CN113793410A

CN113793410A - Video processing method and device, electronic equipment and storage medium

Info

Publication number: CN113793410A
Application number: CN202111017357.7A
Authority: CN
Inventors: 王剑; 高新川; 康乐
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2021-08-31
Filing date: 2021-08-31
Publication date: 2021-12-14

Abstract

The present disclosure relates to a video processing method, apparatus, electronic device, and storage medium, the method comprising: displaying a live video picture at a main broadcasting end, wherein the live video picture comprises a scene picture input by a camera of the main broadcasting end and a paster special effect element superposed on the scene picture; in response to a mirror image processing instruction of a live video picture, carrying out mirror image processing on a candidate picture extracted from the live video picture to obtain a mirror image candidate picture, wherein the candidate picture is a video picture obtained by removing a target paster special effect element from the live video picture; and pushing the mirror image video stream data corresponding to the mirror image candidate picture and the additional special effect data corresponding to the target paster special effect element to a spectator end so that the spectator end can display a picture obtained by integrating the mirror image candidate picture and the target paster special effect element. Therefore, the problem that messy code information which is difficult to understand appears in the content displayed by the video processing method provided by the related technology, so that the special effect elements of the paster are displayed wrongly is solved.

Description

Video processing method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of computers, and in particular, to a video processing method and apparatus, an electronic device, and a storage medium.

Background

Today, in the course of video, many anchor often use some special effects to boost the traffic for the content currently being played. Common holding effects include, for example: mirror images and stickers. The mirror image special effect is to flip the video picture in the video stream left and right.

When the mirror image special effect is used in combination with the sticker, when the original video picture collected by the camera of the anchor is subjected to mirror image turning processing, the sticker attached to the video picture is also subjected to mirror image turning processing at the same time, but many stickers include elements (such as chinese and english characters, numbers and the like) sensitive to left-right turning. Therefore, the display content presented by the video after the mirror image turning is difficult to understand received information by audiences, and the presentation effect of the video is seriously influenced.

That is, when the video processing method provided by the related art is adopted, messy code information which is difficult to understand appears in the displayed content, resulting in the problem of errors in the displayed elements.

In view of the above problems, no effective solution has been proposed.

Disclosure of Invention

The disclosure provides a video processing method, a video processing device, an electronic device and a storage medium, which are used for at least solving the problem that the display elements are wrong due to messy code information which is difficult to understand appearing in the content displayed by the video processing method provided by the related technology. The technical scheme of the disclosure is as follows:

according to a first aspect of the embodiments of the present disclosure, there is provided a video processing method, including: displaying a live video picture at a main broadcasting end, wherein the live video picture comprises a scene picture input by a camera of the main broadcasting end and a paster special effect element superposed on the scene picture; in response to a mirror image processing instruction of the live video picture, carrying out mirror image processing on a candidate picture extracted from the live video picture to obtain a mirror image candidate picture, wherein the candidate picture is a video picture obtained by removing a target paster special effect element from the live video picture, and the difference between the mirror image paster special effect element obtained after the target paster special effect element is subjected to mirror image processing and the target paster special effect element is greater than a target threshold value; and pushing the mirror image video stream data corresponding to the mirror image candidate picture and the additional special effect data corresponding to the target paster special effect element to a viewer so that the viewer can display a picture obtained by integrating the mirror image candidate picture and the target paster special effect element.

As an optional embodiment, before performing mirroring processing on a candidate picture extracted from the live video picture to obtain a mirrored candidate picture, the method further includes: combining the scene picture and the basic sticker special effect element to obtain the candidate picture under the condition that the sticker special effect element superposed on the scene picture comprises the target sticker special effect element and the basic sticker special effect element, wherein the difference degree between the mirror image sticker special effect element obtained after the mirror image processing of the basic sticker special effect element and the basic sticker special effect element is smaller than or equal to the target threshold value; and when the sticker special effect element superimposed on the scene picture is the target sticker special effect element, taking the scene picture input by the camera of the anchor as the candidate picture.

As an optional embodiment, after performing mirroring processing on a candidate picture extracted from the live video picture to obtain a mirrored candidate picture, the method further includes: determining the positions of key points of the human face associated with the target paster special effect elements from the human face area presented in the live video picture; extracting the features of the key points of the human face to obtain human face feature information; determining a face picture area corresponding to the face feature information in the mirror image candidate picture; and generating the mirror image video stream data based on the human face picture area.

As an optional embodiment, after performing feature extraction on the position of the face key point to obtain face feature information, the method further includes: and respectively storing the coordinate information of the pixel point corresponding to each human face key point position into each data bit corresponding to the integer type variable.

As an optional embodiment, the storing the coordinate information of the pixel point corresponding to each of the face key point positions into each data bit corresponding to an integer type variable respectively includes: and storing the abscissa information of the pixel point into the first sequence data bits of the integer type variable, and storing the ordinate information of the pixel point into the second sequence data bits of the integer type variable.

According to a second aspect of the embodiments of the present disclosure, there is provided a video processing method, including: receiving mirror image video stream data sent by a main broadcast terminal and additional special effect data corresponding to a target paster special effect element, wherein the difference degree between the mirror image paster special effect element obtained after the mirror image processing of the target paster special effect element and the target paster special effect element is larger than a target threshold value; analyzing a mirror image candidate picture from the mirror image video stream data, wherein the mirror image candidate picture is a picture obtained by carrying out mirror image processing on a candidate picture, and the candidate picture is a video picture obtained by removing the target paster special effect element from a live video picture; rendering the target paster special effect element to the mirror image candidate picture according to the additional special effect data to obtain a mirror image video picture.

As an alternative embodiment, the rendering the target sticker special effect element onto the mirror image candidate picture according to the additional special effect data to obtain a mirror image video picture includes: acquiring a first display area corresponding to the target paster special effect element from the additional special effect data, wherein the first display area is a display area of the target paster special effect element in a video picture displayed by the main broadcast end; determining a corresponding second display area in the audience after the mirror image processing of the first display area; and when the mirror image candidate picture is displayed, rendering the target paster special effect element in the second display area so as to display the mirror image video picture.

