CN110121105A - Editing video generation method and device - Google Patents

Editing video generation method and device Download PDF

Info

Publication number
CN110121105A
CN110121105A CN201810119047.8A CN201810119047A CN110121105A CN 110121105 A CN110121105 A CN 110121105A CN 201810119047 A CN201810119047 A CN 201810119047A CN 110121105 A CN110121105 A CN 110121105A
Authority
CN
China
Prior art keywords
video
alternative videos
editing
original
clipped
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
Application number
CN201810119047.8A
Other languages
Chinese (zh)
Inventor
狄杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alibaba China Co Ltd
Original Assignee
Shanghai Quan Toodou Cultural Communication Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Quan Toodou Cultural Communication Co Ltd filed Critical Shanghai Quan Toodou Cultural Communication Co Ltd
Priority to CN201810119047.8A priority Critical patent/CN110121105A/en
Publication of CN110121105A publication Critical patent/CN110121105A/en
Pending legal-status Critical Current

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/44Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/44Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
    • H04N21/44016Processing 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 splicing one content stream with another content stream, e.g. for substituting a video clip
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/81Monomedia components thereof
    • H04N21/8106Monomedia components thereof involving special audio data, e.g. different tracks for different languages
    • H04N21/8113Monomedia components thereof involving special audio data, e.g. different tracks for different languages comprising music, e.g. song in MP3 format
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/83Generation or processing of protective or descriptive data associated with content; Content structuring
    • H04N21/845Structuring of content, e.g. decomposing content into time segments
    • H04N21/8456Structuring of content, e.g. decomposing content into time segments by decomposing the content in the time domain, e.g. in time segments
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/85Assembly of content; Generation of multimedia applications
    • H04N21/854Content authoring
    • H04N21/8549Creating video summaries, e.g. movie trailer
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00Details of television systems
    • H04N5/222Studio circuitry; Studio devices; Studio equipment ; Cameras comprising an electronic image sensor, e.g. digital cameras, video cameras, TV cameras, video cameras, camcorders, webcams, camera modules for embedding in other devices, e.g. mobile phones, computers or vehicles
    • H04N5/262Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00Details of television systems
    • H04N5/222Studio circuitry; Studio devices; Studio equipment ; Cameras comprising an electronic image sensor, e.g. digital cameras, video cameras, TV cameras, video cameras, camcorders, webcams, camera modules for embedding in other devices, e.g. mobile phones, computers or vehicles
    • H04N5/262Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
    • H04N5/278Subtitling

Abstract

This disclosure relates to a kind of editing video generation method and device, which comprises carry out image recognition to original video, determine the reference object in the original video according to recognition result;According to the reference object determined, the frame that each reference object occurs is determined in the original video;According to the frame that each reference object determined occurs, the alternative videos of each reference object are intercepted in the original video;The reference object editing video of the original video is obtained according to the alternative videos of each reference object.Reference object editing video made of disclosure editing, can quickly, objectively embody original video.

