CN113422981B - Method and device for identifying opera based on ultra-high definition opera video - Google Patents
Method and device for identifying opera based on ultra-high definition opera video Download PDFInfo
- Publication number
- CN113422981B CN113422981B CN202110740247.7A CN202110740247A CN113422981B CN 113422981 B CN113422981 B CN 113422981B CN 202110740247 A CN202110740247 A CN 202110740247A CN 113422981 B CN113422981 B CN 113422981B
- Authority
- CN
- China
- Prior art keywords
- video
- drama
- original
- similarity
- opera
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000000694 effects Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
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
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/24—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being the cepstrum
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- 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
- H04N21/4394—Processing of audio elementary streams involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio 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
- H04N21/44008—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 operations for analysing video streams, e.g. detecting features or characteristics in the video stream
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the technical field of multimedia, and particularly relates to a method and a device for identifying opera based on ultra-high definition opera video. The method comprises the following steps: step 1: acquiring an original opera video, and capturing musical instruments and roles to obtain an accompanying musical instrument set and a role name set; and 2, step: searching a video library based on the accompaniment instrument set to obtain a plurality of alternative dramas with intersection of the accompaniment instruments; judging the similarity of the original drama video and each alternative drama one by one to obtain the affiliated drama; and 3, step 3: searching programs corresponding to the dramas based on the role name set to obtain a plurality of alternative drama videos with intersection of role names; judging the similarity of the original opera video and each alternative opera video one by one to obtain an opera video set; and 4, step 4: and obtaining the drama video similar to the original drama video in the drama video set based on the similarity. By the method, the obtained drama video can be automatically identified, and the method is high in automation and good in identification effect.
Description
Technical Field
The invention belongs to the technical field of multimedia, and particularly relates to a method and a device for identifying opera based on ultra-high definition opera video.
Background
With the development and popularization of the internet, information on the internet is more and more abundant, people can find desired information through a search engine (such as google, hundredth and the like), for example, related keywords can be input in a search box of the search engine, a button for determining the search is triggered, and then a webpage related to the keywords can be returned.
But excluding text and pictures, video also constitutes a data source, especially a drama video. The world drama source is long, huge and profound, the types of the door are various, and for common audiences, how to quickly lock the video source according to the known video data. The music score is used for rapidly knowing the related introduction program information of the music scores, and is of practical help for improving the program impression, increasing the music score knowledge and popularizing the music score culture.
However, in the related art, there is no device for automatically distinguishing the drama and displaying the program information, so that it is necessary to use a lot of manpower to distinguish, screen and produce drama, which is time consuming and unstable in the effect of the finished product. Therefore, in view of the above disadvantages, the present invention urgently needs to provide a method and an apparatus for identifying drama based on ultra high definition drama video.
Disclosure of Invention
The invention aims to provide a method and a device for identifying opera based on ultra-high-definition opera video, which are used for solving the problems of low automation and poor effect of similar opera video identification in the prior art.
The invention provides a method for identifying opera based on ultra-high definition opera video, which comprises the following steps: step 1: acquiring an original drama video, and capturing musical instruments and roles appearing in the original drama video to obtain an accompanying musical instrument set and a role name set; and 2, step: searching a video library based on the accompaniment instrument set obtained in the step 1 to obtain a plurality of alternative scenarios with intersection of the accompaniment instruments and the accompaniment instrument set; judging the similarity of the original drama video and each alternative drama one by one to obtain the drama to which the original drama video belongs; and step 3: searching the program corresponding to the drama obtained in the step 2 based on the role name set obtained in the step 1 to obtain a plurality of alternative drama videos with intersection of the role names and the role name set; judging the similarity of the original opera video and each alternative opera video one by one to obtain an opera video set with the similarity conforming to the program control factor; and 4, step 4: and obtaining a drama video similar to the original drama video in the drama video set based on the similarity, and outputting the characteristic information of the drama video, wherein the characteristic information is the information of the drama video stream.
The method for identifying the drama based on the ultra high definition drama video as described above is further preferred that the video library stores the drama video and the feature information associated with the drama video, wherein the feature information includes the drama species, the character name, the costume style, the accompaniment instrument, the chapter scenario and the chapter duration.
As described above, the method for identifying a drama based on the ultra high definition drama video further preferably includes, in step 1: step 1.1: obtaining an original opera video, and assigning values to the opera control factor and the program control factor of the opera video stream; step 1.2: capturing musical instruments and roles appearing in the original drama video based on the original drama video to obtain an accompaniment musical instrument set and a role name set; step 1.3: and acquiring the duration of the original opera video.
As described above, the method for identifying a drama based on the ultra high definition drama video further preferably includes, in step 2: step 2.1: searching a video library based on the accompaniment instrument set obtained in the step 1 to obtain a plurality of alternative scenarios with intersection between the accompaniment instruments and the accompaniment instrument set, and intersection between each alternative scenario and the accompaniment instruments of the original drama video; step 2.2: calculating the time length percentage of each element in the concocting music instrument intersection obtained in the step 2.1 in each program in the original drama video and the alternative drama one by one to obtain a similar instrument time length percentage set and an original video instrument time length percentage set; step 2.3: calculating the similarity between the original video and the alternative drama based on the similar musical instrument duration percentage set and the original video musical instrument duration percentage set obtained in the step 2.2 to obtain a musical instrument similarity set; step 2.4: and (4) comparing the sizes of all the elements in the musical instrument similarity set obtained in the step (2.3) with the scenario control factors to obtain a musical instrument similarity subset meeting the requirements of the scenario control factors, and obtaining the scenario to which the original drama video belongs.
In the method for identifying the drama based on the ultra high definition drama video as described above, it is further preferable that in step 2.3, the similarity is calculated as follows:
kj is the similarity of the original video and the j candidate drama based on the musical instrument; j =1,2 \ 8230t; b is a mixture of jx The half-ratio of the duration of the xth accompaniment instrument in the original drama video is the set of the duration percentage of the original video B = { B = { (B) } j1 ,b j2 ,……,b jx Element of { x =1,2, \ 8230, n; c. C jx The duration half-ratio of the xth accompaniment instrument in all the programs corresponding to the jth alternative play is a similar video duration percentage set C = { C = j1 ,c j2 ,……,c jx J =1,2 \8230t, x =1,2 \8230, n.
As described above, the method for identifying drama based on ultra high definition drama video preferably further includes, in step 3: step 3.1: searching programs corresponding to the dramas based on the role name set obtained in the step 1 to obtain a plurality of similar drama videos with the intersection of the role names and the role name set and the intersection of the role names of each similar drama video and the original drama video; step 3.2: calculating the time length percentage of each element in the character name intersection obtained in the step 3.1 in the original opera video and the similar opera video one by one to obtain a similar character time length percentage set and an original video character time length half-ratio set; step 3.3: calculating the similarity between the original video and the similar opera video based on the approximate character duration percentage set and the original video character duration half percentage set obtained in the step 3.2 to obtain a character similarity set; step 3.4: and (3) comparing the sizes of the elements in the role similarity set obtained in the step (3.3) with the program control factors to obtain a role similarity subset meeting the requirements of the program control factors, and combining the similar opera videos corresponding to the elements in the role similarity subset to obtain a opera video set.
In the method for identifying dramas based on ultra high definition drama video, it is further preferable that, in step 2.1, when the set of accompanying instruments is a subset of a set of accompanying instruments which is only one drama, the drama is a drama with similarity conforming to the drama control factor; step 3 is performed directly.
The invention also discloses a device for identifying the drama based on the ultra-high-definition drama video, which is used for realizing the method for identifying the drama based on the ultra-high-definition drama video, and comprises the following steps: the obtaining module is used for obtaining an original opera video and capturing musical instruments and roles appearing in the original opera video to obtain an accompanying musical instrument set and a role name set; the searching module is used for searching the video library according to the accompaniment instrument set to obtain a plurality of alternative dramas with intersections of the accompaniment instruments and the accompaniment instrument set; the method is also used for searching programs corresponding to the drama based on the role name set to obtain a plurality of similar drama videos with intersection of the role names and the role name set; the processing module is used for judging the similarity between the original drama video and each similar drama one by one to obtain a drama set of which the similarity accords with the drama control factor; the system is also used for judging the similarity between the original opera video and each similar opera video one by one to obtain an opera video set of which the similarity accords with the program control factor; and the output module is used for obtaining a drama video similar to the original drama video in the drama video set based on the similarity and outputting the characteristic information of the drama video, wherein the characteristic information is the information of the drama video stream.
