CN109168062A - Methods of exhibiting, device, terminal device and the storage medium of video playing - Google Patents
Methods of exhibiting, device, terminal device and the storage medium of video playing Download PDFInfo
- Publication number
- CN109168062A CN109168062A CN201810989015.3A CN201810989015A CN109168062A CN 109168062 A CN109168062 A CN 109168062A CN 201810989015 A CN201810989015 A CN 201810989015A CN 109168062 A CN109168062 A CN 109168062A
- Authority
- CN
- China
- Prior art keywords
- played
- image frame
- video image
- scene
- progress icon
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/4302—Content synchronisation processes, e.g. decoder synchronisation
-
- 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
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
- H04N21/4312—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
Abstract
This application involves a kind of methods of exhibiting of video playing, device, terminal device and storage medium, the methods of exhibiting of the video playing includes: to obtain video image frame to be played；The video image frame input to be played scene classifier trained in advance is subjected to scene Recognition, obtains scene type；Select progress icon corresponding with the scene type；The progress icon and the video image frame to be played are synchronized into displaying.The application, which is aimed at according to video content, shows progress icon corresponding with video content, to bring more preferably visual effect to user, promotes user experience.
Description
Technical field
This application involves Internet technical field more particularly to a kind of methods of exhibiting of video playing, device, terminal device
And storage medium.
Background technique
With the development of internet technology, the mode of amusing and diverting oneself of people is more and more abundant, and viewing video is increasingly becoming
Most popular one of mode of amusing and diverting oneself.It is risen along with more and more different types of video contents, it is following,
It is exactly the great outburst of video viewing experience upgrading.
For video player, video playing progress bar is generally only used for the currently playing video of aid prompting user
The playback progress of file, function is relatively simple, lacks interest, and bandwagon effect is poor.
Summary of the invention
To overcome the problems in correlation technique, the application provides the methods of exhibiting, device, terminal of a kind of video playing
Equipment and storage medium.
According to the embodiment of the present application in a first aspect, providing a kind of methods of exhibiting of video playing, comprising:
Obtain video image frame to be played；
Video image frame input scene classifier trained in advance is subjected to scene Recognition, obtains scene type；
Select progress icon corresponding with the scene type；
The progress icon is synchronized with the video image frame to be played and is shown.
The scene classifier that video image frame input is trained in advance carries out field in one of the embodiments,
Scape identification, before obtaining scene type, further includes:
Samples pictures set is obtained, includes at least a samples pictures and every sample graph in the samples pictures set
The corresponding scene markup information of piece；
Using the samples pictures and its corresponding scene markup information in the samples pictures set, to preset nerve
Network image disaggregated model is trained, until obtaining the field when preset neural network image disaggregated model convergence
Scape classifier.
The preset neural network image disaggregated model is based on convolutional neural networks in one of the embodiments,
Inception_v3 model.
The video image frame to be played is multiframe in one of the embodiments, video to be played described in each frame
The similarity of picture frame is greater than or equal to preset similarity value.
Selection progress icon corresponding with the scene type in one of the embodiments, comprising:
It is concentrated according to the scene type from the progress icon prestored and obtains corresponding progress icon；
Or,
Progress icon corresponding with the scene type is generated according to the video image frame to be played.
It is described in one of the embodiments, to be generated and the scene type pair according to the video image frame to be played
The progress icon answered, comprising:
The target object for identifying the video image frame to be played generates and the scene class according to the target object
The corresponding progress icon of type；
Or,
Reduce the video image frame to be played, using the video image frame after diminution as with the scene type
Corresponding progress icon；
Or,
Characteristic information is intercepted from the video image frame to be played as progress chart corresponding with the scene type
Mark.
The progress icon sets include: the corresponding progress chart of the preset scene type in one of the embodiments,
Used default progress icon except mark and the preset scene type.
The scene classification that the video image frame input to be played is trained in advance in one of the embodiments,
Device carries out scene Recognition, after obtaining scene type, comprising:
Calculate the confidence level of the scene type；
If the confidence level of the scene type is greater than given threshold, executes and select progress chart corresponding with the scene type
The step of marking, the progress icon and the video image frame to be played synchronized into displaying；
Otherwise displaying is synchronized using default progress icon and the video image frame to be played.
The threshold value is 0.9 in one of the embodiments,.
It is described in one of the embodiments, to obtain video image frame to be played, comprising:
Video to be played is once sampled every m frame, the view that the sample frame that sampling obtains is obtained as needs
Frequency picture frame；
It is described that the progress icon and the video image frame to be played are synchronized into displaying, comprising:
The sample frame and the subsequent m-1 frame of the sample frame are synchronized into displaying using the progress icon.
According to the second aspect of the embodiment of the present application, a kind of displaying device of video playing is provided, comprising:
Module is obtained, is configured as obtaining video image frame to be played；
Identification module is configured as inputting the video image frame into scene classifier progress scene knowledge trained in advance
Not, scene type is obtained；
Selecting module is configured as selection progress icon corresponding with the scene type；
Display module is configured as the progress icon and the video image frame to be played synchronizing displaying.
The displaying device of the video playing in one of the embodiments, further include:
Samples pictures set obtains module, is configured as obtaining samples pictures set, includes in the samples pictures set
An at least samples pictures and the corresponding scene markup information of every samples pictures；
Training module is configured as utilizing the samples pictures and its corresponding scene mark in the samples pictures set
Information is trained preset neural network image disaggregated model, until the preset neural network image disaggregated model
When convergence, the scene classifier is obtained.