Description

Editing video generation method and device
Technical field
This disclosure relates to video production field more particularly to a kind of editing video generation method and device.
Background technique
For the content for promoting video, it usually needs be video production reference object editing video.Such as when a new electricity When shadow or one grade of new TV will be shown, the publicity of early period is usually carried out using the trailer (editing video) of movie or television. It is all manually leaf through drilling duty at present when being handled video (such as the personnel that take part in a performance for needing editing to go out some video) Then person chart manually goes for the reference object segment in video, reapply the editing tool of localization, by each reference object Performance segment in piece manually spliced, editing.When for massive video, inefficient problem just obviously shows.And Will appear the longer phenomenon of fractional time that the higher star of popularity is gone out by editing, be added to more it is artificial it is subjective because Element.
Summary of the invention
In view of this, the present disclosure proposes a kind of editing video generation method and devices, to solve manually generated bat Take the photograph the one sided problem of object editing video.
According to the one side of the disclosure, a kind of editing video generation method is provided, which comprises
Image recognition is carried out to original video, the reference object in the original video is determined according to recognition result;
According to the reference object determined, the frame that each reference object occurs is determined in the original video;
According to the frame that each reference object determined occurs, each reference object is intercepted in the original video Alternative videos;
The reference object editing video of the original video is obtained according to the alternative videos of each reference object.
In one possible implementation, the alternative videos of each reference object are intercepted in the original video, Include:
The alternative videos of each reference object, the alternative videos packet of the reference object are intercepted in the original video Include the frame that the reference object occurs.
In one possible implementation, the shooting of the original video is obtained according to the alternative videos of each reference object Object editing video, comprising:
According to display weight of the reference object in the alternative videos of the reference object, in the standby of each reference object Select the video to be clipped that each reference object is determined in video;
The reference object editing video of the original video is obtained according to the video to be clipped of each reference object.
In one possible implementation, the display power according to reference object in the alternative videos of the reference object Weight determines the video to be clipped of each reference object in the alternative videos of each reference object, comprising:
Determine the image of reference object display weight shared in the frame picture of the alternative videos of the reference object;
According to the display weight and weight threshold, each shooting is determined in the alternative videos of each reference object The video to be clipped of object.
In one possible implementation, the display power according to reference object in the alternative videos of the reference object Weight determines the video to be clipped of each reference object in the alternative videos of each reference object, comprising:
According to display weight and clarity of the reference object in the alternative videos of the reference object, in each shooting The video to be clipped of each reference object is determined in the alternative videos of object.
In one possible implementation, the method also includes:
Editor's information is added in the reference object editing video, obtains the reference object editor view of the original video Frequently, editor's information includes background music information, picture and text special-effect information and the one of which or any in caption character information Combination.
In one possible implementation, the method also includes:
According to the alternative videos of the reference object intercepted in multiple original videos, the shooting pair of the reference object is obtained As editing video.
According to another aspect of the present disclosure, a kind of editing video-generating device is provided, described device includes:
Reference object identification module determines described original for carrying out image recognition to original video according to recognition result Reference object in video;
Reference object frame determining module, for determining each institute in the original video according to the reference object determined State the frame of reference object appearance;
Alternative videos obtain module, the frame for being occurred according to each reference object determined, in the original view The alternative videos of each reference object are intercepted in frequency;
Editing video acquiring module, for obtaining the shooting pair of the original video according to the alternative videos of each reference object As editing video.
In one possible implementation, the alternative videos obtain module, comprising:
Alternative videos acquisition submodule, for intercepting the alternative videos of each reference object in the original video, The alternative videos of the reference object include the frame that the reference object occurs.
In one possible implementation, the editing video acquiring module, comprising:
Video acquisition submodule to be clipped, for the display according to reference object in the alternative videos of the reference object Weight determines the video to be clipped of each reference object in the alternative videos of each reference object;
Editing video acquisition submodule, for obtaining the bat of the original video according to the video to be clipped of each reference object Take the photograph object editing video.
In one possible implementation, the video acquisition submodule to be clipped, comprising:
Weight determines submodule, for determining the image of reference object in the frame picture of the alternative videos of the reference object In shared display weight;
First video submodule to be clipped is used for according to the display weight and weight threshold, in each reference object Alternative videos in determine the video to be clipped of each reference object.
In one possible implementation, the video acquisition submodule to be clipped, comprising:
Second video submodule to be clipped, for the display according to reference object in the alternative videos of the reference object Weight and clarity determine the video to be clipped of each reference object in the alternative videos of each reference object.
In one possible implementation, described device further include:
Information module is edited, for editor's information to be added in the reference object editing video, obtains the original view Reference object editor's video of frequency, editor's information include background music information, picture and text special-effect information and caption character information In one of which or any combination.
In one possible implementation, described device further include:
Reference object editing video acquiring module, for according to the alternative of the reference object intercepted in multiple original videos Video obtains the reference object editing video of the reference object.
According to another aspect of the present disclosure, a kind of editing video-generating device is provided, comprising:
Processor;
Memory for storage processor executable instruction;
Wherein, the processor is configured to: the step of executing described in above-mentioned editing video generation method.
According to another aspect of the present disclosure, a kind of non-volatile computer readable storage medium storing program for executing is provided, is stored thereon with Computer program instructions, the computer program instructions are realized when being executed by processor described in above-mentioned editing video generation method The step of.
In the disclosure, after carrying out image recognition to original video, the reference object in original video is determined, further according to The reference object determined obtains the alternative videos of the frame that each reference object occurs and each reference object, finally utilizes each bat The alternative videos for taking the photograph object obtain the reference object editing video of original video.In such manner, it is possible to complete from original video, accurate Editing obtain the main contents that each reference object is performed, thus meet obtain what any reference object was performed from original video The demand of content.
According to below with reference to the accompanying drawings to detailed description of illustrative embodiments, the other feature and aspect of the disclosure will become It is clear.
Detailed description of the invention
Comprising in the description and constituting the attached drawing of part of specification and specification together illustrates the disclosure Exemplary embodiment, feature and aspect, and for explaining the principles of this disclosure.
Fig. 1 shows the flow chart of the editing video generation method according to one embodiment of the disclosure;
Fig. 2 shows the flow charts according to the editing video generation method of another embodiment of the disclosure;
Fig. 3 shows the flow chart of the editing video generation method according to another embodiment of the disclosure;
Fig. 4 shows the flow chart of the editing video generation method according to another embodiment of the disclosure;
Fig. 5 shows the flow chart of the editing video generation method according to another embodiment of the disclosure;
Fig. 6 shows the flow chart of the editing video generation method according to another embodiment of the disclosure;
Fig. 7 shows the flow chart of the editing video generation method according to another embodiment of the disclosure;
Fig. 8 shows the application exemplary diagram of the editing video generation method according to one embodiment of the disclosure;
Fig. 9 shows the block diagram of the editing video-generating device according to one embodiment of the disclosure;
Figure 10 shows the block diagram of the editing video-generating device according to another embodiment of the disclosure;
Figure 11 is a kind of block diagram for editing video-generating device shown according to an exemplary embodiment.
Specific embodiment
Various exemplary embodiments, feature and the aspect of the disclosure are described in detail below with reference to attached drawing.It is identical in attached drawing Appended drawing reference indicate element functionally identical or similar.Although the various aspects of embodiment are shown in the attached drawings, remove It non-specifically points out, it is not necessary to attached drawing drawn to scale.
Dedicated word " exemplary " means " being used as example, embodiment or illustrative " herein.Here as " exemplary " Illustrated any embodiment should not necessarily be construed as preferred or advantageous over other embodiments.
In addition, giving numerous details in specific embodiment below to better illustrate the disclosure. It will be appreciated by those skilled in the art that without certain details, the disclosure equally be can be implemented.In some instances, for Method, means, element and circuit well known to those skilled in the art are not described in detail, in order to highlight the purport of the disclosure.
Fig. 1 shows the flow chart of the editing video generation method according to one embodiment of the disclosure, as shown in Figure 1, described cut Collecting video generation method includes:
Step S10 carries out image recognition to original video, determines the shooting pair in the original video according to recognition result As.
Reference object includes the personage in original video, animal etc..Image recognition can be based on the feature of reference object Information identifies each reference object.After collecting image or video flowing containing reference object using video camera or camera, benefit Manually intellectual technology carries out reference object detection and tracking face in the picture, and then carries out to the reference object detected Identification.Image recognition includes Identification of Images, face recognition etc..For example, can be with using the neural network model based on image recognition Reference object of taking part in a performance rapidly and accurately is identified in video.
Step S20 determines what each reference object occurred according to the reference object determined in the original video Frame.
In one possible implementation, the frame of each reference object appearance is determined according to the reference object identified When, including determining a frame in the video clip that the reference object continuously occurs, it is also included within the reference object and occurs Video clip in determine multiple frames.
For example, reference object A is respectively in video clip 1, video clip 2 and video clip 3 in an original video Occur.Then a frame by reference object A in video clip 1 (or five frames) is determined as the frame 1 of reference object A appearance;? A frame (or five frames) in video clip 2 is determined as the frame 2 of reference object A appearance;A frame in video clip 3 (or five frames) are determined as the frame 3 of reference object A appearance.
Further, according to image recognition as a result, calculating reference object in the frame image that reference object occurs The image of itself ratio shared in entire frame image determines this frame when calculated ratio is greater than the threshold value of setting Image is the frame that reference object occurs.
Step S30 is intercepted each described according to the frame that each reference object determined occurs in the original video The alternative videos of reference object.
In one possible implementation, the alternative videos of each reference object extracted can embody each The main contents that reference object is performed in original video.According to the purpose of editing, the alternative videos of different durations can be extracted. For example, extracting the alternative videos of the 10 seconds length including the frame that each reference object occurs, or extracting includes each shooting The alternative videos of 1 second length of the frame that object occurs.
Due to the frame that each reference object for extracting in an original video occurs be it is multiple, according to each reference object The alternative videos for the reference object that the frame of appearance extracts also have multiple.For example, the extraction duration of the alternative videos of reference object A It is 20 seconds.The alternative videos 1 that reference object A is extracted according to the frame 1 that reference object A occurs, when alternative videos 1 are in original video Between range be 00:01:29-00:01:49 video clip.The alternative of reference object A is extracted according to the frame 2 that reference object A occurs Video 2, alternative videos 2 are the video clip that time range is 00:15:19-00:15:39 in original video.According to reference object The frame 3 that A occurs extracts the alternative videos 3 of reference object A, and alternative videos 3 are that time range is 00:28:29- in original video The video clip of 00:28:49.
Step S40 obtains the reference object editing video of the original video according to the alternative videos of each reference object.
In one possible implementation, editing is to obtain video clip after selection, choice, decomposition and group connect The process of one complete editing video.Since the alternative videos of each reference object are that each reference object goes out in original video The embodiment for the main contents drilled, therefore the reference object editing video as made of the alternative videos editing of each reference object, It can completely, accurately embody the content that reference object is performed in original video.For example, by the alternative videos 1 of reference object A, After alternative videos 2 and alternative videos 3 carry out editing, the reference object editing video of duration 1 minute reference object A is generated.Together Reason, when in original video further including reference object B and reference object C, by reference object A, reference object B and reference object After the alternative videos of C carry out editing together, the reference object editing video of original video is obtained.
In the present embodiment, after carrying out image recognition to original video, the reference object in original video, then root are determined The alternative videos of frame and each reference object that each reference object occurs are obtained according to the reference object determined, finally using each The alternative videos of reference object obtain the reference object editing video of original video.Due to including the frame of each reference object appearance The alternative videos of each reference object can embody the main contents that each reference object is performed in original video, therefore editing forms Reference object editing video, can quickly, objectively embody original video.
Fig. 2 shows the flow charts according to the editing video generation method of another embodiment of the disclosure, as shown in Fig. 2, with upper State embodiment the difference is that, step S30 includes: in this method
Step S31, intercepts the alternative videos of each reference object in the original video, the reference object it is standby Selecting video includes the frame that the reference object occurs.
When intercepting alternative videos in original video, reference object that can be different is intercepted according to identical setting duration. Can also be according to reference object in the significance level of original video, different reference objects intercepts the alternative videos of different durations. Such as reference object A is leading role, reference object B is supporting role, then in original video, intercepts a length of when the setting of reference object A 20 seconds alternative videos intercept a length of 10 seconds alternative videos when the setting of reference object B.It can also be according to alternative videos in original Position in beginning video, such as when alternative videos are located at the preceding one third position of original video, when the setting of alternative videos Length is shorter, when alternative videos are located at the middle position or rear one third position of original video, the setting duration of alternative videos It is longer.It the use of the actual frame that reference object occurs is standby when the duration for the actual frame that reference object occurs is less than setting duration Select video.
If N seconds a length of when setting, the alternative videos of a length of N seconds of reference object when being extracted in original video, interception There are many ways to alternative videos.For example, using the frame of reference object appearance as the start frame of alternative videos, from original video The middle video clip alternately video for extracting N seconds.For another example, the frame occurred using the reference object is the end of alternative videos Frame extracts N seconds video clips alternately video from original video.It for another example, is standby with the frame that the reference object occurs The center for selecting video, the alternative videos that each video clip extracted N/2 seconds in left and right is used as from original video.
Fig. 3 shows the flow chart of the editing video generation method according to another embodiment of the disclosure, as shown in figure 3, with upper State embodiment the difference is that, step S40 includes: in this method
Step S41, according to display weight of the reference object in the alternative videos of the reference object, in each shooting The video to be clipped of each reference object is determined in the alternative videos of object.
Step S42 obtains the reference object editing video of the original video according to the video to be clipped of each reference object.
In one possible implementation, it usually will appear multiple shootings pair in a photographed scene of original video As, and only one or two main reference objects, the reference object of other appearance may be unrelated with scene content.Therefore, In the alternative videos where reference object, shooting pair can be indicated by the display weight in the scene of each reference object The percentage contribution of elephant.Actual in use, it is preferred that the alternative videos that reference object individually occurs in frame image, and preferably The image of reference object prevailing alternative videos in frame image.For example, it is preferable to which the image of reference object is in frame image In alternative videos of the ratio 50 or more percent.Display weight can be adjusted according to the demand of editing.According to reference object The video to be clipped of each reference object determined of display weight so that the content in video to be clipped is and shooting pair As real relevant content, but also last editing result is more accurate.
Fig. 4 shows the flow chart of the editing video generation method according to another embodiment of the disclosure, as shown in figure 4, with upper State embodiment the difference is that, step S41 includes: in this method
Step S411 determines that the image of reference object is shared in the frame picture of the alternative videos of the reference object and shows Show weight.
Step S412 is determined in the alternative videos of each reference object according to the display weight and weight threshold The video to be clipped of each reference object.
In one possible implementation, can by calculate reference object image in the image of alternative videos institute The weight proportion accounted for obtains the display weight of reference object.Then, by the weight threshold of the weight proportion being calculated and setting It is compared, the alternative videos that weight proportion is greater than the reference object of weight threshold is determined as the to be clipped of the reference object Video.For example, weight proportion of the reference object A in alternative videos 1 is 0.8, the weight proportion in alternative videos 2 is 0.5, Weight proportion in alternative videos 3 is 0.7, weight threshold 0.6.Since reference object A is in alternative videos 1 and alternative videos 3 weight proportion is greater than weight threshold, and alternative videos 1 and alternative videos 3 are determined as to the video to be clipped of reference object A.
Fig. 5 shows the flow chart of the editing video generation method according to another embodiment of the disclosure, as shown in figure 5, with upper State embodiment the difference is that, this method step S41 further include:
Step S413, according to display weight and clarity of the reference object in the alternative videos of the reference object, The video to be clipped of each reference object is determined in the alternative videos of each reference object.
When determining the alternative videos of reference object according to display weight, the clear of the alternative videos that reference object occurs is considered Clear degree, it is such to obtain in the video to be clipped of synthesis reference object after the alternative videos that clarity does not meet established standards are rejected The picture quality of the video to be clipped arrived is high, and editing effect is good.
Fig. 6 shows the flow chart of the editing video generation method according to another embodiment of the disclosure, as shown in fig. 6, with upper State embodiment the difference is that, this method further include:
Editor's information is added in the reference object editing video, obtains the shooting pair of the original video by step S50 As editing video, editor's information includes wherein one in background music information, picture and text special-effect information and caption character information Kind or any combination.
Editor's information can also be the other information for needing to be added editing video according to the practical application scene later period, In the disclosure without limitation.Editor's information such as background music, picture and text special efficacy and subtitle is added in editing video, can make to shoot Object editing video has better viewing effect.Editor's information further includes the watermark of text or image format.
According to the purpose of editing, the alternative videos of all reference objects can be subjected to editing, also can choose part bat The alternative videos for taking the photograph object carry out editing.
In one possible implementation, it to improve the efficiency for adding editor's information, provides for generating editor's information Template.Select different templates that different video effects can be realized according to different requirements,.It can be according to template original Corresponding editor's information is extracted in video, it can also be manually according to template input editing information.
Such as: the caption character information being added using template into editing video can be from the subtitle of original video The text corresponding with frame fragment extracted is also possible to the content etc. of editorial staff oneself input.Using in various templates can be with The font that the text of editing video will be added carries out the processing such as overstriking, amplification, special efficacy.
For another example, the background music being added using template into editing video can be the Presence of the Moment from original video, run-out The snatch of music extracted in bent or other related audios is also possible to editorial staff's recording or other audios of selection etc..
For another example, the head portrait of the personage in editing video is amplified to the special effect processing etc. of display using template, or will The special effect processings such as the text being added in editing video changed colour, fragment.
Fig. 7 shows the flow chart of the editing video generation method according to another embodiment of the disclosure, as shown in fig. 7, with upper State embodiment the difference is that, this method further include:
Step S60 obtains the reference object according to the alternative videos of the reference object intercepted in multiple original videos Reference object editing video.
It in one possible implementation, can be by reference object when a reference object has multiple original videos The alternative videos intercepted in multiple original videos are trimmed into the reference object editing video of reference object jointly.For example, shooting Object A is occurred in original video 1 and original video 2, and the alternative videos a of reference object A has been intercepted in original video 1 With alternative videos b, the alternative videos c, alternative videos d and alternative videos e of reference object A have been intercepted in original video 2, then will After alternative videos a, alternative videos b, alternative videos c, alternative videos d and alternative videos e carry out editing, obtain reference object A's Reference object editing video.
Using example:
Fig. 8 shows the flow chart of the editing video generation method according to another embodiment of the disclosure, as shown in figure 8, the party Method includes:
Step 1, using image recognition technology, from the original video in left side, multiple reference objects are identified, it is respectively bright Star 1, star 2, star 3 and star 4.And the frame that the reference object determined occurs.According to the frame that each reference object occurs, in original The alternative videos of each reference object are intercepted in beginning video.As shown in figure 8, secondary series is respectively star 1, star 2, star 3 from left to right With the alternative videos of star 4.
Step 2, according to the alternative videos of each reference object, the video to be clipped of each reference object is determined.For example, according to bat The display weight for taking the photograph object determines the video to be clipped of each reference object.
Step 3, according to the video to be clipped of each reference object, automatic editing is carried out, obtains the reference object of original video Editing video.
Step 4, during the editing of the reference object editing video of original video be added background music, picture and text special efficacy, Subtitle file etc. edits information, obtains final in blocks.
Fig. 9 shows the block diagram of the editing video-generating device according to one embodiment of the disclosure, as shown in figure 9, the device packet It includes:
Reference object identification module 41 determines the original according to recognition result for carrying out image recognition to original video Reference object in beginning video;
Reference object frame determining module 42, for being determined in the original video each according to the reference object determined The frame that the reference object occurs;
Alternative videos obtain module 43, the frame for being occurred according to each reference object determined, described original The alternative videos of each reference object are intercepted in video;
Editing video acquiring module 44, for obtaining the shooting of the original video according to the alternative videos of each reference object Object editing video.
Figure 10 shows the block diagram of the editing video-generating device according to another embodiment of the disclosure, as shown in Figure 10, one In the possible implementation of kind, the alternative videos obtain module 43, comprising:
Alternative videos acquisition submodule 431, each shooting pair for the interception setting duration in the original video The alternative videos of elephant, the alternative videos of the reference object include the frame that the reference object occurs.
In one possible implementation, the editing video acquiring module 44, comprising:
Video acquisition submodule 441 to be clipped, for according to reference object in the alternative videos of the reference object It shows weight, the video to be clipped of each reference object is determined in the alternative videos of each reference object;
Editing video acquisition submodule 442, for obtaining the original video according to the video to be clipped of each reference object Reference object editing video.
In one possible implementation, the video acquisition submodule 431 to be clipped, comprising:
Weight determines submodule, for determining the image of reference object in the frame picture of the alternative videos of the reference object In shared display weight;
First video submodule to be clipped is used for according to the display weight and weight threshold, in each reference object Alternative videos in determine the video to be clipped of each reference object.
In one possible implementation, the video acquisition submodule 431 to be clipped, comprising:
Second video submodule to be clipped, for the display according to reference object in the alternative videos of the reference object Weight and clarity determine the video to be clipped of each reference object in the alternative videos of each reference object.
In one possible implementation, described device further include:
Information module 45 is edited, for editor's information to be added in the reference object editing video, is obtained described original Reference object editor's video of video, editor's information include background music information, picture and text special-effect information and caption character letter One of which or any combination in breath.
In one possible implementation, described device further include:
Reference object editing video acquiring module 46, for according to the standby of the reference object intercepted in multiple original videos Video is selected, the reference object editing video of the reference object is obtained.
Figure 11 is a kind of block diagram for editing video-generating device 1900 shown according to an exemplary embodiment.Example Such as, device 1900 may be provided as a server.Referring to Fig.1 1, device 1900 includes processing component 1922, is further wrapped One or more processors and memory resource represented by a memory 1932 are included, it can be by processing component for storing The instruction of 1922 execution, such as application program.The application program stored in memory 1932 may include one or one with On each correspond to one group of instruction module.In addition, processing component 1922 is configured as executing instruction, to execute above-mentioned side Method.
Device 1900 can also include that a power supply module 1926 be configured as the power management of executive device 1900, and one Wired or wireless network interface 1950 is configured as device 1900 being connected to network and input and output (I/O) interface 1958.Device 1900 can be operated based on the operating system for being stored in memory 1932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or similar.
In the exemplary embodiment, a kind of non-volatile computer readable storage medium storing program for executing is additionally provided, for example including calculating The memory 1932 of machine program instruction, above-mentioned computer program instructions can be executed by the processing component 1922 of device 1900 to complete The above method.
The disclosure can be system, method and/or computer program product.Computer program product may include computer Readable storage medium storing program for executing, containing for making processor realize the computer-readable program instructions of various aspects of the disclosure.
Computer readable storage medium, which can be, can keep and store the tangible of the instruction used by instruction execution equipment Equipment.Computer readable storage medium for example can be-- but it is not limited to-- storage device electric, magnetic storage apparatus, optical storage Equipment, electric magnetic storage apparatus, semiconductor memory apparatus or above-mentioned any appropriate combination.Computer readable storage medium More specific example (non exhaustive list) includes: portable computer diskette, hard disk, random access memory (RAM), read-only deposits It is reservoir (ROM), erasable programmable read only memory (EPROM or flash memory), static random access memory (SRAM), portable Compact disk read-only memory (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical coding equipment, for example thereon It is stored with punch card or groove internal projection structure and the above-mentioned any appropriate combination of instruction.Calculating used herein above Machine readable storage medium storing program for executing is not interpreted that instantaneous signal itself, the electromagnetic wave of such as radio wave or other Free propagations lead to It crosses the electromagnetic wave (for example, the light pulse for passing through fiber optic cables) of waveguide or the propagation of other transmission mediums or is transmitted by electric wire Electric signal.
Computer-readable program instructions as described herein can be downloaded to from computer readable storage medium it is each calculate/ Processing equipment, or outer computer or outer is downloaded to by network, such as internet, local area network, wide area network and/or wireless network Portion stores equipment.Network may include copper transmission cable, optical fiber transmission, wireless transmission, router, firewall, interchanger, gateway Computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment are received from network to be counted Calculation machine readable program instructions, and the computer-readable program instructions are forwarded, for the meter being stored in each calculating/processing equipment In calculation machine readable storage medium storing program for executing.
Computer program instructions for executing disclosure operation can be assembly instruction, instruction set architecture (ISA) instructs, Machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more programming languages The source code or object code that any combination is write, the programming language include the programming language-of object-oriented such as Smalltalk, C++ etc., and conventional procedural programming languages-such as " C " language or similar programming language.Computer Readable program instructions can be executed fully on the user computer, partly execute on the user computer, be only as one Vertical software package executes, part executes on the remote computer or completely in remote computer on the user computer for part Or it is executed on server.In situations involving remote computers, remote computer can pass through network-packet of any kind It includes local area network (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as benefit It is connected with ISP by internet).In some embodiments, by utilizing computer-readable program instructions Status information carry out personalized customization electronic circuit, such as programmable logic circuit, field programmable gate array (FPGA) or can Programmed logic array (PLA) (PLA), the electronic circuit can execute computer-readable program instructions, to realize each side of the disclosure Face.
Referring herein to according to the flow chart of the method, apparatus (system) of the embodiment of the present disclosure and computer program product and/ Or block diagram describes various aspects of the disclosure.It should be appreciated that flowchart and or block diagram each box and flow chart and/ Or in block diagram each box combination, can be realized by computer-readable program instructions.
These computer-readable program instructions can be supplied to general purpose computer, special purpose computer or other programmable datas The processor of processing unit, so that a kind of machine is produced, so that these instructions are passing through computer or other programmable datas When the processor of processing unit executes, function specified in one or more boxes in implementation flow chart and/or block diagram is produced The device of energy/movement.These computer-readable program instructions can also be stored in a computer-readable storage medium, these refer to It enables so that computer, programmable data processing unit and/or other equipment work in a specific way, thus, it is stored with instruction Computer-readable medium then includes a manufacture comprising in one or more boxes in implementation flow chart and/or block diagram The instruction of the various aspects of defined function action.
Computer-readable program instructions can also be loaded into computer, other programmable data processing units or other In equipment, so that series of operation steps are executed in computer, other programmable data processing units or other equipment, to produce Raw computer implemented process, so that executed in computer, other programmable data processing units or other equipment Instruct function action specified in one or more boxes in implementation flow chart and/or block diagram.
The flow chart and block diagram in the drawings show system, method and the computer journeys according to multiple embodiments of the disclosure The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation One module of table, program segment or a part of instruction, the module, program segment or a part of instruction include one or more use The executable instruction of the logic function as defined in realizing.In some implementations as replacements, function marked in the box It can occur in a different order than that indicated in the drawings.For example, two continuous boxes can actually be held substantially in parallel Row, they can also be executed in the opposite order sometimes, and this depends on the function involved.It is also noted that block diagram and/or The combination of each box in flow chart and the box in block diagram and or flow chart, can the function as defined in executing or dynamic The dedicated hardware based system made is realized, or can be realized using a combination of dedicated hardware and computer instructions.
The presently disclosed embodiments is described above, above description is exemplary, and non-exclusive, and It is not limited to disclosed each embodiment.Without departing from the scope and spirit of illustrated each embodiment, for this skill Many modifications and changes are obvious for the those of ordinary skill in art field.The selection of term used herein, purport In the principle, practical application or technological improvement to the technology in market for best explaining each embodiment, or lead this technology Other those of ordinary skill in domain can understand each embodiment disclosed herein.

Claims (16)

1. a kind of editing video generation method, which is characterized in that the described method includes:
Image recognition is carried out to original video, the reference object in the original video is determined according to recognition result;
According to the reference object determined, the frame that each reference object occurs is determined in the original video;
According to the frame that each reference object determined occurs, the standby of each reference object is intercepted in the original video Select video;
The reference object editing video of the original video is obtained according to the alternative videos of each reference object.
2. the method according to claim 1, wherein intercepting each reference object in the original video Alternative videos, comprising:
The alternative videos of each reference object are intercepted in the original video, the alternative videos of the reference object include institute State the frame of reference object appearance.
3. the method according to claim 1, wherein being obtained according to the alternative videos of each reference object described original The reference object editing video of video, comprising:
According to display weight of the reference object in the alternative videos of the reference object, in the alternative view of each reference object The video to be clipped of each reference object is determined in frequency;
The reference object editing video of the original video is obtained according to the video to be clipped of each reference object.
4. according to the method described in claim 3, it is characterized in that, according to reference object the reference object alternative videos In display weight, the video to be clipped of each reference object is determined in the alternative videos of each reference object, comprising:
Determine the image of reference object display weight shared in the frame picture of the alternative videos of the reference object;
According to the display weight and weight threshold, each reference object is determined in the alternative videos of each reference object Video to be clipped.
5. according to the method described in claim 3, it is characterized in that, according to reference object the reference object alternative videos In display weight, the video to be clipped of each reference object is determined in the alternative videos of each reference object, comprising:
According to display weight and clarity of the reference object in the alternative videos of the reference object, in each reference object Alternative videos in determine the video to be clipped of each reference object.
6. the method according to claim 1, wherein the method also includes:
Editor's information is added in the reference object editing video, obtains reference object editor's video of the original video, Editor's information includes one of or any group in background music information, picture and text special-effect information and caption character information It closes.
7. the method according to claim 1, wherein the method also includes:
According to the alternative videos of the reference object intercepted in multiple original videos, the reference object for obtaining the reference object is cut Collect video.
8. a kind of editing video-generating device, which is characterized in that described device includes:
Reference object identification module determines the original video according to recognition result for carrying out image recognition to original video In reference object;
Reference object frame determining module, for determining each bat in the original video according to the reference object determined Take the photograph the frame of object appearance;
Alternative videos obtain module, the frame for being occurred according to each reference object determined, in the original video Intercept the alternative videos of each reference object;
Editing video acquiring module, the reference object for obtaining the original video according to the alternative videos of each reference object are cut Collect video.
9. device according to claim 8, which is characterized in that the alternative videos obtain module, comprising:
Alternative videos acquisition submodule, it is described for intercepting the alternative videos of each reference object in the original video The alternative videos of reference object include the frame that the reference object occurs.
10. device according to claim 8, which is characterized in that the editing video acquiring module, comprising:
Video acquisition submodule to be clipped, for being weighed according to display of the reference object in the alternative videos of the reference object Weight determines the video to be clipped of each reference object in the alternative videos of each reference object;
Editing video acquisition submodule, for obtaining the shooting pair of the original video according to the video to be clipped of each reference object As editing video.
11. device according to claim 10, which is characterized in that the video acquisition submodule to be clipped, comprising:
Weight determines submodule, for determining the image of the reference object institute in the frame picture of the alternative videos of the reference object The display weight accounted for;
First video submodule to be clipped is used for according to the display weight and weight threshold, in the standby of each reference object Select the video to be clipped that each reference object is determined in video.
12. device according to claim 10, which is characterized in that the video acquisition submodule to be clipped, comprising:
Second video submodule to be clipped, for the display weight according to reference object in the alternative videos of the reference object And clarity, the video to be clipped of each reference object is determined in the alternative videos of each reference object.
13. device according to claim 8, which is characterized in that described device further include:
Information module is edited, for editor's information to be added in the reference object editing video, obtains the original video Reference object editor's video, editor's information include in background music information, picture and text special-effect information and caption character information One of or any combination.
14. device according to claim 8, which is characterized in that described device further include:
Reference object editing video acquiring module, for the alternative view according to the reference object intercepted in multiple original videos Frequently, the reference object editing video of the reference object is obtained.
15. a kind of editing video-generating device characterized by comprising
Processor;
Memory for storage processor executable instruction;
Wherein, the processor is configured to: perform claim require any one of 1 to 7 described in method.
16. a kind of non-volatile computer readable storage medium storing program for executing, is stored thereon with computer program instructions, which is characterized in that institute It states and realizes method described in any one of claim 1 to 7 when computer program instructions are executed by processor.
CN201810119047.8A 2018-02-06 2018-02-06 Editing video generation method and device Pending CN110121105A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810119047.8A CN110121105A (en) 2018-02-06 2018-02-06 Editing video generation method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810119047.8A CN110121105A (en) 2018-02-06 2018-02-06 Editing video generation method and device

Publications (1)

Publication Number Publication Date
CN110121105A true CN110121105A (en) 2019-08-13

Family

ID=67519974

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810119047.8A Pending CN110121105A (en) 2018-02-06 2018-02-06 Editing video generation method and device

Country Status (1)

Country Link
CN (1) CN110121105A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110545408A (en) * 2019-09-06 2019-12-06 苏州凌瑞智能技术有限公司 intelligent manufacturing display system and method based on intelligent service platform
CN110855904A (en) * 2019-11-26 2020-02-28 Oppo广东移动通信有限公司 Video processing method, electronic device and storage medium
CN110996112A (en) * 2019-12-05 2020-04-10 成都市喜爱科技有限公司 Video editing method, device, server and storage medium
CN112135046A (en) * 2020-09-23 2020-12-25 维沃移动通信有限公司 Video shooting method, video shooting device and electronic equipment

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103535023A (en) * 2011-05-18 2014-01-22 高智83基金会有限责任公司 Video summary including a particular person
CN104796781A (en) * 2015-03-31 2015-07-22 小米科技有限责任公司 Video clip extraction method and device
CN105493512A (en) * 2014-12-14 2016-04-13 深圳市大疆创新科技有限公司 Video processing method, video processing device and display device
US20170064247A1 (en) * 2014-12-14 2017-03-02 SZ DJI Technology Co., Ltd. System and method for supporting selective backtracking data recording

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103535023A (en) * 2011-05-18 2014-01-22 高智83基金会有限责任公司 Video summary including a particular person
CN105493512A (en) * 2014-12-14 2016-04-13 深圳市大疆创新科技有限公司 Video processing method, video processing device and display device
US20170064247A1 (en) * 2014-12-14 2017-03-02 SZ DJI Technology Co., Ltd. System and method for supporting selective backtracking data recording
CN104796781A (en) * 2015-03-31 2015-07-22 小米科技有限责任公司 Video clip extraction method and device

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110545408A (en) * 2019-09-06 2019-12-06 苏州凌瑞智能技术有限公司 intelligent manufacturing display system and method based on intelligent service platform
CN110855904A (en) * 2019-11-26 2020-02-28 Oppo广东移动通信有限公司 Video processing method, electronic device and storage medium
WO2021104242A1 (en) * 2019-11-26 2021-06-03 Oppo广东移动通信有限公司 Video processing method, electronic device, and storage medium
CN110996112A (en) * 2019-12-05 2020-04-10 成都市喜爱科技有限公司 Video editing method, device, server and storage medium
WO2021109952A1 (en) * 2019-12-05 2021-06-10 成都市喜爱科技有限公司 Video editing method, apparatus and server, and computer readable storage medium
CN112135046A (en) * 2020-09-23 2020-12-25 维沃移动通信有限公司 Video shooting method, video shooting device and electronic equipment

Similar Documents

Publication Publication Date Title
CN110121105A (en) Editing video generation method and device
US8879788B2 (en) Video processing apparatus, method and system
US20210098024A1 (en) Short video synthesis method and apparatus, and device and storage medium
CN108288027A (en) A kind of detection method of picture quality, device and equipment
CN110121116A (en) Video generation method and device
CN109086780B (en) Method and device for detecting electrode plate burrs
CN108683924A (en) A kind of method and apparatus of video processing
CN104902168B (en) A kind of image combining method, device and capture apparatus
CN106162222B (en) A kind of method and device of video lens cutting
CN110309353A (en) Video index method and device
CN110121104A (en) Video clipping method and device
CN110856039A (en) Video processing method and device and storage medium
CN109819338A (en) A kind of automatic editing method, apparatus of video and portable terminal
US9305600B2 (en) Automated video production system and method
CN104780341B (en) A kind of information processing method and information processing unit
CN109587396A (en) Image pickup method and filming apparatus
CN111754267B (en) Data processing method and system based on block chain
US10657379B2 (en) Method and system for using semantic-segmentation for automatically generating effects and transitions in video productions
CN104185032B (en) A kind of video frequency identifying method and system
US20200304755A1 (en) Aspect ratio conversion with machine learning
CN110211590A (en) A kind of processing method, device, terminal device and the storage medium of meeting hot spot
CN110121033A (en) Video categorization and device
TW201913562A (en) Device and method for generating panorama image
CN110062132B (en) Theater performance reconstruction method and device
US10943127B2 (en) Media processing

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
TA01 Transfer of patent application right

Effective date of registration: 20200521

Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province

Applicant after: Alibaba (China) Co.,Ltd.

Address before: 200241 room 1162, building 555, Dongchuan Road, Shanghai, Minhang District

Applicant before: SHANGHAI QUANTUDOU CULTURE COMMUNICATION Co.,Ltd.

TA01 Transfer of patent application right