In the apparatus for identifying drama based on ultra high definition drama video as described above, it is further preferable that the processing module includes: the duration calculation module is used for calculating the duration percentage of each element in the accompaniment instrument intersection in each program in the original drama video and the alternative drama one by one to obtain a similar instrument duration percentage set and an original video instrument duration percentage set; the method is also used for calculating the time length percentage of each element in the character name intersection in the original opera video and the similar opera video one by one to obtain a similar character time length percentage set and an original video character time length half-ratio set; the similarity calculation module is used for calculating the similarity between the original video and the similar drama based on the similar musical instrument duration percentage set and the original video musical instrument duration percentage set to obtain a musical instrument similarity set; calculating the similarity between the original video and the similar opera video based on the similar role duration percentage set and the original video role duration half percentage set to obtain a role similarity set; the judging module is used for comparing the sizes of all elements in the musical instrument similarity set with the scenario control factors to obtain a musical instrument similarity subset meeting the requirements of the scenario control factors and obtain the scenario to which the original drama video belongs; and the method is also used for comparing the sizes of each element in the role similarity set with the program control factor to obtain a role similarity subset meeting the requirement of the program control factor, and combining the similar opera videos corresponding to each element in the role similarity subset to obtain the opera video set.
The apparatus for identifying drama based on ultra high definition drama video as described above further preferably further comprises a video library updating module, configured to update the video library according to a storage rule of the video library.
The invention discloses a method and a device for identifying opera based on ultra-high definition opera video, wherein the method comprises the following steps: step 1: acquiring an original drama video, and capturing musical instruments and roles appearing in the original drama video to obtain an accompanying musical instrument set and a role name set; step 2: searching a video library based on the accompaniment instrument set obtained in the step 1 to obtain a plurality of similar opera videos with intersection of the accompaniment instruments and the accompaniment instrument set; judging the similarity of the original opera video and each similar opera video one by one to obtain an alternative opera video set with the similarity conforming to the opera control factor; and step 3: searching the alternative drama video set obtained in the step 2 based on the role name set obtained in the step 1 to obtain a plurality of similar drama videos which have intersection with the role name set; judging the similarity between the opera video stream and each similar opera video one by one to obtain a rough selection opera video set of which the similarity accords with a program control factor; and 4, step 4: and obtaining a drama video similar to the original drama video in the roughly selected drama video set based on the similarity, and outputting the characteristic information of the drama video, wherein the characteristic information is the information of the drama video stream. By the method, the obtained drama video can be automatically identified, and the method is high in automation and good in identification effect.
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, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flowchart of a method for identifying drama based on ultra high definition drama video according to the present invention;
fig. 2 is a structural connection diagram of the apparatus for identifying a drama based on an ultra high definition drama video according to the present invention.
Detailed Description
Example 1:
as shown in fig. 1, the method for identifying drama based on ultra high definition drama video disclosed in this embodiment includes:
step 1: acquiring an original drama video, and capturing musical instruments and roles appearing in the original drama video to obtain an accompanying musical instrument set and a role name set;
step 2: searching a video library based on the accompaniment instrument set obtained in the step 1 to obtain a plurality of alternative dramas with intersections of the accompaniment instruments and the accompaniment instrument set; judging the similarity of the original drama video and each alternative drama one by one to obtain the drama to which the original drama video belongs;
and step 3: searching the program corresponding to the drama obtained in the step 2 based on the role name set obtained in the step 1 to obtain a plurality of alternative drama videos with intersection of the role names and the role name set; judging the similarity of the original opera video and each alternative opera video one by one to obtain an opera video set with the similarity conforming to the program control factor;
and 4, step 4: and obtaining a drama video similar to the original drama video in the drama video set based on the similarity, and outputting the characteristic information of the drama video, wherein the characteristic information is the information of the drama video stream.
Specifically, the video library stores a drama video and feature information associated with the drama video, wherein the feature information includes a drama, a character name, a dress style, an accompaniment instrument, a chapter scenario and a chapter duration.
Further, step 1 specifically includes:
step 1.1: obtaining an original opera video a0, and assigning values to a opera control factor K and a program control factor M of the opera video stream; the drama control factor K and the program control factor M are fixed values;
step 1.2: capturing instruments and characters appearing in the original drama video based on the original drama video to obtain an accompanying instrument set Y = { Y1, Y2, \8230;, yn } and a character name set D0= { D1, D2, \8230;, dn };
step 1.3: and acquiring the time length h0 of the original opera video.
Specifically, for the original opera video, instruments appearing in the video are captured from the video audio by means of MFCC, spectrum flatness and the like; a still frame of a character appearing in the video is obtained by cutting a video screenshot, and the image of the matched character (facial makeup and dressing) is compared to obtain the character appearing in the video.
Further, step 2 specifically includes:
step 2.1: searching a video library based on the accompaniment instrument set obtained in the step 1 to obtain a plurality of alternative varieties of the accompaniment instruments, which have intersection with the accompaniment instrument set, and intersection of each alternative variety of the accompaniment instruments and the accompaniment instrument of the original drama video; the accompanying instruments of a plurality of similar drama videos in the video library J are integrated into Y1, Y2, \8230;, yn, and the intersection of the accompanying instruments is A1, A2, \8230An, wherein Y n Y1= A1, Y n Y2= A2, Y n Y2= A3, \8230;, 8230;, Y n = An. In the intersection set of the accompaniment instruments, the scenario corresponding to 1 or more intersection sets with the maximum potential of the set is an alternative scenario set, and the formed alternative scenario set is A = { Ax1, ax2, \8230;, axn }.
Step 2.2: calculating the time length percentage of each element in the concocting music instrument intersection obtained in the step 2.1 in each program in the original drama video and the alternative drama one by one to obtain a similar instrument time length percentage set and an original video instrument time length percentage set; specifically, preparingSelecting a time length percentage set B = { B } of various accompaniment instruments in any element Axn in the play set A in the original play video a0 j1 ,b j2 ,……,b jx Element of, x =1,2, \8230 }, n; the percentage set C = { C } of the similar video duration of each accompaniment instrument in each program of the alternative scenario in any element Axn in the alternative scenario set A j1 ,c j2 ,……,c jx The element of (1), x =1,2, \8230 }, n.
Step 2.3: calculating the similarity between the original video and the alternative drama based on the similar musical instrument duration percentage set and the original video musical instrument duration percentage set obtained in the step 2.2 to obtain a musical instrument similarity set;
further, in step 2.3, the similarity is calculated as:
kj is the similarity of the original video and the jth alternative drama based on the musical instrument; j =1,2 \ 8230t;
b jx the half-ratio of the duration of the xth accompaniment instrument in the original drama video is the set of the duration percentage of the original video B = { B = { (B) } j1 ,b j2 ,……,b jx Element of, x =1,2, \8230 }, n;
c jx the duration half-ratio of the xth accompaniment instrument in all the programs corresponding to the jth alternative play is a similar video duration percentage set C = { C = j1 ,c j2 ,……,c jx J =1,2 \8230t, x =1,2 \8230, n.
Further, a similarity set K0= { K1, K2, \8230;, kt } between the original drama video a0 and the similar drama video set is obtained.
Step 2.4: and (4) comparing the sizes of all the elements in the musical instrument similarity set obtained in the step (2.3) with the scenario control factors to obtain a musical instrument similarity subset meeting the requirements of the scenario control factors, and obtaining the scenario to which the original drama video belongs.
Specifically, the smaller the median value of K0 is, the more similar the a0 drama is, if a parameter smaller than the control factor K exists in K0, the drama jx corresponding to the minimum value K0 therein is the a0 drama; if no parameter smaller than the control factor K exists in K0, it indicates that a0 does not include the drama genre in the core drama genre library, and the procedure may return to step 1 or end.
Further, step 3 specifically includes:
step 3.1: searching programs corresponding to the dramas based on the role name set obtained in the step (1) to obtain a plurality of similar drama videos with intersection of the role names and the role name set and the intersection of the role names of each similar drama video and the original drama video;
step 3.2: calculating the time length percentage of each element in the character name intersection obtained in the step 3.1 in the original opera video and the similar opera video one by one to obtain an approximate character time length percentage set and an original video character time length half ratio set;
step 3.3: calculating the similarity between the original video and the similar drama video based on the approximate character duration percentage set and the original video character duration half-percentage set obtained in the step 3.2 to obtain a character similarity set;
step 3.4: and (3) comparing the sizes of the elements in the role similarity set obtained in the step (3.3) with the program control factors to obtain a role similarity subset meeting the requirements of the program control factors, and combining the similar opera videos corresponding to the elements in the role similarity subset to obtain a opera video set.
The set of roles appearing in a0 is D0= { D1, D2, \8230;, dn }. The set of the appearance sets of the roles corresponding to the programs in the corresponding drama is D = { D1, D2, \8230;, dn }. If there is no set containing D0 in D, a0 does not belong to the program in the core drama program library, and the process may return to link 1 or end. If one or more sets containing D0 exist in D, then the set containing D0 in D Dx = { Dx1, dx2, \8230;, dxn }.
D0 # Dx1= E1, calculating the percentage of the occurrence time length of the character appearing in E1 in a0 and a program ax1 corresponding to Dx1 to the total time length respectively, obtaining a0 character corresponding time length set F = { F1, F2, \8230, fn }, obtaining an ax1 character corresponding time length set G = { G1, G2, \8230, gn }, a0 and D1ax1 similarity
In this way, the similarity set between the set corresponding to the program in Dx and a0 is M0= { M1, M2, \8230;, mn }.
If a parameter smaller than the control factor M exists in M0, the minimum value M0 corresponds to a program ax, namely, the program ax is the same as the program a 0; if there is no parameter smaller than the control factor M in M0, it indicates that a0 may not belong to the program in the core drama program library, and may return to step 1 (increase the core drama program library, or increase the time length for recording a0 program) or end.
Further, in step 2.1, when the accompaniment instrument set is a subset of the accompaniment instrument set of only one scenario, the scenario is a scenario with similarity conforming to the scenario control factor; step 3 is performed directly.
Example 2:
as shown in fig. 2, the present embodiment discloses an apparatus for identifying dramas based on ultra high definition drama video, which is used to implement the method for identifying dramas based on ultra high definition drama video in embodiment 1, and includes:
the obtaining module is used for obtaining an original opera video and capturing musical instruments and roles appearing in the original opera video to obtain an accompanying musical instrument set and a role name set;
the searching module is used for searching the video library according to the accompaniment instrument set to obtain a plurality of alternative dramas with intersections of the accompaniment instruments and the accompaniment instrument set; the method is also used for searching programs corresponding to the drama based on the role name set to obtain a plurality of similar drama videos with intersection of the role names and the role name set;
the processing module is used for judging the similarity between the original drama video and each similar drama one by one to obtain a drama set of which the similarity accords with the drama control factor; the system is also used for judging the similarity between the original opera video and each similar opera video one by one to obtain an opera video set of which the similarity accords with the program control factor;
and the output module is used for obtaining the drama video similar to the original drama video in the drama video set based on the similarity and outputting the characteristic information of the drama video, wherein the characteristic information is the information of the drama video stream. Further, the processing module comprises:
the duration calculation module is used for calculating the duration percentage of each element in the accompaniment instrument intersection in each program in the original drama video and the alternative drama one by one to obtain a similar instrument duration percentage set and an original video instrument duration percentage set; the method is also used for calculating the time length percentage of each element in the character name intersection in the original opera video and the similar opera video one by one to obtain a similar character time length percentage set and an original video character time length half-ratio set;
the similarity calculation module is used for calculating the similarity between the original video and the similar drama based on the similar musical instrument duration percentage set and the original video musical instrument duration percentage set to obtain a musical instrument similarity set; calculating the similarity between the original video and the similar drama video based on the approximate character duration percentage set and the original video character duration half-percentage set to obtain a character similarity set;
the judging module is used for comparing the sizes of all elements in the musical instrument similarity set with the scenario control factors to obtain a musical instrument similarity subset meeting the requirements of the scenario control factors and obtain the scenario to which the original drama video belongs; and the method is also used for comparing the sizes of each element in the role similarity set with the program control factor to obtain a role similarity subset meeting the requirement of the program control factor, and combining the similar opera videos corresponding to each element in the role similarity subset to obtain the opera video set.
Further, the system also comprises a video library updating module used for updating the video library according to the storage rule of the video library. Specifically, the drama videos in the video library are stored in a one-to-one correlation and correspondence mode according to 7 dimensional data such as program names, program types, program instruments, program appearance roles, program basic information, program complete duration, program complete videos and the like. And the video updating module is used for updating the video library according to the storage rule when a new drama program appears.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. A method for identifying opera based on ultra-high definition opera video is characterized by comprising the following steps:
step 1: acquiring an original drama video, and capturing musical instruments and roles appearing in the original drama video to obtain an accompanying musical instrument set and a role name set;
step 2.1: searching a video library based on the accompaniment instrument set obtained in the step 1 to obtain a plurality of alternative varieties of the accompaniment instruments, which have intersection with the accompaniment instrument set, and intersection of each alternative variety of the accompaniment instruments and the accompaniment instrument of the original drama video;
step 2.2: calculating the time length percentage of each element in the accompaniment instrument intersection obtained in the step 2.1 in the original drama video and each program in the alternative drama one by one to obtain a similar instrument time length percentage set and an original video instrument time length percentage set;
step 2.3: calculating the similarity between the original video and the alternative drama based on the similar musical instrument duration percentage set and the original video musical instrument duration percentage set obtained in the step 2.2 to obtain a musical instrument similarity set;
step 2.4: comparing the sizes of the elements in the musical instrument similarity set obtained in the step 2.3 with the scenario control factors to obtain a musical instrument similarity subset meeting the requirements of the scenario control factors and obtain the scenario to which the original drama video belongs;
and 3, step 3: searching the program corresponding to the drama obtained in the step 2 based on the role name set obtained in the step 1 to obtain a plurality of alternative drama videos with intersection of the role names and the role name set; judging the similarity of the original opera video and each alternative opera video one by one to obtain an opera video set with the similarity conforming to the program control factor;
and 4, step 4: and obtaining a drama video similar to the original drama video in the drama video set based on the similarity, and outputting the characteristic information of the drama video, wherein the characteristic information is the information of the drama video stream.
2. The ultra high definition drama video based method for identifying dramas according to claim 1, wherein the video library stores the drama video and feature information associated with the drama video, wherein the feature information comprises a drama, a character name, a dress style, an accompaniment instrument, a chapter scenario and a chapter duration.
3. The method for identifying the drama based on the ultra-high definition drama video according to claim 2, wherein the step 1 specifically comprises:
step 1.1: obtaining an original opera video, and assigning values to the opera control factor and the program control factor of the opera video stream;
step 1.2: capturing musical instruments and roles appearing in the original drama video based on the original drama video to obtain an accompanying musical instrument set and a role name set;
step 1.3: and acquiring the time length of the original opera video.
4. The method for identifying drama based on ultra high definition drama video according to claim 3, wherein in the step 2.3, the similarity is calculated as:
kj is the similarity of the original video and the jth similar drama video based on the musical instrument; j =1,2 \ 8230t;
b jx the duration percentage of the xth accompaniment instrument in the original drama video is the original video duration percentage set B = { B = j1 ,b j2 ,……,b jx Element of { x =1,2, \ 8230, n;
c jx the duration percentage of the xth accompaniment instrument in all the programs corresponding to the alternative dramas is a similar video duration percentage set C = { C = j1 ,c j2 ,……,c jx The element of (1), x =1,2, \8230 }, n.
5. The method for identifying drama based on ultra high definition drama video according to claim 4, wherein the step 3 specifically comprises:
step 3.1: searching programs corresponding to the dramas based on the role name set obtained in the step (1) to obtain a plurality of similar drama videos with intersection of the role names and the role name set and the intersection of the role names of each similar drama video and the original drama video;
step 3.2: calculating the time length percentage of each element in the character name intersection obtained in the step 3.1 in the original opera video and the similar opera video one by one to obtain a similar character time length percentage set and an original video character time length percentage set;
step 3.3: calculating the similarity between the original video and the similar opera video based on the approximate character duration percentage set and the original video character duration percentage set obtained in the step 3.2 to obtain a character similarity set;
step 3.4: and (3) comparing the sizes of the elements in the role similarity set obtained in the step (3.3) with the program control factors to obtain a role similarity subset meeting the requirements of the program control factors, and combining the similar opera videos corresponding to the elements in the role similarity subset to obtain a opera video set.
6. The method for identifying drama based on ultra high definition drama video according to claim 5, wherein in step 2.1, when the set of accompanying musical instruments is a subset of the set of accompanying musical instruments which is only one drama, the drama is the drama with the similarity conforming to the drama control factor; step 3 is directly performed.
7. An apparatus for identifying drama based on ultra high definition drama video, which is used for realizing the method for identifying drama based on ultra high definition drama video according to any one of claims 1 to 6, and comprises:
the obtaining module is used for obtaining an original opera video and capturing musical instruments and roles appearing in the original opera video to obtain an accompanying musical instrument set and a role name set;
the searching module is used for searching the video library according to the accompaniment instrument set to obtain a plurality of alternative drama varieties with intersection of the accompaniment instruments and the accompaniment instrument set; the method is also used for searching programs corresponding to the drama based on the role name set to obtain a plurality of similar drama videos with intersection of the role names and the role name set;
the processing module is used for judging the similarity between the original drama video and each similar drama one by one to obtain a drama set of which the similarity accords with the drama control factor; the system is also used for judging the similarity between the original opera video and each similar opera video one by one to obtain an opera video set of which the similarity accords with the program control factor;
and the output module is used for obtaining a drama video similar to the original drama video in the drama video set based on the similarity and outputting the characteristic information of the drama video, wherein the characteristic information is the information of the drama video stream.
8. The ultra high definition drama video identification device of drama according to claim 7, wherein the processing module comprises:
the duration calculation module is used for calculating the duration percentage of each element in the accompaniment instrument intersection in each program in the original drama video and the alternative drama one by one to obtain a similar instrument duration percentage set and an original video instrument duration percentage set; the method is also used for calculating the time length percentage of each element in the character name intersection in the original opera video and the similar opera video one by one to obtain a similar character time length percentage set and an original video character time length percentage set;
the similarity calculation module is used for calculating the similarity between the original video and the similar drama based on the similar musical instrument duration percentage set and the original video musical instrument duration percentage set to obtain a musical instrument similarity set; calculating the similarity between the original video and the similar opera video based on the similar role duration percentage set and the original video role duration percentage set to obtain a role similarity set;
the judging module is used for comparing the sizes of all elements in the musical instrument similarity set with the scenario control factors to obtain a musical instrument similarity subset meeting the requirements of the scenario control factors and obtain the scenario to which the original drama video belongs; and the method is also used for comparing the sizes of each element in the role similarity set with the program control factor to obtain a role similarity subset meeting the requirement of the program control factor, and combining the similar opera videos corresponding to each element in the role similarity subset to obtain the opera video set.
9. The ultra high definition drama video based identification device of drama as claimed in claim 8, further comprising a video library updating module for updating said video library according to the storage rules of the video library.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110740247.7A CN113422981B (en) | 2021-06-30 | 2021-06-30 | Method and device for identifying opera based on ultra-high definition opera video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110740247.7A CN113422981B (en) | 2021-06-30 | 2021-06-30 | Method and device for identifying opera based on ultra-high definition opera video |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113422981A CN113422981A (en) | 2021-09-21 |
| CN113422981B true CN113422981B (en) | 2023-03-10 |
Family
ID=77717507
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110740247.7A Active CN113422981B (en) | 2021-06-30 | 2021-06-30 | Method and device for identifying opera based on ultra-high definition opera video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113422981B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104166685A (en) * | 2014-07-24 | 2014-11-26 | 北京捷成世纪科技股份有限公司 | Video clip detecting method and device |
| CN109889882A (en) * | 2019-01-24 | 2019-06-14 | 北京亿幕信息技术有限公司 | A kind of video clipping synthetic method and system |
| CN111402919A (en) * | 2019-12-12 | 2020-07-10 | 南京邮电大学 | Game cavity style identification method based on multiple scales and multiple views |
| CN112597335A (en) * | 2020-12-21 | 2021-04-02 | 北京华录新媒信息技术有限公司 | Output device and output method for selecting section of opera |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090264199A1 (en) * | 2008-04-16 | 2009-10-22 | Macedon Productions, Inc. | Using a Musical Instrument as a Video Game Controller |
| CN107591149B (en) * | 2017-09-18 | 2021-09-28 | 腾讯音乐娱乐科技（深圳）有限公司 | Audio synthesis method, device and storage medium |
| CN112070080A (en) * | 2020-08-19 | 2020-12-11 | 湖南师范大学 | Method for classifying cartoon characters playing songs based on Faster R-CNN |
-
2021
- 2021-06-30 CN CN202110740247.7A patent/CN113422981B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104166685A (en) * | 2014-07-24 | 2014-11-26 | 北京捷成世纪科技股份有限公司 | Video clip detecting method and device |
| CN109889882A (en) * | 2019-01-24 | 2019-06-14 | 北京亿幕信息技术有限公司 | A kind of video clipping synthetic method and system |
| CN111402919A (en) * | 2019-12-12 | 2020-07-10 | 南京邮电大学 | Game cavity style identification method based on multiple scales and multiple views |
| CN112597335A (en) * | 2020-12-21 | 2021-04-02 | 北京华录新媒信息技术有限公司 | Output device and output method for selecting section of opera |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113422981A (en) | 2021-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111683209B (en) | Mixed-cut video generation method and device, electronic equipment and computer-readable storage medium | |
| CN110740387B (en) | Barrage editing method, intelligent terminal and storage medium | |
| CN110119711B (en) | Method and device for acquiring character segments of video data and electronic equipment | |
| TWI553494B (en) | Multi-modal fusion based Intelligent fault-tolerant video content recognition system and recognition method | |
| US10277946B2 (en) | Methods and systems for aggregation and organization of multimedia data acquired from a plurality of sources | |
| KR101729195B1 (en) | System and Method for Searching Choreography Database based on Motion Inquiry | |
| CN110430476B (en) | Live broadcast room searching method, system, computer equipment and storage medium | |
| CN113395578B (en) | Method, device, equipment and storage medium for extracting video theme text | |
| CN110457672A (en) | Keyword determines method, apparatus, electronic equipment and storage medium | |
| JP2008077495A (en) | Conference support apparatus, conference support method and conference support program | |
| CN114598933B (en) | Video content processing method, system, terminal and storage medium | |
| US10650814B2 (en) | Interactive question-answering apparatus and method thereof | |
| US20170024379A1 (en) | System and method for speech to speech translation using cores of a natural liquid architecture system | |
| CN113065018A (en) | Audio and video index library creating and retrieving method and device and electronic equipment | |
| KR20200098381A (en) | methods and apparatuses for content retrieval, devices and storage media | |
| JP2003085207A (en) | Video information recommend system, method and device, video recommend program, and recording medium with its program recorded | |
| KR102122918B1 (en) | Interactive question-anwering apparatus and method thereof | |
| CN113422981B (en) | Method and device for identifying opera based on ultra-high definition opera video | |
| CN116910302A (en) | Multi-mode video content effectiveness feedback visual analysis method and system | |
| CN115510362A (en) | System for automatically generating web front-end codes according to natural language description documents | |
| JP6161224B1 (en) | Person information display device, person information display method, and person information display program | |
| CN110659419B (en) | Method and related device for determining target user | |
| CN116704392B (en) | Video processing method, device, equipment, storage medium and product | |
| JP4703483B2 (en) | Video information storage device and video topic detection method used therefor | |
| CN111083558B (en) | Method and system for providing video program content summary |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |