CN111970538A - Teaching video processing method and system - Google Patents

Teaching video processing method and system Download PDF

Info

Publication number
CN111970538A
CN111970538A CN202010875240.1A CN202010875240A CN111970538A CN 111970538 A CN111970538 A CN 111970538A CN 202010875240 A CN202010875240 A CN 202010875240A CN 111970538 A CN111970538 A CN 111970538A
Authority
CN
China
Prior art keywords
video
teaching
subdata
image
data
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
CN202010875240.1A
Other languages
Chinese (zh)
Inventor
樊星
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.)
Shanghai Squirrel Classroom Artificial Intelligence Technology Co Ltd
Original Assignee
Shanghai Squirrel Classroom Artificial Intelligence 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 Shanghai Squirrel Classroom Artificial Intelligence Technology Co Ltd filed Critical Shanghai Squirrel Classroom Artificial Intelligence Technology Co Ltd
Priority to CN202010875240.1A priority Critical patent/CN111970538A/en
Publication of CN111970538A publication Critical patent/CN111970538A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
    • H04N21/23424—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving splicing one content stream with another content stream, e.g. for inserting or substituting an advertisement
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B5/00—Electrically-operated educational appliances
    • G09B5/06—Electrically-operated educational appliances with both visual and audible presentation of the material to be studied
    • G09B5/065—Combinations of audio and video presentations, e.g. videotapes, videodiscs, television systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/233—Processing of audio elementary streams
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/439—Processing of audio elementary streams
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
    • H04N21/44016—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving splicing one content stream with another content stream, e.g. for substituting a video clip
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
    • H04N21/4756—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for rating content, e.g. scoring a recommended movie
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/81—Monomedia components thereof
    • H04N21/816—Monomedia components thereof involving special video data, e.g 3D video

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Educational Administration (AREA)
  • Educational Technology (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Marketing (AREA)
  • Television Signal Processing For Recording (AREA)

Abstract

The invention provides a teaching video processing method and a system, which are characterized in that corresponding original teaching video data are generated by shooting a teaching process at multiple angles, then video quality processing pretreatment, splicing treatment and quality judgment treatment are carried out on the original teaching video data, and finally a teaching spliced video with the optimal video quality is taken as a final teaching video.

