WO2021196890A1 - 多媒体处理方法、装置、电子设备、存储介质 - Google Patents

多媒体处理方法、装置、电子设备、存储介质 Download PDF

Info

Publication number
WO2021196890A1
WO2021196890A1 PCT/CN2021/075500 CN2021075500W WO2021196890A1 WO 2021196890 A1 WO2021196890 A1 WO 2021196890A1 CN 2021075500 W CN2021075500 W CN 2021075500W WO 2021196890 A1 WO2021196890 A1 WO 2021196890A1
Authority
WO
WIPO (PCT)
Prior art keywords
special effect
multimedia
video
original
component
Prior art date
Application number
PCT/CN2021/075500
Other languages
English (en)
French (fr)
Inventor
刘瑶
陈仁健
Original Assignee
腾讯科技(深圳)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 腾讯科技(深圳)有限公司 filed Critical 腾讯科技(深圳)有限公司
Publication of WO2021196890A1 publication Critical patent/WO2021196890A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43Processing 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
    • H04N21/44Processing 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
    • H04N21/44008Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43Processing 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
    • H04N21/435Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • H04N21/472End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
    • H04N21/47205End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for manipulating displayed content, e.g. interacting with MPEG-4 objects, editing locally
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/83Generation or processing of protective or descriptive data associated with content; Content structuring
    • H04N21/84Generation or processing of descriptive data, e.g. content descriptors