The preset neural network image disaggregated model is based on convolutional neural networks in one of the embodiments,
Inception_v3 model.
The video image frame to be played is multiframe in one of the embodiments, video to be played described in each frame
The similarity of picture frame is greater than or equal to preset similarity value.
The selecting module is also configured in one of the embodiments,
It is concentrated according to the scene type from the progress icon prestored and obtains corresponding progress icon；
Or,
Progress icon corresponding with the scene type is generated according to the video image frame to be played.
The selecting module is also configured in one of the embodiments,
The target object for identifying the video image frame to be played generates and the scene class according to the target object
The corresponding progress icon of type；
Or,
Reduce the video image frame to be played, using the video image frame after diminution as with the scene type
Corresponding progress icon；
Or,
Characteristic information is intercepted from the video image frame to be played as progress chart corresponding with the scene type
Mark.
The progress icon sets include: in one of the embodiments,
It is used silent except the corresponding progress icon of preset scene type and the preset scene type
Recognize progress icon.
The displaying device of the video playing in one of the embodiments, further include:
Computing module is configured as calculating the confidence level of the scene type；
If the confidence level of the scene type is greater than given threshold, the display module selection is corresponding with the scene type
Progress icon, the progress icon and the video image frame to be played are synchronized into displaying；
Otherwise the display module synchronizes displaying using default progress icon and the video image frame to be played.
The threshold value is 0.9 in one of the embodiments,.
The acquisition module is additionally configured to carry out one every m frame to video to be played in one of the embodiments,
Secondary sampling, the video image frame that the sample frame that sampling obtains is obtained as needs；
The display module is additionally configured to the sample frame and the subsequent m-1 frame of the sample frame using the progress
Icon synchronizes displaying.
According to the third aspect of the embodiment of the present application, a kind of terminal device is provided, comprising:
Display；
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to:
The step of executing the methods of exhibiting of video playing described in any of the above-described technical solution.
According to the fourth aspect of the embodiment of the present application, provide a kind of storage medium, when the instruction in the storage medium by
When the processor of terminal device executes, so that terminal device is able to carry out a kind of methods of exhibiting of video playing, the method packet
The step of including the methods of exhibiting of video playing described in any of the above-described technical solution.
According to the 5th of the embodiment of the present application the aspect, a kind of computer program product is provided, when in the storage medium
When instruction is executed by the processor of terminal device, so that terminal device is able to carry out a kind of methods of exhibiting of video playing, it is described
Method includes the steps that the methods of exhibiting of video playing described in any of the above-described technical solution.
The technical solution that embodiments herein provides can include the following benefits: the application utilizes scene classifier
Scene Recognition is carried out to video image frame to be played, obtains the corresponding scene type of the video image frame, and according to the field
Scape type selects progress icon corresponding with the scene type, by the progress icon and the video image frame to be played
Displaying is synchronized, progress icon corresponding with video content is shown to realize according to video content, is brought to user
More preferably visual effect promotes user experience.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The application can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows and meets implementation of the invention
Example, and be used to explain the principle of the present invention together with specification.
Fig. 1 is a kind of flow chart of the methods of exhibiting of video playing shown according to an exemplary embodiment.
Fig. 2 is a kind of block diagram of the displaying device of video playing shown according to an exemplary embodiment.
Fig. 3 is a kind of block diagram of terminal device 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 embodiments consistented with the present invention.On the contrary, they be only with it is such as appended
The example of device and method being described in detail in claims, some aspects of the invention are consistent.
Fig. 1 is a kind of flow chart of the methods of exhibiting of video playing shown according to an exemplary embodiment, such as Fig. 1 institute
Showing, for the video player in terminal device, such as in terminal device or software is broadcast live in the methods of exhibiting of the video playing,
The methods of exhibiting of the video playing the following steps are included:
In step s 11, video image frame to be played is obtained.
It in some embodiments, can be by not yet being broadcast in the video file or video file being played on not played
The part put is sampled, and video image frame is obtained.Here video image frame can be from the video for being stored in terminal device
File, the video played online or the video sampling frame obtained in live streaming, can disposably obtain a frame or multiframe.Wherein, exist
In the application one embodiment, when the video image frame to be played is multiframe, video image to be played described in each frame
The similarity of frame is greater than or equal to preset similarity value.
In step s 12, the video image frame input to be played scene classifier trained in advance is subjected to scene
Identification, obtains scene type.
The scene classifier is used to analyze the picture material of the video image frame of input, carries out scene according to picture material
Identification, judges scene type with this.For example, corresponding scene type is to learn when picture material shows people in reading
It practises；For another example, when picture material shows cooking, then its corresponding scene type is culinary art.Thus according to video image frame
The scene type being danced, sung, played games etc..
In some embodiments, it can will be carried out in multiple continuous video image frame inputs scene classifier trained in advance
Identification, obtains the corresponding scene type of every video image frame, and it is shared in all scene types to calculate each scene type
Specific gravity, when specific gravity is greater than preset value, then the corresponding scene type of the specific gravity is video image frame to be played described in multiframe
Corresponding scene type, to effectively improve the accuracy and rapidity of scene Recognition.
In step s 13, progress icon corresponding with the scene type is selected.