As an alternative embodiment, when the mirror image video picture is displayed, the method includes: and under the condition of receiving the mirror image video stream data according to a preset transmission frame rate, carrying out linear interpolation processing between any two displayed frames of the mirror image video pictures.

According to a third aspect of the embodiments of the present disclosure, there is provided a video processing apparatus including: the display unit is arranged for displaying a live video picture at a main broadcast end, wherein the live video picture comprises a scene picture input by a camera of the main broadcast end and a sticker special effect element superposed on the scene picture; the mirror image processing unit is used for responding to a mirror image processing instruction of the live video picture, carrying out mirror image processing on a candidate picture extracted from the live video picture to obtain a mirror image candidate picture, wherein the candidate picture is a video picture obtained by removing a target paster special effect element from the live video picture, and the difference degree between the mirror image paster special effect element obtained by carrying out mirror image processing on the target paster special effect element and the target paster special effect element is larger than a target threshold value; and the pushing unit is used for pushing the mirror image video stream data corresponding to the mirror image candidate picture and the additional special effect data corresponding to the target paster special effect element to a spectator end so as to enable the spectator end to display a picture obtained by integrating the mirror image candidate picture and the target paster special effect element.

As an alternative embodiment, the method further comprises: a first determining unit, configured to merge the scene picture and a base sticker special effect element to obtain a candidate picture when the sticker special effect element superimposed on the scene picture includes the target sticker special effect element and the base sticker special effect element before a candidate picture extracted from the live video picture is subjected to mirroring to obtain a mirrored candidate picture, wherein a degree of difference between the mirrored sticker special effect element obtained after mirroring the base sticker special effect element and the base sticker special effect element is less than or equal to the target threshold; a second determination unit configured to take the scene picture input by the camera of the anchor terminal as the candidate picture, when the sticker special effect element superimposed on the scene picture is the target sticker special effect element.

As an alternative embodiment, the method further comprises: a third determining unit, configured to determine a position of a key point of a face associated with the target sticker special effect element from a face area presented in the live video picture after performing mirroring on a candidate picture extracted from the live video picture to obtain a mirrored candidate picture; the extraction unit is used for extracting the features of the key point positions of the human face to obtain human face feature information; a fourth determining unit configured to determine a face image region corresponding to the face feature information in the mirror image candidate image; a generating unit configured to generate the mirror image video stream data based on the face picture area.

As an alternative embodiment, the method further comprises: and the storage unit is used for respectively storing the coordinate information of the pixel point corresponding to each human face key point position into each data bit corresponding to the integer type variable after the feature extraction is carried out on the human face key point position to obtain the human face feature information.

As an alternative embodiment, the storage unit includes: and the storage module is used for storing the abscissa information of the pixel point into the first sequence data bits of the integer type variable and storing the ordinate information of the pixel point into the second sequence data bits of the integer type variable.

According to a fourth aspect of the embodiments of the present disclosure, there is provided a video processing apparatus including: the receiving unit is arranged for receiving mirror image video stream data sent by a main broadcast terminal and additional special effect data corresponding to a target paster special effect element, wherein the difference degree between the mirror image paster special effect element obtained after the mirror image processing of the target paster special effect element and the target paster special effect element is larger than a target threshold value; the analysis unit is used for analyzing a mirror image candidate picture from the mirror image video stream data, wherein the mirror image candidate picture is a picture obtained by carrying out mirror image processing on the candidate picture, and the candidate picture is a video picture obtained by removing the target paster special effect element from a live video picture; and the rendering unit is used for rendering the target paster special effect element to the mirror image candidate picture according to the additional special effect data so as to obtain a mirror image video picture.

As an optional embodiment, the rendering unit includes: an obtaining module, configured to obtain a first display area corresponding to the target sticker special effect element from the additional special effect data, where the first display area is a display area of the target sticker special effect element in a video picture displayed by the anchor terminal; the determining module is used for determining a corresponding second display area in the audience after the first display area is subjected to mirror image processing; and the rendering module is configured to render the target sticker special effect element in the second display area when the mirror image candidate picture is displayed so as to display the mirror image video picture.

As an optional embodiment, the rendering unit further includes: and the processing module is arranged for carrying out linear interpolation processing on any two displayed frames of the mirror image video pictures under the condition of receiving the mirror image video stream data according to a preset transmission frame rate.

According to a fifth aspect of embodiments of the present disclosure, there is also provided an electronic device, comprising a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the video processing method.

According to a sixth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium, wherein instructions of the computer-readable storage medium, when executed by a processor in an electronic device, enable the electronic device to perform the above-mentioned video processing method.

According to a seventh aspect of the embodiments of the present disclosure, there is provided a computer program product comprising a computer program, wherein the computer program is implemented by a processor to implement the video processing method.

The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:

in the embodiment of the invention, a live video picture is displayed at a main broadcasting end, wherein the live video picture comprises a scene picture input by a camera of the main broadcasting end and a paster special effect element superposed on the scene picture; and in response to a mirror image processing instruction of the live video image, carrying out mirror image processing on a candidate image extracted from the live video image to obtain a mirror image candidate image, wherein the candidate image is a video image from which a target paster special effect element is removed, and the target paster special effect element is a paster special effect element with a large difference before and after the mirror image. And pushing the mirror image video stream data corresponding to the mirror image candidate picture and the additional special effect data corresponding to the target paster special effect element to a spectator end so that the spectator end can display a picture obtained by integrating the mirror image candidate picture and the target paster special effect element. Therefore, the target paster special effect elements are normally rendered and displayed in the mirror image video picture, and the problem that the paster special effect elements are displayed wrongly due to the fact that mirror image processing is directly carried out on the target paster special effect elements sensitive to the mirror image is solved. Thereby achieving the effect of improving the accuracy of content display.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.

FIG. 1 is a schematic diagram illustrating an application environment for an alternative video processing method according to an embodiment of the present disclosure;

FIG. 2 is a flow diagram illustrating an alternative video processing method according to an embodiment of the present disclosure;

FIG. 3 is a schematic diagram illustrating an alternative video processing method according to an embodiment of the present disclosure;

FIG. 4 is a schematic diagram illustrating another alternative video processing method according to an embodiment of the present disclosure;

FIG. 5 is a schematic diagram illustrating yet another alternative video processing method according to an embodiment of the present disclosure;

FIG. 6 is a schematic diagram illustrating yet another alternative video processing method according to an embodiment of the present disclosure;

FIG. 7 is a schematic diagram illustrating yet another alternative video processing method according to an embodiment of the present disclosure;

FIG. 8 is a flow diagram illustrating another alternative video processing method according to an embodiment of the present disclosure;

FIG. 9 is a schematic block diagram of an alternative video processing apparatus according to an embodiment of the present disclosure;

fig. 10 is a schematic structural diagram of another alternative video processing apparatus according to an embodiment of the present disclosure.

Detailed Description

In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

According to an aspect of the embodiments of the present invention, there is provided a video processing method, optionally, the video processing method may be applied, but not limited to, in a video processing system in an application environment as shown in fig. 1, the system includes: terminal device 102, network 104, and terminal device 106. The terminal device 102 is a hardware device used by a anchor terminal, runs a client logged in by using an anchor account, and can share other audience accounts concerning the anchor account through a platform after acquiring a desired scene picture. The terminal device 102 includes a human-computer interaction screen 1022, a processor 1024, and a processor 1026, where the human-computer interaction screen 1022 is used for displaying the video frame and detecting a touch operation. The processor 1024 is configured to generate a corresponding human-computer interaction instruction according to the detected touch operation, so as to execute a background operation according to the human-computer interaction instruction. The memory 1026 is used to store the video pictures described above. The terminal device 106 is a hardware device used by the viewer, and runs a playing client logged in by using a viewer account, and is used for playing the content shared by the anchor. The terminal device 108 includes a human-computer interaction screen 1062, a processor 1064 and a processor 1066, where the human-computer interaction screen 1062 is used for displaying the mirror-image video picture. The processor 1024 is configured to render the target sticker special effect element on the resolved mirror image candidate picture to generate the mirror image video picture. The memory 1026 is used to store the mirror video pictures described above.

The method is realized by the following steps: in step S102, a live video screen is displayed in the terminal device 102, in which a target object with a baseball cap toward the right side is displayed as shown in fig. 1, and a sun sticker and a text sticker "your real club |" are displayed in combination! "the terminal device 102 performs mirror processing on a candidate picture extracted from the live video picture in response to a touch operation of performing mirror processing on the live video picture displayed on the human-computer interaction screen 1022, to obtain a mirror candidate picture, as shown in step S104.

When the mirror image video stream data obtained based on the mirror image candidate screen and the additional special effect data corresponding to the target sticker special effect element (such as the text sticker) are acquired, step S106 is executed, and the mirror image video stream data obtained based on the mirror image candidate screen and the additional special effect data corresponding to the target sticker special effect element are pushed to the terminal device 106 through the network 104. Steps S108 to S110 are executed in the terminal device 106, and a mirror image candidate picture is parsed from the mirror image video stream data, and the target sticker special effect element is rendered onto the mirror image candidate picture according to the additional special effect data, so as to obtain a mirror image video picture. The mirror image video screen displays the target object with the baseball cap toward the left side as shown in FIG. 1, and displays a combination of a sun sticker and a text sticker "true-baseball! "the sun sticker is mapped from the left side of the screen to the right side of the screen due to the mirroring process, and the text sticker as the special effect element of the target sticker is rendered locally in the terminal device 106 and is not mirrored.

It should be noted that, in this embodiment, a live video picture is displayed at a anchor terminal, where the live video picture includes a scene picture input by a camera of the anchor terminal and a sticker special effect element superimposed on the scene picture; and in response to a mirror image processing instruction of the live video image, carrying out mirror image processing on a candidate image extracted from the live video image to obtain a mirror image candidate image, wherein the candidate image is a video image from which a target paster special effect element is removed, and the target paster special effect element is a paster special effect element with a large difference before and after the mirror image. And pushing the mirror image video stream data corresponding to the mirror image candidate picture and the additional special effect data corresponding to the target paster special effect element to a spectator end so that the spectator end can display a picture obtained by integrating the mirror image candidate picture and the target paster special effect element. Therefore, the special effect elements of the target sticker can be normally rendered and displayed in the mirror image video picture, and the problem of wrong display of the special effect elements caused by directly carrying out mirror image processing on the special effect elements of the target sticker sensitive to the mirror image is solved. Thereby achieving the effect of improving the accuracy of content display.

Optionally, in this embodiment, the terminal device may be a terminal device configured with a target client, and may include, but is not limited to, at least one of the following: mobile phones (such as Android phones, iOS phones, etc.), notebook computers, tablet computers, palm computers, MID (Mobile Internet Devices), PAD, desktop computers, smart televisions, etc. The target client may be a video client, an instant messaging client, a browser client, an educational client, etc. that supports online. Such networks may include, but are not limited to: a wired network, a wireless network, wherein the wired network comprises: a local area network, a metropolitan area network, and a wide area network, the wireless network comprising: bluetooth, WIFI, and other networks that enable wireless communication. The server may be a single server, a server cluster composed of a plurality of servers, or a cloud server. The above is merely an example, and this is not limited in this embodiment.

Optionally, as an optional implementation manner, as shown in fig. 2, the video processing method includes:

s202, displaying a live video picture at a main broadcasting end, wherein the live video picture comprises a scene picture input by a camera of the main broadcasting end and a paster special effect element superposed on the scene picture;

s204, in response to a mirror image processing instruction of the live video image, carrying out mirror image processing on a candidate image extracted from the live video image to obtain a mirror image candidate image, wherein the candidate image is a video image obtained by removing a target paster special effect element from the live video image, and the difference between the mirror image paster special effect element obtained by mirror image processing of the target paster special effect element and the target paster special effect element is greater than a target threshold value;

s206, pushing the mirror image video stream data corresponding to the mirror image candidate picture and the additional special effect data corresponding to the target paster special effect element to a spectator end so that the spectator end can display a picture obtained by integrating the mirror image candidate picture and the target paster special effect element.

Optionally, in this embodiment, the video processing method may be widely applied to, but not limited to, scenes such as a front camera of a mobile phone, short video shooting, and video. Video scenes herein may include, but are not limited to: online education, online eating and broadcasting, online shopping, etc. In addition, in this embodiment, the timing of performing the mirroring process on the captured scene picture may include, but is not limited to: camera acquisition, anchor presentation, plug flow, etc. Here, the execution subject of the video processing method may be the terminal device 102 shown in fig. 1 as the anchor in the process. The above list is an example, and this is not limited in this embodiment.

Optionally, in this embodiment, the target sticker special effect element may be, but is not limited to, a sticker special effect element that is sensitive to mirroring, such as a text special effect, for example, elements such as chinese and english characters, numbers, and the like. The text special effect may be, but is not limited to, a sticker special effect, which means that a picture or a video is additionally drawn at a specific position on a screen. Therefore, the additional special effect data corresponding to the target paster special effect element is pushed to the audience for playing as separate service data and mirror image video stream data respectively.

In addition, in this embodiment, but not limited to, face feature information corresponding to positions of key points of a face in a face area in a live video picture may be identified by combining an Artificial Intelligence (AI) technology, and mirror image video stream data generated in the face area determined based on the face feature information and additional special effect data corresponding to a target sticker special effect element are pushed to a viewer together. Therefore, when the audience end locally renders the target paster special effect elements, the target paster special effect elements can be added to corresponding positions in the face area more accurately, and then the target paster special effect elements are matched with various postures (such as front face postures and side face postures) of the face in a dynamic video effect, so that the display effect of the target paster is achieved.

Optionally, in this embodiment, the configured sticker special effect elements of the video frame may further include a base sticker special effect element, where the base sticker special effect element is an element that is not sensitive to image processing, such as a sticker special effect element having symmetry itself, for example, a sun sticker as shown in fig. 1.

Optionally, in this embodiment, when the anchor side pushes the mirrored video stream data and the additional special effect data corresponding to the target sticker special effect element to the viewer side, the transmission rate may be reduced, but not limited to, to 5 frames to 10 frames per second based on the network condition. Thus, the transmission data volume can be reduced from the original 101 points/frame 8 bits/point 15 frames/second 12000 bits/second to 5 points/frame 4 bits/point 10 frames/second 200 bits/second. Thereby achieving nearly 60 times the flow optimization.

The description is made with reference to the example shown in fig. 3: assume that a camera at the anchor side inputs a scene picture, and adds a base special effect (base sticker special effect element) and an additional special effect (target sticker special effect element). Thus, a video picture including the above-described scene picture, the base special effect, and the additional special effect will be presented on the screen of the anchor. The presentation effect here can be as shown in fig. 4 on the left side of the corresponding screen content of the anchor.

And in response to a mirroring processing instruction of the live video picture, mirroring the candidate pictures including the scene picture and the basic special effect to obtain mirrored candidate pictures. And then, taking the mirror image video stream data based on the mirror image candidate picture and the special effect data for adding the special effect as push contents, and pushing the push contents to a viewer end through a network. And locally executing the process of rendering the additional special effect to the analyzed mirror image candidate picture at the audience so as to enable the screen of the audience to present a mirror image video picture comprising the mirror image candidate picture and the additional special effect. The presentation effect here may be the content of the screen corresponding to the viewer side as shown on the right side of fig. 4.

Note that, the timing of performing the mirroring process on the candidate picture may be described with reference to fig. 5, and may include:

for the anchor side: after a scene picture is input by a camera, carrying out mirror image processing on the scene picture, and after the basic paster special effect elements are obtained and before the basic paster special effect elements are presented at an anchor end, carrying out mirror image processing on the basic paster special effect elements; or after the basic paster special effect elements are obtained and before the basic paster special effect elements are presented at the anchor end, carrying out one-time mirror image processing on the scene picture and the basic paster special effect elements.

For the viewer side: after a scene picture is input by a camera, carrying out mirror image processing on the scene picture, and after the special effect elements of the basic sticker are obtained and before network plug flow, carrying out mirror image processing on the special effect elements of the basic sticker; or before the presentation of the audience, carrying out one-time mirror image processing on the scene picture and the special effect elements of the basic sticker.

That is to say, after the method provided by this embodiment is adopted, since the anchor terminal separately transmits the mirror image candidate picture and the target sticker special effect element to the viewer terminal, the viewer terminal can locally complete rendering of the target sticker special effect element, instead of uniformly mirroring all elements in the video picture, thereby avoiding code messy information appearing after mirroring the target sticker special effect element, and further improving the video processing effect.

Through the embodiment provided by the application, in response to a mirror image processing instruction of a live video image, mirror image processing is performed on a candidate image extracted from the live video image to obtain a mirror image candidate image, wherein a target paster special effect element in the live video image is removed from the candidate image, the target paster special effect element is a mirror image sensitive element, and the difference degree between the mirror image paster special effect element obtained after mirror image processing and the target paster special effect element is larger than a target threshold value. And pushing mirror image video stream data obtained based on the mirror image candidate pictures and additional special effect data corresponding to the target paster special effect elements to a spectator end so that the spectator end can display the mirror image video pictures corresponding to the live video pictures. Therefore, the special effect elements of the target sticker can be normally rendered and displayed in the mirror image video picture, the problem that the special effect elements are displayed wrongly due to mirror image processing of the special effect elements of the target sticker sensitive to the mirror image is avoided, and the effect of improving the accuracy of content display is achieved.

As an optional scheme, before performing mirroring processing on a candidate picture extracted from a live video picture to obtain a mirrored candidate picture, the method further includes:

1) combining the scene picture and the basic paster special effect element to obtain a candidate picture under the condition that the paster special effect elements superposed on the scene picture comprise a target paster special effect element and a basic paster special effect element, wherein the difference degree between the mirror image paster special effect element obtained after the basic paster special effect element is subjected to mirror image processing and the basic paster special effect element is smaller than or equal to a target threshold value;

2) and under the condition that the paster special effect element superposed on the scene picture is the target paster special effect element, taking the scene picture input by the camera of the anchor end as a candidate picture.

It should be noted that, in this embodiment, the video picture may include a scene picture captured by a camera, and a special effect element of a sticker configured in a main broadcast terminal. The sticker special effect element here may be, but is not limited to, an element additionally superimposed on the scene picture, and different sticker special effect elements may be, but is not limited to, drawn hierarchically on the scene picture. For example, the base sticker effect element and the target sticker effect element described above may be, but are not limited to being, rendered in different layers. The video picture can comprise basic paster special effect elements or not, wherein the basic paster special effect elements are paster special effect elements insensitive to mirror images, change difference is small after mirror image processing, and understanding and watching of users are not affected.

For example, assuming that the anchor terminal still uses the anchor terminal and the viewer terminal still uses the viewer terminal as an example, the video frame displayed by the anchor terminal includes: scene pictures input by a camera, basic special effects and additional special effects (namely target paster special effect elements). The scene picture input by the camera and the basic special effect can be merged to obtain a candidate picture, and then a plurality of candidate pictures are compressed to obtain a video stream which is pushed to a far-end audience through a network. The above-mentioned additional special effect is an element sensitive to mirroring, and in order to avoid being mirrored, the additional special effect is incorporated as a single part of the push content into the network push stream.

According to the embodiment provided by the application, under the condition that the basic paster special effect elements are arranged in the video image, the scene image collected by the camera is combined with the basic paster special effect elements to obtain a candidate image; and under the condition that the video picture does not comprise the basic paster special effect element, the scene picture collected by the camera is taken as a candidate picture. By carrying out mirror image processing on the candidate pictures, the problem that special effect elements are displayed wrongly due to the fact that the mirror image sensitive target sticker special effect elements are directly subjected to mirror image processing is avoided. Thereby achieving the effect of improving the accuracy of content display.

As an optional scheme, after performing mirroring processing on a candidate picture extracted from a live video picture to obtain a mirrored candidate picture, the method further includes:

s1, determining the positions of key points of the human face associated with the special effect elements of the target sticker from the human face area presented in the live video picture;

s2, extracting the features of the key points of the face to obtain the face feature information;

s3, determining a face picture area corresponding to the face feature information in the mirror image candidate picture;

s4, generating mirror image video stream data based on the face picture area.

It should be noted that, although the problem of code confusion caused by mirror image flipping can be solved by rendering the target sticker special effect elements separately, some target sticker special effect elements may depend on the face area of the target object presented in the video picture (i.e., there is an association relationship). For example, the target special effect element of the sticker is a face-following sticker, the display of the face area will change with the change of the face pose (such as the pose of the front face, the pose of the side face, and the like), the display position of the target special effect element of the sticker will change with the change of the face area, and the type of the target special effect element needs to depend on the processing module to determine the position of the rendering in the face area.

Alternatively, in this embodiment, but not limited to, a face key point position associated with the target sticker special effect element may be determined from a face area presented in a live video picture, and then mirror video stream data may be generated based on the face area determined by face feature information extracted from the face key point position. The position of the key point of the face associated with the target paster special effect element can be, but is not limited to, the display position of the target paster special effect element with the face following effect.

It should be noted that the face area often includes a plurality of face key points, but in this embodiment, mainly the target sticker special effect element is pushed and displayed. Therefore, for the scene, in the transmission process, the face picture area can be determined according to the position of the face key point associated with the target paster special effect element without transmitting all contents in the face area, so that the effect of reducing the transmission quantity is realized.

The mainstream business algorithm in the related art outputs about 100 face key points, and each face key point can represent its X-axis and Y-axis coordinates by using, but not limited to, 2 floating point numbers.

For example, as shown in fig. 6, five face key points, namely, the two sides (A, B) of the face, the chin (E), the eyebrow (B) and the nose (D), can be used, but are not limited to, at the anchor end (i.e., anchor end) to locate the target sticker special effect element with the face following effect. That is, the relative position relationship between the target sticker special effect element and the face key point is obtained, so that the current face pose can be accurately positioned at the audience (namely, the audience) based on the five face key points, and the display position corresponding to the label paper special effect element is marked under the face pose. For example, the head width (AC) is calculated by combining the left and right forehead, the head height (BE) is calculated by combining the eyebrow center (B) and the chin (E), and the face orientation information (BD: DE and AB: BC) is calculated by combining the distance between the nose (D) and the two sides (A, B) of the face.

In addition, in addition to the mode of positioning by using five face key points, more or fewer key points can be transmitted according to business needs to perform more detailed special effect making, such as transmitting all face key points, performing face liquid beauty treatment and makeup treatment, and the like.

For example, as shown in fig. 7, when the anchor terminal performs network streaming to the audience terminal, if it is determined that a target sticker special effect element is arranged (i.e., an additional special effect) is arranged, a face key point position associated with the target sticker special effect element may be determined from a face area presented in a live video screen, a face screen area may be determined based on face feature information extracted from the face key point position, and then mirror image video stream data (such as the attached face AI data shown in the figure) generated based on the face screen area may be streamed to the audience terminal.

According to the embodiment provided by the application, under the condition that the target paster special effect element has an incidence relation with the face area presented in the live video picture, the face picture area of the face key point position which is determined from the face area and is associated with the target paster special effect element and the target paster special effect element are compressed together, so that mirror image video stream data is generated. Therefore, the purposes of reducing the live broadcast transmission data volume and improving the transmission efficiency are achieved.

As an optional scheme, after feature extraction is performed on key point positions of a face to obtain face feature information, the method further includes:

and S1, respectively storing the coordinate information of the pixel point corresponding to each human face key point position into each data bit corresponding to the integer type variable.

It should be noted that, in the case that the key feature point is accurate to the pixel level, the screen of the mobile terminal is considered to be a pixel ratio of 2000 × 3000, and therefore, in the present embodiment, a single integer type variable int may be used, but is not limited to, to represent the coordinates of one pixel point.

According to the embodiment provided by the application, the coordinate information of the special effect element of the target sticker is stored by adopting the integer type variable, so that the position deviation is small, the storage occupied space is small, and the data processing amount is further reduced.

As an optional scheme, storing the coordinate information of the pixel point corresponding to each human face key point position into each data bit corresponding to the integer type variable respectively includes: storing the abscissa information of the pixel points into a first sequence data bit of the integer type variable, and storing the ordinate information of the pixel points into a second sequence data bit of the integer type variable.

For example, a value within 1 hundred million is used to represent coordinate information of a key feature point, wherein ten million to ten thousand bits are used to represent X-axis pixel coordinates, ten thousand to one bit are used to represent Y-axis pixel coordinates, and each coordinate component has 10000 subdivision levels in total to cover pixel orientations of most mobile terminals and avoid large position deviation.

According to the embodiment provided by the application, the abscissa information and the ordinate information of the special effect element of the target sticker are respectively stored in different sequence data bits of the integer type variable, so that transmission by using one variable is realized, the storage occupied space is small, and the data processing amount is further reduced.

According to another aspect of the embodiments of the present invention, there is provided a video processing method, optionally, as shown in fig. 8, the video processing method includes:

s802, receiving mirror image video stream data sent by a main broadcaster and additional special effect data corresponding to a target paster special effect element, wherein the difference degree between the mirror image paster special effect element obtained after the target paster special effect element is subjected to mirror image processing and the target paster special effect element is larger than a target threshold value;

s804, mirror image candidate pictures are analyzed from the mirror image video stream data, wherein the mirror image candidate pictures are obtained after mirror image processing is carried out on the candidate pictures, and the candidate pictures are video pictures obtained after target paster special effect elements are removed from the live broadcast video pictures;

s806, rendering the target paster special effect element to the mirror image candidate picture according to the additional special effect data to obtain a mirror image video picture.

Optionally, in this embodiment, the video processing method may be widely applied to, but not limited to, scenes such as a front camera of a mobile phone, short video shooting, and video. Video scenes herein may include, but are not limited to: online education, online eating and broadcasting, online shopping, etc. In addition, in this embodiment, the timing of performing the mirroring process on the captured scene picture may include, but is not limited to: camera acquisition, anchor presentation, plug flow, etc. The execution subject of the video processing method here may be the terminal device 106 shown in fig. 1 as the viewer side in the process. The above list is an example, and this is not limited in this embodiment.

According to the embodiment provided by the application, under the condition that the mirror image video stream data sent by the anchor terminal and the additional special effect data corresponding to the target paster special effect element are received, the mirror image candidate picture is analyzed from the mirror image video stream data, the target paster special effect element is rendered onto the mirror image candidate picture according to the additional special effect data, so that the mirror image video picture is obtained, and the mirror image video picture is displayed in the audience terminal. Therefore, the special effect elements of the target sticker can be normally rendered and displayed in the mirror image video picture, the problem that the special effect elements are displayed wrongly due to mirror image processing of the special effect elements of the target sticker sensitive to the mirror image is avoided, and the effect of improving the accuracy of content display is achieved.

As an alternative, rendering the target sticker special effect element onto the mirror image candidate picture according to the additional special effect data to obtain a mirror image video picture includes:

s1, acquiring a first display area corresponding to the target paster special effect element from the additional special effect data, wherein the first display area is a display area of the target paster special effect element in a video picture displayed by a main broadcast end;

s2, determining a corresponding second display area in the audience after the mirror image processing of the first display area;

and S3, when the mirror image candidate picture is displayed, rendering the target paster special effect element in the second display area to obtain a mirror image video picture.

It should be noted that, the types of the playback application clients used in the viewer side (i.e., the viewer side) are different, and the display resolutions are different. Therefore, in this embodiment, in order to ensure that the mirrored video picture is not distorted, but not limited to, the mirroring process is performed on the position of the first display region where the target sticker special effect element is located, but the mirroring process is not performed on the target sticker special effect element itself.

For example, the screen position of the anchor side during stream pushing is mapped to the video stream display position of the viewer side in an equal ratio, and when mirror image turning exists, turning operation can be performed on the X axis. The formula of the horizontal flip coordinate is: xnew ═ screen width-Xold. The calculation mode of the vertical flipping can be constructed by referring to the above formula, which is not limited herein.

According to the embodiment provided by the application, after the first display area corresponding to the special effect element of the target paster is obtained from the additional special effect data, the second display area corresponding to the first display area in the audience after mirror image processing is carried out is determined, and therefore when the mirror image candidate picture is displayed, the mirror image accuracy of the display position of the special effect element of the target paster can be ensured.

As an optional solution, when the mirror image video picture is displayed, the method includes:

s1, when the mirror image video stream data is received at the preset transmission frame rate, linear interpolation processing is performed between any two frames of the mirror image video frames displayed.

It should be noted that, in the related art, the standard video streaming transmission rate is 15 frames per second, and in this embodiment, in order to save transmission resources, the transmission rate can be reduced to 5 frames per second to 10 frames per second. However, due to the reduction of the transmission frame rate, when the target sticker special effect element is rendered at the viewer end, the phenomena of display blockage and low updating frequency are generated due to the slow updating of the dependent AI data. In response to this phenomenon, the present embodiment performs a linear difference or 1/2 approximate difference based on the time difference between two frames.

By the embodiment provided by the application, the two frames of mirror image video pictures are subjected to linear interpolation processing, so that smooth transition of the mirror image video pictures received by reducing the transmission frame rate is realized, and the problem of display blockage is avoided.

According to another aspect of the embodiment of the invention, a video processing device is also provided. As shown in fig. 9, the apparatus includes:

1) a display unit 902 configured to display a live video frame at a anchor terminal, where the live video frame includes a scene frame input by a camera of the anchor terminal and a sticker special effect element superimposed on the scene frame;

2) a mirror image processing unit 904 configured to perform mirror image processing on a candidate picture extracted from the live video picture in response to a mirror image processing instruction for the live video picture to obtain a mirror image candidate picture, where the candidate picture is a video picture obtained by removing a target sticker special effect element from the live video picture, and a difference between the mirror image sticker special effect element obtained by mirroring the target sticker special effect element and the target sticker special effect element is greater than a target threshold;

3) the pushing unit 906 is configured to push the image video stream data corresponding to the image candidate picture and the additional special effect data corresponding to the target sticker special effect element to the viewer side, so that the viewer side displays a picture obtained by integrating the image candidate picture and the target sticker special effect element.

It should be noted that, here, the video processing apparatus may be, but is not limited to, a broadcaster side of an application broadcaster side, such as the terminal device 102 shown in fig. 1, and embodiments thereof may refer to the foregoing method embodiments, which are not described herein again.

As an optional scheme, the method further comprises the following steps:

the device comprises a first determining unit, a second determining unit and a third determining unit, wherein the first determining unit is used for merging a scene picture and a basic paster special effect element to obtain a candidate picture under the condition that the paster special effect element superposed on the scene picture comprises a target paster special effect element and the basic paster special effect element before a candidate picture extracted from a live video picture is subjected to mirroring to obtain a mirrored candidate picture, and the difference degree between the mirrored paster special effect element obtained after the basic paster special effect element is subjected to mirroring and the basic paster special effect element is smaller than or equal to a target threshold value;

and the second determining unit is set to take the scene picture input by the camera of the anchor terminal as a candidate picture under the condition that the paster special effect element superposed on the scene picture is the target paster special effect element.

Optionally, in this embodiment, reference may be made to the above method embodiment for embodiments of each module described above, and details are not described here again.

As an optional scheme, the method further comprises the following steps:

the third determining unit is arranged for determining the position of a key point of a human face associated with the special effect element of the target sticker from a human face area presented in the live video picture after the candidate picture extracted from the live video picture is subjected to mirror image processing to obtain a mirror image candidate picture;

the extraction unit is used for extracting the features of the key points of the face to obtain the face feature information;

the fourth determining unit is arranged to determine a face picture area corresponding to the face feature information in the mirror image candidate picture;

a generating unit configured to generate mirror image video stream data based on the face picture area.

As an optional scheme, the method further comprises the following steps:

and the storage unit is used for respectively storing the coordinate information of the pixel point corresponding to each human face key point position into each data bit corresponding to the integer type variable after the feature extraction is carried out on the human face key point position to obtain the human face feature information.

As an alternative, the storage unit includes:

the storage module is used for storing the abscissa information of the pixel points into a first sequence data bit of the integer type variable and storing the ordinate information of the pixel points into a second sequence data bit of the integer type variable.

According to another aspect of the embodiment of the invention, a video processing device is also provided. As shown in fig. 10, the apparatus includes:

1) a receiving unit 1002, configured to receive mirror image video stream data and additional special effect data corresponding to a target sticker special effect element, where a difference between the mirror image sticker special effect element obtained after mirror image processing of the target sticker special effect element and the target sticker special effect element is greater than a target threshold;

2) the analysis unit 1004 is configured to analyze a mirror image candidate picture from mirror image video stream data, wherein the mirror image candidate picture is a picture obtained by performing mirror image processing on the candidate picture, and the candidate picture is a video picture obtained by removing a target sticker special effect element from a live video picture;

3) a rendering unit 1006, arranged to render the target sticker special effect element onto the mirrored candidate picture according to the additional special effect data to obtain a mirrored video picture.

It should be noted that, here, the video processing apparatus may be, but is not limited to, a viewer side of an application anchor side, such as the terminal device 106 shown in fig. 1, and for an embodiment thereof, reference may be made to the foregoing method embodiment, which is not described herein again.

As an alternative, the rendering unit 1006 includes:

the acquisition module is used for acquiring a first display area corresponding to the target paster special effect element from the additional special effect data, wherein the first display area is a display area of the target paster special effect element in a video picture displayed by the anchor terminal;

the determining module is used for determining a corresponding second display area in the audience after the first display area is subjected to mirror image processing;

and the rendering module is configured to render the target paster special effect element in the second display area to obtain the mirror image video picture when the mirror image candidate picture is displayed.

As an optional solution, the rendering unit 1006 further includes:

and the processing module is used for performing linear interpolation processing on any two frames of displayed mirror image video pictures under the condition of receiving mirror image video stream data according to a preset transmission frame rate.

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

In an exemplary embodiment, there is also provided an electronic device including: a processor; a memory for storing processor-executable instructions, wherein the processor is configured to execute the instructions to implement the video processing method recited in any of the embodiments above.

Optionally, in this embodiment, the electronic device may be located in at least one network device of a plurality of network devices of a computer network.

Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:

s1, displaying a live video picture at the anchor terminal, wherein the live video picture comprises a scene picture input by a camera of the anchor terminal and a paster special effect element superposed on the scene picture;

s2, in response to a mirror image processing instruction of the live video picture, carrying out mirror image processing on a candidate picture extracted from the live video picture to obtain a mirror image candidate picture, wherein the candidate picture is a video picture obtained by removing a target paster special effect element from the live video picture, and the difference between the mirror image paster special effect element obtained by mirror image processing of the target paster special effect element and the target paster special effect element is greater than a target threshold value;

and S3, pushing the mirror image video stream data corresponding to the mirror image candidate picture and the additional special effect data corresponding to the special effect element of the target sticker to a spectator, so that the spectator can display the picture obtained by integrating the mirror image candidate picture and the special effect element of the target sticker.

Optionally, in this embodiment, the processor may be further configured to execute, by the computer program, the following steps:

s1, receiving mirror image video stream data sent by a main broadcaster and additional special effect data corresponding to the target paster special effect elements, wherein the difference degree between the mirror image paster special effect elements obtained after the mirror image processing of the target paster special effect elements and the target paster special effect elements is larger than a target threshold value;

s2, mirror image candidate pictures are analyzed from the mirror image video stream data, wherein the mirror image candidate pictures are obtained after mirror image processing is carried out on the candidate pictures, and the candidate pictures are video pictures obtained after target paster special effect elements are removed from the live broadcast video pictures;

and S3, rendering the target paster special effect element to the mirror image candidate picture according to the additional special effect data to obtain a mirror image video picture.

Alternatively, as will be understood by those skilled in the art, the electronic device may also be a terminal device such as a smart phone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, and a Mobile Internet Device (MID), a PAD, etc. The memory may include, among other things, high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include memory located remotely from the processor, and these remote memories may be connected to the terminal through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof. In addition, the video processing apparatus may further include, but is not limited to, other module units in the video processing apparatus, which is not described in this example again.

Optionally, the electronic device may further include a transmission device, configured to receive or transmit data via a network. Examples of the network may include a wired network and a wireless network. In one example, the transmission device includes a Network adapter (NIC) that can be connected to the router via a Network cable and other Network devices to communicate with the internet or a local area Network. In one example, the transmission device is a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.

In an exemplary embodiment, a computer-readable storage medium comprising instructions, such as a memory comprising instructions, executable by a processor of an apparatus to perform the above-described method is also provided. Alternatively, the computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

Optionally, in this embodiment, the computer-readable storage medium may be configured to store computer instructions for performing the following steps:

Optionally, in this embodiment, the computer-readable storage medium may be further configured to store computer instructions for performing the following steps:

In an exemplary embodiment, a computer program product is also provided, comprising a computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to perform the video processing described above.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A video processing method, comprising:

displaying a live video picture at a main broadcasting end, wherein the live video picture comprises a scene picture input by a camera of the main broadcasting end and a paster special effect element superposed on the scene picture;

in response to a mirror image processing instruction of the live video picture, carrying out mirror image processing on a candidate picture extracted from the live video picture to obtain a mirror image candidate picture, wherein the candidate picture is a video picture obtained by removing a target paster special effect element from the live video picture, and the difference between the mirror image paster special effect element obtained by carrying out mirror image processing on the target paster special effect element and the target paster special effect element is greater than a target threshold value;

and pushing the mirror image video stream data corresponding to the mirror image candidate picture and the additional special effect data corresponding to the target paster special effect element to a spectator end so that the spectator end can display a picture obtained by integrating the mirror image candidate picture and the target paster special effect element.

2. The method according to claim 1, wherein before mirroring the candidate pictures extracted from the live video pictures to obtain mirrored candidate pictures, further comprising:

combining the scene picture with the basic paster special effect element to obtain the candidate picture under the condition that the paster special effect elements superposed on the scene picture comprise the target paster special effect element and the basic paster special effect element, wherein the difference degree between the mirror image paster special effect element obtained after the mirror image processing of the basic paster special effect element and the basic paster special effect element is smaller than or equal to the target threshold value;

and taking the scene picture input by the camera of the anchor end as the candidate picture under the condition that the paster special effect element superposed on the scene picture is the target paster special effect element.

3. The method according to claim 1, wherein after performing mirroring on candidate pictures extracted from the live video pictures to obtain mirrored candidate pictures, the method further comprises:

determining the positions of key points of the human face associated with the target paster special effect elements from the human face area presented in the live video picture;

extracting features of the key point positions of the human face to obtain human face feature information;

determining a face picture area corresponding to the face feature information in the mirror image candidate picture;

and generating the mirror image video stream data based on the face picture area.

4. The method of claim 3, wherein after performing feature extraction on the positions of the face key points to obtain face feature information, the method further comprises:

and respectively storing the coordinate information of the pixel point corresponding to each human face key point position into each data bit corresponding to the integer type variable.

5. A video processing method, comprising:

receiving mirror image video stream data sent by a main broadcaster and additional special effect data corresponding to a target paster special effect element, wherein the difference degree between the mirror image paster special effect element obtained after mirror image processing of the target paster special effect element and the target paster special effect element is larger than a target threshold value;

analyzing a mirror image candidate picture from the mirror image video stream data, wherein the mirror image candidate picture is a picture obtained by carrying out mirror image processing on the candidate picture, and the candidate picture is a video picture obtained by removing the target paster special effect element from a live video picture;

rendering the target paster special effect element to the mirror image candidate picture according to the additional special effect data to obtain a mirror image video picture.

6. A video processing apparatus, comprising:

the display unit is arranged for displaying a live video picture at a main broadcasting end, wherein the live video picture comprises a scene picture input by a camera of the main broadcasting end and a paster special effect element superposed on the scene picture;

the mirror image processing unit is used for responding to a mirror image processing instruction of the live video picture, carrying out mirror image processing on a candidate picture extracted from the live video picture to obtain a mirror image candidate picture, wherein the candidate picture is a video picture obtained by removing a target paster special effect element from the live video picture, and the difference degree between the mirror image paster special effect element obtained by mirror image processing of the target paster special effect element and the target paster special effect element is larger than a target threshold value;

and the pushing unit is used for pushing the mirror image video stream data corresponding to the mirror image candidate picture and the additional special effect data corresponding to the target paster special effect element to a spectator end so as to enable the spectator end to display a picture obtained by integrating the mirror image candidate picture and the target paster special effect element.

7. A video processing apparatus, comprising:

the receiving unit is arranged for receiving mirror image video stream data sent by a main broadcast terminal and additional special effect data corresponding to a target paster special effect element, wherein the difference degree between the mirror image paster special effect element obtained after the mirror image processing of the target paster special effect element and the target paster special effect element is larger than a target threshold value;

the analysis unit is used for analyzing a mirror image candidate picture from the mirror image video stream data, wherein the mirror image candidate picture is a picture obtained after mirror image processing is carried out on the candidate picture, and the candidate picture is a video picture obtained after the target paster special effect element is removed from a live video picture;

and the rendering unit is used for rendering the target paster special effect element to the mirror image candidate picture according to the additional special effect data so as to obtain a mirror image video picture.

8. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the video processing method of any of claims 1 to 5.

9. A computer-readable storage medium whose instructions, when executed by a processor of an electronic device, enable the electronic device to perform the video processing method of any of claims 1 to 5.

10. A computer program product comprising a computer program, characterized in that the computer program realizes the video processing method of any of claims 1 to 5 when executed by a processor.