阅读说明：本技术 基于虚拟主播的节目视频生成方法、系统和存储介质 (Program video generation method, system and storage medium based on virtual anchor ) 是由 李新福 于 2020-05-07 设计创作，主要内容包括：本发明公开了一种基于虚拟主播的节目视频生成方法、系统和存储介质,其中方法包括以下步骤：接收虚拟数据,所述虚拟数据由远程生成后通过网络传输至现场,所述虚拟数据包括虚拟视频数据或虚拟主播模型数据的至少之一；获取现场录制的视频数据；将视频数据和虚拟数据进行融合,获得直播视频,所述直播视频中显示有虚拟主持人。本发明通过远程生成的虚拟数据实时传输至录制/直播现场,与现场录制的视频数据进行融合,生成带有虚拟主持人的直播视频,无需再经过后期视频处理,实现了实时融合虚拟数据的播放,可广泛应用于网络技术领域。(The invention discloses a program video generation method, a system and a storage medium based on a virtual anchor, wherein the method comprises the following steps: receiving virtual data, wherein the virtual data is generated remotely and then transmitted to a site through a network, and the virtual data comprises at least one of virtual video data or virtual anchor model data; acquiring video data recorded on site; and fusing the video data and the virtual data to obtain a live video, wherein a virtual host is displayed in the live video. The invention realizes the playing of real-time fusion virtual data by transmitting the remotely generated virtual data to a recording/live broadcasting site in real time and fusing the virtual data with the video data recorded on the site to generate live broadcasting video with a virtual host without post video processing, and can be widely applied to the technical field of networks.)

1. A program video generation method based on virtual anchor is characterized by comprising the following steps:

receiving virtual data, wherein the virtual data is generated remotely and then transmitted to a site through a network, and the virtual data comprises at least one of virtual video data or virtual anchor model data;

acquiring video data recorded on site;

and fusing the video data and the virtual data to obtain a live video, wherein a virtual host is displayed in the live video.

2. The method for generating a program video based on a virtual anchor according to claim 1, wherein the virtual data is a virtual anchor model, and the step of fusing the video data and the virtual data to obtain a live video specifically comprises:

playing the virtual data by adopting a preset air imaging device so as to present a virtual host on the spot;

shooting a scene presenting a virtual host, and taking obtained video data as a live video; or

Shooting the virtual host to obtain a first video, and splicing and fusing the first video and video data to obtain a live video.

3. The method for generating a program video based on a virtual anchor according to claim 1, wherein the virtual data is a virtual anchor model, and the step of fusing the video data and the virtual data to obtain a live video specifically comprises:

and combining the video data, the virtual anchor module and a preset video fusion algorithm for fusion to obtain the live video.

4. The method for generating a program video based on a virtual anchor as claimed in claim 3, further comprising a step of playing a virtual host on site, specifically:

and playing the virtual data by adopting a preset AR device so that field personnel can see the virtual host.

5. The method of any of claims 1-4, wherein the virtual data is transmitted to the scene via a 5G network.

6. The method of claim 1, further comprising the step of presenting or accessing the virtual host using at least one of a smart display screen, a MR device, a VR device, a smart mobile terminal, a wechat applet, an APP, and a page view module.

7. A system for video generation of a program based on a virtual anchor, comprising:

the remote transmission module is used for receiving virtual data, the virtual data is generated remotely and then transmitted to a site through a network, and the virtual data comprises at least one of virtual video data or virtual anchor model data;

the field recording module is used for acquiring field recorded video data;

and the video fusion module is used for fusing the video data and the virtual data to obtain a live video, and a virtual host is displayed in the live video.

8. The system of claim 7, wherein the video fusion module comprises a playing unit, a shooting unit, and a splicing unit;

the playing unit is used for playing the virtual data by adopting a preset air imaging device so as to present a virtual host on the spot;

the shooting unit is used for shooting the presented virtual host to obtain host video data;

the splicing unit is used for splicing and fusing the video data and the host video data to obtain live broadcast video.

9. A system for video generation of a program based on a virtual anchor, comprising:

at least one processor;

at least one memory for storing at least one program;

when executed by the at least one processor, cause the at least one processor to implement a virtual host-based program video generation method of any one of claims 1-6.

10. A storage medium having stored therein processor-executable instructions, which when executed by a processor, are configured to perform the method of any one of claims 1-6.

Technical Field

The present invention relates to the field of network technologies, and in particular, to a program video generation method, system, and storage medium based on a virtual anchor.

Background

With the development of virtual technologies, virtual synthesis is applied to more and more industries, wherein the application in the media industry is the most extensive. Present weather forecast or general military commentary program for more gorgeous visual effect, all can add virtual picture or virtual video, for example when the moderator talkbacks the tank, can "rush out" a tank in the video, increase when this kind of virtual picture is all through later stage video processing now, can't be applicable to in the live video.

Disclosure of Invention

In order to solve the technical problems, the present invention provides a program video generation method, system and storage medium based on virtual anchor suitable for live broadcast.

The technical scheme adopted by the invention is as follows:

a program video generation method based on virtual anchor comprises the following steps:

receiving virtual data, wherein the virtual data is generated remotely and then transmitted to a site through a network, and the virtual data comprises at least one of virtual video data or virtual anchor model data;

acquiring video data recorded on site;

and fusing the video data and the virtual data to obtain a live video, wherein a virtual host is displayed in the live video.

Further, the virtual data is a virtual anchor model, and the step of fusing the video data and the virtual data to obtain a live video specifically includes:

playing the virtual data by adopting a preset air imaging device so as to present a virtual host on the spot;

shooting a scene presenting a virtual host, and taking obtained video data as a live video; or

Shooting the virtual host to obtain a first video, and splicing and fusing the first video and video data to obtain a live video.

Further, the virtual data is a virtual anchor model, and the step of fusing the video data and the virtual data to obtain a live video specifically includes:

and combining the video data, the virtual anchor module and a preset video fusion algorithm for fusion to obtain the live video.

Further, the method also comprises the step of playing the virtual host on site, which specifically comprises the following steps:

and playing the virtual data by adopting a preset AR device so that field personnel can see the virtual host.

Further, the virtual data are transmitted to the site through a 5G network.

And further, the method also comprises the step of displaying or accessing the virtual host by adopting at least one device of an intelligent display screen, MR equipment, VR equipment, an intelligent mobile terminal, a WeChat applet, APP and a page browsing module.

The other technical scheme adopted by the invention is as follows:

a virtual anchor-based program video generation system, comprising:

the remote transmission module is used for receiving virtual data, the virtual data is generated remotely and then transmitted to a site through a network, and the virtual data comprises at least one of virtual video data or virtual anchor model data;

the field recording module is used for acquiring field recorded video data;

and the video fusion module is used for fusing the video data and the virtual data to obtain a live video, and a virtual host is displayed in the live video.

Further, the video fusion module comprises a playing unit, a shooting unit and a splicing unit;

the playing unit is used for playing the virtual data by adopting a preset air imaging device so as to present a virtual host on the spot;

the shooting unit is used for shooting the presented virtual host to obtain host video data;

the splicing unit is used for splicing and fusing the video data and the host video data to obtain live broadcast video.

Further, the video fusion module is used for obtaining the live video after fusion is carried out by combining the video data, the virtual anchor module and a preset video fusion algorithm.

The other technical scheme adopted by the invention is as follows:

a virtual anchor-based program video generation system, comprising:

at least one processor;

at least one memory for storing at least one program;

when executed by the at least one processor, cause the at least one processor to implement the method described above.

The other technical scheme adopted by the invention is as follows:

a storage medium having stored therein processor-executable instructions for performing the method as described above when executed by a processor.

The invention has the beneficial effects that: the invention realizes the real-time playing of the fused virtual data by transmitting the remotely generated virtual data to a recording/live broadcasting site in real time and fusing the virtual data with the video data recorded on the site to generate the live broadcasting video with the virtual host without the need of later video processing.

Drawings

Fig. 1 is a flowchart illustrating steps of a video generation method for a program based on a virtual anchor according to an embodiment;

fig. 2 is a block diagram illustrating a program video generation system based on a virtual anchor according to an embodiment.

Detailed Description

The conception, the specific structure and the technical effects of the present invention will be clearly and completely described in conjunction with the embodiments and the accompanying drawings to fully understand the objects, the schemes and the effects of the present invention.

It should be noted that, unless otherwise specified, when a feature is referred to as being "fixed" or "connected" to another feature, it may be directly fixed or connected to the other feature or indirectly fixed or connected to the other feature. Furthermore, the descriptions of upper, lower, left, right, etc. used in the present disclosure are only relative to the mutual positional relationship of the constituent parts of the present disclosure in the drawings. As used in this disclosure, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. Furthermore, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in the description herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any combination of one or more of the associated listed items.

It will be understood that, although the terms first, second, third, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element of the same type from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of the present disclosure. The use of any and all examples, or exemplary language ("e.g.," such as "or the like") provided herein, is intended merely to better illuminate embodiments of the invention and does not pose a limitation on the scope of the invention unless otherwise claimed.

As shown in fig. 1, the present embodiment provides a program video generating method based on a virtual anchor, including the following steps:

s101, receiving virtual data, wherein the virtual data are generated remotely and then transmitted to a site through a network, and the virtual data comprise at least one of virtual video data or virtual anchor model data.

In this example, the virtual data is sent to the scene after being generated remotely, the virtual data includes virtual video data or virtual anchor model data, the virtual video data can be a picture of the host and other pictures, the anchor model data can be an established virtual image model of the host, and the image model can be a real character image or an avatar. And when the virtual data is virtual video data, the virtual video data is sent to a recording site in real time based on the existing 5G technology. When the virtual data is virtual anchor model data, the virtual anchor model is firstly sent to a recording site, and then the virtual anchor model is controlled according to the recording process of the program, action instructions, voice instructions and the like, so that the switching action of a virtual host is controlled, and the data transmission quantity can be reduced. By remote transmission of virtual data, at least the following effects are achieved: 1. the virtual data only need to be stored in a remote server, and when the virtual data is required to be used on site, the virtual data is remotely transmitted to the site, so that the phenomenon that the virtual data is required to be stored on site excessively is avoided, and the cost of the storage server is reduced. 2. After the virtual data are made once by the background, the virtual data can be applied to a plurality of recording sites through remote transmission, and the utilization rate of the virtual data is improved. 3. Through combining the data that teletransmission came, make the video of recording dazzler more beautiful, improved the video effect. Specifically, the scheme based on the virtual host comprises two hosts, a real host on the spot and a virtual host, and the science and technology sense and the pleasure of the hosting spot are increased by combining the real host and the virtual host.

And S102, acquiring video data recorded on site.

The video data is acquired on site through equipment such as a camera, and the like, and the existing technology is specifically adopted, which is not described herein any more.

S103, fusing the video data and the virtual data to obtain a live video, wherein a virtual host is displayed in the live video.

The live broadcast video is live broadcast in real time, a virtual host is displayed in a video picture, and in order to enable on-site audiences and audiences of the remote terminal to see the virtual host, the embodiment adopts two implementation modes. The first implementation mode comprises the steps A1-A3:

a1, playing virtual data by adopting a preset air imaging device to present a virtual host on the spot;

a2, shooting the scene presenting the virtual host, and taking the obtained video data as live video; or

Shooting the virtual host to obtain a first video, and splicing and fusing the first video and video data to obtain a live video.

In this embodiment, the virtual data is played using an air imaging device, which may be a 3D holographic projection device, to present a virtual host. After the virtual presenter is projected, the person can now view the virtual presenter through naked eyes. The virtual host is shot by the camera and then transmitted to the remote terminal, and the remote audience can see the virtual host. The video data and the virtual data are spliced and fused to form two layers of definitions, wherein the first layer of definitions is as follows: and directly sending video data obtained by shooting the virtual host through the camera to the remote terminal. The second layer is defined as: the method includes the steps that data shot by a virtual host in real time are aimed at through a camera, a first video is obtained, the first video is spliced into video data, and for example, a popup frame is arranged at the lower right corner of a video data picture to play video frequency of the host.

The second implementation is specifically as follows: and combining the video data, the virtual anchor module and a preset video fusion algorithm for fusion to obtain the live video.

In this embodiment, processing is done at the data level and the virtual presenter is not now directly projected for display. Based on this, the audience needs to watch the virtual host by virtue of the terminal device, specifically, the terminal device may be an AR device, a VR device, an MR device, and an intelligent terminal; wherein, based on the intelligent terminal, the virtual host can be viewed through a web browser or an applet. The video fusion algorithm is realized by adopting the existing video fusion technology.

Further as an optional embodiment, the virtual data is transmitted to the site through a 5G network.

Because the 5G network has the advantage of low time delay, data can be transmitted in millisecond level, so that the virtual data and the video data can be synchronized, and the quality of the video is improved.

Further as an optional implementation, the method further includes the step of displaying or accessing the virtual host by using at least one of an intelligent display screen (such as (mobile terminal, tablet computer, notebook computer, PC computer, OLED display screen, LCD display screen)), MR device, VR device, intelligent mobile terminal, wechat applet, APP, and a page browsing module (such as a browser). The viewer can remotely view the virtual host in a variety of ways as described above.

Based on the program video generation method, the AI virtual host developed by means of artificial intelligence 'body-separating' technology enables various links of news operated by manpower to gradually change to man-machine cooperation and mainly change to an intelligent machine, and the intelligent mode of subversion of the traditional broadcast television report pattern is increasingly highlighted. By means of the precision of science and technology, the AI virtual host can reduce errors such as wrong character reading, character missing and character swallowing in broadcasting to the maximum extent, improve the accuracy of news and keep extremely high working efficiency. In addition, when the foreign language manuscripts are broadcasted, the virtual host does not need foreign language bases, the threshold of cross-language broadcasting is greatly reduced, and the requirement of overseas propaganda of news reports is met.

As shown in fig. 2, this embodiment further provides a program video generating system based on a virtual anchor, including:

the remote transmission module is used for receiving virtual data, the virtual data is generated remotely and then transmitted to a site through a network, and the virtual data comprises at least one of virtual video data or virtual anchor model data;

the field recording module is used for acquiring field recorded video data;

and the video fusion module is used for fusing the video data and the virtual data to obtain a live video, and a virtual host is displayed in the live video.

In this example, the virtual data is generated remotely and then sent to the scene, the virtual data may be a picture of a host or other pictures, and the image of the host may be a real character image or an avatar. When the host is the real character image, the video information of the host is acquired in real time and then remotely transmitted to the site, so that remote host is realized. Based on the existing 5G technology, the scene condition is returned to the scene of the host in real time in the hosting process. When the host is a virtual host, the model of the virtual host can be remotely sent to a program recording site, and then an action instruction, a voice instruction and the like are sent according to the recording process of the program, so that the switching action of the virtual host is controlled, and the data transmission quantity can be reduced. Specifically, the scheme based on the virtual host comprises two hosts, a real host on site and a virtual host, and the current technological sense and the pleasure of the host are increased by combining the real host and the virtual host.

Further as an optional implementation manner, the video fusion module includes a playing unit, a shooting unit and a splicing unit;

the playing unit is used for playing the virtual data by adopting a preset air imaging device so as to present a virtual host on the spot;

the shooting unit is used for shooting the presented virtual host to obtain host video data;

the splicing unit is used for splicing and fusing the video data and the host video data to obtain live broadcast video.

Further as an optional implementation manner, the video fusion module is configured to obtain a live video after fusion is performed by combining the video data, the virtual anchor module, and a preset video fusion algorithm.

The program video generation system based on the virtual anchor of the embodiment can execute the program video generation method based on the virtual anchor provided by the method embodiment of the invention, can execute any combination implementation steps of the method embodiment, and has corresponding functions and beneficial effects of the method.

The present embodiment further provides a program video generating system based on a virtual anchor, including:

at least one processor;

at least one memory for storing at least one program;

when executed by the at least one processor, cause the at least one processor to implement the method described above.

The program video generation system based on the virtual anchor of the embodiment can execute the program video generation method based on the virtual anchor provided by the method embodiment of the invention, can execute any combination implementation steps of the method embodiment, and has corresponding functions and beneficial effects of the method.

The present embodiments also provide a storage medium having stored therein processor-executable instructions, which when executed by a processor, are configured to perform the method as described above.

The storage medium of this embodiment may execute the program video generation method based on the virtual anchor provided in the method embodiment of the present invention, may execute any combination of the implementation steps of the method embodiment, and has corresponding functions and beneficial effects of the method.

It should be recognized that embodiments of the present invention can be realized and implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with the computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner, according to the methods and figures described in the detailed description. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.

Further, the operations of processes described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and/or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) collectively executed on one or more processors, by hardware, or combinations thereof. The computer program includes a plurality of instructions executable by one or more processors.

Further, the method may be implemented in any type of computing platform operatively connected to a suitable interface, including but not limited to a personal computer, mini computer, mainframe, workstation, networked or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, and the like. Aspects of the invention may be embodied in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optically read and/or write storage medium, RAM, ROM, or the like, such that it may be read by a programmable computer, which when read by the storage medium or device, is operative to configure and operate the computer to perform the procedures described herein. Further, the machine-readable code, or portions thereof, may be transmitted over a wired or wireless network. The invention described herein includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention also includes the computer itself when programmed according to the methods and techniques described herein.

A computer program can be applied to input data to perform the functions described herein to transform the input data to generate output data that is stored to non-volatile memory. The output information may also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including particular visual depictions of physical and tangible objects produced on a display.

The above description is only a preferred embodiment of the present invention, and the present invention is not limited to the above embodiment, and any modifications, equivalent substitutions, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention as long as the technical effects of the present invention are achieved by the same means. The invention is capable of other modifications and variations in its technical solution and/or its implementation, within the scope of protection of the invention.