Definitions

  • This application relates to the field of image application technology, in particular to a multimedia processing method and device, as well as an electronic device and a computer-readable storage medium.
  • the embodiments of the present application provide a multimedia processing method and device based on multiple aspects, as well as an electronic device and a computer-readable storage medium.
  • a multimedia processing method comprising: obtaining original multimedia for which multimedia special effects are to be generated; performing multimedia content recognition on the original multimedia, and obtaining at least one special effect template matching the multimedia content of the original multimedia, the special effect
  • the template contains at least one special effect component, and the special effect component is used to describe the multimedia special effect; according to the target special effect component contained in the selected special effect template, the multimedia special effect described by the target special effect component is generated in the original multimedia.
  • a multimedia processing method which includes: obtaining original multimedia to be generated with multimedia special effects; Matched at least one special effect template, the special effect template contains at least one special effect component, the special effect component is used to describe the multimedia special effect; the special effect template is sent to a designated device, so that the designated device contains the selected special effect template The target special effect component of generates the multimedia special effect described by the special effect component in the original multimedia.
  • a video processing method which includes: displaying original multimedia to be generated with multimedia special effects; displaying at least one special effect template matching the multimedia content of the original multimedia, and the special effects
  • the template is generated according to a special effect component matching the media content of the original multimedia, the special effect component is used to describe the multimedia special effect;
  • the target special effect template selected from the at least one special effect template is detected, the target special effect template includes There is a target special effect component; the multimedia special effect described by the target special effect component is presented in the displayed original multimedia.
  • a video processing device includes: an original multimedia acquisition module, used to obtain the original multimedia of the multimedia special effects to be generated; At least one special effect template with matching content, the special effect template contains at least one special effect component, and the special effect component is used to describe the multimedia special effect; The multimedia special effects described by the target special effect component are generated in the original multimedia.
  • a multimedia processing device includes: a second original multimedia acquisition module for acquiring original multimedia for which multimedia special effects are to be generated; At least one special effect template that matches the media content of the multimedia, the special effect template contains at least one special effect component, the special effect component is used to describe the multimedia special effect; the special effect template sending module is used to send the special effect template to a designated device, The designated device is enabled to generate the multimedia special effect described by the special effect component in the original multimedia according to the target special effect component contained in the selected special effect template.
  • a multimedia processing device includes: an original multimedia display module for displaying the original multimedia of the video special effect to be generated; a special effect template display module for displaying at least one special effect template matching the media content of the original multimedia, the The special effect template is generated according to the special effect component matching the media content of the original multimedia, the special effect component is used to describe the multimedia special effect; the template selection detection module is used to detect the target special effect selected from the at least one special effect template A template, the target special effect template includes a target special effect component; a multimedia special effect presentation module for presenting the multimedia special effect described by the target special effect component in the displayed original multimedia.
  • An electronic device includes a processor and a memory, and computer-readable instructions are stored on the memory, and the computer-readable instructions implement the multimedia processing method as described above when the computer-readable instructions are executed by the processor.
  • a computer-readable storage medium has computer-readable instructions stored thereon, and when the computer-readable instructions are executed by a processor of a computer, the computer is caused to execute the multimedia processing method as described above.
  • Figure 1 is a schematic diagram of the implementation environment involved in this application.
  • Fig. 2A is a flowchart showing a multimedia processing method according to an exemplary embodiment
  • Fig. 2B is a flowchart showing a multimedia processing method according to an exemplary embodiment
  • FIG. 3 is a flowchart of one embodiment of step 130 in the embodiment shown in FIG. 2B;
  • FIG. 4 is a flowchart of one embodiment of step 133 in the embodiment shown in FIG. 3;
  • FIG. 5 is a flowchart of one embodiment of step 150 in the embodiment shown in FIG. 2B;
  • Fig. 6 is a schematic diagram of a special effect template shown in an exemplary embodiment
  • FIG. 7 is a flowchart of another embodiment of step 130 in the embodiment shown in FIG. 2B;
  • Fig. 8 is a flowchart showing a multimedia processing method according to another exemplary embodiment
  • Fig. 9 is a flowchart showing a multimedia processing method according to another exemplary embodiment.
  • Fig. 10 is a schematic diagram showing a process of generating multimedia special effects according to an exemplary embodiment
  • Fig. 11 is a flowchart showing a multimedia processing method according to another exemplary embodiment
  • Fig. 12 is a schematic diagram showing an interface of a terminal device according to an exemplary embodiment
  • Fig. 13 is a block diagram showing a multimedia processing device according to an exemplary embodiment
  • Fig. 14 is a block diagram showing a multimedia processing device according to another exemplary embodiment
  • Fig. 15 is a block diagram showing a multimedia processing device according to another exemplary embodiment
  • Fig. 16 is a schematic structural diagram showing a multimedia processing device according to an exemplary embodiment.
  • FIG. 1 is a schematic diagram of an implementation environment involved in the present application.
  • the implementation environment includes a terminal 100 and a server 200.
  • a wired or wireless communication connection is established in advance between the terminal 100 and the server 200, so that data transmission can be performed between the terminal 100 and the server 200.
  • the terminal 100 runs a multimedia application program, such as a video application program, which has a user interaction interface and provides the user with video interaction functions such as the generation and release of video special effects through the user interaction interface.
  • the server 200 is used to provide multimedia The normal operation of the application provides data services.
  • the terminal 100 can be any electronic device capable of running the multimedia application, such as a smart phone, a tablet computer, a computer, a notebook, etc., and the multimedia application running on the terminal 100 can be a client application.
  • the server 200 may be a single server, or a server cluster composed of several servers, which is not limited here.
  • the existing multimedia special effect generation scheme the user needs to select the target special effect template from the preset special effect templates, and edit the user video to be generated for the video special effect, so that the user video meets the target special effect template. Therefore, it is possible to generate the video special effects contained in the target special effect target in the edited user multimedia. It can be seen that the existing multimedia special effect generation schemes have great limitations on user multimedia, and it is not convenient to generate video special effects in user multimedia based on preset special effect templates.
  • this embodiment proposes a multimedia processing method.
  • the special effect template that generates multimedia special effects for the user's multimedia can be adaptive to the media content contained in the user's multimedia, without the user having to pre-examine the user.
  • the multimedia editing process completely eliminates the restrictions on the user's multimedia in the process of generating multimedia special effects.
  • Fig. 2A is a flowchart showing a multimedia processing method according to an exemplary embodiment. The method is executed by an electronic device.
  • the electronic device may be the terminal 100 in the implementation environment shown in Fig. 1 or the server 200.
  • the multimedia processing method at least includes the following steps:
  • Step S101 Obtain original multimedia for which multimedia special effects are to be generated.
  • the original multimedia refers to the user multimedia for which multimedia special effects are to be generated, including video and images. Select to obtain from the album), there is no restriction here.
  • Step S102 Perform media content recognition on the original multimedia, and obtain at least one special effect template that matches the media content of the original multimedia.
  • the special effect template contains at least one special effect component, and the special effect component is used to describe the multimedia. Special effects.
  • the media content identification is performed on the original multimedia and at least one special effect template matching the media content of the original multimedia is obtained
  • the media content identification is performed on the original multimedia to obtain the original multimedia content.
  • a multimedia tag corresponding to the media content of the multimedia; according to the multimedia tag, at least one special effect component matching the multimedia tag is obtained from a preset special effect component set; according to at least one special effect matching the multimedia tag Component to generate at least one special effect template.
  • the original multimedia includes an original video; when the original multimedia is identified by the media content to obtain a multimedia tag corresponding to the media content of the original multimedia, according to the video duration of the original video, Intercept at least one frame of video image from the original video; perform content recognition on the at least one frame of video image to obtain the content label of the at least one frame of video image, and use the content label of the at least one frame of video image as and The video tag corresponding to the video content of the original video.
  • generating the multimedia special effect described by the target special effect component in the original multimedia according to the target special effect component contained in the selected special effect template includes: parsing the information of each special effect component contained in the selected special effect template Special effect parameters, the special effect parameters include time parameters, the time parameters are used to describe the relative position and display duration of the special effect components displayed in the original video; according to the time parameters of each special effect component, in the The video special effect content corresponding to each special effect component is generated at the relative position of the original video, and the video special effect content is continuously displayed for the display duration.
  • the original video includes at least two video clips; performing media content identification on the original multimedia to obtain at least one special effect template that matches the media content of the original multimedia includes: The video segment performs video content recognition; according to the identified video content of each video segment, a special effect template that matches the video content of each video segment is obtained.
  • obtaining at least one special effect component matching the multimedia tag from a preset special effect component set according to the multimedia tag includes: determining the special effect component according to a preset tag weight determination rule The weight of the special effect label of each special effect component in the set relative to the multimedia label; according to the weight of the special effect label of each special effect component relative to the multimedia label, a special effect label is selected from the special effect component set to match the multimedia label At least one special effects component.
  • selecting at least one special effect component whose special effect label matches the multimedia label from the special effect component set according to the weight of the special effect label of each special effect component relative to the multimedia label includes: The special effect components in the special effect component set whose weight is greater than the preset weight threshold are used as special effect components matching the multimedia tags, or, according to the special effect tags of the various special effect components, it is determined that the special effect components in the special effect component set belong to the same special effect type
  • the special effect components of each special effect component are selected from the special effect components of each special effect type according to the order of the weight of the special effect label of each special effect component relative to the multimedia label, and the number of the selected special effect components under each type Same as the number of preset special effect templates.
  • generating at least one special effect template according to the special effect component matching the multimedia tag includes: randomly combining the special effect components matching the multimedia tag according to different special effect types to obtain at least One of the special effect templates, or, according to the sorting of the special effect components of different special effect types with respect to the matching degree of the multimedia tags, the special effect components of the different special effect types with the same order are combined to form a special effect template to obtain at least one The special effect template.
  • step S103 the multimedia special effect described by the target special effect component is generated in the original multimedia according to the target special effect component contained in the selected special effect template.
  • the method further includes; according to the special effect editing instruction, calling The special effect components included in the special effect multimedia are formed by the combination of the original multimedia and the multimedia special effects described by the target special effect component; according to the component update instruction, the special effect components included in the special effect multimedia Update.
  • the original multimedia is processed with special effects through the special effect template, and the user does not need to select and add special effects from a large number of special effect materials, which greatly improves the convenience of the multimedia special effect generation process.
  • the special effect template corresponding to the original multimedia of the multimedia special effect to be generated is obtained by recognizing the original multimedia of the multimedia special effect to be generated and automatically matched according to the media content of the original multimedia. Therefore, the special effect template is actively adapted to the multimedia special effect to be generated Then, according to the target special effect component contained in the selected special effect template, the multimedia special effect described by the target special effect component is generated in the original video, so that this application does not need to edit the original multimedia before generating the multimedia special effect on the original multimedia.
  • the generation efficiency of special effects has been greatly improved, and there are no restrictions on the original multimedia in the process of generating multimedia special effects.
  • the multimedia includes videos, images, and so on.
  • the multimedia processing method described in the embodiments of the present application is described below by taking multimedia as video as an example.
  • Fig. 2B is a flowchart showing a multimedia processing method according to an exemplary embodiment. The method can be applied to the terminal 100 in the implementation environment shown in Fig. 1 and is specifically executed by a multimedia application running in the terminal 100.
  • the multimedia (video) processing method includes at least the following steps:
  • Step 110 Obtain the original video of the video special effect to be generated.
  • Step 130 Perform video content recognition on the original video, and obtain at least one special effect template that matches the video content of the original video.
  • the special effect template contains at least one special effect component, and the special effect component is used to describe the video special effect.
  • the video content recognition of the original video is a process of recognizing the video objects contained in the original video.
  • the video objects contained in the original video may be people, objects, or other objects appearing in the original video, which is not limited in this embodiment.
  • the video content of the original video can be obtained.
  • a special effect template is a set of special effect components combined with at least one special effect component. These special effect components are preset, and one special effect component can describe one or more video special effects, so the special effect template can be understood as a set of video special effects.
  • the process of obtaining at least one special effect template that matches the video content of the original video based on the video content of the original video obtained by identification is to adaptively generate at least one special effect template for the original video based on the video content of the original video.
  • Step 150 Generate a video special effect described by the target special effect component in the original video according to the target special effect component contained in the selected special effect template.
  • the selection operation of the special effect template may be triggered by the user through interactive methods such as clicking, double-clicking, long-pressing, etc., which is not performed in this embodiment. limit.
  • these video special effects can be generated correspondingly in the original video.
  • special effect components matching the video content of the original video are selected from the preset special effect components and combined to form at least one special effect template.
  • These special effect templates can be adaptive to the original video.
  • the video special effect described by the target special effect component contained in the selected special effect template can be generated in the original video.
  • the limitation of the original video generated by the special effect template is preset.
  • this embodiment adds video special effects to the original video in the form of a special effect template, which eliminates the need for users to select special effect materials from a large number of special effect materials, and makes the process of generating video special effects more convenient.
  • the method can quickly generate high-quality video effects in the original video.
  • FIG. 3 is a flowchart of one embodiment of step 130 in the embodiment shown in FIG. 2B.
  • performing video content recognition on an original video and obtaining at least one special effect template that matches the video content of the original video includes at least the following steps:
  • Step 131 Perform video content recognition on the original video, and obtain a video tag corresponding to the video content of the original video.
  • the video content recognition of the original video is the process of recognizing the video objects contained in the original video. Therefore, the video tag corresponding to the video content of the original video is the video object contained in the original video. The corresponding label. For example, if a picture of a child is recognized in the original video, the video tag "Cute Baby" can be obtained accordingly.
  • the video tags obtained by performing video content recognition on the original video should also have multiple dimensions.
  • the video tag may be a tag corresponding to the video object contained in the video image in the original video.
  • at least one frame of video image such as several frames, can be intercepted from the original video according to the video duration of the original video, and then content identification is performed on the intercepted video images to obtain the content tags of these video images, and the content tags identify the video.
  • the video objects contained in the image, so that the content tags of these video images are used as the video tags corresponding to the video content of the original video.
  • the number of frames of video images intercepted from the original video can be set accordingly according to specific requirements. If the video duration of the original video is long, so that the obtained video tag can accurately identify the video content of the original video, a larger number of frames of video images can be intercepted for content recognition. In the same way, even if the video duration of the original video is short, video images with a larger number of frames can be intercepted for content, so that the obtained video tags can accurately reflect the video content of the original video.
  • Step 133 According to the video tag, obtain at least one special effect component matching the video tag from the preset special effect component set.
  • the special effect component set includes all preset special effect components, and these special effect components respectively describe different video special effects.
  • the special effect component set includes all preset special effect components, and these special effect components respectively describe different video special effects.
  • at least one special effect component that matches the video tag is selected from the special effect component set to ensure that the obtained special effect component can match the video content of the original video.
  • this embodiment can select different special effect components for video special effect generation for different video contents, thereby forming a diversified video special effect generation scheme.
  • Step 135 Generate at least one special effect template according to the special effect component matching the video tag.
  • the special effect template generated according to these special effect components can also match the video content of the original video. match.
  • special effect components matching the video tags of the original video are obtained from the preset special effect component set, and the special effect components are combined to form the original video tag.
  • At least one special effect template that matches the video content of the video so that this embodiment can generate a rich special effect template through a combination of preset special effect materials, and the generated special effect template can be adapted to the video content of the original video, so that this embodiment
  • the video special effects generation program provided has great adaptability.
  • FIG. 4 is a flowchart of one embodiment of step 133 in the embodiment shown in FIG. 3.
  • obtaining at least one special effect component matching the video tag from the preset special effect component set includes at least the following steps:
  • Step 1331 Determine the weight of the special effect label of each special effect component in the special effect component set relative to the video label according to the preset label weight judgment rule.
  • the special effect label of each special effect component in the special effect component set is used to identify the special effect style of the special effect component.
  • the special effect label can be "European and American retro style", “Chinese style”, etc., and each special effect component can have at least one special effect. Label, at least one label of different special effect components can be the same.
  • the preset tag weight determination rule refers to a rule set in advance and used to determine the weight of the special effect tag relative to the video tag of the original video.
  • the video tags obtained by performing video content recognition for any original video and the special effect tags corresponding to the special effect components are all preset, that is, all the video tags and special effect tags are known Therefore, the weight of each special effect tag relative to each video tag can be determined in advance, and the obtained weight and the corresponding determination condition can be associated and stored, for example, it can be stored in the form of a list, so that the tag weight determination rule can be obtained.
  • the weight of the special effect label of each special effect component in the special effect component set relative to the video label of the original video identified in step 131 can be determined.
  • the weight of the special effect tag relative to the video tag reflects the degree of matching between the corresponding special effect component and the video content of the original video.
  • Step 1333 According to the weight of the special effect label of each special effect component relative to the video label, select at least one special effect component whose special effect label matches the video label from the special effect component set.
  • the degree of matching between the special effect component and the video content of the original video is embodied by the weight of the special effect label of the special effect component relative to the video label of the original video. Therefore, the special effect label of each special effect component in the special effect component set is relatively original.
  • the weight of the video tag of the video can determine at least one special effect component that matches the video content of the original video, and the selected special effect component generates at least one special effect template that matches the video content of the original video.
  • a special effect component with a weight greater than a preset weight threshold in the special effect component set can be used as a special effect component matching the video tag of the original video, and these special effect components can be randomly combined according to different special effect types to obtain At least one special effect template that matches the video content of the original video.
  • the special effect type corresponding to the special effect component is used to indicate the type of the video special effect described by the special effect component.
  • the special effect component can include various special effect types such as opening and ending, time special effects, stickers, atmosphere, filters, transitions, etc., and different special effect types
  • the following can contain multiple special effect components.
  • one special effect component can correspond to one type of video special effect, and multiple special effect components can also form a special effect component, so that one special effect component can correspond to multiple video special effects.
  • the special effect component under the credits type is composed of the opening special effect component and the end special effect component.
  • the stop-motion special effect component and the color-changing special effect component can form the fixed-point color-changing special effect component, so that the fixed-point color-changing component has both the stop-motion special effect and the color-changing special effect.
  • a single special effect component includes at least three special effect parameters, namely type parameters, component parameters and time parameters.
  • the type parameter is used to describe the special effect type corresponding to the special effect component, such as sticker type, filter type, etc.
  • the component parameters are used to describe the specific video special effect content, and the video special effect content described by the special effect component can be drawn according to the component parameters.
  • the corresponding special effect materials can be drawn according to their component parameters; for special effect components that do not contain special effect materials, such as time special effects, the time special effects can be drawn according to their component parameters.
  • the time parameter is used to describe the relative position and display duration of the special effect component in the original video, and the relative position is the temporal position of the special effect component in the original video when the original video is displayed.
  • the special effect type corresponding to the special effect component can be determined.
  • the special effect template contains special effect components of different special effect types, thereby ensuring that each special effect template generates a rich variety in the original video. Video effects.
  • the special effect components belonging to the same type in the special effect component set according to the special effect tags of each special effect component and according to the order of the weight of the special effect tag of each special effect component relative to the video tag in descending order,
  • the special effect components are selected from the special effect components under each type, and the number of the selected special effect components under each type is the same as the number of the preset special effect templates.
  • the special effect components of the same sorting under different special effect types are combined to form a special effect template, thereby obtaining at least one special effect template.
  • these special effect components are classified according to different special effect types, and for the special effect components belonging to the same special effect type, the weight of the special effect tag relative to the video tag of the original video is greater Sort to small, and then according to the preset number of special effect templates, select this number of special effect components from the special effect components under different special effect types in order to combine the special effect components of the same sort to form a special effect template.
  • the number of preset special effect templates corresponds to the number of special effect templates displayed in the video application interface.
  • special effect templates For the display of special effect templates in the video application interface, you can also arrange the special effect templates in the order of the weights corresponding to the special effect components in the special effect templates, so that the special effect templates can be sorted from large to small according to the degree of match between the original video and the video content. Sorting to facilitate the selection of special effect templates.
  • the obtained special effect template is guaranteed It matches the video content of the original video.
  • FIG. 5 is a flowchart of one embodiment of step 150 in the embodiment shown in FIG. 2B.
  • the video special effect described by the target special effect component is generated in the original video to obtain the special effect video corresponding to the original video, including at least The following steps:
  • Step 151 Analyze the special effect parameters of each special effect component contained in the selected special effect template, where the special effect parameters include time parameters.
  • the special effect parameters of the special effect component include at least the type parameter, the component parameter and the time parameter.
  • the time parameter is used to describe the relative position and display duration of the video special effect described by the special effect component in the original video.
  • the time parameter includes the start position of the special effect component relative to the original video display (hereinafter referred to as startOffset), the end position of the special effect component relative to the original video display (hereinafter referred to as endOffse), and the duration (hereinafter referred to as duration).
  • Fig. 6 is a schematic diagram of a selected special effect template shown in an exemplary embodiment.
  • the opening and ending special effects are included in the opening and ending special effects.
  • the opening special effects are displayed from the 0ms position of the original video, and the display duration is 2000ms.
  • the display starts at 8000ms, and the display duration is 2000ms.
  • the spot atmosphere special effects included in the atmosphere component are displayed starting from the 2000th ms of the original video, and the display duration is 8000ms. It should be understood that the end position of the special effect component relative to the original video display can be derived from the start position and the duration together.
  • Step 153 According to the time parameters of each special effect component, generate the video special effect content corresponding to each special effect component in the relative position of the original video, and make the video special effect content continue to be displayed for the display duration included in the display time.
  • the video special effect content corresponding to each special effect component can be generated in the relative position of the original video according to the relative position and display duration described by the time parameter, and make The generated video special effect content lasts for the display duration contained in the display time parameter, so that multiple video special effects corresponding to the selected special effect template are displayed in the original video to realize the generation of video special effects in the original video and obtain the special effects corresponding to the original video video.
  • the obtained special effect video is formed by combining the original video and the video special effects described by each special effect component contained in the selected special effect template.
  • the video special effect corresponding to the selected special effect template is automatically generated in the original video.
  • the process of generating the video special effect is very simple and does not require the user Perform additional operations.
  • the foregoing video processing method further includes the following steps:
  • the background music matching the video content of the original video is selected from the preset background music set, and the background music is integrated into the special effect video.
  • each background music in the background music set is labeled in advance, and music tags are set for each background music according to the genre and other dimensions of the background music. For example, you can set “children's songs”, “cute”, “Mengqu” and other music labels.
  • the background music with the music tag matching the video tag can be selected from the preset background music collection, for example, the background music corresponding to the music tag with the highest matching degree can be selected, and The selected background music is merged into the original video, so that the obtained special effects video contains background music.
  • the background music is distinguished from the special effect templates. After determining the matching background music according to the video content of the original video, for at least one special effect template that matches the video content of the original video, no matter which one is selected Special effect template, the background music in the final special effect video will be consistent.
  • the background music can be used as a special effect type, and the background music component can be combined with other types of special effect components to form a special effect template.
  • the background music set is the background music component set included in the special effect component set.
  • the special effect component that matches the video tag of the original video is obtained from the special effect component set including the background music component.
  • at least one special effect template matching the video content of the original video is formed according to the obtained weights of the music tags of each background music component relative to the video tags, and the weights of the special effect tags of each special effect component relative to the video tags.
  • the background music contained in at least one special effect template matching the original video may be different, thereby further increasing the variety of special effect templates and providing users with a richer video special effect experience.
  • the original video for which the video special effect is to be generated includes at least two video clips, so as to further improve the video special effect.
  • performing video content recognition on the original video to obtain at least one special effect template that matches the video content of the original video includes at least the following steps:
  • Step 132 Perform content identification on each video segment respectively;
  • Step 134 According to the identified video content of each video segment, respectively obtain a special effect template that matches the video content of each video segment.
  • the process of performing content recognition on each video clip in this embodiment is the process of recognizing the video objects contained in each video clip, and the video content of each video clip can be obtained. Match the video tag.
  • the special effect templates that match the video content of each video segment can be obtained according to the method described in the foregoing embodiment.
  • the special effect templates selected for each video segment are respectively, and then the video special effects described by the target special effect components are generated in each video segment according to the target special effect components contained in the selected special effect templates.
  • the method provided in this embodiment adaptively obtains special effect templates for different video clips according to the video content of different video clips, and the user only needs to select different video clips to be generated.
  • the special effect template of the video special effects can make different video clips generate video special effects that match their video content. The whole process still does not require the user to edit each video clip separately, so for multiple video effects to be generated There are no restrictions on video clips.
  • the foregoing multimedia (video) processing method further includes the following steps:
  • step 210 according to the special effect editing instruction, various special effect components included in the special effect video are retrieved.
  • the special effect video is formed by a combination of the original video and the video special effect described by the target special effect component.
  • this embodiment after generating a video special effect for the original video according to the selected special effect template, and obtaining a special effect video corresponding to the original video, this embodiment also provides an editing operation for the special effect video to further improve the user experience.
  • the special effect editing command is used to instruct the editing of the video special effects contained in the special effect video, so it is necessary to call various special effect components contained in the special effect video.
  • the special effect component contained in the special effect video is the target special effect component contained in the special effect template selected in step 150, and the special effect editing instruction may be obtained by detecting that a designated button in the video application interface is triggered.
  • Step 230 According to the component update instruction, update various special effect components included in the special effect video.
  • the component update instruction is used to instruct to update the special effect component contained in the special effect video, where the update operation of the special effect component includes but is not limited to the addition, deletion, and replacement of the special effect component.
  • the component update instruction may also be obtained by detecting that the corresponding button in the video application interface is triggered.
  • the update of the special effect component means that the video special effect generated in the original video is also updated accordingly.
  • Fig. 9 is a flowchart showing a multimedia processing method according to another exemplary embodiment.
  • the multimedia processing method may be applied to the server 200 in the implementation environment shown in Fig. 1. Taking the multimedia as video as an example, the multimedia processing method is described.
  • the multimedia (video) processing method includes at least the following steps:
  • Step 310 Obtain the original video of the video special effect to be generated
  • Step 330 Perform video content recognition on the original video to obtain at least one special effect template that matches the video content of the original video.
  • the special effect template contains at least one special effect component, and the special effect component is used to describe the video special effect;
  • Step 350 Send the special effect template to the designated device, so that the designated device generates the video special effect described by the special effect component in the original video according to the target special effect component contained in the selected special effect template.
  • the designated device is an electronic device running a video application program, for example, the terminal 100 in the implementation environment shown in FIG.
  • the original content of the video special effect to be generated is sent by the designated device, and the designated device sends the original video to the server to obtain from the server at least one special effect template that matches the video content of the original video.
  • the server After the server obtains the special effect template that matches the video content of the original video, it will send the obtained special effect template to the designated device, so that the designated device generates the corresponding video special effect in the original video according to the selected special effect template.
  • the designated device sends the original video to the server.
  • the server obtains the video tag corresponding to the original video by recognizing the video content of the original video, and then selects the background music that matches the original video according to the music tag of the background music.
  • select special effect components that match the original video select special effect components that match the original video, and combine the selected background music and other types of special effect components to form a special effect template that matches the original video, and then deliver the special effect template to the designated device.
  • the designated device generates the video special effects contained in the special effect template into the original video through the selected analysis special effect template.
  • Fig. 11 is a flowchart showing a multimedia processing method according to another exemplary embodiment.
  • the method is applicable to the terminal 100 in the implementation environment shown in Fig. 1 and the designated device in the embodiment shown in Fig. 10.
  • the multimedia processing method at least includes the following steps:
  • Step 410 Display the original multimedia of the video special effect to be generated
  • multimedia in the embodiment of the present application may include video, image, and so on.
  • Step 430 Display at least one special effect template that matches the media content of the original multimedia.
  • the special effect template is generated based on the special effect component that matches the media content of the original multimedia, and the special effect component is used to describe the multimedia special effect;
  • Step 450 Detect a target special effect template selected from at least one special effect template, where the target special effect template includes a target special effect component;
  • Step 470 Present the multimedia special effects described by the target special effect component in the displayed original multimedia.
  • the original multimedia of the video special effect to be generated is displayed, and at least one special effect template that matches the media content of the original multimedia is displayed.
  • the display The original multimedia presents the multimedia special effects described by the target special effect component contained in the target special effect template.
  • the multimedia processing method will be described in detail below by taking a specific application scenario for processing video as an example.
  • the multimedia (video) processing method is applied to a terminal device running a video application program
  • the terminal device may specifically be the terminal 100 in the implementation environment shown in FIG. 1 or the terminal device shown in FIG. 10
  • FIG. 12 is a schematic diagram of the interface of the terminal device.
  • the terminal device displays the original video accordingly.
  • the terminal device displays at least one special effect template that matches the video content of the original video. As shown in Figure 12, the terminal device displays the special effect templates that match the original video in the form of a special effect template list.
  • the special effect template is formed by recognizing the video content of the original video to obtain a video tag corresponding to the original video, and selecting special effect components matching the video content of the original video according to the video tag, and combining these special effect components. It should also be understood that for different original videos selected by the user, the special effect templates contained in the special effect template list are also different.
  • the selected target special effect template is deemed to be detected, and then the video special effect described by the target special effect component contained in the target special effect template is displayed in the original video displayed, that is, the result is displayed Special effects video.
  • the video special effects contained in the special effect template 4 are displayed in the original video, that is, the selected special effect template is previewed in the original video.
  • the obtained special effect video is displayed.
  • the special effect video shown in FIG. 12 contains correspondingly displayed text stickers.
  • the user can also display the "background music”, “adjust material”, “filter” and other buttons in the trigger interface to update the video effect in the special effect video, and finally obtain the special effect video that the user is satisfied with. Then, the user clicks the "Done” button displayed in the interface to store the final special effect video locally, or upload the special effect video to the server for storage, or publish the special effect video to the Internet. There is no restriction here. .
  • the method provided in the embodiments of this application can adaptively match at least one special effect template for the user video, and each special effect template has its own special effect style and contains at least A variety of video special effects, so that the final special effects videos are diversified, and there are no restrictions on user videos.
  • the multimedia in the embodiment of the present application includes video, image, and so on.
  • the following uses multimedia as an image as an example to describe the application of the multimedia processing method provided in the above embodiment to the image special effect generation process. Therefore, based on another aspect of this application, a multimedia processing method is also provided to conveniently perform special effects on user images. generate.
  • the multimedia (image) processing method can also be applied to the terminal 100 in the implementation environment shown in FIG. 1, and is specifically executed by a multimedia application program running in the terminal 100.
  • the multimedia (image) processing method includes at least the following steps:
  • the special effect template contains at least one special effect component, and the special effect component is used to describe the image special effect;
  • the image special effect described by the target special effect component is generated in the original image.
  • the original image may be obtained by the user triggering the camera to shoot, or obtained by the user from a storage module (such as an album), which is not limited here.
  • the process of recognizing the image content of the original image that is, the process of recognizing people, objects, or other objects contained in the original image, is not limited here.
  • the process of obtaining at least one special effect template that matches the image content of the original image is the process of adaptively generating at least one special effect template content for the original image according to the image content of the original image. It is formed by combining at least one special effect component that matches the image content of the original image.
  • the user selects a favorite special effect template from these special effect templates that match the image content of the original image, and then the image special effect described by each target special effect component contained in the selected special effect template can be generated in the original image.
  • the special effect template matching with the image content of the original image may also be implemented based on the image tag of the original image.
  • the image tag of the original image is obtained by recognizing the image content of the original image, so as to obtain at least one special effect component matching the image tag from the preset special effect component set based on the image tag, so as to combine to form at least one special effect template.
  • At least one special effect component whose special effect label matches the video label may be selected from the special effect component set according to the weight of the special effect label of the special effect component relative to the image label to perform the combination of the special effect template. It should be mentioned that there may be some special effect components in the special effect component set that are not suitable for image special effect generation, such as background music components. Therefore, the weight of the special effect label of these special effect components relative to the image label should be lower.
  • the combination of special effect templates can be to randomly combine the special effect components matching the image tags according to different special effect types, or according to the order of the matching degree of the image tags of the special effect components of different special effect types, the different special effect types are sorted the same
  • the special effect components are combined to form a special effect template, thereby obtaining at least one special effect template.
  • the display duration of the original image to be generated for special effects can also be configured as a set duration. For example, if the display duration of the original image is configured to be 2 seconds, a video generated based on the original image can be obtained.
  • the video processing method under implementation generates a matching special effect template for this video, and generates a video special effect in this video according to the selected special effect template.
  • the multiple original images can still be combined to form a video, and a matching special effect template can be generated for the video based on the video processing method described in the foregoing embodiment.
  • the display duration of each original image in the video can be configured to be a fixed duration or any duration, which is not limited in this embodiment.
  • the recognition of the video content is the content recognition of at least one original image.
  • the generated special effect template that matches the video content may contain specific special effect components, such as a special effect component used to describe transition special effects.
  • the relative position of the transition component displayed in the video is The display position between adjacent original images. For example, a video is composed of 4 original images. The display duration of each original image is 2000ms, and the total display duration of the video is 8000ms. The relative position of the transition component displayed in the video includes the 2000th, 4000th, and 6000th of the video. . The display duration of the transition component can be preset.
  • the transition special effect component can also be used as a common special effect component, that is, similar to the other special effect components in the foregoing embodiments, it is obtained through the matching operation between the video tag and the special effect tag.
  • the embodiment is not limited. Based on the combination of original images to form a video, there is a greater demand for transition effects. For example, adding transition effects between different original images can greatly reduce the visual difference caused by image switching. Therefore, the special effect label of the transition effect component is relatively video. The weight of the label should be greater.
  • the relative position of the transition special effect component displayed in the video is still related to the position where the original image is switched and displayed in the video.
  • one or more original images for which special effects are to be generated are formed into a video, and the special effect generation operation performed on the image is converted into the special effect generation operation performed on the video, so that the special effect components applicable to the video are applicable to the video at the same time.
  • Special effect processing for the image, so the special effect template corresponding to the original image can contain richer special effect content, and the user experience can be greatly improved.
  • Fig. 13 is a block diagram showing a multimedia processing device according to an exemplary embodiment.
  • the multimedia processing device includes an original multimedia acquisition module 510, a special effect template acquisition module 530, and a multimedia special effect generation module 550.
  • the original multimedia acquisition module 510 is used to acquire the original multimedia for which the multimedia special effects are to be generated.
  • the special effect template acquisition module 530 is configured to identify the media content of the original multimedia and obtain at least one special effect template that matches the media content of the original multimedia.
  • the special effect template contains at least one special effect component, and the special effect component is used to describe the multimedia special effect.
  • the multimedia special effect generating module 550 is configured to generate a multimedia special effect described by the target special effect component in the original multimedia according to the target special effect component contained in the selected special effect template. It should be noted that multimedia includes videos and images.
  • the special effect template acquisition module 530 includes a video tag acquisition unit, a special effect component acquisition unit, and a special effect component matching unit.
  • the video tag obtaining unit is used for recognizing the media content of the original multimedia, and obtaining a multimedia tag corresponding to the media content of the original multimedia.
  • the special effect component acquiring unit is configured to acquire at least one special effect component matching the multimedia tag from the preset special effect component set according to the multimedia tag.
  • the special effect component matching unit is used for generating at least one special effect template according to at least one special effect component matching the multimedia tag.
  • the original multimedia includes an original video;
  • the multimedia tag acquisition unit includes a video image interception subunit and a video image recognition subunit.
  • the video image interception subunit is used to intercept at least one frame of video image from the original video according to the video duration of the original video.
  • the video image recognition subunit is used to perform content recognition on at least one frame of video image to obtain a content label of at least one frame of video image, and use the content label of at least one frame of video image as a video label corresponding to the video content of the original video.
  • the special effect component obtaining unit includes a weight determination subunit and a weight matching subunit.
  • the weight determination subunit is used to determine the weight of the special effect label of each special effect component in the special effect component set relative to the multimedia label according to a preset label weight determination rule.
  • the weight matching subunit is used to select at least one special effect component whose special effect label matches the multimedia label from the special effect component set according to the weight of the special effect label of each special effect component relative to the multimedia label.
  • the weight matching subunit is used to use a special effect component with a weight greater than a preset weight threshold in the special effect component set as a special effect component matching the multimedia tag; or determine the special effect according to the special effect tag of each special effect component Special effect components belonging to the same special effect type in the component set, and according to the order of the weight of the special effect label of each special effect component relative to the multimedia label, select the special effect components from the special effect components under each special effect type, and select each type
  • the number of special effect components under is the same as the number of preset special effect templates.
  • the special effect component matching unit is configured to randomly combine special effect components matching the multimedia tags according to different special effect types to obtain at least one special effect template;
  • the matching degree of the tags is sorted, and special effect components of the same sort under different special effect types are combined to form a special effect template, and at least one special effect template is obtained.
  • the video special effect generation module 550 includes a special effect parameter analysis unit and a special effect content generation unit.
  • the special effect parameter analysis unit is used to analyze the special effect parameters of each special effect component contained in the selected special effect template.
  • the special effect parameters include time parameters, and the time parameters are used to describe the display of the special effect components in the original video. Relative position and display duration.
  • the special effect content generating unit is configured to generate the video special effect content corresponding to each special effect component on the relative position of the original video according to the time parameter of each special effect component, and make the video special effect content continue to be displayed for the display duration.
  • the multimedia processing device further includes a background music selection module, the background music selection module is used to select the original background music from the preset background music set according to the recognition result of the video content recognition of the original video
  • the background music that matches the video content of the video, and the background music is integrated into the special effects video.
  • the original video includes at least two video clips
  • the special effect template obtaining module 530 includes a video clip identifying unit and a clip template obtaining unit.
  • the video segment identification unit is used to identify the video content of each video segment respectively.
  • the segment template obtaining unit is configured to obtain a special effect template that matches the video content of each video segment according to the video content of each video segment obtained by the identification.
  • the video processing device further includes a special effect component invocation module and a special effect component update module.
  • the special effect component retrieval module is used to retrieve various special effect components contained in the special effect multimedia according to the special effect editing instructions.
  • the special effect multimedia is formed by the combination of the original multimedia and the multimedia special effects described by the target special effect component.
  • the special effect component update module is used to update various special effect components included in the special effect multimedia according to the component update instruction.
  • Fig. 14 is a block diagram showing a multimedia processing device according to another exemplary embodiment.
  • the multimedia processing apparatus includes a second original multimedia acquisition module 610, a second special effect template acquisition module 630, and a special effect template sending module 650.
  • the second original multimedia acquisition module 610 is used to acquire the original multimedia for which the multimedia special effect is to be generated.
  • the second special effect template acquisition module 630 is configured to identify the media content of the original multimedia to obtain at least one special effect template matching the media content of the original multimedia.
  • the special effect template contains at least one special effect component, and the special effect component is used to describe the multimedia special effect.
  • the special effect template sending module 650 is configured to send the special effect template to the designated device, so that the designated device generates the multimedia special effect described by the special effect component in the original multimedia according to the target special effect component contained in the selected special effect template.
  • Fig. 15 is a block diagram showing a multimedia processing device according to another exemplary embodiment.
  • the multimedia processing device includes an original multimedia display module 710, a special effect template display module 730, a template selection detection module 750, and a multimedia special effect presentation module 770.
  • the original multimedia display module 710 is used for displaying original multimedia for which video special effects are to be generated.
  • the special effect template display module 730 is configured to display at least one special effect template that matches the media content of the original multimedia.
  • the special effect template is generated according to the special effect component that matches the media content of the original multimedia, and the special effect component is used to describe the multimedia special effect.
  • the template selection detection module 750 is configured to detect a target special effect template selected from at least one special effect template, and the target special effect template includes a target special effect component.
  • the multimedia special effect presentation module 770 is used to present the multimedia special effects described by the target special effect component in the displayed original multimedia.
  • the multimedia includes videos and images.
  • this application also provides a multimedia processing device, including: an original image acquisition module for acquiring the original image for which special effects are to be generated; a template acquisition module for recognizing the image content of the original image and acquiring the At least one special effect template that matches the image content of the original image.
  • the special effect template contains at least one special effect component.
  • the special effect component is used to describe the image special effect;
  • the image special effect described by the target special effect component is generated in the original image.
  • An embodiment of the present application also provides an electronic device, including a processor and a memory, wherein computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the processor, the aforementioned video processing method or Image processing method.
  • Fig. 16 is a schematic diagram showing the structure of an electronic device according to an exemplary embodiment.
  • the electronic device is only an example adapted to this application, and cannot be considered as providing any restriction on the scope of use of this application.
  • the electronic device also cannot be interpreted as being dependent on or having one or more components in the exemplary electronic device shown in FIG. 16.
  • the electronic device includes a processing component 801, a memory 802, a power supply component 803, a multimedia component 804, an audio component 805, a sensor component 807, and a communication component 808.
  • a processing component 801 a memory 802, a power supply component 803, a multimedia component 804, an audio component 805, a sensor component 807, and a communication component 808.
  • the electronic device can add other components or reduce some components according to its own functional requirements, which is not limited in this embodiment.
  • the processing component 801 generally controls the overall operations of the electronic device, such as operations associated with display, data communication, and log data processing.
  • the processing component 801 may include one or more processors 809 to execute instructions to complete all or part of the steps of the foregoing operations.
  • the processing component 801 may include one or more modules to facilitate the interaction between the processing component 801 and other components.
  • the processing component 801 may include a multimedia module to facilitate the interaction between the multimedia component 804 and the processing component 801.
  • the memory 802 is configured to store various types of data to support operations on the electronic device, and examples of these data include instructions for any application or method to operate on the electronic device.
  • One or more modules are stored in the memory 802, and the one or more modules are configured to be executed by the one or more processors 809 to complete all of the video processing methods or image processing methods described in the foregoing embodiments. Or part of the steps.
  • the power supply component 803 provides power for various components of the electronic device.
  • the power supply component 803 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for electronic devices.
  • the multimedia component 804 includes a screen that provides an output interface between the electronic device and the user.
  • the screen may include TP (Touch Panel, touch panel) and LCD (Liquid Crystal Display, liquid crystal display). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touch, sliding, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure related to the touch or slide operation.
  • the audio component 805 is configured to output and/or input audio signals.
  • the audio component 805 includes a microphone, and when the electronic device is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal.
  • the audio component 805 further includes a speaker for outputting audio signals.
  • the sensor component 807 includes one or more sensors for providing various aspects of state evaluation for the electronic device.
  • the sensor component 807 can detect the on/off state of the electronic device, and can also detect the temperature change of the electronic device.
  • the communication component 808 is configured to facilitate wired or wireless communication between the electronic device and other devices.
  • the electronic device can access a wireless network based on a communication standard, such as Wi-Fi (Wireless-Fidelity, wireless network).
  • Wi-Fi Wireless-Fidelity, wireless network
  • FIG. 16 is only for illustration, and the electronic device may include more or fewer components than those shown in FIG. 16, or have components different from those shown in FIG. 16.
  • Each component shown in FIG. 16 can be implemented by hardware, software, or a combination thereof.
  • Another aspect of the present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the video processing method or the image processing method as described above is implemented.
  • the computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist alone without being assembled into the electronic device.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Human Computer Interaction (AREA)
  • Television Signal Processing For Recording (AREA)

Abstract

本申请的实施例揭示了一种多媒体处理方法、装置、电子设备、计算机可读存储介质。该多媒体处理方法包括: 获取待生成多媒体特效的原始多媒体; 对所述原始多媒体进行媒体内容识别,并获得与所述原始多媒体的媒体内容相匹配的至少一个特效模板,所述特效模板中含有至少一个特效组件,所述特效组件用于描述多媒体特效; 根据选中的特效模板中含有的目标特效组件,在所述原始多媒体中生成所述目标特效组件描述的多媒体特效。

Description

多媒体处理方法、装置、电子设备、存储介质
本申请要求于2020年4月2日提交中国专利局、申请号为202010255390.2、名称为“视频及图像处理方法、装置、电子设备、存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及图像应用技术领域,具体涉及一种多媒体处理方法和装置,以及一种电子设备和一种计算机可读存储介质。
背景
随着互联网技术的迅猛发展,各类视频应用程序层出不穷。这些视频应用程序通常具有特效添加功能,通过在用户视频中生成视频特效,以为用户提供更佳的用户体验。但是,如何提升视频特效生成过程中的便捷性是有待解决的技术问题。
技术内容
本申请的实施例基于多个方面提供了多媒体处理方法和装置,以及一种电子设备和一种计算机可读存储介质。
其中,本申请的实施例采用的技术方案为:
一种多媒体处理方法,该方法包括:获取待生成多媒体特效的原始多媒体;对所述原始多媒体进行多媒体内容识别,并获得与所述原始多媒体的多媒体内容相匹配的至少一个特效模板,所述特效模板中含有至少一个特效组件,所述特效组件用于描述多媒体特效;根据选中的特效模板中含有的目标特效组件,在所述原始多媒体中生成所述目标特效组件描述的多媒体特效。
基于本申请的另一方面,还提供了一种多媒体处理方法,该方法包括:获取待生成多媒体特效的原始多媒体;对所述原始多媒体进行媒体内容识别,获得与所述原始多媒体的媒体内容相匹配的至少一个特效模板,所述特效模板中含有至少一个特效组件,所述特效组件用于描述多媒体特效;将所述特效模板发送至指定设备,使得所述指定设备根据选中的特效模 板中含有的目标特效组件,在所述原始多媒体中生成所述特效组件描述的多媒体特效。
基于本申请的另一方面,还提供了一种视频处理方法,该方法包括:显示待生成多媒体特效的原始多媒体;显示与所述原始多媒体的多媒体内容相匹配的至少一个特效模板,所述特效模板是根据与所述原始多媒体的媒体内容相匹配的特效组件生成的,所述特效组件用于描述多媒体特效;检测从所述至少一个特效模板中选取的目标特效模板,所述目标特效模板包含有目标特效组件;在显示的所述原始多媒体中呈现所述目标特效组件所描述的多媒体特效。
一种视频处理装置,包括:原始多媒体获取模块,用于获取待生成多媒体特效的原始多媒体;特效模板获取模块,用于对所述原始多媒体进行媒体内容识别,并获得与所述原始多媒体的媒体内容相匹配的至少一个特效模板,所述特效模板中含有至少一个特效组件,所述特效组件用于描述多媒体特效;多媒体特效生成模块,用于根据选中的特效模板中含有的目标特效组件,在所述原始多媒体中生成所述目标特效组件描述的多媒体特效。
一种多媒体处理装置,包括:第二原始多媒体获取模块,用于获取待生成多媒体特效的原始多媒体;第二特效模板获取模块,用于对所述原始多媒体进行媒体内容识别,获得与所述原始多媒体的媒体内容相匹配的至少一个特效模板,所述特效模板中含有至少一个特效组件,所述特效组件用于描述多媒体特效;特效模板发送模块,用于将所述特效模板发送至指定设备,使得所述指定设备根据选中的特效模板中含有的目标特效组件,在所述原始多媒体中生成所述特效组件描述的多媒体特效。
一种多媒体处理装置,包括:原始多媒体显示模块,用于显示待生成视频特效的原始多媒体;特效模板显示模块,用于显示与所述原始多媒体的媒体内容相匹配的至少一个特效模板,所述特效模板是根据与所述原始多媒体的媒体内容相匹配的特效组件生成的,所述特效组件用于描述多媒体特效;模板选中检测模块,用于检测从所述至少一个特效模板中选取的目标特效模板,所述目标特效模板包含有目标特效组件;多媒体特效呈现模块,用于在显示的所述原始多媒体中呈现所述目标特效组件所描述的多媒体特效。
一种电子设备,包括处理器及存储器,所述存储器上存储有计算机可读指令,所述计算机可读指令被所述处理器执行时实现如上所述的多媒体处理方法。
一种计算机可读存储介质,其上存储有计算机可读指令,当所述计算机可读指令被计算机的处理器执行时,使计算机执行如上所述的多媒体处理方法。
应当理解的是,以上的一般描述和后文的细节描述仅是示例性和解释性的,并不能限制本申请。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分,示出了符合本申请的实施例,并与说明书一起用于解释本申请的原理。显而易见地,下面描述中的附图仅仅是本申请的一些实施例,对于本领域普通技术者来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。在附图中:
图1是本申请涉及的实施环境的示意图;
图2A是根据一示例性实施例示出的一种多媒体处理方法的流程图;
图2B是根据一示例性实施例示出的一种多媒体处理方法的流程图;
图3是图2B所示实施例中步骤130在一个实施例的流程图;
图4是图3所示实施例中步骤133在一个实施例的流程图;
图5是图2B所示实施例中步骤150在一个实施例的流程图;
图6是一示例性实施例中示出的一种特效模板的示意图;
图7是图2B所示实施例中步骤130在另一个实施例的流程图;
图8是根据另一示例性实施例示出的一种多媒体处理方法的流程图;
图9是根据另一示例性实施例示出的一种多媒体处理方法的流程图;
图10是根据一示例性实施例示出的一种多媒体特效生成过程的示意图;
图11是根据另一示例性实施例示出的一种多媒体处理方法的流程图;
图12是根据一示例性实施例示出的一种终端设备的界面示意图;
图13是根据一示例性实施例示出的一种多媒体处理装置的框图;
图14是根据另一示例性实施例示出的一种多媒体处理装置的框图;
图15是根据另一示例性实施例示出的一种多媒体处理装置的框图;
图16是根据一示例性实施例示出的一种多媒体处理设备的结构示意图。
实施方式
这里将详细地对示例性实施例执行说明,其示例表示在附图中。下面的描述涉及附图时,除非另有表示,不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本申请相一致的所有实施方式。相反,它们仅是与如所附权利要求书中所详述的、本申请的一些方面相一致的装置和方法的例子。
请参阅图1,图1是本申请所涉及的一种实施环境的示意图,该实施环境包括终端100 和服务器200。
其中,终端100与服务器200之间预先建立有线或者无线的通信连接,使得终端100与服务器200之间可以进行数据传输。
终端100中运行有多媒体应用程序,例如视频应用程序,该视频应用程序具有用户交互界面,并通过该用户交互界面为用户提供视频特效的生成、发布等视频交互功能,服务器200则用于为多媒体应用程序的正常运行提供数据服务。
需要说明的是,在本实施环境中,终端100可以是智能手机、平板电脑、计算机、笔记本电脑等任意能够运行该多媒体应用程序的电子设备,终端100所运行多媒体应用程序可以是客户端应用程序或者网页应用程序,服务器200可以是一单独的服务器,也可以是由若干服务器构成的服务器集群,本处均不进行限定。
首先需要说明的是,在现有的多媒体特效生成方案中,需要用户从预先设置的特效模板中选择目标特效模板,并对待生成视频特效的用户视频进行编辑处理,使用户视频满足目标特效模板的要求,从而能够在编辑处理后的用户多媒体中生成目标特效目标所含有的视频特效。可见,现有的多媒体特效生成方案对于用户多媒体具有很大限制,基于预先设置的特效模板并不能方便地在用户多媒体中生成视频特效。
为解决此技术问题,本实施例中提出一种多媒体处理方法,在此多媒体处理方法中,针对用户多媒体生成多媒体特效的特效模板可以自适应于用户多媒体中包含的媒体内容,无需用户预先对用户多媒体进行编辑处理,完全消除了多媒体特效生成过程中对于用户多媒体的限制。
图2A是根据一示例性实施例示出的一种多媒体处理方法的流程图,该方法由电子设备执行,该电子设备可以是图1所示实施环境中的终端100,也可以是服务器200。
如图2A所示,在一示例性实施例中,该多媒体处理方法至少包括如下步骤:
步骤S101,获取待生成多媒体特效的原始多媒体。
需要说明的是,在本实施例中,原始多媒体即是指待生成多媒体特效的用户多媒体,包括视频和图像等该原始多媒体可以是用户触发摄像头拍摄获得的,也可以是用户从存储模块(例如相册)中选取获得,本处不进行限制。
步骤S102,对所述原始多媒体进行媒体内容识别,并获得与所述原始多媒体的媒体内容相匹配的至少一个特效模板,所述特效模板中含有至少一个特效组件,所述特效组件用于描述多媒体特效。
在一些实施例中,对所述原始多媒体进行媒体内容识别,并获得与所述原始多媒体的媒体内容相匹配的至少一个特效模板时,对所述原始多媒体进行媒体内容识别,获得与所述原始多媒体的媒体内容相对应的多媒体标签;根据所述多媒体标签,从预设的特效组件集合中获取与所述多媒体标签相匹配的至少一个特效组件;根据与所述多媒体标签相匹配的至少一 个特效组件,生成至少一个所述特效模板。
在一些实施例中,所述原始多媒体包括原始视频;在对所述原始多媒体进行媒体内容识别,获得与所述原始多媒体的媒体内容相对应的多媒体标签时,根据所述原始视频的视频时长,从所述原始视频中截取至少一帧视频图像;对所述至少一帧视频图像进行内容识别,得到所述至少一帧视频图像的内容标签,将所述至少一帧视频图像的内容标签作为与所述原始视频的视频内容相对应的视频标签。
在一些实施例中,根据选中的特效模板中含有的目标特效组件,在所述原始多媒体中生成所述目标特效组件描述的多媒体特效,包括:解析所述选中的特效模板含有的各个特效组件的特效参数,所述特效参数包括时间参数,所述时间参数用于描述所述特效组件在所述原始视频中进行显示的相对位置和显示时长;根据所述各个特效组件的时间参数,在所述原始视频的相对位置上生成各个特效组件对应的视频特效内容,并使所述视频特效内容持续显示所述显示时长。
在一些实施例中,所述原始视频包括至少两个视频片段;对所述原始多媒体进行媒体内容识别,获得与所述原始多媒体的媒体内容相匹配的至少一个特效模板,包括:分别对每个所述视频片段进行视频内容识别;根据识别得到的每个所述视频片段的视频内容,分别获取与每个所述视频片段的视频内容相匹配的特效模板。
在一些实施例中,根据所述多媒体标签,从预设的特效组件集合中获取与所述多媒体标签相匹配的至少一个特效组件,包括:根据预设的标签权重判定规则,确定所述特效组件集合中各个特效组件的特效标签相对所述多媒体标签的权重;根据所述各个特效组件的特效标签相对所述多媒体标签的权重,从所述特效组件集合中选取特效标签与所述多媒体标签相匹配的至少一个特效组件。
在一些实施例中,所述原始多媒体包括原始图像;所述根据预设的标签权重判定规则,确定所述特效组件集合中各个特效组件的特效标签相对所述多媒体标签的权重,包括:降低不适用于所述原始图像生成特效的特效组件的特效标签相对于所述原始多媒体标签的权重至预设值。
在一些实施例中,根据所述各个特效组件的特效标签相对所述多媒体标签的权重,从所述特效组件集合中选取特效标签与所述多媒体标签相匹配的至少一个特效组件,包括:将所述特效组件集合中权重大于预设权重阈值的特效组件作为与所述多媒体标签相匹配的特效组件,或者,根据所述各个特效组件的特效标签,确定所述特效组件集合中隶属于同一特效类型的特效组件,并按照所述各个特效组件的特效标签相对多媒体标签的权重由大到小的顺序,分别从各个特效类型下的特效组件中选取特效组件,所选取各个类型下的特效组件的数量与预设的特效模板的数量相同。
在一些实施例中,根据与所述多媒体标签相匹配的特效组件,生成至少一个所述特效模 板,包括:将与所述多媒体标签相匹配的特效组件按照不同的特效类型进行随机组合,获得至少一个所述特效模板,或者,根据不同特效类型的所述特效组件分别关于所述多媒体标签的匹配程度的排序,将所述不同特效类型下排序相同的特效组件组合形成一个特效模板,获得至少一个所述特效模板。
步骤S103,根据选中的特效模板中含有的目标特效组件,在所述原始多媒体中生成所述目标特效组件描述的多媒体特效。
在一些实施例中,在根据选中的特效模板中含有的目标特效组件,在所述原始多媒体中生成所述目标特效组件描述的多媒体特效之后,所述方法还包括;根据特效编辑指令,调取特效多媒体中包含的各项特效组件,所述特效多媒体由所述原始多媒体和所述目标特效组件描述的多媒体特效的组合形成;根据组件更新指令,对所述特效多媒体中包含的各项特效组件进行更新。
通过本申请实施例提供的多媒体处理方法,通过特效模板对原始多媒体进行特效处理,不需要用户从大量特效素材中选择添加特效,极大地提升了多媒体特效生成过程中的便捷性。
并且,待生成多媒体特效的原始多媒体所对应的特效模板是对待生成多媒体特效的原始多媒体进行媒体内容识别,并根据原始多媒体的媒体内容自动匹配获得的,因此特效模板是主动适应于待生成多媒体特效的原始多媒体,然后根据选中的特效模板中含有的目标特效组件,在原始视频中生成目标特效组件描述的多媒体特效,使得本申请在对原始多媒体生成多媒体特效之前无需对原始多媒体进行编辑处理,多媒体特效的生成效率得到了极大提升,并且在生成多媒体特效过程中对于原始多媒体没有任何限制。
在本申请的一些实施例中,所述多媒体包括视频和图像等。下面以多媒体为视频为例来描述本申请实施例所述的多媒体处理方法。图2B是根据一示例性实施例示出的一种多媒体处理方法的流程图,该方法可以适用于图1所示实施环境中的终端100,并由终端100中运行的多媒体应用程序具体执行。
如图2B所示,在一示例性实施例中,该多媒体(视频)处理方法至少包括如下步骤:
步骤110,获取待生成视频特效的原始视频。
步骤130,对原始视频进行视频内容识别,并获得与原始视频的视频内容相匹配的至少一个特效模板,该特效模板中含有至少一个特效组件,该特效组件用于描述视频特效。
其中,对原始视频进行的视频内容识别,是对原始视频中包含的视频对象进行识别的过程。原始视频中包含的视频对象可以是原始视频中出现的人物、物体或者其它对象,本实施例不进行限制。通过对原始视频进行的视频内容识别,即可以获得原始视频的视频内容。
特效模板是组合有至少一个特效组件的特效组件集合,这些特效组件是预先设置的,并且一个特效组件可以描述一种或者多种视频特效,因此特效模板可以理解为是视频特效集合。
在本实施例中,根据识别得到的原始视频的视频内容,获得与原始视频的视频内容相匹 配至少一个特效模板的过程,也即是根据原始视频的视频内容,自适应地为原始视频生成至少一个特效模板的过程,其中每个特效模板是由与原始视频的视频内容相匹配的至少一个特效组件组合形成。
步骤150,根据选中的特效模板中含有的目标特效组件,在原始视频中生成目标特效组件描述的视频特效。
其中,在所获得的与原始视频的视频内容相匹配的至少一个特效模板中,特效模板的选中操作可以是用户通过单击、双击、长按等交互方式所触发实现的,本实施例不进行限制。
针对选中的特效模板中含有的目标特效组件,根据各个目标特效组件所分别描述的视频特效,即可实现在原始视频中相应生成这些视频特效。
由此,本实施例中根据原始视频的视频内容,从预先设置的特效组件中选取与原始视频的视频内容相匹配的特效组件组合形成至少一个特效模板,这些特效模板可以自适应于原始视频,然后根据选中的特效模板,即可在原始视频中生成所选中的特效模板中含有的目标特效组件所描述的视频特效,整个视频特效生成过程中无需对原始视频进行编辑处理,避免了现有的视频特效生成方案中预先设置特效模板对于原始视频产生的限制。
并且本实施例以特效模板的形式为原始视频添加视频特效,省去了需要用户从大量的特效素材中进行特效素材挑选的过程,使得视频特效的生成过程更加地便捷化,采用本实施例的方法能够快速地在原始视频中生成高质量的视频特效。
图3是图2B所示实施例中步骤130在一个实施例的流程图。如图3所示,在一示例性实施例中,对原始视频进行视频内容识别,并获得与原始视频的视频内容相匹配的至少一个特效模板,至少包括如下步骤:
步骤131,对原始视频进行视频内容识别,获得与原始视频的视频内容相对应的视频标签。
如前所述,对原始视频进行的视频内容识别,是对原始视频中包含的视频对象进行识别的过程,因此与原始视频的视频内容相对应的视频标签即是原始视频中包含的视频对象所对应的标签。例如识别到原始视频中含有小孩的画面,则可以相应获取视频标签“萌娃”。
应当说明的是,由于原始视频通常含有不同类型的视频对象,因此对原始视频进行视频内容识别所获得的视频标签也应当是多个维度的。
在一个实施例中,视频标签可以是原始视频中的视频图像所含有的视频对象所对应的标签。示例性的,可根据原始视频的视频时长从原始视频中截取至少一帧视频图像例如若干帧,然后对截取的视频图像进行内容识别,得到这些视频图像的内容标签,该内容标签即标识了视频图像中含有的视频对象,从而将这些视频图像的内容标签作为与原始视频的视频内容相对应的视频标签。
需要说明的是,从原始视频中截取的视频图像的帧数可以根据具体需求相应设置。如果原始视频的视频时长较长,为使得获取的视频标签可以准确地标识原始视频的视频内容,则可以截取较多帧数的视频图像进行内容识别。同理,即使原始视频的视频时长较短,也可以截取较多帧数的视频图像进行内容,以使得所获得的视频标签能够准确地反映原始视频的视频内容。
步骤133,根据视频标签,从预设的特效组件集合中获取与视频标签相匹配的至少一个特效组件。
其中,特效组件集合中包含有所有预先设置的特效组件,这些特效组件分别描述不同的视频特效。根据原始视频的视频标签,从特效组件集合中选取于视频标签相匹配的至少一个特效组件,即可保证获取的特效组件可以和原始视频的视频内容相匹配。
由于不同原始视频所对应视频标签也应该不同,因此本实施例针对不同的视频内容,能够选取不同的特效组件进行视频特效生成,进而形成多样化的视频特效生成方案。
步骤135,根据与视频标签相匹配的特效组件,生成至少一个特效模板。
如前所述,由于步骤133中根据视频标签从特效组件集合中获取的至少一个特效组件与原始视频的视频内容相匹配,因此根据这些特效组件生成的特效模板也能与原始视频的视频内容相匹配。
由此,本实施例根据对原始视频进行视频内容识别所获得的视频标签,从预设的特效组件集合中获取与原始视频的视频标签相匹配的特效组件,并通过这些特效组件组合形成与原始视频的视频内容相匹配的至少一个特效模板,使得本实施例可以通过预先设置的特效素材组合生成丰富的特效模板,并且所生成的特效模板能够与原始视频的视频内容相适应,使得本实施例提供的视频特效生成方案具有极大的自适应性。
图4是图3所示实施例中步骤133在一个实施例的流程图。如图4所示,根据视频标签,从预设的特效组件集合中获取与视频标签相匹配的至少一个特效组件,至少包括如下步骤:
步骤1331,根据预设的标签权重判定规则,确定特效组件集合中各个特效组件的特效标签相对视频标签的权重。
首先需要说明,特效组件集合中各个特效组件的特效标签是用于标识特效组件的特效风格,例如特效标签可以是“欧美复古风”、“中国风”等,每个特效组件可以具有至少一个特效标签,不同的特效组件所具有的至少一个标签可以相同。
预设的标签权重判定规则是指预先设置的、且用于判断特效标签相对原始视频的视频标签的权重的规则。在一个实施例中,由于针对任意原始视频进行视频内容识别所获得的视频标签、以及特效组件对应的特效标签均是预先设置的,也即是说,所有的视频标签和特效标签均是已知的,由此可以预先判定各个特效标签分别相对每个视频标签的权重,并将所得权 重以及对应的判定条件进行关联存储,例如可以以列表形式进行存储,由此即可获得标签权重判定规则。
由此,根据标签权重判定规则,可以确定特效组件集合中各个特效组件的特效标签相对步骤131所识别获得的原始视频的视频标签的权重。特效标签相对视频标签的权重,反映了相应特效组件与原始视频的视频内容之间的匹配程度。
步骤1333,根据各个特效组件的特效标签相对视频标签的权重,从特效组件集合中选取特效标签与视频标签相匹配的至少一个特效组件。
如前所述,特效组件与原始视频的视频内容之间的匹配程度通过该特效组件的特效标签相对原始视频的视频标签的权重具体体现,因此根据特效组件集合中各个特效组件的特效标签相对原始视频的视频标签的权重,可以确定与原始视频的视频内容相匹配的至少一个特效组件,并由所选取的特效组件生成与原始视频的视频内容相匹配的至少一个特效模板。
在一个实施例中,可以将特效组件集合中权重大于预设权重阈值的特效组件作为与原始视频的视频标签相匹配的特效组件,以按照不同的特效类型对这些特效组件进行随机组合,从而获得至少一个与原始视频的视频内容相匹配的特效模板。
特效组件对应的特效类型用于表示特效组件所描述的视频特效的类型,例如特效组件可包括片头片尾、时间特效、贴纸、氛围、滤镜、转场等多种特效类型,并且不同的特效类型下可以含有多个特效组件。
还需要说明的是,一个特效组件可以对应一种视频特效,并且多个特效组件也可以组成一个特效组件,以使得一个特效组件能够对应多种视频特效。例如,片头片尾类型下的特效组件是由片头特效组件和片尾特效组件组成,定格特效组件和变色特效组件可以组成定点变色特效组件,使得该定点变色组件具有定格特效和变色特效。
单个特效组件至少包括三种特效参数,分别为类型参数、组件参数和时间参数。其中类型参数用于描述特效组件对应的特效类型,例如贴纸类型、滤镜类型等。组件参数用于描述具体的视频特效内容,根据组件参数可以绘制特效组件所描述的视频特效内容。对于包含由特效素材的特效组件,根据其组件参数即可绘制相应的特效素材;对于不包含特效素材的特效组件,例如时间特效,根据其组件参数即可具体绘制该时间特效。时间参数用于描述特效组件在原始视频中进行显示的相对位置和显示的时长,所述相对位置是特效组件在原始视频中进行显示时,在该原始视频中的时间上的位置。
由此,根据特效组件的类型参数,即可以确定特效组件对应的特效类型。通过将权重大于预设权重阈值的特效组件按照不同的特效类型进行随机组合,即可保证每个特效模板中含有不同特效类型的特效组件,从而确保通过每个特效模板在原始视频中生成丰富的视频特效。
在另一个实施例中,还可以根据各个特效组件的特效标签,确定特效组件集合中隶属于同一类型的特效组件,并按照各个特效组件的特效标签相对视频标签的权重由大到小的顺序, 分别从各个类型下的特效组件中选取特效组件,所选取各个类型下的特效组件的数量与预设的特效模板的数量相同。然后根据不同特效类型的特效组件分别关于视频标签的匹配程度的排序,将不同特效类型下排序相同的特效组件组合形成一个特效模板,由此获得至少一个特效模板。
对于与原始视频的视频标签相匹配的特效组件,将这些特效组件按照不同的特效类型进行分类,并针对隶属于同一特效类型下的特效组件,按照特效标签相对原始视频的视频标签的权重由大到小进行排序,然后根据预先设置有特效模板的数量,从不同特效类型下的特效组件中依次选取此数量的特效组件,即可将排序相同的特效组件组合形成一个特效模板。其中,预先设置的特效模板的数量对应于视频应用界面中所显示的特效模板的数量。
示例性的,如果假设预先设置的特效模板的数量为8,则可以选取片头片尾类型下的权重由大到小排序的特效组件A 1~A 8,滤镜类型下的权重由大到小排序的特效组件B 1~B 8,贴纸类型下的权重由大到小排序的特效组件C 1~C 8。通过将特效组件A 1、B 1和C 1组合形成一个特效模板,将特效组件A 2、B 2和C 2组合形成另一个特效模板,其它特效模板的组合方式同理,由此即可相应获得8个特效模板。
针对特效模板在视频应用界面中的显示,还可以按照特效模板中的特效组件对应的权重顺序进行排列,从而能够将特效模板按照与原始视频的视频内容之间的匹配程度进行由大到小地排序,便于实现特效模板的选中。
需要说明的是,以上两种实施例仅是对与原始视频的视频内容相匹配的特效组件的选取方式的示例,在实际应用中,可以根据实际的需求对特效组件的选取方式进行设置。
由此,以上通过对特效组件进行标签化,并根据特效组件的特效标签相对原始视频的视频标签的权重来反映特效组件与原始视频的视频内容之间的匹配程度,保证了所获得的特效模板与原始视频的视频内容是相匹配的。
图5是图2B所示实施例中步骤150在一个实施例的流程图。如图5所示,在一示例性实施例中,根据选中的特效模板中含有的目标特效组件,在原始视频中生成目标特效组件描述的视频特效,以获得原始视频对应的特效视频,至少包括如下步骤:
步骤151,解析选中的特效模板含有的各个特效组件的特效参数,特效参数包括时间参数。
如前所述的,特效组件的特效参数至少包括类型参数、组件参数和时间参数,时间参数用于描述特效组件所描述的视频特效在原始视频中进行显示的相对位置和显示时长。
示例性的,时间参数包括特效组件相对原始视频显示的起始位置(以下表示为startOffset)、特效组件相对原始视频显示的结束位置(以下表示为endOffse)和持续时长(以下表示为duration)。
图6是一示例性实施例中示出的一种选中的特效模板的示意图。如图6所示,在该示例性的特效模板中,片头片尾组件包含片头特效和片尾特效,片头特效从原始视频的第0ms的位置开始显示,显示时长为2000ms,片尾特效从原始视频的第8000ms的位置开始显示,显示时长为2000ms。氛围组件包含的光斑氛围特效从原始视频的第2000ms开始显示,显示时长为8000ms。应当理解,特效组件相对原始视频显示的结束位置可以由起始位置和持续时长共同得出。
图6所示的片头特效可以详细描述为:{"effectType":"Pag","startOffset":0,"duration":2000,"parameter":{"filePath":"片头.pag","type":"filter"}};片尾特效详细描述为:{"effectType":"Pag","endOffset":0,"duration":2000,"parameter":{"filePath":"片尾.pag","type":"filter"}};光斑氛围特效可以详细描述为:{"effectType":"Pag","startOffset":2000,"endOffset":0,"parameter":{"filePath":"氛围.pag","type":"filter"}}。
步骤153,根据各个特效组件的时间参数,在原始视频的相对位置上生成各个特效组件对应的视频特效内容,并使视频特效内容持续显示时间所包含的显示时长。
根据解析选中的特效模板含有的各个特效组件所得到的时间参数,即可根据时间参数所描述的相对位置和显示时长,在原始视频的相对位置上生成各个特效组件对应的视频特效内容,并使所生成的视频特效内容持续显示时间参数所包含的显示时长,从而将选中的特效模板所对应的多种视频特效显示在原始视频中,实现原始视频中视频特效的生成,获得原始视频对应的特效视频。
如图6所示,所获得的特效视频由原始视频以及选中的特效模板中含有的各个特效组件描述的视频特效组合形成。
由此,本实施例基于特效组件所含有的时间参数,将选中的特效模板所对应的视频特效自动生成在原始视频中,对用户来说,实现视频特效生成的过程十分简便,并不需要用户进行额外的操作。
在另一示例性的实施例中,上述视频处理方法还包括如下步骤:
根据对原始视频进行视频内容识别的识别结果,从预设的背景音乐集合中选取与原始视频的视频内容相匹配的背景音乐,并将背景音乐融合至特效视频中。
在本实施例中,预先对背景音乐集合中的各个背景音乐进行标签化处理,根据背景音乐的曲风等维度,为各个背景音乐设置有音乐标签,例如可设置“儿歌”、“可爱”、“萌趣”等音乐标签。
根据对原始视频进行视频内容识别所获得的视频标签,即可从预设的背景音乐集合中选取音乐标签与视频标签相匹配的背景音乐,例如选取匹配程度最高的音乐标签对应的背景音乐,并将所选取的背景音乐融合至原始视频中,以使获得的特效视频中含有背景音乐。
因此在本实施例中,将背景音乐与特效模板进行区分,根据原始视频的视频内容确定与 相匹配的背景音乐后,针对与原始视频的视频内容相匹配的至少一个特效模板,无论选中任意一个特效模板,最终所获得的特效视频中的背景音乐将保持一致。
在另外的实施例中,背景音乐可作为一种特效类型,背景音乐组件可与其它类型的特效组件组合形成特效模板。具体来说,背景音乐集合为特效组件集合中包含的背景音乐组件集合,步骤133中根据原始视频的视频标签,从特效组件集合中获取与原始视频的视频标签相匹配的特效组件包括背景音乐组件和其它特效组件,根据所获得的各个背景音乐组件的音乐标签相对视频标签的权重,以及各个特效组件的特效标签相对视频标签的权重,形成与原始视频的视频内容相匹配的至少一个特效模板。
由此在本实施例中,至少一个与原始视频相匹配的特效模板中含有的背景音乐可以不同,从而进一步增加了特效模板的多样性,以为用户提供更加丰富的视频特效体验。
在另一示例性的实施例中,待生成视频特效的原始视频包括至少两个视频片段,以进一步提升视频特效的。在现有的视频特效生成方案中,需预先为每个视频片段分别选定特效模板,然后对每个视频片段进行编辑处理,使每个视频片段分别满足对应的特效模板的要求。
可以看出,在对至少两个视频片段生成视频特效的情况下,需要用户进行更多的额外操作,使得视频特效生成的过程更加繁杂,本实施例即是针对此情况提出解决方案。如图7所示,在本实施例中,对原始视频进行视频内容识别,获得与原始视频的视频内容相匹配的至少一个特效模板,至少包括以下步骤:
步骤132,分别对每个视频片段进行内容识别;
步骤134,根据识别到的每个视频片段的视频内容,分别获取与每个视频片段的视频内容相匹配的特效模板。
与前述实施例描述的内容相同,本实施例对每个视频片段进行内容识别的过程,即是对每个视频片段中包含的视频对象进行识别的过程,能够获得与每个视频片段的视频内容相匹配的视频标签。
根据各个视频片段分别对应的视频标签,即可按照前述实施例描述的方法分别获取与各个视频片段的视频内容相匹配的特效模板。在具体执行视频特效的生成过程时,分别为每个视频片段选中的特效模板,进而根据选中的特效模板中含有的目标特效组件,在每个视频片段中生成目标特效组件描述的视频特效。
由此,在多个视频片段的情况下,本实施例提供的方法根据不同视频片段的视频内容,自适应地为不同的视频片段分别获取特效模板,用户只需为不同的视频片段选择待生成的视频特效的特效模板,即可使得不同的视频片段中能够生成与其视频内容相匹配的视频特效,整个过程仍无需用户分别对每个视频片段进行编辑处理,因此对于待生成视频特效的多个视频片段没有任何限制。
在另一示例性实施例中,如图8所示,在步骤150之后,上述多媒体(视频)处理方法 还包括如下步骤:
步骤210,根据特效编辑指令,调取特效视频中包含的各项特效组件,特效视频由原始视频和目标特效组件描述的视频特效的组合形成。
其中,在根据选中的特效模板为原始视频生成视频特效,获得原始视频对应的特效视频之后,本实施例还提供针对特效视频的编辑操作,以进一步提升用户体验。
特效编辑指令用于指示对特效视频含有的视频特效进行编辑处理,因此需要调取特效视频中包含的各项特效组件。应当说明的是,特效视频中包含的特效组件即是步骤150中所选中的特效模板中含有的目标特效组件,特效编辑指令可以是检测视频应用界面中的指定按钮被触发所获得的。
步骤230,根据组件更新指令,对特效视频中包含的各项特效组件进行更新。
组件更新指令用于指示对特效视频中包含的特效组件进行更新,其中特效组件的更新操作包括但不限于特效组件的新增、删除和更换。组件更新指令也可以是检测视频应用界面中的相应按钮被触发所获得的。
示例性的,假设特效视频中含有特效组件A 1、B 1和C 1,如果组件更新指令指示将滤镜类型下的特效组件B 1更换为滤镜类型下的特效组件B 1,则根据组件更新指令的指示执行特效组件的替换。
应当理解,在原始视频对应的特效视频中,特效组件的更新则表示原始视频中生成的视频特效也相应进行了更新。
图9是根据另一示例性实施例示出的一种多媒体处理方法的流程图,该多媒体处理方法可以应用于图1所示实施环境中的服务器200。以该多媒体为视频为例,描述该多媒体处理方法,如图9所示,在一示例性实施例中,该多媒体(视频)处理方法至少包括如下步骤:
步骤310,获取待生成视频特效的原始视频;
步骤330,对原始视频进行视频内容识别,获得与原始视频的视频内容相匹配的至少一个特效模板,特效模板中含有至少一个特效组件,特效组件用于描述视频特效;
步骤350,将特效模板发送至指定设备,使得指定设备根据选中的特效模板中含有的目标特效组件,在原始视频中生成特效组件描述的视频特效。
在本实施例中,指定设备是运行视频应用程序的电子设备,例如是图1所示实施环境中的终端100,指定设备用于根据选中的特效模板在原始视频中生成相应的视频特效。
待生成视频特效的原始内容是指定设备所发送的,指定设备通过将原始视频发送至服务器,以从服务器中获取与原始视频的视频内容相匹配的至少一个特效模板。
需要说明的是,对原始视频进行视频内容识别,获得与原始视频的视频内容相匹配的特效模板的过程请参见前述实施例中描述的特效模板获取的相应内容,本实施例不进行赘述。
服务器获取与原始视频的视频内容相匹配的特效模板后,即将获取的特效模板发送至指 定设备,使得指定设备根据选中的特效模板在原始视频中生成相应的视频特效。
如图10所示,指定设备将原始视频发送至服务器,服务器通过对原始视频进行视频内容识别,获得原始视频对应的视频标签,然后根据背景音乐的音乐标签选取与原始视频相匹配的背景音乐,根据其它特效组件的特效标签选取与原始视频相匹配的特效组件,并由选取的背景音乐和其它类型的特效组件组合形成与原始视频相匹配的特效模板,然后将特效模板下发至指定设备。指定设备通过选中的解析特效模板,进而将特效模板中含有的视频特效生成至原始视频中。
图11是根据另一示例性实施例示出的一种多媒体处理方法的流程图,该方法适用于图1所示实施环境中的终端100和图10所示实施例中的指定设备。如图11所示,在一示例性实施例中,该多媒体处理方法至少包括如下步骤:
步骤410,显示待生成视频特效的原始多媒体;
需要说明的是,本申请实施例中的多媒体可以包括视频和图像等。
步骤430,显示与原始多媒体的媒体内容相匹配的至少一个特效模板,特效模板是根据与原始多媒体的媒体内容相匹配的特效组件生成的,特效组件用于描述多媒体特效;
步骤450,检测从至少一个特效模板中选取的目标特效模板,目标特效模板包含有目标特效组件;
步骤470,在显示的原始多媒体中呈现目标特效组件所描述的多媒体特效。
在本实施例中,针对待生成视频特效的原始多媒体进行显示,并显示与原始多媒体的媒体内容相匹配的至少一个特效模板,当检测到从至少一个特效模板中选中目标特效模板后,在显示的原始多媒体中呈现目标特效模板含有的目标特效组件所描述的多媒体特效。
由此,本实施例通过对原始多媒体生成多媒体特效的过程进行可视化显示,可以得出在多媒体特效的生成过程中,用户只需执行原始多媒体的选取操作以及特效模板的选取操作,而无需执行原始多媒体的编辑处理等额外操作,使得本实施例提供的多媒体特效生成方案具有极佳的用户体验。
为便于理解本实施例揭示的多媒体处理方法,下面将以一个对视频进行处理的具体应用场景为示例对此多媒体处理方法进行详细描述。
在该示例性的应用场景中,该多媒体(视频)处理方法应用于运行有视频应用程序的终端设备,该终端设备具体可以是图1所示实施环境中的终端100,或者是图10所示实施例中的指定设备,图12为该终端设备的界面示意图。
如图12所示,在用户使用终端设备的摄像头拍摄得到待生成视频特效的原始视频,或者从终端设备的相册中选取待生成视频特效的原始视频之后,终端设备相应显示该原始视频。
当检测到设备界面中的“一键出片”按钮被触发时,终端设备显示与原始视频的视频内容相匹配的至少一个特效模板。如图12所示,终端设备以特效模板列表的形式显示于原始 视频相匹配的特效模板。
其中,特效模板是通过对原始视频的视频内容进行识别,获得原始视频对应的视频标签,并根据视频标签选取与原始视频的视频内容相匹配的特效组件,由这些特效组件组合形成的。还应当理解,对于用户选取的不同的原始视频,特效模板列表中含有的特效模板也不同。
如果用户选中特效模板列表中的其中一个特效模板,则视为检测到选中的目标特效模板,进而在显示的原始视频中呈现目标特效模板所含有的目标特效组件描述的视频特效,即显示所形成的特效视频。如图12所示,如果检测到选中了特效模板4,原始视频中相应显示特效模板4所含有的视频特效,即实现在原始视频中预览所选中的特效模板。当用户确定选中目标特效模板后,则显示所获得的特效视频,例如图12所显示的特效视频中含有相应显示的文字贴纸。
在获得特效视频之后,用户还可以通过触发界面中显示“背景音乐”、“调整素材”、“滤镜”等按钮,对特效视频中的视频特效执行更新操作,最终获得用户满意的特效视频。然后,用户点击界面中显示的“做好了”按钮,即可将最终获得的特效视频进行本地存储,或者将特效视频上传至服务器进行存储,或者将特效视频发布至互联网,本处不进行限制。
因此在实际应用过程中,用户选择一段或者多段用户视频后,通过本申请实施例提供的方法,可以自适应地为用户视频匹配至少一个特效模板,每个特效模板具有各自的特效风格并且包含至少一个种视频特效,使得最终获得的特效视频具有多样性,并且对于用户视频没有任何限制。
如前所示,本申请实施例中多媒体包括视频和图像等。下面以多媒体为图像为例,描述以上实施例提供的多媒体处理方法应用至图像特效生成过程,因此基于本申请的另一方面,还提供了一种多媒体处理方法,以方便地针对用户图像进行特效生成。该多媒体(图像)处理方法也可以适用于图1所示实施环境中的终端100,并由终端100中运行的多媒体应用程序具体执行。
在一示例性的实施例中,该多媒体(图像)处理方法至少包括如下步骤:
获取待生成特效的原始图像;
对原始图像进行图像内容识别,并获取与原始图像的图像内容相匹配的至少一个特效模板,特效模板中含有至少一个特效组件,特效组件用于描述图像特效;
根据选中的特效模板中含有的目标特效组件,在原始图像中生成目标特效组件描述的图像特效。
首先需要说明的是,与前述原始视频的获取方式相似,原始图像可以是用户触发摄像头拍摄获得的,或者是用户从存储模块(例如相册)中选取获得的,本处不进行限制。
对原始图像进行图像内容识别的过程,也即是对原始图像中包含的人物、物体或者其它对象进行识别的过程,本处也不进行限制。
获取与原始图像的图像内容相匹配的至少一个特效模板的过程,也即是根据原始图像的图像内容自适应地为原始图像生成至少一个特效模板的内容,其中的每个特效模板是均由与原始图像的图像内容相匹配的至少一个特效组件组合形成的。
用户从这些与原始图像的图像内容相匹配的特效模板中选中一个心仪的特效模板,即可在原始图像中生成所选中的特效模板所含有的各个目标特效组件分别描述的图像特效。
由此,以特效模板的形式为原始图像添加图像特效,无需用户从大量的特效素材中进行特效素材挑选,使得图像特效的生成过程更加地便捷化,并且本实施例生成的特效模板均是与原始图像的图像内容相匹配的,因此采用本实施例的方法能够快速地在原始图像中生成高质量的视频特效。
还需要说明的是,本实施例对于与原始图像的图像内容进行的特效模板匹配也可以是基于原始图像的图像标签所实现的。其中,原始图像的图像标签是通过对原始图像进行图像内容识别得到的,以基于图像标签,从预设的特效组件集合中获取与图像标签相匹配的至少一个特效组件,从而组合形成至少一个特效模板。
在一个实施例中,可以根据特效组件的特效标签相对图像标签的权重,从特效组件集合中选取特效标签与视频标签相匹配的至少一个特效组件,以进行特效模板的组合。需提及的是,特效组件集合可能存在某些特效组件不适用于图像特效生成,例如背景音乐组件,因此这些特效组件的特效标签相对图像标签的权重应当较低。
特效模板的组合方式可以是将与图像标签相匹配的特效组件按照不同的特效类型进行随机组合,或者根据不同特效类型的特效组件分别关于图像标签的匹配程度的排序,将不同特效类型下排序相同的特效组件组合形成一个特效模板,由此获得至少一个特效模板。
在根据选中的特效模板中含有的目标特效组件,在原始图像中生成目标特效组件描述的图像特效之后,也可以对特效图像中含有的各项特效组件进行更新。
需要说明的是,以上过程的具体实施细节可以参考前述实施例中对于视频特效生成过程的描述,本处不再进行赘述。
在另外的实施例中,还可以配置待生成特效的原始图像的显示时长为设定时长,例如配置原始图像的显示时长为2秒,则可获得基于原始图像生成的视频,然后即可按照前述实施中的视频处理方法对此视频生成相匹配的特效模板,并根据选中的特效模板在此视频中生成视频特效。
需要说明的是,在基于原始图像所生成的视频中,由于视频中的每帧图像均为原始图像,因此对视频内容进行的识别相当于是对原始图像进行的内容识别。
如果待生成特效的原始图像有多张,仍可以将多张原始图像组合形成一个视频,并基于前述实施例描述的视频处理方法为该视频生成相匹配的特效模板。其中,可配置每张原始图 像在视频中的显示时长为固定时长的或者任意时长,本实施例不进行限制。对视频内容进行的识别即是对至少一张原始图像的内容识别。
还需要说明的是,在生成的与视频内容相匹配的特效模板中,可以含有特定的特效组件,例如用于描述转场特效的特效组件,该转场组件在视频中进行显示的相对位置为相邻原始图像之间的显示位置。例如视频由4张原始图像组成,每张原始图像的显示时长为2000ms,视频的总显示时长为8000ms,转场组件在视频中进行显示的相对位置即包括视频的第2000ms、第4000ms和第6000ms。转场组件的显示时长可以是预设的。
在其它的实施例中,转场特效组件也可以作为一种普通的特效组件,即与前述实施例中的其它特效组件类似,通过视频标签与特效标签之间进行的匹配操作而获得的,本实施例不进行限制。基于由原始图像组合形成视频对于转场特效的需求较大,例如在不同原始图像之间添加转场特效之后能够极大地减少图像切换带来的视觉差异,因此转场特效组件的特效标签相对视频标签的权重应当较大。并且,转场特效组件在视频中进行显示的相对位置仍与视频中切换显示原始图像的位置有关。
由此,本实施例将待生成特效的一张或者多张原始图像形成视频,并将针对图像进行的特效生成操作转换为针对视频进行的特效生成操作,使得适用于视频的特效组件同时适用于针对图像进行的特效处理,因此原始图像对应的特效模板中能够包含更加丰富的特效内容,用户体验能够得到极大提升。
图13是根据一示例性实施例示出的一种多媒体处理装置的框图。如图13所示,该多媒体处理装置包括原始多媒体获取模块510、特效模板获取模块530和多媒体特效生成模块550。
原始多媒体获取模块510,用于获取待生成多媒体特效的原始多媒体。特效模板获取模块530用于对原始多媒体进行媒体内容识别,并获得与原始多媒体的媒体内容相匹配的至少一个特效模板,特效模板中含有至少一个特效组件,特效组件用于描述多媒体特效。多媒体特效生成模块550用于根据选中的特效模板中含有的目标特效组件,在原始多媒体中生成目标特效组件描述的多媒体特效。需要说明的是,多媒体包括视频和图像等。
在另一示例性实施例中,特效模板获取模块530包括视频标签获取单元、特效组件获取单元和特效组件匹配单元。视频标签获取单元用于对原始多媒体进行媒体内容识别,获得与原始多媒体的媒体内容相对应的多媒体标签。特效组件获取单元用于根据多媒体标签,从预设的特效组件集合中获取与多媒体标签相匹配的至少一个特效组件。特效组件匹配单元用于根据与多媒体标签相匹配的至少一个特效组件,生成至少一个特效模板。
在另一示例性实施例中,所述原始多媒体包括原始视频;多媒体标签获取单元包括视频图像截取子单元和视频图像识别子单元。视频图像截取子单元用于根据原始视频的视频时长,从原始视频中截取至少一帧视频图像。视频图像识别子单元用于对至少一帧视频图像进 行内容识别,得到至少一帧视频图像的内容标签,将至少一帧视频图像的内容标签作为与原始视频的视频内容相对应的视频标签。
在另一示例性实施例中,特效组件获取单元包括权重确定子单元和权重匹配子单元。权重确定子单元用于根据预设的标签权重判定规则,确定特效组件集合中各个特效组件的特效标签相对多媒体标签的权重。权重匹配子单元用于根据各个特效组件的特效标签相对多媒体标签的权重,从特效组件集合中选取特效标签与多媒体标签相匹配的至少一个特效组件。
在另一示例性实施例中,权重匹配子单元用于将特效组件集合中权重大于预设权重阈值的特效组件作为与多媒体标签相匹配的特效组件;或者根据各个特效组件的特效标签,确定特效组件集合中隶属于同一特效类型的特效组件,并按照各个特效组件的特效标签相对多媒体标签的权重由大到小的顺序,分别从各个特效类型下的特效组件中选取特效组件,所选取各个类型下的特效组件的数量与预设的特效模板的数量相同。
在另一示例性实施例中,特效组件匹配单元用于将与多媒体标签相匹配的特效组件按照不同的特效类型进行随机组合,获得至少一个特效模板;或者根据不同特效类型的特效组件分别关于多媒体标签的匹配程度的排序,将不同特效类型下排序相同的特效组件组合形成一个特效模板,获得至少一个特效模板。
在另一示例性实施例中,视频特效生成模块550包括特效参数解析单元和特效内容生成单元。特效参数解析单元用于解析所述选中的特效模板含有的各个特效组件的特效参数,所述特效参数包括时间参数,所述时间参数用于描述所述特效组件在所述原始视频中进行显示的相对位置和显示时长。特效内容生成单元用于根据所述各个特效组件的时间参数,在所述原始视频的相对位置上生成各个特效组件对应的视频特效内容,并使所述视频特效内容持续显示所述显示时长。
在另一示例性实施例中,该多媒体处理装置还包括背景音乐选取模块,该背景音乐选取模块用于根据对原始视频进行视频内容识别的识别结果,从预设的背景音乐集合中选取与原始视频的视频内容相匹配的背景音乐,并将背景音乐融合至特效视频中。
在另一示例性实施例中,原始视频包括至少两个视频片段,特效模板获取模块530包括视频片段识别单元和片段模板获取单元。视频片段识别单元用于分别对每个视频片段进行视频内容识别。片段模板获取单元用于根据识别得到的每个视频片段的视频内容,分别获取与每个视频片段的视频内容相匹配的特效模板。
在另一示例性实施例中,该视频处理装置还包括特效组件调取模块和特效组件更新模块。特效组件调取模块用于根据特效编辑指令,调取特效多媒体中包含的各项特效组件,特效多媒体由原始多媒体和目标特效组件描述的多媒体特效的组合形成。特效组件更新模块用于根据组件更新指令,对特效多媒体中包含的各项特效组件进行更新。
图14是根据另一示例性实施例示出的一种多媒体处理装置的框图。如图14所示,该多 媒体处理装置包括第二原始多媒体获取模块610、第二特效模板获取模块630和特效模板发送模块650。
第二原始多媒体获取模块610用于获取待生成多媒体特效的原始多媒体。第二特效模板获取模块630用于对原始多媒体进行媒体内容识别,获得与原始多媒体的媒体内容相匹配的至少一个特效模板,特效模板中含有至少一个特效组件,特效组件用于描述多媒体特效。特效模板发送模块650用于将特效模板发送至指定设备,使得指定设备根据选中的特效模板中含有的目标特效组件,在原始多媒体中生成特效组件描述的多媒体特效。
图15是根据另一示例性实施例示出的一种多媒体处理装置的框图。如图15所示,该多媒体处理装置包括原始多媒体显示模块710、特效模板显示模块730、模板选中检测模块750和多媒体特效呈现模块770。
原始多媒体显示模块710用于显示待生成视频特效的原始多媒体。特效模板显示模块730用于显示与原始多媒体的媒体内容相匹配的至少一个特效模板,特效模板是根据与原始多媒体的媒体内容相匹配的特效组件生成的,特效组件用于描述多媒体特效。模板选中检测模块750用于检测从至少一个特效模板中选取的目标特效模板,目标特效模板包含有目标特效组件。多媒体特效呈现模块770用于在显示的原始多媒体中呈现目标特效组件所描述的多媒体特效。
如前所述,所述多媒体包括视频和图像等。当多媒体为图像时,本申请还提供一种多媒体处理装置,包括:原始图像获取模块,用于获取待生成特效的原始图像;模板获取模块,用于对原始图像进行图像内容识别,并获取与原始图像的图像内容相匹配的至少一个特效模板,特效模板中含有至少一个特效组件,特效组件用于描述图像特效;图像特效生成模块,用于根据选中的特效模板中含有的目标特效组件,在原始图像中生成目标特效组件描述的图像特效。
需要说明的是,上述实施例所提供的装置与上述实施例所提供的方法属于同一构思,其中各个模块和单元执行操作的具体方式已经在方法实施例中进行了详细描述,此处不再赘述。
本申请的实施例还提供了一种电子设备,包括处理器和存储器,其中,存储器上存储有计算机可读指令,该计算机可读指令被处理器执行时实现如前所述的视频处理方法或者图像处理方法。
图16是根据一示例性实施例示出的一种电子设备的结构示意图。
需要说明的是,该电子设备只是一个适配于本申请的示例,不能认为是提供了对本申请的使用范围的任何限制。该电子设备也不能解释为需要依赖于或者必须具有图16中示出的示例性的电子设备中的一个或者多个组件。
如图16所示,在一示例性实施例中,电子设备包括处理组件801、存储器802、电源组 件803、多媒体组件804、音频组件805、传感器组件807和通信组件808。其中,上述组件并不全是必须的,电子设备可以根据自身功能需求增加其他组件或减少某些组件,本实施例不作限定。
处理组件801通常控制电子设备的整体操作,诸如与显示、数据通信以及日志数据处理相关联的操作等。处理组件801可以包括一个或多个处理器809来执行指令,以完成上述操作的全部或部分步骤。此外,处理组件801可以包括一个或多个模块,便于处理组件801和其他组件之间的交互。例如,处理组件801可以包括多媒体模块,以方便多媒体组件804和处理组件801之间的交互。
存储器802被配置为存储各种类型的数据以支持在电子设备的操作,这些数据的示例包括用于在电子设备上操作的任何应用程序或方法的指令。存储器802中存储有一个或多个模块,该一个或多个模块被配置成由该一个或多个处理器809执行,以完成上述实施例中所描述的视频处理方法或者图像处理方法中的全部或者部分步骤。
电源组件803为电子设备的各种组件提供电力。电源组件803可以包括电源管理系统,一个或多个电源,及其他与为电子设备生成、管理和分配电力相关联的组件。
多媒体组件804包括在电子设备和用户之间的提供一个输出接口的屏幕。在一些实施例中,屏幕可以包括TP(Touch Panel,触摸面板)和LCD(Liquid Crystal Display,液晶显示器)。如果屏幕包括触摸面板,屏幕可以被实现为触摸屏,以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界,而且还检测与所述触摸或滑动操作相关的持续时间和压力。
音频组件805被配置为输出和/或输入音频信号。例如,音频组件805包括一个麦克风,当电子设备处于操作模式,如呼叫模式、记录模式和语音识别模式时,麦克风被配置为接收外部音频信号。在一些实施例中,音频组件805还包括一个扬声器,用于输出音频信号。
传感器组件807包括一个或多个传感器,用于为电子设备提供各个方面的状态评估。例如,传感器组件807可以检测到电子设备的打开/关闭状态,还可以检测电子设备的温度变化。
通信组件808被配置为便于电子设备和其他设备之间有线或无线方式的通信。电子设备可以接入基于通信标准的无线网络,例如Wi-Fi(Wireless-Fidelity,无线网络)。
可以理解,图16所示的结构仅为示意,该电子设备可以包括比图16中所示更多或更少的组件,或者具有与图16所示不同的组件。图16中所示的各组件均可以采用硬件、软件或者其组合来实现。
本申请的另一方面还提供了一种计算机可读存储介质,其上存储有计算机程序,该计算 机程序被处理器执行时实现如前所述的视频处理方法或者图像处理方法。该计算机可读存储介质可以是上述实施例中描述的电子设备中所包含的,也可以是单独存在,而未装配入该电子设备中。
上述内容,仅为本申请的较佳示例性实施例,并非用于限制本申请的实施方案,本领域普通技术人员根据本申请的主要构思和精神,可以十分方便地进行相应的变通或修改,故本申请的保护范围应以权利要求书所要求的保护范围为准。

Claims (19)

  1. 一种多媒体处理方法,由电子设备执行,包括:
    获取待生成多媒体特效的原始多媒体;
    对所述原始多媒体进行媒体内容识别,并获得与所述原始多媒体的媒体内容相匹配的至少一个特效模板,所述特效模板中含有至少一个特效组件,所述特效组件用于描述多媒体特效;
    根据选中的特效模板中含有的目标特效组件,在所述原始多媒体中生成所述目标特效组件描述的多媒体特效。
  2. 根据权利要求1所述的方法,其中对所述原始多媒体进行媒体内容识别,并获得与所述原始多媒体的媒体内容相匹配的至少一个特效模板,包括:
    对所述原始多媒体进行媒体内容识别,获得与所述原始多媒体的媒体内容相对应的多媒体标签;
    根据所述多媒体标签,从预设的特效组件集合中获取与所述多媒体标签相匹配的至少一个特效组件;
    根据与所述多媒体标签相匹配的至少一个特效组件,生成至少一个所述特效模板。
  3. 根据权利要求2所述的方法,其中,所述原始多媒体包括原始视频;
    所述对所述原始多媒体进行媒体内容识别,获得与所述原始多媒体的媒体内容相对应的多媒体标签,包括:
    根据所述原始视频的视频时长,从所述原始视频中截取至少一帧视频图像;
    对所述至少一帧视频图像进行内容识别,得到所述至少一帧视频图像的内容标签,将所述至少一帧视频图像的内容标签作为与所述原始视频的视频内容相对应的视频标签。
  4. 根据权利要求3所述的方法,其中,根据选中的特效模板中含有的目标特效组件,在所述原始多媒体中生成所述目标特效组件描述的多媒体特效,包括:
    解析所述选中的特效模板含有的各个特效组件的特效参数,所述特效参数包括时间参数,所述时间参数用于描述所述特效组件在所述原始视频中进行显示的相对位置和显示时长;
    根据所述各个特效组件的时间参数,在所述原始视频的相对位置上生成各个特效组件对应的视频特效内容,并使所述视频特效内容持续显示所述显示时长。
  5. 根据权利要求3所述的方法,其中,所述原始视频包括至少两个视频片段;对所述原始多媒体进行媒体内容识别,获得与所述原始多媒体的媒体内容相匹配的至少一个特效模板,包括:
    分别对每个所述视频片段进行视频内容识别;
    根据识别得到的每个所述视频片段的视频内容,分别获取与每个所述视频片段的视频内容相匹配的特效模板。
  6. 根据权利要求2所述的方法,其中,根据所述多媒体标签,从预设的特效组件集合中获取与所述多媒体标签相匹配的至少一个特效组件,包括:
    根据预设的标签权重判定规则,确定所述特效组件集合中各个特效组件的特效标签相对所述多媒体标签的权重;
    根据所述各个特效组件的特效标签相对所述多媒体标签的权重,从所述特效组件集合中选取特效标签与所述多媒体标签相匹配的至少一个特效组件。
  7. 根据权利要求6所述的方法,其中,所述原始多媒体包括原始图像;
    所述根据预设的标签权重判定规则,确定所述特效组件集合中各个特效组件的特效标签相对所述多媒体标签的权重,包括:
    降低不适用于所述原始图像生成特效的特效组件的特效标签相对于所述原始多媒体标签的权重至预设值。
  8. 根据权利要求6所述的方法,根据所述各个特效组件的特效标签相对所述多媒体标签的权重,从所述特效组件集合中选取特效标签与所述多媒体标签相匹配的至少一个特效组件,包括:
    将所述特效组件集合中权重大于预设权重阈值的特效组件作为与所述多媒体标签相匹配的特效组件。
  9. 根据权利要求6所述的方法,其中,根据所述各个特效组件的特效标签相对所述多媒体标签的权重,从所述特效组件集合中选取特效标签与所述多媒体标签相匹配的至少一个特效组件,包括:
    根据所述各个特效组件的特效标签,确定所述特效组件集合中隶属于同一特效类型的特效组件,并按照所述各个特效组件的特效标签相对多媒体标签的权重由大到小的顺序,分别从各个特效类型下的特效组件中选取特效组件,所选取各个类型下的特效组件的数量与预设的特效模板的数量相同。
  10. 根据权利要求2所述的方法,根据与所述多媒体标签相匹配的特效组件,生成至少一个所述特效模板,包括:
    将与所述多媒体标签相匹配的特效组件按照不同的特效类型进行随机组合,获得至少一个所述特效模板。
  11. 根据权利要求2所述的方法,其中,根据与所述多媒体标签相匹配的特效组件,生成至少一个所述特效模板,包括:
    根据不同特效类型的所述特效组件分别关于所述多媒体标签的匹配程度的排序,将所述不同特效类型下排序相同的特效组件组合形成一个特效模板,获得至少一个所述特效模板。
  12. 根据权利要求1所述的方法,其中,在根据选中的特效模板中含有的目标特效组件,在所述原始多媒体中生成所述目标特效组件描述的多媒体特效之后,所述方法还包括:
    根据特效编辑指令,调取特效多媒体中包含的各项特效组件,所述特效多媒体由所述原始多媒体和所述目标特效组件描述的多媒体特效的组合形成;
    根据组件更新指令,对所述特效多媒体中包含的各项特效组件进行更新。
  13. 一种多媒体处理方法,其特征在于,包括:
    获取待生成多媒体特效的原始多媒体;
    对所述原始多媒体进行媒体内容识别,获得与所述原始多媒体的媒体内容相匹配的至少一个特效模板,所述特效模板中含有至少一个特效组件,所述特效组件用于描述多媒体特效;
    将所述特效模板发送至指定设备,使得所述指定设备根据选中的特效模板中含有的目标特效组件,在所述原始多媒体中生成所述特效组件描述的多媒体特效。
  14. 一种多媒体处理方法,包括:
    显示待生成视频特效的原始多媒体;
    显示与所述原始多媒体的媒体内容相匹配的至少一个特效模板,所述特效模板是根据与所述原始多媒体的媒体内容相匹配的特效组件生成的,所述特效组件用于描述多媒体特效;
    检测从所述至少一个特效模板中选取的目标特效模板,所述目标特效模板包含有目标特效组件;
    在显示的所述原始多媒体中呈现所述目标特效组件所描述的多媒体特效。
  15. 一种多媒体处理装置,包括:
    原始多媒体获取模块,用于获取待生成多媒体特效的原始多媒体;
    特效模板获取模块,用于对所述原始多媒体进行媒体内容识别,并获得与所述原始多媒体的媒体内容相匹配的至少一个特效模板,所述特效模板中含有至少一个特效组件,所述特效组件用于描述多媒体特效;
    多媒体特效生成模块,用于根据选中的特效模板中含有的目标特效组件,在所述原始多媒体中生成所述目标特效组件描述的多媒体特效。
  16. 一种多媒体处理装置,包括:
    第二原始多媒体获取模块,用于获取待生成多媒体特效的原始多媒体;
    第二特效模板获取模块,用于对所述原始多媒体进行媒体内容识别,获得与所述原始多媒体的媒体内容相匹配的至少一个特效模板,所述特效模板中含有至少一个特效组件,所述特效组件用于描述多媒体特效;
    特效模板发送模块,用于将所述特效模板发送至指定设备,使得所述指定设备根据选中的特效模板中含有的目标特效组件,在所述原始多媒体中生成所述特效组件描述的多媒体特效。
  17. 一种多媒体处理装置,包括:
    原始多媒体显示模块,用于显示待生成视频特效的原始多媒体;
    特效模板显示模块,用于显示与所述原始多媒体的媒体内容相匹配的至少一个特效模板,所述特效模板是根据与所述原始多媒体的媒体内容相匹配的特效组件生成的,所述特效组件用于描述多媒体特效;
    模板选中检测模块,用于检测从所述至少一个特效模板中选取的目标特效模板,所述目标特效模板包含有目标特效组件;
    多媒体特效呈现模块,用于在显示的所述原始多媒体中呈现所述目标特效组件所描述的多媒体特效。
  18. 一种电子设备,包括:
    存储器,存储有计算机可读指令;
    处理器,读取存储器存储的计算机可读指令,以执行权利要求1-14中的任一项所述的方法。
  19. 一种计算机可读存储介质,其上存储有计算机可读指令,当所述计算机可读指令被计算机的处理器执行时,使计算机执行权利要求1-14中的任一项所述的方法。
PCT/CN2021/075500 2020-04-02 2021-02-05 多媒体处理方法、装置、电子设备、存储介质 WO2021196890A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010255390.2A CN111541936A (zh) 2020-04-02 2020-04-02 视频及图像处理方法、装置、电子设备、存储介质
CN202010255390.2 2020-04-02

Publications (1)

Publication Number Publication Date
WO2021196890A1 true WO2021196890A1 (zh) 2021-10-07

Family

ID=71976949

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/075500 WO2021196890A1 (zh) 2020-04-02 2021-02-05 多媒体处理方法、装置、电子设备、存储介质

Country Status (2)

Country Link
CN (1) CN111541936A (zh)
WO (1) WO2021196890A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114896001A (zh) * 2022-04-08 2022-08-12 北京达佳互联信息技术有限公司 一种组件展示方法、装置、电子设备、介质及程序产品
CN115150661A (zh) * 2022-06-23 2022-10-04 深圳市大头兄弟科技有限公司 视频关键片段的包装方法及相关装置
CN116456131A (zh) * 2023-03-13 2023-07-18 北京达佳互联信息技术有限公司 特效渲染方法、装置、电子设备及存储介质
WO2024022391A1 (zh) * 2022-07-29 2024-02-01 北京字跳网络技术有限公司 多媒体数据传输方法、装置、电子设备及存储介质

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111541936A (zh) * 2020-04-02 2020-08-14 腾讯科技(深圳)有限公司 视频及图像处理方法、装置、电子设备、存储介质
CN112153422B (zh) * 2020-09-25 2023-03-31 连尚(北京)网络科技有限公司 视频融合方法和设备
CN112511750B (zh) * 2020-11-30 2022-11-29 维沃移动通信有限公司 视频拍摄方法、装置、设备及介质
CN112689200B (zh) * 2020-12-15 2022-11-11 万兴科技集团股份有限公司 视频编辑方法、电子设备及存储介质
CN112800263A (zh) * 2021-02-03 2021-05-14 上海艾麒信息科技股份有限公司 一种基于人工智能的视频合成系统、方法及介质
CN115269889A (zh) * 2021-04-30 2022-11-01 北京字跳网络技术有限公司 剪辑模板搜索方法及装置
CN115484395A (zh) * 2021-06-16 2022-12-16 荣耀终端有限公司 一种视频处理方法及电子设备
CN115484400B (zh) * 2021-06-16 2024-04-05 荣耀终端有限公司 一种视频数据处理方法及电子设备
CN115484397B (zh) * 2021-06-16 2023-11-10 荣耀终端有限公司 一种多媒体资源分享方法和电子设备
CN115484423A (zh) * 2021-06-16 2022-12-16 荣耀终端有限公司 一种转场特效添加方法及电子设备
CN115484399B (zh) * 2021-06-16 2023-12-12 荣耀终端有限公司 一种视频处理方法和电子设备
CN113542855B (zh) * 2021-07-21 2023-08-22 Oppo广东移动通信有限公司 视频处理方法、装置、电子设备和可读存储介质
CN114339360B (zh) * 2021-09-09 2023-05-02 腾讯科技(深圳)有限公司 一种视频处理的方法、相关装置及设备
CN114173067A (zh) * 2021-12-21 2022-03-11 科大讯飞股份有限公司 一种视频生成方法、装置、设备及存储介质
CN116708917A (zh) * 2022-02-25 2023-09-05 北京字跳网络技术有限公司 视频处理方法、装置、设备及介质
CN116700846B (zh) * 2022-02-28 2024-04-02 荣耀终端有限公司 一种图片显示方法及相关电子设备
CN115442519B (zh) * 2022-08-08 2023-12-15 珠海普罗米修斯视觉技术有限公司 视频处理方法、装置及计算机可读存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002027319A (ja) * 2000-07-12 2002-01-25 Sony Corp 映像特殊効果装置の制御システム
CN105049959A (zh) * 2015-07-08 2015-11-11 腾讯科技(深圳)有限公司 多媒体文件播放方法及装置
CN108495058A (zh) * 2018-01-30 2018-09-04 光锐恒宇(北京)科技有限公司 图像处理方法、装置和计算机可读存储介质
CN108696699A (zh) * 2018-04-10 2018-10-23 光锐恒宇(北京)科技有限公司 一种视频处理的方法和装置
CN110708596A (zh) * 2019-09-29 2020-01-17 北京达佳互联信息技术有限公司 生成视频的方法、装置、电子设备及可读存储介质
CN110865754A (zh) * 2019-11-11 2020-03-06 北京达佳互联信息技术有限公司 信息展示方法、装置及终端
CN111541936A (zh) * 2020-04-02 2020-08-14 腾讯科技(深圳)有限公司 视频及图像处理方法、装置、电子设备、存储介质

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103795897A (zh) * 2014-01-21 2014-05-14 深圳市中兴移动通信有限公司 自动生成背景音乐的方法和装置
CN106488017A (zh) * 2016-10-09 2017-03-08 上海斐讯数据通信技术有限公司 一种移动终端及其对拍摄的图像进行配乐的方法
CN107493440A (zh) * 2017-09-14 2017-12-19 光锐恒宇(北京)科技有限公司 一种在应用中显示图像的方法和装置
CN107888843A (zh) * 2017-10-13 2018-04-06 深圳市迅雷网络技术有限公司 用户原创内容的混音方法、装置、存储介质及终端设备
CN108334540B (zh) * 2017-12-15 2020-11-10 深圳市腾讯计算机系统有限公司 媒体信息的展示方法和装置、存储介质、电子装置
CN108174099A (zh) * 2017-12-29 2018-06-15 光锐恒宇(北京)科技有限公司 图像显示方法、装置和计算机可读存储介质
CN110163050B (zh) * 2018-07-23 2022-09-27 腾讯科技(深圳)有限公司 一种视频处理方法及装置、终端设备、服务器及存储介质
CN109040615A (zh) * 2018-08-10 2018-12-18 北京微播视界科技有限公司 视频特效添加方法、装置、终端设备及计算机存储介质
CN109462776B (zh) * 2018-11-29 2021-08-20 北京字节跳动网络技术有限公司 一种视频特效添加方法、装置、终端设备及存储介质
CN109819179B (zh) * 2019-03-21 2022-02-01 腾讯科技(深圳)有限公司 一种视频剪辑方法和装置
CN110298283B (zh) * 2019-06-21 2022-04-12 北京百度网讯科技有限公司 图像素材的匹配方法、装置、设备以及存储介质
CN110177219A (zh) * 2019-07-01 2019-08-27 百度在线网络技术(北京)有限公司 视频的模板推荐方法和装置
CN110381371B (zh) * 2019-07-30 2021-08-31 维沃移动通信有限公司 一种视频剪辑方法及电子设备
CN110532426A (zh) * 2019-08-27 2019-12-03 新华智云科技有限公司 一种基于模板抽取多媒体素材生成视频的方法及系统
CN110740262A (zh) * 2019-10-31 2020-01-31 维沃移动通信有限公司 背景音乐的添加方法、装置及电子设备
CN110769313B (zh) * 2019-11-19 2022-02-22 广州酷狗计算机科技有限公司 视频处理方法及装置、存储介质

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002027319A (ja) * 2000-07-12 2002-01-25 Sony Corp 映像特殊効果装置の制御システム
CN105049959A (zh) * 2015-07-08 2015-11-11 腾讯科技(深圳)有限公司 多媒体文件播放方法及装置
CN108495058A (zh) * 2018-01-30 2018-09-04 光锐恒宇(北京)科技有限公司 图像处理方法、装置和计算机可读存储介质
CN108696699A (zh) * 2018-04-10 2018-10-23 光锐恒宇(北京)科技有限公司 一种视频处理的方法和装置
CN110708596A (zh) * 2019-09-29 2020-01-17 北京达佳互联信息技术有限公司 生成视频的方法、装置、电子设备及可读存储介质
CN110865754A (zh) * 2019-11-11 2020-03-06 北京达佳互联信息技术有限公司 信息展示方法、装置及终端
CN111541936A (zh) * 2020-04-02 2020-08-14 腾讯科技(深圳)有限公司 视频及图像处理方法、装置、电子设备、存储介质

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114896001A (zh) * 2022-04-08 2022-08-12 北京达佳互联信息技术有限公司 一种组件展示方法、装置、电子设备、介质及程序产品
CN115150661A (zh) * 2022-06-23 2022-10-04 深圳市大头兄弟科技有限公司 视频关键片段的包装方法及相关装置
CN115150661B (zh) * 2022-06-23 2024-04-09 深圳市闪剪智能科技有限公司 视频关键片段的包装方法及相关装置
WO2024022391A1 (zh) * 2022-07-29 2024-02-01 北京字跳网络技术有限公司 多媒体数据传输方法、装置、电子设备及存储介质
CN116456131A (zh) * 2023-03-13 2023-07-18 北京达佳互联信息技术有限公司 特效渲染方法、装置、电子设备及存储介质
CN116456131B (zh) * 2023-03-13 2023-12-19 北京达佳互联信息技术有限公司 特效渲染方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN111541936A (zh) 2020-08-14

Similar Documents

Publication Publication Date Title
WO2021196890A1 (zh) 多媒体处理方法、装置、电子设备、存储介质
CN110521187B (zh) 活动馈送服务
US10739958B2 (en) Method and device for executing application using icon associated with application metadata
US11580155B2 (en) Display device for displaying related digital images
CN107426403B (zh) 移动终端
KR101660271B1 (ko) 메타데이터 태깅 시스템, 이미지 검색 방법, 디바이스 및 이에 적용되는 제스처 태깅방법
US9449107B2 (en) Method and system for gesture based searching
US20150317353A1 (en) Context and activity-driven playlist modification
US20120124517A1 (en) Image display device providing improved media selection
CN112104915B (zh) 一种视频数据处理方法、装置及存储介质
CN112131410A (zh) 多媒体资源展示方法、装置、系统和存储介质
US20120150870A1 (en) Image display device controlled responsive to sharing breadth
US20120130834A1 (en) Method for remotely configuring a digital image display device
US11348587B2 (en) Review system for online communication, method, and computer program
US20180300217A1 (en) Determining user engagement with software applications
WO2023109525A1 (zh) 电子设备的快捷设置方法、装置、存储介质及电子设备
WO2023061414A1 (zh) 一种文件生成方法、装置及电子设备
US11941048B2 (en) Tagging an image with audio-related metadata
CN112765375A (zh) 多媒体资源信息的展示方法、装置、电子设备和存储介质
US20180359456A1 (en) Systems and processes for generating a digital content item
CN115379136A (zh) 特效道具处理方法、装置、电子设备及存储介质
US11303464B2 (en) Associating content items with images captured of meeting content
CN108874172B (zh) 输入方法和装置
CN112770185B (zh) 雪碧图的处理方法、装置、电子设备和存储介质
US20240005364A1 (en) Method and device for editing advertisement content

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21778805

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 14/02/2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21778805

Country of ref document: EP

Kind code of ref document: A1