Description

Teaching video processing method and system
Technical Field
The invention relates to the technical field of intelligent teaching, in particular to a teaching video processing method and a system.
Background
At present, intelligent teaching needs to execute teaching of preset courses by means of corresponding teaching videos, existing teaching videos are generally pre-recorded plane teaching videos, and although the teaching videos can be manufactured in a standardized mode and the manufacturing efficiency of the teaching videos is improved, the teaching videos manufactured and formed in the mode are too single in content and monotonous in video image quality, students cannot experience immersive experience in the process of watching the teaching videos, and meanwhile the display quality of the teaching videos is also reduced.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a teaching video processing method and a system, which comprises the steps of shooting a preset teaching process from two different directions, correspondingly obtaining two original video data related to the preset teaching process, respectively carrying out video quality processing pretreatment on the two original video data, correspondingly obtaining two pretreated video data meeting a preset image quality condition and/or a preset sound quality condition, screening the pretreated video data according to the shooting directions, thus obtaining two video subdata sets related to different shooting directions, sequentially splicing the video subdata contained in the two video subdata sets according to the shooting time sequence, correspondingly obtaining a teaching spliced video, and determining the respective image picture transition continuity degree and sound transition continuity degree of the teaching spliced video, the quality of all the teaching spliced videos is sequenced, so that the optimal teaching spliced video is converted into a three-dimensional teaching video; therefore, the teaching video processing method and the system can ensure that the teaching video can be updated to have higher presentation quality on image quality and sound quality, improve the immersion of users during the watching process and improve the watching quality of the teaching video.
The invention provides a teaching video processing method, which comprises the following steps:
step S1, shooting a preset teaching process from two different directions so as to correspondingly obtain two original video data related to the preset teaching process, and respectively carrying out video quality processing pretreatment on the two original video data so as to correspondingly obtain two pretreated video data meeting preset image quality conditions and/or preset sound quality conditions;
step S2, according to the shooting direction, obtaining two video subdata sets corresponding to two shooting directions from the two preprocessed video data, wherein each video subdata set corresponds to one shooting direction, each video subdata set comprises N video subdata which are connected back and forth on a shooting time sequence, the lengths of the shooting time periods corresponding to all the video subdata are equal, and the N video subdata correspond to the N shooting time periods respectively;
step S3, splicing M times of video subdata according to the shooting time sequence to obtain M teaching spliced videos; wherein, every splicing operation comprises: randomly selecting N1 video subdata from one video subdata set, randomly selecting N2 video subdata from another video subdata set, and selecting N1+ N2 as N; the shooting time periods corresponding to the N1 pieces of video sub-data and the shooting time periods corresponding to the N2 pieces of video sub-data jointly constitute the N shooting time periods; splicing the N1 pieces of video subdata and the N2 pieces of video subdata in sequence according to a shooting time sequence, thereby obtaining a teaching spliced video corresponding to the splicing operation;
and step S4, determining the video goodness of each teaching mosaic video in the M teaching mosaic videos, determining the goodness sequence of the M teaching mosaic videos according to the video goodness, and taking the teaching mosaic video with the optimal video goodness as the final teaching video.
In one embodiment, in the step S1, a preset teaching process is photographed from two different orientations to correspondingly obtain two original video data related to the preset teaching process, and the two original video data are respectively subjected to video quality processing preprocessing, so that two preprocessed video data meeting a preset image quality condition and/or a preset sound quality condition are correspondingly obtained,
step S101, shooting the preset teaching process from two different view angle directions which are mutually crossed, so as to obtain two groups of original video data which have parallax relation and are related to the preset teaching process;
step S102, performing image and sound separation processing on each group of original video data to obtain image data information and sound data information corresponding to each group of original video data, and respectively determining an average image resolution value and an average sound signal-to-noise ratio value corresponding to each group of original video data according to the image data information and the sound data information corresponding to each group of original video data;
step S103, if the average image resolution is smaller than a preset image resolution threshold, performing pixel detail restoration on the image data information, so as to enable the average image resolution to be greater than or equal to the preset image resolution threshold, or, if the average sound signal-to-noise ratio value is smaller than a preset signal-to-noise ratio threshold, performing background noise filtering processing on the sound data information, so as to enable the average signal-to-noise ratio value to be greater than or equal to the preset signal-to-noise ratio threshold;
step S104, recombining the image data information of which the average image resolution is greater than or equal to the preset image resolution threshold and the sound data information of which the average sound signal-to-noise ratio is greater than or equal to the preset signal-to-noise ratio threshold, thereby obtaining the preprocessed video data.
In one embodiment, in step S4, determining the video goodness of each of the M teaching videos spliced together, determining the goodness sequence of the M teaching videos spliced together according to the video goodness, and using the teaching video spliced together with the optimal video goodness as the final teaching video specifically includes:
step S401, the following operation steps S4011-4013 are executed for each teaching mosaic video, so that the video goodness of M teaching mosaic videos is obtained:
step S4011, determining the image picture transition consistency degree between the last image frame of the previous video subdata and the first image frame of the next video subdata in every two adjacent video subdata in the current teaching splicing video;
step S4012, determining the sound transition consistency degree between the last section of sound segment of the previous video subdata and the first section of sound segment of the next video subdata in every two adjacent video subdata in the current teaching splicing video;
step S4013, determining video goodness of the current teaching mosaic video according to image picture transition transformation consistency degree and sound transition transformation consistency degree corresponding to every two adjacent video subdata in the current teaching mosaic video;
and S402, determining the quality sequence of the M teaching spliced videos according to the video goodness, and taking the teaching spliced video with the optimal video goodness as a final teaching video.
In one embodiment, in step S4011, the determining a degree of continuity of image-to-picture transition between a last image frame of a previous video subdata and a first image frame of a next video subdata in every two adjacent video subdata in the current teaching mosaic video specifically includes:
set the reference number mij、mi(j+1)Respectively corresponding to the last image frame of jth video subdata in the ith teaching splicing video and the first image frame of jth +1 video subdata in the ith teaching splicing video, and obtaining an image frame mijImage frame mi(j+1)The resolution of (a) is p x q, wherein p is the maximum pixel number of the image frame in the horizontal direction, q is the maximum pixel number of the image frame in the vertical direction, and (x, y) represents the image frame mijImage frame mi(j+1)The value of x is any positive integer from 0 to p, the value of y is any positive integer from 0 to q, and m is the coordinate value of any pixel pointijs(x,y)、mi(j+1)s(x, y) respectively represent image frames mijImage frame mi(j+1)The normalized color value of the corresponding pixel point (x, y) is calculated as follows:
mijs(x,y)＝106mijR(x,y)+103mijG(x,y)+106mijB(x,y) (1)
mi(j+1)s(x,y)＝106mi(j+1)R(x,y)+103mi(j+1)G(x,y)+106mi(j+1)B(x,y) (2)
in the above formulas (1) and (2), mijR(x,y)、mijG(x,y)、mijB(x, y) respectively represent image frames mijRed, green, blue color values of the upper pixel point (x, y), mi(j+1)R(x,y)、mi(j+1)G(x,y)、mi(j+1)B(x, y) respectively represent image frames mi(j+1)Red, green, blue color values of the upper pixel point (x, y);
then, the image frame m is calculated according to the following formula (3)ijImage frame mi(j+1)Color difference value at pixel point (x, y)
Figure BDA0002652461390000051
Figure BDA0002652461390000052
Then, the image frame m is calculated according to the following formula (4)ijImage frame mi(j+1)Evaluation value of transition consistency of image frames
Figure BDA0002652461390000053
Figure BDA0002652461390000054
Wherein when said
Figure BDA0002652461390000056
The larger the value of (a), the image frame m is indicatedijImage frame mi(j+1)The higher the image picture transition consistency degree between the two is;
and then, calculating a comprehensive evaluation value of the transition consistency degree of the image picture corresponding to the ith teaching spliced video according to the following formula (5):
Figure BDA0002652461390000055
wherein, FiThe comprehensive evaluation value of the transition consistency degree of the image picture corresponding to the ith teaching spliced video is represented; h represents the total number of video subdata in the ith teaching spliced video.
In one embodiment, in step S4012, determining a degree of continuity of sound transition between a last sound segment of previous video sub data and a first sound segment of next video sub data in every two adjacent video sub data in the current teaching spliced video, specifically includes:
set the reference number nij、ni(j+1)Respectively corresponding to the decibel of an ending sound corresponding to the last image frame of jth video subdata in the ith teaching splicing video and the decibel of a starting sound corresponding to the first image frame of jth +1 video subdata in the ith teaching splicing video;
calculating the sound transition consistency degree between the jth video subdata and the jth +1 video subdata in the ith teaching splicing video according to the following formula (6)
Figure BDA0002652461390000061
Figure BDA0002652461390000062
When said
Figure BDA0002652461390000063
The larger the numerical value is, the higher the sound transition consistency degree between the jth video subdata and the jth +1 video subdata in the ith teaching splicing video is;
and then, calculating the comprehensive evaluation of the sound transition consistency degree corresponding to the ith teaching mosaic video according to the following formula (7)Value Wi：
Figure BDA0002652461390000064
In an embodiment, in step S4013, determining a video goodness of the current teaching mosaic video according to an image-picture transition consistency degree and a sound transition consistency degree corresponding to every two adjacent video subdata in the current teaching mosaic video specifically includes:
calculating a video goodness evaluation value P of the ith teaching spliced video according to the following formula (8)i：
Pi＝α1Fi+α2Wi (8)
Wherein alpha is1Denotes a preset FiThe corresponding weight value is a numerical value which is greater than 0 and less than 1; alpha is alpha2Denotes a preset WiThe corresponding calculated weight value is a value greater than 0 and less than 1, and alpha1And alpha2The sum is 1;
Pithe larger the value is, the better the goodness of the ith teaching spliced video is.
The embodiment of the invention also provides a teaching video processing system, which comprises:
the shooting processing module is used for shooting a preset teaching process from two different directions so as to correspondingly obtain two original video data related to the preset teaching process, and respectively carrying out video quality processing preprocessing on the two original video data so as to correspondingly obtain two preprocessed video data meeting a preset image quality condition and/or a preset sound quality condition;
the video processing module is used for obtaining two video subdata sets corresponding to two shooting positions from the two preprocessed video data according to the shooting positions, each video subdata set corresponds to one shooting position, each video subdata set comprises N video subdata which are connected back and forth on a shooting time sequence, the lengths of the shooting time periods corresponding to all the video subdata are equal, and the N video subdata correspond to the N shooting time periods respectively;
the video splicing module is used for splicing M times of video subdata according to a shooting time sequence to obtain M teaching spliced videos; wherein, every splicing operation comprises: randomly selecting N1 video subdata from one video subdata set, randomly selecting N2 video subdata from another video subdata set, and selecting N1+ N2 as N; the shooting time periods corresponding to the N1 pieces of video sub-data and the shooting time periods corresponding to the N2 pieces of video sub-data jointly constitute the N shooting time periods; splicing the N1 pieces of video subdata and the N2 pieces of video subdata in sequence according to a shooting time sequence, thereby obtaining a teaching spliced video corresponding to the splicing operation;
and the final determining module is used for determining the respective video goodness of each teaching mosaic video in the M teaching mosaic videos, determining the goodness sequence of the M teaching mosaic videos according to the video goodness, and taking the teaching mosaic video with the optimal video goodness as the final teaching video.
Compared with the prior art, the teaching video processing method and the system comprise the steps of shooting a preset teaching process from two different directions, correspondingly obtaining two original video data related to the preset teaching process, respectively carrying out video quality processing pretreatment on the two original video data so as to correspondingly obtain two pretreated video data meeting a preset image quality condition and/or a preset sound quality condition, screening the pretreated video data according to the shooting directions so as to obtain two video sub-data sets related to different shooting directions, sequentially splicing the video sub-data contained in each video sub-data set according to the shooting time sequence so as to correspondingly obtain a teaching spliced video, and determining the respective image picture transition continuity degree and sound transition continuity degree of the teaching spliced video, the quality of all the teaching spliced videos is sequenced, so that the optimal teaching spliced video is converted into a three-dimensional teaching video; therefore, the teaching video processing method and the system can ensure that the teaching video can be updated to have higher presentation quality on image quality and sound quality, improve the immersion of users during the watching process and improve the watching quality of the teaching video.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a teaching video processing method according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a teaching video processing method according to an embodiment of the present invention. The teaching video processing method comprises the following steps:
step S1, shooting a preset teaching process from two different directions so as to correspondingly obtain two original video data related to the preset teaching process, and respectively carrying out video quality processing pretreatment on the two original video data so as to correspondingly obtain two pretreated video data meeting preset image quality conditions and/or preset sound quality conditions;
step S2, according to the shooting direction, obtaining two video subdata sets corresponding to two shooting directions from the two preprocessed video data, wherein each video subdata set corresponds to one shooting direction, each video subdata set comprises N video subdata which are connected back and forth on a shooting time sequence, the lengths of the shooting time periods corresponding to all the video subdata are equal, and the N video subdata correspond to the N shooting time periods respectively;
step S3, splicing M times of video subdata according to the shooting time sequence to obtain M teaching spliced videos; wherein, every splicing operation comprises: randomly selecting N1 video subdata from one video subdata set, randomly selecting N2 video subdata from another video subdata set, and selecting N1+ N2 as N; the shooting time periods corresponding to the N1 pieces of video sub-data and the shooting time periods corresponding to the N2 pieces of video sub-data jointly constitute the N shooting time periods; splicing the N1 pieces of video subdata and the N2 pieces of video subdata in sequence according to a shooting time sequence, thereby obtaining a teaching spliced video corresponding to the splicing operation;
and step S4, determining the video goodness of each teaching mosaic video in the M teaching mosaic videos, determining the goodness sequence of the M teaching mosaic videos according to the video goodness, and taking the teaching mosaic video with the optimal video goodness as the final teaching video.
The beneficial effects of the above technical scheme are: the teaching video processing method generates corresponding original teaching video data in a multi-angle shooting mode, then carries out video quality processing pretreatment, splicing treatment and quality judgment treatment on the original teaching video data, and finally takes the teaching spliced video with the optimal video goodness as the final teaching video.
In one embodiment, in the step S1, a preset teaching process is photographed from two different orientations to correspondingly obtain two original video data related to the preset teaching process, and the two original video data are respectively subjected to video quality processing preprocessing, so that two preprocessed video data meeting a preset image quality condition and/or a preset sound quality condition are correspondingly obtained,
step S101, shooting the preset teaching process from two different view angle directions which are mutually crossed, so as to obtain two groups of original video data which have parallax relation and are related to the preset teaching process;
step S102, performing image and sound separation processing on each group of original video data to obtain image data information and sound data information corresponding to each group of original video data, and respectively determining an average image resolution value and an average sound signal-to-noise ratio value corresponding to each group of original video data according to the image data information and the sound data information corresponding to each group of original video data;
step S103, if the average image resolution is smaller than a preset image resolution threshold, performing pixel detail restoration on the image data information, so as to enable the average image resolution to be greater than or equal to the preset image resolution threshold, or, if the average sound signal-to-noise ratio value is smaller than a preset signal-to-noise ratio threshold, performing background noise filtering processing on the sound data information, so as to enable the average signal-to-noise ratio value to be greater than or equal to the preset signal-to-noise ratio threshold;
step S104, recombining the image data information of which the average image resolution is greater than or equal to the preset image resolution threshold and the sound data information of which the average sound signal-to-noise ratio is greater than or equal to the preset signal-to-noise ratio threshold, thereby obtaining the preprocessed video data.
The beneficial effects of the above technical scheme are: corresponding video data information can be comprehensively acquired by shooting the preset teaching process from two different view angle directions which are mutually crossed, and quality restoration processing can be pertinently performed by separating image signals and sound signals in the video data information, so that the preprocessed video data are ensured to have good data quality on an image layer and a sound layer.
In one embodiment, in step S4, determining the video goodness of each of the M teaching videos spliced together, determining the goodness sequence of the M teaching videos spliced together according to the video goodness, and using the teaching video spliced together with the optimal video goodness as the final teaching video specifically includes:
step S401, the following operation steps S4011-4013 are executed for each teaching mosaic video, so that the video goodness of M teaching mosaic videos is obtained:
step S4011, determining the image picture transition consistency degree between the last image frame of the previous video subdata and the first image frame of the next video subdata in every two adjacent video subdata in the current teaching splicing video;
step S4012, determining the sound transition consistency degree between the last section of sound segment of the previous video subdata and the first section of sound segment of the next video subdata in every two adjacent video subdata in the current teaching splicing video;
step S4013, determining video goodness of the current teaching mosaic video according to image picture transition transformation consistency degree and sound transition transformation consistency degree corresponding to every two adjacent video subdata in the current teaching mosaic video;
and S402, determining the quality sequence of the M teaching spliced videos according to the video goodness, and taking the teaching spliced video with the optimal video goodness as a final teaching video.
In one embodiment, in step S4011, the determining a degree of continuity of image-to-picture transition between a last image frame of a previous video subdata and a first image frame of a next video subdata in every two adjacent video subdata in the current teaching mosaic video specifically includes:
set the reference number mij、mi(j+1)Respectively corresponding to the last image frame of jth video subdata in the ith teaching splicing video and the first image frame of jth +1 video subdata in the ith teaching splicing video, and obtaining an image frame mijImage frame mi(j+1)The resolution of (a) is p x q, wherein p is the maximum pixel number of the image frame in the horizontal direction, q is the maximum pixel number of the image frame in the vertical direction, and (x, y) represents the image frame mijImage frame mi(j+1)The value of x is any positive integer from 0 to p, the value of y is any positive integer from 0 to q, and m is the coordinate value of any pixel pointijs(x,y)、mi(j+1)s(x, y) respectively represent image frames mijImage frame mi(j+1)The normalized color value of the corresponding pixel point (x, y) is calculated as follows:
