CN109376266A - Processing method, device, electronic equipment and the storage medium of slow motion video - Google Patents
Processing method, device, electronic equipment and the storage medium of slow motion video Download PDFInfo
- Publication number
- CN109376266A CN109376266A CN201811090066.9A CN201811090066A CN109376266A CN 109376266 A CN109376266 A CN 109376266A CN 201811090066 A CN201811090066 A CN 201811090066A CN 109376266 A CN109376266 A CN 109376266A
- Authority
- CN
- China
- Prior art keywords
- audio
- scene
- section
- motion video
- slow motion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The disclosure provides processing method, device, electronic equipment and the storage medium of a kind of slow motion video；Method therein includes: to carry out identifying processing to the slow motion video of acquisition, obtains the scene Recognition result of the slow motion video；Matched scene audio is obtained according to the scene Recognition result；The former audio of the slow motion video is updated to the scene audio；The scene audio is used for normal speed forward.To which the disclosure effectively improves the presentation effect of slow motion video, user experience is improved, and without other auxiliary tools, advantageously reduce development cost and user-friendly.
Description
Technical field
This disclosure relates to technical field of video processing more particularly to the processing method of slow motion video, device, electronic equipment
And storage medium.
Background technique
Slow motion video is the slow motion shooting function video obtained based on mobile terminal, referred to as " temporal
Feature " generally comprises constant speed section and at a slow speed section；Wherein, constant speed section, which refers to, can reflect subject reality in slow motion video
One section of video of movement velocity, section refers to one section of video more slow-footed than subject actual motion at a slow speed.It is regarded based on slow motion
Yupin effect, can be slack-off by the movement of subject, and a kind of special viewing effect is consequently formed, is observed that user flat
When the details that can't see, such as the slow play of basketball landing, it can be seen that the extruding and deformation of spherical surface when being contacted with ground.
Currently, the implementation of slow motion video is: by the way that when recording slow motion video, mobile terminal is compared with high frame rate
Rate, as 50fps (frame/second) or 240fps goes the fast motion of recording target object；And when playing slow motion video, mobile terminal
With regular frame rate such as 30fps or more low frame rate rate plays out the video recorded.Slow motion video is playing back as a result,
When, substantially the play time of section at a slow speed is elongated.Due to while playing section at a slow speed, the corresponding wave audio of section at a slow speed
Play time be also elongated, the sound so as to cause section at a slow speed is more ear-piercing, mismatches with the scene of section at a slow speed, influences video
Effect is presented.
Summary of the invention
To overcome the problems in correlation technique, present disclose provides the processing method of slow motion video, device, electronics
Equipment and storage medium.
According to the first aspect of the embodiments of the present disclosure, a kind of processing method of slow motion video is provided, which comprises
Identifying processing is carried out to the slow motion video of acquisition, obtains the scene Recognition result of the slow motion video；
Matched scene audio is obtained according to the scene Recognition result；
The former audio of the slow motion video is updated to the scene audio；The scene audio is used for normal speed
It plays.
The embodiment of the present disclosure is by carrying out scene Recognition to slow motion video as a result, according to the acquisition of scene Recognition result
The former audio of slow motion video is updated to the scene audio by the scene audio matched, realization, and by the scene audio with just
Constant velocity plays；It efficiently solves in the related technology because the play time of the wave audio of section at a slow speed is elongated, caused sound
Sound is more ear-piercing, does not match the problem of section scene at a slow speed；But also it can be to avoid the ambient noise that former audio is included to sound
The influence of audio fruit.To effectively improve the presentation effect of slow motion video, user experience is improved, and auxiliary without other
Assistant engineer's tool, advantageously reduces development cost and user-friendly.
Optionally, identifying processing is carried out to the slow motion video of acquisition, obtains the scene Recognition knot of the slow motion video
The step of fruit, the execution when the control that the system that receives is dubbed in background music automatically is triggered generated instruction.
As a result, the embodiment of the present disclosure by the control dubbed in background music automatically in the system that receives be triggered caused by instruction when
Slow motion video is performed corresponding processing, without being carried out at audio update on backstage to each slow motion video
Reason can mitigate the burden of system operation, accelerate the efficiency of slow motion video processing, avoid regarding the unwanted slow motion of user
Frequency is handled, and the validity of slow motion video processing is improved.
Optionally, the disclosure the method also includes:
Receive the customized control dubbed in background music of user be triggered caused by instruction when, show audio list；The audio column
Table is configured with and multiple audio files associated multiple Audio Controls one by one；
Receive Audio Controls be triggered caused by instruction when, the former audio of the slow motion video of acquisition is updated to currently
Audio associated by selected Audio Controls；The associated audio of Audio Controls in described and currently selected is used for positive constant speed
Degree plays.
The embodiment of the present disclosure is by the control that customized can dub in background music for user configuration as a result, and is triggered in the control
After show audio list, for selection by the user, realize user can according to oneself hobby and select suitable scene audio, improve
User experience.
Optionally, the scene audio includes at least one of: scene sound, scene are dubbed in background music.
Optionally, the slow motion video includes constant speed section and section at a slow speed；The scene Recognition result include it is described at a slow speed
The scene Recognition result of section；
The acquisition process of the scene Recognition result of the section at a slow speed includes:
According to scheduled time parameter, identification obtains the section at a slow speed of the slow motion video；
Multiple image is obtained from the section at a slow speed by taking out frame algorithm；
By preparatory trained neural network model scene Recognition processing is carried out to the multiple image respectively, obtains institute
State the scene Recognition result of section at a slow speed.
