and can also select a pseudo background during the video call.

If the first user selects a pseudo background before the video call, the first terminal may determine the target pseudo background according to the first user's selection instruction, and then apply the target pseudo background in the next video call, and The target pseudo background is applied only in the next first video call. Alternatively, before applying the target pseudo background in the video call, the first user is presented with a prompt message to confirm whether the target pseudo background is applied.

If the first user selects a pseudo background during the video call, the first terminal may determine the target pseudo background according to the first user's selection instruction, and then apply the target pseudo background during the current video call, or The target pseudo background replaces the target pseudo background determined before the current time.

The foreground portion of the first video image is identified in step S110, and the foreground portion is subjected to image fusion processing with the target pseudo background to obtain a second video image corresponding to the first video image.

Specifically, after the foreground portion of the first video image is identified, the foreground portion may be extracted, and the foreground portion is embedded into the target pseudo background by an image fusion processing technique to obtain a second video image. Thus, the foreground portion of the obtained second video image is the same as the foreground portion of the first video image, and the background portion of the second video image is the target pseudo background.

Alternatively, after the foreground portion of the first video image is identified, the background portion of the first video image is also identified, and the target pseudo background may be replaced with the background portion of the first video image to obtain a second video image. Thus, the foreground portion of the obtained second video image is still the foreground portion of the first video image, and the background portion of the second video image is the target pseudo background.

In the embodiment of the present invention, the target pseudo background may be a static background or a dynamic background.

When the target pseudo background is a static background, after the true video background replacement is performed on the captured first video image of each frame, the obtained background portion of the second video image of each frame is the same, which is the static background.

When the target pseudo background is a dynamic background, when the true video background replacement is performed for each frame of the captured first video image, the obtained background portion of the second video image of each frame is different, and the dynamic background is different. Video frame.

In a specific implementation manner of the present invention, in a case where the target pseudo background is a dynamic background, the foreground portion of the first video image is image-fused with the predetermined target pseudo background, and specifically, the following steps may be performed. :

a first step: determining, according to a preset correspondence, a target video frame of a target pseudo background corresponding to the first video image;

The second step: performing image fusion processing on the foreground portion of the first video image and the target video frame.

For the convenience of description, the above two steps are combined for explanation.

When the target pseudo background is a dynamic background, such as a video, the target pseudo background is composed of a plurality of video frames. For the captured first video image of each frame, the target video frame of the target pseudo background corresponding to the first video image may be determined according to a preset correspondence. For example, if the first video image is the first frame, the target video frame corresponding to the first video image is the first frame video frame of the target pseudo background.

After determining the target video frame of the target pseudo background corresponding to the first video image, the foreground portion of the first video image may be subjected to image fusion processing with the target video frame.

In this way, a second video image corresponding to the first video image may be obtained, the foreground portion of the second video image being the same as the foreground portion of the first video image, and the background portion of the second video image being the target video frame .

S130: Send the second video image to the second terminal, so that the second terminal displays the second video image to the second user.

In step S120, a second video image corresponding to the first video image may be obtained for each captured first video image. Sending the second video image to the second terminal, the second terminal may display the second video image to the second user. From the perspective of the second user, a plurality of consecutive second video images can be presented as video, and what they see is a video containing a pseudo background.

According to the technical solution provided by the embodiment of the present invention, the first terminal may determine the target pseudo background in advance, so that during the video call between the first terminal and the second terminal, the first terminal is based on the real scene for each frame captured. The first video image can identify the foreground portion of the first video image, and perform image fusion processing on the foreground portion and the target pseudo background to obtain a second video image, and send the second video image to the second terminal. In this way, the second video image displayed by the second terminal to the second user is a video image that includes the target pseudo background, so that the first user can also display the first user when the first user does not want to display the real scene of the second user. The purpose of making a video call with the second user enhances the entertainment of the video call and improves the user experience.

In an embodiment of the present invention, after determining the target pseudo background, the method may further include the following steps:

Step 1: receiving a preview instruction of the first user on the target pseudo background;

Step 2: Capture a third video image based on a real scene where the first user is located according to the preview instruction;

Step 3: For each captured third video image of each frame, identify a foreground portion in the third video image according to the identification rule, and perform image fusion processing on the foreground portion in the third video image and the target pseudo background to obtain an image fusion process. And displaying, by the fourth video image corresponding to the third video image, the fourth video image output to the first user.

For the convenience of description, the above three steps are combined for explanation.

It can be understood that, when the first user selects a pseudo background in the pseudo background resource library, after the first terminal determines the target pseudo background, the first user can view the camouflage effect of the target pseudo background by previewing, if the camouflage effect is If you are not satisfied, you can re-select the pseudo background. This way, you can avoid the situation where the first user is in a video call because the camouflage effect is poor.

When the first user has a need for the target pseudo background preview, the first terminal may issue a corresponding preview instruction. Specifically, the first terminal may provide a preview button for the first user, when the first user clicks the preview button, It can be regarded as a preview instruction for the target pseudo background to the first terminal.

The first terminal receives a preview instruction of the first user to the target pseudo background, and according to the preview instruction, the third video image based on the real scene where the first user is located may be captured by the built-in or external camera. For the captured third video image of each frame, the first terminal may identify the foreground portion of the third video image according to the foregoing identification rule, and perform image fusion processing on the foreground portion of the third video image and the target pseudo background. And obtaining a fourth video image corresponding to the third video image, and displaying the fourth video image output to the first user.

For a specific implementation manner of identifying the foreground portion, performing image fusion processing, and the like, reference may be made to the description of the embodiment shown in FIG. 1 , and details are not described herein again.

In this way, the first user can view the camouflage effect of the target pseudo background, and according to the camouflage effect, determine whether to reselect the pseudo background.

In an embodiment of the present invention, after step S110 and before step S120, the method may further include the following steps:

a first step: determining a display size ratio relationship between a foreground portion of the first video image and a foreground portion of the first video image of the previous frame;

The second step: adjusting the display size of the target pseudo background according to the determined display size ratio relationship.

For the convenience of description, the above two steps are combined for explanation.

It can be understood that the first user does not stand still during the video call using the first terminal, and may adjust to adjust the distance between the built-in or external camera of the first terminal and itself. In this case, the display size of the foreground portion in the first video image of each frame captured by the first terminal may vary. From the perspective of the first user, the foreground portion may zoom in or out. The first terminal may determine, according to the first video image of each frame, a display size ratio relationship between the foreground portion in the first video image and the foreground portion in the first video image of the previous frame, and according to the determined display size proportional relationship , you can adjust the display size of the target pseudo background, which can ensure the realistic effect of the pseudo background.

For example, for the first video image of a certain frame captured, if the foreground portion of the first video image is enlarged by 50% compared with the foreground portion of the first video image of the previous frame, it indicates that the first terminal is The distance between the built-in or external camera and the first user is zoomed in. In this case, according to the display size ratio relationship, the display size of the target pseudo background can be enlarged by 50%.

In an embodiment of the present invention, after obtaining the second video image corresponding to the first video image, the first terminal may further display the second video image to the first user, or simultaneously display the first video to the first user. a first video image and the second video image.

In an actual application, the first terminal may display only the first video image on the screen, or may be only the second video image, and may simultaneously display the first video image and the sub-area on the screen. The second video image is such that the first user observes the authentic background in real time.

The first terminal outputs the played duration of the target pseudo background at the time of displaying the second video image while displaying the second video image to the first user. In this way, the user can know the played duration of the target pseudo background in real time, and can actively end the video call with the second user before the end of the play, to avoid the situation that the target pseudo background loops or displays the real scene.

Applying the above method embodiment, the embodiment of the present invention further provides a video image display device in a video call. The device is applied to the first terminal, and the first terminal and the second terminal both have a video call function.

FIG. 2 is a schematic structural diagram of a video image display device in a video call according to an embodiment of the present invention. The device may include the following modules:

The foreground part identification module 210 is configured to identify, in a video call with the second terminal, the first video image based on the real scene for each captured frame, and identify the first video image according to a preset identification rule. Part of the foreground;

The video image obtaining module 220 is configured to perform image fusion processing on the foreground portion of the first video image identified by the foreground portion identification module 210 and the predetermined target pseudo background to obtain a second video corresponding to the first video image. image;

The video image sending module 230 is configured to send the second video image obtained by the video image obtaining module 220 to the second terminal, so that the second terminal displays the second video image to the second user.

According to the apparatus provided by the embodiment of the present invention, the first terminal may determine the target pseudo background in advance, so that the first terminal is based on the real scene for each frame captured during the video call between the first terminal and the second terminal. a video image can identify a foreground portion of the first video image, and perform image fusion processing on the foreground portion and the target pseudo background to obtain a second video image, and send the second video image to the second terminal, such that The second video image displayed by the second terminal to the second user is a video image including the target pseudo background, so that the first user can also cooperate with the first user when the first user does not want to display the real scene of the second user. The purpose of the second user to make a video call enhances the entertainment of the video call and improves the user experience.

In an embodiment of the invention, the apparatus may further comprise a target pseudo-background determining module configured to determine the target pseudo-background by the following steps:

Receiving a selection instruction of the first user for a pseudo background in the preset pseudo background resource library;

The target pseudo background is determined according to the selection instruction of the first user.

In an embodiment of the present invention, the apparatus may further include a target pseudo background preview module, configured to:

After determining the target pseudo background, receiving a preview instruction of the first user on the target pseudo background;

Capture a third video image based on a real scene where the first user is located according to the preview instruction;

And identifying, in accordance with the identification rule, the foreground portion in the third video image according to the recognition rule, and performing image fusion processing on the foreground portion in the third video image and the target pseudo background to obtain the same And displaying a fourth video image corresponding to the third video image, and displaying the fourth video image output to the first user.

In a specific embodiment of the present invention, the pseudo background resource library includes a first user-defined pseudo background.

In an embodiment of the present invention, the apparatus may further include a display resizing module, configured to:

Determining the foreground portion and the previous frame in the first video image after the foreground portion in the first video image is identified, before the foreground portion in the first video image is image-blended with the predetermined target pseudo-background a display size proportional relationship of the foreground portion in the first video image;

Adjust the display size of the target pseudo background according to the determined display size ratio relationship.

In an embodiment of the present invention, the target pseudo background is a dynamic background, and the video image obtaining module 220 may be specifically configured as:

Determining, according to a preset correspondence, a target video frame of a target pseudo background corresponding to the first video image;

The foreground portion of the first video image is subjected to image fusion processing with the target video frame.

In an embodiment of the present invention, the apparatus may further include a display module, configured to:

After obtaining the second video image corresponding to the first video image, displaying the second video image only to the first user; or

The first video image and the second video image are simultaneously displayed to the first user.

In an embodiment of the present invention, the apparatus may further include a play duration display module, configured to:

While displaying the second video image to the first user, outputting the played duration of the target pseudo background at the time of displaying the second video image.

FIG. 3 is a schematic structural diagram of a video image display apparatus in a video call according to an embodiment of the present invention. As shown, the device 30 in the embodiment of the present invention may be different types of electronic devices, such as: smart phones, tablet computers, handheld computers, and mobile Internet devices, personal digital assistants, media players, smart TVs, smart watches, Smart glasses, smart bracelets, etc. As shown in FIG. 3, the apparatus 30 in the embodiment of the present invention includes: at least one processor 301, such as a CPU, at least one memory 302, and at least one transceiver 303. The processor 301, the memory 302, and the transceiver 303 are connected and communicated through a bus system. The memory 302 may be a high speed RAM memory or a non-volatile memory such as at least one disk memory.

Program code is stored in the memory 302, and the processor 301 can call the program code stored in the memory 302 to perform related functions through a bus system. For example, each module described in FIG. 2 (for example, the foreground portion identification module 210, the video image obtaining module 220, the video image transmitting module 230) and a target pseudo background determining module not shown, a target pseudo background preview a module, a display resizing module, a display module, a play duration display module, and the like, are program codes stored in the memory 302, and are executed by the processor 301, thereby implementing functions of the respective modules to implement a wireless local area network. Communication method.

Specifically, in a video call with the second terminal, the processor 301: identifies the first video image based on the real scene for each captured frame, according to a preset identification rule. a foreground portion in the video image; performing image fusion processing on the foreground portion in the first video image with the predetermined target pseudo background to obtain a second video image corresponding to the first video image; and transmitting the second video image Giving the second terminal, so that the second terminal presents the second video image to the second user.

Specifically, the target pseudo background is determined by the following steps:

Receiving a selection instruction of the first user for a pseudo background in the preset pseudo background resource library;

A target pseudo background is determined according to the selection instruction of the first user.

Specifically, after the determining the target pseudo background, the processor 301:

Receiving a preview instruction of the first user to the target pseudo background;

And capturing, according to the preview instruction, a third video image based on a real scene where the first user is located;

Identifying, in the third video image of each frame, the foreground portion in the third video image according to the identification rule, and performing image fusion processing on the foreground portion in the third video image and the target pseudo background, And obtaining a fourth video image corresponding to the third video image, and displaying the fourth video image output to the first user.

Specifically, after the identifying the foreground portion in the first video image, and performing image fusion processing on the foreground portion in the first video image and the predetermined target pseudo background, the processor 301:

Determining a display size ratio relationship between a foreground portion of the first video image and a foreground portion of the first video image of the previous frame;

Adjusting the display size of the target pseudo background according to the determined display size ratio relationship.

Specifically, the target pseudo background is a dynamic background, and the image fusion processing is performed on the foreground portion in the first video image and the predetermined target pseudo background, including:

Determining, according to a preset correspondence, a target video frame of the target pseudo background corresponding to the first video image;

And performing image fusion processing on the foreground portion in the first video image and the target video frame.

Specifically, after the obtaining the second video image corresponding to the first video image, the processor 301: displaying only the second video image to the first user; or, to the first user The first video image and the second video image are simultaneously displayed.

Specifically, the processor 301: while displaying the second video image to the first user, output the played duration of the target pseudo background at the time of displaying the second video image.

The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on differences from other embodiments, and the same or similar parts of the respective embodiments may be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

A person skilled in the art will further appreciate that the elements and algorithm steps of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software or a combination of both, in order to clearly illustrate the hardware and software. Interchangeability, the composition and steps of the various examples have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the solution. A person skilled in the art can use different methods for implementing the described functions for each particular application, but such implementation should not be considered to be beyond the scope of the present invention.

The steps of a method or algorithm described in connection with the embodiments disclosed herein can be implemented directly in hardware, a software module executed by a processor, or a combination of both. The software module can be placed in random access memory (RAM), memory, read only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or technical field. Any other form of storage medium known.

The video image display method and apparatus for video call provided by the present invention are described in detail above. The principles and embodiments of the present invention have been described herein with reference to specific examples, and the description of the above embodiments is merely provided to aid in understanding the method of the present invention and its core idea. It should be noted that those skilled in the art can make various modifications and changes to the present invention without departing from the spirit and scope of the invention.

Claims (14)

A method for displaying a video image in a video call, which is characterized in that it is applied to a first terminal, and both the first terminal and the second terminal have a video call function, and the method includes: During a video call with the second terminal, the following steps are performed on the first video image based on the real scene for each captured frame: Identifying a foreground portion of the first video image according to a preset identification rule; Performing image fusion processing on the foreground portion in the first video image and the predetermined target pseudo background to obtain a second video image corresponding to the first video image; Sending the second video image to the second terminal, so that the second terminal presents the second video image to the second user. The method of claim 1 wherein said target pseudo background is determined by the following steps: Receiving a selection instruction of the first user for a pseudo background in the preset pseudo background resource library; A target pseudo background is determined according to the selection instruction of the first user. The method according to claim 2, wherein after the determining the target pseudo background, the method further comprises: Receiving a preview instruction of the first user to the target pseudo background; And capturing, according to the preview instruction, a third video image based on a real scene where the first user is located; Identifying, in the third video image of each frame, the foreground portion in the third video image according to the identification rule, and performing image fusion processing on the foreground portion in the third video image and the target pseudo background, And obtaining a fourth video image corresponding to the third video image, and displaying the fourth video image output to the first user. The method according to claim 1, wherein after said identifying a foreground portion in said first video image, said foreground portion of said first video image is image-fused with a predetermined target pseudo-background Before processing, the method further includes: Determining a display size ratio relationship between a foreground portion of the first video image and a foreground portion of the first video image of the previous frame; Adjusting the display size of the target pseudo background according to the determined display size ratio relationship. The method according to any one of claims 1 to 4, wherein the target pseudo background is a dynamic background, and the foreground portion of the first video image is image-fused with a predetermined target pseudo background. ,include: Determining, according to a preset correspondence, a target video frame of the target pseudo background corresponding to the first video image; And performing image fusion processing on the foreground portion in the first video image and the target video frame. The method according to claim 5, wherein after the obtaining the second video image corresponding to the first video image, the method further comprises: Presenting only the second video image to the first user; or, The first video image and the second video image are simultaneously displayed to the first user. The method of claim 6 wherein the method further comprises: While displaying the second video image to the first user, outputting the played duration of the target pseudo background at the time of displaying the second video image. A video call display device in a video call, which is applied to a first terminal, wherein the first terminal and the second terminal both have a video call function, and the device includes: a foreground part identification module, configured to identify, in a video call with the second terminal, a first video image based on a real scene for each captured frame, and identify the first video image according to a preset identification rule Part of the foreground; a video image obtaining module, configured to perform image fusion processing on a foreground portion of the first video image identified by the foreground portion identification module and a predetermined target pseudo background, to obtain a second video corresponding to the first video image image; The video image sending module is configured to send the second video image obtained by the video image obtaining module to the second terminal, so that the second terminal displays the second video image to the second user. The apparatus according to claim 8, wherein said apparatus further comprises a target pseudo background determining module configured to determine said target pseudo background by the following steps: Receiving a selection instruction of the first user for a pseudo background in the preset pseudo background resource library; A target pseudo background is determined according to the selection instruction of the first user. The device according to claim 9, wherein the device further comprises a target pseudo background preview module, which is configured to: Receiving, by the first user, a preview instruction of the target pseudo background after determining the target pseudo background; And capturing, according to the preview instruction, a third video image based on a real scene where the first user is located; Identifying, in the third video image of each frame, the foreground portion in the third video image according to the identification rule, and performing image fusion processing on the foreground portion in the third video image and the target pseudo background, And obtaining a fourth video image corresponding to the third video image, and displaying the fourth video image output to the first user. The device according to claim 8, wherein the device further comprises a display resizing module, configured to: Determining a foreground portion of the first video image after the recognizing the foreground portion in the first video image, and performing image fusion processing on the foreground portion in the first video image and the predetermined target pseudo background a proportional relationship with the display size of the foreground portion in the first video image of the previous frame; Adjusting the display size of the target pseudo background according to the determined display size ratio relationship. The device according to any one of claims 8 to 11, wherein the target pseudo background is a dynamic background, and the video image obtaining module is specifically configured as: Determining, according to a preset correspondence, a target video frame of the target pseudo background corresponding to the first video image; And performing image fusion processing on the foreground portion in the first video image and the target video frame. The device according to claim 12, wherein the device further comprises a display module, configured to: After the obtaining the second video image corresponding to the first video image, displaying the second video image only to the first user; or The first video image and the second video image are simultaneously displayed to the first user. The device according to claim 13, wherein the device further comprises a play duration display module, which is configured to: While displaying the second video image to the first user, outputting the played duration of the target pseudo background at the time of displaying the second video image.

Images