mijs(x,y)＝106mijR(x,y)+103mijG(x,y)+106mijB(x,y) (1)
mi(j+1)s(x,y)＝106mi(j+1)R(x,y)+103mi(j+1)G(x,y)+106mi(j+1)B(x,y) (2)
in the above formulas (1) and (2), mijR(x,y)、mijG(x,y)、mijB(x, y) respectively represent image frames mijRed, green, blue color values of the upper pixel point (x, y), mi(j+1)R(x,y)、mi(j+1)G(x,y)、mi(j+1)B(x, y) respectively represent image frames mi(j+1)Red color of upper pixel point (x, y)Value, green color value, blue color value;
then, the image frame m is calculated according to the following formula (3)ijImage frame mi(j+1)Color difference value at pixel point (x, y)
Figure BDA0002652461390000121
Figure BDA0002652461390000122
Then, the image frame m is calculated according to the following formula (4)ijImage frame mi(j+1)Evaluation value of transition consistency of image frames
Figure BDA0002652461390000123
Figure BDA0002652461390000124
Wherein when said
Figure BDA0002652461390000125
The larger the value of (a), the image frame m is indicatedijImage frame mi(j+1)The higher the image picture transition consistency degree between the two is;
and then, calculating a comprehensive evaluation value of the transition consistency degree of the image picture corresponding to the ith teaching spliced video according to the following formula (5):
Figure BDA0002652461390000131
wherein, FiThe comprehensive evaluation value of the transition consistency degree of the image picture corresponding to the ith teaching spliced video is represented; h represents the total number of video subdata in the ith teaching spliced video.
In one embodiment, in step S4012, determining a degree of continuity of sound transition between a last sound segment of previous video sub data and a first sound segment of next video sub data in every two adjacent video sub data in the current teaching spliced video, specifically includes:
set the reference number nij、ni(j+1)Respectively corresponding to the decibel of an ending sound corresponding to the last image frame of jth video subdata in the ith teaching splicing video and the decibel of a starting sound corresponding to the first image frame of jth +1 video subdata in the ith teaching splicing video;
calculating the sound transition consistency degree between the jth video subdata and the jth +1 video subdata in the ith teaching splicing video according to the following formula (6)
Figure BDA0002652461390000132
Figure BDA0002652461390000133
When said
Figure BDA0002652461390000134
The larger the numerical value is, the higher the sound transition consistency degree between the jth video subdata and the jth +1 video subdata in the ith teaching splicing video is;
and then, calculating a comprehensive evaluation value W of the sound transition consistency degree corresponding to the ith teaching spliced video according to the following formula (7)i：
Figure BDA0002652461390000141
In an embodiment, in step S4013, determining a video goodness of the current teaching mosaic video according to an image-picture transition consistency degree and a sound transition consistency degree corresponding to every two adjacent video subdata in the current teaching mosaic video specifically includes:
calculating the view of the ith teaching spliced video according to the following formula (8)Frequency goodness evaluation value Pi：
Pi＝α1Fi+α2Wi (8)
Wherein alpha is1Denotes a preset FiThe corresponding weight value is a numerical value which is greater than 0 and less than 1; alpha is alpha2Denotes a preset WiThe corresponding calculated weight value is a value greater than 0 and less than 1, and alpha1And alpha2The sum is 1;
Pithe larger the value is, the better the goodness of the ith teaching spliced video is.
The beneficial effects of the above technical scheme are: through carrying out comprehensive evaluation about image picture transition consistency degree and sound transition consistency degree to this teaching mosaic video, can comprehensively and accurately discriminate the best teaching mosaic video of quality to improve final teaching video's viewability, guarantee final teaching video's quality of watching. Compared with video software operation and a traditional method, the speed is obviously improved in the calculation process, and the accuracy is greatly improved.
Corresponding to the teaching video processing method provided by the embodiment of the invention, the invention also provides a teaching video processing system, which comprises:
the shooting processing module is used for shooting a preset teaching process from two different directions so as to correspondingly obtain two original video data related to the preset teaching process, and respectively carrying out video quality processing preprocessing on the two original video data so as to correspondingly obtain two preprocessed video data meeting a preset image quality condition and/or a preset sound quality condition;
the video processing module is used for obtaining two video subdata sets corresponding to two shooting positions from the two preprocessed video data according to the shooting positions, each video subdata set corresponds to one shooting position, each video subdata set comprises N video subdata which are connected back and forth on a shooting time sequence, the lengths of the shooting time periods corresponding to all the video subdata are equal, and the N video subdata correspond to the N shooting time periods respectively;
the video splicing module is used for splicing M times of video subdata according to a shooting time sequence to obtain M teaching spliced videos; wherein, every splicing operation comprises: randomly selecting N1 video subdata from one video subdata set, randomly selecting N2 video subdata from another video subdata set, and selecting N1+ N2 as N; the shooting time periods corresponding to the N1 pieces of video sub-data and the shooting time periods corresponding to the N2 pieces of video sub-data jointly constitute the N shooting time periods; splicing the N1 pieces of video subdata and the N2 pieces of video subdata in sequence according to a shooting time sequence, thereby obtaining a teaching spliced video corresponding to the splicing operation;
and the final determining module is used for determining the respective video goodness of each teaching mosaic video in the M teaching mosaic videos, determining the goodness sequence of the M teaching mosaic videos according to the video goodness, and taking the teaching mosaic video with the optimal video goodness as the final teaching video.
It can be known from the content of the above embodiment that the method and system for processing teaching video includes shooting a preset teaching process from two different orientations, correspondingly obtaining two original video data related to the preset teaching process, respectively performing video quality processing preprocessing on the two original video data, correspondingly obtaining two preprocessed video data satisfying a preset image quality condition and/or a preset sound quality condition, screening the preprocessed video data according to the shooting orientation, thus obtaining two video sub-data sets related to different shooting orientations, sequentially splicing the video sub-data included in each video sub-data set according to the shooting time sequence, correspondingly obtaining a teaching spliced video, and determining respective image-frame transition continuity degree and sound transition continuity degree of the teaching spliced video, the quality of all the teaching spliced videos is sequenced, so that the optimal teaching spliced video is converted into a three-dimensional teaching video; therefore, the teaching video processing method and the system can ensure that the teaching video can be updated to have higher presentation quality on image quality and sound quality, improve the immersion of users during the watching process and improve the watching quality of the teaching video.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (7)

1. The teaching video processing method is characterized by comprising the following steps:
step S1, shooting a preset teaching process from two different directions so as to correspondingly obtain two original video data related to the preset teaching process, and respectively carrying out video quality processing pretreatment on the two original video data so as to correspondingly obtain two pretreated video data meeting preset image quality conditions and/or preset sound quality conditions;
step S2, according to the shooting direction, obtaining two video subdata sets corresponding to two shooting directions from the two preprocessed video data, wherein each video subdata set corresponds to one shooting direction, each video subdata set comprises N video subdata which are connected back and forth on a shooting time sequence, the lengths of the shooting time periods corresponding to all the video subdata are equal, and the N video subdata correspond to the N shooting time periods respectively;
step S3, splicing M times of video subdata according to the shooting time sequence to obtain M teaching spliced videos; wherein, every splicing operation comprises: randomly selecting N1 video subdata from one video subdata set, randomly selecting N2 video subdata from another video subdata set, and selecting N1+ N2 as N; the shooting time periods corresponding to the N1 pieces of video sub-data and the shooting time periods corresponding to the N2 pieces of video sub-data jointly constitute the N shooting time periods; splicing the N1 pieces of video subdata and the N2 pieces of video subdata in sequence according to a shooting time sequence, thereby obtaining a teaching spliced video corresponding to the splicing operation;
and step S4, determining the video goodness of each teaching mosaic video in the M teaching mosaic videos, determining the goodness sequence of the M teaching mosaic videos according to the video goodness, and taking the teaching mosaic video with the optimal video goodness as the final teaching video.
2. The instructional video processing method of claim 1, wherein:
in the step S1, the preset teaching process is photographed from two different orientations to correspondingly obtain two original video data related to the preset teaching process, and the two original video data are respectively subjected to video quality processing preprocessing, so that the two preprocessed video data meeting the preset image quality condition and/or the preset sound quality condition are correspondingly obtained,
step S101, shooting the preset teaching process from two different view angle directions which are mutually crossed, so as to obtain two groups of original video data which have parallax relation and are related to the preset teaching process;
step S102, performing image and sound separation processing on each group of original video data to obtain image data information and sound data information corresponding to each group of original video data, and respectively determining an average image resolution value and an average sound signal-to-noise ratio value corresponding to each group of original video data according to the image data information and the sound data information corresponding to each group of original video data;
step S103, if the average image resolution is smaller than a preset image resolution threshold, performing pixel detail restoration on the image data information, so as to enable the average image resolution to be greater than or equal to the preset image resolution threshold, or, if the average sound signal-to-noise ratio value is smaller than a preset signal-to-noise ratio threshold, performing background noise filtering processing on the sound data information, so as to enable the average signal-to-noise ratio value to be greater than or equal to the preset signal-to-noise ratio threshold;
step S104, recombining the image data information of which the average image resolution is greater than or equal to the preset image resolution threshold and the sound data information of which the average sound signal-to-noise ratio is greater than or equal to the preset signal-to-noise ratio threshold, thereby obtaining the preprocessed video data.
3. The instructional video processing method of claim 1, wherein:
in step S4, determine the respective video goodness of each teaching mosaic video in the M teaching mosaic videos, determine the goodness sequence of the M teaching mosaic videos according to the video goodness, regard the teaching mosaic video with the optimal video goodness as the final teaching video, specifically include:
step S401, the following operation steps S4011-4013 are executed for each teaching mosaic video, so that the video goodness of M teaching mosaic videos is obtained:
step S4011, determining the image picture transition consistency degree between the last image frame of the previous video subdata and the first image frame of the next video subdata in every two adjacent video subdata in the current teaching splicing video;
step S4012, determining the sound transition consistency degree between the last section of sound segment of the previous video subdata and the first section of sound segment of the next video subdata in every two adjacent video subdata in the current teaching splicing video;
step S4013, determining video goodness of the current teaching mosaic video according to image picture transition transformation consistency degree and sound transition transformation consistency degree corresponding to every two adjacent video subdata in the current teaching mosaic video;
and S402, determining the quality sequence of the M teaching spliced videos according to the video goodness, and taking the teaching spliced video with the optimal video goodness as a final teaching video.
4. The instructional video processing method of claim 3, wherein:
in step S4011, determining a degree of image-to-image transition continuity between a last image frame of the previous video sub-data and a first image frame of the next video sub-data in every two adjacent video sub-data in the current teaching mosaic video specifically includes:
set the reference number mij、mi(j+1)Respectively corresponding to the last image frame of jth video subdata in the ith teaching splicing video and the first image frame of jth +1 video subdata in the ith teaching splicing video, and obtaining an image frame mijImage frame mi(j+1)The resolution of (a) is p x q, wherein p is the maximum pixel number of the image frame in the horizontal direction, q is the maximum pixel number of the image frame in the vertical direction, and (x, y) represents the image frame mijImage frame mi(j+1)The value of x is any positive integer from 0 to p, the value of y is any positive integer from 0 to q, and m is the coordinate value of any pixel pointijs(x,y)、mi(j+1)s(x, y) respectively represent image frames mijImage frame mi(j+1)The normalized color value of the corresponding pixel point (x, y) is calculated as follows:
mijs(x,y)＝106mijR(x,y)+103mijG(x,y)+106mijB(x,y) (1)
mi(j+1)s(x,y)＝106mi(j+1)R(x,y)+103mi(j+1)G(x,y)+106mi(j+1)B(x,y) (2)
in the above formulas (1) and (2), mijR(x,y)、mijG(x,y)、mijB(x, y) respectively represent image frames mijRed, green, blue color values of the upper pixel point (x, y), mi(j+1)R(x,y)、mi(j+1)G(x,y)、mi(j+1)B(x, y) each representsImage frame mi(j+1)Red, green, blue color values of the upper pixel point (x, y);
then, the image frame m is calculated according to the following formula (3)ijImage frame mi(j+1)Color difference value at pixel point (x, y)
Figure FDA0002652461380000041
Figure FDA0002652461380000042
Then, the image frame m is calculated according to the following formula (4)ijImage frame mi(j+1)Evaluation value of transition consistency of image frames
Figure FDA0002652461380000043
Figure FDA0002652461380000044
Wherein when said
Figure FDA0002652461380000045
The larger the value of (a), the image frame m is indicatedijImage frame mi(j+1)The higher the image picture transition consistency degree between the two is;
and then, calculating a comprehensive evaluation value of the transition consistency degree of the image picture corresponding to the ith teaching spliced video according to the following formula (5):
Figure FDA0002652461380000046
wherein, FiThe comprehensive evaluation value of the transition consistency degree of the image picture corresponding to the ith teaching spliced video is represented; h represents the total number of video subdata in the ith teaching spliced video.
5. The instructional video processing method of claim 4, wherein:
step S4012, determining a sound transition consistency degree between a last sound segment of a previous video sub data and a first sound segment of a next video sub data in every two adjacent video sub data in the current teaching mosaic video, specifically including:
set the reference number nij、ni(j+1)Respectively corresponding to the decibel of an ending sound corresponding to the last image frame of jth video subdata in the ith teaching splicing video and the decibel of a starting sound corresponding to the first image frame of jth +1 video subdata in the ith teaching splicing video;
calculating the sound transition consistency degree between the jth video subdata and the jth +1 video subdata in the ith teaching splicing video according to the following formula (6)
Figure FDA0002652461380000051
Figure FDA0002652461380000052
When said
Figure FDA0002652461380000053
The larger the numerical value is, the higher the sound transition consistency degree between the jth video subdata and the jth +1 video subdata in the ith teaching splicing video is;
and then, calculating a comprehensive evaluation value W of the sound transition consistency degree corresponding to the ith teaching spliced video according to the following formula (7)i：
Figure FDA0002652461380000054
6. The teaching video processing method of claim 5, wherein:
in step S4013, determining a video goodness of the current teaching mosaic video according to an image picture transition consistency degree and a sound transition consistency degree corresponding to every two adjacent video subdata in the current teaching mosaic video, specifically including:
calculating a video goodness evaluation value P of the ith teaching spliced video according to the following formula (8)i：
Pi＝α1Fi+α2Wi (8)
Wherein alpha is1Denotes a preset FiThe corresponding weight value is a numerical value which is greater than 0 and less than 1; alpha is alpha2Denotes a preset WiThe corresponding calculated weight value is a value greater than 0 and less than 1, and alpha1And alpha2The sum is 1;
Pithe larger the value is, the better the goodness of the ith teaching spliced video is.
7. Teaching video processing system, characterized in that it comprises:
the shooting processing module is used for shooting a preset teaching process from two different directions so as to correspondingly obtain two original video data related to the preset teaching process, and respectively carrying out video quality processing preprocessing on the two original video data so as to correspondingly obtain two preprocessed video data meeting a preset image quality condition and/or a preset sound quality condition;
the video processing module is used for obtaining two video subdata sets corresponding to two shooting positions from the two preprocessed video data according to the shooting positions, each video subdata set corresponds to one shooting position, each video subdata set comprises N video subdata which are connected back and forth on a shooting time sequence, the lengths of the shooting time periods corresponding to all the video subdata are equal, and the N video subdata correspond to the N shooting time periods respectively;
the video splicing module is used for splicing M times of video subdata according to a shooting time sequence to obtain M teaching spliced videos; wherein, every splicing operation comprises: randomly selecting N1 video subdata from one video subdata set, randomly selecting N2 video subdata from another video subdata set, and selecting N1+ N2 as N; the shooting time periods corresponding to the N1 pieces of video sub-data and the shooting time periods corresponding to the N2 pieces of video sub-data jointly constitute the N shooting time periods; splicing the N1 pieces of video subdata and the N2 pieces of video subdata in sequence according to a shooting time sequence, thereby obtaining a teaching spliced video corresponding to the splicing operation;
and the final determining module is used for determining the respective video goodness of each teaching mosaic video in the M teaching mosaic videos, determining the goodness sequence of the M teaching mosaic videos according to the video goodness, and taking the teaching mosaic video with the optimal video goodness as the final teaching video.
CN202010875240.1A 2020-08-27 2020-08-27 Teaching video processing method and system Pending CN111970538A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010875240.1A CN111970538A (en) 2020-08-27 2020-08-27 Teaching video processing method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010875240.1A CN111970538A (en) 2020-08-27 2020-08-27 Teaching video processing method and system

Publications (1)

Publication Number Publication Date
CN111970538A true CN111970538A (en) 2020-11-20

Family

ID=73389906

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010875240.1A Pending CN111970538A (en) 2020-08-27 2020-08-27 Teaching video processing method and system

Country Status (1)

Country Link
CN (1) CN111970538A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114170619A (en) * 2021-10-18 2022-03-11 中标慧安信息技术股份有限公司 Data checking method and system based on edge calculation
CN116226411A (en) * 2023-05-06 2023-06-06 深圳市人马互动科技有限公司 Interactive information processing method and device for interactive project based on animation

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100157050A1 (en) * 2008-12-18 2010-06-24 Honeywell International Inc. Process of sequentially dubbing a camera for investigation and review
CN102254467A (en) * 2010-05-17 2011-11-23 上海量明科技发展有限公司 Tourism resource education equipment with three-dimensional data acquisition and fusion and realization method thereof
US20150085197A1 (en) * 2013-09-26 2015-03-26 Alps Electric Co., Ltd. Video display device
US20150281595A1 (en) * 2014-03-27 2015-10-01 Sony Corporation Apparatus and method for video generation
CN108521589A (en) * 2018-04-25 2018-09-11 北京比特智学科技有限公司 Method for processing video frequency and device
CN110010164A (en) * 2018-11-13 2019-07-12 成都依能科技股份有限公司 Multi-channel sound video automated intelligent edit methods
CN209524299U (en) * 2019-02-18 2019-10-22 陕西师范大学 A kind of multimedia interactive teaching video capture device
CN111432141A (en) * 2020-03-31 2020-07-17 北京字节跳动网络技术有限公司 Method, device and equipment for determining mixed-cut video and storage medium
CN111447462A (en) * 2020-05-20 2020-07-24 上海科技大学 Video live broadcast method, system, storage medium and terminal based on visual angle switching

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100157050A1 (en) * 2008-12-18 2010-06-24 Honeywell International Inc. Process of sequentially dubbing a camera for investigation and review
CN102254467A (en) * 2010-05-17 2011-11-23 上海量明科技发展有限公司 Tourism resource education equipment with three-dimensional data acquisition and fusion and realization method thereof
US20150085197A1 (en) * 2013-09-26 2015-03-26 Alps Electric Co., Ltd. Video display device
US20150281595A1 (en) * 2014-03-27 2015-10-01 Sony Corporation Apparatus and method for video generation
CN108521589A (en) * 2018-04-25 2018-09-11 北京比特智学科技有限公司 Method for processing video frequency and device
CN110010164A (en) * 2018-11-13 2019-07-12 成都依能科技股份有限公司 Multi-channel sound video automated intelligent edit methods
CN209524299U (en) * 2019-02-18 2019-10-22 陕西师范大学 A kind of multimedia interactive teaching video capture device
CN111432141A (en) * 2020-03-31 2020-07-17 北京字节跳动网络技术有限公司 Method, device and equipment for determining mixed-cut video and storage medium
CN111447462A (en) * 2020-05-20 2020-07-24 上海科技大学 Video live broadcast method, system, storage medium and terminal based on visual angle switching

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
宋凡: "精品资源共享课中教学视频的制作方法研究", 《中国优秀硕士学位论文全文数据库 (社会科学Ⅱ辑)》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114170619A (en) * 2021-10-18 2022-03-11 中标慧安信息技术股份有限公司 Data checking method and system based on edge calculation
CN116226411A (en) * 2023-05-06 2023-06-06 深圳市人马互动科技有限公司 Interactive information processing method and device for interactive project based on animation

Similar Documents

Publication Publication Date Title
KR100345630B1 (en) How to determine the positional relationship between subjects and how to convert 2D images to 3D images
EP2246807A1 (en) Information processing apparatus and method, and program
CN111970538A (en) Teaching video processing method and system
CN102263957B (en) Search-window adaptive parallax estimation method
CN108038839A (en) Twisted-pair feeder lay real-time detection method on a kind of flow production line
CN108712627A (en) Video conference content and quality detection apparatus and detection method
CN114494566A (en) Image rendering method and device
US20110037895A1 (en) System And Method For Global Inter-Frame Motion Detection In Video Sequences
CN111798540B (en) Image fusion method and system
CN109688328A (en) A kind of method and apparatus of video-splicing fusion and segmentation based on different point video cameras
CN112788329A (en) Video static frame detection method and device, television and storage medium
CN117237279A (en) Blind quality evaluation method and system for non-uniform distortion panoramic image
JP2013073598A (en) Image processing device, image processing method, and program
CN113365103A (en) Automatic bad frame detection method, device, equipment, storage medium and program product
CN115578260B (en) Attention method and system for directional decoupling of image super-resolution
CN104954889B (en) Head generation method and generation system
CN114449362B (en) Video cover selection method, device, equipment and storage medium
CN116467690A (en) Big data visual analysis display platform based on fused media technology
CN117437120A (en) Image stitching method based on deep learning end to end
CN108696747A (en) A kind of video measurement method and apparatus
CN110996128B (en) Online teaching video push management system
CN113225586B (en) Video processing method and device, electronic equipment and storage medium
CN113628121B (en) Method and device for processing and training multimedia data
CN113542864B (en) Video splash screen area detection method, device and equipment and readable storage medium
CN114782239A (en) Digital watermark adding method and system based on convolutional neural network

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
AD01 Patent right deemed abandoned
AD01 Patent right deemed abandoned

Effective date of abandoning: 20221018