The step of embodiment of the present disclosure is by above-mentioned acquisition scene Recognition result as a result, can improve scene Recognition result
Accuracy further enhances slow motion video so that scence music obtained is more bonded with current slow motion video
Presentation effect.
Optionally, the former audio of the slow motion video is updated to the scene audio, comprising:
The former audio of the section at a slow speed is updated to the scene audio, and retains the former audio of the constant speed section.
The embodiment of the present disclosure is by only updating the former audio of the section at a slow speed as a result, and retains the former sound of the constant speed section
Frequently, operation processing step can be reduced to a certain extent, improve the treatment effeciency to slow motion video.
Optionally, the scene Recognition result further includes the scene Recognition result of the constant speed section；The scene audio packet
Include the scene audio of the constant speed section and the scene audio of the section at a slow speed；
The former audio of the slow motion video is updated to the scene audio, comprising:
The former audio of the constant speed section is updated to the scene audio of the constant speed section；
The former audio of the section at a slow speed is updated to the scene audio of the section at a slow speed.
The embodiment of the present disclosure is by the way that the constant speed section of slow motion video and the at a slow speed former audio of section to be updated to pair respectively as a result,
The scene audio answered can avoid Same Scene audio quilt for constant speed section and in the case of section scene differs larger at a slow speed well
Occur for the phenomenon that two kinds of different scenes, is conducive to further increase video presentation effect.
According to the second aspect of an embodiment of the present disclosure, described present disclose provides a kind of processing unit of slow motion video
Device includes:
Processing module is configured as: being carried out identifying processing to the slow motion video of acquisition, is obtained the slow motion video
Scene Recognition result；
Matching module is configured as: obtaining matched scene audio according to the scene Recognition result；
First update module, is configured as: the former audio of the slow motion video is updated to the scene audio；It is described
Scene audio is used for normal speed forward.
According to the third aspect of an embodiment of the present disclosure, present disclose provides a kind of electronic equipment, the electronic equipment includes:
Processor；
Memory, for storing the computer program that can be executed by the processor；
Wherein, the step of realizing the processing method of the slow motion video when processor executes described program.
According to a fourth aspect of embodiments of the present disclosure, the disclosure provides a kind of computer readable storage medium, stores thereon
The step of having computer program, the processing method of the slow motion video is realized when described program is executed by processor.
Since the device, electronic equipment and computer readable storage medium of the disclosure all cover the slow motion view of the disclosure
The processing method of frequency, therefore the device of the disclosure, electronic equipment and computer readable storage medium all include aforementioned slow motion video
Processing method caused by advantageous effects, details are not described herein.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
Fig. 1 is a kind of disclosure flow chart of the processing method of slow motion video shown according to an exemplary embodiment；
Fig. 2 is the interface schematic diagram of disclosure photograph album application interface shown according to an exemplary embodiment；
Fig. 3 is after the slow motion video in Fig. 2 is clicked, to be switched to interface schematic diagram when dubbing in background music application interface；
Fig. 4 is the interface schematic diagram after the control that system shown in Fig. 3 is dubbed in background music automatically is clicked；
Fig. 5 is a kind of disclosure interface of the application interface of dubbing in background music of slow motion video shown according to an exemplary embodiment
Schematic diagram；
Fig. 6 is after the customized control dubbed in background music of the user in Fig. 5 is clicked, and showing interface has a kind of boundary when audio list
Face schematic diagram；
Fig. 7 is a kind of disclosure structural frames of the processing unit of slow motion video shown according to an exemplary embodiment
Figure；
Fig. 8 is the structural block diagram of disclosure a kind of electronic equipment shown according to an exemplary embodiment.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.
It is only to be not intended to be limiting the disclosure merely for for the purpose of describing particular embodiments in the term that the disclosure uses.
The "an" of the singular used in disclosure and the accompanying claims book, " described " and "the" are also intended to including majority
Form, unless the context clearly indicates other meaning.It is also understood that term "and/or" used herein refers to and wraps
It may be combined containing one or more associated any or all of project listed.
It will be appreciated that though various information, but this may be described using term first, second, third, etc. in the disclosure
A little information should not necessarily be limited by these terms.These terms are only used to for same type of information being distinguished from each other out.For example, not departing from
In the case where disclosure range, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as
One information.Depending on context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determination ".
As shown in Figure 1, Fig. 1 is a kind of disclosure processing method of slow motion video shown according to an exemplary embodiment
Flow chart, the method can be used in terminal, such as in mobile phone, plate mobile terminal, comprising the following steps:
S1 carries out identifying processing to the slow motion video of acquisition, obtains the scene Recognition result of the slow motion video；
S2 obtains matched scene audio according to the scene Recognition result；
The former audio of the slow motion video is updated to the scene audio by S3；The scene audio is used for normal
Speed plays.
In the process of development, the camera applications or phase that the processing method of the slow motion video can be carried as terminal
One of functional module of volume application, that is, the included system camera application or photograph album application of terminal can be upgraded to include
The application of the processing method of the slow motion video, it is possible thereby to it is more user-friendly, and user does not need downloading third
Fang Yingyong.Wherein, in the present embodiment, a wherein function that the processing method of the slow motion video is applied as system photograph album
Module.However, in other embodiments, the processing method of the slow motion video can be packaged into third-party application；It can also
Using a functional module by the processing method of the slow motion video as operating system, with this condition, the slow motion
Although the processing method of video is not belonging to camera applications or photograph album application, but the method can be with camera applications or photograph album application
Association, to be called by camera applications or photograph album application.