The progress icon can be picture, expression packet or Dynamic Graph etc., can close with scene type to correspond
System, for example, progress icon relevant to singing is then selected, such as containing the progress of microphone when the scene type is to sing
Icon etc..Certainly, the scene type and progress icon are also possible to many-one relationship, in order to which user is set as needed certainly
The progress icon that oneself likes realizes personalized designs.It should be noted that the progress icon can be obtained from server,
It can also be obtained from present terminal equipment, the application is not specifically limited herein.
In step S14, the progress icon and the video image frame to be played are synchronized into displaying.
In the present embodiment, when video playing, then to each frame video image frame and corresponding progress icon into
Row is synchronous to be shown, the progress icon can be shown on a progress bar, can also show the other positions at video playing interface.When with
When video is watched at family, the progress icon can be shown in always on video playing interface；It can also be hidden in video playing interface,
It only when getting the wake up instruction of user, is just shown on video playing interface, the mobile mouse of the wake up instruction such as user
Mark clicks the action commands such as video playing interface.
The application carries out scene Recognition to video image frame to be played using scene classifier, obtains the video image frame
Corresponding scene type, and progress icon corresponding with the scene type is selected according to the scene type, by the progress
Icon and the video image frame to be played synchronize displaying, thus realize according to video content show in video
Hold corresponding progress icon, brings more preferably visual effect to user, promote user experience.
The scene classification that the video image frame input to be played is trained in advance in one of the embodiments,
Device carries out scene Recognition, before obtaining scene type, further includes:
Samples pictures set is obtained, includes at least a samples pictures and every sample graph in the samples pictures set
The corresponding scene markup information of piece；
Using the samples pictures and its corresponding scene markup information in the samples pictures set, to preset nerve
Network image disaggregated model is trained, until obtaining the field when preset neural network image disaggregated model convergence
Scape classifier.
In the present embodiment, the scene markup information is the information that can embody the affiliated scene type of the samples pictures.
In the preset neural network image disaggregated model of training, the samples pictures set for having determined that scene type is obtained first, by sample
Samples pictures and its corresponding scene markup information in this picture set input preset neural network image disaggregated model, right
The preset neural network image disaggregated model carries out Softmax classification based training, with the preset neural network of this repetition training
Image classification model, until obtaining scene classifier when its convergence.During training, preset neural network image point
Parameter in class model be it is continually changing, form new neural network image disaggregated model, i.e., each time train when, institute benefit
Neural network image disaggregated model is the last updated neural network image disaggregated model of training, when model is restrained
When namely neural network image disaggregated model when the corresponding scene type of samples pictures can be recognized accurately, final nerve net
Network image classification model is the scene classifier for needing to obtain.Wherein, when the samples pictures for including in samples pictures set are more,
In subsequent identification video image frame to be played, the scene type of the video image frame of identification can be supported also more, known
Other accuracy is also higher.For example, may include up to a million samples pictures in the samples pictures set of the present embodiment.
The preset neural network image disaggregated model is based on convolutional neural networks in one of the embodiments,
Inception_v3 model.
Inception v3 model is based on convolution mind made of the data training in large-scale image data base ImageNet
Through network model, for realizing image classification.Inception v3 model about 25,000,000 parameters do not have figure at one
In the modern terminal equipment of processor, an image classification can be completed in a very short period of time.
Selection progress icon corresponding with the scene type in one of the embodiments, comprising:
It is concentrated according to the scene type from the progress icon prestored and obtains corresponding progress icon；
Or,
Progress icon corresponding with the scene type is generated according to the video image frame to be played.
In the present embodiment, the progress icon can be concentrated from the progress icon prestored and be obtained, in the progress icon
It concentrates, its corresponding scene type is all marked in each progress icon, to identify video figure to be played in scene classifier
After the scene type as belonging to frame, the corresponding progress icon of the scene type quickly can be focused to find out from the progress icon prestored.
In addition, the progress icon can also be directly generated according to the video image frame to be played.
It is described in one of the embodiments, to be generated and the scene type pair according to the video image frame to be played
The progress icon answered, comprising:
The target object for identifying the video image frame to be played generates and the scene class according to the target object
The corresponding progress icon of type；
Or,
Reduce the video image frame to be played, using the video image frame after diminution as with the scene type
Corresponding progress icon；
Or,
Characteristic information is intercepted from the video image frame to be played as progress chart corresponding with the scene type
Mark.
In the present embodiment, when the progress icon is generated according to the video image frame to be played, can by with
Under type generates:
When video image frame to be played has the target object for obviously representing the scene type belonging to it, can directly by
Progress icon is made in the target object, or progress icon will be made with the object of the target object same type, wherein institute
Stating target object can be the maximum pictorial element of clarity highest and/or accounting space in video image frame.
It, can be by directly reducing when the pictorial element of video image frame to be played is relatively simple, accounting space is larger
The size of the video image frame to be played, using the video image frame after diminution as corresponding with the scene type
Progress icon.
It, can be special by interception when having the characteristic information for embodying its scene type in the video image frame to be played
Reference breath generates the progress icon according to the characteristic information, wherein the characteristic information is that can embody video to be played
The pictorial element of the affiliated scene type of picture frame.
The progress icon sets include: in one of the embodiments,
Except the preset corresponding progress icon of scene type and the preset scene type it is used default into
Spend icon.The i.e. described progress icon sets include the corresponding progress icon of the identifiable scene type of scene classifier, and can not
Determine the default progress icon of scene type.
The scene classification that the video image frame input to be played is trained in advance in one of the embodiments,
Device carries out scene Recognition, after obtaining scene type, comprising:
Calculate the confidence level of the scene type；
If the confidence level of the scene type is greater than given threshold, executes and select progress chart corresponding with the scene type
The step of marking, the progress icon and the video image frame to be played synchronized into displaying；
Otherwise displaying is synchronized using default progress icon and the video image frame to be played.
In the present embodiment, when scene type confidence level is greater than or equal to given threshold, then it represents that the scene type is
The corresponding real scene type of video image frame to be played, to select corresponding progress chart according to the scene type
The progress icon and video image frame are synchronized displaying when video playing by mark；It is set when scene type confidence level is less than
When determining threshold value, then it represents that the scene type is not the corresponding real scene type of video image frame to be played, i.e. scene point
Class device can not determine the corresponding scene type of the video image frame, thus using default progress icon and the video image frame into
Row is synchronous to be shown.
The threshold value is 0.9 in one of the embodiments,.When threshold value is higher, described in the scene classifier identification
The accuracy of video image frame to be played is also higher.
It is described in one of the embodiments, to obtain video image frame to be played, comprising:
Video to be played is once sampled every m frame, the view that the sample frame that sampling obtains is obtained as needs
Frequency picture frame；
It is described that the progress icon and the video image frame to be played are synchronized into displaying, comprising:
The sample frame and the subsequent m-1 frame of the sample frame are synchronized into displaying using the progress icon.
In the present embodiment, the video image frame to be played can be obtained by sampling, the sample frame that sampling is obtained
Input scene classifier trained in advance carries out scene Recognition, obtains the scene type of the sample frame with this, and according to described
Scene type selects corresponding progress icon, in video playing, by the sample frame and the subsequent m-1 of the sample frame
Frame synchronizes displaying using the progress icon, wherein m >=2.
Fig. 2 is a kind of displaying device block diagram of video playing shown according to an exemplary embodiment.Referring to Fig. 2, the dress
It sets including obtaining module 21, identification module 22, selecting module 23 and display module 24.
The acquisition module 21 is configured as obtaining video image frame to be played.
It in some embodiments, can be by not yet being broadcast in the video file or video file being played on not played
The part put is sampled, and video image frame is obtained.Here video image frame can be from the video for being stored in terminal device
File, the video played online or the video sampling frame obtained in live streaming, can disposably obtain a frame or multiframe.Wherein, exist
In the application one embodiment, when the video image frame to be played is multiframe, video image to be played described in each frame
The similarity of frame is greater than or equal to preset similarity value.
The identification module 22 is configured as the scene classifier that the video image frame input to be played is trained in advance
Scene Recognition is carried out, scene type is obtained.
The scene classifier is used to analyze the picture material of the video image frame of input, carries out scene according to picture material
Identification, judges scene type with this.For example, corresponding scene type is to learn when picture material shows people in reading
It practises；For another example, when picture material shows cooking, then its corresponding scene type is culinary art.Thus according to video image frame
The scene type being danced, sung, played games etc..
In some embodiments, it can will be carried out in multiple continuous video image frame inputs scene classifier trained in advance
Identification, obtains the corresponding scene type of every video image frame, and it is shared in all scene types to calculate each scene type
Specific gravity, when specific gravity is greater than preset value, then the corresponding scene type of the specific gravity is video image frame to be played described in multiframe
Corresponding scene type, to effectively improve the accuracy and rapidity of scene Recognition.
The selecting module 23 is configured as selection progress icon corresponding with the scene type.
The progress icon can be picture, expression packet or Dynamic Graph etc., can close with scene type to correspond
System, for example, progress icon relevant to singing is then selected, such as containing the progress of microphone when the scene type is to sing
Icon etc..Certainly, the scene type and progress icon are also possible to many-one relationship, in order to which user is set as needed certainly
The progress icon that oneself likes realizes personalized designs.It should be noted that the progress icon can be obtained from server,
It can also be obtained from present terminal equipment, the application is not specifically limited herein.
The display module 24 is configured as the progress icon and the video image frame to be played synchronizing exhibition
Show.
In the present embodiment, when video playing, then to each frame video image frame and corresponding progress icon into
Row is synchronous to be shown, the progress icon can be shown on a progress bar, can also show the other positions at video playing interface.When with
When video is watched at family, the progress icon can be shown in always on video playing interface；It can also be hidden in video playing interface,
It only when getting the wake up instruction of user, is just shown on video playing interface, the mobile mouse of the wake up instruction such as user
Mark clicks the action commands such as video playing interface.
The application carries out scene Recognition to video image frame to be played using scene classifier, obtains the video image frame
Corresponding scene type, and progress icon corresponding with the scene type is selected according to the scene type, by the progress
Icon and the video image frame to be played synchronize displaying, thus realize according to video content show in video
Hold corresponding progress icon, brings more preferably visual effect to user, promote user experience.
The displaying device of the video playing in one of the embodiments, further include:
Samples pictures set obtains module, is configured as obtaining samples pictures set, includes in the samples pictures set
An at least samples pictures and the corresponding scene markup information of every samples pictures；
Training module is configured as utilizing the samples pictures and its corresponding scene mark in the samples pictures set
Information is trained preset neural network image disaggregated model, until the preset neural network image disaggregated model
When convergence, the scene classifier is obtained.
In the present embodiment, the scene markup information is the information that can embody the affiliated scene type of the samples pictures.
In the preset neural network image disaggregated model of training, the samples pictures set for having determined that scene type is obtained first, by sample
Samples pictures and its corresponding scene markup information in this picture set input preset neural network image disaggregated model, right
The preset neural network image disaggregated model carries out Softmax classification based training, with the preset neural network of this repetition training
Image classification model, until obtaining scene classifier when its convergence.During training, preset neural network image point
Parameter in class model be it is continually changing, form new neural network image disaggregated model, i.e., each time train when, institute benefit
Neural network image disaggregated model is the last updated neural network image disaggregated model of training, when model is restrained
When namely neural network image disaggregated model when the corresponding scene type of samples pictures can be recognized accurately, final nerve net
Network image classification model is the scene classifier for needing to obtain.Wherein, when the samples pictures for including in samples pictures set are more,
In subsequent identification video image frame to be played, the type of the video image frame of identification can be supported also more, identification
Accuracy is also higher.For example, may include up to a million samples pictures in the samples pictures set of the present embodiment.
The preset neural network image disaggregated model is based on convolutional neural networks in one of the embodiments,
Inception_v3 model.
Inception v3 model is based on convolution mind made of the data training in large-scale image data base ImageNet
Through network model, for realizing image classification.Inception v3 model about 25,000,000 parameters do not have figure at one
In the modern terminal equipment of processor, an image classification can be completed in a very short period of time.
The selecting module 23 is also configured in one of the embodiments,
It is concentrated according to the scene type from the progress icon prestored and obtains corresponding progress icon；
Or,
Progress icon corresponding with the scene type is generated according to the video image frame to be played.
In the present embodiment, the progress icon can be concentrated from the progress icon prestored and be obtained, in the progress icon
It concentrates, its corresponding scene type is all marked in each progress icon, to identify video figure to be played in scene classifier
After the scene type as belonging to frame, the corresponding progress icon of the scene type quickly can be focused to find out from the progress icon prestored.
In addition, the progress icon can also be directly generated according to the video image frame to be played.
The selecting module 23 is also configured in one of the embodiments,
The target object for identifying the video image frame to be played generates and the scene class according to the target object
The corresponding progress icon of type；
Or,
Reduce the video image frame to be played, using the video image frame after diminution as with the scene type
Corresponding progress icon；
Or,
Characteristic information is intercepted from the video image frame to be played as progress chart corresponding with the scene type
Mark.
In the present embodiment, when the progress icon is generated according to the video image frame to be played, can by with
Under type generates:
When video image frame to be played has the target object for obviously representing the scene type belonging to it, can directly by
Progress icon is made in the target object, or progress icon will be made with the object of the target object same type, wherein institute
Stating target object can be the maximum pictorial element of clarity highest and/or accounting space in video image frame.
It, can be by directly reducing when the pictorial element of video image frame to be played is relatively simple, accounting space is larger
The size of the video image frame to be played, using the video image frame after diminution as corresponding with the scene type
Progress icon.
It, can be special by interception when having the characteristic information for embodying its scene type in the video image frame to be played
Reference breath generates the progress icon according to the characteristic information, wherein the characteristic information is that can embody video to be played
The pictorial element of the affiliated scene type of picture frame.
The progress icon sets include: in one of the embodiments,
Except the preset corresponding progress icon of scene type and the preset scene type it is used default into
Spend icon.The i.e. described progress icon sets include the corresponding progress icon of the identifiable scene type of scene classifier, and can not
Determine the default progress icon of scene type.
The displaying device of the video playing in one of the embodiments, further include:
Computing module is configured as calculating the confidence level of the scene type；
If the confidence level of the scene type is greater than given threshold, the display module selection is corresponding with the scene type
Progress icon, the progress icon and the video image frame to be played are synchronized into displaying；
Otherwise the display module synchronizes displaying using default progress icon and the video image frame to be played.
In the present embodiment, when scene type confidence level is greater than or equal to given threshold, then it represents that the scene type is
The corresponding real scene type of video image frame to be played, to select corresponding progress chart according to the scene type
The progress icon and video image frame are synchronized displaying when video playing by mark；It is set when scene type confidence level is less than
When determining threshold value, then it represents that the scene type is not the corresponding real scene type of video image frame to be played, i.e. scene point
Class device can not determine the corresponding scene type of the video image frame, thus using default progress icon and the video image frame into
Row is synchronous to be shown.
The threshold value is 0.9 in one of the embodiments,.When threshold value is higher, described in the scene classifier identification
The accuracy of video image frame to be played is higher.
The acquisition module is additionally configured to carry out one every m frame to video to be played in one of the embodiments,
Secondary sampling, the video image frame that the sample frame that sampling obtains is obtained as needs；
The display module is additionally configured to the sample frame and the subsequent m-1 frame of the sample frame using the progress
Icon synchronizes displaying.
In the present embodiment, the video image frame to be played can be obtained by sampling, the sample frame that sampling is obtained
Input scene classifier trained in advance carries out scene Recognition, obtains the scene type of the sample frame with this, and according to described
Scene type selects corresponding progress icon, in video playing, by the sample frame and the subsequent m-1 of the sample frame
Frame synchronizes displaying using the progress icon, wherein m >=2.
Fig. 3 is a kind of terminal device 300 of methods of exhibiting for video playing shown according to an exemplary embodiment
Block diagram.For example, terminal device 300 can be mobile phone, computer, digital broadcasting terminal, messaging device, game control
Platform processed, tablet device, Medical Devices, body-building equipment, personal digital assistant etc..
Terminal device 300 may include following one or more components: processing component 302, memory 304, electric power assembly
306, multimedia component 308, audio component 310, the interface 312 of input/output (I/O), sensor module 314, and communication
Component 316.
The integrated operation of the usual controlling terminal equipment 300 of processing component 302, such as with display, call, data are logical
Letter, camera operation and record operate associated operation.Processing component 302 may include one or more processors 320 to hold
Row instruction, to perform all or part of the steps of the methods described above.In addition, processing component 302 may include one or more moulds
Block, convenient for the interaction between processing component 302 and other assemblies.For example, processing component 302 may include multi-media module, with
Facilitate the interaction between multimedia component 308 and processing component 302.
Memory 304 is configured as storing various types of data to support the operation in equipment 300.These data are shown
Example includes the instruction of any application or method for operating on terminal device 300, contact data, telephone directory number
According to, message, picture, video etc..Memory 304 can by any kind of volatibility or non-volatile memory device or they
Combination realize, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable
Programmable read only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, quick flashing
Memory, disk or CD.
Power supply module 306 provides electric power for the various assemblies of terminal device 300.Power supply module 306 may include power supply pipe
Reason system, one or more power supplys and other with for terminal device 300 generate, manage, and distribute the associated component of electric power.
Multimedia component 308 includes the screen of one output interface of offer between the terminal device 300 and user.
In some embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch surface
Plate, screen may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touches
Sensor is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding
The boundary of movement, but also detect duration and pressure associated with the touch or slide operation.In some embodiments,
Multimedia component 308 includes a front camera and/or rear camera.When equipment 300 is in operation mode, as shot mould
When formula or video mode, front camera and/or rear camera can receive external multi-medium data.Each preposition camera shooting
Head and rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 310 is configured as output and/or input audio signal.For example, audio component 310 includes a Mike
Wind (MIC), when terminal device 300 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 304 or via logical
Believe that component 316 is sent.In some embodiments, audio component 310 further includes a loudspeaker, is used for output audio signal.
I/O interface 312 provides interface between processing component 302 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 314 includes one or more sensors, for providing the state of various aspects for terminal device 300
Assessment.For example, sensor module 314 can detecte the state that opens/closes of equipment 300, the relative positioning of component, such as institute
The display and keypad that component is terminal device 300 are stated, sensor module 314 can also detect terminal device 300 or terminal
The position change of 300 1 components of equipment, the existence or non-existence that user contacts with terminal device 300,300 orientation of terminal device
Or the temperature change of acceleration/deceleration and terminal device 300.Sensor module 314 may include proximity sensor, be configured to
It detects the presence of nearby objects without any physical contact.Sensor module 314 can also include optical sensor, such as
CMOS or ccd image sensor, for being used in imaging applications.In some embodiments, which can be with
Including acceleration transducer, gyro sensor, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 316 is configured to facilitate the communication of wired or wireless way between terminal device 300 and other equipment.
Terminal device 300 can access the wireless network based on communication standard, such as WiFi, carrier network (such as 2G, 3G, 4G or 5G),
Or their combination.In one exemplary embodiment, communication component 316 receives via broadcast channel and comes from external broadcasting management
The broadcast singal or broadcast related information of system.In one exemplary embodiment, the communication component 316 further includes that near field is logical
(NFC) module is believed, to promote short range communication.For example, radio frequency identification (RFID) technology, infrared data association can be based in NFC module
Meeting (IrDA) technology, ultra wide band (UWB) technology, bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, terminal device 300 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 electronic components are realized, for executing the above method.
In the exemplary embodiment, a kind of storage medium including instruction, the memory for example including instruction are additionally provided
304, above-metioned instruction can be executed by the processor 320 of terminal device 300 to complete the methods of exhibiting of above-mentioned video playing.For example,
The storage medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk and optical data storage devices etc..
In the exemplary embodiment, additionally provide a kind of computer program product, when the instruction in the storage medium by
When the processor of terminal device 300 executes, so that terminal device 300 is able to carry out a kind of methods of exhibiting of video playing, it is described
Method includes the steps that the methods of exhibiting of video playing described in any of the above-described embodiment.
Those skilled in the art will readily occur to of the invention its after considering specification and the invention applied here of practice
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the invention, these modifications, purposes or
The common knowledge in the art that person's adaptive change follows general principle of the invention and do not apply including the application
Or conventional techniques.The description and examples are only to be considered as illustrative, and true scope and spirit of the invention are by following
Claim is pointed out.
It should be understood that the present invention is not limited to the precise structure already described above and shown in the accompanying drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present invention is limited only by the attached claims.
Claims (10)
1. a kind of methods of exhibiting of video playing characterized by comprising
Obtain video image frame to be played；
The video image frame input to be played scene classifier trained in advance is subjected to scene Recognition, obtains scene class
Type；
Select progress icon corresponding with the scene type；
The progress icon and the video image frame to be played are synchronized into displaying.
2. methods of exhibiting according to claim 1, which is characterized in that described to input the video image frame to be played
Scene classifier trained in advance carries out scene Recognition, before obtaining scene type, further includes:
Samples pictures set is obtained, includes at least a samples pictures and every samples pictures pair in the samples pictures set
The scene markup information answered；
Using the samples pictures and its corresponding scene markup information in the samples pictures set, to preset neural network
Image classification model is trained, until obtaining the scene point when preset neural network image disaggregated model convergence
Class device.
3. methods of exhibiting according to claim 2, which is characterized in that
The preset neural network image disaggregated model is the Inception_v3 model based on convolutional neural networks.
4. methods of exhibiting according to claim 1, which is characterized in that the video image frame to be played is multiframe, respectively
The similarity of video image frame to be played described in frame is greater than or equal to preset similarity value.
5. methods of exhibiting according to claim 1, which is characterized in that described to select progress corresponding with the scene type
Icon, comprising:
It is concentrated according to the scene type from the progress icon prestored and obtains corresponding progress icon；
Or,
Progress icon corresponding with the scene type is generated according to the video image frame to be played.
6. methods of exhibiting according to claim 5, which is characterized in that described raw according to the video image frame to be played
At progress icon corresponding with the scene type, comprising:
The target object for identifying the video image frame to be played generates and the scene type pair according to the target object
The progress icon answered；
Or,
The video image frame to be played is reduced, using the video image frame after diminution as corresponding with the scene type
Progress icon；
Or,
Characteristic information is intercepted from the video image frame to be played as progress icon corresponding with the scene type.
7. methods of exhibiting according to claim 1, which is characterized in that described to obtain video image frame to be played, comprising:
Video to be played is once sampled every m frame, the video figure that the sample frame that sampling obtains is obtained as needs
As frame；
It is described that the progress icon and the video image frame to be played are synchronized into displaying, comprising:
The sample frame and the subsequent m-1 frame of the sample frame are synchronized into displaying using the progress icon.
8. a kind of displaying device of video playing characterized by comprising
Module is obtained, is configured as obtaining video image frame to be played；
Identification module is configured as the video image frame input to be played scene classifier trained in advance carrying out scene
Identification, obtains scene type；
Selecting module is configured as selection progress icon corresponding with the scene type；
Display module is configured as the progress icon and the video image frame to be played synchronizing displaying.
9. a kind of terminal device characterized by comprising
Display；
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to:
The step of executing the methods of exhibiting of video playing according to any one of claims 1 to 7.
10. a kind of storage medium, which is characterized in that when the instruction in the storage medium is executed by the processor of terminal device
When, so that terminal device is able to carry out a kind of methods of exhibiting of video playing, the method includes any one of claims 1 to 7
The step of methods of exhibiting of the video playing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810989015.3A CN109168062B (en) | 2018-08-28 | 2018-08-28 | Video playing display method and device, terminal equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810989015.3A CN109168062B (en) | 2018-08-28 | 2018-08-28 | Video playing display method and device, terminal equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109168062A true CN109168062A (en) | 2019-01-08 |
| CN109168062B CN109168062B (en) | 2020-11-24 |
Family
ID=64893091
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810989015.3A Active CN109168062B (en) | 2018-08-28 | 2018-08-28 | Video playing display method and device, terminal equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109168062B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110225411A (en) * | 2019-05-31 | 2019-09-10 | 北京奇艺世纪科技有限公司 | The segment of programme televised live reviews method, system, computer equipment and medium |
| CN110991246A (en) * | 2019-10-31 | 2020-04-10 | 天津市国瑞数码安全系统股份有限公司 | Video detection method and system |
| CN113591523A (en) * | 2020-04-30 | 2021-11-02 | 聚好看科技股份有限公司 | Display device and experience value updating method |
| WO2021232978A1 (en) * | 2020-05-18 | 2021-11-25 | Oppo广东移动通信有限公司 | Video processing method and apparatus, electronic device and computer readable medium |
| CN113949827A (en) * | 2021-09-30 | 2022-01-18 | 安徽尚趣玩网络科技有限公司 | Video content fusion method and device |
| WO2022152202A1 (en) * | 2021-01-14 | 2022-07-21 | 海信视像科技股份有限公司 | Display device, external device and playing mode switching method |
| CN115334351A (en) * | 2022-08-02 | 2022-11-11 | Vidaa国际控股(荷兰)公司 | Display device and adaptive image quality adjusting method |
| US11924513B2 (en) | 2019-08-18 | 2024-03-05 | Juhaokan Technology Co., Ltd. | Display apparatus and method for display user interface |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100039378A1 (en) * | 2008-08-14 | 2010-02-18 | Toshiharu Yabe | Information Processing Apparatus, Method and Program |
| CN105611413A (en) * | 2015-12-24 | 2016-05-25 | 小米科技有限责任公司 | Method and device for adding video clip class markers |
| CN105812941A (en) * | 2016-03-31 | 2016-07-27 | 北京金山安全软件有限公司 | Video playing method and device and electronic equipment |
| CN106559712A (en) * | 2016-11-28 | 2017-04-05 | 北京小米移动软件有限公司 | Video playback processing method, device and terminal device |
| CN106713965A (en) * | 2016-12-07 | 2017-05-24 | 珠海格力电器股份有限公司 | Information display method and device |
| CN106792212A (en) * | 2016-12-02 | 2017-05-31 | 乐视控股（北京）有限公司 | A kind of video progress adjusting method, device and electronic equipment |
| CN107133631A (en) * | 2016-02-29 | 2017-09-05 | 无锡天脉聚源传媒科技有限公司 | A kind of method and device for recognizing TV station's icon |
| CN107566907A (en) * | 2017-09-20 | 2018-01-09 | 广东欧珀移动通信有限公司 | video clipping method, device, storage medium and terminal |
-
2018
- 2018-08-28 CN CN201810989015.3A patent/CN109168062B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100039378A1 (en) * | 2008-08-14 | 2010-02-18 | Toshiharu Yabe | Information Processing Apparatus, Method and Program |
| CN105611413A (en) * | 2015-12-24 | 2016-05-25 | 小米科技有限责任公司 | Method and device for adding video clip class markers |
| CN107133631A (en) * | 2016-02-29 | 2017-09-05 | 无锡天脉聚源传媒科技有限公司 | A kind of method and device for recognizing TV station's icon |
| CN105812941A (en) * | 2016-03-31 | 2016-07-27 | 北京金山安全软件有限公司 | Video playing method and device and electronic equipment |
| CN106559712A (en) * | 2016-11-28 | 2017-04-05 | 北京小米移动软件有限公司 | Video playback processing method, device and terminal device |
| CN106792212A (en) * | 2016-12-02 | 2017-05-31 | 乐视控股（北京）有限公司 | A kind of video progress adjusting method, device and electronic equipment |
| CN106713965A (en) * | 2016-12-07 | 2017-05-24 | 珠海格力电器股份有限公司 | Information display method and device |
| CN107566907A (en) * | 2017-09-20 | 2018-01-09 | 广东欧珀移动通信有限公司 | video clipping method, device, storage medium and terminal |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110225411A (en) * | 2019-05-31 | 2019-09-10 | 北京奇艺世纪科技有限公司 | The segment of programme televised live reviews method, system, computer equipment and medium |
| US11924513B2 (en) | 2019-08-18 | 2024-03-05 | Juhaokan Technology Co., Ltd. | Display apparatus and method for display user interface |
| CN110991246A (en) * | 2019-10-31 | 2020-04-10 | 天津市国瑞数码安全系统股份有限公司 | Video detection method and system |
| CN113591523A (en) * | 2020-04-30 | 2021-11-02 | 聚好看科技股份有限公司 | Display device and experience value updating method |
| CN113591523B (en) * | 2020-04-30 | 2023-11-24 | 聚好看科技股份有限公司 | Display device and experience value updating method |
| WO2021232978A1 (en) * | 2020-05-18 | 2021-11-25 | Oppo广东移动通信有限公司 | Video processing method and apparatus, electronic device and computer readable medium |
| WO2022152202A1 (en) * | 2021-01-14 | 2022-07-21 | 海信视像科技股份有限公司 | Display device, external device and playing mode switching method |
| CN113949827A (en) * | 2021-09-30 | 2022-01-18 | 安徽尚趣玩网络科技有限公司 | Video content fusion method and device |
| CN113949827B (en) * | 2021-09-30 | 2023-04-07 | 安徽尚趣玩网络科技有限公司 | Video content fusion method and device |
| CN115334351A (en) * | 2022-08-02 | 2022-11-11 | Vidaa国际控股(荷兰)公司 | Display device and adaptive image quality adjusting method |
| CN115334351B (en) * | 2022-08-02 | 2023-10-31 | Vidaa国际控股(荷兰)公司 | Display equipment and self-adaptive image quality adjusting method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109168062B (en) | 2020-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109168062A (en) | Methods of exhibiting, device, terminal device and the storage medium of video playing | |
| CN104219785B (en) | Real-time video providing method, device and server, terminal device | |
| CN106791893A (en) | Net cast method and device | |
| CN106507207B (en) | The method and device interacted in live streaming application | |
| CN109618184A (en) | Method for processing video frequency and device, electronic equipment and storage medium | |
| CN104618218B (en) | Message prompt method and device | |
| CN110188236A (en) | A kind of recommended method of music, apparatus and system | |
| CN106506335B (en) | The method and device of sharing video frequency file | |
| CN106792004A (en) | Content item method for pushing, apparatus and system | |
| CN109729372B (en) | Live broadcast room switching method, device, terminal, server and storage medium | |
| CN109872297A (en) | Image processing method and device, electronic equipment and storage medium | |
| TW202245466A (en) | Video recording method, electronic equipment and computer-readable storage medium | |
| KR20160024002A (en) | Method for providing visual sound image and electronic device implementing the same | |
| CN109348239A (en) | Piece stage treatment method, device, electronic equipment and storage medium is broadcast live | |
| CN109257645A (en) | Video cover generation method and device | |
| US20210029304A1 (en) | Methods for generating video, electronic device and storage medium | |
| CN110413114A (en) | Interaction control method and device under video scene, server, readable storage medium storing program for executing | |
| CN108833991A (en) | Video caption display methods and device | |
| US20220137756A1 (en) | Method for displaying interactive content, electronic device, and storage medium | |
| CN109862380A (en) | Video data handling procedure, device and server, electronic equipment and storage medium | |
| CN109819288A (en) | Determination method, apparatus, electronic equipment and the storage medium of advertisement dispensing video | |
| CN108108671A (en) | Description of product information acquisition method and device | |
| CN108898591A (en) | Methods of marking and device, electronic equipment, the readable storage medium storing program for executing of picture quality | |
| CN109670632A (en) | The predictor method of ad click rate, the estimating device of ad click rate, electronic equipment and storage medium | |
| CN106649712A (en) | Method and device for inputting expression information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |