CN110611846A - Automatic short video editing method - Google Patents

Automatic short video editing method Download PDF

Info

Publication number
CN110611846A
CN110611846A CN201910882919.0A CN201910882919A CN110611846A CN 110611846 A CN110611846 A CN 110611846A CN 201910882919 A CN201910882919 A CN 201910882919A CN 110611846 A CN110611846 A CN 110611846A
Authority
CN
China
Prior art keywords
video
clipping
target
frames
frame
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
CN201910882919.0A
Other languages
Chinese (zh)
Inventor
丁薇
谢交阳
刘洋
黄山山
昂龙
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.)
Anhui Shixuan Culture Technology Co Ltd
Original Assignee
Anhui Shixuan Culture Technology 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 Anhui Shixuan Culture Technology Co Ltd filed Critical Anhui Shixuan Culture Technology Co Ltd
Priority to CN201910882919.0A priority Critical patent/CN110611846A/en
Publication of CN110611846A publication Critical patent/CN110611846A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G11INFORMATION STORAGE
    • G11BINFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
    • G11B27/00Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
    • G11B27/02Editing, e.g. varying the order of information signals recorded on, or reproduced from, record carriers
    • G11B27/031Electronic editing of digitised analogue information signals, e.g. audio or video signals
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/44Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
    • H04N21/44008Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • H04N21/472End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
    • H04N21/47205End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for manipulating displayed content, e.g. interacting with MPEG-4 objects, editing locally
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/83Generation or processing of protective or descriptive data associated with content; Content structuring
    • H04N21/84Generation or processing of descriptive data, e.g. content descriptors
    • H04N21/8405Generation or processing of descriptive data, e.g. content descriptors represented by keywords

Abstract

The invention discloses a short video automatic clipping method, which divides a video material into a plurality of video units, respectively carries out quality diagnosis, abandons the frame number with abnormal condition in each video unit, can avoid the condition of poor video quality in the clipped short video, carries out foreground target identification on a reference frame by extracting a first reference frame and a plurality of second reference frames, can preliminarily know the foreground target in a video image, can more accurately identify the main target shot by carrying out re-identification on the adjacent reference frames with the same foreground target according to time sequence information and target motion information, thereby being used as the basis of video clipping, respectively classifies each video segment with the same main target, matches keywords according to the main target, selects the video segment with the most common keywords from each video segment for clipping, short videos which can reflect the video theme most in the video materials can be effectively edited.

Description

Automatic short video editing method
Technical Field
The invention relates to the technical field of video editing, in particular to a short video automatic editing method.
Background
With the development and popularization of networks, short videos are gradually accepted by the public as a new media form, many self-media and individuals select short videos as a mode for expressing self viewpoints and showing self life, but the use of video processing software by editing short videos has a certain threshold, and not all people have good video processing software operation bases, so that obstacles which are difficult to overcome are brought to the short video editing of the people.
Disclosure of Invention
In view of the above, the present invention is directed to a short video automatic editing method.
Based on the above purpose, the present invention provides a short video automatic clipping method, which comprises:
dividing a video material into a plurality of video units;
performing quality diagnosis on each video unit, and discarding the number of frames with abnormal conditions in each video unit;
extracting a first frame in a video unit as a first reference frame, extracting a plurality of second reference frames by taking the first reference frame as a base point and a set frame number as an interval, and performing foreground target identification on each reference frame;
according to the time sequence information and the target motion information, re-identifying the adjacent reference frames with the same foreground target to obtain a main target in a video clip between the adjacent reference frames;
classifying the video clips with the same main body target respectively, and matching keywords according to the main body target;
selecting the video segments with the most common keywords from all the video segments as clipping materials;
and cutting the clipped material according to the target short video duration, and splicing into a short video.
Preferably, when performing quality diagnosis on video units and discarding the number of frames in each of the video units with abnormal conditions, the method further comprises:
and calculating the number of frames with abnormal conditions in the video units, wherein the abnormal conditions comprise abnormal definition, abnormal brightness, color cast and abnormal gray level, deleting the number of frames with abnormal conditions from each video unit, and reserving the video segments with the residual continuous number of frames in the video units larger than a threshold value.
Preferably, when the clip material is cut, the method further comprises:
the minimum duration of the cut clip material is not lower than the proportional limit of the duration of the target short video.
Preferably, when the cut clip material is spliced into a short video, the method further includes:
transition effects are added between each cut clip material.
Preferably, when a transition special effect is added between the cut clip materials, the method further comprises:
and (4) a transition special effect library is proposed in advance, transition special effects in the transition special effect library are classified according to applicable chromatic aberration, and the transition special effects are randomly selected and added from the applicable transition special effect classification according to edge chromatic aberration between adjacent clipping materials.
Preferably, when the clip material is cut, the audio frequency spectrum of the clip material is analyzed, and if the cut start point is not in the trough of the audio frequency spectrum, the cut start point is forwards or backwards forwards extended to the nearest trough of the audio frequency spectrum.
From the above, it can be seen that the short video automatic clipping method provided by the present invention can avoid the situation of poor video quality in the clipped short video by dividing the video material into a plurality of video units and performing quality diagnosis respectively, abandoning the number of frames with abnormal conditions in each video unit, and can identify the foreground object of the reference frame by extracting the first reference frame and the second reference frames, so as to primarily know the foreground object in the video image, and can identify the adjacent reference frames with the same foreground object again according to the time sequence information and the object motion information, so as to identify the main object shot by video more accurately, so that the video clips with the same main object are used as the basis of video clipping, and the video clips with the most common keywords are selected from the video clips by classifying the video clips respectively and matching the keywords according to the main object, short videos which can reflect the video theme most in the video materials can be effectively edited.
Drawings
Fig. 1 is a flowchart illustrating a short video clipping method according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to specific embodiments and the accompanying drawings.
It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are used for distinguishing two entities with the same name but different names or different parameters, and it should be noted that "first" and "second" are merely for convenience of description and should not be construed as limitations of the embodiments of the present invention, and they are not described in any more detail in the following embodiments.
A short video automatic clipping method comprising the steps of:
s101, dividing a video material into a plurality of video units;
the number of the video units is determined according to the target short video time length and the total time length of the video material, and specifically, 30% of the target short video time length can be used as the standard time length of the video units.
S102, performing quality diagnosis on each video unit, and discarding the number of frames with abnormal conditions in each video unit.
S103, extracting a first frame in a video unit as a first reference frame, extracting a plurality of second reference frames by taking the first reference frame as a base point and a set frame number as an interval, and performing foreground target identification on each reference frame;
in the foreground object identification, a deep learning convolutional neural network can be utilized to perform single-frame identification on the video image of each reference frame, the set frame number is adjusted according to the average change rate of the color in the video unit, if the average change rate of the color in the video unit is higher, the set frame number is shortened, and if the average change rate of the color in the video unit is lower, the set frame number is prolonged.
S104, according to the time sequence information and the target motion information, re-identifying the adjacent reference frames with the same foreground target to obtain a main target in the video clip between the adjacent reference frames;
the problem that a single frame image cannot completely identify and detect the target can be solved, the video information at different moments is integrated, the foreground target always generates certain dynamic change for the front reference frame and the rear reference frame of the same foreground target, and the condition that the foreground target is identified by mistake in single frame identification can be effectively eliminated by combining time sequence change and motion change.
S105, classifying the video clips with the same main body target respectively, and matching keywords according to the main body target;
the method is characterized in that contents irrelevant to the video theme to be shot or useless contents shot due to mistaken shooting and shooting waiting time can be shot in the video shooting, and the contents with high relevance to the video theme and the contents with low relevance can be distinguished by respectively classifying the video segments with the same main object, so that a basis is provided for subsequent cutting and splicing, the contents irrelevant to the video theme in the target short video are avoided, and the keywords can be obtained through artificial intelligence recognition, such as lakes, bridges, automobiles, forests, skyscrapers and the like.
S106, selecting the video segments with the most common keywords from the video segments as the clipping materials.
The finally edited short video subjects can be further consistent through the step, and even if the content of the source video material is disordered, short videos with the highest relevance to the video subjects can be edited from the video material.
And S107, cutting the clip material according to the target short video duration, and splicing into a short video.
The invention divides the video material into a plurality of video units, carries out quality diagnosis respectively, abandons the frame number with abnormal condition in each video unit, can avoid the condition of poor video quality in the clipped short video, carries out foreground target identification on the reference frames by extracting the first reference frame and a plurality of second reference frames, can preliminarily know the foreground target in the video image, carries out re-identification on the adjacent reference frames with the same foreground target according to the time sequence information and the target motion information to obtain the main target in the video segment between the adjacent reference frames, can more accurately identify the main target shot by the video, thereby being used as the basis of video clipping, carries out classification respectively on each video segment with the same main target, matches keywords according to the main target, selects the video segment with the most common keywords from each video segment for clipping, short videos which can reflect the video theme most in the video materials can be effectively edited.
In one embodiment, when the video unit is diagnosed and the number of frames in each video unit having an abnormal condition is discarded, the method further comprises:
and calculating the number of frames with abnormal conditions in the video units, wherein the abnormal conditions comprise abnormal definition, abnormal brightness, abnormal color cast and abnormal gray level, deleting the number of frames with the abnormal conditions from each video unit, and reserving video segments with the residual continuous number of frames in the video units larger than a threshold value.
Since the problem of poor quality of some segments is often encountered in video capturing, and if the video frames with abnormal conditions are simply deleted, the remaining video segments may lack continuity, in this embodiment, only the video segments with the remaining continuous frame number greater than the threshold are retained.
As an embodiment, when the clip material is cut, the method further includes that the minimum length of the cut clip material is not less than a ratio limit of the length of the target short video, where the ratio limit is the minimum percentage limit of the length of the target short video, and if the length of the target short video is 3 minutes, the ratio limit is 10%, that is, the minimum length of the cut clip material is not less than 18 seconds.
As an embodiment, when splicing the cut clip material into a short video, the method further includes:
transition special effects are added among the cut editing materials, so that the ornamental value and the fluency of the short video are improved.
As an embodiment, when adding transition special effects between the clipped clip materials, the method further includes:
and (4) a transition special effect library is proposed in advance, transition special effects in the transition special effect library are classified according to applicable chromatic aberration, and the transition special effects are randomly selected and added from the applicable transition special effect classification according to edge chromatic aberration between adjacent clipping materials.
In the process of video editing, because the edge color differences between adjacent editing materials are different, different transition special effects need to be adopted aiming at different edge color differences, so that the connection transition between video segments is smoother.
As an implementation mode, when a clipping material is clipped, an audio frequency spectrum of the clipping material is analyzed, if a clipping start point is not in a trough of the audio frequency spectrum, the clipping start point is forwards or backwards extended to the nearest trough of the audio frequency spectrum, a picture part is usually considered in a traditional video clip, but the connection between video segments is very hard and discontinuous when the clipping splicing is carried out due to the complex color of the picture part, and the audio frequency spectrum is analyzed.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the idea of the invention, also features in the above embodiments or in different embodiments may be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity.
In addition, well known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures for simplicity of illustration and discussion, and so as not to obscure the invention. Furthermore, devices may be shown in block diagram form in order to avoid obscuring the invention, and also in view of the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the present invention is to be implemented (i.e., specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the invention, it should be apparent to one skilled in the art that the invention can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.
While the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic ram (dram)) may use the discussed embodiments.
The embodiments of the invention are intended to embrace all such alternatives, modifications and variances that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements and the like that may be made without departing from the spirit and principles of the invention are intended to be included within the scope of the invention.

Claims (6)

1. A method for short video automatic clipping, the method comprising:
dividing a video material into a plurality of video units;
performing quality diagnosis on each video unit, and discarding the number of frames with abnormal conditions in each video unit;
extracting a first frame in a video unit as a first reference frame, extracting a plurality of second reference frames by taking the first reference frame as a base point and a set frame number as an interval, and performing foreground target identification on each reference frame;
according to the time sequence information and the target motion information, re-identifying the adjacent reference frames with the same foreground target to obtain a main target in a video clip between the adjacent reference frames;
classifying the video clips with the same main body target respectively, and matching keywords according to the main body target;
selecting the video segments with the most common keywords from all the video segments as clipping materials;
and cutting the clipped material according to the target short video duration, and splicing into a short video.
2. The method of claim 1, wherein when performing quality diagnostics on video units and discarding the number of frames in each of the video units in which an abnormal condition exists, the method further comprises:
and calculating the number of frames with abnormal conditions in the video units, wherein the abnormal conditions comprise abnormal definition, abnormal brightness, color cast and abnormal gray level, deleting the number of frames with abnormal conditions from each video unit, and reserving the video segments with the residual continuous number of frames in the video units larger than a threshold value.
3. The short video automatic clipping method according to claim 1, wherein when clipping material, the method further comprises:
the minimum duration of the cut clip material is not lower than the proportional limit of the duration of the target short video.
4. The short video automatic clipping method according to claim 1, wherein when the clipped clipping material is spliced into a short video, the method further comprises:
transition effects are added between each cut clip material.
5. The short video automatic clipping method according to claim 4, wherein when adding transition effects between clipped clip material, the method further comprises:
and (4) a transition special effect library is proposed in advance, transition special effects in the transition special effect library are classified according to applicable chromatic aberration, and the transition special effects are randomly selected and added from the applicable transition special effect classification according to edge chromatic aberration between adjacent clipping materials.
6. The method of claim 1, wherein when clipping material, the audio spectrum of the clipping material is analyzed, and if the clipping start point is not at a valley in the audio spectrum, the clipping start point is advanced or backward to the nearest audio spectrum valley.
CN201910882919.0A 2019-09-18 2019-09-18 Automatic short video editing method Pending CN110611846A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910882919.0A CN110611846A (en) 2019-09-18 2019-09-18 Automatic short video editing method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910882919.0A CN110611846A (en) 2019-09-18 2019-09-18 Automatic short video editing method

Publications (1)

Publication Number Publication Date
CN110611846A true CN110611846A (en) 2019-12-24

Family

ID=68892398

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910882919.0A Pending CN110611846A (en) 2019-09-18 2019-09-18 Automatic short video editing method

Country Status (1)

Country Link
CN (1) CN110611846A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111246124A (en) * 2020-03-09 2020-06-05 三亚至途科技有限公司 Multimedia digital fusion method and device
CN111541946A (en) * 2020-07-10 2020-08-14 成都品果科技有限公司 Automatic video generation method and system for resource matching based on materials
CN113329261A (en) * 2021-08-02 2021-08-31 北京达佳互联信息技术有限公司 Video processing method and device
CN113473182A (en) * 2021-09-06 2021-10-01 腾讯科技(深圳)有限公司 Video generation method and device, computer equipment and storage medium
CN113810766A (en) * 2021-11-17 2021-12-17 深圳市速点网络科技有限公司 Video clip combination processing method and system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106021496A (en) * 2016-05-19 2016-10-12 海信集团有限公司 Video search method and video search device
US20190026629A1 (en) * 2017-07-19 2019-01-24 Syntiant Systems and Methods for Overshoot Compensation
CN110019880A (en) * 2017-09-04 2019-07-16 优酷网络技术(北京)有限公司 Video clipping method and device
CN110121104A (en) * 2018-02-06 2019-08-13 上海全土豆文化传播有限公司 Video clipping method and device
CN110198432A (en) * 2018-10-30 2019-09-03 腾讯科技(深圳)有限公司 Processing method, device, computer-readable medium and the electronic equipment of video data

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106021496A (en) * 2016-05-19 2016-10-12 海信集团有限公司 Video search method and video search device
US20190026629A1 (en) * 2017-07-19 2019-01-24 Syntiant Systems and Methods for Overshoot Compensation
CN110019880A (en) * 2017-09-04 2019-07-16 优酷网络技术(北京)有限公司 Video clipping method and device
CN110121104A (en) * 2018-02-06 2019-08-13 上海全土豆文化传播有限公司 Video clipping method and device
CN110198432A (en) * 2018-10-30 2019-09-03 腾讯科技(深圳)有限公司 Processing method, device, computer-readable medium and the electronic equipment of video data

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111246124A (en) * 2020-03-09 2020-06-05 三亚至途科技有限公司 Multimedia digital fusion method and device
CN111246124B (en) * 2020-03-09 2021-05-25 三亚至途科技有限公司 Multimedia digital fusion method and device
CN111541946A (en) * 2020-07-10 2020-08-14 成都品果科技有限公司 Automatic video generation method and system for resource matching based on materials
CN113329261A (en) * 2021-08-02 2021-08-31 北京达佳互联信息技术有限公司 Video processing method and device
CN113329261B (en) * 2021-08-02 2021-12-07 北京达佳互联信息技术有限公司 Video processing method and device
CN113473182A (en) * 2021-09-06 2021-10-01 腾讯科技(深圳)有限公司 Video generation method and device, computer equipment and storage medium
CN113810766A (en) * 2021-11-17 2021-12-17 深圳市速点网络科技有限公司 Video clip combination processing method and system

Similar Documents

Publication Publication Date Title
CN110611846A (en) Automatic short video editing method
US7880815B2 (en) Method for detecting and eliminating flash scene in digital video
JP4819912B2 (en) Multi-mode region of interest video object segmentation
US7630561B2 (en) Image processing
EP1416490A1 (en) Systems and methods for automatically editing a video
CA2498664C (en) Method of video coding images comprising address information
US20070263128A1 (en) Key-frame extraction from video
KR101709085B1 (en) Shot Boundary Detection method and apparatus using Convolutional Neural Networks
US20050265581A1 (en) Object detection
US9460533B2 (en) Generating image compositions
US9053355B2 (en) System and method for face tracking
Liensberger et al. Color-based and context-aware skin detection for online video annotation
Hsu et al. Statistical fusion of multiple cues for image tampering detection
US20190384984A1 (en) Method and system for using semantic-segmentation for automatically generating effects and transitions in video productions
US7734096B2 (en) Method and device for discriminating obscene video using time-based feature value
US8223835B2 (en) Categorizing moving objects into familiar colors in video
Men et al. Visual Quality Assessment for Interpolated Slow-Motion Videos Based on a Novel Database
CN113313635A (en) Image processing method, model training method, device and equipment
EP3067859A1 (en) Method and apparatus for generating a superpixel cluster
EP2149099B1 (en) Device and method for processing images to determine a signature of a film
EP2939179B1 (en) Method and apparatus for the segmentation of the image of an eye
Júnior et al. A prnu-based method to expose video device compositions in open-set setups
CN114026874A (en) Video processing method and device, mobile device and readable storage medium
JP2012023727A (en) Detection of semantic video boundaries
CN112653892A (en) Method for realizing transcoding test evaluation by using video characteristics

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