The acquisition modes of the slow motion video include at least one of: being absorbed, passed through by the photographing module of terminal
Network is downloaded from server-side, is copied from another equipment in such a way that data line transmits, by being stored in advance in when leaving the factory
Terminal.
In one embodiment, the step S1 can the execution when meeting following either condition: when the photographing module of terminal
When slow motion video is arrived in intake under slow motion screening-mode, preserving when the photograph album of terminal is absorbed by photographing module
Slow motion video when.As long as can all trigger institute it is to be understood that the photograph album application of terminal detects new slow motion video
Step S1 is stated to be performed.Wherein, how to learn that the video newly saved is slow motion video as photograph album application, reference can be made to related skill
The corresponding content of art, this will not be repeated here.
In the present embodiment, the scene Recognition of the slow motion video is the result is that by taking out frame algorithm and preparatory trained mind
It is obtained, be may comprise steps of based on the slow motion video through network model: S1a, by taking out frame algorithm from described slow
Multiple image is extracted in action video；
S1b carries out scene Recognition to the multiple image by neural network model, obtains scene Recognition result.
Wherein, the pumping frame algorithm can be with 1 frame/second speed abstract image, can also be according to the actual situation with other speed
Spend abstract image.The neural network model is by gathering trained mould in advance based on the relevant a large amount of training of video scene
Type, training process can be found in the relevant technologies, and this will not be repeated here.Wherein, the video scene includes institute in actual photographed environment
All scenes that can be related to, for example, scene relevant to natural flows, scene relevant with life water flow and outdoor activities phase
The scene of pass, scene relevant to indoor activity, scene relevant with natural mountain peak, scene relevant with weather and animal are living
Move relevant scene etc..
The scene Recognition result can be determined by following steps:
S1b1 identifies the multiple image extracted by neural network model one by one, and exports and the multiframe
Image multiple scene identities correspondingly；
S1b2 calculates the quantity of identical scene identity, using the scene identity with maximum quantity as current field
Scape recognition result.
In the step S1b2, if with maximum quantity scene identity there are it is multiple when, can further count respectively
The similarity of the image and scene image corresponding to multiple scene identities with maximum quantity that extract is calculated, and there will be maximum
One scene identity of similarity is as current scene Recognition result；Alternatively, from multiple scene identities with maximum quantity
It is any to choose one of them as current scene Recognition result.
Due to the disclosure prestore in the terminal in advance with multiple scene identities multiple scene audios correspondingly, so
It, can be according to scene Recognition as a result, scene audio corresponding with its scene identity is obtained, to realize field in the step S2
The matching of scape audio.
Optionally, the scene audio includes at least one of: scene sound, scene are dubbed in background music.Wherein, scene sound is
Refer to the sound that the target object in video is issued in the scene, for example, stream is target pair when shooting the flowing of stream
As the sound that stream issues is singing of the stream.It is the sound being not present in video that scene, which is dubbed in background music, is in post-processing for enhancing view
The other increased sound of the presentation effect of frequency, for example, increasing soft light music in the video scene of stream flowing.
It optionally, can be in advance by scene sound and field when the scene audio includes scene sound and scene is dubbed in background music
Scape, which is dubbed in background music, is fused into a segment of audio, and prestores.
The step S3, may comprise steps of:
The former audio of the slow motion video is deleted, and is matched resulting scene audio with normal playback speed by S3a
Into the slow motion video.
In the step S3a, the scene audio is matched in the slow motion video with normal playback speed and is referred to:
The former broadcasting speed of the scene audio is not changed.
Hereinafter, for example sketching an application scenarios of the method:
Assuming that utilizing the jump process of slow motion screening-mode photographic subjects personage by terminal.After the completion of shooting, phase
Volume application can detect new slow motion video, and carry out identifying processing to the slow motion video, according to scene Recognition knot
Fruit obtains scene audio relevant to jump scene, and the former audio of the slow motion video is replaced with the scene audio.
When playing, the broadcasting speed of the section at a slow speed of the slow motion video is although slack-off, and still, the scene audio still can be according to original
Broadcasting speed (normal speed) plays.It wherein, is intuitively to show the disclosure to the normal speed forward of scene audio and drawn
For example the long difference played, illustrates below, it is assumed that the scene audio includes the lyrics --- " I will fly get Geng Gao, fly
It is higher ", when playing, it can show as that " I will fly get Geng Gao, fly get Geng Gao with the lyrics text of normal speed forward
", and the lyrics text for being elongated broadcasting can show as " I --- --- it is winged --- --- more --- height ---
Fly --- --- more --- height --- ".
The embodiment of the present disclosure is by carrying out scene Recognition to slow motion video as a result, according to the acquisition of scene Recognition result
The former audio of slow motion video is updated to the scene audio by the scene audio matched, realization, and by the scene audio with just
Constant velocity plays；It efficiently solves in the related technology because the play time of the wave audio of section at a slow speed is elongated, caused sound
Sound is more ear-piercing, does not match the problem of section scene at a slow speed；But also it can be to avoid the ambient noise that former audio is included to sound
The influence of audio fruit.To effectively improve the presentation effect of slow motion video, user experience is improved, and auxiliary without other
Assistant engineer's tool, advantageously reduces development cost and user-friendly.
In one embodiment, it is the burden for mitigating system operation, accelerates the efficiency of slow motion video processing, the step S1
Execution when instruction caused by being triggered in the control that the system that receives is dubbed in background music automatically.
Optionally, after obtaining slow motion video, slow motion video can be marked, for example, applying boundary in photograph album
When face shows multiple videos, marker graphic A is shown in the display area of slow motion video, as shown in Fig. 2, Fig. 2 is this public affairs
Open the interface schematic diagram of photograph album application interface shown according to an exemplary embodiment；User can be gone out as a result, with fast resolution
In numerous videos, which is only slow motion video.After user clicks slow motion video, preview circle of slow motion video is entered
It face can be configured with the control B that the system is dubbed in background music automatically, as shown in figure 3, Fig. 3 is in Fig. 2 in the preview interface
After slow motion video is clicked, it is switched to interface schematic diagram when dubbing in background music application interface.When user needs to replace current slow motion
When making the former audio of video, the control B that can be dubbed in background music automatically by clicking the system, then, after control B is clicked, just meeting
It generates and triggers the instruction that the step S1 is executed, after the step S1 is performed, the step S2 and the step S3 just meeting
Sequentially executed.
Therefore, the embodiment of the present disclosure by the control dubbed in background music automatically in the system that receives be triggered caused by instruction when
Slow motion video is performed corresponding processing, without being carried out at audio update on backstage to each slow motion video
Reason can mitigate the burden of system operation, accelerate the efficiency of slow motion video processing, avoid regarding the unwanted slow motion of user
Frequency is handled, and the validity of slow motion video processing is improved.
In one embodiment, to distinguish the state when control B that the system is dubbed in background music automatically is not clicked on and when being clicked,
To allow user to learn, whether using having handled the audio of slow motion video, the method can also include following step
It is rapid:
S4, receive the control that the system is dubbed in background music automatically be triggered caused by instruction when, update the display of the control
Color.
As shown in Figure 3 and Figure 4；Fig. 4 is the interface schematic diagram after the control that system shown in Fig. 3 is dubbed in background music automatically is clicked,
When the control B that the system is dubbed in background music automatically is not clicked on, white or Transparent color can be presented in the background of the control B；Work as institute
When stating control B and being clicked, the background of the control B can be updated to black.
In one embodiment, based on the basis of aforementioned any embodiment, the method for the disclosure can also include with
Lower step:
SA, receive the customized control dubbed in background music of user be triggered caused by instruction when, show audio list；The audio
List configuration has and multiple audio files associated multiple Audio Controls one by one；
SB, receive Audio Controls be triggered caused by instruction when, the former audio of the slow motion video of acquisition is updated to
Audio associated by Audio Controls in currently selected；The associated audio of Audio Controls in described and currently selected is used for just
Constant velocity plays.
It is alternatively possible to increase the customized control C to dub in background music of the user on interface shown in Fig. 3, as shown in figure 5,
Fig. 5 is a kind of disclosure interface schematic diagram of the application interface of dubbing in background music of slow motion video shown according to an exemplary embodiment.
When the user clicks after the control C, audio list D can be further displayed in current interface, for selection by the user, such as Fig. 6
Shown, Fig. 6 is after the customized control dubbed in background music of the user in Fig. 5 is clicked, and showing interface has a kind of interface when audio list
Schematic diagram.
The embodiment of the present disclosure is by the control that customized can dub in background music for user configuration as a result, and is triggered in the control
After show audio list, for selection by the user, realize user can according to oneself hobby and select suitable scene audio, improve
User experience.
In one embodiment, based on the basis of aforementioned any embodiment, the slow motion video may include constant speed section
Section at a slow speed.The scene Recognition result can only include the scene Recognition result of the section at a slow speed.Wherein, the constant speed section is
Refer to the one section of video played in slow motion video with speed identical with the actual motion speed of target object；The section at a slow speed is
Refer in slow motion video to be less than another section of video that the speed of the actual motion speed of target object plays.
Based on this, in the step S1, the scene Recognition result of acquisition can be only the scene Recognition knot of the section at a slow speed
Fruit.Wherein, the acquisition process of the scene Recognition result of the section at a slow speed may comprise steps of:
S11, according to scheduled time parameter, identification obtains the section at a slow speed of the slow motion video；
S12 obtains multiple image from the section at a slow speed by taking out frame algorithm；
S13 carries out scene Recognition processing to the multiple image by preparatory trained neural network model respectively, obtains
Obtain the scene Recognition result of the section at a slow speed.
In the step S11, the scheduled time parameter refers to: the video playback module of terminal is playing slow motion view
When frequency, at the beginning of pre-set section at a slow speed, for example, defaulting the 3s from video when playing one section of slow motion video
Start broadcasting speed is slack-off.So the scheduled time parameter can be obtained directly from video playback module.So, institute
The play start time that section at a slow speed is the slow motion part based on slow motion video is stated to identify to obtain.
For the explanation of the step S12 and the step S13, reference can be made to related content documented by aforementioned, herein not
It repeats again.
The step of embodiment of the present disclosure is by above-mentioned acquisition scene Recognition result as a result, can improve scene Recognition result
Accuracy further enhances slow motion video so that scence music obtained is more bonded with current slow motion video
Presentation effect.
In one embodiment, on the basis of based on embodiment corresponding to the step S11~S13, in the step S3,
The former audio of the slow motion video is updated to the scene audio, may comprise steps of:
The former audio of the section at a slow speed is updated to the scene audio, and retains the former audio of the constant speed section by S31.
Namely, it is only necessary to it will currently identify the former audio of the obtained scene audio replacement section at a slow speed, do not need the sound to constant speed section
Frequency carries out any processing.
The embodiment of the present disclosure is by only updating the former audio of the section at a slow speed as a result, and retains the former sound of the constant speed section
Frequently, operation processing step can be reduced to a certain extent, improve the treatment effeciency to slow motion video.
In one embodiment, on the basis of based on embodiment corresponding to the step S11~S13, the scene Recognition
Result further includes the scene Recognition result of the constant speed section；The scene audio includes the scene audio of the constant speed section and described
The scene audio of section at a slow speed.In the step S3, the former audio of the slow motion video is updated to the scene audio, it can be with
The following steps are included:
The former audio of the constant speed section is updated to the scene audio of the constant speed section by S3a；
The former audio of the section at a slow speed is updated to the scene audio of the section at a slow speed by S3b.
That is, identify the scene of the constant speed section and the section at a slow speed respectively, and respectively to the constant speed section and described slow
The scene of fast section is matched.
The embodiment of the present disclosure is by the way that the constant speed section of slow motion video and the at a slow speed former audio of section to be updated to pair respectively as a result,
The scene audio answered can avoid Same Scene audio quilt for constant speed section and in the case of section scene differs larger at a slow speed well
Occur for the phenomenon that two kinds of different scenes, is conducive to further increase video presentation effect.
It is corresponding with the embodiment of the processing method of aforementioned slow motion video, as shown in fig. 7, Fig. 7 is the disclosure according to one
A kind of structural block diagram of the processing unit of slow motion video shown in exemplary embodiment, the disclosure also provide a kind of slow motion view
The processing unit 400 of frequency, described device 400 include:
Processing module 401, is configured as: carrying out identifying processing to the slow motion video of acquisition, obtains the slow motion view
The scene Recognition result of frequency；
Matching module 402, is configured as: obtaining matched scene audio according to the scene Recognition result；
First update module 403, is configured as: the former audio of the slow motion video is updated to the scene audio；
The scene audio is used for normal speed forward.
The scene audio includes at least one of: scene sound, scene are dubbed in background music.
In one embodiment, the processing module can be additionally configured to: be touched in the control that the system that receives is dubbed in background music automatically
Caused by hair when instruction, identifying processing is carried out to the slow motion video of acquisition, obtains the scene Recognition of the slow motion video
As a result.
In one embodiment, described device can also include:
List display module, is configured as: receive the customized control dubbed in background music of user be triggered caused by instruction when,
Show audio list；The audio list is configured with and multiple audio files associated multiple Audio Controls one by one；
Second update module, is configured as: receive Audio Controls be triggered caused by instruction when, by the slow motion of acquisition
The former audio for making video is updated to audio associated by Audio Controls in currently selected；Audio control in described and currently selected
The associated audio of part is used for normal speed forward.
In one embodiment, the slow motion video includes constant speed section and section at a slow speed；The scene Recognition result includes institute
State the scene Recognition result of section at a slow speed；The processing module may include:
First identification submodule, is configured as: according to scheduled time parameter, identification obtains the slow of the slow motion video
Fast section；
First image acquisition submodule, is configured as: obtaining multiple image from the section at a slow speed by taking out frame algorithm；
First processing submodule, is configured as: by preparatory trained neural network model to the multiple image point
Not carry out scene Recognition processing, obtain the scene Recognition result of the section at a slow speed.
In one embodiment, first update module includes:
Local updating submodule, is configured as: the former audio of the section at a slow speed being updated to the scene audio, and is retained
The former audio of the constant speed section.
In another embodiment, the scene Recognition result further includes the scene Recognition result of the constant speed section；The field
Scape audio includes the scene audio of the constant speed section and the scene audio of the section at a slow speed；First update module includes:
First updates submodule, is configured as: the former audio of the constant speed section is updated to the scene sound of the constant speed section
Frequently；
Second updates submodule, is configured as: the former audio of the section at a slow speed is updated to the scene sound of the section at a slow speed
Frequently.
The function of modules and the realization process of effect are specifically detailed in the above method and correspond to step in above-mentioned apparatus
Realization process, details are not described herein.
Corresponding with the embodiment of the processing method of aforementioned slow motion video, the disclosure also provides a kind of slow motion video
The electronic equipment of processing unit, the electronic equipment include:
Processor；
Memory, for storing the computer program that can be executed by the processor；
Wherein, the processing of slow motion video described in aforementioned any embodiment is realized when the processor executes described program
The step of method, comprising:
Identifying processing is carried out to the slow motion video of acquisition, obtains the scene Recognition result of the slow motion video；
Matched scene audio is obtained according to the scene Recognition result；
The former audio of the slow motion video is updated to the scene audio；The scene audio is used for normal speed
It plays.
As shown in figure 8, Fig. 8 is a kind of disclosure processing unit of slow motion video shown according to an exemplary embodiment
Electronic equipment structural block diagram.The electronic equipment 500 can be mobile phone, mobile messaging devices, and plate is set
It is standby, mobile medical equipment, movable body-building equipment, the terminal devices such as personal digital assistant.
Referring to Fig. 8, electronic equipment 500 may include following one or more components: processing component 501, memory 502,
Power supply module 503, multimedia component 504, audio component 505, the interface 506 of input/output (I/O), sensor module 507,
And communication component 508.
The integrated operation of the usual controlling electronic devices 500 of processing component 501, such as with display, call, data are logical
Letter, camera operation and record operate associated operation.Processing component 501 may include one or more processors 509 to hold
Row instruction, to perform all or part of the steps of the methods described above.In addition, processing component 501 may include one or more moulds
Block, convenient for the interaction between processing component 501 and other components.For example, processing component 501 may include multi-media module, with
Facilitate the interaction between multimedia component 504 and processing component 501.
Memory 502 is configured as storing various types of data to support the operation in electronic equipment 500.These data
Example include any application or method for being operated on electronic equipment 500 instruction, contact data, telephone directory
Data, message, picture, video etc..Memory 502 can by any kind of volatibility or non-volatile memory device or it
Combination realize, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable
Except programmable read only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, fastly
Flash memory, disk or CD.
Power supply module 503 provides electric power for the various assemblies of electronic equipment 500.Power supply module 503 may include power supply pipe
Reason system, one or more power supplys and other generates, managees, and distributes the associated component of electric power with for electronic equipment 500.
Multimedia component 504 includes the screen of one output interface of offer between the electronic equipment 500 and user.
The screen may include touch panel (TP), be implemented as touch screen, to receive input signal from the user.Touch panel
Including one or more touch sensors to sense the gesture on touch, slide, and touch panel.The touch sensor can be with
The boundary of a touch or slide action is not only sensed, but also detects duration associated with the touch or slide operation and pressure
Power.In some embodiments, multimedia component 504 includes a front camera and/or rear camera.Work as electronic equipment
500 are in operation mode, and such as in a shooting mode or a video mode, front camera and/or rear camera can receive outside
Multi-medium data.Each front camera and rear camera can be a fixed optical lens system or have focal length
And optical zoom ability.
Audio component 505 is configured as output and/or input audio signal.For example, audio component 505 includes a Mike
Wind (MIC), when electronic equipment 500 is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone
It is configured as receiving external audio signal.The received audio signal can be further stored in memory 502 or via logical
Believe that component 508 is sent.In some embodiments, audio component 505 further includes a loudspeaker, is used for output audio signal.
I/O interface 502 provides interface between processing component 501 and peripheral interface module, and above-mentioned peripheral interface module can
To be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and lock
Determine button.
Sensor module 507 includes one or more sensors, for providing the state of various aspects for electronic equipment 500
Assessment.For example, sensor module 507 can detecte the state that opens/closes of electronic equipment 500, the relative positioning of component, example
As the component be electronic equipment 500 display and keypad, sensor module 507 can also detect electronic equipment 500 or
The position change of 500 1 components of electronic equipment, the existence or non-existence that user contacts with electronic equipment 500, electronic equipment 500
The temperature change of orientation or acceleration/deceleration and electronic equipment 500.Sensor module 507 may include proximity sensor, be configured
For detecting the presence of nearby objects without any physical contact.Sensor module 507 can also include optical sensor,
Such as CMOS or ccd image sensor, for being used in imaging applications.In some embodiments, which may be used also
To include acceleration transducer, gyro sensor, Magnetic Sensor, pressure sensor, temperature sensor, photoelectric sensor or
GPS sensor.
Communication component 508 is configured to facilitate the communication of wired or wireless way between electronic equipment 500 and other equipment.
Electronic equipment 500 can access the wireless network based on communication standard, such as WiFi, 2G, 3G or 4G or their combination.One
In a exemplary embodiment, communication component 508 via broadcast channel receive broadcast singal from external broadcasting management system or
Broadcast related information.In one exemplary embodiment, the communication component 508 further includes near-field communication (NFC) module, to promote
Into short range communication.For example, radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wide can be based in NFC module
Band (UWB) technology, bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, electronic equipment 500 can be by one or more application specific integrated circuit (ASIC), number
Word signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electron component are realized, for executing the above method.
The function of each unit and the realization process of effect are specifically detailed in the above method corresponding step in above-mentioned electronic equipment
Rapid realization process, details are not described herein.
For Installation practice and electronic equipment embodiment, since it corresponds essentially to embodiment of the method, so phase
Place is closed to illustrate referring to the part of embodiment of the method.Installation practice and electronic equipment embodiment described above is only
It is schematical, wherein the unit as illustrated by the separation member may or may not be physically separated, work
It may or may not be physical unit for the component that unit is shown, it can it is in one place, or can also divide
On cloth to multiple network units.Some or all of the modules therein can be selected to realize disclosure side according to the actual needs
The purpose of case.Those of ordinary skill in the art can understand and implement without creative efforts.
Corresponding with the embodiment of the processing method of aforementioned slow motion video, the disclosure also provides a kind of computer-readable deposit
Storage media is stored thereon with computer program, which realizes the slow motion when being executed by the processor 509 of above-mentioned electronic equipment
The step of making the processing method of video, comprising:
Identifying processing is carried out to the slow motion video of acquisition, obtains the scene Recognition result of the slow motion video；
Matched scene audio is obtained according to the scene Recognition result；
The former audio of the slow motion video is updated to the scene audio；The scene audio is used for normal speed
It plays.
It wherein includes storage medium (the including but not limited to disk of program code that the disclosure, which can be used in one or more,
Memory, CD-ROM, optical memory etc.) on the form of computer program product implemented.Computer-usable storage medium packet
Permanent and non-permanent, removable and non-removable media is included, can be accomplished by any method or technique information storage.Letter
Breath can be computer readable instructions, data structure, the module of program or other data.The example packet of the storage medium of computer
Include but be not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM),
Other kinds of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory
(EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM), digital versatile disc
(DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices or any other non-biography
Defeated medium, can be used for storage can be accessed by a computing device information.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
Its embodiment.The disclosure is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following
Claim is pointed out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.
The foregoing is merely the preferred embodiments of the disclosure, not to limit the disclosure, all essences in the disclosure
Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of disclosure protection.
Claims (16)
1. a kind of processing method of slow motion video, which is characterized in that the described method includes:
Identifying processing is carried out to the slow motion video of acquisition, obtains the scene Recognition result of the slow motion video；
Matched scene audio is obtained according to the scene Recognition result；
The former audio of the slow motion video is updated to the scene audio；The scene audio with normal speed for being broadcast
It puts.
2. being obtained the method according to claim 1, wherein the slow motion video to acquisition carries out identifying processing
The step of scene Recognition result of the slow motion video, is triggered generated instruction in the control that the system that receives is dubbed in background music automatically
Shi Zhihang.
3. according to the method described in claim 2, it is characterized by further comprising:
Receive the customized control dubbed in background music of user be triggered caused by instruction when, show audio list；The audio list is matched
It is equipped with and multiple audio files associated multiple Audio Controls one by one；
Receive Audio Controls be triggered caused by instruction when, the former audio of the slow motion video of acquisition is updated to currently selected
In Audio Controls associated by audio；It is described with it is currently selected in the associated audio of Audio Controls be used to broadcast with normal speed
It puts.
4. the method according to claim 1, wherein the scene audio includes at least one of: scene sound
Sound, scene are dubbed in background music.
5. method according to any one of claims 1 to 4, which is characterized in that the slow motion video include constant speed section and
Section at a slow speed；The scene Recognition result includes the scene Recognition result of the section at a slow speed；
The acquisition process of the scene Recognition result of the section at a slow speed includes:
According to scheduled time parameter, identification obtains the section at a slow speed of the slow motion video；
Multiple image is obtained from the section at a slow speed by taking out frame algorithm；
By preparatory trained neural network model scene Recognition processing is carried out to the multiple image respectively, obtained described slow
The scene Recognition result of fast section.
6. according to the method described in claim 5, it is characterized in that, the former audio of the slow motion video is updated to the field
Scape audio, comprising:
The former audio of the section at a slow speed is updated to the scene audio, and retains the former audio of the constant speed section.
7. according to the method described in claim 5, it is characterized in that, the scene Recognition result further includes the field of the constant speed section
Scape recognition result；The scene audio includes the scene audio of the constant speed section and the scene audio of the section at a slow speed；
The former audio of the slow motion video is updated to the scene audio, comprising:
The former audio of the constant speed section is updated to the scene audio of the constant speed section；
The former audio of the section at a slow speed is updated to the scene audio of the section at a slow speed.
8. a kind of processing unit of slow motion video characterized by comprising
Processing module is configured as: being carried out identifying processing to the slow motion video of acquisition, is obtained the scene of the slow motion video
Recognition result；
Matching module is configured as: obtaining matched scene audio according to the scene Recognition result；
First update module, is configured as: the former audio of the slow motion video is updated to the scene audio；The scene
Audio is used for normal speed forward.
9. device according to claim 8, which is characterized in that the processing module is configured as: automatic receiving system
The control dubbed in background music be triggered caused by instruction when, identifying processing is carried out to the slow motion video of acquisition, obtains the slow motion
The scene Recognition result of video.
10. device according to claim 9, which is characterized in that further include:
List display module, is configured as: receive the customized control dubbed in background music of user be triggered caused by instruction when, show
Audio list；The audio list is configured with and multiple audio files associated multiple Audio Controls one by one；
Second update module, is configured as: receive Audio Controls be triggered caused by instruction when, the slow motion of acquisition is regarded
The former audio of frequency is updated to audio associated by the Audio Controls in currently selected；Audio Controls in described and currently selected close
The audio of connection is used for normal speed forward.
11. device according to claim 8, which is characterized in that the scene audio includes at least one of: scene sound
Sound, scene are dubbed in background music.
12. according to the described in any item devices of claim 8~11, which is characterized in that the slow motion video includes constant speed section
Section at a slow speed；The scene Recognition result includes the scene Recognition result of the section at a slow speed；
The processing module includes:
First identification submodule, is configured as: according to scheduled time parameter, identification obtains the slow motion video at a slow speed
Section；
First image acquisition submodule, is configured as: obtaining multiple image from the section at a slow speed by taking out frame algorithm；
First processing submodule, is configured as: by preparatory trained neural network model to the multiple image respectively into
The processing of row scene Recognition obtains the scene Recognition result of the section at a slow speed.
13. device according to claim 12, which is characterized in that first update module includes:
Local updating submodule, is configured as: the former audio of the section at a slow speed being updated to the scene audio, and described in reservation
The former audio of constant speed section.
14. device according to claim 12, which is characterized in that the scene Recognition result further includes the constant speed section
Scene Recognition result；The scene audio includes the scene audio of the constant speed section and the scene audio of the section at a slow speed；
First update module includes:
First updates submodule, is configured as: the former audio of the constant speed section is updated to the scene audio of the constant speed section；
Second updates submodule, is configured as: the former audio of the section at a slow speed is updated to the scene audio of the section at a slow speed.
15. a kind of electronic equipment characterized by comprising
Processor；
Memory, for storing the computer program that can be executed by the processor；
Wherein, the step of any one of claim 1~7 the method is realized when the processor executes described program.
16. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that described program is processed
The step of any one of claim 1~7 the method is realized when device executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811090066.9A CN109376266A (en) | 2018-09-18 | 2018-09-18 | Processing method, device, electronic equipment and the storage medium of slow motion video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811090066.9A CN109376266A (en) | 2018-09-18 | 2018-09-18 | Processing method, device, electronic equipment and the storage medium of slow motion video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109376266A true CN109376266A (en) | 2019-02-22 |
Family
ID=65405042
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811090066.9A Pending CN109376266A (en) | 2018-09-18 | 2018-09-18 | Processing method, device, electronic equipment and the storage medium of slow motion video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109376266A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022127839A1 (en) * | 2020-12-18 | 2022-06-23 | 北京字跳网络技术有限公司 | Video processing method and apparatus, device, storage medium, and computer program product |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1669309A (en) * | 2002-03-01 | 2005-09-14 | 汤姆森许可公司 | Audio data deletion and silencing during trick mode replay |
| CN101901612A (en) * | 2009-05-27 | 2010-12-01 | 珠海扬智电子有限公司 | Sound playing method and device with variable speed and invariable tone |
| CN102314917A (en) * | 2010-07-01 | 2012-01-11 | 北京中星微电子有限公司 | Method and device for playing video and audio files |
| CN103945272A (en) * | 2013-01-23 | 2014-07-23 | 腾讯科技（北京）有限公司 | Video interaction method, apparatus and system |
| US9838731B1 (en) * | 2016-04-07 | 2017-12-05 | Gopro, Inc. | Systems and methods for audio track selection in video editing with audio mixing option |
| EP3324638A1 (en) * | 2016-11-16 | 2018-05-23 | Thomson Licensing | Method for decoding an audio/video stream and corresponding device |
-
2018
- 2018-09-18 CN CN201811090066.9A patent/CN109376266A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1669309A (en) * | 2002-03-01 | 2005-09-14 | 汤姆森许可公司 | Audio data deletion and silencing during trick mode replay |
| CN101901612A (en) * | 2009-05-27 | 2010-12-01 | 珠海扬智电子有限公司 | Sound playing method and device with variable speed and invariable tone |
| CN102314917A (en) * | 2010-07-01 | 2012-01-11 | 北京中星微电子有限公司 | Method and device for playing video and audio files |
| CN103945272A (en) * | 2013-01-23 | 2014-07-23 | 腾讯科技（北京）有限公司 | Video interaction method, apparatus and system |
| US9838731B1 (en) * | 2016-04-07 | 2017-12-05 | Gopro, Inc. | Systems and methods for audio track selection in video editing with audio mixing option |
| EP3324638A1 (en) * | 2016-11-16 | 2018-05-23 | Thomson Licensing | Method for decoding an audio/video stream and corresponding device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022127839A1 (en) * | 2020-12-18 | 2022-06-23 | 北京字跳网络技术有限公司 | Video processing method and apparatus, device, storage medium, and computer program product |
| EP4207783A4 (en) * | 2020-12-18 | 2024-02-28 | Beijing Zitiao Network Technology Co., Ltd. | Video processing method and apparatus, device, storage medium, and computer program product |
| US12003884B2 (en) | 2020-12-18 | 2024-06-04 | Beijing Zitiao Network Technology Co., Ltd. | Video processing method and apparatus, device, storage medium and computer program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3817395A1 (en) | Video recording method and apparatus, device, and readable storage medium | |
| CN108289169A (en) | Image pickup method, device, electronic equipment and storage medium | |
| CN105828201B (en) | Method for processing video frequency and device | |
| WO2015143875A1 (en) | Method for presenting content, method for pushing content presentation mode and intelligent terminal | |
| CN108510597A (en) | Edit methods, device and the non-transitorycomputer readable storage medium of virtual scene | |
| CN109089170A (en) | Barrage display methods and device | |
| CN104834435B (en) | The playing method and device of audio commentary | |
| CN104284240B (en) | Video browsing approach and device | |
| CN106165430A (en) | Net cast method and device | |
| CN109151537A (en) | Method for processing video frequency, device, electronic equipment and storage medium | |
| CN106303187B (en) | Acquisition method, device and the terminal of voice messaging | |
| CN107396177A (en) | Video broadcasting method, device and storage medium | |
| CN110677734B (en) | Video synthesis method and device, electronic equipment and storage medium | |
| CN106911967A (en) | Direct playing and playback method and device | |
| CN109168062A (en) | Methods of exhibiting, device, terminal device and the storage medium of video playing | |
| CN107509021B (en) | Shooting method, shooting device and storage medium | |
| CN109922252A (en) | The generation method and device of short-sighted frequency, electronic equipment | |
| CN109151565A (en) | Play method, apparatus, electronic equipment and the storage medium of voice | |
| CN109039872A (en) | Exchange method, device, electronic equipment and the storage medium of Instant audio messages | |
| CN109413478A (en) | Video editing method, device, electronic equipment and storage medium | |
| CN110019897B (en) | Method and device for displaying picture | |
| CN107124658B (en) | Net cast method and device | |
| CN108986803A (en) | Scenery control method and device, electronic equipment, readable storage medium storing program for executing | |
| CN105430469B (en) | Playback method, device, terminal and the server of audio, video data | |
| CN105100665B (en) | The method and apparatus for storing the multimedia messages of aircraft acquisition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |