CN112911318A - Live broadcast room background replacement method and device, electronic equipment and storage medium - Google Patents

Live broadcast room background replacement method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN112911318A
CN112911318A CN202110057243.9A CN202110057243A CN112911318A CN 112911318 A CN112911318 A CN 112911318A CN 202110057243 A CN202110057243 A CN 202110057243A CN 112911318 A CN112911318 A CN 112911318A
Authority
CN
China
Prior art keywords
image
background
video frame
live video
live
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110057243.9A
Other languages
Chinese (zh)
Other versions
CN112911318B (en
Inventor
林刘生
李武军
王文斓
孔维安
张鹏
张广乾
马海城
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Huya Technology Co Ltd
Original Assignee
Guangzhou Huya Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangzhou Huya Technology Co Ltd filed Critical Guangzhou Huya Technology Co Ltd
Priority to CN202110057243.9A priority Critical patent/CN112911318B/en
Publication of CN112911318A publication Critical patent/CN112911318A/en
Application granted granted Critical
Publication of CN112911318B publication Critical patent/CN112911318B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/21—Server components or server architectures
    • H04N21/218—Source of audio or video content, e.g. local disk arrays
    • H04N21/2187—Live feed
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
    • H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
    • H04N21/23424—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving splicing one content stream with another content stream, e.g. for inserting or substituting an advertisement
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/239—Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests
    • H04N21/2393—Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests involving handling client requests
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/41—Structure of client; Structure of client peripherals
    • H04N21/426—Internal components of the client ; Characteristics thereof
    • H04N21/42653—Internal components of the client ; Characteristics thereof for processing graphics
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/437—Interfacing the upstream path of the transmission network, e.g. for transmitting client requests to a VOD server
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
    • H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
    • H04N21/44016—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving splicing one content stream with another content stream, e.g. for substituting a video clip

Abstract

The embodiment of the application provides a live broadcast room background replacement method and device, electronic equipment and a storage medium, and relates to the technical field of live broadcast image processing. The method comprises the following steps: sending a background replacement request to an AI server; the live broadcast room server responds to a background replacement request and sends an original live broadcast video stream to an AI server; establishing connection with the AI server, and receiving an image mask returned by the AI server for image segmentation of the original live video stream; and acquiring a replacing background video frame, and synthesizing the replacing background video frame, the image mask and the live video frame to obtain a live video image of the replacing background. The technical scheme of the application can ensure the processing speed of the audience end to the live video frame.

Description

Live broadcast room background replacement method and device, electronic equipment and storage medium
Technical Field
The application relates to the technical field of live image processing, in particular to a live room background replacement method and device, an electronic device and a storage medium.
Background
As the network live broadcast room goes deep into the fields of consumption and entertainment, the picture design of the live broadcast room is more and more diversified. The way of background replacement for live rooms is also a form of live room picture design.
At present, the background replacement of a live broadcast room has the following forms, one is that a request for converting the background is started and realized by a main broadcast, and then a live broadcast video stream after the formed background replacement is pushed to a viewer, but the design of the live broadcast background can not meet the favorite requirements of the viewer; the other is that the request for converting the background is initiated and realized by the audience, and the realization method is that the audience device carries out secondary processing on the video image and synthesizes the segmented target image with other backgrounds. However, if the spectator end device processes each frame of image according to the live video stream, since the processing method needs to process the image data in real time, the requirement on the data processing capability of the spectator end is very high, and it is difficult to meet the current common spectator end device.
Disclosure of Invention
In order to solve the problem of data processing pressure caused by the fact that a viewer side carries out live broadcast room background replacement, the application provides a live broadcast room background replacement method and device, electronic equipment and a storage medium.
In a first aspect, an embodiment of the present application provides a method for replacing a main broadcast background of a live broadcast room, where the method includes the following steps:
sending a background replacing request to a live broadcast room server; the live broadcast room server responds to a background replacement request and sends an original live broadcast video stream to an AI server;
establishing connection with an AI server, and receiving an image mask returned by the AI server for image segmentation of the original live video stream;
and acquiring a replacing background video frame, and synthesizing the replacing background video frame, the image mask and the live video frame to obtain a live video image of the replacing background.
In an optional embodiment of the first aspect, compositing the replacement background video frame, the image mask, and the live video frame comprises:
performing image filtering on the live video frame by using the image mask to obtain a filtered image;
and in the range of the live video frames, performing background filling on the filtered image by using the replacement background video frames to obtain a background replacement image of a live room, and displaying the background replacement image after rendering.
In an optional embodiment of the first aspect, the image combining with the live video frame by using the image mask to obtain a filtered image includes:
respectively acquiring timestamps of the image mask and an original live video frame;
matching according to a first timestamp of the live video frame and a second timestamp of the image mask;
and when the matching is successful, performing image filtering by using the image mask and the live video frame to obtain a filtered image after the live video frame is masked.
In an optional embodiment of the first aspect, said matching according to the first timestamp of the live video frame with the second timestamp of the image mask comprises:
caching the image masks according to the sequence of the second timestamps to form a priority matching queue with a set length;
matching the first time stamp of the live video frame with a second time stamp corresponding to the image mask in the priority matching queue according to the first time stamp of the live video frame and a set time difference range;
judging whether the difference value of the first time stamp and the second time stamp is within a preset time difference range or not;
wherein a first timestamp of the live video frame is greater than or equal to a second timestamp of the image mask.
In an optional embodiment of the first aspect, the method for replacing a main broadcast background of a live broadcast room further includes:
when the matching of the first time stamp of the live video frame and the second time stamp of the image mask fails, judging whether a filtering image which is successfully matched is cached;
if so, continuously playing the filtering image until obtaining the next filtering image successfully matched again;
otherwise, playing the current live video frame.
In an optional embodiment of the first aspect, the image filtering the live video frame by using the image mask to obtain a filtered image includes:
covering the image mask on the live video frame, and filtering the live video frame image through the hollow area of the image mask to obtain the filtered image.
In an optional embodiment of the first aspect, before the background filling the filtered image with the replacement background video frame, the method further includes:
acquiring a replacing background video stream, and starting a decoding subprogram to decode the replacing background video stream to obtain a plurality of background frames;
and performing rendering function call-back on each background frame to obtain a corresponding replacement background video frame.
In a second aspect, an embodiment of the present application further provides another anchor background replacement method for a live broadcast room
According to a background replacement request sent by a viewer, acquiring an original live video stream, decoding each live video frame obtained by the original live video stream, and performing image segmentation on the live video frame to obtain an image mask;
and sending the image mask to a viewer end, so that the viewer end performs image combination with the original live video frame according to the background replacement request.
In an optional embodiment of the second aspect, the image segmenting the live video frame to obtain an image mask includes:
performing image recognition on the live video frame according to a preset image to obtain a filtering image area successfully matched with the preset image in the live video frame;
discarding the filtered image area to obtain an image mask along the image boundary and the filtered image area is a hollow area.
In an optional embodiment of the second aspect, the method for replacing the anchor background of the live broadcast room further includes:
sending the image mask to each viewer end of a broadcast group, so that the viewer ends perform image combination with the live video frames according to the respective sent background replacement requests;
wherein the broadcast group comprises a set of all viewers receiving the image mask.
In a third aspect, an embodiment of the present application provides a device for replacing a main broadcast background of a live broadcast room, where the device for replacing a main broadcast background of a live broadcast room includes:
the replacing request sending module is used for sending a background replacing request to the live broadcast room server; the live broadcast room server responds to a background replacement request and sends an original live broadcast video stream to an AI server;
the image mask receiving module is used for establishing connection with an AI server and receiving an image mask returned by the AI server for image segmentation of the original live video stream;
and the image synthesis module is used for acquiring the replacement background video frame, and synthesizing the replacement background video frame, the image mask and the live video frame to obtain the live video image of the replacement background.
In a fourth aspect, an embodiment of the present application further provides another anchor background replacing apparatus for a live broadcast room, where the anchor background replacing apparatus for the live broadcast room includes:
the image segmentation module is used for acquiring an original live video stream according to a background replacement request sent by a viewer, decoding each live video frame obtained by the original live video stream, and performing image segmentation on the live video frame to obtain an image mask;
and the image mask sending module is used for sending the image mask to a spectator end so that the spectator end performs image combination with the original live video frame according to the background replacing request.
In a fifth aspect, an electronic device is provided, which includes:
one or more processors;
a memory;
one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to: the method for replacing the anchor background of the live broadcast room provided by the first aspect or the second aspect of the embodiment of the application is implemented.
In a sixth aspect, a computer-readable storage medium is provided, on which a computer program is stored, where the computer program is executed by a processor, and is characterized in that the program implements a main broadcast background replacement method for a live broadcast room provided in the first aspect or the second aspect of the embodiments of the present application.
The technical scheme provided by the embodiment of the application has the following beneficial effects:
according to the background replacement request sent by the audience, the image of the live video frame obtained by decoding the current live video stream is segmented at the AI server to obtain the image mask, the live video frame and the replacement background are combined to obtain the original live video background which is correspondingly filtered, and the replacement background corresponding to the corresponding background replacement request is added to the live video picture, so that the audience can quickly and automatically control the occurrence of the current live video background and the replacement rhythm; and the running speed is not slowed down because a large number of live video frames need to be subjected to image processing.
According to the other live broadcast room background replacement scheme provided by the embodiment of the application, the AI server completes decoding of the original live broadcast video stream, and meanwhile, image segmentation can be continuously performed on a plurality of live broadcast video frames, so that a spectator end can synthesize live broadcast video images for replacing the background, and limitation to the processing capacity of the spectator end is avoided. Therefore, the technical scheme solves the problem that the processing capacity of the audience terminal cannot meet the background replacement request of the audience to the live broadcast interface, and enables the audience terminal to quickly and automatically control the occurrence of the current live broadcast background and the replacement rhythm; and the running speed is not slowed down because a large number of live video frames need to be subjected to image processing.
Additional aspects and advantages of embodiments of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of embodiments of the present application.
Drawings
The foregoing and/or additional aspects and advantages of embodiments of the present application will become apparent and more readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a diagram of an application environment of an embodiment provided herein;
fig. 2 is a schematic flowchart of a method for replacing a main broadcast background of a live broadcast room according to an embodiment of the present application;
fig. 3 is a schematic flowchart of the step S130 provided in the embodiment of the present application;
FIG. 4a is a diagram of a live video frame provided by an embodiment of the present application;
FIG. 4b is a view of the image mask corresponding to FIG. 4 a;
FIG. 4c is a view of an alternative background video frame;
FIG. 4d is a view of a synthesized live video image with an alternative background;
fig. 5 is an execution framework diagram of a method for replacing a main broadcast background of a live broadcast room according to an embodiment of the present application;
fig. 6 is a flowchart illustrating a method for replacing a main broadcast background of another live broadcast room according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an apparatus for replacing anchor background of a live broadcast room according to an embodiment of the present disclosure;
fig. 8 is a schematic structural diagram of an apparatus for replacing anchor background of another live broadcast room according to an embodiment of the present disclosure;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application, where the method for replacing an anchor background in a live broadcast room is provided.
Detailed Description
Reference will now be made in detail to the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 is a diagram of an application environment of an embodiment provided in the present application.
The application environment in the embodiments provided in the present application includes at least a viewer side, a live room server and an AI server, and a main cast side. In the live broadcasting process, the anchor terminal generates a live video stream and sends the live video stream to the audience terminal through the live broadcasting room server. And the audience end and the AI server form a data transmission line, acquire data for image segmentation from the AI server according to the background replacement request, and synthesize the current live video data and the acquired data for image segmentation at the audience end.
Referring to fig. 2, fig. 2 is a flowchart illustrating a main broadcast background replacing method for a live broadcast room according to an embodiment of the present disclosure.
Taking the application scenario provided above as an example, the anchor background replacement method for a live broadcast room provided in the embodiment of the present application may include the following steps:
s210, sending a background replacing request to a live broadcast room server; and the live broadcast room server responds to the background replacement request and sends the original live broadcast video stream to the AI server for image segmentation.
In this embodiment, when the audience receives a background replacement instruction sent by the audience through an operation interface or other manners, a corresponding background replacement request is generated, and the corresponding background replacement request is sent to the AI server. And the AI server receives and forwards the background replacing request to the live broadcast room server to obtain the current original live broadcast video stream. And the AI server decodes the received original live video stream according to the background replacement request to obtain a plurality of continuous live video frames forming the original live video stream, and performs image segmentation on the live video frames.
S220, establishing connection with an AI server, and receiving an image mask returned by the AI server for image segmentation of the original live video stream.
The AI server acquires the background replacing request, performs image segmentation on the original live video stream, establishes a communication connection relation with the audience terminal, and forms a corresponding transmission line. And receiving an image mask returned by the original live video stream by an AI server by using the transmission line audience.
The live video frame is subjected to image segmentation, and all the obtained live video frames can be subjected to image segmentation processing; if the background replacement obtained by analyzing the background replacement request does not exist continuously, if only exists for a period of time or alternately exists with the original live video frame, the original live video frame corresponding to the corresponding image mask is obtained according to the effect setting of the replacement background, and the image mask corresponding to the live video frame is obtained.
The image mask can be formed according to the image recognition result of the original live video frame, the area with successful image recognition is a filtering image area, and other areas are mask image areas. And hollowing out the filtered image area, and uniformly mixing colors of the mask image area to obtain the image mask hollowed out in the filtered image area.
And S230, acquiring a replacing background video frame, and synthesizing the replacing background video frame, the image mask and the original live video frame to obtain a live video image of the replacing background.
And the audience terminal performs image synthesis on the image mask acquired by the AI server, the original live broadcast video frame obtained by data processing of the original live broadcast video stream from the live broadcast room server and the replacement background video frame requested to be replaced to obtain the live broadcast video image with the replacement background.
The acquisition of the original live video frame can be obtained by decoding the original live video stream.
And for the alternative background video frame, extracting a corresponding alternative background video stream according to the selection of the background of the user at the audience end, starting decoding sub-molding, and decoding the alternative background video stream to obtain a plurality of background frames. In this embodiment, each acquired background frame is subjected to a callback of a rendering function, where the callback may be a callback of a rendering function performed on a background frame according to extracted image parameters of the current original live broadcast video frame, such as brightness, resolution, or depth-of-field aperture coefficient of the background, so as to obtain a substitute background video frame.
According to the method for replacing the main broadcast background of the live broadcast room, the obtained live broadcast video frame obtained by decoding the current live broadcast video stream is subjected to image segmentation at the AI server according to the background replacement request sent by the audience, an image mask is obtained, the image mask, the live broadcast video frame and the replacement background are combined to obtain the original live broadcast video background which is correspondingly filtered, and the replacement background corresponding to the corresponding background replacement request is added to a live broadcast picture, so that the audience can quickly and automatically control the appearance and the replacement rhythm of the current live broadcast background; and the running speed is not slowed down because a large number of live video frames need to be subjected to image processing.
Referring to fig. 3, fig. 3 is a schematic flowchart of step S130 provided in the embodiment of the present application.
The step S230 may further include:
s231, performing image filtering on the live video frame by using the image mask to obtain a filtered image;
and S232, performing background filling on the filtered image by the replacing background video frame within the range of the live video frame to obtain a background replacing image of a live broadcast room, and displaying the background replacing image after rendering.
In steps S231-S232, since the image mask is an image mask hollowed out in the filtered image region, the image mask is overlapped with the live video frame, that is, the live video frame is filtered to obtain a region image corresponding to the hollowed-out image mask.
Referring to fig. 4a, 4b, 4c and 4d, fig. 4a is a view of a live video frame provided in the present embodiment, fig. 4b is a view of an image mask corresponding to fig. 4a, fig. 4c is a view of an alternative background video frame, and fig. 4d is a view of a synthesized live video image with an alternative background.
Referring to fig. 4a, it is possible to obtain a live broadcast of a main broadcast, wherein, in the broadcast, except for the main broadcast, the other parts of the view are main broadcast backgrounds, which are image areas that the viewers want to replace, i.e. mask image areas, and the main broadcast character image areas are filtered image areas.
In this embodiment, the training parameters for the person image region recognition are obtained through a manner such as training of image data of a person. And according to the training parameters, carrying out character recognition on the live video frame, and extracting a character image area as a filtering image area. The filtered image area is hollowed out, and simultaneously, areas outside the character image area of the live video frame are uniformly turned into black to form a hollowed-out area, which is an image mask of the character image, as shown in fig. 4 b.
Covering the image mask to the current original live broadcast video frame, filtering the image area corresponding to the image mask image area of the image mask, and only displaying the filtered image corresponding to the image mask hollow-out area in the live broadcast video frame. In this embodiment, the anchor image in the original live video frame is filtered through image filtering, so as to obtain a filtered image with only the anchor image.
By using the replacement background video frame, as shown in fig. 4c, the image area other than the anchor image in the current original live video frame is background-filled, and a rendering manner is performed, for example, a connection area between the anchor image and the replacement background is filtered and rendered, so as to obtain a background replacement image in the current live video frame, thereby obtaining a live video frame with a replaced background.
In this embodiment, the background filling may be that the obtained filtered image corresponds to a first image layer, and the replacement background video frame corresponds to a second image layer. In the first image layer, only the filtered image obtained through filtering is displayed, and other areas are transparent areas. And the second image layer displays the image in the whole area according to the replacing background video frame. When background filling is performed, the second image layer is placed behind the first image layer, and a live video image with a replaced background is obtained after rendering, as shown in fig. 4 d.
The background filling may also be to obtain a boundary of a hollow-out region according to an image mask, obtain a replacement background region corresponding to a non-hollow-out region through image segmentation in a replacement background video frame according to the boundary, and synthesize the replacement background region and the filtered image to obtain a live video image with a background replaced. And after the live video image with the replaced background is rendered by the audience, the live video image is pushed to a display unit to be displayed.
Continuing the above-mentioned embodiment in which the anchor image is used as the filtering image, the filtering image may also adjust the training parameters of the image recognition according to the current anchor scene, for example, the anchor image and the microphone image are used as the filtering image, and the training parameters such as the position and size of the microphone image are added to the training parameters of the original anchor image, so that the obtained live video image replacing the background can ensure a reasonable picture of the live scene.
For the step S231, the method may further include:
respectively acquiring timestamps of the image mask and an original live video frame; and matching according to the first time stamp of the live video frame and the second time stamp of the image mask. And when the matching is successful, performing image filtering by using the image mask and the live video frame to obtain a filtered image after the live video frame is masked.
In this embodiment, the remaining original live video frames of the image mask are matched by time stamps. In the embodiment, the second timestamp is used for naming, and the timestamp of the current live video frame acquired by the audience through the live broadcast room server is named by the first timestamp so as to be distinguished.
When the audience carries out time stamp matching with a second time stamp of an image mask received from the AI server according to a first time stamp of a live video frame after the live video frame, if the first time stamp and the second time stamp are the same, if the live video frame is marked as a 1000 th frame, and the image mask is also from a live video frame marked as the 1000 th frame, then a character image in the live video frame and a hollow-out area of the image mask aiming at the character image can be completely matched, namely the matching is successful. At this time, the live video frame of the 1000 th frame is subjected to image filtering by using the image mask of the 1000 th frame, so that a filtered image is obtained, in which only the character image in the live video frame is in the filtered image, and other image areas become black areas.
For the step of matching the first timestamp and the second timestamp, the method may further include:
caching the image masks according to the sequence of the second timestamps to form a priority matching queue with a set length;
matching the first time stamp of the live video frame with a second time stamp corresponding to the image mask in the priority matching queue according to the first time stamp of the live video frame and a set time difference range;
judging whether the difference value of the first time stamp and the second time stamp is within a preset time difference range or not;
wherein a first timestamp of the live video frame is greater than or equal to a second timestamp of the image mask.
And the audience terminal caches the received image masks returned by the AI server and sorts the cached image masks according to the corresponding second time stamps to form a priority matching queue. In one embodiment, the priority matching queue is of a certain set length, such as 3 frames. According to the set length, the live video frame data with the recently generated set length is cached, and the historical live video frames are discarded in time, so that the processing pressure in the data processing process of the audience is prevented from being increased.
In this embodiment, due to the setting of the transmission line and the capacity of the transmission data, for the live video frames marked by the same timestamp, the viewer usually acquires the corresponding image mask first and then acquires the corresponding original live video frames, so when receiving the original live video frames and acquiring the corresponding first timestamp, the maximum marked value of the second timestamp of the image mask in the priority matching queue is the same as the marked value of the first timestamp, or is smaller than the value of the first timestamp.
When the audience acquires the current live video frame, extracting a first time stamp of the live video frame, and matching the first time stamp with second time stamps of all image masks in the priority matching queue one by one. And if the second time stamp with the same marking value as the first time stamp does not exist in the priority matching queue, comparing the corresponding time of the first time stamp with the corresponding time of the second time stamp, and if the corresponding time difference of the first time stamp and the second time stamp is within a set time difference range, confirming that the image mask of the second time stamp is successfully matched with the current original live video frame corresponding to the first time stamp.
When the matching modes of the original live video frame and the image mask provided by the embodiment fail to match, whether a history of successfully matched filtered images are cached at present is determined. And if so, continuously playing the latest historical filtering image until the next filtering image which is successfully matched again is obtained. In other words, in the live broadcast picture of the audience, the latest historical filtered image and the replacement background video frame are continuously synthesized, at this time, the character image in the live broadcast video image of the formed replacement background is still in a short time, but the dynamic display of the replacement background, especially the dynamic replacement background, is not influenced, and the normal output of the audio data is not influenced. And continuously synthesizing the obtained new successfully-matched filtered image with the replaced background video frame, and updating the previous live video image with the replaced background.
If the cached historical successfully-matched filtering image does not exist, if the background replacing request is just received, the image mask returned by the AI server is not obtained yet, or the filtering image obtained through matching is obtained, or the historical filtering image is deleted, the viewer end directly pushes the currently-obtained original live video frame to the display device of the viewer end.
Referring to fig. 5, fig. 5 is an execution framework diagram of a main broadcast background replacement method for a live broadcast room according to an embodiment of the present application.
To more clearly illustrate the method for replacing the main broadcasting background between the broadcasters in the foregoing embodiment, an implementation procedure of an embodiment is provided below according to fig. 5, and includes the following steps:
s510, triggering a background replacing request by a viewer;
s520, starting and AI servers to receive the original live video frames and perform image segmentation;
s530, judging whether the audience receives the image mask or not; if yes, executing step S540, otherwise, executing step S531;
s531, pushing an original live video stream;
s540, judging whether the image mask is successfully matched with the time stamp of the original live video frame; if the step is successful, executing the step S550, otherwise, executing the step S531;
s550, decoding the obtained alternative background video stream;
s560, receiving the decoded background frame; if the background frame cannot be received, the process returns to step S550 to decode the alternative background video stream;
s570, synthesizing the alternative background video frame, the image mask and the live video frame;
s580, acquiring live video images of the replaced background;
and S590, displaying after rendering.
The above part is a method for replacing the anchor background of the live broadcast room provided by the audience as the executive party, and correspondingly, the application also provides a method for replacing the anchor background of the live broadcast room, and the executive party is an AI server.
Referring to fig. 6, fig. 6 is a flowchart illustrating a main broadcast background replacing method for another live broadcast room according to an embodiment of the present application.
The anchor background replacing method of the live broadcast room comprises the following steps:
s610, according to a background replacement request sent by a viewer, acquiring an original live video stream, decoding each live video frame obtained by the original live video stream, and performing image segmentation on the live video frame to obtain an image mask;
s620, the image mask is sent to a spectator end, so that the spectator end performs image combination with the original live video frame according to the background replacing request.
In steps S610-S620, when the AI server receives a background replacement request from the viewer, the AI server obtains an original live video stream from the live room server, and decodes the original live video stream to obtain each live video frame in the original live video stream. According to the image recognition result of the original live video frame, the area successfully recognized with the image is a filtering image area, and other areas are mask image areas. And hollowing out the filtered image area, and uniformly mixing colors of the mask image area to obtain the image mask hollowed out in the filtered image area.
The AI server returns the acquired image mask to the audience terminal so that the audience terminal can combine with the original live broadcast video frame acquired from the live broadcast room server to perform image combination, and the original live broadcast video frame is filtered through the hollow-out in the image mask to obtain a filtered image.
In this embodiment, if the number of viewers that can receive the image mask exceeds one, the AI server corresponds to the set of all viewers that can receive the image mask. The audience can join the broadcast group according to the function key of the replacing background on the live broadcast interface or the function of the replacing background which is opened according to different grades and by using the function and other modes.
And when the AI server receives a background replacement request of at least one audience in the broadcast group, the AI server acquires the original live broadcast video stream from the live broadcast room server, decodes the original live broadcast video stream, and performs image segmentation on the corresponding live broadcast video frame to obtain an image mask. And sending the image mask to all the audience terminals in the broadcast group, so that all the audience terminals in the broadcast group can obtain the live broadcast video image with the replaced background by synthesizing the replaced background video frame, the image mask and the live broadcast video frame.
According to the anchor background replacing method for the live broadcast room, the AI server is used for decoding the original live broadcast video stream, and meanwhile, the image segmentation can be continuously carried out on a plurality of live broadcast video frames, so that a spectator end can synthesize live broadcast video images for replacing the background, and the limitation to the processing capacity of the spectator end is avoided. Therefore, the technical scheme solves the problem that the processing capacity of the audience terminal cannot meet the background replacement request of the audience to the live broadcast interface, and enables the audience terminal to quickly and automatically control the occurrence of the current live broadcast background and the replacement rhythm; and the running speed is not slowed down because a large number of live video frames need to be subjected to image processing.
Based on the same application concept as the anchor background replacing method of the first live broadcast room, the embodiment of the present application further provides an anchor background replacing apparatus 700 of a live broadcast room. Referring to fig. 7, fig. 7 is a schematic structural diagram of an apparatus for replacing a main broadcast background of a live broadcast room according to an embodiment of the present disclosure.
The anchor background replacing apparatus 700 of the live broadcast room includes:
a replacement request sending module 710, configured to send a background replacement request to the live webcast server; the live broadcast room server responds to a background replacement request and sends an original live broadcast video stream to an AI server;
an image mask receiving module 720, configured to establish a connection with an AI server, and receive an image mask returned by the AI server after performing image segmentation on the original live video stream;
and the image synthesis module 730 is configured to acquire a replacement background video frame, and synthesize the replacement background video frame, the image mask and the live video frame to obtain a live video image of a replacement background.
According to the anchor background replacement device 700 of the live broadcast room provided by the embodiment of the application, the obtained live broadcast video frame obtained by decoding the current live broadcast video stream is subjected to image segmentation at the AI server according to the background replacement request sent by the audience, so that an image mask is obtained, the image mask, the live broadcast video frame and the replacement background are combined to obtain a corresponding filtered original live broadcast video background, and the replacement background corresponding to the corresponding background replacement request is added to a live broadcast picture, so that the audience can quickly and automatically control the appearance and the replacement rhythm of the current live broadcast background; and the running speed is not slowed down because a large number of live video frames need to be subjected to image processing.
Based on the same application concept as the anchor background replacing method of another live broadcast room, the embodiment of the present application further provides an anchor background replacing apparatus 800 of a live broadcast room. Referring to fig. 8, fig. 8 is a schematic structural diagram of an apparatus for replacing a main broadcast background of another live broadcast room according to an embodiment of the present disclosure.
The anchor background replacing apparatus 800 of the live broadcast room includes:
the image segmentation module 810 is configured to obtain an original live video stream according to a background replacement request sent by a viewer, decode each live video frame obtained by the original live video stream, and perform image segmentation on the live video frame to obtain an image mask;
an image mask sending module 820, configured to send the image mask to a viewer, so that the viewer performs image combination with the original live video frame according to the background replacement request.
The anchor background replacing device 800 of the live broadcast room provided by the embodiment of the application can continuously perform image segmentation on a plurality of live broadcast video frames while finishing decoding of an original live broadcast video stream through the AI server, so that a spectator end can synthesize live broadcast video images of a replacing background, and the device is prevented from being limited by the processing capacity of the spectator end. Therefore, the technical scheme solves the problem that the processing capacity of the audience terminal cannot meet the background replacement request of the audience to the live broadcast interface, and enables the audience terminal to quickly and automatically control the occurrence of the current live broadcast background and the replacement rhythm; and the running speed is not slowed down because a large number of live video frames need to be subjected to image processing.
Based on the same principle as the method shown in the embodiment of the present application, an embodiment of the present application further provides an electronic device, which may include but is not limited to: a processor and a memory; a memory for storing computer operating instructions; and the processor is used for executing the method shown in the embodiment by calling the computer operation instruction.
Corresponding to the method for replacing the main broadcast background of the first live broadcast room, compared with the prior art, the electronic device in the embodiment of the application can perform image segmentation on the live broadcast video frame obtained by decoding the obtained current live broadcast video stream at the AI server according to the background replacement request sent by the audience end to obtain an image mask, combine the image mask, the live broadcast video frame and the replacement background to obtain a corresponding filtered original live broadcast video background, and add the replacement background corresponding to the corresponding background replacement request to the live broadcast picture, so that the audience end can quickly and automatically control the occurrence of the current live broadcast background and the replacement rhythm; and the running speed is not slowed down because a large number of live video frames need to be subjected to image processing.
Corresponding to the main broadcast background replacing method of the other live broadcast room, the AI server can decode the original live broadcast video stream and simultaneously can continuously perform image segmentation on a plurality of live broadcast video frames so as to synthesize live broadcast video images for replacing the background by the audience, thereby avoiding the limitation of the processing capacity of the audience. Therefore, the technical scheme solves the problem that the processing capacity of the audience terminal cannot meet the background replacement request of the audience to the live broadcast interface, and enables the audience terminal to quickly and automatically control the occurrence of the current live broadcast background and the replacement rhythm; and the running speed is not slowed down because a large number of live video frames need to be subjected to image processing.
Referring to fig. 9, fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application, where the method for replacing a main broadcast background of a live broadcast room is provided.
In an alternative embodiment, an electronic device is provided, as shown in fig. 9, the electronic device 900 shown in fig. 9 comprising: a processor 901 and a memory 903. Wherein the processor 901 is coupled to the memory 903, such as via a bus 902. Optionally, the electronic device 900 may also include a transceiver 904. It should be noted that the transceiver 904 is not limited to one in practical applications, and the structure of the electronic device 900 is not limited to the embodiment of the present application.
Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 9 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
The present application provides a computer-readable storage medium, on which a computer program is stored, which, when running on a computer, enables the computer to execute the corresponding content in the foregoing method embodiments.
Corresponding to the method for replacing the anchor background in the first live broadcast room, compared with the prior art, the computer-readable storage medium in the embodiment of the application can perform image segmentation on the live broadcast video frame obtained by decoding the obtained current live broadcast video stream at the AI server according to the background replacement request sent by the audience terminal to obtain an image mask, combine the image mask, the live broadcast video frame and the replacement background to obtain a corresponding filtered original live broadcast video background, and add the replacement background corresponding to the corresponding background replacement request to the live broadcast picture, so that the audience terminal can quickly and automatically control the occurrence and the replacement rhythm of the current live broadcast background; and the running speed is not slowed down because a large number of live video frames need to be subjected to image processing.
Corresponding to the another method for replacing the anchor background in the live broadcast room, compared with the prior art, the computer-readable storage medium in the embodiment of the present application can also continuously perform image segmentation on a plurality of live broadcast video frames while completing decoding of an original live broadcast video stream through the AI server, so that a viewer can synthesize a live broadcast video image replacing the background, and the processing capability of the viewer is not limited. Therefore, the technical scheme solves the problem that the processing capacity of the audience terminal cannot meet the background replacement request of the audience to the live broadcast interface, and enables the audience terminal to quickly and automatically control the occurrence of the current live broadcast background and the replacement rhythm; and the running speed is not slowed down because a large number of live video frames need to be subjected to image processing.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to perform the methods shown in the above embodiments.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the disclosure. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.

Claims (14)

1. A method for replacing a main background of a live broadcast room is applied to a viewer side and is characterized by comprising the following steps:
sending a background replacement request to an AI server; the live broadcast room server responds to a background replacement request and sends an original live broadcast video stream to an AI server;
establishing connection with the AI server, and receiving an image mask returned by the AI server for image segmentation of the original live video stream;
and acquiring a replacing background video frame, and synthesizing the replacing background video frame, the image mask and the live video frame to obtain a live video image of the replacing background.
2. The method of claim 1, wherein compositing the replacement background video frame, the image mask, and the live video frame comprises:
performing image filtering on the live video frame by using the image mask to obtain a filtered image;
and in the range of the live video frames, performing background filling on the filtered image by using the replacement background video frames to obtain a background replacement image of a live room, and displaying the background replacement image after rendering.
3. The method according to claim 2,
the image combination is carried out by utilizing the image mask and the live video frame to obtain a filtering image, and the method comprises the following steps:
respectively acquiring timestamps of the image mask and an original live video frame;
matching according to a first timestamp of the live video frame and a second timestamp of the image mask;
and when the matching is successful, performing image filtering by using the image mask and the live video frame to obtain a filtered image after the live video frame is masked.
4. A method according to claim 3,
said matching according to a first timestamp of the live video frame and a second timestamp of the image mask comprises:
caching the image masks according to the sequence of the second timestamps to form a priority matching queue with a set length;
matching the first time stamp of the live video frame with a second time stamp corresponding to the image mask in the priority matching queue according to the first time stamp of the live video frame and a set time difference range;
judging whether the difference value of the first time stamp and the second time stamp is within a preset time difference range or not;
wherein a first timestamp of the live video frame is greater than or equal to a second timestamp of the image mask.
5. The method of claim 3, further comprising:
when the matching of the first time stamp of the live video frame and the second time stamp of the image mask fails, judging whether a filtering image which is successfully matched is cached;
if so, continuously playing the filtering image until obtaining the next filtering image successfully matched again;
otherwise, playing the current live video frame.
6. The method of claim 2,
the image filtering is performed on the live video frame by using the image mask to obtain a filtered image, and the image filtering method comprises the following steps:
covering the image mask on the live video frame, and filtering the live video frame image through the hollow area of the image mask to obtain the filtered image.
7. The method of claim 2,
before the background filling of the filtered image by the replacement background video frame, the method further includes:
acquiring a replacing background video stream, and starting a decoding subprogram to decode the replacing background video stream to obtain a plurality of background frames;
and performing rendering function call-back on each background frame to obtain a corresponding replacement background video frame.
8. A live broadcast room background replacement method is characterized by comprising the following steps:
according to a background replacement request sent by a viewer, acquiring an original live video stream, decoding each live video frame obtained by the original live video stream, and performing image segmentation on the live video frame to obtain an image mask;
and sending the image mask to a viewer end, so that the viewer end performs image combination with the original live video frame according to the background replacement request.
9. The live room background replacement method as recited in claim 8,
the image segmentation is carried out on the live video frame to obtain an image mask, and the image mask comprises the following steps:
performing image recognition on the live video frame according to a preset image to obtain a filtering image area successfully matched with the preset image in the live video frame;
discarding the filtered image area to obtain an image mask along the image boundary and the filtered image area is a hollow area.
10. The method of claim 9, further comprising:
sending the image mask to each viewer end of a broadcast group, so that the viewer ends perform image combination with the live video frames according to the respective sent background replacement requests;
wherein the broadcast group comprises a set of all viewers receiving the image mask.
11. An anchor background replacement apparatus for a live broadcast room, comprising:
the replacing request sending module is used for sending a background replacing request to the live broadcast room server; the live broadcast room server responds to a background replacement request and sends an original live broadcast video stream to an AI server;
the image mask receiving module is used for establishing connection with an AI server and receiving an image mask returned by the AI server for image segmentation of the original live video stream;
and the image synthesis module is used for acquiring the replacement background video frame, and synthesizing the replacement background video frame, the image mask and the live video frame to obtain the live video image of the replacement background.
12. An anchor background replacement apparatus for a live broadcast room, comprising:
the image segmentation module is used for acquiring an original live video stream according to a background replacement request sent by a viewer, decoding each live video frame obtained by the original live video stream, and performing image segmentation on the live video frame to obtain an image mask;
and the image mask sending module is used for sending the image mask to a spectator end so that the spectator end performs image combination with the original live video frame according to the background replacing request.
13. An electronic device, comprising:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to: a method of performing anchor background replacement for a live broadcast room according to any of claims 1-10.
14. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method of anchor background substitution in a live broadcast room according to any one of claims 1 to 10.
CN202110057243.9A 2021-01-15 2021-01-15 Live broadcast room background replacement method and device, electronic equipment and storage medium Active CN112911318B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110057243.9A CN112911318B (en) 2021-01-15 2021-01-15 Live broadcast room background replacement method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110057243.9A CN112911318B (en) 2021-01-15 2021-01-15 Live broadcast room background replacement method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN112911318A true CN112911318A (en) 2021-06-04
CN112911318B CN112911318B (en) 2023-03-31

Family

ID=76113889

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110057243.9A Active CN112911318B (en) 2021-01-15 2021-01-15 Live broadcast room background replacement method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112911318B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113240702A (en) * 2021-06-25 2021-08-10 北京市商汤科技开发有限公司 Image processing method and device, electronic equipment and storage medium
CN115022654A (en) * 2022-05-18 2022-09-06 北京达佳互联信息技术有限公司 Video editing method and device in live scene
CN115022668A (en) * 2022-07-21 2022-09-06 中国平安人寿保险股份有限公司 Video generation method and device based on live broadcast, equipment and medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101753851A (en) * 2008-12-17 2010-06-23 华为终端有限公司 Method for replacing background, method for synthesizing virtual scene, as well as relevant system and equipment
US20170223431A1 (en) * 2016-01-29 2017-08-03 Disney Enterprises, Inc. Rendering a virtual mark on a video frame
CN109151489A (en) * 2018-08-14 2019-01-04 广州虎牙信息科技有限公司 live video image processing method, device, storage medium and computer equipment
WO2019157344A1 (en) * 2018-02-12 2019-08-15 Avodah Labs, Inc. Real-time gesture recognition method and apparatus
US20200120369A1 (en) * 2017-06-27 2020-04-16 Pixellot Ltd. Method and system for fusing user specific content into a video production
CN111292337A (en) * 2020-01-21 2020-06-16 广州虎牙科技有限公司 Image background replacing method, device, equipment and storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101753851A (en) * 2008-12-17 2010-06-23 华为终端有限公司 Method for replacing background, method for synthesizing virtual scene, as well as relevant system and equipment
US20170223431A1 (en) * 2016-01-29 2017-08-03 Disney Enterprises, Inc. Rendering a virtual mark on a video frame
US20200120369A1 (en) * 2017-06-27 2020-04-16 Pixellot Ltd. Method and system for fusing user specific content into a video production
WO2019157344A1 (en) * 2018-02-12 2019-08-15 Avodah Labs, Inc. Real-time gesture recognition method and apparatus
CN109151489A (en) * 2018-08-14 2019-01-04 广州虎牙信息科技有限公司 live video image processing method, device, storage medium and computer equipment
CN111292337A (en) * 2020-01-21 2020-06-16 广州虎牙科技有限公司 Image background replacing method, device, equipment and storage medium

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113240702A (en) * 2021-06-25 2021-08-10 北京市商汤科技开发有限公司 Image processing method and device, electronic equipment and storage medium
CN115022654A (en) * 2022-05-18 2022-09-06 北京达佳互联信息技术有限公司 Video editing method and device in live scene
CN115022654B (en) * 2022-05-18 2024-01-19 北京达佳互联信息技术有限公司 Video editing method and device in live broadcast scene
CN115022668A (en) * 2022-07-21 2022-09-06 中国平安人寿保险股份有限公司 Video generation method and device based on live broadcast, equipment and medium
CN115022668B (en) * 2022-07-21 2023-08-11 中国平安人寿保险股份有限公司 Live broadcast-based video generation method and device, equipment and medium

Also Published As

Publication number Publication date
CN112911318B (en) 2023-03-31

Similar Documents

Publication Publication Date Title
CN112911318B (en) Live broadcast room background replacement method and device, electronic equipment and storage medium
CN106454407B (en) Video live broadcasting method and device
EP3562163B1 (en) Audio-video synthesis method and system
KR101813196B1 (en) Method, device, program, and recording medium for video communication
CN107682714B (en) Method and device for acquiring online video screenshot
KR100889367B1 (en) System and Method for Realizing Vertual Studio via Network
CN110392306B (en) Data processing method and equipment
US11128894B2 (en) Method and mobile terminal for processing data
CN113141524B (en) Resource transmission method, device, terminal and storage medium
CN111405339B (en) Split screen display method, electronic equipment and storage medium
WO2023279793A1 (en) Video playing method and apparatus
CN111050204A (en) Video clipping method and device, electronic equipment and storage medium
US20120300127A1 (en) System for managing detection of advertisements in an electronic device, for example in a digital tv decoder
CN111935510B (en) Double-browser application loading method and display equipment
CN111757187A (en) Multi-language subtitle display method, device, terminal equipment and storage medium
CN113965768B (en) Live broadcasting room information display method and device, electronic equipment and server
CN115643429A (en) Video playing method and device, electronic equipment and computer readable storage medium
CN112565655A (en) Video data yellow identification method and device, electronic equipment and storage medium
CN110990109A (en) Spliced screen redisplay method, terminal, system and storage medium
CN115278278B (en) Page display method and device, electronic equipment and storage medium
CN109600623A (en) The control method and system of VR live video
CN109451361B (en) Code stream definition switching method and device for Android system, terminal and readable medium
CN111935508B (en) Information processing and acquiring method and device, electronic equipment and storage medium
CN115460436B (en) Video processing method, storage medium and electronic device
CN112261438B (en) Video enhancement method, device, equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant