CN113923512A - Method and device for processing event video of non-live audience and computing equipment - Google Patents
Method and device for processing event video of non-live audience and computing equipment Download PDFInfo
- Publication number
- CN113923512A CN113923512A CN202111194186.5A CN202111194186A CN113923512A CN 113923512 A CN113923512 A CN 113923512A CN 202111194186 A CN202111194186 A CN 202111194186A CN 113923512 A CN113923512 A CN 113923512A
- Authority
- CN
- China
- Prior art keywords
- audience
- simulated
- event
- video
- simulation
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000012545 processing Methods 0.000 title claims abstract description 20
- 238000004088 simulation Methods 0.000 claims abstract description 97
- 238000004891 communication Methods 0.000 claims description 15
- 230000004927 fusion Effects 0.000 claims description 9
- 230000000694 effects Effects 0.000 abstract description 18
- 230000014759 maintenance of location Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 238000002372 labelling Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000009192 sprinting Effects 0.000 description 1
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]
- H04N21/40—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
- H04N21/439—Processing of audio elementary streams
- H04N21/4394—Processing of audio elementary streams involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/206—Drawing of charts or graphs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- 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
- H04N21/439—Processing of audio elementary streams
- H04N21/4398—Processing of audio elementary streams involving reformatting operations of audio signals
-
- 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
- H04N21/44004—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 video buffer management, e.g. video decoder buffer or video display buffer
-
- 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
- H04N21/4402—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 reformatting operations of video signals for household redistribution, storage or real-time display
-
- 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
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/4508—Management of client data or end-user data
- H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
Abstract
The invention discloses a method and a device for processing a live-audience-free event video and computing equipment. The method comprises the following steps: constructing an event venue model corresponding to the event video, and generating a simulation audience set corresponding to the event video; fusing the event venue model and the simulation audience set to generate a simulation venue scene audience model corresponding to the event video; identifying a highlight segment in the event video, and generating a simulated audience audio frequency corresponding to the highlight segment according to a simulated venue site audience model; the simulated spectator audio is embedded in the highlight segments in the event video. By adopting the scheme, the network audience can hear the on-site audience simulation sound effect when watching the wonderful section of the off-site audience event video, the simulation sound effect is high in matching degree with the actual event situation, the on-site audience atmosphere of the event can be realistically simulated by the simulation sound effect, the watching experience of watching the off-site audience event video by the network audience is improved, and the user retention rate of the off-site audience event video playing platform is improved.
Description
Technical Field
The invention relates to the technical field of video processing, in particular to a method and a device for processing a live-audience-free event video and computing equipment.
Background
Sports and other events are popular with many viewers due to their high wonderness and compact tempo. Traditional sporting events typically involve two categories of spectators. One type of the spectators is live spectators, and the spectators watch the events on the spot in the event venue; the other type is network audience, and the audience watches the video of the events such as live events or recorded events and the like through the network.
Due to the influence of factors such as epidemic situations, a plurality of events have no live audience, and the events are events without live audience. Due to the lack of atmosphere of the on-site audiences, the ornamental value of the event video of the off-site audiences can be greatly reduced, the watching experience of the network audiences on the event video of the off-site audiences is reduced, and then the user retention rate of the event video playing platform is reduced.
Disclosure of Invention
In view of the above, the present invention has been developed to provide a method, apparatus, and computing device for processing live audience event video that overcome, or at least partially address, the above-discussed problems.
According to one aspect of the present invention, there is provided a method for processing a video of an off-site spectator event, comprising:
constructing an event venue model corresponding to the event video, and generating a simulation audience set corresponding to the event video;
fusing the event venue model and the simulated spectator set to generate a simulated venue site spectator model corresponding to the event video;
identifying a highlight segment in the event video, and generating a simulated audience audio corresponding to the highlight segment according to the simulated venue site audience model;
embedding the simulated spectator audio into the highlight segments in the event video.
In an alternative embodiment, the event venue model includes at least one simulated seat, each simulated seat having corresponding seat information; the simulation audience set comprises at least one simulation audience, and each simulation audience has corresponding audience information;
said merging said venue model with said set of simulated spectators further comprises:
binding simulated seats in the venue model to simulated spectators in the set of simulated spectators.
In an optional implementation, the event venue model further includes at least one analog video capture device, each analog video capture device having corresponding device location information; the seat information includes seat position information;
generating a simulated audience audio corresponding to the highlight segment according to the simulated venue live audience model further comprises:
aiming at any simulated audience, obtaining the standard audio corpus of the simulated audience according to the audience information of the simulated audience;
calculating the distance between the simulated seats bound by the simulated audience and the simulated video acquisition equipment according to the seat position information of the simulated seats bound by the simulated audience and the equipment position information of the simulated video acquisition equipment, and correcting the standard audio corpus of the simulated audience according to the distance to obtain the corrected audio corpus of the simulated audience;
and generating the simulated audience audio corresponding to the wonderful segment based on the corrected audio corpus of each simulated audience.
In an alternative embodiment, the identifying the highlight segments in the event video further comprises: identifying a highlight segment in the event video and the highlight of the highlight segment;
generating the simulated audience audio corresponding to the highlight segment based on the corrected audio corpus of each simulated audience further comprises: and generating the simulated audience audio corresponding to the wonderful section based on the corrected audio corpus of each simulated audience and the wonderful degree of the wonderful section.
In an alternative embodiment, the seating information includes a category of seating; the audience information comprises country information;
the binding simulated seats in the event venue model with simulated spectators in the set of simulated spectators further comprises:
determining a target simulation seat with a seat class as a core seat in the event venue model;
identifying target simulation audiences of which the country information is matched with the country information of the participants corresponding to the event video from the simulation audience set;
acquiring a preset number of target simulation audiences, and binding the preset number of target simulation audiences with the target simulation seats;
the simulated audience with the currently unbound simulated seats is bound to the non-target simulated seats.
In an optional embodiment, the generating the set of simulated viewers corresponding to the event video further comprises:
acquiring event information corresponding to the event video;
acquiring historical live audience events of which the similarity with the event information is higher than a preset similarity threshold;
acquiring the live audience information of the historical live audience events;
and generating a simulation audience set corresponding to the event video according to the field audience information.
In an alternative embodiment, the event video is a live event stream;
the identifying highlights segments in the event video further comprises: and identifying a wonderful segment in the segment to be played of the event live stream.
According to another aspect of the present invention, there is provided a processing apparatus for a video of an off-site spectator event, comprising:
the venue model building module is used for building an event venue model corresponding to the event video;
the simulated audience generating module is used for generating a simulated audience set corresponding to the event video;
the fusion module is used for fusing the event venue model and the simulation audience set to generate a simulation venue site audience model corresponding to the event video;
the identification module is used for identifying wonderful segments in the event video;
the audio generation module is used for generating the simulated audience audio corresponding to the wonderful segment according to the simulated venue scene audience model;
an embedding module to embed the simulated spectator audio into the highlight segments in the event video.
In an alternative embodiment, the event venue model includes at least one simulated seat, each simulated seat having corresponding seat information; the simulation audience set comprises at least one simulation audience, and each simulation audience has corresponding audience information;
the fusion module is further configured to: binding simulated seats in the venue model to simulated spectators in the set of simulated spectators.
In an optional implementation, the event venue model further includes at least one analog video capture device, each analog video capture device having corresponding device location information; the seat information includes seat position information;
the audio generation module is further configured to: aiming at any simulated audience, obtaining the standard audio corpus of the simulated audience according to the audience information of the simulated audience;
calculating the distance between the simulated seats bound by the simulated audience and the simulated video acquisition equipment according to the seat position information of the simulated seats bound by the simulated audience and the equipment position information of the simulated video acquisition equipment, and correcting the standard audio corpus of the simulated audience according to the distance to obtain the corrected audio corpus of the simulated audience;
and generating the simulated audience audio corresponding to the wonderful segment based on the corrected audio corpus of each simulated audience.
In an optional embodiment, the identification module is further configured to: identifying a highlight segment in the event video and the highlight of the highlight segment;
the audio generation module is further configured to: and generating the simulated audience audio corresponding to the wonderful section based on the corrected audio corpus of each simulated audience and the wonderful degree of the wonderful section.
In an alternative embodiment, the seating information includes a category of seating; the audience information comprises country information;
the fusion module is further configured to: determining a target simulation seat with a seat class as a core seat in the event venue model;
identifying target simulation audiences of which the country information is matched with the country information of the participants corresponding to the event video from the simulation audience set;
acquiring a preset number of target simulation audiences, and binding the preset number of target simulation audiences with the target simulation seats;
the simulated audience with the currently unbound simulated seats is bound to the non-target simulated seats.
In an alternative embodiment, the simulated audience generation module is further configured to:
acquiring event information corresponding to the event video;
acquiring historical live audience events of which the similarity with the event information is higher than a preset similarity threshold;
acquiring the live audience information of the historical live audience events;
and generating a simulation audience set corresponding to the event video according to the field audience information.
In an alternative embodiment, the event video is a live event stream;
the identification module is further to: and identifying a wonderful segment in the segment to be played of the event live stream.
According to yet another aspect of the present invention, there is provided a computing device comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the processing method of the video of the live audience event.
According to yet another aspect of the present invention, there is provided a computer storage medium having at least one executable instruction stored therein, the executable instruction causing a processor to perform operations corresponding to the above-mentioned method for processing a live audience event video.
In the invention, an event venue model corresponding to the event video is constructed, and a simulation audience set corresponding to the event video is generated; fusing the event venue model and the simulation audience set to generate a simulation venue scene audience model corresponding to the event video; identifying a highlight segment in the event video, and generating a simulated audience audio frequency corresponding to the highlight segment according to a simulated venue site audience model; the simulated spectator audio is embedded in the highlight segments in the event video. By adopting the scheme, the network audience can hear the on-site audience simulation sound effect when watching the wonderful section of the off-site audience event video, the simulation sound effect is high in matching degree with the actual event situation, the on-site audience atmosphere of the event can be realistically simulated by the simulation sound effect, the watching experience of watching the off-site audience event video by the network audience is improved, and the user retention rate of the off-site audience event video playing platform is improved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart illustrating a method for processing a live spectator event video according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating a two-dimensional structure of a venue model according to an embodiment of the present invention;
FIG. 3 is a flow chart illustrating a method for generating a simulated audience set according to an embodiment of the invention;
FIG. 4 is a flow chart illustrating a method for fusing an event venue model with a simulated audience set according to an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating a two-dimensional structure of a simulation venue site audience model according to an embodiment of the present invention;
FIG. 6 is a flow chart illustrating a highlight recognition method according to an embodiment of the present invention;
FIG. 7 is a flow chart illustrating a method for simulating audience audio acquisition according to an embodiment of the invention;
FIG. 8 is a schematic diagram of a simulated audience audio control page provided by an embodiment of the invention;
fig. 9 is a schematic structural diagram illustrating a processing apparatus for a non-live audience event video according to an embodiment of the present invention;
fig. 10 is a schematic structural diagram of a computing device according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Fig. 1 is a flow chart illustrating a method for processing a live audience-free event video according to an embodiment of the present invention.
In the embodiment of the invention, the event video refers to the event video corresponding to the non-live audience event, and the event video can be the live event stream of the non-live audience event, the recorded and broadcast video of the non-live audience event and the like.
For the non-live-audience event video, the embodiment of the present invention obtains the simulated venue live audience model corresponding to the non-live-audience event video through steps S110 to S130, so as to simulate the distribution of the live audience in the event venue. And the sound effect of the on-site audience when watching the event highlight is simulated through the step S150, and finally the simulated sound effect is embedded into the highlight corresponding to the event video through the step S160. Therefore, the network audience can hear the simulated sound effect of the live audience when watching the wonderful section of the event video, and the simulated sound effect is vivid and has high matching degree with the actual event situation.
As shown in fig. 1, the method comprises the steps of:
and step S110, constructing an event venue model corresponding to the event video.
Specifically, the event venue information corresponding to the event video is obtained, and modeling is performed based on the event venue information to generate an event venue model corresponding to the no-field-audience event video. The embodiment of the invention does not limit the concrete modeling mode.
In an optional implementation manner, in order to improve the reduction degree of the constructed event venue model to the actual event venue and facilitate subsequent accurate determination of the distribution of the simulated spectators in the event venue model, the event venue model constructed according to the embodiment of the present invention includes at least one simulated seat, and each simulated seat has corresponding seat information. The seat information of each simulated seat in the event venue model in the embodiment of the invention is obtained according to the seat information of the actual seat in the actual event venue. Therefore, the event venue model constructed by the embodiment of the invention has higher matching degree with the actual event venue. The seat information of the simulated seat comprises the seat position information of the simulated seat, and the position of the simulated seat in the event venue model can be uniquely determined through the seat position information of the simulated seat.
Further optionally, the seat categories of the simulated seats are divided according to different event types, so that the distribution of the simulated audiences is more realistic. The seat information of the simulated seat in the embodiment of the present invention further includes the seat category of the simulated seat. Wherein the seat categories include: core seating and non-core seating. When a game includes two participants, the event venue model typically includes simulated seats with the seat class as the core seat. For example, in a table tennis event, the area behind two participants is a simulated seat with a core seat class, and the area is usually occupied by audiences with the same country as the participants; when a game includes a plurality of participants, the event venue model typically does not include simulated seats having a core seat type, for example, in a figure skating event, the simulated seats in the event venue model are of the same type and are all non-core seats.
In another optional implementation manner, in order to further improve the fidelity of the analog sound effect of the subsequently embedded live audience, the event venue model constructed in the embodiment of the present invention further includes at least one analog video capturing device, and each analog video capturing device has corresponding device location information. Wherein each analog video capture device corresponds to a video capture device in an actual event venue. Video capture devices in actual event venues are used to capture images and audio of live events.
In addition, the size of the venue (the length, width, height, etc. of the venue), the type of venue (e.g., closed indoor or open outdoor, etc.), and/or the size of the playing field in the venue (e.g., the length, width, height, etc. of the playing field) of the constructed venue model are determined based on the corresponding information of the actual playing venue.
In yet another alternative implementation, the event venue model and the model adjustment entry corresponding to the constructed event video may be displayed, so as to facilitate viewing and adjusting the constructed event venue model. For example, fig. 2 is a schematic diagram illustrating a two-dimensional structure of a venue model according to an embodiment of the present invention. It should be understood that, in the embodiment of the present invention, a two-dimensional structure diagram is adopted to simplify the event venue model, and in an actual implementation process, the constructed event venue model may be a two-dimensional model, a three-dimensional model, or the like.
As shown in fig. 2, each square block corresponds to one simulated seat. Wherein the shaded square blocks represent simulated seats with the seat type being the core position, and the white square blocks represent simulated seats with the seat type being the non-core position; the circular blocks represent analog video capture devices. When any block is clicked, the seat information of the simulated seat corresponding to the block can be further displayed, or the equipment information of the simulated video capture equipment corresponding to the block can be displayed, and the like. Or, when a certain block is double-clicked or pressed for a long time, the adjustment entrance of the simulated seat or the simulated video capture device corresponding to the block can be displayed, so that the inaccurate simulated seat or the inaccurate simulated video capture device can be adjusted.
Further optionally, this step may be performed before the event video is played, so as to improve the overall execution efficiency of the method.
Step S120, generating a simulation audience set corresponding to the event video.
The simulated audience members are simulations of live audience members in an event corresponding to the non-live audience event video.
In an alternative embodiment, to enhance the fidelity of the simulated audience set, the steps shown in fig. 3 may be used to generate a simulated audience set corresponding to the video of the live audience event. As shown in fig. 3, the method includes the following steps S121 to S124:
and step S121, obtaining event information corresponding to the event video.
Wherein the event information includes an event type and/or an event category, etc. For example, the event type may be a world tournament, the event category may be a table tennis, and so on.
And step S122, acquiring the historical live audience events with the similarity higher than the preset similarity threshold value with the event information.
A historical live spectator event is specifically an event that has ended and has live spectators. Specifically, event information of a historical live audience event is obtained from a database in which historical event data is stored. Then, similarity calculation is performed on the acquired event information of each historical live audience event and the event information corresponding to the event video acquired in step S121. The embodiment of the present invention does not limit the specific similarity calculation manner, and for example, the text similarity between the event information may be calculated, and the semantic similarity between the event information may also be calculated.
And further screening out historical live audience events with the similarity of the event information corresponding to the event video higher than a preset similarity threshold according to the similarity calculation result. For example, if the event information corresponding to the current non-audience event video is the history tournament table tennis, the screened history auditor event can be the history tournament table tennis, and the history tournament table tennis has live audiences to watch.
Step S123, the live audience information of the historical live audience events is obtained.
The live audience information includes at least one of: historical attendance rates, historical audience share for different countries, historical audience share for different genders, and historical audience share for different age groups, among others.
Step S124, generating a simulation audience set corresponding to the event video according to the live audience information.
Because the similarity of the screened historical live audience events and the non-live audience events corresponding to the event videos is higher, the simulated audience set of the current non-live audience events can be accurately simulated based on the live audience information of the historical live audience events.
The generated simulated audience set comprises at least one simulated audience, and each simulated audience has corresponding audience information. The audience information includes at least one of: country information, gender information, and age group information, among others. Wherein, the ratio of the number of the simulated audiences in the simulated audience set to the number of the simulated seats is matched with the historical seating rate acquired in the step S123; the simulated audience proportions of different countries in the simulated audience set are matched with the historical audience proportions of different countries in the step S123; the simulated audience proportions of different genders in the simulated audience set are matched with the historical audience proportions of different genders in the step S123; the simulated audience share ratios of the different age groups in the simulated audience set are matched with the historical audience share ratios of the different age groups in step S123.
Step S130, the event venue model and the simulation audience set are fused to generate a simulation venue site audience model corresponding to the event video.
After the event venue model and the simulation audience set are fused, the distribution condition of each simulation audience in the event venue can be simulated, namely, the simulation venue scene audience model corresponding to the event video is generated.
In an alternative embodiment, the merging of the event venue model with the simulated audience set is performed by binding simulated seats in the event venue model with the simulated audience in the simulated audience set. Wherein a simulated spectator is bound to a simulated seat; a simulated seat may bind a simulated audience or may bind a simulated audience without binding.
For a simulated seat with a seat type as a core seat included in the event venue model, the event venue model and the simulated audience set can be fused through steps S131 to S134 shown in fig. 4:
step S131, determining the target simulation seat with the seat category as the core seat in the event venue model.
As shown in fig. 2, the target simulated seats are simulated seats corresponding to the shaded square blocks in the figure.
Step S132, identifying the target simulation audience of which the country information is matched with the country information of the competitor corresponding to the event video from the simulation audience set.
For example, the participants are the Chinese team and the Japanese team. The country information of the participating parties is china and japan, respectively. A simulated audience of country china (hereinafter referred to as a simulated audience of china) and a simulated audience of country japan (hereinafter referred to as a simulated audience of japan) are obtained from the simulated audience set. The chinese simulated audience and the japanese simulated audience are target simulated audiences.
Step S133, acquiring a preset number of target simulation audiences, and binding the preset number of target simulation audiences with the target simulation seats.
After the target simulation audiences are screened out, a preset number of target simulation audiences are obtained from the screened out target simulation audiences, and each preset number of target simulation audiences is bound with a target simulation seat. Wherein the ratio of the preset number to the number of the target simulated seats is higher than the ratio of the target simulated audience in the non-target simulated seats. I.e. the simulated spectators, which are in line with the competitor's country, are centrally bound to the core seating area.
For example, the participants are the Chinese team and the Japanese team, and the simulated audience set includes 10 simulated audiences in China and 9 simulated audiences in Japan. If the predetermined number is 14, 7 chinese simulated viewers and 7 japanese simulated viewers are obtained. And binding the 7 chinese simulated audiences with any 7 target simulated seats on the left side of fig. 2 one by one, and binding the 7 japanese simulated audiences with any 7 target simulated seats on the right side of fig. 2 one by one. Wherein the ratio of the preset number to the target simulated seats is 7/8, i.e. the ratio of the target simulated audience in the core seat area is 7/8; the remaining target simulated viewers were 3 chinese simulated viewers and 2 japanese simulated viewers, the remaining target simulated viewers were tied to the non-target simulated seats, and the number of the non-target simulated seats in fig. 2 was 48, so that the proportion of chinese simulated viewers in the non-core seating area was 3/48 and the proportion of japanese simulated viewers in the non-core seating area was 2/48.
Step S134, binding the simulated audience with the currently unbound simulated seats with the non-target simulated seats.
After binding a preset number of target simulation audiences with the target simulation seats, binding the remaining simulation audiences (i.e. simulation audiences not currently bound with the simulation seats) with the non-target simulation seats in a random manner and the like.
Fig. 5 is a schematic diagram illustrating a two-dimensional structure of a simulation venue live audience model according to an embodiment of the present invention. As shown in fig. 5, fig. 5 further binds simulated viewers in simulated seats on the basis of fig. 2. In fig. 5, "C" represents a chinese simulated audience, "J" represents a japanese simulated audience, "G" represents a german simulated audience, "a" represents a american simulated audience, "K" represents a korean simulated audience, and "R" represents a russian simulated audience.
Aiming at the simulated seats of which the seat types are not included in the event venue model as core seats, the simulated audiences can be bound with the simulated seats in a random mode and the like.
Step S140, identifying a highlight segment in the event video.
And if the event video is the event live stream, identifying wonderful segments in the segments to be played of the event live stream.
In an alternative highlight recognition approach, the highlight recognition method shown in fig. 6 may be used. As shown in fig. 6, the method includes steps S141 to S143:
step S141, a highlight recognition model is constructed in advance.
The embodiment of the invention does not limit the specific structure of the highlight segment recognition model. For example, the highlight recognition model may be constructed using a 3D convolution algorithm. The 3D convolution algorithm is to form a cube by stacking a number of consecutive frames and then run a 3D convolution kernel in the cube. With this structure, the feature map in the convolutional layer is connected to a plurality of adjacent frames in the previous layer to capture motion information, so that the highlight in the dynamic video can be accurately identified.
And step S142, obtaining a historical event video, labeling the historical event video to generate a training sample, and performing model training on the constructed highlight segment recognition model by using the training sample to obtain a trained highlight segment recognition model.
And carrying out segmentation processing on the acquired historical event videos to generate video segments, and labeling each video segment. In the marking process, marking can be carried out manually according to the overall wonderful degree and/or action difficulty of the video segmentation; or, the marking is automatically carried out through the decibel change of the audio in the video segmentation.
After labeling, extracting a preset number of image frames from each video segment, and inputting the extracted image frames into a constructed highlight segment recognition model for model training. And when the preset finishing condition is met, finishing the training and obtaining the trained highlight recognition model.
Step S143, acquiring a segment to be broadcast of the event live broadcast stream, inputting the segment to be broadcast into the trained wonderful segment recognition model, and acquiring the time period information of the wonderful segment output by the wonderful segment recognition model.
And the wonderful segments of the event video can be recognized in real time by using the trained wonderful segment recognition model. The highlight recognition model may output time period information of the recognized highlight. The time interval information may be a start point and an end point of the highlight.
Further optionally, the highlight identification model may further output the highlights corresponding to each highlight.
In another alternative highlight identification method, a highlight labeling entry is provided, and a labeling person can view the to-be-played highlight in the interface and label the highlight in the to-be-played highlight through the highlight labeling entry. Further optionally, the type of the highlight can be marked through the mark entry, for example, the type can be shooting, entering a ball, breaking a record, sprinting, clearing a stick, a match point, a match spot, and the like. In addition, the wonderness of the current wonderness segment can be determined according to the mapping relation between the type of the wonderness segment and the wonderness.
And S150, generating a simulated audience audio corresponding to the highlight segment according to the simulated venue scene audience model.
The simulation venue site audience model can simulate the distribution condition of each simulation audience in the event venue, and the standard audio corpora of each simulation audience are mixed based on the distribution condition to generate simulation audience audio corresponding to the wonderful fragments. Namely, the simulated audience audio corresponding to the wonderful section is the simulated sound effect generated when the wonderful section is watched by the simulated live audience.
In an alternative embodiment, the method shown in FIG. 7 may be used to obtain simulated audience audio corresponding to highlights. As shown in fig. 7, the method includes the following steps S151 to S153:
step S151, for any simulated audience, obtaining the standard audio corpus of the simulated audience according to the audience information of the simulated audience.
A corpus is constructed in advance, and different audio corpora, such as applause, applause and fueling sounds, are stored in the corpus. The audio corpus can be obtained from a related platform, and can also be simulated and synthesized through sound simulation equipment. Each audio corpus has corresponding corpus information, and the corpus information at least comprises at least one of the following information: corpus identification, memory address, language, gender, age group, and cheering type, etc. The corpus identification is used for uniquely determining the audio corpus, the storage address is used for acquiring the audio corpus, the language is specifically language information affiliated to the audio corpus, the gender is specifically the gender of a speaker of the audio corpus, the age group is specifically the age group of the speaker of the audio corpus, and the cheering type can be specifically the type of oil adding sound, cheering sound and the like.
And acquiring standard audio corpora of any simulated audience based on the constructed corpus. The audio corpus which is obtained from the corpus and matched with the audience information of the simulated audience is the standard audio corpus of the simulated audience. In the process of obtaining the standard audio corpus of the simulated audience, the audience information of the simulated audience is matched with the corpus information of the corpus. For example, the audience information of the simulated audience a is: in China, 20-30 years old, men obtain standard audio corpora of Chinese language, age class 20-30 and gender of male corresponding corpus seat simulation audience A from a corpus.
Optionally, in order to improve the searching efficiency of the standard audio corpus, in the process of obtaining the standard audio corpus of the simulated audience, the standard audio corpus may be searched according to the priorities of the plurality of pieces of audience information of the simulated audience. Wherein, the priority of each audience information is: country > sex > age group. For example, searching an audio corpus matched with the country information of the simulated audience from a corpus, and if the audio corpus matched with the country information cannot be searched, adopting a system to default the audio corpus; if the audio corpora matched with the country information can be found, the audio corpora consistent with the gender of the simulated audience are further screened out from the found audio corpora, and then the audio corpora consistent with the age bracket of the simulated audience are screened out, and the like.
Step S152, calculating a distance between the analog seat bound by the analog audience and the analog video capturing device according to the seat position information of the analog seat bound by the analog audience and the device position information of the analog video capturing device, and correcting the standard audio corpus of the analog audience according to the distance to obtain a corrected audio corpus of the analog audience.
As an alternative embodiment, the standard audio corpus of each simulated audience obtained in step S151 may be directly mixed to generate the simulated audience audio. However, in this way, the mixed simulated audience audio is much different from the actual situation. Based on this, the embodiment of the present invention further modifies the standard audio corpus of the simulated audience through step S152, and obtains the simulated audience audio through the modified audio corpus.
Specifically, the sound level of the live audience collected by the video collecting device is different due to the difference in distance between the live audience and the video collecting device. Therefore, the embodiment of the invention aims at any simulated audience, and corrects the standard audio corpus of the simulated audience according to the distance between the simulated seat bound by the simulated audience and the simulated video acquisition equipment so as to obtain the corrected audio corpus of the simulated audience. Wherein the corrected audio corpus may be obtained by the following formula 1-1:
Fi＝Si/340*fi(formula 1-1)
Wherein, FiTo correct the decibel value of an audio corpus, fiIs the decibel value, S, of the standard audio corpusiThe distance between the simulated seat and the simulated video capture device bound for the simulated audience.
Step S153, based on the corrected audio corpus of each simulated audience, generating the simulated audience audio corresponding to the wonderful segment.
And after the corrected audio corpora of each simulated audience are mixed, the simulated audience audio corresponding to the wonderful segments can be generated.
Optionally, in order to further improve the fidelity of the audio of the simulated spectators, the embodiment of the invention identifies the highlight segments in the event video and the highlights of the highlight segments, and generates the audio of the simulated spectators corresponding to the highlight segments based on the corrected audio corpus of each simulated spectator and the highlights of the highlight segments. Wherein, the higher the wonderful degree, the higher the decibel value of the audio of the analog audience.
Optionally, the simulated audience audio corresponding to the highlight segments may be generated based on the modified audio corpus and the dynamic factors of the simulated audiences. For example, in a closed venue, since the influence of the environment such as wind speed on audio acquisition is small, the dynamic factor may be 1; in an outdoor venue, the dynamic factor may be less than 1 due to the large influence of the environment such as wind speed on audio acquisition.
Optionally, the analog audience audio corresponding to the highlight segment may be generated based on the corrected audio corpus and the mixing duration parameter of each analog audience. Each modified audio corpus may correspond to a mixing duration parameter, and the mixing duration parameter may be randomly determined within a preset range. And determining the time length of the intercepted corrected audio corpus according to the audio mixing time length parameter, and then mixing the intercepted corrected audio corpus to generate the simulated audience audio.
In addition, optionally, as shown in fig. 8, a simulated audience audio control page may be provided for the user, and the user may adjust parameters such as mixing duration, saturation, and dynamic factor in the page. Finally, simulated viewer audio is generated based on the adjusted parameters.
Step S160, embed the simulated spectator audio into the highlight segments in the event video.
Specifically, the event video is analyzed into an event image and an event audio, a timestamp corresponding to the highlight segment is determined, and the simulated audience audio is embedded into the event audio at a position corresponding to the timestamp to obtain the audio of the mixed event. The mixed event audio is then mixed with the event images to generate an event video containing simulated spectator audio.
In addition, in an alternative embodiment, the participants in the event video may be identified and the segments of the simulated spectator audio to be embedded may be determined based on the characteristic information of the participants. For example, if it is recognized that a certain player Z is in the waiting stage and the characteristic information of the player Z is "clapping encouragement at waiting stage", it can be determined that the player Z is in the waiting stage as a segment in which the simulated audience audio is to be embedded. The simulated audience audio can be embedded in the corresponding segment of the weather phase. By adopting the mode, the watching experience of the audience can be further improved.
Therefore, the embodiment of the invention constructs the event venue model and the simulation audience set corresponding to the non-live audience event video, and obtains the simulation venue live audience model capable of simulating the distribution of the live users in the event venue through the fusion of the event venue model and the simulation audience set; and further acquiring a simulated audience audio corresponding to the highlight segment based on the simulated venue live audience model, and embedding the simulated audience audio into the highlight segment of the video of the non-live audience event. By adopting the scheme, the network audience can hear the on-site audience simulation sound effect when watching the wonderful section of the off-site audience event video, the simulation sound effect is high in matching degree with the actual event situation, the on-site audience atmosphere of the event can be realistically simulated by the simulation sound effect, the watching experience of watching the off-site audience event video by the network audience is improved, and the user retention rate of the off-site audience event video playing platform is improved.
Fig. 9 is a schematic structural diagram illustrating a processing apparatus for a non-live audience event video according to an embodiment of the present invention.
As shown in fig. 9, the apparatus 900 for processing a live audience event video includes: a venue model building module 910, a simulated audience generation module 920, a fusion module 930, an identification module 940, an audio generation module 950, and an embedding module 960.
A venue model construction module 910, configured to construct an event venue model corresponding to the event video;
a simulated audience generating module 920, configured to generate a simulated audience set corresponding to the event video;
a fusion module 930, configured to fuse the event venue model with the simulated audience set to generate a simulated venue live audience model corresponding to the event video;
an identifying module 940 for identifying highlights segments in the event video;
an audio generating module 950, configured to generate a simulated audience audio corresponding to the highlight according to the simulated venue live audience model;
an embedding module 960 for embedding the simulated spectator audio into the highlight segments in the event video.
In an alternative embodiment, the event venue model includes at least one simulated seat, each simulated seat having corresponding seat information; the simulation audience set comprises at least one simulation audience, and each simulation audience has corresponding audience information;
the fusion module is further configured to: binding simulated seats in the venue model to simulated spectators in the set of simulated spectators.
In an optional implementation, the event venue model further includes at least one analog video capture device, each analog video capture device having corresponding device location information; the seat information includes seat position information;
the audio generation module is further configured to: aiming at any simulated audience, obtaining the standard audio corpus of the simulated audience according to the audience information of the simulated audience;
calculating the distance between the simulated seats bound by the simulated audience and the simulated video acquisition equipment according to the seat position information of the simulated seats bound by the simulated audience and the equipment position information of the simulated video acquisition equipment, and correcting the standard audio corpus of the simulated audience according to the distance to obtain the corrected audio corpus of the simulated audience;
and generating the simulated audience audio corresponding to the wonderful segment based on the corrected audio corpus of each simulated audience.
In an optional embodiment, the identification module is further configured to: identifying a highlight segment in the event video and the highlight of the highlight segment;
the audio generation module is further configured to: and generating the simulated audience audio corresponding to the wonderful section based on the corrected audio corpus of each simulated audience and the wonderful degree of the wonderful section.
In an alternative embodiment, the seating information includes a category of seating; the audience information comprises country information;
the fusion module is further configured to: determining a target simulation seat with a seat class as a core seat in the event venue model;
identifying target simulation audiences of which the country information is matched with the country information of the participants corresponding to the event video from the simulation audience set;
acquiring a preset number of target simulation audiences, and binding the preset number of target simulation audiences with the target simulation seats;
the simulated audience with the currently unbound simulated seats is bound to the non-target simulated seats.
In an alternative embodiment, the simulated audience generation module is further configured to:
acquiring event information corresponding to the event video;
acquiring historical live audience events of which the similarity with the event information is higher than a preset similarity threshold;
acquiring the live audience information of the historical live audience events;
and generating a simulation audience set corresponding to the event video according to the field audience information.
In an alternative embodiment, the event video is a live event stream;
the identification module is further to: and identifying a wonderful segment in the segment to be played of the event live stream.
The specific implementation process of the apparatus may refer to the description of the corresponding parts in the above method embodiments, and is not repeated herein.
Therefore, the embodiment of the invention can enable the network spectators to hear the simulated sound effect of the on-site spectators when watching the wonderful section of the off-site spectator event video, and the simulated sound effect has high matching degree with the actual event situation, and the simulated sound effect can realistically simulate the atmosphere of the on-site spectators of the event, thereby improving the watching experience of the network spectators watching the off-site spectator event video and improving the user retention rate of the off-site spectator event video playing platform.
Embodiments of the present invention provide a non-volatile computer storage medium, where at least one executable instruction is stored in the computer storage medium, and the computer executable instruction may execute the processing method of the non-live audience event video in any of the above method embodiments.
Fig. 10 is a schematic structural diagram of a computing device according to an embodiment of the present invention. The specific embodiments of the present invention are not intended to limit the specific implementations of computing devices.
As shown in fig. 10, the computing device may include: a processor (processor)1002, a Communications Interface 1004, a memory 1006, and a Communications bus 1008.
Wherein: the processor 1002, communication interface 1004, and memory 1006 communicate with each other via a communication bus 1008. A communication interface 1004 for communicating with network elements of other devices, such as clients or other servers. The processor 1002, configured to execute the program 1010, may specifically perform relevant steps in the above-described embodiments of processing methods for non-live audience event videos.
In particular, the program 1010 may include program code that includes computer operating instructions.
The processor 1002 may be a central processing unit CPU, or an application Specific Integrated circuit asic, or one or more Integrated circuits configured to implement an embodiment of the present invention. The computing device includes one or more processors, which may be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
The memory 1006 is used for storing the program 1010. The memory 1006 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.
Claims (10)
1. A method for processing a video of an event without live audience, comprising:
constructing an event venue model corresponding to the event video, and generating a simulation audience set corresponding to the event video;
fusing the event venue model and the simulated spectator set to generate a simulated venue site spectator model corresponding to the event video;
identifying a highlight segment in the event video, and generating a simulated audience audio corresponding to the highlight segment according to the simulated venue site audience model;
embedding the simulated spectator audio into the highlight segments in the event video.
2. The method of claim 1, wherein the venue model includes at least one simulated seat, each simulated seat having corresponding seat information; the simulation audience set comprises at least one simulation audience, and each simulation audience has corresponding audience information;
said merging said venue model with said set of simulated spectators further comprises:
binding simulated seats in the venue model to simulated spectators in the set of simulated spectators.
3. The method of claim 2, wherein the venue model further comprises at least one analog video capture device, each analog video capture device having corresponding device location information; the seat information includes seat position information;
generating a simulated audience audio corresponding to the highlight segment according to the simulated venue live audience model further comprises:
aiming at any simulated audience, obtaining the standard audio corpus of the simulated audience according to the audience information of the simulated audience;
calculating the distance between the simulated seats bound by the simulated audience and the simulated video acquisition equipment according to the seat position information of the simulated seats bound by the simulated audience and the equipment position information of the simulated video acquisition equipment, and correcting the standard audio corpus of the simulated audience according to the distance to obtain the corrected audio corpus of the simulated audience;
and generating the simulated audience audio corresponding to the wonderful segment based on the corrected audio corpus of each simulated audience.
4. The method of claim 3, wherein identifying highlights segments in the event video further comprises: identifying a highlight segment in the event video and the highlight of the highlight segment;
generating the simulated audience audio corresponding to the highlight segment based on the corrected audio corpus of each simulated audience further comprises: and generating the simulated audience audio corresponding to the wonderful section based on the corrected audio corpus of each simulated audience and the wonderful degree of the wonderful section.
5. The method of claim 2, wherein the seating information includes a category of seating; the audience information comprises country information;
the binding simulated seats in the event venue model with simulated spectators in the set of simulated spectators further comprises:
determining a target simulation seat with a seat class as a core seat in the event venue model;
identifying target simulation audiences of which the country information is matched with the country information of the participants corresponding to the event video from the simulation audience set;
acquiring a preset number of target simulation audiences, and binding the preset number of target simulation audiences with the target simulation seats;
the simulated audience with the currently unbound simulated seats is bound to the non-target simulated seats.
6. The method of any of claims 1-5, wherein generating the set of simulated viewers corresponding to the event video further comprises:
acquiring event information corresponding to the event video;
acquiring historical live audience events of which the similarity with the event information is higher than a preset similarity threshold;
acquiring the live audience information of the historical live audience events;
and generating a simulation audience set corresponding to the event video according to the field audience information.
7. The method of any of claims 1-5, wherein the event video is a live event stream;
the identifying highlights segments in the event video further comprises: and identifying a wonderful segment in the segment to be played of the event live stream.
8. An apparatus for processing a video of an off-site spectator event, comprising:
the venue model building module is used for building an event venue model corresponding to the event video;
the simulated audience generating module is used for generating a simulated audience set corresponding to the event video;
the fusion module is used for fusing the event venue model and the simulation audience set to generate a simulation venue site audience model corresponding to the event video;
the identification module is used for identifying wonderful segments in the event video;
the audio generation module is used for generating the simulated audience audio corresponding to the wonderful segment according to the simulated venue scene audience model;
an embedding module to embed the simulated spectator audio into the highlight segments in the event video.
9. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform operations corresponding to the method of processing a live audience event video according to any of claims 1-7.
10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the method of processing a live audience event video according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111194186.5A CN113923512A (en) | 2021-10-13 | 2021-10-13 | Method and device for processing event video of non-live audience and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111194186.5A CN113923512A (en) | 2021-10-13 | 2021-10-13 | Method and device for processing event video of non-live audience and computing equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113923512A true CN113923512A (en) | 2022-01-11 |
Family
ID=79239971
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111194186.5A Pending CN113923512A (en) | 2021-10-13 | 2021-10-13 | Method and device for processing event video of non-live audience and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113923512A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090019467A1 (en) * | 2007-07-11 | 2009-01-15 | Yahoo! Inc., A Delaware Corporation | Method and System for Providing Virtual Co-Presence to Broadcast Audiences in an Online Broadcasting System |
| CN105263038A (en) * | 2015-09-24 | 2016-01-20 | 天脉聚源（北京）科技有限公司 | Method and apparatus for dynamic display of virtual auditorium |
| CN105635834A (en) * | 2015-12-20 | 2016-06-01 | 天脉聚源（北京）科技有限公司 | Competition result displaying method and device |
| CN107277736A (en) * | 2016-03-31 | 2017-10-20 | 株式会社万代南梦宫娱乐 | Simulation System, Sound Processing Method And Information Storage Medium |
| WO2019067480A1 (en) * | 2017-09-29 | 2019-04-04 | Sony Interactive Entertainment America Llc | Venue mapping for virtual reality spectating of electronic sports |
| US20200294365A1 (en) * | 2019-03-12 | 2020-09-17 | Fayble, LLC | Systems and methods for generation of virtual sporting events |
| US20200289928A1 (en) * | 2019-03-12 | 2020-09-17 | Fayble, LLC | Systems and methods for manipulation of outcomes for virtual sporting events |
| CN113395540A (en) * | 2021-06-09 | 2021-09-14 | 广州博冠信息科技有限公司 | Virtual broadcasting system, virtual broadcasting implementation method, device and equipment, and medium |
-
2021
- 2021-10-13 CN CN202111194186.5A patent/CN113923512A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090019467A1 (en) * | 2007-07-11 | 2009-01-15 | Yahoo! Inc., A Delaware Corporation | Method and System for Providing Virtual Co-Presence to Broadcast Audiences in an Online Broadcasting System |
| CN105263038A (en) * | 2015-09-24 | 2016-01-20 | 天脉聚源（北京）科技有限公司 | Method and apparatus for dynamic display of virtual auditorium |
| CN105635834A (en) * | 2015-12-20 | 2016-06-01 | 天脉聚源（北京）科技有限公司 | Competition result displaying method and device |
| CN107277736A (en) * | 2016-03-31 | 2017-10-20 | 株式会社万代南梦宫娱乐 | Simulation System, Sound Processing Method And Information Storage Medium |
| WO2019067480A1 (en) * | 2017-09-29 | 2019-04-04 | Sony Interactive Entertainment America Llc | Venue mapping for virtual reality spectating of electronic sports |
| US20200294365A1 (en) * | 2019-03-12 | 2020-09-17 | Fayble, LLC | Systems and methods for generation of virtual sporting events |
| US20200289928A1 (en) * | 2019-03-12 | 2020-09-17 | Fayble, LLC | Systems and methods for manipulation of outcomes for virtual sporting events |
| CN113395540A (en) * | 2021-06-09 | 2021-09-14 | 广州博冠信息科技有限公司 | Virtual broadcasting system, virtual broadcasting implementation method, device and equipment, and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021249414A1 (en) | Data processing method and system, related device, and storage medium | |
| US20180025078A1 (en) | Live video streaming services with machine-learning based highlight replays | |
| CN103959802B (en) | Image provides method, dispensing device and reception device | |
| KR101535579B1 (en) | Augmented reality interaction implementation method and system | |
| US11004299B2 (en) | System and method for augmenting content | |
| CN108769723B (en) | Method, device, equipment and storage medium for pushing high-quality content in live video | |
| CN111698575B (en) | Live highlight video editing method, device, equipment and storage medium | |
| US20120102023A1 (en) | Centralized database for 3-d and other information in videos | |
| CN106060578A (en) | Producing video data | |
| CN110727341A (en) | Event augmentation based on augmented reality effects | |
| CN1728781A (en) | Method and apparatus for insertion of additional content into video | |
| CN110830847B (en) | Method and device for intercepting game video clip and electronic equipment | |
| CN106534618B (en) | Method, device and system for realizing pseudo field explanation | |
| US20190378333A1 (en) | Methods and systems for representing a pre-modeled object within virtual reality data | |
| CN106534892A (en) | Virtual reality live broadcast system and method based on visual angle recoding | |
| JP2010021632A (en) | Content information reproducing apparatus, content information reproducing system, content information reproducing method, content information reproducing program, recording medium therefor and information processing apparatus | |
| CN111698554A (en) | Live video album generating method, device, equipment and storage medium | |
| JP2020086983A (en) | Image processing device, image processing method, and program | |
| CN109408672A (en) | A kind of article generation method, device, server and storage medium | |
| CN105981103A (en) | Browsing videos via a segment list | |
| TWI518675B (en) | A method for segmenting videos and audios into clips using speaker recognition | |
| KR102550528B1 (en) | System for selecting segmentation video using high definition camera and the method thereof | |
| CN106407353B (en) | Method and device for playing animation | |
| Young et al. | Telefest: Augmented virtual teleportation for live concerts | |
| CN113923512A (en) | Method and device for processing event video of non-live audience and computing equipment |
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 |